docs: no-mistakes(document): Clarify project path documentation

[verbagem]

Intent

Run a GNHF Companion-mode Capacity Night against Firstmate itself, with the host only orchestrating and reviewing GNHF output. Fix exactly two proven Firstmate control-plane defects: registered external absolute-path projects such as pai-agent must resolve their declared delivery posture without basename guessing or free-form prose parsing, and unchanged non-actionable paused/parked/terminal workers must not produce repetitive captain-facing stale interruptions while real actionable state changes, credentials, decisions, failed checks, PR-ready outcomes, X-mode obligations, dead or missing active workers, and genuine wedges still wake. The implemented branch uses structured data/projects.md path=/absolute/project annotations plus canonical in-home projects/ path matching, preserves unknown-path no-mistakes/off default diagnostics, refuses ambiguous or malformed structured path identities, and updates spawn/fleet-sync callers so brief mode, task metadata, and guarded landing posture agree. The watcher changes coalesce due declared-pause rechecks into one interruption per scan and absorb already-surfaced parked/terminal stale panes while preserving active-run and new-actionable wakes. A detached origin/main comparison worktree at /Users/temp/.treehouse/firstmate-7bab20/2/firstmate-origin-main-baseline-2864 proved the six broad local validation failures reproduce equivalently under the same environment; the receipt and full logs are in .no-mistakes/baseline-receipts/firstmate-capacity-night-2864/. Let the pipeline judge those baseline-aware failures rather than treating them as branch regressions. Do not merge.

What Changed

1fb6685 no-mistakes(document): Clarify project path documentation
536a858 no-mistakes(review): Escalate AFK paused validation outcomes
c32fd09 no-mistakes(review): Surface AFK paused validation outcomes
0a62443 no-mistakes(review): Surface paused validation outcomes once
9b320c7 no-mistakes(document): Update capacity-night docs
50ca7ab no-mistakes(review): Track same-hash terminal run wedges
eb8dae6 no-mistakes(review): Surface same-hash run outcomes
c7dac1d no-mistakes(review): Version run outcome stale markers
e8f8bcb no-mistakes(review): Fix watcher and project path regressions
bbe1891 no-mistakes(review): Fix watcher stale dedupe and path normalization
75637e1 gnhf 1: Captain, Defect 1 is corrected narrowly: path lookups now ignore registry description prose/backticks and resolve external projects only through structured path=/absolute/project annotations or canonical in-home projects/<name> paths.
bb32456 gnhf 3: Captain, this iteration fixed the remaining parked/terminal stale-noise boundary and validated it with focused watcher, continuity, daemon, lint, and whitespace checks.
2c0d125 gnhf 2: Captain, this iteration fixed the remaining live declared-pause stale path so idle paused workers stay on the bounded pause cadence instead of producing bare repeated stale notifications.
c077dd0 gnhf 1: Captain, this iteration root-caused the duplicate declared-pause noise to per-window paused recheck wake exits, added a regression, and fixed the paused-stale path to batch due rechecks from one scan into one watcher interruption.
462a5e5 gnhf 1: Captain, this iteration fixed Defect 1 by making registered project delivery posture resolve by canonical project path instead of basename guessing.

Risk Assessment

✅ Low: The changes are narrowly scoped to path-based project posture resolution and watcher/away-mode stale dedupe behavior, with the latest AFK validation-outcome path now emitting a daemon-distinguishable wake reason while preserving ordinary paused stale self-handling.

Testing

Verified and attached the existing origin/main comparison receipt instead of rerunning the broad baseline suite, ran the targeted task-delivery, fleet-sync, crew-state, daemon, and watcher-triage suites successfully, captured manual end-to-end CLI evidence for the external-path and stale-wake behavior, and confirmed the worktree remained clean.

Evidence: Manual end-to-end CLI evidence

External path lookup resolved pai-agent, free-form prose path defaulted safely, fm-spawn.sh reported the standing posture for pai-agent, paused stale rechecks batched into one wake, and already-surfaced parked/terminal panes stayed quiet until a new decision status was appended.

manual evidence dir: /var/folders/85/0xf5ctz126717j1k2wfdc_4w0000gn/T/no-mistakes-evidence/01KZDY0N5G1RCWNRNX87K8225N/manual-e2e-corrected-20260807054639

## project-mode and spawn path identity
$ FM_HOME=<fixture> bin/fm-project-mode.sh --raw --with-name --path <external pai-agent>
pai-agent no-mistakes off
$ FM_HOME=<fixture> bin/fm-project-mode.sh --with-name --path <canonical projects/canon>
canon direct-PR off
$ FM_HOME=<fixture> bin/fm-project-mode.sh --path <free-form prose-only path>
warn: no project registered for path "/var/folders/85/0xf5ctz126717j1k2wfdc_4w0000gn/T/no-mistakes-evidence/01KZDY0N5G1RCWNRNX87K8225N/manual-e2e-corrected-20260807054639/project-mode/external/unknown/agent"; defaulting agent to no-mistakes off
no-mistakes off
$ fm-spawn external pai-agent with explicit local-only task mode
notice: delivery-extpath-e1 ships mode=local-only while the standing posture for pai-agent is no-mistakes - less rigor than the captain's standing posture; proceed only on a current explicit captain instruction or an intake judgment you can state
spawn_exit=1 (fake tmux is expected to stop launch after delivery checks)

## watcher paused stale batch
watch_stdout:
  stale: paused recheck batch (2): test:fm-held-alpha, test:fm-held-beta
wake_queue_stale_records:
  stale test:fm-held-alpha stale: test:fm-held-alpha (paused 501s, awaiting external - declared pause, rechecked on a long cadence not a wedge; confirm the wait still holds)
  stale test:fm-held-beta stale: test:fm-held-beta (paused 501s, awaiting external - declared pause, rechecked on a long cadence not a wedge; confirm the wait still holds)

## watcher parked terminal dedupe and new decision wake
already_surfaced_watch_still_alive_after_2s=yes
already_surfaced_stdout_bytes=0
already_surfaced_queue_bytes=0
new_decision_watch_stdout:
  signal: /var/folders/85/0xf5ctz126717j1k2wfdc_4w0000gn/T/no-mistakes-evidence/01KZDY0N5G1RCWNRNX87K8225N/manual-e2e-corrected-20260807054639/watch-terminal-dedupe/state/alpha-parked.status
manual_evidence_complete

Evidence: Baseline receipt verification

diff -qr between the driver receipt and the worktree receipt produced 0 bytes; 19 receipt files were hashed and copied into evidence.

verified byte-identical driver and worktree baseline receipt
      19 /var/folders/85/0xf5ctz126717j1k2wfdc_4w0000gn/T/no-mistakes-evidence/01KZDY0N5G1RCWNRNX87K8225N/baseline-receipt-20260807053646/receipt-sha256.txt

Evidence: Attached baseline receipt README

Receipt states the same six broad local validation failures reproduced equivalently on detached origin/main and the task branch under the same environment.

# Baseline Receipt - firstmate-capacity-night-2864

Comparison date: 2026-08-07.

Task branch: `fm/firstmate-capacity-night-2864` at `75637e1b584dcd3341ab8f73807735beca13b84d`.

Baseline worktree: `/Users/temp/.treehouse/firstmate-7bab20/2/firstmate-origin-main-baseline-2864`.

Baseline commit: `70aeba855527f7693082f6dd1bc731e334d0269f`.

The same six exact failing tests were run on detached `origin/main` and on the task branch under the same local environment.

All six failures reproduced equivalently.

| Test | origin/main exit | task branch exit | Decisive matching diagnostic |
| --- | ---: | ---: | --- |
| `tests/fm-gotmp.test.sh` | 1 | 1 | `not ok - teardown exited non-zero with a valid tasktmp` |
| `tests/fm-calm-pi-extension.test.sh` | 1 | 1 | `not ok - /export did not complete while calm mode was on` |
| `tests/fm-decision-hold-lifecycle.test.sh` | 1 | 1 | `fm-decision-hold: compatible tasks-axi is required` and `not ok - could not register route hold` |
| `tests/fm-kimi-harness.test.sh` | 1 | 1 | `fm-kimi-turnend-hook: refused: python3 with tomllib is required to validate config.toml.` |
| `tests/fm-muse-harness.test.sh` | 1 | 1 | `not ok - fm-harness.sh under process 'muse-bin-0.1.0-R708.1' reported '', expected muse` |
| `tests/fm-backend.test.sh` | 1 | 1 | `fm-decision-hold: compatible tasks-axi is required` and `expected exit 0, got 1` |

Full logs are colocated in this directory:

- `origin-main-*.log`
- `task-branch-*.log`
- `origin-main-summary.tsv`
- `task-branch-summary.tsv`

Evidence: fm-task-delivery targeted test log

ok - fm-spawn: a ship spawn requires a valid explicit mode and yolo before anything is created
ok - fm-spawn: scout and secondmate spawns refuse ship delivery flags
ok - fm-spawn: the brief's recorded mode and the spawn's explicit mode must agree
ok - fm-spawn: a rigor downgrade against the registered posture is announced, never blocked
ok - fm-spawn: registry deviation notices resolve external absolute paths to their registered project name
ok - fm-spawn: a scout spawn resolves no delivery posture from the registry
ok - fm-promote: promotion requires the delivery contract and records it exactly once
ok - fm-project-mode: the conditional policy is accepted, mapped for mechanical callers, and readable raw
ok - fm-project-mode: path lookup handles external, in-tree, unknown, ambiguous, and malformed identities
ok - fm-project-mode: path normalization keeps relative overrides based at the caller cwd
# all fm-task-delivery tests passed

Evidence: fm-watch-triage targeted test log

ok - signal_reason_is_actionable: benign absorbed, captain verbs and coalesced batches surfaced
ok - stale_is_terminal: terminal status surfaces, non-terminal and no-status are benign
ok - scan_captain_relevant_statuses lists only captain-relevant statuses
ok - classifier primitives: keyed decisions and activity phases, captain relevance, window-to-task, and overrides
ok - crew_is_provably_working: only working+run-step/pane is provable; idle/finished/parked/failed/unknown surface
ok - status_is_paused: only the leading paused verb matches, and paused is not captain-relevant
ok - crew_absorb_class: working/paused/none from one read; crew_is_paused and crew_is_provably_working agree
ok - signal_crew_provably_working: benign only when every referenced crew is provably working
ok - a no-verb signal whose crew is provably working is absorbed (no exit, no queue, suppressor advanced, beacon present)
ok - a bare turn-end whose crew is provably working (busy pane) is absorbed
ok - a bare turn-end whose crew is not provably working is surfaced (the swallowed-finish fix)
ok - a no-verb working: note whose crew is idle with no running pipeline is surfaced
ok - captain-relevant signal is surfaced (queue + exit) and marked surfaced
ok - a stale pane sitting on a terminal status is surfaced (queue + exit)
ok - already-surfaced parked and terminal stales are absorbed, while a new decision status still wakes
ok - already-surfaced terminal statuses still wake once for parked, PR-ready, or failed run states
ok - already-surfaced terminal stale classification uses one crew-state sample
ok - identical PR-ready and failed run outcomes surface once per validation generation
ok - same-hash working states wedge-track, and PR-ready and failed outcomes surface once
ok - a stale terminal-looking status is overridden and absorbed while a run is actively working, then wedge-escalated
ok - provably-working non-terminal stale is absorbed on first sight, then wedge-escalated past the threshold
ok - consecutive wedge escalations on the same pane accumulate and demand deep inspection at the threshold
ok - a pane becoming active again resets the consecutive wedge-escalation counter
ok - a busy worker below the turn-age bound remains working with no escalation
ok - a busy worker with a stable pane hash still escalates once its completed-turn age reaches the bound
ok - a busy worker whose pane hash changes every poll still escalates once its completed-turn age reaches the bound
ok - touching a busy worker's completed-turn marker resets the age and prevents an old-age escalation
ok - repeated busy turn-age escalations reuse the existing escalation counter and demand deep inspection at the threshold
ok - the production default busy-turn-age bound is 3600s (5min under does not wedge, 66min over does)
ok - a not-provably-working non-terminal stale is surfaced immediately (never left to wait out the timer)
ok - a declared pause is absorbed on first sight, then re-surfaced as a recheck past the threshold, never wedge-escalated
ok - declared pauses use bounded labeled cadence and a later status resumes normal stale behavior
ok - multiple paused stale rechecks from one scan produce one watcher interruption with both durable records queued
ok - a declared paused secondmate re-surfaces on the bounded normal-mode cadence
ok - a non-paused secondmate retains normal stale suppression
ok - a resumed secondmate clears pause and stale tracking before stale exemption
ok - unchanged stale hashes reclassify when a crew enters or leaves pause
ok - a declared pause is periodically rechecked against authoritative active-run state
ok - a paused status overridden by authoritative working preserves its wedge timer and escalates
ok - paused last-status panes wake once for PR-ready or failed run outcomes
ok - AFK paused stale panes wake once for PR-ready or failed run outcomes
ok - matching non-terminal stale suppressors repair missing or corrupt stale-since timers
ok - triage log capping handles wc byte counts with leading spaces
ok - a captured process-event result wakes a healthy watcher proactively, with no manual drain
ok - a process-event wake is delivered once: no duplicate wake while queued, and none once handled
ok - complete process-event queue keys map to distinct seen markers
ok - queue revalidation, proactive output, and marker commit serialize with drain
/Users/temp/.no-mistakes/worktrees/acee6d463bcf/01KZDY0N5G1RCWNRNX87K8225N/bin/fm-push-transition-lib.sh: line 92: echo: write error: Broken pipe
tests/wake-helpers.sh: line 254: 50109 Killed: 9               PATH="$dir/fakebin:$PATH" FM_HOME="$dir" FM_PROCEVENT_CLAIM_ROOT="$dir/claims" FM_CREW_STATE_BIN="$dir/fakebin/fm-crew-state.sh" FM_POLL=0.2 FM_SIGNAL_GRACE=1 FM_CHECK_INTERVAL=999999 FM_HEARTBEAT=999999 "$WATCH" > "$out"
tests/wake-helpers.sh: line 254: 50763 Killed: 9               PATH="$dir/fakebin:$PATH" FM_HOME="$dir" FM_PROCEVENT_CLAIM_ROOT="$dir/claims" FM_CREW_STATE_BIN="$dir/fakebin/fm-crew-state.sh" FM_POLL=0.2 FM_SIGNAL_GRACE=1 FM_CHECK_INTERVAL=999999 FM_HEARTBEAT=999999 "$WATCH" > "$out"
ok - surfacing failures replay before marker commit and suppress only after delivered output
ok - marker failure exits through the shared wake owner, releases its lock, and replays later
ok - a heartbeat with no captain-relevant change is absorbed and backs off the cadence
ok - heartbeat backstop fail-safe surfaces a captain-relevant status the per-wake path missed
ok - the liveness beacon stays fresh while the watcher absorbs benign wakes (fm-guard never false-alarms)
ok - with .afk present the watcher reverts to one-shot so the daemon owns triage (no double-triage)
ok - AFK changed paused panes hand off plain stale identities for daemon-owned pause triage

Evidence: fm-fleet-sync targeted test log

ok - detached clean ancestor is re-attached and fast-forwarded (recovered)
ok - detached HEAD with unique commits is reported STUCK and left untouched
ok - detached clean ancestor with diverged local default is reported STUCK and left untouched
ok - dirty working tree is reported STUCK and left untouched
ok - non-default named branch is reported STUCK and left untouched
ok - diverged default branch is reported STUCK and left untouched
ok - on-default clean behind clone still fast-forwards
ok - already-current clone is reported unchanged
ok - no-origin clone is skipped (benign), not flagged STUCK
ok - local-only clone is skipped (benign), not flagged STUCK
ok - external registered local-only project paths are skipped before remote sync
ok - single-project form accepts a bare project name
ok - single-project bare name resolution is not cwd-sensitive
ok - single-project form accepts a projects/<name> relative name
ok - single-project projects/<name> resolution is not cwd-sensitive
ok - single-project form leaves a genuinely bad name unresolved
ok - whole-fleet form processes every clone under projects/
ok - bootstrap relays recovered: and STUCK: fleet-sync outcomes
ok - orphaned provably-stale packed-refs.lock is cleared and the clone syncs
ok - a live packed-refs.lock is never removed and the sync fails loudly
ok - a live process holding the clone worktree dir blocks lock removal (clone-dir liveness)
ok - a transient packed-refs.lock that self-clears is retried without a force-remove
ok - a non-packed-refs.lock fetch failure keeps today's behavior (no retry)

Evidence: fm-crew-state targeted test log

ok - active run-step is authoritative
ok - stale needs-decision over active run is superseded
ok - stale blocked over active run is superseded
ok - genuine parked run is not flagged superseded
ok - scalar gate parked run is not flagged superseded
ok - gate block parked run is not flagged superseded
ok - ci-ready status log beats monitoring run
ok - ci-monitoring run with checks already green surfaces done
ok - top-level ci status uses ci log green marker
ok - terminal no-checks ci-monitor marker surfaces done
ok - base-advance rearm after green stays working
ok - pending no-checks ci-monitor marker stays working
ok - ci-monitoring run with checks not yet green stays working
ok - a fresh issue after an earlier green reading is not masked
ok - stale checks-green status log does not mask CI relapse
ok - ci fixing is not overridden by an earlier green marker
ok - top-level fixing is not overridden by a stale ci running row
ok - top-level fixing is not overridden by a stale done log
ok - terminal passed run is authoritative
ok - terminal failed run is authoritative
ok - cross-branch run is attributed via the real runs list
ok - cross-branch attribution picks the branch's most recent row
ok - coarse run does not probe another branch's ci log
ok - another branch's run is ignored, falls back
ok - no run + a busy semantic record reads working, attributed to its source
ok - a converted adapter never reads working from rendered footer text
ok - grok still reads working through its isolated rendered-tail fallback
ok - herdr's native busy verdict reads working with no record present
ok - a mid-tool-call crew stays working because its record outranks herdr's generation state
ok - an idle record with idle agent_status stays not-busy (no regression for a human-blocked agent)
ok - no run + idle pane uses the status-log verb
ok - no run + idle pane parses keyed status syntax
ok - no run + idle pane on a paused: status reports state: paused with its reason
ok - no run + idle pane honors the configured paused verb
ok - a trailing resolved: event does not corrupt state render (idle stays idle)
ok - dead window ignores stale status log
ok - closed pane still reports a terminal run-step
ok - closed pane still reports an active run-step
ok - no timeout command uses perl bound
ok - scout skips the run lookup
ok - torn-down worktree is handled gracefully
ok - missing meta is handled gracefully
ok - crew_is_provably_working absorbs a validating crew found only via the runs-list fallback
ok - crew_is_provably_working still surfaces a genuinely stopped crew (safety property preserved)
ok - usage error exits 2
ok - historical same-branch rewritten head is not attributed as current
ok - active run with valid descendant fix head remains current
ok - local work advanced past run head invalidates attribution
ok - missing run head falls back instead of matching by branch
all fm-crew-state tests passed

Evidence: fm-daemon targeted test log

ok - fm-afk-start.sh fails before daemon startup when the afk flag cannot be written
ok - fm-afk-start.sh ignores stale pidfile-only live pids
ok - fm-afk-start.sh reclaims stale daemon locks whose live pid identity no longer matches
ok - supervise daemon state root is scoped by FM_HOME
ok - routine signal self-handles
ok - captain-relevant status verbs escalate
ok - check + unknown escalate; heartbeat self-handles
ok - transient stale self-handles and records a persistence marker
ok - enriched stale wedges bypass status absorption without disturbing busy workers
ok - stale + terminal status escalates immediately
ok - paused reasons with captain phrases remain pause-classified
ok - handle_wake on a paused stale records a pause marker, drops the wedge marker, and does not escalate
ok - paused stale validation run outcomes escalate instead of self-handling
ok - handle_wake records a declared pause from a routine signal for long-cadence rechecks
ok - a terminal signal clears pause and stale tracking across both supervisors
ok - housekeeping migrates a normal-watcher's declared pause into daemon tracking
ok - housekeeping clears an already-resumed watcher pause across both supervisors
ok - housekeeping seeds pause tracking from status without a watcher marker
ok - persistent stale escalates after threshold and clears its marker
ok - resumed (busy) stale clears its marker without escalating
ok - housekeeping re-surfaces a stale declared pause on the long cadence and resets its window
ok - housekeeping clears a paused marker whose pane became busy again, without escalating
ok - housekeeping clears a paused marker once the crew is no longer declaring the pause
ok - housekeeping moves an existing stale marker to pause before wedge escalation
ok - housekeeping clears tracking when a crew leaves pause
ok - persistent herdr stale resolves the target from metadata and escalates
ok - herdr idle busy-footer stale clears through capture corroboration
ok - resumed herdr stale clears through backend-aware busy state
ok - persistent Orca stale resolves the terminal from metadata
ok - multiple escalations flush as a single batched digest
ok - batch flush measures max-delay from the first append, not the last
ok - catch-all scan escalates a missed terminal once, not twice
ok - handle_wake routes routine->self and captain->escalate
ok - INJECT_SKIP forces self-handle, bypassing captain-relevant classification
ok - is_wake_reason distinguishes watcher wake reasons from singleton-status stdout
ok - terminal-stale escalate removes its marker so housekeeping does not re-escalate
ok - captain signal escalate marks seen so the catch-all scan does not re-fire
ok - _collapse_newlines replaces newlines with literal separator
ok - afk flag absent: daemon does not inject, buffer preserved
ok - busy-guard defers injection when supervisor pane is busy
ok - marker detection: marker -> stay afk, no marker -> exit afk
ok - /afk invocation is exempt from afk exit (no self-cancel)
ok - should_exit_afk returns false when afk is not active
ok - strip_injection_marker removes the sentinel marker cleanly
ok - pane_input_pending detects partial input on the cursor line
ok - pane_input_pending: blank cursor line is not pending
ok - pane_input_pending: only proven empty agent prompts pass
ok - fm_tmux_composer_state: a bare shell prompt ($/%/#/>) reads unknown, never empty (dead-shell injection safety)
ok - fm_tmux_composer_state: a bordered composer box and bare agent glyphs (❯/›) still read empty
ok - fm_tmux_composer_state: only matching edge borders form a composer box
ok - pane_input_pending honors FM_COMPOSER_IDLE_RE after border stripping
ok - classify_signal dedupes against the catch-all scan seen marker
ok - classify_stale dedupes against the signal path seen marker
ok - AFK nonterminal working:+merged keeps wedge aging and re-escalates at bound
ok - genuine done: and merge-check events still escalate
ok - pane_input_pending: an idle bordered composer is NOT pending (afk-invx-i5)
ok - pane_input_pending: text inside a bordered composer is still pending
ok - submit-ACK confirms a submit when the composer returns to a bordered-empty box
ok - submit-ACK reports pending on a persistently swallowed Enter (type-once)
ok - max-defer on an empty stuck pane types once, alarms, and preserves the buffer
ok - max-defer flushes and clears the buffer on an empty bordered pane
ok - max-defer on a pending composer alarms without typing
ok - normal flush clears a stale wedge marker
ok - below MAX_DEFER: no inject, no alarm, buffer preserved
ok - max-defer does not flush or alarm while afk is inactive
ok - library mode: sourcing the daemon defaults FM_WEDGE_ALARM_EXEC to discard (no test can fire a real notification)
ok - wake helpers replace inherited notifier overrides with the safe recorder
ok - the discard seam suppresses every notifier, including command: (fires nothing)
ok - direct notifier helpers honor the discard seam, including command:
ok - osascript channel routes through the notifier seam with the summary (never a real notification)
ok - herdr channel routes through the notifier seam with the summary (never a real notification)
ok - command channel runs the captain command with the summary on $1 and on stdin
ok - command channel failures redact configured commands while logging their exit status
ok - unknown channel directives are redacted while the alarm keeps running
ok - off disables every active alert regardless of directive position (marker and tmux flash are unaffected)
ok - auto resolves to the macOS osascript notifier on Darwin (default-on)
ok - auto on a non-macOS platform selects no built-in OS channel (the marker or a configured command carries it)
ok - config/wedge-alarm selects every configured channel and skips comment and blank lines
ok - a failing channel logs and falls back to the next channel, never crashing the alarm
ok - a hung notifier is bounded, logged, and falls through to the next channel
ok - a backgrounded command notifier remains bounded until its process group is reaped
ok - a hung notifier override is bounded, logged, and proceeds to the next channel
/Users/temp/.no-mistakes/worktrees/acee6d463bcf/01KZDY0N5G1RCWNRNX87K8225N/bin/fm-supervise-daemon.sh: line 751: 99909 Terminated: 15          sh -c 'sleep 30 & printf "%s" "$!" > "$1"; wait' sh "$child_file"
ok - daemon shutdown stops and reaps the active notifier process group
ok - inject_wedge_alarm writes the marker AND emits the active alert even with no tmux status-line (herdr backend)
ok - in-process wedge throttle prevents alert spam when the marker cannot persist
ok - fm-send exits non-zero on a confirmed swallow, zero on a clean submit
ok - fm-send exits non-zero when initial text send fails
ok - fm-send exits non-zero unless delivery is proven empty
ok - discover_supervisor_backend: override > TMUX_PANE > HERDR_ENV+HERDR_PANE_ID > tmux fallback
ok - discover_supervisor_target: override > TMUX_PANE > herdr '<session>:<pane-id>' composition > firstmate:0 fallback
ok - pane_is_busy: herdr native busy_state='busy' short-circuits without a capture fallback
ok - primary busy guard isolates rendered signatures by detected harness
ok - pane_is_busy: omitted backend defaults to tmux for Grok's isolated fallback
ok - pane_input_pending: dispatches through fm_backend_composer_state for backend=herdr
ok - inject_msg: herdr busy-guard defers before ever attempting a submit
ok - inject_msg: herdr composer-guard defers before ever attempting a submit
ok - inject_msg: herdr pane-gone check defers before any busy/composer/submit call
ok - inject_msg: dispatches busy-guard/composer-guard/submit through the herdr backend and succeeds on a confirmed empty composer
ok - inject_msg: defers on a dead-shell/unreadable composer (unknown), never typing the escalation into a shell
ok - inject_msg: unrecognized composer states defer by default

- Outcome: 🔧 1 issue found → auto-fixed ✅ across 2 runs (46m4s)

Pipeline

Updates from git push no-mistakes

✅ **intent** - passed

✅ No issues found.

✅ **Rebase** - passed

✅ No issues found.

🔧 **Review** - 1 issue found → auto-fixed (3) ✅

• 🚨 bin/fm-watch.sh:409 - Intent requires that "failed checks" and "PR-ready outcomes" still wake, but the new paused-status branch reduces every non-working crew state to paused. crew_absorb_class returns none for run-step parked, done, and failed, so a worker that resumes validation while its last status is still paused: can later reach PR-ready/failed/parked and this path will still record a paused stale instead of surfacing the run outcome.

🔧 Fix: Surface paused validation outcomes once
1 error still open:

• 🚨 bin/fm-watch.sh:1064 - Intent requires that "failed checks" and "PR-ready outcomes" still wake, but the paused run-outcome surfacer is disabled in away mode by ! afk_present. If a paused pane already has the same stale hash and its no-mistakes run later reaches PR-ready or failed while state/.afk exists, the AFK branch never reads fm-crew-state and the outcome is not surfaced.

🔧 Fix: Surface AFK paused validation outcomes
1 error still open:

• 🚨 bin/fm-watch.sh:1064 - Intent requires that "failed checks" and "PR-ready outcomes" still wake, but the AFK path now calls the paused run-outcome surfacer and that surfacer still emits only a generic stale: <window> reason. The away daemon consumes that stdout, classifies it from the unchanged paused: status line as an ordinary pause, and self-handles it; because the run-state marker was already written, the same PR-ready/failed generation will not retry.

🔧 Fix: Escalate AFK paused validation outcomes
✅ Re-checked - no issues remain.

🔧 **Test** - 1 issue found → auto-fixed ✅

• ⚠️ .no-mistakes/baseline-receipts/firstmate-capacity-night-2864 - The intent says the origin/main comparison receipt and full logs are in .no-mistakes/baseline-receipts/firstmate-capacity-night-2864/, but that directory is absent from this checked-out worktree. I could not independently verify the baseline-aware broad-failure evidence and did not rerun the broad validation suite.
• bash tests/fm-task-delivery.test.sh > /var/folders/85/0xf5ctz126717j1k2wfdc_4w0000gn/T/no-mistakes-evidence/01KZDY0N5G1RCWNRNX87K8225N/fm-task-delivery.test.log 2>&1
• bash tests/fm-fleet-sync.test.sh > /var/folders/85/0xf5ctz126717j1k2wfdc_4w0000gn/T/no-mistakes-evidence/01KZDY0N5G1RCWNRNX87K8225N/fm-fleet-sync.test.log 2>&1
• bash tests/fm-crew-state.test.sh > /var/folders/85/0xf5ctz126717j1k2wfdc_4w0000gn/T/no-mistakes-evidence/01KZDY0N5G1RCWNRNX87K8225N/fm-crew-state.test.log 2>&1
• bash tests/fm-watch-triage.test.sh > /var/folders/85/0xf5ctz126717j1k2wfdc_4w0000gn/T/no-mistakes-evidence/01KZDY0N5G1RCWNRNX87K8225N/fm-watch-triage.test.log 2>&1
• bash tests/fm-daemon.test.sh > /var/folders/85/0xf5ctz126717j1k2wfdc_4w0000gn/T/no-mistakes-evidence/01KZDY0N5G1RCWNRNX87K8225N/fm-daemon.test.log 2>&1
• Manual project registry fixture exercising bin/fm-project-mode.sh --with-name --path <external>, in-home path matching, unknown-path default, free-form prose non-parsing, ambiguous path refusal, and malformed path refusal.
• Manual external git fixture exercising FM_HOME=<fixture> FM_ROOT_OVERRIDE=<repo> bin/fm-fleet-sync.sh <external/agent> to confirm pai-agent: skipped: local-only project.
• Manual watcher fixture exercising due paused stale recheck batching, already-surfaced terminal stale absorption, and new needs-decision: signal wake through bin/fm-watch.sh.
• find .no-mistakes/baseline-receipts/firstmate-capacity-night-2864 -maxdepth 2 -type f -print
• git status --short --branch

🔧 Fix: Attach baseline receipt evidence
✅ Re-checked - no issues remain.

• diff -qr /Users/temp/.treehouse/firstmate-7bab20/2/firstmate/.no-mistakes/baseline-receipts/firstmate-capacity-night-2864 .no-mistakes/baseline-receipts/firstmate-capacity-night-2864
• bash tests/fm-task-delivery.test.sh
• bash tests/fm-fleet-sync.test.sh
• bash tests/fm-crew-state.test.sh
• bash tests/fm-daemon.test.sh
• bash tests/fm-watch-triage.test.sh
• Manual CLI evidence in /var/folders/85/0xf5ctz126717j1k2wfdc_4w0000gn/T/no-mistakes-evidence/01KZDY0N5G1RCWNRNX87K8225N/manual-e2e-corrected-20260807054639/manual-e2e-transcript.log using fm-project-mode.sh, fm-spawn.sh, fm-watch.sh, and wake queue records.
• git status --short --untracked-files=normal

✅ **Document** - passed

✅ No issues found.

✅ **Lint** - passed

✅ No issues found.

✅ **Push** - passed

✅ No issues found.