Interrupting a local child can preserve unclaimed steering while leaving the Agent idle. Activation residency intentionally continues in that state, but completion barriers joined its result forever. The real SDK server reproduced the hang for both direct children and a nested parked leaf.
Join progressing work and cleanup while retaining parked inboxes and their activation results. Observe local activity and maintenance, external execution, unpublished ownership holds, and materialization; rescan after changes. Recheck resumed Agents after concurrent idle observations. Inbox insertion and ownership publication wake pending observations, so late non-waking injection cannot strand a result wait. Existing descendants remain responsible for their own work; no second state store or polling timer is introduced.
Document that persistent SDK/ACP hosts keep these children available for later wake-up, while headless shutdown discards unclaimed input. Simplify the final settlement recheck to retry changed readiness uniformly. Update generated API and event references from their sources.
Validation: real SDK negative controls fail at both depths on the prior manager with clean teardown; 545 tests pass across 27 files. Manager, local activation, and headless runner each reach 100% statements/branches/functions/lines. Six deterministic races cover revival, preparation publication/rollback, flush-time injection, and late children. doc-sync 42/42, targeted build, lint, and whitespace checks pass.
A child completion can wake the parent after its first completed turn. If
that summary cannot append turn/start or turn/end, AgentLoop reports an
agent/error and contains the rejected driver. Whole-agent idleness then
resolves, but the headless runner previously reused the older completed
terminal and exited successfully, sometimes printing the older answer.
Retain failures from the exact owned Agent with the current Session log
offset. Only a later terminal committed by the same Session clears that
failure. After work and persistence drain, fail the run before emitting a
final answer when no such terminal exists. Dispose both observers with
the run. Ordinary durable error outcomes and later successful recovery
continue to use the log's final terminal.
Add real AgentLoop regressions for missing summary start/end commits in
plain and JSON output, ordinary hook failures with and without recovery,
recovery after persistence failures, and unrelated Agent errors. Update
the bilingual exit contract and generated event consumer matrix.
Validation: 106 headless package tests; 100% runner statements, branches,
functions, and lines; 9 focused terminal-failure tests after the typed
append wrapper correction; package TypeScript build; full lint including
host build; 21 quick documentation checks; 42 doc-sync checks; diff check.
Integrate master 78ae4fc2d4d8ecaebb4b674028f781a358b92cc9 after the four
independent review fixes. Keep this base update separate from those fixes
and from subsequent review changes so the integration is independently
reviewable and the observed-master checkpoint remains preserved.
Retain activation-owned execution, caller-independent local discovery,
and unconditional parent final-answer delivery. Preserve master's preset
scoped scheduling tools and all delegated-child schedule deny rules. Move
the new scheduling regression from the removed driver package into the
surviving subagent package and run it through a real Spawn activation.
Preserve master's removal of runtime invariant plugins, dependencies,
exports, and test mounts. Keep context disposal before fixture directory
cleanup. Combine Python workflow ordering with activation/catalog events
without inventing unsupported source-plane import paths.
Keep all frozen Agent Note archives byte-for-byte identical to master;
do not accept Git's automatic edits to renamed archived notes. Retain
current lifecycle and delivery facts in active documentation, repair its
links, and regenerate catalogs/persistence schemas from merged source.
All 62 master persistence roots remain; only subagent/catalog gains the
PR's external membership extension. Keep master's third-party lock graph
and update only workspace dependency changes.
Validation before this checkpoint: 683 focused tests passed, seven
Windows-only cases skipped; 2,772 archived artifacts verified. Generated
catalog and active-pair checks passed. Fresh artifact build and remaining
build-dependent documentation checks continue before publication.
Delete @deepseek-ai/dsh-invariants, every package's ./invariant companion
and its tests, the invariant gates and Vitest setup, the scoped-event
resolver generator, and the INVARIANT-coded listener rethrow paths.
Update docs, READMEs, Agent Notes, and add an upgrade guide.
Address the ds-review-bot suggestions on 4099b84ee8:
- The post-resume comment scopes the write lease to other processes, so it no
longer contradicts the post-idle re-check that defends against a same-process
overlay writer.
- The Agent Note attributes `pnpm-lock.yaml` to the new
`@deepseek-ai/dsh-session-query` workspace link instead of the shared chunk,
which `scripts/check-workspace-constraints.ts` and the manifest publish.
- The package summary keeps "leaves nothing running behind", so it does not
imply the runner leaves no persisted Session behind.
Address the ds-review-bot findings on 472554a29e:
- resolveAgent refuses an Agent already live under the requested id: its owner
may still drive it, and `whenIdle` is not a single-message signal, so the
one-shot runner cannot own an exclusive run interval over it. The adoptability
rules still run first so the refusal stays specific.
- Refresh the README intro, identity section, and limitations, and the Agent
Note live-identity rule and change scope, for adopt-only.
- Clarify the loader-smoke `cwd` JSDoc (the prefix/parent inputs are ignored)
and pin the resumed wake's final text in the two-wake e2e.
Address the ds-review-bot findings on 9aea4b0804:
- Drop the stale "freshly created" wording from the resolveAgent `@returns`
and rewrite its leading comment for the two remaining identity paths.
- Rewrite the README run-flow paragraph (EN and ZH), the intro sentence, and
the cordis.patch.yml header comment for adopt-only.
- Add a real-composition two-wake e2e: capture the generated id from the first
`--json` wake, resume it by `--session-id`, and assert one persisted log holds
both tasks. `runLoaderSmoke` gains an optional caller-owned `cwd` so both
wakes share one world; the harness leaves that directory in place.
`--session-id` now adopts only: an id with no stored Session fails before the
task runs instead of creating an empty history the caller believes it is
resuming. A first round omits the flag, and the runtime reports the minted
`session-<uuid>` identity in the opening `session` event, so a supervisor
persists it and names it on every later wake.
Updates the help text, the README pair, the Agent Note pair, the generated
config catalog, the unit suite, and the product-profile e2e.
Address the ds-review-bot v11 review on PR #3849:
- Accumulate every attempt's usage into `step_end.usage`, including a retried
attempt whose only sample sits in its discarded `assistant/attempt` stream.
- Re-check the adopted Session after the idle wait, so a preset selected in
that window is still rejected.
- Reject a whitespace-only `sessionId` supplied through a Cordis overlay, which
bypasses the CLI trim check.
- Narrow the documented error contract: a profile whose own plugins fail to
load exits before the runner mounts and keeps only stderr diagnostics.
Address the ds-review-bot v10 review on PR #3849: `boundJsonLine` bounded the
serialized JSON but not the newline the writer appends, so an event that
serialized to exactly 32 KiB produced a 32 KiB + 1 byte record. Reserve the
terminator byte inside the cap, document the cap as newline-inclusive, and
assert the written record length in the boundary tests.
Address the ds-review-bot v9 review on PR #3849:
- Require `sessionQuery` before the live fast path too: a later process has no
live Agent and must find the id through the query service, so a live identity
no longer bypasses the check.
- Soften the live `stat` comment to what it proves: a stored record rules out an
in-memory registration, while write-handle ownership is not queryable.
- Complete the `parseArguments` JSDoc and fix the broken English sentence in
README.md and the Agent Note.
Address the ds-review-bot v6 review on PR #3849:
- A persisted `agent-preset/selected` record whose `data.agentPreset` is not a
non-empty string used to read as "no preset", letting the run continue under
this bundle's composition. It now fails closed.
- A live identity now has to be known to `sessionPersistence` (`stat`), since
an Agent registered only in memory has no write handle and would flush
nothing.
- Tool arguments that JSON cannot round-trip (an overflowing number such as
`1e400`) keep their raw text instead of the `null` JSON.stringify reports.
Address the ds-review-bot v6 review on PR #3849: the guard sat before the
create branch only, so adopting an already-live identity could still run a
session whose history dies at exit. Move it to the top of resolveAgent, where
it covers both the live and the create path, and add a rejection test for the
live path alongside the existing create-path one.
Address the ds-review-bot v6 review on PR #3849:
- Require the composed sessionPersistence service before creating an exact
--session-id identity, so a profile that keeps sessionQuery but drops
persistence exits 1 instead of printing an id whose history dies at exit.
- Stop exporting the now-internal boundJsonEvent and describe it in the
present tense; its test now exercises boundJsonLine.
- Say "64 levels or deeper" in the README and Agent Note, matching the
depth budget (an input keeps 63 nested containers, the 64th is cut).
Tests: 77 headless unit tests with per-file 100% coverage on src, 14 profile
e2e tests, constraints/typecheck/lint/doc/pairing gates.
Address the ds-review-bot v6 review on PR #3849:
- Cut a projected payload nested deeper than 64 levels instead of recursing
until the stack overflows; the isolated session listener would otherwise
drop the `tool_call` silently.
- Write both `error` events (startup usage errors and runner failures) through
`boundJsonLine`, so the documented 32 KiB line cap covers JSON-escaping
expansion as well as the 8 KiB message cap.
Tests: 76 headless unit tests with per-file 100% coverage on src, 14 profile
e2e tests, constraints/typecheck/lint/doc/pairing gates.
Address the ds-review-bot v5/v6 review on PR #3849:
- Register the shared `lib/json-stream-*.js` chunk in `packageFileExtras` and
order `files` as the workspace-constraints gate requires, so
`pnpm run constraints` passes.
- Re-validate the preset on the Session `agents.resume` actually attached,
closing the TOCTOU window between `observeSession` and the write lease.
- Bound one serialized event line at 32 KiB: an over-long event keeps its
scalar fields, drops structured ones, and at the extreme reduces to `type`.
- Normalize an empty tool-argument string to `{}`, matching the executor.
- Scan only real `--json` flags (stop at `--`, skip a `--session-id` value)
before installing the JSON error override.
Tests: 74 headless unit tests with per-file 100% coverage on src, 14 profile
e2e tests, constraints/typecheck/lint/doc/pairing gates, tarball import smoke.
Address the ds-review-bot v6 review on PR #3849:
- Publish the `lib/json-stream-*.js` chunk that both entry points import.
Without it the installed tarball failed to load with ERR_MODULE_NOT_FOUND,
because `files` listed only `lib/index.js` and `lib/startup.js`.
- Resolve a Session's preset from its log (`agent-preset/selected`) instead of
only the immutable creation header, so a Session that switched preset while
blank is rejected too. Both the persisted and the live path scan the events.
- Write the `--json` error event for Commander grammar rejections (an unknown
option, a missing option value) as well as the action's own usage errors, and
drop Commander's `error: ` prefix from the event message so one event type
carries one message shape.
- Reject a whitespace-only positional instead of falling back to stdin, so an
accidental blank argument cannot consume a pipe.
- Document the stdin task as verbatim and the widened usage-error contract.
Tests: 68 headless unit tests with per-file 100% coverage on src, 14 profile
e2e tests, plus a packed-tarball import smoke check.
- Reject adopting a Session recorded under an agent preset, and one that
recorded no cwd; align the subagent/forked diagnostic wording.
- Write the bounded JSON `error` event for a --json usage error before exit,
since the runner never mounts to write it.
- Keep the caller's exact --session-id instead of the trimmed value.
- Bound object keys and copy a literal `__proto__` key as data rather than
through the inherited setter.
- Reject a lone `-` mixed with other task words.
- Document the in-turn failure contract and step-commit text/thinking timing.
Apply the rename pass to READMEs and docs the master sweep rewrote, fix
PTC mode anchors and the renamed-note links in the spill READMEs, and
regenerate the doc graphs.
The base-mounted projection cache's write-behind forces session-log flushes
at cache-chosen times, splitting packed chunk rows and changing the durable
JSONL batching the keyless headless and sdk replay fixtures pin. Neither
profile exposes a session-listing surface — the one-shot runner and the SDK
protocol — so both bundles disable the base row, restoring the pre-base
behavior the fixtures were recorded against (the same pattern acp-app uses).
Dudu-0223