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Alternatives now records the superseded event-stamping iteration with the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.
Replace the dsh CLI's three hand-rolled parsing idioms (raw argv[0]/includes
dispatch in bin.ts, per-mode node:util parseArgs in headless.ts/web.ts, and the
bespoke parseResumeArg scanner in dsh-app-boot) with a single Commander adapter
in apps/cli/src/args.ts. parseDshArgs resolves argv into a discriminated
DshInvocation union; bin.ts switches on the mode and dynamic-imports the chosen
module, which now consumes already-parsed values.
- web is a real subcommand; --host uses choices and --port an argParser range
check, moving validation into the parser.
- --resume rejects empty and repeated forms; --prompt rejects empty; a config
positional after --prompt and a root flag placed before web fail loud.
- adds --help/--version; removes parseResumeArg from dsh-app-boot.
- new apps/cli/tests/args.spec.ts (apps/*/tests added to vitest include,
apps/cli/tests to tsconfig.host.json); the tui-agent keyless PTY smoke covers
bin.ts dispatch end to end unchanged.
The fake terminal retains earlier autocomplete frames, so the directory follow-up assertion could pass before the scoped lookup completed. Wait for the quoted file mention to be applied before submitting.
The web host now composes the sandboxed product path (sandbox-local +
sandbox-policy behind bash-sandbox/fs-sandbox, with user-approval and
permission on top); BootHostOptions.sandbox carries the deployment
defaults (workspace-write + ask).
createApiProxy owns the approval pending registry: a ctx.approval ask
becomes an answerable approval/requested mux frame with a stable rpcId,
replayed verbatim on every mux open until settled; respond routes by the
echoed rpcId, validates the ApprovalResponsePayload audit correlation,
and broadcasts approval/resolved; the ask's abort signal withdraws the
question as cancelled.
session.permissions / session.setPermission project ctx.permission into
a protocol-owned PermissionOption select; idle switches are held
last-write-wins and
flushed into the next prompted turn (the ACP bridge's anchoring
pattern). The shared hasOpenTurn fold moved to dsh-session,
deduplicating the private copies in user-approval, the ACP bridge, and
the proxy.
Client, per the designer draft: a pending approval takes over the
composer (ApprovalPanel replaces the InputBar — amber strip,
justification headline, paired command, one-shot refuse/allow, keyed by
rpcId so a queued second approval remounts live; the resolved frame
restores the composer); the sidebar session row shows an amber
waiting-approval dot that outranks the running ring (manager-tracked
approvalId set, idempotent under mux-open replays, cleared per
connection generation, lit for uninstantiated sessions too); the
permission selector is a composer bottom-row chip over an invisible
native select, with a presentation-only title-case transform
(workspace-write renders as Workspace Write; wire names untouched). Question placeholders stay in the message flow. The
connection fixture mirrors the host behavior for keyless browser
acceptance.
The master merge introduced a tui goal-restore test and the guard parent
README that still used the removed context/message event. Point both at
the coalesced plugin-sourced user/message.
