diff --git a/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.i18n.yaml b/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.i18n.yaml new file mode 100644 index 0000000000..a4c2d4ce83 --- /dev/null +++ b/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.md +2026-08-18-product-subagent-failure-facts.md: b1d80cf66172ac67d38dbad873fa4cbd970a775c +2026-08-18-product-subagent-failure-facts.zh.md: df4b14b4a243f7768240678b8d434c7aef7d48a7 diff --git a/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.md b/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.md similarity index 99% rename from .agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.md rename to .agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.md index e47fc3246c..b1d80cf661 100644 --- a/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.md +++ b/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.md @@ -1,6 +1,7 @@ # Agent Note: Product subagents expose bounded structured failure facts Status: implemented +Archived: 2026-08-21 English | [中文](2026-08-18-product-subagent-failure-facts.zh.md) diff --git a/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.zh.md b/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.zh.md similarity index 99% rename from .agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.zh.md rename to .agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.zh.md index 5efd15e0e2..df4b14b4a2 100644 --- a/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.zh.md +++ b/.agents/notes/archived/feature/2026-08-18-product-subagent-failure-facts.zh.md @@ -1,6 +1,7 @@ # Agent Note: 产品 subagent 公开有界结构化失败事实 Status: implemented +Archived: 2026-08-21 [English](2026-08-18-product-subagent-failure-facts.md) | 中文 diff --git a/.agents/notes/archived/manifest.json b/.agents/notes/archived/manifest.json index bb58c4fe5a..f15182f0bc 100644 --- a/.agents/notes/archived/manifest.json +++ b/.agents/notes/archived/manifest.json @@ -295,6 +295,9 @@ "feature/2026-08-11-web-export-command-and-dialog.i18n.yaml": "sha256:db7d523a2a1f82a86f532661bd2953ee8538d971d91f886e4bd4e0d88f7226b2", "feature/2026-08-11-web-export-command-and-dialog.md": "sha256:ec44b47589ca7924018dc24f7fa73379a97b8f053d9e8ccce2aebb600230e47b", "feature/2026-08-11-web-export-command-and-dialog.zh.md": "sha256:ad28e67d397c87300cfe1705ba3d206cc4d054e07f5647c095c718ac8cf4ec98", + "feature/2026-08-18-product-subagent-failure-facts.i18n.yaml": "sha256:0aa7a873fdd878ee7f4b0a850ecf16d7b652b4f85de979acb7efcdf90883b6c1", + "feature/2026-08-18-product-subagent-failure-facts.md": "sha256:f7e05703c44106359798e6e4b76e442a4107b62ff0363554382d4767e4806788", + "feature/2026-08-18-product-subagent-failure-facts.zh.md": "sha256:19d2619fb5b5c6e40305dd82432d837357afa433ab735504ec204a2c25582ce6", "feature/2026-08-18-web-home-path-tilde.i18n.yaml": "sha256:f151e3e3514f59784fc646c2feb3075dc954c65110d48c2cc482ad486fc0b86f", "feature/2026-08-18-web-home-path-tilde.md": "sha256:8c7ecf120ff8c81826160acab5fc906a2a0a14213bcd2958343cfea47328d68e", "feature/2026-08-18-web-home-path-tilde.zh.md": "sha256:3486c5b42aed5bcadf12c62c5e1e6cf7c1b493fc1085ad7d154cdf2ec34076cc", diff --git a/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.i18n.yaml index 748bf5d166..de962f5749 100644 --- a/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.md -2026-07-26-packed-chunk-rows-by-default.md: 141c9a32a07b5cb4885a21b419df30d45dc1061b -2026-07-26-packed-chunk-rows-by-default.zh.md: 30088b8640efa783380a3fe083ed82efdad9e5c8 +2026-07-26-packed-chunk-rows-by-default.md: 14da6b3cbe650e80118e7c960c96bf618acd1e48 +2026-07-26-packed-chunk-rows-by-default.zh.md: f62a8e52a67adc960ac3150552594b4f061e6205 diff --git a/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.md b/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.md index 141c9a32a0..14da6b3cbe 100644 --- a/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.md +++ b/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.md @@ -18,7 +18,7 @@ Reading is unconditional and layout-blind. Packed, unpacked, and mixed files loa ### Logical events and physical rows -Packing stays at the `dsh-session` storage seam through `packChunkRuns()` and `decodeStorageRecord()`. The encoder recognizes exact delta-event shapes, preserves unrecognized events verbatim, and packs only runs of at least three. A packed row is storage vocabulary, not a `SessionEventMap` member: it never enters `Session.events` or fires `session/event`. +The JSONL packing path stays at the `dsh-session` storage seam through `packChunkRuns()` and `decodeStorageRecord()`. The encoder recognizes exact delta-event shapes, preserves unrecognized events verbatim, and packs only runs of at least three. A packed row is encoding vocabulary, not a `SessionEventMap` member: it never enters `Session.events` or fires `session/event`. The [packed session-history transport decision](2026-08-15-packed-session-history-transport.md) reuses this vocabulary for a bounded lossless wire interval without changing those event semantics. The JSONL backend packs each durable append batch. Raw `compression: 'none'` and default Zstandard framing carry the same logical storage records; selecting raw mode for reviewable fixtures does not disable packing. Repository replay readers and normalizers decode the shared row format instead of maintaining snapshot-specific codecs. diff --git a/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.zh.md b/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.zh.md index 30088b8640..f62a8e52a6 100644 --- a/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.zh.md @@ -18,7 +18,7 @@ JSONL 存储 seam 可以在不改变逻辑日志的情况下减少这部分封 ### 逻辑事件与物理行 -打包保留在 `dsh-session` 的存储 seam，并通过 `packChunkRuns()` 和 `decodeStorageRecord()` 实现。编码器识别精确的增量事件形态，原样保留无法识别的事件，并且只打包至少包含 3 个事件的连续段。打包行属于存储词汇，不是 `SessionEventMap` 成员：它绝不会进入 `Session.events`，也不会触发 `session/event`。 +JSONL 打包路径保留在 `dsh-session` 的存储 seam，并通过 `packChunkRuns()` 和 `decodeStorageRecord()` 实现。编码器识别精确的增量事件形态，原样保留无法识别的事件，并且只打包至少包含 3 个事件的连续段。打包行属于编码词汇，不是 `SessionEventMap` 成员：它绝不会进入 `Session.events`，也不会触发 `session/event`。[打包会话历史传输决策](2026-08-15-packed-session-history-transport.zh.md)会为有界的无损协议区间复用该词汇，而不改变这些事件语义。 JSONL 后端会打包每个持久追加批次。原始模式 `compression: 'none'` 与默认 Zstandard 帧承载相同的逻辑存储记录；为使 fixture 便于评审而选择原始模式，不会禁用打包。仓库中的回放读取器和规范化器会解码共享行格式，而不维护快照专用编解码器。 diff --git a/.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.i18n.yaml index eea93dc866..2a37960848 100644 --- a/.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.md -2026-08-09-client-conversation-node-assembly.md: ea2505d4a72f483a9df6fcd78d7e5c9a96b02f5c -2026-08-09-client-conversation-node-assembly.zh.md: b87f127d753cadf2805ed5cd948fc58ad01830aa +2026-08-09-client-conversation-node-assembly.md: 12069d129227cce13eb5f9f39e636921d4bf9efa +2026-08-09-client-conversation-node-assembly.zh.md: 957c2b291293761ff2417f60093b7962bb75bbdf diff --git a/.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.md b/.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.md index ea2505d4a7..12069d1292 100644 --- a/.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.md +++ b/.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.md @@ -8,13 +8,13 @@ English | [中文](2026-08-09-client-conversation-node-assembly.zh.md) Client Session owned transport windows, connection state, and pending interactions while also interpreting Assistant, Tool, message, command, compaction, retry, and turn-tail events in a centralized transcript fold. Adding one business node required changes to Session switches, history replay, indexes, caches, and React grouping; business identity, state evolution, and final presentation had no independent owner. -The old path also placed running Assistant and Tool values outside the finalized flow. They entered the log-ordered node list only after settlement, so their React parent changed and remounted them even when the business ID and `key` remained stable. Full history loads, older prepends, live appends, and token streaming used separate update paths, leaving reference stability and local recomputation dependent on specialized caches spread across the client. +Without target-neutral assembly, running Assistant and Tool values sit outside the finalized flow and enter the log-ordered node list only after settlement. Their React parent then changes and remounts them even when the business ID and `key` remain stable. Separate update paths for full history loads, older prepends, live appends, and token streaming also make reference stability and local recomputation depend on specialized caches spread across the client. Business events also use different correlation models. Tool has call IDs, Assistant correlates by turn and step, Compaction has its own lifecycle and checkpoint, and an Inbox splice represents one instantaneous state in a sequence. Keeping all these distinctions in one fold would make every business change pass through a global lookup and invalidate unrelated caches. ## Decision -Client Runtime provides a target-neutral Conversation Node assembly engine. Business plugins register Event Definitions, and view plugins register per-Session View Builders. `ui-conversation` registers the first built-in Definitions and the `chat` builder; Session only submits the current contiguous Event window to the engine and publishes its snapshot instead of interpreting individual conversation businesses. +Client Runtime provides a target-neutral Conversation Node assembly engine. Business plugins register Event Definitions, and view plugins register per-Session View Builders. `ui-conversation` registers the first built-in Definitions and the `chat` builder; Session only submits the current contiguous `SessionEventLikeEntry` window to the engine and publishes its snapshot instead of interpreting individual conversation businesses. The entry's outer discriminator distinguishes standard and packed records, while both carry an aligned inner `SessionEventLike` for Definition dispatch. This Note retains the derivation, business-by-business validation, responsibilities, algorithms, and trade-offs that remain relevant after implementation. @@ -22,20 +22,20 @@ This Note retains the derivation, business-by-business validation, responsibilit | Layer | Durable responsibility | Explicitly does not own | |---|---|---| -| Session | Maintain the contiguous Event window, distinguish replace, prepend, and append, and schedule snapshot notifications | Interpret Tool, Assistant, Compaction, or other business events | +| Session | Maintain the contiguous logical-event window, distinguish replace, prepend, and scalar append, and schedule snapshot notifications | Interpret Tool, Assistant, Compaction, or other business events | | Event Registry | Retain the unique-`kind` Definitions and sole fallback under Cordis lifecycles | Store one Session's Context or State | -| Assembler | Match Events and maintain Contexts, Locations, dependencies, and the publication dirty set | Interpret business State fields or Chat ordering | +| Assembler | Match standard events or packed runs and maintain Contexts, Locations, dependencies, and the publication dirty set | Interpret business State fields or Chat ordering | | Node Definition | Define one business object's identity, State transitions, Location data, and target Node | Create Contexts, mutate another business's State, or scan all Contexts | -| View Builder | Incrementally organize final target Nodes into that view's snapshot | Reinterpret raw Session Events | +| View Builder | Incrementally organize final target Nodes into that view's snapshot | Reinterpret `SessionEventLike` inputs | | React renderer | Render renderer-owned data by the final Node's `kind` and read business data from the current Node's Location | Pair business Events, scan global Nodes, or decide business lifecycle state | Registry contributions are Cordis effects. Removing a Definition causes a low-frequency registry rebuild for existing Sessions; ordinary business Events do not change the Registry or rebuild every business type. ### Overall `ConversationNodeDefinition` contract -Each [`ConversationNodeDefinition`](../../../../packages/client/ui-conversation/src/client/contract/conversation.ts) independently owns one business object's conversion from Events to State and final view Nodes. A Definition's `kind` is its unique Registry name and the namespace for its business IDs. +Each [`ConversationNodeDefinition`](../../../../packages/client/ui-conversation/src/client/contract/conversation.ts) independently owns one business object's conversion from `SessionEventLike` inputs to State and final view Nodes. A Definition's `kind` is its unique Registry name and the namespace for its business IDs. -One Event may be claimed by several ordinary Definitions. For example, an Assistant Event updates both the Assistant Node and Turn Tail, while a Retry Event updates Retry, Assistant, and Turn Tail. The Assembler asks the fallback only when every ordinary Definition returns `null`. +One input may be claimed by several ordinary Definitions. For example, an Assistant event or packed run updates both the Assistant Node and Turn Tail, while a Retry Event updates Retry, Assistant, and Turn Tail. The Assembler asks the fallback only when every ordinary Definition returns `null`. A Definition holds no mutable business data across Sessions. Each Session's Assembler isolates that Session's Contexts, State, dependencies, and View Builders. @@ -49,9 +49,9 @@ Each `(kind, id)` has at most one start Match. A second start fails immediately; #### `match(event)` -`match(event)` reads only the current raw `SessionEvent` and returns `{ id, role: 'start' | 'update' }` or `null`. It cannot access a Context, history, a Reader, a Location, or the view envelope. +`match(event)` reads only the current `SessionEventLike` and returns `{ id, role: 'start' | 'update' }` or `null`. It cannot access a Context, history, a Reader, a Location, or the view envelope. A `chunkrow/*` event can only be an update; the Assembler rejects it as a start, and `start()` receives a `ConversationStartMatch` containing a standard `SessionEvent`. -This restriction makes one Event's routing cost depend only on the number of registered Definitions. The Assembler never scans a Definition's historical Contexts to decide which one owns an update. +This restriction makes one scalar event or packed run's routing cost depend only on the number of registered Definitions. The Assembler never scans a Definition's historical Contexts to decide which one owns an update. Start, result, resource, checkpoint, and business-owned terminal Events must carry or directly imply the same ID. If one Event cannot yield that ID, its producer extends the Event protocol; the Client does not guess from the "nearest unfinished object." @@ -59,9 +59,9 @@ The `role` describes the State lifecycle, not visibility. A start may produce a #### `ConversationMatch` -After a successful match, the Assembler combines the raw Event, optional wire presentation view, `role`, and engine-computed `location` into a read-only `ConversationMatch`. +After a successful match, the Assembler combines the standard or packed event, `role`, and engine-computed `location` into a read-only `ConversationMatch`. A packed run remains one Match and retains its fragment and timestamp-gap arrays. -A Context's `matches` always remain in ascending Event `seq` order, not network arrival or pagination ingestion order. If a tail page supplies a result before an older page supplies its call, the final Match order still places the call before the result. +A Context's `matches` always remain in ascending first-`seq` order, not network arrival or pagination ingestion order. The Session journal has already rejected overlapping logical ranges. If a tail page supplies a result before an older page supplies its call, the final Match order still places the call before the result. Location can change when prepend fills a boundary or append closes one. The Assembler replaces the affected Matches' read-only Locations and replays the Context; business code does not retain an old Location copy as authority. @@ -71,8 +71,8 @@ Location can change when prepend fills a boundary or append closes one. The Asse |---|---|---| | `key` | Assembler | Stable final identity derived from `kind + id` | | `kind` / `id` | Definition + Assembler | Current business namespace and business ID | -| `matches` | Assembler | Complete business evidence loaded in the current window and sorted by `seq` | -| `start` | Assembler | Unique start Match, or `undefined` before it loads | +| `matches` | Assembler | Complete scalar and packed business evidence loaded in the current window and sorted by first `seq` | +| `start` | Assembler | Unique scalar start Match, or `undefined` before it loads | | `state` | Returned by Definition, held by Assembler | Most recent `start`/`update` return value, or `undefined` before initialization | | `current` | Assembler | Most recently materialized Node or `null` for each target | @@ -108,7 +108,7 @@ Dependencies point strictly from earlier starts to later starts, so transitive r #### `update(context, match)` -`update()` handles a post-start Match that `match()` has already routed exactly to the current `(kind, id)`. It does not decide which Context owns the Event. +`update()` handles a post-start scalar or packed Match that `match()` has already routed exactly to the current `(kind, id)`. It does not decide which Context owns the input. A Definition that consumes Assistant deltas folds each matching `chunkrow/*` value as one batch without constructing member events. The Assembler invokes `update()` in ascending `seq` order. A live tail update can apply incrementally; any non-tail insertion, newly loaded start, or invalidated dependency causes a complete replay from `start()`. @@ -126,9 +126,9 @@ The Assembler does not use State reference equality to decide publication or pro | `animation-frame` | Coalesce high-frequency updates into materialization on the next frame | | `none` | Do not schedule a flush for this Match; retain its State and dirty marker | -Omitting `publication()` means `immediate`. Assistant token deltas use `animation-frame`, invisible Inbox Contexts use `none`, and finals, dependency replays, and Location boundaries publish the latest result through an immediate path. +Omitting `publication()` means `immediate`. Assistant token deltas and packed runs use `animation-frame`, invisible Inbox Contexts use `none`, and finals, dependency replays, and Location boundaries publish the latest result through an immediate path. -Every delta within a frame still executes update. Only `buildViewNode()`, View Builder work, and React snapshot notification are coalesced; no tokens are lost. +Every live delta within a frame still executes `update()`, while one historical packed run executes one batch `update()`. Only `buildViewNode()`, View Builder work, and React snapshot notification are coalesced; no fragments are lost. #### `buildLocationData(context, scope)` @@ -160,7 +160,7 @@ IDs are never reused. Completed Contexts remain in the current window, providing ### Location is a first-class engine fact -[`ConversationLocationIndex`](../../../../packages/client/ui-conversation/src/client/conversation/location-index.ts) maps Events to Locations from `turn/start`, `step/start`, explicit turn and step payloads, `step/end`, and `turn/end`. +[`ConversationLocationIndex`](../../../../packages/client/ui-conversation/src/client/conversation/location-index.ts) maps standard events and packed runs to Locations from `turn/start`, `step/start`, explicit turn and step payloads, `step/end`, and `turn/end`. All members of a row share its turn, step, block index, and delta kind, so the row needs one Location entry at its first `seq`. Location has four shapes: `session`, `turn`, `step`, and `unresolved`. Turns and Steps each carry `open`, `closed`, or `unknown` status plus any loaded start and end Events. @@ -168,31 +168,31 @@ Each Turn and Step also carries a reference-stable Location data store. A Defini `unresolved` means the current history window lacks sufficient preceding boundaries; it does not mean session-level. When older prepend supplies those boundaries, the index corrects Match Locations and replays only Contexts that own those seqs. -An appended ordinary Event only inherits current coordinates, while an appended boundary recalculates only its owning Turn. Prepend rebuilds Location facts from the expanded contiguous window, but reference-stability logic retains unchanged Turn and Step objects. +An appended standard Event only inherits current coordinates, while an appended boundary recalculates only its owning Turn. Prepend rebuilds Location facts from the contiguous `SessionEventLikeEntry` window, but reference-stability logic retains unchanged Turn and Step objects. The Assembler also passes a reference-stable timeline to each View Builder. Businesses do not separately maintain turn order, step lists, last-step values, or boundary Maps. -## Three Event-window paths +## Three input-window paths -"Backward history scanning" describes the UI loading pages from the newest tail toward the Session beginning; it does not mean a Definition executes `update()` in reverse. Regardless of history API order or page-loading direction, the Assembler canonicalizes each current window and each fresh page in ascending `seq` order. +"Backward history scanning" describes the UI loading pages from the newest tail toward the Session beginning; it does not mean a Definition executes `update()` in reverse. The Session journal validates each record's logical range before publication. Regardless of page-loading direction, the Assembler orders every accepted standard event or packed run by its first `seq`. | Scenario | Input range | Context and State handling | View Builder | |---|---|---|---| -| Initial history tail or resync | Current complete contiguous window | Clear and rebuild all Contexts in ascending `seq` order | `replace()` | -| Load one older-history page | Only deduplicated fresh Events before the window | Retain existing Context identity, then add Matches, Locations, dependencies, and local replays | `apply(upserts)` | +| Initial history tail or resync | Current complete contiguous logical window | Clear and rebuild all Contexts in ascending first-`seq` order | `replace()` | +| Load one older-history page | Only range-validated fresh standard events or packed runs before the window | Retain existing Context identity, then add Matches, Locations, dependencies, and local replays | `apply(upserts)` | | Live append | One contiguous tail Event | Match Definitions and update only the exact IDs; boundaries affect only their owning Turn | `apply(upserts)` | ### Initial history tail and logical backward scanning -1. `Session.open()` loads the latest tail page and passes its contiguous History Entries to `replaceWindow(entries, hasMore)`. +1. `Session.open()` loads the latest tail page and passes its contiguous `SessionEventLike` entries to `replaceWindow(entries, hasMore)`. 2. `replaceWindow` clears old Contexts, start-seq indexes, seq reverse indexes, Reader dependencies, and the input Map. -3. It sorts every entry by Event `seq` and stores the resulting current window. +3. It sorts every entry by its first logical `seq` and stores the resulting current window. 4. LocationIndex rebuilds Turn and Step facts for that window. -5. The Assembler visits Events in ascending order and invokes every ordinary Definition's `match(event)`. +5. The Assembler visits standard events and packed runs in ascending order and invokes every ordinary Definition's `match(event)`. 6. Each result gets or creates its `(kind, id)` Context and enters that Context's ordered Match array. 7. A start runs `start()`; a tail update on initialized State runs `update()` directly. 8. If the page contains only a result or resource and omits its start, the ID still creates a Context and collects Matches, while State remains `undefined`. -9. After matching all Events, the Assembler rechecks Reader dependencies so earlier instantaneous states in the same window stabilize before later consumers read them. +9. After matching all inputs, the Assembler rechecks Reader dependencies so earlier instantaneous states in the same window stabilize before later consumers read them. 10. Every Context becomes dirty, and the next flush fully rebuilds Location data in Step→Turn order before invoking `buildViewNode()` for every target. 11. Some businesses return `null` without a start; Compaction, Command, Tool result, and Turn Error can construct fallback Nodes from sufficient update evidence. 12. Each View Builder receives the complete Node set and timeline and establishes the initial snapshot through `replace()`. @@ -206,12 +206,12 @@ If an update with the same ID is genuinely earlier than the start in log order, ### Prepending a newly loaded older page 1. `Session.loadOlder()` requests the immediately preceding page using the current `baseSeq` and first verifies continuity between the page tail and current window. -2. Session prepends the raw Event and view arrays to its own window and passes only that page to `assembler.prepend(entries, hasMore)`. -3. The Assembler removes seqs that overlap the current window, then sorts the fresh page internally in ascending order. +2. Session prepends the accepted standard or packed entries to its own window and passes only that page to `assembler.prepend(entries, hasMore)`. +3. The journal has already removed complete duplicate ranges and rejected partial overlaps; the Assembler sorts the fresh page by first `seq`. 4. Existing Contexts, State, current Nodes, and View Builder instances remain intact. -5. LocationIndex rebuilds facts over the expanded complete input and reports seqs whose Location identity actually changed. +5. LocationIndex rebuilds facts over the extended complete input and reports seqs whose Location identity actually changed. 6. Contexts owning those seqs update their Match Locations and replay from start; unrelated Contexts do not join Location replay. -7. Fresh Events run Definition matchers and enter existing or new Contexts by stable ID. +7. Fresh standard events and packed runs enter existing or new Contexts through the same Definition matcher and stable ID. 8. If the new page supplies a pending Context's start, that Context initializes from the start and then applies every already-collected update in ascending order. 9. If the page establishes a nearer Reader predecessor, changes a predecessor revision, or removes a window gap, the consumer recomputes from `start()`. 10. Reader dependencies propagate replay toward later start seqs; no Event is applied in reverse within the propagation batch. @@ -226,7 +226,7 @@ Reader gap repair is the largest algorithmic difference between prepend and ordi ### Forward live append -1. Session accepts only a live Event immediately after the current tail seq; it deduplicates overlap and runs tail-page repair before accepting a gap. +1. Session accepts only a standard live Event immediately after the current logical tail seq; it deduplicates overlap and runs tail-page repair before accepting a gap. 2. A non-boundary Event enters the current Turn and Step coordinates incrementally; a boundary Event updates Location facts for its owning Turn. 3. The Assembler invokes `match()` once on every ordinary Definition for this Event and scans no Definition's Context set. 4. Each successful result directly locates one Context through `(kind, id)`. @@ -249,7 +249,7 @@ All three paths preserve the same invariants: Context Matches are seq-ordered, S `replaceWindow` is the low-frequency complete replacement for initial open, resync, gap repair, and registry changes; it does not implement ordinary load older. Both `prepend` and `append` retain existing Builder and Context identity. -Page size, the number of history loads, and RAF coalescing affect only when evidence arrives or publishes. They do not change final Context State and Nodes for an equal Event window. +Page size, record packing, the number of history loads, and RAF coalescing affect only when evidence arrives or publishes. They do not change final Context State and Nodes for equal logical evidence. ## How built-in businesses use Definitions @@ -261,7 +261,7 @@ Page size, the number of history loads, and RAF coalescing affect only when evid | Next-step Inbox / `inbox-next-step` | Splice Event seq | Each `agent/inbox/spliced` targeting next-step | None | Build the same per-instruction instantaneous state; Message reads its claimed set | | Message / `input-message` | Message ID | Append-surface `user/message` | None | Use source for a context message, or read the nearest next-step Inbox to distinguish user from steering | | Request Prompt / `request-prompt` | Header Event seq | Each `request/header` | None | Read the preceding Request Prompt through Reader, retain the full prompt state, and classify system/tool changes | -| Assistant / `assistant-step` | `turn:step` | `step/start` | `assistant/chunk`, final `assistant/message`, and same-step Retry | Aggregate blocks, usage, first-token time, final evidence, and retry-hidden state, then publish same-key Step data | +| Assistant / `assistant-step` | `turn:step` | `step/start` | Scalar or packed `assistant/chunk`, final `assistant/message`, and same-step Retry | Aggregate blocks, usage, first-token time, final evidence, and retry-hidden state, then publish same-key Step data | | Tool / `tool-call` | Root call ID | Root `tool/call` | Root result and Code Dispatch start/result | Aggregate the root, children, and parent Map; Dispatch Events route exactly through `rootCallId` | | Command / `command` | Command ID | `command/run` | `command/done` and compact lifecycle/checkpoint Events carrying a source command ID | Aggregate command outcome and manual-compaction evidence | | Automatic Compaction / `compaction` | Compaction ID | `compaction/start` without a source command ID | Summary, end, and replacement checkpoint | Aggregate summary/checkpoint; sufficient checkpoint evidence supports fallback without a start | @@ -278,7 +278,7 @@ Page size, the number of history loads, and RAF coalescing affect only when evid | Inbox | `none` | No Node | Recompute instantaneous states along the Reader chain when prepend supplies earlier splices | | Message | Immediate by default | `user`, `steering`, or `context` | Window-gap repair can reclassify the same message key | | Request Prompt | Immediate by default | One `system-prompt` for every header carrying a non-empty system field | A step's first header anchors before its request messages; a later same-step series anchors after its surface rewrite; prepend of the preceding header can correct a partial-window anchor | -| Assistant | RAF for chunks, immediate for final, none for pure usage/finish | Same-key `assistant-step` with running/settled/interrupted status | Matches support fallback without `step/start`; Location close produces interruption presentation | +| Assistant | RAF for scalar chunks and packed runs, immediate for final, none for pure usage/finish | Same-key `assistant-step` with running/settled/interrupted status | Scalar and packed reducers are equivalent; Matches support fallback without `step/start`; Location close produces interruption presentation | | Tool | Immediate by default | One recursive `tool-call` root containing all `subCalls` | A result-only history window supports fallback; running→settled retains its key | | Command | Immediate by default | Ordinary `command` or integrated `manual-compaction` | Checkpoint arrival may change the anchor without changing the Context key | | Compaction | Immediate by default | `compaction` marker | A checkpoint may render before start; an older start triggers forward replay | @@ -326,20 +326,20 @@ Slot-level contextual Hooks and entry-owned `inject.hooks` remain independent pa The standard `useSession` remains available to every session-scoped slot renderer. `useTurnData()` narrows the common read path rather than acting as a permission sandbox. Whole-window statistics or arbitrary object indexes may still read the Session snapshot explicitly, but they are not modeled as current-Node Turn data. -Assistant streaming to final and Tool running to settled update only one Seat's data and necessary ordering properties. They no longer move from a tail running container into finalized flow, so settlement does not reset component-local State. +Assistant streaming to final and Tool running to settled stay in one Seat while updating its data and necessary ordering properties. Settlement therefore does not reset component-local State through a parent move. When business logic deliberately changes a materialized Node to hidden, it leaves visible order and remounts when visible again. This is explicit business withdrawal of presentation, distinct from the stable-Seat guarantee for running→settled. The concrete Tool renderer remains governed by the [`ui-tool ownership decision`](2026-08-08-client-tool-presentation-ownership.md). Tool Definition supplies recursive root/subcall data, and `ui-tool` dispatches concrete presentation by the Tool-name keyed slot. -Trajectory registers its own target and business Definitions against the same Assembler and Session event window as Chat. Its target builder preserves the stage-oriented read model without consuming the Chat Builder's legacy slice or running an independent history fold. The Chat Builder retains its legacy slice for StatsLine and the top-level public compatibility fields; target-specific Definitions do not change the shared Context, Reader, or Location contracts. +Trajectory registers its own target and business Definitions against the same Assembler and `SessionEventLikeEntry` window as Chat. Its target builder preserves the stage-oriented read model without consuming the Chat Builder's legacy slice or running an independent history fold. Chat and Trajectory keep independent scalar and packed Assistant reducers; target-specific Definitions do not change the shared Context, Reader, or Location contracts. The target-specific Trajectory Definitions, retained stage model, Steering adaptation, complexity bounds, and presentation hot paths are owned by the [Trajectory Context assembly decision](2026-08-11-trajectory-conversation-context-assembly.md). ## Runtime and render path ```text -Session Event window +SessionEventLike window -> ConversationNodeAssembler -> Definition.match(event) -> (kind, id, start/update) -> Context matches + State + Location @@ -361,7 +361,7 @@ Slot type/runtime tests pin required parent-provided common inject, the `hookCon Assembled Web snapshots, GUI tests, and browser scenarios cover the real plugin graph. Browser evidence compares Assistant streaming→settled, Bash running→settled, and Code Mode root + nested subcalls against master layout. -History-path tests cover complete replace, non-overlapping prepend, overlapping-seq deduplication, empty-page `hasMore` convergence, and live append. Equal Event windows ingested through different paths produce equal business State and final Nodes. +History-path tests cover complete replace, non-overlapping prepend, complete-range deduplication, partial-overlap rejection, empty-page `hasMore` convergence, and scalar live append. Scalar and packed representations of the same Assistant history produce equal Chat and Trajectory State, timing boundaries, and final Nodes; one packed run remains one Match through replace, prepend, Location replay, and registry rebuild. ## Alternatives considered @@ -377,6 +377,8 @@ History-path tests cover complete replace, non-overlapping prepend, overlapping- **Define a reverse State fold for backward history scanning.** Rejected: every business would maintain two inverse algorithms, and deletion, non-invertible aggregation, and cross-Context dependencies would be difficult to keep equivalent. Ordered Matches followed by forward replay from start preserve one business meaning. +**Add a separate chunk-run matcher and update lifecycle.** Rejected: a second Definition path would duplicate dispatch, replay, publication, and Context types. `ChunkRowEvent` uses the existing `match(event)` and `update(context, match)` lifecycle while making packed handling explicit through its `chunkrow/*` discriminant. + **Make Inbox a first-class engine concept or one window-wide Context.** Rejected: Inbox is ordinary business State and does not belong in the generic engine. Per-splice instantaneous State plus a strictly backward Reader supports prepend, append, and Message lookup together. **Register specialized query methods for cross-business reads.** Rejected: consumers would still depend on provider APIs, and each new relationship would expand a central interface. Reader exposes a named kind's read-only predecessor Context; the provider writes useful State and the consumer interprets it. @@ -399,14 +401,14 @@ A new business node can register its matcher, State transitions, optional Locati Host business packages declaration-merge their durable Event members into `@deepseek-ai/dsh-session/types`, while Client Definitions type-only import the corresponding business package `/types` subpaths. Augmenting the declaring interface rather than a re-export barrel gives the independent Host and Client TypeScript programs the same Event narrowing without pulling Host runtime into the Client graph. -Initial tail, older prepend, and live append share one set of Context invariants. Missing starts, Reader window gaps, unknown Locations, and high-frequency deltas are explicit engine states and require no direction-specific business cache. +Initial tail, older prepend, and live append share one set of Context invariants. Missing starts, Reader window gaps, unknown Locations, and packed high-frequency deltas are explicit engine states and require no direction-specific business cache. Append does not scan historical Contexts; prepend replays only Contexts whose Matches, Locations, or Reader answers actually changed. A structural Chat change may still recompute visible order and indexes, but does not rerun unrelated business folds or replace unchanged Node identity. -Separating State updates from publication cadence folds every Assistant delta while materializing at most once per animation frame. Step or Turn close and final Events can immediately publish the latest State. +Separating State updates from publication cadence folds every live Assistant delta and each historical packed run while materializing at most once per animation frame. Step or Turn close and final Events can immediately publish the latest State. -Steps and Turns become stable homes for cross-business aggregates. Turn Tail and Deliverables no longer depend on renderers scanning global Nodes; slot-level `useTurnData()` narrows common reads to the current Node's Turn and uses selector equality to isolate unrelated updates. +Steps and Turns are stable homes for cross-business aggregates. Turn Tail and Deliverables derive their values without renderer scans of global Nodes; slot-level `useTurnData()` narrows common reads to the current Node's Turn and uses selector equality to isolate unrelated updates. -The cost is new Runtime contracts for Registry, Assembler, Location data, dependency replay, and per-target Builders, plus parent-owned common inject and per-occurrence `hookContext` in UI Slots. Definition authors must understand stable IDs, unique starts, forward replay, Step→Turn publication order, read-only Reader access, and the prohibition on Node withdrawal. +The cost is new Runtime contracts for Registry, Assembler, Location data, dependency replay, and per-target Builders, plus parent-owned common inject and per-occurrence `hookContext` in UI Slots. Definitions that consume Assistant deltas also maintain equivalent scalar and packed update branches. Definition authors must understand stable IDs, unique scalar starts, forward replay, Step→Turn publication order, read-only Reader access, and the prohibition on Node withdrawal. `useTurnData()` does not revoke the standard `useSession` capability from session-scoped renderers, so this boundary relies on API guidance and tests rather than capability isolation. Registry changes remain low-frequency full rebuilds; the Chat Builder still maintains a legacy slice for StatsLine and the top-level public fields, while Trajectory owns target-specific Definitions and a Builder over the shared Session window. Built-in Definitions remain in their respective UI packages, and these compatibility boundaries do not return business interpretation to Session. diff --git a/.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.zh.md b/.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.zh.md index b87f127d75..957c2b2912 100644 --- a/.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.zh.md @@ -8,13 +8,13 @@ Status: implemented Client Session 既维护传输窗口、连接状态和待处理交互，也在中心化 transcript fold 中解释 Assistant、Tool、消息、命令、压缩、重试及 turn tail 等业务事件。每增加一种业务节点，都要修改 Session 的 switch、历史 replay、索引、缓存和 React 分组；业务 identity、状态演进与最终展示没有独立所有者。 -旧链路还把运行中的 Assistant 和 Tool 放在 finalized flow 之外。它们结算后才进入按日志排序的节点列表，因此 React parent 会改变，即使业务 ID 和 `key` 不变也会重新挂载。全量历史加载、older prepend、实时 append 与 token streaming 又分别走不同更新路径，使引用稳定和局部重算只能靠各处特化缓存维持。 +缺少 target-neutral assembly 时，运行中的 Assistant 和 Tool 会位于 finalized flow 之外，结算后才进入按日志排序的节点列表。React parent 因而改变，即使业务 ID 和 `key` 稳定也会重新挂载。全量历史加载、older prepend、实时 append 与 token streaming 若分别走不同更新路径，引用稳定和局部重算也只能依赖各处特化缓存。 业务事件之间的关联方式并不统一。Tool 有 call ID，Assistant 以 turn/step 关联，Compaction 有独立生命周期和 checkpoint，Inbox splice 则表示一个连续状态的瞬间。把这些差异继续塞进统一 fold，会让任一业务变化都经过全局查表并使无关缓存失效。 ## 决策 -Client Runtime 提供 target-neutral 的 Conversation Node 组装引擎，业务插件注册 Event Definition，视图插件注册 per-Session View Builder。`ui-conversation` 注册第一批内建 Definition 和 `chat` builder；Session 只负责把当前连续事件窗口送入引擎并发布它的 snapshot，不再解释具体 conversation 业务。 +Client Runtime 提供 target-neutral 的 Conversation Node 组装引擎，业务插件注册 Event Definition，视图插件注册 per-Session View Builder。`ui-conversation` 注册第一批内建 Definition 和 `chat` builder；Session 只负责把当前连续 `SessionEventLikeEntry` window 送入引擎并发布它的 snapshot，且不解释具体 conversation 业务。entry 的外层 discriminator 区分标准与 packed record，两者都携带字段对齐的内部 `SessionEventLike`，供 Definition dispatch。 本 Note 保留实现后仍有价值的方案推导、逐业务适配、职责、算法和取舍。 @@ -22,20 +22,20 @@ Client Runtime 提供 target-neutral 的 Conversation Node 组装引擎，业务 | 层 | 长期职责 | 明确不负责 | |---|---|---| -| Session | 维护连续 Event 窗口，区分 replace、prepend、append，调度 snapshot 通知 | 解释 Tool、Assistant、Compaction 等业务事件 | +| Session | 维护连续逻辑 event window，区分 replace、prepend 与 scalar append，调度 snapshot 通知 | 解释 Tool、Assistant、Compaction 等业务事件 | | Event Registry | 按 Cordis 生命周期保存唯一 `kind` 的 Definition 和唯一 fallback | 保存某个 Session 的 Context 或 State | -| Assembler | 匹配 Event，维护 Context、Location、依赖和发布脏集 | 理解业务 State 字段或 Chat 排序 | +| Assembler | 匹配标准 event 或 packed run，维护 Context、Location、依赖和发布脏集 | 理解业务 State 字段或 Chat 排序 | | Node Definition | 定义一个业务对象的 identity、State 演进、Location data 和 target Node | 创建 Context、修改别的业务 State 或扫描全部 Context | -| View Builder | 把最终 target Node 增量整理成该视图的 snapshot | 重新解释原始 Session Event | +| View Builder | 把最终 target Node 增量整理成该视图的 snapshot | 重新解释 `SessionEventLike` input | | React renderer | 按最终 Node 的 `kind` 展示 renderer-owned data，并读取当前 Node 所属 Location 的只读业务 data | 配对业务 Event、扫描全局 Nodes 或决定业务生命周期 | Registry 注册是 Cordis effect，Definition 卸载会触发现有 Session 的低频 registry rebuild。普通业务 Event 不改变 Registry，也不会因此重建全部业务类型。 ### `ConversationNodeDefinition` 总体契约 -每个 [`ConversationNodeDefinition`](../../../../packages/client/ui-conversation/src/client/contract/conversation.ts) 独立拥有一种业务对象从 Event 到 State 和最终 view Node 的转换。Definition 的 `kind` 是 Registry 内唯一名称，也是业务 ID 的命名空间。 +每个 [`ConversationNodeDefinition`](../../../../packages/client/ui-conversation/src/client/contract/conversation.ts) 独立拥有一种业务对象从 `SessionEventLike` input 到 State 和最终 view Node 的转换。Definition 的 `kind` 是 Registry 内唯一名称，也是业务 ID 的命名空间。 -同一个 Event 可以被多个普通 Definition 认领。例如一条 Assistant Event 同时更新 Assistant Node 和 Turn Tail；一条 Retry Event 同时更新 Retry、Assistant 和 Turn Tail。Assembler 只有在全部普通 Definition 都返回 `null` 时才询问 fallback。 +同一个 input 可以被多个普通 Definition 认领。例如一条 Assistant event 或 packed run 同时更新 Assistant Node 和 Turn Tail；一条 Retry Event 同时更新 Retry、Assistant 和 Turn Tail。Assembler 只有在全部普通 Definition 都返回 `null` 时才询问 fallback。 Definition 不持有跨 Session 的可变业务数据。每个 Session 的 Context、State、依赖和 View Builder 都由该 Session 的 Assembler 隔离持有。 @@ -49,9 +49,9 @@ Assembler 使用 `conversationContextKey(kind, id)` 组合无碰撞 key；不同 #### `match(event)` -`match(event)` 只读取当前原始 `SessionEvent`，返回 `{ id, role: 'start' | 'update' }` 或 `null`。它拿不到 Context、历史、Reader、Location 或 view envelope。 +`match(event)` 只读取当前 `SessionEventLike`，返回 `{ id, role: 'start' | 'update' }` 或 `null`。它拿不到 Context、历史、Reader、Location 或 view envelope。`chunkrow/*` event 只能作为 update；Assembler 会拒绝 packed start，`start()` 接收的 `ConversationStartMatch` 只包含标准 `SessionEvent`。 -这项限制使单条 Event 的路由成本只随已注册 Definition 数量增长。Assembler 不会为了判断一条 update 属于谁而遍历该 Definition 的历史 Context。 +这项限制使单条 scalar event 或 packed run 的路由成本只随已注册 Definition 数量增长。Assembler 不会为了判断一条 update 属于谁而遍历该 Definition 的历史 Context。 start、result、resource、checkpoint 及业务自有终止 Event 必须携带或可直接推导同一 ID。若单个 Event 不能算出 ID，生产 Event 的协议负责补足关联字段，Client 不通过“最近一个未完成对象”猜测。 @@ -59,9 +59,9 @@ start、result、resource、checkpoint 及业务自有终止 Event 必须携带 #### `ConversationMatch` -匹配成功后，Assembler 把原始 Event、可选的 wire presentation view、`role` 和引擎计算的 `location` 组成只读 `ConversationMatch`。 +匹配成功后，Assembler 把标准或 packed event、`role` 和引擎计算的 `location` 组成只读 `ConversationMatch`。一个 packed run 始终只占一个 Match，并保留 fragment 与 timestamp-gap 数组。 -Context 的 `matches` 永远按 Event `seq` 升序保存，而不是按网络到达或分页摄入顺序保存。历史尾页先出现 result、older 页后出现 call 时，最终 Match 顺序仍然是 call 在前、result 在后。 +Context 的 `matches` 永远按首 `seq` 升序保存，而不是按网络到达或分页摄入顺序保存。Session journal 已经拒绝逻辑 range 重叠。历史尾页先出现 result、older 页后出现 call 时，最终 Match 顺序仍然是 call 在前、result 在后。 Location 可以随 prepend 补齐边界或 append 关闭边界而改变。Assembler 替换受影响 Match 的只读 Location 并 replay Context；业务不把旧 Location 副本当权威保存。 @@ -71,8 +71,8 @@ Location 可以随 prepend 补齐边界或 append 关闭边界而改变。Assemb |---|---|---| | `key` | Assembler | `kind + id` 的稳定最终 identity | | `kind` / `id` | Definition + Assembler | 当前业务命名空间和业务 ID | -| `matches` | Assembler | 当前窗口已收集且按 `seq` 排序的完整业务证据 | -| `start` | Assembler | 唯一 start Match；尚未加载时为 `undefined` | +| `matches` | Assembler | 当前窗口已收集且按首 `seq` 排序的完整 scalar 与 packed 业务证据 | +| `start` | Assembler | 唯一 scalar start Match；尚未加载时为 `undefined` | | `state` | Definition 返回、Assembler 持有 | 最近一次 `start`/`update` 返回值；未初始化时为 `undefined` | | `current` | Assembler | 各 target 最近一次 materialize 的 Node 或 `null` | @@ -108,7 +108,7 @@ Reader 每次查询都记录 `{ key, revision, windowGap }` 依赖。命中前 #### `update(context, match)` -`update()` 只处理已经由 `match()` 精确路由到当前 `(kind, id)` 的 post-start Match。它不再判断 Event 属于哪个 Context。 +`update()` 只处理已经由 `match()` 精确路由到当前 `(kind, id)` 的 post-start scalar 或 packed Match。它不判断 input 属于哪个 Context。消费 Assistant delta 的 Definition 会把每个匹配的 `chunkrow/*` 值作为一个 batch fold，而不构造成员 event。 Assembler 按 `seq` 升序调用 `update()`。实时尾部 update 可以直接增量应用；任何非尾部证据插入、start 补齐或依赖失效都会从 `start()` 完整 replay。 @@ -126,9 +126,9 @@ Assembler 不以 State 引用相等判断是否需要发布或传播。每次成 | `animation-frame` | 把多条高频更新合并到下一帧 materialize | | `none` | 本 Match 不主动安排 flush，State 和 dirty 标记仍被保留 | -省略 `publication()` 等于 `immediate`。Assistant token delta 使用 `animation-frame`，不可见 Inbox Context 使用 `none`，final、依赖 replay 和 Location 边界会以 immediate 路径发布最新结果。 +省略 `publication()` 等于 `immediate`。Assistant token delta 与 packed run 使用 `animation-frame`，不可见 Inbox Context 使用 `none`，final、依赖 replay 和 Location 边界会以 immediate 路径发布最新结果。 -一帧内的每条 delta 仍执行 update；合并的只是 `buildViewNode()`、View Builder 和 React snapshot 通知，不会丢失 token。 +一帧内的每条 live delta 仍执行 `update()`，一个历史 packed run 则执行一次 batch `update()`；合并的只是 `buildViewNode()`、View Builder 和 React snapshot 通知，不会丢失 fragment。 #### `buildLocationData(context, scope)` @@ -160,7 +160,7 @@ ID 不复用，完成的 Context 继续存在于当前窗口，既提供稳定 ### Location 是一级引擎事实 -[`ConversationLocationIndex`](../../../../packages/client/ui-conversation/src/client/conversation/location-index.ts) 根据 `turn/start`、`step/start`、显式 turn/step payload、`step/end` 和 `turn/end` 建立 Event 到 Location 的映射。 +[`ConversationLocationIndex`](../../../../packages/client/ui-conversation/src/client/conversation/location-index.ts) 根据 `turn/start`、`step/start`、显式 turn/step payload、`step/end` 和 `turn/end` 建立标准 event 与 packed run 到 Location 的映射。同一 row 的成员共享 turn、step、block index 与 delta kind，因此只需以首 `seq` 建立一条 Location entry。 Location 有 `session`、`turn`、`step` 和 `unresolved` 四种形状。Turn/Step 各自带 `open`、`closed` 或 `unknown` 状态，以及已加载的 start/end Event。 @@ -168,31 +168,31 @@ Location 有 `session`、`turn`、`step` 和 `unresolved` 四种形状。Turn/St `unresolved` 表示当前历史窗口缺少足够前序边界，不等于 session-level。older prepend 补入边界后，索引修正 Match Location，并只 replay 拥有这些 seq 的 Context。 -Append 普通 Event 只继承当前坐标；append 边界只重算所属 Turn。Prepend 会基于扩展后的完整连续窗口重建 Location facts，但引用稳定逻辑保留未变化 Turn/Step 对象。 +Append 标准 Event 只继承当前坐标；append 边界只重算所属 Turn。Prepend 会基于连续 `SessionEventLikeEntry` window 重建 Location facts，但引用稳定逻辑保留未变化 Turn/Step 对象。 Assembler 还把 reference-stable timeline 交给 View Builder。业务不重复维护 turn order、step list、last step 或边界 Map。 -## 三种事件窗口链路 +## 三种 input window 链路 -“历史反扫”描述 UI 从最新尾页向 Session 起点逐页加载的方向，不表示 Definition 逆序执行 `update()`。无论历史 API 返回顺序或页面加载方向如何，Assembler 对每个当前窗口和每个 fresh page 都按 `seq` 升序 canonicalize。 +“历史反扫”描述 UI 从最新尾页向 Session 起点逐页加载的方向，不表示 Definition 逆序执行 `update()`。Session journal 会在发布前校验每条 record 的逻辑 range；无论分页加载方向如何，Assembler 都按每个已接受标准 event 或 packed run 的首 `seq` 排序。 | 场景 | 输入范围 | Context/State 处理 | View Builder | |---|---|---|---| -| 初始历史尾页或 resync | 当前完整连续窗口 | 清空并按 `seq` 正序重建全部 Context | `replace()` | -| 加载一页 older history | 只传更早且去重后的 fresh Events | 保留现有 Context identity，补 Match、Location 和依赖后局部 replay | `apply(upserts)` | +| 初始历史尾页或 resync | 当前完整连续逻辑窗口 | 清空并按首 `seq` 正序重建全部 Context | `replace()` | +| 加载一页 older history | 只传通过 range 校验的更早标准 event 或 packed run | 保留现有 Context identity，补 Match、Location 和依赖后局部 replay | `apply(upserts)` | | 实时 append | 一条连续尾部 Event | 只匹配 Definitions 并精确更新命中 ID，边界只影响所属 Turn | `apply(upserts)` | ### 初始历史尾页与逻辑反扫 -1. `Session.open()` 拉取最新 tail page，并把连续 History Entries 交给 `replaceWindow(entries, hasMore)`。 +1. `Session.open()` 拉取最新 tail page，并把连续 `SessionEventLike` entry 交给 `replaceWindow(entries, hasMore)`。 2. `replaceWindow` 清空旧 Context、start-seq 索引、seq 反向索引、Reader 依赖和输入 Map。 -3. 全部 entries 按 Event `seq` 升序排序并写入当前窗口。 +3. 全部 entry 按首个逻辑 `seq` 升序排序并写入当前窗口。 4. LocationIndex 对这个窗口重建 Turn/Step facts。 -5. Assembler 按升序 Event 逐条调用每个普通 Definition 的 `match(event)`。 +5. Assembler 按升序访问标准 event 与 packed run，并逐条调用每个普通 Definition 的 `match(event)`。 6. 每个命中结果按 `(kind, id)` 取得或创建 Context，并把 Match 插入该 Context 的有序数组。 7. 遇到 start 时执行 `start()`；已有 State 的尾部 update 直接执行 `update()`。 8. 当前页只含 result/resource 而缺 start 时，Context 仍会按 ID 创建并收集 Matches，但 State 保持 `undefined`。 -9. 全部 Event 匹配后，Assembler 复查 Reader 依赖，使同一窗口内较早瞬间态先稳定、较晚消费者再读取它。 +9. 全部 input 匹配后，Assembler 复查 Reader 依赖，使同一窗口内较早瞬间态先稳定、较晚消费者再读取它。 10. 所有 Context 标记 dirty，下一次 flush 先按 Step→Turn 完整重建 Location data，再对每个 target 调用 `buildViewNode()`。 11. 某些业务在缺 start 时返回 `null`；Compaction、Command、Tool result 或 Turn Error 等可根据充分 update 证据构造 fallback Node。 12. 每个 View Builder 收到完整 Node 集和 timeline，通过 `replace()` 建立初始 snapshot。 @@ -206,12 +206,12 @@ Assembler 还把 reference-stable timeline 交给 View Builder。业务不重复 ### 新 older 分页的 prepend 1. `Session.loadOlder()` 以当前 `baseSeq` 拉取紧邻前页，并先验证页尾与当前窗口连续。 -2. Session 把 raw Event/view 数组 prepend 到自己的窗口，只把这一页传给 `assembler.prepend(entries, hasMore)`。 -3. Assembler 按 seq 去掉与当前窗口重叠的 Events，再把 fresh page 内部升序排列。 +2. Session 把已接受的标准或 packed entry prepend 到自己的窗口，只把这一页传给 `assembler.prepend(entries, hasMore)`。 +3. Journal 已经丢弃完整重复 range 并拒绝部分重叠；Assembler 再按首 `seq` 排列 fresh page。 4. 已存在的 Context、State、current Nodes 和 View Builder 实例不清空。 5. LocationIndex 用扩展后的完整输入重建 facts，并报告 Location identity 真正变化的 seq。 6. 拥有这些 seq 的 Context 更新 Match Location，并从 start replay；无关 Context 不参与 Location replay。 -7. fresh Events 逐条执行 Definition matcher，并按稳定 ID 插入已有或新 Context 的有序 Matches。 +7. fresh 标准 event 与 packed run 通过同一 Definition matcher 和稳定 ID 进入已有或新 Context。 8. 新页补出 pending Context 的 start 时，该 Context 从 start 初始化，再正序应用已经收集的所有 updates。 9. 新页建立更近的 Reader predecessor、改变 predecessor revision 或消除 window gap 时，消费者从 `start()` 重算。 10. Reader 依赖沿 start seq 向后传递 replay；同一传播批次不会把 Event 逆序应用。 @@ -226,7 +226,7 @@ Reader gap 修复是 prepend 与普通 append 最大的算法差异。新页不 ### 正向实时 append -1. Session 只接受紧邻当前 tail seq 的 live Event；重叠 seq 去重，出现 gap 时先走 tail-page repair。 +1. Session 只接受紧邻当前逻辑 tail seq 的标准 live Event；重叠时去重，出现 gap 时先走 tail-page repair。 2. 非边界 Event 增量写入当前 Turn/Step 坐标；边界 Event 更新所属 Turn 的 Location facts。 3. Assembler 对这一个 Event 的每个普通 Definition 调用一次 `match()`，不会遍历任何 Definition 的 Context 集合。 4. 每个命中结果通过 `(kind, id)` 直接定位一个 Context。 @@ -249,7 +249,7 @@ Chat `order` 的结构性变化仍可能重排当前可见 key；纯 data 更新 `replaceWindow` 是初始打开、resync、gap repair 和 registry 变化的低频完整替换，不用于实现普通 load older。`prepend` 与 `append` 都保留现有 Builder 和 Context identity。 -分页页宽、历史加载次数和 RAF 合批只影响何时得到更多证据或何时发布，不改变窗口证据相同时的最终 Context State 与 Node。 +分页页宽、record packing、历史加载次数和 RAF 合批只影响何时得到更多证据或何时发布，不改变逻辑证据相同时的最终 Context State 与 Node。 ## 内建业务如何使用 Definition @@ -261,7 +261,7 @@ Chat `order` 的结构性变化仍可能重排当前可见 key；纯 data 更新 | Next-step Inbox / `inbox-next-step` | splice Event seq | 每条目标为 next-step 的 `agent/inbox/spliced` | 无 | 同样形成逐指令瞬间态，claimed 集合供 Message 读取 | | Message / `input-message` | message ID | append-surface `user/message` | 无 | 根据 source 生成 context message，或读取最近 next-step Inbox 判断 user/steering | | Request Prompt / `request-prompt` | header Event seq | 每条 `request/header` | 无 | 通过 Reader 读取前一条 Request Prompt，保留完整 prompt 状态，并判定 system/tool 变化 | -| Assistant / `assistant-step` | `turn:step` | `step/start` | `assistant/chunk`、final `assistant/message`、同 step Retry | 聚合 blocks、usage、首 token 时间、final 和 retry 隐藏状态，并发布同 key Step data | +| Assistant / `assistant-step` | `turn:step` | `step/start` | scalar 或 packed `assistant/chunk`、final `assistant/message`、同 step Retry | 聚合 blocks、usage、首 token 时间、final 和 retry 隐藏状态，并发布同 key Step data | | Tool / `tool-call` | root call ID | root `tool/call` | root result、Code Dispatch start/result | 聚合 root、children 和 parent Map；Dispatch Event 用 `rootCallId` 精确路由 | | Command / `command` | command ID | `command/run` | `command/done`、带 source command ID 的 compact lifecycle/checkpoint | 聚合 command outcome 和手动压缩证据 | | Automatic Compaction / `compaction` | compaction ID | 无 source command ID 的 `compaction/start` | summary、end、replacement checkpoint | 聚合 summary/checkpoint；checkpoint 足够时可在缺 start 下 fallback | @@ -278,7 +278,7 @@ Chat `order` 的结构性变化仍可能重排当前可见 key；纯 data 更新 | Inbox | `none` | 不生成 Node | prepend 补前序 splice 时沿 Reader 链重算瞬间态 | | Message | 默认 immediate | `user`、`steering` 或 `context` | window gap 修复可让同一 message key 重新分类 | | Request Prompt | 默认 immediate | 每条带非空 system 字段的 header 都生成一个 `system-prompt` | Step 首条 header 锚定在请求消息之前；同 step 后续序列锚定在表层改写之后；prepend 补入前序 header 后可纠正部分窗口的锚点 | -| Assistant | chunk 为 RAF，final immediate，纯 usage/finish 为 none | 同 key `assistant-step`，状态为 running/settled/interrupted | 缺 `step/start` 可先用 Matches fallback；Location close 生成中断表现 | +| Assistant | scalar chunk 与 packed run 为 RAF，final immediate，纯 usage/finish 为 none | 同 key `assistant-step`，状态为 running/settled/interrupted | scalar 与 packed reducer 等价；缺 `step/start` 可先用 Matches fallback；Location close 生成中断表现 | | Tool | 默认 immediate | 一个递归 `tool-call` root，包含全部 `subCalls` | result-only 历史窗口可 fallback；running→settled 保持 key | | Command | 默认 immediate | 普通 `command` 或集成 `manual-compaction` | checkpoint 到达可改变 anchor，但不改变 Context key | | Compaction | 默认 immediate | `compaction` marker | checkpoint 可先展示，older 补 start 后正序 replay | @@ -326,20 +326,20 @@ Slot-level contextual Hook 与 entry-owned `inject.hooks` 是两条独立路径 标准 `useSession` 仍属于所有 session-scoped slot renderer 的公开能力，`useTurnData()` 是收窄常见读取方式而不是权限沙箱。全窗口统计或任意对象索引仍可显式使用 Session snapshot；它们不能伪装成“当前 Node 的 Turn data”。 -Assistant streaming 到 final、Tool running 到 settled 只更新同一个 Seat 的 data 和必要的排序属性，不再从末尾 running container 移入 finalized flow，因此组件内部 State 不因结算自动归零。 +Assistant streaming 到 final、Tool running 到 settled 始终留在同一个 Seat，只更新 data 和必要的排序属性。结算不会因跨 parent 移动而重置组件内部 State。 业务主动把已发布 Node 改成 hidden 时，它会退出 visible order，恢复 visible 时会重新 mount。这是明确的业务撤显语义，与 running→settled 的稳定 Seat 保证不同。 具体 Tool renderer 仍由 [`ui-tool ownership decision`](2026-08-08-client-tool-presentation-ownership.zh.md) 约束。Tool Definition 只交付递归 root/subcall data，`ui-tool` 再按 Tool name keyed slot 分发具体表现。 -Trajectory 针对与 Chat 相同的 Assembler 和 Session 事件窗口注册自己的 target 与业务 Definition。它的 target builder 保留 stage-oriented read model，既不消费 Chat Builder 的 legacy slice，也不运行独立 history fold。Chat Builder 为 StatsLine 和顶层公共兼容字段保留 legacy slice；target 专属 Definition 不改变共享的 Context、Reader 或 Location 契约。 +Trajectory 针对与 Chat 相同的 Assembler 和 `SessionEventLikeEntry` window 注册自己的 target 与业务 Definition。它的 target builder 保留 stage-oriented read model，既不消费 Chat Builder 的 legacy slice，也不运行独立 history fold。Chat 与 Trajectory 分别维护独立的 scalar 和 packed Assistant reducer；target 专属 Definition 不改变共享的 Context、Reader 或 Location 契约。 target 专属 Trajectory Definition、保留的 stage model、Steering 适配、复杂度上界与表现层热点由 [Trajectory Context 组装决策](2026-08-11-trajectory-conversation-context-assembly.zh.md)负责。 ## 运行时与渲染链路 ```text -Session Event window +SessionEventLike window -> ConversationNodeAssembler -> Definition.match(event) -> (kind, id, start/update) -> Context matches + State + Location @@ -361,7 +361,7 @@ Slot type/runtime tests 固定父注册必须提供声明的 common inject、`ho Assembled Web snapshot、GUI 和浏览器场景覆盖真实 plugin graph。浏览器证据比较 Assistant streaming→settled、Bash running→settled 以及 Code Mode root + nested subcalls 与 master 的布局。 -历史链路验证同时覆盖完整 replace、非重叠 prepend、重叠 seq 去重、空页 `hasMore` 收敛和 live append。相同 Event 窗口通过不同摄入路径得到相同业务 State 与最终 Node。 +历史链路验证同时覆盖完整 replace、非重叠 prepend、完整 range 去重、部分重叠拒绝、空页 `hasMore` 收敛和 scalar live append。相同 Assistant 历史的 scalar 与 packed 表示产生相同 Chat/Trajectory State、timing boundary 与最终 Node；一个 packed run 在 replace、prepend、Location replay 与 registry rebuild 中始终只保留一个 Match。 ## 考虑过的替代方案 @@ -377,6 +377,8 @@ Assembled Web snapshot、GUI 和浏览器场景覆盖真实 plugin graph。浏 **为历史反扫定义逆向 State fold。** 拒绝：每个业务都要维护互为逆运算的两套逻辑，删除、非可逆聚合和跨 Context 依赖很难保持一致。统一 Matches 后从 start 正序 replay 只有一套业务语义。 +**增加独立的 chunk-run matcher 与 update lifecycle。** 拒绝：第二条 Definition 路径会重复 dispatch、replay、publication 与 Context 类型。`ChunkRowEvent` 使用既有 `match(event)` 与 `update(context, match)` lifecycle，并通过 `chunkrow/*` discriminator 明确标记 packed 处理。 + **把 Inbox 做成引擎一级公民或一个窗口级 Context。** 拒绝：Inbox 是普通业务状态，不应污染通用引擎；逐 splice 瞬间态加严格前序 Reader 同时支持 prepend、append 和 Message 查询。 **给跨业务查询注册特化 query method。** 拒绝：消费者仍要依赖提供方 API，新增关系会扩张中心接口。Reader 暴露指定 kind 的只读前序 Context，由提供方写好 State、消费者读懂 State。 @@ -395,18 +397,18 @@ Assembled Web snapshot、GUI 和浏览器场景覆盖真实 plugin graph。浏 ## 后果 -新增业务节点可以局部注册自己的 matcher、State 转换、可选 Location data、最终 target Node 和 renderer，不再修改 Session 的业务 switch。`ChatNodeDataMap` 和 Location data maps 允许业务 package 通过 declaration merging 合入强类型 data；所有相关 Event 仍须暴露可单 Event 推导的稳定 ID。 +新增业务节点可以局部注册自己的 matcher、State 转换、可选 Location data、最终 target Node 和 renderer，无需修改 Session 的业务 switch。`ChatNodeDataMap` 和 Location data maps 允许业务 package 通过 declaration merging 合入强类型 data；所有相关 Event 仍须暴露可单 Event 推导的稳定 ID。 Host 业务 package 把自己的持久 Event 成员 declaration-merge 到 `@deepseek-ai/dsh-session/types`，Client Definition 则通过对应业务 package 的 `/types` 子路径进行 type-only import。增强实际声明接口而不是重导出 barrel，使 Host 和 Client 的独立 TypeScript Program 都能获得相同的 Event narrowing，同时不把 Host runtime 带入 Client 图。 -初始尾页、older prepend 和 live append 共享一套 Context 不变量。缺 start、Reader window gap、Location unknown 以及高频 delta 都是引擎明确表达的状态，不需要业务另建方向相关 cache。 +初始尾页、older prepend 和 live append 共享一套 Context 不变量。缺 start、Reader window gap、Location unknown 以及 packed 高频 delta 都是引擎明确表达的状态，不需要业务另建方向相关 cache。 Append 不扫描历史 Context；prepend 只 replay Match、Location 或 Reader 答案真正受影响的 Context。Chat 结构变化仍可能重算 visible order 和索引，但不会重跑无关业务 fold 或替换未变化 Node identity。 -State 更新与发布频率分离后，Assistant 每条 delta 都被 fold，同时每 animation frame 最多 materialize 一次。step/turn close 和 final 可立即发布最新 State。 +State 更新与发布频率分离后，Assistant 的每条 live delta 与每个历史 packed run 都会被 fold，同时每 animation frame 最多 materialize 一次。step/turn close 和 final 可立即发布最新 State。 -Step/Turn 成为业务间共享聚合的稳定宿主。Turn Tail 和 Deliverables 不再依赖 renderer 扫描全局 Nodes；Slot-level `useTurnData()` 把常见读取限制到当前 Node 所属 Turn，并通过 selector equality 隔离无关更新。 +Step/Turn 是业务间共享聚合的稳定宿主。Turn Tail 和 Deliverables 无需由 renderer 扫描全局 Nodes 即可派生值；Slot-level `useTurnData()` 把常见读取限制到当前 Node 所属 Turn，并通过 selector equality 隔离无关更新。 -代价是 Runtime 新增 Registry、Assembler、Location data、依赖重放和 per-target Builder 契约，UI Slots 也新增 parent-owned common inject 与 per-occurrence `hookContext`。Definition 作者必须理解稳定 ID、唯一 start、正序 replay、Step→Turn 发布顺序、只读 Reader 和 Node 不撤回规则。 +代价是 Runtime 新增 Registry、Assembler、Location data、依赖重放和 per-target Builder 契约，UI Slots 也新增 parent-owned common inject 与 per-occurrence `hookContext`。消费 Assistant delta 的 Definition 还需要维护等价的 scalar 与 packed update 分支。Definition 作者必须理解稳定 ID、唯一 scalar start、正序 replay、Step→Turn 发布顺序、只读 Reader 和 Node 不撤回规则。 `useTurnData()` 不撤销 session-scoped renderer 的标准 `useSession`，因此该边界依靠 API 引导和测试，而不是能力隔离。Registry 变化仍是低频完整 rebuild；Chat Builder 继续为 StatsLine 和顶层公共字段维护 legacy slice，Trajectory 则在共享 Session 窗口上拥有 target 专属 Definition 与 Builder。内建 Definition 分别留在所属 UI package；这些兼容边界不把业务解释权交还给 Session。 diff --git a/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.i18n.yaml index e5891135b9..339ff2b869 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.md -2026-08-10-product-subagent-providers-in-shared-host.md: eca1d5b6b9b0e46b39c6c2ef382bfc261d014e44 -2026-08-10-product-subagent-providers-in-shared-host.zh.md: 374a3ef72e298bb621fd71d306a4fca16c8000b4 +2026-08-10-product-subagent-providers-in-shared-host.md: a998408c4dd01ba8f7ab09eab453a963beb855a4 +2026-08-10-product-subagent-providers-in-shared-host.zh.md: cce746399b7ec553d145441cc3d51df3e051ca9b diff --git a/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.md b/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.md index eca1d5b6b9..a998408c4d 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.md +++ b/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.md @@ -14,9 +14,9 @@ The placement decision must preserve two independent facts. Loading a provider m Product providers remain process-scoped host-plane registrations. The [production-install exclusion decision](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md) supersedes only this note's former base-bundle installation choice: production `dsh-base` neither depends on nor mounts them. A Profile that opts in installs the selected provider Bundle; its patch mounts the default instance, and the Profile may mount additional named instances on the host plane. The [named-instance decision](../feature/2026-08-18-product-subagent-named-instances.md) owns each row's registry identity: both products accept multiple unique `providerName` values while preserving `codex` and `claude-code` as their defaults. Loading either plugin only registers a dormant backend; the corresponding Codex or Claude process starts on the first actual delegation call. Agent Presets independently contribute ordinary `dsh-tool-subagent` rows whose `provider` and `toolName` values expose exactly the configured instances needed by one agent without changing the Host registry. -Each provider package owns its directly installable Bundle patch and private product runtime. This note continues to own process-wide Host placement whenever either provider is installed. The provider-contract note continues to own each product protocol, result mapping, cancellation, process-tree lifecycle, and evidence tiers. The [named-instance decision](../feature/2026-08-18-product-subagent-named-instances.md) owns the optional Claude Code model and other per-instance configuration. The [Agent Preset architecture](2026-08-03-per-session-agent-presets.md) continues to own the Host/Agent split, preset authoring, and the rule that edits affect only newly composed sessions. +Each provider package owns its directly installable Bundle patch and private product runtime. This note continues to own process-wide Host placement whenever either provider is installed. The provider-contract note continues to own each product protocol, result mapping, cancellation, process-tree lifecycle, and evidence tiers. The [named-instance decision](../feature/2026-08-18-product-subagent-named-instances.md) owns both optional product models and other per-instance configuration. The [Agent Preset architecture](2026-08-03-per-session-agent-presets.md) continues to own the Host/Agent split, preset authoring, and the rule that edits affect only newly composed sessions. -Each Bundle delegates executable selection to its package-owned product runtime: the Codex package runs its declared wrapper, while the Claude Code package lets its pinned Agent SDK select the private native executable. Neither provider consults or falls back to a host product command. Profile loading creates no product state, probes no version or authentication, and may supply each mounted Provider instance's deployment configuration, including an optional opaque model where supported and the product-specific `permissionMode` values owned by the [non-interactive permissions decision](../feature/2026-08-15-product-subagent-noninteractive-permissions.md), without moving those choices into an Agent Preset or model-facing tool. Missing platform payloads and product failures remain local to the attempted delegation. +Each Bundle delegates executable selection to its package-owned product runtime: the Codex package runs its declared wrapper, while the Claude Code package lets its pinned Agent SDK select the private native executable. Neither provider consults or falls back to a host product command. Profile loading creates no product state, probes no version or authentication, and may supply each mounted Provider instance's deployment configuration, including an optional opaque model and the product-specific `permissionMode` values owned by the [non-interactive permissions decision](../feature/2026-08-15-product-subagent-noninteractive-permissions.md), without moving those choices into an Agent Preset or model-facing tool. Missing platform payloads and product failures remain local to the attempted delegation. ## Verification diff --git a/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.zh.md b/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.zh.md index 374a3ef72e..cce746399b 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-10-product-subagent-providers-in-shared-host.zh.md @@ -14,9 +14,9 @@ Status: implemented 产品提供方仍是进程级的 host plane（宿主平面）注册。[生产安装排除决策](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md)只取代本说明原先由 base bundle 安装提供方的选择：生产 `dsh-base` 既不依赖也不挂载它们。选择产品集成的 Profile 会安装目标提供方 Bundle；其 patch 挂载默认实例，而 Profile 可以在 host plane 挂载更多命名实例。[命名实例决策](../feature/2026-08-18-product-subagent-named-instances.zh.md)负责每个配置项的注册身份：两个产品都接受多个唯一的 `providerName`，同时保留 `codex` 与 `claude-code` 作为默认值。加载任一插件只会注册一个休眠后端；对应的 Codex 或 Claude 进程直到第一次实际委派调用时才启动。Agent Preset 通过普通 `dsh-tool-subagent` 配置项的 `provider` 与 `toolName` 准确公开单个 agent 所需的已配置实例，而无需更改 Host 注册表。 -每个提供方包都拥有可直接安装的 Bundle patch 与私有产品运行时。本说明继续负责每个已安装提供方的进程级 Host 放置。提供方约定说明继续负责每个产品的协议、结果映射、取消、进程树生命周期与证据层级。[命名实例决策](../feature/2026-08-18-product-subagent-named-instances.zh.md)负责可选 Claude Code 模型及其他逐实例配置。[Agent Preset 架构](2026-08-03-per-session-agent-presets.zh.md)继续负责宿主与 agent 的划分、preset 创作，以及改动只影响新组装会话的规则。 +每个提供方包都拥有可直接安装的 Bundle patch 与私有产品运行时。本说明继续负责每个已安装提供方的进程级 Host 放置。提供方约定说明继续负责每个产品的协议、结果映射、取消、进程树生命周期与证据层级。[命名实例决策](../feature/2026-08-18-product-subagent-named-instances.zh.md)负责两个可选产品模型及其他逐实例配置。[Agent Preset 架构](2026-08-03-per-session-agent-presets.zh.md)继续负责宿主与 agent 的划分、preset 创作，以及改动只影响新组装会话的规则。 -每个 Bundle 都把可执行文件选择交给包自有的产品运行时：Codex 包运行自身声明的 wrapper，Claude Code 包则让锁定的 Agent SDK 选择私有原生可执行文件。两个提供方都不会查询或回退宿主产品命令。加载 Profile 不会创建产品状态、探测版本或测试身份验证；它可以提供每个已挂载 Provider 实例的部署配置，包括产品支持时可选的不透明模型，以及由[非交互权限决策](../feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md)负责的产品专属 `permissionMode` 值，但不会把这些选择移入 Agent Preset 或面向模型的工具。平台载荷缺失和产品故障仍局限于发生问题的那次委派。 +每个 Bundle 都把可执行文件选择交给包自有的产品运行时：Codex 包运行自身声明的 wrapper，Claude Code 包则让锁定的 Agent SDK 选择私有原生可执行文件。两个提供方都不会查询或回退宿主产品命令。加载 Profile 不会创建产品状态、探测版本或测试身份验证；它可以提供每个已挂载 Provider 实例的部署配置，包括可选的不透明模型，以及由[非交互权限决策](../feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md)负责的产品专属 `permissionMode` 值，但不会把这些选择移入 Agent Preset 或面向模型的工具。平台载荷缺失和产品故障仍局限于发生问题的那次委派。 ## 验证 diff --git a/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.i18n.yaml similarity index 55% rename from .agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.i18n.yaml rename to .agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.i18n.yaml index 841a7fa457..a0e3fe3b06 100644 --- a/.agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-18-product-subagent-failure-facts.md -2026-08-18-product-subagent-failure-facts.md: e47fc3246ce20e988cd693b2eb04f785d37bcb27 -2026-08-18-product-subagent-failure-facts.zh.md: 5efd15e0e22d38b0100a96fc020ba3671fd257ed +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.md +2026-08-15-packed-session-history-transport.md: 01e36509b7ad2c878ae4ea04c3a10f029e1b8f3d +2026-08-15-packed-session-history-transport.zh.md: 590385dcfac901ab01e472ee75e766e51bf4b001 diff --git a/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.md b/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.md new file mode 100644 index 0000000000..01e36509b7 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.md @@ -0,0 +1,61 @@ +# Agent Note: Carry packed chunk rows through session history + +Status: implemented + +English | [中文](2026-08-15-packed-session-history-transport.zh.md) + +## Problem + +`session.page` and the opening `session.follow` snapshot serve a bounded logical Session-event interval to remote clients. Provider streams can place hundreds of thousands of token-sized `assistant/chunk` events in one incomplete tail. Expanding every persisted row and then serializing every logical event repeats the same envelope on the wire. Expanding a packed response at the Client boundary recreates the same event objects, journal entries, Location indexing, Definition matches, and State updates before conversation replay can finish. + +The transport must remain lossless. Session sequence numbers are pagination and reconnect evidence; exact fragment boundaries and timestamps remain useful to diagnostics and non-UI API consumers; live streaming, durable export, replay, and model-history derivation continue to require the canonical event stream. Browser presentation does not require one allocated event object and one Definition callback per historical fragment when a Definition can fold the lossless run directly. + +## Decision + +History pages and follow opening snapshots carry `records: SessionHistoryRecord[]`. An ordinary record is `{ type: 'event', event: SessionWireEvent }`; consecutive same-block Assistant delta events use `{ type: 'chunks', event: ChunkRowEvent }` and the shared lossless codec from [the packed JSONL decision](2026-07-26-packed-chunk-rows-by-default.md). The Host constructs the event-shaped value once when it packs the selected page. Its `type` is `chunkrow/text-chunks`, `chunkrow/reasoning-chunks`, or `chunkrow/tool-call-chunks`; `seq` and `time` identify the first member, while `data` retains the original fragment and timestamp-gap arrays. The explicit outer discriminator selects the record class without interpreting that detailed chunk kind. The page is selected from logical events before packing, so message-aligned pagination remains independent of physical persistence layout. + +The generated Remote decoder validates the response fields. `SessionEventStream` passes the original wire records to `RemoteJournalStream` and supplies each record's inclusive logical sequence range: an event covers `[event.seq, event.seq]`, while a row covers `[event.seq, event.seq + memberCount - 1]`. The journal checks page continuity, pagination joins, reconnect repair, complete duplicates, partial overlaps, and live-event deduplication before publishing records. The durable address in the page request selects either an ordinary Session or an authorized direct subagent child without a second history protocol. + +The Client narrows the accepted `SessionHistoryRecord[]` to `SessionEventLikeEntry[]` without allocating replacement entries. The outer `type` remains available to the journal, Session, and assembler; both variants carry an inner value with aligned `type`, `seq`, `time`, and `data` fields. `ChunkRowEvent` is Client history data, not a durable Session event: it is absent from `SessionEventMap`, `Session.events`, and `session/event`. + +Conversation accepts the same `{ type, event }` entries retained by Session. Definitions receive the inner `SessionEventLike`: `match()` and `update()` accept standard or packed values, while `start()` accepts only a standard `SessionEvent`; the assembler uses the outer discriminator to reject a packed start. Chat Assistant, Turn Tail, and Trajectory Assistant handle the three packed tags in their existing reducers. One row therefore remains one Client entry, Conversation input, and Match, while those reducers preserve scalar replay's final blocks, tool-call fields, first-token time, first-visible boundary, retry behavior, and interruption state. + +Live `session.follow` frames remain individual events and use the scalar path, so visible streaming cadence is unchanged. Session persistence, raw export, replay, model-history derivation, and the canonical in-memory log are unchanged. + +## Measured result + +A production-sized private session sample was measured without retaining or committing its content. Its tail page contained 416,756 logical events. The lossless packed response used 696 top-level records, including 116 packed rows. + +| Representation | Top-level records | JSON bytes | gzip bytes | Brotli bytes | +| --- | ---: | ---: | ---: | ---: | +| Raw logical events | 416,756 | 69,433,638 | 4,190,226 | 1,972,998 | +| Completed-step projection candidate | 228,129 | 38,427,209 | 2,324,688 | 957,350 | +| Lossless packed history | 696 | 6,362,724 | 1,154,206 | 528,145 | + +Packing reduced uncompressed JSON by 90.8% relative to raw logical events and by 83.4% relative to the lossy completed-step projection candidate. Brotli output was 73.2% smaller than raw and 44.8% smaller than that projection candidate. These figures describe this sample rather than a protocol guarantee; savings scale with the length and regularity of delta runs. + +One-to-one Client retention keeps the same sample at 696 history entries and Conversation inputs instead of restoring 416,756 event entries. A local synthetic benchmark run measured Client parse, validation, retention, and two-Definition fold at 4,682.11 ms for scalar input and 276.10 ms for packed input, with sampled additional V8 heap peaks of 612,523,344 and 199,436,928 bytes respectively. These machine-dependent values are observations rather than thresholds. + +The opt-in `packages/client/ui-conversation/tests/history-transport.perf.client.ts` benchmark constructs the same logical-event, ordinary-event, and delta-run cardinalities from synthetic content. `DSH_SNAPSHOT=replay pnpm exec vitest run --config vitest.web.perf.config.ts packages/client/ui-conversation/tests/history-transport.perf.client.ts` reports wire sizes, Host/client timing, uncompressed chunked Node loopback transfer medians, combined synthetic API-wait/UI-ready timing, and sampled additional V8 heap peaks under `HISTORY_TRANSPORT_PERF_RESULT`; a second inventory reports batch-fold medians for 10,000-, 20,000-, and 40,000-member whitespace-prefix runs under `HISTORY_WHITESPACE_PREFIX_PERF_RESULT`. The combined timing starts from an in-memory event array and omits cold persistence reads, the production API bridge and RPC envelope, and Chromium scheduling, so it is comparative inventory rather than production wall-clock latency. Heap measurements force garbage collection before three runs and report the median peak observed after each major Host construction/serialization or Client parse/validation/retention/fold stage, relative to the same initialized benchmark state; they do not measure process RSS, external or ArrayBuffer memory, or transients within a sampled stage. The manual performance inventory does not run in CI and carries no machine-dependent timing or memory assertions; structural assertions pin the fixture cardinalities, one Client input per wire record, and identical final state—including delta count and last-delta sequence—from its two-consumer Assistant fold fixture. + +## Alternatives considered + +**Discard completed-step chunks on the Host.** This lowers logical event count but makes transport semantics depend on the current transcript policy, removes exact evidence from all consumers, and still sends every retained incomplete-step token as a separate envelope. The measured packed response is smaller while remaining lossless. + +**Expand each packed row before the Session object layer.** This preserves one callback per historical delta but recreates the browser allocation, indexing, and fold costs that packed transport can avoid. Consumers that require scalar events can still call `decodeStorageRecord()` explicitly. + +**Put the raw row under a distinct `.chunks` payload.** This forces downstream consumers either to retain two payload field names or to allocate an aligned wrapper before assembly. The shared `.event` field preserves fast outer classification and one inner Definition path. + +**Rely on HTTP content encoding.** gzip and Brotli reduce bytes on the network but do not remove repeated JSON parsing, validation, allocation, indexing, and fold work. + +**Page directly over physical persistence rows.** This could also avoid logical expansion in a cold Host read, but page cuts depend on append-origin messages and replacement provenance rather than backend row boundaries. The current decision keeps the API independent of JSONL, SQLite, and future persistence layouts. + +**Return only assembled Assistant snapshots.** The [assembled-messages-only rejection](../../rejected/simplification/2026-06-20-assembled-assistant-messages-only.md) remains applicable: event families outside finalized messages carry user-visible and diagnostic state, and incomplete steps need their actual accumulated chunks. + +## Consequences + +History responses preserve every logical event while reducing wire bytes, Host response serialization and heap, browser JSON parsing and validation, Client entry allocation, and Conversation dispatch for long delta runs. The journal validates logical ranges before publication, so packed records neither create false gaps nor hide partial overlap. Direct `session.page` consumers must switch on `SessionHistoryRecord.type` and explicitly expand `record.event.data` when they require one event per member. + +Cold persisted history is still decoded into the complete logical `SessionEvent[]` before the Host selects and repacks a page. This decision therefore improves transport and browser work, not the Host's cold-read decode memory. Eliminating that expansion requires a persistence-neutral message-boundary index or a separate streaming page reader and remains a distinct optimization. + +The default Client history path exposes `SessionEventLike`, so consumers that require only canonical durable events must remain on Host `Session.events`, `session/event`, or an explicit decode path. A Definition that consumes Assistant deltas maintains equivalent scalar and packed branches. Scalar deltas already received live remain scalar in the current window; online replacement with a packed row is separate work, while reopen and reconnect install packed history. diff --git a/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.zh.md b/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.zh.md new file mode 100644 index 0000000000..590385dcfa --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.zh.md @@ -0,0 +1,61 @@ +# Agent Note: 在会话历史中传输打包分片行 + +Status: implemented + +[English](2026-08-15-packed-session-history-transport.md) | 中文 + +## 问题 + +`session.page` 与 `session.follow` opening snapshot 会向远程 Client 提供一段有界的逻辑 Session event 区间。提供方流可能在一个未完成尾部中产生数十万个 token 大小的 `assistant/chunk` 事件。先展开每条持久化行，再序列化每个逻辑事件，会在协议中重复相同 envelope。在 Client 边界展开 packed response 还会重新创建同样数量的 event object、journal entry、Location index、Definition match 和 State update，拖慢 conversation replay。 + +传输必须保持无损。Session seq 是分页与重连证据；精确 fragment 边界和时间戳对诊断与非 UI API 消费方仍然有用；实时流式传输、持久导出、回放与模型历史派生仍然需要规范事件流。当 Definition 可以直接 fold 无损 run 时，浏览器表现并不需要为每个历史 fragment 分配一个 event object 并执行一次 Definition callback。 + +## 决策 + +历史页与 follow opening snapshot 携带 `records: SessionHistoryRecord[]`。普通 record 为 `{ type: 'event', event: SessionWireEvent }`；连续且属于同一 block 的 Assistant delta event 使用[打包 JSONL 决策](2026-07-26-packed-chunk-rows-by-default.zh.md)中的共享无损 codec，表示为 `{ type: 'chunks', event: ChunkRowEvent }`。Host 在打包已选页面时只构造一次 event-shaped value。其 `type` 为 `chunkrow/text-chunks`、`chunkrow/reasoning-chunks` 或 `chunkrow/tool-call-chunks`；`seq` 与 `time` 表示首成员，`data` 保留原 fragment 与 timestamp-gap 数组。显式外层 discriminator 无需解释详细 chunk kind 即可选择 record 类别。系统先从逻辑 event 中选择页面，再执行打包，因此按消息对齐的分页不依赖物理持久化布局。 + +生成的 Remote decoder 会校验响应字段。`SessionEventStream` 把原始 wire record 交给 `RemoteJournalStream`，并提供每条 record 的逻辑 seq 闭区间：event 覆盖 `[event.seq, event.seq]`，row 覆盖 `[event.seq, event.seq + memberCount - 1]`。Journal 在发布 record 前检查页面连续性、分页拼接、重连修复、完整重复、部分重叠和实时 event 去重。页面请求中的 durable address 既可选择普通 Session，也可选择已授权的 direct subagent child，无需第二套历史协议。 + +Client 不分配替换 entry，直接把已接受的 `SessionHistoryRecord[]` 收窄为 `SessionEventLikeEntry[]`。外层 `type` 会一直保留到 journal、Session 与 assembler；两个分支都携带字段对齐的内部值，其中包含 `type`、`seq`、`time` 与 `data`。`ChunkRowEvent` 是 Client 历史数据，不是持久 Session event：它不会进入 `SessionEventMap`、`Session.events` 或 `session/event`。 + +Conversation 接受 Session 保留的同一组 `{ type, event }` entry。Definition 接收内部 `SessionEventLike`：`match()` 与 `update()` 接受标准或 packed value，`start()` 只接受标准 `SessionEvent`；assembler 使用外层 discriminator 拒绝 packed start。Chat Assistant、Turn Tail 和 Trajectory Assistant 在既有 reducer 中处理三种 packed tag。一条 row 因此始终只对应一个 Client entry、Conversation input 与 Match，而这些 reducer 会保留 scalar replay 的最终 block、tool-call 字段、首 token 时间、首个可见边界、retry 行为和 interruption 状态。 + +实时 `session.follow` frame 仍是单个 event 并走 scalar 路径，因此可见 streaming cadence 不变。Session persistence、原始导出、回放、模型历史派生与规范内存日志均不改变。 + +## 测量结果 + +测量使用了一份生产规模的私有会话样本，未保留或签入其内容。其尾页包含 416,756 个逻辑事件。无损打包响应使用 696 条顶层记录，其中包含 116 条打包行。 + +| 表示 | 顶层记录数 | JSON 字节 | gzip 字节 | Brotli 字节 | +| --- | ---: | ---: | ---: | ---: | +| 原始逻辑事件 | 416,756 | 69,433,638 | 4,190,226 | 1,972,998 | +| 已完成步骤投影候选 | 228,129 | 38,427,209 | 2,324,688 | 957,350 | +| 无损打包历史 | 696 | 6,362,724 | 1,154,206 | 528,145 | + +与原始逻辑事件相比，打包使未压缩 JSON 减少 90.8%；与有损的已完成步骤投影候选相比减少 83.4%。Brotli 输出相对原始形式减少 73.2%，相对该投影候选减少 44.8%。这些数字描述该样本，并非协议保证；收益随 delta run 的长度与规律性变化。 + +一对一 Client 保留使同一规模样本保持为 696 个 history entry 与 Conversation input，而不会恢复成 416,756 个 event entry。一次本地合成 benchmark 观测到：Client parse、validation、retention 与双 Definition fold 在 scalar input 下耗时 4,682.11 ms，在 packed input 下耗时 276.10 ms；采样额外 V8 heap 峰值分别为 612,523,344 与 199,436,928 字节。这些依赖机器的数值是观测结果，不是门槛。 + +可选运行的 `packages/client/ui-conversation/tests/history-transport.perf.client.ts` benchmark 使用合成内容构造相同的逻辑 event 数、普通 event 数与 delta run 数。`DSH_SNAPSHOT=replay pnpm exec vitest run --config vitest.web.perf.config.ts packages/client/ui-conversation/tests/history-transport.perf.client.ts` 会在 `HISTORY_TRANSPORT_PERF_RESULT` 下报告 wire 体积、Host／Client 计时、未压缩且采用 chunked response 的 Node loopback 传输中位数、组合后的合成 API 等待／UI 就绪时间，以及采样的额外 V8 heap 峰值；第二组清单会在 `HISTORY_WHITESPACE_PREFIX_PERF_RESULT` 下报告 10,000、20,000 与 40,000 个成员 whitespace-prefix run 的 batch fold 中位数。组合计时从内存 event 数组开始，不包含冷持久化读取、生产 API bridge 与 RPC envelope，也不包含 Chromium 调度，因此它是对比清单，而非生产环境 wall-clock 延迟。Heap 测量会在三次运行前强制执行垃圾回收，并相对于相同的已初始化 benchmark 状态，报告 Host 构造／序列化或 Client 解析／校验／保留／fold 各主要阶段之后所观察峰值的中位数；该指标不测量进程 RSS、external 或 ArrayBuffer 内存，也可能遗漏单个采样阶段内部的瞬态峰值。CI 不执行这组手动性能用例，其中也没有依赖机器性能的耗时或内存断言；结构断言固定 fixture 规模、每条 wire record 对应一个 Client input，以及双消费方 Assistant fold fixture 的一致最终状态，包括 delta 数量与末个 delta seq。 + +## 曾考虑的替代方案 + +**在 Host 丢弃已完成步骤的分片。** 这会减少逻辑事件数，但会让传输语义取决于当前 transcript 策略，从所有消费方移除精确证据，同时仍把保留的未完成步骤 token 逐个装入信封。实测打包响应在保持无损的同时更小。 + +**在进入 Session 对象层前展开每条 packed row。** 这会保留每个历史 delta 一次 callback 的语义，但也会重新产生 packed transport 原本可以避免的浏览器分配、索引和 fold 成本。确实需要 scalar event 的消费方仍可显式调用 `decodeStorageRecord()`。 + +**把原始 row 放在独立的 `.chunks` payload 下。** 这会迫使下游消费方保留两种 payload 字段名，或在进入 assembly 前分配字段对齐的包装层。共享 `.event` 字段既保留快速外层分类，也保留一条内部 Definition 路径。 + +**只依赖 HTTP 内容编码。** gzip 与 Brotli 会减少网络字节，但不会移除重复的 JSON 解析、校验、分配、索引与 fold 工作。 + +**直接按物理持久化行分页。** 这还可以避免冷 Host 读取时的逻辑展开，但页面切分取决于追加来源消息与替换 provenance，而不是后端行边界。当前决策让 API 保持对 JSONL、SQLite 与未来持久化布局的独立性。 + +**只返回组装后的 Assistant 快照。** [仅保留组装消息的否决记录](../../rejected/simplification/2026-06-20-assembled-assistant-messages-only.zh.md)仍然适用：final message 之外的事件族承载用户可见状态与诊断状态，未完成步骤也需要其实际累计分片。 + +## 后果 + +历史响应保留每个逻辑 event，同时减少长 delta run 的 wire 字节、Host 响应序列化与 heap、浏览器 JSON 解析与校验、Client entry 分配，以及 Conversation dispatch。Journal 在发布前校验逻辑 range，因此 packed record 既不会产生伪 gap，也不会隐藏部分重叠。直接调用 `session.page` 的消费方必须按 `SessionHistoryRecord.type` 分支；需要逐 member event 时再显式展开 `record.event.data`。 + +冷持久历史仍会先解码成完整的逻辑 `SessionEvent[]`，Host 再选择页面并重新打包。因此，本决策改善的是传输与浏览器工作，不是 Host 冷读取的解码内存。消除该展开需要提供方无关的消息边界索引或单独的流式页面读取器，属于另一项优化。 + +默认 Client 历史路径公开 `SessionEventLike`，因此只接受规范持久 event 的消费方必须继续使用 Host `Session.events`、`session/event` 或显式 decode 路径。消费 Assistant delta 的 Definition 需要维护等价的 scalar 与 packed 分支。当前窗口已经实时接收的 scalar delta 仍保持 scalar；在线替换为 packed row 属于另一项工作，reopen 与 reconnect 则安装 packed 历史。 diff --git a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.i18n.yaml b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.i18n.yaml index eba9e6e605..8a9c235a3b 100644 --- a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md -2026-08-04-claude-code-and-codex-subagent-backends.md: 8af99c9171e073e5901390fed29047b350fe4924 -2026-08-04-claude-code-and-codex-subagent-backends.zh.md: 5abc0b16077bcf0be7835b2cf687a1709b53fc81 +2026-08-04-claude-code-and-codex-subagent-backends.md: 04b8fcb9c3fd899a485a12ce9c002b8ab5d6bbb3 +2026-08-04-claude-code-and-codex-subagent-backends.zh.md: de9248ed7c82266bd6083020ab32190a3dfd8d1f diff --git a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md index 8af99c9171..04b8fcb9c3 100644 --- a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md +++ b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md @@ -12,7 +12,7 @@ The product integrations must not become second owners for task text, cwd, cance ## Decision -The harness publishes two sibling one-shot provider packages whose default registry names are `codex` and `claude-code`. This note owns their product protocols, result mapping, and process lifecycle; the [named-instance decision](2026-08-18-product-subagent-named-instances.md) owns Profile-selected provider identity, optional instance model where supported, and static tool binding; the [production-install exclusion decision](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md) owns their independent optional Bundles and host-plane placement; the [product one-shot background decision](2026-08-12-product-subagent-one-shot-background-tasks.md) owns the model-visible scheduling choice; the [non-interactive permissions decision](2026-08-15-product-subagent-noninteractive-permissions.md) owns each product Provider's Profile-selected mode and safe permission decisions; and the [minimal-diagnostics decision](../simplification/2026-08-21-product-subagent-minimal-diagnostics.md) owns coarse product action categories while the [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) continues to describe Codex's current detailed categories. Both packages accept multiple named instances. Loading either provider starts no product process, and each tool accepts only a standalone text task; product and instance selection remain deployment configuration. +The harness publishes two sibling one-shot provider packages whose default registry names are `codex` and `claude-code`. This note owns their product protocols, result mapping, and process lifecycle; the [named-instance decision](2026-08-18-product-subagent-named-instances.md) owns Profile-selected provider identity, optional instance model, and static tool binding; the [production-install exclusion decision](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md) owns their independent optional Bundles and host-plane placement; the [product one-shot background decision](2026-08-12-product-subagent-one-shot-background-tasks.md) owns the model-visible scheduling choice; the [non-interactive permissions decision](2026-08-15-product-subagent-noninteractive-permissions.md) owns each product Provider's Profile-selected mode and safe permission decisions; and the [minimal-diagnostics decision](../simplification/2026-08-21-product-subagent-minimal-diagnostics.md) owns coarse product action categories. Both packages accept multiple named instances. Loading either provider starts no product process, and each tool accepts only a standalone text task; product and instance selection remain deployment configuration. Both providers report `inheritsParentContext: false`, advertise no optional start capabilities, and pass the parent Session cwd without copying the parent conversation. Their documented tools use `backgroundMode: 'one-shot'` and `maxDepth: 'provider-managed'`: the consumer keeps foreground collection as the default and may place the same run in the generic Job runtime, while recursion policy stays with the out-of-process product. Every call creates a fresh product process and a non-resumable product conversation. `ctx.subagents` owns named-request resolution and paired lifecycle events; `dsh-tool-subagent` owns model-visible scheduling and foreground-versus-Job adaptation; `ctx.jobs` and `dsh-tool-jobs` own Job ids, state, output, controls, notices, and parent-owner cancellation; each product provider owns native result mapping, while `dsh-subprocess` owns credential scrubbing, process-tree termination, and whole-tree exit observation. @@ -34,17 +34,17 @@ configured tool -> dsh-tool-subagent -> ctx.subagents -> product provider -> pro ## Codex provider -`@deepseek-ai/dsh-subagent-codex` registers a Profile-selected provider name that defaults to `codex`, resolves the `codex` bin declared by its pinned `@openai/codex@0.147.0` package, and starts that wrapper through the current Node executable with `app-server --stdio`. The wrapper selects the private native platform payload; the provider neither resolves nor falls back to a host `codex`. Its public configuration contains a non-empty `providerName`, an explicit `env` overlay, a positive finite `disposeGraceMs` no greater than the repository's shared `MAX_TIMER_DELAY_MS`, and a three-value native `permissionMode` that defaults to `never`. Each named instance retains those resolved values for its own runs. Installation, login, `CODEX_HOME`, model selection, base URL, and product-session settings remain native Codex or deployment responsibilities; the selected mode owns only the thread approval/reviewer/sandbox fields described by the non-interactive permissions decision. +`@deepseek-ai/dsh-subagent-codex` registers a Profile-selected provider name that defaults to `codex`, resolves the `codex` bin declared by its pinned `@openai/codex@0.149.1` package, and starts that wrapper through the current Node executable with `app-server --stdio`. The wrapper selects the private native platform payload; the provider neither resolves nor falls back to a host `codex`. Its public configuration contains a non-empty `providerName`, an optional non-empty `model`, an explicit `env` overlay, a positive finite `disposeGraceMs` no greater than the repository's shared `MAX_TIMER_DELAY_MS`, and a three-value native `permissionMode` that defaults to `never`. Each named instance retains those resolved values for its own runs. An explicit model is passed unchanged on every ephemeral `thread/start`; omission leaves native Codex settings authoritative. Installation, login, `CODEX_HOME`, model discovery or fallback, base URL, and product-session settings remain native Codex or deployment responsibilities; the selected mode owns only the thread approval/reviewer/sandbox fields described by the non-interactive permissions decision. -Before publication, the provider validates a non-empty text-only task, starts the managed app-server in the parent workspace, completes `initialize` → `initialized`, maps the resolved mode into official `thread/start` fields, and creates an `ephemeral: true` thread. The fixed app-server argv contains no mode or task text. The published run owns exactly one `turn/start`; its thread and turn ids remain private and are never persisted in the parent Session. +Before publication, the provider validates a non-empty text-only task, starts the managed app-server in the parent workspace, completes `initialize` → `initialized`, maps the optional model and resolved mode into official `thread/start` fields, and creates an `ephemeral: true` thread. The fixed app-server argv contains no model, mode, or task text. The published run owns exactly one `turn/start`; its thread and turn ids remain private and are never persisted in the parent Session. -`turn/completed` is the authoritative remote terminal fact. The latest `agentMessage` with `phase: "final_answer"` wins, and that selected message must contain nonblank text. When the product emits no explicit final phase, the latest message with `phase: null` is the compatibility fallback and must likewise be nonblank; commentary never replaces either answer. The [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) owns Codex error-info categories, HTTP status, lifecycle stages, process outcomes, and stop-reason preservation. Local cancellation remains `aborted` without a failure diagnostic. +`turn/completed` is the authoritative remote terminal fact. The latest `agentMessage` with `phase: "final_answer"` wins, and that selected message must contain nonblank text. When the product emits no explicit final phase, the latest message with `phase: null` is the compatibility fallback and must likewise be nonblank; commentary never replaces either answer. The [minimal-diagnostics decision](../simplification/2026-08-21-product-subagent-minimal-diagnostics.md) owns Codex action categories, HTTP status, lifecycle stages, process outcomes, and stop-reason preservation. Local cancellation remains `aborted` without a failure diagnostic. -For command and file approvals, the unattended wire selects a non-approval decision offered by the request, preferring `cancel`; the stable 0.147.0 request shape without an offered-decision list falls back to `decline`. It grants no requested permissions for the turn, answers user-input requests with no answers, and declines MCP elicitation. It records safe categories for those requests, declined command/file items, and `sandboxError`. Codex emits some early `never` rejections and sandbox violations only on structured stderr, so the Provider pipes and forwards stderr unchanged while matching two fixed signatures in a bounded per-run tail; raw stderr never enters the diagnostic. A request with no legal unattended response, or any unknown server request, fails the run instead of waiting for a user interface the provider does not supply. +For command and file approvals, the unattended wire selects a non-approval decision offered by the request, preferring `cancel`; the stable 0.149.1 request shape without an offered-decision list falls back to `decline`. It grants no requested permissions for the turn, answers user-input requests with no answers, and declines MCP elicitation. It records safe categories for those requests, declined command/file items, and structured `sandboxError` terminals. Product stderr is forwarded unchanged to the Host but is neither classified nor copied into the diagnostic. A request with no legal unattended response, or any unknown server request, fails the run instead of waiting for a user interface the provider does not supply. An unpublished startup failure closes the wire, terminates the acquired process tree, waits for exit, detaches the stderr observer, and then rejects `start()` with its fixed operation stage. Published disposal best-effort interrupts a known turn, closes the wire, ends stdin, invokes the shared termination escalation, waits for whole-tree exit, and detaches the observer. Independent cleanup failure reports `teardown`; when startup and rollback both fail, the aggregate's top message retains both safe stage lines while the underlying causes remain internal. -Codex 0.147.0 speaks the Responses protocol, while DeepSeek's public OpenAI-compatible endpoint speaks Chat Completions. The credentialed Codex e2e therefore uses a loopback-only, test-private bridge for one no-tool nonce request: real Codex sends Responses to the bridge, the bridge forwards the received bearer credential and extracted task to the fixed official DeepSeek endpoint, and it wraps the real text in the minimal Responses SSE lifecycle. The bridge is neither a production proxy nor evidence that Codex connects to DeepSeek Chat Completions natively. +Codex 0.149.1 speaks the Responses protocol, while DeepSeek's public OpenAI-compatible endpoint speaks Chat Completions. The credentialed Codex e2e therefore uses a loopback-only, test-private bridge for one no-tool nonce request: real Codex sends Responses to the bridge, the bridge forwards the received bearer credential and extracted task to the fixed official DeepSeek endpoint, and it wraps the real text in the minimal Responses SSE lifecycle. The bridge is neither a production proxy nor evidence that Codex connects to DeepSeek Chat Completions natively. ## Claude Code provider @@ -62,7 +62,7 @@ The credentialed Claude Code e2e uses the official DeepSeek Claude Code contract Each product owns branch-complete package tests, a required keyless real-product spec, a Loader composition e2e, and a credentialed DeepSeek e2e. The keyless product tier uses the exact official distribution under test, a non-empty fake product key, an isolated temporary workspace and product home, and a loopback fixed-answer model. Missing product requests, wrong authentication, altered task text, a non-exact answer, a skipped real product, or a surviving managed handle fails the required test. The Codex Loader fixture exposes two named Codex instances and tools; the Claude Code Loader fixture exposes the default Codex tool plus two named Claude Code instances and tools. Both fixtures include generic Job controls and start neither product process. The credentialed tier starts the same production provider and real product with a runtime-only key, requires a unique nonce from the fixed official DeepSeek service, and proves quiescence again; it self-skips only when a local operator supplied no key, while trusted CI preflights the secret. -The Codex evidence pins `@openai/codex@0.147.0`, `codex-cli 0.147.0`, and all six optional platform aliases. Its real-product spec observes the package-local wrapper argv, exact Bearer key, original task, byte-exact final answer, native permission modes, explicit dangerous-bypass writing in suite-owned temporary storage, and wrapper/native whole-tree exit. An isolated wrapper fixture proves missing-payload failure without host fallback, two named instances retain separate environments and modes, and production never resolves a host `codex` from `PATH`. The [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) owns schema, failure, process-outcome, and final presentation evidence. +The Codex evidence pins `@openai/codex@0.149.1`, `codex-cli 0.149.1`, and all six optional platform aliases. Its generated schema proves optional `ThreadStartParams.model`; the real-product spec observes omitted-model inheritance, two explicit instance models, the package-local wrapper argv, exact Bearer key, original task, byte-exact final answer, native permission modes, explicit dangerous-bypass writing in suite-owned temporary storage, and wrapper/native whole-tree exit. An isolated wrapper fixture proves missing-payload failure without host fallback, named instances retain separate models, environments, and modes, and production never resolves a host `codex` from `PATH`. The [minimal-diagnostics decision](../simplification/2026-08-21-product-subagent-minimal-diagnostics.md) owns failure, process-outcome, and final presentation evidence. The Codex credentialed e2e registers the production provider, starts the same real app-server, and requests one random nonce through the test-private bridge described above. It fixes the external endpoint and model, stores no credential or request payload, requires exactly one completed upstream response, compares the trimmed product answer byte-for-byte with the nonce, and waits for every managed handle to exit. diff --git a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md index 5abc0b1607..de9248ed7c 100644 --- a/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md +++ b/.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md @@ -12,7 +12,7 @@ Status: implemented ## 决策 -harness 交付两个同级的一次性提供方包，其默认注册名称分别为 `codex` 与 `claude-code`。本说明负责它们的产品协议、结果映射和进程生命周期；[命名实例决策](2026-08-18-product-subagent-named-instances.zh.md)负责 Profile 选择的提供方身份、支持时的可选实例模型与静态工具绑定；[生产安装排除决策](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md)负责各自独立的可选 Bundle 与 host plane（宿主平面）放置；[产品一次性后台任务决策](2026-08-12-product-subagent-one-shot-background-tasks.zh.md)负责模型可见的调度选择；[非交互权限决策](2026-08-15-product-subagent-noninteractive-permissions.zh.md)负责各产品提供方的 Profile 模式选择与安全权限决定；[最小诊断决策](../simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md)负责粗粒度产品行动类别，而[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.zh.md)继续描述 Codex 当前的详细类别。两个包都接受多个命名实例。加载任一提供方都不会启动产品进程，而且每个工具只接受独立文本任务；产品与实例选择仍属于部署配置。 +harness 交付两个同级的一次性提供方包，其默认注册名称分别为 `codex` 与 `claude-code`。本说明负责它们的产品协议、结果映射和进程生命周期；[命名实例决策](2026-08-18-product-subagent-named-instances.zh.md)负责 Profile 选择的提供方身份、可选实例模型与静态工具绑定；[生产安装排除决策](../simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md)负责各自独立的可选 Bundle 与 host plane（宿主平面）放置；[产品一次性后台任务决策](2026-08-12-product-subagent-one-shot-background-tasks.zh.md)负责模型可见的调度选择；[非交互权限决策](2026-08-15-product-subagent-noninteractive-permissions.zh.md)负责各产品提供方的 Profile 模式选择与安全权限决定；[最小诊断决策](../simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md)负责粗粒度产品行动类别。两个包都接受多个命名实例。加载任一提供方都不会启动产品进程，而且每个工具只接受独立文本任务；产品与实例选择仍属于部署配置。 这两个提供方都报告 `inheritsParentContext: false`，不声明任何可选的启动能力，并传递父会话 cwd，但不会复制父级对话。文档所示的工具使用 `backgroundMode: 'one-shot'` 与 `maxDepth: 'provider-managed'`：消费方默认在前台收集结果，也可把同一次运行放入通用 Job 运行时，而递归策略仍由进程外产品负责。每次调用都会创建一个全新的产品进程和一次不可续接的产品对话。`ctx.subagents` 负责具名请求解析与成对生命周期事件；`dsh-tool-subagent` 负责模型可见的调度以及前台与 Job 适配；`ctx.jobs` 和 `dsh-tool-jobs` 负责 Job id、状态、输出、控制、通知与父级 owner 取消；各产品提供方负责原生结果映射，`dsh-subprocess` 则负责凭证清洗、进程树终止以及整棵进程树的退出观测。 @@ -34,17 +34,17 @@ configured tool -> dsh-tool-subagent -> ctx.subagents -> product provider -> pro ## Codex 提供方 -`@deepseek-ai/dsh-subagent-codex` 注册由 Profile 选择、默认值为 `codex` 的提供方名称，解析锁定的 `@openai/codex@0.147.0` 包所声明的 `codex` bin，并使用当前 Node 可执行文件加 `app-server --stdio` 启动该 wrapper。Wrapper 会选择私有原生平台载荷；提供方既不解析也不回退宿主 `codex`。其公开配置包含非空的 `providerName`、显式的 `env` 覆盖项、须为正有限值且不得大于仓库共享 `MAX_TIMER_DELAY_MS` 的 `disposeGraceMs`，以及默认使用 `never` 的三值原生 `permissionMode`。每个命名实例会为自己的运行保留这些已解析值。安装、登录、`CODEX_HOME`、模型选择、基础 URL 和产品会话设置仍由 Codex 原生机制或部署环境负责；所选模式只拥有非交互权限决策中描述的线程 approval／reviewer／sandbox 字段。 +`@deepseek-ai/dsh-subagent-codex` 注册由 Profile 选择、默认值为 `codex` 的提供方名称，解析锁定的 `@openai/codex@0.149.1` 包所声明的 `codex` bin，并使用当前 Node 可执行文件加 `app-server --stdio` 启动该 wrapper。Wrapper 会选择私有原生平台载荷；提供方既不解析也不回退宿主 `codex`。其公开配置包含非空的 `providerName`、可选的非空 `model`、显式的 `env` 覆盖项、须为正有限值且不得大于仓库共享 `MAX_TIMER_DELAY_MS` 的 `disposeGraceMs`，以及默认使用 `never` 的三值原生 `permissionMode`。每个命名实例会为自己的运行保留这些已解析值。显式模型会原样传给每个临时 `thread/start`；省略时仍以 Codex 原生设置为权威。安装、登录、`CODEX_HOME`、模型发现或 fallback、基础 URL 和产品会话设置仍由 Codex 原生机制或部署环境负责；所选模式只拥有非交互权限决策中描述的线程 approval／reviewer／sandbox 字段。 -发布前，提供方会验证非空的纯文本任务，在父级工作区中启动受管的 app-server，完成 `initialize` → `initialized` 握手，把已解析模式映射为官方 `thread/start` 字段，并创建一个 `ephemeral: true` 线程。固定 app-server argv 不包含模式或任务文本。已发布的运行只拥有一次 `turn/start`；其线程 ID 与轮次 ID 保持私有，绝不会持久化到父会话。 +发布前，提供方会验证非空的纯文本任务，在父级工作区中启动受管的 app-server，完成 `initialize` → `initialized` 握手，把可选模型与已解析模式映射为官方 `thread/start` 字段，并创建一个 `ephemeral: true` 线程。固定 app-server argv 不包含模型、模式或任务文本。已发布的运行只拥有一次 `turn/start`；其线程 ID 与轮次 ID 保持私有，绝不会持久化到父会话。 -`turn/completed` 是权威的远端终止事实。以最后一条带有 `phase: "final_answer"` 的 `agentMessage` 为准，且选中的消息必须包含非空白文本。若产品没有发出明确的最终阶段，则以最后一条 `phase: null` 的消息作为兼容性回退，该消息也必须包含非空白文本；过程说明绝不会取代上述任一答案。[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.zh.md)负责 Codex error-info 类别、HTTP status、生命周期阶段、进程结果与终止原因保持。本地取消仍是 `aborted` 且不附带失败诊断。 +`turn/completed` 是权威的远端终止事实。以最后一条带有 `phase: "final_answer"` 的 `agentMessage` 为准，且选中的消息必须包含非空白文本。若产品没有发出明确的最终阶段，则以最后一条 `phase: null` 的消息作为兼容性回退，该消息也必须包含非空白文本；过程说明绝不会取代上述任一答案。[最小诊断决策](../simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md)负责 Codex 行动类别、HTTP status、生命周期阶段、进程结果与终止原因保持。本地取消仍是 `aborted` 且不附带失败诊断。 -对于命令与文件审批，无人值守的协议连接会从请求给出的决策选项中选择一项不予批准的决策，并优先选择 `cancel`；稳定的 0.147.0 请求形态没有决策选项列表，因此回退到 `decline`。它不授予该轮次请求的任何权限，不向用户输入请求提供任何答案，并拒绝 MCP elicitation。它会记录这些请求、被拒绝的命令／文件 item 与 `sandboxError` 的安全类别。Codex 的部分早期 `never` 拒绝和 sandbox violation 只写入结构化 stderr，因此提供方会 pipe 并原样转发 stderr，同时在每次运行的有界尾部中匹配两个固定签名；原始 stderr 绝不会进入诊断。若请求在无人值守模式下没有合法响应，或是未知服务器请求，此次运行就会失败，而不会等待本提供方没有提供的用户界面。 +对于命令与文件审批，无人值守的协议连接会从请求给出的决策选项中选择一项不予批准的决策，并优先选择 `cancel`；稳定的 0.149.1 请求形态没有决策选项列表，因此回退到 `decline`。它不授予该轮次请求的任何权限，不向用户输入请求提供任何答案，并拒绝 MCP elicitation。它会记录这些请求、被拒绝的命令／文件 item 与结构化 `sandboxError` 终态的安全类别。产品 stderr 会原样转发给 Host，但既不会被分类，也不会复制进诊断。若请求在无人值守模式下没有合法响应，或是未知服务器请求，此次运行就会失败，而不会等待本提供方没有提供的用户界面。 若启动在发布前失败，提供方会关闭协议连接、终止已获取的进程树、等待其退出、移除 stderr observer，然后用固定操作阶段拒绝 `start()`。对已发布的运行执行资源释放时，提供方会尽力中断已知轮次、关闭协议连接、结束标准输入、调用共享的逐级终止机制，等待整棵进程树退出，并移除 observer。独立清理失败会报告 `teardown`；启动与回滚同时失败时，聚合的顶层消息会保留两条安全阶段说明，而底层 cause 仍只在内部可见。 -Codex 0.147.0 使用 Responses 协议，而 DeepSeek 的公开 OpenAI 兼容端点使用 Chat Completions。因此，带密钥 Codex e2e 会采用一个仅限回环、仅供测试内部使用的桥接层来处理一次不使用工具的随机数请求：真实 Codex 将 Responses 发送到桥接层，桥接层把收到的 Bearer 凭据与提取出的任务转发到固定的 DeepSeek 官方端点，再将真实文本包装进最小化的 Responses SSE（Server-Sent Events）生命周期。该桥接层既不是生产代理，也不能作为 Codex 原生连接 DeepSeek Chat Completions 的证据。 +Codex 0.149.1 使用 Responses 协议，而 DeepSeek 的公开 OpenAI 兼容端点使用 Chat Completions。因此，带密钥 Codex e2e 会采用一个仅限回环、仅供测试内部使用的桥接层来处理一次不使用工具的随机数请求：真实 Codex 将 Responses 发送到桥接层，桥接层把收到的 Bearer 凭据与提取出的任务转发到固定的 DeepSeek 官方端点，再将真实文本包装进最小化的 Responses SSE（Server-Sent Events）生命周期。该桥接层既不是生产代理，也不能作为 Codex 原生连接 DeepSeek Chat Completions 的证据。 ## Claude Code 提供方 @@ -62,7 +62,7 @@ Codex 0.147.0 使用 Responses 协议，而 DeepSeek 的公开 OpenAI 兼容端 每个产品都负责覆盖所有分支的包测试、一项必跑的无密钥真实产品测试、一项 Loader 组合 e2e 和一项带密钥 DeepSeek e2e。无密钥产品层级使用被测的确切官方发行版、非空的伪产品密钥、隔离的临时工作区与产品主目录，以及能返回固定答案的回环模型。产品请求缺失、身份验证错误、任务文本被改动、答案不完全一致、真实产品被跳过或受管句柄仍存活，都会使这项必跑测试失败。Codex Loader fixture 会公开两个命名 Codex 实例与工具；Claude Code Loader fixture 会公开默认 Codex 工具以及两个命名 Claude Code 实例与工具。两个 fixture 都包含通用 Job 控制工具，而且不会启动任何产品进程。带密钥层级会使用仅在运行时提供的密钥启动同一生产提供方与真实产品，要求从固定的 DeepSeek 官方服务取得唯一随机数，并再次证明完全停稳；仅当本地操作者未提供密钥时才会自行跳过，而受信任的 CI 会预检该 secret。 -Codex 证据会锁定 `@openai/codex@0.147.0`、`codex-cli 0.147.0` 与六个平台 alias。其真实产品测试会观测包内 wrapper argv、确切的 Bearer 密钥、原始任务、逐字节完全一致的最终回答、原生权限模式、测试拥有临时存储中的显式危险绕过写入，以及 wrapper／原生整棵进程树退出。独立 wrapper fixture 会证明载荷缺失时不回退宿主命令，两个命名实例会保留彼此独立的环境与模式，生产环境也不会从 `PATH` 解析宿主 `codex`。[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.zh.md)负责 schema、失败、进程结果与最终呈现证据。 +Codex 证据会锁定 `@openai/codex@0.149.1`、`codex-cli 0.149.1` 与六个平台 alias。生成 schema 会证明可选的 `ThreadStartParams.model`；真实产品测试会观测省略模型继承、两个显式实例模型、包内 wrapper argv、确切的 Bearer 密钥、原始任务、逐字节完全一致的最终回答、原生权限模式、测试拥有临时存储中的显式危险绕过写入，以及 wrapper／原生整棵进程树退出。独立 wrapper fixture 会证明载荷缺失时不回退宿主命令，命名实例会保留彼此独立的模型、环境与模式，生产环境也不会从 `PATH` 解析宿主 `codex`。[最小诊断决策](../simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md)负责失败、进程结果与最终呈现证据。 带密钥 Codex e2e 会注册生产提供方，启动同样的真实 app-server，并通过上述测试专用桥接层请求一个随机数。该测试固定外部端点与模型，不存储任何凭据或请求载荷，要求上游恰好完成一次响应，将去除首尾空白后的产品答案与该随机数逐字节比较，并等待所有受管句柄退出。 diff --git a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.i18n.yaml b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.i18n.yaml index 11518aecf3..bcefa42504 100644 --- a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md -2026-08-15-product-subagent-noninteractive-permissions.md: f9fe1e0af4f65b83a53127a64f6475861a13f0a1 -2026-08-15-product-subagent-noninteractive-permissions.zh.md: 2acb1bf095a23022fc761d254f0e515e1acf1588 +2026-08-15-product-subagent-noninteractive-permissions.md: 8ce71cbf156d3e22a22fa8ad526b838ec1a5effe +2026-08-15-product-subagent-noninteractive-permissions.zh.md: e6471b2ce1c8ebbb767254df2426969a3da36f78 diff --git a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md index f9fe1e0af4..8ce71cbf15 100644 --- a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md +++ b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.md @@ -32,7 +32,7 @@ Every query disables `AskUserQuestion`. Non-bypass permission callbacks deny ins ### Codex -Codex defaults to `never` and accepts the three native non-interactive modes exposed by Codex 0.147.0. The Provider starts the fixed app-server command, then maps the selected mode into official `thread/start` fields because CLI-global permission flags do not configure threads created later by an app-server client: +Codex defaults to `never` and accepts the three native non-interactive modes exposed by Codex 0.149.1. The Provider starts the fixed app-server command, then maps the selected mode into official `thread/start` fields because CLI-global permission flags do not configure threads created later by an app-server client: | Value | `thread/start` fields | Native behavior | | --- | --- | --- | @@ -40,13 +40,13 @@ Codex defaults to `never` and accepts the three native non-interactive modes exp | `approve-for-me` | `approvalPolicy: on-request`, `approvalsReviewer: auto_review`, `sandbox: workspace-write` | Route permission requests through Codex automatic review. | | `dangerously-bypass-approvals-and-sandbox` | `approvalPolicy: never`, `sandbox: danger-full-access` | Skip approval and sandbox enforcement. | -The Provider overrides only those thread fields. `CODEX_HOME`, project configuration, model/provider selection, MCP, hooks, skills, authentication, and sandbox facts not selected by the mode remain native Codex state. The wire still denies any unexpected approval, permission, user-input, or MCP request rather than opening a dynamic allow path. +The Provider overrides only those permission and sandbox fields. An optional instance-level model is a separate direct `thread/start` override; `CODEX_HOME`, project configuration, model-provider selection, MCP, hooks, skills, authentication, and sandbox facts not selected by the mode remain native Codex state. The wire still denies any unexpected approval, permission, user-input, or MCP request rather than opening a dynamic allow path. ### Failure diagnostic -`SubagentResult` carries an optional `diagnostic` for provider-authored, non-assistant failure detail. A Provider removes tool inputs, file contents, environment values, credentials, and raw protocol payloads before producing it. The shared out-of-process result boundary limits the complete text to 4096 UTF-8 bytes and marks truncation without splitting a character. The [minimal-diagnostics decision](../simplification/2026-08-21-product-subagent-minimal-diagnostics.md) owns Claude Code's non-permission action categories, while the [structured failure-facts decision](2026-08-18-product-subagent-failure-facts.md) continues to own Codex's current categories; both retain lifecycle stages and process outcomes in the same field. +`SubagentResult` carries an optional `diagnostic` for provider-authored, non-assistant failure detail. A Provider removes tool inputs, file contents, environment values, credentials, and raw protocol payloads before producing it. The shared out-of-process result boundary limits the complete text to 4096 UTF-8 bytes and marks truncation without splitting a character. The [minimal-diagnostics decision](../simplification/2026-08-21-product-subagent-minimal-diagnostics.md) owns both products' non-permission action categories, lifecycle stages, HTTP facts, and process outcomes carried by the same field. -Each product's permission fact contains only the effective mode, request category, unattended decision, and a fixed safe reason. Claude Code derives those facts from SDK callbacks and `permission_denied` messages. Codex derives them from app-server requests, declined items, `sandboxError`, and two fixed permission signatures in a bounded stderr tail; raw stderr is still forwarded to the Host but never copied into the diagnostic. Both Providers place their structured failure line before the latest contributing permission fact. A successful result returns only the strict final answer; local cancellation remains `aborted` without permission detail; an unpublished startup failure still rejects `start()`. The Provider never adds either diagnostic fact to assistant output, structured output, or `subagent/end.lastAssistantMessage`. +Each product's permission fact contains only the effective mode, request category, unattended decision, and a fixed safe reason. Claude Code derives those facts from SDK callbacks and `permission_denied` messages. Codex derives them from app-server requests, declined items, and structured `sandboxError` terminals. Raw stderr is forwarded to the Host but is neither classified nor copied into the diagnostic. Both Providers place their failure line before the latest contributing permission fact. A successful result returns only the strict final answer; local cancellation remains `aborted` without permission detail; an unpublished startup failure still rejects `start()`. The Provider never adds either diagnostic fact to assistant output, structured output, or `subagent/end.lastAssistantMessage`. The foreground consumer presents the stop-reason headline, then the optional diagnostic, then any partial assistant output. The one-shot background adapter stores the same diagnostic beside the stop reason in the failed Job detail. Providers that omit the field retain their previous behavior. @@ -63,7 +63,7 @@ The foreground consumer presents the stop-reason headline, then the optional dia ## Verification -Package tests pin every allowed and rejected Config value, the exact SDK and app-server field mappings, dangerous confirmations, unattended terminal responses, diagnostic sanitization and UTF-8 bound, successful-result omission, concurrent-run isolation, foreground ordering, Job detail, stderr observer disposal, and process cleanup. The real Claude Agent SDK 0.3.241 and Claude Code 2.1.241 fixture proves its safe default, restricted denial, explicit bypass, and whole-tree quiescence. The real Codex app-server fixture proves that thread-level `never` overrides ambient `on-request`, automatic review starts, dangerous bypass writes only inside suite-owned temporary storage, fixed stderr signatures produce safe diagnostics, and the wrapper/native tree exits. Loader composition proves non-default modes can be published without starting either product, and the keyless ACP snapshot records each product's failure diagnostic through foreground and Job presentation while the model-facing product tool schemas contain no permission parameter. +Package tests pin every allowed and rejected Config value, the exact SDK and app-server field mappings, dangerous confirmations, unattended terminal responses, diagnostic sanitization and UTF-8 bound, successful-result omission, concurrent-run isolation, foreground ordering, Job detail, stderr observer disposal, and process cleanup. The real Claude Agent SDK 0.3.241 and Claude Code 2.1.241 fixture proves its safe default, restricted denial, explicit bypass, and whole-tree quiescence. The real Codex 0.149.1 app-server fixture proves that thread-level `never` overrides ambient `on-request`, automatic review starts, dangerous bypass writes only inside suite-owned temporary storage, a rejected escalation leaves no side effect or raw command or path in the diagnostic, stderr remains Host-only, and the wrapper/native tree exits. Loader composition proves non-default modes can be published without starting either product, and the keyless ACP snapshot records each product's failure diagnostic through foreground and Job presentation while the model-facing product tool schemas contain no permission parameter. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md index 2acb1bf095..e6471b2ce1 100644 --- a/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md +++ b/.agents/notes/implemented/feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md @@ -32,7 +32,7 @@ Claude Code 默认使用 `dontAsk`，而且只接受锁定版本 Agent SDK 支 ### Codex -Codex 默认使用 `never`，并接受 Codex 0.147.0 公开的三种原生非交互模式。提供方启动固定的 app-server 命令，再把所选模式映射为官方 `thread/start` 字段，因为 CLI 全局权限 flag 不会配置之后由 app-server 客户端创建的线程： +Codex 默认使用 `never`，并接受 Codex 0.149.1 公开的三种原生非交互模式。提供方启动固定的 app-server 命令，再把所选模式映射为官方 `thread/start` 字段，因为 CLI 全局权限 flag 不会配置之后由 app-server 客户端创建的线程： | 值 | `thread/start` 字段 | 原生行为 | | --- | --- | --- | @@ -40,13 +40,13 @@ Codex 默认使用 `never`，并接受 Codex 0.147.0 公开的三种原生非交 | `approve-for-me` | `approvalPolicy: on-request`、`approvalsReviewer: auto_review`、`sandbox: workspace-write` | 由 Codex 自动评审权限请求。 | | `dangerously-bypass-approvals-and-sandbox` | `approvalPolicy: never`、`sandbox: danger-full-access` | 跳过审批与 sandbox。 | -提供方只覆盖这些线程字段。`CODEX_HOME`、项目配置、模型／provider 选择、MCP、hook、skill、身份验证，以及模式未选择的 sandbox 事实仍属于 Codex 原生状态。wire 仍会拒绝任何意外到达的审批、权限、用户输入或 MCP 请求，而不会开放动态 allow 通道。 +提供方只覆盖这些权限与 sandbox 字段。可选的实例级模型是独立的直接 `thread/start` 覆盖；`CODEX_HOME`、项目配置、模型 provider 选择、MCP、hook、skill、身份验证，以及模式未选择的 sandbox 事实仍属于 Codex 原生状态。wire 仍会拒绝任何意外到达的审批、权限、用户输入或 MCP 请求，而不会开放动态 allow 通道。 ### 失败诊断 -`SubagentResult` 携带可选的 `diagnostic`，用于提供方产生且不属于 assistant 内容的失败说明。提供方在生成它之前会排除工具输入、文件内容、环境值、凭证与原始协议载荷。共享的进程外结果边界会把完整文本限制在 4096 个 UTF-8 字节以内，并在不切断字符的前提下标记截断。[最小诊断决策](../simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md)负责 Claude Code 的非权限行动类别，[结构化失败事实决策](2026-08-18-product-subagent-failure-facts.zh.md)继续负责 Codex 的当前类别；二者都在同一字段中保留生命周期阶段与进程结果。 +`SubagentResult` 携带可选的 `diagnostic`，用于提供方产生且不属于 assistant 内容的失败说明。提供方在生成它之前会排除工具输入、文件内容、环境值、凭证与原始协议载荷。共享的进程外结果边界会把完整文本限制在 4096 个 UTF-8 字节以内，并在不切断字符的前提下标记截断。[最小诊断决策](../simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md)负责两个产品通过同一字段承载的非权限行动类别、生命周期阶段、HTTP 事实与进程结果。 -每个产品的权限事实都只包含有效模式、请求类别、无人值守决定与固定的安全原因。Claude Code 从 SDK 回调和 `permission_denied` 消息取得这些事实。Codex 从 app-server 请求、被拒绝的 item、`sandboxError` 与每次运行有界 stderr 尾部中的两个固定权限签名取得事实；原始 stderr 仍会转发给 Host，但绝不会复制进诊断。两个提供方都会把结构化失败行放在最新参与失败的权限事实之前。成功结果只返回严格的最终答案；本地取消仍以 `aborted` 结算且不附带权限说明；未发布的启动失败仍会拒绝 `start()`。提供方绝不会把任一诊断事实写入 assistant 输出、结构化输出或 `subagent/end.lastAssistantMessage`。 +每个产品的权限事实都只包含有效模式、请求类别、无人值守决定与固定的安全原因。Claude Code 从 SDK 回调和 `permission_denied` 消息取得这些事实。Codex 从 app-server 请求、被拒绝的 item 与结构化 `sandboxError` 终态取得事实。原始 stderr 仍会转发给 Host，但既不会被分类，也绝不会复制进诊断。两个提供方都会把失败行放在最新参与失败的权限事实之前。成功结果只返回严格的最终答案；本地取消仍以 `aborted` 结算且不附带权限说明；未发布的启动失败仍会拒绝 `start()`。提供方绝不会把任一诊断事实写入 assistant 输出、结构化输出或 `subagent/end.lastAssistantMessage`。 前台消费方依次呈现终止原因标题、可选诊断和任何部分 assistant 输出。一次性后台适配器会在失败 Job 的 detail 中，把同一诊断与终止原因一起保存。没有填写该字段的提供方保持原有行为。 @@ -63,7 +63,7 @@ Codex 默认使用 `never`，并接受 Codex 0.147.0 公开的三种原生非交 ## Verification -包测试固定所有允许与拒绝的 Config 值、准确的 SDK 与 app-server 字段映射、危险确认、无人值守终态、诊断脱敏与 UTF-8 上限、成功结果不携带诊断、并发运行隔离、前台顺序、Job detail、stderr observer 释放和进程清理。真实 Claude Agent SDK 0.3.241 与 Claude Code 2.1.241 fixture 证明其安全默认、受限拒绝、显式 bypass 与整棵进程树完全停稳。真实 Codex app-server fixture 证明线程级 `never` 覆盖环境中的 `on-request`、自动评审可以启动、危险绕过只在测试拥有的临时存储中写入、固定 stderr 签名产生安全诊断，而且 wrapper／native 进程树会退出。Loader 组装证明非默认模式可以在不启动任一产品的情况下发布；无密钥 ACP snapshot 则记录每个产品的失败诊断如何经过前台与 Job 呈现，同时面向模型的产品工具 schema 不包含权限参数。 +包测试固定所有允许与拒绝的 Config 值、准确的 SDK 与 app-server 字段映射、危险确认、无人值守终态、诊断脱敏与 UTF-8 上限、成功结果不携带诊断、并发运行隔离、前台顺序、Job detail、stderr observer 释放和进程清理。真实 Claude Agent SDK 0.3.241 与 Claude Code 2.1.241 fixture 证明其安全默认、受限拒绝、显式 bypass 与整棵进程树完全停稳。真实 Codex 0.149.1 app-server fixture 证明线程级 `never` 覆盖环境中的 `on-request`、自动评审可以启动、危险绕过只在测试拥有的临时存储中写入、被拒绝的提权不会留下副作用且诊断不含原始命令或路径、stderr 只供 Host 观测，而且 wrapper／native 进程树会退出。Loader 组装证明非默认模式可以在不启动任一产品的情况下发布；无密钥 ACP snapshot 则记录每个产品的失败诊断如何经过前台与 Job 呈现，同时面向模型的产品工具 schema 不包含权限参数。 ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.i18n.yaml b/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.i18n.yaml index c50a93d632..549dbbf074 100644 --- a/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.md -2026-08-18-product-subagent-named-instances.md: fd4f95dc9de0cc03a95f8f1dcbd6dcded258dc5f -2026-08-18-product-subagent-named-instances.zh.md: 1d8395a21824501c5f26bdbec9c9d7f25d3bf20f +2026-08-18-product-subagent-named-instances.md: 749267e311cbcdebc7a6b8ad84e046fe21acf6fd +2026-08-18-product-subagent-named-instances.zh.md: d39fdd46a30aa665715d782162ddaaaac3a31f3e diff --git a/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.md b/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.md index fd4f95dc9d..749267e311 100644 --- a/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.md +++ b/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.md @@ -6,17 +6,17 @@ English | [中文](2026-08-18-product-subagent-named-instances.zh.md) ## Problem -A Profile can mount one Cordis plugin package in multiple rows, but the Codex and Claude Code product providers previously registered every row under one fixed product name. A second row therefore failed as a duplicate before its distinct model where supported, permission mode, environment, or process-release settings could become usable. Deriving an implicit name from those settings would create a second identity rule, while choosing a provider during a tool call would let model input select deployment authority. +A Profile can mount one Cordis plugin package in multiple rows, but the Codex and Claude Code product providers previously registered every row under one fixed product name. A second row therefore failed as a duplicate before its distinct model, permission mode, environment, or process-release settings could become usable. Deriving an implicit name from those settings would create a second identity rule, while choosing a provider during a tool call would let model input select deployment authority. The existing subagent registry already owns unique provider names, reversible registration, lifecycle events, and holder-owned published runs. The existing `dsh-tool-subagent` configuration already binds one provider name to one model-visible tool name. Product providers need to expose the missing Profile-owned identity without adding another registry or selection protocol. ## Decision -Each product provider Config owns a non-empty `providerName`; the defaults remain `codex` and `claude-code`. The resolved name is fixed when the plugin row loads and becomes the Provider object's `name`; registration, lookup, lifecycle events, run logs, and HMR removal therefore use the same value. Each mounted row retains its own `permissionMode`, `env`, `disposeGraceMs`, and run resources. Claude Code rows also retain an optional non-empty `model`; an explicit value is fixed for every query from that instance, while omission leaves native settings authoritative. +Each product provider Config owns a non-empty `providerName`; the defaults remain `codex` and `claude-code`. The resolved name is fixed when the plugin row loads and becomes the Provider object's `name`; registration, lookup, lifecycle events, run logs, and HMR removal therefore use the same value. Each mounted row retains its own optional non-empty `model`, `permissionMode`, `env`, `disposeGraceMs`, and run resources. An explicit model is fixed for every query or thread from that instance, while omission leaves the native product settings authoritative. Profiles may mount multiple Codex or Claude Code rows when every row uses a distinct `providerName`. Each `dsh-tool-subagent` row continues to bind its existing `provider` field to that exact name and exposes an independently configured `toolName`. Tool calls carry no provider selector, alias, or permission input. A duplicate provider name fails through the existing `DUPLICATE_PROVIDER` path and leaves the first registration intact. -Removing one provider row blocks new starts and removes only tools bound to that name. Runs already published by the removed instance remain owned by their holders and settle or dispose independently. Sibling instances remain registered and keep their own configured model where supported, environment, native permission mode, cancellation controller, product process, and cleanup grace. +Removing one provider row blocks new starts and removes only tools bound to that name. Runs already published by the removed instance remain owned by their holders and settle or dispose independently. Sibling instances remain registered and keep their own configured model, environment, native permission mode, cancellation controller, product process, and cleanup grace. ### Ownership and lifecycle @@ -25,11 +25,11 @@ Removing one provider row blocks new starts and removes only tools bound to that | Provider instance name | Product Provider Config | One immutable registry name per mounted row, with the existing default when omitted | | Name uniqueness and lifecycle events | `ctx.subagents` | Duplicate registration fails; disposal removes only the matching name | | Model-visible tool name and binding | `dsh-tool-subagent` Config | One static tool resolves one configured provider name | -| Model where supported, permission, environment, and process cleanup | One Provider instance | Concurrent runs and sibling instances do not share deployment configuration or run resources | +| Model, permission, environment, and process cleanup | One Provider instance | Concurrent runs and sibling instances do not share deployment configuration or run resources | ## Verification -Both product packages pin their default and custom names, empty-name rejection, duplicate rollback, actual-name diagnostics, two concurrent instances with different permission modes, environments, and cleanup grace, cancellation isolation, and removal of one instance while its published run remains valid. Claude Code additionally pins empty-model rejection, omitted-model inheritance, two explicit models, and exact per-query isolation through the real SDK/CLI fixture. Public Loader compositions mount two rows and two distinct tools for each product without starting either product, while keyless ACP snapshots pin the four-tool combined roster and the absence of dynamic provider or model parameters. +Both product packages pin their default and custom names, empty-name and empty-model rejection, duplicate rollback, actual-name diagnostics, two concurrent instances with different models, permission modes, environments, and cleanup grace, cancellation isolation, and removal of one instance while its published run remains valid. Official product fixtures prove omitted-model inheritance and exact per-query or per-thread model isolation. Public Loader compositions mount two rows and two distinct tools for each product without starting either product, while keyless ACP snapshots pin the four-tool combined roster and the absence of dynamic provider or model parameters. ## Alternatives considered @@ -43,6 +43,6 @@ Both product packages pin their default and custom names, empty-name rejection, ## Consequences -A Profile can expose several Codex and Claude Code tools backed by separate native permission modes and environments, and Claude Code instances may additionally fix separate models, while existing configurations continue to resolve `codex` and `claude-code`. Provider and tool names remain independent configuration facts, so changing one requires updating the binding that refers to it. +A Profile can expose several Codex and Claude Code tools backed by separate models, native permission modes, and environments while existing configurations continue to resolve `codex` and `claude-code`. Provider and tool names remain independent configuration facts, so changing one requires updating the binding that refers to it. The design adds no runtime renaming, model-visible provider or model selector, generated tool name, persistent instance directory, shared process pool, model discovery, fallback, or compatibility alias. Correct multi-instance configurations require unique provider names and unique tool names; duplicate tool-name waiting remains a separate limitation. diff --git a/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.zh.md b/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.zh.md index 1d8395a218..d39fdd46a3 100644 --- a/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.zh.md +++ b/.agents/notes/implemented/feature/2026-08-18-product-subagent-named-instances.zh.md @@ -6,17 +6,17 @@ Status: implemented ## 问题 -Profile 可以用多个配置项挂载同一个 Cordis 插件包，但 Codex 与 Claude Code 产品提供方此前会把每个配置项都注册到一个固定产品名称下。因此，第二个配置项会在其支持时使用的独立模型、权限模式、环境或进程释放设置可用前因名称重复而失败。根据这些设置隐式派生名称会建立第二套身份规则，而在工具调用期间选择提供方会让模型输入决定部署权限。 +Profile 可以用多个配置项挂载同一个 Cordis 插件包，但 Codex 与 Claude Code 产品提供方此前会把每个配置项都注册到一个固定产品名称下。因此，第二个配置项会在其独立模型、权限模式、环境或进程释放设置可用前因名称重复而失败。根据这些设置隐式派生名称会建立第二套身份规则，而在工具调用期间选择提供方会让模型输入决定部署权限。 现有 subagent 注册表已经拥有提供方名称唯一性、可逆注册、生命周期事件和由持有方拥有的已发布运行。现有 `dsh-tool-subagent` 配置也已经把一个提供方名称绑定到一个模型可见工具名称。产品提供方只需公开缺失的 Profile 所有身份，无需增加另一套注册表或选择协议。 ## 决策 -每个产品提供方 Config 都拥有非空的 `providerName`；默认值仍分别为 `codex` 与 `claude-code`。插件配置项加载时会固定解析后的名称，并把它作为 Provider 对象的 `name`；注册、查找、生命周期事件、运行日志和 HMR（热模块替换）移除因此使用同一个值。每个已挂载配置项保留自己的 `permissionMode`、`env`、`disposeGraceMs` 和运行资源。Claude Code 配置项还会保留可选的非空 `model`；显式值为该实例的每次 query 固定，省略时仍以原生设置为权威。 +每个产品提供方 Config 都拥有非空的 `providerName`；默认值仍分别为 `codex` 与 `claude-code`。插件配置项加载时会固定解析后的名称，并把它作为 Provider 对象的 `name`；注册、查找、生命周期事件、运行日志和 HMR（热模块替换）移除因此使用同一个值。每个已挂载配置项保留自己的可选非空 `model`、`permissionMode`、`env`、`disposeGraceMs` 和运行资源。显式模型会为该实例的每次 query 或线程固定，省略时仍以原生产品设置为权威。 当每个配置项使用不同的 `providerName` 时，Profile 可以挂载多个 Codex 或 Claude Code 配置项。每个 `dsh-tool-subagent` 配置项继续用已有的 `provider` 字段绑定这个准确名称，并公开独立配置的 `toolName`。工具调用不携带提供方选择器、别名或权限输入。重复提供方名称沿用现有 `DUPLICATE_PROVIDER` 路径失败，而且不会替换第一个注册项。 -移除一个提供方配置项会阻止新的启动，并且只移除绑定到该名称的工具。该实例已经发布的运行仍由其持有方拥有，并会独立结算或 dispose（资源释放）。兄弟实例继续保持注册，并保留各自支持时配置的模型、环境、原生权限模式、取消控制器、产品进程和清理宽限期。 +移除一个提供方配置项会阻止新的启动，并且只移除绑定到该名称的工具。该实例已经发布的运行仍由其持有方拥有，并会独立结算或 dispose（资源释放）。兄弟实例继续保持注册，并保留各自配置的模型、环境、原生权限模式、取消控制器、产品进程和清理宽限期。 ### 所有权与生命周期 @@ -25,11 +25,11 @@ Profile 可以用多个配置项挂载同一个 Cordis 插件包，但 Codex 与 | 提供方实例名称 | 产品提供方 Config | 每个已挂载配置项拥有一个不可变注册名称；省略时使用现有默认值 | | 名称唯一性与生命周期事件 | `ctx.subagents` | 重复注册失败；资源释放只移除匹配名称 | | 模型可见工具名称与绑定 | `dsh-tool-subagent` Config | 一个静态工具解析一个已配置的提供方名称 | -| 支持时的模型、权限、环境与进程清理 | 一个提供方实例 | 并发运行与兄弟实例不共享部署配置或运行资源 | +| 模型、权限、环境与进程清理 | 一个提供方实例 | 并发运行与兄弟实例不共享部署配置或运行资源 | ## 验证 -两个产品包测试都会固定默认与自定义名称、空名称拒绝、重复注册回滚、实际名称诊断、使用不同权限模式、环境与清理宽限期的两个并发实例、取消隔离，以及移除一个实例后其已发布运行仍然有效。Claude Code 还会固定空模型拒绝、省略模型继承、两个显式模型，以及通过真实 SDK／CLI fixture 证明逐 query 精确隔离。公共 Loader 组合会为每个产品挂载两个配置项与两个不同工具，而且不启动任一产品；无密钥 ACP 快照固定最终四工具组合，并证明没有动态提供方或模型参数。 +两个产品包测试都会固定默认与自定义名称、空名称和空模型拒绝、重复注册回滚、实际名称诊断、使用不同模型、权限模式、环境与清理宽限期的两个并发实例、取消隔离，以及移除一个实例后其已发布运行仍然有效。官方产品 fixture 会证明省略模型继承，以及逐 query 或逐线程的准确模型隔离。公共 Loader 组合会为每个产品挂载两个配置项与两个不同工具，而且不启动任一产品；无密钥 ACP 快照固定最终四工具组合，并证明没有动态提供方或模型参数。 ## 考虑过的替代方案 @@ -43,6 +43,6 @@ Profile 可以用多个配置项挂载同一个 Cordis 插件包，但 Codex 与 ## 结果 -Profile 可以公开多个由不同原生权限模式与环境支持的 Codex 与 Claude Code 工具，Claude Code 实例还可分别固定模型，而现有配置仍会解析为 `codex` 与 `claude-code`。提供方名称与工具名称继续是彼此独立的配置事实，因此修改其中一项时必须同时更新引用它的绑定。 +Profile 可以公开多个由不同模型、原生权限模式与环境支持的 Codex 与 Claude Code 工具，而现有配置仍会解析为 `codex` 与 `claude-code`。提供方名称与工具名称继续是彼此独立的配置事实，因此修改其中一项时必须同时更新引用它的绑定。 本设计不增加运行时改名、模型可见的提供方或模型选择器、自动生成的工具名称、持久实例目录、共享进程池、模型发现、fallback 或兼容别名。正确的多实例配置要求提供方名称与工具名称都保持唯一；重复工具名称的等待问题仍是独立限制。 diff --git a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.i18n.yaml b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.i18n.yaml index 8f6947d232..d0e225ad3b 100644 --- a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.i18n.yaml +++ b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md -2026-08-08-native-windows-pull-request-ci.md: 24f1a5fa0c72255f678b837c910eb779445dee27 -2026-08-08-native-windows-pull-request-ci.zh.md: 805974192577b835b565bd42688c574473ac63bf +2026-08-08-native-windows-pull-request-ci.md: dad23f1a49393fbfc3c0798407ed9abe21ff3df2 +2026-08-08-native-windows-pull-request-ci.zh.md: 0d81b160fd40ae0a26569351bca6e631aab9a8de diff --git a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md index 24f1a5fa0c..dad23f1a49 100644 --- a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md +++ b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.md @@ -32,7 +32,7 @@ Windows durable JSONL paths keep drive roots in native spelling and apply the ex Post-boot profile watcher setup proceeds only while the root fiber and Loader are both live. A concurrent setup error is contained only when the same invocation's recorded signal already owns shutdown; unrelated HMR failures remain loud. The [process-shutdown controller](../bug-fix/2026-08-03-cli-signal-shutdown-escalation.md) lets a successful one-shot completion drain Node's remaining handles after root disposal, while teardown failure, deadline, and signal escalation retain forced exit. The vendored Include serializes debounced writes, retries only transient access or busy failures with bounded backoff, and observes every timer rejection. A terminal persistence failure remains on the queue and is rethrown to the teardown owner, while successful teardown drains the latest write. -Shiki disables lazy TextMate-regex compilation and warms each boot grammar before user content enters the unchanged per-line tokenization budget, so scheduler contention cannot publish a partial highlighted stream. The Codex real-product fixture is pinned to stable 0.147.0 schemas and selects an actually advertised command tool and argument shape, preserving the provider-owned protocol while proving unattended rejection and whole-tree exit on each host. +Shiki disables lazy TextMate-regex compilation and warms each boot grammar before user content enters the unchanged per-line tokenization budget, so scheduler contention cannot publish a partial highlighted stream. The Codex real-product fixture is pinned to stable 0.149.1 schemas and selects an actually advertised command tool and argument shape, preserving the provider-owned protocol while proving unattended rejection and whole-tree exit on each host. ## Alternatives considered diff --git a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.zh.md b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.zh.md index 8059741925..0d81b160fd 100644 --- a/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.zh.md +++ b/.agents/notes/implemented/process/2026-08-08-native-windows-pull-request-ci.zh.md @@ -32,7 +32,7 @@ Windows 的持久 JSONL 路径会保留驱动器根目录的原生写法，并 启动后，只有根 fiber 与 Loader 均处于活跃状态时，系统才会继续设置 profile watcher。只有当同一次调用所记录的信号已取得关闭流程所有权时，系统才会隔离并发设置错误；无关 HMR 故障仍会响亮失败。[进程关闭控制器](../bug-fix/2026-08-03-cli-signal-shutdown-escalation.zh.md)会在根级 dispose 成功后让单次任务的正常完成流程排空 Node 剩余句柄，同时让拆卸失败、截止时间到期和信号升级继续强制退出。vendored Include 会串行化防抖写入，只对瞬时访问或忙碌故障执行有界退避重试，并确保每个由计时器触发的拒绝都得到观察。持久化最终失败后，该故障会保留在队列中，并重新抛给拆卸责任方；成功拆卸则会排空最新写入。 -Shiki 会禁用 TextMate 正则的延迟编译，并在用户内容进入保持不变的逐行 tokenization（词元化）预算前预热每种启动语法，从而避免调度器争用发布不完整的高亮流。Codex 真实产品 fixture 固定使用稳定版 0.147.0 schema，并选择实际提供的命令工具与对应参数形态；这样既保留由提供方负责的协议，也能在每种宿主上证明无人值守拒绝和整棵进程树退出。 +Shiki 会禁用 TextMate 正则的延迟编译，并在用户内容进入保持不变的逐行 tokenization（词元化）预算前预热每种启动语法，从而避免调度器争用发布不完整的高亮流。Codex 真实产品 fixture 固定使用稳定版 0.149.1 schema，并选择实际提供的命令工具与对应参数形态；这样既保留由提供方负责的协议，也能在每种宿主上证明无人值守拒绝和整棵进程树退出。 ## 曾考虑的替代方案 diff --git a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.i18n.yaml b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.i18n.yaml index 2304f13c73..a017cbbc22 100644 --- a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md -2026-08-12-production-dsh-excludes-product-subagent-providers.md: aaa6ddc70a0320c85d0d784441dfc82d74831a90 -2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md: 37b861ad879995ac7dbd91903cf92332a83f9d92 +2026-08-12-production-dsh-excludes-product-subagent-providers.md: 551cf86bd0d1901e5ad8e33588b7bf274cb2c8fe +2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md: 611c6192c501f6289911c18c36ca21a31c57e2cd diff --git a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md index aaa6ddc70a..551cf86bd0 100644 --- a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md +++ b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.md @@ -16,7 +16,7 @@ The two Bundles remain independent. The Codex Bundle owns the pinned official wr ## Verification -Package tests pin both Bundle manifests, published patches, exact self-provider rows, and product runtime dependencies. Claude coverage pins Agent SDK 0.3.241, Claude Code 2.1.241, all eight platform packages, SDK-selected execution, and missing-payload failure without host fallback. Codex coverage pins wrapper 0.147.0, all six platform aliases, package-declared execution, native descendant quiescence, and the same missing-payload behavior. Workspace validation derives each published patch from its Bundle declaration rather than a package catalog. Package/base assertions plus actual pnpm production evidence prove the default and selected-product dependency boundaries, while real Bundle-patch and Agent-Preset composition covers none, either product, both, the tool-grant intersection, later-Session adoption, and zero startup processes. +Package tests pin both Bundle manifests, published patches, exact self-provider rows, and product runtime dependencies. Claude coverage pins Agent SDK 0.3.241, Claude Code 2.1.241, all eight platform packages, SDK-selected execution, and missing-payload failure without host fallback. Codex coverage pins wrapper 0.149.1, all six platform aliases, package-declared execution, native descendant quiescence, and the same missing-payload behavior. Workspace validation derives each published patch from its Bundle declaration rather than a package catalog. Package/base assertions plus actual pnpm production evidence prove the default and selected-product dependency boundaries, while real Bundle-patch and Agent-Preset composition covers none, either product, both, the tool-grant intersection, later-Session adoption, and zero startup processes. ## Alternatives considered diff --git a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md index 37b861ad87..611c6192c5 100644 --- a/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md +++ b/.agents/notes/implemented/simplification/2026-08-12-production-dsh-excludes-product-subagent-providers.zh.md @@ -16,7 +16,7 @@ Status: implemented ## 验证 -包测试会固定两个 Bundle 的 manifest、发布 patch、准确的自身提供方行与产品运行时依赖。Claude 覆盖会固定 Agent SDK 0.3.241、Claude Code 2.1.241、八个平台包、SDK 所选执行路径，以及载荷缺失时不回退宿主命令的失败。Codex 覆盖会固定 wrapper 0.147.0、六个平台 alias、包声明的执行路径、原生后代进程停稳，以及同样的载荷缺失行为。工作区验证会从 Bundle 声明派生每份发布 patch，而非维护包目录。包与 base 断言加上实际 pnpm 生产证据会证明默认与所选产品的依赖边界；真实 Bundle patch 与 Agent Preset 组装则覆盖未安装、任一单包、双包、工具授权交集、后续 Session 采纳以及零启动进程。 +包测试会固定两个 Bundle 的 manifest、发布 patch、准确的自身提供方行与产品运行时依赖。Claude 覆盖会固定 Agent SDK 0.3.241、Claude Code 2.1.241、八个平台包、SDK 所选执行路径，以及载荷缺失时不回退宿主命令的失败。Codex 覆盖会固定 wrapper 0.149.1、六个平台 alias、包声明的执行路径、原生后代进程停稳，以及同样的载荷缺失行为。工作区验证会从 Bundle 声明派生每份发布 patch，而非维护包目录。包与 base 断言加上实际 pnpm 生产证据会证明默认与所选产品的依赖边界；真实 Bundle patch 与 Agent Preset 组装则覆盖未安装、任一单包、双包、工具授权交集、后续 Session 采纳以及零启动进程。 ## 考虑过的替代方案 diff --git a/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.i18n.yaml b/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.i18n.yaml index 3e1f13366d..9aaf9322f1 100644 --- a/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.md -2026-08-21-product-subagent-minimal-diagnostics.md: a4d51c325738e6e3e6c74561deb877c9bca3c016 -2026-08-21-product-subagent-minimal-diagnostics.zh.md: 409b548e0e6169479cec892d349dc8c969b24637 +2026-08-21-product-subagent-minimal-diagnostics.md: b99ed487911a7ac9bf7c0751ea02290ff92cad6a +2026-08-21-product-subagent-minimal-diagnostics.zh.md: 46f948334df0268a095f8cb34ab1a7707eee811b diff --git a/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.md b/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.md index a4d51c3257..b99ed48791 100644 --- a/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.md +++ b/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.md @@ -26,7 +26,20 @@ Claude Code maps Agent SDK results into five categories: The diagnostic also retains the derived `query-start`, `query-run`, `process`, or `teardown` stage and independently observed exit code and signal. A contributing permission decision follows the failure line. Successful completion and local cancellation expose no failure diagnostic, and original SDK text remains only on the internal cause chain and in Host observation. -Codex currently retains the version-pinned categories documented by the [structured failure-facts decision](../feature/2026-08-18-product-subagent-failure-facts.md). The two providers may adopt the minimal mapping independently because neither shares a public error enum or asks a consumer to branch on category text. +Codex maps app-server failures into eight categories: + +| Category | Safe input | +| --- | --- | +| `limit` | Context, session-budget, or usage limits | +| `access-policy` | Authentication, cyber-policy, product-policy, or sandbox failures | +| `service` | Overload or internal service failures | +| `transport` | HTTP and response-stream connection failures or exhausted attempts | +| `product-error` | Invalid requests, rollback, active-turn, or other product failures | +| `invalid-result` | A completed turn without a nonblank final answer | +| `process` | The managed app-server exits before another terminal result | +| `unknown` | Startup, teardown, malformed protocol values, or failures without a more specific safe fact | + +The Codex diagnostic retains `initialize`, `thread-start`, `turn-start`, `turn`, `process`, or `teardown`, plus applicable numeric HTTP status and independently observed exit code and signal. `contextWindowExceeded` still maps the shared stop reason to `max-tokens`; every other category remains `error`. Only structured protocol facts contribute permission detail. Product stderr is Host-only observation and is neither classified nor copied into the result. ### Ownership and lifecycle @@ -40,7 +53,7 @@ Codex currently retains the version-pinned categories documented by the [structu ## Verification -Claude Code package tests cover every coarse category, all four stages, unknown structured values, permission ordering, raw-text exclusion, success and cancellation omission, concurrent-run isolation, and independent exit code and signal fields. The real Agent SDK 0.3.241 and Claude Code 2.1.241 fixture produces an actual max-turns limit, process failure, permission denial, strict final answer, cancellation, and whole-tree quiescence. Loader and keyless product compositions continue to expose static tools without a diagnostic parser or model-visible category input. +Claude Code package tests cover every coarse category, all four stages, unknown structured values, permission ordering, raw-text exclusion, success and cancellation omission, concurrent-run isolation, and independent exit code and signal fields. The real Agent SDK 0.3.241 and Claude Code 2.1.241 fixture produces an actual max-turns limit, process failure, permission denial, strict final answer, cancellation, and whole-tree quiescence. Codex package tests cover every coarse category, all six stages, applicable HTTP status, structured permission ordering, stderr exclusion, success and cancellation omission, concurrency, and cleanup aggregation. The real 0.149.1 app-server fixture produces service, product-error, process, final-answer, model-isolation, cancellation, and quiescence evidence. Loader and keyless product compositions continue to expose static tools without a diagnostic parser or model-visible category input. ## Alternatives considered @@ -54,6 +67,6 @@ Claude Code package tests cover every coarse category, all four stages, unknown ## Consequences -Claude Code upgrades no longer require a model-visible promise for every SDK error subtype. Parents still distinguish a limit, general product failure, invalid result, managed process exit, and unknown failure while retaining stage, permission, and process facts. +Product runtime upgrades no longer require a model-visible promise for every SDK or app-server error member. Parents still distinguish limits, access and policy restrictions, service and transport failures, general product failures, invalid results, managed process exits, and unknown failures while retaining applicable stage, permission, HTTP, and process facts. The diagnostic remains safe display text rather than a recovery protocol. This change adds no raw error forwarding, fallback model, automatic retry, product session persistence, public structured result field, or dynamic provider and model selection. diff --git a/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md b/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md index 409b548e0e..46f948334d 100644 --- a/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md +++ b/.agents/notes/implemented/simplification/2026-08-21-product-subagent-minimal-diagnostics.zh.md @@ -26,7 +26,20 @@ Claude Code 会把 Agent SDK 结果映射为五种类别： 诊断还会保留派生的 `query-start`、`query-run`、`process` 或 `teardown` 阶段，以及分别观测到的退出码与信号。参与失败的权限决定会跟在失败行之后。成功完成与本地取消不公开失败诊断，原始 SDK 文本只留在内部 cause 链和 Host 观测中。 -Codex 当前仍保留[结构化失败事实决策](../feature/2026-08-18-product-subagent-failure-facts.zh.md)记录的锁定版本类别。两个提供方可以分别采用最小映射，因为它们既不共享公共错误枚举，也不要求消费方根据类别文本分支。 +Codex 会把 app-server 失败映射为八种类别： + +| 类别 | 安全输入 | +| --- | --- | +| `limit` | 上下文、会话预算或用量限制 | +| `access-policy` | 身份验证、网络安全策略、产品策略或 sandbox 失败 | +| `service` | 过载或内部服务失败 | +| `transport` | HTTP 与响应 stream 连接失败或尝试耗尽 | +| `product-error` | 无效请求、回滚、活动轮次或其他产品失败 | +| `invalid-result` | 已完成轮次没有非空白最终答案 | +| `process` | 受管 app-server 在其他终态结果前退出 | +| `unknown` | 启动、清理、格式错误的协议值，或没有更具体安全事实的失败 | + +Codex 诊断会保留 `initialize`、`thread-start`、`turn-start`、`turn`、`process` 或 `teardown`，以及适用的数值 HTTP status 和分别观测到的退出码与信号。`contextWindowExceeded` 仍把共享终止原因映射为 `max-tokens`；其他所有类别仍使用 `error`。只有结构化协议事实会贡献权限说明。产品 stderr 只供 Host 观测，既不会被分类，也不会复制进结果。 ### 所有权与生命周期 @@ -40,7 +53,7 @@ Codex 当前仍保留[结构化失败事实决策](../feature/2026-08-18-product ## Verification -Claude Code 包测试覆盖全部粗粒度类别、四个阶段、未知结构化值、权限顺序、原始文本排除、成功与取消时省略、并发运行隔离，以及彼此独立的退出码与信号字段。真实 Agent SDK 0.3.241 与 Claude Code 2.1.241 fixture 会产生实际 max-turns 限制、进程失败、权限拒绝、严格最终答案、取消与整棵进程树完全停稳。Loader 与无密钥产品组合继续公开静态工具，不增加诊断解析器或模型可见类别输入。 +Claude Code 包测试覆盖全部粗粒度类别、四个阶段、未知结构化值、权限顺序、原始文本排除、成功与取消时省略、并发运行隔离，以及彼此独立的退出码与信号字段。真实 Agent SDK 0.3.241 与 Claude Code 2.1.241 fixture 会产生实际 max-turns 限制、进程失败、权限拒绝、严格最终答案、取消与整棵进程树完全停稳。Codex 包测试覆盖全部粗粒度类别、六个阶段、适用 HTTP status、结构化权限顺序、stderr 排除、成功与取消时省略、并发及清理聚合。真实 0.149.1 app-server fixture 会产生服务、产品错误、进程、最终答案、模型隔离、取消与完全停稳证据。Loader 与无密钥产品组合继续公开静态工具，不增加诊断解析器或模型可见类别输入。 ## Alternatives considered @@ -54,6 +67,6 @@ Claude Code 包测试覆盖全部粗粒度类别、四个阶段、未知结构 ## Consequences -Claude Code 升级不再要求为每个 SDK 错误 subtype 提供模型可见承诺。父级仍可区分限制、一般产品失败、无效结果、受管进程退出与未知失败，并保留阶段、权限与进程事实。 +产品运行时升级不再要求为每个 SDK 或 app-server 错误成员提供模型可见承诺。父级仍可区分限制、访问与策略限制、服务与传输失败、一般产品失败、无效结果、受管进程退出与未知失败，并保留适用的阶段、权限、HTTP 与进程事实。 诊断仍是安全展示文本，而不是恢复协议。本改动不增加原始错误转发、fallback 模型、自动重试、产品会话持久化、公共结构化结果字段或动态提供方与模型选择。 diff --git a/apps/cli/tests/github-webhook-real.e2e.ts b/apps/cli/tests/github-webhook-real.e2e.ts index fd465714d3..ecec861d30 100644 --- a/apps/cli/tests/github-webhook-real.e2e.ts +++ b/apps/cli/tests/github-webhook-real.e2e.ts @@ -11,6 +11,7 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { setTimeout as delay } from 'node:timers/promises' import { fileURLToPath } from 'node:url' +import { decodeStorageRecord } from '@deepseek-ai/dsh-session/chunk-rows' import { describe, expect, it } from 'vitest' import WebSocket from 'ws' @@ -59,15 +60,23 @@ interface WorkspaceBaseline { } interface HistoryPage { - events: Array<{ - event: { - type: string - data: unknown - } - }> + records: Array< + | { type: 'event'; event: HistoryEvent } + | { type: 'chunks'; event: HistoryChunkEvent } + > hasMore: boolean } +interface HistoryEvent { + type: string + data: unknown +} + +interface HistoryChunkEvent extends HistoryEvent { + seq: number + time: number +} + interface ProcessObservation { readonly ready: Promise readonly text: () => string @@ -255,10 +264,10 @@ async function history(baseUrl: string, sessionId: string): Promise { request: { address: { kind: 'session', sessionId }, maxMessages: 100 } }, value => isRecord(value) && value.type === 'snapshot' - && Array.isArray(value.events) + && Array.isArray(value.records) && typeof value.hasMore === 'boolean', ) - return { events: frame.events as HistoryPage['events'], hasMore: frame.hasMore as boolean } + return { records: frame.records as HistoryPage['records'], hasMore: frame.hasMore as boolean } } /** Poll a public observation until it satisfies the test's behavior predicate. */ @@ -294,7 +303,7 @@ async function eventually( /** Return every text block from durable assistant messages. */ function assistantText(page: HistoryPage): string { const text: string[] = [] - for (const { event } of page.events) { + for (const event of historyEvents(page)) { if (event.type !== 'assistant/message' || !isRecord(event.data) || !isRecord(event.data.message)) continue const content = event.data.message.content if (!Array.isArray(content)) continue @@ -305,6 +314,18 @@ function assistantText(page: HistoryPage): string { return text.join('\n') } +/** Expand lossless history records for assertions over the public event stream. */ +function historyEvents(page: HistoryPage): HistoryEvent[] { + return page.records.flatMap(record => record.type === 'event' + ? [record.event] + : decodeStorageRecord({ + type: record.event.type.replace(/^chunkrow\//u, ''), + seq0: record.event.seq, + time0: record.event.time, + data: record.event.data, + })) +} + /** Stop the spawned CLI through its normal signal path, escalating only on a stuck teardown. */ async function stop(child: ChildProcess): Promise { if (child.exitCode !== null) return @@ -410,7 +431,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('GitHub webhook through the real 'webhook provenance, title, and permission events', async () => await history(baseUrl, sessionId), (page) => { - const events = page.events.map(item => item.event) + const events = historyEvents(page) const title = events.find(event => event.type === 'session/title') const permission = events.find(event => event.type === 'permission/preset' @@ -429,7 +450,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('GitHub webhook through the real }, 30_000, ) - const webhookMessage = admitted.events.map(item => item.event) + const webhookMessage = historyEvents(admitted) .find(event => event.type === 'user/message' && isRecord(event.data) && isRecord(event.data.source) diff --git a/apps/web/tests/cordis-tool-round.e2e.ts b/apps/web/tests/cordis-tool-round.e2e.ts index 6dfebd0e98..c258520c45 100644 --- a/apps/web/tests/cordis-tool-round.e2e.ts +++ b/apps/web/tests/cordis-tool-round.e2e.ts @@ -134,6 +134,16 @@ describe('web e2e: Cordis tools use their owned cards', () => { await input.fill(STOP_PROMPT) await input.press('Enter') await stopTurnSettled + await expect.poll(() => { + const stop = sessionEvents.find( + (event): event is Extract => + event.type === 'tool/call' && event.data.name === 'cordis_stop', + ) + return stop !== undefined && sessionEvents.some( + event => event.type === 'tool/result' + && String(event.data.message.source.callId) === String(stop.data.callId), + ) + }, { timeout: 15_000 }).toBe(true) if (MODE === 'record') { assertCompleteCordisLifecycle(sessionEvents) await expect.poll(() => page.getByText('CORDIS_UI_DONE', { exact: true }).count(), { timeout: 15_000 }) @@ -181,6 +191,12 @@ describe('web e2e: Cordis tools use their owned cards', () => { it.skipIf(MODE === 'record')('matches the conversation aria golden', async () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-cordis-aria')) console.log('MODEL_TRACE', { modelChanges, frameCount: modelFrames.length, modelFrames }) + // Final Assistant text precedes turn/end. Three footers prove every turn + // reached the render state covered by the ARIA golden. + await expect.poll( + () => page.getByRole('button', { name: 'Branch into a new conversation', exact: true }).count(), + { timeout: 15_000 }, + ).toBe(3) await page.locator('[data-conversation-scroll]').evaluate((host) => { host.scrollTop = host.scrollHeight }) await expect.poll( async () => page.getByRole('button', { name: 'Back to bottom', exact: true }).count(), diff --git a/apps/web/tests/smoke-real.e2e.ts b/apps/web/tests/smoke-real.e2e.ts index 5fad795736..a5c5de075f 100644 --- a/apps/web/tests/smoke-real.e2e.ts +++ b/apps/web/tests/smoke-real.e2e.ts @@ -180,17 +180,26 @@ async function sessionCursor(baseUrl: string, sessionId: string): Promise { return typeof value === 'object' && value !== null } function providerTitle(page: HistoryPage): string | undefined { - for (let index = page.events.length - 1; index >= 0; index--) { - const event = page.events[index]!.event + const events = page.records.flatMap(record => record.type === 'event' ? [record.event] : []) + for (let index = events.length - 1; index >= 0; index--) { + const event = events[index] as HistoryEvent if (event.type !== 'session/title' || !isRecord(event.data)) continue const source = event.data.source if (typeof event.data.title === 'string' && isRecord(source) && source.kind === 'provider') { @@ -201,7 +210,9 @@ function providerTitle(page: HistoryPage): string | undefined { } function hasAssistantMarker(page: HistoryPage, marker: string): boolean { - return page.events.some(({ event }) => { + return page.records.some((record) => { + if (record.type !== 'event') return false + const { event } = record if (event.type !== 'assistant/message' || !isRecord(event.data) || !isRecord(event.data.message)) return false const content = event.data.message.content if (!Array.isArray(content)) return false @@ -556,16 +567,18 @@ describe('dsh web keyless CLI smoke', () => { return hasAssistantMarker(page, recoveredMarker) }, { timeout: 20_000 }).toBe(true) if (page === undefined) throw new Error('retry history was not observed') - const retry = page.events.find(({ event }) => event.type === 'llm/retry')?.event + const retry = page.records.find(record => ( + record.type === 'event' && record.event.type === 'llm/retry' + )) expect(mainAttempts).toBe(2) - expect(retry?.data).toMatchObject({ + expect(retry?.type === 'event' ? retry.event.data : undefined).toMatchObject({ turn: 1, step: 1, retry: 1, maxRetries: 5, failure: { code: 'TRANSPORT' }, }) - expect(JSON.stringify(page.events)).toContain('WEB_RETRY_DISCARDED') + expect(JSON.stringify(page.records)).toContain('WEB_RETRY_DISCARDED') } finally { const closed = child.exitCode === null ? new Promise((resolveClose) => { child.once('close', () => { resolveClose() }) }) diff --git a/docs/config-catalog.i18n.yaml b/docs/config-catalog.i18n.yaml index cb68b4c9e1..2ffc7c93e6 100644 --- a/docs/config-catalog.i18n.yaml +++ b/docs/config-catalog.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/config-catalog.md -config-catalog.md: a2cf48a332698d79ba20f975e682b10a68340d34 -config-catalog.zh.md: c2563cf978fe13d3ca2911c52ca5f980936db7ac +config-catalog.md: aea69321f733b73eb81be5ea8183b8e49ad9a42f +config-catalog.zh.md: e5105a731ed56042160c0d0569d2f48bbd7aae7c diff --git a/docs/config-catalog.md b/docs/config-catalog.md index a2cf48a332..aea69321f7 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -2318,10 +2318,12 @@ Source: [`packages/subagent/subagent-claude-code/src/index.ts:38`](../packages/s Requires: `subagents` · `subprocess` ```ts config-catalog -/** Deployment-owned permission, environment, and process-release settings. */ +/** Deployment-owned model, permission, environment, and process-release settings. */ export interface Config { /** Provider name on `ctx.subagents` (default `codex`). */ providerName?: string + /** Native Codex model fixed for this instance; omitted to inherit Codex settings. */ + model?: string /** * Explicit environment entries layered over the subprocess seam's * credential-scrubbed parent environment. diff --git a/docs/config-catalog.zh.md b/docs/config-catalog.zh.md index c2563cf978..e5105a731e 100644 --- a/docs/config-catalog.zh.md +++ b/docs/config-catalog.zh.md @@ -2320,10 +2320,12 @@ export type ClaudeCodePermissionMode = typeof CLAUDE_CODE_PERMISSION_MODES[numbe 需要：`subagents` · `subprocess` ```ts config-catalog -/** Deployment-owned permission, environment, and process-release settings. */ +/** Deployment-owned model, permission, environment, and process-release settings. */ export interface Config { /** Provider name on `ctx.subagents` (default `codex`). */ providerName?: string + /** Native Codex model fixed for this instance; omitted to inherit Codex settings. */ + model?: string /** * Explicit environment entries layered over the subprocess seam's * credential-scrubbed parent environment. diff --git a/docs/event-producer-consumer.i18n.yaml b/docs/event-producer-consumer.i18n.yaml index c112b79bfd..89cb5e6c17 100644 --- a/docs/event-producer-consumer.i18n.yaml +++ b/docs/event-producer-consumer.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/event-producer-consumer.md -event-producer-consumer.md: 7182dd4bfba60922ecf419eaf39fa6518fdea194 -event-producer-consumer.zh.md: 2ada50a065014802a10a9ea2cc153f3a076f52bf +event-producer-consumer.md: c4610aa3e6ad59764e4d3f85db33c8e0f285ac6e +event-producer-consumer.zh.md: d6f4903d93d3829ccf753ad98d9237094d726c3e diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 7182dd4bfb..c4610aa3e6 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -21,11 +21,11 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `agent/session-start` | `emit` | [`packages/core/agent/src/runtime-types.ts:224`](../packages/core/agent/src/runtime-types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | `agent-team`, [`goal`](../packages/goal/goal), [`goal-round-driver`](../packages/goal/goal-round-driver), [`hooks-claude-code`](../packages/hooks/hooks-claude-code), [`hooks-codex`](../packages/hooks/hooks-codex) | | `agent/status` | `emit` | [`packages/core/agent/src/runtime-types.ts:185`](../packages/core/agent/src/runtime-types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`agent`](../packages/core/agent), `agent-team`, [`compaction-basic`](../packages/compaction/compaction-basic), [`goal-round-driver`](../packages/goal/goal-round-driver), [`schedule`](../packages/schedule/schedule), `server`, `session-controller` | | `agent/turn-stopping` | `serial` | [`packages/core/agent/src/runtime-types.ts:285`](../packages/core/agent/src/runtime-types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`hooks-claude-code`](../packages/hooks/hooks-claude-code), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `api-session/activity` | `emit` | [`packages/api/session-controller/src/types.ts:482`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | -| `api-session/added` | `emit` | [`packages/api/session-controller/src/types.ts:462`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | -| `api-session/error` | `emit` | [`packages/api/session-controller/src/types.ts:489`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | -| `api-session/removed` | `emit` | [`packages/api/session-controller/src/types.ts:468`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | -| `api-session/status` | `emit` | [`packages/api/session-controller/src/types.ts:475`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | +| `api-session/activity` | `emit` | [`packages/api/session-controller/src/types.ts:503`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | +| `api-session/added` | `emit` | [`packages/api/session-controller/src/types.ts:483`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | +| `api-session/error` | `emit` | [`packages/api/session-controller/src/types.ts:510`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | +| `api-session/removed` | `emit` | [`packages/api/session-controller/src/types.ts:489`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | +| `api-session/status` | `emit` | [`packages/api/session-controller/src/types.ts:496`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | | `approval/request` | `waterfall` | [`packages/interaction/user-approval/src/types.ts:85`](../packages/interaction/user-approval/src/types.ts) | [`user-approval`](../packages/interaction/user-approval) (`waterfall`) | [`acp`](../packages/acp/acp), `remotes` | | `authorization/settled` | `emit` | [`packages/credentials/authorization/src/index.ts:57`](../packages/credentials/authorization/src/index.ts) | [`authorization`](../packages/credentials/authorization) (`events.dispatch`) | [`authorization`](../packages/credentials/authorization) | | `commands/change` | `emit` | [`packages/interaction/commands/src/types.ts:80`](../packages/interaction/commands/src/types.ts) | [`commands`](../packages/interaction/commands) (`events.dispatch`) | `remotes` | diff --git a/docs/event-producer-consumer.zh.md b/docs/event-producer-consumer.zh.md index 2ada50a065..d6f4903d93 100644 --- a/docs/event-producer-consumer.zh.md +++ b/docs/event-producer-consumer.zh.md @@ -23,11 +23,11 @@ | `agent/session-start` | `emit` | [`packages/core/agent/src/runtime-types.ts:224`](../packages/core/agent/src/runtime-types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emitAgentEvent`) | `agent-team`, [`goal`](../packages/goal/goal), [`goal-round-driver`](../packages/goal/goal-round-driver), [`hooks-claude-code`](../packages/hooks/hooks-claude-code), [`hooks-codex`](../packages/hooks/hooks-codex) | | `agent/status` | `emit` | [`packages/core/agent/src/runtime-types.ts:185`](../packages/core/agent/src/runtime-types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`agent`](../packages/core/agent), `agent-team`, [`compaction-basic`](../packages/compaction/compaction-basic), [`goal-round-driver`](../packages/goal/goal-round-driver), [`schedule`](../packages/schedule/schedule), `server`, `session-controller` | | `agent/turn-stopping` | `serial` | [`packages/core/agent/src/runtime-types.ts:285`](../packages/core/agent/src/runtime-types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`hooks-claude-code`](../packages/hooks/hooks-claude-code), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `api-session/activity` | `emit` | [`packages/api/session-controller/src/types.ts:482`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | -| `api-session/added` | `emit` | [`packages/api/session-controller/src/types.ts:462`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | -| `api-session/error` | `emit` | [`packages/api/session-controller/src/types.ts:489`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | -| `api-session/removed` | `emit` | [`packages/api/session-controller/src/types.ts:468`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | -| `api-session/status` | `emit` | [`packages/api/session-controller/src/types.ts:475`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | +| `api-session/activity` | `emit` | [`packages/api/session-controller/src/types.ts:503`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | +| `api-session/added` | `emit` | [`packages/api/session-controller/src/types.ts:483`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | +| `api-session/error` | `emit` | [`packages/api/session-controller/src/types.ts:510`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | +| `api-session/removed` | `emit` | [`packages/api/session-controller/src/types.ts:489`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | +| `api-session/status` | `emit` | [`packages/api/session-controller/src/types.ts:496`](../packages/api/session-controller/src/types.ts) | `session-controller` (`emit`) | `remotes` | | `approval/request` | `waterfall` | [`packages/interaction/user-approval/src/types.ts:85`](../packages/interaction/user-approval/src/types.ts) | [`user-approval`](../packages/interaction/user-approval) (`waterfall`) | [`acp`](../packages/acp/acp), `remotes` | | `authorization/settled` | `emit` | [`packages/credentials/authorization/src/index.ts:57`](../packages/credentials/authorization/src/index.ts) | [`authorization`](../packages/credentials/authorization) (`events.dispatch`) | [`authorization`](../packages/credentials/authorization) | | `commands/change` | `emit` | [`packages/interaction/commands/src/types.ts:80`](../packages/interaction/commands/src/types.ts) | [`commands`](../packages/interaction/commands) (`events.dispatch`) | `remotes` | diff --git a/docs/persistence-catalog.i18n.yaml b/docs/persistence-catalog.i18n.yaml index 04ad9a33d7..36b89eabc3 100644 --- a/docs/persistence-catalog.i18n.yaml +++ b/docs/persistence-catalog.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/persistence-catalog.md -persistence-catalog.md: 12558eeadc009b498c9a178cfcc79116bf1b7c2b +persistence-catalog.md: 7c63cd8dfdb181fac09cf3ce2e4bcec96d2bd59c persistence-catalog.zh.md: f855d6969aa2dcade159ac8d6549e5f0350a7f0f diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index 12558eeadc..7c63cd8dfd 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -512,7 +512,7 @@ Source: [`packages/llm/llm-retry/src/types.ts:11`](../packages/llm/llm-retry/src 'model/selection': ModelSelection ``` -Source: [`packages/api/session-controller/src/types.ts:39`](../packages/api/session-controller/src/types.ts) +Source: [`packages/api/session-controller/src/types.ts:40`](../packages/api/session-controller/src/types.ts) ### `permission/*` diff --git a/docs/subsystems/conversation.i18n.yaml b/docs/subsystems/conversation.i18n.yaml index dc3e51e636..a915f868f5 100644 --- a/docs/subsystems/conversation.i18n.yaml +++ b/docs/subsystems/conversation.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/subsystems/conversation.md -conversation.md: d26abf73292faacdf3a4186819c4738d1de0270e -conversation.zh.md: 7fff9e0433b0022c75a35d3885398f241818a21d +conversation.md: 28a7b3d497182f2f560f2b54f89fcfd3091af673 +conversation.zh.md: 7cf98fe2b18d9fd53e5f49f48330a5585e04c54d diff --git a/docs/subsystems/conversation.md b/docs/subsystems/conversation.md index d26abf7329..28a7b3d497 100644 --- a/docs/subsystems/conversation.md +++ b/docs/subsystems/conversation.md @@ -2,18 +2,18 @@ English | [中文](conversation.zh.md) -Conversation is the target-neutral assembly layer between a Client Session event window and browser views. [`ui-conversation`](../../packages/client/ui-conversation/README.md) owns the event and view registries, one identity-stable binding per `SessionBinding`, Turn/Step locations, incremental Context assembly, target sources, the shared shell, and input orchestration. Target packages such as [`ui-chat`](../../packages/client/ui-chat/README.md) and [`ui-trajectory`](../../packages/client/ui-trajectory/README.md) own their Definitions, final snapshots, and rendering. +Conversation is the target-neutral assembly layer between a Client `SessionEventLikeEntry` window and browser views. [`ui-conversation`](../../packages/client/ui-conversation/README.md) owns the event and view registries, one identity-stable binding per `SessionBinding`, Turn/Step locations, incremental Context assembly, target sources, the shared shell, and input orchestration. Target packages such as [`ui-chat`](../../packages/client/ui-chat/README.md) and [`ui-trajectory`](../../packages/client/ui-trajectory/README.md) own their Definitions, final snapshots, and rendering. This page defines the data model and the extension path for a business-owned Conversation node. The [Web Client architecture](web-client.md) places the subsystem between Client models and Slots; the [Conversation Node assembly decision](../../.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.md) owns its rationale. ## Data model and ownership -The Session Controller owns the contiguous loaded event window. `ui-conversation` observes that existing source and converts each entry to `{ event, view? }`; it never opens a second history stream. One `ConversationNodeAssembler` per Session applies every registered Definition and publishes an independent source for each registered view target. +The Session Controller owns the contiguous loaded logical-event window. Each `SessionEventLikeEntry` is either `{ type: 'event', event: SessionEvent }` or `{ type: 'chunks', event: ChunkRowEvent }`; both inner events expose `type`, `seq`, `time`, and `data`. `ui-conversation` passes these entries to the assembler without opening a second history stream, converting records, or expanding packed members. One `ConversationNodeAssembler` per Session applies every registered Definition and publishes an independent source for each registered view target. | Concept | Owner and purpose | |---|---| -| Event Definition | A business package matches one event at a time, correlates it by stable `(kind, id)`, folds deterministic State, and optionally materializes one target node. | -| Context | The engine-owned ordered Matches and current State for one `(kind, id)`. Update-only evidence may remain pending until pagination supplies its unique start. | +| Event Definition | A business package matches one standard event or packed Assistant run at a time, correlates it by stable `(kind, id)`, folds deterministic State, and optionally materializes one target node. | +| Context | The engine-owned ordered Matches and current State for one `(kind, id)`. A packed run occupies one update Match; update-only evidence may remain pending until pagination supplies its unique scalar start. | | Location | The engine-owned Session, Turn, or Step coordinates derived from durable boundary events. Definitions may publish typed data onto one Turn or Step. | | View Definition | A target package creates one incremental builder per Session and owns the final snapshot type for that target. | | View | A Slot entry such as Chat or Trajectory reads only its target snapshot and renders target-owned nodes. | @@ -36,6 +36,8 @@ Use the producer-owned branded id type across the process boundary. Put the `Ses Incremental events are supported. Prefer whole-value checkpoints when the producer can emit them cheaply, because they remain useful when the start is outside the loaded window. Each delta must carry the stable id and produce deterministic State when replayed in ascending log `seq`; it must not depend on live-only memory. If the current history window contains only updates, the assembler keeps a pending Context and builds no State until an older page supplies the start. If the product must render before the start is loaded, a terminal or checkpoint event must carry enough whole fallback state for the Definition to build that result directly; do not recover it by scanning unrelated events. +Historical runs of consecutive same-block `assistant/chunk` deltas arrive as `chunkrow/text-chunks`, `chunkrow/reasoning-chunks`, or `chunkrow/tool-call-chunks`. Their top-level `seq` and `time` identify the first logical member, and their `data` retains each fragment and timestamp gap. These Client-only events can only be updates; `start()` receives a standard `SessionEvent`. A Definition that consumes Assistant deltas handles the relevant packed tags in the same `match()` and `update()` methods, while other Definitions return `null` without expanding the run. + ## Definition and typed Chat payload The example keeps the producer declarations and client contribution in one block so the complete relationship is visible. In a package family, keep the branded id and `SessionEventMap` declaration with the event producer, and keep the Definition, Chat data merge, and renderer in the client plugin. @@ -208,7 +210,7 @@ export function apply(ctx: ClientContext): void { } ``` -`match(event)` is an identity extractor, not a fold: it receives only the current event and returns the Definition-local id and lifecycle role. After a match, the assembler locates the Context by `(kind, id)` and calls `start` once or `update` with the current State. Both functions return the State that the engine adopts; returning a new immutable value is preferred, but a function that mutates and returns the same object has the same adoption semantics. +`match(event)` is an identity extractor, not a fold: it receives only the current `SessionEventLike` and returns the Definition-local id and lifecycle role. After a match, the assembler locates the Context by `(kind, id)` and calls `start` once for a standard event or `update` for a standard or packed event. Both functions return the State that the engine adopts; returning a new immutable value is preferred, but a function that mutates and returns the same object has the same adoption semantics. `buildLocationData(context, scope)` optionally publishes Definition-owned data onto an engine-owned Turn or Step. Use declaration merging to give each key a precise value type. Another Node in the same Location can consume that value through its constrained slot hook, such as `useTurnData(key)`, without receiving the Session or scanning `snapshot.chat.nodes`. @@ -222,17 +224,17 @@ The assembler records that dependency. If an older prepend later supplies a near ## Window update paths -History may be requested from the tail backward one page at a time, but every accepted page is normalized into ascending `seq` before State replay. +History may be requested from the tail backward one page at a time. The Session journal validates non-overlapping logical sequence ranges first; the Assembler then orders accepted inputs by their first `seq` before State replay. | Path | Engine work | Definition-visible behavior | |---|---|---| -| Replace on open, resync, or gap repair | Rebuild the loaded window, match every event once per Definition, then replay each started Context | `start`, followed by its updates in ascending `seq`; pending update-only Contexts remain without State | -| Prepend one older page | Match only fresh older events, merge them into Contexts by `(kind, id)`, preserve existing keyed nodes, and replay only affected Contexts and dependencies | A newly found start activates its collected updates; a changed Location or predecessor may rerun the Context | -| Append one live event | Call each Definition's `match` once, look up the matched Context by key, and update only that Context | One `update` and one requested publication for a matching post-start event; no existing Context scan | +| Replace on open, resync, or gap repair | Rebuild the loaded window, match every standard event or packed run once per Definition, then replay each started Context | `start`, followed by its updates in ascending logical `seq`; pending update-only Contexts remain without State | +| Prepend one older page | Match only fresh older inputs, merge them into Contexts by `(kind, id)`, preserve existing keyed nodes, and replay only affected Contexts and dependencies | A newly found scalar start activates its collected scalar and packed updates; a changed Location or predecessor may rerun the Context | +| Append one live event | Call each Definition's `match` once, look up the matched Context by key, and update only that Context | One scalar `update` and one requested publication for a matching post-start event; no existing Context scan | -With `D` registered Definitions, one incoming event performs `D` current-event matches and constant-time Context-key lookup after a match. Definition code must preserve that property: do not traverse the complete event window, every Context, `context.matches`, or the rendered Node collection on the normal append path. Use State for accumulated facts, Location data for same-Turn/Step sharing, and `reader.previous()` for indexed predecessor dependencies. +With `D` registered Definitions, one incoming scalar event or packed run performs `D` current-input matches and constant-time Context-key lookup after a match. Definition code must preserve that property: do not traverse the complete event window, every Context, `context.matches`, or the rendered Node collection on the normal append path. Use State for accumulated facts, Location data for same-Turn/Step sharing, and `reader.previous()` for indexed predecessor dependencies. -`publication` controls when changed State is materialized. Use `immediate` for structural or terminal changes, `animation-frame` for high-frequency visible deltas, and `none` when the State change feeds only a later publication. The engine still applies every update in log order; cadence only coalesces view publication. +`publication` controls when changed State is materialized. Use `immediate` for structural or terminal changes, `animation-frame` for high-frequency visible deltas, and `none` when the State change feeds only a later publication. The engine applies every scalar update in log order and every packed run in one batch update; cadence only coalesces view publication. ## Verification obligations @@ -244,5 +246,6 @@ Add focused tests that establish these outcomes: 4. Prepending an older page adds earlier rows without replacing existing keyed Node values whose data did not change. 5. Repeated visible deltas preserve `context.key` and publish at most once per animation frame when requested. 6. The keyed renderer consumes `node.data` and constrained Location hooks only; it does not scan the Session event window, Contexts, or Chat Nodes. +7. Scalar and packed Assistant history produce the same final State, timing boundaries, and target snapshot, while one packed run remains one Match through replace, prepend, Location replay, and registry rebuild. Use [`packages/client/ui-chat/src/client/conversation-nodes/assistant.ts`](../../packages/client/ui-chat/src/client/conversation-nodes/assistant.ts) for streaming and interruption, [`inbox.ts`](../../packages/client/ui-chat/src/client/conversation-nodes/inbox.ts) plus [`message.ts`](../../packages/client/ui-chat/src/client/conversation-nodes/message.ts) for predecessor queries, and [`packages/client/ui-deliverables`](../../packages/client/ui-deliverables) for a Definition that publishes Turn data without creating its own Node. diff --git a/docs/subsystems/conversation.zh.md b/docs/subsystems/conversation.zh.md index 7fff9e0433..7cf98fe2b1 100644 --- a/docs/subsystems/conversation.zh.md +++ b/docs/subsystems/conversation.zh.md @@ -2,18 +2,18 @@ [English](conversation.md) | 中文 -Conversation 是 Client Session event window 与浏览器 view 之间的 target-neutral assembly 层。[`ui-conversation`](../../packages/client/ui-conversation/README.zh.md)拥有 event 与 view registry、每个 `SessionBinding` 对应的 identity-stable binding、Turn/Step Location、增量 Context assembly、target source、共享 shell 与输入编排。[`ui-chat`](../../packages/client/ui-chat/README.zh.md)和 [`ui-trajectory`](../../packages/client/ui-trajectory/README.zh.md)等 target 包拥有各自的 Definition、最终 snapshot 与渲染。 +Conversation 是 Client `SessionEventLikeEntry` window 与浏览器 view 之间的 target-neutral assembly 层。[`ui-conversation`](../../packages/client/ui-conversation/README.zh.md)拥有 event 与 view registry、每个 `SessionBinding` 对应的 identity-stable binding、Turn/Step Location、增量 Context assembly、target source、共享 shell 与输入编排。[`ui-chat`](../../packages/client/ui-chat/README.zh.md)和 [`ui-trajectory`](../../packages/client/ui-trajectory/README.zh.md)等 target 包拥有各自的 Definition、最终 snapshot 与渲染。 本文定义数据模型与业务自有 Conversation node 的扩展路径。[Web Client 架构](web-client.zh.md)说明该子系统在 Client model 与 Slots 之间的位置；[Conversation Node 组装决策](../../.agents/notes/implemented/architecture/2026-08-09-client-conversation-node-assembly.zh.md)记录其设计理由。 ## 数据模型与所有权 -Session Controller 拥有连续的已加载 event window。`ui-conversation` 观察这一个现有 source，并把每个 entry 转换为 `{ event, view? }`；它绝不另开一条 history stream。每个 Session 对应一个 `ConversationNodeAssembler`，它应用所有已注册 Definition，并为每个已注册 view target 发布独立 source。 +Session Controller 拥有连续的已加载逻辑 event window。每个 `SessionEventLikeEntry` 都是 `{ type: 'event', event: SessionEvent }` 或 `{ type: 'chunks', event: ChunkRowEvent }`；两种内部 event 都公开 `type`、`seq`、`time` 与 `data`。`ui-conversation` 把这些 entry 直接交给 assembler，不另开 history stream、不转换 record，也不展开 packed member。每个 Session 对应一个 `ConversationNodeAssembler`，它应用所有已注册 Definition，并为每个已注册 view target 发布独立 source。 | 概念 | Owner 与用途 | |---|---| -| Event Definition | 业务包一次匹配一条 event，以稳定 `(kind, id)` 关联事件、折叠确定性 State，并可选择 materialize 一个 target node。 | -| Context | Engine 为一个 `(kind, id)` 拥有的有序 Match 与当前 State。只有 update 的证据可以保持 pending，直到分页补齐其唯一 start。 | +| Event Definition | 业务包一次匹配一条标准 event 或一个 packed Assistant run，以稳定 `(kind, id)` 关联输入、折叠确定性 State，并可选择 materialize 一个 target node。 | +| Context | Engine 为一个 `(kind, id)` 拥有的有序 Match 与当前 State。一个 packed run 只占一个 update Match；只有 update 的证据可以保持 pending，直到分页补齐其唯一 scalar start。 | | Location | Engine 根据持久 boundary event 推导的 Session、Turn 或 Step 坐标。Definition 可以向一个 Turn 或 Step 发布类型化数据。 | | View Definition | Target 包为每个 Session 创建一个增量 builder，并拥有该 target 的最终 snapshot 类型。 | | View | Chat 或 Trajectory 等 Slot entry 只读取自身 target snapshot，并渲染 target 自有 node。 | @@ -36,6 +36,8 @@ Chat 与 Trajectory 可以识别同一个持久 event family，但各自保留 系统支持增量事件。如果生产方能以较低成本发出 whole-value checkpoint，应优先采用，因为 start 位于已加载窗口之外时它仍可直接使用。每条 delta 都必须携带稳定 id，并且按照日志 `seq` 升序回放时能够确定性地产生 State；它不能依赖只存在于实时内存中的状态。如果当前历史窗口只有 update，Assembler 会保留一个 pending Context，并在更早分页补齐 start 前不构造 State。如果产品必须在 start 尚未加载时渲染，terminal 或 checkpoint 事件就必须携带足够的完整 fallback 状态，让 Definition 能直接构造结果；不要通过扫描无关事件恢复它。 +连续且属于同一 block 的历史 `assistant/chunk` delta 会以 `chunkrow/text-chunks`、`chunkrow/reasoning-chunks` 或 `chunkrow/tool-call-chunks` 到达。顶层 `seq` 与 `time` 表示首个逻辑成员，`data` 保留每个 fragment 与 timestamp gap。这些 Client-only event 只能充当 update；`start()` 只接收标准 `SessionEvent`。消费 Assistant delta 的 Definition 在同一组 `match()` 与 `update()` 方法里处理相关 packed tag，其他 Definition 直接返回 `null`，无需展开该 run。 + ## Definition 与类型化 Chat payload 为了完整展示关联关系，下面把生产方声明和 Client 贡献写在同一个代码块里。实际的包族中，branded id 与 `SessionEventMap` 声明留在事件生产方，Definition、Chat data 合并与 renderer 留在 Client 插件。 @@ -208,7 +210,7 @@ export function apply(ctx: ClientContext): void { } ``` -`match(event)` 是身份提取器，不是 fold：它只能收到当前事件，并返回 Definition 内部 id 与生命周期角色。命中后，Assembler 通过 `(kind, id)` 定位 Context，再调用一次 `start`，或把当前 State 交给 `update`。两个函数都必须返回引擎随后采用的 State；推荐返回新的 immutable value，但函数原地修改后返回同一对象时，采用语义也相同。 +`match(event)` 是身份提取器，不是 fold：它只能收到当前 `SessionEventLike`，并返回 Definition 内部 id 与生命周期角色。命中后，Assembler 通过 `(kind, id)` 定位 Context；标准 event 可触发一次 `start`，标准或 packed event 可把当前 State 交给 `update`。两个函数都必须返回引擎随后采用的 State；推荐返回新的 immutable value，但函数原地修改后返回同一对象时，采用语义也相同。 `buildLocationData(context, scope)` 可以把 Definition 拥有的数据发布到引擎拥有的 Turn 或 Step 上。通过 declaration merging 为每个 key 指定精确 value 类型。同一 Location 内的另一个 Node 可以使用受限 slot hook（例如 `useTurnData(key)`）读取该值，无须取得 Session，也无须扫描 `snapshot.chat.nodes`。 @@ -222,17 +224,17 @@ Assembler 会记录这项依赖。如果后续 older prepend 带来了更近的 ## Window 更新路径 -历史可能从尾部开始一页一页向前请求，但每个已接收分页都会先按 `seq` 升序归一化，再进入 State 回放。 +历史可能从尾部开始一页一页向前请求。Session journal 先校验互不重叠的逻辑 seq range，Assembler 再按每个已接受 input 的首 `seq` 排序并进入 State 回放。 | 路径 | 引擎工作 | Definition 可观察到的行为 | |---|---|---| -| open、resync 或 gap repair 时 replace | 重建已加载窗口，每条事件对每个 Definition 匹配一次，再回放每个已有 start 的 Context | 先执行 `start`，再按 `seq` 升序执行其 update；只有 update 的 pending Context 仍没有 State | -| prepend 一页更早历史 | 只匹配新增的更早事件，按 `(kind, id)` 合并进 Context，保留现有 keyed node，并只重放受影响的 Context 与依赖 | 新发现的 start 会激活已收集 update；Location 或前序依赖变化也可能重跑 Context | -| append 一条实时事件 | 每个 Definition 各调用一次 `match`，按 key 查找命中的 Context，只更新该 Context | 对 start 之后的匹配事件执行一次 `update` 并请求一次发布；不扫描已有 Context | +| open、resync 或 gap repair 时 replace | 重建已加载窗口，每条标准 event 或 packed run 对每个 Definition 匹配一次，再回放每个已有 start 的 Context | 先执行 `start`，再按逻辑 `seq` 升序执行其 update；只有 update 的 pending Context 仍没有 State | +| prepend 一页更早历史 | 只匹配新增的更早 input，按 `(kind, id)` 合并进 Context，保留现有 keyed node，并只重放受影响的 Context 与依赖 | 新发现的 scalar start 会激活已收集的 scalar 与 packed update；Location 或前序依赖变化也可能重跑 Context | +| append 一条实时事件 | 每个 Definition 各调用一次 `match`，按 key 查找命中的 Context，只更新该 Context | 对 start 之后的匹配事件执行一次 scalar `update` 并请求一次发布；不扫描已有 Context | -注册 `D` 个 Definition 时，一条新事件会进行 `D` 次仅当前事件匹配；命中后的 Context key 查询是常数时间。Definition 代码必须维持这个性质：正常 append 热路径不得遍历完整事件窗口、所有 Context、`context.matches` 或已渲染 Node 集合。累计事实放进 State，同 Turn/Step 共享信息放进 Location data，有索引的前序依赖使用 `reader.previous()`。 +注册 `D` 个 Definition 时，一条新 scalar event 或 packed run 会进行 `D` 次仅当前 input 匹配；命中后的 Context key 查询是常数时间。Definition 代码必须维持这个性质：正常 append 热路径不得遍历完整事件窗口、所有 Context、`context.matches` 或已渲染 Node 集合。累计事实放进 State，同 Turn/Step 共享信息放进 Location data，有索引的前序依赖使用 `reader.previous()`。 -`publication` 控制发生 State 变更后何时物化。结构或 terminal 变化使用 `immediate`，高频可见 delta 使用 `animation-frame`，只为后续发布积累 State 时使用 `none`。引擎仍会按日志顺序应用每条 update；该选项只合并视图发布频率。 +`publication` 控制发生 State 变更后何时物化。结构或 terminal 变化使用 `immediate`，高频可见 delta 使用 `animation-frame`，只为后续发布积累 State 时使用 `none`。引擎按日志顺序应用每条 scalar update，并用一次 batch update 应用一个 packed run；该选项只合并视图发布频率。 ## 验证要求 @@ -244,5 +246,6 @@ Assembler 会记录这项依赖。如果后续 older prepend 带来了更近的 4. prepend 更早分页只增加更早的行；数据未变化的既有 keyed Node value 不被替换。 5. 重复的可见 delta 保持 `context.key`，并在请求 `animation-frame` 时每帧最多发布一次。 6. keyed renderer 只消费 `node.data` 与受限 Location hook，不扫描 Session 事件窗口、Context 或 Chat Node。 +7. scalar 与 packed Assistant 历史产生相同的最终 State、timing boundary 和 target snapshot；一个 packed run 在 replace、prepend、Location replay 与 registry rebuild 中始终只保留一个 Match。 流式与中断处理可参考 [`packages/client/ui-chat/src/client/conversation-nodes/assistant.ts`](../../packages/client/ui-chat/src/client/conversation-nodes/assistant.ts)，前序查询可参考 [`inbox.ts`](../../packages/client/ui-chat/src/client/conversation-nodes/inbox.ts) 与 [`message.ts`](../../packages/client/ui-chat/src/client/conversation-nodes/message.ts)，只发布 Turn data 而不创建自有 Node 的例子见 [`packages/client/ui-deliverables`](../../packages/client/ui-deliverables)。 diff --git a/docs/subsystems/web-client.i18n.yaml b/docs/subsystems/web-client.i18n.yaml index 5406522b5b..98e549a149 100644 --- a/docs/subsystems/web-client.i18n.yaml +++ b/docs/subsystems/web-client.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/subsystems/web-client.md -web-client.md: a06f6aaf45a482437b0509e65b6ee8332ec35a44 -web-client.zh.md: 09f25bc45369a34ebf32c7a0b2b995c6732c9b29 +web-client.md: e67da4980af881e426f2bc031c6ec49cc1df2857 +web-client.zh.md: c5e9904226de66381a54bcb8a4783a062d70750f diff --git a/docs/subsystems/web-client.md b/docs/subsystems/web-client.md index a06f6aaf45..e67da4980a 100644 --- a/docs/subsystems/web-client.md +++ b/docs/subsystems/web-client.md @@ -2,7 +2,7 @@ English | [中文](web-client.zh.md) -The Web Client is a browser-side Cordis application assembled from independently loaded plugins. Its architecture has four reusable foundations: [Client Modules](client-modules.md) loads the plugin graph, the [API Gateway](../api-gateway.md) provides typed Host communication, [Slots](slots.md) composes React UI, and [Conversation](conversation.md) turns a Session event window into target-owned views. This page connects those systems and defines where Client models and feature packages belong. +The Web Client is a browser-side Cordis application assembled from independently loaded plugins. Its architecture has four reusable foundations: [Client Modules](client-modules.md) loads the plugin graph, the [API Gateway](../api-gateway.md) provides typed Host communication, [Slots](slots.md) composes React UI, and [Conversation](conversation.md) turns a Session history window into target-owned views. This page connects those systems and defines where Client models and feature packages belong. ## Layers and ownership @@ -12,7 +12,7 @@ The Web Client is a browser-side Cordis application assembled from independently | Transport and API assembly | `client/connection`, `api/gateway`, `api/remotes` | Establish a Client generation, expose generated `ctx.remote` methods and streams, forward selected Cordis events, and carry cancellation and results. | | Client models | `api/session-controller/client`, `api/workspace-controller/client` | Maintain React-free mirrors of Host state, resolve stream/unary races, own object identities and subscriptions, and expose narrow command services. | | UI adapters | `client/ui-session`, `client/ui-workspace` | Convert model observables into root or Session-scoped standard Slot sources without taking ownership of business state. | -| Conversation data | `client/ui-conversation`, target packages such as `ui-chat` and `ui-trajectory` | Assemble durable Session events into independent target snapshots and own the shared conversation shell and input flow. | +| Conversation data | `client/ui-conversation`, target packages such as `ui-chat` and `ui-trajectory` | Assemble standard events and compact historical Assistant runs into independent target snapshots and own the shared conversation shell and input flow. | | Composition and rendering | `client/ui-slots`, `client/ui-renderer`, `client/ui-layout`, feature UI packages | Declare extension locations, derive component props, bind observables to React hooks, and mount the final tree. | The dependency direction is Host state → Remote transport → Client model → UI adapter → Conversation or presentation → Slots → React. User actions travel back through callbacks that close over an injected Client service or generated Remote namespace. A presentation component never receives Cordis `ctx`, a transport object, or another feature plugin's implementation. @@ -41,9 +41,9 @@ Each API controller package owns a paired Host and Client face. The Host side ow - `ClientSessions` provides `ctx.sessions`, owns Session scopes and stable `SessionBinding` objects, and projects the selected list state. - `SessionManager` owns the list baseline, live list/control updates, lazy Session instances, queues, projection stores, subagent catalogs, and conflict ordering between pulls and later updates. -- Each `Session` owns one contiguous event window, paging, follow, prompt/control state, and the observable snapshot consumed by adapters. +- Each `Session` owns one contiguous logical-event window represented by `SessionEventLikeEntry` values, paging, follow, prompt/control state, and the observable snapshot consumed by adapters. -The durable event path opens `follow()`, whose first frame contains the current header, tail page, cursor, and complete projection baseline. Each physical generation atomically replaces the retained window from that snapshot; live events then append by sequence. `page()` is reserved for older history and gap repair. The transient control stream starts every generation with a complete baseline and then applies queue, job, and projection updates. +The durable event path opens `follow()`, whose first frame contains the current header, tail page, cursor, and complete projection baseline. History records have an explicit `event` or `chunks` discriminator and an aligned inner `event`; the journal validates each inclusive logical sequence range before the Client retains the records as `SessionEventLikeEntry` values without per-record conversion. Each physical generation atomically replaces the retained window from that snapshot; standard live events then append by sequence. `page()` is reserved for older history and gap repair. The transient control stream starts every generation with a complete baseline and then applies queue, job, and projection updates. ### Workspaces @@ -55,7 +55,7 @@ This pairing is not a second source of business truth. Host controllers decide d `ui-session` installs the `session` scope adapter and publishes `useSessions`, `useSession`, `sessionId`, and `useProjection`. Domain adapters add further standard sources without putting React hooks on the model objects. -`ui-conversation` binds once to each `SessionBinding.eventSource`. Its event registry correlates raw durable events into stable business Contexts, and its view registry materializes target snapshots. `ui-chat` and `ui-trajectory` register separate Definitions and builders: they may interpret the same event family, but they do not import or share each other's final display model. The shell selects a registered view and passes its snapshot through standard hooks and Slots. [Conversation](conversation.md) defines Context identity, replay, Location data, target builders, and keyed renderers. +`ui-conversation` binds once to each `SessionBinding.eventSource`. Its event registry correlates standard events and Client-only `chunkrow/*` history events into stable business Contexts, and its view registry materializes target snapshots. Packed runs stay single inputs and Matches through replay; Chat Assistant, Trajectory Assistant, and Turn Tail are the built-in Definitions that interpret them. `ui-chat` and `ui-trajectory` register separate Definitions and builders: they may interpret the same event family, but they do not import or share each other's final display model. The shell selects a registered view and passes its snapshot through standard hooks and Slots. [Conversation](conversation.md) defines Context identity, replay, Location data, target builders, and keyed renderers. `ui-slots` provides the typed registry and lifecycle ledger; `ui-renderer` is the only package that binds bare observables through `useSyncExternalStore`, owns React contexts, and renders the root tree. Feature components receive framework hooks, owner props, store actions, and explicit injection through their derived props. [Web Client Slots](slots.md) lists those inputs, extension APIs, and the current Slot hierarchy. @@ -63,7 +63,7 @@ This pairing is not a second source of business truth. Host controllers decide d | Path | Sequence | |---|---| -| durable Session display | Host Session log → Remote `follow` plus `page` → Client `Session` event window → Conversation Contexts → target snapshot (`chat`, `trajectory`, or another registered target) → Slot view → React | +| durable Session display | Host Session log → packed Remote `follow`/`page` history → Client `SessionEventLikeEntry` window → Conversation Contexts → target snapshot (`chat`, `trajectory`, or another registered target) → Slot view → React | | transient Session control | Host control baseline → Remote snapshot stream → `SessionManager` queue/job/projection stores → Session and list snapshots → standard hooks → components | | Workspace state | Host Workspace baseline and increments → `ClientWorkspaceModel` → `ctx.workspaces.list` → `useWorkspaces` → sidebar, hero, and navigation entries | | scoped interaction | Host Cordis waterfall → API Remotes `$events` → `ctx.remote.$on()` on the Session Context → owning UI package → result or `next()` | @@ -75,7 +75,7 @@ Physical and logical recovery are separate. Gateway mux restores the physical We Recovery follows the data's semantics: -- A durable Session journal replaces its window from every generation's opening snapshot; `page()` supplies older history and repairs any later sequence gap. +- A durable Session journal validates logical sequence ranges and replaces its window from every generation's opening snapshot; `page()` supplies older history and repairs any later range gap. - Session control and Workspace streams retain the last published value while disconnected, then atomically replace it from a fresh opening baseline. - Ordinary forwarded notifications are not replayed. Stateful domains need a baseline, cursor, or explicit query; scoped waterfalls retain their own request lifetime. diff --git a/docs/subsystems/web-client.zh.md b/docs/subsystems/web-client.zh.md index 09f25bc453..c5e9904226 100644 --- a/docs/subsystems/web-client.zh.md +++ b/docs/subsystems/web-client.zh.md @@ -2,7 +2,7 @@ [English](web-client.md) | 中文 -Web Client 是由独立加载插件组装而成的浏览器侧 Cordis 应用。它有四个可复用底座：[Client Modules](client-modules.zh.md) 加载插件图，[API Gateway](../api-gateway.zh.md) 提供类型化 Host 通信，[Slots](slots.zh.md) 组合 React UI，[Conversation](conversation.zh.md) 把 Session 事件窗口变成各 target 自有的视图。本文串联这些系统，并规定 Client model 与功能包各自所在的位置。 +Web Client 是由独立加载插件组装而成的浏览器侧 Cordis 应用。它有四个可复用底座：[Client Modules](client-modules.zh.md) 加载插件图，[API Gateway](../api-gateway.zh.md) 提供类型化 Host 通信，[Slots](slots.zh.md) 组合 React UI，[Conversation](conversation.zh.md) 把 Session 历史窗口变成各 target 自有的视图。本文串联这些系统，并规定 Client model 与功能包各自所在的位置。 ## 分层与所有权 @@ -12,7 +12,7 @@ Web Client 是由独立加载插件组装而成的浏览器侧 Cordis 应用。 | 传输与 API assembly | `client/connection`、`api/gateway`、`api/remotes` | 建立 Client generation，公开生成的 `ctx.remote` method 与 stream，转发选定的 Cordis event，并承载取消和结果。 | | Client model | `api/session-controller/client`、`api/workspace-controller/client` | 维护不依赖 React 的 Host 状态镜像，处理 stream/unary 竞态，拥有对象 identity 与订阅，并公开收窄的 command service。 | | UI adapter | `client/ui-session`、`client/ui-workspace` | 把 model observable 转换为 root 或 Session scope 的标准 Slot source，不接管业务状态所有权。 | -| Conversation 数据 | `client/ui-conversation`、`ui-chat` 与 `ui-trajectory` 等 target package | 把持久 Session event 组装成相互独立的 target snapshot，并拥有共享的 Conversation shell 与输入流程。 | +| Conversation 数据 | `client/ui-conversation`、`ui-chat` 与 `ui-trajectory` 等 target package | 把标准 event 与紧凑的 Assistant 历史批次组装成相互独立的 target snapshot，并拥有共享的 Conversation shell 与输入流程。 | | 组合与渲染 | `client/ui-slots`、`client/ui-renderer`、`client/ui-layout`、各 UI 功能包 | 声明扩展位置、推导组件 props、把 observable 绑定成 React hook，并挂载最终组件树。 | 依赖方向是 Host 状态 → Remote 传输 → Client model → UI adapter → Conversation 或 presentation → Slots → React。用户操作通过 callback 反向进入注入的 Client service 或生成的 Remote namespace。Presentation component 绝不接收 Cordis `ctx`、transport object 或其他功能插件的实现。 @@ -41,9 +41,9 @@ Connection 拥有 request correlation、`/api` carrier、trust check、Host desc - `ClientSessions` 提供 `ctx.sessions`，拥有 Session scope 与稳定的 `SessionBinding` object，并投影选中的 list state。 - `SessionManager` 拥有 list baseline、实时 list/control update、惰性 Session instance、queue、projection store、subagent catalog，以及 pull 与后到 update 之间的冲突顺序。 -- 每个 `Session` 拥有一段连续 event window、pagination、follow、prompt/control state 与供 adapter 消费的 observable snapshot。 +- 每个 `Session` 拥有一段由 `SessionEventLikeEntry` value 表示的连续逻辑 event window、pagination、follow、prompt/control state 与供 adapter 消费的 observable snapshot。 -持久 event 路径打开 `follow()`，其首帧包含当前 header、tail page、cursor 与完整 projection baseline。每个物理 generation 都根据该 snapshot 原子替换保留窗口，随后按 seq append 实时 event。`page()` 只用于更早历史与 gap repair。瞬态 control stream 每代以完整 baseline 开始，随后应用 queue、job 与 projection update。 +持久 event 路径打开 `follow()`，其首帧包含当前 header、tail page、cursor 与完整 projection baseline。历史 record 带有显式 `event` 或 `chunks` 判别字段和字段对齐的内部 `event`；journal 先校验每条 record 的逻辑 seq 闭区间，Client 再直接把这些 record 保留为 `SessionEventLikeEntry`，无需逐 record 转换。每个物理 generation 都根据该 snapshot 原子替换保留窗口，随后按 seq append 标准实时 event。`page()` 只用于更早历史与 gap repair。瞬态 control stream 每代以完整 baseline 开始，随后应用 queue、job 与 projection update。 ### Workspaces @@ -55,7 +55,7 @@ Connection 拥有 request correlation、`/api` carrier、trust check、Host desc `ui-session` 安装 `session` scope adapter，并提供 `useSessions`、`useSession`、`sessionId` 和 `useProjection`。领域 adapter 可以继续添加标准 source，但不会把 React hook 放进 model object。 -`ui-conversation` 对每个 `SessionBinding.eventSource` 只绑定一次。它的 event registry 把原始持久 event 关联成稳定的业务 Context，view registry 则 materialize target snapshot。`ui-chat` 与 `ui-trajectory` 分别注册自己的 Definition 和 builder：它们可以解释同一 event family，但不会导入或共享彼此的最终 display model。Shell 选择一个已注册 view，再通过标准 hook 与 Slot 交付其 snapshot。[Conversation](conversation.zh.md)定义 Context identity、replay、Location data、target builder 与 keyed renderer。 +`ui-conversation` 对每个 `SessionBinding.eventSource` 只绑定一次。它的 event registry 把标准 event 与 Client-only `chunkrow/*` 历史 event 关联成稳定的业务 Context，view registry 则 materialize target snapshot。packed run 在 replay 全程保持为单个 input 与 Match；Chat Assistant、Trajectory Assistant 和 Turn Tail 是解释它的三个内建 Definition。`ui-chat` 与 `ui-trajectory` 分别注册自己的 Definition 和 builder：它们可以解释同一 event family，但不会导入或共享彼此的最终 display model。Shell 选择一个已注册 view，再通过标准 hook 与 Slot 交付其 snapshot。[Conversation](conversation.zh.md)定义 Context identity、replay、Location data、target builder 与 keyed renderer。 `ui-slots` 提供类型化 registry 与 lifecycle ledger；`ui-renderer` 是唯一通过 `useSyncExternalStore` 绑定裸 observable、拥有 React context 并渲染 root tree 的包。功能 component 通过推导出的 props 接收 framework hook、owner prop、store action 与显式 injection。[Web Client Slots](slots.zh.md)列出这些输入、扩展 API 与当前 Slot 层级。 @@ -63,7 +63,7 @@ Connection 拥有 request correlation、`/api` carrier、trust check、Host desc | 路径 | 顺序 | |---|---| -| 持久 Session 展示 | Host Session log → Remote `follow` 加 `page` → Client `Session` event window → Conversation Context → target snapshot（`chat`、`trajectory` 或其他已注册 target）→ Slot view → React | +| 持久 Session 展示 | Host Session log → packed Remote `follow`/`page` 历史 → Client `SessionEventLikeEntry` window → Conversation Context → target snapshot（`chat`、`trajectory` 或其他已注册 target）→ Slot view → React | | 瞬态 Session control | Host control baseline → Remote snapshot stream → `SessionManager` queue/job/projection store → Session 与 list snapshot → 标准 hook → component | | Workspace 状态 | Host Workspace baseline 与 increment → `ClientWorkspaceModel` → `ctx.workspaces.list` → `useWorkspaces` → sidebar、hero 与 navigation entry | | scoped interaction | Host Cordis waterfall → API Remotes `$events` → Session Context 上的 `ctx.remote.$on()` → 所属 UI 包 → result 或 `next()` | @@ -75,7 +75,7 @@ Connection 拥有 request correlation、`/api` carrier、trust check、Host desc 恢复方式由数据语义决定： -- 持久 Session journal 根据每个 generation 的 opening snapshot 替换窗口；`page()` 提供更早历史并修复后续 seq gap。 +- 持久 Session journal 校验逻辑 seq range，并根据每个 generation 的 opening snapshot 替换窗口；`page()` 提供更早历史并修复后续 range gap。 - Session control 与 Workspace stream 在断开期间保留最后一次发布的值，再用新的 opening baseline 原子替换。 - 普通 forwarded notification 不会 replay。需要可靠恢复的 stateful domain 必须提供 baseline、cursor 或显式 query；scoped waterfall 保留自身的 request lifetime。 diff --git a/knip.json b/knip.json index 8d53876de8..59b4ea9e20 100644 --- a/knip.json +++ b/knip.json @@ -91,6 +91,14 @@ ] }, "packages/client/ui-conversation": { + "entry": [ + "tests/**/*.spec.{ts,tsx}", + "tests/**/*.perf.client.ts" + ], + "project": [ + "src/**/*.{ts,tsx}", + "tests/**/*.{ts,tsx}" + ], "ignoreDependencies": [ "@deepseek-ai/dsh-client-ui-workspace" ] diff --git a/packages/api/gateway/README.i18n.yaml b/packages/api/gateway/README.i18n.yaml index cfeead8e18..b0a004e667 100644 --- a/packages/api/gateway/README.i18n.yaml +++ b/packages/api/gateway/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/api/gateway/README.md -README.md: 2546b0c4e54ea106c9203ce419027fe8253c7ca5 -README.zh.md: 9281519cda422137c6fd08ff6680ba0d57902913 +README.md: 1c3860ec836bcbefd26b04dca76b56955847c755 +README.zh.md: ca3d9f75d5f226a21c44ba59b1befcbe5f321bac diff --git a/packages/api/gateway/README.md b/packages/api/gateway/README.md index 2546b0c4e5..1c3860ec83 100644 --- a/packages/api/gateway/README.md +++ b/packages/api/gateway/README.md @@ -24,7 +24,7 @@ Host composition can register one application event source through `registerRemo Each unary call validates positional inputs, constructs the descriptor's exact named `args`, and sends it through `ctx.connection.rpc.call('/api', endpoint, ...)`. A generated stream method returns an `AsyncIterable` and opens one logical stream through an in-process Connection carrier when available, otherwise through the shared Gateway WebSocket. Generated cancellation-aware methods accept a final optional `AbortSignal`; the Client combines it with the contribution mount lifetime before invoking the carrier. Unary results and every stream item are validated before reaching application code. Withdrawing a contribution removes its descriptors and methods together, aborts in-flight calls and streams, and makes retained method handles reject. -`ctx.remote.$stream()` returns a single-consumer `RemoteStream` spanning physical carrier generations. It permits one immediate retry while the Host remains available, otherwise waits for the next connected Host generation, and annotates each item with its physical generation. The domain consumer validates and accepts each generation's opening value; business and protocol failures remain terminal. `RemoteSnapshotStream` adds one opening snapshot followed by deltas, while `RemoteJournalStream` adds follow-before-page opening, cursor deduplication, pagination, reconnect catch-up, and gap repair. Disposing any stream cancels its requests and resolves after the active iterator is fully stopped. +`ctx.remote.$stream()` returns a single-consumer `RemoteStream` spanning physical carrier generations. It permits one immediate retry while the Host remains available, otherwise waits for the next connected Host generation, and annotates each item with its physical generation. The domain consumer validates and accepts each generation's opening value; business and protocol failures remain terminal. `RemoteSnapshotStream` adds one opening snapshot followed by deltas. `RemoteJournalStream` adds follow-before-page opening, pagination, reconnect catch-up, and gap repair over domain-defined inclusive entry ranges; it removes complete duplicates and rejects gaps, inverted ranges, and partial overlaps. Disposing any stream cancels its requests and resolves after the active iterator is fully stopped. `ctx.remote.$on()` subscribes to one forwarded Host event. Its legal keys are exactly the Host assembly's forwarding selection, and the listener type is the owning package's own Cordis `Events` declaration, so no second signature can drift from it. Each subscription belongs to the calling fiber and disappears with it. The Client Remote service registers the `$events` pump as a Connection generation source when it activates, whether or not any `$on` listener exists. Browsers use Remote mux, while in-process compositions use `connection.rpc.open`; the `ready` item and `host.describe` jointly establish a Connection generation. Carrier failure, Remote stream failure, unexpected normal completion, a non-ready opening item, or a malformed event item ends that generation and lets Connection reopen it after backoff. Ordinary notifications run in registration order and isolate listener failures. Agent-scoped waterfalls let a listener return a result, call `next()`, or reject; Gateway returns that outcome through the existing HTTP unary carrier. diff --git a/packages/api/gateway/README.zh.md b/packages/api/gateway/README.zh.md index 9281519cda..ca3d9f75d5 100644 --- a/packages/api/gateway/README.zh.md +++ b/packages/api/gateway/README.zh.md @@ -24,7 +24,7 @@ Host 组合可通过 `registerRemoteEvents()` 注册唯一的应用事件 source 每次一元调用都会校验位置参数，构造与描述符完全匹配的具名 `args`，再通过 `ctx.connection.rpc.call('/api', endpoint, ...)` 发送。生成的流方法返回 `AsyncIterable`，并在进程内 Connection 载体可用时通过它打开逻辑流，否则通过共享的 Gateway WebSocket 打开。生成的支持取消的方法接受最后一个可选 `AbortSignal`；Client 会在调用载体前将它与贡献项的挂载生命周期合并。一元结果和每个流项都经过校验后才会交给应用代码。撤回贡献项会同时移除其描述符和方法、中止正在进行的调用与流，并使外部仍持有的方法句柄在调用时返回拒绝。 -`ctx.remote.$stream()` 返回跨越多个物理载体代次的单消费方 `RemoteStream`。Host 仍在线时，它允许一次立即重试；Host 离线时，它等待下一代连接，并为每个流项标注物理代次。领域消费方校验并接受各代次的 opening value；业务与协议错误仍然终止流。`RemoteSnapshotStream` 在此之上规定每代由一个 opening snapshot 和后续 delta 组成，`RemoteJournalStream` 则提供 follow-before-page、cursor 去重、分页、重连追赶与缺口修复。dispose 任一种 stream 都会取消其请求，并在活动 iterator 完全停止后完成。 +`ctx.remote.$stream()` 返回跨越多个物理载体代次的单消费方 `RemoteStream`。Host 仍在线时，它允许一次立即重试；Host 离线时，它等待下一代连接，并为每个流项标注物理代次。领域消费方校验并接受各代次的 opening value；业务与协议错误仍然终止流。`RemoteSnapshotStream` 在此之上规定每代由一个 opening snapshot 和后续 delta 组成。`RemoteJournalStream` 基于领域提供的 entry 闭区间提供 follow-before-page、分页、重连追赶与缺口修复；它丢弃完整重复项，并拒绝缺口、倒置区间和部分重叠。dispose 任一种 stream 都会取消其请求，并在活动 iterator 完全停止后完成。 `ctx.remote.$on()` 订阅一条被转发的 Host 事件。它的合法键恰好等于 Host 装配声明的转发选择，listener 类型就是事件所属包自己的 Cordis `Events` 声明，因此不存在会与之漂移的第二份签名。每个订阅归属发起调用的 fiber，并随该 fiber 一起消失。Client Remote 服务激活时就把 `$events` pump 注册为 Connection generation source，因此即使当前无 `$on` 订阅，它也会在 Connection 循环启动时打开。浏览器使用 Remote mux，进程内组合使用 `connection.rpc.open`；`ready` 项与 `host.describe` 共同建立一个 Connection generation。物理 carrier 失败、Remote stream error、意外正常结束、非 ready 首项或畸形事件项都会终止该 generation，由 Connection 退避后重开。普通通知按注册顺序运行并隔离 listener 失败；Agent-scoped waterfall 允许 listener 返回结果、调用 `next()` 或拒绝，Gateway 再通过现有 HTTP 一元载体回送该结果。 diff --git a/packages/api/gateway/src/client/journal-stream.ts b/packages/api/gateway/src/client/journal-stream.ts index 306779ba94..7a6f2e8166 100644 --- a/packages/api/gateway/src/client/journal-stream.ts +++ b/packages/api/gateway/src/client/journal-stream.ts @@ -50,8 +50,10 @@ export interface RemoteJournalStreamOptions { readonly entries: (page: Page) => readonly Entry[] /** Read whether an older page exists. */ readonly hasMore: (page: Page) => boolean - /** Read one entry's durable cursor. */ - readonly cursor: (entry: Entry) => Cursor + /** Read the inclusive first durable cursor covered by one entry. */ + readonly first: (entry: Entry) => Cursor + /** Read the inclusive final cursor, which must not precede the first. */ + readonly last: (entry: Entry) => Cursor /** Compare two cursors. */ readonly compare: (left: Cursor, right: Cursor) => number /** Test whether the right cursor immediately follows the left cursor. */ @@ -175,15 +177,15 @@ export abstract class RemoteJournalStream this.options.compare(this.options.cursor(entry), before) < 0) + : entries.filter(entry => this.options.compare(this.options.first(entry), before) < 0) const tail = accepted.at(-1) if (tail !== undefined && before !== undefined - && !this.options.follows(this.options.cursor(tail), before)) { + && !this.options.follows(this.options.last(tail), before)) { this.options.publish({ type: 'prepend', page, entries: [], hasMore: false }) throw new Error(`${this.options.name} history page is discontinuous`) } const first = accepted[0] - if (first !== undefined) this.firstCursor = this.options.cursor(first) + if (first !== undefined) this.firstCursor = this.options.first(first) this.options.publish({ type: 'prepend', page, @@ -268,7 +270,7 @@ export abstract class RemoteJournalStream, iterator: AsyncIterator>, ): Promise { - const cursor = this.options.cursor(entry) + const { first, last: cursor } = this.entryRange(entry) const last = this.lastCursor as Cursor if (this.options.compare(cursor, last) <= 0) return - if (!this.options.follows(last, cursor)) { + if (this.options.compare(first, last) <= 0) { + throw new Error(`${this.options.name} emitted a partially overlapping entry`) + } + if (!this.options.follows(last, first)) { const request = this.repairPageRequest() const superseded = await this.replaceThrough( request, @@ -302,7 +307,7 @@ export abstract class RemoteJournalStream ( - this.options.compare(this.options.cursor(left), this.options.cursor(right)) + this.options.compare(this.options.first(left), this.options.first(right)) )) let tail = this.tailCursor(entries) for (const entry of sorted) { - const cursor = this.options.cursor(entry) - if (this.options.compare(cursor, tail) <= 0) continue - if (!this.options.follows(tail, cursor)) return undefined + const first = this.options.first(entry) + const last = this.options.last(entry) + if (this.options.compare(last, tail) <= 0) continue + if (this.options.compare(first, tail) <= 0) { + throw new Error(`${this.options.name} replacement contains a partially overlapping entry`) + } + if (!this.options.follows(tail, first)) return undefined entries.push(entry) - tail = cursor + tail = last } return entries } @@ -452,7 +462,7 @@ export abstract class RemoteJournalStream 0) result = candidate } return result @@ -495,22 +505,32 @@ export abstract class RemoteJournalStream 0) { + throw new Error(`${this.options.name} entry has an inverted cursor range`) + } + return { first, last } + } + private assertPageThrough(page: Page, through: Cursor): void { const tail = this.tailCursor(this.options.entries(page)) if (this.options.compare(tail, through) !== 0) { diff --git a/packages/api/gateway/tests/journal-stream.client.spec.ts b/packages/api/gateway/tests/journal-stream.client.spec.ts index cc364bbf51..0d134f3d99 100644 --- a/packages/api/gateway/tests/journal-stream.client.spec.ts +++ b/packages/api/gateway/tests/journal-stream.client.spec.ts @@ -12,6 +12,7 @@ import { interface Entry { readonly seq: number + readonly lastSeq?: number } interface Page { @@ -51,12 +52,20 @@ const AVAILABLE_CONNECTION = { const entries = (...seqs: number[]): Entry[] => seqs.map(seq => ({ seq })) +const rangedEntry = (first: number, last: number): Entry => ({ seq: first, lastSeq: last }) + const page = (marker: string, seqs: number[], hasMore = false): Page => ({ entries: entries(...seqs), hasMore, marker, }) +const rangedPage = (marker: string, values: Entry[], hasMore = false): Page => ({ + entries: values, + hasMore, + marker, +}) + const STREAM_FACTORY = { $stream(options: RemoteStreamOptions): RemoteStream { return new RemoteStream(AVAILABLE_CONNECTION, options) @@ -80,7 +89,8 @@ class FixtureJournal extends RemoteJournalStream value.entries, hasMore: value => value.hasMore, - cursor: entry => entry.seq, + first: entry => entry.seq, + last: entry => entry.lastSeq ?? entry.seq, compare: (left, right) => left - right, follows: (left, right) => right === left + 1, publish: (change) => { changes.push(change) }, @@ -196,6 +206,40 @@ function controlledFactory( } describe('RemoteJournalStream', () => { + it('replaces from pages whose entries cover contiguous cursor ranges', async () => { + const snapshot = rangedPage( + 'ranged', + [rangedEntry(0, 2), rangedEntry(3, 5)], + true, + ) + const fixture = journalFixture( + [{ frames: [opened(5, snapshot)], hold: true }], + [], + ) + + await fixture.journal.open({}) + + expect(fixture.changes).toEqual([{ + type: 'replace', + page: snapshot, + entries: snapshot.entries, + hasMore: true, + }]) + await fixture.journal.dispose() + }) + + it('rejects an inverted cursor range', async () => { + const fixture = journalFixture( + [{ frames: [opened(2, rangedPage('inverted', [rangedEntry(3, 2)]))], hold: true }], + [], + ) + + await expect(fixture.journal.open({})).rejects.toThrow( + 'fixture journal entry has an inverted cursor range', + ) + expect(fixture.changes).toEqual([]) + }) + it('opens from the follow snapshot, removes overlap, appends live entries, and prepends history', async () => { const fixture = journalFixture( [{ @@ -288,6 +332,67 @@ describe('RemoteJournalStream', () => { await followed.journal.dispose() }) + it('prepends at the first cursor and rejects a partially overlapping ranged entry', async () => { + const initial = rangedPage('initial', [rangedEntry(4, 6)], true) + const older = rangedPage('older', [rangedEntry(0, 3)]) + const fixture = journalFixture( + [{ frames: [opened(6, initial)], hold: true }], + [older], + ) + + await fixture.journal.open({}) + await fixture.journal.prepend({ before: 4 }) + + expect(fixture.pageCursors).toEqual([6]) + expect(fixture.changes.at(-1)).toEqual({ + type: 'prepend', page: older, entries: older.entries, hasMore: false, + }) + await fixture.journal.dispose() + + const overlap = rangedPage('overlap', [rangedEntry(0, 4)], true) + const overlapping = journalFixture( + [{ frames: [opened(6, initial)], hold: true }], + [overlap], + ) + await overlapping.journal.open({}) + + await expect(overlapping.journal.prepend({ before: 4 })).rejects.toThrow( + 'history page is discontinuous', + ) + expect(overlapping.changes.at(-1)).toEqual({ + type: 'prepend', page: overlap, entries: [], hasMore: false, + }) + await overlapping.journal.dispose() + }) + + it('deduplicates complete ranged entries and rejects partial live overlap', async () => { + const initial = rangedPage('initial', [rangedEntry(0, 2)]) + const fixture = journalFixture( + [{ + frames: [ + opened(2, initial), + { type: 'entry', entry: rangedEntry(0, 2) }, + { type: 'entry', entry: rangedEntry(3, 5) }, + { type: 'entry', entry: rangedEntry(5, 7) }, + ], + hold: true, + }], + [], + ) + + await fixture.journal.open({}) + await vi.waitFor(() => { expect(fixture.failed).toHaveBeenCalledOnce() }) + + expect(fixture.changes).toHaveLength(2) + expect(fixture.changes.at(-1)).toEqual({ + type: 'append', entry: rangedEntry(3, 5), + }) + expect(fixture.failed.mock.calls[0]?.[0]).toMatchObject({ + message: 'fixture journal emitted a partially overlapping entry', + }) + await fixture.journal.dispose() + }) + it('repairs a replacement generation through one tail page and drops replay overlap', async () => { const lost = new RemoteStreamCarrierError('carrier lost') const fixture = journalFixture( @@ -392,6 +497,26 @@ describe('RemoteJournalStream', () => { await fixture.journal.dispose() }) + it('reports a page failure during live-gap repair', async () => { + const fixture = journalFixture( + [{ + frames: [ + opened(0, page('initial', [0])), + { type: 'entry', entry: { seq: 2 } }, + ], + hold: true, + }], + [() => Promise.reject(new Error('repair page failed'))], + ) + + await fixture.journal.open({}) + await vi.waitFor(() => { expect(fixture.failed).toHaveBeenCalledOnce() }) + + expect(fixture.failed.mock.calls[0]?.[0]).toMatchObject({ message: 'repair page failed' }) + expect(fixture.changes).toHaveLength(1) + await fixture.journal.dispose() + }) + it('replaces a superseded live-gap repair with the next generation', async () => { const gap = Promise.withResolvers() const fixture = journalFixture( @@ -543,6 +668,39 @@ describe('RemoteJournalStream', () => { await fixture.journal.dispose() }) + it('rejects a partially overlapping ranged entry queued during repair', async () => { + const firstLive = Promise.withResolvers() + const secondLive = Promise.withResolvers() + const secondConsumed = Promise.withResolvers() + const repair = Promise.withResolvers() + const fixture = journalFixture( + [{ + frames: [ + opened(1, page('initial', [0, 1])), + firstLive.promise, + secondLive.promise, + ], + hold: true, + afterFrame: (index) => { if (index === 2) secondConsumed.resolve(undefined) }, + }], + [repair.promise], + ) + + await fixture.journal.open({}) + firstLive.resolve({ type: 'entry', entry: rangedEntry(3, 5) }) + await vi.waitFor(() => { expect(fixture.pageCursors).toEqual([5]) }) + secondLive.resolve({ type: 'entry', entry: rangedEntry(5, 7) }) + await secondConsumed.promise + repair.resolve(rangedPage('repair', [rangedEntry(0, 2), rangedEntry(3, 5)])) + + await vi.waitFor(() => { expect(fixture.failed).toHaveBeenCalledOnce() }) + expect(fixture.changes).toHaveLength(1) + expect(fixture.failed.mock.calls[0]?.[0]).toMatchObject({ + message: 'fixture journal replacement contains a partially overlapping entry', + }) + await fixture.journal.dispose() + }) + it('rejects when queued entries advance beyond the second repair page', async () => { const firstLive = Promise.withResolvers() const secondLive = Promise.withResolvers() diff --git a/packages/api/session-controller/README.i18n.yaml b/packages/api/session-controller/README.i18n.yaml index 31c76de3e1..d417370290 100644 --- a/packages/api/session-controller/README.i18n.yaml +++ b/packages/api/session-controller/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/api/session-controller/README.md -README.md: 7631e1623f90f9349eca78bc76d46505d13d2e0e -README.zh.md: 7a733b45b1cdbb17096d1e76bb25b54d3bdc0e06 +README.md: 510f336c76dd80ed01bdd2bd4a364106f418831f +README.zh.md: 4503a8f9d0bcfc7f669f00cbc4db69e0d3efd3cd diff --git a/packages/api/session-controller/README.md b/packages/api/session-controller/README.md index 7631e1623f..510f336c76 100644 --- a/packages/api/session-controller/README.md +++ b/packages/api/session-controller/README.md @@ -4,11 +4,11 @@ English | [中文](README.zh.md) `@deepseek-ai/dsh-api-session-controller` owns the Host `ctx.sessionController` service and the generated Client `ctx.remote.session` namespace. It serves Session list, search, creation, model selection, rename, fork, prompt, attachment, queue, cancellation, message-aligned history, live log following, and Host-wide control state. -History pages and follow event frames carry only raw `SessionWireEvent` values. Tool arguments, result content, failures, and `tool/result.data.meta` pass through unchanged; the controller does not resolve a Tool definition, run a presenter, or attach UI data. +History pages and follow opening snapshots carry a discriminated `SessionHistoryRecord`. Both variants use `{ type, event }`: `type: 'event'` carries one raw `SessionWireEvent`, while `type: 'chunks'` carries one lossless `ChunkRowEvent` for consecutive same-block `assistant/chunk` deltas. Both inner values expose `type`, `seq`, `time`, and `data`, so the Client retains each accepted record as one `SessionEventLikeEntry` without record-by-record conversion. A packed event's `seq` and `time` identify its first member, and `data` retains the fragment and timestamp-gap arrays. Live follow frames remain individual `event` records. Tool arguments, result content, failures, and `tool/result.data.meta` pass through unchanged; the controller does not resolve a Tool definition, run a presenter, or attach UI data. Each endpoint states its activation policy. List, search, attachment, history pages, and log following can inspect persistence without activating an Agent; queue mutation and cancellation require the corresponding live state; model, rename, and prompt commands may explicitly resume an ordinary Session. Create and fork are the only operations that create a new Agent. The service applies one preset-aware resume policy and subagent ownership fence to its own methods and to the Typert Agent and Session lookups used by other Remote namespaces. -The Client adapter exposes `SessionEventStream`, a Gateway `RemoteJournalStream` bound to one ordinary or direct-subagent address. It opens follow before the initial page, publishes only contiguous `replace`, `prepend`, and `append` changes, and repairs reconnect or sequence gaps through a tail page. A business, persistence, or unresolved continuity failure terminates the stream, while only physical carrier loss selects automatic resumption. `SessionControlStream` is a Gateway `RemoteSnapshotStream`; every generation opens with a complete process-local baseline, so reconnect replaces queue, jobs, and projection state instead of treating transient values as durable events. +The Client adapter exposes `SessionEventStream`, a Gateway `RemoteJournalStream` bound to one ordinary or direct-subagent address. It opens follow before the initial page, publishes only contiguous `replace`, `prepend`, and `append` changes, and repairs reconnect or sequence gaps through a tail page. Ordinary records cover `[event.seq, event.seq]`; packed rows cover `[event.seq, event.seq + memberCount - 1]`. A business, persistence, or unresolved continuity failure terminates the stream, while only physical carrier loss selects automatic resumption. `SessionControlStream` is a Gateway `RemoteSnapshotStream`; every generation opens with a complete process-local baseline, so reconnect replaces queue, jobs, and projection state instead of treating transient values as durable events. ## Model Experience diff --git a/packages/api/session-controller/README.zh.md b/packages/api/session-controller/README.zh.md index 7a733b45b1..4503a8f9d0 100644 --- a/packages/api/session-controller/README.zh.md +++ b/packages/api/session-controller/README.zh.md @@ -4,11 +4,11 @@ `@deepseek-ai/dsh-api-session-controller` 拥有 Host 的 `ctx.sessionController` 服务和生成的 Client `ctx.remote.session` namespace。它提供 Session 列表、搜索、创建、模型选择、重命名、fork、prompt、附件、queue、取消、按消息对齐的历史、live 日志跟随和 Host 范围 control 状态。 -历史页与 follow event frame 只携带原始 `SessionWireEvent`。工具参数、结果内容、失败信息和 `tool/result.data.meta` 原样通过；controller 不解析 Tool definition、不运行 presenter，也不附加 UI 数据。 +历史页与 follow opening snapshot 携带带判别字段的 `SessionHistoryRecord`。两个分支都使用 `{ type, event }`：`type: 'event'` 携带一个原始 `SessionWireEvent`，`type: 'chunks'` 则携带一个由连续且属于同一 block 的 `assistant/chunk` delta 组成的无损 `ChunkRowEvent`。两种内部值都公开 `type`、`seq`、`time` 与 `data`，因此 Client 无需逐 record 转换，就能把每条已接受 record 保留为一个 `SessionEventLikeEntry`。packed event 的 `seq` 与 `time` 表示首成员，`data` 保留 fragment 与 timestamp-gap 数组。实时 follow frame 继续携带单个 `event` record。工具参数、结果内容、失败信息和 `tool/result.data.meta` 原样通过；controller 不解析 Tool definition、不运行 presenter，也不附加 UI 数据。 每个 endpoint 都声明自己的激活策略。列表、搜索、附件、历史页和日志跟随可以在不激活 Agent 的情况下检查 persistence；queue 变更和取消要求对应 live 状态仍然存在；模型、重命名和 prompt 命令可以显式恢复普通 Session。只有 create 和 fork 会创建新 Agent。该服务把同一套感知 preset 的恢复策略和 subagent ownership fence 同时用于自身方法，以及其他 Remote namespace 使用的 Typert Agent 与 Session lookup。 -Client adapter 提供 `SessionEventStream`，即绑定到一个普通 Session 或 direct subagent address 的 Gateway `RemoteJournalStream`。它在读取首个 page 前打开 follow，只发布连续的 `replace`、`prepend` 和 `append` 变更，并通过 tail page 修复重连或 seq 缺口。业务、persistence 或无法恢复的连续性错误会终止 stream，只有物理载体断开才触发自动恢复。`SessionControlStream` 是 Gateway `RemoteSnapshotStream`；每代都以完整的进程本地 baseline 开始，因此重连会替换 queue、jobs 和 projection 状态，而不会把瞬态值当作 durable event。 +Client adapter 提供 `SessionEventStream`，即绑定到一个普通 Session 或 direct subagent address 的 Gateway `RemoteJournalStream`。它在读取首个 page 前打开 follow，只发布连续的 `replace`、`prepend` 和 `append` 变更，并通过 tail page 修复重连或 seq 缺口。普通 record 覆盖 `[event.seq, event.seq]`，packed row 覆盖 `[event.seq, event.seq + memberCount - 1]`。业务、persistence 或无法恢复的连续性错误会终止 stream，只有物理载体断开才触发自动恢复。`SessionControlStream` 是 Gateway `RemoteSnapshotStream`；每代都以完整的进程本地 baseline 开始，因此重连会替换 queue、jobs 和 projection 状态，而不会把瞬态值当作 durable event。 ## 模型体验 diff --git a/packages/api/session-controller/src/client/contract/events.ts b/packages/api/session-controller/src/client/contract/events.ts index 2f8bc48f82..39ce09ccab 100644 --- a/packages/api/session-controller/src/client/contract/events.ts +++ b/packages/api/session-controller/src/client/contract/events.ts @@ -1,10 +1,22 @@ /** Observable contiguous Session event window consumed by domain assemblers. */ import { notifySubscribers, type ObservableSnapshot } from '@deepseek-ai/dsh-client-store' -import type { SessionEventEntry } from '../../types.ts' +import type { SessionEvent } from '@deepseek-ai/dsh-session/types' +import type { ChunkRowEvent } from '../../types.ts' + +/** Standard Session event or compact historical Assistant run. */ +export type SessionEventLike = SessionEvent | ChunkRowEvent + +/** Client history entry retaining its coarse transport discriminator. */ +export type SessionEventLikeEntry = + | { readonly type: 'event'; readonly event: SessionEvent } + | { readonly type: 'chunks'; readonly event: ChunkRowEvent } + +/** Scalar live entry accepted by append-only Client paths. */ +export type SessionLiveEventEntry = Extract interface EventWindowLeaf { readonly kind: 'leaf' - readonly entries: readonly SessionEventEntry[] + readonly entries: readonly SessionEventLikeEntry[] readonly length: number } @@ -17,7 +29,7 @@ interface EventWindowConcat { type EventWindowNode = EventWindowLeaf | EventWindowConcat -function leaf(entries: readonly SessionEventEntry[]): EventWindowLeaf { +function leaf(entries: readonly SessionEventLikeEntry[]): EventWindowLeaf { return { kind: 'leaf', entries, length: entries.length } } @@ -25,9 +37,9 @@ function concat(left: EventWindowNode, right: EventWindowNode): EventWindowConca return { kind: 'concat', left, right, length: left.length + right.length } } -function materialize(node: EventWindowNode): readonly SessionEventEntry[] { +function materialize(node: EventWindowNode): readonly SessionEventLikeEntry[] { if (node.kind === 'leaf') return node.entries - const entries = new Array(node.length) + const entries = new Array(node.length) const pending: EventWindowNode[] = [node] let index = 0 while (pending.length > 0) { @@ -50,7 +62,7 @@ function windowSnapshot( revision: number, change: SessionEventChange, ): SessionEventWindow { - let entries: readonly SessionEventEntry[] | undefined + let entries: readonly SessionEventLikeEntry[] | undefined return { get entries() { entries ??= materialize(node) @@ -64,13 +76,13 @@ function windowSnapshot( /** Exact delta that produced the latest event-window revision. */ export type SessionEventChange = - | { readonly kind: 'replace'; readonly entries: readonly SessionEventEntry[] } - | { readonly kind: 'prepend'; readonly entries: readonly SessionEventEntry[] } - | { readonly kind: 'append'; readonly entries: readonly SessionEventEntry[] } + | { readonly kind: 'replace'; readonly entries: readonly SessionEventLikeEntry[] } + | { readonly kind: 'prepend'; readonly entries: readonly SessionEventLikeEntry[] } + | { readonly kind: 'append'; readonly entries: readonly SessionLiveEventEntry[] } /** Current contiguous event window and its latest synchronous delta. */ export interface SessionEventWindow { - readonly entries: readonly SessionEventEntry[] + readonly entries: readonly SessionEventLikeEntry[] readonly hasMore: boolean readonly revision: number readonly change: SessionEventChange @@ -108,7 +120,7 @@ export class MutableSessionEventSource implements SessionEventSource { * @param entries - complete window. * @param hasMore - whether older history remains. */ - replace(entries: readonly SessionEventEntry[], hasMore: boolean): void { + replace(entries: readonly SessionEventLikeEntry[], hasMore: boolean): void { this.window = leaf(entries) this.publish(hasMore, { kind: 'replace', entries }) } @@ -118,7 +130,7 @@ export class MutableSessionEventSource implements SessionEventSource { * @param entries - newly loaded older entries. * @param hasMore - whether still older history remains. */ - prepend(entries: readonly SessionEventEntry[], hasMore: boolean): void { + prepend(entries: readonly SessionEventLikeEntry[], hasMore: boolean): void { this.window = concat(leaf(entries), this.window) this.publish(hasMore, { kind: 'prepend', entries }) } @@ -127,7 +139,7 @@ export class MutableSessionEventSource implements SessionEventSource { * Append one contiguous live entry. * @param entry - live tail entry. */ - append(entry: SessionEventEntry): void { + append(entry: SessionLiveEventEntry): void { const entries = [entry] this.window = concat(this.window, leaf(entries)) this.publish(this.snapshot.hasMore, { diff --git a/packages/api/session-controller/src/client/index.ts b/packages/api/session-controller/src/client/index.ts index 86735be6ea..7fa6ede0d0 100644 --- a/packages/api/session-controller/src/client/index.ts +++ b/packages/api/session-controller/src/client/index.ts @@ -43,7 +43,14 @@ export type { export type { ISession, ProjectionsFace, SessionFace } from './contract/session.ts' export type { ISessions } from './contract/sessions.ts' export { MutableSessionEventSource } from './contract/events.ts' -export type { SessionEventChange, SessionEventSource, SessionEventWindow } from './contract/events.ts' +export type { + SessionEventChange, + SessionEventLike, + SessionEventLikeEntry, + SessionEventSource, + SessionEventWindow, + SessionLiveEventEntry, +} from './contract/events.ts' export type { OpenState, PromptError, diff --git a/packages/api/session-controller/src/client/sessions/history-records.ts b/packages/api/session-controller/src/client/sessions/history-records.ts new file mode 100644 index 0000000000..77ed4ad980 --- /dev/null +++ b/packages/api/session-controller/src/client/sessions/history-records.ts @@ -0,0 +1,39 @@ +/** Client range access and type narrowing for aligned Session history records. */ + +import type { + SessionHistoryRecord, +} from '../../types.ts' +import type { SessionEventLikeEntry } from '../contract/events.ts' + +/** + * Narrow aligned wire records to their Client event types without allocation. + * @param records - validated history transport records. + * @returns the same record array with typed inner events. + */ +export function historyEntries( + records: readonly SessionHistoryRecord[], +): readonly SessionEventLikeEntry[] { + return records as unknown as readonly SessionEventLikeEntry[] +} + +/** + * Read the first logical sequence represented by one wire record. + * @param record - validated scalar event or packed Assistant delta run. + * @returns inclusive first Session sequence. + */ +export function historyRecordFirstSeq(record: SessionHistoryRecord): number { + return record.event.seq +} + +/** + * Read the final logical sequence represented by one wire record. + * @param record - validated scalar event or packed Assistant delta run. + * @returns inclusive final Session sequence. + */ +export function historyRecordLastSeq(record: SessionHistoryRecord): number { + if (record.type === 'event') return record.event.seq + const length = record.event.type === 'chunkrow/tool-call-chunks' + ? record.event.data.args.length + : record.event.data.texts.length + return record.event.seq + length - 1 +} diff --git a/packages/api/session-controller/src/client/sessions/session.ts b/packages/api/session-controller/src/client/sessions/session.ts index 7239e3149a..182d8514d9 100644 --- a/packages/api/session-controller/src/client/sessions/session.ts +++ b/packages/api/session-controller/src/client/sessions/session.ts @@ -7,7 +7,7 @@ import type { IApiClient, SubagentAddress, } from '@deepseek-ai/dsh-client-connection/client' import type { MessageId } from '@deepseek-ai/dsh-llm/brand' -import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session/types' +import type { SessionId } from '@deepseek-ai/dsh-session/types' import { SessionEventStream, sessionStreamFailure, @@ -18,7 +18,6 @@ import type { QueueAction, SessionAddress, SessionControlFrame, - SessionEventEntry, SessionQueuedItem, SessionRequestId, SessionError, @@ -30,6 +29,9 @@ import type { OpenState, PromptError, SessionSnapshot, } from '../contract/snapshot.ts' import { MutableSessionEventSource } from '../contract/events.ts' +import type { + SessionEventLikeEntry, SessionLiveEventEntry, +} from '../contract/events.ts' import { Notifier } from './notifier.ts' import type { RemoteResult } from '@deepseek-ai/dsh-typert-protocol' import type { SessionRemotes } from './remotes.ts' @@ -72,7 +74,6 @@ export interface SessionOptions { */ export class Session implements SessionFace { // ---- Window and derived state (all private; the snapshot is the only read API) ---- - private eventWindow: SessionEvent[] = [] private baseSeq = 0 private hasMore = false private openState: OpenState = 'cold' @@ -400,7 +401,6 @@ export class Session implements SessionFace { this.openPromise = null this.openState = 'cold' this.openError = null - this.eventWindow = [] this.baseSeq = 0 this.notifier.markDirty() await this.open() @@ -575,28 +575,25 @@ export class Session implements SessionFace { } /** Replace the complete contiguous window and apply page-owned projection metadata. */ - private installWindow(entries: readonly SessionEventEntry[], hasMore: boolean, projections?: ProjectionsBaseline): void { - this.eventWindow = entries.map(entry => entry.event as SessionEvent) - this.baseSeq = this.eventWindow[0]?.seq ?? 0 + private installWindow(entries: readonly SessionEventLikeEntry[], hasMore: boolean, projections?: ProjectionsBaseline): void { + this.baseSeq = entries[0]?.event.seq ?? 0 this.hasMore = hasMore - if (this.eventWindow.some(event => event.type === 'turn/start')) this.firstPromptPendingTurn = false + if (entries.some(entry => entry.event.type === 'turn/start')) this.firstPromptPendingTurn = false if (projections !== undefined) this.projections.seed(projections) this.eventSource.replace(entries, hasMore) this.notifier.markDirty() } /** Prepend one stream-validated history page. */ - private prependWindow(entries: readonly SessionEventEntry[], hasMore: boolean): void { - this.eventWindow = [...entries.map(entry => entry.event as SessionEvent), ...this.eventWindow] - this.baseSeq = this.eventWindow[0]?.seq ?? 0 + private prependWindow(entries: readonly SessionEventLikeEntry[], hasMore: boolean): void { + this.baseSeq = entries[0]?.event.seq ?? this.baseSeq this.hasMore = hasMore this.eventSource.prepend(entries, hasMore) } /** Append one stream-validated live event. */ - private appendLive(entry: SessionEventEntry): boolean { - const event = entry.event as SessionEvent - this.eventWindow.push(event) + private appendLive(entry: SessionLiveEventEntry): boolean { + const event = entry.event const awaitingFirstTurn = this.firstPromptPendingTurn if (event.type === 'turn/start') this.firstPromptPendingTurn = false const queueChanged = this.queueMirror.acceptDurable(event) diff --git a/packages/api/session-controller/src/client/transport.ts b/packages/api/session-controller/src/client/transport.ts index 0e8ca83d28..48298268bb 100644 --- a/packages/api/session-controller/src/client/transport.ts +++ b/packages/api/session-controller/src/client/transport.ts @@ -14,11 +14,17 @@ import { import type { SessionAddress, SessionControlFrame, - SessionEventEntry, + SessionHistoryRecord, SessionPage, SessionPageRequest, SessionProjectionBaseline, } from '../types.ts' +import { + historyEntries, + historyRecordFirstSeq, + historyRecordLastSeq, +} from './sessions/history-records.ts' +import type { SessionEventLikeEntry, SessionLiveEventEntry } from './contract/events.ts' export { SESSION_SEARCH_RESULT_LIMIT, @@ -37,7 +43,33 @@ interface SessionJournalPage extends SessionPage { } /** One complete publication from the Session journal stream. */ -export type SessionJournalChange = RemoteJournalChange +export type SessionJournalChange = + | { + readonly type: 'replace' | 'prepend' + readonly page: SessionJournalPage + readonly entries: readonly SessionEventLikeEntry[] + readonly hasMore: boolean + } + | { readonly type: 'append'; readonly entry: SessionLiveEventEntry } + +function toSessionJournalChange( + change: RemoteJournalChange, +): SessionJournalChange { + switch (change.type) { + case 'replace': + case 'prepend': + return { ...change, entries: historyEntries(change.entries) } + case 'append': { + if (change.entry.type !== 'event') { + throw new Error('session live stream emitted a packed history record') + } + return { + type: 'append', + entry: change.entry as unknown as SessionLiveEventEntry, + } + } + } +} type SessionControlBaselineFrame = Extract type SessionControlDeltaFrame = Exclude @@ -100,7 +132,7 @@ export function createSessionControlStream( /** Gateway-owned event journal bound to one ordinary or direct-subagent Session address. */ export class SessionEventStream extends RemoteJournalStream< SessionJournalPage, - SessionEventEntry, + SessionHistoryRecord, number, ClientSessionPageRequest > { @@ -117,12 +149,13 @@ export class SessionEventStream extends RemoteJournalStream< super(remote, { name: 'session event stream', emptyCursor: -1, - entries: page => page.events, + entries: page => page.records, hasMore: page => page.hasMore, - cursor: entry => entry.event.seq, + first: historyRecordFirstSeq, + last: historyRecordLastSeq, compare: (left, right) => left - right, follows: (left, right) => right === left + 1, - publish: options.publish, + publish: (change) => { options.publish(toSessionJournalChange(change)) }, ...(options.carrierFailed === undefined ? {} : { carrierFailed: options.carrierFailed }), @@ -134,7 +167,7 @@ export class SessionEventStream extends RemoteJournalStream< protected override async * follow( request: ClientSessionPageRequest, signal: AbortSignal, - ): AsyncIterable> { + ): AsyncIterable> { for await (const frame of this.remote.session.follow({ address: this.address, ...(request.maxMessages === undefined ? {} : { maxMessages: request.maxMessages }), @@ -144,15 +177,14 @@ export class SessionEventStream extends RemoteJournalStream< type: 'opened', cursor: frame.cursor, page: { - events: frame.events, + records: frame.records, hasMore: frame.hasMore, projections: frame.projections, }, } continue } - const { type: _type, ...entry } = frame - yield { type: 'entry', entry } + yield { type: 'entry', entry: frame } } } diff --git a/packages/api/session-controller/src/history.ts b/packages/api/session-controller/src/history.ts index a1fb6b541b..d78509e49b 100644 --- a/packages/api/session-controller/src/history.ts +++ b/packages/api/session-controller/src/history.ts @@ -2,15 +2,18 @@ import type { Context } from '@deepseek-ai/cordis' import { isAppendSurfaceEvent } from '@deepseek-ai/dsh-session' +import { isChunkRow, packChunkRuns, type ChunkRow } from '@deepseek-ai/dsh-session/chunk-rows' import type { SessionEvent, SessionHeader, SessionId } from '@deepseek-ai/dsh-session' import { SessionQueryError, type SessionObservation } from '@deepseek-ai/dsh-session-query' import type {} from '@deepseek-ai/dsh-subagent' import { TypertRemoteFailure } from '@deepseek-ai/dsh-typert-protocol' import type { SessionAddress, + SessionChunkRun, SessionEventEntry, SessionFollowRequest, SessionFollowFrame, + SessionHistoryRecord, SessionPage, SessionPageRequest, SessionProjectionBaseline, @@ -68,9 +71,9 @@ export class SessionHistoryController { request.maxMessages ?? DEFAULT_MAX_MESSAGES, request.throughSeq, ) - const entries = page.events.map(entryFor) + const records = pageRecords(page.events) return { - events: entries, + records, hasMore: page.hasMore, } } @@ -128,7 +131,7 @@ export class SessionHistoryController { type: 'snapshot', header: source.header, cursor, - events: page.events.map(entryFor), + records: pageRecords(page.events), hasMore: page.hasMore, projections: source.projections === undefined ? { asOfSeq: cursor, values: {} } @@ -155,7 +158,7 @@ export class SessionHistoryController { reject('internal', `session event stream skipped seq ${String(nextSeq)}`, {}) } nextSeq++ - yield { type: 'event', ...entryFor(item) } + yield entryFor(item) } } finally { this.closeFollowers.delete(close) @@ -313,7 +316,35 @@ function paginate( function entryFor(event: SessionEvent): SessionEventEntry { return { + type: 'event', // Session.append validates and freezes event data as JSON before publication. event: event as unknown as SessionWireEvent, } } + +function chunkEntryFor(row: ChunkRow): SessionChunkRun { + switch (row.type) { + case 'text-chunks': + return { + type: 'chunks', + event: { type: 'chunkrow/text-chunks', seq: row.seq0, time: row.time0, data: row.data }, + } + case 'reasoning-chunks': + return { + type: 'chunks', + event: { type: 'chunkrow/reasoning-chunks', seq: row.seq0, time: row.time0, data: row.data }, + } + case 'tool-call-chunks': + return { + type: 'chunks', + event: { type: 'chunkrow/tool-call-chunks', seq: row.seq0, time: row.time0, data: row.data }, + } + } +} + +/** Encode one bounded logical page without changing its pagination cut. */ +function pageRecords(events: readonly SessionEvent[]): SessionHistoryRecord[] { + return packChunkRuns(events).map(record => isChunkRow(record) + ? chunkEntryFor(record) + : entryFor(record)) +} diff --git a/packages/api/session-controller/src/types.ts b/packages/api/session-controller/src/types.ts index 33e6d0ef46..5f02c41765 100644 --- a/packages/api/session-controller/src/types.ts +++ b/packages/api/session-controller/src/types.ts @@ -6,6 +6,7 @@ import type { import type { Branded } from '@deepseek-ai/dsh-brand' import type { MessageId } from '@deepseek-ai/dsh-llm/brand' import type { ContentBlock } from '@deepseek-ai/dsh-llm/types' +import type { ChunkRow } from '@deepseek-ai/dsh-session/chunk-rows' import type { JsonValue, SessionHeader, SessionId, SurfaceOp } from '@deepseek-ai/dsh-session/types' import type { SessionProjectionMap } from '@deepseek-ai/dsh-session-projection/types' import type { JobId } from '@deepseek-ai/dsh-jobs/brand' @@ -361,9 +362,29 @@ export type SessionAddress = /** One raw Session event in the Remote journal. */ export interface SessionEventEntry { + readonly type: 'event' readonly event: SessionWireEvent } +/** Event-shaped wire representation of one packed chunk row. */ +export type ChunkRowEvent = { + [Kind in ChunkRow['type']]: { + readonly type: `chunkrow/${Kind}` + readonly seq: number + readonly time: number + readonly data: Extract['data'] + } +}[ChunkRow['type']] + +/** One lossless run of consecutive Assistant delta events in a history page. */ +export interface SessionChunkRun { + readonly type: 'chunks' + readonly event: ChunkRowEvent +} + +/** One history-page record: a raw event or a packed Assistant delta run. */ +export type SessionHistoryRecord = SessionEventEntry | SessionChunkRun + /** Session event wire form; durable readers own recognition of merge-extensible event names. */ export interface SessionWireEvent { readonly type: string @@ -392,7 +413,7 @@ export interface SessionFollowRequest { /** One contiguous backwards page of a Session log. */ export interface SessionPage { - readonly events: readonly SessionEventEntry[] + readonly records: readonly SessionHistoryRecord[] readonly hasMore: boolean } @@ -402,11 +423,11 @@ export type SessionFollowFrame = readonly type: 'snapshot' readonly header: SessionHeader readonly cursor: number - readonly events: readonly SessionEventEntry[] + readonly records: readonly SessionHistoryRecord[] readonly hasMore: boolean readonly projections: SessionProjectionBaseline } - | ({ readonly type: 'event' } & SessionEventEntry) + | SessionEventEntry /** One pending inbox occurrence in the authoritative queue snapshot. */ export interface SessionQueuedItem { diff --git a/packages/api/session-controller/tests/client-contract.client.spec.ts b/packages/api/session-controller/tests/client-contract.client.spec.ts index 9b3a7fa015..789fe04d6d 100644 --- a/packages/api/session-controller/tests/client-contract.client.spec.ts +++ b/packages/api/session-controller/tests/client-contract.client.spec.ts @@ -1,16 +1,17 @@ -import type { SessionEventEntry } from '@deepseek-ai/dsh-api-session-controller/types' import { describe, expect, it, vi } from 'vitest' -import { MutableSessionEventSource } from '../src/client/contract/events.ts' +import { + MutableSessionEventSource, type SessionLiveEventEntry, +} from '../src/client/contract/events.ts' import { transportResult } from '../src/client/contract/result.ts' -function entry(seq: number): SessionEventEntry { +function entry(seq: number): SessionLiveEventEntry { return { + type: 'event', event: { - type: 'fixture/event', + type: 'turn/start', seq, time: seq, - data: { seq }, - ignorable: true, + data: { turn: seq }, }, } } diff --git a/packages/api/session-controller/tests/event-script.client.ts b/packages/api/session-controller/tests/event-script.client.ts index 6aba942774..4722192353 100644 --- a/packages/api/session-controller/tests/event-script.client.ts +++ b/packages/api/session-controller/tests/event-script.client.ts @@ -5,6 +5,11 @@ import { // host emits; only the fields the object layer reads). import type { ContentBlock } from '@deepseek-ai/dsh-llm/types' import type { SessionEvent } from '@deepseek-ai/dsh-session/types' +import type { + SessionEventEntry, + SessionPage, + SessionWireEvent, +} from '../src/types.ts' /** One text content block (local helper). */ const text = (t: string): ContentBlock[] => [{ type: 'text', text: t }] @@ -143,6 +148,14 @@ export function plainTurn(startSeq: number, turn: number, ask: string, answer: s } /** Wrap raw events in the journal envelope returned by history. */ -export function entries(events: readonly SessionEvent[]): { event: SessionEvent }[] { - return events.map(event => ({ event })) +export function entries(events: readonly SessionEvent[]): SessionEventEntry[] { + return events.map(event => ({ type: 'event', event: event as unknown as SessionWireEvent })) +} + +/** Build one view-less history response value. */ +export function historyValue(events: readonly SessionEvent[], hasMore = false): SessionPage { + return { + records: entries(events), + hasMore, + } } diff --git a/packages/api/session-controller/tests/fake-api.client.ts b/packages/api/session-controller/tests/fake-api.client.ts index c0a1b1b780..b8725dfee4 100644 --- a/packages/api/session-controller/tests/fake-api.client.ts +++ b/packages/api/session-controller/tests/fake-api.client.ts @@ -28,6 +28,7 @@ import { } from '@deepseek-ai/dsh-api-gateway/client' import { RpcId } from '@deepseek-ai/dsh-client-connection/client' import type { SessionRemotes } from '../src/client/sessions/remotes.ts' +import { historyRecordLastSeq } from '../src/client/sessions/history-records.ts' const AVAILABLE_STREAM_CONNECTION = { hostDescription: { @@ -137,7 +138,7 @@ export class FakeApiClient implements IApiClient { onFork: (payload: unknown) => Promise> = () => Promise.resolve(ok({ sessionId: 'fk-fork' as SessionId })) onHistory: (payload: { sessionId: SessionId; throughSeq?: number; beforeSeq?: number; maxMessages?: number }) => Promise> = - () => Promise.resolve(ok({ events: [], hasMore: false })) + () => Promise.resolve(ok({ records: [], hasMore: false })) onPrompt: (payload: unknown) => Promise> = () => Promise.resolve(ok({ accepted: true as const })) onAttachment: (payload: unknown) => Promise> = @@ -439,7 +440,8 @@ export class FakeApiClient implements IApiClient { ok: true, value: { ...result.value, - events: result.value.events.filter(entry => entry.event.seq <= request.throughSeq), + records: result.value.records + .filter(record => historyRecordLastSeq(record) <= request.throughSeq), }, } } @@ -467,7 +469,8 @@ export class FakeApiClient implements IApiClient { ) } const page = response.result.value - const cursor = this.followCursor ?? page.events.at(-1)?.event.seq ?? -1 + const tail = page.records.at(-1) + const cursor = this.followCursor ?? (tail === undefined ? -1 : historyRecordLastSeq(tail)) yield { type: 'snapshot', header: { @@ -479,7 +482,7 @@ export class FakeApiClient implements IApiClient { : {}), }, cursor, - events: page.events.filter(entry => entry.event.seq <= cursor), + records: page.records.filter(record => historyRecordLastSeq(record) <= cursor), hasMore: page.hasMore, projections: page.projections ?? { asOfSeq: cursor, values: {} }, } diff --git a/packages/api/session-controller/tests/history-records.client.spec.ts b/packages/api/session-controller/tests/history-records.client.spec.ts new file mode 100644 index 0000000000..4a91fb04a8 --- /dev/null +++ b/packages/api/session-controller/tests/history-records.client.spec.ts @@ -0,0 +1,78 @@ +/** Packed history records become one event-shaped Client value per wire record. */ + +import { describe, expect, it } from 'vitest' +import { CallId } from '@deepseek-ai/dsh-llm/brand' +import type { SessionHistoryRecord } from '../src/types.ts' +import { + historyEntries, + historyRecordFirstSeq, + historyRecordLastSeq, +} from '../src/client/sessions/history-records.ts' + +describe('Session history record projection', () => { + it('retains an ordinary event and its point cursor', () => { + const ordinary: SessionHistoryRecord = { + type: 'event', + event: { type: 'turn/start', seq: 7, time: 1, data: { turn: 1 } }, + } + + const records = [ordinary] + const [entry] = historyEntries(records) + + expect(historyEntries(records)).toBe(records) + expect(entry).toBe(ordinary) + expect(historyRecordFirstSeq(ordinary)).toBe(7) + expect(entry?.event.time).toBe(1) + expect(historyRecordLastSeq(ordinary)).toBe(7) + }) + + it('retains one packed text row without copying or reshaping it', () => { + const packed: SessionHistoryRecord = { + type: 'chunks', + event: { + type: 'chunkrow/text-chunks', + seq: 11, + time: 20, + data: { turn: 1, step: 2, index: 0, dt: [1, 2, 3], texts: ['a', 'b', 'c', 'd'] }, + }, + } + + const [entry] = historyEntries([packed]) + if (entry?.type !== 'chunks') throw new Error('expected packed history entry') + const { event } = entry + + expect(entry).toBe(packed) + expect(event).toBe(packed.event) + expect(historyRecordFirstSeq(packed)).toBe(11) + expect(event.time).toBe(20) + expect(historyRecordLastSeq(packed)).toBe(14) + }) + + it('preserves a packed tool-call row and optional-name absence', () => { + const packed: SessionHistoryRecord = { + type: 'chunks', + event: { + type: 'chunkrow/tool-call-chunks', + seq: 20, + time: 200, + data: { + turn: 2, + step: 4, + index: 1, + id: CallId('call-1'), + dt: [2, 3], + args: ['', '{"x":', '1}'], + }, + }, + } + + const [entry] = historyEntries([packed]) + if (entry?.type !== 'chunks') throw new Error('expected packed history entry') + const { event } = entry + + if (event.type !== 'chunkrow/tool-call-chunks') throw new Error('expected packed history event') + expect(event).toBe(packed.event) + expect(Object.hasOwn(event.data, 'name')).toBe(false) + expect(historyRecordLastSeq(packed)).toBe(22) + }) +}) diff --git a/packages/api/session-controller/tests/manager.client.spec.ts b/packages/api/session-controller/tests/manager.client.spec.ts index d21d3b25bd..d271845e78 100644 --- a/packages/api/session-controller/tests/manager.client.spec.ts +++ b/packages/api/session-controller/tests/manager.client.spec.ts @@ -759,7 +759,7 @@ describe('connected generation', () => { it('refreshes query baselines without rebuilding independently resumed Session sources', async () => { const api = new FakeApiClient() api.onHistory = () => Promise.resolve(ok({ - events: entries(plainTurn(0, 0, 'a', 'b')) as never[], + records: entries(plainTurn(0, 0, 'a', 'b')) as never[], hasMore: false, modelSelection: { provider: 'deepseek-official', model: 'deepseek-chat' }, })) diff --git a/packages/api/session-controller/tests/projection-store.client.spec.ts b/packages/api/session-controller/tests/projection-store.client.spec.ts index f12bd4475b..0a9700b960 100644 --- a/packages/api/session-controller/tests/projection-store.client.spec.ts +++ b/packages/api/session-controller/tests/projection-store.client.spec.ts @@ -105,7 +105,7 @@ describe('Session tail-page seeding', () => { const api = new FakeApiClient() const session = new Session(SID, api, fakeRemote(api)) api.onHistory = () => Promise.resolve(ok({ - events: entries(plainTurn(0, 0, '问', '答')) as never[], hasMore: false, + records: entries(plainTurn(0, 0, '问', '答')) as never[], hasMore: false, projections: { asOfSeq: 5, values: { 'test/marks': { marks: ['from-baseline'] } } }, } as never)) await session.open() @@ -116,7 +116,7 @@ describe('Session tail-page seeding', () => { const api = new FakeApiClient() const session = new Session(SID, api, fakeRemote(api)) api.onHistory = () => Promise.resolve(ok({ - events: entries(plainTurn(0, 0, 'a', 'b')) as never[], hasMore: false, + records: entries(plainTurn(0, 0, 'a', 'b')) as never[], hasMore: false, projections: { asOfSeq: 5, values: { 'test/marks': { marks: ['baseline'] } } }, } as never)) await session.open() @@ -128,7 +128,7 @@ describe('Session tail-page seeding', () => { it('treats a blockless response as no reset: pushed values survive', async () => { const api = new FakeApiClient() const session = new Session(SID, api, fakeRemote(api)) - api.onHistory = () => Promise.resolve(ok({ events: entries(plainTurn(0, 0, 'a', 'b')) as never[], hasMore: false })) + api.onHistory = () => Promise.resolve(ok({ records: entries(plainTurn(0, 0, 'a', 'b')) as never[], hasMore: false })) await session.open() session.projections.apply('test/marks', { marks: ['pushed'] }, 9) await session.resync() diff --git a/packages/api/session-controller/tests/session-cold.host.spec.ts b/packages/api/session-controller/tests/session-cold.host.spec.ts index 7771bc112d..7156ac569d 100644 --- a/packages/api/session-controller/tests/session-cold.host.spec.ts +++ b/packages/api/session-controller/tests/session-cold.host.spec.ts @@ -390,7 +390,7 @@ describe('cold history recovery view', () => { maxMessages: 10, }) if (!history.ok) throw new Error('history failed') - expect(history.value.events.map(entry => entry.event)).toMatchInlineSnapshot(` + expect(history.value.records.map(record => record.event)).toMatchInlineSnapshot(` [ { "data": { @@ -564,7 +564,8 @@ describe('subagent ownership fence', () => { }, throughSeq: 3, }, new AbortController().signal) - expect(history.events.map(entry => entry.event.type)).toEqual(events.map(event => event.type)) + expect(history.records.map(record => record.event.type)) + .toEqual(events.map(event => event.type)) expect(ctx.agents.get(sessionId)).toBeUndefined() const prompt = await remote.prompt(promptRequest({ diff --git a/packages/api/session-controller/tests/session-history-journal.host.spec.ts b/packages/api/session-controller/tests/session-history-journal.host.spec.ts index 56b2fe5948..c52dda5b92 100644 --- a/packages/api/session-controller/tests/session-history-journal.host.spec.ts +++ b/packages/api/session-controller/tests/session-history-journal.host.spec.ts @@ -4,10 +4,16 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from '@deepseek-ai/cordis' import AgentRegistry from '@deepseek-ai/dsh-agent' import SessionStore from '@deepseek-ai/dsh-session' +import { decodeStorageRecord, type ChunkRow } from '@deepseek-ai/dsh-session/chunk-rows' import { CallId, createMessage, createToolResultMessage, createUserMessage } from '@deepseek-ai/dsh-llm' import type { Session, SessionEvent, SessionId } from '@deepseek-ai/dsh-session' import { SessionHistoryController } from '@deepseek-ai/dsh-api-session-controller/src/history.ts' -import type { SessionFollowFrame } from '@deepseek-ai/dsh-api-session-controller/types' +import type { + ChunkRowEvent, + SessionFollowFrame, + SessionPage, + SessionWireEvent, +} from '@deepseek-ai/dsh-api-session-controller/types' import { createSessionTestRemote, installSessionReadTestServices } from './test-remote.ts' /** Append a production-shaped human prompt to the session surface. */ @@ -77,6 +83,24 @@ async function openFollow( return { [Symbol.asyncIterator]: () => iterator } } +/** Expand packed page records for assertions over the logical journal. */ +function pageEvents(page: SessionPage): SessionWireEvent[] { + return page.records.flatMap(record => record.type === 'event' + ? [record.event] + : decodeStorageRecord(chunkRow(record.event)).map(event => event as unknown as SessionWireEvent)) +} + +function chunkRow(event: ChunkRowEvent): ChunkRow { + switch (event.type) { + case 'chunkrow/text-chunks': + return { type: 'text-chunks', seq0: event.seq, time0: event.time, data: event.data } + case 'chunkrow/reasoning-chunks': + return { type: 'reasoning-chunks', seq0: event.seq, time0: event.time, data: event.data } + case 'chunkrow/tool-call-chunks': + return { type: 'tool-call-chunks', seq0: event.seq, time0: event.time, data: event.data } + } +} + describe('Session history raw journal', () => { it('follows raw tool events and preserves result metadata without a Tools service', async () => { const { ctx } = await harness() @@ -169,10 +193,10 @@ describe('Session history raw journal', () => { }) expect(response.ok).toBe(true) if (!response.ok) throw new Error('unreachable') - expect(response.value.events).toEqual([ - { event: start }, - { event: call }, - { event: result }, + expect(response.value.records).toEqual([ + { type: 'event', event: start }, + { type: 'event', event: call }, + { type: 'event', event: result }, ]) }) @@ -210,7 +234,7 @@ describe('Session history raw journal', () => { maxMessages: 2, }) if (!response.ok) throw new Error('unreachable') - const page = response.value.events.map(entry => entry.event) + const page = pageEvents(response.value) // Two append-origin messages fill the page even though a replacement copy of // the same event type sits in the window: the copy is model-only. const messages = page.filter(event => event.type === 'user/message' || event.type === 'assistant/message') @@ -230,10 +254,10 @@ describe('Session history raw journal', () => { const remote = createSessionTestRemote(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp' }) const session = ctx.sessions.create(undefined, { meta: { cwd: '/workspace' } }) session.append('turn/start', { turn: 1 }) - const sources = Array.from({ length: 128 }, (_unused, index) => session.append('assistant/chunk', { + const sources = Array.from({ length: 128 }, () => session.append('assistant/chunk', { turn: 1, step: 1, - chunk: { type: 'text-delta', index, text: 'x' }, + chunk: { type: 'text-delta', index: 0, text: 'x' }, }).seq) const message = session.append('assistant/message', { turn: 1, @@ -257,13 +281,71 @@ describe('Session history raw journal', () => { maxMessages: 1, }) if (!response.ok) throw new Error('unreachable') - expect(response.value.events.map(entry => entry.event.seq)).toEqual([...sources, message.seq]) + expect(pageEvents(response.value).map(event => event.seq)).toEqual([...sources, message.seq]) + expect(response.value.records.filter(record => record.type === 'chunks')).toHaveLength(1) expect(response.value.hasMore).toBe(true) } finally { min.mockRestore() } }) + it('encodes reasoning and tool-call runs as aligned chunk events', async () => { + const { ctx } = await harness() + const remote = createSessionTestRemote(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp' }) + const session = ctx.sessions.create(undefined, { meta: { cwd: '/workspace' } }) + const reasoning = [0, 1, 2].map(index => session.append('assistant/chunk', { + turn: 1, + step: 1, + chunk: { type: 'reasoning-delta', index: 0, text: `r${String(index)}` }, + })) + const callId = CallId('packed-call') + const toolCall = [0, 1, 2].map(index => session.append('assistant/chunk', { + turn: 1, + step: 1, + chunk: { type: 'tool-call-delta', index: 1, id: callId, argumentsDelta: `a${String(index)}` }, + })) + + const response = await remote.page({ + address: { kind: 'session', sessionId: session.id }, + throughSeq: session.seq - 1, + }) + if (!response.ok) throw new Error('unreachable') + expect(response.value.records).toEqual([ + { + type: 'chunks', + event: { + type: 'chunkrow/reasoning-chunks', + seq: reasoning[0]?.seq, + time: reasoning[0]?.time, + data: { + turn: 1, + step: 1, + index: 0, + dt: reasoning.slice(1).map((event, index) => event.time - (reasoning[index]?.time ?? 0)), + texts: ['r0', 'r1', 'r2'], + }, + }, + }, + { + type: 'chunks', + event: { + type: 'chunkrow/tool-call-chunks', + seq: toolCall[0]?.seq, + time: toolCall[0]?.time, + data: { + turn: 1, + step: 1, + index: 1, + id: callId, + dt: toolCall.slice(1).map((event, index) => event.time - (toolCall[index]?.time ?? 0)), + args: ['a0', 'a1', 'a2'], + }, + }, + }, + ]) + await ctx.fiber.dispose() + }) + it('follows a result after turn/end without reading the addressed Session log', async () => { const { ctx } = await harness() const session = ctx.sessions.create(undefined, { meta: { cwd: '/workspace' } }) @@ -273,11 +355,17 @@ describe('Session history raw journal', () => { const iterator = stream[Symbol.asyncIterator]() session.append('turn/start', { turn: 1 }) - await expect(iterator.next()).resolves.toMatchObject({ value: { event: { type: 'turn/start' } } }) + await expect(iterator.next()).resolves.toMatchObject({ + value: { type: 'event', event: { type: 'turn/start' } }, + }) session.append('tool/call', { turn: 1, step: 1, callId: CallId('c-late'), name: 'term', arguments: '{"cmd":"tail"}' }) - await expect(iterator.next()).resolves.toMatchObject({ value: { event: { type: 'tool/call' } } }) + await expect(iterator.next()).resolves.toMatchObject({ + value: { type: 'event', event: { type: 'tool/call' } }, + }) session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - await expect(iterator.next()).resolves.toMatchObject({ value: { event: { type: 'turn/end' } } }) + await expect(iterator.next()).resolves.toMatchObject({ + value: { type: 'event', event: { type: 'turn/end' } }, + }) const events = vi.spyOn(session, 'events', 'get').mockImplementation(() => { throw new Error('live result rescanned Session history') }) diff --git a/packages/api/session-controller/tests/session-projections.host.spec.ts b/packages/api/session-controller/tests/session-projections.host.spec.ts index ee6c777e80..fd30f66158 100644 --- a/packages/api/session-controller/tests/session-projections.host.spec.ts +++ b/packages/api/session-controller/tests/session-projections.host.spec.ts @@ -148,11 +148,12 @@ describe('session.history projections block', () => { ctx.sessionProjections.register(lastUserUnit()) seedMessages(session, 3) const snapshot = await opening(remote(ctx), session.id) - const { events, projections } = snapshot + const { records, projections } = snapshot expect(projections.asOfSeq).toBe(session.seq - 1) expect(projections.values['test/last-user']).toEqual({ text: 'm2' }) // asOfSeq IS the window tail: the last served event carries it. - expect(events.at(-1)?.event.seq).toBe(projections.asOfSeq) + const last = records.at(-1) + expect(last?.event.seq).toBe(projections.asOfSeq) }) it('returns a complete current replacement cut on each follow generation', async () => { @@ -162,7 +163,7 @@ describe('session.history projections block', () => { const snapshot = await opening(remote(ctx), session.id) - expect(snapshot.events.map(entry => entry.event.seq)).toEqual([0, 1]) + expect(snapshot.records.map(record => record.event.seq)).toEqual([0, 1]) expect(snapshot.projections.asOfSeq).toBe(1) expect(snapshot.projections.values).toEqual( expect.objectContaining({ 'test/last-user': { text: 'm1' } }), @@ -175,7 +176,7 @@ describe('session.history projections block', () => { const snapshot = await opening(remote(ctx), session.id) - expect(snapshot.events).toEqual([]) + expect(snapshot.records).toEqual([]) expect(snapshot.projections.asOfSeq).toBe(-1) expect(snapshot.projections.values).toEqual( expect.objectContaining({ 'test/last-user': null }), diff --git a/packages/api/session-controller/tests/session.client.spec.ts b/packages/api/session-controller/tests/session.client.spec.ts index 79fac7b7b8..6ee5bd9ba4 100644 --- a/packages/api/session-controller/tests/session.client.spec.ts +++ b/packages/api/session-controller/tests/session.client.spec.ts @@ -6,7 +6,7 @@ import type { SessionEvent } from '@deepseek-ai/dsh-session/types' import type { SessionId } from '@deepseek-ai/dsh-api-remotes/client' import { Session, type SessionOptions } from '../src/client/sessions/session.ts' import { FakeApiClient, deferred, err, fakeRemote, ok } from './fake-api.client.ts' -import { entries, ev, plainTurn } from './event-script.client.ts' +import { entries, ev, historyValue, plainTurn } from './event-script.client.ts' const SID = 'fk-s1' as SessionId const PARENT = 'fk-parent' as SessionId @@ -41,8 +41,7 @@ function eventSeqs(session: Session): number[] { } function histResponse(events: SessionEvent[], hasMore = false) { - // History returns raw journal envelopes around each event. - return Promise.resolve(ok({ events: entries(events) as never[], hasMore })) + return Promise.resolve(ok(historyValue(events, hasMore))) } describe('Session open', () => { @@ -106,7 +105,7 @@ describe('Session open', () => { follow(api, ev.user(16, '插进来的')), ] gate.resolve(ok({ - events: entries(page) as never[], + records: entries(page) as never[], hasMore: false, modelSelection: { provider: 'deepseek-official', model: 'deepseek-v4-flash' }, })) @@ -227,7 +226,7 @@ describe('paging', () => { const first = session.loadOlder() const second = session.loadOlder() gate.resolve(ok({ - events: entries(plainTurn(0, 0, 'a', 'b')) as never[], + records: entries(plainTurn(0, 0, 'a', 'b')) as never[], hasMore: false, modelSelection: { provider: 'deepseek-official', model: 'deepseek-v4-flash' }, })) @@ -571,7 +570,7 @@ describe('remaining branches', () => { api.onHistory = () => histResponse(plainTurn(6, 1, '新', '代')) const resynced = session.resync() stale.resolve(ok({ - events: entries(plainTurn(0, 0, '旧', '代')) as never[], + records: entries(plainTurn(0, 0, '旧', '代')) as never[], hasMore: false, modelSelection: { provider: 'deepseek-official', model: 'stale' }, })) // success, but its generation is gone @@ -590,7 +589,7 @@ describe('remaining branches', () => { api.onHistory = () => histResponse(plainTurn(6, 1, 'c', 'd')) const resynced = session.resync() // bumps the generation repairPull.resolve(ok({ - events: entries(plainTurn(0, 0, '旧', '页')) as never[], + records: entries(plainTurn(0, 0, '旧', '页')) as never[], hasMore: false, modelSelection: { provider: 'deepseek-official', model: 'stale' }, })) // repair result: stale, dropped @@ -617,25 +616,25 @@ describe('remaining branches', () => { const historyCall = ev.toolCall(6, 1, 'h1', 'bash', '{"cmd":"pwd"}') const historyResult = ev.toolResult(7, 1, 'h1', 'done') api.onHistory = () => Promise.resolve(ok({ - events: [ + records: [ ...entries(plainTurn(0, 0, 'a', 'b')), - { event: historyCall }, - { event: historyResult }, + { type: 'event', event: historyCall }, + { type: 'event', event: historyResult }, ] as never[], hasMore: false, modelSelection: { provider: 'deepseek-official', model: 'deepseek-v4-flash' }, })) await session.open() expect(windowEntries(session).slice(-2)).toEqual([ - { event: historyCall }, - { event: historyResult }, + { type: 'event', event: historyCall }, + { type: 'event', event: historyResult }, ]) const liveCall = ev.toolCall(8, 2, 'l1', 'write', '{"file_path":"a.ts"}') await follow(api, liveCall) - expect(windowEntries(session).at(-1)).toEqual({ event: liveCall }) + expect(windowEntries(session).at(-1)).toEqual({ type: 'event', event: liveCall }) const liveResult = ev.toolResult(9, 2, 'l1', 'ok') await follow(api, liveResult) - expect(windowEntries(session).at(-1)).toEqual({ event: liveResult }) + expect(windowEntries(session).at(-1)).toEqual({ type: 'event', event: liveResult }) }) }) @@ -669,7 +668,7 @@ describe('resync', () => { ]) expect(session.eventSource.getSnapshot()).toBe(oldWindow) replacement.resolve(ok({ - events: entries(plainTurn(10, 2, '终', '页')) as never[], + records: entries(plainTurn(10, 2, '终', '页')) as never[], hasMore: false, modelSelection: { provider: 'deepseek-official', model: 'deepseek-v4-flash' }, })) diff --git a/packages/api/session-controller/tests/sessions-service.client.spec.ts b/packages/api/session-controller/tests/sessions-service.client.spec.ts index f602607e02..39f61a6663 100644 --- a/packages/api/session-controller/tests/sessions-service.client.spec.ts +++ b/packages/api/session-controller/tests/sessions-service.client.spec.ts @@ -274,7 +274,7 @@ describe('Agent scope disposal lifecycle', () => { createdAt: 0, }, cursor: -1, - events: [], + records: [], hasMore: false, projections: { asOfSeq: -1, values: {} }, } as const, @@ -343,7 +343,7 @@ describe('Agent scope disposal lifecycle', () => { type: 'snapshot', header: { version: 0, id: sessionId, createdAt: 0 }, cursor: -1, - events: [], + records: [], hasMore: false, projections: { asOfSeq: -1, values: {} }, } as const, diff --git a/packages/api/session-controller/tests/transport.client.spec.ts b/packages/api/session-controller/tests/transport.client.spec.ts index 3960e05285..1ad1d4e858 100644 --- a/packages/api/session-controller/tests/transport.client.spec.ts +++ b/packages/api/session-controller/tests/transport.client.spec.ts @@ -19,6 +19,7 @@ import type { SessionEventEntry, SessionFollowFrame, SessionFollowRequest, + SessionHistoryRecord, SessionPage, SessionPageRequest, } from '../src/types.ts' @@ -36,16 +37,28 @@ const AVAILABLE_CONNECTION = { } function entry(seq: number): SessionEventEntry { - return { event: { type: 'turn/start', seq, time: seq, data: { turn: seq } } } + return { type: 'event', event: { type: 'turn/start', seq, time: seq, data: { turn: seq } } } } -function page(events: readonly SessionEventEntry[], hasMore = false): SessionPage { - return { events, hasMore } +function chunks(seq0: number): SessionHistoryRecord { + return { + type: 'chunks', + event: { + type: 'chunkrow/text-chunks', + seq: seq0, + time: seq0, + data: { turn: 1, step: 1, index: 0, texts: ['a', 'b', 'c'], dt: [1, 1] }, + }, + } +} + +function page(records: readonly SessionHistoryRecord[], hasMore = false): SessionPage { + return { records, hasMore } } function snapshot( cursor: number, - events: readonly SessionEventEntry[], + records: readonly SessionHistoryRecord[], hasMore = false, ): SessionFollowFrame { return { @@ -56,7 +69,7 @@ function snapshot( createdAt: 0, }, cursor, - events, + records, hasMore, projections: { asOfSeq: cursor, values: {} }, } @@ -123,13 +136,60 @@ class ScriptedSessionRemote implements SessionTransportRemote { } describe('Session Client stream adapters', () => { + it('validates a packed logical range before publishing one compact Client entry', async () => { + const row = chunks(1) + const remote = new ScriptedSessionRemote( + [{ frames: [snapshot(4, [entry(0), row, entry(4)]), entry(5)], hold: true }], + [], + ) + const changes: SessionJournalChange[] = [] + const stream = new SessionEventStream(sessionClient(remote), ADDRESS, { + publish: (change) => { changes.push(change) }, + failed: vi.fn(), + }) + + await stream.open({}) + await vi.waitFor(() => { expect(changes).toHaveLength(2) }) + + expect(changes[0]).toMatchObject({ + type: 'replace', + entries: [ + entry(0), + row, + entry(4), + ], + }) + expect(changes[0]?.type === 'replace' ? changes[0].entries[1] : undefined).toBe(row) + expect(changes[1]).toEqual({ type: 'append', entry: entry(5) }) + await stream.dispose() + }) + + it('rejects a packed record emitted by the live follow path', async () => { + const failed = vi.fn() + const remote = new ScriptedSessionRemote( + [{ frames: [snapshot(-1, []), chunks(0) as SessionFollowFrame], hold: true }], + [], + ) + const stream = new SessionEventStream(sessionClient(remote), ADDRESS, { + publish: vi.fn(), + failed, + }) + + await stream.open({}) + await vi.waitFor(() => { expect(failed).toHaveBeenCalledOnce() }) + expect(failed.mock.calls[0]?.[0]).toMatchObject({ + message: 'session live stream emitted a packed history record', + }) + await stream.dispose() + }) + it('binds an event journal to one address and publishes replace, append, and prepend changes', async () => { const remote = new ScriptedSessionRemote( [{ frames: [ snapshot(3, [entry(2), entry(3)], true), - { type: 'event', ...entry(3) }, - { type: 'event', ...entry(4) }, + entry(3), + entry(4), ], hold: true, }], @@ -165,7 +225,7 @@ describe('Session Client stream adapters', () => { const remote = new ScriptedSessionRemote( [ { - frames: [snapshot(1, [entry(0), entry(1)]), { type: 'event', ...entry(2) }], + frames: [snapshot(1, [entry(0), entry(1)]), entry(2)], terminal: lost, }, { frames: [snapshot(4, [entry(0), entry(1), entry(2), entry(3), entry(4)])], hold: true }, @@ -221,7 +281,7 @@ describe('Session Client stream adapters', () => { it('repairs a live gap without adding an absent message limit', async () => { const remote = new ScriptedSessionRemote( - [{ frames: [snapshot(0, [entry(0)]), { type: 'event', ...entry(2) }], hold: true }], + [{ frames: [snapshot(0, [entry(0)]), entry(2)], hold: true }], [{ ok: true, value: page([entry(0), entry(1), entry(2)]) }], ) const changes: SessionJournalChange[] = [] diff --git a/packages/api/session-controller/tests/transport.host.spec.ts b/packages/api/session-controller/tests/transport.host.spec.ts index 65338e27ae..d23faacb94 100644 --- a/packages/api/session-controller/tests/transport.host.spec.ts +++ b/packages/api/session-controller/tests/transport.host.spec.ts @@ -87,7 +87,7 @@ describe('SessionHistoryController', () => { { address: { kind: 'session', sessionId: session.id }, throughSeq: 1 }, new AbortController().signal, ) - expect(page.events.map(entry => entry.event.seq)).toEqual([0, 1]) + expect(page.records.map(entry => entry.event.seq)).toEqual([0, 1]) abort.abort() expect(await iterator.next()).toMatchObject({ done: true }) @@ -137,7 +137,11 @@ describe('SessionHistoryController', () => { value: { type: 'snapshot', cursor: 2, - events: [{ event: { seq: 0 } }, { event: { seq: 1 } }, { event: { seq: 2 } }], + records: [ + { type: 'event', event: { seq: 0 } }, + { type: 'event', event: { seq: 1 } }, + { type: 'event', event: { seq: 2 } }, + ], }, }) session.append('turn/end', { turn: 2, reason: { kind: 'completed' } }) @@ -200,7 +204,12 @@ describe('SessionHistoryController', () => { await expect(opening).resolves.toMatchObject({ done: false, value: { - type: 'snapshot', cursor: 1, events: [{ event: { seq: 0 } }, { event: { seq: 1 } }], + type: 'snapshot', + cursor: 1, + records: [ + { type: 'event', event: { seq: 0 } }, + { type: 'event', event: { seq: 1 } }, + ], }, }) expect(attached.id).toBe(sessionId) @@ -301,7 +310,7 @@ describe('SessionHistoryController', () => { await expect(iterator.next()).resolves.toMatchObject({ done: false, value: { type: 'snapshot', cursor: -1 } }) await expect(transport.page({ address: { kind: 'session', sessionId: session.id }, throughSeq: -1, - }, signal())).resolves.toMatchObject({ events: [], hasMore: false }) + }, signal())).resolves.toMatchObject({ records: [], hasMore: false }) abort.abort() await expect(iterator.next()).resolves.toMatchObject({ done: true }) }) @@ -377,7 +386,9 @@ describe('SessionHistoryController', () => { await expect(transport.page({ address: { kind: 'subagent', parentSessionId, childSessionId, mode: 'continuable' }, throughSeq: 0, - }, signal)).resolves.toMatchObject({ events: [{ event: { type: 'subagent/descriptor' } }] }) + }, signal)).resolves.toMatchObject({ + records: [{ type: 'event', event: { type: 'subagent/descriptor' } }], + }) await expect(transport.page({ address: { kind: 'subagent', @@ -505,7 +516,9 @@ describe('SessionHistoryController', () => { await expect(ordinaryBench.transport.page({ address: { kind: 'session', sessionId: ordinaryId }, throughSeq: 0, - }, signal())).resolves.toMatchObject({ events: [{ event: { seq: 0 } }] }) + }, signal())).resolves.toMatchObject({ + records: [{ type: 'event', event: { seq: 0 } }], + }) const parentSessionId = SessionId('cold-parent') const childSessionId = SessionId('cold-child') @@ -618,12 +631,13 @@ describe('SessionHistoryController', () => { const page = await transport.page({ address: { kind: 'session', sessionId: session.id }, throughSeq: replacement.seq, maxMessages: 2, }, signal()) - expect(page.events.map(entry => entry.event.seq)).toEqual([3, 4, 5, replacement.seq]) + expect(page.records.map(entry => entry.event.seq)) + .toEqual([3, 4, 5, replacement.seq]) expect(page.hasMore).toBe(true) const before = await transport.page({ address: { kind: 'session', sessionId: session.id }, throughSeq: replacement.seq, beforeSeq: 3, maxMessages: 1, }, signal()) - expect(before.events.map(entry => entry.event.seq)).toEqual([2]) + expect(before.records.map(entry => entry.event.seq)).toEqual([2]) }) it('keeps cited source events in the page that owns their appended message', async () => { @@ -637,7 +651,7 @@ describe('SessionHistoryController', () => { const page = await transport.page({ address: { kind: 'session', sessionId: session.id }, throughSeq: 1, maxMessages: 1, }, signal()) - expect(page.events.map(entry => entry.event.seq)).toEqual([0, 1]) + expect(page.records.map(entry => entry.event.seq)).toEqual([0, 1]) expect(page.hasMore).toBe(false) }) diff --git a/packages/client/AGENTS.md b/packages/client/AGENTS.md index b45dc60a48..27f1761cea 100644 --- a/packages/client/AGENTS.md +++ b/packages/client/AGENTS.md @@ -99,7 +99,7 @@ The seam is `loader.internal = modules`: cordis reaches plugin code through `Ent ## Conversation Node discipline - A Chat business feature registers one `ConversationNodeDefinition` and its keyed `conversation.chat.node` renderer; do not add its event switch or fold to `Session`, `SessionManager`, or a central built-in dispatcher. Follow the [Conversation reference](../../docs/subsystems/conversation.md). -- `match(event)` reads only the current event. Every event in a multi-event Context carries or independently derives the same stable business id; `update` folds one Match into State and remains deterministically replayable by log `seq`. +- `match(event)` reads only the current `SessionEventLike`. Every scalar event or packed Assistant run in a multi-input Context carries or independently derives the same stable business id; `update` folds one Match into State and remains deterministically replayable by logical log `seq`. Packed rows are update-only, and a Definition that consumes Assistant deltas implements both scalar and `chunkrow/*` branches without expanding members. - The append hot path and renderers never scan the full event window, Contexts, or Chat Nodes. Accumulate in State, publish same-Turn/Step facts through `buildLocationData()`, and consume final Node data or constrained Location hooks. ## Directory regime (plugin packages) diff --git a/packages/client/connection/src/client/fixture.ts b/packages/client/connection/src/client/fixture.ts index c27a1cae4c..26fe838edc 100644 --- a/packages/client/connection/src/client/fixture.ts +++ b/packages/client/connection/src/client/fixture.ts @@ -22,6 +22,8 @@ import type { SessionHeader, SessionId, } from '@deepseek-ai/dsh-session/types' +import { isChunkRow, packChunkRuns } from '@deepseek-ai/dsh-session/chunk-rows' +import type { ChunkRow } from '@deepseek-ai/dsh-session/chunk-rows' import type { TodoItem } from '@deepseek-ai/dsh-tool-todo/client' // Type-only: the brand constructor is host-side; the fixture casts at its // wire-fabrication boundary (the schema layer's one-cast-point posture). @@ -73,9 +75,26 @@ interface FixtureProjectionsBlock { } interface FixtureHistoryEntry { + readonly type: 'event' readonly event: SessionEvent } +type FixtureChunkRowEvent = { + [Kind in ChunkRow['type']]: { + readonly type: `chunkrow/${Kind}` + readonly seq: number + readonly time: number + readonly data: Extract['data'] + } +}[ChunkRow['type']] + +interface FixtureHistoryChunkRun { + readonly type: 'chunks' + readonly event: FixtureChunkRowEvent +} + +type FixtureHistoryRecord = FixtureHistoryEntry | FixtureHistoryChunkRun + type FixtureSessionAddress = | { readonly kind: 'session'; readonly sessionId: SessionId } | { @@ -102,11 +121,11 @@ type FixtureFollowFrame = readonly type: 'snapshot' readonly header: SessionHeader readonly cursor: number - readonly events: readonly FixtureHistoryEntry[] + readonly records: readonly FixtureHistoryRecord[] readonly hasMore: boolean readonly projections: FixtureProjectionsBlock } - | ({ readonly type: 'event' } & FixtureHistoryEntry) + | FixtureHistoryEntry type FixtureFollowEventFrame = Extract @@ -1392,7 +1411,7 @@ function pageOf( log: readonly SessionEvent[], beforeSeq: number | undefined, maxMessages: number, -): { events: FixtureHistoryEntry[]; hasMore: boolean } { +): { records: FixtureHistoryRecord[]; hasMore: boolean } { const end = beforeSeq === undefined ? log.length : Math.max(0, Math.min(beforeSeq, log.length)) let start = 0 let messages = 0 @@ -1406,8 +1425,27 @@ function pageOf( break } } - const events = log.slice(start, end).map((event): FixtureHistoryEntry => ({ event })) - return { events, hasMore: start > 0 } + const records = packChunkRuns(log.slice(start, end)).map((record): FixtureHistoryRecord => { + if (!isChunkRow(record)) return { type: 'event', event: record } + switch (record.type) { + case 'text-chunks': + return { + type: 'chunks', + event: { type: 'chunkrow/text-chunks', seq: record.seq0, time: record.time0, data: record.data }, + } + case 'reasoning-chunks': + return { + type: 'chunks', + event: { type: 'chunkrow/reasoning-chunks', seq: record.seq0, time: record.time0, data: record.data }, + } + case 'tool-call-chunks': + return { + type: 'chunks', + event: { type: 'chunkrow/tool-call-chunks', seq: record.seq0, time: record.time0, data: record.data }, + } + } + }) + return { records, hasMore: start > 0 } } /** Fixture mirror of host session-scoped attachment authorization. */ @@ -1874,7 +1912,7 @@ function createFixtureWorld(options: FixtureOptions): FixtureWorld { for (const conn of remoteEventConns.values()) conn.push(frame) } const emitFollow = (sessionId: SessionId, entry: FixtureHistoryEntry): void => { - for (const conn of followConns.get(sessionId) ?? []) conn.push({ type: 'event', ...entry }) + for (const conn of followConns.get(sessionId) ?? []) conn.push(entry) } /** OK response echoing the caller's rpcId (contract: responses always backfill, never mint). */ @@ -1932,7 +1970,7 @@ function createFixtureWorld(options: FixtureOptions): FixtureWorld { const log = logOf(id) const event = { seq: log.length, time: Date.now(), ...e } as unknown as SessionEvent log.push(event) - emitFollow(id, { event }) + emitFollow(id, { type: 'event', event }) // Host eager-drive parallel: a unit-advancing event pushes its finished value. for (const frame of projectionFramesOf(id, log, event)) emitControl(frame) if (event.type === 'user/message' && event.data.source.kind === 'user') { @@ -2968,7 +3006,7 @@ function createFixtureWorld(options: FixtureOptions): FixtureWorld { ...(summary.agentPreset === undefined ? {} : { agentPreset: summary.agentPreset }), }, cursor, - events: initial.events, + records: initial.records, hasMore: initial.hasMore, projections: { asOfSeq: cursor, values: projectionValuesOf(snapshot) }, } diff --git a/packages/client/connection/tests/fixture.client.spec.ts b/packages/client/connection/tests/fixture.client.spec.ts index 918b802aab..77f996044b 100644 --- a/packages/client/connection/tests/fixture.client.spec.ts +++ b/packages/client/connection/tests/fixture.client.spec.ts @@ -9,6 +9,8 @@ import type { SessionId, } from '../src/client/api.ts' import { RpcId } from '../src/client/api.ts' +import { decodeStorageRecord } from '@deepseek-ai/dsh-session/chunk-rows' +import type { ChunkRow } from '@deepseek-ai/dsh-session/chunk-rows' import { FixtureApiClient, createFixtureFaces, @@ -35,26 +37,60 @@ interface FixtureSessionSummary { } interface FixtureHistoryEntry { + readonly type: 'event' readonly event: SessionEvent } +type FixtureChunkRowEvent = { + [Kind in ChunkRow['type']]: { + readonly type: `chunkrow/${Kind}` + readonly seq: number + readonly time: number + readonly data: Extract['data'] + } +}[ChunkRow['type']] + +interface FixtureHistoryChunkRun { + readonly type: 'chunks' + readonly event: FixtureChunkRowEvent +} + +type FixtureHistoryRecord = FixtureHistoryEntry | FixtureHistoryChunkRun + interface FixturePage { - readonly events: readonly FixtureHistoryEntry[] + readonly records: readonly FixtureHistoryRecord[] readonly hasMore: boolean } +function historyEvents(records: readonly FixtureHistoryRecord[]): SessionEvent[] { + return records.flatMap(record => record.type === 'event' + ? [record.event] + : decodeStorageRecord(chunkRow(record.event))) +} + +function chunkRow(event: FixtureChunkRowEvent): ChunkRow { + switch (event.type) { + case 'chunkrow/text-chunks': + return { type: 'text-chunks', seq0: event.seq, time0: event.time, data: event.data } + case 'chunkrow/reasoning-chunks': + return { type: 'reasoning-chunks', seq0: event.seq, time0: event.time, data: event.data } + case 'chunkrow/tool-call-chunks': + return { type: 'tool-call-chunks', seq0: event.seq, time0: event.time, data: event.data } + } +} + type FixtureFollowFrame = | { readonly type: 'snapshot' readonly cursor: number - readonly events: readonly FixtureHistoryEntry[] + readonly records: readonly FixtureHistoryRecord[] readonly hasMore: boolean readonly projections: { readonly asOfSeq: number readonly values: Readonly> } } - | ({ readonly type: 'event' } & FixtureHistoryEntry) + | FixtureHistoryEntry type FixtureControlFrame = | { @@ -580,21 +616,22 @@ describe('createFixtureApi', () => { if (!tail.result.ok) throw new Error('history failed') const tailPage = tail.result.value expect(tailPage.hasMore).toBe(true) - expect(tailPage.events[0]?.event.type).toBe('turn/start') // cut lands on a turn boundary - const boundary = tailPage.events[0]?.event.seq ?? 0 + const tailEvents = historyEvents(tailPage.records) + expect(tailEvents[0]?.type).toBe('turn/start') // cut lands on a turn boundary + const boundary = tailEvents[0]?.seq ?? 0 expect(boundary).toBeGreaterThan(0) const older = await api.sessions.history(req({ sessionId: sid('fx-alpha'), beforeSeq: boundary, maxMessages: 10 })) if (!older.result.ok) throw new Error('older failed') - const olderTail = older.result.value.events.at(-1)?.event + const olderTail = historyEvents(older.result.value.records).at(-1) expect((olderTail?.seq ?? -1) + 1).toBe(boundary) // pages stitch with no hole/overlap // Out-of-range beforeSeq clamps instead of exploding. const clamped = await api.sessions.history(req({ sessionId: sid('fx-alpha'), beforeSeq: -5, maxMessages: 10 })) if (!clamped.result.ok) throw new Error('clamped failed') - expect(clamped.result.value.events).toEqual([]) + expect(clamped.result.value.records).toEqual([]) // Unknown session: empty page, not an error (history of a bare id). const empty = await api.sessions.history(req({ sessionId: sid('no-such'), maxMessages: 10 })) if (!empty.result.ok) throw new Error('empty failed') - expect(empty.result.value).toEqual({ events: [], hasMore: false }) + expect(empty.result.value).toEqual({ records: [], hasMore: false }) }) it('serves raw history entries with replayable tool-result metadata', async () => { @@ -602,10 +639,8 @@ describe('createFixtureApi', () => { const response = await api.sessions.history(req({ sessionId: sid('fx-alpha'), maxMessages: 200 })) if (!response.result.ok) throw new Error('history failed') - const entries = response.result.value.events - expect(entries.every(entry => !Object.hasOwn(entry, 'view'))).toBe(true) - const results = entries - .map(entry => entry.event) + const records = response.result.value.records + const results = historyEvents(records) .filter(event => event.type === 'tool/result') expect(results.find(event => event.data.turn === 64)).toMatchObject({ @@ -668,7 +703,7 @@ describe('createFixtureApi', () => { await new Promise(resolve => setTimeout(resolve, 600)) const after = await api.sessions.history(req({ sessionId })) if (!after.result.ok) throw new Error('history failed') - expect(JSON.stringify(after.result.value.events)).toContain('openai/gpt-5') + expect(JSON.stringify(after.result.value.records)).toContain('openai/gpt-5') }) it('serves configured DeepSeek readiness and keeps credential values write-only', async () => { @@ -705,7 +740,7 @@ describe('createFixtureApi', () => { const api = createFixtureApi() const tail = await api.sessions.history(req({ sessionId: sid('fx-alpha'), maxMessages: 10 })) if (!tail.result.ok) throw new Error('history failed') - const events = tail.result.value.events.map(e => e.event) + const events = historyEvents(tail.result.value.records) const todoAt = events.findIndex(e => e.type === 'todo/write') expect(todoAt).toBeGreaterThan(0) // Production ordering (the tool appends mid-execution): call → snapshot → result. @@ -1134,8 +1169,8 @@ describe('createFixtureApi', () => { // so the event is located by seq and its payload checked structurally). const history = await api.sessions.history(req({ sessionId: sid('fx-alpha'), maxMessages: 100 })) if (!history.result.ok) throw new Error('history failed') - const appended = history.result.value.events.find(entry => entry.event.seq === acceptedSeq) - expect(appended?.event).toMatchObject({ + const appended = historyEvents(history.result.value.records).find(event => event.seq === acceptedSeq) + expect(appended).toMatchObject({ type: 'session/title', data: { title: '重命名', messageSeqs: [], source: { kind: 'user' } }, }) @@ -1433,8 +1468,9 @@ describe('createFixtureApi', () => { await new Promise(resolve => setTimeout(resolve, 10)) await vi.waitFor(() => { const snapshot = followed.find(frame => frame.type === 'snapshot') - expect(snapshot?.events.some(entry => JSON.stringify(entry.event.data).includes('静默丢帧'))).toBe(true) - expect(snapshot?.events.some(entry => JSON.stringify(entry.event.data).includes('正常直播'))).toBe(true) + const events = snapshot === undefined ? [] : historyEvents(snapshot.records) + expect(events.some(event => JSON.stringify(event.data).includes('静默丢帧'))).toBe(true) + expect(events.some(event => JSON.stringify(event.data).includes('正常直播'))).toBe(true) }) hooks.appendTitle('fx-alpha', 'Fixture 修订标题') hooks.beginModelRetry('fx-alpha') @@ -1456,7 +1492,7 @@ describe('createFixtureApi', () => { // Paging and resumed follow agree on the recovered durable event. const repull = await api.sessions.history(req({ sessionId: sid('fx-alpha'), maxMessages: 5 })) if (!repull.result.ok) throw new Error('repull failed') - expect(JSON.stringify(repull.result.value.events)).toContain('静默丢帧') + expect(JSON.stringify(repull.result.value.records)).toContain('静默丢帧') // breakStreams force-ends follow and control without client aborts. await new Promise(resolve => setTimeout(resolve, 10)) hooks.breakStreams() @@ -1593,7 +1629,7 @@ describe('FixtureApiClient (protocol-level fake carrier)', () => { const goalHistory = await sessions.history({ sessionId: id }) if (!goalHistory.result.ok) throw new Error('goal history failed') - const goalEvents = goalHistory.result.value.events.map(entry => entry.event as unknown as { + const goalEvents = historyEvents(goalHistory.result.value.records).map(event => event as unknown as { type: string data: { operation?: string diff --git a/packages/client/ui-chat/README.i18n.yaml b/packages/client/ui-chat/README.i18n.yaml index bbb66d8882..9d7849145b 100644 --- a/packages/client/ui-chat/README.i18n.yaml +++ b/packages/client/ui-chat/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-chat/README.md -README.md: cc79de10289069ef94105397bd77a5194b4e6808 -README.zh.md: 3d4eb91492a497ff4544bd6378ae212810342c64 +README.md: 551824caf707c38fced5b813d82a5b9c746e7b82 +README.zh.md: a0ab1807d244db6e9ac9f7ac50847e5872c54f44 diff --git a/packages/client/ui-chat/README.md b/packages/client/ui-chat/README.md index cc79de1028..551824caf7 100644 --- a/packages/client/ui-chat/README.md +++ b/packages/client/ui-chat/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -The browser Chat target for Conversation assembly. It registers Chat event definitions and snapshot construction, supplies `useChat`, renders transcript nodes and details, and owns Chat-specific stores, actions, localization, and scroll restoration; historical image URLs resolve through the Conversation-owned per-session cache (`ctx.uiConversation.imageUrl`). +The browser Chat target for Conversation assembly. It registers Chat event definitions and snapshot construction, supplies `useChat`, renders transcript nodes and details, and owns Chat-specific stores, actions, localization, and scroll restoration; historical image URLs resolve through the Conversation-owned per-session cache (`ctx.uiConversation.imageUrl`). Its Assistant and Turn Tail definitions fold packed historical Assistant runs without expanding their members. ## System prompt row diff --git a/packages/client/ui-chat/README.zh.md b/packages/client/ui-chat/README.zh.md index 3d4eb91492..a0ab1807d2 100644 --- a/packages/client/ui-chat/README.zh.md +++ b/packages/client/ui-chat/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -Conversation 组装的浏览器 Chat target。本包注册 Chat event definition 与 snapshot 构造、提供 `useChat`、渲染 transcript node 和详情，并拥有 Chat 专属 store、action、本地化与滚动位置恢复；历史图片 URL 通过 Conversation 持有的按会话缓存（`ctx.uiConversation.imageUrl`）解析。 +Conversation 组装的浏览器 Chat target。本包注册 Chat event definition 与 snapshot 构造、提供 `useChat`、渲染 transcript node 和详情，并拥有 Chat 专属 store、action、本地化与滚动位置恢复；历史图片 URL 通过 Conversation 持有的按会话缓存（`ctx.uiConversation.imageUrl`）解析。其中 Assistant 与 Turn Tail definition 会直接 fold packed Assistant 历史 run，不展开其成员。 ## 系统提示词行 diff --git a/packages/client/ui-chat/src/client/conversation-nodes/assistant.ts b/packages/client/ui-chat/src/client/conversation-nodes/assistant.ts index f0f2b9be88..a6a460f0ea 100644 --- a/packages/client/ui-chat/src/client/conversation-nodes/assistant.ts +++ b/packages/client/ui-chat/src/client/conversation-nodes/assistant.ts @@ -1,4 +1,5 @@ import type { Context } from '@deepseek-ai/cordis' +import type { ChunkRowEvent } from '@deepseek-ai/dsh-api-session-controller/types' import type { ConversationLocation, ConversationMatch, ConversationNodeContext, ConversationNodeDefinition, } from '@deepseek-ai/dsh-client-ui-conversation/client' @@ -29,6 +30,7 @@ interface AssistantState { readonly turn: number readonly step: number readonly blocks: readonly (AssistantBlock | undefined)[] + readonly visibleBlocks: number readonly firstVisibleSeq: number | undefined readonly firstVisibleTime: number | undefined readonly firstTokenTime: number | undefined @@ -37,11 +39,18 @@ interface AssistantState { readonly usage: unknown } +function isChunkRunEvent(event: ConversationMatch['event']): event is ChunkRowEvent { + return event.type === 'chunkrow/text-chunks' + || event.type === 'chunkrow/reasoning-chunks' + || event.type === 'chunkrow/tool-call-chunks' +} + function initialState(turn: number, step: number): AssistantState { return { turn, step, blocks: [], + visibleBlocks: 0, firstVisibleSeq: undefined, firstVisibleTime: undefined, firstTokenTime: undefined, @@ -55,12 +64,20 @@ function compactBlocks(blocks: readonly (AssistantBlock | undefined)[]): Assista return blocks.filter((block): block is AssistantBlock => block !== undefined) } +function blockIsVisible(block: AssistantBlock | undefined): boolean { + if (block === undefined || block.kind === 'tool-call') return false + if (block.kind === 'text' || block.kind === 'reasoning') return block.text.trim() !== '' + return true +} + +function countVisibleBlocks(blocks: readonly AssistantBlock[]): number { + let count = 0 + for (const block of blocks) if (blockIsVisible(block)) count++ + return count +} + function hasVisibleContent(blocks: readonly AssistantBlock[]): boolean { - return blocks.some((block) => { - if (block.kind === 'tool-call') return false - if (block.kind === 'text' || block.kind === 'reasoning') return block.text.trim() !== '' - return true - }) + return blocks.some(blockIsVisible) } function hasInterruptionEvidence(blocks: readonly AssistantBlock[]): boolean { @@ -82,22 +99,32 @@ function updateChunk(state: AssistantState, match: ConversationMatch): Assistant if (match.event.type !== 'assistant/chunk') return state const chunk = match.event.data.chunk const blocks = [...state.blocks] + let changedIndex = -1 + let previousVisible = false switch (chunk.type) { case 'block-start': + changedIndex = chunk.index + previousVisible = blockIsVisible(blocks[chunk.index]) blocks[chunk.index] = emptyAssistantBlock(chunk.blockType) break case 'text-delta': { const previous = blocks[chunk.index] + changedIndex = chunk.index + previousVisible = blockIsVisible(previous) blocks[chunk.index] = { kind: 'text', text: (previous?.kind === 'text' ? previous.text : '') + chunk.text } break } case 'reasoning-delta': { const previous = blocks[chunk.index] + changedIndex = chunk.index + previousVisible = blockIsVisible(previous) blocks[chunk.index] = { kind: 'reasoning', text: (previous?.kind === 'reasoning' ? previous.text : '') + chunk.text } break } case 'tool-call-delta': { const previous = blocks[chunk.index] + changedIndex = chunk.index + previousVisible = blockIsVisible(previous) const base = previous?.kind === 'tool-call' ? previous : { kind: 'tool-call' as const, callId: '', name: '', argsRaw: '' } @@ -110,6 +137,8 @@ function updateChunk(state: AssistantState, match: ConversationMatch): Assistant break } case 'block-end': + changedIndex = chunk.index + previousVisible = blockIsVisible(blocks[chunk.index]) blocks[chunk.index] = toAssistantBlock(chunk.block) break case 'usage': @@ -117,13 +146,16 @@ function updateChunk(state: AssistantState, match: ConversationMatch): Assistant default: return state } - const visible = hasVisibleContent(compactBlocks(blocks)) + const visibleBlocks = state.visibleBlocks + - Number(previousVisible) + + Number(blockIsVisible(blocks[changedIndex])) const firstToken = isTokenDelta(chunk) return { ...state, blocks, - hidden: visible ? false : state.hidden, - ...visible && state.firstVisibleSeq === undefined + visibleBlocks, + hidden: visibleBlocks > 0 ? false : state.hidden, + ...visibleBlocks > 0 && state.firstVisibleSeq === undefined ? { firstVisibleSeq: match.event.seq, firstVisibleTime: match.event.time } : {}, ...firstToken && state.firstTokenTime === undefined @@ -132,6 +164,88 @@ function updateChunk(state: AssistantState, match: ConversationMatch): Assistant } } +interface ChunkRunBoundaries { + readonly firstTokenTime: number | undefined + readonly firstVisible: { readonly seq: number; readonly time: number } | undefined +} + +function chunkRunBoundaries( + event: ChunkRowEvent, + needsToken: boolean, + needsVisible: boolean, + visibleFromStart: boolean, +): ChunkRunBoundaries { + const fragments = event.type === 'chunkrow/tool-call-chunks' ? event.data.args : event.data.texts + const nameStartsToken = event.type === 'chunkrow/tool-call-chunks' + && Object.hasOwn(event.data, 'name') + let firstTokenTime: number | undefined + let firstVisible: ChunkRunBoundaries['firstVisible'] + let time = event.time + for (let index = 0; index < fragments.length; index++) { + const fragment = fragments[index] as string + if (needsToken && firstTokenTime === undefined && (nameStartsToken || fragment !== '')) { + firstTokenTime = time + } + if (needsVisible && firstVisible === undefined + && (visibleFromStart + || (event.type !== 'chunkrow/tool-call-chunks' && fragment.trim() !== ''))) { + firstVisible = { seq: event.seq + index, time } + } + if ((!needsToken || firstTokenTime !== undefined) + && (!needsVisible || firstVisible !== undefined)) break + time += event.data.dt[index] ?? 0 + } + return { firstTokenTime, firstVisible } +} + +function updateChunkRun(state: AssistantState, event: ChunkRowEvent): AssistantState { + const blocks = [...state.blocks] + const previous = blocks[event.data.index] + const previousVisible = blockIsVisible(previous) + let visibleFromStart = state.visibleBlocks - Number(previousVisible) > 0 + if (event.type === 'chunkrow/text-chunks') { + const text = previous?.kind === 'text' ? previous.text : '' + visibleFromStart ||= text.trim() !== '' + blocks[event.data.index] = { kind: 'text', text: text + event.data.texts.join('') } + } else if (event.type === 'chunkrow/reasoning-chunks') { + const text = previous?.kind === 'reasoning' ? previous.text : '' + visibleFromStart ||= text.trim() !== '' + blocks[event.data.index] = { kind: 'reasoning', text: text + event.data.texts.join('') } + } else { + const base = previous?.kind === 'tool-call' + ? previous + : { kind: 'tool-call' as const, callId: '', name: '', argsRaw: '' } + blocks[event.data.index] = { + kind: 'tool-call', + callId: base.callId || String(event.data.id), + name: Object.hasOwn(event.data, 'name') ? event.data.name as string : base.name, + argsRaw: base.argsRaw + event.data.args.join(''), + } + } + const boundaries = chunkRunBoundaries( + event, + state.firstTokenTime === undefined, + state.firstVisibleSeq === undefined, + visibleFromStart, + ) + const visibleBlocks = state.visibleBlocks + - Number(previousVisible) + + Number(blockIsVisible(blocks[event.data.index])) + return { + ...state, + blocks, + visibleBlocks, + hidden: visibleBlocks > 0 ? false : state.hidden, + ...(boundaries.firstVisible === undefined ? {} : { + firstVisibleSeq: boundaries.firstVisible.seq, + firstVisibleTime: boundaries.firstVisible.time, + }), + ...(boundaries.firstTokenTime === undefined ? {} : { + firstTokenTime: boundaries.firstTokenTime, + }), + } +} + function closedBoundary(location: ConversationLocation): { seq: number; time: number } | undefined { if (location.kind === 'step' && location.step.status === 'closed' && location.step.end !== undefined) { return location.step.end @@ -169,8 +283,9 @@ function finalNode( } const location = context.start?.location ?? context.matches.at(-1)?.location const boundary = location === undefined ? undefined : closedBoundary(location) + if (boundary === undefined) return undefined const blocks = compactBlocks(state.blocks) - if (boundary === undefined || !hasInterruptionEvidence(blocks)) return undefined + if (!hasInterruptionEvidence(blocks)) return undefined return { kind: 'assistant', seq: boundary.seq + CHAT_SYNTHETIC_SEQ_OFFSETS.interruptedAssistant, @@ -185,6 +300,11 @@ function finalNode( function fallbackState(context: ConversationNodeContext): AssistantState | undefined { let state: AssistantState | undefined for (const match of context.matches) { + if (isChunkRunEvent(match.event)) { + state ??= initialState(match.event.data.turn, match.event.data.step) + state = updateChunkRun(state, match.event) + continue + } if (match.event.type === 'assistant/chunk') { state ??= initialState(match.event.data.turn, match.event.data.step) state = updateChunk(state, match) @@ -192,9 +312,11 @@ function fallbackState(context: ConversationNodeContext): Assist } if (match.event.type === 'assistant/message') { state ??= initialState(match.event.data.turn, match.event.data.step) + const blocks = toAssistantBlocks(match.event.data.message.content) state = { ...state, - blocks: toAssistantBlocks(match.event.data.message.content), + blocks, + visibleBlocks: countVisibleBlocks(blocks), hidden: false, final: match, usage: match.event.data.usage, @@ -220,7 +342,7 @@ function projectAssistant(context: ConversationNodeContext): Ass if (state === undefined) return undefined const settled = finalNode(state, context) const blocks = settled?.blocks ?? compactBlocks(state.blocks) - const visible = hasVisibleContent(blocks) + const visible = settled === undefined ? state.visibleBlocks > 0 : hasVisibleContent(blocks) const status = settled?.interrupted === true ? 'interrupted' : settled === undefined ? 'running' : 'settled' @@ -252,6 +374,9 @@ export const assistantDefinition: ConversationNodeDefinition = { || (event.type === 'assistant/message' && isAppendSurfaceEvent(event))) { return { id: `${event.data.turn}:${event.data.step}`, role: 'update' } } + if (isChunkRunEvent(event)) { + return { id: `${event.data.turn}:${event.data.step}`, role: 'update' } + } if (event.type === 'llm/retry') { return { id: `${event.data.turn}:${event.data.step}`, role: 'update' } } @@ -262,11 +387,16 @@ export const assistantDefinition: ConversationNodeDefinition = { return initialState(match.event.data.turn, match.event.data.step) }, update: (context, match) => { + if (isChunkRunEvent(match.event)) { + return updateChunkRun(context.state, match.event) + } if (match.event.type === 'assistant/chunk') return updateChunk(context.state, match) if (match.event.type === 'assistant/message') { + const blocks = toAssistantBlocks(match.event.data.message.content) return { ...context.state, - blocks: toAssistantBlocks(match.event.data.message.content), + blocks, + visibleBlocks: countVisibleBlocks(blocks), hidden: false, final: match, usage: match.event.data.usage, @@ -279,6 +409,7 @@ export const assistantDefinition: ConversationNodeDefinition = { }, publication: (match) => { if (match.event.type === 'step/start') return 'none' + if (isChunkRunEvent(match.event)) return 'animation-frame' if (match.event.type !== 'assistant/chunk') return 'immediate' const type = match.event.data.chunk.type return type === 'usage' || type === 'finish' ? 'none' : 'animation-frame' diff --git a/packages/client/ui-chat/src/client/conversation-nodes/fallback.ts b/packages/client/ui-chat/src/client/conversation-nodes/fallback.ts index 356b46ed62..5c5a77c82c 100644 --- a/packages/client/ui-chat/src/client/conversation-nodes/fallback.ts +++ b/packages/client/ui-chat/src/client/conversation-nodes/fallback.ts @@ -15,9 +15,12 @@ declare module '../contract/chat-nodes.ts' { export const unknownFallbackDefinition: ConversationNodeDefinition = { kind: 'unknown-surface', target: 'chat', - match: event => isAppendSurfaceEvent(event) - ? { id: String(event.seq), role: 'start' } - : null, + match: (event) => { + if (event.type === 'chunkrow/text-chunks' + || event.type === 'chunkrow/reasoning-chunks' + || event.type === 'chunkrow/tool-call-chunks') return null + return isAppendSurfaceEvent(event) ? { id: String(event.seq), role: 'start' } : null + }, start: (_context, match) => ({ kind: 'unknown', seq: match.event.seq, diff --git a/packages/client/ui-chat/src/client/conversation-nodes/retry.ts b/packages/client/ui-chat/src/client/conversation-nodes/retry.ts index 5209e1dbc2..eeaf8d461b 100644 --- a/packages/client/ui-chat/src/client/conversation-nodes/retry.ts +++ b/packages/client/ui-chat/src/client/conversation-nodes/retry.ts @@ -1,6 +1,6 @@ import type { Context } from '@deepseek-ai/cordis' import type { - ConversationLocation, ConversationNodeDefinition, + ConversationLocation, ConversationMatch, ConversationNodeDefinition, } from '@deepseek-ai/dsh-client-ui-conversation/client' import type {} from '@deepseek-ai/dsh-llm-retry/types' import type { RetryChatData } from '../contract/chat-nodes.ts' @@ -21,7 +21,7 @@ export interface RetryState { readonly attempts: readonly ModelRetryNode[] } -function scheduledNode(match: Parameters[1]): ModelRetryNode | undefined { +function scheduledNode(match: ConversationMatch): ModelRetryNode | undefined { if (match.event.type !== 'llm/retry') return undefined return { kind: 'model-retry', diff --git a/packages/client/ui-chat/src/client/conversation-nodes/turn-tail.ts b/packages/client/ui-chat/src/client/conversation-nodes/turn-tail.ts index 0ca941fb3a..9791ee5ceb 100644 --- a/packages/client/ui-chat/src/client/conversation-nodes/turn-tail.ts +++ b/packages/client/ui-chat/src/client/conversation-nodes/turn-tail.ts @@ -4,6 +4,7 @@ import type { } from '@deepseek-ai/dsh-client-ui-conversation/client' import type {} from '@deepseek-ai/dsh-llm-retry/types' import { isAppendSurfaceEvent } from '@deepseek-ai/dsh-session/surface' +import type { SessionEvent } from '@deepseek-ai/dsh-session/types' import { deriveTurnTokenUsage } from '@deepseek-ai/dsh-token-meter/client' import type { AssistantChatData, FinalAssistantChatData, TurnTailChatData, @@ -36,6 +37,12 @@ interface StepEvidence { readonly finalized: boolean } +function isSessionEvent(event: ConversationMatch['event']): event is SessionEvent { + return event.type !== 'chunkrow/text-chunks' + && event.type !== 'chunkrow/reasoning-chunks' + && event.type !== 'chunkrow/tool-call-chunks' +} + function hasTextAssistant(event: Parameters[0]): boolean { return event.type === 'assistant/message' && isAppendSurfaceEvent(event) @@ -44,6 +51,11 @@ function hasTextAssistant(event: Parameters } function chunkHasText(event: Parameters[0]): boolean { + if (event.type === 'chunkrow/text-chunks') { + return event.data.texts.some(text => text.trim() !== '') + } + if (event.type === 'chunkrow/reasoning-chunks' + || event.type === 'chunkrow/tool-call-chunks') return false if (event.type !== 'assistant/chunk') return false const chunk = event.data.chunk if (chunk.type === 'text-delta') return chunk.text.trim() !== '' @@ -59,6 +71,9 @@ function turnCoordinates(event: Parameters[ if (event.type === 'assistant/message' || event.type === 'assistant/chunk' || event.type === 'step/start' + || event.type === 'chunkrow/text-chunks' + || event.type === 'chunkrow/reasoning-chunks' + || event.type === 'chunkrow/tool-call-chunks' || event.type === 'step/end') { return { turn: event.data.turn, step: event.data.step } } @@ -80,7 +95,10 @@ function closingAnchor(context: ConversationNodeContext): number const coordinates = turnCoordinates(event) if (coordinates?.step === undefined) continue const previous = steps.get(coordinates.step) ?? { streamedText: false, finalized: false } - if (event.type === 'assistant/chunk') { + if (event.type === 'assistant/chunk' + || event.type === 'chunkrow/text-chunks' + || event.type === 'chunkrow/reasoning-chunks' + || event.type === 'chunkrow/tool-call-chunks') { steps.set(coordinates.step, { ...previous, streamedText: previous.streamedText || chunkHasText(event), @@ -143,7 +161,7 @@ function tailData(context: ConversationNodeContext): TurnTailChat } const metrics = deriveTurnMetrics(finalized.map(candidate => candidate.finalNode)).get(end.event.data.turn) const tokenUsage = context.start?.event.type === 'turn/start' - ? deriveTurnTokenUsage(context.matches.map(match => match.event)) + ? deriveTurnTokenUsage(context.matches.map(match => match.event).filter(isSessionEvent)) : undefined return { turn: end.event.data.turn, diff --git a/packages/client/ui-chat/tests/conversation-node-definitions.client.spec.ts b/packages/client/ui-chat/tests/conversation-node-definitions.client.spec.ts index 83af5fa4d7..14f291f117 100644 --- a/packages/client/ui-chat/tests/conversation-node-definitions.client.spec.ts +++ b/packages/client/ui-chat/tests/conversation-node-definitions.client.spec.ts @@ -2,12 +2,19 @@ import { describe, expect, it } from 'vitest' import type { ChatConversationViewNode, ChatSnapshot, } from '@deepseek-ai/dsh-client-ui-chat/client' +import type { + SessionEventLikeEntry, SessionLiveEventEntry, +} from '@deepseek-ai/dsh-api-session-controller/client' +import type { + ChunkRowEvent, +} from '@deepseek-ai/dsh-api-session-controller/types' import { ConversationNodeAssembler, - type ConversationEventInput, type ConversationNodeDefinition, type ConversationViewDefinition, } from '@deepseek-ai/dsh-client-ui-conversation/client' +import { isChunkRow, packChunkRuns, type ChunkRow } from '@deepseek-ai/dsh-session/chunk-rows' +import type { SessionEvent } from '@deepseek-ai/dsh-session/types' import { assistantDefinition } from '../src/client/conversation-nodes/assistant.ts' import { chatViewDefinition } from '../src/client/conversation-nodes/chat-snapshot-builder.ts' import { commandDefinition } from '../src/client/conversation-nodes/command.ts' @@ -62,19 +69,38 @@ function at( type: string, data: unknown, extra: Record = {}, -): ConversationEventInput { +): SessionLiveEventEntry { return { + type: 'event', event: { seq, time: 1_700_000_000_000 + seq, type, data, ...extra, - } as unknown as ConversationEventInput['event'], + } as unknown as SessionEvent, } } -function assembler(entries: readonly ConversationEventInput[] = [], hasMore = false): ConversationNodeAssembler { +function chunkEntry(row: ChunkRow): SessionEventLikeEntry { + return { + type: 'chunks', + event: { + type: `chunkrow/${row.type}`, + seq: row.seq0, + time: row.time0, + data: row.data, + } as ChunkRowEvent, + } +} + +function packedInputs(entries: readonly SessionLiveEventEntry[]): SessionEventLikeEntry[] { + return packChunkRuns(entries.map(entry => entry.event)).map((record) => { + return isChunkRow(record) ? chunkEntry(record) : { type: 'event', event: record } + }) +} + +function assembler(entries: readonly SessionEventLikeEntry[] = [], hasMore = false): ConversationNodeAssembler { const value = new ConversationNodeAssembler(new TestEventDefinitions(), new TestViewDefinitions()) value.replaceWindow(entries, hasMore) value.flush() @@ -311,6 +337,139 @@ describe('built-in conversation node Definitions', () => { }) }) + it('folds packed Assistant runs to the same Chat and Turn Tail state as scalar deltas', () => { + const runningHistory = [ + at(1, 'turn/start', { turn: 1 }), + at(2, 'step/start', { turn: 1, step: 1 }), + at(3, 'assistant/chunk', { + turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: '' }, + }, { time: 1_000 }), + at(4, 'assistant/chunk', { + turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: ' ' }, + }, { time: 1_000 }), + at(5, 'assistant/chunk', { + turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: '\t' }, + }, { time: 995 }), + at(6, 'assistant/chunk', { + turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'answer' }, + }, { time: 1_004 }), + at(7, 'assistant/chunk', { + turn: 1, step: 1, chunk: { type: 'reasoning-delta', index: 1, text: '' }, + }), + at(8, 'assistant/chunk', { + turn: 1, step: 1, chunk: { type: 'reasoning-delta', index: 1, text: 'think' }, + }), + at(9, 'assistant/chunk', { + turn: 1, step: 1, chunk: { type: 'reasoning-delta', index: 1, text: 'ing' }, + }), + at(10, 'assistant/chunk', { + turn: 1, step: 1, + chunk: { type: 'tool-call-delta', index: 2, id: 'call-1', argumentsDelta: '' }, + }), + at(11, 'assistant/chunk', { + turn: 1, step: 1, + chunk: { type: 'tool-call-delta', index: 2, id: 'call-1', argumentsDelta: '{"x":' }, + }), + at(12, 'assistant/chunk', { + turn: 1, step: 1, + chunk: { type: 'tool-call-delta', index: 2, id: 'call-1', argumentsDelta: '1}' }, + }), + ] + const scalar = assembler(runningHistory) + const packedHistory = packedInputs(runningHistory) + expect(packedHistory.filter(input => input.event.type.startsWith('chunkrow/'))).toHaveLength(3) + const packed = assembler(packedHistory) + + expect(snapshot(packed)).toEqual(snapshot(scalar)) + const running = node(snapshot(packed), 'assistant-step') + expect(running).toMatchObject({ anchorSeq: 6 }) + expect(running?.data).toMatchObject({ + time: 1_004, + blocks: [ + { kind: 'text', text: ' \tanswer' }, + { kind: 'reasoning', text: 'thinking' }, + { kind: 'tool-call', callId: 'call-1', name: '', argsRaw: '{"x":1}' }, + ], + }) + + for (const value of [scalar, packed]) { + value.append(at(13, 'step/end', { turn: 1, step: 1 })) + value.append(at(14, 'turn/end', { turn: 1, reason: { kind: 'completed' } })) + value.flush() + } + expect(snapshot(packed)).toEqual(snapshot(scalar)) + expect(node(snapshot(packed), 'turn-tail')?.anchorSeq).toBe(12.2) + + const partialHistory = [ + ...runningHistory.slice(2), + at(13, 'step/end', { turn: 1, step: 1 }), + at(14, 'turn/end', { turn: 1, reason: { kind: 'completed' } }), + ] + const partialScalar = snapshot(assembler(partialHistory, true)) + const partialPacked = snapshot(assembler(packedInputs(partialHistory), true)) + expect(partialPacked).toEqual(partialScalar) + expect(node(partialPacked, 'assistant-step')?.data).toMatchObject({ status: 'interrupted' }) + expect(node(partialPacked, 'turn-tail')?.anchorSeq).toBe(12.2) + + const finalizedHistory = [ + at(20, 'turn/start', { turn: 2 }), + at(21, 'step/start', { turn: 2, step: 1 }), + at(22, 'assistant/chunk', { + turn: 2, step: 1, chunk: { type: 'text-delta', index: 0, text: '' }, + }, { time: 2_000 }), + at(23, 'assistant/chunk', { + turn: 2, step: 1, chunk: { type: 'text-delta', index: 0, text: ' ' }, + }, { time: 1_999 }), + at(24, 'assistant/chunk', { + turn: 2, step: 1, chunk: { type: 'text-delta', index: 0, text: 'first' }, + }, { time: 2_000 }), + at(25, 'llm/retry', { + retryId: 'packed-retry', turn: 2, step: 1, provider: 'fake', mode: 'normal', + policyKey: 'fake-normal', retry: 1, maxRetries: 2, delayMs: 10, + failure: { code: 'TRANSPORT', message: 'temporary' }, + }), + at(26, 'assistant/chunk', { + turn: 2, step: 1, chunk: { type: 'text-delta', index: 0, text: '' }, + }), + at(27, 'assistant/chunk', { + turn: 2, step: 1, chunk: { type: 'text-delta', index: 0, text: 'second' }, + }), + at(28, 'assistant/chunk', { + turn: 2, step: 1, chunk: { type: 'text-delta', index: 0, text: ' attempt' }, + }), + at(29, 'assistant/message', { + turn: 2, step: 1, message: assistantMessage('packed-final', 'done'), + }, { surfaceOp: 'append' }), + ] + const finalizedScalar = snapshot(assembler(finalizedHistory)) + const finalizedPacked = snapshot(assembler(packedInputs(finalizedHistory))) + expect(finalizedPacked).toEqual(finalizedScalar) + const finalNode = (node(finalizedPacked, 'assistant-step')?.data as AssistantChatData).finalNode + expect(finalNode?.timing?.firstTokenTime).toBe(1_999) + + const namedToolHistory = [ + at(40, 'turn/start', { turn: 3 }), + at(41, 'step/start', { turn: 3, step: 1 }), + ...[42, 43, 44].map(seq => at(seq, 'assistant/chunk', { + turn: 3, step: 1, + chunk: { type: 'tool-call-delta', index: 0, id: 'call-2', name: 'read', argumentsDelta: '' }, + }, { time: 4_000 + seq - 42 })), + at(45, 'assistant/message', { + turn: 3, + step: 1, + message: { + ...assistantMessage('named-tool-final', ''), + content: [{ type: 'tool-call', id: 'call-2', name: 'read', arguments: '' }], + }, + }, { surfaceOp: 'append' }), + ] + const namedToolScalar = snapshot(assembler(namedToolHistory)) + const namedToolPacked = snapshot(assembler(packedInputs(namedToolHistory))) + expect(namedToolPacked).toEqual(namedToolScalar) + const namedTool = (node(namedToolPacked, 'assistant-step')?.data as AssistantChatData).finalNode + expect(namedTool?.timing?.firstTokenTime).toBe(4_000) + }) + it('keeps one keyed Tool node from running through settlement and replays nested dispatch after prepend', () => { const value = assembler([ at(1, 'turn/start', { turn: 1 }), diff --git a/packages/client/ui-conversation/README.i18n.yaml b/packages/client/ui-conversation/README.i18n.yaml index 7169ca2c67..074dd13968 100644 --- a/packages/client/ui-conversation/README.i18n.yaml +++ b/packages/client/ui-conversation/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-conversation/README.md -README.md: 8506cc9e2d2935151003ad11e34d056dda70e0ff -README.zh.md: bf6643112878f6537d3db1d1686db046202fada5 +README.md: 95eba59baa637e32b7bec596bc1cd3b1a44e789c +README.zh.md: 17dfd95b6f3928ed74abafd08689bc245fd1c16f diff --git a/packages/client/ui-conversation/README.md b/packages/client/ui-conversation/README.md index 8506cc9e2d..95eba59baa 100644 --- a/packages/client/ui-conversation/README.md +++ b/packages/client/ui-conversation/README.md @@ -2,13 +2,13 @@ English | [中文](README.zh.md) -`ui-conversation` owns target-neutral Conversation assembly and the shared browser shell. It consumes Session Controller event feeds, exposes React-free registries and per-Session bindings through `ctx.uiConversation`, and contributes the `useConversation`, `useInput`, and `inputActions` standard props through `ctx.uiSession`. It also owns the per-session durable image URL cache: `ctx.uiConversation.imageUrl(sessionId, attachment)` resolves one session-authorized browser URL per attachment and revokes it with the Session binding, so every Conversation target shares one `session.attachment` read. Concrete targets such as Chat are separate packages that register their own Definitions, snapshot builders, Views, and renderers. +`ui-conversation` owns target-neutral Conversation assembly and the shared browser shell. It consumes Session Controller `SessionEventLikeEntry` feeds, exposes React-free registries and per-Session bindings through `ctx.uiConversation`, and contributes the `useConversation`, `useInput`, and `inputActions` standard props through `ctx.uiSession`. It also owns the per-session durable image URL cache: `ctx.uiConversation.imageUrl(sessionId, attachment)` resolves one session-authorized browser URL per attachment and revokes it with the Session binding, so every Conversation target shares one `session.attachment` read. Concrete targets such as Chat are separate packages that register their own Definitions, snapshot builders, Views, and renderers. ## Conversation assembly `UiConversation.events` is the single registry for event Definitions, and `UiConversation.views` is the single registry for target snapshot builders. Both registries reject duplicate keys, preserve registration order, return idempotent disposers, and rebuild existing bindings when their contribution roster changes. `UiConversation.binding(bindingOrSessionId)` returns one identity-stable Conversation binding for the current Session Controller binding. It does not open another event source. -The adapter converts each `SessionEventEntry` to a `{ event }` `ConversationEventInput` and preserves the raw Session event, including tool-result metadata. Contiguous append and prepend revisions use incremental assembly; replacement windows and revision gaps rebuild from the complete loaded window. The assembler owns Context matching, Turn/Step locations, target node materialization, target activity, and stable target sources. `ConversationSnapshot` contains only target-neutral views and active-target facts; Session lifecycle state remains in `SessionSnapshot`. +The adapter passes each `SessionEventLikeEntry` directly to the assembler. Its outer `type` distinguishes scalar and packed records, while its inner `event` always exposes `type`, `seq`, `time`, and `data`; Definitions receive that inner `SessionEventLike`. Historical replace and prepend accept both entry variants, while live append accepts only `SessionLiveEventEntry`. Every Definition uses the same `match` and `update` methods for both event forms, while `start` receives only a standard event and the assembler rejects a packed start. Definitions that do not consume Assistant deltas return `null` for the packed tags. Replacement windows and revision gaps rebuild from the complete loaded window; contiguous append and prepend revisions use incremental assembly without expanding packed members. The assembler owns Context matching, Turn/Step locations, target node materialization, target activity, and stable target sources. `ConversationSnapshot` contains only target-neutral views and active-target facts; Session lifecycle state remains in `SessionSnapshot`. Target packages declaration-merge their snapshot and Location data maps, then register with `ctx.uiConversation.events.register(...)` and `ctx.uiConversation.views.register(...)`. A target reads its Session-owned source with `ctx.uiConversation.binding(binding).target(targetId)`. Registrations are Cordis effects and their returned disposers remove the contribution from the same registry. diff --git a/packages/client/ui-conversation/README.zh.md b/packages/client/ui-conversation/README.zh.md index bf66431128..17dfd95b6f 100644 --- a/packages/client/ui-conversation/README.zh.md +++ b/packages/client/ui-conversation/README.zh.md @@ -2,13 +2,13 @@ [English](README.md) | 中文 -`ui-conversation` 拥有与 target 无关的 Conversation 组装和共享浏览器 shell。它消费 Session Controller event feed，通过 `ctx.uiConversation` 暴露不依赖 React 的 registry 与逐 Session binding，并通过 `ctx.uiSession` 提供 `useConversation`、`useInput` 和 `inputActions` 标准 props。它还拥有按会话的持久化图片 URL 缓存：`ctx.uiConversation.imageUrl(sessionId, attachment)` 为每个附件解析一个经会话授权的浏览器 URL，并随 Session binding 释放而撤销，因此所有 Conversation target 共享一次 `session.attachment` 读取。Chat 等具体 target 位于独立 package，由各自 package 注册 Definition、snapshot builder、View 和 renderer。 +`ui-conversation` 拥有与 target 无关的 Conversation 组装和共享浏览器 shell。它消费 Session Controller 的 `SessionEventLikeEntry` feed，通过 `ctx.uiConversation` 暴露不依赖 React 的 registry 与逐 Session binding，并通过 `ctx.uiSession` 提供 `useConversation`、`useInput` 和 `inputActions` 标准 props。它还拥有按会话的持久化图片 URL 缓存：`ctx.uiConversation.imageUrl(sessionId, attachment)` 为每个附件解析一个经会话授权的浏览器 URL，并随 Session binding 释放而撤销，因此所有 Conversation target 共享一次 `session.attachment` 读取。Chat 等具体 target 位于独立 package，由各自 package 注册 Definition、snapshot builder、View 和 renderer。 ## Conversation 组装 `UiConversation.events` 是 event Definition 的唯一 registry，`UiConversation.views` 是 target snapshot builder 的唯一 registry。两者都拒绝重复 key、保持注册顺序、返回幂等 disposer，并在 contribution roster 变化时重建现有 binding。`UiConversation.binding(bindingOrSessionId)` 为当前 Session Controller binding 返回 identity 稳定的 Conversation binding，不会另开 event source。 -adapter 将每个 `SessionEventEntry` 转换成 `{ event }` 形式的 `ConversationEventInput`，并保留原始 Session event，包括工具结果 metadata。连续 revision 的 append 和 prepend 使用增量组装；replace window 或 revision 断档从完整已加载窗口重建。assembler 拥有 Context 匹配、Turn/Step location、target node 物化、target activity 和稳定 target source。`ConversationSnapshot` 只包含与 target 无关的 View 与 active-target 事实；Session lifecycle 状态仍属于 `SessionSnapshot`。 +adapter 把每个 `SessionEventLikeEntry` 直接交给 assembler。外层 `type` 区分 scalar 与 packed record，内部 `event` 则统一公开 `type`、`seq`、`time` 与 `data`；Definition 接收这个内部 `SessionEventLike`。历史 replace 与 prepend 接受两种 entry，实时 append 只接受 `SessionLiveEventEntry`。两种 event 都使用 Definition 的同一组 `match` 与 `update` 方法，`start` 则只接收标准 event，assembler 会拒绝 packed start。不消费 Assistant delta 的 Definition 对 packed tag 返回 `null`。replace window 或 revision 断档从完整已加载窗口重建；连续 revision 的 append 和 prepend 使用增量组装，并且不展开 packed member。assembler 拥有 Context 匹配、Turn/Step location、target node 物化、target activity 和稳定 target source。`ConversationSnapshot` 只包含与 target 无关的 View 与 active-target 事实；Session lifecycle 状态仍属于 `SessionSnapshot`。 target package 通过 declaration merge 扩展 snapshot 与 Location data map，再调用 `ctx.uiConversation.events.register(...)` 和 `ctx.uiConversation.views.register(...)`。target 通过 `ctx.uiConversation.binding(binding).target(targetId)` 读取其 Session-owned source。注册属于 Cordis effect，返回的 disposer 从同一个 registry 移除 contribution。 diff --git a/packages/client/ui-conversation/package.json b/packages/client/ui-conversation/package.json index e80dd8e04f..76655ba2da 100644 --- a/packages/client/ui-conversation/package.json +++ b/packages/client/ui-conversation/package.json @@ -112,7 +112,8 @@ "@deepseek-ai/dsh-workspace": "workspace:^", "@deepseek-ai/dsh-util-workspace-path": "workspace:^", "@types/react": "~18.3.1", - "react": "^18.2.0" + "react": "^18.2.0", + "zod": "^4.4.3" }, "files": [ "lib/index.js", diff --git a/packages/client/ui-conversation/src/client/contract/conversation.ts b/packages/client/ui-conversation/src/client/contract/conversation.ts index d8954bb8cf..1fdb89053f 100644 --- a/packages/client/ui-conversation/src/client/contract/conversation.ts +++ b/packages/client/ui-conversation/src/client/contract/conversation.ts @@ -1,14 +1,10 @@ +import type { SessionEventLike } from '@deepseek-ai/dsh-api-session-controller/client' import type { SessionEvent } from '@deepseek-ai/dsh-session/types' /* oxlint-disable typescript/no-duplicate-type-constituents, typescript/no-redundant-type-constituents -- * The unaugmented declaration-merge maps intentionally resolve to never in the Runtime program; * installed business packages supply their concrete keys in consuming Client programs. */ -/** One raw Session log event consumed by Conversation assembly. */ -export interface ConversationEventInput { - readonly event: SessionEvent -} - /** Definition-local identity and lifecycle role extracted from one event. */ export interface ConversationMatchResult { readonly id: string @@ -93,12 +89,23 @@ export type ConversationLocation = | { readonly kind: 'step'; readonly turn: TurnLocation; readonly step: StepLocation } | { readonly kind: 'unresolved' } -/** One event accepted by a Definition, with its current resolved Location. */ -export interface ConversationMatch extends ConversationEventInput { - readonly role: 'start' | 'update' +interface ConversationMatchOf< + Event extends SessionEventLike, + Role extends ConversationMatchResult['role'], +> { + readonly event: Event + readonly role: Role readonly location: ConversationLocation } +/** One scalar event accepted as a Context's unique start. */ +export type ConversationStartMatch = ConversationMatchOf + +/** One event accepted by a Definition, with its lifecycle role and resolved Location. */ +export type ConversationMatch = + | ConversationStartMatch + | ConversationMatchOf + /** Target-neutral identity returned by a business Definition. */ export interface ConversationViewNode { readonly key: string @@ -125,7 +132,7 @@ export interface ConversationNodeContext { readonly kind: string readonly id: string readonly matches: readonly ConversationMatch[] - readonly start: ConversationMatch | undefined + readonly start: ConversationStartMatch | undefined readonly state: State | undefined readonly current: ReadonlyMap } @@ -164,10 +171,10 @@ export interface ConversationNodeDefinition { readonly target?: string /** * Extract this Definition's stable business identity from one event. - * @param event - raw Session event; no Context or history access is available. + * @param event - standard or compact Client history event; no Context or history access is available. * @returns identity and lifecycle role, or null when unrelated. */ - match(event: SessionEvent): ConversationMatchResult | null + match(event: SessionEventLike): ConversationMatchResult | null /** * Create State from the unique start Match. * @param context - complete evidence currently collected for the Context. @@ -177,7 +184,7 @@ export interface ConversationNodeDefinition { */ start( context: ConversationNodeContext, - match: ConversationMatch, + match: ConversationStartMatch, reader: ConversationContextReader, ): State /** diff --git a/packages/client/ui-conversation/src/client/conversation/assembler.ts b/packages/client/ui-conversation/src/client/conversation/assembler.ts index a51b531bfe..a8267bd6ba 100644 --- a/packages/client/ui-conversation/src/client/conversation/assembler.ts +++ b/packages/client/ui-conversation/src/client/conversation/assembler.ts @@ -1,7 +1,11 @@ import type { - ConversationContextReader, ConversationEventInput, ConversationLocationData, ConversationMatch, + SessionEventLikeEntry, SessionLiveEventEntry, +} from '@deepseek-ai/dsh-api-session-controller/client' +import type { + ConversationContextReader, ConversationLocationData, ConversationMatch, ConversationNodeContext, ConversationNodeDefinition, ConversationPreviousContext, ConversationLocationDataScope, ConversationPublication, ConversationViewBuilder, + ConversationStartMatch, ConversationViewDefinition, ConversationViewNode, ConversationViewSnapshotMap, ConversationViewSnapshotStore, } from '../contract/conversation.ts' @@ -23,7 +27,7 @@ interface InternalContext { readonly id: string readonly definition: ConversationNodeDefinition startSeq: number | undefined - start: ConversationMatch | undefined + start: ConversationStartMatch | undefined matches: ConversationMatch[] state: unknown revision: number @@ -117,6 +121,21 @@ function mergeMatches( return merged } +function conversationMatch( + key: string, + input: SessionEventLikeEntry, + role: ConversationMatch['role'], + location: ConversationMatch['location'], +): ConversationMatch { + if (role === 'start') { + if (input.type === 'chunks') { + throw new Error(`conversation Context ${key} received a packed start Match`) + } + return { event: input.event, role, location } + } + return { event: input.event, role, location } +} + /** Event Registry subset consumed by a Session-owned Assembler. */ export interface ConversationEventDefinitions { /** @returns ordinary Definitions in registration order. */ @@ -139,7 +158,7 @@ export class ConversationNodeAssembler implements ConversationViewSnapshotStore private readonly contexts = new Map() private readonly contextsByKind = new Map() private readonly contextsBySeq = new Map>() - private readonly inputs = new Map() + private readonly inputs = new Map() private readonly locationIndex = new ConversationLocationIndex() private readonly dirty = new Set() private readonly revised = new Set() @@ -166,7 +185,7 @@ export class ConversationNodeAssembler implements ConversationViewSnapshotStore * @param hasMore - whether older history remains outside the window. * @returns immediate publication request. */ - replaceWindow(entries: readonly ConversationEventInput[], hasMore: boolean): ConversationPublication { + replaceWindow(entries: readonly SessionEventLikeEntry[], hasMore: boolean): ConversationPublication { this.contexts.clear() this.contextsByKind.clear() this.contextsBySeq.clear() @@ -189,17 +208,18 @@ export class ConversationNodeAssembler implements ConversationViewSnapshotStore /** * Add one contiguous live tail event without scanning existing Contexts. - * @param input - appended Session event. + * @param record - appended Session event entry. * @returns highest requested publication cadence. */ - append(input: ConversationEventInput): ConversationPublication { - if (this.inputs.has(input.event.seq)) return 'none' + append(record: SessionLiveEventEntry): ConversationPublication { + const event = record.event + if (this.inputs.has(event.seq)) return 'none' this.revised.clear() - this.inputs.set(input.event.seq, input) + this.inputs.set(event.seq, record) let publication: ConversationPublication = 'none' - if (isLocationBoundary(input.event.type)) { + if (isLocationBoundary(event.type)) { const previousTimeline = this.locationIndex.snapshot() - const changed = this.locationIndex.appendBoundary(input.event) + const changed = this.locationIndex.appendBoundary(event) if (this.locationIndex.snapshot() !== previousTimeline) { this.timelineDirty = true publication = 'immediate' @@ -207,9 +227,9 @@ export class ConversationNodeAssembler implements ConversationViewSnapshotStore this.replayContexts(this.refreshMatchLocations(changed)) if (changed.size > 0) publication = 'immediate' } else { - this.locationIndex.appendNonBoundary(input.event) + this.locationIndex.appendNonBoundary(event) } - publication = maximumPublication(publication, this.matchInput(input)) + publication = maximumPublication(publication, this.matchInput(record)) if (this.replayRevisedDependents()) publication = 'immediate' this.revised.clear() return publication @@ -221,7 +241,7 @@ export class ConversationNodeAssembler implements ConversationViewSnapshotStore * @param hasMore - whether history still precedes the expanded window. * @returns highest requested publication cadence. */ - prepend(entries: readonly ConversationEventInput[], hasMore: boolean): ConversationPublication { + prepend(entries: readonly SessionEventLikeEntry[], hasMore: boolean): ConversationPublication { this.revised.clear() let publication: ConversationPublication = 'none' const previousHasMore = this.hasMore @@ -343,26 +363,27 @@ export class ConversationNodeAssembler implements ConversationViewSnapshotStore return active } - private sortedInputs(): ConversationEventInput[] { + private sortedInputs(): SessionEventLikeEntry[] { return [...this.inputs.values()].sort((left, right) => left.event.seq - right.event.seq) } - private matchInput(input: ConversationEventInput): ConversationPublication { + private matchInput(input: SessionEventLikeEntry): ConversationPublication { return this.dispatchInput(input, (definition, id, role) => this.acceptMatch(definition, id, role, input)) } private collectInput( - input: ConversationEventInput, + input: SessionEventLikeEntry, pending: Map, ): ConversationPublication { return this.dispatchInput(input, (definition, id, role) => { const key = conversationContextKey(definition.kind, id) - const match: ConversationMatch = { - ...input, + const match = conversationMatch( + key, + input, role, - location: this.locationIndex.locationOf(input.event), - } + this.locationIndex.locationOf(input.event), + ) const matches = pending.get(key) ?? [] matches.push({ definition, id, match }) pending.set(key, matches) @@ -371,17 +392,18 @@ export class ConversationNodeAssembler implements ConversationViewSnapshotStore } private dispatchInput( - input: ConversationEventInput, + input: SessionEventLikeEntry, accept: ( definition: ConversationNodeDefinition, id: string, role: ConversationMatch['role'], ) => ConversationPublication, ): ConversationPublication { + const event = input.event const matchedTargets = new Set() let publication: ConversationPublication = 'none' for (const definition of this.eventDefinitions.entries()) { - const result = definition.match(input.event) + const result = definition.match(event) if (result === null) continue if (definition.target !== undefined) matchedTargets.add(definition.target) publication = maximumPublication(publication, accept(definition, result.id, result.role)) @@ -389,7 +411,7 @@ export class ConversationNodeAssembler implements ConversationViewSnapshotStore const fallback = this.eventDefinitions.fallbackEntry() const target = fallback?.target if (fallback !== undefined && target !== undefined && !matchedTargets.has(target)) { - const result = fallback.match(input.event) + const result = fallback.match(event) if (result !== null) { publication = maximumPublication(publication, accept(fallback, result.id, result.role)) } @@ -401,7 +423,7 @@ export class ConversationNodeAssembler implements ConversationViewSnapshotStore definition: ConversationNodeDefinition, id: string, role: ConversationMatch['role'], - input: ConversationEventInput, + input: SessionEventLikeEntry, ): ConversationPublication { const key = conversationContextKey(definition.kind, id) let context = this.contexts.get(key) @@ -425,11 +447,12 @@ export class ConversationNodeAssembler implements ConversationViewSnapshotStore } this.contexts.set(key, context) } - const match: ConversationMatch = { - ...input, + const match = conversationMatch( + key, + input, role, - location: this.locationIndex.locationOf(input.event), - } + this.locationIndex.locationOf(input.event), + ) const previous = context.matches.at(-1) if (previous !== undefined && previous.event.seq >= input.event.seq) { throw new Error(`conversation Context ${key} received non-appended Match ${input.event.seq}`) @@ -438,7 +461,7 @@ export class ConversationNodeAssembler implements ConversationViewSnapshotStore throw new Error(`conversation Context ${key} received an update before its start Match`) } context.matches.push(match) - if (role === 'start') { + if (match.role === 'start') { context.startSeq = input.event.seq context.start = match this.indexStartedContext(context) @@ -447,7 +470,7 @@ export class ConversationNodeAssembler implements ConversationViewSnapshotStore owners.add(context) this.contextsBySeq.set(input.event.seq, owners) - if (role === 'start') { + if (match.role === 'start') { this.replayContext(context) } else if (context.state !== undefined) { const typed = contextSnapshot(context) as ConversationNodeContext & { readonly state: unknown } @@ -485,7 +508,7 @@ export class ConversationNodeAssembler implements ConversationViewSnapshotStore } this.contexts.set(key, context) } - let discoveredStart: ConversationMatch | undefined + let discoveredStart: ConversationStartMatch | undefined const additions = entries .map((entry) => { if (entry.definition !== context.definition || entry.id !== context.id) { @@ -707,9 +730,15 @@ export class ConversationNodeAssembler implements ConversationViewSnapshotStore let start = context.start const matches = context.matches.map((match): ConversationMatch => { if (!changedSeqs.has(match.event.seq)) return match - const refreshed = { ...match, location: this.locationIndex.locationOf(match.event) } - if (match === start) start = refreshed - return refreshed + if (match.role === 'start') { + const refreshed: ConversationStartMatch = { + ...match, + location: this.locationIndex.locationOf(match.event), + } + if (match === start) start = refreshed + return refreshed + } + return { ...match, location: this.locationIndex.locationOf(match.event) } }) context.matches = matches context.start = start diff --git a/packages/client/ui-conversation/src/client/conversation/assembly.ts b/packages/client/ui-conversation/src/client/conversation/assembly.ts index 9a8a429292..ffb132cd92 100644 --- a/packages/client/ui-conversation/src/client/conversation/assembly.ts +++ b/packages/client/ui-conversation/src/client/conversation/assembly.ts @@ -4,13 +4,12 @@ import type { ImageAttachmentRef } from '@deepseek-ai/dsh-attachment' import type { ISessions, SessionBinding, SessionEventSource, SessionEventWindow, } from '@deepseek-ai/dsh-api-session-controller/client' -import type { SessionEventEntry } from '@deepseek-ai/dsh-api-session-controller/types' import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session/types' import { createSnapshotStore, type ObservableSnapshot, type SnapshotStore, } from '@deepseek-ai/dsh-client-store' import type { - ConversationEventInput, ConversationPublication, ConversationViewSnapshotMap, + ConversationPublication, ConversationViewSnapshotMap, ConversationViewSnapshotStore, } from '../contract/conversation.ts' import type { ConversationSnapshot } from '../contract/snapshot.ts' @@ -81,7 +80,7 @@ class BoundConversation implements ConversationBinding { private replace(window: SessionEventWindow): void { this.revision = window.revision - this.publish(this.assembler.replaceWindow(window.entries.map(conversationInput), window.hasMore)) + this.publish(this.assembler.replaceWindow(window.entries, window.hasMore)) } private accept(window: SessionEventWindow): void { @@ -93,12 +92,12 @@ class BoundConversation implements ConversationBinding { this.revision = window.revision switch (window.change.kind) { case 'prepend': - this.publish(this.assembler.prepend(window.change.entries.map(conversationInput), window.hasMore)) + this.publish(this.assembler.prepend(window.change.entries, window.hasMore)) return case 'append': { let publication: ConversationPublication = 'none' - for (const entry of window.change.entries) { - const next = this.assembler.append(conversationInput(entry)) + for (const event of window.change.entries) { + const next = this.assembler.append(event) if (next === 'immediate' || publication === 'none') publication = next } this.publish(publication) @@ -131,10 +130,6 @@ class BoundConversation implements ConversationBinding { } } -function conversationInput(entry: SessionEventEntry): ConversationEventInput { - return { event: entry.event as unknown as SessionEvent } -} - interface BindingRecord { readonly source: SessionBinding readonly binding: BoundConversation diff --git a/packages/client/ui-conversation/src/client/conversation/location-index.ts b/packages/client/ui-conversation/src/client/conversation/location-index.ts index f4ce189b13..9b5f966bcd 100644 --- a/packages/client/ui-conversation/src/client/conversation/location-index.ts +++ b/packages/client/ui-conversation/src/client/conversation/location-index.ts @@ -1,6 +1,9 @@ +import { + type SessionEventLike, type SessionEventLikeEntry, +} from '@deepseek-ai/dsh-api-session-controller/client' import type { SessionEvent } from '@deepseek-ai/dsh-session/types' import type { - ConversationEventInput, ConversationLocation, ConversationLocationData, + ConversationLocation, ConversationLocationData, ConversationLocationDataStore, ConversationStepDataMap, ConversationTimelineSnapshot, ConversationTurnDataMap, StepLocation, TurnLocation, } from '../contract/conversation.ts' @@ -82,7 +85,7 @@ interface TurnDraft { const SESSION_LOCATION = { kind: 'session' } as const const UNRESOLVED_LOCATION = { kind: 'unresolved' } as const -function payloadCoordinates(event: SessionEvent): Coordinates { +function payloadCoordinates(event: SessionEventLike): Coordinates { const data = event.data as unknown as { turn?: unknown; step?: unknown } if (data.turn === null) return { session: true } const turn = Number.isSafeInteger(data.turn) && (data.turn as number) >= 0 @@ -194,7 +197,7 @@ export class ConversationLocationIndex { * @param event - event already ingested into this index. * @returns current Location, falling back to session when it has no Turn/Step affinity. */ - locationOf(event: SessionEvent): ConversationLocation { + locationOf(event: SessionEventLike): ConversationLocation { return this.locations.get(event.seq) ?? SESSION_LOCATION } @@ -203,7 +206,7 @@ export class ConversationLocationIndex { * @param entries - complete current window in ascending seq order. * @returns seqs whose resolved Location changed. */ - rebuild(entries: readonly ConversationEventInput[]): ReadonlySet { + rebuild(entries: readonly SessionEventLikeEntry[]): ReadonlySet { const previousLocations = this.locations const turns = new Map() const coordinates = new Map() diff --git a/packages/client/ui-conversation/src/client/index.ts b/packages/client/ui-conversation/src/client/index.ts index 587772b9d3..67e2f28611 100644 --- a/packages/client/ui-conversation/src/client/index.ts +++ b/packages/client/ui-conversation/src/client/index.ts @@ -5,10 +5,11 @@ export type { ConversationBinding } from './conversation/assembly.ts' export { ConversationController, UnsupportedImageMediaTypeError } from './service.ts' export type { IConversation } from './service.ts' export type { - ConversationContextReader, ConversationEventInput, ConversationLocation, + ConversationContextReader, ConversationLocation, ConversationLocationData, ConversationLocationDataScope, ConversationLocationDataStore, ConversationMatch, ConversationMatchResult, ConversationNodeContext, ConversationNodeDefinition, ConversationPreviousContext, ConversationPublication, + ConversationStartMatch, ConversationStepDataMap, ConversationTimelineSnapshot, ConversationTurnDataMap, ConversationViewBuilder, ConversationViewDefinition, ConversationViewNode, ConversationViewSnapshotMap, ConversationViewSnapshotStore, StepLocation, TurnLocation, diff --git a/packages/client/ui-conversation/tests/conversation-assembler.client.spec.ts b/packages/client/ui-conversation/tests/conversation-assembler.client.spec.ts index ed2c25bd15..6465559e96 100644 --- a/packages/client/ui-conversation/tests/conversation-assembler.client.spec.ts +++ b/packages/client/ui-conversation/tests/conversation-assembler.client.spec.ts @@ -1,8 +1,13 @@ import { describe, expect, it, vi } from 'vitest' +import type { + SessionEventLike, SessionEventLikeEntry, SessionLiveEventEntry, +} from '@deepseek-ai/dsh-api-session-controller/client' +import type { ChunkRowEvent } from '@deepseek-ai/dsh-api-session-controller/types' +import type { ChunkRow } from '@deepseek-ai/dsh-session/chunk-rows' import type { SessionEvent } from '@deepseek-ai/dsh-session/types' import { ConversationNodeAssembler } from '@deepseek-ai/dsh-client-ui-conversation/client' import type { - ConversationEventInput, ConversationMatch, ConversationNodeContext, + ConversationMatch, ConversationNodeContext, ConversationNodeDefinition, ConversationViewDefinition, ConversationViewNode, } from '@deepseek-ai/dsh-client-ui-conversation/client' @@ -91,8 +96,18 @@ function at(seq: number, type: string, data: unknown): SessionEvent { return { seq, time: 1_700_000_000_000 + seq, type, data } as SessionEvent } -function input(event: SessionEvent): ConversationEventInput { - return { event } +function input(event: SessionEvent): SessionLiveEventEntry { + return { type: 'event', event } +} + +function chunkInput(row: ChunkRow): SessionEventLikeEntry { + const event = { + type: `chunkrow/${row.type}`, + seq: row.seq0, + time: row.time0, + data: row.data, + } as ChunkRowEvent + return { type: 'chunks', event } } function testSnapshot(assembler: ConversationNodeAssembler): TestSnapshot | undefined { @@ -215,6 +230,215 @@ describe('ConversationNodeAssembler', () => { expect([...testSnapshot(assembler)?.nodes.values() ?? []][0]?.data).toBe(1_000) }) + it('keeps one packed Match through replace, Location replay, and Registry rebuild', () => { + interface State { + readonly updates: readonly string[] + readonly packedStatus: string | undefined + } + + const matches = vi.fn((event: SessionEventLike) => { + if (event.type === 'step/start') return { id: '2:3', role: 'start' as const } + if ((event.type as string) === 'probe/update' + || event.type === 'chunkrow/text-chunks') { + return { id: '2:3', role: 'update' as const } + } + return null + }) + const passiveMatches = vi.fn(() => null) + const updates = vi.fn(( + context: ConversationNodeContext & { readonly state: State }, + match: ConversationMatch, + ): State => { + if (match.event.type === 'chunkrow/text-chunks') { + return { + ...context.state, + updates: [ + ...context.state.updates, + `packed:${String(match.event.seq)}-${String(match.event.seq + match.event.data.texts.length - 1)}`, + ], + packedStatus: match.location.kind === 'step' + ? match.location.step.status + : match.location.kind, + } + } + return { + ...context.state, + updates: [...context.state.updates, `event:${String(match.event.seq)}`], + } + }) + const definition: ConversationNodeDefinition = { + kind: 'packed-probe', + match: matches, + start: () => ({ updates: [], packedStatus: undefined }), + update: updates, + target: 'test', + buildViewNode: context => context.state === undefined + ? null + : node(context, { + ...context.state, + matches: context.matches.map(match => ({ + type: match.event.type, + seq: match.event.seq, + })), + }), + } + const passive: ConversationNodeDefinition = { + kind: 'packed-passive', + match: passiveMatches, + start: () => null, + update: context => context.state, + } + const run = chunkInput({ + type: 'text-chunks', + seq0: 12, + time0: 1_700_000_000_012, + data: { turn: 2, step: 3, index: 0, dt: [1, 1], texts: ['a', 'b', 'c'] }, + }) + const inputs: SessionEventLikeEntry[] = [ + input(at(10, 'step/start', { turn: 2, step: 3 })), + input(at(11, 'probe/update', { turn: 2, step: 3 })), + run, + input(at(15, 'probe/update', { turn: 2, step: 3 })), + ] + const assembler = new ConversationNodeAssembler( + new TestEventDefinitions([definition, passive]), + new TestViewDefinitions([testView()]), + ) + + assembler.replaceWindow(inputs, false) + assembler.flush() + + expect(matches).toHaveBeenCalledTimes(4) + expect(passiveMatches).toHaveBeenCalledTimes(4) + expect(updates).toHaveBeenCalledTimes(3) + expect(updates.mock.calls.filter(([, match]) => ( + match.event.type === 'chunkrow/text-chunks' + ))).toHaveLength(1) + expect([...testSnapshot(assembler)?.nodes.values() ?? []][0]?.data).toEqual({ + updates: ['event:11', 'packed:12-14', 'event:15'], + packedStatus: 'open', + matches: [ + { type: 'step/start', seq: 10 }, + { type: 'probe/update', seq: 11 }, + { type: 'chunkrow/text-chunks', seq: 12 }, + { type: 'probe/update', seq: 15 }, + ], + }) + + assembler.append(input(at(16, 'step/end', { turn: 2, step: 3 }))) + assembler.flush() + + expect(updates.mock.calls.filter(([, match]) => ( + match.event.type === 'chunkrow/text-chunks' + ))).toHaveLength(2) + expect([...testSnapshot(assembler)?.nodes.values() ?? []][0]?.data).toMatchObject({ + updates: ['event:11', 'packed:12-14', 'event:15'], + packedStatus: 'closed', + }) + + matches.mockClear() + passiveMatches.mockClear() + updates.mockClear() + assembler.rebuildRegistry() + assembler.flush() + + expect(matches).toHaveBeenCalledTimes(5) + expect(passiveMatches).toHaveBeenCalledTimes(5) + expect(updates).toHaveBeenCalledTimes(3) + expect(updates.mock.calls.filter(([, match]) => ( + match.event.type === 'chunkrow/text-chunks' + ))).toHaveLength(1) + }) + + it('replays one pending packed Match after prepend supplies its scalar start', () => { + const starts = vi.fn(() => ({ batches: 0, status: 'unresolved' })) + const updates = vi.fn(( + context: ConversationNodeContext<{ batches: number; status: string }> & { + readonly state: { batches: number; status: string } + }, + match: ConversationMatch, + ) => ({ + batches: context.state.batches + 1, + status: match.location.kind === 'step' ? match.location.step.status : match.location.kind, + })) + const definition: ConversationNodeDefinition<{ batches: number; status: string }> = { + kind: 'packed-pending', + match: (event) => { + if (event.type === 'step/start') { + return { id: `${String(event.data.turn)}:${String(event.data.step)}`, role: 'start' } + } + if (event.type === 'chunkrow/reasoning-chunks') { + return { id: `${String(event.data.turn)}:${String(event.data.step)}`, role: 'update' } + } + return null + }, + start: starts, + update: updates, + target: 'test', + buildViewNode: context => context.state === undefined + ? null + : node(context, { + ...context.state, + matches: context.matches.map(match => [match.event.type, match.event.seq]), + }), + } + const assembler = new ConversationNodeAssembler( + new TestEventDefinitions([definition]), + new TestViewDefinitions([testView()]), + ) + const run = chunkInput({ + type: 'reasoning-chunks', + seq0: 21, + time0: 1_700_000_000_021, + data: { turn: 4, step: 5, index: 0, dt: [0, -1], texts: ['', ' ', 'x'] }, + }) + + assembler.replaceWindow([run], true) + assembler.flush() + + expect(starts).not.toHaveBeenCalled() + expect(updates).not.toHaveBeenCalled() + expect(testSnapshot(assembler)?.order).toEqual([]) + + assembler.prepend([ + input(at(20, 'step/start', { turn: 4, step: 5 })), + ], false) + assembler.flush() + + expect(starts).toHaveBeenCalledOnce() + expect(updates).toHaveBeenCalledOnce() + expect([...testSnapshot(assembler)?.nodes.values() ?? []][0]?.data).toEqual({ + batches: 1, + status: 'open', + matches: [['step/start', 20], ['chunkrow/reasoning-chunks', 21]], + }) + }) + + it('rejects a packed event classified as a Context start', () => { + const definition: ConversationNodeDefinition = { + kind: 'invalid-packed-start', + match: event => event.type === 'chunkrow/text-chunks' + ? { id: 'one', role: 'start' } + : null, + start: () => null, + update: context => context.state, + } + const assembler = new ConversationNodeAssembler( + new TestEventDefinitions([definition]), + new TestViewDefinitions([testView()]), + ) + const run = chunkInput({ + type: 'text-chunks', + seq0: 1, + time0: 1_700_000_000_001, + data: { turn: 1, step: 1, index: 0, dt: [1, 1], texts: ['a', 'b', 'c'] }, + }) + + expect(() => assembler.replaceWindow([run], false)).toThrow( + 'conversation Context 20:invalid-packed-startone received a packed start Match', + ) + }) + it('merges an older page and replays its affected Context once', () => { const starts = vi.fn(() => 0) const updates = vi.fn((context: ConversationNodeContext & { readonly state: number }) => ( diff --git a/packages/client/ui-conversation/tests/history-transport.perf.client.ts b/packages/client/ui-conversation/tests/history-transport.perf.client.ts new file mode 100644 index 0000000000..57ddd806e1 --- /dev/null +++ b/packages/client/ui-conversation/tests/history-transport.perf.client.ts @@ -0,0 +1,694 @@ +/** Opt-in synthetic benchmark for packed session-history transport and exact replay. */ + +import { createHash } from 'node:crypto' +import { createServer, type Server } from 'node:http' +import { performance } from 'node:perf_hooks' +import { brotliCompressSync, gzipSync } from 'node:zlib' +import { expect, it } from 'vitest' +import { z } from 'zod' +import { createUserMessage } from '@deepseek-ai/dsh-llm' +import { isChunkRow, packChunkRuns } from '@deepseek-ai/dsh-session/chunk-rows' +import type { ChunkRow } from '@deepseek-ai/dsh-session/chunk-rows' +import type { SessionEvent, SessionEventMap } from '@deepseek-ai/dsh-session/types' +import type { + ChunkRowEvent, + SessionEventEntry, + SessionHistoryRecord, + SessionWireEvent, +} from '@deepseek-ai/dsh-api-session-controller/types' +import { historyEntries } from '@deepseek-ai/dsh-api-session-controller/src/client/sessions/history-records.ts' +import type { SessionEventLikeEntry } from '@deepseek-ai/dsh-api-session-controller/client' +import { ConversationNodeAssembler } from '@deepseek-ai/dsh-client-ui-conversation/client' +import type { + ConversationNodeDefinition, + ConversationViewDefinition, + ConversationViewNode, +} from '@deepseek-ai/dsh-client-ui-conversation/client' + +const LOGICAL_EVENTS = 416_756 +const DELTA_EVENTS = 416_176 +const ORDINARY_EVENTS = LOGICAL_EVENTS - DELTA_EVENTS +const DELTA_RUNS = 116 +const TIME_ZERO = 1_700_000_000_000 + +interface Timed { + readonly value: T + readonly ms: number +} + +interface HeapPeaks { + readonly value: T + readonly medianPeakBytes: number + readonly peakBytes: readonly number[] +} + +interface TransferSample { + readonly headersMs: number + readonly bodyMs: number + readonly totalMs: number +} + +interface TransferTimings { + readonly headersMs: number + readonly bodyMs: number + readonly totalMs: number + readonly samples: readonly TransferSample[] +} + +interface FoldState { + readonly blocks: readonly string[] + readonly deltaCount: number + readonly lastDeltaSeq?: number + readonly firstTokenTime?: number + readonly firstVisibleSeq?: number + readonly firstVisibleTime?: number +} + +interface FoldSnapshots { + readonly chat: unknown + readonly trajectory: unknown +} + +interface RawHistoryValue { + readonly events: SessionEventEntry[] + readonly hasMore: boolean +} + +interface PackedHistoryValue { + readonly records: SessionHistoryRecord[] + readonly hasMore: boolean +} + +const safeIntegerSchema = z.number().int().min(Number.MIN_SAFE_INTEGER).max(Number.MAX_SAFE_INTEGER) +const sessionWireEventSchema = z.object({ + type: z.string(), + seq: safeIntegerSchema, + time: safeIntegerSchema, + data: z.json(), + ignorable: z.literal(true).optional(), + sourceEventSeqs: z.array(safeIntegerSchema).optional(), + surfaceOp: z.json().optional(), +}).strict() +const historyEntrySchema = z.object({ + type: z.literal('event'), + event: sessionWireEventSchema, +}).strict() +const chunkRunBaseSchema = { + turn: z.number(), + step: z.number(), + index: z.number(), + dt: z.array(safeIntegerSchema), +} +const textChunkEventSchema = z.object({ + type: z.enum(['chunkrow/text-chunks', 'chunkrow/reasoning-chunks']), + seq: safeIntegerSchema.nonnegative(), + time: safeIntegerSchema, + data: z.object({ + ...chunkRunBaseSchema, + texts: z.array(z.string()).min(1), + }).strict(), +}).strict() +const toolCallChunkEventSchema = z.object({ + type: z.literal('chunkrow/tool-call-chunks'), + seq: safeIntegerSchema.nonnegative(), + time: safeIntegerSchema, + data: z.object({ + ...chunkRunBaseSchema, + id: z.string(), + name: z.string().optional(), + args: z.array(z.string()).min(1), + }).strict(), +}).strict() +const chunkEventSchema: z.ZodType = z.discriminatedUnion('type', [ + textChunkEventSchema, + toolCallChunkEventSchema, +]).superRefine((event, context) => { + const members = event.type === 'chunkrow/tool-call-chunks' ? event.data.args : event.data.texts + if (event.data.dt.length !== members.length - 1) { + context.addIssue({ + code: 'custom', + message: 'packed chunk dt length must be one less than member count', + path: ['data', 'dt'], + }) + } + if (members.length - 1 > Number.MAX_SAFE_INTEGER - event.seq) { + context.addIssue({ code: 'custom', message: 'packed chunk seqs must stay safe integers', path: ['seq'] }) + } + let time = event.time + for (let index = 0; index < event.data.dt.length; index++) { + time += event.data.dt[index] as number + if (Number.isSafeInteger(time)) continue + context.addIssue({ + code: 'custom', + message: 'packed chunk times must stay safe integers', + path: ['data', 'dt', index], + }) + break + } +}) as z.ZodType +const packedHistoryValueSchema: z.ZodType = z.object({ + records: z.array(z.union([ + historyEntrySchema, + z.object({ type: z.literal('chunks'), event: chunkEventSchema }).strict(), + ])), + hasMore: z.boolean(), +}) as z.ZodType +const rawSessionHistoryValueSchema: z.ZodType = z.object({ + events: z.array(historyEntrySchema), + hasMore: z.boolean(), +}) as z.ZodType + +function timed(run: () => T): Timed { + const start = performance.now() + const value = run() + return { value, ms: performance.now() - start } +} + +function rounded(value: number): number { + return Math.round(value * 100) / 100 +} + +function reduction(before: number, after: number): number { + return rounded((1 - after / before) * 100) +} + +function median(values: readonly number[]): number { + const ordered = [...values].sort((left, right) => left - right) + return ordered[Math.floor(ordered.length / 2)]! +} + +async function listen(server: Server): Promise { + await new Promise((resolve, reject) => { + const failed = (error: Error): void => { reject(error) } + server.once('error', failed) + server.listen(0, '127.0.0.1', () => { + server.off('error', failed) + resolve() + }) + }) + const address = server.address() + if (address === null || typeof address === 'string') throw new Error('history transport benchmark server has no TCP port') + return address.port +} + +async function close(server: Server): Promise { + if (!server.listening) return + await new Promise((resolve, reject) => { + server.close((error) => { + if (error === undefined) resolve() + else reject(error) + }) + }) +} + +async function loopbackTransfer(json: string): Promise { + const server = createServer((_request, response) => { + // Production Response.json reaches the bridge without content-length, so + // leave Node's response chunked for the same body-transfer behavior. + response.writeHead(200, { 'content-type': 'application/json' }) + response.write(json) + response.end() + }) + const port = await listen(server) + const once = async (): Promise => { + const started = performance.now() + const response = await fetch(`http://127.0.0.1:${String(port)}/`) + const headers = performance.now() + const body = await response.text() + const completed = performance.now() + if (body !== json) throw new Error('history transport benchmark received a changed body') + return { + headersMs: headers - started, + bodyMs: completed - headers, + totalMs: completed - started, + } + } + try { + await once() + const samples: TransferSample[] = [] + for (let index = 0; index < 5; index++) samples.push(await once()) + return { + headersMs: median(samples.map(sample => sample.headersMs)), + bodyMs: median(samples.map(sample => sample.bodyMs)), + totalMs: median(samples.map(sample => sample.totalMs)), + samples, + } + } finally { + await close(server) + } +} + +/** Measure caller-sampled additional V8 heap from forced-GC baselines. */ +function sampledPeakHeap(run: (sample: () => void) => T): HeapPeaks { + const forceGc = globalThis.gc + if (forceGc === undefined) { + throw new Error('history transport memory benchmark requires Vitest worker --expose-gc') + } + const samples = Array.from({ length: 3 }, () => { + forceGc() + forceGc() + const baseline = process.memoryUsage().heapUsed + let peak = baseline + const sample = (): void => { + peak = Math.max(peak, process.memoryUsage().heapUsed) + } + const value = run(sample) + sample() + return { value, peakBytes: peak - baseline } + }) + return { + value: samples[0]!.value, + medianPeakBytes: median(samples.map(sample => sample.peakBytes)), + peakBytes: samples.map(sample => sample.peakBytes), + } +} + +function append( + events: SessionEvent[], + type: Type, + data: SessionEventMap[Type], + options: { readonly surfaceOp?: 'append'; readonly ignorable?: true } = {}, +): void { + const seq = events.length + events.push({ type, seq, time: TIME_ZERO + seq, data, ...options } as SessionEvent) +} + +function appendSeparator(events: SessionEvent[], run: number, separator: number): void { + const seq = events.length + events.push({ + type: 'benchmark/separator', + seq, + time: TIME_ZERO + seq, + data: { run, separator }, + ignorable: true, + } as SessionEvent) +} + +function fragment(run: number, index: number): string { + const value = (Math.imul(run + 1, 0x9E3779B1) ^ Math.imul(index + 1, 0x85EBCA6B)) >>> 0 + return value.toString(36).padStart(7, '0').slice(-2) +} + +/** Build the private sample's event/run cardinality from deterministic synthetic content. */ +function buildEvents(): SessionEvent[] { + const events: SessionEvent[] = [] + append(events, 'turn/start', { turn: 1 }) + append(events, 'user/message', createUserMessage({ + content: [{ type: 'text', text: 'synthetic history transport benchmark' }], + source: { kind: 'user' }, + }), { surfaceOp: 'append' }) + append(events, 'step/start', { turn: 1, step: 1 }) + + const baseRunLength = Math.floor(DELTA_EVENTS / DELTA_RUNS) + const longerRuns = DELTA_EVENTS % DELTA_RUNS + for (let run = 0; run < DELTA_RUNS; run++) { + const runLength = baseRunLength + (run < longerRuns ? 1 : 0) + for (let index = 0; index < runLength; index++) { + append(events, 'assistant/chunk', { + turn: 1, + step: 1, + chunk: { + type: 'reasoning-delta', + index: run, + text: fragment(run, index), + }, + }) + } + const separators = run < 3 ? 4 : 5 + for (let separator = 0; separator < separators; separator++) { + appendSeparator(events, run, separator) + } + } + return events +} + +function memberTime(event: ChunkRowEvent, index: number): number { + let time = event.time + for (let cursor = 0; cursor < index; cursor++) time += event.data.dt[cursor] as number + return time +} + +function foldDefinition(kind: string, target: string): ConversationNodeDefinition { + return { + kind, + target, + match: (event) => { + if (event.type === 'step/start') return { id: `${String(event.data.turn)}:${String(event.data.step)}`, role: 'start' } + if (event.type === 'assistant/chunk' && event.data.chunk.type === 'reasoning-delta') { + return { id: `${String(event.data.turn)}:${String(event.data.step)}`, role: 'update' } + } + if (event.type === 'chunkrow/reasoning-chunks') { + return { id: `${String(event.data.turn)}:${String(event.data.step)}`, role: 'update' } + } + return null + }, + start: () => ({ blocks: [], deltaCount: 0 }), + update: (context, match) => { + if (match.event.type === 'chunkrow/reasoning-chunks') { + const event = match.event + const blocks = [...context.state.blocks] + blocks[event.data.index] = (blocks[event.data.index] ?? '') + event.data.texts.join('') + const firstToken = event.data.texts.findIndex(text => text !== '') + const firstVisible = event.data.texts.findIndex(text => text.trim() !== '') + return { + ...context.state, + blocks, + deltaCount: context.state.deltaCount + event.data.texts.length, + lastDeltaSeq: event.seq + event.data.texts.length - 1, + ...context.state.firstTokenTime === undefined && firstToken >= 0 + ? { firstTokenTime: memberTime(event, firstToken) } + : {}, + ...context.state.firstVisibleSeq === undefined && firstVisible >= 0 + ? { + firstVisibleSeq: event.seq + firstVisible, + firstVisibleTime: memberTime(event, firstVisible), + } + : {}, + } + } + if (match.event.type !== 'assistant/chunk' || match.event.data.chunk.type !== 'reasoning-delta') { + return context.state + } + const chunk = match.event.data.chunk + const blocks = [...context.state.blocks] + blocks[chunk.index] = (blocks[chunk.index] ?? '') + chunk.text + const visible = blocks.some(block => block.trim() !== '') + return { + ...context.state, + blocks, + deltaCount: context.state.deltaCount + 1, + lastDeltaSeq: match.event.seq, + ...context.state.firstTokenTime === undefined ? { firstTokenTime: match.event.time } : {}, + ...visible && context.state.firstVisibleSeq === undefined + ? { firstVisibleSeq: match.event.seq, firstVisibleTime: match.event.time } + : {}, + } + }, + buildViewNode: context => context.state === undefined + ? null + : { + key: context.key, + kind: context.kind, + id: context.id, + target, + data: context.state, + }, + } +} + +function viewDefinition(target: string): ConversationViewDefinition { + return { + target, + create: () => ({ + empty: [], + replace: ({ nodes }) => nodes, + apply: ({ upserts }) => upserts, + }), + } +} + +function wireEntry(event: SessionEvent): SessionEventEntry { + return { type: 'event', event: event as unknown as SessionWireEvent } +} + +function wireEntries(events: readonly SessionEvent[]): SessionEventEntry[] { + return events.map(wireEntry) +} + +function chunkEntry(row: ChunkRow): SessionHistoryRecord { + return { + type: 'chunks', + event: { + type: `chunkrow/${row.type}`, + seq: row.seq0, + time: row.time0, + data: row.data, + } as ChunkRowEvent, + } +} + +function historyRecord(record: SessionEvent | ChunkRow): SessionHistoryRecord { + return isChunkRow(record) ? chunkEntry(record) : wireEntry(record) +} + +function assemble(entries: readonly SessionEventLikeEntry[]): FoldSnapshots { + const definitions = [ + foldDefinition('benchmark-chat-assistant', 'chat'), + foldDefinition('benchmark-trajectory-assistant', 'trajectory'), + ] + const assembler = new ConversationNodeAssembler( + { entries: () => definitions, fallbackEntry: () => undefined }, + { entries: () => [viewDefinition('chat'), viewDefinition('trajectory')] }, + ) + assembler.replaceWindow(entries, false) + assembler.flush() + return { + chat: assembler.snapshot('chat'), + trajectory: assembler.snapshot('trajectory'), + } +} + +function digest(value: unknown): string { + return createHash('sha256').update(JSON.stringify(value)).digest('hex') +} + +it('reports packed history transport and exact replay costs', async () => { + const fixture = timed(buildEvents) + + assemble(historyEntries(wireEntries(fixture.value.slice(0, 1_000)))) + const rawHostHeap = sampledPeakHeap((sample) => { + const entries = wireEntries(fixture.value) + sample() + const json = JSON.stringify({ events: entries, hasMore: false } satisfies RawHistoryValue) + sample() + return Buffer.byteLength(json) + }) + const packedHostHeap = sampledPeakHeap((sample) => { + const packedEvents = packChunkRuns(fixture.value) + sample() + const records = packedEvents.map(historyRecord) + sample() + const json = JSON.stringify({ + records, + hasMore: false, + } satisfies PackedHistoryValue) + sample() + return Buffer.byteLength(json) + }) + + const rawEntries = timed(() => wireEntries(fixture.value)) + const packed = timed(() => packChunkRuns(fixture.value)) + const packedRecords = timed(() => packed.value.map(historyRecord)) + const rawValue: RawHistoryValue = { events: rawEntries.value, hasMore: false } + const packedValue: PackedHistoryValue = { + records: packedRecords.value, + hasMore: false, + } + + const rawJson = timed(() => JSON.stringify(rawValue)) + const packedJson = timed(() => JSON.stringify(packedValue)) + const rawGzip = timed(() => gzipSync(rawJson.value).byteLength) + const packedGzip = timed(() => gzipSync(packedJson.value).byteLength) + const rawBrotli = timed(() => brotliCompressSync(rawJson.value).byteLength) + const packedBrotli = timed(() => brotliCompressSync(packedJson.value).byteLength) + const rawTransfer = await loopbackTransfer(rawJson.value) + const packedTransfer = await loopbackTransfer(packedJson.value) + + const rawClientHeap = sampledPeakHeap((sample) => { + const wire: unknown = JSON.parse(rawJson.value) + sample() + const parsed = rawSessionHistoryValueSchema.parse(wire) + sample() + const prepared = historyEntries(parsed.events) + sample() + const folded = assemble(prepared) + sample() + return digest(folded) + }) + const packedClientHeap = sampledPeakHeap((sample) => { + const wire: unknown = JSON.parse(packedJson.value) + sample() + const parsed = packedHistoryValueSchema.parse(wire) + sample() + const prepared = historyEntries(parsed.records) + sample() + const folded = assemble(prepared) + sample() + return digest(folded) + }) + + const parsedRaw = timed((): unknown => JSON.parse(rawJson.value)) + const parsedPacked = timed((): unknown => JSON.parse(packedJson.value)) + const rawValidation = timed(() => rawSessionHistoryValueSchema.parse(parsedRaw.value)) + const packedValidation = timed(() => packedHistoryValueSchema.parse(parsedPacked.value)) + const rawPreparation = timed(() => historyEntries(rawValidation.value.events)) + const packedPreparation = timed(() => historyEntries(packedValidation.value.records)) + + assemble(rawPreparation.value.slice(0, 1_000)) + assemble(packedPreparation.value) + const rawFold = timed(() => assemble(rawPreparation.value)) + const packedFold = timed(() => assemble(packedPreparation.value)) + + const rawBytes = Buffer.byteLength(rawJson.value) + const packedBytes = Buffer.byteLength(packedJson.value) + const packedRows = packed.value.filter(isChunkRow) + expect(fixture.value).toHaveLength(LOGICAL_EVENTS) + expect(fixture.value.filter(event => event.type !== 'assistant/chunk')).toHaveLength(ORDINARY_EVENTS) + expect(packedRows).toHaveLength(DELTA_RUNS) + expect(packed.value).toHaveLength(696) + expect(packedPreparation.value).toHaveLength(696) + expect(digest(packedFold.value)).toBe(digest(rawFold.value)) + expect(packedClientHeap.value).toBe(rawClientHeap.value) + expect(rawHostHeap.value).toBe(rawBytes) + expect(packedHostHeap.value).toBe(packedBytes) + expect(packedBytes).toBeLessThan(rawBytes) + + const rawResponseMs = rawEntries.ms + rawJson.ms + const packedResponseMs = packed.ms + packedRecords.ms + packedJson.ms + const rawClientMs = parsedRaw.ms + rawValidation.ms + rawPreparation.ms + rawFold.ms + const packedClientMs = parsedPacked.ms + packedValidation.ms + packedPreparation.ms + packedFold.ms + const rawSyntheticApiWaitMs = rawResponseMs + rawTransfer.totalMs + parsedRaw.ms + rawValidation.ms + const packedSyntheticApiWaitMs = packedResponseMs + packedTransfer.totalMs + parsedPacked.ms + packedValidation.ms + const rawSyntheticReadyMs = rawResponseMs + rawTransfer.totalMs + rawClientMs + const packedSyntheticReadyMs = packedResponseMs + packedTransfer.totalMs + packedClientMs + process.stdout.write(`HISTORY_TRANSPORT_PERF_RESULT ${JSON.stringify({ + fixture: { + buildMs: rounded(fixture.ms), + logicalEvents: fixture.value.length, + ordinaryEvents: ORDINARY_EVENTS, + deltaEvents: DELTA_EVENTS, + deltaRuns: packedRows.length, + packedRecords: packed.value.length, + conversationInputs: packedPreparation.value.length, + }, + bytes: { + rawJson: rawBytes, + packedJson: packedBytes, + jsonReductionPct: reduction(rawBytes, packedBytes), + rawGzip: rawGzip.value, + packedGzip: packedGzip.value, + gzipReductionPct: reduction(rawGzip.value, packedGzip.value), + rawBrotli: rawBrotli.value, + packedBrotli: packedBrotli.value, + brotliReductionPct: reduction(rawBrotli.value, packedBrotli.value), + }, + memory: { + samples: 3, + rawHostAdditionalHeapPeakBytes: rawHostHeap.medianPeakBytes, + packedHostAdditionalHeapPeakBytes: packedHostHeap.medianPeakBytes, + hostReductionPct: reduction(rawHostHeap.medianPeakBytes, packedHostHeap.medianPeakBytes), + rawClientAdditionalHeapPeakBytes: rawClientHeap.medianPeakBytes, + packedClientAdditionalHeapPeakBytes: packedClientHeap.medianPeakBytes, + clientReductionPct: reduction(rawClientHeap.medianPeakBytes, packedClientHeap.medianPeakBytes), + rawHostPeakSamples: rawHostHeap.peakBytes, + packedHostPeakSamples: packedHostHeap.peakBytes, + rawClientPeakSamples: rawClientHeap.peakBytes, + packedClientPeakSamples: packedClientHeap.peakBytes, + }, + host: { + rawEntryWrapMs: rounded(rawEntries.ms), + packMs: rounded(packed.ms), + packedRecordWrapMs: rounded(packedRecords.ms), + rawStringifyMs: rounded(rawJson.ms), + packedStringifyMs: rounded(packedJson.ms), + rawGzipMs: rounded(rawGzip.ms), + packedGzipMs: rounded(packedGzip.ms), + rawBrotliMs: rounded(rawBrotli.ms), + packedBrotliMs: rounded(packedBrotli.ms), + rawResponseMs: rounded(rawResponseMs), + packedResponseMs: rounded(packedResponseMs), + responseReductionPct: reduction(rawResponseMs, packedResponseMs), + }, + transport: { + samples: 5, + rawHeadersMs: rounded(rawTransfer.headersMs), + packedHeadersMs: rounded(packedTransfer.headersMs), + rawBodyMs: rounded(rawTransfer.bodyMs), + packedBodyMs: rounded(packedTransfer.bodyMs), + rawTotalMs: rounded(rawTransfer.totalMs), + packedTotalMs: rounded(packedTransfer.totalMs), + totalReductionPct: reduction(rawTransfer.totalMs, packedTransfer.totalMs), + rawSamples: rawTransfer.samples.map(sample => ({ + headersMs: rounded(sample.headersMs), + bodyMs: rounded(sample.bodyMs), + totalMs: rounded(sample.totalMs), + })), + packedSamples: packedTransfer.samples.map(sample => ({ + headersMs: rounded(sample.headersMs), + bodyMs: rounded(sample.bodyMs), + totalMs: rounded(sample.totalMs), + })), + }, + client: { + rawParseMs: rounded(parsedRaw.ms), + packedParseMs: rounded(parsedPacked.ms), + rawValidationMs: rounded(rawValidation.ms), + packedValidationMs: rounded(packedValidation.ms), + rawPrepareMs: rounded(rawPreparation.ms), + packedPrepareMs: rounded(packedPreparation.ms), + rawFoldMs: rounded(rawFold.ms), + packedFoldMs: rounded(packedFold.ms), + rawHistoryMs: rounded(rawClientMs), + packedHistoryMs: rounded(packedClientMs), + historyReductionPct: reduction(rawClientMs, packedClientMs), + }, + combined: { + rawSyntheticApiWaitMs: rounded(rawSyntheticApiWaitMs), + packedSyntheticApiWaitMs: rounded(packedSyntheticApiWaitMs), + syntheticApiWaitReductionPct: reduction(rawSyntheticApiWaitMs, packedSyntheticApiWaitMs), + rawSyntheticReadyMs: rounded(rawSyntheticReadyMs), + packedSyntheticReadyMs: rounded(packedSyntheticReadyMs), + syntheticReadyReductionPct: reduction(rawSyntheticReadyMs, packedSyntheticReadyMs), + }, + })}\n`) +}, 600_000) + +it('reports compact folding cost for long whitespace-prefix runs', () => { + historyEntries([{ + type: 'chunks', + event: { + type: 'chunkrow/reasoning-chunks', + seq: 0, + time: TIME_ZERO, + data: { turn: 1, step: 1, index: 0, dt: [], texts: ['x'] }, + }, + }]) + const results = [10_000, 20_000, 40_000].map((members) => { + const record: SessionHistoryRecord = { + type: 'chunks', + event: { + type: 'chunkrow/reasoning-chunks', + seq: 1, + time: TIME_ZERO + 1, + data: { + turn: 1, + step: 1, + index: 0, + dt: Array.from({ length: members - 1 }, () => 1), + texts: Array.from({ length: members }, (_, index) => index === members - 1 ? 'x' : ' '), + }, + }, + } + const start = wireEntry({ + type: 'step/start', + seq: 0, + time: TIME_ZERO, + data: { turn: 1, step: 1 }, + }) + const inputs = historyEntries([start, record]) + const folded = assemble(inputs) + const samplesMs = Array.from({ length: 5 }, () => timed(() => assemble(inputs)).ms) + expect((folded.chat as readonly { readonly data: FoldState }[])[0]?.data).toMatchObject({ + deltaCount: members, + lastDeltaSeq: members, + firstVisibleSeq: members, + firstVisibleTime: TIME_ZERO + members, + }) + return { + members, + medianMs: rounded(median(samplesMs)), + samplesMs: samplesMs.map(rounded), + } + }) + process.stdout.write(`HISTORY_WHITESPACE_PREFIX_PERF_RESULT ${JSON.stringify(results)}\n`) +}) diff --git a/packages/client/ui-deliverables/tests/produced-files.client.spec.tsx b/packages/client/ui-deliverables/tests/produced-files.client.spec.tsx index 4cbfe8c294..9117fa3925 100644 --- a/packages/client/ui-deliverables/tests/produced-files.client.spec.tsx +++ b/packages/client/ui-deliverables/tests/produced-files.client.spec.tsx @@ -8,12 +8,13 @@ import { Context } from '@deepseek-ai/cordis' import { act, cleanup, fireEvent, render, within } from '@testing-library/react' import { afterEach, describe, expect, it, vi } from 'vitest' +import type { SessionLiveEventEntry } from '@deepseek-ai/dsh-api-session-controller/client' import { ConversationNodeAssembler, UiConversation, } from '@deepseek-ai/dsh-client-ui-conversation/client' import type { - ConversationEventInput, ConversationLocationDataStore, ConversationMatch, ConversationNodeDefinition, - ConversationTimelineSnapshot, ConversationTurnDataMap, ConversationViewDefinition, + ConversationLocationDataStore, ConversationMatch, ConversationNodeDefinition, + ConversationStartMatch, ConversationTimelineSnapshot, ConversationTurnDataMap, ConversationViewDefinition, ConversationViewNode, TurnLocation, } from '@deepseek-ai/dsh-client-ui-conversation/client' import { SlotRegistry } from '@deepseek-ai/dsh-client-ui-renderer/client' @@ -30,6 +31,7 @@ import { import { apply, inject } from '../src/client/index.ts' import { apply as applyInvariant } from '../src/invariant.ts' import { en, zh } from '../src/client/locales.ts' +import type { SessionEvent } from '@deepseek-ai/dsh-session/types' const originalClientWidth = Object.getOwnPropertyDescriptor(HTMLElement.prototype, 'clientWidth') @@ -109,17 +111,20 @@ function at( seq: number, type: string, data: unknown, -): ConversationEventInput { +): SessionLiveEventEntry { return { + type: 'event', event: { seq, time: seq * 1_000, type, data, ...(type === 'tool/result' ? { surfaceOp: 'append' } : {}), - } as ConversationEventInput['event'], + } as SessionEvent, } } -function matched(input: ConversationEventInput, role: ConversationMatch['role']): ConversationMatch { - return { ...input, role, location: { kind: 'unresolved' } } +function matched(input: SessionLiveEventEntry, role: 'start'): ConversationStartMatch +function matched(input: SessionLiveEventEntry, role: 'update'): ConversationMatch +function matched(input: SessionLiveEventEntry, role: ConversationMatch['role']): ConversationMatch { + return { event: input.event, role, location: { kind: 'unresolved' } } } function call( @@ -128,7 +133,7 @@ function call( name: string, args: Readonly>, turn = 1, -): ConversationEventInput { +): SessionLiveEventEntry { return rawCall(seq, callId, name, JSON.stringify(args), turn) } @@ -138,7 +143,7 @@ function rawCall( name: string, argsRaw: string, turn = 1, -): ConversationEventInput { +): SessionLiveEventEntry { return at( seq, 'tool/call', @@ -146,7 +151,7 @@ function rawCall( ) } -function result(seq: number, callId: string, isError = false, turn = 1): ConversationEventInput { +function result(seq: number, callId: string, isError = false, turn = 1): SessionLiveEventEntry { return at(seq, 'tool/result', { turn, step: 1, @@ -157,7 +162,7 @@ function result(seq: number, callId: string, isError = false, turn = 1): Convers }) } -function assembler(entries: readonly ConversationEventInput[], hasMore = false): ConversationNodeAssembler { +function assembler(entries: readonly SessionLiveEventEntry[], hasMore = false): ConversationNodeAssembler { const value = new ConversationNodeAssembler(new TestEventDefinitions(), new TestViewDefinitions()) value.replaceWindow(entries, hasMore) value.flush() @@ -330,7 +335,7 @@ describe('produced-file Turn data', () => { event: { ...replacement.event, surfaceOp: { op: 'replace', start: 1, end: 1 }, - } as ConversationEventInput['event'], + } as SessionEvent, }, at(26, 'turn/end', { turn: 1, reason: { kind: 'interrupted' } }), ]) @@ -354,7 +359,11 @@ describe('produced-file Turn data', () => { const unrelated = matched(at(2, 'turn/end', { turn: 1, reason: { kind: 'completed' } }), 'update') const context: Parameters[0] = { ...emptyContext, state } - expect(() => deliverablesDefinition.start(emptyContext, unrelated, reader)) + expect(() => deliverablesDefinition.start( + emptyContext, + unrelated as ConversationStartMatch, + reader, + )) .toThrow('deliverables start requires turn/start') expect(deliverablesDefinition.update(context, unrelated)).toBe(state) }) diff --git a/packages/client/ui-goal/tests/goal-command-input.client.spec.tsx b/packages/client/ui-goal/tests/goal-command-input.client.spec.tsx index 811e922118..d8fc191f84 100644 --- a/packages/client/ui-goal/tests/goal-command-input.client.spec.tsx +++ b/packages/client/ui-goal/tests/goal-command-input.client.spec.tsx @@ -1,8 +1,9 @@ // @vitest-environment jsdom import { cleanup, render, within } from '@testing-library/react' import { afterEach, describe, expect, it } from 'vitest' +import type { SessionLiveEventEntry } from '@deepseek-ai/dsh-api-session-controller/client' import type { - ConversationEventInput, ConversationNodeDefinition, ConversationViewDefinition, + ConversationNodeDefinition, ConversationViewDefinition, } from '@deepseek-ai/dsh-client-ui-conversation/client' import { ConversationNodeAssembler } from '@deepseek-ai/dsh-client-ui-conversation/client' import type { @@ -37,13 +38,14 @@ class TestViewDefinitions { } } -function entry(seq: number, type: string, data: unknown): ConversationEventInput { +function entry(seq: number, type: string, data: unknown): SessionLiveEventEntry { return { - event: { seq, time: 1_700_000_000_000 + seq, type, data } as ConversationEventInput['event'], + type: 'event', + event: { seq, time: 1_700_000_000_000 + seq, type, data } as SessionEvent, } } -function snapshot(entries: readonly ConversationEventInput[], hasMore = false): ChatSnapshot { +function snapshot(entries: readonly SessionLiveEventEntry[], hasMore = false): ChatSnapshot { const assembler = new ConversationNodeAssembler(new TestEventDefinitions(), new TestViewDefinitions()) assembler.replaceWindow(entries, hasMore) assembler.flush() diff --git a/packages/client/ui-tool/tests/tool-details-render.client.tsx b/packages/client/ui-tool/tests/tool-details-render.client.tsx index b915b39de9..fd41bfd474 100644 --- a/packages/client/ui-tool/tests/tool-details-render.client.tsx +++ b/packages/client/ui-tool/tests/tool-details-render.client.tsx @@ -1,6 +1,6 @@ /** Test adapter for the production conversation.details.tool registration. */ import type { HostDescription } from '@deepseek-ai/dsh-client-connection/client' -import type { SessionEventEntry } from '@deepseek-ai/dsh-api-session-controller/types' +import type { SessionLiveEventEntry } from '@deepseek-ai/dsh-api-session-controller/client' import { isJsonValue, type JsonValue } from '@deepseek-ai/dsh-session' import type { ChatConversationViewNode, ChatSnapshot, ConversationNode, DetailsSlotProps, @@ -68,10 +68,11 @@ export function toolChatSnapshot( } /** Build the Session event window that projects settled root Tool calls into Chat. */ -export function toolSessionEvents(nodes: readonly ToolResultNode[]): readonly SessionEventEntry[] { +export function toolSessionEvents(nodes: readonly ToolResultNode[]): readonly SessionLiveEventEntry[] { const firstTime = nodes[0]?.callTime ?? nodes[0]?.time ?? 0 - const entries: SessionEventEntry[] = [ + const entries: SessionLiveEventEntry[] = [ { + type: 'event', event: { seq: 1, time: firstTime - 2, @@ -80,6 +81,7 @@ export function toolSessionEvents(nodes: readonly ToolResultNode[]): readonly Se }, }, { + type: 'event', event: { seq: 2, time: firstTime - 1, @@ -91,7 +93,8 @@ export function toolSessionEvents(nodes: readonly ToolResultNode[]): readonly Se for (const [index, node] of nodes.entries()) { if (node.call === null) throw new Error(`tool fixture "${node.callId}" requires its call event`) const callSeq = 3 + index * 2 - const callEntry: SessionEventEntry = { + const callEntry: SessionLiveEventEntry = { + type: 'event', event: { seq: callSeq, time: node.callTime ?? node.time - 1, @@ -103,10 +106,11 @@ export function toolSessionEvents(nodes: readonly ToolResultNode[]): readonly Se name: node.call.name, arguments: node.call.argsRaw, }, - }, + } as unknown as SessionLiveEventEntry['event'], } entries.push(callEntry) - const resultEntry: SessionEventEntry = { + const resultEntry: SessionLiveEventEntry = { + type: 'event', event: { seq: callSeq + 1, time: node.time, @@ -129,7 +133,7 @@ export function toolSessionEvents(nodes: readonly ToolResultNode[]): readonly Se ...(node.meta === undefined ? {} : { meta: node.meta }), }), surfaceOp: 'append', - }, + } as unknown as SessionLiveEventEntry['event'], } entries.push(resultEntry) } diff --git a/packages/client/ui-trajectory/README.i18n.yaml b/packages/client/ui-trajectory/README.i18n.yaml index 96f48c6888..f4063bbb80 100644 --- a/packages/client/ui-trajectory/README.i18n.yaml +++ b/packages/client/ui-trajectory/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/ui-trajectory/README.md -README.md: c623105b9bb84edbd8ff6a91244271f6fc92d943 -README.zh.md: 007f4451be9ac2f19c7fdd8e6eefe410813c7eb7 +README.md: c29dc1c819f6dc422f979b64da6c06cd4d6cc5a1 +README.zh.md: b4f279ad217fa393601c6361d0dc19d582a1d4a8 diff --git a/packages/client/ui-trajectory/README.md b/packages/client/ui-trajectory/README.md index c623105b9b..c29dc1c819 100644 --- a/packages/client/ui-trajectory/README.md +++ b/packages/client/ui-trajectory/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -Trajectory renders a turn-aware event ledger with selectable User, Assistant, Tool, and nested Subtool records. Thick rules mark Turn boundaries, compact inline markers identify Steps, and the main ledger keeps only index, event, and content; selection opens a local inspector for token usage, duration, Input, Output, and Timing. Durable image attachments in user input, assistant output, and tool results render through the `conversation.trajectory.images` gallery slot: a record without text labels its row with the image count, the inspector shows each image with the shared loading, retry, and lightbox behavior, and image URLs come from the Conversation-owned per-session cache, so Chat and Trajectory share one authorized read per attachment. Scrollable Summary regions keep their scrollbar thumbs transparent until the region is hovered or contains keyboard focus, without changing the reserved scroll geometry. A standalone compaction request appears chronologically in its own `Between turns` section, while a numbered compaction remains inside its owning turn. Long ledgers open at the current tail, load one older page when the user reaches the loaded range's top, and mount only the visible row window plus a small overscan; request-only separators share the next measurable virtual item, while semantic row keys and ARIA indexes survive prepends. Selection, timeline navigation, folding, search, and Request totals cover the currently loaded window. The ledger covers records with an explicit loading row until the initial tail is positioned. While an older prefix remains unloaded, a first-row control precedes the loaded records, loads one earlier page on click, and changes in place to a disabled loading status while that page is pending. A fixed Overview above the ledger projects real record start/duration timing from left to right; when earlier records remain unloaded and the viewport includes the loaded domain's start, a neutral ellipsis control identifies the omitted prefix and loads one earlier page without assigning unknown history fabricated duration. Assistant spans divide recorded TTFT from decoding, and a 500 ms hover reveals exact clock and duration details. Dragging an interval focuses the ledger on every record active at any point in that inclusive range, while clearing the selection restores the full loaded ledger. Wheel gestures zoom the time domain. A right-button click clears the selected interval, while a right-button drag pans an already zoomed viewport without changing it. The initial view and streaming updates stay at the tail; scrolling upward suspends following so new records do not interrupt inspection of earlier rows. Content-only stream frames preserve virtual row keys and heights, reuse measurements, and do not issue repeated tail-scroll writes. Completed replies retain assembled blocks, timing, and usage in Trajectory target State, while the shared Session window keeps the raw Events. Trajectory asks the conversation shell to float the composer over the full-height ledger, while its responsive vertical scrollers reserve the composer's live height so final rows remain reachable. Trajectory-owned Definitions assemble business records, including durable cancellation-finalized prefixes, chunk-only interruption fallbacks, and interrupted Tool records, from the shared Session window, so Trajectory neither reads nor changes the Chat conversation snapshot. The package provides no service and declares no Context merge; it registers target-specific Event Definitions, a Trajectory view builder, and one tab in the conversation's `'conversation.view'` slot ring. Its typed `trajectory` locale namespace owns every product-authored ledger, timeline, inspector, tooltip, and accessibility phrase; event content, tool names, identifiers, and provider diagnostics remain verbatim data. +Trajectory renders a turn-aware event ledger with selectable User, Assistant, Tool, and nested Subtool records. Thick rules mark Turn boundaries, compact inline markers identify Steps, and the main ledger keeps only index, event, and content; selection opens a local inspector for token usage, duration, Input, Output, and Timing. Durable image attachments in user input, assistant output, and tool results render through the `conversation.trajectory.images` gallery slot: a record without text labels its row with the image count, the inspector shows each image with the shared loading, retry, and lightbox behavior, and image URLs come from the Conversation-owned per-session cache, so Chat and Trajectory share one authorized read per attachment. Scrollable Summary regions keep their scrollbar thumbs transparent until the region is hovered or contains keyboard focus, without changing the reserved scroll geometry. A standalone compaction request appears chronologically in its own `Between turns` section, while a numbered compaction remains inside its owning turn. Long ledgers open at the current tail, load one older page when the user reaches the loaded range's top, and mount only the visible row window plus a small overscan; request-only separators share the next measurable virtual item, while semantic row keys and ARIA indexes survive prepends. Selection, timeline navigation, folding, search, and Request totals cover the currently loaded window. The ledger covers records with an explicit loading row until the initial tail is positioned. While an older prefix remains unloaded, a first-row control precedes the loaded records, loads one earlier page on click, and changes in place to a disabled loading status while that page is pending. A fixed Overview above the ledger projects real record start/duration timing from left to right; when earlier records remain unloaded and the viewport includes the loaded domain's start, a neutral ellipsis control identifies the omitted prefix and loads one earlier page without assigning unknown history fabricated duration. Assistant spans divide recorded TTFT from decoding, and a 500 ms hover reveals exact clock and duration details. Dragging an interval focuses the ledger on every record active at any point in that inclusive range, while clearing the selection restores the full loaded ledger. Wheel gestures zoom the time domain. A right-button click clears the selected interval, while a right-button drag pans an already zoomed viewport without changing it. The initial view and streaming updates stay at the tail; scrolling upward suspends following so new records do not interrupt inspection of earlier rows. Content-only stream frames preserve virtual row keys and heights, reuse measurements, and do not issue repeated tail-scroll writes. Completed replies retain assembled blocks, timing, and usage in Trajectory target State, while the shared Session window keeps standard events and packed historical Assistant runs. Trajectory asks the conversation shell to float the composer over the full-height ledger, while its responsive vertical scrollers reserve the composer's live height so final rows remain reachable. Trajectory-owned Definitions assemble business records, including durable cancellation-finalized prefixes, chunk-only interruption fallbacks, and interrupted Tool records, from the shared Session window and fold packed runs without member expansion, so Trajectory neither reads nor changes the Chat conversation snapshot. The package provides no service and declares no Context merge; it registers target-specific Event Definitions, a Trajectory view builder, and one tab in the conversation's `'conversation.view'` slot ring. Its typed `trajectory` locale namespace owns every product-authored ledger, timeline, inspector, tooltip, and accessibility phrase; event content, tool names, identifiers, and provider diagnostics remain verbatim data. ## Model Experience diff --git a/packages/client/ui-trajectory/README.zh.md b/packages/client/ui-trajectory/README.zh.md index 007f4451be..b4f279ad21 100644 --- a/packages/client/ui-trajectory/README.zh.md +++ b/packages/client/ui-trajectory/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -Trajectory 渲染按轮次组织的事件记录表，其中可选择用户、助手、工具和嵌套子工具记录。较粗的分割线标示轮次边界，紧凑的行内标记标识步骤，主记录表仅保留索引、事件和内容；选择记录则会打开局部检查器，查看 token 用量、耗时、输入、输出和计时。用户输入、助手输出和工具结果中的持久化图片附件通过 `conversation.trajectory.images` 画廊 slot 渲染：没有文本的记录行以图片数量标注，检查器内展示每张图片并复用共享的加载、重试与灯箱行为，图片 URL 来自 Conversation 持有的按会话缓存，因此 Chat 与 Trajectory 对同一附件共享一次经会话授权的读取。可滚动的概述区域默认保持滚动条滑块透明，直到鼠标悬停该区域或其中包含键盘焦点时才显示，同时不改变滚动条预留的几何空间。独立运行的压缩（compaction）请求会按时间顺序显示在自己的 `Between turns` 区段中，而带编号的压缩仍位于其所属轮次内。长记录表打开时定位于当前尾部，用户到达已加载范围顶部时加载一页更早的历史，并且只挂载可见行窗口和少量额外缓冲行；仅含请求的分隔行并入下一个具备可测高度的虚拟项，语义行键和 ARIA 索引在向前补页后保持不变。选择、时间线导航、折叠、搜索和请求汇总只覆盖当前已加载的窗口。初始尾部完成定位前，记录表会用明确的加载行遮住真实记录。更早的前缀仍未加载时，已加载记录前会始终保留首行控件；单击它会加载一页更早的历史，页面加载期间则会原地变为禁用的加载状态。固定在记录表上方的 Overview 区域从左到右投影记录的真实开始时间与耗时；仍有更早记录未加载且 viewport 包含已加载时间域起点时，中性的省略号控件会标识被省略的前缀，并可加载一页更早历史，而不会为未知部分虚构耗时。助手时间条会区分记录到的 TTFT 与解码时间，悬停 500 ms 后可查看精确时刻和耗时详情。拖选一个区间会将记录表聚焦到活动区间与该闭区间有重叠的所有记录，清除选择则恢复完整的已加载记录表。滚轮手势用于缩放时间域。右键单击会清除所选区间；在已放大的 viewport 上按住右键拖动则只会平移视图，不会改变该区间。初始视图和流式更新都会停留在尾部；向上滚动会暂停跟随，因此新记录不会打断对旧记录的检查。仅含内容更新的流式帧会保持虚拟行的键和高度不变、复用测量结果，并且不会重复写入末尾滚动位置。已完成的回复会在 Trajectory target State 中保留组装后的 blocks、计时与用量，共享 Session 窗口则保留原始 Event。Trajectory 要求会话壳将 composer 作为浮层置于全高记录表上方；其响应式纵向滚动容器会预留 composer 的实时高度，确保仍可滚动到最后几行。Trajectory 自有的 Definition 从共享 Session 窗口组装业务记录，其中包括持久化的取消定稿前缀、只能从分片恢复的打断前缀和被打断的工具记录，因此 Trajectory 既不读取也不改变 Chat 会话快照。该包不提供 service，也不声明 Context 合并；它会注册 target 专属 Event Definition、Trajectory view builder，以及会话 `'conversation.view'` slot 环中的一个视图标签页。其 typed `trajectory` locale namespace 持有 ledger、时间线、检查器、tooltip 与无障碍短语中的全部产品编写文案；事件内容、工具名称、标识符与提供方诊断仍作为数据原样呈现。 +Trajectory 渲染按轮次组织的事件记录表，其中可选择用户、助手、工具和嵌套子工具记录。较粗的分割线标示轮次边界，紧凑的行内标记标识步骤，主记录表仅保留索引、事件和内容；选择记录则会打开局部检查器，查看 token 用量、耗时、输入、输出和计时。用户输入、助手输出和工具结果中的持久化图片附件通过 `conversation.trajectory.images` 画廊 slot 渲染：没有文本的记录行以图片数量标注，检查器内展示每张图片并复用共享的加载、重试与灯箱行为，图片 URL 来自 Conversation 持有的按会话缓存，因此 Chat 与 Trajectory 对同一附件共享一次经会话授权的读取。可滚动的概述区域默认保持滚动条滑块透明，直到鼠标悬停该区域或其中包含键盘焦点时才显示，同时不改变滚动条预留的几何空间。独立运行的压缩（compaction）请求会按时间顺序显示在自己的 `Between turns` 区段中，而带编号的压缩仍位于其所属轮次内。长记录表打开时定位于当前尾部，用户到达已加载范围顶部时加载一页更早的历史，并且只挂载可见行窗口和少量额外缓冲行；仅含请求的分隔行并入下一个具备可测高度的虚拟项，语义行键和 ARIA 索引在向前补页后保持不变。选择、时间线导航、折叠、搜索和请求汇总只覆盖当前已加载的窗口。初始尾部完成定位前，记录表会用明确的加载行遮住真实记录。更早的前缀仍未加载时，已加载记录前会始终保留首行控件；单击它会加载一页更早的历史，页面加载期间则会原地变为禁用的加载状态。固定在记录表上方的 Overview 区域从左到右投影记录的真实开始时间与耗时；仍有更早记录未加载且 viewport 包含已加载时间域起点时，中性的省略号控件会标识被省略的前缀，并可加载一页更早历史，而不会为未知部分虚构耗时。助手时间条会区分记录到的 TTFT 与解码时间，悬停 500 ms 后可查看精确时刻和耗时详情。拖选一个区间会将记录表聚焦到活动区间与该闭区间有重叠的所有记录，清除选择则恢复完整的已加载记录表。滚轮手势用于缩放时间域。右键单击会清除所选区间；在已放大的 viewport 上按住右键拖动则只会平移视图，不会改变该区间。初始视图和流式更新都会停留在尾部；向上滚动会暂停跟随，因此新记录不会打断对旧记录的检查。仅含内容更新的流式帧会保持虚拟行的键和高度不变、复用测量结果，并且不会重复写入末尾滚动位置。已完成的回复会在 Trajectory target State 中保留组装后的 blocks、计时与用量，共享 Session 窗口则保留标准 event 与 packed Assistant 历史 run。Trajectory 要求会话壳将 composer 作为浮层置于全高记录表上方；其响应式纵向滚动容器会预留 composer 的实时高度，确保仍可滚动到最后几行。Trajectory 自有的 Definition 从共享 Session 窗口组装业务记录，其中包括持久化的取消定稿前缀、只能从分片恢复的打断前缀和被打断的工具记录，并直接 fold packed run 而不展开 member，因此 Trajectory 既不读取也不改变 Chat 会话快照。该包不提供 service，也不声明 Context 合并；它会注册 target 专属 Event Definition、Trajectory view builder，以及会话 `'conversation.view'` slot 环中的一个视图标签页。其 typed `trajectory` locale namespace 持有 ledger、时间线、检查器、tooltip 与无障碍短语中的全部产品编写文案；事件内容、工具名称、标识符与提供方诊断仍作为数据原样呈现。 ## 模型体验 diff --git a/packages/client/ui-trajectory/src/client/trajectory-assistant-definition.ts b/packages/client/ui-trajectory/src/client/trajectory-assistant-definition.ts index 98df63117e..72d78bb01e 100644 --- a/packages/client/ui-trajectory/src/client/trajectory-assistant-definition.ts +++ b/packages/client/ui-trajectory/src/client/trajectory-assistant-definition.ts @@ -1,4 +1,5 @@ import type { Context } from '@deepseek-ai/cordis' +import type { ChunkRowEvent } from '@deepseek-ai/dsh-api-session-controller/types' import type { AssistantBlock, AssistantMessageNode, ConversationLocation, ConversationMatch, ConversationNodeContext, ConversationNodeDefinition, @@ -36,6 +37,7 @@ interface AssistantState { readonly started: boolean readonly sawChunk: boolean readonly blocks: readonly (AssistantBlock | undefined)[] + readonly visibleBlocks: number readonly firstVisibleSeq: number | undefined readonly firstVisibleTime: number | undefined readonly firstTokenTime: number | undefined @@ -45,6 +47,12 @@ interface AssistantState { readonly stepEnd: ConversationMatch | undefined } +function isChunkRunEvent(event: ConversationMatch['event']): event is ChunkRowEvent { + return event.type === 'chunkrow/text-chunks' + || event.type === 'chunkrow/reasoning-chunks' + || event.type === 'chunkrow/tool-call-chunks' +} + function initialState( turn: number, step: number, @@ -60,6 +68,7 @@ function initialState( started, sawChunk: false, blocks: [], + visibleBlocks: 0, firstVisibleSeq: undefined, firstVisibleTime: undefined, firstTokenTime: undefined, @@ -74,12 +83,16 @@ function compactBlocks(blocks: readonly (AssistantBlock | undefined)[]): Assista return blocks.filter((block): block is AssistantBlock => block !== undefined) } -function hasVisibleContent(blocks: readonly AssistantBlock[]): boolean { - return blocks.some((block) => { - if (block.kind === 'tool-call') return false - if (block.kind === 'text' || block.kind === 'reasoning') return block.text.trim() !== '' - return true - }) +function blockIsVisible(block: AssistantBlock | undefined): boolean { + if (block === undefined || block.kind === 'tool-call') return false + if (block.kind === 'text' || block.kind === 'reasoning') return block.text.trim() !== '' + return true +} + +function countVisibleBlocks(blocks: readonly AssistantBlock[]): number { + let count = 0 + for (const block of blocks) if (blockIsVisible(block)) count++ + return count } function hasInterruptionEvidence(blocks: readonly AssistantBlock[]): boolean { @@ -112,12 +125,18 @@ function updateChunk(state: AssistantState, match: ConversationMatch): Assistant return { ...state, sawChunk: true, usage: addUsage(state.usage, chunk.usage) } } const blocks = [...state.blocks] + let changedIndex = -1 + let previousVisible = false switch (chunk.type) { case 'block-start': + changedIndex = chunk.index + previousVisible = blockIsVisible(blocks[chunk.index]) blocks[chunk.index] = emptyAssistantBlock(chunk.blockType) break case 'text-delta': { const previous = blocks[chunk.index] + changedIndex = chunk.index + previousVisible = blockIsVisible(previous) blocks[chunk.index] = { kind: 'text', text: (previous?.kind === 'text' ? previous.text : '') + chunk.text, @@ -126,6 +145,8 @@ function updateChunk(state: AssistantState, match: ConversationMatch): Assistant } case 'reasoning-delta': { const previous = blocks[chunk.index] + changedIndex = chunk.index + previousVisible = blockIsVisible(previous) blocks[chunk.index] = { kind: 'reasoning', text: (previous?.kind === 'reasoning' ? previous.text : '') + chunk.text, @@ -134,6 +155,8 @@ function updateChunk(state: AssistantState, match: ConversationMatch): Assistant } case 'tool-call-delta': { const previous = blocks[chunk.index] + changedIndex = chunk.index + previousVisible = blockIsVisible(previous) const base = previous?.kind === 'tool-call' ? previous : { kind: 'tool-call' as const, callId: '', name: '', argsRaw: '' } @@ -146,17 +169,22 @@ function updateChunk(state: AssistantState, match: ConversationMatch): Assistant break } case 'block-end': + changedIndex = chunk.index + previousVisible = blockIsVisible(blocks[chunk.index]) blocks[chunk.index] = toAssistantBlock(chunk.block) break default: return { ...state, sawChunk: true } } - const visible = hasVisibleContent(compactBlocks(blocks)) + const visibleBlocks = state.visibleBlocks + - Number(previousVisible) + + Number(blockIsVisible(blocks[changedIndex])) return { ...state, sawChunk: true, blocks, - ...(visible && state.firstVisibleSeq === undefined + visibleBlocks, + ...(visibleBlocks > 0 && state.firstVisibleSeq === undefined ? { firstVisibleSeq: match.event.seq, firstVisibleTime: match.event.time } : {}), ...(isTokenDelta(chunk) && state.firstTokenTime === undefined @@ -165,6 +193,88 @@ function updateChunk(state: AssistantState, match: ConversationMatch): Assistant } } +interface ChunkRunBoundaries { + readonly firstTokenTime: number | undefined + readonly firstVisible: { readonly seq: number; readonly time: number } | undefined +} + +function chunkRunBoundaries( + event: ChunkRowEvent, + needsToken: boolean, + needsVisible: boolean, + visibleFromStart: boolean, +): ChunkRunBoundaries { + const fragments = event.type === 'chunkrow/tool-call-chunks' ? event.data.args : event.data.texts + const nameStartsToken = event.type === 'chunkrow/tool-call-chunks' + && Object.hasOwn(event.data, 'name') + let firstTokenTime: number | undefined + let firstVisible: ChunkRunBoundaries['firstVisible'] + let time = event.time + for (let index = 0; index < fragments.length; index++) { + const fragment = fragments[index] as string + if (needsToken && firstTokenTime === undefined && (nameStartsToken || fragment !== '')) { + firstTokenTime = time + } + if (needsVisible && firstVisible === undefined + && (visibleFromStart + || (event.type !== 'chunkrow/tool-call-chunks' && fragment.trim() !== ''))) { + firstVisible = { seq: event.seq + index, time } + } + if ((!needsToken || firstTokenTime !== undefined) + && (!needsVisible || firstVisible !== undefined)) break + time += event.data.dt[index] ?? 0 + } + return { firstTokenTime, firstVisible } +} + +function updateChunkRun(state: AssistantState, event: ChunkRowEvent): AssistantState { + const blocks = [...state.blocks] + const previous = blocks[event.data.index] + const previousVisible = blockIsVisible(previous) + let visibleFromStart = state.visibleBlocks - Number(previousVisible) > 0 + if (event.type === 'chunkrow/text-chunks') { + const text = previous?.kind === 'text' ? previous.text : '' + visibleFromStart ||= text.trim() !== '' + blocks[event.data.index] = { kind: 'text', text: text + event.data.texts.join('') } + } else if (event.type === 'chunkrow/reasoning-chunks') { + const text = previous?.kind === 'reasoning' ? previous.text : '' + visibleFromStart ||= text.trim() !== '' + blocks[event.data.index] = { kind: 'reasoning', text: text + event.data.texts.join('') } + } else { + const base = previous?.kind === 'tool-call' + ? previous + : { kind: 'tool-call' as const, callId: '', name: '', argsRaw: '' } + blocks[event.data.index] = { + kind: 'tool-call', + callId: base.callId || String(event.data.id), + name: Object.hasOwn(event.data, 'name') ? event.data.name as string : base.name, + argsRaw: base.argsRaw + event.data.args.join(''), + } + } + const boundaries = chunkRunBoundaries( + event, + state.firstTokenTime === undefined, + state.firstVisibleSeq === undefined, + visibleFromStart, + ) + const visibleBlocks = state.visibleBlocks + - Number(previousVisible) + + Number(blockIsVisible(blocks[event.data.index])) + return { + ...state, + sawChunk: true, + blocks, + visibleBlocks, + ...(boundaries.firstVisible === undefined ? {} : { + firstVisibleSeq: boundaries.firstVisible.seq, + firstVisibleTime: boundaries.firstVisible.time, + }), + ...(boundaries.firstTokenTime === undefined ? {} : { + firstTokenTime: boundaries.firstTokenTime, + }), + } +} + function closedBoundary( context: ConversationNodeContext, ): { seq: number; time: number } | undefined { @@ -180,15 +290,28 @@ function closedBoundary( function fallbackState(context: ConversationNodeContext): AssistantState | undefined { let state: AssistantState | undefined for (const match of context.matches) { + if (isChunkRunEvent(match.event)) { + state ??= initialState( + match.event.data.turn, + match.event.data.step, + match.event.seq, + match.event.time, + false, + ) + state = updateChunkRun(state, match.event) + continue + } const event = match.event if (event.type === 'assistant/chunk') { state ??= initialState(event.data.turn, event.data.step, event.seq, event.time, false) state = updateChunk(state, match) } else if (event.type === 'assistant/message') { state ??= initialState(event.data.turn, event.data.step, event.seq, event.time, false) + const blocks = toAssistantBlocks(event.data.message.content) state = { ...state, - blocks: toAssistantBlocks(event.data.message.content), + blocks, + visibleBlocks: countVisibleBlocks(blocks), final: match, usage: state.usage ?? event.data.usage, } @@ -228,8 +351,9 @@ function finalNode( } } const boundary = closedBoundary(context) + if (boundary === undefined) return undefined const blocks = compactBlocks(state.blocks) - if (boundary === undefined || !hasInterruptionEvidence(blocks)) return undefined + if (!hasInterruptionEvidence(blocks)) return undefined return { kind: 'assistant', seq: boundary.seq - 0.9, @@ -291,6 +415,9 @@ const trajectoryAssistantDefinition: ConversationNodeDefinition || event.type === 'step/end') { return { id: `${event.data.turn}:${event.data.step}`, role: 'update' } } + if (isChunkRunEvent(event)) { + return { id: `${event.data.turn}:${event.data.step}`, role: 'update' } + } return null }, start: (_context, match) => { @@ -306,11 +433,14 @@ const trajectoryAssistantDefinition: ConversationNodeDefinition ) }, update: (context, match) => { + if (isChunkRunEvent(match.event)) return updateChunkRun(context.state, match.event) if (match.event.type === 'assistant/chunk') return updateChunk(context.state, match) if (match.event.type === 'assistant/message') { + const blocks = toAssistantBlocks(match.event.data.message.content) return { ...context.state, - blocks: toAssistantBlocks(match.event.data.message.content), + blocks, + visibleBlocks: countVisibleBlocks(blocks), final: match, usage: context.state.usage ?? match.event.data.usage, } @@ -340,6 +470,7 @@ const trajectoryAssistantDefinition: ConversationNodeDefinition }, publication: (match) => { if (match.event.type === 'step/start') return 'none' + if (isChunkRunEvent(match.event)) return 'animation-frame' if (match.event.type !== 'assistant/chunk') return 'immediate' const type = match.event.data.chunk.type return type === 'usage' || type === 'finish' ? 'none' : 'animation-frame' diff --git a/packages/client/ui-trajectory/tests/conversation-definitions.client.spec.ts b/packages/client/ui-trajectory/tests/conversation-definitions.client.spec.ts index 788b42f845..bd7623142e 100644 --- a/packages/client/ui-trajectory/tests/conversation-definitions.client.spec.ts +++ b/packages/client/ui-trajectory/tests/conversation-definitions.client.spec.ts @@ -1,9 +1,17 @@ import type { Context } from '@deepseek-ai/cordis' import { describe, expect, it } from 'vitest' import type { - ConversationEventInput, ConversationNodeDefinition, ConversationViewDefinition, + SessionEventLikeEntry, SessionLiveEventEntry, +} from '@deepseek-ai/dsh-api-session-controller/client' +import type { + ChunkRowEvent, +} from '@deepseek-ai/dsh-api-session-controller/types' +import type { + ConversationNodeDefinition, ConversationViewDefinition, } from '@deepseek-ai/dsh-client-ui-conversation/client' import { ConversationNodeAssembler, inspectRequestPrompt } from '@deepseek-ai/dsh-client-ui-conversation/client' +import { isChunkRow, packChunkRuns, type ChunkRow } from '@deepseek-ai/dsh-session/chunk-rows' +import type { SessionEvent } from '@deepseek-ai/dsh-session/types' import { registerTrajectoryAssistantDefinition } from '../src/client/trajectory-assistant-definition.ts' import { registerTrajectoryCompactionDefinitions } from '../src/client/trajectory-compaction-definition.ts' import type { TrajectorySnapshot } from '../src/client/trajectory-contract.ts' @@ -52,19 +60,38 @@ function at( type: string, data: unknown, extra: Record = {}, -): ConversationEventInput { +): SessionLiveEventEntry { return { + type: 'event', event: { seq, time: 1_700_000_000_000 + seq, type, data, ...extra, - } as unknown as ConversationEventInput['event'], + } as unknown as SessionEvent, } } -function assembler(events: readonly ConversationEventInput[]): ConversationNodeAssembler { +function chunkEntry(row: ChunkRow): SessionEventLikeEntry { + return { + type: 'chunks', + event: { + type: `chunkrow/${row.type}`, + seq: row.seq0, + time: row.time0, + data: row.data, + } as ChunkRowEvent, + } +} + +function packedInputs(entries: readonly SessionLiveEventEntry[]): SessionEventLikeEntry[] { + return packChunkRuns(entries.map(entry => entry.event)).map((record) => { + return isChunkRow(record) ? chunkEntry(record) : { type: 'event', event: record } + }) +} + +function assembler(events: readonly SessionEventLikeEntry[]): ConversationNodeAssembler { const value = new ConversationNodeAssembler( new TestEventDefinitions(), new TestViewDefinitions(), @@ -153,6 +180,139 @@ describe('Trajectory conversation Definitions', () => { }]) }) + it('folds packed Assistant runs to the same Trajectory state as scalar deltas', () => { + const runningHistory = [ + at(1, 'turn/start', { turn: 1 }), + at(2, 'step/start', { turn: 1, step: 1 }), + at(3, 'assistant/chunk', { + turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: '' }, + }), + at(4, 'assistant/chunk', { + turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: ' ' }, + }), + at(5, 'assistant/chunk', { + turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'answer' }, + }), + at(6, 'assistant/chunk', { + turn: 1, step: 1, chunk: { type: 'reasoning-delta', index: 1, text: '' }, + }), + at(7, 'assistant/chunk', { + turn: 1, step: 1, chunk: { type: 'reasoning-delta', index: 1, text: 'think' }, + }), + at(8, 'assistant/chunk', { + turn: 1, step: 1, chunk: { type: 'reasoning-delta', index: 1, text: 'ing' }, + }), + at(9, 'assistant/chunk', { + turn: 1, step: 1, + chunk: { type: 'tool-call-delta', index: 2, id: 'call-1', argumentsDelta: '' }, + }), + at(10, 'assistant/chunk', { + turn: 1, step: 1, + chunk: { type: 'tool-call-delta', index: 2, id: 'call-1', argumentsDelta: '{"x":' }, + }), + at(11, 'assistant/chunk', { + turn: 1, step: 1, + chunk: { type: 'tool-call-delta', index: 2, id: 'call-1', argumentsDelta: '1}' }, + }), + ] + const runningScalar = snapshot(assembler(runningHistory)) + const packedHistory = packedInputs(runningHistory) + expect(packedHistory.filter(input => input.event.type.startsWith('chunkrow/'))).toHaveLength(3) + const runningPacked = snapshot(assembler(packedHistory)) + expect(runningPacked).toEqual(runningScalar) + expect(runningPacked.partial?.blocks).toEqual([ + { kind: 'text', text: ' answer' }, + { kind: 'reasoning', text: 'thinking' }, + { kind: 'tool-call', callId: 'call-1', name: '', argsRaw: '{"x":1}' }, + ]) + + const partialHistory = [ + ...runningHistory.slice(2), + at(12, 'step/end', { turn: 1, step: 1 }), + ] + const partialScalar = snapshot(assembler(partialHistory)) + const partialPacked = snapshot(assembler(packedInputs(partialHistory))) + expect(partialPacked).toEqual(partialScalar) + expect(partialPacked.eventNodes).toMatchObject([{ + kind: 'assistant', + interrupted: true, + blocks: [ + { kind: 'text', text: ' answer' }, + { kind: 'reasoning', text: 'thinking' }, + { kind: 'tool-call', callId: 'call-1', name: '', argsRaw: '{"x":1}' }, + ], + }]) + + const finalizedHistory = [ + at(20, 'turn/start', { turn: 2 }), + at(21, 'step/start', { turn: 2, step: 1 }), + at(22, 'assistant/chunk', { + turn: 2, step: 1, chunk: { type: 'text-delta', index: 0, text: '' }, + }, { time: 3_000 }), + at(23, 'assistant/chunk', { + turn: 2, step: 1, chunk: { type: 'text-delta', index: 0, text: ' ' }, + }, { time: 3_000 }), + at(24, 'assistant/chunk', { + turn: 2, step: 1, chunk: { type: 'text-delta', index: 0, text: 'first' }, + }, { time: 2_998 }), + at(25, 'assistant/chunk', { + turn: 2, step: 1, chunk: { type: 'usage', usage: { inputTokens: 10, outputTokens: 3 } }, + }), + at(26, 'llm/retry', { + retryId: 'packed-retry', turn: 2, step: 1, provider: 'test', mode: 'normal', + policyKey: 'test-normal', retry: 1, maxRetries: 2, delayMs: 25, + failure: { code: 'TRANSPORT', message: 'temporary failure' }, + }), + at(27, 'assistant/chunk', { + turn: 2, step: 1, chunk: { type: 'text-delta', index: 0, text: '' }, + }), + at(28, 'assistant/chunk', { + turn: 2, step: 1, chunk: { type: 'text-delta', index: 0, text: 'second' }, + }), + at(29, 'assistant/chunk', { + turn: 2, step: 1, chunk: { type: 'text-delta', index: 0, text: ' attempt' }, + }), + at(30, 'assistant/message', { + turn: 2, step: 1, message: assistantMessage('packed-final', 'done'), + }), + at(31, 'step/end', { turn: 2, step: 1 }), + ] + const finalizedScalar = snapshot(assembler(finalizedHistory)) + const finalizedPacked = snapshot(assembler(packedInputs(finalizedHistory))) + expect(finalizedPacked).toEqual(finalizedScalar) + expect(finalizedPacked.eventNodes.find(node => node.kind === 'assistant')).toMatchObject({ + timing: { firstTokenTime: 3_000 }, + }) + expect(finalizedPacked.requests).toMatchObject([{ + purpose: 'assistant', + usage: { inputTokens: 10, outputTokens: 3 }, + retry: 1, + }]) + + const namedToolHistory = [ + at(40, 'turn/start', { turn: 3 }), + at(41, 'step/start', { turn: 3, step: 1 }), + ...[42, 43, 44].map(seq => at(seq, 'assistant/chunk', { + turn: 3, step: 1, + chunk: { type: 'tool-call-delta', index: 0, id: 'call-2', name: 'read', argumentsDelta: '' }, + }, { time: 4_000 + seq - 42 })), + at(45, 'assistant/message', { + turn: 3, + step: 1, + message: { + ...assistantMessage('named-tool-final', ''), + content: [{ type: 'tool-call', id: 'call-2', name: 'read', arguments: '' }], + }, + }), + ] + const namedToolScalar = snapshot(assembler(namedToolHistory)) + const namedToolPacked = snapshot(assembler(packedInputs(namedToolHistory))) + expect(namedToolPacked).toEqual(namedToolScalar) + expect(namedToolPacked.eventNodes.find(node => node.kind === 'assistant')).toMatchObject({ + timing: { firstTokenTime: 4_000 }, + }) + }) + it('classifies a cancellation-finalized prefix as an interrupted request result', () => { const current = snapshot(assembler([ at(1, 'turn/start', { turn: 1 }), diff --git a/packages/client/ui-workflow-run/tests/workflow-run.client.spec.tsx b/packages/client/ui-workflow-run/tests/workflow-run.client.spec.tsx index 9016b974d9..1758c8c27e 100644 --- a/packages/client/ui-workflow-run/tests/workflow-run.client.spec.tsx +++ b/packages/client/ui-workflow-run/tests/workflow-run.client.spec.tsx @@ -6,12 +6,15 @@ import { ConversationNodeAssembler, UiConversation, } from '@deepseek-ai/dsh-client-ui-conversation/client' import type { - ConversationEventInput, ConversationMatch, ConversationNodeDefinition, ConversationViewDefinition, + ConversationMatch, ConversationNodeDefinition, ConversationStartMatch, + ConversationViewDefinition, } from '@deepseek-ai/dsh-client-ui-conversation/client' import type { ChatConversationViewNode } from '@deepseek-ai/dsh-client-ui-chat/client' import { SlotRegistry } from '@deepseek-ai/dsh-client-ui-renderer/client' -import type { SessionListState } from '@deepseek-ai/dsh-api-session-controller/client' -import type { SessionId } from '@deepseek-ai/dsh-session/types' +import type { + SessionListState, SessionLiveEventEntry, +} from '@deepseek-ai/dsh-api-session-controller/client' +import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session/types' import { apply as applyLocale, inject as localeInject } from '@deepseek-ai/dsh-client-locale/client' import { chatSnapshot as emptyChatSnapshot, conversationSnapshot, makeTranslate, sessionSnapshot, @@ -84,15 +87,17 @@ const chatViewDefinition: ConversationViewDefinition, tag: ChunkRow['type']): Chu // outside any encoder's image: float arithmetic would round it to a // different number than exact arithmetic, a silent corruption. Within safe // range every step is exact, so the first departure is always caught. - if (!Number.isSafeInteger((value.seq0 as number) + payload.length - 1)) { + if (payload.length - 1 > Number.MAX_SAFE_INTEGER - (value.seq0 as number)) { malformed(tag, 'member seqs must stay safe integers') } let time = value.time0 as number @@ -313,9 +334,11 @@ function expandRow(row: ChunkRow): SessionEvent[] { argumentsDelta: members[k] as string, } break - /* v8 ignore next 2 -- validateRow only returns the three row tags */ - default: - return assertNever(row, 'chunk-rows expandRow') + /* v8 ignore next 4 -- validateRow only returns the three row tags */ + default: { + const unreachable: never = row + throw new Error(`chunk-rows received unsupported row ${String(unreachable)}`) + } } events.push({ type: 'assistant/chunk', diff --git a/packages/core/session/tests/chunk-rows.spec.ts b/packages/core/session/tests/chunk-rows.spec.ts index 4fe14894e5..0fbe7c1631 100644 --- a/packages/core/session/tests/chunk-rows.spec.ts +++ b/packages/core/session/tests/chunk-rows.spec.ts @@ -9,6 +9,7 @@ import fc from 'fast-check' import { CallId } from '@deepseek-ai/dsh-llm' import type { StreamChunk } from '@deepseek-ai/dsh-llm' import { decodeStorageRecord, packChunkRuns } from '@deepseek-ai/dsh-session' +import { chunkRowLength, isChunkRow } from '@deepseek-ai/dsh-session/chunk-rows' import type { ChunkRow, SessionEvent, StorageRecord } from '@deepseek-ai/dsh-session' /** Build an `assistant/chunk` event with the exact live-append shape. */ @@ -37,6 +38,9 @@ describe('packChunkRuns', () => { expect(row.seq0).toBe(0) expect(row.time0).toBe(1000) expect(row.data).toMatchObject({ turn: 1, step: 1, index: 0, dt: [10, 10, 10, 10], texts: ['t0', 't1', 't2', 't3', 't4'] }) + expect(isChunkRow(row)).toBe(true) + expect(chunkRowLength(row)).toBe(5) + expect(isChunkRow(events[0] as SessionEvent)).toBe(false) expect(decodeAll(packed)).toStrictEqual(events) }) @@ -48,6 +52,7 @@ describe('packChunkRuns', () => { expect(packed.map(r => (r as ChunkRow).type)).toStrictEqual(['reasoning-chunks', 'tool-call-chunks']) const row = packed[1] as ChunkRow & { type: 'tool-call-chunks' } expect(row.data).toMatchObject({ id: 'c1', name: 'write', args: ['a4', 'a5', 'a6'] }) + expect(chunkRowLength(row)).toBe(3) expect(decodeAll(packed)).toStrictEqual([...reasoning, ...toolCall]) }) @@ -167,7 +172,7 @@ describe('decodeStorageRecord', () => { ['a dt arity mismatch', { type: 'text-chunks', seq0: 0, time0: 1, data: { turn: 1, step: 1, index: 0, dt: [1, 2], texts: ['a', 'b'] } }], ['a non-finite dt gap', { type: 'text-chunks', seq0: 0, time0: 1, data: { turn: 1, step: 1, index: 0, dt: [NaN], texts: ['a', 'b'] } }], ['a fractional dt gap', { type: 'text-chunks', seq0: 0, time0: 1, data: { turn: 1, step: 1, index: 0, dt: [0.5], texts: ['a', 'b'] } }], - ['a member seq leaving safe range', { type: 'text-chunks', seq0: Number.MAX_SAFE_INTEGER, time0: 1, data: { turn: 1, step: 1, index: 0, dt: [0, 0], texts: ['a', 'b', 'c'] } }], + ['a member seq leaving safe range', { type: 'text-chunks', seq0: Number.MAX_SAFE_INTEGER, time0: 1, data: { turn: 1, step: 1, index: 0, dt: [0], texts: ['a', 'b'] } }], ['a member time leaving safe range', { type: 'text-chunks', seq0: 0, time0: Number.MAX_SAFE_INTEGER, data: { turn: 1, step: 1, index: 0, dt: [1], texts: ['a', 'b'] } }], ['a non-numeric turn', { type: 'text-chunks', seq0: 0, time0: 1, data: { turn: 'x', step: 1, index: 0, dt: [], texts: ['a'] } }], ['a tool-call row without id', { type: 'tool-call-chunks', seq0: 0, time0: 1, data: { turn: 1, step: 1, index: 0, dt: [], args: ['a'] } }], diff --git a/packages/extensions/cordis-client-runner/src/client/api-catalog.ts b/packages/extensions/cordis-client-runner/src/client/api-catalog.ts index 1635660caf..993b191b07 100644 --- a/packages/extensions/cordis-client-runner/src/client/api-catalog.ts +++ b/packages/extensions/cordis-client-runner/src/client/api-catalog.ts @@ -445,6 +445,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'ChildrenDecl', declaration: 'export type ChildrenDecl = {\n [P in keyof SlotMap & string]?: SlotSpec;\n};', }, + { + name: 'ChunkRowEvent', + declaration: 'export type ChunkRowEvent = {\n [Kind in ChunkRow[\'type\']]: {\n readonly type: `chunkrow/${Kind}`;\n readonly seq: number;\n readonly time: number;\n readonly data: Extract[\'data\'];\n };\n}[ChunkRow[\'type\']];', + }, { name: 'ClientConnectionRpc', declaration: 'export interface ClientConnectionRpc {\n call(channel: string, endpoint: string, payload: unknown, signal?: AbortSignal): Promise>;\n readonly open?: (channel: string, endpoint: string, payload: unknown, signal: AbortSignal) => AsyncIterable;\n}', @@ -643,11 +647,11 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SessionEventChange', - declaration: 'export type SessionEventChange = {\n readonly kind: \'replace\';\n readonly entries: readonly SessionEventEntry[];\n} | {\n readonly kind: \'prepend\';\n readonly entries: readonly SessionEventEntry[];\n} | {\n readonly kind: \'append\';\n readonly entries: readonly SessionEventEntry[];\n};', + declaration: 'export type SessionEventChange = {\n readonly kind: \'replace\';\n readonly entries: readonly SessionEventLikeEntry[];\n} | {\n readonly kind: \'prepend\';\n readonly entries: readonly SessionEventLikeEntry[];\n} | {\n readonly kind: \'append\';\n readonly entries: readonly SessionLiveEventEntry[];\n};', }, { - name: 'SessionEventEntry', - declaration: 'export interface SessionEventEntry {\n readonly event: SessionWireEvent;\n}', + name: 'SessionEventLikeEntry', + declaration: 'export type SessionEventLikeEntry = {\n readonly type: \'event\';\n readonly event: SessionEvent;\n} | {\n readonly type: \'chunks\';\n readonly event: ChunkRowEvent;\n};', }, { name: 'SessionEventSource', @@ -655,7 +659,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SessionEventWindow', - declaration: 'export interface SessionEventWindow {\n readonly entries: readonly SessionEventEntry[];\n readonly hasMore: boolean;\n readonly revision: number;\n readonly change: SessionEventChange;\n}', + declaration: 'export interface SessionEventWindow {\n readonly entries: readonly SessionEventLikeEntry[];\n readonly hasMore: boolean;\n readonly revision: number;\n readonly change: SessionEventChange;\n}', }, { name: 'SessionFace', @@ -665,6 +669,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'SessionIdOf', declaration: 'export type SessionIdOf = SessionStandardProps extends {\n sessionId: infer S;\n} ? S : string;', }, + { + name: 'SessionLiveEventEntry', + declaration: 'export type SessionLiveEventEntry = Extract;', + }, { name: 'SessionMaybeStandardProps', declaration: 'export interface SessionMaybeStandardProps {\n}', @@ -685,10 +693,6 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'SessionStandardProps', declaration: 'export interface SessionStandardProps {\n}', }, - { - name: 'SessionWireEvent', - declaration: 'export interface SessionWireEvent {\n readonly type: string;\n readonly seq: number;\n readonly time: number;\n readonly data: JsonValue;\n readonly ignorable?: true;\n readonly sourceEventSeqs?: number[];\n readonly surfaceOp?: SurfaceOp;\n}', - }, { name: 'SlotComponent', declaration: 'export type SlotComponent

= (props: P) => ReactNode;', diff --git a/packages/extensions/tool-cordis/src/api-catalog.ts b/packages/extensions/tool-cordis/src/api-catalog.ts index d742bda274..ea872d4dd9 100644 --- a/packages/extensions/tool-cordis/src/api-catalog.ts +++ b/packages/extensions/tool-cordis/src/api-catalog.ts @@ -3343,6 +3343,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'Branded', declaration: 'export type Branded = string & {\n readonly [BRAND]: B;\n};', }, + { + name: 'ChunkRowEvent', + declaration: 'export type ChunkRowEvent = {\n [Kind in ChunkRow[\'type\']]: {\n readonly type: `chunkrow/${Kind}`;\n readonly seq: number;\n readonly time: number;\n readonly data: Extract[\'data\'];\n };\n}[ChunkRow[\'type\']];', + }, { name: 'ClientArtifactBaseline', declaration: 'export interface ClientArtifactBaseline {\n readonly path: string;\n readonly mtimeMs: number;\n readonly size: number;\n readonly mapMtimeMs: number | null;\n readonly mapSize: number | null;\n}', @@ -4443,6 +4447,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'SessionCancelValue', declaration: 'export interface SessionCancelValue {\n readonly accepted: true;\n}', }, + { + name: 'SessionChunkRun', + declaration: 'export interface SessionChunkRun {\n readonly type: \'chunks\';\n readonly event: ChunkRowEvent;\n}', + }, { name: 'SessionControlBaseline', declaration: 'export interface SessionControlBaseline {\n readonly queues: Readonly>;\n readonly jobs: Readonly>;\n readonly projections: Readonly>;\n}', @@ -4473,7 +4481,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SessionEventEntry', - declaration: 'export interface SessionEventEntry {\n readonly event: SessionWireEvent;\n}', + declaration: 'export interface SessionEventEntry {\n readonly type: \'event\';\n readonly event: SessionWireEvent;\n}', }, { name: 'SessionEventMap', @@ -4537,7 +4545,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SessionFollowFrame', - declaration: 'export type SessionFollowFrame = {\n readonly type: \'snapshot\';\n readonly header: SessionHeader;\n readonly cursor: number;\n readonly events: readonly SessionEventEntry[];\n readonly hasMore: boolean;\n readonly projections: SessionProjectionBaseline;\n} | ({\n readonly type: \'event\';\n} & SessionEventEntry);', + declaration: 'export type SessionFollowFrame = {\n readonly type: \'snapshot\';\n readonly header: SessionHeader;\n readonly cursor: number;\n readonly records: readonly SessionHistoryRecord[];\n readonly hasMore: boolean;\n readonly projections: SessionProjectionBaseline;\n} | SessionEventEntry;', }, { name: 'SessionFollowRequest', @@ -4559,6 +4567,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'SessionHeader', declaration: 'export interface SessionHeader {\n readonly version: number;\n readonly id: SessionId;\n readonly createdAt: number;\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n readonly origin?: \'subagent\';\n readonly delegationDepth?: number;\n readonly agentPreset?: string;\n}', }, + { + name: 'SessionHistoryRecord', + declaration: 'export type SessionHistoryRecord = SessionEventEntry | SessionChunkRun;', + }, { name: 'SessionId', declaration: 'export type SessionId = Branded<\'SessionId\'>;', @@ -4605,7 +4617,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SessionPage', - declaration: 'export interface SessionPage {\n readonly events: readonly SessionEventEntry[];\n readonly hasMore: boolean;\n}', + declaration: 'export interface SessionPage {\n readonly records: readonly SessionHistoryRecord[];\n readonly hasMore: boolean;\n}', }, { name: 'SessionPageRequest', diff --git a/packages/subagent/subagent-codex/README.i18n.yaml b/packages/subagent/subagent-codex/README.i18n.yaml index fd0cccc02d..b4cb448bd2 100644 --- a/packages/subagent/subagent-codex/README.i18n.yaml +++ b/packages/subagent/subagent-codex/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/subagent/subagent-codex/README.md -README.md: 5016d6b9aa4b57c9d1e83701a0ccfc4b04616f6d -README.zh.md: adabd942c362a28a4eeabe7a4d1b27b138aee4c6 +README.md: 7ff5e1dd06f18cc5e313cca1a84576e976e96454 +README.zh.md: 8532f6cfb5ece282aa916771eb971d0f3edfab53 diff --git a/packages/subagent/subagent-codex/README.md b/packages/subagent/subagent-codex/README.md index 5016d6b9aa..7ff5e1dd06 100644 --- a/packages/subagent/subagent-codex/README.md +++ b/packages/subagent/subagent-codex/README.md @@ -6,13 +6,13 @@ This package registers a Profile-named Codex subagent provider whose default nam ## Start and ownership -`start(request)` accepts only a non-empty sequence of text blocks and derives the child cwd from the parent Session. It then spawns the fixed command through [`dsh-subprocess`](../../subprocess/subprocess/README.md), performs `initialize` → `initialized`, maps the Profile-selected mode into official `thread/start` approval/reviewer/sandbox fields beside `{ cwd, ephemeral: true }`, and publishes the run only after Codex returns a valid ephemeral thread. A failure or cancellation before publication closes the wire, terminates the managed process tree, waits for it to exit, and rejects `start()`. Non-cancellation rejections expose only the fixed `initialize` or `thread-start` stage plus an already observed process outcome; raw product and Host errors remain on internal cause chains. +`start(request)` accepts only a non-empty sequence of text blocks and derives the child cwd from the parent Session. It then spawns the fixed command through [`dsh-subprocess`](../../subprocess/subprocess/README.md), performs `initialize` → `initialized`, maps the Profile-selected mode and optional model into official `thread/start` fields beside `{ cwd, ephemeral: true }`, and publishes the run only after Codex returns a valid ephemeral thread. A failure or cancellation before publication closes the wire, terminates the managed process tree, waits for it to exit, and rejects `start()`. Non-cancellation rejections expose only the fixed `initialize` or `thread-start` stage plus an already observed process outcome; raw product and Host errors remain on internal cause chains. The published `run.result` starts exactly one turn. It accepts only notifications for that run's thread and turn, then waits for the authoritative `turn/completed` terminal notification. The latest `agentMessage` with `phase: "final_answer"` wins; when Codex emits no explicit final phase, the latest message with `phase: null` is the compatibility fallback. Commentary never replaces either answer, and a successful turn with no nonblank answer settles as an error. -For command and file approvals, the unattended provider selects a non-approval decision offered by the request, preferring `cancel`; the stable 0.147.0 request shape without an offered-decision list falls back to `decline`. It answers permission requests with an empty turn-scoped permission set, answers user-input requests with no answers, and declines MCP elicitation. A request with no legal unattended response, or any unknown server request, fails the run. The wire records only the effective mode, request category, decision, and fixed safe reason. It also recognizes declined command/file items and `sandboxError` terminals. Codex 0.147.0 writes some early `never` rejections and sandbox violations only to structured stderr, so the Provider pipes stderr, forwards it unchanged to the host, and matches two fixed signatures in a bounded per-run tail; raw stderr never enters the diagnostic. +For command and file approvals, the unattended provider selects a non-approval decision offered by the request, preferring `cancel`; the stable 0.149.1 request shape without an offered-decision list falls back to `decline`. It answers permission requests with an empty turn-scoped permission set, answers user-input requests with no answers, and declines MCP elicitation. A request with no legal unattended response, or any unknown server request, fails the run. The wire records only the effective mode, request category, decision, and fixed safe reason. It also recognizes declined command/file items and structured `sandboxError` terminals. Product stderr is forwarded unchanged to the Host but is never classified or copied into the diagnostic. -Local cancellation wins the result race and maps to `aborted`. For failed turns, the diagnostic preserves all eleven string and five object variants in the Codex 0.147.0 `codexErrorInfo` union; the four connection/stream variants retain a numeric `httpStatusCode` when supplied, while `activeTurnNotSteerable` does not expose `turnKind`. The diagnostic also names `turn-start`, `turn`, or `process`, independently includes available exit code and signal, and uses `unknown` for unrecognized or malformed values without copying raw fields. `contextWindowExceeded` remains `max-tokens`; every other remote interruption or failure remains `error`, and the provider produces no `refusal`. A contributing permission decision follows the structured failure line. Successful and locally cancelled runs omit both facts. +Local cancellation wins the result race and maps to `aborted`. Failed turns use the coarse categories `limit`, `access-policy`, `service`, `transport`, `product-error`, `invalid-result`, or `unknown`; an early app-server exit uses `process`. Applicable connection and stream failures retain a numeric `httpStatusCode`. The diagnostic also names `turn-start`, `turn`, or `process` and independently includes available exit code and signal without copying raw fields. `contextWindowExceeded` remains `max-tokens`; every other remote interruption or failure remains `error`, and the provider produces no `refusal`. A contributing structured permission decision follows the failure line. Successful and locally cancelled runs omit both facts. `dispose()` is idempotent: it requests a best-effort `turn/interrupt` with both current ids when they are known, closes the JSON-RPC wire, ends stdin, invokes the shared process-tree termination escalation, waits for whole-tree exit, and detaches the stderr observer. Independent cleanup rejection uses the fixed `teardown` stage and any available process outcome. When startup and rollback both fail, the top-level aggregate message preserves both safe stage lines while the raw failures remain internal. @@ -25,6 +25,7 @@ The provider advertises no optional start-time capabilities and reports `inherit | Key | Default | Meaning | |---|---|---| | `providerName` | `codex` | Non-empty registry name on `ctx.subagents`; each mounted instance needs a unique value. | +| `model` | native Codex settings | Optional non-empty native model name fixed for every thread from this Provider instance; omission sends no app-server override. | | `env` | `{}` | Explicit child environment layered over the subprocess seam's credential-scrubbed parent environment. | | `permissionMode` | `never` | Native non-interactive approval and sandbox mode fixed for every thread from this Provider instance. | | `disposeGraceMs` | `3000` | Positive finite grace in milliseconds, no greater than [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.md), between the shared process-tree owner's termination tiers; disposal then waits for whole-tree exit. | @@ -35,7 +36,7 @@ The provider advertises no optional start-time capabilities and reports `inherit | `approve-for-me` | `approvalPolicy: on-request`, `approvalsReviewer: auto_review`, `sandbox: workspace-write` | Route permission requests through Codex automatic review without a human. | | `dangerously-bypass-approvals-and-sandbox` | `approvalPolicy: never`, `sandbox: danger-full-access` | Skip approval and sandbox enforcement; this value must be selected explicitly. | -Production resolves the `codex` bin declared by its pinned `@openai/codex@0.147.0` dependency and launches that JavaScript wrapper with the current Node executable. The wrapper selects the matching native platform payload; the provider neither inspects nor falls back to a host `codex` on `PATH`. Native Codex configuration and authentication remain authoritative through the parent cwd, `HOME`, and `CODEX_HOME`, while the Provider overrides only the selected thread approval/reviewer/sandbox fields. All other project, model, provider, MCP, hook, skill, and account settings remain native. The plugin does not select a model, create `CODEX_HOME`, log in, or probe an account. Credential-shaped ambient variables are removed by the subprocess seam before the explicit `env` overlay is applied. +Production resolves the `codex` bin declared by its pinned `@openai/codex@0.149.1` dependency and launches that JavaScript wrapper with the current Node executable. The wrapper selects the matching native platform payload; the provider neither inspects nor falls back to a host `codex` on `PATH`. Native Codex configuration and authentication remain authoritative through the parent cwd, `HOME`, and `CODEX_HOME`. A configured `model` is passed unchanged on each ephemeral `thread/start`; omission leaves the field absent, and the Provider does not discover models, rewrite aliases, select `modelProvider` or `serviceTier`, or set a fallback. The selected permission mode remains the only other thread-level override. The plugin does not create `CODEX_HOME`, log in, or probe an account. Credential-shaped ambient variables are removed by the subprocess seam before the explicit `env` overlay is applied. This package is an optional Profile Bundle. Install it into the target Profile, then restart that Profile; installation brings the official wrapper and one compatible native platform payload into that Profile, while the declared `cordis.patch.yml` layer registers only the dormant `codex` Host provider and starts no Codex process. Removing the package withdraws that provider and its private runtime closure on the next Profile start. @@ -45,7 +46,7 @@ dsh plugin --profile remove @deepseek-ai/dsh-subagent-codex dsh --profile ``` -Installation controls Host availability, not model permission. The Bundle supplies the dormant default `codex` row; the Profile may replace that row's complete config or mount additional rows with distinct `providerName`, `permissionMode`, and `env` values. Loading an instance starts no Codex process until a bound tool calls it. Each `dsh-tool-subagent` row names one provider and needs its own `toolName`, so the model sees static tools rather than a dynamic provider selector. Full Agent Presets carry a matching default product tool row with `disabled: true`; copy a preset and remove that field to expose `subagent_codex` only to agents composed from the copy. Its `one-shot` policy keeps omitted or `false` `run_in_background` calls in the foreground, while explicit `true` returns a parent-owned Job id for `job_output` or `job_kill`. The base host and full presets already provide the generic Job registry and controls. +Installation controls Host availability, not model permission. The Bundle supplies the dormant default `codex` row; the Profile may replace that row's complete config or mount additional rows with distinct `providerName`, `model`, `permissionMode`, and `env` values. Loading an instance starts no Codex process until a bound tool calls it. Each `dsh-tool-subagent` row names one provider and needs its own `toolName`, so the model sees static tools rather than a dynamic provider or model selector. Full Agent Presets carry a matching default product tool row with `disabled: true`; copy a preset and remove that field to expose `subagent_codex` only to agents composed from the copy. Its `one-shot` policy keeps omitted or `false` `run_in_background` calls in the foreground, while explicit `true` returns a parent-owned Job id for `job_output` or `job_kill`. The base host and full presets already provide the generic Job registry and controls. The standalone composition below shows the complete explicit capability. A Profile based on `@deepseek-ai/dsh-base` keeps its existing Job rows, adds the product provider and tool rows, and does not mount duplicate Job services. @@ -54,6 +55,7 @@ The standalone composition below shows the complete explicit capability. A Profi name: '@deepseek-ai/dsh-subagent-codex' config: providerName: codex-safe + model: approved-review-model permissionMode: never env: OPENAI_API_KEY: !!js process.env.OPENAI_API_KEY @@ -62,6 +64,7 @@ The standalone composition below shows the complete explicit capability. A Profi name: '@deepseek-ai/dsh-subagent-codex' config: providerName: codex-bypass + model: approved-edit-model permissionMode: dangerously-bypass-approvals-and-sandbox env: OPENAI_API_KEY: !!js process.env.OPENAI_API_KEY @@ -94,9 +97,9 @@ The standalone composition below shows the complete explicit capability. A Profi ## Product compatibility and evidence -The production wire intentionally implements only the app-server methods required by this one-shot contract. The runtime dependency and all six optional-dependency aliases are pinned to `@openai/codex@0.147.0` / `codex-cli 0.147.0`. A normal install selects one payload for the current OS and CPU. For the current darwin-arm64 payload, `npm pack --dry-run --json @openai/codex@0.147.0-darwin-arm64` reports 111,199,052 packed bytes and 274,777,843 unpacked bytes. That package contains native `codex`, `codex-code-mode-host`, `rg`, and `zsh` resources; other platforms may differ, and these values are disclosure rather than an installation threshold. +The production wire intentionally implements only the app-server methods required by this one-shot contract. The runtime dependency and all six optional-dependency aliases are pinned to `@openai/codex@0.149.1` / `codex-cli 0.149.1`. A normal install selects one payload for the current OS and CPU. For the current darwin-arm64 payload, `npm pack --dry-run --json @openai/codex@0.149.1-darwin-arm64` reports 114,152,335 packed bytes and 282,491,555 unpacked bytes. That package contains native `codex`, `codex-code-mode-host`, `rg`, and `zsh` resources; other platforms may differ, and these values are disclosure rather than an installation threshold. -Generated schema evidence and package tests pin all sixteen error-info variants, HTTP-status locations, six lifecycle stages, process outcomes, stop-reason mapping, unknown fallback, sanitization, permission ordering, cancellation, concurrency, and cleanup aggregation. The keyless real-product test drives the package wrapper against a loopback Responses fixture and observes the package-local argv, exact Bearer key, original task, byte-exact final answer, thread-level `never` overriding ambient `on-request`, automatic-review startup, unattended rejection without file side effects, a real `internalServerError`, explicit dangerous-bypass writing in suite-owned temporary storage, process/protocol failure with safe exit facts, and wrapper/native quiescence. The same tier proves two named instances retain separate environments and native modes. +Generated schema evidence pins the optional `ThreadStartParams.model` field, while package tests cover representative error groups, applicable HTTP status, six lifecycle stages, process outcomes, stop-reason mapping, unknown fallback, sanitization, structured permission ordering, cancellation, concurrency, and cleanup aggregation. The keyless real-product test drives the package wrapper against a loopback Responses fixture and observes the package-local argv, omitted-model inheritance, two explicit instance models, exact Bearer key, original task, byte-exact final answer, thread-level `never` overriding ambient `on-request`, automatic-review startup, unattended rejection without file side effects, a real service failure, explicit dangerous-bypass writing in suite-owned temporary storage, process/protocol failure with safe exit facts, and wrapper/native quiescence. Installing with optional dependencies omitted, using an unsupported platform, or losing the selected payload makes the first delegation fail at `initialize` with the safe `unknown` category and any observed process outcome. Raw wrapper text remains on Host stderr; the provider neither probes a host CLI nor retries with one. An isolated wrapper fixture separately proves the native payload failure and absence of host fallback. @@ -106,7 +109,7 @@ Installing with optional dependencies omitted, using an unsupported platform, or #### What the model sees -The Codex child receives the standalone text blocks as one turn in a fresh ephemeral thread. Its workspace is the parent Session cwd; its model, system instructions, tools, and authentication come from native Codex configuration, the selected Provider instance's Profile configuration fixes the thread's environment, non-interactive approval policy, and sandbox mode, and the executable version comes from the Bundle's pinned platform payload. +The Codex child receives the standalone text blocks as one turn in a fresh ephemeral thread. Its workspace is the parent Session cwd; the selected Provider instance fixes any configured model, environment, non-interactive approval policy, and sandbox mode, while an omitted model and every other product setting come from native Codex configuration. The executable version comes from the Bundle's pinned platform payload. #### Token effect @@ -120,7 +123,7 @@ Independent of the parent request cache. Reuse depends only on Codex's own provi #### What the model sees -Through `dsh-tool-subagent`, a foreground call gives the parent the selected final Codex answer or an error containing the stop reason and optional safe diagnostic for a non-completed result. The diagnostic can distinguish the fixed error-info category, protocol stage, numeric HTTP status, and observed process outcome without copying product prose. A background call first returns a Job id; the generic job controls later deliver a completion notice, expose the same final answer or failed status detail through `job_output`, and let `job_kill` request cancellation. Codex commentary, reasoning, tool activity, raw stderr, workspace diffs, usage, product ids, commands, paths, and protocol payloads are not copied into the parent Session. +Through `dsh-tool-subagent`, a foreground call gives the parent the selected final Codex answer or an error containing the stop reason and optional safe diagnostic for a non-completed result. The diagnostic can distinguish a coarse action category, protocol stage, applicable numeric HTTP status, and observed process outcome without copying product prose or stderr. A background call first returns a Job id; the generic job controls later deliver a completion notice, expose the same final answer or failed status detail through `job_output`, and let `job_kill` request cancellation. Codex commentary, reasoning, tool activity, raw stderr, workspace diffs, usage, product ids, commands, paths, and protocol payloads are not copied into the parent Session. #### Token effect @@ -133,10 +136,10 @@ Append-only: foreground adds one result after the reusable parent prefix, while ## Known Limitations and Deferred Work - **One fresh process, thread, and turn per run** — there is no continuation, resume, pooling, progress stream, or product-session persistence. -- **Static instance selection** — Profile rows fix provider names and tool bindings; calls cannot choose a provider dynamically, and every exposed tool needs a unique `toolName`. +- **Static instance selection** — Profile rows fix provider names, optional models, and tool bindings; calls cannot choose or change either a provider or model dynamically, and every exposed tool needs a unique `toolName`. - **Authentication and account state remain native** — the Bundle supplies the CLI but does not create an account, log in, trust a project, or rewrite Codex settings; configuration and authentication failures surface with their lifecycle stage and the safe `unknown` fallback rather than a separate public taxonomy. - **The native platform payload is required at delegation time** — installs that omit optional dependencies, unsupported platforms, and missing or damaged payloads fail at the first run; there is no host-CLI fallback. -- **Compatibility is pinned by development evidence** — upgrading from the verified 0.147.0 protocol baseline requires regenerating upstream schema evidence and rerunning handshake, answer-selection, approval, cancellation, keyless real-product, and credentialed DeepSeek nonce tests. +- **Compatibility is pinned by development evidence** — upgrading from the verified 0.149.1 protocol baseline requires regenerating upstream schema evidence and rerunning handshake, answer-selection, approval, cancellation, keyless real-product, and credentialed DeepSeek nonce tests. - **No human approval path** — known unattended approval requests are denied and unknown server requests fail closed; the three Profile modes never create a DSH interaction channel or per-call allow policy. - **Assistant payload is final text only** — a failed run may additionally expose the separate safe diagnostic; reasoning, commentary, intermediate messages, tool traffic, usage, raw stderr, and workspace diffs remain outside the parent Session, while generic Job ids, notices, and status come from the shared job runtime. - **No optional shared capabilities** — `agentOptions`, output schemas, child personas, tool filtering, and harness depth enforcement are rejected by the shared service for this provider. diff --git a/packages/subagent/subagent-codex/README.zh.md b/packages/subagent/subagent-codex/README.zh.md index adabd942c3..8532f6cfb5 100644 --- a/packages/subagent/subagent-codex/README.zh.md +++ b/packages/subagent/subagent-codex/README.zh.md @@ -6,13 +6,13 @@ ## 启动与所有权 -`start(request)` 只接受非空的文本块序列，并根据父会话确定子级 cwd。随后，它通过 [`dsh-subprocess`](../../subprocess/subprocess/README.zh.md) spawn 固定命令，依次执行 `initialize` → `initialized`，把 Profile 选择的模式映射为官方 `thread/start` approval／reviewer／sandbox 字段并与 `{ cwd, ephemeral: true }` 一起发送，且仅在 Codex 返回有效的临时线程后才发布此次运行。若在发布前发生失败或取消，它会关闭通信链路、终止受管进程树并等待其退出，然后拒绝 `start()` 调用。非取消拒绝只公开固定的 `initialize` 或 `thread-start` 阶段及已经观测到的进程结果；原始产品与 Host 错误只保留在内部 cause 链中。 +`start(request)` 只接受非空的文本块序列，并根据父会话确定子级 cwd。随后，它通过 [`dsh-subprocess`](../../subprocess/subprocess/README.zh.md) spawn 固定命令，依次执行 `initialize` → `initialized`，把 Profile 选择的模式与可选模型映射为官方 `thread/start` 字段并与 `{ cwd, ephemeral: true }` 一起发送，且仅在 Codex 返回有效的临时线程后才发布此次运行。若在发布前发生失败或取消，它会关闭通信链路、终止受管进程树并等待其退出，然后拒绝 `start()` 调用。非取消拒绝只公开固定的 `initialize` 或 `thread-start` 阶段及已经观测到的进程结果；原始产品与 Host 错误只保留在内部 cause 链中。 已发布的 `run.result` 恰好启动一个轮次。它只接受与此次运行的线程和轮次匹配的通知，随后等待权威的终止通知 `turn/completed`。以最后一条 `phase: "final_answer"` 的 `agentMessage` 为准；若 Codex 没有发出明确的最终阶段，则以最后一条 `phase: null` 的消息作为兼容性回退。过程说明绝不会取代上述任一答案；成功完成的轮次若没有非空白答案，结果也会判为错误。 -对于命令与文件审批，无人值守的提供方会从请求给出的决策选项中选择一项不予批准的决策，并优先选择 `cancel`；稳定的 0.147.0 请求形态没有决策选项列表，因此回退到 `decline`。它对权限请求返回作用域限于当前轮次的空权限集，不向用户输入请求提供任何答案，并拒绝 MCP elicitation。若请求在无人值守模式下没有合法响应，或是未知服务器请求，此次运行就会失败。wire 只记录有效模式、请求类别、决定与固定的安全原因，也会识别被拒绝的命令／文件 item 和 `sandboxError` 终态。Codex 0.147.0 的部分早期 `never` 拒绝和 sandbox violation 只写入结构化 stderr，因此提供方会 pipe stderr、原样转发给 Host，并在每次运行的有界尾缓冲中匹配两个固定签名；原始 stderr 不会进入诊断。 +对于命令与文件审批，无人值守的提供方会从请求给出的决策选项中选择一项不予批准的决策，并优先选择 `cancel`；稳定的 0.149.1 请求形态没有决策选项列表，因此回退到 `decline`。它对权限请求返回作用域限于当前轮次的空权限集，不向用户输入请求提供任何答案，并拒绝 MCP elicitation。若请求在无人值守模式下没有合法响应，或是未知服务器请求，此次运行就会失败。wire 只记录有效模式、请求类别、决定与固定的安全原因，也会识别被拒绝的命令／文件 item 和结构化 `sandboxError` 终态。产品 stderr 会原样转发给 Host，但绝不会被分类或复制进诊断。 -本地取消会在结果竞态中胜出并映射为 `aborted`。对于失败轮次，诊断会保留 Codex 0.147.0 `codexErrorInfo` 联合中的全部十一种字符串与五种对象 variant；四种连接／stream variant 会在上游提供时保留数值 `httpStatusCode`，而 `activeTurnNotSteerable` 不公开 `turnKind`。诊断还会注明 `turn-start`、`turn` 或 `process`，分别包含可用的退出码与信号，并对无法识别或格式错误的值使用 `unknown`，且不复制原始字段。`contextWindowExceeded` 仍映射为 `max-tokens`；其他任何远端中断或失败仍映射为 `error`，且该提供方不会产生 `refusal`。参与失败的权限决定会跟在结构化失败行之后。成功与本地取消都不附带这两类事实。 +本地取消会在结果竞态中胜出并映射为 `aborted`。失败轮次使用粗粒度类别 `limit`、`access-policy`、`service`、`transport`、`product-error`、`invalid-result` 或 `unknown`；app-server 提前退出使用 `process`。适用的连接与 stream 失败会保留数值 `httpStatusCode`。诊断还会注明 `turn-start`、`turn` 或 `process`，分别包含可用的退出码与信号，且不复制原始字段。`contextWindowExceeded` 仍映射为 `max-tokens`；其他任何远端中断或失败仍映射为 `error`，且该提供方不会产生 `refusal`。参与失败的结构化权限决定会跟在失败行之后。成功与本地取消都不附带这两类事实。 `dispose()`（资源释放）具有幂等性：如果当前的两个标识符均已知，它会尽力请求 `turn/interrupt`，关闭 JSON-RPC 通信链路，结束标准输入，调用共享的进程树逐级终止机制，等待整棵进程树退出，并移除 stderr observer。独立清理拒绝使用固定的 `teardown` 阶段与可用进程结果。当启动与回滚同时失败时，顶层聚合消息会保留两条安全阶段说明，而原始失败仍只在内部可见。 @@ -25,6 +25,7 @@ | 配置键 | 默认值 | 含义 | |---|---|---| | `providerName` | `codex` | `ctx.subagents` 中的非空注册名称；每个已挂载实例都需要唯一值。 | +| `model` | Codex 原生设置 | 可选的非空原生模型名称，为该实例的每个线程固定；省略时不发送 app-server 覆盖。 | | `env` | `{}` | 显式指定的子进程环境，叠加在由子进程 seam 清除凭证后的父环境之上。 | | `permissionMode` | `never` | 为该提供方实例的每个线程固定原生非交互审批与沙箱模式。 | | `disposeGraceMs` | `3000` | 共享进程树责任方各终止层级之间的宽限期，单位为毫秒且须为正有限值，并不得大于仓库共享的 [`MAX_TIMER_DELAY_MS`](../../util/timeout/README.zh.md)；随后资源释放会等待整棵进程树退出。 | @@ -35,7 +36,7 @@ | `approve-for-me` | `approvalPolicy: on-request`、`approvalsReviewer: auto_review`、`sandbox: workspace-write` | 由 Codex 自动评审权限请求，不等待人工。 | | `dangerously-bypass-approvals-and-sandbox` | `approvalPolicy: never`、`sandbox: danger-full-access` | 跳过审批与 sandbox；必须显式选择该值。 | -生产环境会解析锁定的 `@openai/codex@0.147.0` 依赖所声明的 `codex` bin，并使用当前 Node 可执行文件启动该 JavaScript wrapper。Wrapper 会选择匹配的原生平台载荷；提供方既不检查也不回退 `PATH` 中的宿主 `codex`。父会话 cwd、`HOME` 与 `CODEX_HOME` 继续让原生 Codex 配置和身份验证保持权威，而提供方只覆盖选定线程的 approval／reviewer／sandbox 字段。其他项目、模型、provider、MCP、hook、skill 与账户设置仍由原生机制负责。本插件不选择模型、不创建 `CODEX_HOME`、不执行登录，也不探测账户。子进程 seam 会先移除具有凭证特征的环境变量，再应用显式 `env` 覆盖。 +生产环境会解析锁定的 `@openai/codex@0.149.1` 依赖所声明的 `codex` bin，并使用当前 Node 可执行文件启动该 JavaScript wrapper。Wrapper 会选择匹配的原生平台载荷；提供方既不检查也不回退 `PATH` 中的宿主 `codex`。父会话 cwd、`HOME` 与 `CODEX_HOME` 继续让原生 Codex 配置和身份验证保持权威。已配置的 `model` 会原样传给每个临时 `thread/start`；省略时不设置该字段，且提供方不会发现模型、改写别名、选择 `modelProvider` 或 `serviceTier`，也不会设置 fallback。所选权限模式仍是唯一的另一项线程级覆盖。本插件不创建 `CODEX_HOME`、不执行登录，也不探测账户。子进程 seam 会先移除具有凭证特征的环境变量，再应用显式 `env` 覆盖。 本包是可选的 Profile Bundle。将它安装进目标 Profile 后重启该 Profile；安装会把官方 wrapper 与一个兼容的原生平台载荷带入该 Profile，而包所声明的 `cordis.patch.yml` 层只注册休眠的 `codex` Host provider，不会启动 Codex 进程。移除该包后，下一次 Profile 启动会撤回这一 provider 及其私有运行时闭包。 @@ -45,7 +46,7 @@ dsh plugin --profile remove @deepseek-ai/dsh-subagent-codex dsh --profile ``` -安装决定 Host 可用性，而不是模型权限。Bundle 会提供休眠的默认 `codex` 配置项；Profile 可以替换该配置项的完整 config，也可以挂载更多具有不同 `providerName`、`permissionMode` 与 `env` 的配置项。加载实例本身不会在绑定工具调用前启动 Codex 进程。每个 `dsh-tool-subagent` 配置项指定一个提供方，并需要独立的 `toolName`，因此模型看到的是静态工具，而不是动态提供方选择器。完整 Agent Preset 携带对应的默认产品工具行并设置 `disabled: true`；复制一个 preset 后删除该字段，即可只向由该副本组装的 agent 暴露 `subagent_codex`。其 `one-shot` 策略会让省略 `run_in_background` 或传入 `false` 的调用继续在前台等待，而显式传入 `true` 会返回由父 agent 拥有的 Job ID，供 `job_output` 或 `job_kill` 使用。base host（基础宿主）与完整 preset 已提供通用作业注册表和控制工具。 +安装决定 Host 可用性，而不是模型权限。Bundle 会提供休眠的默认 `codex` 配置项；Profile 可以替换该配置项的完整 config，也可以挂载更多具有不同 `providerName`、`model`、`permissionMode` 与 `env` 的配置项。加载实例本身不会在绑定工具调用前启动 Codex 进程。每个 `dsh-tool-subagent` 配置项指定一个提供方，并需要独立的 `toolName`，因此模型看到的是静态工具，而不是动态提供方或模型选择器。完整 Agent Preset 携带对应的默认产品工具行并设置 `disabled: true`；复制一个 preset 后删除该字段，即可只向由该副本组装的 agent 暴露 `subagent_codex`。其 `one-shot` 策略会让省略 `run_in_background` 或传入 `false` 的调用继续在前台等待，而显式传入 `true` 会返回由父 agent 拥有的 Job ID，供 `job_output` 或 `job_kill` 使用。base host（基础宿主）与完整 preset 已提供通用作业注册表和控制工具。 下列独立组装展示完整的显式能力。基于 `@deepseek-ai/dsh-base` 的 Profile 保留已有 Job 配置项，新增产品提供方与工具配置项，而且不重复挂载 Job 服务。 @@ -54,6 +55,7 @@ dsh --profile name: '@deepseek-ai/dsh-subagent-codex' config: providerName: codex-safe + model: approved-review-model permissionMode: never env: OPENAI_API_KEY: !!js process.env.OPENAI_API_KEY @@ -62,6 +64,7 @@ dsh --profile name: '@deepseek-ai/dsh-subagent-codex' config: providerName: codex-bypass + model: approved-edit-model permissionMode: dangerously-bypass-approvals-and-sandbox env: OPENAI_API_KEY: !!js process.env.OPENAI_API_KEY @@ -94,9 +97,9 @@ dsh --profile ## 产品兼容性与证据 -生产环境的协议层有意只实现这一单次执行约定所需的 app-server 方法。运行时依赖与六个 optional-dependency alias 均锁定到 `@openai/codex@0.147.0` / `codex-cli 0.147.0`。普通安装会按当前操作系统与 CPU 选择一个载荷。对于当前 darwin-arm64 载荷，`npm pack --dry-run --json @openai/codex@0.147.0-darwin-arm64` 报告压缩包为 111,199,052 字节、解包后为 274,777,843 字节。该包包含原生 `codex`、`codex-code-mode-host`、`rg` 与 `zsh` 资源；其他平台可能不同，这些数值只用于披露而不是安装阈值。 +生产环境的协议层有意只实现这一单次执行约定所需的 app-server 方法。运行时依赖与六个 optional-dependency alias 均锁定到 `@openai/codex@0.149.1` / `codex-cli 0.149.1`。普通安装会按当前操作系统与 CPU 选择一个载荷。对于当前 darwin-arm64 载荷，`npm pack --dry-run --json @openai/codex@0.149.1-darwin-arm64` 报告压缩包为 114,152,335 字节、解包后为 282,491,555 字节。该包包含原生 `codex`、`codex-code-mode-host`、`rg` 与 `zsh` 资源；其他平台可能不同，这些数值只用于披露而不是安装阈值。 -生成的 schema 证据与包测试会固定全部十六种 error-info variant、HTTP status 所在位置、六个生命周期阶段、进程结果、终止原因映射、unknown 回退、脱敏、权限顺序、取消、并发与清理聚合。无密钥真实产品测试会驱动包内 wrapper 连接回环 Responses fixture，并观测包内 argv、确切的 Bearer 密钥、原始任务、逐字节完全一致的最终回答、线程级 `never` 对环境中 `on-request` 的覆盖、自动评审启动、不产生文件副作用的无人值守拒绝、真实 `internalServerError`、测试拥有临时存储中的显式危险绕过写入、携带安全退出事实的进程／协议失败，以及 wrapper／原生进程完全停稳。同一层级还会证明两个命名实例保留彼此独立的环境与原生模式。 +生成的 schema 证据会固定可选的 `ThreadStartParams.model` 字段，包测试则覆盖代表性的错误分组、适用 HTTP status、六个生命周期阶段、进程结果、终止原因映射、unknown 回退、脱敏、结构化权限顺序、取消、并发与清理聚合。无密钥真实产品测试会驱动包内 wrapper 连接回环 Responses fixture，并观测包内 argv、省略模型继承、两个显式实例模型、确切的 Bearer 密钥、原始任务、逐字节完全一致的最终回答、线程级 `never` 对环境中 `on-request` 的覆盖、自动评审启动、不产生文件副作用的无人值守拒绝、真实服务失败、测试拥有临时存储中的显式危险绕过写入、携带安全退出事实的进程／协议失败，以及 wrapper／原生进程完全停稳。 如果安装时省略 optional dependencies、当前平台不受支持，或所选载荷缺失，第一次委派会在 `initialize` 阶段以安全 `unknown` 类别和已观测到的进程结果失败。原始 wrapper 文本只保留在 Host stderr；提供方既不会探测宿主 CLI，也不会用它重试。独立 wrapper fixture 会另行证明原生载荷失败与不存在宿主回退。 @@ -106,7 +109,7 @@ dsh --profile #### 模型看到的内容 -Codex 子级会在一个全新的临时线程中，以单个轮次接收这些独立文本块。它的工作区是父会话 cwd；其模型、系统指令、工具和身份验证来自原生 Codex 配置，所选提供方实例的 Profile 配置会固定该线程的环境、非交互审批策略与沙箱模式，而可执行版本来自 Bundle 锁定的平台载荷。 +Codex 子级会在一个全新的临时线程中，以单个轮次接收这些独立文本块。它的工作区是父会话 cwd；所选提供方实例会固定已配置的模型、环境、非交互审批策略与沙箱模式，而省略的模型及其余产品设置来自 Codex 原生配置。可执行版本来自 Bundle 锁定的平台载荷。 #### 对 token 的影响 @@ -120,7 +123,7 @@ Codex 子级会在一个全新的临时线程中，以单个轮次接收这些 #### 模型看到的内容 -通过 `dsh-tool-subagent`，前台调用会让父级模型看到选定的 Codex 最终答案；若结果未完成，错误中会包含终止原因和可选的安全诊断。该诊断可以区分固定 error-info 类别、协议阶段、数值 HTTP status 和已观测的进程结果，而不复制产品正文。后台调用会先返回 Job id；随后通用作业控制面会送达完成通知，通过 `job_output` 公开同一最终答案或失败状态 detail，并允许 `job_kill` 请求取消。Codex 的过程说明、推理（reasoning）、工具活动、原始 stderr、工作区差异、用量信息、产品标识符、命令、路径和协议载荷均不会复制到父会话。 +通过 `dsh-tool-subagent`，前台调用会让父级模型看到选定的 Codex 最终答案；若结果未完成，错误中会包含终止原因和可选的安全诊断。该诊断可以区分粗粒度行动类别、协议阶段、适用的数值 HTTP status 和已观测的进程结果，而不复制产品正文或 stderr。后台调用会先返回 Job id；随后通用作业控制面会送达完成通知，通过 `job_output` 公开同一最终答案或失败状态 detail，并允许 `job_kill` 请求取消。Codex 的过程说明、推理（reasoning）、工具活动、原始 stderr、工作区差异、用量信息、产品标识符、命令、路径和协议载荷均不会复制到父会话。 #### 对 token 的影响 @@ -133,10 +136,10 @@ Codex 子级会在一个全新的临时线程中，以单个轮次接收这些 ## 已知限制与后续工作 - **每次运行均新建一个进程、一个线程和一个轮次**：不支持续接、恢复、池化、进度流或产品会话持久化。 -- **静态选择实例**：Profile 配置项固定提供方名称与工具绑定；调用无法动态选择提供方，而且每个公开工具都需要唯一的 `toolName`。 +- **静态选择实例**：Profile 配置项固定提供方名称、可选模型与工具绑定；调用无法动态选择或修改提供方与模型，而且每个公开工具都需要唯一的 `toolName`。 - **身份验证与账户状态仍由原生机制管理**：Bundle 会提供 CLI，但不会创建账户、登录、信任项目或改写 Codex 设置；配置与身份验证失败会公开其生命周期阶段与安全的 `unknown` 回退，而不会增加单独的公开分类体系。 - **委派时必须存在原生平台载荷**：省略 optional dependencies 的安装、不受支持的平台以及缺失或损坏的载荷都会在第一次运行时失败；不会回退到宿主 CLI。 -- **兼容性由开发证据锁定**：若要从已验证的 0.147.0 协议基线升级，必须重新生成上游 schema 证据，并重新运行握手、答案选择、审批、取消、无密钥真实产品以及带密钥的 DeepSeek 随机数测试。 +- **兼容性由开发证据锁定**：若要从已验证的 0.149.1 协议基线升级，必须重新生成上游 schema 证据，并重新运行握手、答案选择、审批、取消、无密钥真实产品以及带密钥的 DeepSeek 随机数测试。 - **没有人工审批路径**：已知的无人值守审批请求会被拒绝，未知服务器请求会以默认拒绝方式使运行失败；三种 Profile 模式都不会创建 DSH 交互通道或逐次调用 allow 策略。 - **assistant 载荷仅包含最终文本**：失败运行可以额外公开独立的安全诊断；推理、过程说明、中间消息、工具通信、用量信息、原始 stderr 和工作区差异不会进入父会话，通用 Job id、通知与状态来自共享作业运行时。 - **没有可选的共享能力**：对于本提供方，共享服务会拒绝 `agentOptions`、输出 schema、子任务角色设定、工具筛选和 harness 深度强制约束。 diff --git a/packages/subagent/subagent-codex/package.json b/packages/subagent/subagent-codex/package.json index 6ea97f6d2e..0c4c32d696 100644 --- a/packages/subagent/subagent-codex/package.json +++ b/packages/subagent/subagent-codex/package.json @@ -49,7 +49,7 @@ "dependencies": { "@deepseek-ai/dsh-sdk-protocol": "workspace:^", "@deepseek-ai/schemastery": "workspace:^", - "@openai/codex": "0.147.0" + "@openai/codex": "0.149.1" }, "devDependencies": { "@deepseek-ai/cordis-plugin-loader": "workspace:^", diff --git a/packages/subagent/subagent-codex/src/index.ts b/packages/subagent/subagent-codex/src/index.ts index 79fbdab078..84005ac866 100644 --- a/packages/subagent/subagent-codex/src/index.ts +++ b/packages/subagent/subagent-codex/src/index.ts @@ -32,10 +32,12 @@ export const inject = ['subagents', 'subprocess'] const DEFAULT_PROVIDER_NAME = 'codex' -/** Deployment-owned permission, environment, and process-release settings. */ +/** Deployment-owned model, permission, environment, and process-release settings. */ export interface Config { /** Provider name on `ctx.subagents` (default `codex`). */ providerName?: string + /** Native Codex model fixed for this instance; omitted to inherit Codex settings. */ + model?: string /** * Explicit environment entries layered over the subprocess seam's * credential-scrubbed parent environment. @@ -49,13 +51,14 @@ export interface Config { export const Config: z = z.object({ providerName: z.string().min(1).default(DEFAULT_PROVIDER_NAME), + model: z.string().min(1), env: z.dict(z.string()).default({}), permissionMode: z.union([...CODEX_PERMISSION_MODES]) .default(DEFAULT_CODEX_PERMISSION_MODE), disposeGraceMs: z.number().default(DEFAULT_DISPOSE_GRACE_MS), }) -type ResolvedConfig = Required +type ResolvedConfig = Omit, 'model'> & Pick class CodexProvider implements SubagentProvider { readonly capabilities: SubagentCapabilities = NO_START_CAPABILITIES @@ -91,6 +94,7 @@ class CodexProvider implements SubagentProvider { } const spec: CodexRunSpec = { cwd, + ...this.config.model === undefined ? {} : { model: this.config.model }, permissionMode: this.config.permissionMode, env: this.config.env, disposeGraceMs: this.config.disposeGraceMs, @@ -108,11 +112,12 @@ class CodexProvider implements SubagentProvider { /** * Register one Profile-named Codex provider. * @param ctx - context carrying shared subagent and subprocess services. - * @param config - registry name, permission mode, child environment, and disposal grace. + * @param config - registry name, optional model, permission mode, child environment, and disposal grace. */ export function apply(ctx: Context, config: Config): void { const resolved: ResolvedConfig = { providerName: config.providerName ?? DEFAULT_PROVIDER_NAME, + ...config.model === undefined ? {} : { model: config.model }, env: config.env as Record, permissionMode: config.permissionMode ?? DEFAULT_CODEX_PERMISSION_MODE, disposeGraceMs: config.disposeGraceMs as number, diff --git a/packages/subagent/subagent-codex/src/run.ts b/packages/subagent/subagent-codex/src/run.ts index 9db5d7086c..520174806c 100644 --- a/packages/subagent/subagent-codex/src/run.ts +++ b/packages/subagent/subagent-codex/src/run.ts @@ -74,9 +74,11 @@ type CodexFailureStage = | 'process' | 'teardown' +type CodexFailureCategory = CodexWireFailureFacts['category'] | 'process' + interface CodexFailureFacts { readonly stage: CodexFailureStage - readonly category: string + readonly category: CodexFailureCategory readonly httpStatus?: number | undefined readonly outcome?: SubprocessOutcome | undefined } @@ -137,6 +139,8 @@ export function codexAppServerArgv(): string[] { export interface CodexRunSpec { /** Parent Session workspace, also supplied to `thread/start`. */ readonly cwd: string + /** Profile-selected native model; omitted to preserve Codex settings. */ + readonly model?: string /** Profile-selected native non-interactive permission mode. */ readonly permissionMode: CodexPermissionMode /** Explicit deployment/test environment layered after the shared scrub. */ @@ -251,10 +255,10 @@ export async function startCodexRun( child.stdout as NonNullable, child.stdin as NonNullable, spec.permissionMode, + spec.model, ) const onStderr = (chunk: Buffer | string): void => { const bytes = typeof chunk === 'string' ? Buffer.from(chunk) : chunk - wire.observeStderr(bytes.toString()) try { // Synchronous fd forwarding preserves byte order without owning a // backpressure queue. A slow host sink can block this event-loop turn. @@ -272,8 +276,8 @@ export async function startCodexRun( const disposeProcess = async (): Promise => { try { await disposeCodexChild(wire, child) - // Let stderr already queued by the process close reach both bounded - // diagnostic consumers before their listeners are detached. + // Let stderr already queued by the process close reach the Host before + // its forwarding listeners are detached. await new Promise((resolve) => { setImmediate(resolve) }) } finally { child.stderr?.off('data', onStderr) @@ -286,7 +290,7 @@ export async function startCodexRun( (outcome) => { processFailureFacts = { stage: 'process', - category: 'process-exit', + category: 'process', outcome, } throw new CodexRunFailure(processFailureFacts) @@ -385,14 +389,14 @@ export async function startCodexRun( publishedProcessFailure, ]) if (terminal.stopReason === 'completed') return terminal - // Let stderr already queued with the terminal frame contribute its - // fixed permission fact before the non-completed result is snapshotted. + // Let stderr already queued with the terminal frame reach the Host + // before the non-completed result settles. await new Promise((resolve) => { setImmediate(resolve) }) const facts = withProcessOutcome(wire.collectFailure()) return { ...terminal, diagnostic: recordFailureDiagnostic(facts) } } catch (error: unknown) { - // Give stderr data already queued in Node one turn to reach the wire - // before settlement snapshots the diagnostic. + // Give stderr data already queued in Node one turn to reach the Host + // before error settlement. await new Promise((resolve) => { setImmediate(resolve) }) const endedBeforeTerminal = wire.endedBeforeTerminal() if ( diff --git a/packages/subagent/subagent-codex/src/wire.ts b/packages/subagent/subagent-codex/src/wire.ts index cbc0504e08..474d7a9a32 100644 --- a/packages/subagent/subagent-codex/src/wire.ts +++ b/packages/subagent/subagent-codex/src/wire.ts @@ -1,5 +1,5 @@ /** - * Minimal Codex app-server 0.147.0 protocol adapter. The shared JSON-RPC + * Minimal Codex app-server 0.149.1 protocol adapter. The shared JSON-RPC * transport owns framing and request correlation; this module owns only the * product methods, current thread/turn association, unattended approval * responses, and terminal-answer selection. @@ -18,7 +18,14 @@ type JsonObject = Record /** Product facts owned by the Codex wire after publication. */ export interface CodexWireFailureFacts { readonly stage: 'turn-start' | 'turn' - readonly category: string + readonly category: + | 'limit' + | 'access-policy' + | 'service' + | 'transport' + | 'product-error' + | 'invalid-result' + | 'unknown' readonly httpStatus?: number | undefined } @@ -35,40 +42,6 @@ const THREAD_PERMISSION_PARAMS: Readonly }, } -const STDERR_PERMISSION_SIGNATURES = [ - { - text: 'approval policy is Never; reject command', - request: 'command execution', - decision: 'denied', - reason: 'Codex rejected an escalation because the selected policy never asks for approval', - }, - { - text: 'recorded sandbox violation:', - request: 'sandbox execution', - decision: 'failed', - reason: 'Codex reported a sandbox violation', - }, -] as const - -const STDERR_SIGNATURE_TAIL_CHARS = Math.max( - ...STDERR_PERMISSION_SIGNATURES.map(signature => signature.text.length), -) - 1 - -function stderrSignatureTail(value: string): string { - for ( - let length = Math.min(STDERR_SIGNATURE_TAIL_CHARS, value.length) - ; length > 0 - ; length -= 1 - ) { - const tail = value.slice(-length) - if (STDERR_PERMISSION_SIGNATURES.some(signature => - tail.length < signature.text.length && signature.text.startsWith(tail))) { - return tail - } - } - return '' -} - function object(value: unknown, label: string): JsonObject { if (value === null || typeof value !== 'object' || Array.isArray(value)) { throw new Error(`subagent-codex: app-server returned invalid ${label}`) @@ -102,10 +75,14 @@ function numericHttpStatus(value: unknown): number | undefined { : undefined } -function objectFailureInfo(value: JsonObject): { - readonly category: string +interface ParsedFailureInfo { + readonly category: CodexWireFailureFacts['category'] readonly httpStatus?: number | undefined -} { + readonly maxTokens?: true + readonly sandboxFailure?: true +} + +function objectFailureInfo(value: JsonObject): ParsedFailureInfo { const keys = Object.keys(value) const category = keys[0] if (keys.length !== 1 || category === undefined) { @@ -124,20 +101,17 @@ function objectFailureInfo(value: JsonObject): { { const httpStatus = numericHttpStatus(fields.httpStatusCode) return httpStatus === undefined - ? { category } - : { category, httpStatus } + ? { category: 'transport' } + : { category: 'transport', httpStatus } } case 'activeTurnNotSteerable': - return { category } + return { category: 'product-error' } default: return { category: 'unknown' } } } -function failureInfo(turn: JsonObject): { - readonly category: string - readonly httpStatus?: number | undefined -} { +function failureInfo(turn: JsonObject): ParsedFailureInfo { if (turn.status !== 'failed') return { category: 'unknown' } const error = turn.error if (error === null || typeof error !== 'object' || Array.isArray(error)) { @@ -147,17 +121,23 @@ function failureInfo(turn: JsonObject): { if (typeof info === 'string') { switch (info) { case 'contextWindowExceeded': + return { category: 'limit', maxTokens: true } case 'sessionBudgetExceeded': case 'usageLimitExceeded': + return { category: 'limit' } case 'serverOverloaded': - case 'cyberPolicy': case 'internalServerError': + return { category: 'service' } + case 'cyberPolicy': + case 'misalignmentPolicyViolation': case 'unauthorized': + return { category: 'access-policy' } case 'badRequest': case 'threadRollbackFailed': - case 'sandboxError': case 'other': - return { category: info } + return { category: 'product-error' } + case 'sandboxError': + return { category: 'access-policy', sandboxFailure: true } default: return { category: 'unknown' } } @@ -236,7 +216,6 @@ export class CodexAppServerWire { readonly decision: Parameters[2] readonly reason: string } | undefined - private stderrTail = '' private inputEnded = false private terminalObserved = false private closed = false @@ -245,6 +224,7 @@ export class CodexAppServerWire { private readonly input: Readable, output: Writable, private readonly permissionMode: CodexPermissionMode, + private readonly model?: string, ) { this.transport = new JsonRpcLineTransport(input, output) // Fatal protocol state can arrive after the current guarded operation has @@ -309,6 +289,7 @@ export class CodexAppServerWire { const response = object(await this.guarded(this.transport.request('thread/start', { cwd, ephemeral: true, + ...this.model === undefined ? {} : { model: this.model }, ...THREAD_PERMISSION_PARAMS[this.permissionMode], }, signal), signal), 'thread/start response') const thread = object(response.thread, 'thread/start thread') @@ -370,7 +351,7 @@ export class CodexAppServerWire { category: parsed.category, httpStatus: parsed.httpStatus, }) - if (parsed.category === 'sandboxError') { + if (parsed.sandboxFailure) { this.recordDiagnostic( 'sandbox execution', 'failed', @@ -378,7 +359,7 @@ export class CodexAppServerWire { completed.order, ) } - if (parsed.category === 'contextWindowExceeded') { + if (parsed.maxTokens) { return { output: this.collectOutput(), stopReason: 'max-tokens' } } const detail = status === 'failed' ? `: ${parsed.category}` : '' @@ -386,7 +367,7 @@ export class CodexAppServerWire { } const output = this.collectOutput() if (output.length === 0) { - this.recordFailure({ stage: 'turn', category: 'unknown' }) + this.recordFailure({ stage: 'turn', category: 'invalid-result' }) throw new Error('subagent-codex: Codex completed without a final answer') } return { output, stopReason: 'completed' } @@ -432,28 +413,6 @@ export class CodexAppServerWire { return this.failure as CodexWireFailureFacts } - /** - * Observe product stderr while retaining only enough tail to recognize fixed - * permission signatures. The raw text is never copied into the diagnostic. - * @param chunk - one decoded stderr chunk already forwarded to the host. - */ - observeStderr(chunk: string): void { - const observed = `${this.stderrTail}${chunk}` - let latestIndex = -1 - let latest: (typeof STDERR_PERMISSION_SIGNATURES)[number] | undefined - for (const signature of STDERR_PERMISSION_SIGNATURES) { - const index = observed.lastIndexOf(signature.text) - if (index > latestIndex) { - latestIndex = index - latest = signature - } - } - if (latest !== undefined) { - this.recordDiagnostic(latest.request, latest.decision, latest.reason) - } - this.stderrTail = stderrSignatureTail(observed) - } - /** Detach JSON-RPC listeners and reject outstanding requests. Idempotent. */ close(): void { if (this.closed) return diff --git a/packages/subagent/subagent-codex/tests/fixtures/loader/cordis.yml b/packages/subagent/subagent-codex/tests/fixtures/loader/cordis.yml index 5794306154..a898426ba1 100644 --- a/packages/subagent/subagent-codex/tests/fixtures/loader/cordis.yml +++ b/packages/subagent/subagent-codex/tests/fixtures/loader/cordis.yml @@ -13,11 +13,13 @@ name: '@deepseek-ai/dsh-subagent-codex' config: providerName: codex-primary + model: codex-primary-model - id: subagent-codex-secondary name: '@deepseek-ai/dsh-subagent-codex' config: providerName: codex-secondary + model: codex-secondary-model - id: tool-subagent-codex name: '@deepseek-ai/dsh-tool-subagent' diff --git a/packages/subagent/subagent-codex/tests/real-deepseek.e2e.ts b/packages/subagent/subagent-codex/tests/real-deepseek.e2e.ts index c12e96a306..a7014070a0 100644 --- a/packages/subagent/subagent-codex/tests/real-deepseek.e2e.ts +++ b/packages/subagent/subagent-codex/tests/real-deepseek.e2e.ts @@ -109,8 +109,8 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)( const version = await execFileAsync(process.execPath, [codexEntry, '--version'], { env: { ...process.env, ...env }, }) - expect(codexPackage.version).toBe('0.147.0') - expect(version.stdout.trim()).toBe('codex-cli 0.147.0') + expect(codexPackage.version).toBe('0.149.1') + expect(version.stdout.trim()).toBe('codex-cli 0.149.1') const parent = { id: 'deepseek-e2e-parent', diff --git a/packages/subagent/subagent-codex/tests/real-product.spec.ts b/packages/subagent/subagent-codex/tests/real-product.spec.ts index bbebd46f10..77e1102d63 100644 --- a/packages/subagent/subagent-codex/tests/real-product.spec.ts +++ b/packages/subagent/subagent-codex/tests/real-product.spec.ts @@ -183,7 +183,7 @@ function expectedProcessExitDiagnostic(outcome: SubprocessOutcome): string { const fields = [ 'product: Codex', 'stage: process', - 'category: process-exit', + 'category: process', ] if (outcome.exitCode !== null) fields.push(`exit code: ${outcome.exitCode}`) if (outcome.signal !== null) fields.push(`signal: ${outcome.signal}`) @@ -191,9 +191,6 @@ function expectedProcessExitDiagnostic(outcome: SubprocessOutcome): string { } interface JsonSchemaNode { - readonly enum?: string[] - readonly format?: string - readonly minimum?: number readonly properties?: Record readonly required?: string[] readonly type?: string | string[] @@ -215,18 +212,18 @@ function responseInputTexts(body: Record): string[] { }) } -describe('real @openai/codex 0.147.0 product', () => { +describe('real @openai/codex 0.149.1 product', () => { it('starts approve-for-me through the real app-server and returns exact text', async () => { - const sentinel = 'REAL_CODEX_SENTINEL_0_147_0' + const sentinel = 'REAL_CODEX_SENTINEL_0_149_1' const task = 'Return the fixture sentinel exactly.' const { harness, fixture } = await realHarness([ { kind: 'complete', text: sentinel }, ], 'approve-for-me') - expect(codexPackage.version).toBe('0.147.0') + expect(codexPackage.version).toBe('0.149.1') const version = await execFileAsync(process.execPath, [codexEntry, '--version'], { env: { ...process.env, ...harness.env }, }) - expect(version.stdout.trim()).toBe('codex-cli 0.147.0') + expect(version.stdout.trim()).toBe('codex-cli 0.149.1') const schemaRoot = mkdtempSync(join(tmpdir(), 'dsh-codex-schema-')) roots.push(schemaRoot) await execFileAsync(process.execPath, [ @@ -237,46 +234,17 @@ describe('real @openai/codex 0.147.0 product', () => { schemaRoot, ], { env: { ...process.env, ...harness.env } }) const schema = JSON.parse(readFileSync( - join(schemaRoot, 'ServerNotification.json'), + join(schemaRoot, 'ClientRequest.json'), 'utf8', )) as { definitions: { - CodexErrorInfo: { - oneOf: JsonSchemaNode[] - } + ThreadStartParams: JsonSchemaNode } } - expect(schema.definitions.CodexErrorInfo.oneOf[0]?.enum).toEqual([ - 'contextWindowExceeded', - 'sessionBudgetExceeded', - 'usageLimitExceeded', - 'serverOverloaded', - 'cyberPolicy', - 'internalServerError', - 'unauthorized', - 'badRequest', - 'threadRollbackFailed', - 'sandboxError', - 'other', - ]) - expect(schema.definitions.CodexErrorInfo.oneOf.slice(1).map(variant => - Object.keys(variant.properties ?? {})[0])).toEqual([ - 'httpConnectionFailed', - 'responseStreamConnectionFailed', - 'responseStreamDisconnected', - 'responseTooManyFailedAttempts', - 'activeTurnNotSteerable', - ]) - for (const variant of schema.definitions.CodexErrorInfo.oneOf.slice(1, 5)) { - const category = Object.keys(variant.properties ?? {})[0]! - const detail = variant.properties?.[category] - expect(detail?.required).toBeUndefined() - expect(detail?.properties?.httpStatusCode).toEqual({ - format: 'uint16', - minimum: 0, - type: ['integer', 'null'], - }) - } + expect(schema.definitions.ThreadStartParams.properties?.model).toEqual({ + type: ['string', 'null'], + }) + expect(schema.definitions.ThreadStartParams.required).toBeUndefined() const run = await harness.ctx.subagents.start('codex', { prompt: [{ type: 'text', text: task }], @@ -301,6 +269,7 @@ describe('real @openai/codex 0.147.0 product', () => { expect(recorded.method).toBe('POST') expect(recorded.path).toBe('/v1/responses') expect(recorded.headers.authorization).toBe('Bearer dsh-fake-openai-key') + expect(recorded.body.model).toBe('fixture-model') expect(responseInputTexts(recorded.body)).toContain(task) await expectQuiescent(harness.handles) }, 60_000) @@ -332,12 +301,14 @@ describe('real @openai/codex 0.147.0 product', () => { const { ctx, handles, spawnSpecs } = await realRuntime() const safeFiber = await ctx.plugin(codex, { providerName: 'codex-safe', + model: 'codex-safe-model', env: safeInstance.env, permissionMode: 'never', disposeGraceMs: 2_000, }) const bypassFiber = await ctx.plugin(codex, { providerName: 'codex-bypass', + model: 'codex-bypass-model', env: bypassInstance.env, permissionMode: 'dangerously-bypass-approvals-and-sandbox', disposeGraceMs: 2_000, @@ -385,6 +356,8 @@ describe('real @openai/codex 0.147.0 product', () => { await Promise.all([safeRun.dispose(), bypassRun.dispose()]) expect(safeInstance.fixture.requests).toHaveLength(1) expect(bypassInstance.fixture.requests).toHaveLength(1) + expect(safeInstance.fixture.requests[0]?.body.model).toBe('codex-safe-model') + expect(bypassInstance.fixture.requests[0]?.body.model).toBe('codex-bypass-model') expect(safeInstance.fixture.requests[0]?.body.input) .not.toEqual(bypassInstance.fixture.requests[0]?.body.input) expect(spawnSpecs.map(spec => spec.env?.CODEX_HOME).sort()).toEqual([ @@ -440,13 +413,9 @@ describe('real @openai/codex 0.147.0 product', () => { expect(result.stopReason).toBe('error') const diagnosticLines = result.diagnostic?.split('\n') ?? [] expect(diagnosticLines[0]).toBe( - 'Product subagent failure (product: Codex; stage: turn; category: other)', + 'Product subagent failure (product: Codex; stage: turn; category: product-error)', ) - expect([ - 'Codex unattended decision (mode: never; request: command approval; decision: cancelled): the provider does not grant interactive approval', - 'Codex unattended decision (mode: never; request: sandbox execution; decision: failed): Codex reported a sandbox failure', - 'Codex unattended decision (mode: never; request: command execution; decision: denied): Codex rejected an escalation because the selected policy never asks for approval', - ]).toContain(diagnosticLines[1]) + expect(diagnosticLines).toHaveLength(1) expect(result.diagnostic).not.toContain(command) expect(result.diagnostic).not.toContain(harness.workspace) await run.dispose() @@ -478,7 +447,7 @@ describe('real @openai/codex 0.147.0 product', () => { const result = await run.result expect(result).toMatchObject({ output: [], stopReason: 'error' }) expect(result.diagnostic).toBe( - 'Product subagent failure (product: Codex; stage: turn; category: internalServerError)', + 'Product subagent failure (product: Codex; stage: turn; category: service)', ) expect(result.diagnostic).not.toContain('SECRET_TOKEN') expect(result.diagnostic).not.toContain('/private/secret.txt') diff --git a/packages/subagent/subagent-codex/tests/responses-fixture.ts b/packages/subagent/subagent-codex/tests/responses-fixture.ts index c2ef18d803..e960f36bb2 100644 --- a/packages/subagent/subagent-codex/tests/responses-fixture.ts +++ b/packages/subagent/subagent-codex/tests/responses-fixture.ts @@ -94,7 +94,7 @@ function responseObject(text: string): Record { } /** - * Build the minimal Responses SSE event sequence consumed by Codex 0.147.0. + * Build the minimal Responses SSE event sequence consumed by Codex 0.149.1. * @param text - exact assistant answer. * @returns ordered response lifecycle events. */ diff --git a/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts b/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts index 296c8afa09..80a286274b 100644 --- a/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts +++ b/packages/subagent/subagent-codex/tests/subagent-codex.spec.ts @@ -65,7 +65,7 @@ vi.mock('node:fs', async (importOriginal) => { type JsonObject = Record -const CODEX_VERSION = '0.147.0' +const CODEX_VERSION = '0.149.1' const CODEX_PLATFORM_PACKAGES = [ '@openai/codex-darwin-arm64', '@openai/codex-darwin-x64', @@ -266,7 +266,7 @@ async function initializeWire(): Promise<{ wire.start() const initializing = wire.initialize(new AbortController().signal) const initialize = await child.peer.nextMethod('initialize') - child.peer.respond(initialize, { userAgent: 'codex-cli 0.147.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await initializing expect(await child.peer.nextMethod('initialized')).toEqual({ jsonrpc: '2.0', @@ -286,7 +286,7 @@ async function publishRun( ) { const starting = startCodexRun(request(undefined, signal), runSpec(child, specOverrides)) const initialize = await child.peer.nextMethod('initialize') - child.peer.respond(initialize, { userAgent: 'codex-cli 0.147.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await child.peer.nextMethod('initialized') const threadStart = await child.peer.nextMethod('thread/start') child.peer.respond(threadStart, { thread: { id: 'thread-1', ephemeral: true } }) @@ -479,12 +479,14 @@ describe('task admission and package contracts', () => { ctx.on('subagent/provider-removed', providerName => void removed.push(providerName)) const safeFiber = await ctx.plugin(codex, { providerName: 'codex-safe', + model: 'codex-safe-model', env: { DSH_CODEX_INSTANCE: 'safe' }, permissionMode: 'never', disposeGraceMs: 11, }) const bypassFiber = await ctx.plugin(codex, { providerName: 'codex-bypass', + model: 'codex-bypass-model', env: { DSH_CODEX_INSTANCE: 'bypass' }, permissionMode: 'dangerously-bypass-approvals-and-sandbox', disposeGraceMs: 29, @@ -498,11 +500,15 @@ describe('task admission and package contracts', () => { request(undefined, safeController.signal), ) const bypassStarting = ctx.subagents.start('codex-bypass', request()) - for (const child of [safeChild, bypassChild]) { + for (const [child, model] of [ + [safeChild, 'codex-safe-model'], + [bypassChild, 'codex-bypass-model'], + ] as const) { const initialize = await child.peer.nextMethod('initialize') - child.peer.respond(initialize, { userAgent: 'codex-cli 0.147.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await child.peer.nextMethod('initialized') const threadStart = await child.peer.nextMethod('thread/start') + expect(threadStart.params).toMatchObject({ model }) child.peer.respond(threadStart, { thread: { id: 'thread-1', ephemeral: true }, }) @@ -570,11 +576,14 @@ describe('task admission and package contracts', () => { await ctx.fiber.dispose() }) - it('accepts only the three fixed non-interactive permission modes', () => { + it('accepts an optional non-empty model and the three fixed permission modes', () => { expect(codex.Config({}).providerName).toBe('codex') + expect(codex.Config({}).model).toBeUndefined() expect(codex.Config({ providerName: 'codex-safe' }).providerName) .toBe('codex-safe') expect(() => codex.Config({ providerName: '' })).toThrow() + expect(codex.Config({ model: 'gpt-codex' }).model).toBe('gpt-codex') + expect(() => codex.Config({ model: '' })).toThrow() expect(codex.Config({}).permissionMode).toBe(DEFAULT_CODEX_PERMISSION_MODE) for (const permissionMode of CODEX_PERMISSION_MODES) { expect(codex.Config({ permissionMode }).permissionMode).toBe(permissionMode) @@ -588,8 +597,29 @@ describe('task admission and package contracts', () => { const ctx = new Context() await ctx.plugin(SubagentRuntime) await ctx.plugin(LocalSubprocessRuntime) + const child = fakeChild() + vi.spyOn(ctx.subprocess, 'spawn').mockReturnValue(child.handle) codex.apply(ctx, { env: {}, disposeGraceMs: 3_000 }) expect(ctx.subagents.getProvider('codex')).toBeDefined() + const starting = ctx.subagents.start('codex', request()) + const initialize = await child.peer.nextMethod('initialize') + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) + await child.peer.nextMethod('initialized') + const threadStart = await child.peer.nextMethod('thread/start') + expect(threadStart.params).not.toHaveProperty('model') + child.peer.respond(threadStart, { thread: { id: 'thread-1', ephemeral: true } }) + const run = await starting + const turnStart = await child.peer.nextMethod('turn/start') + child.peer.send( + { id: turnStart.id, result: { turn: { id: 'turn-1' } } }, + agentMessage('native model answer', 'final_answer'), + turnCompleted('completed'), + ) + await expect(run.result).resolves.toEqual({ + output: [{ type: 'text', text: 'native model answer' }], + stopReason: 'completed', + }) + await run.dispose() await ctx.fiber.dispose() }) @@ -614,7 +644,7 @@ describe('task admission and package contracts', () => { wire.start() const initializing = wire.initialize(new AbortController().signal) const initialize = await child.peer.nextMethod('initialize') - child.peer.respond(initialize, { userAgent: 'codex-cli 0.147.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await initializing await child.peer.nextMethod('initialized') const starting = wire.startThread('/workspace', new AbortController().signal) @@ -624,6 +654,34 @@ describe('task admission and package contracts', () => { ephemeral: true, ...expected, }) + expect(threadStart.params).not.toHaveProperty('model') + child.peer.respond(threadStart, { thread: { id: 'thread-1', ephemeral: true } }) + await starting + wire.close() + }) + + it('sends an explicit model on each ephemeral thread', async () => { + const child = fakeChild() + const wire = new CodexAppServerWire( + child.handle.stdout!, + child.handle.stdin!, + 'never', + 'codex-explicit-model', + ) + wire.start() + const initializing = wire.initialize(new AbortController().signal) + const initialize = await child.peer.nextMethod('initialize') + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) + await initializing + await child.peer.nextMethod('initialized') + const starting = wire.startThread('/workspace', new AbortController().signal) + const threadStart = await child.peer.nextMethod('thread/start') + expect(threadStart.params).toEqual({ + cwd: '/workspace', + ephemeral: true, + model: 'codex-explicit-model', + approvalPolicy: 'never', + }) child.peer.respond(threadStart, { thread: { id: 'thread-1', ephemeral: true } }) await starting wire.close() @@ -695,7 +753,7 @@ describe('CodexAppServerWire', () => { requestAttestation: false, }, }) - child.peer.respond(initialize, { userAgent: 'codex-cli 0.147.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await initializing await child.peer.nextMethod('initialized') @@ -770,21 +828,17 @@ describe('CodexAppServerWire', () => { wire.close() }) - it('maps the complete string error union without changing stop reasons', async () => { - const categories = [ - 'contextWindowExceeded', - 'sessionBudgetExceeded', - 'usageLimitExceeded', - 'serverOverloaded', - 'cyberPolicy', - 'internalServerError', - 'unauthorized', - 'badRequest', - 'threadRollbackFailed', - 'sandboxError', - 'other', + it('groups representative string errors without changing stop reasons', async () => { + const scenarios = [ + ['contextWindowExceeded', 'limit', 'max-tokens'], + ['sessionBudgetExceeded', 'limit', 'error'], + ['cyberPolicy', 'access-policy', 'error'], + ['misalignmentPolicyViolation', 'access-policy', 'error'], + ['serverOverloaded', 'service', 'error'], + ['badRequest', 'product-error', 'error'], + ['sandboxError', 'access-policy', 'error'], ] as const - for (const category of categories) { + for (const [codexErrorInfo, category, stopReason] of scenarios) { const { child, wire } = await initializeWire() const result = wire.runTurn(['task'], new AbortController().signal) const turnStart = await child.peer.nextMethod('turn/start') @@ -793,10 +847,10 @@ describe('CodexAppServerWire', () => { agentMessage('partial answer', null), turnCompleted('failed', 'turn-1', 'thread-1', { message: 'SECRET_TOKEN in /private/secret.txt', - codexErrorInfo: category, + codexErrorInfo, }), ) - if (category === 'contextWindowExceeded') { + if (stopReason === 'max-tokens') { await expect(result).resolves.toEqual({ output: [{ type: 'text', text: 'partial answer' }], stopReason: 'max-tokens', @@ -814,22 +868,21 @@ describe('CodexAppServerWire', () => { } }) - it('maps all object error variants and only numeric HTTP status', async () => { + it('groups object errors and retains only numeric HTTP status', async () => { const scenarios = [ - ['httpConnectionFailed', { httpStatusCode: 503 }, 503], - ['responseStreamConnectionFailed', { httpStatusCode: null }, undefined], - ['responseStreamDisconnected', {}, undefined], - ['responseTooManyFailedAttempts', { httpStatusCode: '503' }, undefined], - ['activeTurnNotSteerable', { turnKind: 'review' }, undefined], + ['httpConnectionFailed', { httpStatusCode: 503 }, 'transport', 503], + ['responseStreamDisconnected', {}, 'transport', undefined], + ['responseTooManyFailedAttempts', { httpStatusCode: '503' }, 'transport', undefined], + ['activeTurnNotSteerable', { turnKind: 'review' }, 'product-error', undefined], ] as const - for (const [category, detail, httpStatus] of scenarios) { + for (const [codexErrorInfo, detail, category, httpStatus] of scenarios) { const { child, wire } = await initializeWire() const result = wire.runTurn(['task'], new AbortController().signal) const turnStart = await child.peer.nextMethod('turn/start') child.peer.respond(turnStart, { turn: { id: 'turn-1' } }) child.peer.send(turnCompleted('failed', 'turn-1', 'thread-1', { message: 'SECRET_TOKEN in /private/secret.txt', - codexErrorInfo: { [category]: detail }, + codexErrorInfo: { [codexErrorInfo]: detail }, })) await expect(result).rejects.toThrow(`status failed: ${category}`) expect(wire.collectFailure()).toEqual({ @@ -908,10 +961,12 @@ describe('CodexAppServerWire', () => { const scenarios: Array<{ readonly frames: JsonObject[] readonly message: string + readonly category: 'invalid-result' | 'unknown' }> = [ { frames: [turnCompleted('completed')], message: 'without a final answer', + category: 'invalid-result', }, { frames: [ @@ -920,30 +975,37 @@ describe('CodexAppServerWire', () => { turnCompleted('completed'), ], message: 'without a final answer', + category: 'invalid-result', }, { frames: [agentMessage(42, 'final_answer')], message: 'invalid agent message', + category: 'unknown', }, { frames: [agentMessage('answer', 'future_phase')], message: 'unknown agent message phase', + category: 'unknown', }, { frames: [turnCompleted('failed', 'turn-1', 'thread-1', { message: 'no' })], message: 'status failed', + category: 'unknown', }, { frames: [turnCompleted('failed', 'turn-1', 'thread-1', 'SECRET_TOKEN')], message: 'status failed', + category: 'unknown', }, { frames: [turnCompleted('interrupted')], message: 'status interrupted', + category: 'unknown', }, { frames: [turnCompleted('inProgress')], message: 'invalid terminal turn status', + category: 'unknown', }, ] for (const scenario of scenarios) { @@ -956,7 +1018,7 @@ describe('CodexAppServerWire', () => { await expect(result).rejects.toThrow(scenario.message) expect(wire.collectFailure()).toEqual({ stage: 'turn', - category: 'unknown', + category: scenario.category, }) wire.close() } @@ -1160,75 +1222,6 @@ describe('CodexAppServerWire', () => { wire.close() }) - it('recognizes large, split, and ordered stderr signatures without retaining raw text', () => { - const first = fakeChild() - const largeWire = new CodexAppServerWire( - first.handle.stdout!, - first.handle.stdin!, - 'never', - ) - largeWire.observeStderr( - `SECRET_TOKEN approval policy is Never; reject command${'x'.repeat(2_048)}`, - ) - expect(largeWire.collectDiagnostic()).toBe( - 'Codex unattended decision (mode: never; request: command execution; decision: denied): Codex rejected an escalation because the selected policy never asks for approval', - ) - expect(largeWire.collectDiagnostic()).not.toContain('SECRET_TOKEN') - - const second = fakeChild() - const splitWire = new CodexAppServerWire( - second.handle.stdout!, - second.handle.stdin!, - 'never', - ) - splitWire.observeStderr('SECRET_TOKEN approval policy is Ne') - splitWire.observeStderr('ver; reject command — /private/secret.txt') - expect(splitWire.collectDiagnostic()).toBe( - 'Codex unattended decision (mode: never; request: command execution; decision: denied): Codex rejected an escalation because the selected policy never asks for approval', - ) - expect(splitWire.collectDiagnostic()).not.toContain('SECRET_TOKEN') - expect(splitWire.collectDiagnostic()).not.toContain('/private/secret.txt') - - const third = fakeChild() - const orderedWire = new CodexAppServerWire( - third.handle.stdout!, - third.handle.stdin!, - 'dangerously-bypass-approvals-and-sandbox', - ) - orderedWire.observeStderr( - 'approval policy is Never; reject command; recorded sandbox violation: path=/private/secret.txt', - ) - expect(orderedWire.collectDiagnostic()).toBe( - 'Codex unattended decision (mode: dangerously-bypass-approvals-and-sandbox; request: sandbox execution; decision: failed): Codex reported a sandbox violation', - ) - expect(orderedWire.collectDiagnostic()).not.toContain('/private/secret.txt') - }) - - it('does not reapply an old stderr signature after a newer request diagnostic', async () => { - const { child, wire } = await initializeWire() - wire.observeStderr('recorded sandbox violation:') - const result = wire.runTurn(['task'], new AbortController().signal) - const turnStart = await child.peer.nextMethod('turn/start') - child.peer.respond(turnStart, { turn: { id: 'turn-1' } }) - await nextTask() - child.peer.send({ - id: 'file-approval', - method: 'item/fileChange/requestApproval', - params: { - threadId: 'thread-1', - turnId: 'turn-1', - availableDecisions: ['decline'], - }, - }) - await child.peer.nextResponse('file-approval') - expect(wire.collectDiagnostic()).toContain('request: file approval') - wire.observeStderr('later benign stderr') - expect(wire.collectDiagnostic()).toContain('request: file approval') - child.peer.send(agentMessage('answer', 'final_answer'), turnCompleted('completed')) - await expect(result).resolves.toMatchObject({ stopReason: 'completed' }) - wire.close() - }) - it('keeps a newer request diagnostic after replaying an older early item', async () => { const { child, wire } = await initializeWire() const result = wire.runTurn(['task'], new AbortController().signal) @@ -1259,25 +1252,6 @@ describe('CodexAppServerWire', () => { wire.close() }) - it('keeps a newer stderr fact after replaying an older early terminal', async () => { - hostStderrWrite.capture = true - hostStderrWrite.chunks.length = 0 - const { child, wire } = await initializeWire() - const result = wire.runTurn(['task'], new AbortController().signal) - const turnStart = await child.peer.nextMethod('turn/start') - child.peer.send(turnCompleted('failed', 'turn-1', 'thread-1', { - message: 'sandbox failure', - codexErrorInfo: 'sandboxError', - })) - await nextTask() - wire.observeStderr('approval policy is Never; reject command') - child.peer.respond(turnStart, { turn: { id: 'turn-1' } }) - await expect(result).rejects.toThrow('sandboxError') - expect(wire.collectDiagnostic()).toContain('request: command execution') - wire.close() - hostStderrWrite.capture = false - }) - it('fails the run on unknown requests or wrong request association', async () => { for (const serverRequest of [ { @@ -1529,7 +1503,7 @@ describe('run lifecycle and quiescence', () => { void starting.then(() => { published = true }) const initialize = await child.peer.nextMethod('initialize') expect(published).toBe(false) - child.peer.respond(initialize, { userAgent: 'codex-cli 0.147.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await child.peer.nextMethod('initialized') const threadStart = await child.peer.nextMethod('thread/start') expect(published).toBe(false) @@ -1619,13 +1593,15 @@ describe('run lifecycle and quiescence', () => { it('preserves representative terminal categories, HTTP status, and mapping', async () => { const scenarios = [ - ['contextWindowExceeded', 'max-tokens', undefined], - ['sessionBudgetExceeded', 'error', undefined], - [{ httpConnectionFailed: { httpStatusCode: 503 } }, 'error', 503], - [{ activeTurnNotSteerable: { turnKind: 'review' } }, 'error', undefined], - ['futureError', 'error', undefined], + ['contextWindowExceeded', 'limit', 'max-tokens', undefined], + ['sessionBudgetExceeded', 'limit', 'error', undefined], + ['unauthorized', 'access-policy', 'error', undefined], + ['internalServerError', 'service', 'error', undefined], + [{ httpConnectionFailed: { httpStatusCode: 503 } }, 'transport', 'error', 503], + [{ activeTurnNotSteerable: { turnKind: 'review' } }, 'product-error', 'error', undefined], + ['futureError', 'unknown', 'error', undefined], ] as const - for (const [codexErrorInfo, stopReason, httpStatus] of scenarios) { + for (const [codexErrorInfo, category, stopReason, httpStatus] of scenarios) { const { child, run, turnStart } = await publishRun() child.peer.respond(turnStart, { turn: { id: 'turn-1' } }) child.peer.send( @@ -1635,12 +1611,6 @@ describe('run lifecycle and quiescence', () => { codexErrorInfo, }), ) - const category = typeof codexErrorInfo === 'string' - && codexErrorInfo !== 'futureError' - ? codexErrorInfo - : typeof codexErrorInfo === 'object' - ? Object.keys(codexErrorInfo)[0]! - : 'unknown' const result = await run.result expect(result).toEqual({ output: [{ type: 'text', text: 'partial answer' }], @@ -1656,22 +1626,29 @@ describe('run lifecycle and quiescence', () => { } }) - it('includes a queued stderr permission fact in a max-token result', async () => { + it('includes a structured permission fact in a max-token result', async () => { const { child, run, turnStart } = await publishRun() child.peer.respond(turnStart, { turn: { id: 'turn-1' } }) - setImmediate(() => { - child.stderr.write('approval policy is Never; reject command') - child.peer.send( - agentMessage('partial answer', null), - turnCompleted('failed', 'turn-1', 'thread-1', { - codexErrorInfo: 'contextWindowExceeded', - }), - ) + child.peer.send({ + id: 'approval-before-limit', + method: 'item/commandExecution/requestApproval', + params: { + threadId: 'thread-1', + turnId: 'turn-1', + availableDecisions: ['cancel'], + }, }) + await child.peer.nextResponse('approval-before-limit') + child.peer.send( + agentMessage('partial answer', null), + turnCompleted('failed', 'turn-1', 'thread-1', { + codexErrorInfo: 'contextWindowExceeded', + }), + ) child.settle({ exitCode: 17, signal: null }) await expect(run.result).resolves.toEqual({ output: [{ type: 'text', text: 'partial answer' }], - diagnostic: `${expectedFailureDiagnostic('turn', 'contextWindowExceeded', { outcome: { exitCode: 17, signal: null } })}\nCodex unattended decision (mode: never; request: command execution; decision: denied): Codex rejected an escalation because the selected policy never asks for approval`, + diagnostic: `${expectedFailureDiagnostic('turn', 'limit', { outcome: { exitCode: 17, signal: null } })}\nCodex unattended decision (mode: never; request: command approval; decision: cancelled): the provider does not grant interactive approval`, stopReason: 'max-tokens', }) await run.dispose() @@ -1692,13 +1669,13 @@ describe('run lifecycle and quiescence', () => { child.settle(outcome) await expect(run.result).resolves.toEqual({ output: [], - diagnostic: expectedFailureDiagnostic('process', 'process-exit', { + diagnostic: expectedFailureDiagnostic('process', 'process', { outcome, }), stopReason: 'error', }) expect(errors.at(-1)).toBe( - `subagent-codex: ${expectedFailureDiagnostic('process', 'process-exit', { outcome })}`, + `subagent-codex: ${expectedFailureDiagnostic('process', 'process', { outcome })}`, ) await run.dispose().catch(() => {}) } @@ -1717,7 +1694,7 @@ describe('run lifecycle and quiescence', () => { child.fromChild.emit('end') await expect(run.result).resolves.toEqual({ output: [], - diagnostic: expectedFailureDiagnostic('process', 'process-exit', { + diagnostic: expectedFailureDiagnostic('process', 'process', { outcome, }), stopReason: 'error', @@ -1736,7 +1713,7 @@ describe('run lifecycle and quiescence', () => { child.settle({ exitCode: 17, signal: null }) await expect(run.result).resolves.toEqual({ output: [], - diagnostic: expectedFailureDiagnostic('turn', 'other', { + diagnostic: expectedFailureDiagnostic('turn', 'product-error', { outcome: { exitCode: 17, signal: null }, }), stopReason: 'error', @@ -1812,13 +1789,13 @@ describe('run lifecycle and quiescence', () => { })) await expect(run.result).resolves.toEqual({ output: [], - diagnostic: `${expectedFailureDiagnostic('turn', 'other')}\nCodex unattended decision (mode: never; request: command approval; decision: cancelled): the provider does not grant interactive approval`, + diagnostic: `${expectedFailureDiagnostic('turn', 'product-error')}\nCodex unattended decision (mode: never; request: command approval; decision: cancelled): the provider does not grant interactive approval`, stopReason: 'error', }) await run.dispose() }) - it('drains queued stderr before settling a failed published run', async () => { + it('drains queued stderr to the Host without classifying it', async () => { hostStderrWrite.capture = true hostStderrWrite.chunks.length = 0 const { child, run, turnStart } = await publishRun() @@ -1832,14 +1809,16 @@ describe('run lifecycle and quiescence', () => { }) await expect(run.result).resolves.toEqual({ output: [], - diagnostic: `${expectedFailureDiagnostic('turn', 'badRequest')}\nCodex unattended decision (mode: never; request: command execution; decision: denied): Codex rejected an escalation because the selected policy never asks for approval`, + diagnostic: expectedFailureDiagnostic('turn', 'product-error'), stopReason: 'error', }) + expect(Buffer.concat(hostStderrWrite.chunks).toString()) + .toContain('approval policy is Never; reject command') await run.dispose() hostStderrWrite.capture = false }) - it('forwards stderr while extracting only a fixed safe permission signature', async () => { + it('forwards stderr without copying or classifying it', async () => { const child = fakeChild() hostStderrWrite.capture = true hostStderrWrite.chunks.length = 0 @@ -1854,7 +1833,7 @@ describe('run lifecycle and quiescence', () => { })) await expect(run.result).resolves.toEqual({ output: [], - diagnostic: `${expectedFailureDiagnostic('turn', 'badRequest')}\nCodex unattended decision (mode: never; request: command execution; decision: denied): Codex rejected an escalation because the selected policy never asks for approval`, + diagnostic: expectedFailureDiagnostic('turn', 'product-error'), stopReason: 'error', }) expect(Buffer.concat(hostStderrWrite.chunks).toString()).toContain('SECRET_TOKEN') @@ -1877,7 +1856,7 @@ describe('run lifecycle and quiescence', () => { })) await expect(run.result).resolves.toEqual({ output: [], - diagnostic: `${expectedFailureDiagnostic('turn', 'badRequest')}\nCodex unattended decision (mode: never; request: command execution; decision: denied): Codex rejected an escalation because the selected policy never asks for approval`, + diagnostic: expectedFailureDiagnostic('turn', 'product-error'), stopReason: 'error', }) await run.dispose() @@ -1975,7 +1954,7 @@ describe('run lifecycle and quiescence', () => { const threadChild = fakeChild() const threadStarting = startCodexRun(request(), runSpec(threadChild)) const threadInitialize = await threadChild.peer.nextMethod('initialize') - threadChild.peer.respond(threadInitialize, { userAgent: 'codex-cli 0.147.0' }) + threadChild.peer.respond(threadInitialize, { userAgent: 'codex-cli 0.149.1' }) await threadChild.peer.nextMethod('initialized') const invalidThread = await threadChild.peer.nextMethod('thread/start') threadChild.peer.respond(invalidThread, { thread: { id: '', ephemeral: true } }) @@ -1990,7 +1969,7 @@ describe('run lifecycle and quiescence', () => { ) const exitedThreadInitialize = await exitedThreadChild.peer.nextMethod('initialize') exitedThreadChild.peer.respond(exitedThreadInitialize, { - userAgent: 'codex-cli 0.147.0', + userAgent: 'codex-cli 0.149.1', }) await exitedThreadChild.peer.nextMethod('initialized') await exitedThreadChild.peer.nextMethod('thread/start') @@ -2009,7 +1988,7 @@ describe('run lifecycle and quiescence', () => { const eofBeforeCloseInitialize = await eofBeforeCloseChild.peer .nextMethod('initialize') eofBeforeCloseChild.peer.respond(eofBeforeCloseInitialize, { - userAgent: 'codex-cli 0.147.0', + userAgent: 'codex-cli 0.149.1', }) await eofBeforeCloseChild.peer.nextMethod('initialized') await eofBeforeCloseChild.peer.nextMethod('thread/start') @@ -2027,7 +2006,7 @@ describe('run lifecycle and quiescence', () => { const stderrStarting = startCodexRun(request(), runSpec(stderrChild)) const stderrInitialize = await stderrChild.peer.nextMethod('initialize') stderrChild.stderr.emit('error', new Error('startup stderr broke')) - stderrChild.peer.respond(stderrInitialize, { userAgent: 'codex-cli 0.147.0' }) + stderrChild.peer.respond(stderrInitialize, { userAgent: 'codex-cli 0.149.1' }) await stderrChild.peer.nextMethod('initialized') const stderrThreadStart = await stderrChild.peer.nextMethod('thread/start') stderrChild.peer.respond(stderrThreadStart, { @@ -2053,7 +2032,7 @@ describe('run lifecycle and quiescence', () => { runSpec(child), ) const initialize = await child.peer.nextMethod('initialize') - child.peer.respond(initialize, { userAgent: 'codex-cli 0.147.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await child.peer.nextMethod('initialized') const threadStart = await child.peer.nextMethod('thread/start') expect(threadStart.params).toEqual({ @@ -2139,12 +2118,12 @@ describe('run lifecycle and quiescence', () => { })) await expect(first.run.result).resolves.toEqual({ output: [], - diagnostic: `${expectedFailureDiagnostic('turn', 'other')}\nCodex unattended decision (mode: never; request: command approval; decision: cancelled): the provider does not grant interactive approval`, + diagnostic: `${expectedFailureDiagnostic('turn', 'product-error')}\nCodex unattended decision (mode: never; request: command approval; decision: cancelled): the provider does not grant interactive approval`, stopReason: 'error', }) await expect(second.run.result).resolves.toEqual({ output: [], - diagnostic: `${expectedFailureDiagnostic('turn', 'other')}\nCodex unattended decision (mode: dangerously-bypass-approvals-and-sandbox; request: MCP elicitation; decision: declined): the provider does not collect interactive MCP input`, + diagnostic: `${expectedFailureDiagnostic('turn', 'product-error')}\nCodex unattended decision (mode: dangerously-bypass-approvals-and-sandbox; request: MCP elicitation; decision: declined): the provider does not collect interactive MCP input`, stopReason: 'error', }) await Promise.all([first.run.dispose(), second.run.dispose()]) @@ -2162,6 +2141,7 @@ describe('run lifecycle and quiescence', () => { }) as typeof ctx.logger.warn await ctx.plugin(codex, { providerName: 'codex-diagnostic', + model: 'codex-diagnostic-model', env: { OPENAI_API_KEY: 'fake' }, permissionMode: 'approve-for-me', disposeGraceMs: 25, @@ -2207,12 +2187,13 @@ describe('run lifecycle and quiescence', () => { signal: new AbortController().signal, }) const initialize = await child.peer.nextMethod('initialize') - child.peer.respond(initialize, { userAgent: 'codex-cli 0.147.0' }) + child.peer.respond(initialize, { userAgent: 'codex-cli 0.149.1' }) await child.peer.nextMethod('initialized') const threadStart = await child.peer.nextMethod('thread/start') expect(threadStart.params).toEqual({ cwd: process.cwd(), ephemeral: true, + model: 'codex-diagnostic-model', approvalPolicy: 'on-request', approvalsReviewer: 'auto_review', sandbox: 'workspace-write', @@ -2239,7 +2220,7 @@ describe('run lifecycle and quiescence', () => { })) await expect(run.result).resolves.toEqual({ output: [], - diagnostic: `${expectedFailureDiagnostic('turn', 'other')}\nCodex unattended decision (mode: approve-for-me; request: command approval; decision: cancelled): the provider does not grant interactive approval`, + diagnostic: `${expectedFailureDiagnostic('turn', 'product-error')}\nCodex unattended decision (mode: approve-for-me; request: command approval; decision: cancelled): the provider does not grant interactive approval`, stopReason: 'error', }) expect(spawn).toHaveBeenCalledWith(expect.objectContaining({ @@ -2249,7 +2230,7 @@ describe('run lifecycle and quiescence', () => { })) expect(warnings).toEqual([ expect.stringContaining( - `subagent-codex "codex-diagnostic": child run failed (error): subagent-codex: ${expectedFailureDiagnostic('turn', 'other')}`, + `subagent-codex "codex-diagnostic": child run failed (error): subagent-codex: ${expectedFailureDiagnostic('turn', 'product-error')}`, ), ]) expect(warnings.join('\n')).not.toContain('SECRET_TOKEN') diff --git a/packages/test-support/client-runtime/src/fixtures.ts b/packages/test-support/client-runtime/src/fixtures.ts index dc0ff57744..098e81a2a8 100644 --- a/packages/test-support/client-runtime/src/fixtures.ts +++ b/packages/test-support/client-runtime/src/fixtures.ts @@ -1,8 +1,7 @@ /** Controller and UI-domain fixture shapes for the client test runtime. */ import type { - ISession, SessionSnapshot, SessionSummary, + ISession, SessionEventLikeEntry, SessionSnapshot, SessionSummary, } from '@deepseek-ai/dsh-api-session-controller/client' -import type { SessionEventEntry } from '@deepseek-ai/dsh-api-session-controller/types' import type { WorkspaceSnapshot } from '@deepseek-ai/dsh-api-workspace-controller/client' import type { SessionId } from '@deepseek-ai/dsh-session/types' import { @@ -53,7 +52,7 @@ export interface SessionFixture { /** Session behavior face: exactly the methods the feature under test calls (ISession subset + extras). */ session?: SessionBehaviorOverrides /** Initial contiguous event window consumed by Conversation assembly. */ - events?: readonly SessionEventEntry[] + events?: readonly SessionEventLikeEntry[] /** Whether the initial event window has an older page. */ hasMore?: boolean } diff --git a/packages/test-support/client-runtime/src/sessions.ts b/packages/test-support/client-runtime/src/sessions.ts index cbd3b9a2e2..b269eb9bf4 100644 --- a/packages/test-support/client-runtime/src/sessions.ts +++ b/packages/test-support/client-runtime/src/sessions.ts @@ -6,9 +6,9 @@ import { } from '@deepseek-ai/dsh-api-session-controller/client' import type { AgentContext, ISessions, ProjectionsFace, SessionBinding, SessionFace, SessionListState, - SessionSearchResultItem, SessionSnapshot, SessionSummary, + SessionEventLikeEntry, SessionLiveEventEntry, SessionSearchResultItem, + SessionSnapshot, SessionSummary, } from '@deepseek-ai/dsh-api-session-controller/client' -import type { SessionEventEntry } from '@deepseek-ai/dsh-api-session-controller/types' import type { SubagentAddress } from '@deepseek-ai/dsh-client-connection/client' import { createSnapshotStore } from '@deepseek-ai/dsh-client-store' import type { ObservableSnapshot, SnapshotStore } from '@deepseek-ai/dsh-client-store' @@ -259,7 +259,7 @@ export class TestSessions implements ISessions { */ async replaceEvents( id: string, - entries: readonly SessionEventEntry[], + entries: readonly SessionEventLikeEntry[], hasMore = false, ): Promise { await this.stabilize(() => { this.require(id).session.eventSource.replace(entries, hasMore) }) @@ -273,7 +273,7 @@ export class TestSessions implements ISessions { */ async prependEvents( id: string, - entries: readonly SessionEventEntry[], + entries: readonly SessionEventLikeEntry[], hasMore = false, ): Promise { await this.stabilize(() => { this.require(id).session.eventSource.prepend(entries, hasMore) }) @@ -284,7 +284,7 @@ export class TestSessions implements ISessions { * @param id - Session identity. * @param entry - live event entry. */ - async appendEvent(id: string, entry: SessionEventEntry): Promise { + async appendEvent(id: string, entry: SessionLiveEventEntry): Promise { await this.stabilize(() => { this.require(id).session.eventSource.append(entry) }) } diff --git a/packages/test-support/client-runtime/tests/helpers.client.spec.tsx b/packages/test-support/client-runtime/tests/helpers.client.spec.tsx index 58d639864d..2fb223150a 100644 --- a/packages/test-support/client-runtime/tests/helpers.client.spec.tsx +++ b/packages/test-support/client-runtime/tests/helpers.client.spec.tsx @@ -1,6 +1,6 @@ // @vitest-environment jsdom import { act, cleanup, renderHook } from '@testing-library/react' -import type { SessionEventEntry } from '@deepseek-ai/dsh-api-session-controller/types' +import type { SessionLiveEventEntry } from '@deepseek-ai/dsh-api-session-controller/client' import { createSnapshotStore } from '@deepseek-ai/dsh-client-store' import { EMPTY_CHAT_SNAPSHOT } from '@deepseek-ai/dsh-client-ui-chat/client' import { EMPTY_CONVERSATION_SNAPSHOT } from '@deepseek-ai/dsh-client-ui-conversation/client' @@ -24,15 +24,16 @@ afterAll(() => { expect(navigator.language).toBe(originalLanguage) }) -function entry(seq: number): SessionEventEntry { +function entry(seq: number): SessionLiveEventEntry { return { + type: 'event', event: { type: 'fixture/event', seq, time: seq, data: { seq }, ignorable: true, - }, + } as SessionLiveEventEntry['event'], } } diff --git a/packages/test-support/session-snapshot/tests/fixtures/subagent-result-diagnostic.ts b/packages/test-support/session-snapshot/tests/fixtures/subagent-result-diagnostic.ts index 9a37a257a6..9725788b74 100644 --- a/packages/test-support/session-snapshot/tests/fixtures/subagent-result-diagnostic.ts +++ b/packages/test-support/session-snapshot/tests/fixtures/subagent-result-diagnostic.ts @@ -24,12 +24,12 @@ const RESULTS = [ }, { id: '00000000-0000-4000-8000-0000000000d3', - diagnostic: 'Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)', + diagnostic: 'Product subagent failure (product: Codex; stage: turn; category: transport; HTTP status: 503)', output: [{ type: 'text' as const, text: 'partial assistant text' }], }, { id: '00000000-0000-4000-8000-0000000000d4', - diagnostic: 'Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)', + diagnostic: 'Product subagent failure (product: Codex; stage: turn; category: transport; HTTP status: 503)', output: [], }, ] as const diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index fe8afd035e..b7317d7eaa 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -2161,6 +2161,9 @@ importers: react: specifier: ^18.2.0 version: 18.3.1 + zod: + specifier: ^4.4.3 + version: 4.4.3 packages/client/ui-deliverables: devDependencies: @@ -8250,8 +8253,8 @@ importers: specifier: link:../../../vendor/schemastery version: link:../../../vendor/schemastery '@openai/codex': - specifier: 0.147.0 - version: 0.147.0 + specifier: 0.149.1 + version: 0.149.1 devDependencies: '@deepseek-ai/cordis': specifier: workspace:^ @@ -11566,43 +11569,43 @@ packages: resolution: {integrity: sha512-da6KbdNCV5sr1/txD896V+6W0iamFWrvVl8cHkBSPT+YlvmT3DwXa4jxZnQc+gnuTEqSWbBeoSZYTayXH9wXcw==} engines: {node: '>= 20'} - '@openai/codex@0.147.0': - resolution: {integrity: sha512-EQLEXecAG2ptxI7UpBMo2TR/ga5596/c/OsYF/0LoUDh5JANZ7IoGqlzBEWbuEVQ76JePIbtTW/ihCkp1a7Z3w==} + '@openai/codex@0.149.1': + resolution: {integrity: sha512-6q5pbcpFbJbqOpkubSDBwXmktQ55aD8eUzGzBF1zASob2DjwhBKDSNGtdZKalfrNJUdTDTPDMmzCXEXs5tMBYA==} engines: {node: '>=16'} hasBin: true - '@openai/codex@0.147.0-darwin-arm64': - resolution: {integrity: sha512-BEUVkiOW7kLcRyrMLfAr/h9wF8sRVJyZDy6OHtVn6QGDXiv3BvAZVTY1Pu9xF7KdIdkYXbp4uayN0aDQQaAUJw==} + '@openai/codex@0.149.1-darwin-arm64': + resolution: {integrity: sha512-6X84kTCbnTgPIJ2EdcPsrvwS0Wxsqpa+bCswGmRf4BjhcQ5nPMnBC6yCAaCMj+vrbXQHj+L6sa9FaR4QkmA1qw==} engines: {node: '>=16'} cpu: [arm64] os: [darwin] - '@openai/codex@0.147.0-darwin-x64': - resolution: {integrity: sha512-Tb8McE5SvJIH0Vs5R6sq7u+quiC931yan2KOOl6km1OdZ82+Wi7eF5XrSFPs5CF7xCgoIK4Vs+byMbT5hN+ZUw==} + '@openai/codex@0.149.1-darwin-x64': + resolution: {integrity: sha512-MfLBQLfcElJL9tvj6y45qVHHMGSXCPnQOixuD3/Zq0g1BW/eFizkrGLdn48cFpc+l8cK+gt5nYG5pQYwVs6g4A==} engines: {node: '>=16'} cpu: [x64] os: [darwin] - '@openai/codex@0.147.0-linux-arm64': - resolution: {integrity: sha512-SLC1JXw2TYfr/c3HhrJubyyLelq7vTOLWVmiThFA+z0+WgzCPmaseJ/kzDD3Gge/TO7fCnnj7UcPmC0d2c8XAg==} + '@openai/codex@0.149.1-linux-arm64': + resolution: {integrity: sha512-OqxUfZ1TVvHd18zHPKK/8ZRlpk8Vy11mg5CMHaLxNWldTbwVImDKtSLWT+m8m4NM5Sz4PbjtZMrVT/RfpBW/mQ==} engines: {node: '>=16'} cpu: [arm64] os: [linux] - '@openai/codex@0.147.0-linux-x64': - resolution: {integrity: sha512-0W9MBxPpWW0cSkNqrTDN2jR7rzzT7oNMhQY5446lT2Lw5cz5yhDTck4Va9rjkQEm+HlFzP/dmEMSZbXfJsINmw==} + '@openai/codex@0.149.1-linux-x64': + resolution: {integrity: sha512-Of5fGYgr7tAMsyj6vhXb4/RM/UoA3Zq8BLegUBDC09UNy1XTLGYP/2XD+UX8z3qh0NDwxYdCjFIWdDNijKZggQ==} engines: {node: '>=16'} cpu: [x64] os: [linux] - '@openai/codex@0.147.0-win32-arm64': - resolution: {integrity: sha512-e2ZstJ8zT8Rm1nvR7CUVO+Gr3cTChE41+VfOzGhynzDXEoW0wfbjUQbc2bWbh1arG94LMm4y3dqBtUIbSrfeGA==} + '@openai/codex@0.149.1-win32-arm64': + resolution: {integrity: sha512-5K0DmOKGK9Bos627p8sK8ATHjovPK0sDyT6h9Cb+4v+5CW5SGw1HLgjGxoLfJ8g3cg6mtg/pRCXXo2L/j71UVA==} engines: {node: '>=16'} cpu: [arm64] os: [win32] - '@openai/codex@0.147.0-win32-x64': - resolution: {integrity: sha512-oT7Ss5fAPf2fiWE9QNURqZcQGAAawSVxmIUdgPzckq4KFZAM+pRz9JbM4Rr498CjtbNgTOjWvDJ+DXvIBSfOPA==} + '@openai/codex@0.149.1-win32-x64': + resolution: {integrity: sha512-G3QXGAg7nyyhqOeooAMUekBCeHd8a1QByhKcVAFyzNBaI06t6Ft7nsF+1SzFS0spuIdU4YyMi5YD26ukADBQUQ==} engines: {node: '>=16'} cpu: [x64] os: [win32] @@ -17223,31 +17226,31 @@ snapshots: '@octokit/request-error': 7.1.1 '@octokit/webhooks-methods': 6.0.0 - '@openai/codex@0.147.0': + '@openai/codex@0.149.1': optionalDependencies: - '@openai/codex-darwin-arm64': '@openai/codex@0.147.0-darwin-arm64' - '@openai/codex-darwin-x64': '@openai/codex@0.147.0-darwin-x64' - '@openai/codex-linux-arm64': '@openai/codex@0.147.0-linux-arm64' - '@openai/codex-linux-x64': '@openai/codex@0.147.0-linux-x64' - '@openai/codex-win32-arm64': '@openai/codex@0.147.0-win32-arm64' - '@openai/codex-win32-x64': '@openai/codex@0.147.0-win32-x64' + '@openai/codex-darwin-arm64': '@openai/codex@0.149.1-darwin-arm64' + '@openai/codex-darwin-x64': '@openai/codex@0.149.1-darwin-x64' + '@openai/codex-linux-arm64': '@openai/codex@0.149.1-linux-arm64' + '@openai/codex-linux-x64': '@openai/codex@0.149.1-linux-x64' + '@openai/codex-win32-arm64': '@openai/codex@0.149.1-win32-arm64' + '@openai/codex-win32-x64': '@openai/codex@0.149.1-win32-x64' - '@openai/codex@0.147.0-darwin-arm64': + '@openai/codex@0.149.1-darwin-arm64': optional: true - '@openai/codex@0.147.0-darwin-x64': + '@openai/codex@0.149.1-darwin-x64': optional: true - '@openai/codex@0.147.0-linux-arm64': + '@openai/codex@0.149.1-linux-arm64': optional: true - '@openai/codex@0.147.0-linux-x64': + '@openai/codex@0.149.1-linux-x64': optional: true - '@openai/codex@0.147.0-win32-arm64': + '@openai/codex@0.149.1-win32-arm64': optional: true - '@openai/codex@0.147.0-win32-x64': + '@openai/codex@0.149.1-win32-x64': optional: true '@opentelemetry/api-logs@0.220.0': diff --git a/pnpm-workspace.yaml b/pnpm-workspace.yaml index 96ddf2a429..17f76800d4 100644 --- a/pnpm-workspace.yaml +++ b/pnpm-workspace.yaml @@ -70,6 +70,9 @@ minimumReleaseAgeExclude: - '@anthropic-ai/claude-agent-sdk-win32-arm64@0.3.241' - '@anthropic-ai/claude-agent-sdk-win32-x64@0.3.241' - '@anthropic-ai/claude-agent-sdk@0.3.241' + # All platform aliases resolve to the @openai/codex package name, so their + # reviewed exact versions must share one version-union policy entry. + - '@openai/codex@0.149.1||0.149.1-darwin-arm64||0.149.1-darwin-x64||0.149.1-linux-arm64||0.149.1-linux-x64||0.149.1-win32-arm64||0.149.1-win32-x64' patchedDependencies: node-pty@1.2.0-beta.15: patches/node-pty@1.2.0-beta.15.patch diff --git a/snapshots/session/product-subagent-both/cordis.snapshot.yml b/snapshots/session/product-subagent-both/cordis.snapshot.yml index 37b74391b6..d37ad32391 100644 --- a/snapshots/session/product-subagent-both/cordis.snapshot.yml +++ b/snapshots/session/product-subagent-both/cordis.snapshot.yml @@ -18,10 +18,12 @@ name: '@deepseek-ai/dsh-subagent-codex' config: providerName: codex-primary + model: codex-primary-model - id: subagent-codex-secondary name: '@deepseek-ai/dsh-subagent-codex' config: providerName: codex-secondary + model: codex-secondary-model - id: subagent-claude-primary name: '@deepseek-ai/dsh-subagent-claude-code' config: diff --git a/snapshots/session/product-subagent-both/cordis.yml b/snapshots/session/product-subagent-both/cordis.yml index 3891fbcc6c..2e50aa4875 100644 --- a/snapshots/session/product-subagent-both/cordis.yml +++ b/snapshots/session/product-subagent-both/cordis.yml @@ -6,10 +6,12 @@ name: '@deepseek-ai/dsh-subagent-codex' config: providerName: codex-primary + model: codex-primary-model - id: subagent-codex-secondary name: '@deepseek-ai/dsh-subagent-codex' config: providerName: codex-secondary + model: codex-secondary-model - id: subagent-claude-primary name: '@deepseek-ai/dsh-subagent-claude-code' config: diff --git a/snapshots/session/product-subagent-codex/cordis.snapshot.yml b/snapshots/session/product-subagent-codex/cordis.snapshot.yml index 71ac58f715..9e1cbb5d9e 100644 --- a/snapshots/session/product-subagent-codex/cordis.snapshot.yml +++ b/snapshots/session/product-subagent-codex/cordis.snapshot.yml @@ -18,10 +18,12 @@ name: '@deepseek-ai/dsh-subagent-codex' config: providerName: codex-primary + model: codex-primary-model - id: subagent-codex-secondary name: '@deepseek-ai/dsh-subagent-codex' config: providerName: codex-secondary + model: codex-secondary-model - id: tool-subagent-codex-primary name: '@deepseek-ai/dsh-tool-subagent' config: diff --git a/snapshots/session/product-subagent-codex/cordis.yml b/snapshots/session/product-subagent-codex/cordis.yml index 8ab76d8d2f..f5851447d4 100644 --- a/snapshots/session/product-subagent-codex/cordis.yml +++ b/snapshots/session/product-subagent-codex/cordis.yml @@ -6,10 +6,12 @@ name: '@deepseek-ai/dsh-subagent-codex' config: providerName: codex-primary + model: codex-primary-model - id: subagent-codex-secondary name: '@deepseek-ai/dsh-subagent-codex' config: providerName: codex-secondary + model: codex-secondary-model - id: tool-subagent-codex-primary name: '@deepseek-ai/dsh-tool-subagent' config: diff --git a/snapshots/session/product-subagent-result-diagnostic/session.jsonl b/snapshots/session/product-subagent-result-diagnostic/session.jsonl index 13e7e3ed2f..9105aaccb7 100644 --- a/snapshots/session/product-subagent-result-diagnostic/session.jsonl +++ b/snapshots/session/product-subagent-result-diagnostic/session.jsonl @@ -51,7 +51,7 @@ {"type":"assistant/chunk","data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","data":{"turn":1,"step":4,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_codex_foreground","name":"subagent_codex","arguments":"{\"description\":\"Observe Codex foreground diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":false}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"{{message:10}}"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":4,"callId":"call_codex_foreground","name":"subagent_codex","arguments":"{\"description\":\"Observe Codex foreground diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":false}"}} -{"type":"tool/result","data":{"turn":1,"step":4,"message":{"source":{"kind":"tool","callId":"call_codex_foreground"},"content":[{"type":"tool-result","toolCallId":"call_codex_foreground","content":[{"type":"text","text":"Error: subagent run failed\nDiagnostic: Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)\nPartial output before the run ended:\npartial assistant text"}],"isError":true}],"role":"user","id":"{{message:11}}"}},"sourceEventSeqs":[51],"surfaceOp":"append"} +{"type":"tool/result","data":{"turn":1,"step":4,"message":{"source":{"kind":"tool","callId":"call_codex_foreground"},"content":[{"type":"tool-result","toolCallId":"call_codex_foreground","content":[{"type":"text","text":"Error: subagent run failed\nDiagnostic: Product subagent failure (product: Codex; stage: turn; category: transport; HTTP status: 503)\nPartial output before the run ended:\npartial assistant text"}],"isError":true}],"role":"user","id":"{{message:11}}"}},"sourceEventSeqs":[51],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":4}} {"type":"step/start","data":{"turn":1,"step":5}} {"type":"assistant/chunk","data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} @@ -61,12 +61,12 @@ {"type":"assistant/chunk","data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","data":{"turn":1,"step":5,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_codex_background","name":"subagent_codex","arguments":"{\"description\":\"Observe Codex background diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":true}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"{{message:12}}"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":5,"callId":"call_codex_background","name":"subagent_codex","arguments":"{\"description\":\"Observe Codex background diagnostic\",\"prompt\":\"Return the Codex diagnostic failure.\",\"run_in_background\":true}"}} -{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"background job subagent-2 (subagent: Observe Codex background diagnostic) finished [status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)]. Read its output with job_output."}],"source":{"kind":"plugin","plugin":"tool-jobs","form":"notice","summary":"subagent Observe Codex background diagnostic [status: failed, error; diagnostic: Product subagent failure (product: Cod…"},"role":"user","id":"{{message:13}}"}]}} +{"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"inserted":[{"content":[{"type":"text","text":"background job subagent-2 (subagent: Observe Codex background diagnostic) finished [status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: transport; HTTP status: 503)]. Read its output with job_output."}],"source":{"kind":"plugin","plugin":"tool-jobs","form":"notice","summary":"subagent Observe Codex background diagnostic [status: failed, error; diagnostic: Product subagent failure (product: Cod…"},"role":"user","id":"{{message:13}}"}]}} {"type":"tool/result","data":{"turn":1,"step":5,"message":{"source":{"kind":"tool","callId":"call_codex_background"},"content":[{"type":"tool-result","toolCallId":"call_codex_background","content":[{"type":"text","text":"started background subagent job subagent-2"}],"isError":false}],"role":"user","id":"{{message:14}}"}},"sourceEventSeqs":[61],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":5}} {"type":"agent/inbox/spliced","data":{"target":"next-step","start":0,"removedCount":1,"inserted":[]}} {"type":"step/start","data":{"turn":1,"step":6}} -{"type":"user/message","data":{"content":[{"type":"text","text":"background job subagent-2 (subagent: Observe Codex background diagnostic) finished [status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)]. Read its output with job_output."}],"source":{"kind":"plugin","plugin":"tool-jobs","form":"notice","summary":"subagent Observe Codex background diagnostic [status: failed, error; diagnostic: Product subagent failure (product: Cod…"},"role":"user","id":"{{message:13}}"},"surfaceOp":"append"} +{"type":"user/message","data":{"content":[{"type":"text","text":"background job subagent-2 (subagent: Observe Codex background diagnostic) finished [status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: transport; HTTP status: 503)]. Read its output with job_output."}],"source":{"kind":"plugin","plugin":"tool-jobs","form":"notice","summary":"subagent Observe Codex background diagnostic [status: failed, error; diagnostic: Product subagent failure (product: Cod…"},"role":"user","id":"{{message:13}}"},"surfaceOp":"append"} {"type":"assistant/chunk","data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","data":{"turn":1,"step":6,"chunk":{"type":"tool-call-delta","index":0,"id":"call_codex_output","name":"job_output","argumentsDelta":"{\"job_id\":\"subagent-2\",\"wait\":true}"}}} {"type":"assistant/chunk","data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_codex_output","name":"job_output","arguments":"{\"job_id\":\"subagent-2\",\"wait\":true}"}}}} @@ -74,7 +74,7 @@ {"type":"assistant/chunk","data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","data":{"turn":1,"step":6,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_codex_output","name":"job_output","arguments":"{\"job_id\":\"subagent-2\",\"wait\":true}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-pro"},"id":"{{message:15}}"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[68,69,70,71,72],"surfaceOp":"append"} {"type":"tool/call","data":{"turn":1,"step":6,"callId":"call_codex_output","name":"job_output","arguments":"{\"job_id\":\"subagent-2\",\"wait\":true}"}} -{"type":"tool/result","data":{"turn":1,"step":6,"message":{"source":{"kind":"tool","callId":"call_codex_output"},"content":[{"type":"tool-result","toolCallId":"call_codex_output","content":[{"type":"text","text":"(no new output)\n[status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: httpConnectionFailed; HTTP status: 503)]"}],"isError":false}],"role":"user","id":"{{message:16}}"}},"sourceEventSeqs":[74],"surfaceOp":"append"} +{"type":"tool/result","data":{"turn":1,"step":6,"message":{"source":{"kind":"tool","callId":"call_codex_output"},"content":[{"type":"tool-result","toolCallId":"call_codex_output","content":[{"type":"text","text":"(no new output)\n[status: failed, error; diagnostic: Product subagent failure (product: Codex; stage: turn; category: transport; HTTP status: 503)]"}],"isError":false}],"role":"user","id":"{{message:16}}"}},"sourceEventSeqs":[74],"surfaceOp":"append"} {"type":"step/end","data":{"turn":1,"step":6}} {"type":"step/start","data":{"turn":1,"step":7}} {"type":"assistant/chunk","data":{"turn":1,"step":7,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} diff --git a/tsconfig.base.json b/tsconfig.base.json index 0183f8b57d..e418fd7f6b 100644 --- a/tsconfig.base.json +++ b/tsconfig.base.json @@ -64,6 +64,7 @@ "@deepseek-ai/dsh-typert-generator": ["./packages/typert/generator/src/index.ts"], "@deepseek-ai/dsh-attachment/types": ["./packages/attachment/attachment/src/types.ts"], "@deepseek-ai/dsh-session/types": ["./packages/core/session/src/types.ts"], + "@deepseek-ai/dsh-session/chunk-rows": ["./packages/core/session/src/chunk-rows.ts"], "@deepseek-ai/dsh-session/surface": ["./packages/core/session/src/surface.ts"], "@deepseek-ai/dsh-session-projection/types": ["./packages/session/session-projection/src/types.ts"], "@deepseek-ai/dsh-tool-todo/types": ["./packages/todo/tool-todo/src/types.ts"], diff --git a/vitest.web.perf.config.ts b/vitest.web.perf.config.ts index ddb37f0fb7..722de820c5 100644 --- a/vitest.web.perf.config.ts +++ b/vitest.web.perf.config.ts @@ -1,13 +1,19 @@ import { defineConfig } from 'vitest/config' import webConfig from './vitest.web.config.ts' +import { vitestExecArgv } from './vitest.shared.ts' -// Manual high-cardinality diagnostics stay outside vitest.web.config.ts's -// .e2e.ts/.snapshot.ts inventory and therefore outside the CI web gate. +// Manual high-cardinality diagnostics stay outside every default Vitest +// inventory and therefore outside CI's executed test lanes. export default defineConfig({ ...webConfig, test: { ...webConfig.test, - include: ['apps/web/tests/**/*.perf.ts'], + // Memory diagnostics use forced-GC baselines only in this manual inventory. + execArgv: [...vitestExecArgv, '--expose-gc'], + include: [ + 'apps/web/tests/**/*.perf.ts', + 'packages/client/ui-conversation/tests/**/*.perf.client.ts', + ], disableConsoleIntercept: true, hookTimeout: 180_000, testTimeout: 600_000,