@event4u/agent-config 9.31.0 → 9.33.0

package/.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Bootstrap shim for the event4u agent-config suite. This plugin ships ONLY the dispatcher hooks plus one install-pointer skill — ALL content (skills, rules, commands) is installed via `npx -y @event4u/agent-config init`, which writes the file projection AND registers the same hooks in ~/.claude/settings.json. DEPRECATED as a content channel; kept so the marketplace listing stays discoverable and existing installs keep working hooks.",
-    "version": "9.31.0",
+    "version": "9.33.0",
     "keywords": [
       "agent-config",
       "skills",

package/CHANGELOG.md

@@ -321,6 +321,152 @@ Entry-shape contract: [`docs/contracts/CHANGELOG-conventions.md`](docs/contracts
 > that forces a new era split (`# Era: 9.32.x`, etc.) — see
 > [`docs/contracts/CHANGELOG-conventions.md § Era splits`](docs/contracts/CHANGELOG-conventions.md).
 
+## [9.33.0](https://github.com/event4u-app/agent-config/compare/9.32.0...9.33.0) (2026-08-11)
+
+### Release highlights
+
+<!-- Curated head: fill before merge, keep it under 10 lines, and leave `_none_` where it is genuinely the answer. The generated log below is unchanged. -->
+- **Behaviour changes:** _auto-derived, rewrite before merge:_ rule/schema diffs, breaking commits or removed public surface in e625e69, 9ec8042.
+- **Default changes + migration:** _auto-derived, rewrite before merge:_ commits naming a default, migration or migrate in 2588c5b.
+- **Security and correctness:** _auto-derived, rewrite before merge:_ security-scoped commits in b17d1f3.
+- **Honest nulls:** _auto-derived, rewrite before merge:_ commits carrying an honest-null marker in 9e999d6, b86a4a9.
+- **Known limitations:** _none_
+
+### Features
+
+* **gates:** add --reply, the reply-close projection over open blockers ([dd88d21](https://github.com/event4u-app/agent-config/commit/dd88d2116dcc73a1351e292047c0b22a8f84fdd7))
+* **funnel:** the missing Opportunity stage ([ca5aabd](https://github.com/event4u-app/agent-config/commit/ca5aabd834db73755f2a6eba8efa5dc2edd2bb1b))
+* **recycle:** --verify validates without writing, plus an envelope mutation suite ([a9ad7d8](https://github.com/event4u-app/agent-config/commit/a9ad7d88ea214f2eb9dd12e406f93e9cbfb7bc17))
+* **conformance:** --why <id> traces one conformance check ([807a85c](https://github.com/event4u-app/agent-config/commit/807a85caed1a7b79499f1071d4202ed17142b6e2))
+* **doctor:** --anatomy renders the injection anatomy from existing measurements ([6ed0aac](https://github.com/event4u-app/agent-config/commit/6ed0aac994ef14b42d5e65bd86a5c4734648cceb))
+* **cost-summary:** report what caching bought, when spend happened, and where input went ([3dbc570](https://github.com/event4u-app/agent-config/commit/3dbc57082506a00a51dca76fdb06610e720a754d))
+* **cost-ledger:** record the model that actually answered, not the one asked for ([8b79067](https://github.com/event4u-app/agent-config/commit/8b790671bb780629fd30a06a47dacf957da93c3d))
+* **council:** mark a solo-concluded pass in the rendered quorum line ([b6a90ab](https://github.com/event4u-app/agent-config/commit/b6a90ab405a2d0a5bdee655f8fa34f45b3ae4d74))
+* **ci:** resolve workflow path filters against the tree, and repair 20 dead ones ([77f200f](https://github.com/event4u-app/agent-config/commit/77f200f0885d5ac6b28c9d5b98d737665d847954))
+* **council:** make a solo-concluded quorum distinguishable in the event log ([5addcd0](https://github.com/event4u-app/agent-config/commit/5addcd0a9bee200ec2fbc529a6365254c397e68f))
+* **budget:** register the three attendance metrics before any data exists ([b6bf44d](https://github.com/event4u-app/agent-config/commit/b6bf44dd799c2854e7caa576ca3cd2d29889f560))
+* **council:** make a solo-concluded pass visible in the event log ([ec8ede6](https://github.com/event4u-app/agent-config/commit/ec8ede6ec50b8aa5e9daecfcc35c26486ad1bb14))
+* **budget:** the cost-parity target table, with a gate that refuses an untraceable number ([b86a4a9](https://github.com/event4u-app/agent-config/commit/b86a4a9d4efc2ab1dff74ba56724b07061850b8e))
+
+### Bug Fixes
+
+* **cost-ledger:** repair the seven findings from the R2 completion review ([4204a99](https://github.com/event4u-app/agent-config/commit/4204a99a118ab8e8ed04fb3674821b69c0616f1a))
+* **changelog:** curate the shipped v9.32.0 head, record the cadence decision ([27616e6](https://github.com/event4u-app/agent-config/commit/27616e6046424b12d5b203399dbd3435fb535c48))
+* **install:** record the .vscode bridge merge, surface trampoline removal failures ([c1f15c1](https://github.com/event4u-app/agent-config/commit/c1f15c18f1da0d6e079a2bc4e16f311af6b1ccba))
+* **pricing:** stop pricing a dated model alias at nothing, and stop hiding it ([3fbcc52](https://github.com/event4u-app/agent-config/commit/3fbcc52c436bbdc063aa1476b9a3dc281b38180e))
+* **wedge:** regenerate the production-validator projection after the pragma ([8ab3012](https://github.com/event4u-app/agent-config/commit/8ab3012ab40a54d228d11fadfd0ba072a0fa08fa))
+* **security-lint:** the bare-shell detector had never read a subagent ([b17d1f3](https://github.com/event4u-app/agent-config/commit/b17d1f33653438ab6489c64f33dce403a4f8d2c1))
+* **test:** drop the last v1 label the schema bump left behind ([6f53010](https://github.com/event4u-app/agent-config/commit/6f530100a3b2af7cc4b43b7e58fcb2862df9a48a))
+* **council:** measure the dispatch shape, and stop dividing entries by clients ([d716386](https://github.com/event4u-app/agent-config/commit/d7163864715e15d879ce6af1c1f6db028832d824))
+* **council:** make the attendance metrics able to answer their own questions ([8f92902](https://github.com/event4u-app/agent-config/commit/8f929020301bfdb50e6d788a71e1050f9ff58d43))
+* **ci:** describe the retired tree without naming its dead path ([bd2e726](https://github.com/event4u-app/agent-config/commit/bd2e726883aecf5106522fa7324c1d11aa3a0473))
+* **roadmap:** re-date the index risk review after the substantial rewrite ([6f71cb4](https://github.com/event4u-app/agent-config/commit/6f71cb4f23cfbf2eb344be4a070281e45b2c1fdf))
+* **schema:** let a subagent express the scoped tool grant tool-safety asks for ([9ec8042](https://github.com/event4u-app/agent-config/commit/9ec8042d2c73162931c0d7900826934fdaafccfa))
+* **review-routing:** give the role vocabulary a home that exists ([ec4d392](https://github.com/event4u-app/agent-config/commit/ec4d392faf4feaaf5fbf0694bc028b6e54d0fe2c))
+* **skills:** re-home two sections the rule migration dropped ([2588c5b](https://github.com/event4u-app/agent-config/commit/2588c5be9f82bab41ebedcddd0ad4302dbfc245a))
+* **review:** name the skip artefact so the gate can discover it ([b693b61](https://github.com/event4u-app/agent-config/commit/b693b61e94e5ded5463c22124acb20a1ca776d00))
+* **roadmap:** correct three false premises in the gate-integrity kernel blocker ([2e6c07e](https://github.com/event4u-app/agent-config/commit/2e6c07e66eec04ddf8afb8e233340c2e628141fa))
+* **roadmap:** stop two sub-headings from parsing as phantom phases ([05ed949](https://github.com/event4u-app/agent-config/commit/05ed9493b153c19253fcad3c98a939d76dd09f31))
+
+### Documentation
+
+* **adr:** ADR-222 — blocker handover is delivered, not remembered ([961ac12](https://github.com/event4u-app/agent-config/commit/961ac12705db642f54119f39dfef9ac5cbea870c))
+* **reply-close:** state the blocker handover as part of the one summary ([ec761e0](https://github.com/event4u-app/agent-config/commit/ec761e04b13e05ea671ba906bfbfd05999e25563))
+* **review:** re-bind the completion review to the repaired scope ([0a585db](https://github.com/event4u-app/agent-config/commit/0a585db2279c83bbf09a1b3afd18852833795c89))
+* **roadmap:** release-surface integrity, 11 of 12 steps closed ([70cec30](https://github.com/event4u-app/agent-config/commit/70cec30255f61de1aeaa39551e008992c63f606c))
+* **context:** Continuation Protocol v1 decided, the runtime graph deferred ([3bafcc0](https://github.com/event4u-app/agent-config/commit/3bafcc075c6db2bcaf9a9725ee87fdb190bd7a73))
+* **contracts:** the model ceiling escalates, never silently degrades ([e625e69](https://github.com/event4u-app/agent-config/commit/e625e696fb4f2d90110f8678dd86e208ec0f4729))
+* **cli:** name the three new flags in the registry synopses and dispatcher help ([1f43731](https://github.com/event4u-app/agent-config/commit/1f4373195ca2d477d06e1fcaa467df2120d8043b))
+* **context:** give the corrected carrier-divergence figure a stable surface ([4812f9d](https://github.com/event4u-app/agent-config/commit/4812f9de9d6bd96b6109776001191a8fbb95feb9))
+* **proof:** re-render after the surgical-uninstall claim moved to exec evidence ([5e489ee](https://github.com/event4u-app/agent-config/commit/5e489ee7b58428f79fc211d07fda754c76efda0e))
+* **review:** record the R2 completion-review findings before any fix ([2954d66](https://github.com/event4u-app/agent-config/commit/2954d663fa26980113331653c31d3dc3ef88c649))
+* **roadmap:** restore install-lifecycle 2.3 to open-and-blocked ([4b61e7f](https://github.com/event4u-app/agent-config/commit/4b61e7f4ba61c560bd3a836368ebb73864e0d285))
+* **roadmap:** land the org-pack reopening brief, close install-lifecycle Phase 2 ([b172d28](https://github.com/event4u-app/agent-config/commit/b172d28ed0a8f2f112a3b0fb43c4e5fe9c54edd6))
+* **roadmap:** close install-lifecycle Phase 1, cancel 1.2 on a failed premise ([920910b](https://github.com/event4u-app/agent-config/commit/920910bc2d6acf978ebe70f5fdb844420b2002c4))
+* **install-layout:** correct the untracked-surfaces list and the vscode pointer shape ([26982c6](https://github.com/event4u-app/agent-config/commit/26982c62eafd452f4c2cf6cd929a7a74dd68dbc6))
+* **roadmap:** record the unapplied Phase 1 implementation and its two open calls ([25fc56d](https://github.com/event4u-app/agent-config/commit/25fc56da7356e446f13bbb1da866a4ddc70091d1))
+* **roadmap:** carry the re-homing the merge commit described but did not contain ([a7a469f](https://github.com/event4u-app/agent-config/commit/a7a469f87592580fab38a1180e17d2320e861337))
+* **roadmap:** council dispositions and four cited corrections ([10c25c4](https://github.com/event4u-app/agent-config/commit/10c25c4753212c2c4b93e972707b3090e06cb431))
+* **review:** re-bind round 2 — six fixed, one accepted as debt ([7b451cb](https://github.com/event4u-app/agent-config/commit/7b451cb75f65b787f4c5ebf3903b49e90382c98a))
+* **review:** record round 2 — the fixes introduced two of their own ([4a0504c](https://github.com/event4u-app/agent-config/commit/4a0504cfcf302b00a3f9773ba89eb284f2b7f573))
+* **review:** re-bind the findings to what the fixes actually did ([baba417](https://github.com/event4u-app/agent-config/commit/baba417297bbb6db0d0d250785e3c049f7e33fd7))
+* **review:** record the completion review before any fix lands ([7dc1f1f](https://github.com/event4u-app/agent-config/commit/7dc1f1f4ea511bcd30a67ac416937511c6420721))
+* **roadmap:** split the 2026-08-10 harvest into eight executable roadmaps ([72a1078](https://github.com/event4u-app/agent-config/commit/72a10788336fc54cff25833ae1568328765f4011))
+* **roadmap:** close Phase 1 and steps 3.2 / 3.5 / 3.8, and re-frame 3.6 ([dc12894](https://github.com/event4u-app/agent-config/commit/dc128947b844d0afb147b9e413c12c1dadbc7346))
+* **roadmap:** close Phase 1 — the quorum-attendance defect ([12e0bc1](https://github.com/event4u-app/agent-config/commit/12e0bc14f7813691c8708d25b6eb23c8bcf4f116))
+* **review:** declare the no-code-surface skip for this completion ([3771eaf](https://github.com/event4u-app/agent-config/commit/3771eafda510306cf238539f3c910481f7e36b1a))
+* **ledger:** record that the three dangling pointers were repaired ([03cf5f8](https://github.com/event4u-app/agent-config/commit/03cf5f8699dce20224479a58a6ece39509deb6a0))
+* **roadmap:** triage the 2026-08-10 inbox batch ([9e999d6](https://github.com/event4u-app/agent-config/commit/9e999d64eb3b34612bcbe7d8d4e91bad56c7cc54))
+* **roadmap:** correct two roadmap claims the tree contradicts ([e1f271e](https://github.com/event4u-app/agent-config/commit/e1f271e6bbe50f9ebaf9814ce47b83bc4111d871))
+* **roadmap:** add the risk register the telemetry record made due ([82268d7](https://github.com/event4u-app/agent-config/commit/82268d7e4e417e688bfb453d9c75f0ded1b0991e))
+* **roadmap:** record the measured telemetry state on both orchestration blockers ([10a2790](https://github.com/event4u-app/agent-config/commit/10a2790e19b245280dd5764cdbfcb873ff586be7))
+* **roadmap:** close and archive the cost-parity program — 23 steps, 6 criteria, every claim re-verified ([af57abf](https://github.com/event4u-app/agent-config/commit/af57abf96ae30234de73446f965d93eba45423f7))
+* **decision:** give the router-is-unused finding an owner before someone acts on it ([bf70104](https://github.com/event4u-app/agent-config/commit/bf701040cf44e873b4fb1eb115a599ed39f7190f))
+* **cost-parity:** one ledger for the family's order, and the per-host table the diet actually needs ([fa188ee](https://github.com/event4u-app/agent-config/commit/fa188ee44ecddf4898abf8feea3c4a12155b1f29))
+
+### Tests
+
+* **subagent:** assert the tool-grant behaviour, not which keyword rejected it ([59ee093](https://github.com/event4u-app/agent-config/commit/59ee0938eac9289a7f711600eb3bf45500ded1d4))
+* **workspace-inbox:** re-record the inline snapshot that embeds the docker skill ([f395d79](https://github.com/event4u-app/agent-config/commit/f395d79dec3d7e5e39cded83871d384f1008594e))
+* **pricing:** cross-check the two cache-rate tables that nothing compared ([e623e0c](https://github.com/event4u-app/agent-config/commit/e623e0c8fe285dd5ff8e824ac58b7a7cf2d222b0))
+
+### Build
+
+* **install:** refresh dist/install/install.mjs for the vscode bridge and trampoline warning ([440b046](https://github.com/event4u-app/agent-config/commit/440b046fb75448bfbe6cf854f0084ae19fd9c8f4))
+
+Tests: 12935 (+117 since 9.32.0)
+
+## [9.32.0](https://github.com/event4u-app/agent-config/compare/9.31.0...9.32.0) (2026-08-10)
+
+### Release highlights
+
+<!-- Curated head: fill before merge, keep it under 10 lines, and leave `_none_` where it is genuinely the answer. The generated log below is unchanged. -->
+- **Behaviour changes:** the work-engine's two red-check lanes now run a bounded self-fix loop before halting to `BLOCKED` — at most three attempts per validation target, stopped early when a verdict signature repeats (1f01490, wired in 10c8f7e). e05de77 edits a rule file only and changes no behaviour.
+- **Default changes + migration:** _none_
+- **Security and correctness:** _none_
+- **Honest nulls:** _none_
+- **Known limitations:** _none_
+
+### Features
+
+* **work-engine:** route both red-check lanes through the self-fix loop ([10c8f7e](https://github.com/event4u-app/agent-config/commit/10c8f7eafbf21fc03a5f301163c941a20df4a885))
+* **work-engine:** bounded self-fix loop primitive + executable dod schema ([1f01490](https://github.com/event4u-app/agent-config/commit/1f0149035c1a27729b729dab1dedd861ccdf9812))
+* **envelope:** drift anchor, scripted grounding, verbatim error strings ([6c9187e](https://github.com/event4u-app/agent-config/commit/6c9187e30f41c87553764759096a3f7f4d19a126))
+* **envelope:** successor tailoring, mandatory failed_approaches, data-never-instruction boundary ([b03beac](https://github.com/event4u-app/agent-config/commit/b03beac1ad1325253c89a63eac9abc9f051269d3))
+* **orchestration:** report per-field provenance for host capabilities ([f4958de](https://github.com/event4u-app/agent-config/commit/f4958decf4a70b445a38747bff768ab449877d52))
+
+### Bug Fixes
+
+* **gates:** stop the R2 review-input copy from laundering fixture secrets ([c63d350](https://github.com/event4u-app/agent-config/commit/c63d3502013e7bc261096d02e2c102a52e2f1ec7))
+* **golden:** teach the replay the delegated bad-verdict surface, re-lock baselines ([1ff480c](https://github.com/event4u-app/agent-config/commit/1ff480c6adeb88af32198a19d41838e2f9f5dcc0))
+* **envelope:** close the eight R2 review findings ([b0d153c](https://github.com/event4u-app/agent-config/commit/b0d153cb3084dac2a20093b73d28a3ce3c12324c))
+* **tests:** type the self-fix state helpers against the wire types ([60d2724](https://github.com/event4u-app/agent-config/commit/60d272419b07b5abea1ce6ffa430faf127fcde4a))
+* **handoff:** stop offering the caller its own empty session ([b72f772](https://github.com/event4u-app/agent-config/commit/b72f772a03207aa4feeded3acd5b68823e3fd79c))
+* **tests:** narrow regex captures in the capability parity block ([6f27615](https://github.com/event4u-app/agent-config/commit/6f276154b83781404d6551113c6d43e5cf040423))
+* **carrier:** a paths: disagreement is a delivery defect, not inert metadata ([318fb81](https://github.com/event4u-app/agent-config/commit/318fb818eb543f27fc4c3b138ce762dc8c9e9640))
+
+### Documentation
+
+* **review:** re-bind the findings artefact to the post-fix scope ([7a9bbbb](https://github.com/event4u-app/agent-config/commit/7a9bbbb2d7f4f04786771914bf7b3b68aba23e10))
+* **review:** record the R2 completion-review findings before fixing them ([27322e8](https://github.com/event4u-app/agent-config/commit/27322e876c76f96d6a67131f9e96a1759290a8f5))
+* **roadmap:** P2.2 build half shipped, its threshold unevaluated with a blocker ([1e478fd](https://github.com/event4u-app/agent-config/commit/1e478fdc317fdf12df001c1b98ef264df54a3742))
+* **contracts:** the flow contract documents the self-fix loop and the dod slot ([0ebaaba](https://github.com/event4u-app/agent-config/commit/0ebaabae9e12c75446efefc5be6f6b33b9d0435f))
+* **roadmap:** capability-answerability Phase 1 closed, blocker narrowed to one question ([c37af04](https://github.com/event4u-app/agent-config/commit/c37af045ecbf62b31e6878befdc88d763498d7a9))
+* **rules:** delegation-policy names the capability provenance check ([e05de77](https://github.com/event4u-app/agent-config/commit/e05de771d74e8284e2e64e91e33be66b1bd15e23))
+* **contracts:** the host-capability contract documents six fields, not five ([566b984](https://github.com/event4u-app/agent-config/commit/566b984681d1a1a5ef76643fa6f90f297c284e81))
+
+### Tests
+
+* **work-engine:** pin the loop contract and update the changed halt shapes ([eb88aa6](https://github.com/event4u-app/agent-config/commit/eb88aa695121a01c0c1e10de9804f1df3424c334))
+
+### Other
+
+* **carrier:** re-bind to the post-merge scope — the fixed point ([884104c](https://github.com/event4u-app/agent-config/commit/884104c15d8257579a320932c671b489d96e7b06))
+* **carrier:** re-bind the R2 round to the shipping content, all 6 terminal ([9bbfbc3](https://github.com/event4u-app/agent-config/commit/9bbfbc35388f54c77fdae27315025843a6ea79f5))
+* **carrier:** R2 completion review round 1 — 6 findings, all open ([75be940](https://github.com/event4u-app/agent-config/commit/75be940f4f9bcbf71e1f1248467637fc51c6b63b))
+
+Tests: 12818 (+89 since 9.31.0)
+
 ## [9.31.0](https://github.com/event4u-app/agent-config/compare/9.30.0...9.31.0) (2026-08-10)
 
 ### Release highlights

package/dist/agent-src/commands/review/routing.md

@@ -59,9 +59,8 @@ changed-file list. The skill:
 4. Computes overall severity (`high` wins).
 5. Returns the structured block.
 
-If neither data file exists, the skill returns the generic fallback
-from [`reviewer-awareness`](../../rules/reviewer-awareness.md). That is
-valid output — do not invent owners.
+If neither data file exists, the skill returns the generic fallback from
+its own common role vocabulary. That is valid output — do not invent owners.
 
 ### 3. Present the result
 
@@ -121,7 +120,7 @@ After the block, ask:
 ## See also
 
 - [`review-routing`](../../skills/review-routing/SKILL.md) — the resolver
-- [`reviewer-awareness`](../../rules/reviewer-awareness.md) — role vocabulary + data-source rules
+- [`reviewer-awareness`](../../rules/reviewer-awareness.md) — the rule that routes here: paths and risk over seniority, primary + secondary on medium/high
 - [`review-routing-data-format`](../../../docs/guidelines/agent-infra/review-routing-data-format.md)
   — YAML schemas
 - [`create-pr-description`](../../skills/create-pr:description-only/SKILL.md) —

package/dist/agent-src/contexts/communication/rules-auto/reply-close-mechanics.md

@@ -23,6 +23,53 @@ hunts for it. One PR → one URL line.
 - Only when a PR was actually created/updated **this turn**. No PR → no link line.
 - The raw URL (not a masked markdown link) so it is unmistakable and clickable.
 
+## Blocker handover — when the reply leaves work stuck
+
+A work reply that stops because something is waiting on the **user** closes
+with the blocker, in the same one summary, above the PR-URL line. Not a second
+summary — this is what "what remains" looks like when what remains is not yours
+to do.
+
+`agent-config gates --reply` renders it. Call it, paste what it returns, and
+mirror the labels into the user's language. It prints **nothing** when nothing
+is owned by the user, so it is safe to call unconditionally: the "no blocker →
+no block" rule is a property of the command, not a judgement you have to make.
+
+Three obligations the command cannot carry for you:
+
+- **The options ARE the blocker decision — never a choice of substitute work.**
+  This is the measured failure, not a hypothetical one: a session that ended
+  every reply with well-formed numbered options still left its real blockers
+  unresolved for nine rounds, because each option block asked *"which work
+  should I do while your decision sits there"* (option 3 was reliably "nothing
+  more autonomously"). The user answered every one of them with a digit and
+  decided nothing. Offering the agent's next task is not a handover.
+- **The action travels, not a pointer to it.** "The three readings are in the
+  roadmap" is not a decidable option — the user cannot answer without reading
+  first. Where a real choice exists, write the alternatives out, one line each
+  for what speaks for them, then the single recommendation line
+  ([`user-interaction`](../../../rules/user-interaction.md)).
+- **Owner ≠ agent.** If you could clear it with a tool or a command, it is not
+  a blocker, it is unfinished work — do it now. A blocker whose owner is the
+  agent, announced instead of executed, is the promissory close that
+  [`verify-before-complete`](../../../rules/verify-before-complete.md) forbids.
+
+## Why the blocker handover is not a trailing checklist
+
+[`mandated-lines`](../../execution/mandated-lines.md) bans the end-of-reply
+checklist, and this shape has to answer that ban rather than sit beside it.
+
+- **It fires only when owed.** Nothing waiting on the user ⇒ nothing emitted,
+  enforced by the renderer. It never appears as evidence that blockers were
+  checked for — which is exactly the ceremony the ban targets.
+- **The end of the reply IS the decision point here.** The turn stops because
+  the decision is the user's. A line emitted where the decision lands is the
+  rule's own criterion, not an exception to it.
+- **One blocker in full, the rest as a count.** The blocking one is written
+  out; everything else is `N other decisions also wait on you` plus the
+  command. A roster is the failure mode — "twelve decisions across two
+  documents, ~850 lines" produced no decision at all.
+
 ## Why it does not collide with sibling rules
 
 - **`language-and-tone`** last-line rule: a raw URL is language-neutral, so it
@@ -34,6 +81,15 @@ hunts for it. One PR → one URL line.
   last among interactive elements; the PR URL sits below it as the final line and
   is not an "open question," so it does not trip the no-trailing-open-question
   rule.
+- **`ask-when-uncertain`** (one question per turn): reporting N blockers is
+  **zero** questions — it is a report. What the turn may carry is at most ONE
+  numbered-options block, for the one blocking decision, with one recommendation
+  line. Per-blocker questions are the violation that rule names.
+- **`no-cheap-questions`** IL4: the handover ends on `Done when:` — a decidable
+  signal, not "shall I continue once you've sorted this out?".
+- **`scope-control`** post-artifact hard stop: the steps address the **user**.
+  A handover that routes a slash-command back to the agent ("Blocker X — shall I
+  start Phase 1?") is the execution menu that rule forbids, wearing a new label.
 
 ## Failure modes
 
@@ -43,3 +99,12 @@ hunts for it. One PR → one URL line.
   scroll/search.
 - Masking the URL behind link text so it is not obviously the PR.
 - Adding a PR-link line when no PR was created this turn.
+- Closing on a blocker while offering the agent's next task instead of the
+  decision the blocker actually needs.
+- Handing over options as a count ("four options, see the template") or as a
+  file reference — the user cannot answer either without reading first.
+- Listing every open blocker flat, leaving the user to work out which one is
+  the one holding the chain.
+- Reporting the same blocker again, turn after turn, with no resolution path —
+  a repeat with nothing moved is itself the finding, and belongs in the reply
+  as such.

package/dist/agent-src/contexts/execution/host-capability-manifest.md

@@ -16,7 +16,8 @@ A single JSON object, `schema_version: 1`:
   "parallel_spawn": false,
   "status_polling": false,
   "separate_quota_pool": false,
-  "agent_teams": false
+  "agent_teams": false,
+  "worker_respawn": false
 }
 ```
 
@@ -64,11 +65,41 @@ to in-session execution rather than attempting an unsupported primitive.
 | `status_polling` | bool | Monitoring running subagents (progress / completion checks). `false` → fire-and-collect only, no mid-run polling. |
 | `separate_quota_pool` | bool | Quota-arbitrage bonus (Phase 2) — subagents draw from a distinct quota pool than the session. `false` → assume shared quota. |
 | `agent_teams` | bool | Claude Code's experimental multi-instance Agent Teams primitive (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS`). `false` → the [judgment ladder](auto-dispatch-classification.md#judgment-ladder-phase-2--road-to-always-on-orchestration)'s rung 3 (team) degrades to parallel subagents, recorded as `degraded_from: 3`. |
+| `worker_respawn` | bool | The host can kill a running worker and spawn a fresh one that continues the SAME task mid-flight. `false` on every host today, deliberately — set `true` only once OBSERVED, never by inference from spawning and killing existing separately. `false` → degrade to stop-loss behaviour, loudly. |
 
 A field being `true` is a **precondition**, not a mandate: `parallel_spawn:
 true` permits concurrency but the dispatch cap still applies (see
 `subagents.max_parallel` in subagent-configuration.md).
 
+## Provenance — "probe" is a misnomer for five of the six fields
+
+```
+NEVER READ A false FIELD AS "THIS HOST CANNOT DO IT".
+A REGISTRY ROW IS A COMMITTED OBSERVATION, NOT A LIVE CHECK.
+A default FIELD MEANS NOBODY ANSWERED — RENDERED AS false BECAUSE THAT IS THE
+SAFE DEGRADATION, NOT BECAUSE ANYTHING WAS MEASURED.
+```
+
+The six booleans look alike and are not. `HOST_CAPABILITY_REGISTRY` holds
+exactly one row today, so on every other host **all six** fields are the safe
+default — and `agent_teams` is the only field any live check touches. The name
+`probeHostCapabilities` says "detected" about values that were mostly asserted
+at authoring time.
+
+`describeHostCapabilities(hostId)` returns the same manifest plus a
+`sources` map naming, per field, which of the three answered:
+
+| Source | Means | Re-checked at run time |
+|---|---|---|
+| `registry` | this repo observed the capability on this host once and committed it to the table | no |
+| `live-probe` | established in THIS process, from the environment | yes |
+| `default` | nothing answered; `SAFE_DEFAULT` applied | n/a |
+
+`agent-config routing:doctor [--platform <host>]` prints it. Read the
+provenance before treating a `false` as a host limitation: on an unrecognized
+host every field is `default`, which is an absence of knowledge and not a
+measurement.
+
 ## Related
 
 - [`subagent-configuration`](../subagent-configuration.md) — the `subagents.*`

package/dist/agent-src/contexts/execution/orchestration-telemetry.md

@@ -68,6 +68,9 @@ v1 forward-compat rule on unknown fields).
 | `rules_used` | int \| null | **Lean-init extension (L6 demand signal).** Rules the worker actually applied/cited. Validation: never exceeds `rules_carried`. `null` = not measured. Counts only. |
 | `work_tokens` | int \| null | **Dispatch-economy extension.** Tokens the worker consumed AFTER init — the delta from first worker turn to envelope close. With `init_tokens`, yields the `dispatch_floor` ratio (`src/config/dispatch-economy-metrics.json`). Sourced from the transcript ledger (`_lib/cc_transcript.ts` `billable_input` semantics) by the report/backfill, never model-estimated without the tag below. `null` = not measured. |
 | `floor_provenance` | enum \| null | **Dispatch-economy extension.** Provenance of the `init_tokens`/`work_tokens` pair: `measured` (transcript ledger) · `estimated`. Auto-defaults to `estimated` when either field is present untagged — mirrors `token_delta_provenance`. `null` = neither field present. |
+| `model_requested` | string \| null | **Served-model-truth extension (`inbox-harvest-2026-08-b-ledger-truth` Phase 1).** The model id that was ASKED for — the id `tier_chosen`, `tier_source`, `session_tier` and the downshift cost-% are all derived from. `null` = not recorded. Id only, never free-form. |
+| `model_served` | string \| null | **Served-model-truth extension.** The model id the provider reported ANSWERING with. `''`/`null` when the transport reports none (every CLI client) — absent is the honest value, not a defect. Attribution only: never route or tier on it. |
+| `model_divergent` | bool \| null | **Served-model-truth extension.** DERIVED, never supplied: `true` when both ids are present and differ (an alias or provider substitution — every tier-derived figure on this line attributes to a model that never ran), `false` when both are present and match. `null` when either is absent, because a comparison that never happened must not read as "checked, and they matched". |
 | `return_channel_chars` | int \| null | **Dispatch-economy extension (Phase 6.3).** Serialized chars of the tool result returned into the orchestrator context (sync completions, hook-derived count — content never enters the record). Detector for "isolation win refunded through the return channel"; committed cap: `MAX_ENVELOPE_CHARS` (12,000) via `return_channel` in `dispatch-economy-metrics.json`. `null` = async ack. |
 
 These routing + cost fields are additive and optional — a line without them is

package/dist/agent-src/rules/delegation-policy.md

@@ -66,6 +66,12 @@ primitive → run in-session (clean no-op).
 2. **Tier-size** each slice (`lite|medium|high`) per the classification context —
    never the orchestrator's own session tier (the cost win is the per-call
    downsize; see [`subagent-routing`](../contexts/execution/subagent-routing.md)).
+   Where `subagents.model_ceiling` caps the tier and the slice does not fit under
+   it, the worker **escalates and never silently delivers the degraded result**;
+   the orchestrator re-slices, runs in-session, or surfaces the ceiling to the
+   human, and never raises the ceiling itself (class C — `settings:set` refuses
+   it by construction). Absent is *uncapped*, never a low cap. Full contract:
+   [`subagent-boundary § The model ceiling`](../docs/contracts/subagent-boundary.md).
 3. **Dispatch** via the form gate + matching `subagent-orchestration` mode
    (independent → do-in-parallel; ordered → do-in-steps; risk/correctness →
    + judge; UI-heavy → live-app judge, efficacy-gated).
@@ -105,7 +111,17 @@ plus this telemetry). The
 capability gate itself resolves from the committed host registry merged with a
 live environment probe in `src/scripts/_lib/host_capability.ts`
 (`probeHostCapabilities` — capability is a fact about the host, never a
-settings override). What stays
+settings override).
+
+**Never read a `false` capability as a host limitation without checking where it
+came from.** The registry holds one row, so on every other host all six fields
+are the all-false safe default — which records that *nobody answered*, not that
+the host cannot spawn. `agent-config routing:doctor [--platform <host>]` prints
+the value **and** its provenance per field (`registry` = a committed observation
+this repo made once · `live-probe` = established in this process · `default` =
+no answer). Run it before concluding delegation is unavailable here; the
+same-shaped wrong guess about the council is the incident
+[`council-availability`](council-availability.md) exists for. What stays
 model-carried, honestly: the decomposition itself, the per-return
 verification, and every dispatch on hosts without hook slots. The nudges are
 advisory by design — whether they change behaviour is measured by the

package/dist/agent-src/scripts/roadmap_gates.ts

@@ -18,10 +18,34 @@
  * Blocking a pipeline on "the user has an open decision" would turn a
  * visibility aid into a second thing to fight.
  *
+ * `--reply` is the same projection shaped for the END OF A CHAT REPLY rather
+ * than a terminal pane, and it exists because the pull channel above is only
+ * read by someone who already knows to ask. Transcript forensics over three
+ * consumer sessions found five "what do I do now?" follow-ups, every one of
+ * them next to a blocker the agent HAD reported — as a file reference, as a
+ * bare option count, or as a choice of substitute work. What the same corpus
+ * also shows is that a tool's output gets carried into the reply verbatim
+ * (the dashboard's step count appears word-for-word inside eight option
+ * blocks). So the fix is not to make the agent format better from memory; it
+ * is to hand it the finished text. See ADR-222.
+ *
+ * Two properties carry the contract mechanically:
+ *   - Nothing owned by the user open ⇒ EMPTY output. "No blocker → no block"
+ *     stops being a judgement call, so the command is safe to call
+ *     unconditionally at reply-close.
+ *   - Exactly ONE blocker is rendered in full — the one that unblocks most.
+ *     Every other one is a single trailing line. The user is never handed a
+ *     flat list to weigh themselves.
+ *
+ * Labels are English like the rest of the CLI surface; the agent mirrors them
+ * into the user's language when it lifts them into a reply, exactly as it does
+ * for `Recommendation:` / `Empfehlung:`.
+ *
  * Invocation (from project root):
  *   ./agent-config gates            # decisions owned by the user
  *   ./agent-config gates --all      # every open blocker, grouped by owner
  *   ./agent-config gates --json     # machine-readable
+ *   ./agent-config gates --reply    # reply-close form; empty when none
  */
 
 import * as path from 'node:path';
@@ -209,6 +233,76 @@ function render(entries: readonly Entry[], all: boolean): string {
     return lines.join('\n') + '\n';
 }
 
+/**
+ * Reply-close form: the one blocking decision in full, the rest as one line.
+ *
+ * Deliberately narrower than `render()`. `Status` and `Owner` are roadmap-file
+ * metadata that a reader of a reply cannot act on, so they are dropped; what
+ * survives is what the user has to DO and how they will know it is done. The
+ * five-field shape stays where it is enforced — in the roadmap file — and does
+ * not follow the blocker into prose it would only pad.
+ *
+ * Returns '' when nothing is owned by the user, so the caller can append the
+ * result unconditionally and get silence when silence is correct.
+ */
+function renderReply(entries: readonly Entry[]): string {
+    const mine = entries.filter((e) => needsUser(e.blocker.owner));
+    if (mine.length === 0) {
+        return '';
+    }
+
+    // `collectEntries` already sorted by unblocking weight, so the first entry
+    // IS the one that matters most. Picking it here rather than asking the
+    // caller to choose is the point: a flat list is the failure mode.
+    const lead = mine[0] as Entry;
+    const rest = mine.slice(1);
+    const lines: string[] = [];
+
+    lines.push(`Blocked: ${lead.blocker.blocks} — ${lead.roadmapRel}`);
+
+    const steps = regroupTodo(lead.blocker.todo);
+    const doLabel = isLegacy(lead.blocker) ? 'Blocked until:' : 'Do:';
+    if (steps.length === 0) {
+        lines.push(
+            `${doLabel} (no steps recorded — the blocker entry needs a **What to do:** list)`,
+        );
+    } else if (steps.length === 1) {
+        lines.push(...wrap(`${doLabel} ${steps[0] as string}`, WIDTH, '    '));
+    } else {
+        // Emitted as authored, never re-numbered: real blocker entries already
+        // carry their own `1.` / `2.` markers (the CI-enforced `What to do:`
+        // shape), so adding our own would produce "1. 1. …". An entry that
+        // arrives unnumbered stays unnumbered — that is a fact about the
+        // roadmap entry, and papering over it here would hide it from the
+        // person who could fix it.
+        lines.push(`${doLabel}`);
+        for (const s of steps) {
+            lines.push(...wrap(`  ${s}`, WIDTH, '     '));
+        }
+    }
+    lines.push(...wrap(`Done when: ${lead.blocker.resolvedWhen}`, WIDTH, '    '));
+
+    if (rest.length > 0) {
+        // A count, not a roster. Naming all of them reproduces the exact
+        // failure this form exists to end — "zwölf Entscheidungen bei Dir …
+        // rund 850 Zeilen", which the transcript shows produced no decision at
+        // all. The one that blocks is written out above; the rest are one
+        // command away, and saying so is shorter than listing them and more
+        // honest than hiding them.
+        lines.push('');
+        lines.push(
+            ...wrap(
+                `${rest.length} other decision${rest.length !== 1 ? 's' : ''} also wait${rest.length === 1 ? 's' : ''} on you, ` +
+                    'none blocking this — `agent-config gates`.',
+                WIDTH,
+                '    ',
+            ),
+        );
+    }
+
+    return lines.join('\n') + '\n';
+}
+
 function renderJson(entries: readonly Entry[], all: boolean): string {
     const pick = all ? entries : entries.filter((e) => needsUser(e.blocker.owner));
     return (
@@ -270,18 +364,28 @@ function main(argv?: readonly string[]): number {
     const args = argv ?? process.argv.slice(2);
     const all = args.includes('--all');
     const json = args.includes('--json');
+    const reply = args.includes('--reply');
 
     const repoRoot = _resolveRepoRoot(process.cwd());
     const roadmapRoot = path.join(repoRoot, 'agents', 'roadmaps');
     if (!_isDir(roadmapRoot)) {
+        // `--reply` stays silent here too: a project without roadmaps has no
+        // blocker to hand over, and a reply-close line saying so would be the
+        // ceremony the form exists to avoid.
         process.stdout.write(
-            json ? '{"needsYou":0,"other":0,"blockers":[]}\n' : 'No roadmaps directory — nothing to report.\n',
+            reply
+                ? ''
+                : json
+                  ? '{"needsYou":0,"other":0,"blockers":[]}\n'
+                  : 'No roadmaps directory — nothing to report.\n',
         );
         return 0;
     }
 
     const entries = collectEntries(roadmapRoot);
-    process.stdout.write(json ? renderJson(entries, all) : render(entries, all));
+    process.stdout.write(
+        reply ? renderReply(entries) : json ? renderJson(entries, all) : render(entries, all),
+    );
     return 0;
 }
 
@@ -308,5 +412,5 @@ if (_isCliEntry()) {
     process.exitCode = main();
 }
 
-export { main, needsUser, regroupTodo, wrap, collectEntries, render, renderJson };
+export { main, needsUser, regroupTodo, wrap, collectEntries, render, renderJson, renderReply };
 export type { Entry };

package/dist/agent-src/skills/docker/SKILL.md

@@ -83,6 +83,17 @@ Read `docker-compose.yml` / `compose.yaml` to discover the actual service names.
 - Use `make console` for interactive shell access.
 - Use `make console-xdebug` for Xdebug container access.
 
+### Tooling detection
+
+Which test runner and quality commands exist depends on the project shape.
+Check for `artisan` in the project root before picking one:
+
+- **Laravel** (`artisan` present) — `php artisan test`, `vendor/bin/phpstan analyse`, `vendor/bin/rector process`
+- **Plain Composer** (no `artisan`) — `vendor/bin/phpunit`, `vendor/bin/phpstan analyse`, `vendor/bin/rector process`
+
+Either way the command runs inside the container:
+`docker compose exec -T <php-service> <command>`.
+
 ### Image building
 
 - Production images use `target: pro` — no dev dependencies.

package/dist/agent-src/skills/laravel/SKILL.md

@@ -157,6 +157,17 @@ Then add these **Laravel-specific** checks:
 - Extract reusable UI pieces into components/partials when it matches project patterns.
 - Escape output by default and use raw output only when safe and intentional.
 
+## Translations and language files
+
+- **Flat dot-notation keys only** — `'type.daily_report' => 'Daily Report'`.
+  Nested arrays (`'type' => ['daily_report' => …]`) are forbidden: they break
+  key referencing and make a one-line addition a nested diff.
+- Reference with the helper and the same flat key —
+  `__('report.type.daily_report')`, `__('email.report.created.subject', ['number' => $number])`.
+- Every key exists in **every** shipped locale. Adding to `lang/en/` without
+  `lang/de/` is a bug, not a TODO — the app ships to both audiences.
+- Never hardcode a user-visible string in PHP.
+
 ## What NOT to do
 
 - Do not put business logic into controllers, models, or Blade templates.

package/dist/agent-src/skills/review-routing/SKILL.md

@@ -28,8 +28,8 @@ packs:
 
 Do NOT use when:
 
-- The diff is low-risk and no ownership map exists — fall back to
-  [`reviewer-awareness`](../../rules/reviewer-awareness.md) defaults.
+- The diff is low-risk and no ownership map exists — fall back to the
+  common role vocabulary below.
 - A full PR description is requested — route to
   [`create-pr-description`](../create-pr:description-only/SKILL.md) and let
   it call this skill for the routing block.
@@ -55,7 +55,7 @@ Check, in order:
 Parse each with YAML. Validate `version: 1` is present. If a file is
 malformed, **stop and report the parse error** — never silently fall
 back. If neither file exists, emit the generic role-based fallback
-using [`reviewer-awareness`](../../rules/reviewer-awareness.md).
+using the common role vocabulary below.
 
 **Also** pull agent-written signals via the shared abstraction (see
 [`memory-access`](../../../docs/guidelines/agent-infra/memory-access.md)):
@@ -114,12 +114,29 @@ If `ownership-map.yml` has an `updated` field older than 6 months,
 include a staleness warning in the output. Still use the data — just
 flag it.
 
+## Common role vocabulary
+
+The fallback set when no ownership entry matches. Extend it per project, but
+keep these as the shared names — a role nobody else uses routes to nobody.
+
+| Role | Typical focus |
+|---|---|
+| `backend` | business logic, validation, side effects, data integrity |
+| `frontend` | UX, accessibility, client-side state, rendering |
+| `security` | authz, secrets, trust boundaries, data exposure |
+| `infra` / `ops` | rollout, migration safety, observability, retries |
+| `database` | schema changes, indexes, query plans, rollback realism |
+| `domain owner` | business invariants, policy intent, edge-case correctness |
+| `qa` | test coverage, regression scenarios, flake risk |
+
+Roles, never individuals: a package-shipped artifact names `security`, and the
+consumer's CODEOWNERS or ownership map maps that to a person.
+
 ## Validation
 
 Before returning:
 
-1. Every emitted role is either in the common vocabulary
-   ([`reviewer-awareness`](../../rules/reviewer-awareness.md)) or sourced
+1. Every emitted role is either in the common vocabulary above or sourced
    from an ownership entry — never invented.
 2. Every historical-pattern match cites its `id` and `required_test`
    verbatim.
@@ -191,7 +208,7 @@ Data source: <"ownership-map.yml + historical-bug-patterns.yml"
 
 ## See also
 
-- [`reviewer-awareness`](../../rules/reviewer-awareness.md) — role vocabulary + data-source rules
+- [`reviewer-awareness`](../../rules/reviewer-awareness.md) — the rule that routes here: anchor reviewer choice in paths and risk, never seniority
 - [`review-routing-data-format`](../../../docs/guidelines/agent-infra/review-routing-data-format.md)
 - [`create-pr-description`](../create-pr:description-only/SKILL.md)
 - [`judge-test-coverage`](../judge-test-coverage/SKILL.md) — consumes

package/dist/agent-src/templates/agents/agent-project-settings.example.yml

@@ -39,7 +39,7 @@ schema_version: 1
 # CI guard: a release bump of `package.json` must update this value
 # in lockstep — see scripts/check_template_pin_drift.ts (road-to-
 # portable-runtime-and-update-check P3.3).
-agent_config_version: "9.31.0"
+agent_config_version: "9.33.0"
 
 # --- Project identity ---
 project: