The ShellDialect marker on BashExecutor and the load-time rejection in
tool-bash/tool-pwsh force every test and example fake executor to declare
a dialect for a guard with no in-repo or plausible deployment to catch
(shipped compositions always pair the tool with its matching executor),
and they break the example composition suites that stub ctx.bash without
a dialect (agent-spine-demo/cli-demo/acp-demo lost the bash tool).
Keep the non-dialect doc fixes that landed with the attempt: the tool-bash
README bashEnv contract trim with the stale example import removed, the
acp-snapshot suite.ts 'usable pwsh' JSDoc, and the pwsh.cordis.yml comment
indent. The parity note records the attempt and revert under Alternatives.
The seam gains ShellDialect ('bash' | 'powershell' - concrete shells, not
families: zsh or fish would be their own values, never 'bash'); bash-local
declares bash (bash-sandbox inherits), pwsh-local declares powershell, and
both tools throw at load when the mounted executor speaks another dialect -
previously tool-pwsh over bash-local handed PowerShell text to bash -c and
the deployment error surfaced as ordinary nonzero exits. Pinned by mismatch
tests on both tools; the parity note records the contract (both languages).
Also from the review round: the tool-bash README's managed-environment
section becomes a summary linking the owning dsh-bash-env contract (the
duplicated prose carried a stale owner in its example import), the
pwshOnly JSDoc drops the stale 'on PATH' phrasing, and the task-tools
contract comment in the two pwsh compositions is indented into its block.
The native adapter's route was named deepseek, colliding with pi-ai's
catalog provider of the same name, so the two DeepSeek paths could never
be mounted side by side. The web settings page needs both configurable at
once. Compositions, fixtures, goldens, scaffolding defaults, and docs all
move together (pre-release, no shim); TUI/session-query-spill/
missing-credential goldens re-recorded through their keyless refresh
modes because provider-name length shifts box padding and spill
truncation points.
Review round on #758.
bash.run() only promises to resolve for nonzero exits, timeouts, and aborts,
and bash.resolve() can reject on policy grounds, so either could escape the
serial agent/step listener and abort the model turn — contradicting the
plugin's documented failed-query no-op contract. Contain both and log a
warning instead; the location is optional context.
The Agent Note claimed an unchanged location suppresses the query. It does
not: only the interval floor is checked before the query, while change
suppression compares state the query returned. Corrected in both languages
and re-recorded the i18n pairs.
The headless-agent test fixtures and the e2e test that depended on them
are out of scope for this PR. Unit tests in tmux-context.spec.ts cover
the plugin behavior.
The headless-agent test fixtures were removed; move the driver, cordis.yml,
and mocks into packages/context/tmux-context/tests/fixtures/ so the e2e test
is self-contained.
Add @deepseek-ai/dsh-tmux-context: an opt-in per-turn context plugin that
reads which tmux session/window/pane this agent process runs in (plus the
window layout tree) via the ctx.bash seam, and injects it as one durable,
source-attributed user/message when the location changes.
- Pull on the first step of each turn; no tmux hook or background process.
- Detect a real pane by tty, not $TMUX_PANE alone: a terminal launched from
a tmux shell inherits $TMUX/$TMUX_PANE from that ancestor, so the command
also matches the pane's #{pane_tty} against this process's controlling
terminal and emits fields only on a match.
- No-op outside a real pane, without a bash executor, or on a malformed
reading.
- Own location and layout only: no pane sizes, no sibling-pane scraping.
- Unit tests at 100% per-file coverage, plus a keyless Loader e2e with a
mock bash provider so it replays without tmux.
- Agent Note: 2026-07-27-tmux-location-context.
The mount-local baseline guard was seeded from "a baseline already exists in
the log", which a resumed session and a hot plugin remount both satisfy. That
made a resume skip its baseline, so offline AGENTS.md edits or removals never
reached the first resumed request — violating the documented resume contract.
Distinguish the two by agent/session-start: a startup or resume emits it before
the first step, while a remount attaches to an already-live session and never
witnesses it. Only a remount (no witnessed start, baseline already logged)
keeps the single logged baseline and skips; a resume falls through and
re-composes from current files. Adds a regression that resumes a session with
an offline baseline edit and asserts the fresh baseline reflects it.
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.
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).
Huanqi Cao
Dudu-0223
Tianyi Cui
ZiyaZhang
Hypatia May
Yichen Jiang
kingwl
imccyu
xjt
j-xiang
Turtle
_Kerman