fix(bin): require project clone roots during fleet sync - #2849
Merged
Conversation
Git repository discovery walks upward, so `git -C projects/<dir>` on a plain directory nested under projects/ resolves to the enclosing repository - in a firstmate home, the firstmate checkout itself. fm-fleet-sync.sh guarded its candidates with `rev-parse --is-inside-work-tree`, which such a directory passes, so every later git call read, pruned and fast-forwarded firstmate's own default branch and reported it under the project directory's label. A running session's AGENTS.md changed underneath it, and the report named a project that had nothing to do with the change. Require each candidate to be the root of its own work tree before any other git command: compare `rev-parse --show-toplevel` against the directory's own physical path. Both sides are physical, so a symlinked clone still compares equal. Anything else is skipped by name, naming the repository that would have been touched, and bootstrap relays that as a FLEET_SYNC line. Regression coverage reproduces the wrong-repo fast-forward against a home nested inside another repository, in both the whole-fleet and single-project forms, and pins that a symlinked clone dir still syncs.
Confidence Score: 5/5The PR appears safe to merge, with the clone-root guard preventing the unintended enclosing-repository update while preserving supported synchronization paths. The changed script rejects candidates whose physical directory is not their resolved Git work-tree root before running subsequent Git operations, and the added tests cover both vulnerable invocation forms plus the symlink compatibility case. Reviews (1): Last reviewed commit: "no-mistakes(review): Keep enclosing fixt..." | Re-trigger Greptile |
Owner
|
Speaking as Kun's firstmate: Scheduled 3:10am PT 8/23 pass. Main reconfirmed VISION (inspected Class: corrective. Replaces Security: none. Path comparison plus a louder skip. No Overlap / HOLD: not spawn/teardown, does not edit CI / NM: HEAD Workflows: already approved (CI completed SUCCESS on this HEAD). Run IDs: 32629198233 (CI), 32629198212 (Require no-mistakes), 32630050933 (Require no-mistakes). No pending first-time-fork approval. Land-eligible rec: YES (corrective, green CI+NM matching this HEAD, VISION aligns, not default-behavior, not a spawn/teardown/herdr hold). Captain-flag NOW: no. |
Owner
|
Speaking as Kun's firstmate: this is merged. Thank you @karotkriss — really appreciate you taking the time on this. |
doitdigital0495
added a commit
to doitdigital0495/firstmate
that referenced
this pull request
Aug 23, 2026
* fix(bearings): restore decision options and add close controls (kunchenguid#2707) * fix(bearings): always show decision options and a close/drop control Freeform-only Captain's Call cards hid the option buttons the board was designed around, and there was no way to drop a stale hold without inventing an answer. Require selectable options, keep freeform as a supplement, and route the reserved __drop__ answer through decline so the hold leaves Captain's Call. * no-mistakes(review): Fix drop closure and decision-only option validation * no-mistakes(review): Preserve answerability for non-decision cards * no-mistakes(document): Clarify decision drop documentation * ci: require no-mistakes pipeline step attestation (kunchenguid#2710) Signature-only PRs can hide skipped review, test, or document steps. Fail unless no-mistakes >= 1.46.0 attests those three steps completed. * feat: collapse decisions into tasks held for the captain (kunchenguid#2728) * feat(captain-hold): collapse the decisions concept into tasks held for the captain A decision is no longer a separate type: it is an ordinary backlog task held for the captain, identified by its task id. bin/fm-captain-hold.sh owns the surviving behaviors - guarded hold creation, the recorded-answer close (answer/answers with a release mode for captain-gated work), the source bindings, and the investigation completion gate - and bin/fm-decision-hold.sh becomes a one-release compatibility shim over it. The fleet snapshot now parses hold-until and computes captain_actionable as queued + captain-held + unblocked + due, independent of row kind, plus a presentation-only deferred_marker for prose-deferred rows. Bearings renders every due captain-held task in Captain's Call, date-deferred holds as dated Charted Next gates, suppresses prose-deferred rows from default views with an omitted disclosure, and excludes from Recently Landed anything that closed while still held for the captain. Legacy compatibility: pre-collapse <origin>-decision-<key> rows are already plain task ids and keep working; short keys in recorded metadata, concrete origin bindings, chat --resolve-key fallbacks, and old resolution records all resolve in place. * no-mistakes(review): Fix captain answer replay and body preservation * no-mistakes(review): Fix captain hold idempotency and legacy replay * no-mistakes(review): Validate card close modes and compatibility routing * no-mistakes(review): Enforce release replay mode matching * no-mistakes(review): Prevent duplicate decision cards and released replay mismatches * no-mistakes(review): Preserve answer columns and legacy resolve replays * no-mistakes(document): Document strict replay and legacy compatibility * no-mistakes(lint): Quote done literals to satisfy ShellCheck * no-mistakes: apply CI fixes * fix(rebase): keep collapsed captain hold board semantics * fix: bound recovery announcements and preserve supervision (kunchenguid#2733) * fix(watch): announce recovery once per generation and keep successors supervising A lost Pi/OpenCode handling handshake re-announced the same recovery generation on every cycle and spent the successor's first ~55s blind, so a real crew event could be ignored and then dropped. Record the announcement in the durable marker, confirm the handshake before the follow-up without swallowing failure, and enter the poll loop immediately. * no-mistakes(review): Tighten recovery event timing regression * no-mistakes(document): Document recovery-loop supervision guarantees * fix(bin): surface captain-call record divergence (kunchenguid#2744) * fix(bin): signal a captain call resolved in the log but still held A captain call has two records and closing one has never closed the other: a `resolved [key=...]` line closes the status-log fold, while the backlog task held for the captain closes only through `fm-captain-hold.sh answer`. Answering on the status side alone left no trace of the disagreement - the fold went quiet, the durable record kept saying the captain owed an answer, and nothing warned. The defect was never the separation; it was the silence. Add `fm-captain-hold.sh diverged`, a read-only report of that contradiction, and print it from `fm-wake-drain.sh` as a bounded RECORD DIVERGENCE section beside OPEN DECISIONS on every drain. It flags one condition: a task still open and still carrying the captain-hold annotations whose key was closed on the status side by the resolve verb, under the collapsed identity or the legacy derived one. It closes nothing, ever. A captain call closed wrongly leaves review entirely, which is worse than the noise, so both reconciliation directions stay human-owned and the printed hint names both - a resolution is not proof the captain ruled, since a call can dissolve on a false premise or turn out to have been a question of fact. Three states are deliberately not divergence: a `captain-held` close is the verified transfer `complete` writes, a still-open keyed decision belongs to the OPEN DECISIONS fold, and a captain call with no routed work item is legitimate rather than incomplete, so routed work is no part of the test. `fm-classify-lib.sh` gains `status_key_closing_verb`, which reports how the status side currently reads one key by replaying the existing `_fm_decision_fold_line` rule rather than re-deriving it, so the two closing verbs stay distinguishable in one place. The per-wake cost is one `tasks-axi list`, one key scan per status log, and the precise per-key fold only for a key that already names a still-open task; the call is hard-bounded so a slow backlog tool can never delay wake presentation. * fix(document): Correct divergence lifecycle documentation * fix(document): Neutralize divergence lifecycle prose * fix(bin): re-arm after an abandoned auto-arm claim and defer a wedge escalation while a worktree is written (kunchenguid#2524) * fix(watch): re-arm supervision after an abandoned auto-arm claim A Claude auto-arm cycle that armed, delivered one rewake, and exited left its single-flight lock behind. Both Stop-event participants then deferred to that lock forever, because its recorded pid was still live: the turn-end guard read it as recovery under way and allowed the stop, and the next Stop firing treated it as another owner and declined to arm. On 2026-08-14 a home with two tasks in flight lost supervision for about 40 minutes with no watcher process and no watcher lock, its beacon frozen at the one delivery, and both crewmates' finished reports sat in the durable queue until an operator drained it by hand. Abandonment is now proven from the epoch ledger instead of inferred from pid liveness. A lock whose holder pid matches the ledger's own owner_pid while the recorded outcome is anything other than arming has already finished its decision, so that claim is reclaimed under the lock's steal mutex, stops counting as recovery ownership in the guard, and is cleared by the guard's terminal check rather than deferred to. A failed clear re-blocks instead of allowing a blind stop, and an arming entry stays in flight however old it is, because its owner foregrounds the arm for the whole watcher cycle. Issue kunchenguid#2251's PR kunchenguid#2263 does not cover this failure. It is closed and unmerged, lives entirely in bin/fm-watch-arm.sh, and retires the stalled watcher and matching stale watcher lock of an arm that is currently running. Here no arm and no watcher were running and no watcher lock existed, so it has nothing to retire and the home stays blind. tests/fm-claude-stop-autoarm.test.sh covers the reclaim, the still-arming and unnamed-owner cases that must keep the gate closed, and the failed clear. tests/fm-turnend-guard.test.sh covers the guard side of the same boundary. Both fail without this change. * fix(watch): defer a wedge escalation while the task worktree is written The wedge detector had two inputs, rendered pane quietness and the run step, and neither can see a crew that is writing source, then tests, then documentation behind a static pane. On 2026-08-14 one crewmate produced eight consecutive possible-wedge escalations in a single afternoon, three of them demanding deep inspection, while it was demonstrably working and then committed. Every one of them cost a supervision turn to disprove by hand. Add write activity inside the crew's own recorded worktree as a third liveness input. crew_worktree_written_since compares the worktree against the caller's existing idle-window timer file, so -newer needs no clock arithmetic, no temp file, and no portable mtime write. The probe runs only inside the branch that was about to escalate, which bounds it to one pruned, depth-bounded walk per window per FM_STALE_ESCALATE_SECS and leaves the per-poll stale sweep exactly as cheap as before. Positive evidence defers rather than cancels. The idle timer restarts so the next window probes again, the escalation counter is neither advanced nor reset so a later genuine wedge keeps the demand-deep-inspection history it earned, and a .writing-since marker ages the whole deferral chain so the pane still re-surfaces once per FM_PAUSE_RESURFACE_SECS, through the same throttle shape a declared pause already uses, labeled as a recheck rather than a wedge. This can only reduce false positives: every absence of evidence, including no recorded worktree, a torn-down worktree, a missing anchor, and a failed walk, falls through to the unchanged escalation schedule, so a crew that writes nothing still escalates on the existing timetable. What the signal cannot see, by design or by construction: - CPU burn with no writes, such as a long compaction, is invisible. That case keeps the old behavior exactly. - A commit-only phase writes only .git, which is pruned first so that firstmate's own read-only git commands against the worktree can never make the probe self-fulfilling. - Writes under the pruned generated trees, or deeper than FM_WORKTREE_WRITE_MAXDEPTH, do not count. - The probe cannot attribute a write to the crew, so a background build or another process touching the tree looks the same. The hourly re-surface is what bounds that, and a churny file cannot buy silence. - The away-mode daemon's own escalation path is deliberately untouched. tests/fm-watch-triage.test.sh covers the classifier including the .git prune, both halves of the live case on one fixture (quiet plus writing defers, quiet plus silent still escalates and counts), and the bounded re-surface. All three fail without this change. * no-mistakes(review): prove autoarm claims by identity; skip mate-home write probe * no-mistakes(document): document away-mode wedge boundary and probe filesystem limit * no-mistakes(document): qualify turn-end recovery condition for abandoned auto-arm claims * fix(watch): keep a write deferral scoped to its own idle window Two consistency gaps in the worktree write probe, both found while reviewing the wedge-deferral change on this branch. A write deferral is a bounded chain: its .writing-since marker ages the whole chain so a churning worktree still re-surfaces once per resurface window. That is only sound while the chain belongs to the current quiet stretch, so every path that restarts the idle-window timer has to drop it too. Two did not: the corrupt-timer repair in wedge_timer_check, and both first-sight branches for a captain-relevant status. A chain left over from an earlier quiet stretch made the first deferral of the new window re-surface immediately instead of after a full fresh window. FM_WORKTREE_WRITE_PRUNE is a skip list, so clearing it reads as "skip nothing" and is the obvious way to widen the probe to the whole depth-bounded tree. Instead an empty list reported no evidence at all, quietly costing the wedge detector its third liveness input on a home that meant to widen the walk. An empty list now widens the walk, and the header says so. Neither change alters when a stall that writes nothing escalates. Regressions in tests/fm-watch-triage.test.sh cover all three paths and each one fails on the pre-fix code. * no-mistakes(review): honor an empty write-prune, bound the probe, share window_key * no-mistakes(document): align probe knob count and guard regression-coverage ownership * no-mistakes(lint): silence deliberate single-quote SC2016 in write-prune env test * fix(bin): give a captain hold the same bounded pause cadence as a declared pause (kunchenguid#2748) * fix(bin): give a captain hold the same bounded pause cadence as a declared pause Two supervisors read a finished task's last status line and disagreed about which declarations mean an idle endpoint is expected. bin/fm-inactive-reconcile.sh suppresses its inactive-outcome scan only on `captain-held`, while the away-mode daemon's wedge path gated deferral on `paused` alone. Both read the LAST line, so the two verbs are mutually exclusive and no finished task waiting on a person could satisfy both at once. Marking 11 such tasks `captain-held:` silenced the 900s outcome scan and immediately produced five possible-wedge escalations in one batch, because the 240s wedge detector no longer saw a pause verb. fm-classify-lib.sh's status_is_paused_or_captain_held already owns the combined question, and bin/fm-watch.sh's ordinary-crew wedge path already asked it. This extends that same answer to the paths still asking the narrower one: - bin/fm-supervise-daemon.sh, all six sites, which form one subsystem and have to move together. classify_stale returns the pause action, reconcile_pause_tracking and migrate_watcher_pause_markers record and migrate the marker, and housekeeping defers the wedge and then re-surfaces the recheck. Changing only the stale-persistence gate would defer the escalation while reconcile_pause_tracking recorded nothing, so the wedge marker would persist and the sweep would `continue` past it forever: quiet, but never re-surfacing. - bin/fm-watch.sh's secondmate stale gate, whose downstream owner pause_state_class already treats both declarations identically. - bin/fm-push-transition-lib.sh's absorb, where either declaration already names the human the transition would report and the wait is already durably recorded. Quieting alone would be half a fix, so the bounded re-surface had to reach a hold too. A hold has no current-state mapping, unlike `paused`, so authoritative crew state reports it as unknown and pause_state_class received `none`. An ordinary crew recovers pause classification from that state through confirmed agent death, which proves no live decision gate is being silenced. A secondmate's endpoint liveness is deliberately never read there, because an idle mate is healthy by design, so that confirmation is unavailable by construction and cannot be required: without recovering the classification for a mate, every caller silenced a held mate outright and its hold would rot invisibly. That promotion is bounded by the declared-wait guard at the top of the function, so it can only reclassify a task that already declared a wait and shows no positive working evidence. Two narrow `status_is_paused` calls are deliberately left alone. bin/fm-crew-state.sh's map_log_state is a current-state reporting contract, not a wedge path; reporting a hold as `paused` would erase the distinction status_key_closing_verb and fm-captain-hold.sh depend on, where a `captain-held` close is a verified durable transfer and a `resolved` close claims outright settlement. fm-classify-lib.sh's call inside status_is_captain_relevant needs no change because that function's own case list already returns non-relevant for `captain-held`. bin/fm-inactive-reconcile.sh keeps its `captain-held` suppression as it is. Its guard exists because a finished task's crew state still reports done from a higher-priority source than the log, and a declared pause needs no such guard: the scan only reports done or failed, and nothing else reaches its record path. Widening it would change a separate subsystem's reporting contract, which this defect does not require. Coverage extends the existing colocated patterns for these predicates and asserts both halves. tests/fm-daemon.test.sh covers the classification, the wedge marker converting to pause tracking with no escalation, the bounded re-surface with its window reset, and the boundary case where an answered hold stops claiming the cadence. tests/fm-watch-triage.test.sh covers a held secondmate re-surfacing on the same bounded cadence without being labeled a wedge. tests/fm-supervision-events.test.sh covers the absorbed push transition. Every one of these fails on the pre-fix code except the answered-hold boundary case, which is there to pin that the quieting was not widened too far. The `paused:` workaround appended to those 11 tasks is live supervision state and is untouched here. It can be retired once this lands. * no-mistakes(review): name the captain in a held task's bounded recheck * no-mistakes(document): extend declared-wait supervision docs to captain-held holds * fix(bin): make lint prerequisites and harness tests reliable (kunchenguid#2758) * fix(lint): name the installer when ShellCheck or actionlint is missing A missing actionlint exited 127 like a bare command-not-found. Fail with exit 1 and point at the pinned installer, matching the missing-ShellCheck path, without weakening the version pin. * test: isolate kimi and muse detection from inherited Cursor markers Harness detection checks CURSOR_AGENT before ancestry, so these markerless-adapter cases failed when the suite itself ran under Cursor. Clear the verified markers the same way the secondmate harness tests already do. * no-mistakes(document): Document Muse Cursor marker cleanup * feat(bin): report watched tooling updates that are available or installed but inert (kunchenguid#2684) * feat(checks): report tool updates that are available or installed but inert Firstmate had no way to notice that tooling this home depends on needs an update, and no way at all to notice the worse case: an update that installed correctly and then did nothing. That second case is why this exists. A tool that self-installs into ~/.local/bin while a version manager keeps its own older copy earlier on PATH looks completely up to date to anything that asks only "is a newer version published". On 2026-08-20 a Herdr update landed at 0.8.2 while an older 0.8.0 copy stayed earlier on PATH, so every Herdr command failed on a protocol mismatch and firstmate could not read its own fleet. bin/fm-tool-update-check.sh reports the two conditions separately: <tool> update available a newer version exists at the update source. <tool> update not in effect a newer copy is installed on this host, but PATH still resolves an older one. PATH skew is measured, never inferred. Every executable copy of a watched command on PATH is asked for its own version and those answers are compared, so one lookup cannot hide the skew, and a directory name is never read as a version because a version manager's "latest" directory can hold an older build. A copy that will not report a version is a check failure, not a pass. The watched tools live in local, gitignored config/watched-tools.json, so adding a tool is a config edit rather than a code change, and the file is never propagated to another home. Update sources cover both shapes: a local clone's commit distance from its remote branch, and a command's own version and update announcement, including a tool like no-mistakes that prints its version on one command and announces a new release on another. The check prints one line when something needs attention and prints nothing otherwise, so it rides the existing watcher state-check contract with its trust binding instead of introducing a schedule of its own, and state/.tool-updates keeps the same pending update from being reported on every poll. The check only reports. It never installs, updates, reorders PATH, touches a version manager, or fetches into a watched repository; every git probe is read-only. Tests cover the skew case as a regression, and it was verified by mutation: removing the skew report, or stopping after the first PATH hit as a single lookup would, each make that test fail. * no-mistakes(review): fix tool update check probe reporting, budget, and shim write * no-mistakes(review): keep sweeps alive on broken patterns and oversized budgets * no-mistakes(review): roll back failed arm, widen budget clamp, bound repo probe * no-mistakes(review): guard git probes at the budget, record uncut findings * no-mistakes(document): fix stale watched-tool report-record wording in docs and header * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes The behavior shard's watch-triage suite failed on the new worktree-write wedge tests. Those five tests are the only ones in the file that do not use its standard waits. They give a fixed 3 second liveness budget to the one poll that now spawns the bounded worktree walk, and 4 seconds to an escalating watcher where every other test in the file gives 10. On a loaded runner that poll outlives the fixed budget, so the round is reaped before the deferral it asserts on is recorded, and the test reports a lost deferral instead of the deferral under test. Wait for a completed poll cycle through the file's own wait_poll_cycle, which is what its header documents this hazard for, and use the file's standard 100 tick exit budget. Verified against a load that reproduces the failure: 11 of 12 runs failed before, 8 of 8 pass after. Verified by mutation too, so the waits still prove the behavior: removing the write deferral, and keeping a finished deferral chain across an idle-timer repair, each still fail their test. * fix: decouple ask-user decisions from yolo (kunchenguid#2764) * fix: treat yolo as merge authority only, not ask-user finding authority Yolo on/off was documented as also deciding no-mistakes ask-user findings, which hid firstmate's duty to judge unambiguous-toward-design findings itself. Keep every safety boundary; this is a contract clarification, not a relaxation. * no-mistakes(document): Clarify yolo documentation ownership and merge posture * feat(bin): add a spoken interface that answers from records and hands work over (kunchenguid#2767) * feat(voice): spoken round trip on Nova Sonic 2 with a measured relay cost Step one of the spoken interface: the laptop captures and plays audio, this desktop holds the model session, and no AWS credential leaves the desktop. Measured, amazon.nova-2-sonic-v1:0 in eu-north-1, end of speech to first byte of reply audio, 6 runs each, all answered, on a question that forces a records read: relay path 1.229 1.379 1.428 1.447 1.481 1.516 median 1.438 direct 1.147 1.179 1.203 1.237 1.244 1.317 median 1.220 The relay costs about 0.22s of the median. The direct figure reproduces the earlier survey, which is what makes it a usable control. Excluded: the captain's own ssh round trip, microphone capture, and speaker output. This desktop has no microphone and no speaker, so every run used audio files. Three pieces: bin/fm-voice-relay.py holds the conversation on this host bin/fm_voice_records.py what a spoken answer may read, and the handover bin/fm-voice-client.py the laptop end; audio devices UNVERIFIED bin/fm_voice_frame.py the wire format both machines share Real work is handed to the existing bin/fm-inbox.sh rather than a second queueing surface, and the agent says it is handing over rather than answering as firstmate. Read scope: Done history and free-form note bodies are never assembled at any scope, so the wide default cannot reach the places commercial detail accumulates. config/voice-read-scope narrows it to counts only, and config/voice-read-deny excludes a named item in one line. The boundary is an executable test that widening the reader fails. Push to talk is the default because it is cheaper and the choice is still open; --listen open-mic is the single flip. Two traps worth knowing: a clip with no trailing silence is never answered, and the end of a reply is contentEnd with stopReason END_TURN, not completionEnd. A second user turn in one session is treated as barge-in unconditionally, and an interrupted turn that calls a tool is lost, so the session reconnects per turn and gives up conversational memory. That is the concrete thing step three has to solve. * no-mistakes(review): fix voice relay credential reuse, frame validation and record parsing * no-mistakes(review): test uplink header guard, bound unknown expiry, align state dir * no-mistakes(review): decide deny per item, guard turn failures, bound ambient credentials * no-mistakes(review): read account config from home, harden deny and turn failures * no-mistakes(review): close status verb set, fix inbox help, pair data override * no-mistakes(review): keep profile-free relay alive, unblock loop, fix dead assertion * no-mistakes(review): hide finished pull requests, refuse open mic, keep suite offline * no-mistakes(review): survive reader failures, release devices, fix claims A failure while handling a model event, or while sending a tool result, left the reader task dead with ended and turn_done clear, and close() re-raised the stored failure on every await. One dropped stream became a relay that could never build another session. The reader now reports the session over in a finally whatever killed it, and close() absorbs the task the same way it already absorbed its sends. The laptop client releases what it already started when a later startup step refuses, SystemExit from the handshake wait included, and names a device refusal instead of leaking a raw PortAudio error. Whether it releases correctly against a real device is still unverified here. The records docstring claimed every reading was filtered to open ids. Only the pull request count and list are; the worker count and the state histogram cover every live runtime record, finished ids included, because a meta file still on disk still needs tearing down. The finished-work deny half of the suite asserted things that held with the deny list absent. It is replaced by a deny on an open title, which removes the row and says so while the count stays honest. * no-mistakes(review): name reader failures, split file and device refusals A failure inside the model reader released the waiting turn and told nobody. The session was not marked spent, no notice reached the client, and the client waits for a reply end or a notice, so the captain got their whole timeout of silence and then a record saying the turn went unanswered with nothing about why. Both ends of the relay now name a failed turn through one function, once per turn, and --self-test carries the cause in relay_error the way the client's own record does. Two things that are not failures stay that way. A stream that simply ends is the end of a session, which serve still reads on its own terms. A stream that goes away because close() asked it to is an ordinary renew, and announcing it would have put a failure notice in front of the captain on every turn. On the laptop end, the refusal that became a device error covered the file-backed playback and capture too, so a mistyped --in-file was reported as an audio device failure and the advice named the flag that had just failed. The file ends now report the path and the flag that chose it and stay an OSError; the device ends keep the device advice and name the flag for that end. The device paths remain unrun here, so only the file halves are covered by a test. * no-mistakes(test): survive model session end, order client turn frames * no-mistakes(document): sync voice relay docs with reviewed relay behavior * no-mistakes(document): re-measure relay latency and correct its cause * no-mistakes(document): correct measurement date and name the unmeasured SSH hop * no-mistakes(document): describe the unpublished control measurement, fix list formatting * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes * fix(bin): preserve Relay follow-up loops until explicit disposition (kunchenguid#2763) * fix: keep Relay public loops open until retire Delivering a promised-final reply was deleting the only record that tied a public thread to later work, so a follow-on ship silently owed no closing reply. Retain the registration after delivery, rechain follow-on work onto the same thread, and make retire --reason the only close. * no-mistakes(review): Propagate public follow-up registration removal failures * no-mistakes(review): Persist retire receipts and align parent resolution * no-mistakes(review): Make rechain resumable after partial obligation creation * no-mistakes(review): Repair follow-up state, briefs, and expiry escalation * no-mistakes(review): Serialize follow-up delivery stamps with retirement * no-mistakes(review): Serialize rechain claims and protect registration terminal states * no-mistakes(review): Avoid reporting retired delivery loops as open * no-mistakes(document): Refresh public-loop documentation and verification evidence * no-mistakes: apply CI fixes * no-mistakes(review): Preserve delivered follow-up bindings during registration replay * no-mistakes(review): Harden public follow-up retirement and rechain races * no-mistakes(review): Fail closed on unresolved secondmate retirement * no-mistakes(review): Bind secondmate cleanup to its recorded canonical home * no-mistakes(review): Fix rechain command output and expiry validation * no-mistakes(review): Validate brief keys and warn on remote promotion * no-mistakes(document): Document retained public follow-up loops * no-mistakes(lint): Remove unused bounded-wait loop variable * feat(bin): merge GitLab merge requests through the guarded PR merge path (kunchenguid#2779) * feat(bin): merge GitLab merge requests through the guarded PR merge path bin/fm-pr-lib.sh already parses a GitLab merge request URL for the watcher, but bin/fm-pr-merge.sh refused every non-github provider, so a merge request had to be merged by hand and got none of the recording, guards, or audit trail a pull request gets. The merge path now dispatches on the parsed provider. A GitHub URL keeps its exact previous behavior. A GitLab URL is addressed through glab by the project URL rebuilt from the parsed host and path, so a merge request on any instance resolves and no host is hardcoded, and no merge-method flag is added because the project's own merge method is what should apply. A GitLab merge happens only after one live read of the merge request confirms it is open, detailed_merge_status is mergeable, has_conflicts is false, blocking_discussions_resolved is true, and the head pipeline succeeded at the exact current head. Every failing condition is reported, not just the first. The verified head is bound to the merge with glab's --sha, so a push landing between the read and the merge fails the merge instead of landing commits nothing verified. Recorded metadata is never the authority for any of this: a rebase moves the head and leaves a recorded value stale, so a recorded head that disagrees with the live one is reported rather than trusted, and the recorded value is read before the recording step because that step drops a GitLab head it cannot resolve. * no-mistakes(review): reject bundled -R clusters and make tool-absence cases host-independent * no-mistakes(test): state authorised GitHub narrowing of bundled -R guard This branch NARROWS GitHub behaviour. The narrowing was authorised deliberately rather than slipping in by accident, and it applies to both providers, GitHub and GitLab alike, because a script that guards one provider and not the other is a trap for the next reader. What bin/fm-pr-merge.sh now refuses is extra merge arguments containing a bundled short-option cluster that includes R, for example "-dR other/repo". The forge CLIs expand such a cluster one character at a time, so it carries "--repo other/repo", and that later value wins over the repository the URL named. Before this change, "fm-pr-merge.sh <task> <github-url> -- -dR other/repo" reached "gh-axi pr merge 12 --repo example/repo --squash -dR other/repo" and exited 0 with pr= recorded and the merge poll armed. It now exits 1 with "extra merge arguments must not override the repository", records nothing, and invokes no forge merge command. Every other GitHub invocation is byte-identical to the base commit. Closing that hole honours the existing rule rather than departing from it. The file header already forbids --repo and -R because the repository must come only from the URL, so a bundled cluster carrying a repository override was never legitimate behaviour to preserve: it was that guard being evaded. Redirecting a merge to a repository the URL does not name is exactly what the guard exists to prevent. The refusal is already pinned on both paths by the existing case test_bundled_repo_override_args_refuse_before_recording in tests/fm-pr-merge.test.sh. On GitHub ("-dR wrong/repo") and on GitLab ("-yR https://other.example/g/p") it asserts exit 1, the refusal wording, no pr= in the task meta, no armed merge poll, and no forge merge command invoked, with a control case proving a cluster that carries no repository override still reaches the forge. No duplicate assertion was added. Both assertions were confirmed to have teeth by narrowing the guard back to a bare -R and watching each path fail. This commit carries no file change: the guard and its coverage landed in 614853d, and this message exists so the pull request description states the narrowing. * no-mistakes(document): fix README pointer for GitLab watch and merge doc * no-mistakes: apply CI fixes * fix(bin): record a lost relay connection instead of an unanswered turn (kunchenguid#2788) * no-mistakes: apply CI fixes * fix(bin): drop a private record citation and narrow the review rule Three corrections to the spoken interface that landed in kunchenguid#2767, plus one fix carried over from that branch after its pull request had already been merged. The confidentiality fix. The module docstring of bin/fm-voice-relay.py cited a private, gitignored fleet record by exact path and section number. That widens what this public repository points at, and it cannot resolve for any reader here, because the path has never been in the repository. Both traps it pointed at are already described in full in the list immediately below it, and docs/voice-relay.md carries the same two for operators with no citation at all, so the pointer is removed and no claim is weakened by losing it. Two comments that referred to "the survey" as though it were something a reader could open are reworded the same way. Neither exposed a path, so that half is comprehensibility rather than confidentiality. The review rule. .greptile/rules.md is kept, because its conditions are right and deleting it would leave the next reviewer to re-litigate a decision already argued out. What was wrong with it is narrower than its existence: it read as settled repository policy, when whether VISION.md itself should be reconciled is an open question belonging to the captain. One sentence now says so, and says that the conditions listed below it are what the interpretation depends on. That narrows the claim rather than widening it. The carried-over fix. The first commit on this branch is 7f98e79 from fm/voice-relay-build-v4, taken verbatim rather than rewritten. It closes the window where a transport failure was recorded and then erased, so a run could be emitted as answered false with relay_error null. That matters more than it looks: relay_error is the field that keeps an infrastructure failure from being averaged into a latency figure, so the failure mode is a dead connection wearing the costume of a slow reply. It landed fifteen minutes after kunchenguid#2767 merged and so never reached the default branch. * no-mistakes(review): name a reason on every unanswered-turn close path * no-mistakes(review): guard the downlink body and pin frames to their turn * no-mistakes(review): attribute reply audio to its own turn and tell endings apart * no-mistakes(review): tell a cut-short reply from an unanswered turn * no-mistakes(review): discard reply audio arriving after the output closes * no-mistakes(review): count discarded reply audio on the speaker path too * no-mistakes(review): keep a reason off a turn already answered in full * no-mistakes(review): say a reset cut a reply short, not that none arrived * no-mistakes(review): read one turn's audio count once, and hush a tidy exit * no-mistakes(document): fix stale session-end relay_error claim in voice-relay guide * fix(composer): stop a blocked pi pane from proving an empty composer (kunchenguid#2811) A pi worker parked on an interactive prompt - a permission dialog, a question menu, a trust dialog - reports agent_status=blocked, because it is waiting on a human keystroke. Pi draws that menu above its separator pair, so the composer region between the rules is blank and structure alone looks like a free composer. _fm_composer_pi_verdict admitted blocked alongside idle and done, so the shared classifier reported an affirmatively empty composer for exactly the pane where typing is unsafe. Every "is it safe to type here?" consumer reads that verdict and proceeds only on an affirmative empty, so both are told yes on a parked prompt: the away-mode injection guard in bin/fm-supervise-daemon.sh, and fm-send's pre-type refusal. The keys then answer the menu instead of composing a message - the highlighted default is selected, the text is discarded, and the record attributes a decision to a human who never made it. blocked now defers to unknown, which every consumer already treats as fail-closed. idle and done still prove an empty composer, so ordinary steering is unchanged, and Cursor is unaffected because its always-blocked panes never reach this pi-only branch. Regression coverage lands first at both levels: the verdict owner (a blocked pi defers) and the herdr adapter (a parked pi prompt is not an empty composer). * fix(bin): require project clone roots during fleet sync (kunchenguid#2849) * fix(bin): require a clone root before fleet-sync touches a project Git repository discovery walks upward, so `git -C projects/<dir>` on a plain directory nested under projects/ resolves to the enclosing repository - in a firstmate home, the firstmate checkout itself. fm-fleet-sync.sh guarded its candidates with `rev-parse --is-inside-work-tree`, which such a directory passes, so every later git call read, pruned and fast-forwarded firstmate's own default branch and reported it under the project directory's label. A running session's AGENTS.md changed underneath it, and the report named a project that had nothing to do with the change. Require each candidate to be the root of its own work tree before any other git command: compare `rev-parse --show-toplevel` against the directory's own physical path. Both sides are physical, so a symlinked clone still compares equal. Anything else is skipped by name, naming the repository that would have been touched, and bootstrap relays that as a FLEET_SYNC line. Regression coverage reproduces the wrong-repo fast-forward against a home nested inside another repository, in both the whole-fleet and single-project forms, and pins that a symlinked clone dir still syncs. * no-mistakes(review): Keep enclosing fixture clean during clone-root regression * fix(bin): retry transient Lavish poll interruptions (kunchenguid#2846) * fix(procevent): retry a transient Lavish poll interruption quietly A live Lavish listener can be cut short by the server with exactly error: Lavish Editor poll response was interrupted code: SERVER_ERROR while the session's marks remain available. Firstmate registered raw `lavish-axi poll` output, so the generic process-event runner captured that transient response as a result and woke the whole fleet over what is really an internal retry. The Lavish adapter now registers its own listener command, which reruns the published blocking poll up to 12 times at 5 second intervals for that one exact two-line response. The match is deliberately narrow: real feedback, ended and missing sessions, any other SERVER_ERROR, and the same interruption still standing once the bound is spent all pass straight through and are captured and announced as before. The retry is a Lavish fact, so the generic runner stays adapter-agnostic. `FM_LAVISH_POLL_RETRY_DELAY` is a bounded 0 to 60 second override for the interval only, refused rather than rounded when malformed, so a test can exercise the real bound without waiting it out. * no-mistakes(review): Harden Lavish retry matching, validation, and cleanup * no-mistakes(review): Bound Lavish retry staging and stabilize regression * no-mistakes(document): docs: explain Lavish retry adoption * no-mistakes(lint): Restore Lavish trap ShellCheck suppression * fix(brief): stop the documented {TASK} fill from corrupting the Herdr gate (kunchenguid#2838) The unguarded Herdr declaration quoted `{TASK}` in its own prose while the scaffold instructs firstmate to replace every `{TASK}` placeholder. The documented global replace therefore spliced the whole task body into the middle of the safety gate's sentence, silently destroying the one contract that exists precisely because the scaffold cannot inspect the task text. Reword the gate to refer to the task text filled in above, leaving the placeholder only at its genuine fill site. Rewording rather than renaming the token keeps the unfilled-charter guards in fm-home-seed.sh and fm-remote-home-seed.sh working unchanged. Add a regression test that performs the documented global fill on ship and scout scaffolds and asserts the body lands once and the gate survives. * fix(bin): resolve the busy-state lock mtime with the platform's own stat form (kunchenguid#2837) The writer lock's stale-lock branch read the lock's mtime with `stat -f %m ... || stat -c %Y ...`. On GNU coreutils `-f` is filesystem stat, so it consumed the format string as a path, complained on stderr, printed a partial filesystem dump (" File: ...") on stdout, and still exited 0. The GNU form in the fallback therefore never ran, and the following arithmetic evaluated the word `File`, aborting the writer under `set -u` with "File: unbound variable". fm-teardown.sh died there after returning the worktree, leaving state/<id>.meta, .status, .busy-gen, .busy-state, .busy-state.lock/ and .turn-ended behind. The surviving metadata kept the watcher monitoring an endpoint whose agent was gone, so a finished task produced stale wakes forever, and every re-run died identically because the abandoned lock was never broken. Detect the platform once and pick the right stat form, the pattern bin/fm-watch.sh already documents, and treat any non-numeric result as "just created" so a future portability surprise degrades to a lock-timeout refusal rather than killing teardown mid-way. * fix(stow): add opt-in pass horizon for memory decay (kunchenguid#2850) * fix(stow): give memory decay a per-pass horizon so the clock fires The tiered decay clocks were wall-clock only, while admission is per-pass: each /stow admits the findings that pass produced. In a home that stows daily those two rates diverge by the stow cadence, an entry the fleet keeps exercising never reaches 30 days unreinforced, and memory only grows while the pass reports decay evaluated. Give each dated marker an optional unreinforced-pass counter and make both tiers stale at whichever horizon comes first: 10 passes or 30 days for aging, 3 passes or 7 days for perishable. Reinforcement clears the counter and nothing else does, so the existing evidence-based restamp rule stays the only way an entry renews its lease. An absent /N means zero, so entries that stay exercised carry no extra marker bytes, and a rarely stowed home keeps its current behaviour through the unchanged date horizon. * no-mistakes(document): Align stow workflow with dual decay clocks * fix(stow): make the per-pass decay horizon opt-in The unreinforced-pass horizon shipped as a new default archival cadence, which is a product default rather than a restoration of the existing wall-clock contract. Keep the 30-day and 7-day horizons as the only default clock, and put the 10-pass and 3-pass horizons behind an explicit opt-in: config/stow-pass-horizon for the firstmate home, and the file's own header pointer for the public skill. With the opt-in absent no counter is written and no counter is read, so a home that does not ask for it decays exactly as it does today. * no-mistakes(review): Preserve frozen counters and correct archive provenance * test(watcher): stop fixture confirmation budgets racing real child startup (kunchenguid#2876) tests/fm-watcher-lock.test.sh passed in isolation but failed intermittently under full-suite and ambient concurrent load. bin/fm-watch-arm.sh computes its confirmation deadline immediately after forking the real child watcher, so the child's entire fork, exec, lock acquisition and beacon publication has to land inside that wall clock. Two cases shrank that budget to one second, leaving a two-second window for work measured at 3.1-4.9s under CPU oversubscription, so the arm honestly reported "FAILED - no live watcher with a fresh beacon" and their premises collapsed. A third case ran on the production budget, but its child must also execute a registered check before exiting: measured at 1.9-2.3s idle and 9.1-13.1s under load, against an 11s budget. The two cases that must confirm a real child now hold the arm to production's own budget instead of a shrunken fixture one, the immediate-wake case gets an explicit budget with headroom over its measured loaded cost, and the two waits for the arm's typed failure are sized off the largest production default rather than a fixed eight seconds. No bin/ change and no default behavior change: the lock's fail-closed semantics, SIGSTOP handling, stale-heartbeat detection and the arm's typed failures are untouched. Verified 4/4 green at 3x CPU oversubscription (loadavg 75-80) after 3/3 red before the change, and CONTRIBUTING.md records the convention. * fix(bin): deterministically order remote tool paths (kunchenguid#2870) * fix(bin): order discovered tool installs by the shell's own expansion fm_remote_job_compose_operator_path built the asdf and mise install directories with `compgen -G`, which does not sort. Bash sorts glob matches in pathexp.c, on the shell's own pathname-expansion path only; `compgen -G` reaches the same glob_filename through pcomplete.c, which sorts nothing. On bash 3.2 (macOS /bin/bash) and every bash before 5.3 that handed the composition raw readdir order, so which install of a multi-version tool a remote job resolved was decided by directory order on disk rather than by this composition. Expand the globs at the call sites and let the function take the matches, so the composition and the documented portable-PATH contract are the same operation. Quoting the account home at the call site also stops a home whose name contains glob metacharacters from being reinterpreted. The colocated regression pins both the order and the mechanism: bash 5.3 moved sorting into the glob library, so an order-only assertion cannot see the defect there. * no-mistakes(review): Remove source-reading PATH regression guard * no-mistakes(document): fix portable serial shard counts after upstream merge * no-mistakes: apply CI fixes --------- Co-authored-by: Kun Chen <3233006+kunchenguid@users.noreply.github.com> Co-authored-by: Mickaël Rémond <mremond@process-one.net> Co-authored-by: Inthuson <iaminthuson@gmail.com> Co-authored-by: Inthuson <inthuson@amazon.com> Co-authored-by: Christopher McKay <101884182+karotkriss@users.noreply.github.com> Co-authored-by: Daan Aerts <daan@daeverhuur.nl>
Vinosaamaa
added a commit
to Vinosaamaa/firstmate
that referenced
this pull request
Aug 24, 2026
* fix(composer): stop a blocked pi pane from proving an empty composer (kunchenguid#2811) A pi worker parked on an interactive prompt - a permission dialog, a question menu, a trust dialog - reports agent_status=blocked, because it is waiting on a human keystroke. Pi draws that menu above its separator pair, so the composer region between the rules is blank and structure alone looks like a free composer. _fm_composer_pi_verdict admitted blocked alongside idle and done, so the shared classifier reported an affirmatively empty composer for exactly the pane where typing is unsafe. Every "is it safe to type here?" consumer reads that verdict and proceeds only on an affirmative empty, so both are told yes on a parked prompt: the away-mode injection guard in bin/fm-supervise-daemon.sh, and fm-send's pre-type refusal. The keys then answer the menu instead of composing a message - the highlighted default is selected, the text is discarded, and the record attributes a decision to a human who never made it. blocked now defers to unknown, which every consumer already treats as fail-closed. idle and done still prove an empty composer, so ordinary steering is unchanged, and Cursor is unaffected because its always-blocked panes never reach this pi-only branch. Regression coverage lands first at both levels: the verdict owner (a blocked pi defers) and the herdr adapter (a parked pi prompt is not an empty composer). * fix(bin): require project clone roots during fleet sync (kunchenguid#2849) * fix(bin): require a clone root before fleet-sync touches a project Git repository discovery walks upward, so `git -C projects/<dir>` on a plain directory nested under projects/ resolves to the enclosing repository - in a firstmate home, the firstmate checkout itself. fm-fleet-sync.sh guarded its candidates with `rev-parse --is-inside-work-tree`, which such a directory passes, so every later git call read, pruned and fast-forwarded firstmate's own default branch and reported it under the project directory's label. A running session's AGENTS.md changed underneath it, and the report named a project that had nothing to do with the change. Require each candidate to be the root of its own work tree before any other git command: compare `rev-parse --show-toplevel` against the directory's own physical path. Both sides are physical, so a symlinked clone still compares equal. Anything else is skipped by name, naming the repository that would have been touched, and bootstrap relays that as a FLEET_SYNC line. Regression coverage reproduces the wrong-repo fast-forward against a home nested inside another repository, in both the whole-fleet and single-project forms, and pins that a symlinked clone dir still syncs. * no-mistakes(review): Keep enclosing fixture clean during clone-root regression * fix(bin): retry transient Lavish poll interruptions (kunchenguid#2846) * fix(procevent): retry a transient Lavish poll interruption quietly A live Lavish listener can be cut short by the server with exactly error: Lavish Editor poll response was interrupted code: SERVER_ERROR while the session's marks remain available. Firstmate registered raw `lavish-axi poll` output, so the generic process-event runner captured that transient response as a result and woke the whole fleet over what is really an internal retry. The Lavish adapter now registers its own listener command, which reruns the published blocking poll up to 12 times at 5 second intervals for that one exact two-line response. The match is deliberately narrow: real feedback, ended and missing sessions, any other SERVER_ERROR, and the same interruption still standing once the bound is spent all pass straight through and are captured and announced as before. The retry is a Lavish fact, so the generic runner stays adapter-agnostic. `FM_LAVISH_POLL_RETRY_DELAY` is a bounded 0 to 60 second override for the interval only, refused rather than rounded when malformed, so a test can exercise the real bound without waiting it out. * no-mistakes(review): Harden Lavish retry matching, validation, and cleanup * no-mistakes(review): Bound Lavish retry staging and stabilize regression * no-mistakes(document): docs: explain Lavish retry adoption * no-mistakes(lint): Restore Lavish trap ShellCheck suppression * fix(brief): stop the documented {TASK} fill from corrupting the Herdr gate (kunchenguid#2838) The unguarded Herdr declaration quoted `{TASK}` in its own prose while the scaffold instructs firstmate to replace every `{TASK}` placeholder. The documented global replace therefore spliced the whole task body into the middle of the safety gate's sentence, silently destroying the one contract that exists precisely because the scaffold cannot inspect the task text. Reword the gate to refer to the task text filled in above, leaving the placeholder only at its genuine fill site. Rewording rather than renaming the token keeps the unfilled-charter guards in fm-home-seed.sh and fm-remote-home-seed.sh working unchanged. Add a regression test that performs the documented global fill on ship and scout scaffolds and asserts the body lands once and the gate survives. * fix(bin): resolve the busy-state lock mtime with the platform's own stat form (kunchenguid#2837) The writer lock's stale-lock branch read the lock's mtime with `stat -f %m ... || stat -c %Y ...`. On GNU coreutils `-f` is filesystem stat, so it consumed the format string as a path, complained on stderr, printed a partial filesystem dump (" File: ...") on stdout, and still exited 0. The GNU form in the fallback therefore never ran, and the following arithmetic evaluated the word `File`, aborting the writer under `set -u` with "File: unbound variable". fm-teardown.sh died there after returning the worktree, leaving state/<id>.meta, .status, .busy-gen, .busy-state, .busy-state.lock/ and .turn-ended behind. The surviving metadata kept the watcher monitoring an endpoint whose agent was gone, so a finished task produced stale wakes forever, and every re-run died identically because the abandoned lock was never broken. Detect the platform once and pick the right stat form, the pattern bin/fm-watch.sh already documents, and treat any non-numeric result as "just created" so a future portability surprise degrades to a lock-timeout refusal rather than killing teardown mid-way. * fix(stow): add opt-in pass horizon for memory decay (kunchenguid#2850) * fix(stow): give memory decay a per-pass horizon so the clock fires The tiered decay clocks were wall-clock only, while admission is per-pass: each /stow admits the findings that pass produced. In a home that stows daily those two rates diverge by the stow cadence, an entry the fleet keeps exercising never reaches 30 days unreinforced, and memory only grows while the pass reports decay evaluated. Give each dated marker an optional unreinforced-pass counter and make both tiers stale at whichever horizon comes first: 10 passes or 30 days for aging, 3 passes or 7 days for perishable. Reinforcement clears the counter and nothing else does, so the existing evidence-based restamp rule stays the only way an entry renews its lease. An absent /N means zero, so entries that stay exercised carry no extra marker bytes, and a rarely stowed home keeps its current behaviour through the unchanged date horizon. * no-mistakes(document): Align stow workflow with dual decay clocks * fix(stow): make the per-pass decay horizon opt-in The unreinforced-pass horizon shipped as a new default archival cadence, which is a product default rather than a restoration of the existing wall-clock contract. Keep the 30-day and 7-day horizons as the only default clock, and put the 10-pass and 3-pass horizons behind an explicit opt-in: config/stow-pass-horizon for the firstmate home, and the file's own header pointer for the public skill. With the opt-in absent no counter is written and no counter is read, so a home that does not ask for it decays exactly as it does today. * no-mistakes(review): Preserve frozen counters and correct archive provenance * test(watcher): stop fixture confirmation budgets racing real child startup (kunchenguid#2876) tests/fm-watcher-lock.test.sh passed in isolation but failed intermittently under full-suite and ambient concurrent load. bin/fm-watch-arm.sh computes its confirmation deadline immediately after forking the real child watcher, so the child's entire fork, exec, lock acquisition and beacon publication has to land inside that wall clock. Two cases shrank that budget to one second, leaving a two-second window for work measured at 3.1-4.9s under CPU oversubscription, so the arm honestly reported "FAILED - no live watcher with a fresh beacon" and their premises collapsed. A third case ran on the production budget, but its child must also execute a registered check before exiting: measured at 1.9-2.3s idle and 9.1-13.1s under load, against an 11s budget. The two cases that must confirm a real child now hold the arm to production's own budget instead of a shrunken fixture one, the immediate-wake case gets an explicit budget with headroom over its measured loaded cost, and the two waits for the arm's typed failure are sized off the largest production default rather than a fixed eight seconds. No bin/ change and no default behavior change: the lock's fail-closed semantics, SIGSTOP handling, stale-heartbeat detection and the arm's typed failures are untouched. Verified 4/4 green at 3x CPU oversubscription (loadavg 75-80) after 3/3 red before the change, and CONTRIBUTING.md records the convention. * fix(bin): deterministically order remote tool paths (kunchenguid#2870) * fix(bin): order discovered tool installs by the shell's own expansion fm_remote_job_compose_operator_path built the asdf and mise install directories with `compgen -G`, which does not sort. Bash sorts glob matches in pathexp.c, on the shell's own pathname-expansion path only; `compgen -G` reaches the same glob_filename through pcomplete.c, which sorts nothing. On bash 3.2 (macOS /bin/bash) and every bash before 5.3 that handed the composition raw readdir order, so which install of a multi-version tool a remote job resolved was decided by directory order on disk rather than by this composition. Expand the globs at the call sites and let the function take the matches, so the composition and the documented portable-PATH contract are the same operation. Quoting the account home at the call site also stops a home whose name contains glob metacharacters from being reinterpreted. The colocated regression pins both the order and the mechanism: bash 5.3 moved sorting into the glob library, so an order-only assertion cannot see the defect there. * no-mistakes(review): Remove source-reading PATH regression guard * fix(bin): prevent routed secondmate work from stranding (kunchenguid#2848) * fix: surface stalled secondmate queues and wake handoffs * no-mistakes(review): Make handoff wakes retryable and stall alerts crash-safe * no-mistakes(review): Prevent duplicate handoff wakes and cover remote delivery * no-mistakes(review): Serialize local handoffs and preserve pre-move wake intent * no-mistakes(review): Serialize teardown with handoffs and retain remote wake confirmation * no-mistakes(review): Reconcile correlated handoff wake delivery after crashes * no-mistakes(review): Keep failed wakes retryable and isolate stall receipts * no-mistakes(review): Reset known-undelivered wake attempts for durable retries * no-mistakes(review): Refuse duplicate sends for unresolved delivery attempts * no-mistakes(review): Atomically restore retryability after reconciled send failures * no-mistakes(review): Serialize delivery confirmation with reconciliation * no-mistakes(document): Document routed wake and stall supervision * no-mistakes(lint): Fix ShellCheck expansion and subshell warnings * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes * no-mistakes(review): Retire stale wake state and defer pre-move wakes * no-mistakes(review): Secure markers, bind batches, and preserve teardown routes * no-mistakes(review): Preserve unresolved prepared wakes across unrelated handoffs * no-mistakes(review): Preserve prepared wakes before unrelated moving handoffs * no-mistakes(document): Document prepared wake batch ownership * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes * no-mistakes(review): Make local wake retirement recoverable * no-mistakes(document): Clarify handoff recovery and teardown documentation * fix: make macOS inbox test path portable (kunchenguid#2857) * feat(bin): deliver local steers through durable task inboxes (kunchenguid#2856) * feat(bin): steer local tasks by durable inbox record plus constant doorbell Stage 1 (local steers) of the captain-adopted reframe in data/fm-send-reliability-reframe-s1/report.md: an ordinary fm-send text steer to a task recorded in this home is appended as a sequenced durable record under state/<id>.inbox/ and the terminal receives only one constant self-describing doorbell line, best-effort. The worker acknowledges by moving the record into handled/; the watcher re-rings an unacknowledged message on an idle pane and escalates once as an ordinary stale wake. --resolve-key closes decisions at enqueue time, because the durable enqueue IS delivery to the task's record. bin/fm-task-inbox-lib.sh owns the record format, doorbell line, and re-ring ladder. The typed plane remains for what must reach the terminal itself: lifecycle keys, harness-native slash and codex $-skill invocations, explicit backend targets, and the remote secondmate leg (unchanged until the remote inbox leg ships separately). The composer classifier is demoted from delivery proof to an advisory ring guard that skips only on a proven pending verdict. Verified live against claude, codex, opencode, pi, grok, and muse: each real worker read its record, acted, and acked with the mv (docs/verification/runtime-backends.md "Steering-inbox doorbell"). * docs(verification): flag the grok 1.0.5 composer-matrix staleness observed by the doorbell run * test(captain-hold): read the chat-channel answer from the durable inbox record * test: migrate fm-control's marker contrast to the inbox record and fix macOS wc padding in the tool-update suite * no-mistakes(review): Harden inbox locking, teardown races, and acknowledgements * no-mistakes(review): Serialize watcher actions with inbox acknowledgements * no-mistakes(review): Bound metadata locking and tighten acknowledgement rechecks * no-mistakes(review): Preserve exact inbox bytes and harden delivery recovery * no-mistakes(review): Harden watcher bookkeeping against concurrent inbox teardown * no-mistakes(document): Update inbox and typed-plane documentation * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes * revert(pipeline): keep parser-native secondmate marking and the both-failed exit out of stage 1 The CI monitor's fix changed the secondmate marking contract for parser-native invocations (appending the marker after the text) and softened the both-commit-and-marker-failed branch to exit 0. The merge authority ruled the marking question out of scope for this stage-1 transport PR (follow-up: fm-send-secondmate-harness-invocation-r1) and ruled the both-failed case a loud nonzero local failure. Restore both, keeping the monitor's legitimate migrations and hardening. * no-mistakes(document): Document inbox and typed-plane boundaries * no-mistakes(document): Scope backend transport docs to typed plane * no-mistakes(document): Clarify inbox attempt-budget documentation * no-mistakes: apply CI fixes * fix(send): the durable record alone governs the inbox exit status Captain-refined ruling on the F2/Greptile finding: the durable inbox record is what delivers the steer, so pending-reply bookkeeping trouble after a successful enqueue never exits nonzero - a resend-inviting status would make automated callers enqueue the delivered instruction again under a new sequence. With the recovery marker stored the watcher reconciles silently; with the commit and marker both lost the send surfaces a distinct reply-tracking-degraded do-not-resend warning and still exits 0. Nonzero remains only where nothing was delivered (or a decision close needs its manual command). Regression: record durable + both bookkeeping writes lost -> exit 0, one record, no duplicate. * no-mistakes(review): Preserve inbox ordering with drain-all doorbells * no-mistakes(review): Surface unwritable inbox ladder bookkeeping * no-mistakes(review): Silence ladder failures after inbox acknowledgement * no-mistakes(document): Update steering inbox documentation * no-mistakes: apply CI fixes * feat(bin): add fast local lint mode (kunchenguid#2891) * feat: add fast local lint mode * fix: preserve complete fm-lint help * fix: isolate fast lint mode * no-mistakes(document): Clarify lint mode documentation ownership * no-mistakes: apply CI fixes * feat(bin): deliver remote steers through durable inboxes (kunchenguid#2901) * feat(bin): deliver remote secondmate steers through durable task inboxes Stage 2 of the inbox+doorbell steer channel (stage 1: kunchenguid#2856). A remote secondmate steer now crosses fm-on.sh as a durable record written idempotently into the remote home's steering inbox plus a best-effort remote doorbell, and the last typed-payload steer transport is deleted: - fm-remote-secondmate-control.sh cmd_send writes the record via the new fm_task_inbox_write_idempotent and rings the doorbell; it no longer types the payload through an inner fm-send at an explicit pane target. - fm-send.sh routes every remote text steer (harness-native included, which marking already reduced to chat) onto the remote inbox leg, retries the identical leg once on ssh 255, closes --resolve-key decisions at enqueue for remote too, and preserves a marked request's reply expectation when completion stays unknown. The exit-3-as- delivered remap, the 255 do-not-resend trap, and the remote typed submit block are removed. - fm-task-inbox-lib.sh owns the idempotent enqueue: an exact-body re-run lands on the existing record, handled or not, so an ambiguous transport can always be safely re-run. - Tests pin the new contract end to end (record + doorbell + no typed payload across ssh, one-record idempotence under an ambiguous transport, enqueue-time decision close, loud real failures, and the deleted typed-payload behaviors gone), and AGENTS.md plus docs/remote-secondmates.md describe the remote leg's new semantics. * no-mistakes(review): Harden remote inbox delivery against lifecycle races * no-mistakes(review): Enable correlation-preserving remote steer resends * no-mistakes(review): Fail closed on stale correlation resends * no-mistakes(review): Include home context in remote resend commands * no-mistakes(review): Lock and revalidate remote parent routes * no-mistakes(document): Clarify remote steer retry documentation * no-mistakes: apply CI fixes * feat: add persistent Pi supervision branch (kunchenguid#2858) * wip: forked supervision on Pi (checkpoint before docs) * fix(pi-branch): harden mirror delivery, fallback encoding, and session replacement Peek-then-shift mirror flush so a failed append retries instead of dropping; durable mirror cursor commits only after delivery into the branch; the main fallback wake is operational-encoded like every watcher injection; session_shutdown quiesces the generation and session_start re-arms, so /new and /resume no longer kill the branch permanently. Registers the extension in the strict typecheck, adds the dispatch handshake test, the branch extension suite, the bash-level regression suite, the session-start replay test, and the opt-in real-SDK live guard. * test(fixtures): carry the branch-dispatch lib and lease lib into isolated fixtures The watcher extension now imports lib/fm-branch-dispatch.ts and fm-teardown sources fm-lease-lib.sh, so every fixture that copies or symlinks those files in isolation gains the new sibling. * no-mistakes(review): Prevent shutdown wake loss and serialize lease claims * no-mistakes(review): Durably hand off wakes and retain portable leases * no-mistakes(review): Require durable reports and clear disposed branch leases * no-mistakes(review): Enforce per-wake outcomes and quiescent lease cleanup * no-mistakes(review): Require wake acknowledgements and tighten branch lifecycle boundaries * no-mistakes(review): Require complete acknowledgements and replay cleanup failures * no-mistakes(review): Bind supervision to lock ownership and durable delivery * no-mistakes(review): Activate branch lazily after session lock acquisition * no-mistakes(review): Preserve undelivered mirror context across extension rebinds * no-mistakes(review): Acknowledge startup replay only after main delivery * no-mistakes(review): Isolate replay metadata from untrusted digest content * no-mistakes(review): Reject duplicate reports for active wake sequences * no-mistakes(review): Retain failed fallbacks and deduplicate outcome replay * no-mistakes(review): Deduplicate durable outcomes and cache delivery receipts * no-mistakes(review): Anchor wake sequence matching to outcome fields * no-mistakes(document): Clarify Pi supervision durability contracts * no-mistakes(lint): Fix ShellCheck issues in branch supervision scripts * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes * refactor(pi-branch): collapse to confused-agent-grade guards per captain decision Captain decision A: the lease/actor guards target the CONFUSED-AGENT threat model bin/fm-gate-refuse-lib.sh already documents; adversarial-grade separation is impossible in the shared-process design and is filed as separate follow-up work. Rip out the machinery that chased it: the generation fence and shell-provenance markers, the wrapper-tagged ancestry walks, guard auto-claim with per-script release traps, the pending-wake files and ack-receipt correlation (the durable wake queue already re-presents anything unacknowledged), the delivery-receipt store with contiguous cursor advancement, the session-start replay-metadata channel, and the branch tool quiescence counters. Keep the behaviors the board requires, each on its simplest implementation: lazy per-action session-lock ownership (cold start activates after the lock lands; a secondary session stays inert), mirror durability across extension rebinds via the durable cursor, replay-exactly-once from the one read cursor, the awaited operational-encoded fallback, per-generation stray-lease cleanup, session-lock-bound lease liveness (a recycled pid or a non-Pi home never honors a leftover lease), the loud accidental-override guards (readonly actor prelude, cross-actor claim refusal), and the role-partition refinements (no forced teardown, no direct relaunch for the branch). Default-on-for-Pi is unchanged. * no-mistakes(review): Enforce lock ownership and serialize lease mutations * no-mistakes(review): Synchronize guard cleanup and bind leases to lock owner * no-mistakes(review): Report outcomes before acknowledging durable wakes * no-mistakes(review): Restrict leases to Pi and instruct main claims * no-mistakes(review): Reject malformed lease locks and torn outcome tails * no-mistakes(review): Validate complete outcome tails before appending * no-mistakes(review): Guard branch side effects across session replacements * no-mistakes(document): Update Pi supervision durability and lease documentation * no-mistakes(lint): Suppress intentional nested-shell expansion warning * no-mistakes: apply CI fixes * fix(pi-branch): authorize lease releases by caller * fix(lint): break redundant source-analysis path in fm-lease-lib.sh fm-lease-lib.sh's lazy fallback source of fm-wake-lib.sh gave ShellCheck's --external-sources traversal a second path into an already 1540-line file that fm-send.sh and fm-teardown.sh also source directly, blowing up the recursive analysis past CI's lint timeout. Mark it a source=/dev/null analysis boundary, matching the existing fm-task-inbox-lib.sh convention. Also restores bin/fm-lint.sh and tests/fm-lint.test.sh to the shared serial-lint definition (dropping an unrelated parallel-sharding change that was itself hanging and masked this root cause). * no-mistakes(document): Correct lease caller-authorization documentation * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes * fix(bin): parallelize startup network sweeps (kunchenguid#2927) * feat(bin): parallelize session-start remote secondmate network sweeps Run per-secondmate liveness and convergence probes concurrently and overlap clone refresh, while replaying each mate's fail-closed diagnostic in original order. Ignore scratchpad* so untracked scratch no longer blocks remote sync. Co-authored-by: Cursor <cursoragent@cursor.com> * no-mistakes(document): Document parallel startup network sweeps * no-mistakes(lint): Fix empty environment assignment lint warning * no-mistakes: apply CI fixes --------- Co-authored-by: Cursor <cursoragent@cursor.com> * test: handle absent watcher wake queues (kunchenguid#2845) * fix(tests): count declared-pause wakes without crashing on an absent queue The exited-declared-pause case counts queued stale wakes by handing state/.wake-queue straight to awk. A watcher that queues nothing never creates that file, and awk aborts on a missing path before its END rule runs, so the count collapses to the empty string. The next comparison then fails as an integer-expression error and surfaces as a wake flood with no number, hiding the real contract breach the following grep names. Read the queue the way the drain-count assertion at the end of this file already does: silence awk's open error and default an absent queue to zero. Applied to all four counts in this case, including the live external-decision gate pair whose queue an acknowledged drain can also leave behind. An absent queue now reports "did not use the bounded paused recheck", while a genuine flood still fails with its real count. Fixes kunchenguid#2628 * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes --------- Co-authored-by: Christopher McKay <101884182+karotkriss@users.noreply.github.com> Co-authored-by: Kun Chen <3233006+kunchenguid@users.noreply.github.com> Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: wenkxu <v-wenkxu@expediagroup.com>
chsong1
added a commit
to chsong1/firstmate
that referenced
this pull request
Aug 25, 2026
* feat(stow): add open-record persistence to /stow before reset (#2488)
* feat(stow): persist the open records a session is holding
/stow curated memory and captured session knowledge, but never touched
record state, while AGENTS.md called it an "unfinished-work sweep" and the
receipt declared the session "safe to reset" - wording that implied a
record-correctness guarantee stow does not make. A shipped PR with no
backlog item, a queued umbrella whose phases had merged, and four decision
holds left open after their answers shipped all survived repeated stows.
Add a bounded pass that files record state from the same volatile input the
rest of stow already uses: the open threads in context, minutes before the
reset destroys them. It creates a record for an unfiled thread and corrects
one the session knows is wrong, through the owning path, and states its
boundary as part of the contract - it never enumerates the backlog, lists
holds, or queries a forge, because it cannot be a reconciliation and must
not be read as one.
Correct the wording in AGENTS.md and the completion receipt so reset-safe
means what it actually guarantees: nothing this session knew was lost.
* no-mistakes(review): correct stow decision-hold inspection to read hold via tasks-axi
* no-mistakes(document): note /stow open-record persistence in README command catalog
* refactor(stow): state open-record persistence as principle, not procedure
The first version enumerated triggers, named commands, and prescribed an
ordered procedure. That is too rigid for an agent skill: it invites literal
execution of a checklist instead of judgment, and every enumerated example
is a way for the guidance to go stale.
Reduce it to the intent - before a reset, the important open work you are
holding in context must end up durably recorded rather than dying with the
session, filing what is unfiled and correcting what is stale - and let the
agent judge importance, the record, and the owning write path.
Keep the scope bound, since it is a decided contract and not a mechanic:
this covers the open work the session is holding, never a reconciliation of
durable records against repository or forge reality. The wording
corrections in AGENTS.md and the completion receipt are unchanged.
* fix(decisions): close decision holds at answer time via one general keyed-answer path (#2490)
* fix(decisions): close captain holds at answer time
Firstmate had two "a decision is open" ledgers with asymmetric closing
mechanics. The live status-log ledger closes atomically at answer time,
because bin/fm-send.sh --resolve-key makes answering a decision be the
act that closes it. The durable backlog hold ledger had no such coupling:
answering and recording were two separate acts, and only the first was
forced by the workflow.
That asymmetry lost four real captain decisions. Their answers were
captured durably to disk, keyed character for character by the hold
decision keys, acknowledged, and even implemented and shipped, yet the
holds stayed open for two days and the captain was asked to re-answer
decisions already on his own disk.
Give the hold ledger the same answer-time-closure property:
- bin/fm-decision-hold.sh gains an `answer` subcommand, the hold ledger's
counterpart to --resolve-key. It shares one unrouted close
implementation with `decline`, so it carries every existing guard - the
captain decision file, the active-hold requirement, retry identity, and
the refusal to release still-routed work - and differs only in the
resolution mode it records. `decline` keeps its stronger meaning that
the answer routes no follow-up work at all.
- bin/fm-procevent-lavish.sh wires the channel that actually carried the
lost answers. `arm --decisions-origin` binds a deck to the origin whose
holds it carries, `answers` reads the structured choices out of a
captured poll result, `close-decisions` maps each key to its hold and
closes it through the command above, and `autohandle` lets the runner
apply that at capture time.
Safety is preserved rather than traded away. Only rows tagged `choice`
are read, so freeform captain prose cannot forge a decision key. Closure
is confined to the one bound origin. The decision text is a pure function
of the captured result, so a replayed capture is idempotent. A hold that
is absent, already closed, or still blocking routed work is skipped and
left for `resolve`, never forced. A deck armed without the binding
touches no hold at all. And autohandle deliberately never reports full
handling, because recording an answer is transcription while acting on it
is firstmate's judgement - so the check wake still reaches the handler.
fm-send --resolve-key is untouched.
* no-mistakes(document): document state/lavish-decisions binding dir in AGENTS.md state inventory
* refactor(decisions): make keyed-answer closure one general capability
The previous pass gave holds answer-time closure but built it as bespoke
Lavish wiring: the review adapter carried the source-to-origin binding,
mapped keys to hold identities, wrote decision records, decided what to
skip, and closed holds itself. That treated a review deck as a special
decision source. It is not - it is an ephemeral discussion format that
happens to carry answers.
Collapse it into ONE general capability with one owner.
bin/fm-decision-hold.sh now owns the whole of "a keyed answer closes its
matching hold":
- `answers <origin> --source <provenance>` is the channel-agnostic
intake. It reads key/answer/label lines on stdin, maps each key to its
hold, and closes it through the same `answer` path, so every guard
applies identically whatever channel the answer came from. --source is
provenance recorded in the decision, never a behavior switch; there is
no per-channel branch and no knowledge of chat, decks, or transports.
- `bind`/`unbind`/`binding` own the source-to-origin binding for any
channel whose answers arrive detached from their origin.
Every channel is now an ordinary caller that only turns what it received
into keyed lines:
- bin/fm-send.sh (chat) feeds the intake for a key that names an active
hold. This also fixes a real gap: once `complete` transfers a decision
to its hold it closes the live status copy, so --resolve-key alone
could never answer a transferred decision.
- bin/fm-procevent.sh feeds it generically. A bound source's captured
result goes to `<adapter> answers <result-file>` and whatever that
prints is piped into the intake. The runner names no adapter, parses
no result, and carries no decision rule, so any future adapter with an
`answers` command works with no change here.
- bin/fm-procevent-lavish.sh keeps only `answers`, which reports the
structured choices a review captured and stops. It maps nothing to a
hold and closes nothing; it lost ~160 lines of decision logic.
Feeding is independent of handling, so it never acknowledges a result
and never suppresses a wake - recording an answer is transcription,
acting on it stays firstmate's judgement.
The regression that proves closure now drives a FIXTURE adapter that is
not the review adapter, so what is proven is that any bound channel
reaches the intake rather than that one channel is wired specially. A
new regression drives the real fm-send over a stubbed transport for the
chat side. Every prior guarantee still holds, and fm-send's status-log
behavior is unchanged.
* no-mistakes(review): test(decisions): drop source-content grep from hold-closure regression
* fix(memory): emit a real @AGENTS.md pointer instead of a CLAUDE.md symlink (#2512)
A Write aimed at CLAUDE.md followed the symlink and destroyed AGENTS.md.
The installer now creates and migrates to a recoverable two-line pointer file.
* fix(ci): keep CLAUDE.md pointer check valid (#2515)
* ci: gate GitHub workflows with pinned actionlint (#2517)
* fix(lint): catch malformed GitHub workflows before merge
A self-broken ci.yml cannot report its own breakage, so parse every
workflow in the local lint path that no-mistakes already runs.
* fix(lint): pin actionlint instead of Ruby for workflow lint
A self-broken ci.yml still has to fail in the local lint path, and the
named tool for that gate is actionlint, not a new Ruby runtime.
* no-mistakes(document): Clarify pinned workflow lint documentation
* fix: install pinned lint tools across supported platforms (#2546)
* fix: install pinned shellcheck and actionlint on macOS and linux arm64
The installers were hardcoded to linux amd64 and sha256sum, so a Mac
dev could not satisfy the refuse-on-mismatch lint gate. Select the
official per-platform archive and checksum, and fall back to shasum -a 256.
* no-mistakes(document): Document cross-platform pinned lint installers
* docs: reconcile test-evidence docs with store_in_repo: true (#2548)
.no-mistakes.yaml has set test.evidence.store_in_repo: true since #2355, but
CONTRIBUTING.md, docs/configuration.md, and docs/architecture.md still described
the old policy of keeping evidence out of the repo in a temp directory.
The current no-mistakes behavior for store_in_repo: true is to publish each run's
test evidence to the orphan no-mistakes/evidence branch and link it from the PR
body. That branch shares no history with code branches, so evidence never enters
a pushed feature branch or the default branch, and CI's tracked personal fleet
paths rule stays accurate.
Docs only. No change to .no-mistakes.yaml or any workflow.
* docs: clarify test evidence branch storage (#2549)
* docs: correct test evidence storage comment in .no-mistakes.yaml
* no-mistakes: apply CI fixes
* docs: hint that live scouts may host their own Lavish review loop (#2563)
Make that a first-class option in always-loaded instructions so firstmate does not default to mediating and tearing the scout down between iteration rounds.
* fix(bin): report remote secondmate delivery and state truthfully (#2570)
* fix(bin): report remote secondmate delivery and state truthfully
A steer to a remote secondmate crosses fm-on.sh to a host-local fm-send
leg whose unconfirmed submit read-back (verdict=pending, typically a busy
mate whose harness queues the steer) was flattened into exit 1, so the
parent printed "error: text not submitted" / "error: text not sent" and
discarded the pending-reply expectation for a steer that had actually
landed. fm-send now carries the verdict across the ssh boundary as a
documented delivered-unconfirmed exit 3: the parent reports the steer as
delivered with confirmation pending, exits 0, keeps the expectation armed
(awaiting_report), and closes --resolve-key decisions, while transport
loss (ssh 255) and real remote failures keep failing loudly with the
remote leg's stderr attached. A local unconfirmed submit now also exits 3
with an honest non-error message and still never closes a decision key.
fm-crew-state.sh and fm-peek.sh no longer read a remote mate's endpoint
through local probes (which misreported a healthy mate as "worktree gone"
/ "can't find session: remote"): both now use the true remote source over
fm-on.sh, and an unreachable or unreadable remote reads as unknown-remote,
never as gone or dead.
* no-mistakes(document): Document remote delivery and state truth
* no-mistakes: apply CI fixes
* feat: adopt spendPriority for quota dispatch (#2574)
* Adopt quota-axi 0.1.29 spendPriority-primary array dispatch.
quota-axi 0.1.29 publishes schema 5 with selection.spendPriority as the primary comparative signal and demotes derivation fields out of default --json. Rank comparable-fit candidates on that scalar, keep runway versus the completion horizon as a hard gate, and raise the compatibility floor so a pre-consolidation build cannot reach dispatch intake.
* no-mistakes(review): Correct schema fixtures and remove prescriptive selection prompts
* no-mistakes(document): Correct quota verification evidence chronology
* Collapse quota-array-dispatch onto TOON-first spendPriority ranking.
Decide from quota-axi's default TOON; keep --json as a rare defensive fallback.
Rank by spendPriority after eligibility, reasoning-class, and runway-feasibility gates, and drop the hand-computed Pareto, pace, reserve, and window-id layers.
* no-mistakes(review): Permit ambiguous JSON fallback and correct reset fixtures
* no-mistakes(review): Correct runway semantics and escalate unresolved uncertainty
* no-mistakes(document): Document TOON-first quota dispatch evidence
* docs: add GROK_BOT.md Grok Bot system prompt (#2590)
* docs: add GROK_BOT.md Grok Bot system prompt
* docs: amend GROK_BOT.md with charter report-back and delegation marker
* docs: classify GROK_BOT.md as public-product
* docs: make GROK_BOT.md the plain Grok Bot system prompt
* docs: update GROK_BOT.md nautical terms and self-improvement (#2592)
* doc: Update language in GROK_BOT.md for clarity
Refine language for clarity and consistency in instructions.
* fix(bin): preserve inactive reconciliation scan progress (#2595)
* fix(bin): guarantee inactive-reconcile scan progress under second quantization
The inactive-outcome scan computed its aggregate deadline in whole seconds,
so a 1-second budget's effective value lands anywhere in (0,1]; a scan
starting just before a wall-clock second boundary rounded its whole budget
away mid-scan and exited having visited no child, while the durable cursor
had already advanced past the never-examined child. This is the CI flake
behind tests/fm-inactive-reconcile.test.sh's 'next bounded scan did not
resume with the following child' (watcher-wake-lock family, portable
serial 2, seen on the PR #2590 run).
Every scan now visits at least its first due child with the per-child
state-read bound floored at one second, so no invocation can be a zero-work
no-op. The outer process-group kill moves to budget+1s: the scan's own
deadline enforces the budget, and the kill is a backstop for a scan wedged
in an unbounded wait instead of a racer that routinely preempts the clean
bounded exit. The wake-lock-wait test bound tracks the backstop (3s -> 4s);
the previously flaky assertion is unchanged.
* no-mistakes(document): Document inactive-reconcile deadline backstop
* doc: Revise Firstmate delegation and communication guidelines
Refactor the guidelines for Firstmate's role and delegation process, emphasizing the importance of crewmates and asynchronous work.
* doc: Update work delegation and secret management instructions
Clarified guidelines for handing off work to crewmates and managing secrets.
* test(procevent): make the process-event suite's detached-runner assertions deterministic (#2617)
Three assertions in tests/fm-procevent.test.sh depended on a detached runner
having finished work that the command starting it does not wait for.
reconcile's replacement runner is started through detach_runner, which only
forks: reconcile returns and counts the start before that runner has claimed
its source or exec'd its child. Any assertion taken straight after reconcile
therefore samples a race.
- The publish-before-apply recovery section left its always-ready /bin/echo
source registered across the recovery reconcile, so that reconcile launched
a competing detached poll (observed: started=1) that then raced every later
assertion for the source claim, the next capture sequence, and this home's
applied record, and outlived the section holding a live claim. It is now
retired before that reconcile - re-announcement is proven from the durable
inbox alone and needs no registration - and started=0 is asserted so a
competing poll cannot be reintroduced unnoticed. This is the same
retire-before-reconcile discipline the self-announcing section already
carries; that section acquired it after the identical race made its
"not-autohandled: self-src" assertion read "already owned: self-src".
- The crashed-leader replacement section snapshotted the replacement's claim
file and execution log behind a fixed 0.5s settle window. On a loaded
machine that window expires first, which is the CI flake behind "a
replacement runner started without recording its own claim" and "reconcile
did not start exactly one replacement source". Both effects are now waited
for with the suite's bounded wait helpers; the exact one-replacement count
is still asserted afterwards, unchanged.
- The duplicate-start section slept 0.5s for reconcile's runner to record
ownership before asserting that a second start loses to it. It now waits
for that claim.
Also tighten one assertion that could not fail as written: "autohandled:
self-src" is a substring of "not-autohandled: self-src", so the applied path
was accepted even when the runner reported the capture left for the handler.
Evidence: on the unmodified suite, 128 full runs at 6-8x concurrency produced
6 failing runs, all in the crashed-leader section. On the fixed suite, 216
full runs under the same load produced none. Reverting the self-announcing
section's retire-before-reconcile line reproduces "already owned: self-src"
on the first iteration, confirming the shared mechanism.
* fix: preserve pending replies and defer remote reposts (#2618)
* fix(bin): keep pending-reply expectations honest on both send legs
Two related asymmetries let the parent-owned secondmate reply guard drop or
nag requests it should not have.
Local delivered-unconfirmed dropped the expectation. A marked request whose
submit read-back stayed unconfirmed (verdict=pending) is the same
not-a-failure outcome the remote leg reports as delivered, but fm-send
discarded the parent's pending-reply record for it, so a request that very
likely landed stopped being tracked entirely. The record now stays armed on
its unconfirmed-delivery marker: a correlated report still resolves it, and
an unanswered one still surfaces through the library's own reconciliation.
Exit 3 and the local rule that an unconfirmed answer never closes a decision
key are unchanged.
Remote replies were nagged for a repost they did not need. A remote mate's
report reaches the parent's status log only through the asynchronous mirror
in fm-procevent-remote-reply.sh, yet the guard read an absent correlated
line as proof the mate never reported - even while the answer was still in
flight, which is the common case because the mirror's poll window is
comparable to the recovery grace. The mirror now publishes one caught-up
watermark from a quiet window, and the guard admits a missing report as
evidence only once that watermark passes the turn that should have produced
it. A genuinely missed report still gets exactly one repost, and a channel
that is behind, unarmed, or broken leaves the request durably open and
un-nagged rather than nagging blind; the mirror escalates its own continuity
failures as before.
Tests: a local unconfirmed secondmate send keeps its expectation armed and
resolvable; a mirrored correlated remote reply resolves with no repost; a
stale or absent watermark withholds the repost while a fresh one still
releases it; a quiet remote window publishes the watermark and retirement
clears it.
* no-mistakes(review): Distinguish preempted polls from quiet windows
* no-mistakes(document): Clarify remote reply channel freshness
* no-mistakes(lint): Annotate shared remote preemption exit constant
* fix(bin): honor declared pauses in busy-pane wedge checks (#2619)
* fix(watch): honor a declared pause on a busy pane's completed-turn bound
A worker that declares an external wait (`paused:`) and then blocks in one
long foreground call - a review-hosting scout parked in a single blocking
`lavish-axi poll`, a bounded watch loop, a rate-limit sleep - keeps its pane
BUSY, so the stale path that already honors declared pauses never ran for it.
The busy-pane completed-turn bound instead routed it straight into
wedge_timer_check, which re-escalated "possible wedge, escalation N" (and, past
the threshold, demand-deep-inspection) every FM_STALE_ESCALATE_SECS for as long
as the review stayed open.
busy_turn_bound_check now owns which absorber takes a crossed bound: a crew
whose own last status line declares an external wait or a verified captain-held
transfer takes the bounded FM_PAUSE_RESURFACE_SECS recheck, and everything else
keeps the unchanged wedge timer. The discriminator is the declaration together
with liveness (the caller has already confirmed the pane is busy), never a
blanket silencing - a crew that declared nothing, or whose pane is not live,
escalates exactly as before, and a declared pause still re-surfaces once per
long cadence so a forgotten wait cannot rot invisibly. Away mode is untouched:
the daemon owns pause triage there and already reads the same vocabulary.
The two call sites also no longer clear pause bookkeeping in the same poll the
pause cadence recorded it, which would have erased the re-surface throttle and
turned the long cadence back into a per-poll re-surface.
Tests: a three-phase regression fixture pins the absorbed pause, its long-cadence
recheck, and the restored wedge escalation once the declaration is lifted on the
same busy over-age pane.
Also de-flakes tests/fm-watch-triage.test.sh, which failed spuriously on a loaded
machine: fixed liveness budgets were reaping watchers mid-startup, so assertions
on post-poll state passed vacuously or failed spuriously. Waits that describe a
poll's outcome now wait for a completed poll cycle via the liveness beacon, the
heartbeat test waits for the heartbeat it asserts on, and every wait_for_exit
budget is the uniform 10s already used elsewhere in the file.
* no-mistakes(review): Fail poll-cycle waits on timeout
* no-mistakes(review): Prevent poll timeout test hangs
* no-mistakes(document): Clarify paused busy-pane supervision
* doc: Enhance communication guidelines for decision-making
Added guidelines for decision communication to the captain.
* doc: Update task delegation and communication guidelines
Clarify communication protocols with crewmates regarding task delegation and reporting.
* fix(bin): reliably confirm herdr steer submission (#2647)
* fix(herdr): confirm local steers that native agent-state misses
Herdr can leave agent_status idle for a landed Claude turn and can keep
queued Enter text visible while busy, so fm-send was reporting false
swallows. Confirm those cases through the shared queued-Enter verdict
and a cleared composer, and keep a genuine idle pending composer as
unconfirmed.
* no-mistakes(review): Stop Herdr Enter retries on unreadable composers
* no-mistakes(review): Reject queued delivery when all Herdr Enter sends fail
* no-mistakes(review): Prevent confirmation after failed Herdr Enter
* no-mistakes(review): Pace Herdr retries and clarify submit fallback
* no-mistakes(review): Align Herdr submit docs with idle fallback
* no-mistakes(document): Correct Herdr submit-confirmation documentation
* feat(bearings): add interactive Lavish fleet board (#2659)
* feat(bin): accept any-origin decision bindings with full-identity keys
An aggregation surface (the bearings board) carries captain answers for holds
across origins, but a binding was one-origin-per-source and the Lavish adapter
capped question keys at 64 chars while real full hold identities measure 69-81.
- fm-decision-hold.sh: bind <source-id> --any-origin records the (any) marker;
binding prints it verbatim and answers accepts it, so the runner's feed seam
carries an any-origin source with no runner change. In any-origin mode each
key is a full hold identity <origin>-decision-<key>, split at its first
-decision-; a key with no separator (merge/dispatch instructions) is skipped
and feeds nothing, keeping non-decision answers out of the hold ledger by
construction. Every existing close guard applies unchanged.
- fm-procevent-lavish.sh: raise the question-key cap 64 -> 128 so a full hold
identity fits; the slug-shape security property is unchanged.
- tests: cross-origin closure through the real runner seam, an 81-char
identity through the adapter, cap and shape refusals, routed-work skips,
nonexistent-identity skips, and idempotent replay.
* feat(bearings): add the /bearings lavish interactive fleet board
/bearings lavish renders the bearings snapshot onto a shipped, reusable board
template and arms it as a Lavish process-event source, so the captain answers
Captain's Call items on the board and firstmate is woken by an ordinary check
wake - no conversational turn ever blocks on a poll.
- .agents/skills/bearings/assets/board-template.html: the shipped template
(myfirstmate design system inlined, one fm-bearings-board.v1 JSON slot,
fail-closed schema guard that renders an error card instead of an empty
fleet). Per-invocation agent work is composing the payload only.
- bin/fm-bearings-board.sh: build/refresh owner - fail-closed payload
validation, slot injection with a round-trip check and \u003c escaping,
stable board path, any-origin bind ALWAYS before arm, arm-if-absent.
- bearings SKILL.md: the lavish invocation option, board composition rules,
board-wake handling, and the captain-ruled merge-click authorization with
its mandatory safeguards (PR resolved from the task's own meta record,
wake-time green re-verification, never a red or changed PR, merges only
through bin/fm-pr-merge.sh, chat echo with the full PR URL).
- process-event-sources SKILL.md: one-line board-wake routing trigger.
- tests: payload refusals, injection round-trip, bind-before-arm, idempotent
re-arm, and template slot integrity.
Fleet pickup: homes receive this after merge plus a firstmate self-update;
landing timing is coordinated with the main firstmate.
* no-mistakes(review): Harden bearings board validation and wake handling
* no-mistakes(review): Require HTTPS for bearings board PR links
* no-mistakes(review): Fail closed and bound bearings board answers
* no-mistakes(review): Enforce UTF-8 byte limits for board answers
* no-mistakes(review): Serve bearings board before arming and reject empty actions
* no-mistakes(review): Prove bind-before-arm ordering through live answer consumption
* no-mistakes(document): Document bearings board and cross-origin answers
* fix(bearings): restore decision options and add close controls (#2707)
* fix(bearings): always show decision options and a close/drop control
Freeform-only Captain's Call cards hid the option buttons the board was designed around, and there was no way to drop a stale hold without inventing an answer. Require selectable options, keep freeform as a supplement, and route the reserved __drop__ answer through decline so the hold leaves Captain's Call.
* no-mistakes(review): Fix drop closure and decision-only option validation
* no-mistakes(review): Preserve answerability for non-decision cards
* no-mistakes(document): Clarify decision drop documentation
* ci: require no-mistakes pipeline step attestation (#2710)
Signature-only PRs can hide skipped review, test, or document steps. Fail unless no-mistakes >= 1.46.0 attests those three steps completed.
* feat: collapse decisions into tasks held for the captain (#2728)
* feat(captain-hold): collapse the decisions concept into tasks held for the captain
A decision is no longer a separate type: it is an ordinary backlog task held
for the captain, identified by its task id. bin/fm-captain-hold.sh owns the
surviving behaviors - guarded hold creation, the recorded-answer close
(answer/answers with a release mode for captain-gated work), the source
bindings, and the investigation completion gate - and bin/fm-decision-hold.sh
becomes a one-release compatibility shim over it.
The fleet snapshot now parses hold-until and computes captain_actionable as
queued + captain-held + unblocked + due, independent of row kind, plus a
presentation-only deferred_marker for prose-deferred rows. Bearings renders
every due captain-held task in Captain's Call, date-deferred holds as dated
Charted Next gates, suppresses prose-deferred rows from default views with an
omitted disclosure, and excludes from Recently Landed anything that closed
while still held for the captain.
Legacy compatibility: pre-collapse <origin>-decision-<key> rows are already
plain task ids and keep working; short keys in recorded metadata, concrete
origin bindings, chat --resolve-key fallbacks, and old resolution records all
resolve in place.
* no-mistakes(review): Fix captain answer replay and body preservation
* no-mistakes(review): Fix captain hold idempotency and legacy replay
* no-mistakes(review): Validate card close modes and compatibility routing
* no-mistakes(review): Enforce release replay mode matching
* no-mistakes(review): Prevent duplicate decision cards and released replay mismatches
* no-mistakes(review): Preserve answer columns and legacy resolve replays
* no-mistakes(document): Document strict replay and legacy compatibility
* no-mistakes(lint): Quote done literals to satisfy ShellCheck
* no-mistakes: apply CI fixes
* fix(rebase): keep collapsed captain hold board semantics
* fix: bound recovery announcements and preserve supervision (#2733)
* fix(watch): announce recovery once per generation and keep successors supervising
A lost Pi/OpenCode handling handshake re-announced the same recovery
generation on every cycle and spent the successor's first ~55s blind, so
a real crew event could be ignored and then dropped. Record the
announcement in the durable marker, confirm the handshake before the
follow-up without swallowing failure, and enter the poll loop immediately.
* no-mistakes(review): Tighten recovery event timing regression
* no-mistakes(document): Document recovery-loop supervision guarantees
* fix(bin): surface captain-call record divergence (#2744)
* fix(bin): signal a captain call resolved in the log but still held
A captain call has two records and closing one has never closed the
other: a `resolved [key=...]` line closes the status-log fold, while the
backlog task held for the captain closes only through
`fm-captain-hold.sh answer`. Answering on the status side alone left no
trace of the disagreement - the fold went quiet, the durable record kept
saying the captain owed an answer, and nothing warned. The defect was
never the separation; it was the silence.
Add `fm-captain-hold.sh diverged`, a read-only report of that
contradiction, and print it from `fm-wake-drain.sh` as a bounded RECORD
DIVERGENCE section beside OPEN DECISIONS on every drain. It flags one
condition: a task still open and still carrying the captain-hold
annotations whose key was closed on the status side by the resolve verb,
under the collapsed identity or the legacy derived one.
It closes nothing, ever. A captain call closed wrongly leaves review
entirely, which is worse than the noise, so both reconciliation
directions stay human-owned and the printed hint names both - a
resolution is not proof the captain ruled, since a call can dissolve on a
false premise or turn out to have been a question of fact.
Three states are deliberately not divergence: a `captain-held` close is
the verified transfer `complete` writes, a still-open keyed decision
belongs to the OPEN DECISIONS fold, and a captain call with no routed
work item is legitimate rather than incomplete, so routed work is no part
of the test.
`fm-classify-lib.sh` gains `status_key_closing_verb`, which reports how
the status side currently reads one key by replaying the existing
`_fm_decision_fold_line` rule rather than re-deriving it, so the two
closing verbs stay distinguishable in one place. The per-wake cost is one
`tasks-axi list`, one key scan per status log, and the precise per-key
fold only for a key that already names a still-open task; the call is
hard-bounded so a slow backlog tool can never delay wake presentation.
* fix(document): Correct divergence lifecycle documentation
* fix(document): Neutralize divergence lifecycle prose
* fix(bin): re-arm after an abandoned auto-arm claim and defer a wedge escalation while a worktree is written (#2524)
* fix(watch): re-arm supervision after an abandoned auto-arm claim
A Claude auto-arm cycle that armed, delivered one rewake, and exited left
its single-flight lock behind. Both Stop-event participants then deferred
to that lock forever, because its recorded pid was still live: the
turn-end guard read it as recovery under way and allowed the stop, and the
next Stop firing treated it as another owner and declined to arm. On
2026-08-14 a home with two tasks in flight lost supervision for about 40
minutes with no watcher process and no watcher lock, its beacon frozen at
the one delivery, and both crewmates' finished reports sat in the durable
queue until an operator drained it by hand.
Abandonment is now proven from the epoch ledger instead of inferred from
pid liveness. A lock whose holder pid matches the ledger's own owner_pid
while the recorded outcome is anything other than arming has already
finished its decision, so that claim is reclaimed under the lock's steal
mutex, stops counting as recovery ownership in the guard, and is cleared
by the guard's terminal check rather than deferred to. A failed clear
re-blocks instead of allowing a blind stop, and an arming entry stays in
flight however old it is, because its owner foregrounds the arm for the
whole watcher cycle.
Issue #2251's PR #2263 does not cover this failure. It is closed and
unmerged, lives entirely in bin/fm-watch-arm.sh, and retires the stalled
watcher and matching stale watcher lock of an arm that is currently
running. Here no arm and no watcher were running and no watcher lock
existed, so it has nothing to retire and the home stays blind.
tests/fm-claude-stop-autoarm.test.sh covers the reclaim, the still-arming
and unnamed-owner cases that must keep the gate closed, and the failed
clear. tests/fm-turnend-guard.test.sh covers the guard side of the same
boundary. Both fail without this change.
* fix(watch): defer a wedge escalation while the task worktree is written
The wedge detector had two inputs, rendered pane quietness and the run
step, and neither can see a crew that is writing source, then tests, then
documentation behind a static pane. On 2026-08-14 one crewmate produced
eight consecutive possible-wedge escalations in a single afternoon, three
of them demanding deep inspection, while it was demonstrably working and
then committed. Every one of them cost a supervision turn to disprove by
hand.
Add write activity inside the crew's own recorded worktree as a third
liveness input. crew_worktree_written_since compares the worktree against
the caller's existing idle-window timer file, so -newer needs no clock
arithmetic, no temp file, and no portable mtime write. The probe runs only
inside the branch that was about to escalate, which bounds it to one
pruned, depth-bounded walk per window per FM_STALE_ESCALATE_SECS and
leaves the per-poll stale sweep exactly as cheap as before.
Positive evidence defers rather than cancels. The idle timer restarts so
the next window probes again, the escalation counter is neither advanced
nor reset so a later genuine wedge keeps the demand-deep-inspection
history it earned, and a .writing-since marker ages the whole deferral
chain so the pane still re-surfaces once per FM_PAUSE_RESURFACE_SECS,
through the same throttle shape a declared pause already uses, labeled as
a recheck rather than a wedge. This can only reduce false positives: every
absence of evidence, including no recorded worktree, a torn-down worktree,
a missing anchor, and a failed walk, falls through to the unchanged
escalation schedule, so a crew that writes nothing still escalates on the
existing timetable.
What the signal cannot see, by design or by construction:
- CPU burn with no writes, such as a long compaction, is invisible. That
case keeps the old behavior exactly.
- A commit-only phase writes only .git, which is pruned first so that
firstmate's own read-only git commands against the worktree can never
make the probe self-fulfilling.
- Writes under the pruned generated trees, or deeper than
FM_WORKTREE_WRITE_MAXDEPTH, do not count.
- The probe cannot attribute a write to the crew, so a background build or
another process touching the tree looks the same. The hourly re-surface
is what bounds that, and a churny file cannot buy silence.
- The away-mode daemon's own escalation path is deliberately untouched.
tests/fm-watch-triage.test.sh covers the classifier including the .git
prune, both halves of the live case on one fixture (quiet plus writing
defers, quiet plus silent still escalates and counts), and the bounded
re-surface. All three fail without this change.
* no-mistakes(review): prove autoarm claims by identity; skip mate-home write probe
* no-mistakes(document): document away-mode wedge boundary and probe filesystem limit
* no-mistakes(document): qualify turn-end recovery condition for abandoned auto-arm claims
* fix(watch): keep a write deferral scoped to its own idle window
Two consistency gaps in the worktree write probe, both found while reviewing
the wedge-deferral change on this branch.
A write deferral is a bounded chain: its .writing-since marker ages the whole
chain so a churning worktree still re-surfaces once per resurface window. That
is only sound while the chain belongs to the current quiet stretch, so every
path that restarts the idle-window timer has to drop it too. Two did not: the
corrupt-timer repair in wedge_timer_check, and both first-sight branches for a
captain-relevant status. A chain left over from an earlier quiet stretch made
the first deferral of the new window re-surface immediately instead of after a
full fresh window.
FM_WORKTREE_WRITE_PRUNE is a skip list, so clearing it reads as "skip nothing"
and is the obvious way to widen the probe to the whole depth-bounded tree.
Instead an empty list reported no evidence at all, quietly costing the wedge
detector its third liveness input on a home that meant to widen the walk. An
empty list now widens the walk, and the header says so.
Neither change alters when a stall that writes nothing escalates.
Regressions in tests/fm-watch-triage.test.sh cover all three paths and each
one fails on the pre-fix code.
* no-mistakes(review): honor an empty write-prune, bound the probe, share window_key
* no-mistakes(document): align probe knob count and guard regression-coverage ownership
* no-mistakes(lint): silence deliberate single-quote SC2016 in write-prune env test
* fix(bin): give a captain hold the same bounded pause cadence as a declared pause (#2748)
* fix(bin): give a captain hold the same bounded pause cadence as a declared pause
Two supervisors read a finished task's last status line and disagreed about which
declarations mean an idle endpoint is expected. bin/fm-inactive-reconcile.sh
suppresses its inactive-outcome scan only on `captain-held`, while the away-mode
daemon's wedge path gated deferral on `paused` alone. Both read the LAST line, so
the two verbs are mutually exclusive and no finished task waiting on a person
could satisfy both at once. Marking 11 such tasks `captain-held:` silenced the
900s outcome scan and immediately produced five possible-wedge escalations in one
batch, because the 240s wedge detector no longer saw a pause verb.
fm-classify-lib.sh's status_is_paused_or_captain_held already owns the combined
question, and bin/fm-watch.sh's ordinary-crew wedge path already asked it. This
extends that same answer to the paths still asking the narrower one:
- bin/fm-supervise-daemon.sh, all six sites, which form one subsystem and have to
move together. classify_stale returns the pause action, reconcile_pause_tracking
and migrate_watcher_pause_markers record and migrate the marker, and
housekeeping defers the wedge and then re-surfaces the recheck. Changing only
the stale-persistence gate would defer the escalation while
reconcile_pause_tracking recorded nothing, so the wedge marker would persist and
the sweep would `continue` past it forever: quiet, but never re-surfacing.
- bin/fm-watch.sh's secondmate stale gate, whose downstream owner
pause_state_class already treats both declarations identically.
- bin/fm-push-transition-lib.sh's absorb, where either declaration already names
the human the transition would report and the wait is already durably recorded.
Quieting alone would be half a fix, so the bounded re-surface had to reach a hold
too. A hold has no current-state mapping, unlike `paused`, so authoritative crew
state reports it as unknown and pause_state_class received `none`. An ordinary
crew recovers pause classification from that state through confirmed agent death,
which proves no live decision gate is being silenced. A secondmate's endpoint
liveness is deliberately never read there, because an idle mate is healthy by
design, so that confirmation is unavailable by construction and cannot be
required: without recovering the classification for a mate, every caller silenced
a held mate outright and its hold would rot invisibly. That promotion is bounded
by the declared-wait guard at the top of the function, so it can only reclassify a
task that already declared a wait and shows no positive working evidence.
Two narrow `status_is_paused` calls are deliberately left alone.
bin/fm-crew-state.sh's map_log_state is a current-state reporting contract, not a
wedge path; reporting a hold as `paused` would erase the distinction
status_key_closing_verb and fm-captain-hold.sh depend on, where a `captain-held`
close is a verified durable transfer and a `resolved` close claims outright
settlement. fm-classify-lib.sh's call inside status_is_captain_relevant needs no
change because that function's own case list already returns non-relevant for
`captain-held`.
bin/fm-inactive-reconcile.sh keeps its `captain-held` suppression as it is. Its
guard exists because a finished task's crew state still reports done from a
higher-priority source than the log, and a declared pause needs no such guard: the
scan only reports done or failed, and nothing else reaches its record path.
Widening it would change a separate subsystem's reporting contract, which this
defect does not require.
Coverage extends the existing colocated patterns for these predicates and asserts
both halves. tests/fm-daemon.test.sh covers the classification, the wedge marker
converting to pause tracking with no escalation, the bounded re-surface with its
window reset, and the boundary case where an answered hold stops claiming the
cadence. tests/fm-watch-triage.test.sh covers a held secondmate re-surfacing on
the same bounded cadence without being labeled a wedge.
tests/fm-supervision-events.test.sh covers the absorbed push transition. Every one
of these fails on the pre-fix code except the answered-hold boundary case, which
is there to pin that the quieting was not widened too far.
The `paused:` workaround appended to those 11 tasks is live supervision state and
is untouched here. It can be retired once this lands.
* no-mistakes(review): name the captain in a held task's bounded recheck
* no-mistakes(document): extend declared-wait supervision docs to captain-held holds
* fix(bin): make lint prerequisites and harness tests reliable (#2758)
* fix(lint): name the installer when ShellCheck or actionlint is missing
A missing actionlint exited 127 like a bare command-not-found. Fail with
exit 1 and point at the pinned installer, matching the missing-ShellCheck
path, without weakening the version pin.
* test: isolate kimi and muse detection from inherited Cursor markers
Harness detection checks CURSOR_AGENT before ancestry, so these
markerless-adapter cases failed when the suite itself ran under Cursor.
Clear the verified markers the same way the secondmate harness tests already do.
* no-mistakes(document): Document Muse Cursor marker cleanup
* feat(bin): report watched tooling updates that are available or installed but inert (#2684)
* feat(checks): report tool updates that are available or installed but inert
Firstmate had no way to notice that tooling this home depends on needs an
update, and no way at all to notice the worse case: an update that installed
correctly and then did nothing.
That second case is why this exists. A tool that self-installs into
~/.local/bin while a version manager keeps its own older copy earlier on PATH
looks completely up to date to anything that asks only "is a newer version
published". On 2026-08-20 a Herdr update landed at 0.8.2 while an older 0.8.0
copy stayed earlier on PATH, so every Herdr command failed on a protocol
mismatch and firstmate could not read its own fleet.
bin/fm-tool-update-check.sh reports the two conditions separately:
<tool> update available a newer version exists at the update source.
<tool> update not in effect a newer copy is installed on this host, but
PATH still resolves an older one.
PATH skew is measured, never inferred. Every executable copy of a watched
command on PATH is asked for its own version and those answers are compared,
so one lookup cannot hide the skew, and a directory name is never read as a
version because a version manager's "latest" directory can hold an older
build. A copy that will not report a version is a check failure, not a pass.
The watched tools live in local, gitignored config/watched-tools.json, so
adding a tool is a config edit rather than a code change, and the file is
never propagated to another home. Update sources cover both shapes: a local
clone's commit distance from its remote branch, and a command's own version
and update announcement, including a tool like no-mistakes that prints its
version on one command and announces a new release on another.
The check prints one line when something needs attention and prints nothing
otherwise, so it rides the existing watcher state-check contract with its
trust binding instead of introducing a schedule of its own, and
state/.tool-updates keeps the same pending update from being reported on
every poll.
The check only reports. It never installs, updates, reorders PATH, touches a
version manager, or fetches into a watched repository; every git probe is
read-only.
Tests cover the skew case as a regression, and it was verified by mutation:
removing the skew report, or stopping after the first PATH hit as a single
lookup would, each make that test fail.
* no-mistakes(review): fix tool update check probe reporting, budget, and shim write
* no-mistakes(review): keep sweeps alive on broken patterns and oversized budgets
* no-mistakes(review): roll back failed arm, widen budget clamp, bound repo probe
* no-mistakes(review): guard git probes at the budget, record uncut findings
* no-mistakes(document): fix stale watched-tool report-record wording in docs and header
* no-mistakes: apply CI fixes
* no-mistakes: apply CI fixes
* no-mistakes: apply CI fixes
* no-mistakes: apply CI fixes
* no-mistakes: apply CI fixes
The behavior shard's watch-triage suite failed on the new worktree-write wedge
tests. Those five tests are the only ones in the file that do not use its
standard waits. They give a fixed 3 second liveness budget to the one poll that
now spawns the bounded worktree walk, and 4 seconds to an escalating watcher
where every other test in the file gives 10. On a loaded runner that poll
outlives the fixed budget, so the round is reaped before the deferral it asserts
on is recorded, and the test reports a lost deferral instead of the deferral
under test. Wait for a completed poll cycle through the file's own
wait_poll_cycle, which is what its header documents this hazard for, and use the
file's standard 100 tick exit budget.
Verified against a load that reproduces the failure: 11 of 12 runs failed
before, 8 of 8 pass after. Verified by mutation too, so the waits still prove
the behavior: removing the write deferral, and keeping a finished deferral chain
across an idle-timer repair, each still fail their test.
* fix: decouple ask-user decisions from yolo (#2764)
* fix: treat yolo as merge authority only, not ask-user finding authority
Yolo on/off was documented as also deciding no-mistakes ask-user findings, which hid firstmate's duty to judge unambiguous-toward-design findings itself. Keep every safety boundary; this is a contract clarification, not a relaxation.
* no-mistakes(document): Clarify yolo documentation ownership and merge posture
* feat(bin): add a spoken interface that answers from records and hands work over (#2767)
* feat(voice): spoken round trip on Nova Sonic 2 with a measured relay cost
Step one of the spoken interface: the laptop captures and plays audio, this
desktop holds the model session, and no AWS credential leaves the desktop.
Measured, amazon.nova-2-sonic-v1:0 in eu-north-1, end of speech to first byte
of reply audio, 6 runs each, all answered, on a question that forces a records
read:
relay path 1.229 1.379 1.428 1.447 1.481 1.516 median 1.438
direct 1.147 1.179 1.203 1.237 1.244 1.317 median 1.220
The relay costs about 0.22s of the median. The direct figure reproduces the
earlier survey, which is what makes it a usable control. Excluded: the
captain's own ssh round trip, microphone capture, and speaker output. This
desktop has no microphone and no speaker, so every run used audio files.
Three pieces:
bin/fm-voice-relay.py holds the conversation on this host
bin/fm_voice_records.py what a spoken answer may read, and the handover
bin/fm-voice-client.py the laptop end; audio devices UNVERIFIED
bin/fm_voice_frame.py the wire format both machines share
Real work is handed to the existing bin/fm-inbox.sh rather than a second
queueing surface, and the agent says it is handing over rather than answering
as firstmate.
Read scope: Done history and free-form note bodies are never assembled at any
scope, so the wide default cannot reach the places commercial detail
accumulates. config/voice-read-scope narrows it to counts only, and
config/voice-read-deny excludes a named item in one line. The boundary is an
executable test that widening the reader fails.
Push to talk is the default because it is cheaper and the choice is still open;
--listen open-mic is the single flip.
Two traps worth knowing: a clip with no trailing silence is never answered, and
the end of a reply is contentEnd with stopReason END_TURN, not completionEnd.
A second user turn in one session is treated as barge-in unconditionally, and
an interrupted turn that calls a tool is lost, so the session reconnects per
turn and gives up conversational memory. That is the concrete thing step three
has to solve.
* no-mistakes(review): fix voice relay credential reuse, frame validation and record parsing
* no-mistakes(review): test uplink header guard, bound unknown expiry, align state dir
* no-mistakes(review): decide deny per item, guard turn failures, bound ambient credentials
* no-mistakes(review): read account config from home, harden deny and turn failures
* no-mistakes(review): close status verb set, fix inbox help, pair data override
* no-mistakes(review): keep profile-free relay alive, unblock loop, fix dead assertion
* no-mistakes(review): hide finished pull requests, refuse open mic, keep suite offline
* no-mistakes(review): survive reader failures, release devices, fix claims
A failure while handling a model event, or while sending a tool result,
left the reader task dead with ended and turn_done clear, and close()
re-raised the stored failure on every await. One dropped stream became a
relay that could never build another session. The reader now reports the
session over in a finally whatever killed it, and close() absorbs the
task the same way it already absorbed its sends.
The laptop client releases what it already started when a later startup
step refuses, SystemExit from the handshake wait included, and names a
device refusal instead of leaking a raw PortAudio error. Whether it
releases correctly against a real device is still unverified here.
The records docstring claimed every reading was filtered to open ids.
Only the pull request count and list are; the worker count and the state
histogram cover every live runtime record, finished ids included,
because a meta file still on disk still needs tearing down.
The finished-work deny half of the suite asserted things that held with
the deny list absent. It is replaced by a deny on an open title, which
removes the row and says so while the count stays honest.
* no-mistakes(review): name reader failures, split file and device refusals
A failure inside the model reader released the waiting turn and told
nobody. The session was not marked spent, no notice reached the client,
and the client waits for a reply end or a notice, so the captain got
their whole timeout of silence and then a record saying the turn went
unanswered with nothing about why. Both ends of the relay now name a
failed turn through one function, once per turn, and --self-test carries
the cause in relay_error the way the client's own record does.
Two things that are not failures stay that way. A stream that simply
ends is the end of a session, which serve still reads on its own terms.
A stream that goes away because close() asked it to is an ordinary
renew, and announcing it would have put a failure notice in front of the
captain on every turn.
On the laptop end, the refusal that became a device error covered the
file-backed playback and capture too, so a mistyped --in-file was
reported as an audio device failure and the advice named the flag that
had just failed. The file ends now report the path and the flag that
chose it and stay an OSError; the device ends keep the device advice and
name the flag for that end. The device paths remain unrun here, so only
the file halves are covered by a test.
* no-mistakes(test): survive model session end, order client turn frames
* no-mistakes(document): sync voice relay docs with reviewed relay behavior
* no-mistakes(document): re-measure relay latency and correct its cause
* no-mistakes(document): correct measurement date and name the unmeasured SSH hop
* no-mistakes(document): describe the unpublished control measurement, fix list formatting
* no-mistakes: apply CI fixes
* no-mistakes: apply CI fixes
* no-mistakes: apply CI fixes
* fix(bin): preserve Relay follow-up loops until explicit disposition (#2763)
* fix: keep Relay public loops open until retire
Delivering a promised-final reply was deleting the only record that tied a public thread to later work, so a follow-on ship silently owed no closing reply. Retain the registration after delivery, rechain follow-on work onto the same thread, and make retire --reason the only close.
* no-mistakes(review): Propagate public follow-up registration removal failures
* no-mistakes(review): Persist retire receipts and align parent resolution
* no-mistakes(review): Make rechain resumable after partial obligation creation
* no-mistakes(review): Repair follow-up state, briefs, and expiry escalation
* no-mistakes(review): Serialize follow-up delivery stamps with retirement
* no-mistakes(review): Serialize rechain claims and protect registration terminal states
* no-mistakes(review): Avoid reporting retired delivery loops as open
* no-mistakes(document): Refresh public-loop documentation and verification evidence
* no-mistakes: apply CI fixes
* no-mistakes(review): Preserve delivered follow-up bindings during registration replay
* no-mistakes(review): Harden public follow-up retirement and rechain races
* no-mistakes(review): Fail closed on unresolved secondmate retirement
* no-mistakes(review): Bind secondmate cleanup to its recorded canonical home
* no-mistakes(review): Fix rechain command output and expiry validation
* no-mistakes(review): Validate brief keys and warn on remote promotion
* no-mistakes(document): Document retained public follow-up loops
* no-mistakes(lint): Remove unused bounded-wait loop variable
* feat(bin): merge GitLab merge requests through the guarded PR merge path (#2779)
* feat(bin): merge GitLab merge requests through the guarded PR merge path
bin/fm-pr-lib.sh already parses a GitLab merge request URL for the watcher,
but bin/fm-pr-merge.sh refused every non-github provider, so a merge request
had to be merged by hand and got none of the recording, guards, or audit
trail a pull request gets.
The merge path now dispatches on the parsed provider. A GitHub URL keeps its
exact previous behavior. A GitLab URL is addressed through glab by the project
URL rebuilt from the parsed host and path, so a merge request on any instance
resolves and no host is hardcoded, and no merge-method flag is added because
the project's own merge method is what should apply.
A GitLab merge happens only after one live read of the merge request confirms
it is open, detailed_merge_status is mergeable, has_conflicts is false,
blocking_discussions_resolved is true, and the head pipeline succeeded at the
exact current head. Every failing condition is reported, not just the first.
The verified head is bound to the merge with glab's --sha, so a push landing
between the read and the merge fails the merge instead of landing commits
nothing verified. Recorded metadata is never the authority for any of this: a
rebase moves the head and leaves a recorded value stale, so a recorded head
that disagrees with the live one is reported rather than trusted, and the
recorded value is read before the recording step because that step drops a
GitLab head it cannot resolve.
* no-mistakes(review): reject bundled -R clusters and make tool-absence cases host-independent
* no-mistakes(test): state authorised GitHub narrowing of bundled -R guard
This branch NARROWS GitHub behaviour. The narrowing was authorised
deliberately rather than slipping in by accident, and it applies to both
providers, GitHub and GitLab alike, because a script that guards one provider
and not the other is a trap for the next reader.
What bin/fm-pr-merge.sh now refuses is extra merge arguments containing a
bundled short-option cluster that includes R, for example "-dR other/repo".
The forge CLIs expand such a cluster one character at a time, so it carries
"--repo other/repo", and that later value wins over the repository the URL
named. Before this change, "fm-pr-merge.sh <task> <github-url> -- -dR
other/repo" reached "gh-axi pr merge 12 --repo example/repo --squash -dR
other/repo" and exited 0 with pr= recorded and the merge poll armed. It now
exits 1 with "extra merge arguments must not override the repository", records
nothing, and invokes no forge merge command. Every other GitHub invocation is
byte-identical to the base commit.
Closing that hole honours the existing rule rather than departing from it. The
file header already forbids --repo and -R because the repository must come
only from the URL, so a bundled cluster carrying a repository override was
never legitimate behaviour to preserve: it was that guard being evaded.
Redirecting a merge to a repository the URL does not name is exactly what the
guard exists to prevent.
The refusal is already pinned on both paths by the existing case
test_bundled_repo_override_args_refuse_before_recording in
tests/fm-pr-merge.test.sh. On GitHub ("-dR wrong/repo") and on GitLab ("-yR
https://other.example/g/p") it asserts exit 1, the refusal wording, no pr= in
the task meta, no armed merge poll, and no forge merge command invoked, with a
control case proving a cluster that carries no repository override still
reaches the forge. No duplicate assertion was added. Both assertions were
confirmed to have teeth by narrowing the guard back to a bare -R and watching
each path fail.
This commit carries no file change: the guard and its coverage landed in
614853d, and this message exists so the pull request description states the
narrowing.
* no-mistakes(document): fix README pointer for GitLab watch and merge doc
* no-mistakes: apply CI fixes
* fix(bin): record a lost relay connection instead of an unanswered turn (#2788)
* no-mistakes: apply CI fixes
* fix(bin): drop a private record citation and narrow the review rule
Three corrections to the spoken interface that landed in #2767, plus one
fix carried over from that branch after its pull request had already been
merged.
The confidentiality fix. The module docstring of bin/fm-voice-relay.py
cited a private, gitignored fleet record by exact path and section number.
That widens what this public repository points at, and it cannot resolve
for any reader here, because the path has never been in the repository.
Both traps it pointed at are already described in full in the list
immediately below it, and docs/voice-relay.md carries the same two for
operators with no citation at all, so the pointer is removed and no claim
is weakened by losing it. Two comments that referred to "the survey" as
though it were something a reader could open are reworded the same way.
Neither exposed a path, so that half is comprehensibility rather than
confidentiality.
The review rule. .greptile/rules.md is kept, because its conditions are
right and deleting it would leave the next reviewer to re-litigate a
decision already argued out. What was wrong with it is narrower than its
existence: it read as settled repository policy, when whether VISION.md
itself should be reconciled is an open question belonging to the captain.
One sentence now says so, and says that the conditions listed below it are
what the interpretation depends on. That narrows the claim rather than
widening it.
The carried-over fix. The first commit on this branch is 7f98e797 from
fm/voice-relay-build-v4, taken verbatim rather than rewritten. It closes
the window where a transport failure was recorded and then erased, so a
run could be emitted as answered false with relay_error null. That matters
more than it looks: relay_error is the field that keeps an infrastructure
failure from being averaged into a latency figure, so the failure mode is
a dead connection wearing the costume of a slow reply. It landed fifteen
minutes after #2767 merged and so never reached the default branch.
* no-mistakes(review): name a reason on every unanswered-turn close path
* no-mistakes(review): guard the downlink body and pin frames to their turn
* no-mistakes(review): attribute reply audio to its own turn and tell endings apart
* no-mistakes(review): tell a cut-short reply from an unanswered turn
* no-mistakes(review): discard reply audio arriving after the output closes
* no-mistakes(review): count discarded reply audio on the speaker path too
* no-mistakes(review): keep a reason off a turn already answered in full
* no-mistakes(review): say a reset cut a reply short, not that none arrived
* no-mistakes(review): read one turn's audio count once, and hush a tidy exit
* no-mistakes(document): fix stale session-end relay_error claim in voice-relay guide
* fix(composer): stop a blocked pi pane from proving an empty composer (#2811)
A pi worker parked on an interactive prompt - a permission dialog, a
question menu, a trust dialog - reports agent_status=blocked, because it
is waiting on a human keystroke. Pi draws that menu above its separator
pair, so the composer region between the rules is blank and structure
alone looks like a free composer. _fm_composer_pi_verdict admitted
blocked alongside idle and done, so the shared classifier reported an
affirmatively empty composer for exactly the pane where typing is unsafe.
Every "is it safe to type here?" consumer reads that verdict and proceeds
only on an affirmative empty, so both are told yes on a parked prompt:
the away-mode injection guard in bin/fm-supervise-daemon.sh, and fm-send's
pre-type refusal. The keys then answer the menu instead of composing a
message - the highlighted default is selected, the text is discarded, and
the record attributes a decision to a human who never made it.
blocked now defers to unknown, which every consumer already treats as
fail-closed. idle and done still prove an empty composer, so ordinary
steering is unchanged, and Cursor is unaffected because its always-blocked
panes never reach this pi-only branch.
Regression coverage lands first at both levels: the verdict owner
(a blocked pi defers) and the herdr adapter (a parked pi prompt is not an
empty composer).
* fix(bin): require project clone roots during fleet sync (#2849)
* fix(bin): require a clone root before fleet-sync touches a project
Git repository discovery walks upward, so `git -C projects/<dir>` on a plain
directory nested under projects/ resolves to the enclosing repository - in a
firstmate home, the firstmate checkout itself. fm-fleet-sync.sh guarded its
candidates with `rev-parse --is-inside-work-tree`, which such a directory
passes, so every later git call read, pruned and fast-forwarded firstmate's own
default branch and reported it under the project directory's label. A running
session's AGENTS.md changed underneath it, and the report named a project that
had nothing to do with the change.
Require each candidate to be the root of its own work tree before any other git
command: compare `rev-parse --show-toplevel` against the directory's own
physical path. Both sides are physical, so a symlinked clone still compares
equal. Anything else is skipped by name, naming the repository that would have
been touched, and bootstrap relays that as a FLEET_SYNC l…
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fixes #2691
Intent
Fix a defect in bin/fm-fleet-sync.sh, reported as issue #2691: the project-clone refresh treats every directory under projects/ as a clone. Git repository discovery walks upward, so for a directory that is not itself a repository (for example a worktree container left under projects/, where the actual repository is one level below), every 'git -C
' resolves to the ENCLOSING repository. In a firstmate home that enclosing repository is the firstmate checkout itself, so a routine fleet refresh silently fetched, pruned and fast-forwarded firstmate's own default branch and reported the result under the unrelated project directory's label - an unrequested self-update outside the guarded update path, with a report that named the wrong repository.The goal is the minimal, targeted guard the issue asks for: before any other git command runs against a candidate under projects/, require that the candidate is the root of its OWN work tree, comparing 'git rev-parse --show-toplevel' against the directory's own physical path. Anything else is skipped by name, loudly enough to be noticed, and the skip message names the repository that would otherwise have been touched so an operator can see what discovery resolved to. The existing 'skipped: not a git repo' wording and behavior for a candidate that resolves to no repository at all is deliberately left unchanged, so only the new enclosing-repository case gets new wording.
Deliberate decisions a reviewer reading only the diff would not know:
What Changed
Risk Assessment
✅ Low: Captain, the targeted root guard closes the reported upward discovery path, preserves intended skip behavior, and the corrected regression fixture now genuinely exercises the pre-fix fast-forward risk.
Testing
The focused regression suite passed, and an end-to-end CLI transcript proves the fixed behavior, preserved cases, and historical failure reproduction. The first transcript command was rejected before execution due to its cleanup syntax, then rerun successfully without worktree changes.
Evidence: Issue #2691 end-to-end CLI transcript
Source: Issue #2691 end-to-end CLI transcript
Pipeline
Updates from git push no-mistakes
✅ **intent** - passed
✅ No issues found.
✅ **Rebase** - passed
✅ No issues found.
🔧 **Review** - 1 issue found → auto-fixed (2) ✅
tests/fm-fleet-sync.test.sh:116- The regression fixture does not reproduce the reported fast-forward. Its initial commit contains only AGENTS.md, so creating projects/not-a-clone makes the enclosing checkout dirty. Against the pre-fix script, fetch succeeds but status --porcelain sees that untracked directory and returns STUCK instead of fast-forwarding. Track a firstmate-like .gitignore containing /projects/ in the fixture's initial commit so the enclosing checkout remains clean and the before/after SHA assertion proves the dangerous mutation.🔧 Fix: Confirm clone-root regression fixture remains valid
1 warning still open:
tests/fm-fleet-sync.test.sh:116- The fixture does not reproduce the reported fast-forward. Its initial commit tracks only AGENTS.md, so creating projects/not-a-clone makes the enclosing checkout dirty. Against the pre-fix script, status --porcelain therefore reports STUCK instead of advancing HEAD. Track a .gitignore containing /projects/ in the initial fixture commit so the checkout remains clean and the SHA assertion proves the dangerous mutation.🔧 Fix: Keep enclosing fixture clean during clone-root regression
✅ Re-checked - no issues remain.
✅ **Test** - passed
✅ No issues found.
bash tests/fm-fleet-sync.test.sh(run twice; both completed successfully)Invokedbin/fm-fleet-sync.shin whole-fleet and single-project forms against a nested candidate whose enclosing repository had a pending fast-forward; verified the skip output named the enclosing repository and HEAD remained unchangedInvokedbin/fm-fleet-sync.sh symlinked-clone; verified physical and Git top-level paths matched and the clone fast-forwardedInvokedbin/fm-fleet-sync.sh plain-diroutside any repository; verifiedskipped: not a git reporemained unchangedExecuted base revision8714c9aagainst the same enclosing-repository fixture; reproduced the mislabeled sync and unintended fast-forward✅ **Document** - passed
✅ No issues found.
✅ **Push** - passed
✅ No issues found.