mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
401f8a2cc9
* feat(board): Pest Control — the first project-scoped Board Program The Product Owner hunts latent defects (what the org records but nobody reads): a weekly cycle — accelerated off-schedule when the trailing-7-day rework rate crosses pest_rework_threshold, with the cheap dedup/scope gates evaluated before the metrics queries — opens one held exploration task against the least-recently-explored opted-in project (deterministic round-robin; opted_in_projects gains a stable ORDER BY), with server- assembled evidence in the spawn prompt (rework hotspots, recurring-findings and waived-minor ledger aggregates, all capped) plus prior-cycle LEARN context. The PO calls the new PO-only propose_bug_hunt verb once: ≤5 items, evidence required per item, targets validated against pest_control participation. CEO decides per item — approve materializes a BACKLOG task (source pest_control, never auto-starts), reject records the reason; both feed the LEARN ledger by exploration task id; all-terminal completes the cycle. Telegram queue pushes carry working Approve/Reject handlers mirroring the roadmap kind. Doctrine: board.md Pest Control section + product-owner verb entry + regenerated verb tables. * feat(panel): Pest Control review queue Command Center gains the pest review queue (per-item approve/reject with reason, mirroring the roadmap queue); the Programs card and the project settings participates-in checkboxes pick the new program up registry-driven — the settings section renders for the first time now that a project-scoped program exists. * feat(board): Periscope — HoM market-research brief program Weekly org-scoped cycle: a solo HoM spawn researches the market (web research with mandatory source URLs — uncited findings are rejected) and files one structured brief via the new HoM-only propose_market_brief verb: headline, cited findings, threats/opportunities, positioning note, all soup-checked and screened through the injection guard at persist time (web-derived text later reaches prompts; flags recorded, content never dropped). A brief is a report, not a proposal: the verb completes the exploration in the same call (the x_feature asymmetry), the cycle ledger auto-closes, and the CEO gets a best-effort notification with no approve/reject surface (periscope deliberately never joins Telegram's action kinds). The latest brief is injected into the roadmap exploration prompt — Periscope feeds Printer, the first cross-role program input. * feat(panel): Market Briefs tab (read-only) Business page gains a Market Briefs tab listing Periscope briefs — headline, cited findings, threats/opportunities — read-only by design; a report has nothing to approve. * feat(board): Coroner — event-triggered Auditor postmortems The first EVENT program: no cron — three best-effort hooks open an autopsy when a task bounces to its 3rd revision (the audit chokepoint), is cancelled after work started, or is budget-blocked; all gated on arming + one-open-autopsy dedup, none can fail the underlying transition. A solo Auditor spawn reads the incident (server-assembled findings + transition context) and files one propose_postmortem: incident summary, root cause, failed stage (validated against the real status vocabulary), and ONE process change — a playbook-kind change drafts via PlaybookService directly into the normal pending-curation queue; the briefed draft_playbook manifest grant was deliberately NOT added, preserving the existing 'auditor curates but never drafts' invariant test. Complete-at-propose (report asymmetry), cycle ledger auto-closes, CEO notified link-only. Integrated as a union with Periscope across the shared program surfaces. * feat(panel): Coroner postmortems card Read-only postmortems list under Business → Programs — incident, root cause, failed stage, process change; nothing to approve, the process-change artifact (a draft playbook) rides the existing curation queue. * feat(board): Sentinel — Auditor drift-watch quality reports Weekly org-scoped cycle: a solo Auditor spawn receives a server-assembled drift context (waived-findings trend, open findings by severity, conventions-violation hotspots, top spend — all capped, pure ORM) and files one propose_quality_report: headline, 1-7 area-validated items with evidence and suggested actions, overall assessment. Report semantics — complete-at-propose, cycle auto-closes, CEO notified display-only (never on Telegram's approve/reject surface); items are structured so a later convert-to-task control is cheap. Integration adopts Sentinel's module- level dict-dispatch for board-program routing (xenon-driven), folding all prior programs in; app router mounting extracted to a helper for the same budget. * feat(panel): Quality Reports tab (read-only) Business page gains the Sentinel quality-reports tab — headline, per-area observations with evidence and suggested actions; read-only, a report has nothing to approve. * feat(board): Spackle — gap-fill audit program Biweekly project-scoped PO cycle over the half-shipped surface area: API routes without panel surfaces (and vice versa), armed flags without docs, docs promises the code doesn't keep, dead-end tabs — the inventory diffing is the PO's own read-tool work, ordered by the spawn prompt with file:line citations required; the server injects only prior-cycle LEARN and the rotation target. Rotation is now a shared module-level helper (pick_rotation_target, parameterized by source) both project-scoped engines use — pest_control delegates to it, behavior-identical, with a cross-pollution test proving the two programs' rotations stay independent. propose_gap_fill mirrors the bug-hunt verb (≤5 items, two-sided evidence required, participation gate); per-item CEO decide materializes BACKLOG source=spackle tasks; full Telegram kind incl. approve/reject handlers. All seven program routers now mount from one helper. * feat(panel): Spackle gap-fill review queue Command Center gains the gap-fill queue mirroring the pest-control one — per-item approve/reject with the two-sided gap evidence rendered. * feat(board): Scales — monthly portfolio rebalance Org-scoped PO cycle over the stale backlog: the spawn receives a capped stale-task snapshot (BACKLOG/PENDING unclaimed >30 days) plus the charter and prior-cycle LEARN, and files one propose_rebalance — 1-7 items, each a resolvable task_ref with action reprioritize (validated new priority) or cancel, rationale required. Per-item CEO decide: approve EXECUTES the action (audited priority update, or the normal cancel path) — the first program whose materializer mutates existing tasks instead of creating them; reject records the reason; LEARN by exploration task id; all-terminal completes the cycle. Full Telegram decide-kind wiring. Integrated as the eight-program union (registry, dict dispatch, routers helper, teardown enumerations). * feat(panel): Scales rebalance review queue Command Center gains the rebalance queue — per-item approve/reject with the action, target task, and rationale rendered. * feat(board): Mirror — quarterly positioning audit Project-scoped HoM cycle over messaging surfaces: README claims vs shipped reality, docs-site promises vs code, charter alignment — the audit is the HoM's own read-tool work with citations required; the server injects the charter, prior-cycle LEARN, and the shared rotation target. propose_ messaging_fixes mirrors the gap-fill verb (≤5 items, drift evidence naming claim + contradicting reality, participation gate); per-item CEO decide materializes BACKLOG source=mirror documentation tasks; full Telegram decide-kind wiring. Nine-program union across the shared surfaces. * feat(panel): Mirror messaging-fixes review queue * feat(board): Megaphone — HoM standing editorial calendar Cron cycle (3 days, org-scoped, gated on X credentials — drafting content nobody can post is pointless): the HoM receives a shipped-this-week digest plus Unreleased changelog bullets and files one propose_editorial_post (angle-validated, ≤280, brand voice) that materializes a held x_editorial draft through the SAME X-queue origination chokepoint release posts use — zero new approval surface, notifications and CEO decide for free. Complete-at-propose; cycle auto-closes. Ten-program union. * feat(panel): x_editorial source labels in the X queue surfaces * feat(board): Librarian — proactive playbook mining Biweekly org-scoped Auditor cycle: mines recurring non-private learning journals (≥2-count grouping with a recency fallback) against the existing playbook-title inventory and files one propose_playbook_drafts — 1-3 drafts, each with the repeated-pattern evidence that justifies it, duplicate titles rejected in-batch and against the live store. Drafts are created via PlaybookService directly (the Coroner precedent — the 'auditor curates but never drafts' do-verb invariant stays intact and tested) and land in the normal pending-curation queue the Auditor's own triage already surfaces; no new panel surface. Complete-at-propose; display-only CEO notification. Eleven-program union. * feat(board): War Room — release campaign planning EVENT program with a REAL originator (unlike coroner's stub): a release publish hooks a campaign brief beside the release-post seam, and the CEO's run-now originates on demand — the cron loop never fires it. The HoM designs a 2-6 post arc (teaser → launch → follow-up → spotlight; 280-cap, future strictly-ascending publish_after, stage vocabulary) and one propose_campaign call materializes each post as a held x_campaign draft through the X-queue chokepoint. V1 is manual-cadence by design: publish_ after renders as queue guidance and the CEO approves each post at its moment — nothing auto-posts, ever; the auto-schedule upgrade is a documented ceiling. Twelve-program union: full registry complete. * feat(panel): x_campaign labels + publish-after guidance in the X queue * feat(board): Barfly — adjacent-conversation replies Cron cycle (2 days, org-scoped, X-credentials gated): the engine searches X for conversations where RoboCo is relevant but unmentioned (new OAuth- signed search_recent on the client; queries + candidate cap configurable), screens every fetched tweet through the injection guard (stored unclamped — a clamp was truncating the candidate under the envelope, caught by the dev's own tests), dedupes via the existing x_seen_mentions ledger (no migration; also prevents double-drafting against the mentions poll), and opens one held HoM exploration carrying the screened candidates. propose_ conversation_replies enforces candidate-id-only replies (≤5, 280-cap); each materializes a held x_barfly draft through the X-queue chokepoint, threaded via a new in_reply_to seam on post_tweet that only x_barfly drafts use. The X redraft machinery is now dict-dispatch over per-source extractors with reply-ref carry for x_barfly. Thirteen-program registry. War Room's test fakes gained the new abstract search_recent stub. * feat(board): Dogfood — the PO walks the product The fourteenth and final registry entry, completing the catalog. EVENT program (release-publish hook beside the war-room hook + CEO run-now, both through the same real originator; the cron loop never fires it), project- scoped with shared rotation. The permission surface is the careful part: the PO's dogfood spawn — and ONLY that spawn — gets the Playwright MCP mounted, via a task-scoped fail-closed probe mirroring the video-authoring precedent (a PO spawned for roadmap/pest/scales never sees browser tools; tested both ways); the PM agent image bakes chromium unconditionally like the ux image, the mount stays task-gated in code. The walk targets the rotation target's live surfaces (panel_base_url only when the target is the org's own project, honest degradation otherwise); propose_friction_ fixes files ≤5 walked-path-evidenced items; per-item CEO decide materializes BACKLOG source=dogfood tasks; full Telegram decide kind. Also: megaphone/librarian/war_room arming keys restored to the settings validator — their panel toggles would have been rejected (dropped in earlier unions; the same silent-arming class the drill killed once already). * feat(panel): Dogfood friction review queue * chore(board): final whole-branch sweep fixes The night's closing adversarial pass over the integrated fourteen-program registry found ONE functional defect — the war-room test fakes' post_tweet predated Barfly's in_reply_to_tweet_id kwarg (LSP violation, the only red in an otherwise fully green gate) — plus doc/test drift, all fixed: the source-parity test completes to fourteen (spackle/mirror were silently absent while its neighboring comment claimed full coverage), the PO identity doc gains its missing Dogfood verb, the auditor quick-list gains propose_postmortem, three stale comments corrected (rotation docstring, panel registry header, X source enumerations), the dogfood release-hook gains the exception-swallow test its four sibling hooks already had, and the CHANGELOG's Unreleased section documents the whole Board Programs train. Full make quality: exit 0, all gates green. * docs: full documentation sweep for the Board Programs train CLAUDE.md's roadmap-engine entry superseded by the Board Program registry entry (all fourteen programs, arming, scoping, LEARN, guardrails) with the role verb tables and playwright row refreshed; docs/rag gains the agent- facing architecture doc plus full propose_* call-shape sections in the three board role docs, and corrects the strategy-engine section to shipped reality (only idle→roadmap is wired); docs/map covers the registry + all twelve engines with flags, gotchas, and drift notes. The 0.27.0 reference inventory confirmed only the release-executor's canonical set carries the version — left for the 0.28.0 cut. * feat(board): human titles + descriptions on every program surface Raw registry keys rendered as bare panel labels — an operator reading x_feature had no idea what enabling or running it does. The registry dataclass gains title/description (test-enforced non-empty for every entry, unique titles), the API passes them through, and every surface renders title-with-description-tooltip instead of the key: the Programs card (label, toggle hint, run-now toast), and the project settings participates-in/excluded-from checkboxes. --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com>
96 lines
13 KiB
Markdown
96 lines
13 KiB
Markdown
# Board Program Registry
|
|
|
|
## What It Is
|
|
|
|
Fourteen periodic/event-driven origination cycles — the Board actually doing strategic work instead of only reviewing it — ride one generic registry + engine instead of bespoke per-engine loops. `BoardProgram` (`roboco/foundation/policy/board_programs.py`) is a frozen registry entry; `PROGRAMS` holds all fourteen. `BoardProgramEngine` (`roboco/services/board_programs.py`) is the shared trigger/dedup/originate/LEARN machinery every entry rides. Every artifact any program produces is HELD — the CEO is the only path to materialization. Nothing auto-starts, auto-posts, or auto-merges.
|
|
|
|
The lifecycle is uniform across every program:
|
|
|
|
```
|
|
TRIGGER → EXPLORE → PROPOSE → DECIDE → MATERIALIZE → LEARN
|
|
(loop) (solo (one verb (CEO (per-program (outcome fed to
|
|
spawn, call, queue, materializer) next cycle's
|
|
read-only held) per-item) exploration prompt)
|
|
```
|
|
|
|
## The fourteen programs
|
|
|
|
| Key | Role | Trigger | Scope | Source marker | Proposal verb | Materializer |
|
|
|-----|------|---------|-------|----------------|----------------|---------------|
|
|
| `roadmap` (Printer) | product_owner | cron, weekly | org | `board_roadmap` | `propose_roadmap` | backlog tasks, per-item CEO decision |
|
|
| `pest_control` (Pest Control) | product_owner | cron, weekly + rework-spike metric | project | `board_pest_control` | `propose_bug_hunt` | backlog tasks, per-item CEO decision |
|
|
| `spackle` (Spackle) | product_owner | cron, biweekly | project | `board_spackle` | `propose_gap_fill` | backlog tasks, per-item CEO decision |
|
|
| `scales` (Scales) | product_owner | cron, monthly | org | `board_scales` | `propose_rebalance` | mutates a LIVE task in place (reprioritize/cancel) on approval — never creates a task |
|
|
| `dogfood` (Dogfood) | product_owner | event (release-publish hook or CEO run-now) | project | `board_dogfood` | `propose_friction_fixes` | backlog tasks, per-item CEO decision |
|
|
| `periscope` (Periscope) | head_marketing | cron, weekly | org | `board_periscope` | `propose_market_brief` | held report only, no task, no per-item decision |
|
|
| `megaphone` (Megaphone) | head_marketing | cron, every 3 days | org | `board_megaphone` | `propose_editorial_post` | held X draft (existing X queue) |
|
|
| `mirror` (Mirror) | head_marketing | cron, quarterly | project | `board_mirror` | `propose_messaging_fixes` | backlog docs tasks, per-item CEO decision |
|
|
| `barfly` (Barfly) | head_marketing | cron, every 2 days | org | `board_barfly` | `propose_conversation_replies` | held X draft per reply (existing X queue) |
|
|
| `war_room` (War Room) | head_marketing | event (release-publish hook or CEO run-now) | org | `board_war_room` | `propose_campaign` | N held X drafts as one batch (existing X queue) |
|
|
| `x_feature` (feature spotlight) | head_marketing | cron, default daily | org | `x_feature_exploration` | `propose_feature_spotlight` | held X draft (existing X queue) |
|
|
| `coroner` (Coroner) | auditor | event only — no cron | org | `board_coroner` | `propose_postmortem` | a held process-change item, or a playbook drafted directly when `process_change.kind='playbook'` |
|
|
| `librarian` (Librarian) | auditor | cron, biweekly | org | `board_librarian` | `propose_playbook_drafts` | 1-3 DRAFT playbooks via `PlaybookService` directly, into the same curation queue |
|
|
| `sentinel` (Sentinel) | auditor | cron, weekly | org | `board_sentinel` | `propose_quality_report` | held report only, no task, no per-item decision |
|
|
|
|
`roadmap` and `x_feature` predate the registry; migrating them onto it was deliberately behavior-identical (Phase 1). The other twelve are new (Phase 2/3).
|
|
|
|
## Enable/Disable — no master flag
|
|
|
|
Unlike most feature-flagged subsystems, there is **no `ROBOCO_BOARD_PROGRAMS_ENABLED`**. Every program is armed independently through `program_armed(session, key)` — THE single chokepoint every origination path routes through (the cron loop, the metric-predicate check, the CEO's "run now", the strategy-engine idle trigger). It reads a settings-store row `board_program.{key}.enabled`; only `roadmap` and `x_feature` fall back to a legacy env flag (`ROBOCO_ROADMAP_ENGINE_ENABLED`; `ROBOCO_X_ENGINE_ENABLED` AND `ROBOCO_X_FEATURE_SPOTLIGHT_ENABLED`) when no settings-store row exists yet. Every other program is settings-store-only and defaults **off** — a fresh deployment originates nothing until the CEO flips a toggle on the Board Programs panel page.
|
|
|
|
The one env knob among the twelve new programs: `ROBOCO_PEST_REWORK_THRESHOLD` (default `0.3`) — the 7-day rework rate above which Pest Control's metric predicate opens a cycle off-schedule, on top of its own weekly cron. No other new program has a compose-level setting; per-program cadence overrides (when set) also live in the settings store, not env.
|
|
|
|
## Scope and dual-polarity project participation
|
|
|
|
`projects.board_programs` (migration `088`, nullable jsonb list of strings) governs which projects a program runs against or outputs into:
|
|
|
|
- **`scope="project"`** programs (they read one repo: Pest Control, Spackle, Dogfood, Mirror — see the table above) need an **affirmative opt-in**: the plain key (`"pest_control"`) must be present in the list, or the program has no opted-in project and a cycle is never even opened (`_scope_gate`). Null/absent = out.
|
|
- **`scope="org"`** programs (they read the org's own process or the external market: roadmap, Scales, Periscope, Megaphone, Barfly, War Room, Coroner, Librarian, Sentinel, x_feature) run **org-wide by default** and are excluded per-project only by the opposite-polarity entry: `"!roadmap"` opts a project OUT of that program's output. Null/absent = in.
|
|
|
|
One pure helper, `project_participates(program, board_programs_field)`, implements both polarities; `validate_board_programs_field` rejects an unknown key, a meaningless `"!"` on a project-scoped key, or a meaningless plain key on an org-scoped key. Panel: the project settings page's budget/ops card renders project-scoped programs as "participates in" checkboxes and org-scoped programs as "excluded from" checkboxes.
|
|
|
|
## The engine mechanics
|
|
|
|
`BoardProgramEngine.run_due_programs` (called by the orchestrator's `_board_program_loop` on a floor interval — the shortest registered cadence, clamped 300s-3600s) walks every CRON program: enabled → scope-gated → dedup-checked against the `board_program_cycles` ledger (migration `087`; one row per cycle, `closed_at IS NULL` = open, auto-closed the moment its exploration task goes terminal) → cron-due (`program_due`) → originate via the program's `_ORIGINATORS` callable (each program's own engine's `run_cycle`, e.g. `PestControlEngine.run_cycle`) → record the cycle row. It then separately runs every registered metric predicate (`_METRIC_PREDICATES`, today only Pest Control's rework-spike check) — cheap gates (scope, dedup) run BEFORE the predicate itself, so a multi-query metric check never runs on a tick that was always going to be rejected.
|
|
|
|
`open_program_cycle(key)` is the same enabled+scope+dedup path minus the cron-due check — the seam the CEO's panel "run now" button and the Strategy Engine's `idle` trigger both use (`docs/rag/architecture/company-layer.md`). **Only Printer is wired to the strategy-engine idle trigger** — the design intent to also trigger Coroner off `stranded_blocked` was not built; Coroner is event-only, triggered exclusively by its own three hooks (see below).
|
|
|
|
Every exploration is a **solo one-shot spawn** — the board dispatcher's `_dispatch_board_program_exploration` (a dict-dispatch table keyed by `task['source']`) routes it to a dedicated one-shot dispatcher (e.g. `_dispatch_pest_control_exploration`) that bypasses the two-reviewer board-review gate (`_handle_board_assigned_task`) entirely — a program cycle has exactly one author, never a PO+HoM pair. Every dispatcher reuses the `_board_dispatched` one-shot tracker + respawn breaker. Every program source is in the dispatchers' skip bucket (`_is_non_dev_dispatch_source`) — a program exploration task is never mistaken for delivery work.
|
|
|
|
### Coroner's event hooks
|
|
|
|
Coroner is the one program with `trigger=event` AND a real trigger wired outside the loop (unlike `war_room`, whose event trigger IS also reachable through `open_program_cycle` for a CEO on-demand run — Coroner has no on-demand path, only incidents). Three chokepoints call `CoronerEngine.open_for_incident(task_id, kind=...)` directly:
|
|
|
|
- `TaskService`'s bounce transition — a task crossing into `needs_revision` for the 3rd+ time (`revision_count >= 3`), `kind="bounced"`.
|
|
- `TaskService`'s cancel path — a task cancelled after real work had started, `kind="cancelled"`.
|
|
- The orchestrator's budget-block path — a task blocked on a budget breach, `kind="budget"`.
|
|
|
|
Only one autopsy is open at a time (the same `board_program_cycles` dedup every cron program uses); a second incident firing while one is open waits.
|
|
|
|
### War Room and Dogfood's release hooks
|
|
|
|
`WarRoomEngine.open_for_release(...)` and the release-publish path both bypass `_ORIGINATORS` entirely and open a cycle directly, mirroring Coroner's `open_for_incident` shape — War Room's release brief carries the version + curated highlights so posts never invent a feature; a CEO on-demand run (blank brief) instead rides the ordinary `open_program_cycle("war_room")` path. Dogfood similarly has a real `_ORIGINATORS["dogfood"]` binding (unlike Coroner's always-`None` stub) — a walk needs no external incident id, just the next opted-in project in rotation, so both the release-publish hook and a CEO "run now" open a cycle through the ordinary path.
|
|
|
|
### Rotation for project-scoped programs
|
|
|
|
Pest Control, Spackle, Mirror, and Dogfood share one round-robin picker, `pick_rotation_target`: among a program's opted-in projects, never-explored beats explored, else the oldest `last_opened_at` wins (read from the programs' own exploration tasks, not the LEARN ledger — a project-scoped program can run its engine's `run_cycle` directly, outside `BoardProgramEngine`, so the ledger alone would be blind to some cycles).
|
|
|
|
## LEARN
|
|
|
|
`BoardProgramEngine.record_decision(program_key, item_ref, verdict, reason, exploration_task_id=...)` accrues one CEO approve/reject onto the cycle row's `decisions` jsonb column, incrementing `items_proposed`/`items_approved`/`items_rejected`. `prior_cycle_context(program_key, limit=2)` renders the last two CLOSED cycles ("proposed N, approved N; rejected: item — reason") for injection into the NEXT cycle's exploration prompt — every producer of a per-item decision (`RoadmapService`, `PestControlService`-equivalent per-program services) calls this, so a program stops re-proposing something the CEO already rejected without explanation. This is the one genuinely new pipeline stage the registry introduced; the pre-registry roadmap/spotlight engines had no memory of prior outcomes at all.
|
|
|
|
## Panel and API
|
|
|
|
`GET /api/board-programs` and `POST /api/board-programs/{key}/run-now` (`roboco/api/routes/board_programs.py`, CEO-only, `require_ceo_role`) back the Board Programs page (Business section, `board-programs-card.tsx`): each program's live enablement, trigger kind, scope, opted-in project slugs, last-run timestamp, whether a cycle is currently open, and the most recent closed cycle's summary — plus a `Switch` that writes `board_program.{key}.enabled` through the generic feature-flag settings endpoint and a "Run now" button (disabled while a cycle is already open) that calls `open_program_cycle` off-schedule. `run-now` 404s on an unregistered key and 409s when the program is disabled, already has an open cycle, or (a project-scoped program) has no opted-in project — the three collapse into one `None` result with no finer-grained distinction available to the caller.
|
|
|
|
Per-program held artifacts reuse existing queues where the shape matches — the roadmap review queue, the X post queue (Megaphone/Barfly/War Room/spotlight all land there) — rather than growing a new panel surface per program; reports (Periscope, Sentinel) and process-change items (Coroner) and the playbook curation queue (Librarian) are the only genuinely distinct surfaces.
|
|
|
|
## Related
|
|
|
|
- CLAUDE.md's "Board Program registry" entry — the condensed architectural summary.
|
|
- `docs/rag/architecture/company-layer.md` — the Strategy Engine's `idle` → Printer trigger.
|
|
- `docs/rag/architecture/x-engine.md` — the X held-draft queue every X-bound program (Megaphone/Barfly/War Room/spotlight) materializes into.
|
|
- `docs/rag/architecture/review-findings.md` — the findings ledger Pest Control reads.
|
|
- `docs/rag/roles/auditor.md` — the playbook curation queue (`approve_playbook`/`reject_playbook`/`archive_playbook`) Coroner and Librarian both feed.
|
|
- `docs/rag/roles/product-owner.md` / `docs/rag/roles/head-marketing.md` / `docs/rag/roles/auditor.md` — each role's exact `propose_*` call shape and when it fires.
|