Codex review of the trace-event fold found two merge-blockers.
Blocker #1 — format version. Folding usage onto assistant/message and removing
the standalone usage/error events changed the persisted SessionEventMap shape,
which per the AGENTS.md "bump the version and reject — don't migrate" policy
requires a backend to reject any non-current log. Centralize the version in an
exported SESSION_FORMAT_VERSION constant (dsh-session), read by both write sites
(Session constructor default, SessionStore.prepare header) and the coordinator's
load-time assertVersion check. The constant is pinned at 0: while unreleased the
on-disk format is unstable/pre-release, so breaking shape churn is absorbed at v0
(no monotonic bump until the first tagged release) and any non-0 log is rejected
on load — no migration. Update every test/fixture/doc that stamps a
currently-written header to the constant, bump the ACP snapshot fixture + golden
headers to v0, and keep the version-rejection test meaningful by switching its
bad value to a clearly non-current 99. AGENTS.md documents both the monotonic
(SQLite SCHEMA_VERSION) and pinned-0 (session log) pre-release stances.
Blocker #2 — restore the late turn-end warn. failTurn now sets the error reason
only while the turn is still open; once turn/end is appended (a throwing
agent/turn-end listener after closeTurn) the reason can no longer reach the
durable log, so the late throw is logged via ctx.logger.warn instead of
vanishing into a futile post-close assignment. A regression test asserts the
warn fires.
Also guard the normal-step assistant/message append with the same
content-or-usage condition as the max-tokens branch (a content-less, usage-less
step records no trace-only row), with a covering test.
Model-driving ACP snapshot scenarios shipped both session.jsonl (the
replay fixture) and session.golden.jsonl (the expected re-persisted log).
For recorded scenarios the normalized fixture and golden were byte-identical
— pure duplication. Remove session.golden.jsonl entirely: every model
scenario now has at most one committed session-log artifact, session.jsonl,
which doubles as the replay source AND the expected produced log.
The snapshot test compares the replay run's persisted log against the
session.jsonl fixture, normalizing BOTH sides — but each against its OWN
volatile values, not a shared context. A raw harvested fixture bakes in the
recording run's session id / cwd / timestamps, distinct from the live replay
run's; since normalizeSessionLog scrubs cwd by exact string match, the
fixture must be normalized against its own header (new fixtureContext helper)
or its stale recorded cwd would leak unscrubbed and the compare would fail.
The session side uses a normalized-string toEqual, NOT toMatchFileSnapshot,
so a run never overwrites the fixture.
Authored override scenarios (error-finish, cancel) now hold their expected
produced log in session.jsonl. Verified llm-replay ignores the fixture for
model chunks when an override exists: loadReplayScript() returns the override
array and never reads config.file, so committing the full expected log there
does not affect replay behavior.
The required-fixture guard is now per-kind: every scenario needs input.json +
stdout.golden.jsonl; model scenarios need session.jsonl; authored ones
additionally need replay.override.json. Updates the ACP-snapshot-tests RFC to
the reduced fixture set and moves the proposing RFC proposed -> implemented.
The session event vocabulary carried two standalone trace-only events that
were not load-bearing as separate records. Fold their facts into nearby
load-bearing events and delete the standalone variants.
- Token usage now rides on `assistant/message` as an optional `usage` field —
the assembled model output and its accounting travel together. The loop folds
`assembler.usage` onto the append instead of emitting a separate `usage`
event.
- The max-tokens path is the no-data-loss host: a step cut off with usage but
EMPTY content (e.g. only a dropped tool call) previously emitted a standalone
`usage`; it now records an empty-content `assistant/message { content: [],
usage }`. `deriveMessages()` skips empty-content assistant messages, so the
usage host never injects a spurious content-less assistant turn into the
provider transcript. A step with neither content nor usage appends nothing.
- An operational error's step number now rides on `turn/end.reason` for
`kind: 'error'` (`{ kind: 'error', step, message, code? }`) — the durable
turn outcome ACP and resume already consume. `failTurn` sets the reason
directly (no separate session `error` event). `agent/error` + logging are
unchanged for live diagnostics.
- No format-version bump: pre-release, no persisted data, so per the format
policy there is nothing to migrate or reject (the RFC's "refresh the format
version" criterion over-reached). `version` stays 1.
- ACP fixtures + goldens re-recorded (keyless replay): dropped standalone
usage/error lines, usage folded onto assistant/message, error step on
turn/end.reason.
RFC moved proposed -> implemented with an implementation note recording the two
scope refinements.
Codex's no-ship was a completeness/docs-sync gap, not loop behavior:
- docs/architecture.md: drop the public abort() handle row; the teardown
signal is now cancel() then await whenIdle().
- cancel.spec.ts: the module doc and the turn-start comment contrasted
cancel() against a public abort() verb that no longer exists — reword to
name the loop's private step AbortController.
- packages/ui/acp/src/index.ts: the post-resume-leak comment cited abort();
cancel() is the surviving stop verb that likewise does not unregister.
- Move the RFC proposed -> implemented/simplification with amended text:
Status flips, the both-removal proposal is narrowed to abort-only, and an
implementation note records why whenIdle() is retained (load-bearing
quiescence primitive with live ACP consumers). Update docs/rfc/README.md.
- AGENTS.md "RFCs are proposals, not golden truth": add the concrete
abort/whenIdle worked example now that the implemented RFC exists to link.
- Regenerate the cordis catalog (line-number drift from the rebase).
The public Agent handle exposed abort() (step-only) and cancel() (queue-aware).
No production caller used abort() — ACP maps session/cancel to cancel(), and
lifecycle owners tear down via AgentHandle.dispose(); the loop's own stop paths
abort their per-step AbortController directly. So abort() is latent generality
that keeps a private loop mechanic public.
RFC-premise correction: the public-agent-stop-surface RFC proposed removing
whenIdle() too. Implementation found whenIdle() load-bearing — a real
quiescence primitive with a deliberate loop contract (settle-without-transition,
the replacement-turn race) and ACP test consumers; its proposed replacement
("observe the running->idle transition") is exactly the async-state race
AGENTS.md warns against. So only abort() is removed; whenIdle() stays. The RFC
is amended on the way to implemented/ to record the narrowed scope, and the new
AGENTS.md "RFCs are proposals, not golden truth" principle (PR1) gets its
worked example.
- Remove Agent.abort() from the interface + the ReactLoopAgent impl; the no-arg
'aborted' default goes with it (cancel() keeps its 'cancelled' default).
- Migrate tests: empty-queue abort() -> cancel(reason); the two review-fixes
tests whose subject is the in-flight step's AbortController drive that
controller directly via the private currentAbort field (cancel() would clear
the inbox and destroy the queued steering one of them proves survives a step
abort). The no-arg-default test is dropped (cancel()'s default is already
covered in cancel.spec.ts).
- Resulting public stop surface: cancel() + whenIdle(). Update agent/agent-loop
READMEs, architecture.md, core.md type-equiv, the extension cookbook, the
lifecycle RFC (short note), and the proposed ACP RFC.
Implements docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md
Type-only change (brands are zero-cost casts; no runtime/wire impact). Closes
the two gaps in the "brand ids that cross package boundaries" policy and fixes
the dependency direction so a capability package never pulls in an unrelated one.
- Extract the `Branded<B>` primitive into a new standalone type-only package
`@deepseek-ai/dsh-brand` (packages/util/brand) with no harness-package deps.
dsh-llm keeps its owned CallId but imports Branded from dsh-brand; dsh-session,
dsh-agent, and dsh-bash all import Branded from there. dsh-bash depends on
dsh-brand ALONE — never on dsh-llm or dsh-session (the architectural fix: a
generic execution backend must not couple to the LLM or session vocabulary).
- Mint BashTaskId + OwnerToken in dsh-bash and thread them through BashTask.id,
the get/ownerOf/list/readOutput/kill seam, the bash-local generation site, and
the dsh-tool-bash validate/access surface. OwnerToken is a DISTINCT brand from
SessionId so the seam stays decoupled; dsh-tool-bash is the single boundary
that casts SessionId -> OwnerToken.
- Brand at the SOURCE, not via mid-pipeline casts: agent-loop's Config types
agents[].id as AgentId and resumeSessionId as SessionId, so the brand enters
at the config boundary and the inner create()/resume casts disappear (only the
genuinely-new per-run session-id string is cast).
- Stop brand erosion: propagate CallId/SessionId/AgentId to the registry/store
Map keys and public params/exports (SessionStore, AgentRegistry + factory
options, the ACP session-id surface + ToolPresenter CallId map, the
persistence coordinator, invariants pendingCalls, the pi-ai tool-call maps).
- Docs: document BashTaskId/OwnerToken in bash.md (type-equiv re-pasted), point
the Branded type-equiv at dsh-brand, fix stale param types in the session/
agent/bash READMEs, regenerate the cordis catalog + module graph.
Implements docs/rfc/proposed/architecture/2026-06-20-branded-ids.md
The original prune removed BashExecutor.get()/.list() too, but each is a
one-line accessor over the executor's already-tracked tasks map, and removing
them forced dsh-tool-bash's tests onto a ~35-line onTaskDone completion-tracking
harness just to replace the one-line ctx.bash.get(id) lookup. Per the AGENTS.md
"RFCs are proposals, not golden truth" principle, that disproportionate
migration cost is evidence the methods earn their keep — a test harness IS a
consumer programming against the seam.
Restore get()/list() (seam + LocalBashExecutor impl + the bash tests that used
them, dropping the doneFor/trackCompletions scaffolding). The persistence
has()/delete()/deleteStored removal stands — it had only contract-test callers
and no test-ergonomics cost. The RFC is retitled persistence-only with an
implementation note recording the bash revert.
Second Codex pass caught two proposed RFCs that describe the bash seam as it
WAS (with get/list) and would read stale once this prune lands, plus a latent
test-helper edge:
- docs/rfc/proposed/architecture/2026-06-20-branded-ids.md and
2026-06-20-generic-long-running-tool-runtime.md: drop get/list from the
BashExecutor seam description (surviving: resolve/run/start/ownerOf/
readOutput/kill/onTaskDone). branded-ids will be further updated when it is
implemented; this keeps it accurate in the meantime.
- trackCompletions now records every completion to `done` unconditionally (and
also wakes a parked waiter), so a second doneFor(id) after completion resolves
instead of hanging.
Codex review of the PR2 diff caught doc/comment sites doc-sync does not gate
(core-data-structures prose) and a latent test-helper race:
- docs/core-data-structures/persistence.md + bash.md, sqlite README, and two
source comments (coordinator.ts, jsonl.spec.ts) still listed the removed
has/delete/get/list methods — updated to the surviving four-method
persistence surface and the get/list-free bash seam.
- doneFor(ctx, id) attached its onTaskDone listener lazily, after the task
could already have closed (e.g. `true`), so it could miss the completion and
hang. Replaced with trackCompletions(ctx): one eagerly-installed listener
(mounted in setup() before any task starts) records every completion, and
doneFor resolves immediately for an already-finished task or on completion
otherwise. Race-free, and there is no get-by-id seam left to poll instead.
Two capability seams carried abstract methods no production consumer calls.
A method no consumer programs against is not a seam — it is speculative
surface every implementation must still provide and test.
- SessionPersistence: remove has() and delete(), the coordinator's
has/delete/deleteCore, and the PersistenceBackend.deleteStored hook (with its
jsonl + sqlite + in-spec memory-stub impls). Surviving service surface:
create/append/load/list. Production uses only load() (resume) and list()
(ACP session/list).
- BashExecutor: remove get(id) and list(), the abstract decls and the
LocalBashExecutor impls. The internal tasks map survives (it backs
ownerOf/readOutput/kill); get/list were pure public accessors over it with no
shipping caller and no bash_list tool.
- Migrate tests that reached through ctx.bash.get(id) to the public completion
seam: a doneFor(id) helper over onTaskDone awaits a task by id, and the
HMR-reload ownership test now proves task survival through A's own bash_output
([status: running]) plus ownerOf + B-rejection — a stronger through-the-tool
assertion than the removed lookup peek.
- Update seam READMEs (six -> four service methods, drop the deleteStored hook
and the get/list row) and the two implemented persistence RFCs in place.
Implements docs/rfc/implemented/simplification/2026-06-20-prune-dead-seam-methods.md
Codex review of the PR1 diff surfaced docs/cleanup drift:
- LlmService class JSDoc still advertised "streaming / non-streaming call
surfaces, both interceptable via waterfall events" — corrected to the single
streaming surface; regenerated the cordis catalog so its mirror updates.
- Removed GenerateResult from gen-cordis-catalog.ts LINK_MAP (the type is gone).
- The adapter-change RFC's acceptance criterion named the retired
verify-event-taxonomy gate; updated to verify-cordis-catalog.
- Dropped the now-tautological "streaming and one-shot assembly agree" property
test (the streaming/one-shot distinction lived in the removed flush API;
usage/finish remain covered by assembler.spec.ts and the finish property).
The LLM service exposed three call surfaces (stream/streamBlocks/generate) but
the only production consumer — the agent loop — uses stream() exclusively,
feeding raw chunks through its own BlockAssembler for replay fidelity. Drop the
speculative convenience surfaces and the registry-change event that no listener
consumed, leaving stream() as the single model-call contract for both
production and tests.
- Remove LlmService.streamBlocks() and generate(), the llm/generate waterfall,
and GenerateResult.
- Remove the llm/adapter-change event (declaration + emits) and the
listener-throw rollback ordering that existed only to protect it; keep the
HMR rollback disposer.
- Remove BlockAssembler.flushReady()/flushRemaining()/result() and the flushed
cursor — the streaming-flush slice existed only for streamBlocks().
- Adapter tests drive a stream()+BlockAssembler helper (tests/assemble.ts)
instead of generate(), exercising the same path production uses.
- Land the AGENTS.md "RFCs are proposals, not golden truth" principle and move
both RFCs proposed -> implemented.
Implements:
- docs/rfc/implemented/simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md
- docs/rfc/implemented/simplification/2026-06-20-drop-unconsumed-llm-assembled-surfaces.md
The merge brought in two new proposed/architecture RFCs that reference
the old flat packages/<name> paths and the package-hierarchy RFC's old
proposed/ location. Rewrite their package paths to the grouped layout and
repoint the cross-link to implemented/architecture/ — the verify-package-paths
and verify-md-links gates caught both.
Self-audited every factual claim against the shipped branch (hierarchy
tree, no group manifests, the dsh-* paths wildcard in both tsconfigs,
publint glob, explicit build references, the two new gates). Phrase the
paths-wildcard bullet as current state, and record the doc-typecheck
JSONC-parse subtlety the wildcard introduced so a future editor does not
reintroduce the regex comment-strip bug.
git mv it from proposed/ to rejected/architecture/ (preserving history)
and fold the supersede note into a one-line rejected Status. The
extract-example-app-packages RFC subsumes it: once the spine moves into
dsh-agent-core and the base*.yml files are deleted, there is no shared
base YAML left to rename. Move its README row to Rejected -> Architecture
and repoint the supersede cross-link to the new path.
Add a README to each group dir (core/llm/bash/session-persistence/ui/
support) stating its role and product-vs-support classification, and
rewrite packages/README.md around the hierarchy (group table, grouped
"what goes where", removed the package-hierarchy FIXME).
Move the package-hierarchy RFC to implemented/architecture/ and rewrite
it to describe what shipped (placement rationale, the paths-wildcard and
publint dedup, the two new guardrail gates). Fold the remaining
tsconfig.build.json references dedup into the discover-package-inventory
proposal and fix its cross-link.
Update AGENTS.md: regrouped repo-layout map, depth-2 globs, the new
verify-package-paths gate in the doc-sync listing, and a note that we
lean toward stricter lint in the agentic-coding era (machine-caught
errors and a consistent foundation outweigh the one-time cost).
Self-review against the actual source surfaced three imprecisions:
- agent-loop placement: the core bundle forwards agent-loop's `agents`
list as its own config (default []), matching AgentLoop.Config, rather
than hardcoding []. This is what lets a shared core coexist with stdio
pre-creating `main` and acp pre-creating none — and it directly rebuts
the reason base-core.yml gives today for keeping the loop out of core.
- timer is universal and stdout-safe, so it lives in the shared spine,
not the per-app front-door cluster (only logger + hmr are app-specific).
- model/systemPrompt land in different places per app (stdio onto the
pre-created agent, acp onto the bridge plugin), routed by the app
package's own Config — not a single uniform bundle entry.
Merge brought in the RFC-classification reorg and two new doc gates;
rewrite every drifted packages/<name> cross-link (Markdown link targets,
moved-README relative depths, and .ts comment paths) to the grouped paths.
Add two doc-sync/hygiene gates so the manual checks this restructure
needed become automated:
- verify-package-paths.ts: flags a packages/<path> reference (in Markdown
or a .ts comment/string) that does not resolve AND names a real package
in a segment — i.e. a stale path to a MOVED package. A path naming a
non-existent package (a forward-looking proposal) is left alone, so it
applies uniformly across proposed/implemented/rejected.
- check-workspace-constraints: assert the packages/<group>/<pkg> depth-2
shape (group dirs carry no package.json; no flat or over-nested
packages). Group names stay open; only the shape is fixed.
- Correct the SessionStore signature: `get(id: string)` is non-optional,
not `get(id?: string)` (only create/prepare take an optional id).
- Broaden the ACP brand-erosion description and the acceptance criterion
beyond `Map<string>`: the session-id surface also includes the
`bySession` WeakMap, the `loadingIds` Set, and the exported
`streamSessionEventUpdate(sessionId)` signature.
- Use bare inline code spans for code paths instead of markdown links,
matching the house style of the other architecture RFCs and removing the
link/bare-span inconsistency within this file (doc-to-doc cross-links
stay markdown links per docs/AGENTS.md).
Add a proposed architecture RFC to make the examples folder thin: each
example becomes mostly an invocation of an app package. A shared
dsh-agent-core bundle owns the providerless spine; dsh-stdio-agent and
dsh-acp-agent app packages bake in their coupled front-door cluster
(UI + logger/hmr policy + agent pre-creation), turning the ACP
stdout-purity footgun into a property of the artifact. Leaf cordis.yml
shrinks to backends + config; start.ts is dropped in favor of a package
bin.
Supersedes the providerless-example-base RFC (cross-linked) and indexes
the new RFC under Proposed -> Architecture.
Move the 18 flat packages/<name> packages into role-grouped dirs:
core/, llm/, bash/, session-persistence/, ui/, support/. Group dirs are
pure containers; each package keeps its @deepseek-ai/dsh-* name.
Collapse the per-package tsconfig paths maps (base + typecheck) into one
@deepseek-ai/dsh-* wildcard with a candidate per group, and derive the
publint list from the hierarchy. Update all depth-coupled globs/configs
(workspace, tsdown, vitest, eslint, knip, tsconfig includes/refs,
per-package tsconfigs, generators, doc-script scopes, type-equiv manifest)
and the cross-package/script relative imports in tests.
Fix doc-typecheck's workspacePaths() to parse tsconfig JSONC via the
TypeScript API instead of a regex comment-strip, which corrupted the
new wildcard `/*/` path candidates.
WIP: doc cross-links and package/RFC docs still to update.
Extend the existing Branded<B> machinery (CallId/SessionId/AgentId) to the
unbranded cross-boundary IDs that meet the brand.ts policy bar — chiefly the
model-facing bash task id (BashTask.id, the `bash-N` counter that shares
SessionId's `name-N` shape) and a distinct OwnerToken brand for the bash
owner token — and fix the brand erosion where existing brands decay back to
`string` at Map keys and method params.
Scoped focused per the "not every string needs a brand" policy: ModelId,
ToolName, numeric ordinals, and validated construction are listed as
deferred extensions, not in-scope work. Filed under proposed/architecture.
Add a second axis to every RFC — its class (feature, bug-fix,
simplification, architecture, process, testing) — encoded in the path
as docs/rfc/{lifecycle}/{class}/file.md. The folder is the label, so
the closed set is enforced by structure rather than a parsed field.
Two new doc-sync gates back it:
- verify-rfc-classification: every RFC sits in a valid class folder and
the README index lists it under the matching lifecycle→class heading.
- verify-doc-refs: every docs/*.md path cited in a packages|examples TS
comment resolves — closes a drift class verify-md-links can't see, and
catches the four comment refs this reorg moved.
The README gains a Classification section explaining the taxonomy and
per-class index sub-sections. A self-referential process RFC records why
the scheme is path-encoded and gated.
PR #71 shipped the core-data-structures catalog and the verify-type-equiv
drift gate without an RFC (judged small at the time). Add the retroactive
implemented RFC so the sibling pair is documented symmetrically: the
spine-vs-seam scoping rule (discovered by testing candidate definitions against
borderline types like BashExecRequest and ToolDefinition), the
verbatim-match-over-assignability choice for the gate, and the process —
including the Codex-caught scan-gap bug fixed in 6da7a0f. Cross-link the two
catalog RFCs to each other and index the new one.
- Exclude protected methods from the generated service interface: a protected
member (e.g. BashExecutor.notifyTaskDone) is a subclass hook, not part of the
public ctx.<key> surface a plugin author calls. The method filter now drops
private, protected, and static.
- Add BashTaskRead to the type cross-link map so readOutput()'s return type
links to its core-data-structures page.
- Reword the generator module comment and the AGENTS.md @mode rule to state the
current capability without narrating the retired event-taxonomy verifier
(that history lives in the RFC).
Add scripts/gen-cordis-catalog.ts: a fully-generated docs/cordis-catalog/
events-and-services.md cataloging every cordis event (exact signature + @mode)
and ctx.<key> service (exact interface), modeled on gen-module-graph's
--write/--check freshness gate. The harness tier renders in full from the
interface Events / interface Context declarations and their JSDoc; the inherited
cordis-core/loader/hmr/timer surface renders tersely from a curated table.
The generator hard-errors on a missing @mode tag and on a tag that contradicts
a conclusive signature shape (a trailing next param is structurally a
waterfall). Signature blocks use a ts cordis-catalog fence that doc-typecheck
skips. Type tokens cross-link to the core-data-structures catalog.
This supersedes the hand-maintained event-taxonomy table: verify-event-taxonomy
is deleted and verify-cordis-catalog joins doc-sync. architecture.md keeps the
Event taxonomy heading (TOC anchor) but points at the catalog; the Service-map
role table stays. RFC, AGENTS.md @mode authoring rule, and dependent doc/skill
references updated. Negative gate tests cover the missing-tag and
tag/shape-contradiction paths.
Review found verify-type-equiv only scanned docs the manifest already named, so
a type-equiv block in an unmanifested doc was silently skipped — defeating the
1:1 guarantee. Scan all docs in the markdown glob scope instead, so an orphan
block in any doc is caught. Also parse `abstract class` in blockSymbol (matches
sourceDeclaration's class support).
persistence.md listed the SessionPersistence surface as create/append/load/list;
the abstract service also exposes has/delete. AGENTS.md's doc-sync command
summary omitted verify-md-links and verify-type-equiv.
A new docs/core-data-structures/ folder: a self-contained core.md defining what
counts as a "core" data structure (the agent-loop spine) and covering the spine
vocabulary, plus per-seam sub-pages (llm-streaming, session, persistence, tools,
bash). Type definitions are pasted verbatim via `ts type-equiv` blocks and
drift-checked by verify-type-equiv. Cross-linked from architecture.md; the
`ts type-equiv` mechanics are documented in development.md.
Review follow-ups on the bash owner-token PR:
- packages/acp/README.md still described task isolation in object-identity terms
("records each background task's owning agent", "a different agent"). Rewrite
to the session-token model: ownership is by `session.header.id`, stored on the
executor's task, so a different Agent object on the same session may access it
and ownership survives a tool-bash HMR reload.
- The reviewer flagged that the notice routes by `session.header.id` while the
registry only enforces unique `agent.id`, so a programmatic caller could
register two agents sharing a session token and mis-route a notice (not
reachable via ACP). Rather than bolt a session-id invariant onto the generic
registry, add a proposed RFC (2026-06-20-unify-agent-and-session-id) to remove
the precondition by construction — an agent IS its session, one id — with a
full risks discussion (forecloses multi-session-actor / fork futures, makes the
config resume-or-create policy load-bearing, migration churn). The actual
unification ships as its own Codex-converged PR. Cross-linked from the
agent-lifecycle RFC's seam-precondition note.
- Reframe the tool-bash module-doc ownership paragraph to current-state (per the
new AGENTS.md doc convention): contrast storing the token on the executor vs
in the plugin as a standing rationale, not as "closing the old gap".
A reviewer found that window 2 (a cancel from a synchronous agent/status('running')
listener) had the same early-whenIdle() race that window 1 already guards: it
unconditionally `setStatus('idle')` + continue, which settles `whenIdle()`
waiters — so if the running listener cancels AND queues replacement work, the
waiter resolves while the replacement is still queued-and-unrun (the next
iteration runs it later, but the caller already observed quiescence).
Mirror window 1: after clearing the marker, only `setStatus('idle')` when
nothing new is queued; otherwise fall through to run the queued replacement
(status is already `running`), so `whenIdle()` resolves on that turn's
running→idle. Regression test reproduces the reviewer's interleaving (running
listener cancels A, sends B; whenIdle() resolves only after B ran).
Also syncs the cancellation contract in the two ACP RFCs that describe the live
behavior: `session/cancel` is the queue-aware `agent.cancel()` (drops an
about-to-start turn), not the old best-effort `agent.abort()` pre-step
limitation.
Delete the `taskOwner: Map<string, Agent>` entirely — it served two roles
(access control AND holding a live Agent for completion notices), both now
stateless:
- Access control: `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to
the caller's token (`exec.agent?.session.header.id`) with `!== undefined`
semantics (an empty-string token is still a real owner). The owner is stamped
at spawn via `resolve({ …, owner })`. Ownership now lives on the task in the
executor, so it SURVIVES a tool-bash HMR reload — closing the old
XXX(tool-bash-owner-hmr) gap.
- Completion notice: `onTaskDone` reads `ctx.bash.ownerOf(task.id)` and finds
the live agent by scanning `ctx.get('agents')?.list()` for a matching
`session.header.id` (read via `ctx.get` — the listener runs on the bash
fiber, a foreign fiber, where the `ctx.agents` proxy would throw). No
registry / owner gone → drop the notice cleanly.
Token is `session.header.id` (NOT `session.id`): every other subsystem keys off
the header id, and the test fakes populate only `session.header.id`, so reading
`session.id` would make every fake unowned and pass the isolation tests for the
wrong reason.
Tests give A and B DISTINCT real session tokens (a same-token-different-Agent
case is now ALLOWED — identity no longer matters); the HMR test inverts to
assert ownership SURVIVES a tool-bash reload; a new test covers the
owner-agent-gone-before-completion drop. Migrates the agent-lifecycle RFC
proposed->implemented (recording all three seams + the session-id-uniqueness
precondition) and updates the tool-bash README + the now-implemented RFC's
cross-links.
Background-task ownership needs a stable home that survives a consumer HMR
reload. Add an optional `owner?: string` to `BashExecRequest` and a
required-but-nullable `owner: string | undefined` to the resolved
`BashExecSpec` (mirroring how `workdir`/`timeoutMs` are required on the spec —
a forgotten owner is a visible `undefined`, never a silently-absent property
that yields an unowned, cross-session-readable task). `resolve()` carries it
through.
Expose the stored token via a new `BashExecutor.ownerOf(id): string |
undefined` seam (ONE read path — not also on the public `BashTask`). The
executor stores and returns the token verbatim and NEVER interprets it: the
access POLICY lives in the consumer (`dsh-tool-bash`). `bash-local` stores
`owner` on its `TrackedTask` and implements `ownerOf`; unknown-id and
known-but-ownerless both read as `undefined`. Because ownership lives on the
task in the executor (disposed with the `dsh-bash` fiber), it survives a
`tool-bash` HMR reload.
Updates the StubExecutor seam test and the bash/bash-local READMEs.
The bridge now holds each session's `AgentHandle` disposer in its
`SessionRecord` and runs it on teardown (client disconnect or fiber dispose)
instead of the old `abort()` + `whenIdle()` drain that left agents
registered. A bare client disconnect now leaves NO registered agent and NO
session-store entry — not an idled-but-still-registered one. The queue-aware
`cancel()` inside the disposer also closes the former pre-step best-effort
window (a turn about to start is dropped), so teardown reaches true
quiescence.
The `session/load`-races-teardown leak is fixed: if the bridge closed while
`resume()` was pending, the just-resumed handle is disposed before throwing,
so it leaves no orphan (it has no SessionRecord, so quiesce() never sees it).
Tests: the disconnect test now asserts (through the SAME memoized teardown)
that the agent is unregistered AND its session removed; a durability test
re-loads the persisted log after dispose and asserts the closing turn/end is
on disk (guards the teardown-order contract); a sibling-isolation test proves
one handle's dispose() leaves other agents untouched. Docs: agent /
agent-loop / acp READMEs, architecture.md, and the stale in-code quiesce()
ownership comment updated to the per-agent disposal model; the now-resolved
TODO(rfc010-agent-disposal) / TODO(rfc010-cancel-prestep) teardown notes
removed.
abort() only kills the in-flight step, so a queued-but-not-yet-started prompt
ran to completion after a cancel and a prompt accepted right after could be
batched into the cancelled turn (the loop merges queued messages into one turn).
This closes TODO(rfc010-cancel-prestep) with a distinct cancel() verb.
cancel() clears the queued + steering FIFOs, aborts the in-flight step, and
drives a turn-scoped marker on the LoopHandle that the driver checks at EVERY
point a turn could start or continue:
- right after the idle wait (window 1): drop the about-to-run turn and settle
whenIdle() waiters directly (no running→idle transition fires, and no
agent/status is emitted, so an ACP listener can't see a spurious idle that
resolves a freshly-queued prompt as cancelled);
- after the synchronous setStatus('running') emit (window 2): a running listener
can cancel in the gap before runTurn;
- in the step-start window (before runStep, after setAbort): a synchronous
turn-start/step-start listener can cancel before any AbortController exists;
- at the continuation gate: a cancel during the continuation waterfall (the
finished step's controller already cleared) ends the turn aborted.
The marker is ARMED only when there is something to cancel (running, an
in-flight step, or queued/steering work) — an idle no-op cancel cannot leave it
set to drop a later prompt — and RESET unconditionally once per loop iteration,
so it governs exactly one turn and never leaks onto the next prompt (even when a
send() lands in the cancelled turn's flush window).
ACP session/cancel now maps to agent.cancel() (keeping the synchronous
settlePrompt). Teardown/disconnect still use abort('disposed') until PR D, so
the ACP README narrows the remaining best-effort window to teardown only.
Tests (agent-loop/cancel.spec.ts) cover every window unit-level (the F1 hang
guard: a whenIdle() waiter registered before a pre-step cancel resolves; the F2
leak guard: idle cancel then a prompt runs; mid-step, continuation, both
pre-step windows, turn-start-listener, steering-cleared, marker-reset). ACP
turns.spec.ts adds the through-bridge tests with NO intervening whenIdle (idle
cancel→prompt runs; mid-stream cancel→immediate next prompt runs) and updates
the stale pre-step test to the queue-aware guarantee. The existing cancel
snapshot golden is byte-identical (it drives the new cancel() path end-to-end
through the real subprocess), so no new golden is needed. 100% coverage.
The JSONL and SQLite backends were byte-identical (or same-algorithm) for ALL
of their write-path orchestration — the four maps (states/buffers/chains/inits),
installWritePath, initFor, onCreated's four adoption cases, flush, drain,
serialize, adopt/adoptLivePrefix, assertVersion, and the create/append/load/
has/delete skeletons. Only the storage primitives (write bytes vs INSERT rows)
differed, so every fix landed twice.
Extract that orchestration into a PersistenceCoordinator in the seam package.
Each backend composes one (new PersistenceCoordinator(ctx, this)), implements a
small PersistenceBackend hook interface (loadStored, loadLive, appendBatch,
commitRepair, deleteStored, list, optional close), and delegates its six public
service methods to it. Composition, not inheritance — a backend exposes only the
hooks, can't reach the coordinator's private state, and the public
SessionPersistence API is unchanged so a third-party backend may still implement
it directly.
The crash-repair torn-tail token is OPAQUE: the coordinator computes the
synthetic closers (it owns interruptedTurnClosers) but only tests
`tornMarker !== undefined` and round-trips it to commitRepair, never inspecting
it (JSONL = byte offset, SQLite = seq). loadStored vs loadLive stay distinct so
HMR adoption is cwd-scoped (a same-id log at a different cwd is a collision, not
a resume). appendBatch carries meta so lazy-materialize + first-batch commit
atomically (no separate materialize hook).
Tests: the duplicated orchestration tests (adoption, HMR, collision,
dispose-drain, crash-tail) move into one runCoordinatorContract suite run once
per backend (memory + jsonl + sqlite) via hook fixtures; per-backend specs keep
only storage mechanics. A through-coordinator torn-tail test per real backend
keeps the commitRepair-with-marker branch covered under the 100% gate.
Net -112 lines (the dedup outweighs the new coordinator + shared suite); 100%
coverage; backends shrank ~1200 lines of duplicated churn. Migrates the
write-coordinator RFC proposed -> implemented.
Codex's converge pass on PR A flagged three now-false references the deletion
left behind:
- the proposed write-coordinator RFC still listed an "update summary" backend
hook and "sidecar behavior" in its test focus;
- the JSONL README's format-version note still said a format change needs a
"version bump + migration" (contradicting the no-migration pre-release stance);
- a stale "sidecar pathing" comment in findLog's cwd-recovery branch.
All three corrected to current truth.
Tianyi Cui