diff --git a/.agents/notes/archived/architecture/2026-07-26-packed-chunk-rows-by-default.i18n.yaml b/.agents/notes/archived/architecture/2026-07-26-packed-chunk-rows-by-default.i18n.yaml new file mode 100644 index 0000000000..511824cdc1 --- /dev/null +++ b/.agents/notes/archived/architecture/2026-07-26-packed-chunk-rows-by-default.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/architecture/2026-07-26-packed-chunk-rows-by-default.md +2026-07-26-packed-chunk-rows-by-default.md: c230c1f1faf5e597321654ebd01d60fae725f518 +2026-07-26-packed-chunk-rows-by-default.zh.md: e354efdf6bb68c02f30dc17c8d4ba17a495b61bd diff --git a/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.md b/.agents/notes/archived/architecture/2026-07-26-packed-chunk-rows-by-default.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.md rename to .agents/notes/archived/architecture/2026-07-26-packed-chunk-rows-by-default.md index bd4b3b9f77..c230c1f1fa 100644 --- a/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.md +++ b/.agents/notes/archived/architecture/2026-07-26-packed-chunk-rows-by-default.md @@ -1,6 +1,7 @@ # Agent Note: Make packed chunk rows the default JSONL layout Status: implemented +Archived: 2026-09-01 English | [中文](2026-07-26-packed-chunk-rows-by-default.zh.md) diff --git a/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.zh.md b/.agents/notes/archived/architecture/2026-07-26-packed-chunk-rows-by-default.zh.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.zh.md rename to .agents/notes/archived/architecture/2026-07-26-packed-chunk-rows-by-default.zh.md index eafe663215..e354efdf6b 100644 --- a/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.zh.md +++ b/.agents/notes/archived/architecture/2026-07-26-packed-chunk-rows-by-default.zh.md @@ -1,6 +1,7 @@ # Agent Note: 将打包分片行设为默认 JSONL 布局 Status: implemented +Archived: 2026-09-01 [English](2026-07-26-packed-chunk-rows-by-default.md) | 中文 diff --git a/.agents/notes/archived/architecture/2026-08-15-packed-session-history-transport.i18n.yaml b/.agents/notes/archived/architecture/2026-08-15-packed-session-history-transport.i18n.yaml new file mode 100644 index 0000000000..b632e8918b --- /dev/null +++ b/.agents/notes/archived/architecture/2026-08-15-packed-session-history-transport.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/architecture/2026-08-15-packed-session-history-transport.md +2026-08-15-packed-session-history-transport.md: 1fe8c78a89a0541475d10fae9ad643203f144c30 +2026-08-15-packed-session-history-transport.zh.md: b2aa5bf0bc0bc4952df29674f0b9ffe836368f73 diff --git a/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.md b/.agents/notes/archived/architecture/2026-08-15-packed-session-history-transport.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.md rename to .agents/notes/archived/architecture/2026-08-15-packed-session-history-transport.md index 01e36509b7..1fe8c78a89 100644 --- a/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.md +++ b/.agents/notes/archived/architecture/2026-08-15-packed-session-history-transport.md @@ -1,6 +1,7 @@ # Agent Note: Carry packed chunk rows through session history Status: implemented +Archived: 2026-09-01 English | [中文](2026-08-15-packed-session-history-transport.zh.md) diff --git a/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.zh.md b/.agents/notes/archived/architecture/2026-08-15-packed-session-history-transport.zh.md similarity index 99% rename from .agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.zh.md rename to .agents/notes/archived/architecture/2026-08-15-packed-session-history-transport.zh.md index 6ef847a14d..b2aa5bf0bc 100644 --- a/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.zh.md +++ b/.agents/notes/archived/architecture/2026-08-15-packed-session-history-transport.zh.md @@ -1,6 +1,7 @@ # Agent Note: 在会话历史中传输打包分片行 Status: implemented +Archived: 2026-09-01 [English](2026-08-15-packed-session-history-transport.md) | 中文 diff --git a/.agents/notes/archived/manifest.json b/.agents/notes/archived/manifest.json index 18173d7d3d..8c0142d851 100644 --- a/.agents/notes/archived/manifest.json +++ b/.agents/notes/archived/manifest.json @@ -37,6 +37,9 @@ "architecture/2026-07-24-dsh-commander-argument-adapter.i18n.yaml": "sha256:cf99eda0e58b49630d5f95792459d7095666fafbef61f614165d5cdd031b7118", "architecture/2026-07-24-dsh-commander-argument-adapter.md": "sha256:705654c8a43bcd199f72c21a77d24ca8bfa02447aff1c7f3e4e820be61dcd562", "architecture/2026-07-24-dsh-commander-argument-adapter.zh.md": "sha256:3844f02d7659d18caf5d39e1131ed775c789cbf92dc44b4a446c7d6468aa5d00", + "architecture/2026-07-26-packed-chunk-rows-by-default.i18n.yaml": "sha256:41aa86c65f78e125ca2178295d02d5994d5e0f2e9359b1465777db1aba4a105b", + "architecture/2026-07-26-packed-chunk-rows-by-default.md": "sha256:2b4e14675d12a1fc07eb373ab8566c3e63c7c15e2b5a0b391e6acbc896c7359d", + "architecture/2026-07-26-packed-chunk-rows-by-default.zh.md": "sha256:e0b0e8a4ab529a3461c22f434cbbe1e7b0ea381592871caf7e3fe5157ef844ba", "architecture/2026-07-27-tui-chat-channel-module-split.i18n.yaml": "sha256:7b9dbe8b4a340640610abe7e54fb29492d77a187c176996a53d0e1fc7c8e1945", "architecture/2026-07-27-tui-chat-channel-module-split.md": "sha256:3e2cd43f306a18b3eaf9bac23e6bdc3a5dbdc7388b7c399ce71e4f71b8f71d2a", "architecture/2026-07-27-tui-chat-channel-module-split.zh.md": "sha256:d6b84fdcd91a2693b72cf6884b3a0c39e56e571b2b694f630805d894a6ba292f", @@ -52,6 +55,9 @@ "architecture/2026-08-11-plugin-settings-tabs.i18n.yaml": "sha256:0365da2b317fc5f94dd190064198565f4c624afc91d2e62161ab9170f79d11bc", "architecture/2026-08-11-plugin-settings-tabs.md": "sha256:fdd92cfe55b6c4cd31b3f768dd46a2ecf129a04c9818249cbdd33857cf722bbf", "architecture/2026-08-11-plugin-settings-tabs.zh.md": "sha256:8993df1a0178aba1ea35c460ee67c522900344a4b386287bba9dfac2bfb87efa", + "architecture/2026-08-15-packed-session-history-transport.i18n.yaml": "sha256:547b89497b009593db5acfae2a3b989f17b8392f5df73ef631b38f8f68f629f1", + "architecture/2026-08-15-packed-session-history-transport.md": "sha256:ec7f84d59eea95668a8cb6c92ae433a2b7e7b76446a27e57dd5dba05856f563f", + "architecture/2026-08-15-packed-session-history-transport.zh.md": "sha256:0d8eb5444557a18f76c68ce5ae9f0779c580eaddb921ee8651464baea34e0e53", "architecture/2026-08-18-sqlite-physical-chunk-row-compression.i18n.yaml": "sha256:42bce930799cb511e9fb245dec5e26efd78bdab4c9b75f7393e37b40fbee4d10", "architecture/2026-08-18-sqlite-physical-chunk-row-compression.md": "sha256:4fe241f1b272278d9f3ca1a4431971220e1fa54411df043826ef6f59225bf949", "architecture/2026-08-18-sqlite-physical-chunk-row-compression.zh.md": "sha256:73178c9ec5abf571680d8facfb145cbadc1efbb2e67e3f039747c2f9cf4bb730", diff --git a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml index d664537d10..8f050e3cba 100644 --- a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.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/2026-06-14-session-persistence.md -2026-06-14-session-persistence.md: 989beb6f8cc65c8d033206a61b4408f3aecdbbc7 -2026-06-14-session-persistence.zh.md: 9dcdbffc7df89ce6fcd5341ef77f99e47643aa92 +2026-06-14-session-persistence.md: 8cca8a25a1795b50ad1b8282d0d3b0d1776fff24 +2026-06-14-session-persistence.zh.md: 2a4e8098625135c20d569c20bad37d1b36c55fe0 diff --git a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md index 989beb6f8c..8cca8a25a1 100644 --- a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md +++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.md @@ -15,11 +15,11 @@ The [event-sourced model](2026-06-11-event-sourced-sessions.md) makes the append Persistence is a **capability seam** with an abstract Service Definition ([capability seams](2026-06-13-capability-seams.md), the `dsh-shell` template), not loop or core logic: 1. **Interface** (`dsh-session-persistence`, `ctx.sessionPersistence`) — an abstract `SessionPersistence` service: `locate`/`create`/`append`/`prepare`/`load`/`inspect`/`readFrom`/`list`/`listSnapshots`. Its persisted unit IS the existing `SessionEvent` (`{ type, seq, time, data }`), reused verbatim — no conversion type. -2. **Implementation** (`dsh-session-persistence-jsonl`) — an append-only logical JSONL log per session: a `SessionHeader` line followed by storage records that losslessly represent the contiguous `SessionEvent` stream. Eligible `assistant/chunk` delta runs use packed rows by default; [checksummed Zstandard frames](2026-07-19-zstandard-jsonl-session-logs.md) are the default physical encoding, with raw lines configurable. +2. **Implementation** (`dsh-session-persistence-jsonl`) — an append-only logical JSONL log per session: a `SessionHeader` line followed by storage records that losslessly represent the contiguous `SessionEvent` stream. Current v2 writes one event per row; frozen v0 and v1 readers retain their historical packed-delta representation. [Checksummed Zstandard frames](2026-07-19-zstandard-jsonl-session-logs.md) are the default physical encoding, with raw lines configurable. Key durable, contested choices: -- **The canonical durable log persists every `SessionEvent` losslessly, including `assistant/chunk`.** JSONL storage may encode a consecutive delta run as one packed row, but logical readers reconstruct the exact event boundaries, sequence numbers, and timestamps. `deriveMessages()` skips chunks, and a chunk-filtered rollout (Codex's `policy.rs`) is tempting — but `seq = log.length` and validation of `events[i].seq === i` require a *contiguous* logical log; filtering chunks out would leave holes and break both the contract and resume. A chunk-filtered projection is possible later as a derived view with its own renumbering, but it is NOT the canonical log. +- **The canonical durable log persists every current `SessionEvent` losslessly.** In v2, one `assistant/message` or `assistant/attempt` embeds the exact timed provider stream for an attempt; `deriveMessages()` projects only the surface message. Dropping embedded stream members is tempting, but it loses replay, timing, usage, partial-failure, and diagnostic facts. Removing a complete event likewise requires dense renumbering because `seq = log.length` and `events[i].seq === i`; the [v1-to-v2 migration](2026-09-01-v2-embedded-assistant-streams.md) performs that rewrite explicitly rather than filtering the canonical log. - **Ordinary writes append; a crashed turn is closed, never truncated.** Flushed current-generation events are never rewritten by normal persistence. A format migration leaves the exact physical source path, bytes, and inode unchanged, then publishes one re-encoded current successor at a previously absent canonical versioned filename after only edge-owned normalization and current crash repair. The [semantic checkpoint policy](../bug-fix/2026-07-21-semantic-session-checkpoints.md) drains the request before model dispatch, a recorded top-level call before tool dispatch, and the complete response/result batch after a step; the loop drains the final turn boundary. Because one interrupted turn may contain substantial valid work, cold inspection preserves its contiguous, parseable events and adds risk-classified error results for unanswered assistant calls, a missing `step/end`, and `turn/end` with `{ kind: 'interrupted' }` to the in-memory logical view. `prepare` or `load` commits those closers before returning a recoverable view; the synthetic results keep resumed provider transcripts valid. Only an incomplete final record is discarded during committed repair; a parse error or sequence gap at or before the last real `turn/end` is corruption and makes the session unloadable. - **The file backend is canonical while the service remains extensible.** `dsh-session-persistence-jsonl` is the sole first-party provider and passes `runPersistenceContract`; the abstract service and coordinator remain available to out-of-tree providers. The [JSONL-only persistence decision](../simplification/2026-08-30-jsonl-only-session-persistence.md) owns removal of the first-party database provider and its deliberate compatibility cut. - **Metadata is out-of-log.** Format version, cwd, and lineage are storage concerns, not replayable conversation state, so they live in a `SessionHeader` owned by `dsh-session` and attached to a `Session` via a new readonly `session.header` — never in `SessionEventMap`, never reaching `deriveMessages()`. `createdAt` is non-negative safe-integer Unix epoch milliseconds: live creation and persistence registration reject fractional values, and JSONL validates the decoded header. The alternative (a merge-extensible `session/meta` event as log line 0) was rejected: an in-log event would ride along with a seeded/forked session for free, but metadata is not replayable state, so the explicit out-of-log header boundary is the cleaner cost. (The header was originally split into an immutable `SessionHeader` plus a mutable `SessionSummary` whose union was `SessionMeta`; the mutable summary was later removed as dead state — see [Drop the mutable session summary](../simplification/2026-06-19-drop-mutable-session-summary.md).) @@ -27,10 +27,10 @@ Key durable, contested choices: ## Alternatives considered -Each key choice above records its rejected alternative where the choice is stated: a **chunk-filtered canonical log** (Codex's `policy.rs` shape) — breaks the contiguous-seq contract; **truncating a crashed turn** — silently destroys a long autonomous run's real work; an **in-log `session/meta` event as log line 0** — metadata is not replayable state; **finite fractional `createdAt` values** — have no producer and diverge from integer Unix-millisecond storage; **hard-injecting `sessionPersistence` into the loop** — would pend non-persistent demos forever. +Each key choice above records its rejected alternative where the choice is stated: a **stream-filtered canonical log** — loses attempt evidence, while removing events without an explicit migration breaks contiguous sequence numbers; **truncating a crashed turn** — silently destroys a long autonomous run's real work; an **in-log `session/meta` event as log line 0** — metadata is not replayable state; **finite fractional `createdAt` values** — have no producer and diverge from integer Unix-millisecond storage; **hard-injecting `sessionPersistence` into the loop** — would pend non-persistent demos forever. -Format versioning: the header carries a `version`; current Session and coordinator code accept only `SESSION_FORMAT_VERSION = 1`. JSONL event-body reads compose the static adjacent migration chain before constructing a Session, and the v0-to-v1 edge owns the former narrow import upgrades such as [pre-identity message recovery](../bug-fix/2026-07-28-load-pre-identity-session-messages.md). V0 remains at suffixless `session.jsonl[.zstd]`, while v1 and later use immutable lowercase `session.vN.jsonl[.zstd]` names ([released Session migration](2026-08-31-released-session-format-migrations.md)). Current-generation append and flush are robust to partial trailing writes tolerated during cold preparation; a future provider or write-ahead log needs its own power-loss and recovery contract. +Format versioning: the header carries a `version`; current Session and coordinator code accept only `SESSION_FORMAT_VERSION = 2`. JSONL event-body reads compose the static v0-to-v1 and v1-to-v2 adjacent migration chain before constructing a Session; the first edge owns bounded legacy normalization, while the second owns Assistant stream embedding and dense reference remapping. V0 remains at suffixless `session.jsonl[.zstd]`, while positive versions use immutable lowercase `session.vN.jsonl[.zstd]` names ([released Session migration](2026-08-31-released-session-format-migrations.md)). Current-generation append and flush are robust to partial trailing writes tolerated during cold preparation; a future provider or write-ahead log needs its own power-loss and recovery contract. ## Consequences -The Service Definition, JSONL provider, and metadata contract in `dsh-session` (`session.header`, the `create(id?, options?)` signature) buy durable resume/fork, a read/replay path, crash tolerance, and host-side session access over the existing event-sourced log. The reusable `runPersistenceContract` suite holds the provider and future implementations to the same append-only, contiguous-seq, lazy-materialization, logical-recovery, integer-metadata, and serializability semantics. Persisting the full logical log also settles event fidelity: every `assistant/chunk` survives exactly even when JSONL packs several into one storage row. +The Service Definition, JSONL provider, and metadata contract in `dsh-session` (`session.header`, the `create(id?, options?)` signature) buy durable resume/fork, a read/replay path, crash tolerance, and host-side session access over the existing event-sourced log. The reusable `runPersistenceContract` suite holds the provider and future implementations to the same append-only, contiguous-seq, lazy-materialization, logical-recovery, integer-metadata, and serializability semantics. Persisting the full logical log also settles event fidelity: every Assistant attempt retains its exact compact timed stream in one durable settlement. diff --git a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md index 9dcdbffc7d..2a4e809862 100644 --- a/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-14-session-persistence.zh.md @@ -15,11 +15,11 @@ Status: implemented 持久化是一个具有抽象 Service Definition 的**能力 seam**（[能力 seam](2026-06-13-capability-seams.zh.md)，`dsh-shell` 模板），而非循环或核心逻辑： 1. **接口**（`dsh-session-persistence`，`ctx.sessionPersistence`）：一个抽象的 `SessionPersistence` 服务，提供 `locate`/`create`/`append`/`prepare`/`load`/`inspect`/`readFrom`/`list`/`listSnapshots`。其持久化单元就是现有的 `SessionEvent`（`{ type, seq, time, data }`），原样复用，无转换类型。 -2. **实现**（`dsh-session-persistence-jsonl`）：每个会话一个仅追加的逻辑 JSONL 日志：先是一行 `SessionHeader`，随后是无损表示连续 `SessionEvent` 流的存储记录。符合条件的 `assistant/chunk` 增量连续段默认使用打包行；[带校验和的 Zstandard 帧](2026-07-19-zstandard-jsonl-session-logs.zh.md)是默认物理编码，也可通过配置使用原始行。 +2. **实现**（`dsh-session-persistence-jsonl`）：每个会话一个仅追加的逻辑 JSONL 日志：先是一行 `SessionHeader`，随后是无损表示连续 `SessionEvent` 流的存储记录。当前 v2 每行写入一个事件；冻结的 v0 与 v1 读取器保留其历史 packed-delta 表示。[带校验和的 Zstandard 帧](2026-07-19-zstandard-jsonl-session-logs.zh.md)是默认物理编码，也可通过配置使用原始行。 长期有效、存在争议的关键选择： -- **规范的持久日志无损保留每个 `SessionEvent`，包括 `assistant/chunk`。** JSONL 存储可以将一段连续的增量事件编码为一条打包行，但逻辑读取方会重建精确的事件边界、序号与时间戳。`deriveMessages()` 跳过分片，而过滤分片的方案（Codex 的 `policy.rs`）很有吸引力，但 `seq = log.length` 以及 `events[i].seq === i` 验证要求*连续*的逻辑日志；过滤掉分片会留下空洞，同时破坏约定和恢复功能。基于分片过滤的投影可以作为派生视图在后续实现（带有自己的重新编号），但它不是规范日志。 +- **规范持久日志无损保留每个当前 `SessionEvent`。** 在 v2 中，一个 `assistant/message` 或 `assistant/attempt` 会嵌入一次 attempt 的精确带时间 provider stream；`deriveMessages()` 只投影 surface message。丢弃嵌入式 stream 成员很有吸引力，但会丢失 replay、时间、usage、部分失败与诊断事实。移除完整事件同样需要密集重编号，因为 `seq = log.length` 且 `events[i].seq === i`；[v1 到 v2 迁移](2026-09-01-v2-embedded-assistant-streams.zh.md)会显式执行该重写，而不是过滤规范日志。 - **普通写入仅追加；崩溃的轮次被关闭，而非截断。** 正常持久化绝不重写已刷入当前 generation 的事件。格式迁移保持精确物理源路径、字节与 inode 不变，再只经过迁移边拥有的归一化与当前崩溃修复，在此前不存在的规范具名版本文件下发布一个重新编码的当前后继。[语义检查点策略](../bug-fix/2026-07-21-semantic-session-checkpoints.zh.md)会在调用模型前排空请求、在调用工具前排空已记录的顶层调用，并在步骤结束后排空完整的响应/结果批次；循环则排空最终轮次边界。由于一个被中断的轮次可能包含大量有效工作，冷检查会保留其连续、可解析的事件，并在内存逻辑视图中为未应答的 assistant 调用添加按风险分类的错误结果、补一个缺失的 `step/end`，以及带 `{ kind: 'interrupted' }` 的 `turn/end`。`prepare` 或 `load` 在返回可恢复视图前提交这些收尾事件；合成结果保证恢复后的提供方 transcript（文本记录）仍然有效。只有不完整的最后一条记录会在提交修复时被丢弃；在最后一个真实 `turn/end` 处或之前出现解析错误或序号间隙，属于数据损坏，会使该会话不可加载。 - **文件后端为规范实现，服务保持可扩展。** `dsh-session-persistence-jsonl` 是唯一 first-party provider，并通过 `runPersistenceContract`；抽象服务与 coordinator 继续供仓库外 provider 使用。[JSONL-only 持久化决策](../simplification/2026-08-30-jsonl-only-session-persistence.zh.md)负责 first-party 数据库 provider 的删除及其明确 compatibility cut。 - **元数据在日志之外。** 格式版本、cwd 和谱系是存储关注点，不是可回放的对话状态，因此它们存放在 `dsh-session` 拥有的 `SessionHeader` 中，并通过新的只读属性 `session.header` 附加到 `Session` 上——永远不进入 `SessionEventMap`，永远不到达 `deriveMessages()`。`createdAt` 是以 Unix epoch 毫秒表示的非负安全整数：运行时创建和持久化注册会拒绝小数值，JSONL 会验证解码后的 header。替代方案（一个可合并扩展的 `session/meta` 事件作为日志第 0 行）被否决：日志内事件会自然随 seed/fork 的会话携带，但元数据不是可回放状态，因此显式的日志外 header 边界是更清晰的取舍。（header 最初被拆分为不可变的 `SessionHeader` 加可变的 `SessionSummary`，二者的联合类型为 `SessionMeta`；可变 summary 后来因属于死状态而被移除——见 [移除可变会话摘要](../simplification/2026-06-19-drop-mutable-session-summary.zh.md)。） @@ -27,10 +27,10 @@ Status: implemented ## 曾考虑的替代方案 -上述每个关键选择都在陈述处记录了被否决的替代方案：**过滤分片的规范日志**（Codex 的 `policy.rs` 形式）破坏连续 seq 约定；**截断崩溃的轮次**会静默销毁长时间自主运行中的真实工作；**日志内 `session/meta` 事件作为第 0 行**——元数据不是可回放状态；**有限的非整数 `createdAt` 值**没有生产方，且与整数 Unix 毫秒存储不一致；**将 `sessionPersistence` 硬注入循环**会让非持久化的演示永远挂起。 +上述每个关键选择都在陈述处记录了被否决的替代方案：**过滤 stream 的规范日志**会丢失 attempt 证据，而未通过显式迁移移除事件会破坏连续序号；**截断崩溃的轮次**会静默销毁长时间自主运行中的真实工作；**日志内 `session/meta` 事件作为第 0 行**——元数据不是可回放状态；**有限的非整数 `createdAt` 值**没有生产方，且与整数 Unix 毫秒存储不一致；**将 `sessionPersistence` 硬注入循环**会让非持久化的演示永远挂起。 -格式版本控制：header 携带一个 `version`；当前 Session 与协调器代码只接受 `SESSION_FORMAT_VERSION = 1`。JSONL 的事件正文读取会在构造 Session 前组合静态相邻迁移链，v0-to-v1 边拥有原有的范围受限导入升级，例如[消息标识机制引入前的消息恢复](../bug-fix/2026-07-28-load-pre-identity-session-messages.zh.md)。V0 保留在无后缀 `session.jsonl[.zstd]`，v1 及后续版本使用不可变的小写 `session.vN.jsonl[.zstd]` 名称（[已发布 Session 迁移](2026-08-31-released-session-format-migrations.zh.md)）。当前 generation 的追加与 flush 能承受冷准备时可容忍的尾部不完整写入；未来 provider 或 write-ahead log 需要自有的断电与恢复约定。 +格式版本控制：header 携带一个 `version`；当前 Session 与 coordinator 代码只接受 `SESSION_FORMAT_VERSION = 2`。JSONL 事件正文读取会在构造 Session 前组合静态 v0-to-v1 与 v1-to-v2 相邻迁移链；第一条迁移边拥有有界旧格式规范化，第二条拥有 Assistant stream 嵌入与密集引用重映射。V0 保留在无后缀 `session.jsonl[.zstd]`，正版本使用不可变的小写 `session.vN.jsonl[.zstd]` 名称（[已发布 Session 迁移](2026-08-31-released-session-format-migrations.zh.md)）。当前 generation 的追加与 flush 能承受冷准备时可容忍的尾部不完整写入；未来 provider 或 write-ahead log 需要自有的断电与恢复约定。 ## 后果 -Service Definition、JSONL provider 与 `dsh-session` 中的元数据约定（`session.header`，`create(id?, options?)` 签名）带来持久恢复/fork、读取/回放路径、崩溃容忍，以及基于现有事件溯源日志的宿主侧会话访问。可复用的 `runPersistenceContract` 测试套件以相同的仅追加、连续 seq、惰性物化、逻辑恢复、整数元数据与可序列化语义约束该 provider 与未来实现。持久化完整的逻辑日志还确定了事件保真度：即使 JSONL 将多个 `assistant/chunk` 打包到一条存储行中，每个事件也会精确保留。 +Service Definition、JSONL provider 与 `dsh-session` 中的元数据约定（`session.header`，`create(id?, options?)` 签名）带来持久恢复/fork、读取/replay 路径、崩溃容忍，以及基于现有事件溯源日志的宿主侧 Session 访问。可复用 `runPersistenceContract` 测试套件以相同的仅追加、连续 seq、惰性物化、逻辑恢复、整数元数据与可序列化语义约束该 provider 与未来实现。持久化完整逻辑日志也确定了事件保真度：每个 Assistant attempt 都在一个持久 settlement 中保留其精确紧凑带时间 stream。 diff --git a/.agents/notes/implemented/architecture/2026-06-18-session-surface.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-18-session-surface.i18n.yaml index 1a123eb416..ed7ac8f6d5 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-session-surface.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-18-session-surface.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/2026-06-18-session-surface.md -2026-06-18-session-surface.md: e9331ca2f827edd291d6365ef1356520c8f1927a -2026-06-18-session-surface.zh.md: 26b58afe6aec3a192da94b2c29d4ec0c95d88a6b +2026-06-18-session-surface.md: 0139cc4beba766e4e8b936594899649304234eaa +2026-06-18-session-surface.zh.md: 0596d2a0425890924276265dd9cc6c32fcffb974 diff --git a/.agents/notes/implemented/architecture/2026-06-18-session-surface.md b/.agents/notes/implemented/architecture/2026-06-18-session-surface.md index e9331ca2f8..0139cc4beb 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-session-surface.md +++ b/.agents/notes/implemented/architecture/2026-06-18-session-surface.md @@ -16,7 +16,7 @@ Add a **surface** — a derived, cached order of event sequences (the subset of Every `SessionEvent` gains two optional fields (structural metadata, like `seq`/`time`): -- **`sourceEventSeqs?: number[]`** — seq numbers of earlier events cited as sources (e.g., the `assistant/chunk` seqs that built an `assistant/message`, or the surface nodes shadowed by a compaction marker). A present `[]` is valid only on `assistant/message` and records a known empty provider stream; when the field is absent, a legacy or foreign event does not record which earlier events produced the message. Other surface events require a non-empty list when the field is present. Without these cited seqs, replay cannot validate that a replace-range operation names every event it removed. +- **`sourceEventSeqs?: number[]`** — seq numbers of earlier events cited as sources, such as a `tool/call` cited by its result or surface nodes shadowed by a compaction marker. A present list is non-empty, unique, earlier, and known. V2 `assistant/message` embeds its provider stream and cannot carry this field. Without cited seqs, replay cannot validate that a replace-range operation names every event it removed. - **`surfaceOp?: SurfaceOp`** — how this event entered the surface. Absent for non-surface events. ### SurfaceOp: two operations @@ -27,7 +27,7 @@ export type SurfaceOp = | { op: 'replace'; start: number; end: number } // shadow [start, end] inclusive ``` -1. **Append** — add the new event seq to the tail. Used by `user/message`, `assistant/message`, `tool/result`, `context/message`. The loop passes `surfaceOp: 'append'` on all such appends and records `sourceEventSeqs` where applicable: every successful `assistant/message` records its complete `assistant/chunk` source set, including `[]`, while `tool/result` records its `tool/call` source. +1. **Append** — add the new event seq to the tail. Used by `user/message`, `assistant/message`, `tool/result`, `context/message`. The loop passes `surfaceOp: 'append'` on all such appends and records `sourceEventSeqs` where applicable: `tool/result` records its `tool/call` source, while `assistant/message` owns its embedded stream directly. 2. **Replace** — remove entries from `start` through `end` (both inclusive) and insert the new event seq in their place. Both `start` and `end` must be present in the current surface; `start === end` replaces one entry. The event's `sourceEventSeqs` must contain every shadowed surface seq. The shadowed events remain in the log but are no longer on the surface. @@ -49,7 +49,7 @@ The `repair.ts` module synthesizes `tool/result` closers for orphaned tool calls ### Invariants -`Session` validates `sourceEventSeqs` and `surfaceOp` at the always-on seed/append boundary: only `assistant/message` may use an empty source-event list; references are unique, earlier, and known; replacement endpoints exist in surface order; and `sourceEventSeqs` covers every shadowed node. These are single-record acceptance and storage-projection rules, not optional invariant-service contributions. +`Session` validates `sourceEventSeqs` and `surfaceOp` at the always-on seed/append boundary: source lists are non-empty, unique, earlier, and known; `assistant/message` carries no source list; replacement endpoints exist in surface order; and `sourceEventSeqs` covers every shadowed node. These are single-record acceptance and storage-projection rules, not optional invariant-service contributions. Every surface-eligible event must carry `surfaceOp` or it would disappear from derived history. Typed `append` overloads enforce this for literal event types; runtime checks in `append` and the seed constructor cover widened unions and current loaded logs. Historical v0 validation and normalization belong to the v0-to-v1 edge rather than generic Session code. diff --git a/.agents/notes/implemented/architecture/2026-06-18-session-surface.zh.md b/.agents/notes/implemented/architecture/2026-06-18-session-surface.zh.md index 26b58afe6a..0596d2a042 100644 --- a/.agents/notes/implemented/architecture/2026-06-18-session-surface.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-18-session-surface.zh.md @@ -16,7 +16,7 @@ Status: implemented 每个 `SessionEvent` 获得两个可选字段（结构性元数据，与 `seq`/`time` 同级）： -- **`sourceEventSeqs?: number[]`**：被引用为数据来源的早期事件 seq 编号（例如构成 `assistant/message` 的各 `assistant/chunk` 的 seq，或被压缩标记遮蔽的 surface 节点）。出现的 `[]` 只在 `assistant/message` 上有效，表示已知为空的提供方流；旧格式或外部事件缺少该字段时，没有记录这条消息由哪些早期事件产生。其他 surface 事件一旦出现此字段，就必须是非空列表。如果没有这些引用的 seq，回放就无法验证 replace-range 操作是否列出了它移除的每个事件。 +- **`sourceEventSeqs?: number[]`**：被引用为数据来源的早期事件 seq 编号，例如 result 引用的 `tool/call`，或被 compaction marker 遮蔽的 surface 节点。出现的列表必须非空、唯一、更早且已知。V2 `assistant/message` 嵌入其 provider stream，不能携带该字段。如果没有这些引用的 seq，回放就无法验证 replace-range 操作是否列出了它移除的每个事件。 - **`surfaceOp?: SurfaceOp`**：该事件如何进入 surface。非 surface 事件不携带此字段。 ### SurfaceOp：两种操作 @@ -27,7 +27,7 @@ export type SurfaceOp = | { op: 'replace'; start: number; end: number } // shadow [start, end] inclusive ``` -1. **Append**：在尾部追加新事件的 seq。`user/message`、`assistant/message`、`tool/result`、`context/message` 使用此操作。agent loop（智能体循环）在所有此类追加上传入 `surfaceOp: 'append'`，并在适用时记录 `sourceEventSeqs`：每个成功的 `assistant/message` 都记录完整的 `assistant/chunk` 来源集合（包括 `[]`），而 `tool/result` 记录其 `tool/call` 来源。 +1. **Append**：在尾部追加新事件的 seq。`user/message`、`assistant/message`、`tool/result`、`context/message` 使用此操作。agent loop（智能体循环）在所有此类追加上传入 `surfaceOp: 'append'`，并在适用时记录 `sourceEventSeqs`：`tool/result` 记录其 `tool/call` 来源，`assistant/message` 则直接拥有其嵌入式 stream。 2. **Replace**：移除从 `start` 到 `end`（两端包含）的条目，并在其位置插入新事件的 seq。`start` 和 `end` 都必须存在于当前 surface；`start === end` 表示替换单个条目。该事件的 `sourceEventSeqs` 必须包含所有被遮蔽的 surface seq。被遮蔽的事件仍留在日志中，但不再出现在 surface 上。 @@ -49,7 +49,7 @@ export type SurfaceOp = ### 不变式 -`Session` 在始终启用的 seed/append 边界校验 `sourceEventSeqs` 与 `surfaceOp`：只有 `assistant/message` 可以使用空的源事件列表；引用必须唯一、更早且已知；替换端点必须存在于 surface 顺序中；`sourceEventSeqs` 必须覆盖每个被遮蔽的节点。这些是单记录接纳与存储投影规则，不是由可选的不变式服务提供的规则。 +`Session` 在始终启用的 seed/append 边界校验 `sourceEventSeqs` 与 `surfaceOp`：source list 必须非空、唯一、更早且已知；`assistant/message` 不携带 source list；replacement endpoint 必须存在于 surface 顺序中；`sourceEventSeqs` 必须覆盖每个被遮蔽的节点。这些是单记录接纳与存储投影规则，不是由可选 invariant service 提供的规则。 每个可进入 surface 的事件都必须携带 `surfaceOp`，否则它将从派生历史中消失。类型化的 `append` 重载对字面事件类型强制执行此规则；`append` 和种子构造函数中的运行时检查覆盖宽化联合类型和当前已加载日志。历史 v0 的校验与规范化属于 v0-to-v1 边，而不属于通用 Session 代码。 diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml index a0af3cb0e6..670e4f18e9 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.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/2026-06-21-bounded-llm-request-recovery.md -2026-06-21-bounded-llm-request-recovery.md: 42bf460e52133b2a5471479fa3d7647e70092b48 -2026-06-21-bounded-llm-request-recovery.zh.md: 2a13f0a740348a5f74bd3d90120a148b25f2e870 +2026-06-21-bounded-llm-request-recovery.md: 6ae3915462c00eadcc550c80165fab7247a9170c +2026-06-21-bounded-llm-request-recovery.zh.md: 82e2e783fffaedcb5bfaabe72f56f7c4176d3784 diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md index 42bf460e52..6ae3915462 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.md @@ -10,7 +10,7 @@ The [per-provider request retry policy](../feature/2026-07-24-provider-retry-pol Provider adapters can fail by throwing during dispatch or iteration or by ending with `finish { kind: 'error' | 'aborted' }`. The final adapter boundary normalizes thrown values to that terminal finish protocol before `dsh-agent-loop` receives them; middleware and result-processing defects remain thrown. The loop offers a terminal model-request failure to `agent/request-error`. An unhandled failure is terminal; a handling listener repairs policy-owned state, returns `{ kind: 'retry' }`, and stops waterfall delegation. The [retry-action decision](../simplification/2026-07-27-request-error-retry-action.md) owns this return contract. -That boundary is already safe for another request attempt. Raw `assistant/chunk` events carry the failed `turn` and `step`, message derivation ignores them unless a successful `assistant/message` cites them, tool calls are dispatched only after a successful terminal finish and assembly, and a retry reconstructs its next attempt from the durable log. The harness therefore does not need a second response lifecycle or tentative-output protocol to keep two attempts separate. +That boundary is already safe for another request attempt. Each failed stream commits one log-only `assistant/attempt` with its exact compact stream, message derivation ignores it, tool calls are dispatched only after a successful terminal finish and assembled `assistant/message`, and a retry reconstructs its next attempt from the durable surface. The harness therefore does not need a second response lifecycle or tentative-output protocol to keep two attempts separate. The prior boundary left three narrower gaps. @@ -38,7 +38,7 @@ interface LlmFailure { } ``` -`code` remains the provider-neutral machine-routing taxonomy established by `HarnessError`; the new fields are observations from the provider boundary. `ProviderRequestId` is owned and constructed by `dsh-llm`, then serializes as its provider-issued string. The payload deliberately has no `retryable`, `failover`, `partialOutput`, provider, model, phase, or route id fields. Retryability belongs to policy, provider/model are already in the durable request header, and partial output is derived from the failed step's `assistant/chunk` events. +`code` remains the provider-neutral machine-routing taxonomy established by `HarnessError`; the new fields are observations from the provider boundary. `ProviderRequestId` is owned and constructed by `dsh-llm`, then serializes as its provider-issued string. The payload deliberately has no `retryable`, `failover`, `partialOutput`, provider, model, phase, or route id fields. Retryability belongs to policy, provider/model are already in the durable request header, and partial output is preserved by the failed attempt's embedded stream. `LlmError` carries `failure: LlmFailure` and preserves `failure.code === error.code`. `FinishReasonMap.error` and `FinishReasonMap.aborted` carry the same payload instead of parallel failure shapes. The final adapter boundary detaches those facts from adapter-thrown values and emits the appropriate terminal finish; unknown SDK exceptions receive an `UNKNOWN` payload. Exact thrown-object identity does not cross the LLM stream seam. @@ -82,7 +82,7 @@ Boundary tests prove termination at both actual transports. The hand-written ada ### Keep attempts separate in the existing log -A failed attempt may leave `assistant/chunk` events in its step, but it never appends `assistant/message` and never dispatches a tool. A retry continues inside the failing turn and step, reconstructs the request from the durable surface, and produces its own chunks; only the final outcome closes the turn. UIs may render live chunks while a step is open, then mark or clear that transient view when `llm/retry` identifies the failed attempt or `turn/end` records failure. Web validates the complete retry payload contract, clears the failed partial at `llm/retry`, projects each producer-correlated `retryId` chain into one stable row updated to the latest attempt, and derives scheduled, started, or cancelled status from `llm/retry-started` and the owning turn and step boundaries' closure. Its countdown anchors the scheduled delay to browser receipt rather than the Host event clock, uses ceiling-rounded seconds with a one-second floor, animates only while unresolved, and keeps exact latest failure details collapsed behind the row. Retry nodes anchor their own trajectory turn even when the failed attempt has no assistant node. Message derivation continues to ignore the failed chunks, and Web applies the same projection during history rebuild so refreshing cannot resurrect discarded partials or duplicate retry rows. +A failed attempt appends `assistant/attempt` with its embedded stream, but never appends a surface `assistant/message` or dispatches a tool. A retry continues inside the failing turn and step, reconstructs the request from the durable surface, and produces its own settlement; only the final outcome closes the turn. UIs may render transient `assistant/live-chunk` updates while a step is open, then settle the failed attempt when `llm/retry` identifies it or `turn/end` records failure. Web validates the complete retry payload contract, projects each producer-correlated `retryId` chain into one stable row updated to the latest attempt, and derives scheduled, started, or cancelled status from `llm/retry-started` and the owning turn and step boundaries' closure. Its countdown anchors the scheduled delay to browser receipt rather than the Host event clock, uses ceiling-rounded seconds with a one-second floor, animates only while unresolved, and keeps exact latest failure details collapsed behind the row. Retry nodes anchor their own trajectory turn even when the failed attempt has no surface Assistant node. Message derivation ignores `assistant/attempt`, and Web applies the same projection during history rebuild so refreshing cannot promote failed partials into model history or duplicate retry rows. If recovery is exhausted, the final failure is stored once on `turn/end.reason` with the structured facts. Web derives one `turn-error` node at that sequence position and renders its display-safe message and optional code inline; AUTH projections replace provider copy that may echo credential fragments with `API key is invalid`, while the raw diagnostic remains in the session log. The same fold runs for live events and history replay. While transient recovery continues, `llm/retry` is the durable home for each intermediate failure and delay; the terminal row exists only once `turn/end` records the error, and because exhausted recovery shares the failing turn, the turn's retry history never suppresses that row — the settled retry chain and the terminal error render side by side. No standalone final-error event or response-id vocabulary is added. diff --git a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md index 2a13f0a740..82e2e783ff 100644 --- a/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-21-bounded-llm-request-recovery.zh.md @@ -10,7 +10,7 @@ Status: implemented 提供方适配器可能在分发或迭代时抛出异常，也可能以 `finish { kind: 'error' | 'aborted' }` 结束。最终适配器边界会在 `dsh-agent-loop` 接收前把抛出值规范化为该终止 finish 协议；middleware 与结果处理缺陷仍会抛出。loop 会将终止模型请求失败交给 `agent/request-error`。未被处理的失败是终态；处理失败的监听器修复策略自有状态，返回 `{ kind: 'retry' }`，并停止 waterfall（瀑布式事件）委托。[重试动作决策](../simplification/2026-07-27-request-error-retry-action.zh.md)规定这一返回约定。 -该边界已能安全地再次发起请求。原始 `assistant/chunk` 事件携带失败的 `turn` 和 `step`；除非某条成功的 `assistant/message` 引用这些事件，否则消息派生会忽略它们。只有终止性 finish 成功且组装完成后，系统才会分发工具调用；重试则会从持久日志重建下一次尝试。因此，harness 无需引入第二套响应生命周期或暂定输出协议，即可分隔两次尝试。 +该边界已能安全地再次发起请求。每个失败 stream 会提交一个包含精确紧凑 stream 的仅日志 `assistant/attempt`，message derivation 会忽略它；系统只会在 terminal finish 成功并组装 `assistant/message` 后分派工具调用，重试则从持久 surface 重建下一次 attempt。因此，harness 无需引入第二套响应生命周期或暂定输出协议，即可分隔两次 attempt。 此前的边界还留有三个较窄的缺口。 @@ -38,7 +38,7 @@ interface LlmFailure { } ``` -`code` 仍是 `HarnessError` 建立的提供方无关机器路由分类体系；新字段是在提供方边界观测到的事实。`ProviderRequestId` 由 `dsh-llm` 拥有并构造，序列化后为提供方发放的字符串。该载荷有意不包含 `retryable`、`failover`、`partialOutput`、提供方、模型、阶段或路由 id 字段。是否可重试属于策略，提供方／模型已位于持久请求头中，部分输出则从失败步骤的 `assistant/chunk` 事件派生。 +`code` 仍是 `HarnessError` 建立的 provider-neutral 机器路由分类；新字段是在 provider 边界观测到的事实。`ProviderRequestId` 由 `dsh-llm` 拥有并构造，序列化后是 provider 发放的字符串。该 payload 有意不包含 `retryable`、`failover`、`partialOutput`、provider、model、phase 或 route id。是否可重试属于 policy，provider/model 已位于持久 request header 中，部分输出由失败 attempt 的嵌入式 stream 保留。 `LlmError` 携带 `failure: LlmFailure`，并保持 `failure.code === error.code`。`FinishReasonMap.error` 和 `FinishReasonMap.aborted` 携带同一载荷，而不是并行的失败形状。最终适配器边界会从适配器抛出值中分离这些事实，并发出相应的终止 finish；未知 SDK 异常会获得 `UNKNOWN` 载荷。精确的抛出对象身份不会跨越 LLM 流 seam。 @@ -82,7 +82,7 @@ agent loop（智能体循环）会将终止 finish 的 `LlmFailure` 传给 `agen ### 在现有日志中分隔尝试 -一次失败尝试可以在其步骤中留下 `assistant/chunk` 事件，但绝不会追加 `assistant/message`，也不会分发工具。重试在失败的轮次与步骤内继续，从持久表层重建请求，并生成自己的分片；只有最终结果才会关闭该轮次。步骤仍处于打开状态时，UI 可以渲染实时分片；当 `llm/retry` 标识失败尝试，或 `turn/end` 记录失败时，UI 再标记或清除这份暂时视图。Web 会验证完整的重试载荷约定，在 `llm/retry` 到达时清除失败的部分输出，将每条生产方关联的 `retryId` 重试链投影为稳定的一行，并用最新一次尝试更新该行，再从 `llm/retry-started` 与所属轮次、步骤边界的关闭派生 scheduled、started 或 cancelled 状态。倒计时以浏览器收到事件的时刻为计划延迟的起点，而不是使用 Host 事件时钟；它按向上取整且不低于 1 秒的秒数显示，仅在重试尚未结束时显示动画，并把最近一次失败的准确详情折叠在该行之后。即使失败尝试没有 assistant 节点，重试节点也会锚定自身的轨迹轮次。消息派生仍会忽略失败分片；Web 在重建历史时也会应用同一投影，因此刷新页面不会让已丢弃的部分输出重新出现，也不会生成重复的重试行。 +失败 attempt 会追加带嵌入式 stream 的 `assistant/attempt`，但绝不追加 surface `assistant/message` 或分派工具。重试在失败 turn 与 step 内继续，从持久 surface 重建请求，并产生自己的 settlement；只有最终结果才会关闭 turn。step 打开时，UI 可以渲染瞬态 `assistant/live-chunk` update；当 `llm/retry` 标识失败 attempt 或 `turn/end` 记录失败时，UI 再结算它。Web 会校验完整 retry payload contract，把每条 producer-correlated `retryId` chain 投影为稳定一行并更新到最新 attempt，再从 `llm/retry-started` 与所属 turn、step boundary 的关闭派生 scheduled、started 或 cancelled 状态。倒计时以浏览器收到 event 的时刻为计划延迟起点，而不是 Host event clock；它按向上取整且不低于 1 秒的秒数显示，只在未结算时动画，并把最新失败详情折叠在该行后。即使失败 attempt 没有 surface Assistant node，retry node 也会锚定自己的 trajectory turn。Message derivation 会忽略 `assistant/attempt`，Web 在历史重建时应用同一投影，因此刷新不会把失败 partial 提升进模型历史，也不会生成重复 retry row。 如果恢复预算耗尽，最终失败会连同结构化事实在 `turn/end.reason` 中存储一次。Web 会在该序列位置派生一个 `turn-error` 节点，并内联渲染适合展示的消息与可选错误码；AUTH 投影会把可能回显凭据片段的提供方文案替换为 `API key is invalid`，原始诊断仍保留在会话日志中。实时事件和历史回放使用同一套折叠逻辑。暂时性恢复继续期间，`llm/retry` 是每次中间失败与延迟的持久归属位置；终态错误行只在 `turn/end` 记录错误后才存在，而由于耗尽的恢复与失败共享同一轮次，该轮次的重试历史绝不会抑制这一行——定格的重试链与终态错误并列渲染。本决策不增加独立的最终错误事件或响应 id 词汇。 diff --git a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml index feb512101f..94a99ad44f 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.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/2026-06-30-event-domain-semantics.md -2026-06-30-event-domain-semantics.md: 70da718b5471ce309a090c8aade3e7290cc949dc -2026-06-30-event-domain-semantics.zh.md: c3b12a167da0a41b792914d82a675a98b3a0b860 +2026-06-30-event-domain-semantics.md: f3e4686a1e9e14c9284de5a4bff16501c50aa907 +2026-06-30-event-domain-semantics.zh.md: f4bc92111666b0c30586222e14ee1aeab49ebb3f diff --git a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md index 70da718b54..f3e4686a1e 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md +++ b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.md @@ -21,7 +21,7 @@ This vocabulary is the foundation for interception decisions, the durable `hook/ **Three domains, one job each, with a single boundary rule.** - **`session/*` — the durable, replayable FACT log.** Owns `SessionEventMap`; every entry is JSON-only (no live objects). One `session/event` emit per append, plus the `session/flush` parallel durability checkpoint. It is also the live transcript feed: a consumer that wants to render or react to what happened subscribes here, so live rendering and replay projections share one path. -- **`agent/*` — the LIVE runtime surface.** Always carries the live `Agent`. Interception waterfalls (`agent/pre-step`, `agent/request`, `agent/request-error`) transform, reject, or recover; awaited `agent/turn-stopping` observes the stop boundary; transient emits report lifecycle, status, inbox insertion/claim/discard, and errors. Turn and step BOUNDARIES are NOT here — they are durable session events read off `session/event`, as are the token stream (`assistant/chunk`) and mid-turn steering (a `user/message`). +- **`agent/*` — the LIVE runtime surface.** Always carries the live `Agent`. Interception waterfalls (`agent/pre-step`, `agent/request`, `agent/request-error`) transform, reject, or recover; awaited `agent/turn-stopping` observes the stop boundary; transient emits report lifecycle, status, inbox insertion/claim/discard, errors, and process-local `agent/assistant-stream` frames. Turn and step BOUNDARIES are NOT here — they are durable session events read off `session/event`; Assistant stream evidence becomes durable only inside one `assistant/message` or `assistant/attempt` settlement, and mid-turn steering is a durable `user/message`. - **`tools/*` — the tool registry and execution pipeline.** **The boundary rule:** a durable, replayable fact is a `SessionEvent`; a live interception or a transient/live-object signal is an `agent`/`tools` Cordis event. A turn or step boundary is a durable fact, so it lives in the session log and is read off the `session/event` feed — it is NOT mirrored as an `agent/*` emit. diff --git a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md index c3b12a167d..f4bc921116 100644 --- a/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md +++ b/.agents/notes/implemented/architecture/2026-06-30-event-domain-semantics.zh.md @@ -21,7 +21,7 @@ harness 通过 Cordis 事件分类体系扩展 agent loop（智能体循环） **三个域，各司其职，以一条边界规则统一。** - **`session/*`——持久的、可回放的事实日志。** 拥有 `SessionEventMap`；每条记录仅含 JSON（无活对象）。每次追加触发一次 `session/event` emit，加上 `session/flush` 并行持久性检查点。它同时也是实时 transcript（文本记录）源：想渲染或响应已发生事件的消费方在此订阅，因此实时渲染与回放投影共享同一路径。 -- **`agent/*`——运行时实时表面。** 始终携带活的 `Agent`。拦截 waterfall（瀑布式事件）（`agent/pre-step`、`agent/request`、`agent/request-error`）负责变换、拒绝或恢复；awaited `agent/turn-stopping` 观察停止边界；瞬态 emit 报告生命周期、状态、inbox 的插入、领取和丢弃，以及错误。轮次和步骤边界不在此处——它们是持久的会话事件，从 `session/event` 读取；token 流（`assistant/chunk`）和轮次中途以 `user/message` 呈现的 steering（中途引导）同理。 +- **`agent/*`——运行时实时表面。** 始终携带活的 `Agent`。拦截 waterfall（瀑布式事件）（`agent/pre-step`、`agent/request`、`agent/request-error`）负责变换、拒绝或恢复；awaited `agent/turn-stopping` 观察停止边界；瞬态 emit 报告生命周期、状态、inbox 插入、领取与丢弃、错误，以及进程本地 `agent/assistant-stream` frame。轮次和步骤边界不在此处——它们是从 `session/event` 读取的持久 Session event；Assistant stream 证据只在一个 `assistant/message` 或 `assistant/attempt` settlement 内变为持久事实，轮次中途 steering 则是持久 `user/message`。 - **`tools/*`——工具注册表与执行流水线。** **边界规则：** 持久的、可回放的事实是 `SessionEvent`；实时拦截或瞬态/活对象信号是 `agent`/`tools` Cordis 事件。轮次或步骤边界是持久事实，因此存在于会话日志中并从 `session/event` 源读取——不会被镜像为 `agent/*` emit。 diff --git a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.i18n.yaml index 76348b2cb2..881bd5a13c 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.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/2026-07-19-zstandard-jsonl-session-logs.md -2026-07-19-zstandard-jsonl-session-logs.md: a79bc3907c4f6c02851ba1814f733684ce373898 -2026-07-19-zstandard-jsonl-session-logs.zh.md: 178420c126b68689983d5b01f4ffae29b17fe657 +2026-07-19-zstandard-jsonl-session-logs.md: 471419749ad65c811d0d1914e329f4d94597a54d +2026-07-19-zstandard-jsonl-session-logs.zh.md: 382ea5d5d8d80e7314f5a718dab6e2773fa3614f diff --git a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md index a79bc3907c..471419749a 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md +++ b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.md @@ -6,7 +6,7 @@ English | [中文](2026-07-19-zstandard-jsonl-session-logs.zh.md) ## Problem -The JSONL persistence backend keeps every `SessionEvent` verbatim, including high-volume `assistant/chunk` records. Raw text makes logs inspectable but spends storage and I/O on repeated JSON keys and model text. Compression must retain the existing append/fsync commit boundary, collision-safe first materialization, crash repair, and metadata-only listing; rewriting a whole compressed file after every turn would discard those properties. +The JSONL persistence backend keeps every `SessionEvent` verbatim, including Assistant settlements with embedded model streams. Raw text makes logs inspectable but spends storage and I/O on repeated JSON keys and model text. Compression must retain the existing append/fsync commit boundary, collision-safe first materialization, crash repair, and metadata-only listing; rewriting a whole compressed file after every turn would discard those properties. The encoding also has to remain explicit at the deployment boundary. Snapshot fixtures and external line readers require raw JSONL, while a backend cannot safely guess between compressed and raw artifacts in one root or silently migrate pre-release session data. diff --git a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.zh.md b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.zh.md index 178420c126..382ea5d5d8 100644 --- a/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-19-zstandard-jsonl-session-logs.zh.md @@ -6,7 +6,7 @@ Status: implemented ## 问题 -JSONL 持久化后端会逐字保留每个 `SessionEvent`，其中包括数量庞大的 `assistant/chunk` 记录。原始文本便于检查，但重复的 JSON 键和模型文本会增加存储与 I/O 开销。压缩编码必须保留既有的 append/fsync 提交边界、首次物化时的无冲突发布、崩溃修复以及仅元数据列举；如果每轮都重写整个压缩文件，就会失去这些属性。 +JSONL 持久化后端会逐字保留每个 `SessionEvent`，包括嵌入模型 stream 的 Assistant settlement。原始文本便于检查，但重复的 JSON key 和模型文本会增加存储与 I/O 开销。压缩编码必须保留既有 append/fsync 提交边界、首次物化时的无冲突发布、崩溃修复与仅元数据列举；如果每轮都重写整个压缩文件，就会失去这些属性。 编码还必须在部署边界上保持显式。快照 fixture（测试前置数据）与外部逐行读取器需要原始 JSONL，而后端无法在同一根目录中安全猜测压缩产物与原始产物，也不能静默迁移预发布会话数据。 diff --git a/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.i18n.yaml index 8baf8386d1..6c3733e600 100644 --- a/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.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/2026-07-29-projected-token-usage-and-request-context.md -2026-07-29-projected-token-usage-and-request-context.md: 75a05e5a0e8f0183fef1e7d80701ce6d81041cd6 -2026-07-29-projected-token-usage-and-request-context.zh.md: 7cce5989d719156f1d66c48937780ff8aed02a42 +2026-07-29-projected-token-usage-and-request-context.md: edcf80659a5456ae557a1591a7f290f5dac0c5f8 +2026-07-29-projected-token-usage-and-request-context.zh.md: 84ab782f23d08f6214767b17650a29d91885ce58 diff --git a/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.md b/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.md index 75a05e5a0e..edcf80659a 100644 --- a/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.md +++ b/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.md @@ -14,7 +14,7 @@ Context occupancy needs a numerator and a denominator that no existing surface c Both values are ordinary durable session-projection state. `@deepseek-ai/dsh-token-meter` registers two units when `ctx.sessionProjections` is present. -`tokenUsage` folds the complete durable log into uncached input, output, cache-read, and cache-write buckets. An `assistant/chunk` usage sample survives a later failed request; an `assistant/message` usage value replaces the earlier sample from the same model attempt instead of double-counting it. A matching `llm/retry-started` boundary ends that replacement scope, so a retry with the same `(turn, step)` contributes a new attempt. Reasoning stays an output subdivision. Compaction and surface replacement do not erase earlier billing. +`tokenUsage` folds the complete durable log into uncached input, output, cache-read, and cache-write buckets. It expands each `assistant/message` or `assistant/attempt` stream and takes the last usage sample; a message's top-level usage takes precedence over its embedded sample instead of double-counting it. `assistant/attempt` therefore preserves usage from failed requests. A matching `llm/retry-started` boundary opens a new attempt, so a retry with the same `(turn, step)` contributes separately. Reasoning stays an output subdivision. Compaction and surface replacement do not erase earlier billing. Token-meter also owns the shared pure attempt/Turn fold over durable events. It applies the same retry boundary while adding the stricter completeness and exact-total checks required by an exact per-Turn disclosure. A presentation consumer may select a complete Turn window and invoke that fold, but does not own or duplicate the accounting semantics. diff --git a/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.zh.md b/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.zh.md index 7cce5989d7..84ab782f23 100644 --- a/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-29-projected-token-usage-and-request-context.zh.md @@ -14,7 +14,7 @@ Web 统计行原先从当前已加载的会话节点推导 token 总量。该窗 这两个值都是普通的持久会话投影状态。当 `ctx.sessionProjections` 存在时，`@deepseek-ai/dsh-token-meter` 会注册两个单元。 -`tokenUsage` 将完整持久日志归并为未缓存输入、输出、缓存读取和缓存写入四类计数项。即使后续请求失败，`assistant/chunk` 用量样本仍会保留；`assistant/message` 用量值会替换同一次模型 attempt 的先前样本，不会重复计数。匹配的 `llm/retry-started` 边界会结束该替换作用域，因此复用同一 `(turn, step)` 的重试会贡献一次新的 attempt。推理（reasoning）仍是输出的细分项。压缩和表层替换不会抹除先前的计费用量。 +`tokenUsage` 将完整持久日志归并为未缓存输入、输出、缓存读取和缓存写入四类计数项。它会展开每个 `assistant/message` 或 `assistant/attempt` stream 并采用最后一个 usage sample；message 顶层 usage 优先于其嵌入式 sample，因此不会重复计数。`assistant/attempt` 由此保留失败请求的 usage。匹配的 `llm/retry-started` 边界会打开新 attempt，因此复用同一 `(turn, step)` 的重试会单独贡献用量。推理（reasoning）仍是输出的细分项。compaction 和 surface replacement 不会抹除先前计费。 token-meter 还拥有在持久事件上运行的共享纯 attempt／Turn fold。它采用相同的重试边界，并增加精确单轮次 disclosure 所需的更严格完整性与精确总量检查。展示消费方可以选择完整 Turn 窗口并调用该 fold，但不拥有或复制记账语义。 diff --git a/.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.i18n.yaml index 18313964ec..3d54f62991 100644 --- a/.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.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/2026-08-05-large-session-jsonl-restore-pipeline.md -2026-08-05-large-session-jsonl-restore-pipeline.md: 309d9dc6bdb5c3160f3e6e76a8318915df58fe59 -2026-08-05-large-session-jsonl-restore-pipeline.zh.md: 28acd3ebe804dca22a0619c257ff3ad9c09500a9 +2026-08-05-large-session-jsonl-restore-pipeline.md: e87777cc407e50a0e4808b77c3a7d554659d62e7 +2026-08-05-large-session-jsonl-restore-pipeline.zh.md: 32762bd19914423ef38c6472f0a8087e3e7e45fa diff --git a/.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.md b/.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.md index 309d9dc6bd..e87777cc40 100644 --- a/.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.md +++ b/.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.md @@ -30,7 +30,7 @@ The scanner stops retaining events at the first unparsable row or sequence gap b ### Restore admission -Persistence transfers freshly materialized JSON values to `Session.fromRestore`. These values are detached, acyclic trees, and packed chunk rows expand into newly allocated events, so the restore-only path validates the fixed event envelope with one `for...in` and `switch`, dispatches current-shape checks by event discriminant, and iteratively freezes the owned graph with an explicit `pending` array and no cycle-tracking set. Surface validation records one transition plan and commits that plan when the exact candidate enters the log instead of planning the same event twice. +Persistence transfers freshly materialized current JSON values to `Session.fromRestore`. These values are detached, acyclic trees; historical packed rows and adjacent migrations have already produced newly allocated v2 settlements. The restore-only path validates the fixed event envelope with one `for...in` and `switch`, dispatches current-shape checks by event discriminant, and iteratively freezes the owned graph with an explicit `pending` array and no cycle-tracking set. Surface validation records one transition plan and commits that plan when the exact candidate enters the log instead of planning the same event twice. Borrowed seeds used by ordinary creation and fork paths still take a JSON snapshot and use the generic cycle-safe deep freeze. The specialization therefore changes only durable restoration; it does not weaken acceptance for caller-owned values. diff --git a/.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.zh.md b/.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.zh.md index 28acd3ebe8..32762bd199 100644 --- a/.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-05-large-session-jsonl-restore-pipeline.zh.md @@ -30,7 +30,7 @@ Zstandard 结构扫描器会在解码前识别完整帧范围。系统单独解 ### 恢复准入 -持久化层把刚物化的 JSON 值转移给 `Session.fromRestore`。这些值是已分离且无环的树，打包的分片行也会展开成新分配的事件。因此，恢复专用路径使用一次 `for...in` 与 `switch` 校验固定事件信封，按事件判别字段执行当前数据形状检查，并通过显式 `pending` 数组迭代冻结所拥有的对象图，不使用循环跟踪集合。`surface` 校验会记录一次转换计划；当同一个候选事件进入日志时，系统直接提交该计划，不再对同一事件规划两次。 +持久化把刚物化的当前 JSON 值转移给 `Session.fromRestore`。这些值是已分离且无环的 tree；历史 packed row 与相邻 migration 已经生成新分配的 v2 settlement。restore-only path 使用一次 `for...in` 与 `switch` 校验固定 event envelope，按 event discriminant 执行当前表示检查，并通过显式 `pending` array 迭代冻结 owned object graph，不使用 cycle-tracking set。`surface` 校验记录一次 transition plan，并在同一个 candidate event 进入 log 时提交该 plan。 普通创建与 fork 路径使用的借用 `seed` 仍会创建 JSON 快照，并使用支持循环检测的通用深度冻结。因此，这项特化仅改变持久恢复，不会放宽调用方所有值的准入要求。 diff --git a/.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.i18n.yaml index 0ff8938b30..9f33dde503 100644 --- a/.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.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/2026-08-08-bounded-session-persistence-write-batching.md -2026-08-08-bounded-session-persistence-write-batching.md: 20c16991b0be30ffe546a94c257bc65f86cb57eb -2026-08-08-bounded-session-persistence-write-batching.zh.md: ac0384f4e28175922f84d23296dfb13848cf5dd3 +2026-08-08-bounded-session-persistence-write-batching.md: 97610093b9d80eded1d890f47f02b6b28bdd7f64 +2026-08-08-bounded-session-persistence-write-batching.zh.md: d076d5df3ba06021f73daa1a0d39b9f802cb7370 diff --git a/.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.md b/.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.md index 20c16991b0..97610093b9 100644 --- a/.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.md +++ b/.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.md @@ -6,13 +6,13 @@ English | [中文](2026-08-08-bounded-session-persistence-write-batching.zh.md) ## Problem -Streaming responses can emit many `assistant/chunk` events in a short interval. The persistence coordinator previously scheduled a provider append as soon as an idle queue received one event. Events arriving while that append was active shared a follow-up batch, but a fast provider could still produce many small durable appends. Each JSONL append creates and syncs a Zstandard frame or raw suffix. +One agent step can emit several durable events in a short interval: request metadata, one Assistant settlement, tool lifecycles, plugin facts, and execution boundaries. Scheduling a provider append as soon as an idle queue receives one event can therefore produce many small durable appends. Each JSONL append creates and syncs a Zstandard frame or raw suffix. -Dropping chunk events or replacing them with assembled messages would reduce logical storage, but it would also change the event log, replay, sequence numbers, timestamps, and the chunk seqs cited by assistant messages. The write-amplification problem does not require that larger semantic change. +Assistant stream embedding reduces one high-volume event family, but write cadence remains a provider-neutral lifecycle concern for every other burst and for historical generations. The batching decision does not change event semantics or storage encoding. ### Quantified baseline -Repository fixtures make the logical volume concrete. Decoding the current packed rows in [`goal-multi-turn-actions`](../../../../snapshots/web/goal-multi-turn-actions/session.jsonl) yields 2,098 events: 2,017 chunks (96.1%). Their unpacked JSONL lines occupy 332,647 of 379,225 event bytes (87.7%), while chunk packing reduces the committed file to 89,176 bytes and 182 storage rows, including 23 packed chunk rows. [`permission-policy-context`](../../../../snapshots/web/permission-policy-context/session.jsonl) yields 813 events: 746 chunks (91.8%) and 118,935 of 184,821 unpacked event bytes (64.4%); its packed file is 84,917 bytes and 123 storage rows, including 14 packed rows. These are tracked deterministic fixtures, not a production workload distribution, but they demonstrate why deleting chunks would reduce logical volume and why the existing packed-row layout already removes much of their JSON envelope cost. +Released-v1 repository fixtures established the original logical volume. Decoding the packed `goal-multi-turn-actions` generation yielded 2,098 events, including 2,017 chunks (96.1%); unpacked chunk lines occupied 332,647 of 379,225 event bytes, while the packed file used 89,176 bytes and 182 rows. The packed `permission-policy-context` generation yielded 813 events, including 746 chunks (91.8%); unpacked chunk lines occupied 118,935 of 184,821 event bytes, while the packed file used 84,917 bytes and 123 rows. These deterministic historical measurements explain why v2 embeds streams, but they are not a production workload distribution or a current-format size claim. JSONL writes one Zstandard frame and fsync per durable append batch. Runtime files do not record former append boundaries, so fixture row counts cannot honestly be presented as fsync counts. @@ -28,7 +28,7 @@ Each live Session receives a package-private `SessionWriteBehind`. When its pend `session/flush` cancels any remaining wait and becomes a shared quiescence barrier. It drains the active attempt and every event admitted while the barrier is running before it resolves. Session retirement and backend disposal use that same barrier, so lifecycle teardown never waits for the batching timer. The checkpoint policy continues to place mandatory barriers before model requests and top-level tool side effects. -Every event remains durable in its original order and shape. The controller copies each event on admission; no `assistant/chunk`, `seq`, `time`, surface metadata, or storage record is removed or rewritten. JSONL can therefore encode more events in one append frame without changing its on-disk format. +Every admitted event remains durable in its original order and representation. The controller copies each event on admission; batching removes or rewrites no sequence, timestamp, surface metadata, embedded Assistant stream, or storage record. JSONL can therefore encode more events in one append frame without changing the Session format. A failed background append restores its complete batch before any newer pending events, reports the failure once, and pauses automatic retry. The next newly admitted event opens a fresh fixed window; an explicit flush, retirement, or disposal retries immediately and surfaces a repeated failure to its caller. This avoids a timer-driven failure loop while preserving the existing recoverable flush boundary. @@ -36,7 +36,7 @@ This decision supersedes only the immediate scheduling cadence in [Collapse live ## Alternatives considered -**Do not persist streaming chunk events.** Rejected here: it changes the event-sourced authority and recovery semantics rather than only physical write cadence. The existing [assembled-message rejection](../../rejected/simplification/2026-06-20-assembled-assistant-messages-only.md) remains the guardrail until a no-information-loss replacement defines replay, fork, cited source-event links, sequence, and crash behavior independently. The [packed-row decision](2026-07-26-packed-chunk-rows-by-default.md) remains the complementary JSONL storage-size optimization. +**Use one settlement per Assistant attempt instead of batching writes.** The [v2 Assistant stream decision](2026-09-01-v2-embedded-assistant-streams.md) provides that no-information-loss event model and reduces Assistant event cardinality. It does not replace bounded batching for other adjacent events, historical-generation publication, or providers with the same append interface. **Write only at semantic checkpoints.** Rejected: it maximizes batching but makes the ordinary crash-loss window depend on a separately mounted policy. Bounded background writes preserve progress between checkpoints while mandatory flushes keep their stronger ordering contract. @@ -50,10 +50,10 @@ The controller tests use a fake clock to prove the fixed, non-resetting 200 ms w ## Consequences -High-frequency event bursts normally produce fewer durable append operations while preserving the exact logical event count. The reduction depends on arrival rate and backend latency: a burst inside one 200 ms window becomes one batch, while mandatory flushes and sparse events can still produce small batches. +High-frequency event bursts normally produce fewer durable append operations while preserving the exact admitted event sequence. The reduction depends on arrival rate and backend latency: a burst inside one 200 ms window becomes one batch, while mandatory flushes and sparse events can still produce small batches. This decision does not cap pending event count or bytes behind a slow provider, and it does not reduce the decoded logical log. A demonstrated memory bound or logical-retention policy would require its own failure and replay contract rather than another hidden timer rule. An admitted event can remain only in memory during the configured window, and then while scheduling or backend work is outstanding. Deployments choose a smaller value for a narrower ordinary loss window or a larger value for stronger batching. Explicit durability boundaries remain unchanged and bypass the wait. -The deep module gives the timer, active write, pending prefix, retry pause, and barrier one owner. `PersistenceCoordinator` retains initialization and identity serialization; the provider retains only durable storage primitives. `SESSION_FORMAT_VERSION` remains unchanged. +The deep module gives the timer, active write, pending prefix, retry pause, and barrier one owner. `PersistenceCoordinator` retains initialization and identity serialization; the provider retains only durable storage primitives. Batching itself never changes `SESSION_FORMAT_VERSION`. diff --git a/.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.zh.md b/.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.zh.md index ac0384f4e2..d076d5df3b 100644 --- a/.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-08-bounded-session-persistence-write-batching.zh.md @@ -6,13 +6,13 @@ Status: implemented ## 问题 -流式响应可能会在短时间内发出大量 `assistant/chunk` 事件。此前，只要空闲队列收到一个事件，持久化协调器就会立即调度一次 provider 追加。该追加仍在进行时到达的事件会共用一个后续批次，但如果 provider 速度很快，仍可能产生大量小规模的持久化追加。每次 JSONL 追加都会创建并同步一个 Zstandard 帧或原始格式后缀。 +一个 agent 步骤可以在短时间内发出多个持久事件：请求元数据、一个 Assistant settlement、工具生命周期、插件事实与执行边界。只要空闲队列收到一个事件就立即调度 provider 追加，仍可能产生大量小规模的持久化追加。每次 JSONL 追加都会创建并同步一个 Zstandard 帧或原始格式后缀。 -丢弃分片事件或用组装后的消息替代它们可以减少逻辑存储量，但也会改变事件日志、回放、序列号、时间戳，以及助手消息引用的分片 seq。写放大问题不要求采取这项语义变化更大的方案。 +Assistant stream 嵌入会减少一个高频事件 family，但对于其他事件突发与历史 generation，写入节奏仍是 provider-neutral 生命周期问题。批处理决策不会改变事件语义或存储编码。 ### 量化基线 -仓库 fixture（测试前置数据）让逻辑数据量有了具体依据。对当前 [`goal-multi-turn-actions`](../../../../snapshots/web/goal-multi-turn-actions/session.jsonl) 中的打包行进行解码，可得到 2,098 个事件，其中 2,017 个是分片（96.1%）。这些分片解包后的 JSONL 行共 332,647 字节，占全部事件 379,225 字节的 87.7%；分片打包则把仓库中的已提交文件缩小到 89,176 字节和 182 个存储行，其中包括 23 个打包分片行。[`permission-policy-context`](../../../../snapshots/web/permission-policy-context/session.jsonl) 可得到 813 个事件，其中 746 个是分片（91.8%）；这些分片解包后的 JSONL 行共 118,935 字节，占全部事件 184,821 字节的 64.4%。其打包文件为 84,917 字节，共 123 个存储行，其中包括 14 个打包行。这些是纳入版本控制的确定性 fixture，不代表生产工作负载分布；但它们说明了删除分片为何会降低逻辑数据量，也说明现有打包行布局已经消除了大量 JSON 包装开销。 +已发布 v1 仓库 fixture 建立了原始逻辑数据量。解码 packed `goal-multi-turn-actions` generation 得到 2,098 个事件，其中 2,017 个是 chunk（96.1%）；解包的 chunk 行占 379,225 个事件字节中的 332,647 字节，而 packed 文件使用 89,176 字节与 182 行。packed `permission-policy-context` generation 得到 813 个事件，其中 746 个是 chunk（91.8%）；解包的 chunk 行占 184,821 个事件字节中的 118,935 字节，而 packed 文件使用 84,917 字节与 123 行。这些确定性历史测量解释了 v2 为何嵌入 stream，但不代表生产工作负载分布或当前格式大小。 JSONL 每个持久化追加批次会写入一个 Zstandard 帧并执行一次 fsync。运行时文件不记录原有追加边界，因此不能把 fixture 的存储行数当作 fsync 次数。 @@ -28,7 +28,7 @@ JSONL provider 公开 `writeBatchMaxDelayMs`，其值必须是一个不超过 No `session/flush` 会取消剩余等待，并充当共享的完全停稳屏障。它会在完成前等待活跃写入尝试，并排空屏障运行期间接纳的每个事件。会话退役与后端 dispose（资源释放）共用该屏障，因此生命周期 teardown 绝不会等待批处理计时器。检查点策略仍会在模型请求与顶层工具副作用之前设置强制屏障。 -每个事件仍会按原有顺序和形态持久化。控制器会在接纳时复制每个事件；任何 `assistant/chunk`、`seq`、`time`、surface 元数据或存储记录都不会被删除或重写。因此，JSONL 可以在一个追加帧中编码更多事件，而无需改变其磁盘格式。 +每个已接纳事件仍会按原有顺序和表示持久化。控制器会在接纳时复制每个事件；批处理不会删除或改写任何序号、时间戳、surface 元数据、嵌入式 Assistant stream 或存储记录。因此，JSONL 可以在一个追加 frame 中编码更多事件，而无需改变 Session 格式。 后台追加失败后，控制器会把完整批次恢复到所有较新的待处理事件之前，报告一次该失败，并暂停自动重试。随后新接纳的第一个事件会开启新的固定窗口；显式 flush、退役或 dispose 会立即重试，如果故障再次发生，则会向调用方暴露该故障。这可以避免计时器驱动的失败循环，同时保留现有可恢复的 flush 边界。 @@ -36,7 +36,7 @@ JSONL provider 公开 `writeBatchMaxDelayMs`，其值必须是一个不超过 No ## 备选方案 -**不持久化流式分片事件。** 这里不采纳：这会改变事件溯源的权威地位及恢复语义，而不只是改变物理写入节奏。在无信息损失的替代方案独立定义回放、fork、引用源事件的关联、序列和崩溃行为之前，现有的[拒绝仅保留组装消息的决策](../../rejected/simplification/2026-06-20-assembled-assistant-messages-only.zh.md)仍是防护规则。[打包行决策](2026-07-26-packed-chunk-rows-by-default.zh.md)仍是配套的 JSONL 存储体积优化。 +**使用每个 Assistant attempt 一个 settlement 代替批处理写入。** [v2 Assistant stream 决策](2026-09-01-v2-embedded-assistant-streams.zh.md)提供该无信息损失事件模型，并减少 Assistant 事件基数。它不能替代其他相邻事件、历史 generation 发布或使用同一 append 接口的 provider 所需的有界批处理。 **仅在语义检查点写入。** 不采纳：此方案会最大化批处理，却让普通的崩溃丢失窗口取决于另行挂载的策略。有界后台写入会在检查点之间持久化进度，而强制 flush 继续提供更强的顺序约定。 @@ -50,10 +50,10 @@ JSONL provider 公开 `writeBatchMaxDelayMs`，其值必须是一个不超过 No ## 后果 -高频事件突发通常会减少持久化追加操作，同时保持逻辑事件数量完全不变。减少幅度取决于事件到达速率和后端延迟：位于同一 200 ms 窗口内的突发事件会成为一个批次，而强制 flush 与稀疏事件仍可能产生小批次。 +高频事件突发通常会减少持久化追加操作，同时保持已接纳事件序列完全不变。减少幅度取决于事件到达速率和后端延迟：位于同一 200 ms 窗口内的突发事件会成为一个批次，而强制 flush 与稀疏事件仍可能产生小批次。 本决策不会限制因 provider 缓慢而积压的待处理事件数量或字节数，也不会减少解码后的逻辑日志。若要建立经过验证的内存上界或逻辑保留策略，就必须为其另行定义失败与回放约定，而不是再引入一条隐式计时器规则。 接纳后的事件在配置窗口内可能只存在于内存中，此后在等待调度或后端工作完成期间也可能如此。部署可以选择较小的值以缩短普通丢失窗口，也可以选择较大的值以加强批处理。显式持久性边界保持不变，并会绕过等待。 -deep 模块统一负责计时器、活跃写入、待处理前缀、重试暂停和屏障。`PersistenceCoordinator` 继续负责初始化和按标识串行化；provider 仍只负责持久存储原语。`SESSION_FORMAT_VERSION` 保持不变。 +deep 模块统一负责计时器、活跃写入、待处理前缀、重试暂停和屏障。`PersistenceCoordinator` 继续负责初始化和按标识串行化；provider 仍只负责持久存储原语。批处理本身绝不改变 `SESSION_FORMAT_VERSION`。 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 c60b8ae3ba..1e49aa359b 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: 4831c2261791749804b6d0bd555423b7d4894520 -2026-08-09-client-conversation-node-assembly.zh.md: 37463d0543bbabc5d236f662827b932b55bbb11d +2026-08-09-client-conversation-node-assembly.md: abf03b52c174156b650f5c88425991892cc7615f +2026-08-09-client-conversation-node-assembly.zh.md: f4c8c7e1675dcf5b2bc846cb0731cc914532090a 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 4831c22617..abf03b52c1 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 @@ -51,7 +51,7 @@ Each `(kind, id)` has at most one start Match. A second start fails immediately; #### `match(event)` -`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`. +`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 Client-only `assistant/live-chunk` event can only be an update; the Assembler rejects every transient start, and `start()` receives a `ConversationStartMatch` containing a durable `SessionEvent`. 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. @@ -110,7 +110,7 @@ Dependencies point strictly from earlier starts to later starts, so transitive r #### `update(context, match)` -`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. +`update()` handles a post-start durable or transient Match that `match()` has already routed exactly to the current `(kind, id)`. It does not decide which Context owns the input. An Assistant Definition folds each `assistant/live-chunk` update directly and expands an embedded `assistant/message` or `assistant/attempt` stream during history replay. 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()`. @@ -262,7 +262,7 @@ Page size, record packing, the number of history loads, and RAF coalescing affec | Next-step Inbox / `inbox-next-step` | Splice Event seq | Each `agent/inbox/spliced` targeting next-step | None | Append message IDs to persistent splice state; materialize once per claim and expose the shared current claimed batch to Message | | 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` | 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 | +| Assistant / `assistant-step` | `turn:step` | `step/start` | Live `assistant/live-chunk`, durable `assistant/message` or `assistant/attempt`, and same-step Retry | Aggregate blocks, usage, first-token time, settlement 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 | @@ -382,7 +382,7 @@ History-path tests cover complete replace, non-overlapping prepend, complete-ran **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. +**Add a separate live-stream matcher and update lifecycle.** Rejected: a second Definition path would duplicate dispatch, replay, publication, and Context types. Client-only `assistant/live-chunk` and durable settlements use the existing `match(event)` and `update(context, match)` lifecycle; only the event discriminator and stream expansion differ. **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. 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 37463d0543..f4c8c7e167 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 @@ -51,7 +51,7 @@ Assembler 使用 `conversationContextKey(kind, id)` 组合无碰撞 key；不同 #### `match(event)` -`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`。 +`match(event)` 只读取当前 `SessionEventLike`，返回 `{ id, role: 'start' | 'update' }` 或 `null`。它拿不到 Context、history、Reader、Location 或 view envelope。Client-only `assistant/live-chunk` event 只能作为 update；Assembler 会拒绝每个 transient start，`start()` 接收的 `ConversationStartMatch` 只包含持久 `SessionEvent`。 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。 @@ -110,7 +110,7 @@ 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 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。 +`update()` 只处理已由 `match()` 精确路由到当前 `(kind, id)` 的 post-start durable 或 transient Match。它不判断 input 属于哪个 Context。Assistant Definition 会直接 fold 每个 `assistant/live-chunk` update，并在 history replay 期间展开嵌入式 `assistant/message` 或 `assistant/attempt` stream。 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。 @@ -262,7 +262,7 @@ 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 | 把消息 ID 追加到持久 splice state；每次 claim 只 materialize 一次，并向 Message 暴露共享的当前 claimed batch | | 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` | 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 | +| Assistant / `assistant-step` | `turn:step` | `step/start` | Live `assistant/live-chunk`、持久 `assistant/message` 或 `assistant/attempt`、同 step Retry | 聚合 block、usage、首 token 时间、settlement 证据与 retry-hidden state，再发布同 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 | @@ -382,7 +382,7 @@ 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。 +**增加独立 live-stream matcher 与 update lifecycle。** 拒绝：第二条 Definition path 会重复 dispatch、replay、publication 与 Context type。Client-only `assistant/live-chunk` 与持久 settlement 使用既有 `match(event)` 和 `update(context, match)` lifecycle；只有 event discriminator 与 stream expansion 不同。 **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。 diff --git a/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.i18n.yaml index d9823a5e88..b471d553d6 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.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-cancelled-stream-prefix-finalize.md -2026-08-10-cancelled-stream-prefix-finalize.md: fd397a02663908f5984b4e1798d1b1759b140c79 -2026-08-10-cancelled-stream-prefix-finalize.zh.md: 44adb2ff4163cd1904a9a93895c99519bae2f234 +2026-08-10-cancelled-stream-prefix-finalize.md: 1e6fe59bcc1b323941b69d0e9232f0bcf9e56f53 +2026-08-10-cancelled-stream-prefix-finalize.zh.md: 7aa81f179b80925ef47a8820f8a80c1ef37ec5ea diff --git a/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.md b/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.md index fd397a0266..1e6fe59bcc 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.md +++ b/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.md @@ -6,23 +6,23 @@ English | [中文](2026-08-10-cancelled-stream-prefix-finalize.zh.md) ## Problem -A cancelled stream can leave `assistant/chunk` events that clients continue rendering while `deriveMessages()` excludes them because no `assistant/message` records the delivered prefix. A follow-up such as "expand on your second point" then lacks text the user read, and a fork at the cancelled turn inherits the same gap. +A cancelled stream can leave transient chunks that clients have rendered while `deriveMessages()` excludes them because no `assistant/message` records the delivered prefix. A follow-up such as "expand on your second point" then lacks text the user read, and a fork at the cancelled turn inherits the same gap. The model history must contain assistant content that remains visible to the user after cancellation. ## Decision -`ReactLoopAgent.step()` catches cancellation while consuming a model stream, when its `BlockAssembler`, logged chunk seqs, and provider route identify the delivered prefix. It appends that prefix as the step's `assistant/message` with `interrupted: true`, `surfaceOp: 'append'`, and `sourceEventSeqs` containing exactly the logged chunks. The append precedes `step/end` and the aborted `turn/end`. +`ReactLoopAgent.step()` catches cancellation while consuming a model stream, when its `BlockAssembler`, compact stream accumulator, and provider route identify the delivered prefix. It appends that prefix as the step's `assistant/message` with `interrupted: true`, `surfaceOp: 'append'`, and the exact embedded timed stream. The append precedes the committed `agent/assistant-stream` end frame, `step/end`, and the aborted `turn/end`. -`BlockAssembler.interruptedBlocks()` returns closed and open `text` and `reasoning` blocks with non-whitespace content in stream order. It omits tool calls because interruption precedes dispatch and no real result exists; it also omits empty blocks and open unknown block types. An empty result appends no assistant message. Provider `error` and `aborted` finishes leave the stream-consumption scope before `agent/request-error`, so provider failures and cancellation during recovery commit no content from the failed request. +`BlockAssembler.interruptedBlocks()` returns closed and open `text` and `reasoning` blocks with non-whitespace content in stream order. It omits tool calls because interruption precedes dispatch and no real result exists; it also omits empty blocks and open unknown block types. An empty result appends `assistant/attempt` instead of a surface message. Provider `error` and `aborted` finishes also commit `assistant/attempt` before `agent/request-error`, so their streams remain durable without contributing failed-request content to model history. -Chat and Trajectory Conversation Definitions read `interrupted` from the durable message. Chat renders the Stopped marker, while Trajectory keeps the provider request in the error lifecycle after `step/end` and retains the durable result seq and provenance. Cancellation during tool execution follows the tool scheduler contract because the assistant message has already committed: started calls produce real results, and undispatched calls receive `ABORTED_BEFORE_DISPATCH` results. +Chat and Trajectory Conversation Definitions read `interrupted` from the durable message. Chat renders the Stopped marker, while Trajectory keeps the provider request in the error lifecycle after `step/end` and retains the durable result seq and provider information. Cancellation during tool execution follows the tool scheduler contract because the assistant message has already committed: started calls produce real results, and undispatched calls receive `ABORTED_BEFORE_DISPATCH` results. ## Alternatives considered **Always discard the prefix.** This avoids a new durable marker but makes every cancel-then-follow-up and fork omit assistant content that remains visible to the user. -**Assemble the prefix from chunks during projection.** `deriveMessages()` and client Conversation Definitions would each need interruption assembly rules, and the log would have no authoritative assistant message for the prefix. This also expands model history beyond the three `SurfaceEventType` events. +**Assemble the prefix from the embedded attempt during projection.** `deriveMessages()` and Client Conversation Definitions would each need interruption assembly rules, and the log would have no authoritative surface message for the prefix. This also expands model history beyond the three `SurfaceEventType` events. **Retain complete tool calls with synthetic aborted results.** These calls never dispatched, so synthetic results would claim an execution outcome that did not occur and add content the user did not receive as a tool result. @@ -32,8 +32,8 @@ Chat and Trajectory Conversation Definitions read `interrupted` from the durable Post-cancel follow-ups and forks include the delivered prefix. The ACP bridge drains ordered assistant output before settling the prompt, so the final `agent_message_chunk` update precedes the cancelled stop reason. -Terminal provider errors still discard their streamed prefix. That asymmetry remains because an error turn ends without the user's cancellation decision and requires its own retention policy. +Terminal provider errors retain their stream in `assistant/attempt` but keep its content out of model history. Only the user's cancellation decision turns visible delivered text into an interrupted surface message. ## Testing -`packages/core/agent-loop/tests/cancel.spec.ts` covers content, cited seqs, event order, next-request parity, reasoning-only output, tool-call omission, recovery cancellation, and the empty-prefix case. `packages/llm/llm/tests/assembler.spec.ts` covers `interruptedBlocks()`. `packages/client/ui-chat/tests/conversation-node-definitions.client.spec.ts` and `packages/client/ui-trajectory/tests/conversation-definitions.client.spec.ts` cover both client projections. The keyless `cancel` ACP snapshot and `goal-round-driver` goal snapshot cover assembled applications. +`packages/core/agent-loop/tests/cancel.spec.ts` covers content, embedded streams, event order, next-request parity, reasoning-only output, tool-call omission, recovery cancellation, and the empty-prefix attempt. `packages/llm/llm/tests/assembler.spec.ts` covers `interruptedBlocks()`. `packages/client/ui-chat/tests/conversation-node-definitions.client.spec.ts` and `packages/client/ui-trajectory/tests/conversation-definitions.client.spec.ts` cover both Client projections. The keyless `cancel` ACP snapshot and `goal-round-driver` goal snapshot cover assembled applications. diff --git a/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.zh.md b/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.zh.md index 44adb2ff41..7aa81f179b 100644 --- a/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-10-cancelled-stream-prefix-finalize.zh.md @@ -6,23 +6,23 @@ Status: implemented ## Problem -被取消的流可能留下客户端继续渲染的 `assistant/chunk` 事件，但如果没有 `assistant/message` 记录已送达前缀，`deriveMessages()` 就会排除这部分内容。后续的「第二点展开讲讲」之类追问会缺少用户已读到的文本，在该轮次上创建的分支也会继承这个缺口。 +被取消的流可能留下 Client 已经渲染的瞬态 chunk，但如果没有 `assistant/message` 记录已送达前缀，`deriveMessages()` 就会排除这部分内容。后续的「第二点展开讲讲」之类追问会缺少用户已读到的文本，在该轮次上创建的分支也会继承这个缺口。 模型历史必须包含取消后仍对用户可见的 assistant 内容。 ## Decision -`ReactLoopAgent.step()` 在消费模型流期间捕捉取消，此时 `BlockAssembler`、已记录的分片 seq 和提供方路由可以确定已送达前缀。循环把该前缀追加为 step 的 `assistant/message`，并设置 `interrupted: true`、`surfaceOp: 'append'` 以及恰好包含已记录分片的 `sourceEventSeqs`。该追加先于 `step/end` 和记录 aborted 的 `turn/end`。 +`ReactLoopAgent.step()` 在消费模型 stream 期间捕捉取消，此时 `BlockAssembler`、紧凑 stream accumulator 与 provider route 可以确定已送达前缀。loop 把该前缀追加为 step 的 `assistant/message`，并设置 `interrupted: true`、`surfaceOp: 'append'` 与精确嵌入式带时间 stream。该追加先于 committed `agent/assistant-stream` end frame、`step/end` 和记录 aborted 的 `turn/end`。 -`BlockAssembler.interruptedBlocks()` 按流顺序返回内容非空白的已闭合和未闭合 `text` 与 `reasoning` 块。打断先于分派，没有真实工具结果，因此它会省略工具调用，也会省略空块和未闭合的未知块类型。返回结果为空时不追加 assistant 消息。提供方的 `error` 和 `aborted` finish 会在 `agent/request-error` 前离开流消费范围，因此提供方故障和恢复期间的取消都不会提交失败请求的内容。 +`BlockAssembler.interruptedBlocks()` 按 stream 顺序返回内容非空白的已闭合和未闭合 `text` 与 `reasoning` block。打断先于分派，没有真实工具结果，因此它会省略工具调用，也会省略空 block 和未闭合的未知 block 类型。返回结果为空时追加 `assistant/attempt`，而不是 surface message。Provider `error` 与 `aborted` finish 也会在 `agent/request-error` 前提交 `assistant/attempt`，因此其 stream 保持持久，但失败请求内容不会进入模型历史。 -Chat 和 Trajectory Conversation Definition 从持久消息读取 `interrupted`。Chat 渲染 Stopped 标记，Trajectory 则在 `step/end` 后把提供方请求保持在 error 生命周期，并保留持久结果 seq 和提供方信息。工具执行期间的取消遵循工具调度器约定，因为 assistant 消息已提交：已启动的调用生成真实结果，未分派的调用获得 `ABORTED_BEFORE_DISPATCH` 结果。 +Chat 和 Trajectory Conversation Definition 从持久 message 读取 `interrupted`。Chat 渲染 Stopped marker，Trajectory 则在 `step/end` 后把 provider request 保持在 error 生命周期，并保留持久 result seq 与 provider 信息。工具执行期间的取消遵循工具调度器约定，因为 assistant message 已提交：已启动的调用生成真实结果，未分派的调用获得 `ABORTED_BEFORE_DISPATCH` 结果。 ## Alternatives considered **始终丢弃前缀。** 这能避免新增持久标记，但每次取消后的追问和分支都会缺少仍对用户可见的 assistant 内容。 -**在投影时从分片组装前缀。** `deriveMessages()` 和客户端 Conversation Definition 都需要实现打断组装规则，日志中也没有该前缀的权威 assistant 消息。这还会让模型历史超出三类 `SurfaceEventType` 事件。 +**在投影时从嵌入式 attempt 组装前缀。** `deriveMessages()` 与 Client Conversation Definition 都需要实现打断组装规则，日志中也没有该前缀的权威 surface message。这还会让模型历史超出三类 `SurfaceEventType` 事件。 **保留完整工具调用并合成 aborted 结果。** 这些调用从未分派，合成结果会声称一个并未发生的执行结果，还会增加用户未收到的工具结果内容。 @@ -32,8 +32,8 @@ Chat 和 Trajectory Conversation Definition 从持久消息读取 `interrupted` 取消后的追问和分支会包含已送达前缀。ACP 桥会在结算 prompt 前排空按序传送的 assistant 输出，因此最后一条 `agent_message_chunk` 更新先于 cancelled stop reason。 -终局提供方错误仍会丢弃已流出前缀。该不对称保留，因为 error 轮次的结束不来自用户的取消决定，需要独立的保留策略。 +终局 provider error 会在 `assistant/attempt` 中保留其 stream，但不让内容进入模型历史。只有用户的取消决策会把可见的已送达文本变成 interrupted surface message。 ## Testing -`packages/core/agent-loop/tests/cancel.spec.ts` 覆盖内容、引用的 seq、事件顺序、下一请求的一致性、仅 reasoning 的输出、工具调用省略、恢复期间的取消和空前缀情形。`packages/llm/llm/tests/assembler.spec.ts` 覆盖 `interruptedBlocks()`。`packages/client/ui-chat/tests/conversation-node-definitions.client.spec.ts` 和 `packages/client/ui-trajectory/tests/conversation-definitions.client.spec.ts` 覆盖两种客户端投影。keyless 的 `cancel` ACP 快照和 `goal-round-driver` goal 快照覆盖完整应用。 +`packages/core/agent-loop/tests/cancel.spec.ts` 覆盖 content、嵌入式 stream、事件顺序、下一请求的一致性、仅 reasoning 的输出、工具调用省略、恢复期间的取消和空前缀 attempt。`packages/llm/llm/tests/assembler.spec.ts` 覆盖 `interruptedBlocks()`。`packages/client/ui-chat/tests/conversation-node-definitions.client.spec.ts` 与 `packages/client/ui-trajectory/tests/conversation-definitions.client.spec.ts` 覆盖两种 Client 投影。keyless `cancel` ACP snapshot 与 `goal-round-driver` goal snapshot 覆盖组装应用。 diff --git a/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.i18n.yaml deleted file mode 100644 index d8af00effc..0000000000 --- a/.agents/notes/implemented/architecture/2026-08-15-packed-session-history-transport.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# 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/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: 6ef847a14da1b4ec1bd59e5aaad9093162b42d84 diff --git a/.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.i18n.yaml index d7990f37fe..13c4e2fb9b 100644 --- a/.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.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/2026-08-21-deepseek-llm-api-request-extensions.md -2026-08-21-deepseek-llm-api-request-extensions.md: 018b93115f5376affd86a4da3c76f0f367ba9ed0 -2026-08-21-deepseek-llm-api-request-extensions.zh.md: 4bc0f0c992445c5897069b68efa47fdba46dfdb4 +2026-08-21-deepseek-llm-api-request-extensions.md: eadbe2a5f17de446c345120f9a6aeeeb531c43b4 +2026-08-21-deepseek-llm-api-request-extensions.zh.md: f45210adbc075c30484754ce7f8c2b65b515be6c diff --git a/.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.md b/.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.md index 018b93115f..eadbe2a5f1 100644 --- a/.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.md +++ b/.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.md @@ -73,7 +73,7 @@ The receiver would also need to traverse the tagged tree, resolve paths into the ### Why not omit assistant chunks or overlapping event data? -About 98% of the measured real-session events were `assistant/chunk`. Omitting chunks after reference encoding reduced the complete identity JSON by another 84.79% for late enable and 6.49% for steady state, but it prevents lossless canonical-log reconstruction and leaves `assistant/message.sourceEventSeqs` pointing to absent events. Fuzzy or normalized substitutions have the same reconstruction defect. +About 98% of the measured v1 real-session events were `assistant/chunk`. Omitting them after reference encoding reduced the complete identity JSON by another 84.79% for late enable and 6.49% for steady state, but prevented lossless reconstruction and left message provenance dangling. V2 embeds compact streams in attempt settlements; `dsh_session_log` still sends every current canonical event whole and does not omit those embedded records. Fuzzy or normalized substitutions have the same reconstruction defect. **Keep the upload cursor only in memory.** Rejected because a normal process restart would resend the entire Session. A canonical acceptance event makes restart recovery best-effort durable without another storage backend; the remaining crash window produces allowed duplicates. diff --git a/.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.zh.md b/.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.zh.md index 4bc0f0c992..f45210adbc 100644 --- a/.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-21-deepseek-llm-api-request-extensions.zh.md @@ -73,7 +73,7 @@ Status: implemented ### 为什么不省略 assistant 分片或重叠事件数据？ -实测真实会话事件中约 98% 为 `assistant/chunk`。在引用编码后省略分片，会让完整未压缩 JSON 在延迟启用场景进一步减少 84.79%，在稳态场景进一步减少 6.49%，但这会阻止权威日志的无损重建，并让 `assistant/message.sourceEventSeqs` 指向缺失事件。模糊替换或规范化替换也存在同一重建缺陷。 +实测 v1 真实 Session event 中约 98% 为 `assistant/chunk`。在引用编码后省略它们，会让完整 identity JSON 在延迟启用场景进一步减少 84.79%，在稳态场景进一步减少 6.49%，但会阻止无损重建并让 message provenance 悬空。V2 把紧凑 stream 嵌入 attempt settlement；`dsh_session_log` 仍会完整发送每个当前规范 event，且不会省略这些嵌入式 record。模糊或规范化替换也有相同重建缺陷。 **只在内存中保留上传游标。** 已否决，因为普通进程重启会重发完整会话。权威接受事件让重启恢复获得尽力而为的持久性，无需另一存储后端；剩余崩溃窗口只会产生允许的重复。 diff --git a/.agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.i18n.yaml b/.agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.i18n.yaml index 0fb0ceca81..007f722536 100644 --- a/.agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.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/2026-08-31-live-assistant-stream-frames.md -2026-08-31-live-assistant-stream-frames.md: 9e848cadbfa71f8281caf14207b36d05f1f95d99 -2026-08-31-live-assistant-stream-frames.zh.md: dc672d6d8af31f1b45694299125d3f91cb1874ee +2026-08-31-live-assistant-stream-frames.md: b91dde47259c2e455a2a2068c644a66aef136836 +2026-08-31-live-assistant-stream-frames.zh.md: a32124f24db94c04360f36baca7be29f5c062b7d diff --git a/.agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.md b/.agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.md index 9e848cadbf..b91dde4725 100644 --- a/.agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.md +++ b/.agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.md @@ -6,19 +6,19 @@ English | [中文](2026-08-31-live-assistant-stream-frames.zh.md) ## Problem -The session log keeps every `assistant/chunk` so replay, cold reads, telemetry, and request reconstruction observe one durable v1 history. A live consumer also needs prompt frame-by-frame presentation while a request runs. Treating a transient presentation update as a new durable event would change persistence semantics and make a process-lifetime concern survive restart. +The v2 session log keeps one `assistant/message` or `assistant/attempt` settlement with the complete compact timed stream, so replay, cold reads, telemetry, and request reconstruction observe one durable history. A live consumer also needs prompt frame-by-frame presentation while a request runs. Treating a transient presentation update as another durable event would restore token-level event cardinality and make a process-lifetime concern survive restart. ## Decision -`dsh-agent-loop` emits scoped `agent/assistant-stream` frames for each model attempt. `start`, `chunk`, and `end` carry a branded process-local `LlmAttemptId`; every emitted frame advances one Session-local revision. The `start` frame captures a safe-integer wall-clock `startedTime`, chunk indexes are dense from zero, and `end.index` equals the next chunk position. Stream acquisition and its final cancellation check occur before `start`; a failure there emits no frame, while every started attempt emits a terminal `end`. The loop appends every v1 `assistant/chunk` before its matching live chunk frame, records that exact `legacyChunkSeq`, and appends the final `assistant/message` before a committed end frame. The existing authenticated Session-follow accepts an explicit Web opt-in, opens with a cached active-attempt baseline, and carries durable events and cursorless frames in one FIFO. Each follower captures a local arrival ordinal with the opening baseline and drops buffered frames at or before that cut; frame revisions can restart at one with a replacement Agent, so they do not define the opening cut. If the durable opening snapshot precedes the Assistant baseline, a baseline may already acknowledge a chunk whose durable event remains buffered; the Web Session publishes that event when it arrives because the baseline's exact `legacyChunkSeq` proves its matching frame. A final message arriving after an active opening remains staged until the matching `end.index` and ordered provenance arrive; an earlier retry at the same Turn and Step remains visible. Revision, dense-index, or provenance gaps re-open follow and replace the baseline. The TypeScript and Python SDK protocols do not expose these frames. The durable log remains the source of replay and model history. +`dsh-agent-loop` emits scoped `agent/assistant-stream` frames for each model attempt. `start`, `chunk`, and `end` carry a branded process-local `LlmAttemptId`; every frame advances one Session-local revision. The start frame captures a safe-integer wall-clock `startedTime`, chunk indexes are dense from zero, chunk timestamps are reused by the compact stream, and `end.index` equals the next chunk position. The loop appends the final `assistant/message` or `assistant/attempt` before a committed end frame names that event and seq; an abandoned end names no durable event. Authenticated Session-follow accepts an explicit Web opt-in, opens with a cached active-attempt compact baseline, and carries durable events and cursorless frames in one FIFO. Each follower captures a local arrival ordinal with the opening baseline and drops buffered frames at or before that cut; frame revisions can restart at one with a replacement Agent, so they do not define the opening cut. An opening between a durable settlement and its end frame reconstructs the active Client-only `assistant/live-chunk` updates, stages only the settlement owned by that attempt's `startedTime`, Turn, and Step, and releases it after the matching end index, type, and seq; an earlier retry at the same Turn and Step remains visible. Revision, dense-index, or settlement gaps reopen follow and replace the baseline. The TypeScript and Python SDK protocols do not expose these frames. Durable settlements remain the source of replay and model history; the [v2 stream decision](2026-09-01-v2-embedded-assistant-streams.md) owns their representation. ## Alternatives considered -- **Replace `assistant/chunk` with a live-only stream** — rejected because cold reads, replay, telemetry, and the completed assistant message's source references require the durable raw chunk history. -- **Add a durable assistant-stream event type** — rejected because process-local attempts, revisions, and reconnect presentation are not facts that survive restart or affect model reconstruction. +- **Keep only the live stream** — rejected because cold reads, replay, telemetry, usage accounting, and failed-attempt diagnostics require the durable embedded stream. +- **Persist each live frame as its own event** — rejected because process-local attempt ids, revisions, and reconnect presentation do not survive restart or affect model reconstruction; one settlement owns the durable stream. - **Use an unbranded request string as the attempt key** — rejected because consumers need an opaque identity that cannot be confused with provider request IDs or durable Session IDs. - **Let UI Chat subscribe to a second live source** — rejected because the Session object owns stream reconciliation and UI Conversation is the sole event-source subscriber; a second source would make settlement order target-dependent. ## Consequences -The Web client renders in-memory chunks before persistence flush while retaining one durable v1 history, without changing `SESSION_FORMAT_VERSION` or the chunk-row encoding. A process restart has no active assistant frames; reconnect and cold replay use durable records. Cursorless notifications never advance the journal cursor, and notifications observed during durable gap repair wait for the replacement page. That page has no Assistant baseline, so the Client clears transient attempts and lets the held notification reopen follow once for an atomically paired page and baseline. The frame declaration remains agent-scoped, so a listener observes only its owning Agent unless it explicitly registers globally. +The Web client renders in-memory chunks before the attempt settles while retaining one durable v2 history. A process restart has no active Assistant frames; reconnect can restore only the baseline held by the current process, while cold replay expands durable settlements. Cursorless notifications never advance the journal cursor, and notifications observed during durable gap repair wait for the replacement page. The frame declaration remains agent-scoped, so a listener observes only its owning Agent unless it explicitly registers globally. diff --git a/.agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.zh.md b/.agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.zh.md index dc672d6d8a..a32124f24d 100644 --- a/.agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.zh.md +++ b/.agents/notes/implemented/architecture/2026-08-31-live-assistant-stream-frames.zh.md @@ -6,19 +6,19 @@ Status: implemented ## 问题 -Session log 保留每个 `assistant/chunk`，因此重放、冷读、遥测和请求重建都能观察同一份持久 v1 历史。实时消费方还需要在请求运行时逐帧呈现。把短暂的呈现更新当作新的持久事件会改变持久化语义，并让只属于进程生命周期的事实跨重启保留。 +v2 Session log 通过一个 `assistant/message` 或 `assistant/attempt` settlement 保留完整紧凑带时间 stream，因此 replay、冷读、遥测与请求重建都能观察同一份持久历史。实时消费方还需要在请求运行时逐帧呈现。把瞬态呈现 update 当作另一种持久事件，会恢复 token 粒度事件基数，并让只属于进程生命周期的事实跨重启保留。 ## 决定 -`dsh-agent-loop` 为每次模型尝试发出作用域内的 `agent/assistant-stream` 帧。`start`、`chunk` 和 `end` 带有带品牌的进程本地 `LlmAttemptId`；每个已发出的帧都会推进一次 Session 本地 revision。`start` 帧会把壁钟时间捕获为安全整数 `startedTime`，chunk index 从零开始连续递增，`end.index` 等于下一个 chunk 位置。循环会先取得 stream 并执行最终取消检查，再发出 `start`；这些步骤失败时不发出任何帧，而每个已开始的尝试都会发出终态 `end`。循环在匹配的实时 chunk 帧之前追加每个 v1 `assistant/chunk`，记录精确的 `legacyChunkSeq`，并在已提交的 end 帧之前追加最终 `assistant/message`。现有的已认证 Session-follow 接受显式 Web opt-in，以缓存的活跃尝试 baseline 打开，并在一个 FIFO 中携带持久事件和无 cursor 的帧。每个 follower 会随 opening baseline 捕获本地到达序号，并丢弃该 cut 及之前的 buffered frame；replacement Agent 的 frame revision 可以从一重新开始，因此 revision 不定义 opening cut。如果持久 opening snapshot 早于 Assistant baseline，baseline 可能已经确认一个持久事件仍在 buffer 中的 chunk；该事件到达时，Web Session 会依据 baseline 中精确的 `legacyChunkSeq` 已证明其匹配帧而直接发布。活跃 opening 之后到达的最终 message 会保持暂存，直到匹配的 `end.index` 与有序来源到达；同一 Turn 和 Step 中更早的 retry 仍保持可见。revision、连续 index 或来源缺口会重新打开 follow 并替换 baseline。TypeScript 和 Python SDK 协议不公开这些帧。持久 log 仍然是重放和模型历史的真源。 +`dsh-agent-loop` 为每次模型 attempt 发出作用域内的 `agent/assistant-stream` frame。`start`、`chunk` 和 `end` 带有带品牌的进程本地 `LlmAttemptId`；每个 frame 都会推进一次 Session 本地 revision。start frame 会把壁钟时间捕获为安全整数 `startedTime`，chunk index 从零开始密集递增，chunk 时间戳会被紧凑 stream 复用，`end.index` 等于下一个 chunk 位置。loop 会在 committed end frame 命名事件与 seq 前追加最终 `assistant/message` 或 `assistant/attempt`；abandoned end 不命名持久事件。已认证 Session-follow 接受显式 Web opt-in，以缓存的活跃 attempt 紧凑 baseline 打开，并在一个 FIFO 中携带持久事件和无 cursor frame。每个 follower 会随 opening baseline 捕获本地到达序号，并丢弃该 cut 及之前的 buffered frame；replacement Agent 的 frame revision 可以从一重新开始，因此 revision 不定义 opening cut。opening 位于持久 settlement 与对应 end frame 之间时，会重建活跃的 Client-only `assistant/live-chunk` update，只暂存由该 attempt 的 `startedTime`、Turn 与 Step 所有的 settlement，并在匹配的 end index、type 与 seq 到达后释放；同一 Turn 和 Step 中更早的 retry 仍保持可见。revision、密集 index 或 settlement 缺口会重新打开 follow 并替换 baseline。TypeScript 和 Python SDK 协议不公开这些 frame。持久 settlement 仍是 replay 与模型历史的真源；其表示由 [v2 stream 决策](2026-09-01-v2-embedded-assistant-streams.zh.md)负责。 ## 曾考虑的替代方案 -- **用仅实时的流替换 `assistant/chunk`**：不采用，因为冷读、重放、遥测和已完成 assistant message 的来源引用都需要持久的原始 chunk 历史。 -- **添加持久的 assistant-stream 事件类型**：不采用，因为进程本地尝试、revision 和重连呈现不是会跨重启保留或影响模型重建的事实。 +- **只保留 live stream**：不采用，因为冷读、replay、遥测、usage 记账与失败 attempt 诊断需要持久嵌入式 stream。 +- **把每个 live frame 作为独立事件持久化**：不采用，因为进程本地 attempt id、revision 与重连呈现不会跨重启保留或影响模型重建；一个 settlement 拥有持久 stream。 - **用未加品牌的请求字符串作为尝试键**：不采用，因为消费方需要一个不透明身份，不能把它与 provider request ID 或持久 Session ID 混淆。 - **让 UI Chat 订阅第二个实时 source**：不采用，因为 Session 对象拥有 stream 对账，UI Conversation 是唯一的 event-source 订阅方；第二个 source 会使结算顺序依赖 target。 ## 影响 -Web client 可以在 persistence flush 前渲染内存 chunk，同时保留一份持久 v1 历史，而不改变 `SESSION_FORMAT_VERSION` 或 chunk-row 编码。进程重启后没有活跃 assistant 帧；重连和冷重放使用持久记录。无 cursor 的通知绝不推进 journal cursor，在持久缺口修复期间观察到的通知会等待 replacement page。该 page 不携带 Assistant baseline，因此 Client 会清空瞬态尝试，并让 held notification 重新打开 follow 一次，以取得原子配对的 page 与 baseline。帧声明保持 agent 作用域，因此监听器只观察所属 Agent，除非它显式全局注册。 +Web client 可以在 attempt settlement 前渲染内存 chunk，同时保留一份持久 v2 历史。进程重启后没有活跃 Assistant frame；重连只能恢复当前进程持有的 baseline，冷 replay 则展开持久 settlement。无 cursor 通知绝不推进 journal cursor，在持久缺口修复期间观察到的通知会等待 replacement page。frame 声明保持 agent 作用域，因此监听器只观察所属 Agent，除非它显式全局注册。 diff --git a/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.i18n.yaml b/.agents/notes/implemented/architecture/2026-09-01-v2-embedded-assistant-streams.i18n.yaml similarity index 56% rename from .agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.i18n.yaml rename to .agents/notes/implemented/architecture/2026-09-01-v2-embedded-assistant-streams.i18n.yaml index 58dcf1ee20..3472483442 100644 --- a/.agents/notes/implemented/architecture/2026-07-26-packed-chunk-rows-by-default.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-09-01-v2-embedded-assistant-streams.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/architecture/2026-07-26-packed-chunk-rows-by-default.md -2026-07-26-packed-chunk-rows-by-default.md: bd4b3b9f773afbf6aa7e88d51b6e842d6634c222 -2026-07-26-packed-chunk-rows-by-default.zh.md: eafe6632150aadd74395f4d0f09d064fb703a03d +# pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-09-01-v2-embedded-assistant-streams.md +2026-09-01-v2-embedded-assistant-streams.md: 2f01905ba844b4ef4bdbce6e2f193c77d61ff8e4 +2026-09-01-v2-embedded-assistant-streams.zh.md: d4e84463986ddb3113181d2920973fa54cacb678 diff --git a/.agents/notes/implemented/architecture/2026-09-01-v2-embedded-assistant-streams.md b/.agents/notes/implemented/architecture/2026-09-01-v2-embedded-assistant-streams.md new file mode 100644 index 0000000000..2f01905ba8 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-09-01-v2-embedded-assistant-streams.md @@ -0,0 +1,68 @@ +# Agent Note: Embed Assistant streams in v2 attempt settlements + +Status: implemented + +English | [中文](2026-09-01-v2-embedded-assistant-streams.zh.md) + +## Problem + +Token-sized `assistant/chunk` events preserve exact stream order, timing, usage, terminal state, replay metadata, and partial failed output, but making each chunk a top-level Session event repeats envelopes throughout persistence, telemetry, history transport, indexing, and client assembly. Physical packed rows reduce JSONL bytes without reducing logical event count or the work of consumers that receive the canonical stream. + +Storing only assembled successful messages would remove that overhead but lose failed and abandoned output, token boundaries, timestamps, and deterministic provider replay. The durable record needs one unit per model attempt without reducing the evidence that replay, diagnostics, cancellation recovery, usage accounting, snapshots, and UI history rely on. + +Changing event cardinality also changes Session sequence numbers. A released migration must preserve the relative order of unrelated events, rewrite every declared same-Session reference, retain the exact fork cut, and refuse any relationship it cannot preserve semantically. + +## Decision + +Session format v2 has no top-level `assistant/chunk` event. Each model attempt commits one durable settlement containing `stream: AssistantStreamRecord[]`: + +- `assistant/message` is the surface settlement for a successful response or a cancelled response with visible assembled content. It embeds the exact compact timed stream beside the assembled message, optional usage, and optional `interrupted: true` marker. +- `assistant/attempt` is log-only. It preserves the stream for a failed, retried, cancelled, or crash-tail attempt that commits no surface message, so diagnostics and accounting do not fabricate model-visible history. + +`AssistantStreamAccumulator` snapshots each chunk once. Consecutive text, reasoning, or tool-argument deltas for the same block become one compact run with its first timestamp, exact timestamp gaps, and one array member per original delta. Every other chunk remains a timestamped raw record. `expandAssistantStream()` strictly validates and reconstructs the exact timed sequence; compaction never joins delta boundaries. + +The current v2 validator requires the embedded stream to reproduce a non-empty `assistant/message`'s content, usage, and replay state. An empty stream remains valid for a migrated legacy message that had no source chunks. `assistant/message` cannot carry obsolete chunk `sourceEventSeqs`; ordinary user and tool surface provenance remains available. + +### Live presentation and durable replay + +`agent/assistant-stream` publishes process-local start, transient chunk, and end frames. The loop appends the complete `assistant/message` or `assistant/attempt` before a committed end frame names its type and sequence. An abandoned end has no settlement. + +The Web follow adapter opts into these cursorless frames. It presents chunks as Client-only `assistant/live-chunk` updates between durable cursors, stages the matching settlement until the committed end, and reopens follow on a revision gap. A reconnect baseline carries the active attempt's compact prefix. Paged history, replay, telemetry, token accounting, and cold UI assembly read the durable embedded stream rather than the live frames. + +### Released v1 to v2 migration + +The adjacent migration validates the complete frozen v1 artifact, groups chunks by turn, step, terminal boundary, and exact message provenance, and then substitutes one settlement per attempt. A successful group's chunks move into its message. An unclaimed group becomes `assistant/attempt` at the last consumed chunk's position. Unrelated interleaved events retain their relative order, and survivors receive dense v2 sequence numbers. + +The edge remaps the finite declared reference inventory: envelope provenance, surface replacement endpoints, command source events, compaction ranges and shadowed lists, and title message lists. A reference to a consumed chunk refuses migration; it is never redirected to a settlement with different meaning. The edge also refuses an inherited cut that splits an attempt. + +The v2 physical header requires `isSeeded` and stores no numeric cut. A seeded artifact marks its exact cut with `session/end-seed { inherited: true }`; decoding derives the cut from the last tagged marker. The v2 codec writes one durable event per physical row and range-encodes only `sourceEventSeqs`. Frozen v0 and v1 codecs retain packed-row decoding for their immutable historical generations. + +Generation selection and publication follow the [released Session migration decision](2026-08-31-released-session-format-migrations.md): the source path, bytes, and inode remain unchanged, only the final version-named successor is published, and retained predecessors provide neither fallback nor downgrade support. + +## Verification + +The compact-stream tests pin exact accumulation and expansion for text, reasoning, tool arguments, raw chunks, timestamp gaps, malformed records, and detached snapshots. The v1-to-v2 tests cover successful and failed attempts, interleaving, dense sequence and reference remapping, seed-cut insertion and split refusal, strict source and target validation, one-row v2 encoding, provenance ranges, raw and Zstandard publication, and no-write current reads. + +The manual performance acceptance compares current v2 catalog dispatch with a direct-current read of the same physical input across three runs, 100 warmup pairs, and 600 measured pairs. It requires every pooled median and p95 regression to remain within 5%; the accepted run's worst p95 regression was 2.201%. `--smoke` reports a non-gating diagnostic sample. + +Agent-loop tests pin durable-before-end ordering, interrupted visible prefixes, failed and retry attempts, abandonment, usage, and replay metadata. Session Controller and Conversation tests pin live transient display, reconnect baselines, committed settlement release, history replay, Chat and Trajectory parity, while TypeScript and Python SDK snapshots pin the external event representation. + +## Alternatives considered + +**Persist only assembled successful messages.** This loses partial failed output, timing, token boundaries, usage from attempts without a message, and exact deterministic replay. `assistant/attempt` and the embedded compact stream preserve those facts without adding them to model history. + +**Keep top-level chunks and pack only physical rows.** This preserves the v1 logical representation but leaves sequence density, telemetry volume, wire envelopes, Client entries, and consumer dispatch proportional to token count. Historical codecs still decode that representation; it is not the current event model. + +**Carry packed chunk rows through the history API.** This reduces wire and Client work for v1 but gives the Client a second event vocabulary and keeps transport coupled to token-row cardinality. The current API carries scalar durable settlements plus a separate live transient stream. + +**Store the stream in a sidecar or replay-only fixture.** This splits one attempt's message and evidence across durability owners and cannot give ordinary resumed sessions the same failed-output and timing facts. The settlement is the atomic owner. + +**Redirect references from consumed chunks to their settlement.** A chunk and an attempt settlement are not interchangeable facts. Refusal prevents a migration from silently changing the meaning of plugin-owned references. + +## Consequences + +Current logs, telemetry, history pages, and cold Client assembly scale by model attempts rather than token chunks while retaining exact stream evidence inside each settlement. Live presentation remains incremental and intentionally process-local. + +One settlement can be large, and v1-to-v2 migration materializes the whole artifact plus its sequence map. The closed alpha inventory refuses unknown v1 events and undeclared references instead of guessing. Consumers that need individual chunks call `expandAssistantStream()` and must not infer durability from `agent/assistant-stream`. + +Migration changes sequence numbers after consumed v1 chunks, so every same-Session reference belongs to an explicit rewrite rule. This constraint makes future cardinality-changing migrations expensive by design and keeps silent semantic redirection out of the format chain. diff --git a/.agents/notes/implemented/architecture/2026-09-01-v2-embedded-assistant-streams.zh.md b/.agents/notes/implemented/architecture/2026-09-01-v2-embedded-assistant-streams.zh.md new file mode 100644 index 0000000000..d4e8446398 --- /dev/null +++ b/.agents/notes/implemented/architecture/2026-09-01-v2-embedded-assistant-streams.zh.md @@ -0,0 +1,68 @@ +# Agent Note: 在 v2 attempt settlement 中嵌入 Assistant stream + +Status: implemented + +[English](2026-09-01-v2-embedded-assistant-streams.md) | 中文 + +## 问题 + +Token 粒度的 `assistant/chunk` 事件会保留精确的 stream 顺序、时间、usage、terminal state、replay metadata 与失败时的部分输出，但让每个 chunk 成为顶层 Session event 会在持久化、遥测、历史传输、索引和 Client 组装中重复信封。物理 packed row 可以减少 JSONL 字节，却不会减少逻辑事件数，也不会减少接收规范 stream 的消费方工作量。 + +只存储组装后的成功 message 可以消除这些开销，但会丢失失败与放弃的输出、token 边界、时间戳和确定性 provider replay。持久记录需要让每个模型 attempt 只占一个单位，同时不减少 replay、诊断、取消恢复、usage 记账、snapshot 与 UI 历史依赖的证据。 + +改变事件基数也会改变 Session 序号。已发布迁移必须保留无关事件的相对顺序、改写每个已声明的同 Session 引用、保留精确 fork 切点，并拒绝任何无法保持语义的关系。 + +## 决策 + +Session format v2 没有顶层 `assistant/chunk` 事件。每个模型 attempt 提交一个包含 `stream: AssistantStreamRecord[]` 的持久 settlement： + +- `assistant/message` 是成功响应或具有可见组装内容的已取消响应所对应的 surface settlement。它在组装 message 旁嵌入精确的紧凑带时间 stream、可选 usage 与可选 `interrupted: true` marker。 +- `assistant/attempt` 只进入日志。它保留失败、重试、取消或崩溃尾部 attempt 的 stream；这些 attempt 没有提交 surface message，因此诊断与记账不会虚构模型可见历史。 + +`AssistantStreamAccumulator` 对每个 chunk 只快照一次。同一 block 的连续 text、reasoning 或 tool argument delta 会变成一个紧凑 run，包含首个时间戳、精确时间戳间隔和每个原始 delta 对应的一个数组成员。其他 chunk 保留为带时间戳的 raw record。`expandAssistantStream()` 会严格校验并重建精确的带时间序列；压缩绝不会合并 delta 边界。 + +当前 v2 校验器要求嵌入式 stream 能复现非空 `assistant/message` 的 content、usage 与 replay state。对于没有源 chunk 的已迁移旧 message，空 stream 仍然有效。`assistant/message` 不能携带已停用的 chunk `sourceEventSeqs`；普通 user 与 tool surface provenance 保持可用。 + +### 实时呈现与持久回放 + +`agent/assistant-stream` 发布进程本地 start、瞬态 chunk 与 end frame。loop 会在 committed end frame 命名其类型和序号前追加完整的 `assistant/message` 或 `assistant/attempt`。abandoned end 没有 settlement。 + +Web follow adapter 显式选择接收这些无 cursor frame。它把 chunk 呈现为持久 cursor 之间的 Client-only `assistant/live-chunk` update，把匹配的 settlement 暂存到 committed end，并在 revision 缺口时重新打开 follow。重连 baseline 携带活跃 attempt 的紧凑前缀。分页历史、replay、遥测、token 记账与冷 UI 组装读取持久嵌入式 stream，而不是 live frame。 + +### 已发布 v1 到 v2 迁移 + +相邻迁移会校验完整的冻结 v1 产物，按 turn、step、terminal boundary 与精确 message provenance 对 chunk 分组，再为每个 attempt 替换一个 settlement。成功分组的 chunk 移入其 message。未被认领的分组会在最后一个被消费 chunk 的位置变成 `assistant/attempt`。无关的交错事件保持相对顺序，存活事件获得密集 v2 序号。 + +该迁移边会重映射有限的已声明引用清单：信封 provenance、surface replacement 端点、command source event、compaction range 与 shadowed list，以及 title message list。指向被消费 chunk 的引用会使迁移失败；它绝不会被重定向到含义不同的 settlement。该迁移边也会拒绝切开 attempt 的继承切点。 + +v2 物理 header 要求 `isSeeded`，且不存储数值切点。带 seed 的产物用 `session/end-seed { inherited: true }` 标记其精确切点；解码从最后一个 tagged marker 推导切点。v2 编解码器为每个持久事件写一条物理行，并且只对 `sourceEventSeqs` 做范围编码。冻结的 v0 与 v1 编解码器继续为不可变历史 generation 解码 packed row。 + +Generation 选择与发布遵循[已发布 Session 迁移决策](2026-08-31-released-session-format-migrations.zh.md)：源路径、字节与 inode 保持不变，只发布最终具名版本 successor；保留 predecessor 不提供 fallback 或 downgrade 支持。 + +## 验证 + +紧凑 stream 测试固定 text、reasoning、tool argument、raw chunk、时间戳间隔、格式错误 record 与分离 snapshot 的精确累积和展开。v1 到 v2 测试覆盖成功与失败 attempt、交错、密集序号与引用重映射、seed 切点插入与切分拒绝、严格源与目标校验、每行一个事件的 v2 编码、provenance range、原始与 Zstandard 发布，以及无写入的当前读取。 + +手工 performance acceptance 会在三轮、100 组 warmup pair 与 600 组 measured pair 下，把当前 v2 catalog dispatch 与同一物理输入的 direct-current 读取比较。它要求每个 pooled median 与 p95 regression 保持在 5% 以内；已接受运行的最差 p95 regression 为 2.201%。`--smoke` 报告不参与 gate 的诊断 sample。 + +Agent-loop 测试固定先持久后 end 的顺序、中断的可见前缀、失败与重试 attempt、abandonment、usage 与 replay metadata。Session Controller 与 Conversation 测试固定实时瞬态显示、重连 baseline、committed settlement 发布、历史回放以及 Chat 与 Trajectory 一致性；TypeScript 与 Python SDK snapshot 固定外部事件表示。 + +## 备选方案 + +**只持久化组装后的成功 message。** 这会丢失部分失败输出、时间、token 边界、没有 message 的 attempt usage，以及精确确定性 replay。`assistant/attempt` 与嵌入式紧凑 stream 会保留这些事实，且不把它们加入模型历史。 + +**保留顶层 chunk，只打包物理行。** 这会保留 v1 逻辑表示，却让序号密度、遥测量、wire 信封、Client entry 与消费方 dispatch 继续与 token 数成正比。历史编解码器仍然解码该表示；它不是当前事件模型。 + +**通过历史 API 传递 packed chunk row。** 这会减少 v1 的 wire 与 Client 工作，却让 Client 拥有第二套事件词汇，并让传输继续与 token-row 基数耦合。当前 API 携带标量持久 settlement，并使用独立的实时瞬态 stream。 + +**把 stream 存在 sidecar 或 replay-only fixture 中。** 这会把一个 attempt 的 message 与证据拆给不同持久性 owner，也无法让普通恢复 Session 获得相同的失败输出与时间事实。settlement 是原子 owner。 + +**把被消费 chunk 的引用重定向到其 settlement。** Chunk 与 attempt settlement 不是可互换事实。拒绝可以防止迁移悄然改变插件自有引用的含义。 + +## 后果 + +当前日志、遥测、历史页与冷 Client 组装按模型 attempt 而非 token chunk 扩展，同时在每个 settlement 内保留精确 stream 证据。实时呈现保持增量，并且有意仅存在于进程内。 + +一个 settlement 可能很大，v1 到 v2 迁移会物化完整产物及其序号映射。封闭的 Alpha 清单会拒绝未知 v1 事件与未声明引用，而不会猜测。需要单独 chunk 的消费方调用 `expandAssistantStream()`，并且绝不能从 `agent/assistant-stream` 推断持久性。 + +迁移会改变被消费 v1 chunk 之后的序号，因此每个同 Session 引用都必须属于显式改写规则。该约束有意让未来的基数变化迁移保持昂贵，并防止格式链执行无声的语义重定向。 diff --git a/.agents/notes/implemented/bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.i18n.yaml index f234acb000..f2c184f557 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.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/bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md -2026-07-21-compaction-summary-prefix-cache-reuse.md: 08ceb820ee415cbac9aded7a6b4f55933dc64cf3 -2026-07-21-compaction-summary-prefix-cache-reuse.zh.md: 2d796c8518c703d872ebcec4f548a0e52d91994b +2026-07-21-compaction-summary-prefix-cache-reuse.md: a1066cd9925b37a05ea06c22b60b81d6107cd336 +2026-07-21-compaction-summary-prefix-cache-reuse.zh.md: 3f487f63250713570ccc7962ba0afab869bc656a diff --git a/.agents/notes/implemented/bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md b/.agents/notes/implemented/bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md index 08ceb820ee..a1066cd992 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md +++ b/.agents/notes/implemented/bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.md @@ -29,7 +29,7 @@ Auto-compaction always anchors at the surface head, so the shadowed region is th - **Keep the summarizer system prompt but reuse the rest** — rejected: the system slot is the very first token region a provider caches on, so a distinct summarizer system prompt invalidates the whole prefix regardless of what follows. Only moving the directive off the front recovers the cache. - **Send only the shadowed region without the `system`/`tools` head** — rejected: a differently-headed sequence still diverges from the cached request at the first token, so it caches no better while losing the framing the summary needs. - **Omit `tools` from the summarization request** (the model never calls one) — rejected: tool schemas are part of the cached token sequence; omitting them misaligns every following token and defeats reuse. -- **A dedicated `assistant/chunk`-emitting summarization sub-session for snapshot replay** — rejected: the durable `compaction/summary` event records the successful local call's position and complete output, while its explicit call marker prevents replay from treating template or remote output as a local stream. +- **A dedicated Agent-backed summarization sub-session for snapshot replay** — rejected: the durable `compaction/summary` event records the successful local call's position and complete output, while its explicit call marker prevents replay from treating template or remote output as a local stream. Creating a sub-session solely to obtain an Assistant settlement adds an unrelated lifecycle. ## Consequences diff --git a/.agents/notes/implemented/bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.zh.md b/.agents/notes/implemented/bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.zh.md index 2d796c8518..3f487f6325 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-21-compaction-summary-prefix-cache-reuse.zh.md @@ -29,7 +29,7 @@ Status: implemented - **保留摘要器系统提示词但复用其余部分**——否决：system 槽位正是提供方最先做缓存的 token 区域，因此一个不同的摘要器系统提示词无论后面跟着什么都会使整个前缀失效。只有把指令移离前端才能恢复缓存。 - **只发送被遮蔽区域而不带 `system`/`tools` 头部**——否决：头部不同的序列在第一个 token 处仍然与已缓存请求分叉，因此缓存效果并不更好，反而丢失了摘要所需的框架。 - **从摘要请求中省略 `tools`**（模型从不调用任何工具）——否决：工具 schema 是已缓存 token 序列的一部分；省略它们会让后续每个 token 失去对齐，破坏复用。 -- **为快照回放专门建立一个发出 `assistant/chunk` 的摘要子会话**——否决：持久的 `compaction/summary` 事件会记录成功本地调用的位置和完整输出，而显式调用标记可防止回放把模板或远程输出当作本地流。 +- **为 snapshot replay 专门建立 Agent-backed summarization sub-session**——否决：持久 `compaction/summary` event 会记录成功本地调用的位置与完整输出，显式 call marker 可防止 replay 把 template 或 remote output 当作本地 stream。仅为获得 Assistant settlement 而创建 sub-session 会增加无关 lifecycle。 ## 后果 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.i18n.yaml index 60c2a60e42..9e02707a9b 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.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/bug-fix/2026-07-31-english-compaction-checkpoints.md -2026-07-31-english-compaction-checkpoints.md: dc95ed187a6ba5b86800f06ebefb2776995f9421 -2026-07-31-english-compaction-checkpoints.zh.md: 1dc98b43e5bf2ca66cb3480b8124af6e7a9479b2 +2026-07-31-english-compaction-checkpoints.md: a1123b3d679a8bab2dbd9ecdc7b2079a78ffe28a +2026-07-31-english-compaction-checkpoints.zh.md: 1543d87493a9cbfb28b18f00afa4ee4d3a074179 diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.md b/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.md index dc95ed187a..a1123b3d67 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.md +++ b/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.md @@ -25,4 +25,4 @@ The requirement is integrated into the first sentence of the trailing compaction - New checkpoints normalize narrative context into English while retaining the exact strings that future tool use and code work depend on. - Existing checkpoint structure, compaction routing, and cache alignment are unchanged; only the final user instruction is different. -- The direct summarization call remains outside transcript snapshots because it emits no `assistant/chunk` events. The real-loop regression instead asserts the exact final instruction received by the summarization request. +- The direct summarization call remains outside transcript snapshots because it emits no Agent-owned Assistant settlement. The real-loop regression instead asserts the exact final instruction received by the summarization request. diff --git a/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.zh.md b/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.zh.md index 1dc98b43e5..1543d87493 100644 --- a/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-07-31-english-compaction-checkpoints.zh.md @@ -25,4 +25,4 @@ Status: implemented - 新检查点会将叙述性上下文规范化为英语，同时保留未来工具使用和代码工作所依赖的精确字符串。 - 既有检查点结构、压缩路由和缓存对齐保持不变；只有最后一条 user 指令不同。 -- 直接摘要调用仍不纳入 transcript（文本记录）快照，因为它不会发出 `assistant/chunk` 事件。真实循环回归改为断言摘要请求收到的精确最终指令。 +- 直接 summarization call 仍不纳入 transcript snapshot，因为它不会发出 Agent-owned Assistant settlement。真实 loop regression 改为断言 summarization request 收到的精确最终 instruction。 diff --git a/.agents/notes/implemented/bug-fix/2026-08-10-subagent-empty-terminal-message-output.i18n.yaml b/.agents/notes/implemented/bug-fix/2026-08-10-subagent-empty-terminal-message-output.i18n.yaml index 16713035e7..006a91edf1 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-10-subagent-empty-terminal-message-output.i18n.yaml +++ b/.agents/notes/implemented/bug-fix/2026-08-10-subagent-empty-terminal-message-output.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/bug-fix/2026-08-10-subagent-empty-terminal-message-output.md -2026-08-10-subagent-empty-terminal-message-output.md: 24bab01ad844a5b48e0bf6fe0fc54df6403f4bb7 -2026-08-10-subagent-empty-terminal-message-output.zh.md: 28d8d85e316fe4770e55685e9d5641fda846c5c5 +2026-08-10-subagent-empty-terminal-message-output.md: 6ecb0ef254bd9734664aac71fe63c1eb3caf45b7 +2026-08-10-subagent-empty-terminal-message-output.zh.md: bcc6cad60fb5c791c328da1057e836cc1267d11b diff --git a/.agents/notes/implemented/bug-fix/2026-08-10-subagent-empty-terminal-message-output.md b/.agents/notes/implemented/bug-fix/2026-08-10-subagent-empty-terminal-message-output.md index 24bab01ad8..6ecb0ef254 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-10-subagent-empty-terminal-message-output.md +++ b/.agents/notes/implemented/bug-fix/2026-08-10-subagent-empty-terminal-message-output.md @@ -6,11 +6,11 @@ English | [中文](2026-08-10-subagent-empty-terminal-message-output.zh.md) ## Problem -The agent loop appends an empty-content `assistant/message` when a `max-tokens` step assembled only tool-call blocks because `BlockAssembler.blocks()` drops truncated tool calls; the message records usage only. Three consumers selected the child's output independently and treated that usage record as output. The in-process driver's `readResult` and the continuable Activation's `subagent/end` capture selected the last `assistant/message` without filtering, while the SDK backend's observer let any `assistant/message` take precedence over accumulated text. In a multi-step turn cut off at max-tokens, the final empty message caused the real partial answer to be omitted from `SubagentResult.output`, the tool result, telemetry, and `subagent/end.lastAssistantMessage`. The in-process driver also lacked a streamed-text fallback, so a cancelled child whose only text existed in `assistant/chunk` events reported `[]`. +The agent loop appends an empty-content `assistant/message` when a `max-tokens` step assembled only tool-call blocks because `BlockAssembler.blocks()` drops truncated tool calls; the message retains its stream and usage but contributes no output blocks. Three consumers selected the child's output independently and treated that record as output. The in-process driver's `readResult` and the continuable Activation's `subagent/end` capture selected the last `assistant/message` without filtering, while the SDK backend's observer let any `assistant/message` take precedence over accumulated text. In a multi-step turn cut off at max-tokens, the final empty message caused the real partial answer to be omitted from `SubagentResult.output`, the tool result, telemetry, and `subagent/end.lastAssistantMessage`. The in-process driver also lacked a streamed-text fallback, so a cancelled child whose only text existed in an embedded Assistant stream reported `[]`. ## Decision -`dsh-subagent` owns one canonical selection rule in `src/assistant-output.ts`: select the last non-empty assistant message; without one, select the accumulated `text-delta` stream; ignore empty-content messages. The incremental `AssistantOutputFold` implements the rule through `push(event)` for session-event transports, `pushText(text)` for chunk-only transports, and `collect()` for selection. `finalAssistantOutput(events)` applies it to a complete event suffix for the in-process `readResult` and Activation capture. The SDK backend folds notification events; the ACP backend exposes no complete assistant messages and folds raw chunk text. `SubagentResult.output` defines the result contract, and `subagent/end.lastAssistantMessage` uses the same rule. When a child produces neither form of output, the lifecycle field is absent rather than an empty array for both one-shot and continuable runs. A `max-tokens` or `aborted` result retains its actual stop reason. +`dsh-subagent` owns one canonical selection rule in `src/assistant-output.ts`: select the last non-empty Assistant message; without one, select accumulated `text-delta` content from embedded `assistant/message` and `assistant/attempt` streams or a chunk-only transport; ignore empty-content messages. The incremental `AssistantOutputFold` implements the rule through `push(event)`, `pushText(text)`, and `collect()`. `finalAssistantOutput(events)` applies it to a complete event suffix for the in-process `readResult` and Activation capture. The SDK backend folds notification events; the ACP backend exposes no complete Assistant messages and folds raw chunk text. `SubagentResult.output` defines the result contract, and `subagent/end.lastAssistantMessage` uses the same rule. When a child produces neither form of output, the lifecycle field is absent rather than an empty array for both one-shot and continuable runs. A `max-tokens` or `aborted` result retains its actual stop reason. The foreground delegation tool uses the same selection. A non-`completed` result remains an `isError` tool result, but its message presents the optional safe Provider diagnostic owned by the [non-interactive permissions decision](../feature/2026-08-15-product-subagent-noninteractive-permissions.md) after the stop-reason headline and appends the child's partial text afterward. The parent model receives the failure, separate infrastructure detail, and available assistant output without conflating them. diff --git a/.agents/notes/implemented/bug-fix/2026-08-10-subagent-empty-terminal-message-output.zh.md b/.agents/notes/implemented/bug-fix/2026-08-10-subagent-empty-terminal-message-output.zh.md index 28d8d85e31..bcc6cad60f 100644 --- a/.agents/notes/implemented/bug-fix/2026-08-10-subagent-empty-terminal-message-output.zh.md +++ b/.agents/notes/implemented/bug-fix/2026-08-10-subagent-empty-terminal-message-output.zh.md @@ -6,11 +6,11 @@ Status: implemented ## 问题 -当 `max-tokens` 步骤只组装了工具调用块时，agent loop（智能体循环）会追加一条空内容的 `assistant/message`，因为 `BlockAssembler.blocks()` 会丢弃被截断的工具调用；这条消息仅记录 usage。三个消费方独立选取子 agent 的输出，并把这条 usage 记录当成输出。进程内驱动的 `readResult` 与 continuable Activation 的 `subagent/end` capture 不加过滤地选取最后一条 `assistant/message`，SDK 后端的观察器则让任何 `assistant/message` 优先于累积的文本。在被 max-tokens 截断的多步轮次中，最后那条空消息导致 `SubagentResult.output`、工具结果、遥测与 `subagent/end.lastAssistantMessage` 都漏掉真实的部分回答。进程内驱动也没有流式文本兜底，因此被取消的子 agent 若其唯一文本只存在于 `assistant/chunk` 事件中，也会报告 `[]`。 +当 `max-tokens` step 只组装出 tool-call block 时，agent loop 会追加空 content `assistant/message`，因为 `BlockAssembler.blocks()` 会丢弃被截断的 tool call；该 message 保留 stream 与 usage，但不贡献 output block。三个消费方独立选取 child agent 输出，并把该 record 当成输出。进程内 driver 的 `readResult` 与 continuable Activation 的 `subagent/end` capture 不加过滤地选取最后一条 `assistant/message`，SDK backend observer 则让任何 `assistant/message` 优先于累计 text。在被 max-tokens 截断的多 step turn 中，最后的空 message 导致 `SubagentResult.output`、tool result、telemetry 与 `subagent/end.lastAssistantMessage` 漏掉真实 partial answer。进程内 driver 也缺少 streamed-text fallback，因此被取消 child 的唯一 text 若只存在于嵌入式 Assistant stream 中，也会报告 `[]`。 ## 决策 -`dsh-subagent` 在 `src/assistant-output.ts` 中拥有唯一的规范选取规则：选取最后一条非空 assistant 消息；没有时选取累积的 `text-delta` 流；忽略空内容消息。增量的 `AssistantOutputFold` 通过 `push(event)` 处理会话事件传输，通过 `pushText(text)` 处理仅分片传输，并通过 `collect()` 完成选取。`finalAssistantOutput(events)` 把规则应用于完整的事件后缀，供进程内 `readResult` 与 Activation capture 使用。SDK 后端折叠通知事件；ACP 后端不暴露完整的 assistant 消息，而是折叠原始分片文本。`SubagentResult.output` 定义结果约定，`subagent/end.lastAssistantMessage` 使用同一规则。子 agent 不产生这两种输出中的任何一种时，一次性与 continuable 运行的生命周期字段都会缺省，而不是空数组。`max-tokens` 或 `aborted` 结果保留实际的终止原因。 +`dsh-subagent` 在 `src/assistant-output.ts` 中拥有唯一规范选取规则：选取最后一条非空 Assistant message；没有时，从嵌入式 `assistant/message` 与 `assistant/attempt` stream 或 chunk-only transport 选取累计 `text-delta` content；忽略空 content message。增量 `AssistantOutputFold` 通过 `push(event)`、`pushText(text)` 与 `collect()` 实现该规则。`finalAssistantOutput(events)` 把规则应用于完整 event suffix，供进程内 `readResult` 与 Activation capture 使用。SDK backend 折叠 notification event；ACP backend 不公开完整 Assistant message，并折叠 raw chunk text。`SubagentResult.output` 定义 result contract，`subagent/end.lastAssistantMessage` 使用同一规则。child 不产生任一种输出时，一次性与 continuable run 的 lifecycle field 都缺省，而不是空 array。`max-tokens` 或 `aborted` result 保留实际 stop reason。 前台委派工具使用同一选取规则。非 `completed` 的结果仍是 `isError` 工具结果，但其消息会在终止原因标题之后呈现由[非交互权限决策](../feature/2026-08-15-product-subagent-noninteractive-permissions.zh.md)负责的可选安全提供方诊断，再附上子 agent 的部分文本。父模型会同时收到失败、独立的基础设施说明与已有 assistant 输出，而且不会把它们混为一体。 diff --git a/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.i18n.yaml b/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.i18n.yaml index 0c6fb58564..75a4fe2cbc 100644 --- a/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.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/2026-07-19-fresh-agent-ralph-workflow-tool.md -2026-07-19-fresh-agent-ralph-workflow-tool.md: f374fcee7abc89c61c3ff6654093d1026cc8a715 -2026-07-19-fresh-agent-ralph-workflow-tool.zh.md: 1362e9ba528230b9247bb65e3bbfa2c61a72c568 +2026-07-19-fresh-agent-ralph-workflow-tool.md: 9eedc022f04f733feb5c4e5abb4b0528c0d10f60 +2026-07-19-fresh-agent-ralph-workflow-tool.zh.md: 23c614d5b5eadbe583469acff1efa01b398498db diff --git a/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.md b/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.md index f374fcee7a..9eedc022f0 100644 --- a/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.md +++ b/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.md @@ -46,7 +46,7 @@ Human-facing presentation uses a generic `ralph` card whose raw input is the obj Unit tests cover config and call-cap resolution, provider capability rejection, fixed start-request routing and child ceiling, all successful terminal outcomes, ordinary child-failure envelopes, malformed and oversized boundary values, exact successful-result truncation, abort timing, disposal, render intent, prompt lifecycle, and namespace-plugin shape at per-file 100% coverage. Worker-engine tests prove synchronous provider-route validation, per-run child ceilings below the deployment ceiling, and that a provider override selects every child without changing the configured default, including the built `lib/worker.cjs` under plain Node. -A keyless real-stack integration drives the fixed script through the actual worker-thread engine, spawn provider, structured-output runtime, and agent loop. It proves distinct child identities, absent `seedLength`, inherited cwd, no parent-history markers in either child request, exact previous-report handoff only in the following round, one phase event, terminal completion, and disposal of both children. The same real stack covers blocker and round-limit outcomes, unnormalized and semantically invalid reports, oversized handoffs, ordinary child failure with the last good handoff, and cancellation to child quiescence. The keyless [`ralph-loop` headless snapshot](../../../../snapshots/session/ralph-loop/) invokes `ralph`, pins the parent stream transcript, and inspects persisted logs for two distinct unseeded child sessions and the round-one handoff appearing only in round two. Tool tests pin generic call/result presentation, while request-header snapshots pin the shipped schema and prompt-guidance transcript output. +A keyless real-stack integration drives the fixed script through the actual worker-thread engine, spawn provider, structured-output runtime, and agent loop. It proves distinct child identities, `isSeeded: false` with cut zero, inherited cwd, no parent-history markers in either child request, exact previous-report handoff only in the following round, one phase event, terminal completion, and disposal of both children. The same real stack covers blocker and round-limit outcomes, unnormalized and semantically invalid reports, oversized handoffs, ordinary child failure with the last good handoff, and cancellation to child quiescence. The keyless [`ralph-loop` headless snapshot](../../../../snapshots/session/ralph-loop/) invokes `ralph`, pins the parent stream transcript, and inspects persisted logs for two distinct unseeded child sessions and the round-one handoff appearing only in round two. Tool tests pin generic call/result presentation, while request-header snapshots pin the shipped schema and prompt-guidance transcript output. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.zh.md b/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.zh.md index 1362e9ba52..23c614d5b5 100644 --- a/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.zh.md +++ b/.agents/notes/implemented/feature/2026-07-19-fresh-agent-ralph-workflow-tool.zh.md @@ -46,7 +46,7 @@ Ralph 插件的 `subagentProvider` 默认为 `spawn`。每次调用前，它要 单元测试覆盖配置与调用上限解析、提供方能力拒绝、固定启动请求路由与子 agent 上限、全部成功终止结果、普通子 agent 失败外层值、畸形及过大边界值、成功结果精确截断、中止时序、dispose（资源释放）、渲染意图、提示生命周期和命名空间插件形状，并达到逐文件 100% 覆盖率。工作流引擎测试证明提供方路由会同步验证、每次运行的子 agent 上限可低于部署上限，并且提供方覆盖会选择每个子 agent 且不改变配置默认值，其中包括普通 Node 下构建后的 `lib/worker.cjs`。 -一项无密钥真实栈集成测试通过实际工作线程引擎、spawn 提供方、结构化输出运行时和 agent loop 驱动固定脚本。它证明子 agent 标识不同、没有 `seedLength`、继承 cwd、两个子请求都不含父历史标记、上一份报告只精确出现在下一 Round 的交接中、只产生一个阶段事件、终止完成以及两个子 agent 都已 dispose。同一真实栈还覆盖阻塞与 Round 上限结果、未规范化及语义无效报告、过大交接、保留上一份有效交接的普通子 agent 失败，以及取消后子 agent 完全停稳。无密钥 [`ralph-loop` headless 快照](../../../../snapshots/session/ralph-loop/)会调用 `ralph`、固定父级流式 transcript，并检查持久化日志中存在两个不同且无种子的子会话，且 Round 1 的交接只出现在 Round 2。工具测试固定通用调用／结果展示，请求头快照固定发布的 schema 与提示指导 transcript 表面。 +一项无 key 真实栈 integration 通过实际 worker-thread engine、spawn provider、structured-output runtime 与 agent loop 驱动固定 script。它证明 child agent identity 不同、`isSeeded: false` 且 cut 为零、继承 cwd、两个 child request 都不含 parent-history marker、上一份 report 只精确出现在下一 Round handoff 中、只产生一个 phase event、terminal completion，以及两个 child agent 都已 dispose。同一真实栈还覆盖 blocker 与 Round-limit outcome、未规范化及语义无效 report、过大 handoff、保留上一份有效 handoff 的普通 child failure，以及取消后 child 完全停稳。无 key [`ralph-loop` headless snapshot](../../../../snapshots/session/ralph-loop/)调用 `ralph`、固定 parent stream transcript，并检查持久 log 中存在两个不同且 unseeded 的 child Session，且 Round 1 handoff 只出现在 Round 2。Tool test 固定通用 call/result presentation，request-header snapshot 固定已发布 schema 与 prompt-guidance transcript。 ## 考虑过的替代方案 diff --git a/.agents/notes/implemented/feature/2026-07-24-provider-retry-policies.i18n.yaml b/.agents/notes/implemented/feature/2026-07-24-provider-retry-policies.i18n.yaml index 47eb54b338..2291fbad05 100644 --- a/.agents/notes/implemented/feature/2026-07-24-provider-retry-policies.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-24-provider-retry-policies.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/2026-07-24-provider-retry-policies.md -2026-07-24-provider-retry-policies.md: 968f40272d3d3cb0efa362c97dcb8630888f80ec -2026-07-24-provider-retry-policies.zh.md: 3274d0311bb79825ef9551549e4783a33c1cb6ee +2026-07-24-provider-retry-policies.md: 996e7fcef2f323044761126d82dc53f73d3dde88 +2026-07-24-provider-retry-policies.zh.md: 8b3cb96ddb78f5bf0d680f8e9762622f1383286b diff --git a/.agents/notes/implemented/feature/2026-07-24-provider-retry-policies.md b/.agents/notes/implemented/feature/2026-07-24-provider-retry-policies.md index 968f40272d..996e7fcef2 100644 --- a/.agents/notes/implemented/feature/2026-07-24-provider-retry-policies.md +++ b/.agents/notes/implemented/feature/2026-07-24-provider-retry-policies.md @@ -40,7 +40,7 @@ Always mode asks downstream recovery first so a specialized policy such as conte Both modes use exponential local delays from `initialDelayMs` to `maxDelayMs`. `jitterRatio` multiplies each target by a uniform sample in `[1 - jitterRatio, 1 + jitterRatio]`, then applies the cap. A positive provider `Retry-After` within the cap remains exact and unjittered. An over-cap provider delay makes normal mode delegate; always mode retains its guarantee by using the configured local backoff. -Each scheduled retry appends a non-surface `llm/retry` event with the failed provider, policy mode, canonical resolved-policy key, provider-policy retry number, delay, and failure facts. Normal events carry finite `maxRetries`; always events omit it, and UIs render the limit as `∞`. The event and failed `assistant/chunk` records do not contribute surface messages, so the next request contains the same derived context as the failed request unless another recovery policy deliberately changes the surface. +Each scheduled retry appends a non-surface `llm/retry` event with the failed provider, policy mode, canonical resolved-policy key, provider-policy retry number, delay, and failure facts. Normal events carry finite `maxRetries`; always events omit it, and UIs render the limit as `∞`. Neither that event nor the failed attempt's `assistant/attempt` settlement contributes a surface message, so the next request contains the same derived context as the failed request unless another recovery policy deliberately changes the surface. ## Alternatives considered diff --git a/.agents/notes/implemented/feature/2026-07-24-provider-retry-policies.zh.md b/.agents/notes/implemented/feature/2026-07-24-provider-retry-policies.zh.md index 3274d0311b..8b3cb96ddb 100644 --- a/.agents/notes/implemented/feature/2026-07-24-provider-retry-policies.zh.md +++ b/.agents/notes/implemented/feature/2026-07-24-provider-retry-policies.zh.md @@ -40,7 +40,7 @@ always 模式先请求下游恢复，使上下文溢出压缩（compaction）之 两种模式的本地延迟都按指数增长，从 `initialDelayMs` 增至 `maxDelayMs`。`jitterRatio` 用 `[1 - jitterRatio, 1 + jitterRatio]` 区间内的均匀随机样本乘以每次目标值，再应用上限。提供方给出的正数 `Retry-After` 若未超过上限，则保持精确且不加抖动。若提供方延迟超过上限，normal 模式会委托后续处理；always 模式则改用配置的本地退避，以维持无限重试保证。 -每次安排重试都会追加一条不进入表层的 `llm/retry` 事件，其中包含失败的提供方、策略模式、已解析策略的规范键、提供方策略内的重试编号、延迟和失败事实。normal 事件包含有限的 `maxRetries`；always 事件省略该字段，UI 将上限渲染为 `∞`。该事件与失败的 `assistant/chunk` 记录都不会生成表层消息，因此除非其他恢复策略有意改变表层，否则下一次请求包含的派生上下文与失败请求相同。 +每次安排 retry 都会追加一条不进入 surface 的 `llm/retry` event，其中包含失败 provider、policy mode、resolved policy 的规范 key、provider-policy retry number、delay 与 failure facts。normal event 包含有限 `maxRetries`；always event 省略该字段，UI 把上限渲染为 `∞`。该 event 与失败 attempt 的 `assistant/attempt` settlement 都不产生 surface message，因此除非其他 recovery policy 有意改变 surface，否则下一次请求包含与失败请求相同的派生 context。 ## 曾考虑的替代方案 diff --git a/.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.i18n.yaml b/.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.i18n.yaml index 4a864f9071..24a50b382d 100644 --- a/.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.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/2026-08-03-web-search-source-scroll.md -2026-08-03-web-search-source-scroll.md: 6fe532e2a2989e834b926cf48d531ae60a32f58b -2026-08-03-web-search-source-scroll.zh.md: 12bc6d3decb3c13ea759a9f25322b94e45db1322 +2026-08-03-web-search-source-scroll.md: 0609f45a198c5c9a35c2e2dd1f2ac8c3aaba7ccc +2026-08-03-web-search-source-scroll.zh.md: 1649598dfc9198bdbbd36b82df6a4606af4c3e4d diff --git a/.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.md b/.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.md index 6fe532e2a2..0609f45a19 100644 --- a/.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.md +++ b/.agents/notes/implemented/feature/2026-08-03-web-search-source-scroll.md @@ -38,7 +38,7 @@ Every source the tool returned is always in the DOM, so no source the view carri `packages/client/ui-primitives/tests/web-block.client.spec.tsx` drops the collapse cases (head/tail slice, expand-on-click, collapsed-tail numbering, expander-out-of-numbering, head-alone, default cap) and adds: a 30-source card renders all 30 `
  • ` with no `[aria-expanded]` and no `