feat: merge upstream through 52d20f1 and stabilize serial test lane - #16
Merged
Conversation
…d mate (kunchenguid#2457) The lightweight Relay follow-up link lives in the answering home's own state/<task-id>.meta, so it can only bind work that home owns. When a Relay-linked request is routed to a second mate, the task record lives in the second mate's home, fm-x-link.sh failed with a bare "no such task ...meta", and nothing else picked the promise up: only the soft acknowledgement was ever posted. The typed promised-final path already supports --work-home secondmate:<id>; the playbook simply never chose it. - fmx-respond now states the routing rule crisply: a task in this home takes the lightweight link, and second-mate-routed work takes a promised-final commitment bound to that home, registered up front with the brief command carried into the routed worker's instructions. - fm-x-link.sh refuses a task with no local record by naming the registered second mate whose home actually holds it and printing the promised-final registration command, with the exact --work-home when the match is unambiguous. A home with no registered second mates keeps the plain error. - fm-backlog-handoff.sh reports, after a successful move, any moved key that still owes a public reply bound to main/<key>, since that binding no longer names the home owning the work. The move itself is never blocked. Docs and the secondmate handoff prose follow the same rule. Tests cover the refusal, its scoping, the unchanged local-link path, and both handoff outcomes at the script boundary.
…verdicts (kunchenguid#2456) * fix(skills): hint that remote secondmate liveness verdicts false-negative fm-crew-state and fm-send routinely misreport a live remote secondmate as dead; confirm against the pane before relaunching, and relaunch only through fm-spawn.sh, never raw herdr pane surgery. * no-mistakes: apply CI fixes
Pi 0.83.0 added a status line to every tool-expansion change, and Pi updates the previous status line in place when two status messages arrive back to back. Calm's post-export redraw cycled tool expansion on the macrotask right after Pi printed "Session exported to: <path>", so both expansion status lines coalesced over that confirmation and the captain was left with no record of where their export landed. Calm now repaints only the tool rows it presents, by invalidating each row through the render context Pi hands its render slots, and requests the surrounding redraw through setStatus. Neither appends to the transcript. The repaint is still needed because Pi can re-render a row asynchronously - the built-in edit row invalidates itself once its diff is ready - and that re-render can land inside the window where /export forces stock rendering. The real-terminal /export case now asserts the confirmation is still on screen after the redraw has settled, and that the redraw restored every Calm-hidden row, instead of only racing the moment the confirmation first appeared.
…nguid#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.
…eyed-answer path (kunchenguid#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
…mlink (kunchenguid#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(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
…d#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
…uid#2548) .no-mistakes.yaml has set test.evidence.store_in_repo: true since kunchenguid#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: correct test evidence storage comment in .no-mistakes.yaml * no-mistakes: apply CI fixes
…nchenguid#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.
…chenguid#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
* 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 * 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
Refine language for clarity and consistency in instructions.
…#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 kunchenguid#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
Refactor the guidelines for Firstmate's role and delegation process, emphasizing the importance of crewmates and asynchronous work.
Clarified guidelines for handing off work to crewmates and managing secrets.
…tions deterministic (kunchenguid#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(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
…d#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
Added guidelines for decision communication to the captain.
Clarify communication protocols with crewmates regarding task delegation and reporting.
* 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(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
…enguid#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
Signature-only PRs can hide skipped review, test, or document steps. Fail unless no-mistakes >= 1.46.0 attests those three steps completed.
…#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
…id#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): 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
…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
…lared 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
…guid#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
…lled 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: 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
Takes the 10 genuinely-missing upstream commits through kunchenguid#2764: the captain-hold rework (kunchenguid#2707/kunchenguid#2728/kunchenguid#2744/kunchenguid#2748), watcher robustness (kunchenguid#2524/kunchenguid#2733), ask-user/yolo decouple (kunchenguid#2764), tool-update watch (kunchenguid#2684), and CI/lint (kunchenguid#2710/kunchenguid#2758). Stops at 52d20f1 per the divergence assessment: voice (fbe37e9) is deliberately skipped, and Relay follow-up preservation (dc0172c) cannot be merged without it since fbe37e9 is its ancestor. Resolution stance: fork deviations preserved throughout - the slim AGENTS.md (upstream hunks hand-ported, including the 'gh-axi for all GitHub operations' wording), the jq argv-limit staged-file fix in fm-fleet-snapshot.sh/fm-bearings-snapshot.sh (upstream's kunchenguid#2728 hold-until/captain_actionable hunks threaded onto it), worktree-claim and git-identity hooks, the brief's verification and isolation clauses, and the fork's PR-#15 polling fixes in fm-pi-watch-extension.test.sh. decision-hold-lifecycle ripples hand-ported to captain-hold-lifecycle.
The serial lane fails intermittently on CI with a different shard each run: the fixtures race their deadlines under load. Following the PR #15 pattern, each fix polls the condition actually being waited for with a ceiling calibrated to the fixture's real cost; no assertion weakened, no retries, no skips. - fm-remote-job: the worker's execution deadline used SECONDS whole- second arithmetic that could fire up to ~1s early (a nominal 3s window could deliver ~1-2s real time); measure against EPOCHREALTIME instead, record the claim deadline as the first whole second after intended expiry, and give the readiness probe a 60s ceiling for loaded starts. Fixture: crash-recovery mutation delay outlasts legitimate recovery latency; the symlinked-argv case stages with a queue window that outlasts a loaded fresh-worker startup. - fm-watch-triage: watcher-written .stale-since marker waits get the file's documented 100-tick budget (3s cannot cover a full fm-watch.sh boot plus one poll under load). - fm-secondmate-harness: the first-config-push marker wait polls the same condition with a 60s ceiling (the push's real work costs ~6-8s unloaded, more under load; old ceiling was 2s). - fm-tool-update-check: the sweep-budget case uses a budget the 30s probe stall still fully consumes (1s could be spent before the probe started, yielding a different report); the watcher checkpoint ceiling rises past FM_CHECK_TIMEOUT for loaded watcher startup. Each fix proven: failing under induced load before, passing under the same load after (3/3) and unloaded.
digbycampbell
changed the title
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
4 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.
Intent
Bring the fork back into true ancestry with upstream by true-merging upstream through 52d20f1 as a merge commit (preserving every fork deviation, deliberately skipping the voice and Relay tip commits), then fix the load-sensitive flaky serial test lane by waiting on real conditions without loosening any guard
What Changed
52d20f1as a real merge commit, restoring fork ancestry while preserving every fork-specific deviation and deliberately excluding the upstream voice and Relay tip commits.bin/fm-captain-hold.sh,.agents/skills/captain-hold-lifecycle/SKILL.md,docs/captain-hold-lifecycle.md, andtests/fm-captain-hold-lifecycle.test.sh, replacing/superseding the old decision-hold implementation (bin/fm-decision-hold.shheavily trimmed,docs/decision-hold-lifecycle.mdand its legacy test removed).bin/fm-tool-update-check.sh+tests/fm-tool-update-check.test.sh) and updates a broad set of supporting scripts, docs, skills, CI workflows, and tests across the merged tree (fm-watch.sh,fm-wake-lib.sh,fm-classify-lib.sh,fm-supervise-daemon.sh,fm-send.sh,fm-remote-job-worker.sh, etc.).tests/fm-watch-triage.test.sh,tests/fm-daemon.test.sh, and related fixtures).Risk Assessment
✅ Low: The merge commit brings in already-reviewed upstream commits with no conflict markers and verified fork-deviation preservation (argv-limit fix, gh-axi wording, PR#15 polling fixes); the follow-up test-fix commit correctly replaces early-firing SECONDS-based deadlines with EPOCHREALTIME-based ones (with a sound whole-second fallback) and widens polling ceilings without weakening any assertion.
Testing
Confirmed the merge commit gives true upstream ancestry through 52d20f1 while the voice/Relay tip commits remain unreachable, and confirmed all four flaky-lane fixture files the fix touched pass cleanly, exercising the exact modified wait/deadline assertions; no regressions or weakened guards found.
Pipeline
Updates from git push no-mistakes
✅ **intent** - passed
✅ No issues found.
✅ **Rebase** - passed
✅ No issues found.
✅ **Review** - passed
✅ No issues found.
✅ **Test** - passed
✅ No issues found.
git merge-base --is-ancestor 52d20f1 HEAD (confirms true ancestry)git merge-base --is-ancestor fbe37e9 HEAD / dc0172c HEAD against full non-shallow history (confirms deliberate exclusion of voice and Relay tip commits)bash tests/fm-remote-job.test.sh (23/23 ok, includes the EPOCHREALTIME deadline fix and 60s/300-iteration readiness-probe ceiling)bash tests/fm-watch-triage.test.sh (all ok, includes the three wait_numeric_file(...,100) stale-since marker cases)bash tests/fm-tool-update-check.test.sh (20/20 ok, includes the 5s sweep-budget case and 60s watcher-checkpoint ceiling case)bash tests/fm-secondmate-harness.test.sh (all ok, includes the first-config-push marker-wait 3000-iteration ceiling case)✅ **Document** - passed
✅ No issues found.
🔧 **Lint** - 1 issue found → auto-fixed ✅
🔧 Fix: No changes needed; lint passes with actionlint now on PATH
✅ Re-checked - no issues remain.
✅ **Push** - passed
✅ No issues found.