The reference-admission discard listener matched on followup()'s returned id,
but an agent/inbox/enqueue listener that synchronously cancels emits
agent/inbox/discard before followup() returns to assign that id. The match
then missed, leaking both the submit and discard listeners plus the attached
context per referenced prompt. Match on the content reference instead — the
same value send() carries onto the message, known before followup() runs, and
symmetric with the submit wrapper's content check.
The prior "ordinary allowed path" test passed only because the fake agent
returned a fixed 'stub' id that collided with the id the test constructed;
it now releases each wrapper through its own allowed admission, and a new
regression drives the synchronous-discard timing directly.
Review fixes (ds-review-bot on #623):
- Persistence adoption compares the immutable policy baselines: onCreated's
ownerless claim and adoptLivePrefix retain the STORED header, so a
same-id live session with a conflicting baseline now rejects as a
collision instead of appending under read-only and resuming under the
stored danger-full-access.
- resolve() resolves the session override BEFORE applying an explicit
approved mode: the one-shot grant no longer bypasses the unconditional
durable-header validation.
- The approval narrator attributes positionally over the session's OWN
events (past the seed boundary): a fork child whose baseline delta has
no own override narrates 'inherited from the delegating session' instead
of misattributing a stale seed-carried switch to the user or the
operator.
Red-first: baseline-conflict adoption in the shared coordinator contract
(both backends), resolve-with-explicit-mode validation, and the fork-child
narration attribution case.
Review fixes (ds-review-bot on #623):
- overrideOf (both knobs) rejects a seedLength past the log end before
slicing: a malformed durable boundary would otherwise empty the
own-switch slice until the log outgrew it, letting a wide baseline
shadow a REAL later tightening. Malformed durable metadata fails loud,
never open.
- The session-query derived index carries the two baseline fields end to
end: schema columns on both session tables (SESSION_QUERY_SQLITE_SCHEMA
_VERSION 6 — derived, rebuilds in place), inserts, header selects, the
candidates CTE, rowHeader, sameHeader, and the cross-source
assertSessionHeadersCompatible — so a search hit's header keeps the
child's inherited confinement and conflicting live/persisted baselines
reject.
Red-first: out-of-range seedLength tests in both policy suites;
baseline round-trip and live/persisted baseline-conflict tests in the
session-query sqlite suite.
Review fix (ds-review-bot on #623): the unconditional slice regressed the
public SessionStore.fork path — a generic fork child gets seedLength but no
policy baseline, so slicing discarded its seed-carried sandbox/approval
switches and silently widened it to the deployment defaults (a forked
read-only/never parent produced a workspace-write/ask child).
overrideOf now branches on baseline presence: with a header baseline (a
delegation child) the fold covers only own post-seed switches — the
baseline captured from the parent's FULL log subsumes seed history; without
one, the whole log — seeded switches ARE the replayed inherited truth. The
permission preset fold scopes the same way. Red-first: generic-fork
seed-carried override tests in both policy suites.
goal-session rides retry turns and survives admission failures. A
recovery policy closes a goal round's failed turn and reopens its
history under a retry trigger; the attempt now adopts that turn and
drops the failed turn's provisional reason, so the round settles from
the retry's own outcome instead of blocking an armed goal with
turn-error after a successful response. A downstream admission hook
that throws (rather than blocks) used to strand the queued reservation
forever; the listener now clears a still-turnless matching attempt on
the rejection path and reschedules the round.
agent-loop contains a persistently rejecting step close in the catch
path the same way the finally contains the turn close, so the
post-finally tail always publishes the terminal status — previously a
double veto escaped run(), leaving status at running while whenIdle()
resolved. The whenIdle catch arm is annotated as the backstop it now
is: every driver rejection path is contained today.
workspace-context folds an already-appended baseline from the session
log when the plugin is hot-remounted over a live session, instead of
injecting a duplicate from its fresh mount-local guard.
The TUI's reference-admission discard listener installs before
followup(): admission runs synchronously inside it on the common path,
so a listener installed afterwards missed its own cleanup and leaked
one callback per referenced prompt.
Validate replay sidecars and cross-copy failure facts, make browser console tripwires and macOS temp paths deterministic, and wait for asynchronous TUI resume details. Keep the owning docs, translations, and generated catalog aligned.
The dedup guard pinned 'no duplicate stamp' — under the header baseline no
stamping exists, so its event-count assertion became a tautology and its
fence assertions a subset of the stale-seed case. The spec docblock claimed
the session invariants pin the stamping design (superseded); it now names
the three review-found timing threats the suite pins as distinct shapes.
Service overrideOf JSDoc shrinks to a pointer at the owning pure export.
The TUI's referenced-prompt snapshot now rides the prompt's own
admission transaction instead of a pre-admission inject: while idle, a
one-shot prepended agent/prompt-submit wrapper appends the snapshot to
the allow decision's additionalContexts, so a blocking hook discards
the prompt and its attached context together instead of stranding the
snapshot in history for the next unrelated prompt. A prompt discarded
before admission releases the wrapper; steering keeps the inject path
since it bypasses admission and drains at the same boundary. The
session-reference snapshot adapter pinned the old context-before-prompt
order; the branch-wide order (prompt first, its contexts after) is now
asserted and the fixture re-recorded.
tool-tasks drops the last consumer of the removed thrown-disposed
contract: completion notices now inject unconditionally, which is
well-defined during owner teardown — the loop treats disposal like any
cancel, so the notice appends as durable idle context (persisted for
resume while the session is attached, dropped with the detached log
after). README pair and the owner-disposal tests state the new
delivery contract.
Review fixes (ds-review-bot warnings on #623):
- One chain, every consumer: the override resolution (own post-seed
switches ?? header baseline, closed-vocabulary validated) moves into pure
exports (sandboxOverrideOf / approvalOverrideOf); the services delegate,
and the permission presets consume them — current(session) and set()
now see inherited baselines, so a child inheriting danger-full-access
gets REAL knob switches when workspace-write is selected instead of a
silent no-op, and a seed-carried preset selection is subsumed by the
baseline. current(events) becomes current(session) (pre-release; the
only callers were tests).
- Unconditional durable validation: a malformed header baseline fails
loud on every read, no longer shadowed by an own switch.
- The two policy peers are declared optional (peerDependenciesMeta), so a
thin spawn/fork deployment without policy plugins can consume the
driver; verify-runtime-closure honors the flag.
Red-first: inherited-preset derive/switch-away and seeded-selection tests
in the permission suite; malformed-baseline-with-own-switch tests in both
policy suites.
Review fix (ds-review-bot critical #2 on #623): the first-turn event stamp
had a durability hole no turn anchoring can close — an idle SessionStart-
style injection persists a complete one-shot turn before any prompt turn
opens, so a crash in that window left a resumable-looking child with no
inherited policy, falling back to a possibly wider deployment default.
The captured overrides now ride the child's creation meta into its
immutable SessionHeader (sandboxMode/approvalPolicy, neutral strings at the
session boundary — the delegationDepth precedent), durable from the moment
the session exists: no listener ordering can starve the baseline and no
crash window can lose it. overrideOf(session) on both policy services
resolves fold(events past header.seedLength) ?? header baseline, validating
against the closed vocabulary on read; stampOverride and the prompt-submit
listener machinery are deleted. The header field rides both persistence
backends (JSONL header line; SQLite sessions columns, SCHEMA_VERSION 11 —
pre-release, no migration). pty-local reads through overrideOf so PTY
spawns see the baseline too.
Red-first: header-durability-before-any-turn test (the injection crash
window shape), baseline/seed-boundary/closed-vocabulary contract tests in
both service suites; the real-wall suite (race, veto, fork stale-seed,
grandchild) re-anchored on header assertions and green. The Agent Note's
Alternatives now records the superseded event-stamping iteration with the
review evidence; bilingual docs updated.
Downstream packages lost the tests that exercised their agent-loop-facing
edges when the loop was rewritten. Restore 100% per-file coverage with
behavior tests through public seams: llm-retry config validation and
cancellation races, goal replay drift/staleness/teardown edges, plan-mode
disposed-flush, workspace-context empty-change commits, api-proxy
synchronous send failures, acp-snapshot spill-path extraction and refresh
write-back, ACP injection-triggered turns, cli-demo and tui inbox
lifecycle edges, and agent-loop retry/settlement/lifecycle branches.
The only source changes are narrowly-justified v8 ignore annotations on
invariant guards and one redundant-guard removal (workspace-context).
run_code gains a required bash-style description parameter: presentCall
titles the card with it and moves the program to rawInput, so every
surface gets a readable label. tool/code-dispatch now logs each
sub-call's complete content/isError (the tool/result vocabulary),
replacing the bounded resultSummary and deleting the summarize/cwd
machinery — a UI renders sub-calls through the identical path as native
results. The dsh config tree mounts the worker code runtime and reads
DSH_TOOLS_MODE (temporary seam until per-session mode selection lands).
Session format stays v0 (pre-release churn). Code-mode ACP/TUI fixtures
re-recorded; TUI presenter pin refreshed; catalogs regenerated. Keyless
web smoke pins the code-mode wire contract (tools=[run_code] + SDK
prompt section).
Integrate the Commander adapter with master's headless rework (dsh -p now boots
through AppCLIEntry — the same cordis.yml composition as dsh web, web-observable
while it runs — via toFetchHandler(ctx.apiProxy)).
- headless.ts: keep master's AppCLIEntry-based body but take the adapter's
pre-parsed `task` (drop the re-added parseArgs). Old startHost path and the
now-deleted packages/host/runtime dependency are gone.
- remove the stale packages/host/runtime dir left on disk by master's deletion
(mirrors the earlier packages/ui/acp cleanup).
Integrate the Commander argument adapter and dsh-front-door work with master's
config-tree `dsh web` (#601: AppCLIEntry + apps/cli/cordis.yml) and the
packages/ui/acp → packages/acp/acp relocation.
- web.ts: keep master's AppCLIEntry-based boot, but take the adapter's parsed
(host, port, dev) instead of an internal parseArgs. The adapter's host/port
defaults (127.0.0.1/3080) match cordis.yml, so always passing them is
behavior-equivalent to master's "undefined keeps the yml default".
- apps/cli/package.json: master's expanded config-tree dep set + commander.
- retire-readline Agent Note: point the TUI refusal proof at
apps/cli/tests/built-bin.e2e.ts (both languages), re-record the pair.
- READMEs reconciled (demo-bin removal + master's ACP/channel rewording).
Address review and cut ceremony: the adapter no longer models help/version/
errors as DshInvocation members. Commander owns those under exitOverride — it
prints usage or the diagnostic and one try/catch in parseDshArgs turns the
thrown CommanderError into process.exit with the intended code. bin.ts drops its
help/version/error cases; the union is the three real modes.
Domain checks bail via command.error(print + exit 1): --prompt rejects an empty
task or a stray config/--resume, empty --resume= fails loud, and --host/--port
are validated. A repeated --resume or a flag captured as a value is Commander's
standard behavior, left alone (a bad id fails loud downstream). dsh --help
discloses web via addHelpText. Net: args.ts 185 -> 112 lines.
Also fixes review nits: built-bin e2e resolves on `close`; the /resume handoff
uses `dsh --resume=<id> -- <config>` so a config named `web` stays a positional;
and stale prose (cordis.yml comment, app-boot module doc + duplicate JSDoc,
ui/README, two feature notes, an agent-loop test name) tracks the shipped state.
Removes tui-demo's now-dead plugin-include dep and vendor/loader + app-boot
tsconfig references.
Remove the redundant dsh-tui-demo bin and the RESUME_SESSION_ID environment
variable, leaving dsh as the one terminal entrypoint.
The dsh-tui-demo package was a plugin (the TUI app bundle mounted by dsh's
config) plus a bin that booted a leaf cordis.yml — the same job `dsh [config]`
does. The bin, its ./bin export, its built-bin.e2e.ts, the tsdown bin entry,
and the now-unused dsh-app-boot dependency are removed; the package keeps its
plugin and invariant. demo:cordis, demo:code-mode, and the tui-agent and
cordis-agent keyless PTY smokes now launch through apps/cli/src/bin.ts with the
config as the positional argument. cli-demo/acp-demo/jsonrpc-demo keep their
bins (distinct surfaces).
RESUME_SESSION_ID was the only bridge from --resume into the shipped config;
--resume now provides the id on the boot context via ctx.provide(
RESUME_SESSION_ID_KEY, id), and the four configs read it as a bare identifier
through a quoted typeof-guarded !!js expression. The TUI resumeCommand fixtures
and docs move to `dsh --resume {session}`.
Agent Note and its Chinese pair updated; config-catalog regenerated.
Integrate the Commander argument adapter with master's safe session-resume
feature and dsh web --dev flag.
- args.ts: add --dev to the web parser.
- tui.ts: keep master's process.execve in-place resume handoff, but take the
adapter's parsed (config, resume); inject the resume id through boot's
prepare(ctx) hook via ctx.provide(RESUME_SESSION_ID_KEY, id) instead of the
RESUME_SESSION_ID env var; rebuild the re-exec argv as `dsh --resume <id>`.
- app-boot: drop master's replaceResumeArg (no longer needed) alongside the
already-removed parseResumeArg; add RESUME_SESSION_ID_KEY.
- the four tui-agent/cordis configs read the ctx-provided resumeSessionId via a
typeof-guarded !!js expression, so resume needs no env var.
- web.ts: keep master's client roster and --dev watch, take parsed host/port/dev.
Review fixes (ds-review-bot on #623):
- Capture-at-delegation: the driver now reads overrideOf(parent.session)
for both knobs synchronously before its first await, and the prompt-submit
listener stamps those captured values — a parent switch racing the child's
asynchronous creation belongs to the parent's future, not the child. The
inheritOverride(parent, child) service method is split into its two halves
(overrideOf / stampOverride) accordingly.
- Veto safety: the one-shot prompt-submit listener registers with
prepend: true, so a veto-capable listener (a denying UserPromptSubmit
hook) cannot close the child's first turn without the durable stamp.
Both regressions are pinned red-first in inheritance.spec.ts: the
delegation-vs-late-switch race (delegate tool flips the caller wider while
the creation transaction is pending) and a blocking prompt-submit listener
(stamp survives a promptless first turn). Service contract tests renamed to
the split API; READMEs and the bilingual Agent Note updated.
Per-session policy overrides (sandbox/mode, approval/policy) never crossed
the delegation boundary: a spawn child of a read-only-switched parent ran
under the wider deployment default, and a fork child missed any switch made
after its seed boundary — delegation was a bypass channel for a user's
tightening.
The in-process driver now snapshots the delegating parent's override chain
and stamps it onto the child through the canonical write paths
(SandboxPolicyService.inheritOverride / ApprovalService.inheritOverride),
anchored inside the child's first turn via a one-shot agent/prompt-submit
listener: turn-enclosed (durable), ahead of the first request (an inherited
'never' reaches the child's first system prompt), and positioned after any
stale fork-seed switch so the ordinary last-event-wins fold resolves it.
Only overrides are copied — an unswitched parent stamps nothing and the
child follows the live deployment default; both services are consumed
opportunistically, so compositions without them delegate unchanged. Nesting
composes by construction (each stamp folds the already-stamped parent log).
Evidence: inheritance.spec.ts drives scripted-model children into the real
dsh-fs-sandbox fence through the real write tool (disk-state + denial-marker
assertions; spawn, stale-seed fork, grandchild, escalation fail-closed, and
no-stamp guards), inheritOverride contract tests in both service suites, and
the recorded subagent-sandbox-inheritance ACP snapshot (read-only preset →
delegate → child denied, replayed keylessly).
See .agents/notes/implemented/feature/2026-07-25-subagent-policy-inheritance.md.
The automation-only rewrite edited many implemented Agent Notes; several
edits replaced still-live or historical rationale instead of reframing:
- llm-model-catalog: restore the prompt/request consistency section and
selection-ownership alternatives — installAgentLlmTarget and the TUI
/model selector still ship that design; only the ACP wire is gone.
- plan-specific-collaboration-state, acp-multi-session, todo-write,
ask-user-question: link the superseding automation-only note instead
of silently rewriting the original decision or motivation; drop a
paragraph duplicating the Web-provider facts stated two paragraphs up.
- sandbox: stop claiming unit coverage for turn-enclosed config writes
(that mechanism left with the bridge) and retitle the commit-boundary
paragraph accordingly.
- Fix the missing blank line before '## Consequences' in the
plugin-command-registration pair, the JSON-RPC/Web render-intent
consumer misattribution (the second consumer is the host/client
runtime), stale bash_output/bash_kill names, and 'optional goals' in
architecture.md.
- examples/acp-agent/README.md: point at the package contract instead
of restating it; packages/ui/permission and plan-mode READMEs record
the consumer-less preset service and the exit_plan_mode coverage gap
under Known Limitations.
- 2026-06-19-acp-snapshot-tests: the new note defers the corpus
migration rather than committing to it; say so.
Re-record the touched bilingual pairs.
