fix(prose-tests): the stop hook records, and names the model that walked

.claude/agents/prose-asserter.md

@@ -83,6 +83,10 @@ the actions.
 
 Return exactly this and nothing else:
 
+0. **Model** — the model named on the recorded `SubagentStop` line, quoted
+   as recorded. If no such line exists, say `unrecorded`. A verdict is
+   only as trustworthy as the model that produced the walk, so it is
+   stated before anything is judged, never inferred, and never omitted.
 1. **Path** — one line per expected step: PASS or FAIL, each PASS quoting
    the transcript line that shows it, each FAIL stating what is missing
    or contradicting.

.claude/agents/prose-orchestrator.md

@@ -1,6 +1,6 @@
 ---
 name: prose-orchestrator
-description: Runs one prose-test case end to end — builds the world, dispatches the walker, computes the delta, dispatches the asserter, escalates a failure to Opus, destroys the world — and returns just the verdict. Dispatched by the /prose-test skill, one per case.
+description: Runs one prose-test case end to end — builds the world, dispatches the walker, computes the delta, dispatches the asserter, reruns a failure from a fresh world to confirm it, destroys the world — and returns just the verdict. Dispatched by the /prose-test skill, one per case.
 tools: Bash, Read, Agent
 model: sonnet
 hooks:
@@ -90,6 +90,7 @@ Return exactly this and nothing else:
 
 ```
 CASE: <case-id>
+MODEL: <the model the asserter reported, or `unrecorded`>
 VERDICT: PASS | FAIL | FLAKY | INVALID | HARNESS ERROR
 PATH: <n>/<total> steps passed
 WORLD: PASS | FAIL

.claude/skills/prose-test/SKILL.md

@@ -38,8 +38,14 @@ about an expected result can leak into a later dispatch.
 ## Step 3: Collate
 
 Report a verdict table from what the orchestrators returned: case id,
-verdict, path steps passed, world, markers. Quote the evidence line for
-every failure.
+model, verdict, path steps passed, world, markers. Quote the evidence
+line for every failure.
+
+The model column comes from the harness record, not from any agent's
+say-so. An edited agent definition does not reach a running session until
+its plugins are reloaded, so a run can silently use the previous model —
+if the column disagrees with what the agent definitions declare, say so
+and treat every verdict in the run as unproven.
 
 A `FLAKY` verdict means a failure did not reproduce on a second run from
 a fresh world — surface both runs, resolve neither.

package.json

@@ -7,7 +7,7 @@
     "build": "node build/knowledge.build.js",
     "knowledge:repl": "node scripts/knowledge-repl.js",
     "typecheck": "tsc -p tsconfig.json",
-    "test": "node --test tests/scripts/test-render.cjs tests/scripts/test-engine-gateway.cjs tests/scripts/test-engine-epic-projections.cjs tests/scripts/test-engine-start-projections.cjs tests/scripts/test-engine-workunit-projections.cjs tests/scripts/test-engine-discussion-map.cjs tests/scripts/test-engine-discovery-map.cjs tests/scripts/test-engine-tasks.cjs tests/scripts/test-engine-render-surfaces.cjs tests/scripts/test-engine-transactions.cjs tests/scripts/test-engine-workunit-create.cjs tests/scripts/test-engine-workunit-pivot.cjs tests/scripts/test-engine-workunit-absorb.cjs tests/scripts/test-engine-workunit-promote.cjs tests/scripts/test-engine-discovery-session.cjs tests/scripts/test-engine-cache.cjs tests/scripts/test-engine-manifest-io.cjs tests/scripts/test-engine-manifest-fields.cjs tests/scripts/test-engine-boot.cjs tests/scripts/test-migration-orchestrator.cjs tests/scripts/test-migration-047.cjs tests/scripts/test-migration-048.cjs tests/scripts/test-migration-049.cjs tests/scripts/test-migration-050.cjs tests/scripts/test-migration-051.cjs tests/scripts/test-migration-052.cjs tests/scripts/test-engine-specification-projections.cjs tests/scripts/test-engine-discovery-projections.cjs tests/scripts/test-gateway-for-start.cjs tests/scripts/test-gateway-for-specification.cjs tests/scripts/test-gateway-for-workflow-continue-epic.cjs tests/scripts/test-gateway-for-workflow-continue-feature.cjs tests/scripts/test-gateway-for-workflow-continue-bugfix.cjs tests/scripts/test-gateway-for-workflow-continue-quickfix.cjs tests/scripts/test-gateway-for-workflow-continue-cross-cutting.cjs tests/scripts/test-gateway-for-discovery-skill.cjs tests/scripts/test-gateway-for-bridge.cjs tests/scripts/test-reads-derivations.cjs tests/scripts/test-ensure-discovery-item.cjs tests/scripts/test-legacy-research-split.cjs tests/scripts/test-knowledge-chunker.cjs tests/scripts/test-knowledge-config.cjs tests/scripts/test-knowledge-discovery.cjs tests/scripts/test-knowledge-embeddings.cjs tests/scripts/test-knowledge-integration.cjs tests/scripts/test-knowledge-openai.cjs tests/scripts/test-knowledge-openai-compatible.cjs tests/scripts/test-knowledge-openai-integration.cjs tests/scripts/test-knowledge-progress.cjs tests/scripts/test-knowledge-rerank.cjs tests/scripts/test-knowledge-retry.cjs tests/scripts/test-knowledge-setup-forms.cjs tests/scripts/test-knowledge-store.cjs tests/scripts/test-conventions-lint.cjs tests/scripts/test-pipeline-simulation.cjs tests/scripts/test-engine-agent-state.cjs tests/scripts/test-prose-cases.cjs tests/scripts/test-prose-snapshots.cjs",
+    "test": "node --test tests/scripts/test-render.cjs tests/scripts/test-engine-gateway.cjs tests/scripts/test-engine-epic-projections.cjs tests/scripts/test-engine-start-projections.cjs tests/scripts/test-engine-workunit-projections.cjs tests/scripts/test-engine-discussion-map.cjs tests/scripts/test-engine-discovery-map.cjs tests/scripts/test-engine-tasks.cjs tests/scripts/test-engine-render-surfaces.cjs tests/scripts/test-engine-transactions.cjs tests/scripts/test-engine-workunit-create.cjs tests/scripts/test-engine-workunit-pivot.cjs tests/scripts/test-engine-workunit-absorb.cjs tests/scripts/test-engine-workunit-promote.cjs tests/scripts/test-engine-discovery-session.cjs tests/scripts/test-engine-cache.cjs tests/scripts/test-engine-manifest-io.cjs tests/scripts/test-engine-manifest-fields.cjs tests/scripts/test-engine-boot.cjs tests/scripts/test-migration-orchestrator.cjs tests/scripts/test-migration-047.cjs tests/scripts/test-migration-048.cjs tests/scripts/test-migration-049.cjs tests/scripts/test-migration-050.cjs tests/scripts/test-migration-051.cjs tests/scripts/test-migration-052.cjs tests/scripts/test-engine-specification-projections.cjs tests/scripts/test-engine-discovery-projections.cjs tests/scripts/test-gateway-for-start.cjs tests/scripts/test-gateway-for-specification.cjs tests/scripts/test-gateway-for-workflow-continue-epic.cjs tests/scripts/test-gateway-for-workflow-continue-feature.cjs tests/scripts/test-gateway-for-workflow-continue-bugfix.cjs tests/scripts/test-gateway-for-workflow-continue-quickfix.cjs tests/scripts/test-gateway-for-workflow-continue-cross-cutting.cjs tests/scripts/test-gateway-for-discovery-skill.cjs tests/scripts/test-gateway-for-bridge.cjs tests/scripts/test-reads-derivations.cjs tests/scripts/test-ensure-discovery-item.cjs tests/scripts/test-legacy-research-split.cjs tests/scripts/test-knowledge-chunker.cjs tests/scripts/test-knowledge-config.cjs tests/scripts/test-knowledge-discovery.cjs tests/scripts/test-knowledge-embeddings.cjs tests/scripts/test-knowledge-integration.cjs tests/scripts/test-knowledge-openai.cjs tests/scripts/test-knowledge-openai-compatible.cjs tests/scripts/test-knowledge-openai-integration.cjs tests/scripts/test-knowledge-progress.cjs tests/scripts/test-knowledge-rerank.cjs tests/scripts/test-knowledge-retry.cjs tests/scripts/test-knowledge-setup-forms.cjs tests/scripts/test-knowledge-store.cjs tests/scripts/test-conventions-lint.cjs tests/scripts/test-pipeline-simulation.cjs tests/scripts/test-engine-agent-state.cjs tests/scripts/test-prose-record-action.cjs tests/scripts/test-prose-cases.cjs tests/scripts/test-prose-snapshots.cjs",
     "test:migrations": "for t in tests/scripts/test-migration-*.sh; do bash $t || exit 1; done",
     "test:cli": "for t in tests/scripts/test-engine-manifest.sh tests/scripts/test-inbox-promotion.sh tests/scripts/test-knowledge-cli.sh tests/scripts/test-knowledge-build.sh; do bash $t || exit 1; done"
   },

tests/prose/lib/record-action.cjs

@@ -13,15 +13,24 @@
 //
 // Every event is captured, not just the call: the intent before it
 // (PreToolUse), the result after it (PostToolUse, with output), the
-// failures (PostToolUseFailure), and the finish (Stop). Logs are
-// throwaway — they live in the disposable world and die with it — so
-// there is no reason to record less than everything.
+// failures (PostToolUseFailure), and the finish (SubagentStop, carrying
+// the model the walk actually ran on). Logs are throwaway — they live in
+// the disposable world and die with it — so there is no reason to record
+// less than everything.
+//
+// The model matters because an edited agent definition does not reach a
+// running session until its plugins are reloaded. A walk can therefore
+// run on a model nobody intended, and a verdict trusted at the wrong one
+// is worse than no verdict. Recording it makes that visible in the
+// result rather than something to remember.
 //
 // Self-scoping: a prose world lives at a temp path containing
 // `prose-world-`. The payload is scanned for one, and anything happening
-// outside a world is ignored. The asserter is the exception: it is
-// contracted to use NO tools, so any tool call it makes is a contract
-// violation and lands in a repo-local log instead of a world.
+// outside a world is ignored. A stop event names no file, so its world
+// and its model both come from the agent transcript the payload points
+// at. The asserter is the exception: it is contracted to use NO tools,
+// so any tool call it makes is a contract violation and lands in a
+// repo-local log instead of a world.
 //
 // The log is written to <world>/.walk-actions.log, which collectTree()
 // excludes, so recording never shows up as a world difference.
@@ -56,6 +65,34 @@ function summarise(input) {
   return flatten(raw, 200);
 }
 
+/**
+ * The agent's own harness transcript — written by the runtime, not the
+ * agent. Authority on the model it ran on, and on which world it walked,
+ * neither of which a stop payload states.
+ */
+function fromTranscript(transcriptPath) {
+  const blank = { world: null, model: '' };
+  if (!transcriptPath) return blank;
+  let raw;
+  try {
+    raw = fs.readFileSync(transcriptPath, 'utf8');
+  } catch {
+    return blank;
+  }
+  const models = new Set();
+  for (const line of raw.split('\n')) {
+    try {
+      const model = JSON.parse(line)?.message?.model;
+      if (model) models.add(model);
+    } catch { /* a partial line is not worth failing the record over */ }
+  }
+  const found = raw.match(WORLD);
+  return {
+    world: found ? found[2].replace(/\\+/g, '') : null,
+    model: [...models].join(',') || '',
+  };
+}
+
 function main() {
   const payload = read();
   if (!payload) return;
@@ -71,26 +108,39 @@ function main() {
     const projectDir = process.env.CLAUDE_PROJECT_DIR;
     if (projectDir) {
       try {
-        fs.appendFileSync(path.join(projectDir, VIOLATIONS),
+        const file = path.join(projectDir, VIOLATIONS);
+        fs.mkdirSync(path.dirname(file), { recursive: true });
+        fs.appendFileSync(file,
           `${agent}\t${event}\t${tool}\t${summarise(payload.tool_input)}\n`);
       } catch { /* a hook must never break what it observes */ }
     }
     return;
   }
 
+  // A stop event carries no tool input, so the world path that scopes
+  // every other event is absent from it — resolve it from the transcript.
+  const stop = event === 'Stop' || event === 'SubagentStop';
+  const traced = stop ? fromTranscript(payload.agent_transcript_path) : null;
   const found = JSON.stringify(payload).match(WORLD);
-  if (!found) return;
-  const world = found[2].replace(/\\+/g, '');
-  if (!fs.existsSync(world)) return;
+  const world = found ? found[2].replace(/\\+/g, '') : traced && traced.world;
+  if (!world || !fs.existsSync(world)) return;
 
-  const parts = [event, tool, summarise(payload.tool_input).split(world).join('.')];
+  const parts = [
+    event,
+    tool,
+    stop
+      ? traced.model || 'model-unknown'
+      : summarise(payload.tool_input).split(world).join('.'),
+  ];
 
   if (event === 'PostToolUse') {
     parts.push(payload.tool_output_is_error ? 'ERROR' : 'ok');
     parts.push(flatten(payload.tool_output, MAX_OUTPUT).split(world).join('.'));
   } else if (event === 'PostToolUseFailure') {
     parts.push('FAILED');
     parts.push(flatten(payload.tool_output ?? payload.error, MAX_OUTPUT));
+  } else if (stop) {
+    parts.push(flatten(payload.last_assistant_message, MAX_OUTPUT).split(world).join('.'));
   }
 
   try {