@deftai/directive-content 0.84.0 → 0.86.0

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

@@ -92,12 +92,60 @@ The release pipeline's Step 9/10/11 git mutations carry the bypass in subprocess
 
 ⊗ Foreground-block the operator chat on reconcile / `ci:local` / `release:e2e` when background dispatch is available (#1880 Gap D / #2692).
 
+### Fixable check failure — file-and-merge before resume (#2859)
+
+! When Step 4 (`task ci:local` or `task check`) fails on a **fixable product or test defect** (hang, failing test, validation bug — not operator env misconfiguration), the release cut MUST pause and route the blocker through normal issue → xBRIEF → feature branch → PR → merge before resuming Phase 1.
+
+? **Step 5 branch-coverage threshold misses** during `task release` (Vitest branch coverage below 85% with no other failure mode) are carved out to § Step 5 branch-coverage threshold — open-issue ledger hatch (#2866) below — not this file-and-merge path.
+
+**Required path:**
+1. File a GitHub issue with root cause, recurrence signature, and acceptance criteria.
+2. Ingest / promote / activate scope xBRIEF; implement on a feature branch with `drive-to: merge-ready`.
+3. Merge; confirm `task check` / `ci:local` is green for the failure mode.
+4. Resume the release cut from Phase 1 (re-run Step 4).
+
+⊗ Lead with an inline-only hotfix on the release branch / default branch without a tracked issue and merged PR.
+⊗ Suggest untracked `--skip-ci` or `--allow-skip-ci` without a **tracked issue number** as the first recovery when the failure is a clear, shippable bug.
+⊗ Continue the cut with "raise timeouts," "fix it here," or other shortcut theater before file-and-merge completes.
+
+? **`--skip-ci` / `--allow-skip-ci=#N` remains valid** only under explicit operator incident review with a **tracked issue** cited on the flag (Phase 4 contract). It is NOT a substitute for filing and merging a fixable defect discovered in Phase 1.
+
+**AGENTS.md bulk rejected (#2859):** Expanding `AGENTS.md` / `content/templates/agents-entry.md` with an always-on pin for this release-phase reminder was considered and **rejected**. This rule lives in the release skill (and optional lesson); do NOT add AGENTS.md / agents-entry bulk for it.
+
+See [`docs/RELEASING.md`](../../../docs/RELEASING.md) § Fixable check failure during release for the operator runbook and the existing `--allow-skip-ci=#N` incident contract.
+
+### Step 5 branch-coverage threshold — open-issue ledger hatch (#2866)
+
+! When **`task release` Step 5** fails on Vitest coverage below the 85% goal, apply this hatch **only** when **branches** is the **sole** metric below 85% (hairline branch miss — lines, functions, and statements all ≥ 85%). Confirm via the Step 5 failure output or `task coverage:hotspots` before hatching. If **any other metric** is also below 85%, or the failure is a hang / failing test / non-coverage defect, STOP — use § Fixable check failure — file-and-merge before resume (#2859) instead.
+
+**Runtime disclosure (#2573):** `--allow-coverage-debt=#N` sets vitest coverage thresholds to zero for the release Step 5 run (`vitest.config.ts`). The hatch is justified only for branch-only hairlines; the filed debt issue MUST require restoring **all four metrics** (lines, functions, branches, statements) to ≥ 85% before close.
+
+**Open-issue ledger (release-scoped only):**
+
+1. Check for an **open coverage-debt tracking issue** (unpaid hatch from a prior cut) — union all three probes and dedupe by issue number:
+   - **Marker search** (new-format debt issues):
+     ```
+     gh issue list --repo <owner>/<repo> --state open --search "coverage-debt in:title,body" --limit 20
+     gh issue list --repo <owner>/<repo> --state open --search "allow-coverage-debt in:body" --limit 20
+     ```
+   - **CHANGELOG citation scan** (legacy hatch issues filed before markers were mandatory): parse `CHANGELOG.md` `[Unreleased]` plus the last three `## [version]` sections for `--allow-coverage-debt=#N` / `allow-coverage-debt=#N` citations; for each `#N`, run `gh issue view N --json state --jq .state` — `OPEN` counts as unpaid debt even when title/body lack the new markers (#2866).
+2. If **no open coverage-debt issue exists** → file `#N` with title prefix `coverage-debt:` and body containing both markers `coverage-debt` and `--allow-coverage-debt`, documenting measured metrics, branch-only trigger, and acceptance criteria (restore **all four** coverage metrics ≥ 85%). Continue the cut with `--allow-coverage-debt=#N` on `task release` (PowerShell-safe: `--allow-coverage-debt=N` or `--allow-coverage-debt="#N"` — see Anti-Patterns #2621). The open `#N` remains WIP until coverage is restored and the issue is closed.
+3. If an **open coverage-debt issue from a prior hatch still exists** → ⊗ soft-pass again; restore real coverage (all four metrics ≥ 85%) and close the debt issue before the cut proceeds.
+
+⊗ Auto-pass on a near-miss band without `#N` (#2573).
+⊗ Silent soft-pass with no tracked issue.
+⊗ File a debt issue without `coverage-debt` / `allow-coverage-debt` markers in title or body — the ledger query will miss it and permit a consecutive soft-pass (#2866).
+⊗ Use this carve-out when lines, functions, or statements are also below 85%, or for hangs, failing tests, or non-coverage Step 5 failures — those stay under #2859 file-and-merge.
+⊗ Treat file-debt-then-hatch as the default for ordinary PR / `task check` work outside a release cut — this hatch is release-scoped only.
+
+See [`docs/RELEASING.md`](../../../docs/RELEASING.md) § Coverage debt hatch during release.
+
 ~ **Frozen Go-installer bridge (#1912 / #1972 / #1987):** by default a release tag *above* the frozen line (the `LAST_GO_INSTALLER` constant in `packages/core/src/legacy-bridge/sot.ts`) will NOT rebuild the 6 Go binaries -- the CI `freeze-gate` job in `.github/workflows/release.yml` skips the build (the run stays green; npm still ships from the separate `npm-publish.yml`). If this release must rebuild the Go installer, follow the runbook in [`docs/RELEASING.md`](../../../docs/RELEASING.md) § Frozen Go-installer bridge: roll `LAST_GO_INSTALLER` forward to the cut tag BEFORE tagging (pinning to the exact cut tag both releases the gate AND re-freezes at the new line), then see that section's "After the release" step for the re-pin.
 
 1. ! Verify the operator is on the configured base branch (default `master`) and the working tree is clean
 2. ! Confirm the next version number (`X.Y.Z`) with the user. Major / minor / patch decision flows from the `[Unreleased]` content (breaking change → major; new feature → minor; fix-only → patch)
 3. ! Inspect `[Unreleased]` content vs the proposed version bump. If a breaking change appears in `### Changed` / `### Removed` but only a patch is proposed, surface the mismatch and ask the user to choose
-4. ! Verify `task ci:local` passes locally (or `task check` as the graceful-degradation fallback per `tasks/release.yml` line 9-10). The `task release` script will refuse to proceed otherwise -- but Phase 1 catches it earlier
+4. ! Verify `task ci:local` passes locally (or `task check` as the graceful-degradation fallback per `tasks/release.yml` line 9-10). The `task release` script will refuse to proceed otherwise -- but Phase 1 catches it earlier — **on failure from a fixable defect, STOP and follow § Fixable check failure below (#2859); do NOT proceed to step 5**
 5. ! Verify `gh auth status` reports authenticated (`task release` will refuse otherwise)
 6. ! **Run `task reconcile:issues -- --apply-lifecycle-fixes` to clear any closed-issue / non-completed-folder xBRIEFs before invoking `task release`** (#734). The release pipeline carries the deterministic gate at Step 3 (`scripts/release.py::check_vbrief_lifecycle_sync`, refuses with `EXIT_VIOLATION` on any Section (c) mismatch), but Phase 1 is the operator's first-line defence -- running the apply-mode flag here is the canonical clean path; `--allow-vbrief-drift` on the pipeline exists only as the explicit-acknowledgment escape hatch (analogous to `--allow-dirty`). The recurrence record is the v0.21.0 cut, which surfaced 13 stranded xBRIEFs (8 cycle-relevant + 5 historical residue) post-publish; the gate now blocks that drift before any irreversible action
 7. ! **Verify the proposed `v<version>` tag is not already in use locally, on origin, or as a published GitHub release** (#784). The release pipeline carries the deterministic gate at Step 4 (`scripts/release.py::check_tag_available`, refuses with `EXIT_VIOLATION` before any state mutation -- CHANGELOG promotion, ROADMAP refresh, build, commit), but Phase 1 is the operator's first-line defence. Quickly probe with `git tag -l v<version>` (local), `git ls-remote --tags origin refs/tags/v<version>` (remote), and `gh release view v<version> --repo <owner>/<repo>` (release-only, where `gh release view` exits 0 only when the release exists). The recurrence record is the v0.22.0 → v0.23.0 release attempt on 2026-05-01: the operator typed `0.22.0` (the prior release from 12 hours earlier) and the legacy pipeline ran 8 steps before failing at `git tag` -- leaving a wrong-version local commit + `dist/deft-0.22.0.zip` orphan + manual `git reset --hard` recovery. The new pre-flight gate blocks that mode before any irreversible action
@@ -310,4 +358,4 @@ Where `<one-line guidance>` is one of:
 - ⊗ Manually rewrite the Phase 8 Slack `*Summary*:` line to deviate from the CHANGELOG `[<version>]` blockquote -- the canonical narrative is authored ONCE at Phase 1 via `--summary` and propagates verbatim across all three audiences (CHANGELOG / GitHub release body / Slack). Per-audience hand-edits create documentation drift that the deterministic `--summary` flow is designed to prevent. If the operator wants Slack-specific tone, fold it into the canonical Phase 1 wording before passing `--summary`, OR amend the CHANGELOG blockquote BEFORE Phase 8 so all three surfaces stay aligned
 - ⊗ Export `DEFT_ALLOW_DEFAULT_BRANCH_COMMIT=1` for the entire release session or wrap `task release` / `task ci:local` in it (#1553) -- the env var is process-wide and leaks into nested tests and temporary repos, producing false preflight failures. Prefer `task policy:allow-direct-commits -- --confirm` and restore with `task policy:enforce-branches` after the cut (closeout commit+push may use a **scoped** env prefix on those three git commands only — see Branch-Protection Policy Guard, #2623)
 - ⊗ Pass `--allow-coverage-debt=#N` unquoted on Windows PowerShell (#2621) -- `#` starts a comment and silently drops the issue number. Use `--allow-coverage-debt=N` or `--allow-coverage-debt="#N"`
-- ⊗ Soft-pass coverage debt on consecutive releases when the prior cut already cited debt (#2618 / #2573) -- restore real branch coverage >= 85% instead of reusing the escape hatch
+- ⊗ Soft-pass coverage debt while an **open** coverage-debt issue from a prior hatch still exists (#2866 / #2573) -- restore real branch coverage >= 85% and close the debt issue before reusing `--allow-coverage-debt`; the ledger is open GitHub issues, not prior CHANGELOG citations (#2618 superseded by open-issue ledger)

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

@@ -239,6 +239,8 @@ Both commands extract the "Comments Outside Diff" section with surrounding conte
 
 ! **Worker-owns-lifecycle (#1880 Gap C):** When this skill runs as part of an implementation worker scoped `drive-to: merge-ready`, the worker owns the full review/fix loop through merge-ready in its own tool loop — do NOT exit at PR-open expecting the orchestrator to spawn a separate review leaf.
 
+! **Swarm monitor must not self-implement (#2843 / Gap C):** When a cohort monitor receives `BLOCKED` or DONE-with-blockers from a `drive-to: merge-ready` implementation leaf, the monitor MUST NOT enter the review/fix loop inline on Tier 1 — background-dispatch ONE continuation leaf scoped `drive-to: merge-ready` on the same worktree. Monitor-inline review-cycle is permitted only on Tier 3 or with explicit operator consent (see `skills/deft-directive-swarm/SKILL.md` Phase 5 completion-notification decision tree).
+
 
 
 ! Select the monitoring approach based on runtime capability detection (the matrix in `skills/deft-directive-swarm/SKILL.md` Phase 3 Step 1, extended per #1342 slices 1-2 for `spawn_subagent` / "grok-build" and per #1877 for Cursor as first-class Tier-1 tiers). Probe the environment (tool set + env vars) to obtain the stable platform descriptor (`grok-build`, `warp-orchestrated`, `warp-manual`, `cursor-composer`, `cursor-cloud-agent`, etc.) from the launch adapter / `get_platform_capabilities` and map the descriptor to the appropriate tier + dispatch primitive (`start_agent`, `spawn_subagent`, or the Cursor `Task` tool). The descriptor (not hard-coded tool presence) is the single source of truth for both launch and review monitoring.
@@ -251,11 +253,17 @@ Both commands extract the "Comments Outside Diff" section with surrounding conte
 
 ! Swarm agents (whether launched via `start_agent` or `spawn_subagent` per the platform descriptor) SHOULD prefer Approach 1 for their own review-monitor sub-agent. Approach 2's yield-between-polls is not self-sustaining for swarm agents (see warning below). Always include the canonical `templates/agent-prompt-preamble.md` (AGENTS.md read mandate, #810 xBRIEF gate, #798 PowerShell UTF-8, pre-PR + review-cycle mandates) when spawning a poller sub-agent.
 
-! **Deterministic review-monitor gate (#2655):** When Tier 1 is available, run `task verify:review-monitor -- --pr <N> [--call-site solo]` before yielding, entering Approach 3, or claiming review monitoring started. After spawning Approach 1, register with `task review-monitor:register -- --pr <N> --monitor-agent-id <id> --platform-primitive start_agent|spawn_subagent|cursor-task`. Exit `0` ready / `1` not ready / `2` config. Approach 3 on Tier 1 is a gate failure — use `--approach3 --approach3-warned` only on Tier 3 after the user warning.
+! **Deterministic review-monitor gate (#2655 / #2814):** When Tier 1 is available, run `task verify:review-monitor -- --pr <N> [--call-site solo]` before yielding, entering Approach 3, or claiming review monitoring started. After spawning Approach 1, claim the PR-anchored lease with `task review-monitor:register -- --pr <N> --monitor-agent-id <id> --platform-primitive start_agent|spawn_subagent|cursor-task`. Release with `task review-monitor:release -- --pr <N>` when done. Exit `0` ready / `1` not ready or held-by-other / `2` config. The sole source of truth is the sticky GitHub PR comment (`<!-- deft:review-owner -->`); legacy `.deft/review-monitor.json` is obsolete and ignored. On register conflict, attach to the existing owner or stop — do not parallel-fix.
+
+! **Regression trigger (#2797):** A leaf that claims a monitor is active without a preceding successful `task review-monitor:register` GitHub claim MUST fail the review-monitor checklist/eval; a backgrounded `task pr:watch` shell is insufficient.
+
+
 
 ! **CI-holdout carve-out (#2688):** When `task pr:watch --one-shot --json` reports `clean_gate_holdout=ci_failures` with Greptile fields otherwise satisfied on current HEAD, do **not** freeze on `verify:review-monitor` / spawn-monitor as if Greptile latency were the blocker. Fix CI first (same ownership as Greptile P0). Keep or register a review-monitor only while still waiting on Greptile latency; a `BLOCKED: ci_failures` DONE handback to the implementation owner is correct.
 
 
+! **Cursor leaf boundary (#2797):** A Cursor `Task` leaf cannot reliably spawn another Cursor `Task`; nested Task (leaf spawning leaf) is unsupported for an Approach 1 review-monitor. A Cursor `drive-to: merge-ready` leaf MUST either keep ownership in the same agent by blocking on `task pr:watch -- <N>`, or its envelope MUST instead be `stop-at: pr-open` so the orchestrator can spawn and register a sibling review-monitor. A background shell `task pr:watch` is not a monitor and MUST NOT be claimed as one.
+
 **Approach 1 (preferred -- sub-agent orchestration available per platform descriptor):**
 
 ! **Background dispatch (#1880):** Spawn the review-monitor sub-agent via the matching primitive IN THE BACKGROUND (Cursor: Task `run_in_background: true`; Grok Build: `spawn_subagent` with parent yielding). The parent MUST remain interactive while the poller runs.

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

@@ -455,6 +455,8 @@ Cross-references: `packages/core/src/swarm/routing.ts` (`SWARM_WORKER_ROLES`), `
 
 ! **Deliberate model routing before ANY dispatch:** Before launching ANY worker in this phase (cohort OR solo), run `task verify:routing` and resolve each `(dispatch_provider, worker_role)` via `task swarm:routing-set` / `.deft/routing.local.json`. Populate `## Worker metadata` per `templates/agent-prompt-preamble.md` §2.6 and pass `resolved_model` into the actual dispatch primitive when non-null. Never silently inherit the monitor's model. Deterministic gate enforcement is #1877; this rule is behavioral doctrine (#1880).
 
+! **Cursor ownership split (#2797):** A Cursor `Task` implementation leaf MUST NOT launch a nested Cursor `Task` review-monitor: nested Task (leaf spawning leaf) is unsupported/unreliable. For Cursor, a `drive-to: merge-ready` leaf owns a blocking `task pr:watch -- <N>` in its own process, or the dispatcher uses `stop-at: pr-open` and itself launches a sibling monitor then runs `task review-monitor:register`. A leaf that backgrounds `task pr:watch` and exits MUST NOT claim monitoring is active; this is a review-monitor-gate failure.
+
 ! **Worker-owns-lifecycle (Gap C):** Every implementation-worker dispatch prompt MUST declare the unit-of-work boundary: `stop-at: pr-open` OR `drive-to: merge-ready` (default for story xBRIEF work). Workers scoped `drive-to: merge-ready` own pre-PR, push, PR open, Greptile review-cycle poll/fix, and the #1259 Step 6 fail-closed exit as ONE dispatch — they spawn their own review poller per `skills/deft-directive-review-cycle/SKILL.md` monitoring tiers. The monitor MUST NOT plan a separate post-PR review leaf for a worker already scoped merge-ready.
 
 ! **Post-merge scope lifecycle (#2321 / Gap C):** Workers scoped `stop-at: pr-open` MUST NOT run `task scope:complete` before exit — their activation checkpoint rides into master on merge. The monitor (or Phase 6 `task swarm:finalize-cohort` / `task swarm:complete-cohort` on the headless path) MUST run `task scope:complete` or `task scope:cancel` for each shipped story xBRIEF after its PR merges. Workers scoped `drive-to: merge-ready` (or `drive-to: merge`) MUST include `task scope:complete` on their active xBRIEF as part of the same unit of work (after merge when appropriate). `task verify:orphan-active` fails closed when active/running briefs remain after their issues close or PR merges.
@@ -609,7 +611,16 @@ For each agent's PR:
 1. ! Check that Greptile has reviewed the latest commit (compare "Last reviewed commit" SHA to branch HEAD)
 2. ! Verify Greptile confidence score > 3
 3. ! Verify no P0 or P1 issues remain (P2 are non-blocking style suggestions)
-4. ! **Worker-owns-lifecycle fallback (#1880):** Prefer workers scoped `drive-to: merge-ready` so this step is rare. When a worker exits at PR-open without reaching merge-ready, the monitor MAY run `skills/deft-directive-review-cycle/SKILL.md` itself or dispatch ONE review-cycle owner — but MUST NOT split review polling and fix batches across separate leaf agents for the same PR (#727 + #1880 Gap C).
+4. ! **Blocked-leaf continuation (#1880 / #2843):** Prefer workers scoped `drive-to: merge-ready` so this step is rare. When a leaf exits `BLOCKED` (or a false-terminal DONE-with-blockers — see `templates/agent-prompt-preamble.md` §11) before merge-ready:
+   - **Tier 1 available** (`start_agent`, `spawn_subagent`, Cursor `Task`): the monitor MUST background-dispatch ONE continuation leaf (`drive-to: merge-ready`, same worktree) owning fix batches + blocking `task pr:watch` + merge readiness. The monitor MUST NOT run inline code edits or review-cycle fix batches in its own turn (#2843 monitor-as-implementer recurrence).
+   - **Tier 3 only** (no sub-agent primitive): the monitor MAY run `skills/deft-directive-review-cycle/SKILL.md` itself after explicit operator consent — or offer serial self-execution downgrade from Phase 3.
+   - ⊗ Split review polling and fix batches across separate leaf agents for the same PR (#727 + #1880 Gap C).
+
+! **Completion-notification decision tree (#2843):** When a background leaf completion notification arrives, parse the terminal message per preamble §11:
+   - `DONE` + merge-ready verified (`task pr:merge-ready -- <N>` exit 0): may proceed to merge / `task scope:complete` per Phase 5→6 / Phase 6.
+   - `BLOCKED` (+ optional `REDISPATCH_OK`): resume the same leaf if the host supports it, OR background-dispatch ONE continuation leaf with the cited PR/SHA/worktree — no monitor-inline fixes on Tier 1.
+   - `FAILED` / silent (no terminal message): run `task verify:subagent-alive`; on exit 1 print `REDISPATCH_OK` and background-dispatch ONE continuation leaf.
+   - ⊗ Treat `DONE` without merge-ready verification as success — that is the false-terminal pattern §11 closes.
 
 ### Complete xBRIEFs
 

package/tasks/agent.yml

@@ -0,0 +1,15 @@
+version: '3'
+
+vars:
+  DEFT_ROOT: '{{joinPath .TASKFILE_DIR ".."}}'
+
+tasks:
+  monitor:
+    desc: "Sub-agent heartbeat sweep (#1365 / #2824). Three-state exit (0 ok / 1 stale-or-malformed / 2 config). Alias for the raw subagent-monitor engine."
+    dir: '{{.USER_WORKING_DIR}}'
+    deps:
+      - task: :engine:_ts-build
+    cmds:
+      - task: :engine:invoke
+        vars:
+          ENGINE_CMD: 'subagent-monitor {{.CLI_ARGS}}'

package/tasks/docs.yml

@@ -0,0 +1,37 @@
+version: '3'
+
+# Maintainer documentation tasks.
+#
+# docs:rule-map renders the Rule Map: a maintainer-facing view of how the
+# framework's rules are layered and grouped. Source of truth is content/ +
+# tasks/ + the packs; the map is a derived view, so regenerate after changing
+# rules rather than hand-editing the outputs.
+#
+#   docs/RULE-MAP.md          committed, diff-friendly Markdown (no timestamps)
+#   docs/rule-map/index.html  gitignored, self-contained interactive explorer
+#
+# Implemented as the `rule-map` engine verb (packages/core/src/render/rule-map.ts),
+# dispatched through the TS engine like the other render gates. No Python, no
+# external dependencies, no network.
+
+tasks:
+
+  rule-map:
+    desc: "Build the maintainer Rule Map (docs/RULE-MAP.md + gitignored docs/rule-map/index.html)"
+    dir: '{{.USER_WORKING_DIR}}'
+    deps:
+      - task: :engine:_ts-build
+    cmds:
+      - task: :engine:invoke
+        vars:
+          ENGINE_CMD: 'rule-map --project-root "{{.USER_WORKING_DIR}}" {{.CLI_ARGS}}'
+
+  rule-map:check:
+    desc: "Fail if committed docs/RULE-MAP.md is out of date (for CI / pre-commit gating)"
+    dir: '{{.USER_WORKING_DIR}}'
+    deps:
+      - task: :engine:_ts-build
+    cmds:
+      - task: :engine:invoke
+        vars:
+          ENGINE_CMD: 'rule-map --project-root "{{.USER_WORKING_DIR}}" --check'

package/tasks/policy.yml

@@ -62,6 +62,16 @@ tasks:
         vars:
           ENGINE_CMD: 'policy enable-value-feedback --project-root "{{.USER_WORKING_DIR}}" {{.CLI_ARGS}}'
 
+  clear-value-feedback:
+    desc: "Remove typed plan.policy.valueFeedback so trusted-org repos return to org-auto resolution (#2822). -- task policy:clear-value-feedback"
+    dir: '{{.USER_WORKING_DIR}}'
+    deps:
+      - task: :engine:_ts-build
+    cmds:
+      - task: :engine:invoke
+        vars:
+          ENGINE_CMD: 'policy clear-value-feedback --project-root "{{.USER_WORKING_DIR}}" {{.CLI_ARGS}}'
+
   wip-cap:
     desc: "Set plan.policy.wipCap=N (#1124 / D4 of #1119). Requires --set N --confirm. Default cap is 20 (#2319; raised from the original 10 per umbrella #1119 Current Shape v3)."
     dir: '{{.USER_WORKING_DIR}}'

package/tasks/review-monitor.yml

@@ -5,7 +5,7 @@ vars:
 
 tasks:
   register:
-    desc: "Record an active Approach 1 review-monitor after spawn (#2655). Writes .deft/review-monitor.json at the main worktree root."
+    desc: "Claim PR-anchored review-owner lease via sticky GitHub comment (#2814). Does not write local JSON."
     dir: '{{.USER_WORKING_DIR}}'
     deps:
       - task: :engine:_ts-build
@@ -13,3 +13,13 @@ tasks:
       - task: :engine:invoke
         vars:
           ENGINE_CMD: 'review-monitor-register {{.CLI_ARGS}}'
+
+  release:
+    desc: "Release PR-anchored review-owner lease by editing the sticky GitHub comment (#2814)."
+    dir: '{{.USER_WORKING_DIR}}'
+    deps:
+      - task: :engine:_ts-build
+    cmds:
+      - task: :engine:invoke
+        vars:
+          ENGINE_CMD: 'review-monitor-release {{.CLI_ARGS}}'

package/tasks/verify.yml

@@ -466,3 +466,13 @@ tasks:
       - task: :engine:invoke
         vars:
           ENGINE_CMD: 'verify-review-monitor {{.CLI_ARGS}}'
+
+  subagent-alive:
+    desc: "Fail-closed worker liveness gate (#2824): missing/STALE heartbeats for in-flight drive-to:merge* workers exit 1 with REDISPATCH_OK. Three-state exit (0 alive / 1 stale-or-missing / 2 config error)."
+    dir: '{{.USER_WORKING_DIR}}'
+    deps:
+      - task: :engine:_ts-build
+    cmds:
+      - task: :engine:invoke
+        vars:
+          ENGINE_CMD: 'verify-subagent-alive {{.CLI_ARGS}}'

package/templates/agent-prompt-preamble.md

@@ -449,6 +449,8 @@ These rules bind **orchestrators** dispatching implementation, fix, or review-cy
 **Worker-owns-lifecycle (Gap C):**
 
 - ! When dispatching an implementation worker, the dispatch envelope MUST declare the unit-of-work boundary explicitly: `stop-at: pr-open` (worker opens PR and exits) OR `drive-to: merge-ready` (worker owns PR + Greptile review cycle + fix batches through merge-ready as ONE unit of work, spawning its own review poller per `skills/deft-directive-review-cycle/SKILL.md` monitoring tiers). Default for story implementation dispatches is `drive-to: merge-ready`.
+- ! **Cursor Task ownership split (#2797 / #2814):** A Cursor `Task` implementation leaf MUST NOT spawn another Cursor `Task` review-monitor: nested Task (leaf spawning leaf) is unsupported/unreliable. A Cursor `drive-to: merge-ready` leaf instead owns a blocking `task pr:watch -- <N>` in its own process. To use an Approach 1 monitor, scope the leaf `stop-at: pr-open`; the orchestrator that owns the Task primitive then launches the sibling monitor and runs `task review-monitor:register -- --pr <N> --monitor-agent-id <id> --platform-primitive cursor-task` (GitHub sticky `<!-- deft:review-owner -->` lease — not local JSON).
+- ⊗ Let a Cursor leaf background `task pr:watch` and claim review monitoring is active. The process dies with the leaf and has no GitHub review-owner lease; treat that claim as a regression/eval failure and let `task verify:review-monitor -- --pr <N>` fail closed.
 - ! **Post-merge scope lifecycle (#2321 / Gap C):** Workers scoped `stop-at: pr-open` MUST NOT run `task scope:complete` before exit — their activation checkpoint rides into master on merge. The **orchestrator** (or Phase 6 `task swarm:finalize-cohort` / `task swarm:complete-cohort` on the headless path) MUST run `task scope:complete` or `task scope:cancel` for each shipped story xBRIEF after its PR merges. Workers scoped `drive-to: merge-ready` (or `drive-to: merge`) MUST include `task scope:complete` on their active xBRIEF as part of the same unit of work (after merge when appropriate).
 - ! Workers scoped `drive-to: merge-ready` MUST drive to merge-ready in their own tool loop — pre-PR, push, PR open, review-cycle poll/fix loop, and the #1259 Step 6 fail-closed exit — without handing back at PR-open for the orchestrator to re-dispatch separate leaf agents for review or fixes.
 - ⊗ Re-dispatch a separate review-monitor or fix agent after an implementation worker exits at PR-open when the original envelope scoped `drive-to: merge-ready` — that split recreates cross-agent state-handoff hazards and terminal lifecycle gaps (#1878 / Gap C).
@@ -502,6 +504,11 @@ The contract in one paragraph:
 
 The parent monitor watches the heartbeat file directly (three-state exit 0 ok / 1 stale-or-malformed / 2 config error). Skipping the heartbeat is a hard `⊗` for any long-running sub-agent: a stalled agent with no heartbeat surface is the exact #1166 failure mode this contract closes.
 
+! **Cursor false-alive / REDISPATCH_OK (#2824):** On the Cursor `Task` path, the host may report a leaf as "still running" after it has gone silent (empty transcript, no heartbeats, no DONE/FAILED). When `task verify:subagent-alive` exits `1` for a registered in-flight `drive-to: merge*` worker — missing heartbeat, STALE heartbeat, or no recent git/PR activity — the monitor MUST treat the worker as dead and print `REDISPATCH_OK` to authorize takeover re-dispatch. Do NOT block on host resume when the liveness gate has failed closed.
+
+- Monitors run `task verify:subagent-alive -- --require-agent <agent-id> [--scratch-dir <worktree>/.deft-scratch/subagent-status]` each poll iteration.
+- Workers run `task agent:monitor` (raw sweep) or the gate verb above; both wrap `subagent-monitor` (#1365).
+
 ## 11. Mandatory DONE message even on early exit
 
 Every worker MUST send a final status message before exiting its tool loop, regardless of outcome:
@@ -511,6 +518,12 @@ Every worker MUST send a final status message before exiting its tool loop, rega
 - Failure: `FAILED: <reason> + recovery hint`
 - Stand-down: `STOOD-DOWN: <reason>` (e.g. user said "wait" with no follow-up dispatch)
 
+! **`drive-to: merge-ready` DONE reservation (#2843):** When the dispatch envelope scoped `drive-to: merge-ready` (or `drive-to: merge`), `DONE` is reserved for merge-ready completion — `task pr:merge-ready -- <N>` exit 0 on current HEAD, or merge + `task scope:complete` when the envelope included merge authority. Greptile P0/P1 outstanding, CI failure, branch behind, review-cycle cap, or any other merge blocker MUST NOT exit as `DONE`.
+
+! **Mid-cycle BLOCKED contract (#2843):** A `drive-to: merge-ready` worker that must exit before merge-ready (blocker, cap, context limit, host turn budget) MUST emit `BLOCKED:` (never `DONE`) with: PR number (or `no-pr`), HEAD SHA, blocker class (`greptile_p0_p1` / `ci_failures` / `behind_base` / `review_cycle_cap` / `context_limit` / other), worktree path, and `REDISPATCH_OK` when a continuation leaf should take over. Example: `BLOCKED: Greptile P1 on HEAD abc1234 (PR #2842, blocker greptile_p0_p1, worktree .deft-scratch/worktrees/2839-appsec, REDISPATCH_OK)`.
+
+⊗ Emit `DONE` from a `drive-to: merge-ready` worker while merge-ready is false — a false-terminal `DONE` pulls the cohort monitor into inline Greptile fixes and violates Gap D (#2843 monitor-as-implementer recurrence).
+
 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.
 
 ## 12. Session ritual + `task verify:cache-fresh` gates before `start_agent` (#1348 / #1127)

package/tools/package-manager-network.md

@@ -13,7 +13,8 @@ Directive runs against arbitrary repositories, including private monorepos with
 ## Rules
 
 - ! Read-only, session-start, and session-ritual flows (`deft session:start`, `deft verify:session-ritual`, `deft verify:tools`) MUST perform no npm/pnpm registry access. Tool-presence probes MUST use PATH lookups (`which`/`accessSync`) or `--version` checks, never a subcommand that can resolve dependencies or query a registry.
-- ! `deft doctor` MUST default to an OFFLINE tier: no check in the default run may contact an npm/pnpm registry. The one check that can (`payload-staleness`, which uses `git ls-remote` to verify the installed pin and `npm view <package> version` to compare a release-tag install with the latest stable package) is gated behind the explicit `--network` flag and is skipped by default with a pointer to that flag.
+- ! `npm config get @deftai:registry` and `npm config get registry` are offline configuration reads, not registry access. `deft doctor` MAY use them in its default tier to identify effective routing, but MUST NOT print the raw values because registry URLs can contain internal hostnames or credentials.
+- ! `deft doctor` MUST default to an OFFLINE tier: no check in the default run may contact an npm/pnpm registry. The one check that can (`payload-staleness`, which uses `git ls-remote` to verify the installed pin and `npm view <package> version --registry=https://registry.npmjs.org/ --ignore-scripts` to compare a release-tag install with the latest stable package) is gated behind the explicit `--network` flag and is skipped by default with a pointer to that flag.
 - ! Before a network-gated check runs, `deft doctor --network` MUST print a disclosure line naming the tool and registry class it may contact (for example, "may contact your git remote and the npm registry") BEFORE any network call is attempted.
 - ! Any future doctor check, session step, or read-only command that needs to invoke `npm`/`pnpm` in a way that can reach a registry MUST follow the same pattern: explicit flag or subcommand, disclosed registry class before the call, and offline by default.
 - ~ Where a package-manager operation is unavoidable in an explicitly-invoked flow (e.g. a release or install workflow that legitimately needs to fetch packages), prefer offline/frozen modes (`--offline`, `--prefer-offline`, `--frozen-lockfile`) when the operation only needs to validate local state rather than resolve fresh metadata.
@@ -26,4 +27,4 @@ This does not ban dependency installation or registry verification from explicit
 
 ## Reference implementation
 
-`packages/core/src/doctor/payload-staleness.ts` is the only code path in the TS engine that shells out to `npm` (`npm view`) or performs a git-remote network call for framework-currency checks; `packages/core/src/doctor/main.ts` gates it behind `--network` and prints the disclosure line first. `packages/core/src/session/session-start.ts` and `packages/core/src/verify-env/verify-tools.ts` perform no package-manager network access at all -- tool presence is resolved via PATH probing only.
+`packages/core/src/doctor/npm-registry.ts` performs only the two offline `npm config get` reads above and redacts their values from findings. `packages/core/src/doctor/payload-staleness.ts` owns the network-capable doctor probes (`git ls-remote` and `npm view`); `packages/core/src/doctor/main.ts` gates them behind `--network` and prints the disclosure line first. The npm release lookup pins `--registry=https://registry.npmjs.org/` and `--ignore-scripts`, so a configured mirror cannot silently report an old latest release. `packages/core/src/session/session-start.ts` and `packages/core/src/verify-env/verify-tools.ts` perform no package-manager network access at all -- tool presence is resolved via PATH probing only.