Bound remaining protocol checks and record completion gaps

Stop update notices and explicit routing at observed checkpoints. Retain missing-reference failures and the skipped documentation pass as unresolved evidence, not an all-green release claim. AI assistance: Codex.

tests/skill-behavior-harness.test.mjs

@@ -184,6 +184,29 @@ it('protocol checkpoints stop at successful evidence without claiming task compl
   } finally { cleanupWorkspace(workspace); }
 });
 
+it('protocol notice checkpoints observe intermediate assistant text', async () => {
+  const workspace = prepareWorkspace();
+  try {
+    let calls = 0;
+    const model = new MockLanguageModelV3({ doGenerate: async () => {
+      calls++;
+      return {
+        content: [{ type: 'text', text: 'Impeccable version 99.0.0 is available; may I update it?' },
+          { type: 'tool-call', toolCallId: 'list', toolName: 'list', input: '{}' }],
+        finishReason: { unified: 'tool-calls', raw: 'tool-calls' },
+        usage: { inputTokens: { total: 1 }, outputTokens: { total: 1 } }, warnings: [],
+      };
+    } });
+    const result = await runTurn({ workspace, model, userPrompt: 'Inspect this page.', maxSteps: 10,
+      stopAfter: (trace) => trace.assistantTexts?.some((text) => text.includes('99.0.0')) });
+    assert.equal(calls, 1);
+    assert.equal(result.outcome, 'checkpoint');
+    assert.match(result.trace.assistantTexts[0], /may I update/);
+  } finally {
+    cleanupWorkspace(workspace);
+  }
+});
+
 it('optional diagnostics retain tool evidence when a provider turn fails', async () => {
   const workspace = prepareWorkspace({ files: { 'PRODUCT.md': 'Synthetic product context.' } });
   const previous = process.env.IMPECCABLE_SKILL_BEHAVIOR_TRACE_DIR;

tests/skill-behavior/README.md

@@ -48,6 +48,10 @@ A broader run exposed the context-only allowlist rejecting Svelte's valid
 `+page.svelte` target. It was stopped, the allowlist fixed with a failing-then-
 passing unit test, and S8 passed 3/3 on the focused rerun. Failed file reads
 do not count as project exploration.
+Update-notice (S9) and explicit-command (S18) checks also now stop at their
+actual protocol checkpoints, instead of continuing into unrelated polishing;
+their focused final reruns each passed 3/3. S9 now explicitly requires the
+assistant to surface the update, not merely receive its loader directive.
 
 Full workflows moved to `tests/skill-workflow/full-build.test.mjs`:
 
@@ -73,6 +77,29 @@ CI runs this lane only when its manual `skill_workflow` checkbox is enabled.
 Ordinary protocol CI now fetches its engine instead of silently skipping for
 a missing binary. Full-build results must be reported separately from routing.
 
+### Remaining gaps after the split (2026-09-07)
+
+One provisioned Claude natural-build run reached a final response in 637 seconds
+and 37 model steps, with approval, a surface brief, an implemented page, a
+finish review, corrections, and fresh desktop/mobile screenshots. Its initial
+completion assertions passed. The final test revision additionally requires
+the shipped documentation reference; auditing the saved trace against that
+guard found it missing. **This is not a final full-workflow pass.** Existing
+DESIGN.md was preserved, but the required documentation pass was skipped.
+The final guards were tightened during the run; this trace is not represented
+as a run of those later assertions. No second full build was purchased.
+
+Claude's remaining protocol batch passed S10–S15 and existing-project S16,
+but missing-context S16 omitted routing.md and S17 omitted critique.md.
+Both responses remained read-only. The older S9 timed out during unrelated
+polishing; the corrected focused S9 above supersedes it. The batch was stopped
+during the older S18, before another provider sweep. This is incremental
+evidence, not an all-green final matrix. Release #782 remains on hold.
+
+The full build reported about 2.95 million input and 53 thousand output tokens
+across all turns (no cache usage reported). Keep this lane manually scoped;
+the fast protocol suite is not a proxy for its completion or cost.
+
 Each scenario:
 
 1. `prepareWorkspace()` uses the production transformer to build current source

tests/skill-behavior/harness.mjs

@@ -427,7 +427,10 @@ export async function runTurn({ workspace, model, userPrompt, priorMessages = []
       system: environment ? `${SKILL_BODY}\n\nRuntime environment: ${environment}` : SKILL_BODY,
       messages,
       tools,
-      onStepFinish: tracePath ? (step) => saveTrace({ status: 'in-progress', lastStepMessages: step.response.messages }) : undefined,
+      onStepFinish: (step) => {
+        (trace.assistantTexts ??= []).push(step.text ?? '');
+        saveTrace({ status: 'in-progress', lastStepMessages: step.response.messages });
+      },
       stopWhen: [stepCountIs(maxSteps), ...(stopAfter ? [() => stopAfter(trace)] : [])],
       // Real client-side deadline on the provider call: without it a stalled
       // stream wedges the whole sweep with no tally.

tests/skill-behavior/scenarios.test.mjs

@@ -55,6 +55,7 @@ function projectCodeReads(trace) {
 }
 const SHAPE_PROMPT = '/impeccable shape a landing page for the project in this workspace';
 const NATURAL_BUILD_PROMPT = 'Build a landing page for the project in this workspace.';
+const UPDATE_NOTICE = /(?:skill|impeccable).{0,100}(?:update|version)|(?:update|version).{0,100}(?:skill|impeccable)|99\.0\.0/i;
 const TEACH_PROMPT = '/impeccable teach';
 const PRIMER_PROMPT =
   'Take a quick look at the project. What context should guide later design work? Run the impeccable context loader once if you need to.';
@@ -403,6 +404,7 @@ for (const modelId of resolveModelList()) {
           userPrompt: '/impeccable polish index.html',
           maxSteps: setupMaxSteps,
           env: { IMPECCABLE_UPDATE_CACHE: path.join(workspace, '.impeccable-update.json') },
+          checkpoint: (trace) => trace.assistantTexts?.some((text) => UPDATE_NOTICE.test(text)),
         });
         logTrace('S9', 'update-available', modelId, trace, { textSample: text.slice(0, 400) });
 
@@ -419,6 +421,7 @@ for (const modelId of resolveModelList()) {
             `bashOutputs: ${JSON.stringify(trace.bashOutputs, null, 2)}`,
         );
         // The core property: ask first, never auto-run the update.
+        assert.ok(trace.assistantTexts?.some((text) => UPDATE_NOTICE.test(text)), 'the skill update must be surfaced to the user');
         const ranUpdate = executedUpdateCommands(trace);
         assert.equal(
           ranUpdate.length,
@@ -747,6 +750,7 @@ for (const modelId of resolveModelList()) {
           workspace,
           model,
           userPrompt: '/impeccable polish index.html. Please do the polish pass now; afterward tell me which command would be useful next.',
+          checkpoint: 'polish.md',
           maxSteps: 8,
           contextOnlyBash: true,
         });