feat(bin): add durable task and event supervision

.agents/skills/afk/SKILL.md

@@ -92,14 +92,15 @@ The daemon never injects into an in-use pane. Two checks run before every
 injection, dispatched through `bin/fm-backend.sh` for the supervisor's own
 backend (tmux or herdr; see "Auto-discovered supervisor pane" below):
 
-- **`pane_is_busy`** - the harness shows a busy footer (agent mid-turn) on tmux (shared with `fm-send.sh` via `bin/fm-tmux-lib.sh`); on herdr, tries the native `agent.get`-backed busy state first, trusts only `busy` outright, and corroborates every non-`busy` verdict with the same regex-over-capture reader.
+- **Primary-pane busy guard** - `pane_is_busy` trusts Herdr native `busy` when available, otherwise matches rendered output against only the detected primary harness's signature.
+  This narrow delivery guard never classifies a recorded worker task and never uses a global union of vendor patterns.
 - **Composer-state guard** - `inject_msg` reads the full `empty`/`pending`/`unknown` verdict from `fm_backend_composer_state` and injects only when it is affirmatively `empty`.
   `pending` means real unsubmitted text, while `unknown` includes an unreadable pane and a bare shell prompt left after the agent exits, so both defer.
   The shared `bin/fm-composer-lib.sh` owns the content decision after each backend captures and structurally identifies its own composer row.
   It preserves idle bordered composers such as claude's `│ > … │` and bare agent glyphs as empty, but a bare shell glyph is unknown unless inside a genuine bordered composer box; see `docs/herdr-backend.md` "Composer and injection safety" for the complete contract.
   `pane_input_pending` remains the tested predicate for callers that only need to know whether real unsubmitted text is present, but it is insufficient for an injection-safety decision because it cannot distinguish `empty` from `unknown`.
 
-Either condition, or any composer verdict other than `empty`, defers the injection; the buffered escalation survives in `state/.subsuper-escalations` and is retried on the next housekeeping tick.
+A busy primary pane, or any composer verdict other than `empty`, defers the injection; the buffered escalation survives in `state/.subsuper-escalations` and is retried on the next housekeeping tick.
 In afk mode the composer guard is belt-and-suspenders (no human is typing), but it protects against the race window between the captain returning and their message landing, a dead shell, and the daemon's own previous injection sitting unsent.
 
 **Max-defer escape (the daemon must never silently wedge).**
@@ -181,14 +182,14 @@ the operational prefix lets firstmate distinguish it from a real captain message
 - **Single-line digest** - embedded newlines are collapsed to a literal
   separator before injection, so submission is unambiguous regardless of
   harness.
-- **Composer guard on the supervisor pane** - before injecting, the daemon checks `pane_is_busy` (harness busy footer means agent mid-turn) and reads `fm_backend_composer_state` directly.
+- **Busy and composer guards on the supervisor pane** - before injecting, the daemon runs the detected-primary-harness rendered busy guard and reads `fm_backend_composer_state` directly.
   Only `empty` permits injection; `pending` protects half-typed or swallowed input, and `unknown` protects unreadable panes and bare dead-shell prompts.
   Every other result preserves the buffer for retry, so the daemon never merges its digest into the captain's half-typed line or types it into a shell.
 - The shared composer classifier receives a candidate row only after the active backend performs its own capture and structural row recognition.
   tmux and herdr route their raw styled candidate rows through the shared `fm_composer_strip_ghost` extractor, which removes dim/faint and dark-TRUECOLOR ghost/placeholder text before classification.
   They read the composer shape from a separately ANSI-stripped plain row because a dark TRUECOLOR border can be stripped with ghost content.
   A ghost-only or idle bordered composer such as claude's `│ > ... │` therefore reads empty without allowing an unbordered shell prompt to do the same.
-  `FM_COMPOSER_IDLE_RE` still overrides tmux empty-composer matching after shared ghost and border stripping, and `FM_BUSY_REGEX` overrides busy footers.
+  `FM_COMPOSER_IDLE_RE` still overrides tmux empty-composer matching after shared ghost and border stripping, and `FM_BUSY_REGEX` overrides the rendered delivery guards plus Grok's isolated task-state fallback.
 - **Max-defer escape** - the daemon must never silently wedge. If anything stays
   buffered past `FM_MAX_DEFER_SECS` (default 300s), the daemon attempts one
   normal flush, which still requires an idle pane and an affirmatively empty composer. If that

.agents/skills/firstmate-coding-guidelines/SKILL.md

@@ -44,7 +44,7 @@ Every contract - a data format, a state machine, a decision procedure - is state
 Every other mention of it is a one-line cross-reference, never a restatement.
 A single deliberate one-line reinforcement at a genuine risk point is allowed, for example a "don't forget X" placed exactly where forgetting X is costly.
 Restating the contract's substance a second time is not allowed: the two copies will drift the moment only one is edited.
-When you touch a contract, grep the repo for its other mentions and update the cross-references, not duplicate the change into a second full copy.
+When you touch a contract, patch, replace, or prune the owner's existing language rather than appending a new clause or paragraph wherever possible, then grep the repo for its other mentions and update the cross-references, not duplicate the change into a second full copy.
 
 ## Inline-stub pattern
 
@@ -61,7 +61,7 @@ Apply the decision tree above to every line you are about to add to `AGENTS.md`.
 If an addition needs more than a few lines of conditional detail (detail that matters only in a specific situation) or reference detail (a wire format, an exact schema, historical rationale), you are almost certainly adding it to the wrong file.
 `AGENTS.md`'s token cost is paid by every session of every fleet member, every time, whether or not that session ever hits the situation the new lines describe.
 A skill's cost is paid only by the sessions that actually load it.
-When in doubt, write the fact into the skill or doc first, and add only the one-line trigger to `AGENTS.md`.
+When in doubt, write the fact into the skill or doc first by patching that owner's existing language, and add only the one-line trigger to `AGENTS.md`.
 
 ## Trigger hygiene
 

.agents/skills/fmx-respond/SKILL.md

@@ -4,7 +4,8 @@ description: >-
   Agent-only playbook for handling X mode mentions and follow-ups.
   Use on an "x-mention <request_id>" check wake to read the stashed mention, classify it, act autonomously on eligible requests, reply or dismiss, and link spawned work.
   Also use on an "x-mode-error ..." check wake to report the X-mode configuration blocker instead of answering a mention.
-  Also use on milestone and terminal wakes for an X-mode-linked task before posting completion follow-ups, ending terminal outcomes with --final.
+  Also use on milestone and terminal wakes for an X-mode-linked task before posting completion follow-ups, using typed promised-final reconciliation when registered and --final otherwise.
+  Also use on a "public-followup ..." check wake, and whenever a promised final public reply must be created, reconciled, or delivered.
   Loaded only when X mode is enabled.
 user-invocable: false
 metadata:
@@ -56,7 +57,7 @@ How the reply lands depends on whether the work finishes during this turn:
      The exact resolution and fail-safe posting contract is owned by `docs/configuration.md`.
      If a recovery respawns the same relay request onto a successor task, relink with the paired `--carry-count <n> --carry-ts <epoch>` flags plus any prior `x_platform=` and `x_reply_max_chars=` as `--carry-platform <x|discord> --carry-max <n>` so the successor keeps the consumed follow-up count, original 7-day window, and reply split budget.
   4. **Follow up on genuine milestones, sparingly.** Firstmate gets up to **three** follow-ups per mention, within a 7-day window, chained in the same thread - spend them only on changes the captain would actually want to hear about (e.g. investigation done and a build started, work shipped or ready, or the task failing), never on routine internal churn.
-     The task's final outcome - shipped / reported / merged / failed - is always posted with `--final`, which clears the link regardless of how many follow-ups remain.
+     A task without a promised-final commitment posts its final outcome - shipped / reported / merged / failed - with `--final`, which clears the link regardless of how many follow-ups remain. A typed promised-final commitment uses the deterministic consumer instead.
      That posting happens on the task's milestone and completion wakes (see "Completion follow-up" below), not this turn.
 
 So every drained mention sorts into one of three cases (the worthiness judgment, widened):
@@ -141,7 +142,7 @@ Treat `state/x-inbox/` as the source of truth and process **every** file you fin
       **If the request spawned a real, longer-running task** (you ran `bin/fm-spawn.sh`), link that task to this mention so milestone and completion follow-ups can be posted: `bin/fm-x-link.sh <task-id> <request_id>`.
       **Link here, in step 2c, before the step 2f inbox cleanup** - `bin/fm-x-link.sh` can copy both the mention's reply platform and explicit budget from the still-present inbox payload without a relay lookup.
       If that local context is incomplete it uses the durable resolution contract in `docs/configuration.md` and warns loudly, while the follow-up path refuses to post unless both values can be resolved authoritatively.
-      Then step 2d's reply is an **acknowledgement** ("on it, captain"), and genuine milestone updates plus the final outcome come later as follow-ups (see "Completion follow-up" below), with the terminal one posted using `--final`.
+      Then step 2d's reply is an **acknowledgement** ("on it, captain"), and genuine milestone updates plus the final outcome come later as follow-ups (see "Completion follow-up" below), with the terminal one posted using `--final` when no typed promised-final commitment exists.
       If the work completed in this turn (a backlog item filed, a question answered), there is no task to link and step 2d reports the outcome directly.
    d. **Compose the reply.** For a **question**, answer `.text` from the fleet state gathered in step 1. For an **actionable request that completed now**, report the outcome of step 2c (what was done, or - for escalated work - that it has been flagged for the captain). For an **actionable request that spawned a linked task**, acknowledge that you have the order and are on it - milestone updates and the final outcome follow later as completion follow-ups, so do not promise a result you do not yet have. Either way keep it short, in firstmate's voice, and public-safe.
       Conversation continuity: when `in_reply_to` is present this is a conversation reply - read `in_reply_to.text` (what `in_reply_to.author_handle` said just before) as **context** and continue that thread, resolving "it", "that", "and then?" against the parent; for a fresh mention (`in_reply_to` is null) answer on its own.
@@ -198,14 +199,50 @@ This skill's own responsibility during the mention-handling turn is linking the
 - On each such milestone, firstmate checks whether a follow-up is still due with `bin/fm-x-followup.sh --check <task-id>` (prints the `request_id` when the link exists, the count is under the cap, and the window has not lapsed; silent otherwise, pruning an exhausted or expired link).
 - If due, it composes a short, public-safe update and posts it with `bin/fm-x-followup.sh <task-id> --text-file <path>` (or stdin), which posts via the relay's follow-up endpoint; a successful non-final post increments the counter and keeps the link so a later milestone can still post against it.
   When the update carries one real visual artifact, add `--image <path>`; the helper forwards it to `bin/fm-x-reply.sh --followup` so the same image contract used for ordinary replies applies here too.
-- On a terminal wake (PR merged / scout report / local merge / failed), firstmate posts the task's **final** outcome ("done, here's the result"; for a failure, an honest "this one didn't pan out") with `bin/fm-x-followup.sh <task-id> --final --text-file <path>`, which always clears the link after that post regardless of how many follow-ups remain under the cap.
+- On a terminal wake (PR merged / scout report / local merge / failed), firstmate posts the task's **final** outcome ("done, here's the result"; for a failure, an honest "this one didn't pan out") with `bin/fm-x-followup.sh <task-id> --final --text-file <path>` only when no promised-final public commitment is registered for that work. When the promised-final procedure above applies, `bin/fm-public-followup.sh consume` and `deliver` own the terminal reply and clear the legacy link at the validated receipt boundary, so do not call `fm-x-followup.sh --final` for the same outcome. If delivery reports that link cleanup needs reconciliation, do not post anything else; `bin/fm-x-followup.sh --clear <task-id>` is the clear-only recovery command in the bound work home.
 - Every follow-up is held to the exact same public-safety bar as every reply here: outcomes only, no task ids, internals, captain-private material, or secrets. Past the window, past the cap, or on the relay's own rejection of an exhausted binding, a follow-up attempt is skipped silently and the link is cleared - never treated as a failure worth retrying.
 - If either a follow-up's platform or explicit budget cannot be authoritatively resolved from per-request context, inbox payload, or relay answer, `bin/fm-x-followup.sh` does NOT post it: the fail-safe holds it (the link is kept, exit non-zero) rather than use a local default. This is a retryable hold - a later milestone wake retries it once both values are recoverable.
 
+## Promised final replies (the commitment that must survive compaction)
+
+The follow-up budget above is a courtesy.
+A **promised final reply** - "I'll report back when this lands" - is a commitment, and forgetting it is publicly visible.
+Never carry one in your head: the moment you promise a specific outcome in a public thread, turn it into durable state and let the scripts reconcile it.
+This section is the sole owner of that procedure.
+`tasks-axi public-followup --help` owns the typed obligation, its states, and its file contracts; `bin/fm-public-followup.sh --help` owns firstmate's flags; do not restate either here.
+
+**When you promise a final:**
+
+1. Create the typed obligation with `tasks-axi public-followup add` and bind the work with `bind-work`, keeping the public-safe summary and the opaque thread binding in the obligation and the full request context where the poll already put it.
+2. Register it with `bin/fm-public-followup.sh register <obligation-id> --relation <relation-id> --work-home <main|secondmate:<id>> --work-id <task-id> --generation <n>`.
+   This is what makes the commitment reconcilable without you.
+3. Put `bin/fm-public-followup.sh brief <obligation-id>` output straight into the worker's brief.
+   It prints the exact reporting command for that binding.
+   Never ask a worker to find the thread or post the reply: only this home holds the relay consent and the thread binding.
+
+**When work reports back, or on a `public-followup ...` check wake, or when the session-start digest lists a public commitment:**
+
+1. Run `bin/fm-public-followup.sh consume`.
+   It reconciles every typed terminal result from disk and prints `ready <obligation-id> <request-id> <platform>` for each commitment that became deliverable.
+   A refusal prints `rejected <event-id>: <reason>` and quarantines that event; read the reason rather than re-emitting blindly.
+2. For each ready commitment, run `bin/fm-public-followup.sh deliver <obligation-id>`.
+   With no `--text-file` it reuses the accepted terminal outcome exactly, which is the preferred path for a landed result.
+   Only pass `--text-file` when the outcome genuinely needs composing, and hold it to the same public-safety bar as every other reply here.
+   Delivery clears the bound task's legacy X link at the validated receipt boundary; if it reports a cleanup failure, use its reconciliation message and do not post a legacy final.
+3. Read the outcome and stop guessing at anything it refuses:
+   - "still waiting on its bound work" means the work has not reported a typed terminal result yet - do not post.
+   - "recorded as retryable" means nothing was posted; retry on a later wake.
+   - "held" means the thread's platform or budget is unresolvable right now; retry once it is recoverable.
+   - "mid-delivery" means a previous post started and its outcome was never recorded. Do NOT deliver again. Establish whether that post landed, then either close it with `record-posted <id> --attempt <n> --chunks <exact-count>` or escalate. Posting again would put a second reply in a public thread.
+   - "the relay no longer accepts a follow-up" is a captain decision, not a retry.
+
+Cleanup refuses while a commitment is still owed for that exact work, so never reach for `--force` to get past it.
+Treat a commitment as kept only after a validated posted receipt or an explicit captain waiver.
+
 ## Notes
 
 - The direct author is always your own captain (owner-only routing), and in live mode you answer and act on eligible requests **autonomously**: enabling X mode is the captain's standing authorization, so never ask the captain before posting and never hold a worthwhile reply for a chat-side OK. For reply-worthy mentions, dry-run (`FMX_DRY_RUN`) is the only non-posting path; pure acknowledgments use the relay dismiss path instead.
-- An actionable mention is **acted on** through the normal lifecycle (intake, backlog, dispatch, investigate, ship), not merely replied to. Work that finishes now gets one outcome reply; work that spawns a real task gets an **acknowledgement now** plus up to three **completion follow-ups** over time, ending with a `--final` one (link the task with `bin/fm-x-link.sh` so those follow-ups can post). A reply alone, with no work behind an actionable ask, is the bug to avoid.
+- An actionable mention is **acted on** through the normal lifecycle (intake, backlog, dispatch, investigate, ship), not merely replied to. Work that finishes now gets one outcome reply; work that spawns a real task gets an **acknowledgement now** plus up to three **completion follow-ups** over time, ending with a `--final` one when no typed promised-final commitment exists (link the task with `bin/fm-x-link.sh` so those follow-ups can post). A reply alone, with no work behind an actionable ask, is the bug to avoid.
 - Destructive, irreversible, or security-sensitive asks are flagged to the captain through the trusted channel first and never run straight from a mention; the public reply says only that it has been flagged.
 - One answered mention = one reply (plus up to three completion follow-ups for a spawned task, spent only on genuine milestones); a skipped mention posts no reply but is **dismissed at the relay** (`bin/fm-x-dismiss.sh`) so the relay drops it rather than re-offering it (which would otherwise churn every poll and end in an "offline" auto-reply). A single wake may cover several pending mentions - drain them all.
 - Conversations: `in_reply_to` carries the parent post for continuity; a pure acknowledgment with nothing to answer is dismissed at the relay and skipped, not replied to. The relay already guards against self-replies and caps replies per conversation, so you only judge "is there something to answer here?".