ds-review-bot round: the backstop stopped at a file's first declare-module
block while the projection it guards reads them all; the textual prefilter
matched only single quotes; .tsx sources escaped the glob. All three are the
silent-vanish class the scan exists to prevent. contextMergeFiles now yields
one entry per block (quote-agnostic prefilter, ts+tsx patterns), and a third
partition direction requires everything rendered to be scan-visible, so a
future scan regression is a hard error. Spec fixture made projection-
consistent; the partially superseded 2026-07-28 regions note is rewritten to
the current mechanism and cross-linked both ways.
The rendering projection walks only files reachable from host-face package
exports, so client-face Events merges vanished silently (12 events) and the
services backstop's top-level glob missed 13 nested client Context keys.
Events now get the exact mirror of the service backstop (EVENT_WALK_EXEMPTIONS,
name-keyed because client events share scopes with rendered host events), both
scans read packages/*/*/src/**/*.ts, and the partition judgment is the pure
walkPartitionProblems() so every acceptance path is unit-provable.
core.md claimed to be the packages/core reference but opened on repo-wide type patterns and never documented the ownership vocabulary: AgentHandle, CreateAgentOptions, ResumeAgentOptions, and AgentFactory were TYPE_LINK_EXEMPTIONS pointing at a package README, invisible to the folder that calls itself the type reference. The page now reads spine map -> creation and ownership (AgentHandle pasted; the options and factory summarized with links into the generated registry section) -> the Agent handle (AgentStatus, AgentOptions, SteeringOutcome, SteeringReceipt, and SettleReason now pasted; the one settlement prose wall split by topic; delivery vocabulary ordered as a message travels) -> initiator -> interception -> a Sessions summary -> the ToolDefinition pointer -> an explicitly framed repo-wide patterns tail (the ...Map pattern, branded ids). The duplicate SessionEvent paste is gone -- session.md owns it and LINK_MAP follows -- the four ownership types moved from TYPE_LINK_EXEMPTIONS into LINK_MAP -> core.md, and three dead LINK_MAP entries (ContinuationDecision, ContinuationStop, HookContext) no longer name types absent from the source tree. The "what this page owns" meta-section folds into the intro.
The subsystems README index silently lost tasks.md and session-reference.md on both language sides during a base absorption; the rows are restored and scripts/project-doc-site.spec.ts now fails when any page misses either side of the index (proven red on a removed row). tools.md links ToolSchema to its llm-streaming.md declaration instead of calling it core; subagent.md links AgentHandle and CreateAgentOptions.seed to the new section. A new Agent Note records the package-anchored page-scoping decision; the 2026-06-20 catalog note marks its spine-vs-seam rule superseded as the page-scoping rule while keeping the type-equiv mechanism current, and docs/AGENTS.md cites the new note.
core.md read as a type grab-bag: LLM wire vocabulary up front, the agent/loop story buried, and no correspondence to packages/core. It now opens on the packages/core control spine — the package-by-package loop map with a Page column into session/system-prompt/tools/scope — and keeps only what the spine group declares plus the repo-wide patterns: the Agent handle with its delivery/cancellation/interception contracts, the SessionEvent envelope, branded ids, the …Map pattern. The conversation vocabulary (Message/ContentBlock, the model request, adapters — 17 type-equiv blocks) moves to llm-streaming.md, which now declares packages/llm end-to-end; the duplicate ContentBlockMap paste near its seam section folds into the moved section, and the manifest, LINK_MAP, README table rows, website label (Core data structures → Core), and inbound anchors follow.
Every packages/<group>/README pair is now a thin front door in one shape: a why-first intro (bash's seam-pattern-first paragraph rewritten as 'shell execution for the agent'), the package table, and a closing pointer to the owning docs/subsystems page — the bash-style table stays the load-bearing middle. Load-bearing trailing paragraphs relocate rather than vanish: the fs no-timeout rationale becomes a filesystem.md section (both languages), session's four sectioned tables merge into one 12-row table, examples' legacy-bin H2 collapses to a pointer at jsonrpc-demo's README, and design rationale that already lives in an Agent Note or subsystem page is now linked instead of restated. All 40 pair records re-recorded.
Rebuild of the region machinery (PR3) on the post-#904 Typert projection:
renderPageRegion/renderInheritedPage live in dsh-typert-generator beside the
projection; scripts/gen-cordis-catalog.ts owns the curated SERVICE_PAGE /
EVENT_SCOPE_PAGE / SERVICE_WALK_EXEMPTIONS / LINK_MAP partition (fail-loud in
both directions, with the independent Context-merge scan backstopping the
projection's blind spot), spliceRegion, and the guarded pair auto-record.
docs/cordis-catalog/ is deleted: the flat events/services catalogs dissolve
into per-page regions and docs/cordis-catalog/core moves to docs/cordis-api/
with the inherited tier as its own generated page. The partition absorbs the
post-regrouping surface: ctx.typert → invariants.md, ctx.directoryPicker →
workspace.md, skills/* events → skills.md, and the four launcher-provided tui
accessor values join the named exemptions.
ds-review-bot round 3:
- set() after a turn's final step lands in a later turn (selection
never forces continuation) — the same-turn phrasing overstated the
guarantee; set() JSDoc + subsystem page (both languages).
- Workspace attach/insert/detach no-op claims now carry the
filtered-candidate-prune caveat: mutate() durably prunes stale
candidates even when the requested change is a no-op, a state the
sessionIds contract explicitly permits; Workspace fence re-synced on
both page sides; catalogs regenerated.
telemetry.md joins the eight pages after the OTel telemetry seam landed
on master (ctx.telemetry + telemetry/record were the one service and
event scope still without a page). All nine pages gain zh counterparts
translated whole-document per dsh-translate-docs; the eleven touched
pairs (nine new + core + the subsystems-catalog note) are recorded;
TelemetryRecord moves from TYPE_LINK_EXEMPTIONS to LINK_MAP and the
catalogs are regenerated.
permission, plan, invariants, http-server, storage (hub + backend seam +
domain form + domain/changed), workspace, tui, and client-modules complete
the docs/subsystems tier: every ctx service and event scope now has one
owning page, the precondition for generating per-subsystem service/event
reference into these pages. 25 new type-equiv manifest entries; 16 types
move from TYPE_LINK_EXEMPTIONS to LINK_MAP now that they have catalog
homes (dead InvariantRegistration exemption removed; catalogs
regenerated); core.md's sub-page table gains the eight rows in both
languages; the owning subsystems-catalog Agent Note records the coverage
extension. Chinese counterparts and pair records follow in the next
commit.
The folder is becoming the home of one-doc-per-subsystem pages (intro +
data structures + cordis services/events), so the name must describe the
whole contract, not just the type-vocabulary third of it. Mechanical
rename rebuilt on current master: every inbound Markdown link, generator
constant, website route, type-equiv manifest path, and spec expectation
moves together; the zh sides of the notes whose prose names the folder
are aligned (子系统) in the same change; touched bilingual pairs
re-recorded; translation-prompt snapshot re-recorded (its example embeds
development.md). Historical Agent Note slugs keep their dated
filenames.
git mv timeout-policy beside repeat-tool-guard (both are loop-hygiene
policies on the tool-execution pipeline, and the timeout/ group name
collided with util/timeout) and tool-cordis into self-modification/
(naming the role the framework name obscured). Merged/renamed group
README triplets, tsconfig globs, generator sources, hierarchy tables,
catalogs, and the timeout-policy design note's group references
follow. Adds the fifth FIXME marker (dsh-timeout-guard, recorded as a
suggestion to settle at resolution time).
guard + self-modification suites: 197 passed.
git mv per the regrouping RFC: the five human-collaboration seams and
tui join packages/interaction/, app-boot becomes packages/boot/, and
jsonrpc joins the renamed scaffold/ (formerly sdk/) as its server half
beside client/protocol/create-sdk/helper/scripts/telemetry, whose
folders drop the legacy sdk- prefix. Three new group README triplets
replace the ui/ and sdk/ ones; tsconfig references/paths/globs,
knip keys, vitest globs, gate scripts, catalogs, docs, and the
lockfile follow. Adds the four settled FIXME rename markers
(dsh-sdk-server, dsh-sdk-telemetry, dsh-sdk-helper, dsh-sdk-scripts).
The scaffold folders diverge from their npm names until those renames
land, so tsconfig.base.json maps the three affected names explicitly
beside the group wildcard. Also repairs two pre-existing stale-path
classes the strengthened sweep surfaced: docs/web-styling.md's retired
web-ui host package and type-model spec fixture-literal joins.
app-boot's three Loader-composition specs time out at the default 5s
under full-suite parallel load on this filesystem (pre-existing;
pass isolated with --testTimeout=30000); interaction/scaffold/boot
suites otherwise green (687 passed).
git mv the 12 packages from session-persistence/, session-projection/,
session-title/, and telemetry/ into one session/ group per the
regrouping RFC; merge the four group READMEs into one bilingual
triplet; rewrite the group segment in tsconfig references (intra-group
references shorten to ../<pkg>), tsconfig.base.json paths/globs,
knip.json keys, vitest include, gate scripts, and authored doc/note
citations; regenerate module graph, doc graphs, catalogs, and the
lockfile importer keys. No npm names change.
Full unit suite: 8779 passed; the 18 reported failures reproduce as
env flakes (ambient-proxy IPv6 tunneling, watched-dir inotify
timeouts under parallel load) — each passes in isolation with
NO_PROXY set, matching their known pre-existing behavior on master.
The task registry has run every background bash, pwsh, pty-send, and
one-shot subagent since it landed, but only the model could read it: a
human at the Web client could not see that a build was running, tell a
finished task from a stuck one, or find its outcome anywhere but the
`run_in_background` tool card that printed an id and never updated.
Task state now reaches the browser as one whole-snapshot `session/tasks`
mux frame per session, pushed at every registry commit that changes what
that session can see. `TaskService` gains `onTasksChanged`, which is
owner-granular because owner-disposal removal is a change no per-task
record can express. The carrier reads the exact owner the listener hands
it, so a push stays correct while that scope tears down, and reads the
baseline through the non-resuming `ctx.agents.get` so listing never
revives a cold session. The client keeps a last-wins mirror on
`SessionListState`, and a new `dsh-client-ui-task` package renders it
beside the subagent catalog — rendering nothing at all until the session
has a task, so an ordinary conversation grows no new chrome.
Streamed per-task output and human-initiated cancellation are separate
phases; the note records why neither has to undo this channel, and why
no Web path may call the consuming `ctx.tasks.read()`.
interrupt_agent(agent_id) passes the calling agent as the ancestor
authority for ctx.subagents.interrupt(); the service verifies live
registry identity and recorded lineage, so a direct child or deeper
descendant stops with the same generic parameter while send_message keeps
its exact-direct-parent authority.
Discovery: list_agents gains an optional scope. descendants walks the new
SubagentService.listDescendants() — one lineage trace flattened in stable
pre-order across ordinary and one-shot intermediates, each entry carrying
its verified parentId and depth — and every status now comes from the
live Agent registry (running/idle/complete).
Refs #1535
ctx.subagents.interrupt() stops one live continuable child's current turn
via Agent.cancel(cause, { keepInbox: true }) under either a human durable
parent address or an exact live ancestor Agent. Fire-and-return: admission
is synchronous, quiescence is not awaited. Pending inbox work, the
Activation, and published descendants are preserved; only a later waking
send resumes the parked FIFO queue. Absent, one-shot, and disposing
targets are accepted no-ops.
The new Host RPC subagent.interrupt calls only that primitive with user
authority — no catalog, history, persistence, or parent-registry lookup —
so a live child stays stoppable while its parent Agent is offline.
Refs #1535
The composer's preset seat stays removed here — this layer moved it to the
hero chip and the session-header action — so only the model seat takes the
`modelSeatLocked` narrowing master introduced.
Conflicts:
apps/web/tests/snapshots/*/*.expected.md
packages/client/connection/README.md
packages/client/connection/README.zh.md
packages/client/ui-conversation/src/client/skeleton/InputBar.tsx
packages/host/apiproxy/src/fetch/client.ts
Code Mode was a deployment-wide field on the host `tools` row: a
deployment ran every session that way or none. The obvious product
shape — 代码模式 beside 标准/极简/创造 in the preset picker — had
nothing to hang on.
The registry itself cannot move into a preset; the agent loop's
scheduler, the api-proxy's presenters, and every tool plugin are its
consumers. So split the registry from its projection: `presentAs(mode)`
writes one cell on the calling agent's scope layer, exactly as
`restrict()` does, and the three reads that decided presentation take
that scope's mode instead of the service's. The config `mode` becomes
the default agents shadow rather than a process-wide fact.
Two consequences are load-bearing. `run_code` now enters a view only
for scopes whose own mode presents it — a native agent must not find it
dispatchable because another agent in the process does — and the
reserved name holds whatever the configured mode, since any agent may
select a code mode later.
`dsh-agent-tool-mode` is the row a preset carries to declare this. A
code mode waits for the host's `codeRuntime` rather than assuming it,
so a runtime-less deployment fails the preset at mount, naming the
row, instead of at the session's first request.
The shipped `code` preset is `standard` plus that row, ordered second.
A picker showed directory names, so the settings page could only ever list
`standard` / `core-web` / `cordis` and hope the reader knew what they meant.
A preset may now publish display text in an optional `preset.yml` beside
its composition, and the section renders cards — name, description, and the
one in use — instead of rows.
The file carries display text ONLY. `id` is the directory name and `trust`
comes from the root a preset was discovered under, so neither is writable
there: otherwise a locally authored preset could name itself into the
shipped set. It is a separate file because a composition is a top-level list
of plugin rows — YAML cannot carry sibling keys beside it, and a fake
metadata row would hand the Loader something to load.
Every read failure degrades to no metadata; absent, malformed, wrongly
typed, and blank all mean the same thing and the picker falls back to the
id. Presentation is not capability: a preset whose name is broken still
mounts.
The editor gained name and description fields above the YAML, and clearing
both removes the file rather than storing a blank name.
A preset is a directory holding one `agent.cordis.yml`. Mounting it under an
agent's scope context during `setup(agentCtx)` gives that one session its own
tools and prompt sections while every other live session keeps its own.
No registry gains a tier. `dsh-tools` and `dsh-system-prompt` already file
registrations into the calling context's scope layer, and entry contexts chain
to the context a subtree was plugged into, so a composition mounted under
`agent.ctx` is that agent's alone and unwinds with it.
The mount audits itself because a directly-plugged subtree is absent from
`ctx.loader.entries()` and no boot audit covers it. It rejects an unscoped
target, a row that never became usable, and a row that published a service into
the root service realm — that last one is process-global rather than
per-session, and its collision with the next session surfaces as an unhandled
rejection `setup` never observes, leaving a half-composed agent that looks
healthy. The package invariant re-checks that rule on every service
notification, since a row publishing from a timer would escape a one-shot audit.
Raises the `packages/README.md` word ceiling from 920 to 980: the group table
must enumerate every group, and the new `preset/` row is necessary content.
Design: .agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.md
Once a pi-ai route became a declaration rather than a catalog lookup,
adding an OpenAI-compatible gateway meant knowing its model ids up
front. Most such endpoints publish that list at `GET /models`, but no
seam operation could ask: every one is keyed by a registered provider
route, and the provider being added has no route, no stored profile,
and no stored credential — the endpoint and key are values in a form.
Interrogation is therefore keyed by settings namespace, which a
configuration surface already holds from the configurable-provider
directory. `registerModelDiscovery` offers it per namespace,
`discoverModels` asks, and the request carries the draft itself. The
reply is candidates, not a catalog: every field but the id is optional
because most listings disclose nothing else, and adopting one is a
settings write like any other. Nothing here reads or writes settings or
credentials, so `settings.yaml` still decides what a route serves.
`llm.discoverModels` carries the same draft over the wire. Its apiKey is
the third and last payload a secret may ride, and it is never stored,
logged, or echoed; every refusal folds into `model-discovery-failed`,
naming the endpoint asked but never the credential offered.
The pi-ai side is a plain GET for OpenAI-compatible protocols only —
their listing shape is the one gateways, self-hosted servers, and the
official endpoints agree on. Others say so, sending the user to
hand-entry rather than reporting a guessed shape as an empty provider.
The reply is read under a four-megabyte ceiling held on the bytes
actually received, because the endpoint is a URL the user typed.
Review found four defects in the declared-provider work.
`PiAiAdapter` reused one `Models` collection and mutated it whenever the
configuration changed. `Models.streamSimple()` resolves its provider
lazily — when the stream is first consumed, which is after the adapter
awaits the route's credential — so a configuration change landing in
that window let an in-flight request finish under a configuration it
never resolved against, or fail on a provider that no longer existed.
Each resolution now produces an immutable snapshot and every operation
captures one before its first await, which is what makes the seam's
per-step freeze (`llm.prepareCall()`) hold end to end: switching models
mid-reply takes effect on the next step, never inside the one in flight.
`defaultMaxTokens` was materialized from the catalog's `Model.maxTokens`.
The two answer different questions: pi-ai requires that field as the
model's output capability, while the seam's is a cap the deployment
chose to send on requests naming none, so every request had started
carrying a number nobody picked. Only an explicitly configured cap
reaches the seam now.
The configurable-provider directory was refreshed by disposing its
registration and making a new one. A candidate set the registry refuses
— a profile keyed `deepseek-official`, which llm-deepseek declares —
left the whole directory withdrawn and the Models page empty, silently,
because the settings callback contains the failure. The seam's
registration handle now carries `replace()` with the same
validate-first atomicity `registerAdapter` has.
The protocol table offered every pi-ai streaming API, including four
whose authentication a profile cannot express: Bedrock signs with SigV4
over AWS credentials and a region, Vertex needs a project, a location,
and ADC, Azure needs provider environment plus an api-version, and Codex
uses OAuth. Offering them handed back routes that cannot authenticate.
Catalog routes still reach them through their own provider.
Yichen Jiang