@deftai/directive-content 0.91.0 → 0.92.0

package/skills/deft-directive-review-cycle/SKILL.md

@@ -55,7 +55,7 @@ On repos with `.deft/core/` installed, **PR shepherding intent** routes here --
 On OpenClaw hosts with Directive installed (`.deft/core/` or equivalent content deposit), **babysit / shepherd / watch** intent likewise routes here -- not host-local freestyle poll loops and not OpenClaw `cron` alone.
 
 - ! When the OpenClaw tool surface exposes `sessions_spawn`, Approach 1 is the **default** babysit path: spawn a background review-monitor via `sessions_spawn` (register with `--platform-primitive sessions_spawn` or the alias `openclaw-sessions-spawn`).
-- ! Prefer a **visible** Control UI subagent when OpenClaw Control UI is the operator control plane so humans can inspect the monitor.
+- ! Prefer a **visible** Control UI subagent (`visible:true` when the tool surface allows) when OpenClaw Control UI is the operator control plane so humans can inspect the monitor (#3044; invisible empty settles are higher FC04 residual risk).
 - ! Long review-monitor ownership (>~3 min) MUST NOT block the parent OpenClaw session — background `sessions_spawn` + parent yield; same Gap D rule as Cursor/Grok Build (#1880).
 - ! Prefer deep-think gates inside the monitor via the dual-invoke probe order (#2893): `deft pr:watch` / `deft pr:merge-ready` first, then `task deft:pr:watch` when the Taskfile include is present, then the #2878 gh-only fallback — bare `task pr:watch` is not the consumer form.
 - ⊗ Treat OpenClaw `cron` (or any host scheduler alone) as Approach 1. Cron/timer re-invocation is Approach 2 only when `sessions_spawn` is unavailable.
@@ -362,7 +362,7 @@ Remediation:
 
 ! **Heartbeat contract for Cursor pollers (#1877 / #1166 / #2876):** OpenClaw sessions_spawn pollers share this contract. A Cursor `Task` or OpenClaw `sessions_spawn` review-monitor poller whose loop runs > ~3 min MUST honour the sub-agent heartbeat contract (`docs/subagent-heartbeat.md`), same as the `spawn_subagent` path — emit periodic progress so the parent can distinguish a live poller from a hung one.
 
-~ **Visible Control UI (OpenClaw):** When OpenClaw Control UI is the operator control plane, SHOULD spawn the review-monitor as a **visible** subagent so humans can inspect progress without attaching to the parent session.
+~ **Visible Control UI (OpenClaw / #3044):** When OpenClaw Control UI is the operator control plane, SHOULD spawn the review-monitor with `visible:true` when the tool surface allows so humans can inspect progress without attaching to the parent session; invisible empty settles are higher FC04 residual risk.
 
 ! When the platform descriptor indicates Tier 1 (sub-agent support), spawn a review-monitor sub-agent using the primitive matching the descriptor:
 
@@ -374,6 +374,51 @@ Remediation:
 
 ⊗ Use OpenClaw `cron` alone as Approach 1 when `sessions_spawn` is available — cron is Approach 2 scheduler fallback only (#2876).
 
+### Empty announce ≠ done (parent DoD) (#3044 / FC04 residual)
+
+! When a review-monitor settle arrives with **empty body**, **missing `STATUS:` line**, or **status unknown** (including host `(no output)` / empty `subagent_announce`):
+
+1. ! The parent MUST run **same-turn ground truth** before any DONE / CLEAN / merge-ready claim: at least `gh pr view <N>` (or REST `pulls/<N>`), `gh pr checks <N>`, and current HEAD SHA (`gh api repos/<owner>/<repo>/pulls/<N> -q .head.sha`).
+2. ! Classify the settle as **FC04 residual** (empty babysit ≠ done) until ground truth shows a terminal merge/close outcome **or** an explicit structured `BLOCKED` / `FAILED` handback.
+3. ⊗ Treat empty / unknown settle as `DONE`, `CLEAN`, merge-ready, or batch-complete.
+4. ⊗ Spawn a second review-monitor solely because the first settle was empty/unknown without completing the ground-truth batch first (#3044 dual-lease recurrence).
+
+~ Recurrence: enterprize PR #43 (2026-08-02) — first monitor polled live, host settled empty/unknown; parent spawned a second same-`taskName` monitor; dual lease collision while PR stayed open. See also `meta/lessons.md` and FC04 / growth friction R1 + R10.
+
+### Single review-monitor lease (#3044 / #2814)
+
+! **One sticky lease per PR:** ownership is the single sticky GitHub PR comment `<!-- deft:review-owner -->` (or the dual-invoke `review-monitor:register` form that writes it). Parallel ownership is forbidden.
+
+! **Pre-spawn check:** before launching another Approach 1 review-monitor (`sessions_spawn`, `spawn_subagent`, Cursor `Task`, `start_agent`):
+
+1. ! Read the sticky lease (dual-invoke `verify:review-monitor` when available, else `gh api` issues comments for `<!-- deft:review-owner -->`).
+2. ! List active same-PR / same-`taskName` subagents when the host exposes that surface (OpenClaw `subagents list` or equivalent).
+3. ⊗ Spawn a second monitor while a prior owner is **running**.
+4. ⊗ Spawn a second monitor when the last settle was **empty/unknown** and ground truth has **not** shown a terminal merge/close (or explicit structured handback that releases ownership).
+5. ! If the prior owner is **dead** (liveness fail / `REDISPATCH_OK` / `verify:subagent-alive` exit 1) and the PR is still open: spawn **one** replacement monitor and re-claim the lease with **`--force`** (CLI: `deft review-monitor:register --pr <N> --monitor-agent-id <id> --force` / task: `task review-monitor:register -- --pr <N> --monitor-agent-id <id> --force`, or host equivalent force takeover) so a non-expired foreign lease does not block replacement — then **update** the sticky lease comment to the new owner. Never silent dual ownership.
+6. ! On register conflict when the prior owner is **still alive**: attach to the existing owner or stop — do not parallel-fix.
+7. ⊗ Refuse replacement of a dead owner solely because the 30-minute lease has not expired without attempting force takeover (#3044).
+
+### Required non-empty monitor handback (#3044)
+
+! Approach 1 review-monitor prompts (including `templates/swarm-greptile-poller-prompt.md` and any host-filled spawn prompt) MUST require a **non-empty** final handback with these fields:
+
+```text
+STATUS: DONE|BLOCKED|FAILED
+HEAD: <sha>
+CHECKS: <summary>
+MERGE: <url|error|n/a>
+ISSUE: <closed|open|n/a>
+NOTES: <short>
+```
+
+⊗ Empty final assistant message from a review-monitor.
+⊗ Parent treating a settle that lacks `STATUS:` as success.
+
+~ **Visible Control UI risk (#3044):** When OpenClaw Control UI is the operator plane, prefer `visible:true` on the review-monitor spawn; invisible empty settles are higher risk for FC04 misclassification. Cross-link: `skills/deft-directive-swarm/references/host-openclaw.md` Babysit / review-monitor residual.
+
+
+
 **Approach 2 (fallback -- no sub-agent primitive for the descriptor):**
 
 ! When the platform descriptor indicates no sub-agent orchestration (or the primitive is unavailable), use discrete tool calls with a yield between checks. For `grok-build` / spawn_subagent descriptor this path is normally avoided in favor of Approach 1; it exists for pure interactive or limited runtimes.
@@ -566,3 +611,6 @@ task lifecycle:event -- emit plan:approved \
 - ⊗ Activate Approach 3 (blocking `Start-Sleep` loop) without first warning the user that it will lock the conversation pane and receiving confirmation
 - ⊗ Exit the review loop on a Greptile confidence number alone while the check run is non-terminal -- a confidence score is NOT a verdict without a terminal check-run (`completed` + `{success, neutral}`) AND a HEAD-matching `Last reviewed commit:` completion marker (#1259)
 - ⊗ Call `gh pr merge` on cached/earlier review state without an immediately-preceding pre-merge re-poll that re-satisfies the Step 6 fail-closed all-of (#1259)
+- ⊗ Treat empty/unknown review-monitor settle as DONE/CLEAN/merge-ready without same-turn ground truth (#3044 / FC04 residual)
+- ⊗ Spawn a second review-monitor while prior owner is running or last settle was empty/unknown without terminal ground truth (#3044)
+- ⊗ Accept empty review-monitor final message missing STATUS/HEAD/CHECKS/MERGE handback (#3044)

package/skills/deft-directive-setup/SKILL.md

@@ -23,6 +23,7 @@ Legend (from RFC2119): !=MUST, ~=SHOULD, ≉=SHOULD NOT, ⊗=MUST NOT, ?=MAY.
 - User says "set up deft", "configure deft", or "bootstrap my project"
 - User asks to create USER.md, PROJECT-DEFINITION.xbrief.json, or a specification
 - User clones a deft-enabled repo for the first time with no config
+- User says "revisit experimental rules", "toggle experimental meta", "enable SOUL", "disable morals", or wants to change Experimental Rules after bootstrap (#46)
 
 ## Opt-out flag (`.no-deft-directive`) (#2926)
 
@@ -194,12 +195,28 @@ VBA (Excel macros), VHDL, Visual Basic (.NET), Zig, 6502-DASM
 2. ! If `deft_version` is present but **differs from the current framework version** (0.20.0): check whether any expected fields are missing from the USER.md
 3. ! If fields are missing: query the user for each missing field individually -- do NOT re-run the full Phase 1 interview
 4. ! After completing any field queries (even if none were needed), write the current `deft_version` (0.20.0) to USER.md
-5. ~ If `deft_version` matches the current version and all expected fields are present: no action needed (USER.md is fresh)
+5. ~ If `deft_version` matches the current version and all expected fields are present: USER.md is fresh — do **not** re-run Phase 1. ! Still offer the **Returning-user re-entry** menu below so the operator can revisit Experimental Rules or continue to Phase 2 without a full re-interview (#46).
 
 Expected USER.md fields: **Name**, **Custom Rules**, **Default Strategy**, and optionally **Coverage** and **Experimental Rules**.
 
 ⊗ Re-run the full Phase 1 interview when only individual fields are missing from a stale USER.md -- query missing fields individually instead.
 
+### Returning-user re-entry (#46)
+
+! When USER.md already exists (fresh or after individual missing-field fill), present a deterministic numbered menu before assuming Phase 1 is "done and silent":
+
+> "USER.md is in place. What next?"
+> 1. Continue to Phase 2 (project configuration) ★ (recommended when project config is still missing)
+> 2. **Revisit experimental rules** — enable/disable SOUL / morals / code-field without hand-editing schema
+> 3. Not now (exit setup)
+> 4. Discuss
+> 5. Back
+
+- ! Final two numbered options MUST be `Discuss` and `Back` per [`../../contracts/deterministic-questions.md`](../../contracts/deterministic-questions.md)
+- ! On option 2, enter **Revisit experimental rules** (next section) — not a full Phase 1 re-interview
+- ⊗ Silently skip past a complete USER.md with no re-entry offer when the operator entered setup (or asked to configure preferences)
+- ⊗ Invent a `deft config` / `task config:*` verb family for this slice — setup skill re-entry is the product surface (#46)
+
 ### Interview Rules
 
 ! This phase follows the deterministic interview loop defined in `skills/deft-directive-interview/SKILL.md`. The core rules (one question per turn, numbered options with stated default, explicit "other" escape, depth gate, default acceptance, confirmation gate, structured handoff) apply here. Key points repeated for emphasis:
@@ -307,6 +324,89 @@ for project-scoped settings (strategy, coverage).
 
 ---
 
+## Revisit experimental rules (#46)
+
+**Goal:** Guided enable/disable of USER.md **Experimental Rules** entries that *reference* framework deposit meta files (`meta/SOUL.md`, `meta/morals.md`, `meta/code-field.md`). This is a post-bootstrap return path — not Phase 1 bootstrap, not a general preferences UI, and not an editor for framework meta file bodies.
+
+### When to enter
+
+- Returning-user re-entry option **Revisit experimental rules**
+- Direct user ask: "revisit experimental rules", "toggle experimental meta", "turn on SOUL", "disable code-field", etc.
+- USER.md exists and is complete enough to edit (Name present); missing non-meta fields still use Freshness Detection individual queries first
+
+### Out of scope
+
+- ⊗ General preferences UI / rewriting Personal or Defaults sections as part of this path
+- ⊗ Editing framework `meta/*.md` content (deposit owns SOUL / morals / code-field bodies; `directive update` refreshes deposit)
+- ⊗ Deposit layout changes
+- ⊗ Inventing a full `deft config` mega-surface or new `task config:*` verb family for this slice
+- ⊗ Re-building USER.md bootstrap / non-overwrite semantics
+- ⊗ Treating Experimental Rules lines as project-local copies of meta files — they are **references** only
+
+### Flow
+
+! **Each message MUST contain exactly ONE question** (same interview rule as Phase 1).
+
+1. ! Resolve USER.md via Platform Detection (`$DEFT_USER_PATH` → platform path). Read the file as **UTF-8**.
+2. ! Parse current Experimental Rules state (on/off) for the three paths:
+   - `meta/SOUL.md`
+   - `meta/morals.md`
+   - `meta/code-field.md`
+   - Detection: any line containing that path counts as **on** (custom wording still counts).
+3. ! Show a **current state** summary (table or short list), for example:
+
+   | Entry | State | Role |
+   |-------|-------|------|
+   | SOUL.md | on/off | Results-first agent persona |
+   | morals.md | on/off | Epistemic honesty |
+   | code-field.md | on/off | Pre-code assumption protocol |
+
+4. ! Ask which entry to change with a deterministic numbered menu (one question). Options MUST include each of the three entries as toggle targets, plus **Done (save)** / **Done (discard)**, and final two options `Discuss` and `Back`:
+
+   > "Toggle which experimental meta entry? (current state shown above)"
+   > 1. SOUL.md — currently {on|off}
+   > 2. morals.md — currently {on|off}
+   > 3. code-field.md — currently {on|off}
+   > 4. Done — save changes
+   > 5. Done — discard changes
+   > 6. Discuss
+   > 7. Back
+
+5. ! When the user picks an entry (1–3), optionally show the short Phase 1 explainer (steps **5a–5c** copy below), then confirm the new on/off value with a Y/n or numbered keep/flip menu. Update the **in-memory** desired state; do not write yet. Return to the toggle menu (step 4) until Done.
+6. ! On **Done — save**: show a confirmation summary of the three final on/off values and require explicit affirmative (`yes` / `confirmed` / `approve`) before write — same Post-Interview Confirmation Gate strictness.
+7. ! On **Done — discard** or **Back** without save: leave USER.md unchanged and return to the Returning-user re-entry menu (or exit if invoked directly).
+
+### Explainers (reuse Phase 1 steps 5a–5c)
+
+- **SOUL.md** — Results-first agent persona (inspired by Winston Wolf). Enforces assess-before-acting, finish-what-you-start, right-tool-for-the-job, and play-the-long-game. Keeps the AI decisive and concise. Includes a named persona ('Vinston') — drop if you prefer to define your own agent personality.
+- **morals.md** — Epistemic honesty rules. No presenting speculation as fact, label unverified claims, self-correct when wrong. Foundational trust rules for any AI agent. Strongly recommended.
+- **code-field.md** — Pre-code assumption protocol. Requires stating assumptions and naming failure modes before writing a single line. Fights the 'it compiles, ship it' instinct. Based on NeoVertex1 context-field.
+
+### Safe write rules (non-clobber)
+
+! When persisting toggles to USER.md:
+
+1. ! Write **UTF-8** (no BOM). Create parent directories only if the resolved path's parent is missing — never relocate USER.md.
+2. ! Change **only** the `## Experimental Rules` section (add the section if enabling when absent; remove the section when all three are off and no custom bullets remain).
+3. ! Canonical enable lines (match Phase 1 template):
+   - `- ! Use meta/SOUL.md for strategic context and purpose-driven guidance`
+   - `- ! Use meta/morals.md for ethical AI development principles`
+   - `- ~ Use meta/code-field.md for advanced architecture patterns`
+4. ! Disable = remove lines that mention that path. Preserve any **custom** non-meta bullets under Experimental Rules.
+5. ! **Personal** and **Defaults** section bodies MUST remain byte-identical to the pre-write file (non-clobber).
+6. ~ Prefer the pure helper `applyExperimentalRulesState` / `setExperimentalRule` from `@deftai/directive-core` `userConfig` (`packages/core/src/user-config/experimental-rules.ts`) when the package is importable (framework checkout, tests, or a thin local script). When editing by hand as an agent, apply the same rules: section-only edit, UTF-8, path-based match, canonical enable lines.
+7. ! After write, re-read USER.md and show the final on/off state to the user.
+
+⊗ Rewrite the whole USER.md from the Phase 1 template when only Experimental Rules changed
+⊗ Clobber or reformat **Personal** / **Defaults** content while toggling experimental meta
+⊗ Hand-edit framework `meta/SOUL.md`, `meta/morals.md`, or `meta/code-field.md` bodies as part of this path
+⊗ Invent `deft config` / `task config:experimental-*` for this product slice when setup re-entry suffices
+
+### Then
+
+- ! After a successful save (or discard), re-offer the Returning-user re-entry menu (Continue to Phase 2 / Revisit again / Exit / Discuss / Back) unless the user asked only for the toggle and is done.
+- ~ If Phase 2 is already complete, prefer Exit over Continue unless the user wants project reconfiguration.
+
 ## Phase 2 — Project Configuration (PROJECT-DEFINITION.xbrief.json)
 
 **Goal:** Project-specific configuration — tech stack, type, quality standards — written as a xBRIEF file at `./xbrief/PROJECT-DEFINITION.xbrief.json`.
@@ -741,3 +841,6 @@ Per [strategies/interview.md](../../strategies/interview.md#interview-rules-shar
 - ⊗ Present choices through a host UI that replaces the canonical numbers with alphabetic affordances or unlabeled buttons
 - ⊗ Resolve paths relative to the skill file, AGENTS.md, or framework directory instead of the user's pwd at skill entry
 - ⊗ Generate an authoritative PRD.md — PRD.md is a read-only export via `task prd:render`, never a source of truth
+- ⊗ Skip the Returning-user re-entry / Revisit experimental rules path when USER.md exists and the operator entered setup to change experimental meta (#46)
+- ⊗ Clobber Personal or Defaults while toggling Experimental Rules (#46)
+- ⊗ Invent a full `deft config` verb family for experimental meta when setup re-entry suffices (#46)

package/skills/deft-directive-swarm/references/core-ops.md

@@ -92,6 +92,7 @@ CONSTRAINTS:
 
 ## Anti-Patterns
 
+- ⊗ Parent conversation implements or babysits product fix/CI loops for **through merge** / **drive-to: merge-ready** story work when background subagent/worktree dispatch is available — even if cohort size is 1; use the swarm/solo-worker launch path (#3032 / #1880 Gap C)
 - ⊗ Start prompts with context or description instead of an imperative TASK directive
 - ⊗ Use `--mcp` with Warp MCP server UUIDs from standalone (non-Warp) terminals
 - ⊗ Assign overlapping files to multiple agents

package/skills/deft-directive-swarm/references/core-phase-0.md

@@ -4,6 +4,12 @@
 
 ! Before assigning work to agents, build the cohort from the triage queue (queue-driven per #1142 / N2; see Step 0 below), then read project state and plan allocation against the activated cohort.
 
+### Through-merge / N=1 still uses the launch path (#3032)
+
+! When operator intent is **through merge**, **drive to merge**, **land/ship issue**, or explicit **drive-to: merge-ready** for story work, the parent (monitor) conversation MUST NOT implement product code or own the implementation PR as the leaf. Parent MUST run this skill's launch path: worktree isolation when available, worker envelope with `drive-to: merge-ready`, xBRIEF preflight, pre-pr + review-cycle, then merge/`scope:complete` per #1880 Gap C.
+! **Cohort size N=1 is still a cohort for dispatch.** Solo through-merge uses the same swarm/solo-worker launch path as multi-story (`dispatch_kind: solo` or a one-story swarm-cohort). Do not treat "only one issue" as permission for the parent to code.
+⊗ Parent implements, babysits product fix loops, or skips worktree + worker dispatch for through-merge / drive-to:merge-ready work when background subagent/worktree dispatch is available (#3032).
+
 ### Headless cohort fast-path: low-ceremony launch (C1 / #1387)
 
 ! When the operator supplies a **pre-approved cohort** via the **C1** `task swarm:launch` CLI, Phase 0 runs in headless / low-ceremony mode: the per-phase interactive approval gates (the Step 0c promote-fill prompts, the Step 0.5 lifecycle-bridge approval, and the Step 4/5 allocation approval) collapse into a SINGLE consent -- the `## Allocation context` token (#1378) carried in the dispatch envelope. The interactive promote-fill loop (Step 0a -- 0d below) is SKIPPED.

package/skills/deft-directive-swarm/references/host-openclaw.md

@@ -73,6 +73,16 @@ Package install alone does not put always-pins into `~/.openclaw/workspace/skill
 ! Babysit / PR shepherd on OpenClaw remains **Approach 1** via `sessions_spawn` (`skills/deft-directive-review-cycle/SKILL.md`). Cron alone is not Approach 1 (#2874 / #2876).
 ⊗ Regress babysit to main-session `gh` poll + cron when `sessions_spawn` is available.
 
+### Empty announce ≠ done + single lease residual (#3044)
+
+Skill residual of #2874 / #2876 (spawn routing fixed; post-spawn ownership still thrashed). Canonical MUST language lives in `skills/deft-directive-review-cycle/SKILL.md` (`### Empty announce ≠ done`, `### Single review-monitor lease`, `### Required non-empty monitor handback`).
+
+! On empty body / missing `STATUS:` / status-unknown review-monitor settle (`subagent_announce` with `(no output)` included): parent MUST same-turn ground truth (`gh pr view` + `gh pr checks` + HEAD) and MUST NOT treat the settle as DONE/CLEAN/merge-ready — **FC04 residual**.
+! One sticky `<!-- deft:review-owner -->` lease per PR. Pre-spawn: list active same-`taskName` / lease holder. ⊗ Second monitor while prior owner is running **or** last settle was empty/unknown without terminal ground truth. Dead owner + open PR → one replacement + lease update only.
+! Monitor handback MUST be non-empty with `STATUS` / `HEAD` / `CHECKS` / `MERGE` (see review-cycle skill + `templates/swarm-greptile-poller-prompt.md`).
+~ Prefer `visible:true` when Control UI is the operator plane; invisible empty settles raise FC04 misclassification risk.
+~ Recurrence: enterprize PR #43 (2026-08-02) dual-monitor + empty settle.
+
 ## Monitor / completion channel
 
 ! Completion is parent push / announce. Do not poll via Grok Build `get_command_or_subagent_output` or Cursor Task-complete semantics.

package/templates/agent-prompt-preamble.md

@@ -543,9 +543,12 @@ Every worker MUST send a final status message before exiting its tool loop, rega
 
 ! **Thin DONE is not success (#2943):** A terminal message that lacks PR URL / merge evidence (no `PR #N`, no PR URL, no merge confirmation) is a **thin DONE** / failed-leaf signal for the parent monitor — re-dispatch or take over after ground truth. Prefer structured completion fields when the host supplies them (`prUrl`, `mergeStatus`, `emptyDiff`). Workers MUST NOT exit with mid-edit prose and call it `DONE` when the envelope required a PR or merge-ready outcome.
 
+! **Empty announce ≠ done / single review-monitor lease (#3044 / FC04 residual):** An empty settle, missing `STATUS:` line, or `status: unknown` from a review-monitor (`subagent_announce` with `(no output)` included) is **not** DONE/CLEAN/merge-ready. Parent MUST same-turn ground truth (`gh pr view` + checks + HEAD) and MUST NOT spawn a second monitor while the prior owner is running or only falsely settled. Prefer one sticky `<!-- deft:review-owner -->` lease and a non-empty `STATUS`/`HEAD`/`CHECKS`/`MERGE` handback. Full MUST language: `skills/deft-directive-review-cycle/SKILL.md` + OpenClaw host adapter residual.
+
 ! **Parent tool-first after leaf completion (#2943):** When a parent / monitor receives a leaf completion event (`subagent_announce`, parent-push, or host completion notify), its **first response** MUST be a **tool-first** ground-truth batch (`gh` / `git` / worktree or file status) **or** a host **yield** (`sessions_yield` on OpenClaw, or equivalent). ⊗ Multi-sentence progress-only first response with zero tools / yield — the OpenClaw text-repetition hang class (#2943).
 
 ⊗ Treat thin DONE (no PR URL / merge evidence) as success (#2943).
+⊗ Treat empty/unknown review-monitor settle as DONE without same-turn ground truth, or dual-spawn a second monitor while the first lease is live (#3044).
 
 Per-step acks during the run are noise. ONE start message, ONE final message; intermediate messages only on `BLOCKED` / `FAILED`. The final message lets the dispatcher distinguish a clean exit from a silent timeout when the lifecycle event arrives.
 

package/templates/agents-entry.md

@@ -5,6 +5,11 @@ Deft is installed in .deft/core/. Full guidelines: .deft/core/main.md
 
 ! If any .deft/core/.agents/skills/ path referenced in this file cannot be read (missing file, stale path from a previous framework version, or a deprecation redirect stub), read .deft/core/QUICK-START.md instead and follow it. QUICK-START refreshes this section idempotently for the current framework version.
 
+## Temporary test kill-switch (#3039)
+
+! Before further Directive process load, check root `.deft-directive-disable` (presence = flag). If present → stop DD load; recovery = delete file + NEW agent session. Deposit OK; not `.no-deft-directive` (#2926). Docs: `.deft/core/docs/deft-directive-disable.md`.
+⊗ Claim full operation while the flag exists or after delete without a NEW agent session.
+
 ## Session routing (#2176)
 
 ! **Read-only default** until mutation intent: load AGENTS.md / main.md / USER.md / `xbrief/PROJECT-DEFINITION.xbrief.json`; resolve USER.md via `deft session:start` (`USER.md resolved …`; win32 `%APPDATA%\deft\USER.md`; unix `~/.config/deft/USER.md`; ⊗ invent `~/.config/deft` on Windows #2544); confirm Deft alignment + addressing-name; ⊗ no mutable `deft session:start` / triage welcome / sync / branch-policy unless asked or implementation-ready (#2176) — `.deft/core/commands.md` § Session routing. Bootstrap: cold-start → README § Cold-start (#2273) ⊗ never `.deft/core/`; pre-cutover → setup Pre-Cutover (#2068); missing USER.md / PROJECT-DEFINITION → setup Phase 1/2 (#1813) ⊗ before answering; else main → USER → PROJECT-DEFINITION; ~ sync. Mutation → `deft session:start` then `deft verify:session-ritual -- --tier=gated` (#1149). ? `deft session:start -- --read-only` (#2176).
@@ -63,6 +68,11 @@ Legacy `vbrief/` read-accepted; `deft migrate:xbrief` for `xbrief/` (v0.6→v0.8
 ! **Default always-pins:** `deft-directive-build`, `deft-directive-pre-pr`, `deft-directive-review-cycle`, `deft-directive-swarm` — read each `SKILL.md` when that work type starts.
 ⊗ Pin entire language packs, deployment docs, or framework bulk into AGENTS.md — pins are for false-negative-sensitive process gates only (#2508).
 
+## Through-merge worker dispatch (#3032)
+
+! On **through merge** / **drive to merge** / land-ship / **drive-to: merge-ready** story intent: parent MUST dispatch a `drive-to: merge-ready` worker (worktree, preflight, pre-pr, review-cycle, merge/`scope:complete`) via the **swarm/solo-worker launch path** even if **cohort size is 1** — parent MUST NOT implement as the leaf. Depth: swarm Phase 0 + skill-pin-policy (#3032 / #1880 Gap C).
+⊗ Parent conversation implements or babysits product fix/CI loops for drive-to:merge-ready work when background subagent/worktree dispatch is available (#3032).
+
 ## Review-surface precedence (#2308)
 
 ! Route PR shepherding / review work through `deft-directive-review-cycle` — `.deft/core/.agents/skills/deft-directive-review-cycle/SKILL.md`; host `babysit` / `bugbot` / `security-review` advisory-only (#2308 / #2261).

package/templates/swarm-greptile-poller-prompt.md

@@ -426,10 +426,14 @@ Send to parent:
 
     Subject: PR #{pr_number} CLEAN -- ready for merge
     Body:
-      Greptile review on HEAD <sha> is clean.
+      STATUS: DONE
+      HEAD: <sha>
+      CHECKS: <list of CheckRun statuses>
+      MERGE: n/a
+      ISSUE: open
+      NOTES: Greptile CLEAN confidence <N>/5; ready for merge
       Confidence: <N>/5
       Findings: P0=0, P1=0
-      CI: <list of CheckRun statuses>
       Last reviewed commit: <sha>
       -- no more polling, exiting now
 
@@ -445,9 +449,13 @@ If the same review surfaces 3 consecutive review cycles (push -> review -> still
 
     Subject: PR #{pr_number} escalation -- 3 review cycles still surfacing P0/P1
     Body:
-      Three consecutive review cycles after push still surfaced P0/P1 findings.
+      STATUS: BLOCKED
+      HEAD: <sha>
+      CHECKS: see latest findings
+      MERGE: n/a
+      ISSUE: open
+      NOTES: 3 review cycles still surfacing P0/P1; <summary>
       Latest findings: <summary>
-      Latest HEAD: <sha>
       -- no more polling, exiting now
 
 ### (3) ERRORED
@@ -458,7 +466,12 @@ Retry ONCE: post `@greptileai review` as a PR comment via `gh pr comment {pr_num
 
     Subject: PR #{pr_number} Greptile errored -- escalation required
     Body:
-      Greptile errored on HEAD <sha>; retry via @greptileai also errored.
+      STATUS: FAILED
+      HEAD: <sha>
+      CHECKS: Greptile errored (retry also errored)
+      MERGE: n/a
+      ISSUE: open
+      NOTES: escalate per swarm Phase 6 Step 1 (wait / empty retrigger / override)
       Parent should escalate to user with the three-way choice per
       skills/deft-directive-swarm/SKILL.md Phase 6 Step 1:
         (a) wait longer (~15-20 min)
@@ -474,6 +487,12 @@ Send:
 
     Subject: PR #{pr_number} poll cap exceeded -- parent should escalate
     Body:
+      STATUS: BLOCKED
+      HEAD: <sha>
+      CHECKS: <statuses>
+      MERGE: n/a
+      ISSUE: open
+      NOTES: poll cap exceeded; holdout=<which-of-the-five-conditions-failed>
       {poll_cap_minutes}-minute poll cap exceeded.
       Latest state:
         last_reviewed_sha: <sha or "unparsed">
@@ -494,6 +513,12 @@ Increment the `stall_streak` counter introduced under `## CLEAN gate evaluation,
 
     Subject: PR #{pr_number} poll loop wedged -- terminal-condition detection failure
     Body:
+      STATUS: BLOCKED
+      HEAD: <sha>
+      CHECKS: holdout=<which-of-the-five-conditions-failed>
+      MERGE: n/a
+      ISSUE: open
+      NOTES: STALL — detector cannot reach CLEAN or P0/P1; diagnose instrumentation
       Detector cannot reach CLEAN or NEW P0/P1 FINDINGS but no blocking signals
       are visible. Likely terminal-condition detection gap on this PR's review surface.
       Latest state:
@@ -515,6 +540,12 @@ Send:
 
     Subject: PR #{pr_number} informal-clean missing canonical fields -- recovery required
     Body:
+      STATUS: BLOCKED
+      HEAD: <sha>
+      CHECKS: informal-clean missing canonical fields
+      MERGE: n/a
+      ISSUE: open
+      NOTES: #1543 informal-clean; recovery @greptileai or override
       Greptile informal-clean missing-canonical-fields state (#1543).
       Latest Greptile comment says the diff is clean / prior issues resolved,
       but lacks canonical `Last reviewed commit:` and `Confidence Score: X/5`.
@@ -542,6 +573,18 @@ Send:
 - ! Use Python scripts (single `run_shell_command` call) for the poll loop, NEVER shell `Start-Sleep` + repeated tool calls. The Python script handles `time.sleep({poll_interval_seconds})` between polls and exits when a terminal condition fires.
 - ! Always pass `do_not_summarize_output: true` semantics when fetching `gh pr view --comments` -- summarizers silently drop the Outside-Diff section.
 - ! Send a status message to `{parent_agent_id}` at start (acknowledging the task) and at every terminal exit (CLEAN / NEW P0/P1 FINDINGS escalation / ERRORED / TIMEOUT / STALL / INFORMAL-CLEAN). Route it through the host completion channel for your primitive (see Role posture -- OpenClaw `sessions_spawn` uses parent push / announce). Do NOT silently complete.
+- ! **Required non-empty monitor handback (#3044):** every terminal exit message MUST be non-empty and include these structured fields (map CLEAN → `STATUS: DONE`, NEW P0/P1 / INFORMAL-CLEAN / TIMEOUT / STALL → `STATUS: BLOCKED`, ERRORED → `STATUS: FAILED` unless a hard failure):
+
+```text
+STATUS: DONE|BLOCKED|FAILED
+HEAD: <sha>
+CHECKS: <summary>
+MERGE: <url|error|n/a>
+ISSUE: <closed|open|n/a>
+NOTES: <short>
+```
+
+⊗ Empty final assistant message / empty `subagent_announce` body. Parents treat empty or missing-`STATUS` settles as FC04 residual, not success (`skills/deft-directive-review-cycle/SKILL.md` Empty announce ≠ done).
 
 ## Implementation Notes