task-pipeline-skill 1.94.1 → 1.96.0

package/CHANGELOG.md

@@ -1,3 +1,76 @@
+## v1.96.0 — 2026-10-15
+
+Source candidate; not published.
+
+Guards: 439 → **447**; property checks 15 → **15**.
+
+An iteration now stops at a finish line instead of when a search runs dry. The new
+`references/finish-line.md` fixes a contract at intake — objective, exit checks run on
+the released, installed or deployed artefact, scope, budget and base — in the brief's
+`## Finish line`. Every finding is triaged when found: blocking only by one of four
+tests (a red exit check, a hotfix-lane entry, a regression against base, a verified
+REQ or published claim false on the artefact), deferred to the board with its
+evidence, or noise as one ledger line. Severity words and effort never change the
+class. An iteration is done after two consecutive rounds with no new blocking
+finding; it stops at `run.finish.maxRounds` (default 3) or `maxReleases` (default 2)
+with each open blocker handed back as a `needs-operator` row, and diverging rounds go
+to the loop guard. Stopping is not idle: the next iteration starts from the board by
+priority, never by re-opening the closed one.
+
+`scripts/waves.py finish` computes the verdict from the inventory's new optional item
+fields (`triage`, `test`, `round`, `base_repro`, plus `blast` and `rung` for known
+risks) and prints the finish block; deferred and noise items never change it. The round
+count is explicit — `--rounds` or the run ledger's new `round:` lines, which must agree
+with the inventory — because a clean round leaves no item to count. Done needs the exit
+checks supplied and green (`--checks`), stays within `maxRounds` (at least 2) unless the
+operator's go is passed, and `next:` ranks every open non-blocking row by priority,
+never by freshness. B2 also covers a defect that would be a hotfix-lane entry once
+released; a defect in a node's own diff stays with review. Stage 0's
+gate requires the finish line filled; stage 10's requires the `finish:` line printed.
+Iteration, waves, loop-guard, audit, continuity, review and progress doctrine point to
+the one rule, and seven validator guards hold its vocabulary, budgets, hotfix set,
+brief fields, hand-back field and script enums equal across their surfaces.
+
+## v1.95.0 — 2026-10-13
+
+Source candidate; not published.
+
+Guards: 438 → **439**; property checks 15 → **15**.
+
+The default stage list keeps every full gate and routes each stage to its own
+procedure before work on entry or resume. Custom profiles keep their own stages
+and doctrine. The split preserves the original stage text and reduces the measured
+entry reading component; it does not claim a native-host or billed-token result.
+Scenario artifacts remain mandatory for user-facing work, while an equivalent
+provider or the documented inline fallback can supply them without installing a
+specific companion plugin. The new route refusal and relocated source checks keep
+these obligations addressable after the split.
+
+Checkpoint recovery now follows the selected project profile's declared stage order,
+including custom names and nonconsecutive ids. Malformed or changed profiles refuse
+instead of silently injecting default stages into a saved workflow. Run-local profile
+binding survives record/retry; relocated ledgers can name their project root explicitly.
+This is an offline-tested payload correction, not a live Observatory acceptance claim.
+
+Owner release preparation now records an unpublished local annotated tag before the
+complete suite, binds its exact source/context/evidence, and publishes only the
+verified annotation to one destination. The existing release hook recognizes
+explicit tag-destination refspecs. Mechanical evidence does not confer external
+authority, native interception or successful registry publication.
+
+Test runners use one safely opened family scratch lock across TMPDIR settings and
+owners, matching their shared fixed scratch paths. The lock now stays held while a
+plant's Bash or its synchronously writing child is alive, even if the runner itself is
+killed; an interrupted runner signals and drains its own process groups before it
+closes its copy, and on macOS a group of exited-but-unreaped members no longer aborts
+that cancellation. An interrupted run no longer leaves its repository snapshot in
+TMPDIR. Existing older runner versions, deliberately detached descendants and direct
+plant invocation remain outside that mechanism.
+
+The owner-gate helpers' seam headers declare `diverges: none` with their extraction
+scope on a separate line, so the umbrella's shared-copy check reads them as identical
+to the other members' copies.
+
 ## v1.94.1 — 2026-10-13
 
 Records the missing retrospective declarations that stopped the v1.94.0 release

package/CONTRIBUTING.md

@@ -51,6 +51,38 @@ To try your change in a real agent:
 node bin/task-pipeline.js --force   # the same, through the npm installer
 ```
 
+## Owner release admission
+
+For this repository's release, the unpublished annotated candidate tag must exist
+locally on the accepted commit **before** the complete suite runs. A green untagged
+run is insufficient: inspect whether release-stamp checks actually looked.
+`pipeline.json` stage7 and standing instruction R-010 in `docs/evidence/retro.md`
+use this same order; R-004 requires the next operation to depend on gate success.
+
+In a standalone full clone of the owning source repository, use the owner-only
+`scripts/release_candidate.py`. Set `candidate_tag` to the chosen unpublished
+version and `actual_project_root` to the same-source project holding the real
+current run context. These are operator/run inputs, not generated approval:
+
+```bash
+python3 scripts/release_candidate.py prepare --tag "$candidate_tag" --context-root "$actual_project_root" &&
+python3 scripts/release_candidate.py check --tag "$candidate_tag" &&
+python3 scripts/release_candidate.py publish --tag "$candidate_tag"
+```
+
+`prepare` creates and binds the owned local annotation; `check` runs the fixed
+`npm run test:all` with that tag visible and retains its exact evidence.
+`publish` requires faithful bound context, the existing release hook, unchanged
+source/tag/evidence and the verified single destination/ref. The helper does not
+verify external authorization or create a ledger. Without faithful context,
+prepare/check remain usable and publication refuses. Never move a published tag;
+changed or ambiguous state requires read-only reconciliation before another action.
+
+Its PUBLISHED state confirms the tag's remote object and peel, not successful npm
+publication. Watch every release job and verify the published payload separately.
+The helper and private Git-directory receipts belong to the owner checkout and
+are not a plugin API or part of the installed skill.
+
 ## Repository layout
 
 | Path | What it is |

package/HOW-IT-WORKS.md

@@ -65,9 +65,10 @@ because it rots the moment the vendor ships a new one.
 
 **Companions.** `super-ux`, `copywriting`, `sheleg-design`, `graphify`, the wiki.
 The detection block prints once. A missing companion states its fallback and
-**does not block** — the single exception being the stage-3 UX track on
-user-facing work, where shipping without it is a decision someone has to make out
-loud.
+**does not block on installation**. For user-facing work, stage 3 requires a valid
+scenario artifact under the [provider rule](plugins/task-pipeline/skills/task-pipeline/references/companion-skills.md).
+Unavailable checks are named as NOT_RUN; a fallback is not evidence that a missing
+tool ran.
 
 ---
 

package/README.md

@@ -167,9 +167,9 @@ ledgers, so the link is the repository's rather than the package's.
 The doctrine each stage runs on ships inside the skill. Nothing to install for it,
 nothing to resolve at preflight, no version skew with someone else's repo, and
 **no stage blocks on an install** — stage 1 falls back to web search, the wiki and
-the code graph are recommendations. The one exception is deliberate and named: on a
-user-facing task the stage-3 UX track requires super-ux, and the spec gate stops
-until it is installed.
+the code graph are recommendations. On user-facing tasks the stage-3 UX gate
+requires a valid scenario artifact. The preferred provider, an equivalent provider
+and the inline fallback satisfy the same [provider contract](plugins/task-pipeline/skills/task-pipeline/references/companion-skills.md).
 
 | Stage | Built-in doctrine |
 |---|---|
@@ -189,6 +189,7 @@ until it is installed.
 | 10 Acceptance | [`acceptance.md`](plugins/task-pipeline/skills/task-pipeline/references/acceptance.md) — REQ coverage table, evidence rules, the closing question |
 | 10 + any audit | [`audit.md`](plugins/task-pipeline/skills/task-pipeline/references/audit.md) — the L0→L7 ladder and its seams, axis rotation, ratchets, proven checks |
 | any loop | [`loop-guard.md`](plugins/task-pipeline/skills/task-pipeline/references/loop-guard.md) — churn detection, caps, the break protocol |
+| when an iteration stops | [`finish-line.md`](plugins/task-pipeline/skills/task-pipeline/references/finish-line.md) — a contract fixed at intake (objective, exit checks on the artefact, scope, budget, base), every finding triaged when found — blocking, deferred or noise — and a stop at two rounds with no new blocking finding or at the budget, computed by `waves.py finish` |
 | every gate + stage 10 | [`residue.md`](plugins/task-pipeline/skills/task-pipeline/references/residue.md) — what the run leaves **running** and leaves **behind**: eight classes enumerated by class rather than by one tool, `holds: N` beside every verdict, and a teardown that ends what this run started and only reports what it did not |
 | run-wide reporting | [`progress.md`](plugins/task-pipeline/skills/task-pipeline/references/progress.md) — the header block at task start and the one-line iteration close: the stage rail computed from the project's own `pipeline.json`, every number borrowed from the gate that measured it |
 | run-wide pacing | [`continuity.md`](plugins/task-pipeline/skills/task-pipeline/references/continuity.md) — the loop mode (`run.loop`, default off, never collapses a manual gate) and the context budget (fires on a harness signal, never on an estimate) |
@@ -634,8 +635,8 @@ must say so.
 ### Held to Anthropic's own Skill authoring guidance
 
 Audited against the four Agent Skills pages. Most of it already held — `name`
-13/64 chars, `description` 887/1024 chars, `SKILL.md` 270/500 lines, all 41 references
-linked **directly** from `SKILL.md`, and the bundle far under the 30 MB ceiling. What
+13/64 chars, `description` 887/1024 chars, `SKILL.md` 275/500 lines, all 53 references
+reachable from `SKILL.md` through explicit reference routes, and the bundle far under the 30 MB ceiling. What
 did not, now does:
 
 - **Every reference over 100 lines carries a `## Contents` list**, and the list is
@@ -971,7 +972,7 @@ skill. Four optional companions make individual stages better:
 
 | Companion | For | Required? |
 |---|---|---|
-| [super-ux](https://github.com/ssheleg/super-ux) | the stage-3 UX track | only for user-facing tasks |
+| [super-ux](https://github.com/ssheleg/super-ux) | the stage-3 UX track | preferred provider; valid scenario artifact required for user-facing tasks |
 | context7 (MCP) | stage-1 docs study | recommended — web-search fallback |
 | [obsidian-wiki](https://github.com/ar9av/obsidian-wiki) | stage-0 harvest + stage-9 sync | recommended — never a gate |
 | [graphify](https://github.com/Graphify-Labs/graphify) | stage-0 reach queries + stage-9 refresh + the graph↔docs divergence check | recommended — never a gate |
@@ -987,7 +988,18 @@ recommendation, so you arm the whole run in one exchange. Detail:
 | File | What's in it |
 |---|---|
 | [`SKILL.md`](plugins/task-pipeline/skills/task-pipeline/SKILL.md) | the orchestrator: how to run, the stage table, the model decision |
-| [`references/stages.md`](plugins/task-pipeline/skills/task-pipeline/references/stages.md) | per-stage detail and the exact gate criteria |
+| [`references/stages.md`](plugins/task-pipeline/skills/task-pipeline/references/stages.md) | complete gate criteria and exact per-stage detail routes |
+| [`references/stage-00-intake.md`](plugins/task-pipeline/skills/task-pipeline/references/stage-00-intake.md) | stage 0 procedure, read on entry or resume |
+| [`references/stage-01-docs-study.md`](plugins/task-pipeline/skills/task-pipeline/references/stage-01-docs-study.md) | stage 1 procedure, read on entry or resume |
+| [`references/stage-02-brainstorm.md`](plugins/task-pipeline/skills/task-pipeline/references/stage-02-brainstorm.md) | stage 2 procedure, read on entry or resume |
+| [`references/stage-03-spec.md`](plugins/task-pipeline/skills/task-pipeline/references/stage-03-spec.md) | stage 3 procedure, read on entry or resume |
+| [`references/stage-04-plan.md`](plugins/task-pipeline/skills/task-pipeline/references/stage-04-plan.md) | stage 4 procedure, read on entry or resume |
+| [`references/stage-05-dev.md`](plugins/task-pipeline/skills/task-pipeline/references/stage-05-dev.md) | stage 5 procedure, read on entry or resume |
+| [`references/stage-06-tests.md`](plugins/task-pipeline/skills/task-pipeline/references/stage-06-tests.md) | stage 6 procedure, read on entry or resume |
+| [`references/stage-07-lint-deploy.md`](plugins/task-pipeline/skills/task-pipeline/references/stage-07-lint-deploy.md) | stage 7 procedure, read on entry or resume |
+| [`references/stage-08-post-deploy.md`](plugins/task-pipeline/skills/task-pipeline/references/stage-08-post-deploy.md) | stage 8 procedure, read on entry or resume |
+| [`references/stage-09-docs-wiki.md`](plugins/task-pipeline/skills/task-pipeline/references/stage-09-docs-wiki.md) | stage 9 procedure, read on entry or resume |
+| [`references/stage-10-acceptance.md`](plugins/task-pipeline/skills/task-pipeline/references/stage-10-acceptance.md) | stage 10 procedure, read on entry or resume |
 | [`references/doctrine-map.md`](plugins/task-pipeline/skills/task-pipeline/references/doctrine-map.md) | which reference owns which stage — the map SKILL.md used to carry inline |
 | [`references/artifacts.md`](plugins/task-pipeline/skills/task-pipeline/references/artifacts.md) | the canonical document layout each stage writes to |
 | [`references/conventions.md`](plugins/task-pipeline/skills/task-pipeline/references/conventions.md) | how stages 6–10 read the host project's `CLAUDE.md`, and how the documentation regime is detected |

package/SKILL-CARD.md

@@ -12,9 +12,9 @@ harmless.
 |---|---|
 | **Purpose** | Runs a substantial task through ten gated delivery stages — intake grill, docs study, brainstorm, spec, plan, subagent build, tests, lint/deploy, post-deploy, docs+registers, acceptance — refusing to advance until each gate passes |
 | **Owner** | ssheleg ([github.com/ssheleg/task-pipeline](https://github.com/ssheleg/task-pipeline)) |
-| **Version** | 1.94.1 |
+| **Version** | 1.96.0 |
 | **Surface** | Claude Code (filesystem skill + plugin) and the vercel `skills` CLI. **Not** uploaded to the Skills API; custom Skills do not sync across surfaces |
-| **Dependencies** | None required. Optional: `context7` (MCP), `figma` (MCP), super-ux, agent-sync, graphify, obsidian-wiki, and **one of two browser channels** — `playwright` (CLI or MCP) or `chrome-devtools` (MCP); either satisfies the browser step and neither is required. Every stage's doctrine ships in-repo; the one conditional requirement is super-ux for the stage-3 UX track on a user-facing task |
+| **Dependencies** | None required. Optional: `context7` (MCP), `figma` (MCP), super-ux, agent-sync, graphify, obsidian-wiki, and **one of two browser channels** — `playwright` (CLI or MCP) or `chrome-devtools` (MCP); either satisfies the browser step and neither is required. Every stage's doctrine ships in-repo; user-facing stage 3 requires a valid scenario artifact; super-ux is preferred, with equivalent-provider and inline-fallback paths under the provider contract |
 | **Evaluation status** | Suite authored, 5 categories. One recorded run, **self-observed by the author**; **zero blind runs on zero of three models** — the split, and the numbers, live in [`evals/RESULTS.md`](evals/RESULTS.md) and are computed by `evals/run.py` |
 
 ## Risk-tier disclosure

package/evals/RESULTS.md

@@ -1,10 +1,11 @@
 # Evaluation results — task-pipeline
 
 **Status: three suites authored (task-pipeline, evidence-docs, project-audit);
-one self-observed run and, since 2026-08-31, three blind trigger runs — one per
-model (haiku, sonnet, opus).** The instruction-following cases remain unexecuted
-and say so per run, because they need a full interactive session — a skip is not
-a pass, and a guessed verdict is worse than a vacant row.
+one self-observed run, three blind trigger runs on 2026-08-31 — one per model
+(haiku, sonnet, opus) — and three more on 2026-10-14 over the release-iteration
+phrasings (TRIG-11, TRIG-12, NOTRIG-09), one per model.** The instruction-following
+cases remain unexecuted and say so per run, because they need a full interactive
+session — a skip is not a pass, and a guessed verdict is worse than a vacant row.
 
 **The numbers below are computed, not asserted.** `python3 evals/run.py` counts the
 suite and the dated run headings in this file. A value typed here that disagrees with
@@ -40,11 +41,11 @@ or it belongs in a check.
 
 | Metric | Value | Computed by | As of |
 |---|---|---|---|
-| Evals authored | 48 (three suites: task-pipeline 30, evidence-docs 9, project-audit 9) | `python3 evals/run.py` → `suite: N evals` | 2026-10-12 |
+| Evals authored | 55 (three suites: task-pipeline 37, evidence-docs 9, project-audit 9) | `python3 evals/run.py` → `suite: N evals` | 2026-10-14 |
 | Categories covered | 5 of 5, per suite | the suite's own `category` fields | 2026-08-31 |
-| Dated runs recorded | **4** | `python3 evals/run.py` → `recorded runs: N` | 2026-08-31 |
-| …of those, **blind** | **3** | run headings not marked `self-observed` | 2026-08-31 |
-| Models exercised blind | **3 of 3** | distinct models across blind runs | 2026-08-31 |
+| Dated runs recorded | **7** | `python3 evals/run.py` → `recorded runs: N` | 2026-10-14 |
+| …of those, **blind** | **6** | run headings not marked `self-observed` | 2026-10-14 |
+| Models exercised blind | **3 of 3** | distinct models across blind runs | 2026-10-14 |
 
 **The last three rows are the honest state of this skill's behavioural evidence**, and
 the split matters more than the total: a run the author watched, knowing the expected
@@ -84,6 +85,52 @@ model NAMED the skill; it does not prove a full session loaded and obeyed the
 doctrine — the INSTR cases need exactly that and are recorded as **not
 reproducible from this harness**, not guessed.
 
+## 2026-10-14 · haiku · blind trigger probes, subagent protocol
+
+**3 of 3 scored cases passed** — the two release-iteration triggers and their
+explanation control, added by release iteration 1 (node M-4, USR-015). Method as
+2026-08-31 below, with two differences, stated rather than implied: the offered
+list was the family's **38** skills (the family grew from 28), built once from the
+members' `SKILL.md` frontmatters on 2026-10-14 (sha256 `12115a8b24f1…`); and each
+subagent reported the model id from its own system context, recorded here as the
+model that answered: `claude-haiku-5-5`. The other new cases of that node
+(INSTR-09…13, TP-OUT-006/007) were not run: the INSTR cases need a full interactive
+session, and the two outcome cases need an executor driving an arm in a sandbox —
+their fixtures' command checks are proven to pass and to fail by
+`test/audit_regressions/usr_015_evals.py`, which is not a run of the case.
+
+| id | verdict | what happened |
+|---|---|---|
+| TRIG-11 | pass | named `task-pipeline` — cited the description's 'waves'/'волнами' |
+| TRIG-12 | pass | named `task-pipeline` — cited 'итерация релиза' in the description |
+| NOTRIG-09 | pass | answered `none` — the description excludes explaining |
+
+## 2026-10-14 · sonnet · blind trigger probes, subagent protocol
+
+**3 of 3 scored cases passed.** Same protocol and list as the haiku run above;
+the answering model reported `claude-sonnet-5-5`.
+
+| id | verdict | what happened |
+|---|---|---|
+| TRIG-11 | pass | named `task-pipeline` — matched «закрой их волнами» to the waves mode |
+| TRIG-12 | pass | named `task-pipeline` — matched the 'release iteration' trigger |
+| NOTRIG-09 | pass | answered `none` — a plain explanation question |
+
+## 2026-10-14 · opus · blind trigger probes, subagent protocol
+
+**3 of 3 scored cases passed.** Same protocol and list as the haiku run above;
+the answering model reported `claude-opus-5-5[1m]`.
+
+| id | verdict | what happened |
+|---|---|---|
+| TRIG-11 | pass | named `task-pipeline` — the board closed «волнами» |
+| TRIG-12 | pass | named `task-pipeline` — the board-closing release loop |
+| NOTRIG-09 | pass | answered `none` — named the trigger phrase and the explaining exclusion |
+
+INSTR-09…13 and TP-OUT-006/007: **not run** in any of the three 2026-10-14 runs,
+for the reasons given under the haiku run. A trigger `pass` still means only that
+the model NAMED the skill.
+
 ## 2026-08-31 · haiku · blind trigger probes, subagent protocol
 
 **39 of 42 scored cases passed** across the three suites' trigger-shaped

package/evals/cases/task-pipeline.json

@@ -186,6 +186,145 @@
      }
     ]
    }
+  },
+  {
+   "schema_version": "outcome-case/1",
+   "id": "TP-OUT-006-waves-validate-refuses-unclaimed-item",
+   "skill": "task-pipeline",
+   "prompt": {
+    "text": "Wave 0 of `/task-pipeline waves`: the inventory, module table and wave plan are the frozen files under evals/fixtures/waves-unclaimed/. Check that every item lands on a node with the skill's own inventory validator, without editing the fixture, and write waves-validate.md with the command you ran, its exit code and what it reported (USR-015).",
+    "files": [
+     {
+      "path": "evals/fixtures/waves-unclaimed/inventory.json",
+      "sha256": "8ffb7e0f291c8cfb5b77910424b3dac55459e8f6b58f7e63343fcef258bb2102"
+     },
+     {
+      "path": "evals/fixtures/waves-unclaimed/modules.json",
+      "sha256": "9d13ac48c1c49d0bd315ed5643b68de993d1f33ee125e1e23718f6c60fe296d5"
+     },
+     {
+      "path": "evals/fixtures/waves-unclaimed/plan.json",
+      "sha256": "cc42a367ac8a966214beb21d8459c04e3704c461f220dd3a34d7f5fca315dbc8"
+     },
+     {
+      "path": "evals/fixtures/waves-unclaimed/expect-refusal.sh",
+      "sha256": "857a48783bdb89ff82c4d16d5adb93dc2159e3d89cb5b8dea069fa0439d60517"
+     }
+    ]
+   },
+   "environment": {
+    "model": "inherit",
+    "host": "any",
+    "case_digest": "480a16d5aef3efa8ae30e872e15948d2fa4906fd50211803295e5084d7403fe8"
+   },
+   "checks": {
+    "tool": [
+     {
+      "name": "python3 present",
+      "command": "python3 -c 'pass'"
+     },
+     {
+      "name": "bash present",
+      "command": "bash -c 'true'"
+     }
+    ],
+    "load_trace": {
+     "expect_loaded": [
+      "task-pipeline"
+     ],
+     "expect_not_loaded": []
+    },
+    "outcome": [
+     {
+      "name": "the validator still refuses the frozen fixture (inverted through the wrapper)",
+      "kind": "command-exit-0",
+      "target": "bash evals/fixtures/waves-unclaimed/expect-refusal.sh"
+     },
+     {
+      "name": "the record exists",
+      "kind": "artifact-exists",
+      "target": "waves-validate.md"
+     },
+     {
+      "name": "the record names the item that lands nowhere",
+      "kind": "artifact-contains",
+      "target": "waves-validate.md",
+      "expect": "B-103"
+     },
+     {
+      "name": "the record carries the refusal's exit code",
+      "kind": "artifact-contains",
+      "target": "waves-validate.md",
+      "expect": "exit 1"
+     }
+    ]
+   }
+  },
+  {
+   "schema_version": "outcome-case/1",
+   "id": "TP-OUT-007-lessons-query-fires-on-fixture",
+   "skill": "task-pipeline",
+   "prompt": {
+    "text": "Stage 0 of a run for 'add a retry policy to the webhook handler'. The machine's local lesson index is the frozen file evals/fixtures/lessons/index.jsonl and the session lists no shared lesson store. Read the lessons source the way the skill's harvest does, and write ledger.md with the source-ledger lines for both lesson layers and the citation of every lesson that fires (USR-015).",
+    "files": [
+     {
+      "path": "evals/fixtures/lessons/index.jsonl",
+      "sha256": "6b73a4345e8f361a565e15a93a1fa204a141f791b82946a08260d475b2aef28d"
+     },
+     {
+      "path": "evals/fixtures/lessons/expect-match.sh",
+      "sha256": "bed8b0b6363128108ff6a6985240d4b1fdeda01448ddc32ef32caa43c4e2a814"
+     }
+    ]
+   },
+   "environment": {
+    "model": "inherit",
+    "host": "any",
+    "case_digest": "eef134f07ba724082236b6a5977009dd744076ca7391fd562fe562bdd171cd88"
+   },
+   "checks": {
+    "tool": [
+     {
+      "name": "python3 present",
+      "command": "python3 -c 'pass'"
+     },
+     {
+      "name": "bash present",
+      "command": "bash -c 'true'"
+     }
+    ],
+    "load_trace": {
+     "expect_loaded": [
+      "task-pipeline"
+     ],
+     "expect_not_loaded": []
+    },
+    "outcome": [
+     {
+      "name": "the query over a copy of the fixture fires the webhook lesson only",
+      "kind": "command-exit-0",
+      "target": "bash evals/fixtures/lessons/expect-match.sh"
+     },
+     {
+      "name": "the ledger cites the lesson that fires",
+      "kind": "artifact-contains",
+      "target": "ledger.md",
+      "expect": "[lesson L-70cf4d4825df]"
+     },
+     {
+      "name": "the ledger states the local layer's count",
+      "kind": "artifact-contains",
+      "target": "ledger.md",
+      "expect": "local lessons: 1 match"
+     },
+     {
+      "name": "the ledger states the shared layer is absent",
+      "kind": "artifact-contains",
+      "target": "ledger.md",
+      "expect": "shared lessons: absent"
+     }
+    ]
+   }
   }
  ]
 }

package/evals/fixtures/lessons/expect-match.sh

@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+# TP-OUT-007's command check: `lessons.py query` over this fixture index must
+# fire the webhook lesson (L-70cf4d4825df) on the task's nouns and leave the
+# unrelated cache lesson (L-8487303c010c) out. The index is queried from a
+# temporary copy, because the script takes a lock file beside the index and a
+# check must not write into the tree it reads.
+set -u
+here="$(cd "$(dirname "$0")" && pwd)"
+scripts="${TASK_PIPELINE_SCRIPTS:-$here/../../../plugins/task-pipeline/skills/task-pipeline/scripts}"
+if [ ! -f "$scripts/lessons.py" ]; then
+  echo "expect-match: lessons.py not found under $scripts (set TASK_PIPELINE_SCRIPTS)" >&2
+  exit 2
+fi
+tmp="$(mktemp -d)"
+cp "$here/index.jsonl" "$tmp/index.jsonl"
+out="$(python3 "$scripts/lessons.py" query webhook retry handler --index "$tmp/index.jsonl")"
+rc=$?
+rm -f "$tmp/index.jsonl" "$tmp/.lock"
+rmdir "$tmp"
+if [ "$rc" -ne 0 ]; then
+  echo "expect-match: lessons.py query exited $rc" >&2
+  exit 1
+fi
+case "$out" in
+  *"[lesson L-8487303c010c]"*) echo "expect-match: the unrelated lesson fired" >&2; exit 1 ;;
+esac
+case "$out" in
+  *"[lesson L-70cf4d4825df]"*) exit 0 ;;
+  *) echo "expect-match: the webhook lesson did not fire: $out" >&2; exit 1 ;;
+esac

package/evals/fixtures/lessons/index.jsonl

@@ -0,0 +1,2 @@
+{"check": "a test that renames and reads back through the cache", "classKey": "cache-invalidation-on-rename", "grade": 2, "id": "L-8487303c010c", "nouns": ["cache", "invalidation", "rename"], "origins": [{"commit": "2222222222222222222222222222222222222222", "lesson": {"check": "a test that renames and reads back through the cache", "classKey": "cache-invalidation-on-rename", "grade": 2, "nouns": ["cache", "rename", "invalidation"], "stages": {"owned": 4, "surfaced": 6}, "title": "a renamed record kept serving its old cached name", "trigger": "a rename that does not touch the cache key"}, "project": "p-0a1b2c3d4e5f", "retro": "docs/evidence/retro.md#cache-rename"}], "projects": 1, "schema": "lesson-index/1", "seen": 1, "stages": {"owned": 4, "surfaced": 6}, "status": "local", "title": "a renamed record kept serving its old cached name", "trigger": "a rename that does not touch the cache key"}
+{"check": "a test that delivers the same event twice and asserts one effect", "classKey": "webhook-retry-without-idempotency-key", "grade": 2, "id": "L-70cf4d4825df", "nouns": ["delivery", "idempotency", "retry", "webhook"], "origins": [{"commit": "1111111111111111111111111111111111111111", "lesson": {"check": "a test that delivers the same event twice and asserts one effect", "classKey": "webhook-retry-without-idempotency-key", "grade": 2, "nouns": ["webhook", "retry", "idempotency", "delivery"], "stages": {"owned": 4, "surfaced": 6}, "title": "a retried delivery applied twice because the handler kept no idempotency key", "trigger": "a handler that retries or receives redelivered events"}, "project": "p-0a1b2c3d4e5f", "retro": "docs/evidence/retro.md#webhook-retry"}], "projects": 1, "schema": "lesson-index/1", "seen": 1, "stages": {"owned": 4, "surfaced": 6}, "status": "local", "title": "a retried delivery applied twice because the handler kept no idempotency key", "trigger": "a handler that retries or receives redelivered events"}

package/evals/fixtures/waves-unclaimed/expect-refusal.sh

@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+# TP-OUT-006's command check: `waves.py validate` must REFUSE this fixture.
+# The inventory holds three open items; the plan's only node closes two, so
+# B-103 lands nowhere. Exit 0 means the refusal happened and named B-103;
+# any other result — including the validator accepting the fixture, or the
+# script not being found — is non-zero, so a missing tool can never pass.
+set -u
+here="$(cd "$(dirname "$0")" && pwd)"
+scripts="${TASK_PIPELINE_SCRIPTS:-$here/../../../plugins/task-pipeline/skills/task-pipeline/scripts}"
+if [ ! -f "$scripts/waves.py" ]; then
+  echo "expect-refusal: waves.py not found under $scripts (set TASK_PIPELINE_SCRIPTS)" >&2
+  exit 2
+fi
+err="$(python3 "$scripts/waves.py" validate \
+  --inventory "$here/inventory.json" \
+  --modules "$here/modules.json" \
+  --plan "$here/plan.json" 2>&1 >/dev/null)"
+rc=$?
+if [ "$rc" -ne 1 ]; then
+  echo "expect-refusal: waves.py validate exited $rc, expected 1" >&2
+  exit 1
+fi
+case "$err" in
+  *B-103*) exit 0 ;;
+  *) echo "expect-refusal: the refusal did not name B-103: $err" >&2; exit 1 ;;
+esac

package/evals/fixtures/waves-unclaimed/inventory.json

@@ -0,0 +1,33 @@
+{
+  "schema": "inventory/1",
+  "topic": "eval-fixture-unclaimed-item",
+  "items": [
+    {
+      "id": "B-101",
+      "title": "export endpoint times out past ten thousand rows",
+      "area": "export",
+      "kind": "bug",
+      "severity": "high",
+      "evidence": "src/export.py:42 buffers the whole result set before the first byte",
+      "proposed_fix": "stream rows in pages"
+    },
+    {
+      "id": "B-102",
+      "title": "export CSV header omits the timezone",
+      "area": "export",
+      "kind": "gap",
+      "severity": "low",
+      "evidence": "src/export.py:17 writes created_at without an offset",
+      "proposed_fix": "write ISO 8601 with offset"
+    },
+    {
+      "id": "B-103",
+      "title": "settings page loses unsaved edits on navigation",
+      "area": "settings",
+      "kind": "bug",
+      "severity": "medium",
+      "evidence": "web/settings.tsx:88 drops the draft on route change",
+      "proposed_fix": "keep the draft in route state"
+    }
+  ]
+}

package/evals/fixtures/waves-unclaimed/modules.json

@@ -0,0 +1,4 @@
+{
+  "export": ["B-101", "B-102"],
+  "settings": ["B-103"]
+}

package/evals/fixtures/waves-unclaimed/plan.json

@@ -0,0 +1,5 @@
+{
+  "nodes": [
+    {"id": "N-001", "wave": 1, "closes": ["B-101", "B-102"]}
+  ]
+}