ci: fix invalid YAML in CLAUDE.md pointer check - #2515
Merged
Conversation
AmadeuReal
pushed a commit
to AmadeuReal/firstmate
that referenced
this pull request
Aug 17, 2026
EvanAgee
added a commit
to EvanAgee/firstmate
that referenced
this pull request
Aug 17, 2026
* fix(decisions): close decision holds at answer time via one general keyed-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 * fix(memory): emit a real @AGENTS.md pointer instead of a CLAUDE.md symlink (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(ci): keep CLAUDE.md pointer check valid (kunchenguid#2515) * feat(outage): keep landing work while GitHub is down Two coupled parts so the fleet keeps moving during a GitHub outage. Part A - detection: - bin/fm-github-health.sh: a bounded, mostly-unauthenticated GitHub reachability probe. Silent when reachable; on confirmed unreachability (majority of attempts fail, so one bad request never parks the fleet) it sets state/.github-down with a first-seen timestamp, and clears it on recovery. A transition command owns the report-once-per-change dedup. - bin/fm-watch.sh: calls the probe once per check interval and wakes the captain once on each down/up change, never per poll. Part B - local landing and sync-on-return: - bin/fm-merge-local.sh: generalized to take an explicit lane branch (or read it from the task worktree) and to let a normally-PR-bound task land locally only while GitHub is down. Every existing guard is kept: clean tree, default branch, fast-forward-only, diverged-refusal. A yolo-on outage auto-land also requires proof that a second, independent agent adversarially reviewed the change (the captain's decision), so an auto-land can never happen on one review. Each outage landing is recorded in state/outage-landings/<project>.log. - bin/fm-outage-sync.sh: on return, per ledger entry it fast-forward-pushes local main when clean-ahead, dispatches the deferred schedule-only workflows, and clears the entry. A diverged main escalates rather than force-pushing. Idempotent: a commit already on origin is a no-op. - .agents/skills/outage-local-landing: the procedure firstmate follows on a health transition and before landing during an outage. Colocated tests cover the probe (confirmed-down, recovery, single-transient tolerance, boundedness, transition dedup), the watcher hook, the merge gates (refuse when up, accept during outage, diverged escalation, review gate, local-only back-compat), and sync (push+dispatch, idempotency, diverged refusal, undispatched-deferred note). * no-mistakes(document): docs: align outage-landing docs with the new scripts * no-mistakes(document): fix outage-landing ledger field list in skill doc * chore: re-trigger CI on the fork * chore: trigger CI now that fork workflows are enabled * fix(test): make outage-sync fixtures branch-default-independent The diverged-case fixture cloned the bare origin and pushed 'main', but on a runner whose init.defaultBranch is master the clone checked out master and the push failed with 'src refspec main does not match any'. Force the bare origin's HEAD to main and check out main explicitly in the clone so the fixtures work on any runner default. Reproduced and verified with init.defaultBranch=master. * no-mistakes(document): docs: list outage-landings ledger and github-down flag in AGENTS.md state inventory --------- Co-authored-by: Kun Chen <3233006+kunchenguid@users.noreply.github.com>
joliverMI
pushed a commit
to joliverMI/firstmate
that referenced
this pull request
Aug 17, 2026
joliverMI
added a commit
to joliverMI/firstmate
that referenced
this pull request
Aug 17, 2026
* feat(stow): add open-record persistence to /stow before reset (kunchenguid#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 (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 * fix(memory): emit a real @AGENTS.md pointer instead of a CLAUDE.md symlink (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(ci): keep CLAUDE.md pointer check valid (kunchenguid#2515) * feat(dashboard): add the Admiral's Fleet Dashboard task board Replaces the generated Lavish status page with a purpose-built board: a zero-dependency Python backend (stdlib http.server + sqlite3), a vendored React frontend styled to match Spectra, an agent-facing CLI (bin/fm-dashboard.sh) that is the only way agents touch it, and the fleet-dashboard skill teaching the fleet auditor and other agents how to use it. The board owns its own persistent records rather than mirroring any backlog - its six-status vocabulary and four review tabs don't map onto tasks-axi state, and the fleet auditor needs a separate claim to check against live reality. See docs/dashboard.md for the full architecture, the deploy story, and the drift-risk tradeoff that choice implies. Link posting rejects GitHub/PR links and local-only hosts structurally (standing order 17), not just by agent memory. The page shows a loud, persistent banner when it cannot reach its own API, and the auditor's "never run" state is rendered distinctly from a clean sweep, so an absence of confirmation is never shown as a confirmed-good state. --------- Co-authored-by: Kun Chen <3233006+kunchenguid@users.noreply.github.com> Co-authored-by: joliverMI <joliver@sensibletech.biz>
wonder-media
added a commit
to wonder-media/firstmate
that referenced
this pull request
Aug 18, 2026
* fix: keep the public promise reachable when work is routed to a second 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. * docs(skills): add remote-secondmate recovery hint for false-negative 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 * fix(calm): keep Pi's export confirmation visible (kunchenguid#2461) 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. * feat(stow): add open-record persistence to /stow before reset (kunchenguid#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 (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 * fix(memory): emit a real @AGENTS.md pointer instead of a CLAUDE.md symlink (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(ci): keep CLAUDE.md pointer check valid (kunchenguid#2515) * ci: gate GitHub workflows with pinned actionlint (kunchenguid#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 (kunchenguid#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 (kunchenguid#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: clarify test evidence branch storage (kunchenguid#2549) * docs: correct test evidence storage comment in .no-mistakes.yaml * no-mistakes: apply CI fixes * feat: add worker auto-compaction launch config * no-mistakes(document): docs: add crew-autocompact to AGENTS.md config file inventory --------- Co-authored-by: Kun Chen <3233006+kunchenguid@users.noreply.github.com>
digbycampbell
added a commit
to digbycampbell/firstmate
that referenced
this pull request
Aug 18, 2026
… decision-hold bindings (#8) * fix: keep the public promise reachable when work is routed to a second 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. * docs(skills): add remote-secondmate recovery hint for false-negative 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 * fix(calm): keep Pi's export confirmation visible (kunchenguid#2461) 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. * feat(stow): add open-record persistence to /stow before reset (kunchenguid#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 (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 * fix(memory): emit a real @AGENTS.md pointer instead of a CLAUDE.md symlink (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(ci): keep CLAUDE.md pointer check valid (kunchenguid#2515) * ci: gate GitHub workflows with pinned actionlint (kunchenguid#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 (kunchenguid#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 (kunchenguid#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: clarify test evidence branch storage (kunchenguid#2549) * docs: correct test evidence storage comment in .no-mistakes.yaml * no-mistakes: apply CI fixes * fix(stow): take upstream's description wording verbatim in the merge resolution The conflict resolution had kept our dropped 'e.g.'; the captain's standing direction is to prefer upstream wording where the two genuinely conflict. Only the block-scalar reflow remains ours, so the file keeps one sentence per line as the repo style requires. --------- Co-authored-by: Kun Chen <3233006+kunchenguid@users.noreply.github.com>
BohnBawerick
added a commit
to BohnBawerick/firstmate
that referenced
this pull request
Aug 18, 2026
* fix(bin): prevent false Pi watcher alarms during hand-offs (kunchenguid#2304) * fix(guard): stop the false send-time watcher-down alarm on Pi primaries On a Pi primary the watcher process is not the liveness signal. The Pi extension tears the watcher down on every actionable wake and spawns the replacement itself, so the singleton lock is legitimately unheld between cycles: every one of the 799 cycles in a live primary's ledger ends with lock_after=pid:none, and a live capture caught the guard verdict flipping to no-watcher during one hand-off with the beacon 63s old. bin/fm-guard.sh classified Pi as a persistent-watcher harness, which demands a live identity-matched lock holder at all times, so any guarded command landing in a hand-off painted the full WATCHER DOWN - SUPERVISION IS OFF banner and told firstmate to repair a cycle the extension already owns and is restoring. Add an extension supervision model for pi and pi-signed. A live identity-matched watcher stays the ordinary healthy state; an unheld lock is healthy only while the beacon is fresh within grace AND a live Pi session provably owns continuity - both primary extensions recorded in their state markers at their current on-disk builds by the process named in state/.lock, with that process still alive. Without that proof the banner fires exactly as before, so an unloaded, version-drifted, or exited Pi session is loud immediately and a cycle the extension never restores is loud once the beacon passes grace. The queued-wake warning, the PID-strict turn-end guard, and every other primary's detection are untouched. Fold session-start's duplicate Pi marker predicate into the shared library so the ownership contract has one owner. * no-mistakes(review): Restrict Pi hand-off tolerance to unheld watcher locks * no-mistakes(document): Document Pi watcher hand-off supervision * feat: support Cursor Agent CLI as a primary harness (kunchenguid#2305) * feat(cursor): add Cursor Agent CLI primary hooks, park supervision, and session start Register a tracked project-scope .cursor/hooks.json for Cursor's stop, sessionStart, preCompact, and preToolUse steps. bin/fm-turnend-guard-cursor.sh owns Cursor's turn boundary as a park: it foregrounds the watcher arm, holds the boundary open until an actionable close, and returns that wake as one follow-up. Exit 2 is a silent no-op on Cursor's stop step, so the adapter never uses it. The follow-up loop is bounded twice, by Cursor's own loop_limit and by the payload's loop_count. bin/fm-sessionstart-cursor.sh delivers the digest as additional_context at sessionStart, and stages it for the next turn boundary at preCompact, which cannot inject context. Cursor also loads the tracked Claude settings, so bin/fm-hook-host-lib.sh lets each tracked Claude-shaped entrypoint stand down on a Cursor-delivered payload rather than running every covered event twice. bin/fm-tmux-lib.sh reclassifies a Cursor pane's composer cursorlessly, because Cursor parks its terminal cursor outside the composer, which restores a genuine composer-empty proof and unblocks away-mode escalation delivery. * feat(cursor): make Cursor Agent CLI a verified primary harness Resolve Cursor in the session-lock ancestry through bin/fm-cursor-lib.sh, which a Cursor primary needs before it can hold its own home lock, and classify its stop-hook park under the autoarm supervision model so the mid-turn pull guard stops reporting a healthy between-turns watcher as down. Read a Cursor pane's composer cursorlessly on tmux, gated on Cursor's own structural process identity, which restores a genuine composer-empty proof and lets away-mode escalations reach a Cursor primary with no daemon change. Lift the secondmate refusals in bin/fm-spawn.sh and bin/fm-control-lib.sh now that the supervision protocol exists and is recorded. Cover the whole surface with a portable regression over real processes, an opt-in live guard against the installed cursor-agent, and dated per-harness evidence. * docs(cursor): record Cursor as a verified primary across the owning surfaces Update the turn-end guard, session-start, arm-seatbelt, cd-guard, watcher continuity, architecture, configuration, README, and harness-adapters owners, and add dated live evidence to the supervision and runtime-backend verification records. Correct the recorded Cursor tmux composer verdict: the cursor-anchored read is still blind, but the composite reader is no longer unknown. Lift the remaining remote-secondmate refusal missed in the previous commit, and add the new libs to the existing fixtures that copy a fixed dependency list. * refactor(cursor): name the park's stand-down condition for both its causes Also record that Cursor's preCompact firing itself is not yet live-verified, while the static evidence that it cannot inject context, and the staging path that follows from it, both are. * test: give the pretool fixtures their new dependency and one lint owner The cd-guard fixture copies a fixed dependency list and now needs the shared hook-host predicate. Both pretool suites also asserted cleanliness with a bare shellcheck call, a second and weaker copy of the lint definition that bin/fm-lint.sh owns: it omits --external-sources, so it failed the moment these checkers sourced a shared library. They now delegate to that owner. * test: assert the cursor secondmate contract instead of its removed refusal A cursor secondmate now launches, so the suite asserts what its park actually needs: --trust so the home's project hooks load at all, its own home pinned as the workspace, and the autoarm supervision model inherited across the launch. * no-mistakes(review): Serialize Cursor wakes and bind staged context * no-mistakes(review): Serialize Cursor context and nag state commits * no-mistakes(review): Enforce Cursor ceiling before staged context delivery * no-mistakes(review): Serialize Cursor claims and staged context * no-mistakes(review): Serialize Cursor ownership and state commits * no-mistakes(review): Protect Cursor context across session takeover * no-mistakes(review): Preserve Cursor context across session takeover * no-mistakes(review): Enforce owner-keyed Cursor staged context * no-mistakes(review): Atomically claim Cursor follow-ups and staged context * no-mistakes(review): Defer Cursor preCompact staging and simplify supersession * no-mistakes(review): Serialize Cursor park commits and defer preCompact * no-mistakes(review): Stop Cursor parks after session takeover * no-mistakes(test): Route Cursor preCompact context through stop follow-up * no-mistakes(document): Update Cursor primary documentation * revert(cursor): cut preCompact staging from this change Carrying a compaction digest across two concurrently running stop hooks kept producing races that could deliver it twice or strand it indefinitely, and closing them kept enlarging a critical section inside a hook Cursor awaits at the turn boundary. Native preCompact firing was never observed either, so the surface has no empirical basis yet. Remove the adapter, its registration, its staged path in the park, and its tests, and record the surface as deferred and uncovered alongside the Codex interactive TUI. A regression now asserts preCompact stays unregistered so it cannot return without its own design and evidence. This change ships the proven core only: the turn-end follow-up park, the run-tier session start, and away-mode delivery. * no-mistakes(review): Correct Cursor park supersession documentation * no-mistakes(document): Clarify Cursor run-tier verification ownership * no-mistakes: apply CI fixes * no-mistakes: apply CI fixes --------- Co-authored-by: kunchenguid <kun-1@kunchenguid.com> * feat(bin): add decline and repair paths for decision holds (kunchenguid#2330) * feat(bin): add unrouted close paths to the captain decision gate A captain who declines a held decision leaves no follow-up work to route, so `resolve` could not express that answer: it requires at least one `--routed-to` task. The only way to close such a hold was a direct `tasks-axi done`, which never writes the durable resolution record the completion gate reads, so the originating investigation could no longer pass `verify` and its cleanup stayed blocked. Add two close paths that route no work: - `decline` closes an actively held hold with a recorded captain decision and no routed task. It refuses while any task is still blocked by the hold, because releasing routed work without recording it is `resolve`'s job. - `repair` records the missing resolution block on a hold that was already closed outside this script. It never reopens a hold and never clears a dependency edge, and it refuses a hold that is still actively held. Both require a non-empty captain decision file and share `resolve`'s digest-based retry identity, so an exact retry is idempotent while a changed decision is rejected. The recorded body now also names which path closed the hold, and each routed entry regains its own line. The gate itself is unchanged: an unanswered decision still fails completion and blocks teardown, and neither new path can close a hold without the captain's recorded word. * fix(bin): require captain-hold provenance before repairing a decision `repair` checked only that the backlog item was kind captain and Done, so an ordinary captain-kind task that was never held for the captain could be closed, repaired, and then pass the completion gate. tasks-axi keeps `hold_kind` through a close, so it is the surviving proof that an identity really was a captain hold. Require it before writing the resolution record, and cover the case in the gate regression. * no-mistakes(document): Correct decision-hold lifecycle documentation * fix(bin): surface buried wake status lines once (kunchenguid#2331) * fix(bin): surface buried status notes on wake drain A note: answer immediately followed by a routine note was dropped because annotations kept only the newest line and note: never enters OPEN DECISIONS. Present every unread note and pending-reply resolution since the last drain cursor, and annotate every unread line on a queued signal. * no-mistakes(review): Fix unread status cursor races and overflow * no-mistakes(review): Preserve cursors when status span reads fail * no-mistakes(review): Make status presentation transactional under I/O failures * no-mistakes(review): Simplify unread status cursor and presentation locking * no-mistakes(review): Align cursor failure regressions with transactional presentation * no-mistakes(review): Retire stale presentation cursors during task teardown * no-mistakes(review): Preserve routine status until signal annotation * no-mistakes(review): Correct unread status cap documentation * no-mistakes(document): Document unread wake status presentation * no-mistakes(lint): Fix wake surfacing ShellCheck warnings * no-mistakes: apply CI fixes * feat: add max Calm presentation level (kunchenguid#2334) * feat(calm): add a max presentation level that hides mid-turn working notes Calm's home-local preference becomes a three-state level instead of a boolean: "off" is stock Pi, "on" is today's Calm, and "max" is Calm plus hiding the assistant text of messages the model did not end its response with. `/calm max` selects it from any state, a plain `/calm` steps max back to ordinary Calm and otherwise keeps the existing on/off cycle, and any other argument keeps that cycle too. `config/calm` now persists "max" as its own literal value, so a session start, resume, fork, or reload restores the stored level rather than treating it as unrecognized and dropping to off. The hide rule keys on Pi's intrinsic per-message stopReason: "toolUse", or "length" with tool calls present. Streaming ("pending") text is never filtered, because suppressing it would also stop a genuine reply from streaming. The existing assistant layout adapter filters the blocks out of the same shallow presentation copy it already uses for collapsed thinking, so the message, model context, session storage, /export, and delivery are untouched and a hidden mid-turn row collapses to zero height. The new "assistant-working-note" class keeps that choice in the visibility policy owner, where ordinary Calm keeps it visible. * no-mistakes(document): Clarify Calm max persistence and taxonomy * feat(calm): hide mid-turn working notes by default (kunchenguid#2339) * feat(calm): make hiding mid-turn working notes the ordinary Calm state Calm collapses back to the two-state on/off toggle it was before the max presentation level, with max's hide rule promoted into ordinary Calm. Calm on now hides mid-turn assistant working notes in addition to what it already hid, and the /calm command parses no argument again. The hide rule itself is unchanged: assistant text is removed from the shallow presentation copy when the message's own stopReason is "toolUse", or "length" with tool calls present. Streaming ("pending") text is never filtered, so a genuine reply still streams. The message, model context, session storage, /export, and delivery remain untouched. config/calm persists only "on" and "off" again, but the reader still maps a persisted "max" to on so a home upgraded from the removed level keeps Calm on instead of dropping to off. The mid-turn hide is now default behavior rather than an opt-in level, so docs/calm.md documents it for users, docs/configuration.md records the two written values plus the legacy max mapping, and the feasibility taxonomy drops its level-scoped wording. * no-mistakes(document): Document ordinary Calm working-note hiding * chore: store no-mistakes test evidence in the repo (kunchenguid#2355) * chore: ignore scratchpad/ at the repo root (kunchenguid#2359) * fix(ci): fail hung Herdr behavior runs in 20 minutes (kunchenguid#2413) A wedged family-run step was occupying the runner until the 75-minute job cap; bound that step so cleanup and timing artifacts still upload. * fix: keep the public promise reachable when work is routed to a second 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. * docs(skills): add remote-secondmate recovery hint for false-negative 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 * fix(calm): keep Pi's export confirmation visible (kunchenguid#2461) 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. * feat(stow): add open-record persistence to /stow before reset (kunchenguid#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 (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 * fix(memory): emit a real @AGENTS.md pointer instead of a CLAUDE.md symlink (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(ci): keep CLAUDE.md pointer check valid (kunchenguid#2515) * ci: gate GitHub workflows with pinned actionlint (kunchenguid#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 (kunchenguid#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 (kunchenguid#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: clarify test evidence branch storage (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 * fix(bin): distinguish unreadable away-mode panes from gone ones Away-mode housekeeping treated every failed capture as a gone pane and dropped the marker with no escalation. A redraw, timeout, or backend hiccup then silently stopped watching a worker that was still there, which is the failure this path exists to prevent. Both the stale-wedge and pause-resurface sites now share stale_window_recheck: retry the capture twice (0.4s apart) before verdict, then ask fm_backend_agent_state. Only an authoritatively missing endpoint is gone. A present dead shell is ordinary idle. Every other state, including an unreadable or unverified probe, escalates and keeps the marker on the same cadence because the watcher cannot recapture an unreadable pane. target_exists is not used as a gone proof: tmux can fall back to the active window, and Orca's check is itself a capture. Tests cover gone, unreadable-present (alive/unreadable/unverified), retry-then-ordinary, and dead-is-not-gone at both call sites. --------- Co-authored-by: Kun Chen <3233006+kunchenguid@users.noreply.github.com> Co-authored-by: kunchenguid <kun-1@kunchenguid.com>
kaan-sirin
pushed a commit
to kaan-sirin/firstmate
that referenced
this pull request
Aug 18, 2026
joliverMI
added a commit
to joliverMI/firstmate
that referenced
this pull request
Aug 19, 2026
* feat(stow): add open-record persistence to /stow before reset (kunchenguid#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 (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 * fix(memory): emit a real @AGENTS.md pointer instead of a CLAUDE.md symlink (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(ci): keep CLAUDE.md pointer check valid (kunchenguid#2515) * feat(dashboard): add the Admiral's Fleet Dashboard task board Replaces the generated Lavish status page with a purpose-built board: a zero-dependency Python backend (stdlib http.server + sqlite3), a vendored React frontend styled to match Spectra, an agent-facing CLI (bin/fm-dashboard.sh) that is the only way agents touch it, and the fleet-dashboard skill teaching the fleet auditor and other agents how to use it. The board owns its own persistent records rather than mirroring any backlog - its six-status vocabulary and four review tabs don't map onto tasks-axi state, and the fleet auditor needs a separate claim to check against live reality. See docs/dashboard.md for the full architecture, the deploy story, and the drift-risk tradeoff that choice implies. Link posting rejects GitHub/PR links and local-only hosts structurally (standing order 17), not just by agent memory. The page shows a loud, persistent banner when it cannot reach its own API, and the auditor's "never run" state is rendered distinctly from a clean sweep, so an absence of confirmation is never shown as a confirmed-good state. --------- Co-authored-by: Kun Chen <3233006+kunchenguid@users.noreply.github.com> Co-authored-by: joliverMI <joliver@sensibletech.biz>
quinnbot-ai
added a commit
to quinnbot-ai/firstmate
that referenced
this pull request
Aug 19, 2026
…sidebar (#135) * fix(decisions): close decision holds at answer time via one general keyed-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 * fix(memory): emit a real @AGENTS.md pointer instead of a CLAUDE.md symlink (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(ci): keep CLAUDE.md pointer check valid (kunchenguid#2515) * ci: gate GitHub workflows with pinned actionlint (kunchenguid#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 (kunchenguid#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 (kunchenguid#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: clarify test evidence branch storage (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 * 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. * feat(herdr): make crewmates, scouts, and second mates legible in the sidebar Herdr's Spaces and Agents sidebar lists are drawn from configurable row templates fed by display-only pane and workspace metadata. Firstmate never reported any, so every spawned entry rendered identically and only the fm-<id> tab label distinguished one worker from another. Report, once per spawn, the facts only Firstmate knows: whether an entry is a persistent second mate, an ordinary crewmate, or a scout; the domain or project it belongs to; its task; and its owning home. The reported display name improves the sidebar under a completely unconfigured Herdr, while the fm_role, fm_glyph, fm_scope, fm_task, and fm_home tokens let a captain compose their own rows and colors in their own Herdr config, which is where presentation taste belongs. The surface is display-only and carries no authority. Reporting never renames a workspace or tab and never touches a value that placement, endpoint metadata, the presentation journal, husk replacement, list-live discovery, bare-selector resolution, or cleanup resolves a worker by; the task tab stays exactly fm-<id>. Every report is best-effort, and the display name and the tokens are reported separately so an older release that cannot store tokens still shows the readable name. Reporting happens at spawn time only, so no running worker is retitled and an existing fleet converges as its tasks turn over. * doc: point architecture at the Herdr sidebar legibility boundary * no-mistakes(review): derive herdr Space role from journal, stabilize home scope * no-mistakes(review): report Space role from spawn state, skip on relaunch * doc(herdr): state the true reason a relaunch re-badges its pane The relaunch arm adopts the recorded endpoint and creates no pane, so the previous rationale - that the replacement pane carries no metadata yet - was wrong. The adopted pane keeps its reported tokens; the re-report is a refresh for facts that can change while the endpoint stays the same. The concrete case is promotion: fm-promote.sh flips a task from scout to ship in place on the same endpoint without going through spawn, so the badge reads scout until a later relaunch re-reads that kind and re-badges it as crew. Promotion alone does not update the sidebar, and the refresh is not a promise that a badge is continuously current. Wording only; no behavior change. * no-mistakes(document): doc(herdr): fm_role covers projected one-task Spaces --------- Co-authored-by: Kun Chen <3233006+kunchenguid@users.noreply.github.com> Co-authored-by: QuinnBot <quinnbot@proton.me>
prajwal-395
added a commit
to prajwal-395/firstmate
that referenced
this pull request
Aug 19, 2026
…-ahead behaviour (#21) * fix(ci): fail hung Herdr behavior runs in 20 minutes (kunchenguid#2413) A wedged family-run step was occupying the runner until the 75-minute job cap; bound that step so cleanup and timing artifacts still upload. * fix: keep the public promise reachable when work is routed to a second 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. * docs(skills): add remote-secondmate recovery hint for false-negative 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 * fix(calm): keep Pi's export confirmation visible (kunchenguid#2461) 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. * feat(stow): add open-record persistence to /stow before reset (kunchenguid#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 (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 * fix(memory): emit a real @AGENTS.md pointer instead of a CLAUDE.md symlink (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(ci): keep CLAUDE.md pointer check valid (kunchenguid#2515) * ci: gate GitHub workflows with pinned actionlint (kunchenguid#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 (kunchenguid#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 (kunchenguid#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: clarify test evidence branch storage (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 * 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 (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: preserve pending replies and defer remote reposts (kunchenguid#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 (kunchenguid#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 * fix(ci): rebalance portable serial shard weight hints from measured CI timings The old weight hints (from 2026-08-02, 69 scripts) left 52 tests at the 20000ms default. Many live-e2e tests actually run in <100ms while several new tests run over 100s, so the LPT algorithm's apparently balanced assignment was wildly skewed in practice: shard 1 took ~14.1 min vs 7.9-9.8 for the others, hitting the 15-min job timeout. Refresh all hints from CI run 32302063973 (2026-08-19, 119 scripts, ~39 min total). Three unmeasured new tests use 5000ms conservative estimates. The rebalanced shards each estimate ~589s (~9.8 min) with a 2ms imbalance. Also bump the CI timeout from 15 to 20 minutes (~2x margin on the ~10 min balanced target), and update docs/fm-test-portable-shards.md to match. --------- Co-authored-by: Kun Chen <3233006+kunchenguid@users.noreply.github.com>
digbycampbell
added a commit
to digbycampbell/firstmate
that referenced
this pull request
Aug 21, 2026
* fix: keep the public promise reachable when work is routed to a second 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. * docs(skills): add remote-secondmate recovery hint for false-negative 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 * fix(calm): keep Pi's export confirmation visible (kunchenguid#2461) 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. * feat(stow): add open-record persistence to /stow before reset (kunchenguid#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 (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 * fix(memory): emit a real @AGENTS.md pointer instead of a CLAUDE.md symlink (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(ci): keep CLAUDE.md pointer check valid (kunchenguid#2515) * ci: gate GitHub workflows with pinned actionlint (kunchenguid#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 (kunchenguid#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 (kunchenguid#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: clarify test evidence branch storage (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 * 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 (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: preserve pending replies and defer remote reposts (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 (kunchenguid#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 --------- Co-authored-by: Kun Chen <3233006+kunchenguid@users.noreply.github.com>
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
1 participant
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
Fix firstmate CI: the CLAUDE.md-pointer check added in #2512 currently embeds a column-0 heredoc body inside a run: | YAML block scalar in .github/workflows/ci.yml, making the workflow invalid and causing recent CI runs, including main, to fail or parse as zero jobs. Reproduce the malformed YAML and recent main CI failures, then rework only this check so the workflow is valid while it still rejects a CLAUDE.md symlink and any wrong or non-canonical pointer, and still asserts the exact canonical CLAUDE.md bytes: followed by @AGENTS.md. Keep the adjacent .claude/skills symlink assertion working and do not change unrelated CI behavior. Validate and ship the fix through the no-mistakes pipeline, and require the PR CI run to go green as regression proof; do not merge the PR because the captain owns the merge.
What Changed
.github/workflows/ci.ymlso the canonical bytes are built withmktemp+printfand compared viacmp, replacing the column-0 heredoc body that broke out of therun: |block scalar and made the workflow parse as invalid.CLAUDE.mdsymlink, asserts the exact canonical pointer bytes (<!-- Points Claude at AGENTS.md via import; edit AGENTS.md, not this file. -->followed by@AGENTS.md), and keeps the adjacent.claude/skillssymlink assertion intact.Risk Assessment
✅ Low: A minimal, well-bounded CI fix that makes the workflow valid YAML (verified: base fails to parse, target parses with all 9 jobs) while preserving the symlink rejection, exact canonical-bytes assertion (verified byte-for-byte against the real CLAUDE.md), and the .claude/skills symlink check, with no unrelated behavior changed.
Testing
Reproduced the reported bug by parsing the base ci.yml with a real YAML parser (fails at the column-0 heredoc body inside the run:| block scalar, yielding zero parseable jobs), confirmed the target ci.yml parses cleanly into all 9 jobs including invariants, then extracted the actual fixed check step from the parsed workflow and executed it against symlink / wrong-bytes / wrong-pointer / broken-skills fixtures plus the real repo files - every case behaves as intended, the canonical CLAUDE.md bytes (100644, exact) and .claude/skills symlink (120000) assertions hold, and the worktree is clean; the PR-CI-green regression proof named in the intent is owned by the remote pipeline outside this test phase.
Evidence: CI check test evidence
Source: CI check test evidence
Evidence: YAML parse: base fails, target 9 jobs
Evidence: Extracted check run against fixtures
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.
ruby -ryamlparse of base ci.yml (4913723) -> Psych::SyntaxError at line 381 col 1 (malformed)ruby -ryamlparse of target ci.yml (b62f5f9) -> OK, 9 jobs incl invariantsExtracted real invariants step body from parsed YAML, ran under bash against 5 fixtures: canonical_ok pass; claudemd_symlink/wrong_bytes/wrong_pointer/skills_broken fail with correct ::error:: messagesRan extracted check against real worktree -> exit 0git ls-files -s CLAUDE.md .claude/skillsandxxd CLAUDE.mdconfirm 100644 regular file, 120000 symlink, exact canonical bytes✅ **Document** - passed
✅ No issues found.
✅ **Lint** - passed
✅ No issues found.
✅ **Push** - passed
✅ No issues found.