Merge origin/master into codex/truncated-design

packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts

@@ -1,19 +1,7 @@
 /**
- * Scripted fake ACP agent bin for `dsh-acp-snapshot`'s unit specs. Speaks
- * newline-delimited JSON-RPC on stdio like the real `dsh-acp-agent` bin, but
- * every behavior — how prompts settle, whether session/new rejects, which
- * session logs get persisted, what filesystem noise to leave — comes from a
- * `behavior.json` sitting NEXT to the `$DSH_SNAPSHOT_FILE` fixture, so a spec
- * scripts a whole subprocess run from data. The specs launch it through the
- * REAL `runScenario` spawn path (tsx loader, temp cwd, env plumbing), so the
- * harness plumbing is exercised for real; only the agent behind the protocol
- * is scripted.
- *
- * The specs (not the golden tier) own this bin: it asserts nothing, echoes
- * observable facts into `session/update` text chunks (env probe, permission
- * outcome, seeded-workspace listing) for the spec to read off `rawStdout`, and
- * exits 0 on stdin EOF after writing the scripted logs — mirroring the real
- * bin's dispose-flush-exit shape.
+ * Scripted ACP agent for snapshot-kit tests. A fixture-adjacent `behavior.json` controls the
+ * subprocess reached through the real harness path; the bin reports observations over ACP and
+ * writes scripted logs before exiting on stdin EOF.
  */
 
 import { mkdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs'

packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/session.jsonl

@@ -1,2 +1,2 @@
 {"type":"session","id":"ccdc749f-56f3-4267-9750-598b5c60b7b2","createdAt":600,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-nOQ4Gy"}
-{"type":"request/header","seq":0,"time":4,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":[{"name":"t1","description":"D1","parameters":{"type":"object"}}]},"reason":"initial"}}
+{"type":"request/header","seq":0,"time":4,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}

packages/support/acp-snapshot/tests/fixtures/record-suite/rec-pin/tool-schemas.golden.json

@@ -0,0 +1,12 @@
+{
+  "initial": [
+    {
+      "name": "t1",
+      "description": "D1",
+      "parameters": {
+        "type": "object"
+      }
+    }
+  ],
+  "deltas": []
+}

packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/session.jsonl

@@ -1,4 +1,4 @@
 {"type":"session","id":"12121212-3434-4545-8686-787878787878","createdAt":7,"cwd":"/rec/pin-cwd"}
-{"type":"request/header","seq":0,"time":7,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":[{"name":"t1","description":"D1","parameters":{"type":"object"}}]},"reason":"initial"}}
+{"type":"request/header","seq":0,"time":7,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}
 {"type":"request/header-delta","seq":1,"time":7,"data":{"system":{"keepStart":1,"keepEnd":0,"insert":["{{system}}"]}}}
 {"type":"turn/start","seq":2,"time":7,"data":{"turn":1}}

packages/support/acp-snapshot/tests/fixtures/suite/pin-turn/tool-schemas.golden.json

@@ -0,0 +1,12 @@
+{
+  "initial": [
+    {
+      "name": "t1",
+      "description": "D1",
+      "parameters": {
+        "type": "object"
+      }
+    }
+  ],
+  "deltas": []
+}

packages/support/acp-snapshot/tests/harness.spec.ts

@@ -308,11 +308,8 @@ describe('runScenario', () => {
 
   it('rejects the run on a scripted permission kind the agent never offered', { timeout: 20_000 }, async () => {
     const { fixtureFile } = await scenario({ permissionProbe: true })
-    // The fake bin offers allow_once/reject_once; scripting allow_always is a
-    // scenario bug. The agent is answered `cancelled` (it must not be able to
-    // absorb the bug as an error-means-denial), and the RUN fails: a callback
-    // throw would only reach the agent as a JSON-RPC error response, letting
-    // a tolerant agent carry on and the scenario pass — or record.
+    // The fake offers only allow_once/reject_once. The harness must reject an impossible click,
+    // not merely send an RPC error that a tolerant agent could absorb.
     await expect(runScenario(
       { steps: [...boot, { op: 'prompt', text: 'impossible click' }], permissionAnswers: [{ kind: 'allow_always' }] },
       { agent: AGENT, mode: 'replay', fixtureFile },

packages/support/acp-snapshot/tests/normalize.spec.ts

@@ -5,6 +5,7 @@ import {
   normalizeStdout,
   scrubRequestHeaders,
   scrubSystemPrompts,
+  scrubToolSchemas,
 } from '../src/normalize.ts'
 
 /**
@@ -352,3 +353,45 @@ describe('scrubSystemPrompts', () => {
     expect(scrubSystemPrompts(out)).toBe(out)
   })
 })
+
+describe('scrubToolSchemas', () => {
+  it('scrubs only tool-schema payloads while keeping prompts and prefixes verbatim', () => {
+    const header = JSON.stringify({
+      type: 'request/header', seq: 1, time: 2,
+      data: {
+        header: {
+          system: 'full prompt',
+          tools: [{ name: 'read', description: 'full schema', parameters: { type: 'object' } }],
+          messagePrefix: [{ role: 'user', content: [{ type: 'text', text: 'full prefix' }] }],
+        },
+        reason: 'initial',
+      },
+    })
+    const delta = JSON.stringify({
+      type: 'request/header-delta', seq: 2, time: 3,
+      data: {
+        system: { keepStart: 1, keepEnd: 2, insert: ['new prompt line'] },
+        tools: { added: [{ name: 'grep', description: 'new schema' }], changed: [{ name: 'read', description: 'changed schema' }] },
+        messagePrefix: [{ role: 'user', content: [{ type: 'text', text: 'changed prefix' }] }],
+      },
+    })
+    const systemOnly = JSON.stringify({
+      type: 'request/header', seq: 3, time: 4,
+      data: { header: { system: 'prompt only' }, reason: 'resume' },
+    })
+
+    const out = scrubToolSchemas(`${header}\n${delta}\n${systemOnly}\n`)
+    expect(out).toContain('"tools":"{{tools}}"')
+    expect(out).toContain('"added":[{"name":"grep","description":"{{tools}}"}]')
+    expect(out).toContain('"changed":[{"name":"read","description":"{{tools}}"}]')
+    expect(out).not.toContain('full schema')
+    expect(out).not.toContain('new schema')
+    expect(out).not.toContain('changed schema')
+    expect(out).toContain('full prompt')
+    expect(out).toContain('new prompt line')
+    expect(out).toContain('full prefix')
+    expect(out).toContain('changed prefix')
+    expect(out.split('\n')[2]).toBe(systemOnly)
+    expect(scrubToolSchemas(out)).toBe(out)
+  })
+})

packages/support/acp-snapshot/tests/suite.spec.ts

@@ -9,30 +9,29 @@ import {
   childFixturePaths,
   fixtureContext,
   formatSystemPromptSnapshot,
+  formatToolSchemasSnapshot,
   headerDeltaCount,
   normalizedHeaders,
   normalizedSystemPromptDeltas,
   normalizedSystemPrompts,
+  normalizedToolSchemaDeltas,
+  normalizedToolSchemas,
+  parseToolSchemasSnapshot,
   refreshFixtureReplacements,
+  restorePinnedToolSchemas,
   stabilizeRefreshLog,
+  unknownToolCallIds,
 } from '../src/suite.ts'
 
 /**
- * Unit tests for the suite factory, by running it: two synthetic suites over
- * the scripted fake ACP bin (./fixtures/fake-acp-agent.ts) register REAL
- * describe/it trees at collection time, so every factory path — golden and log
- * compares, the per-suite header pin and its uniformity guard, record-mode
- * fixture write-back, skip semantics, and the fixture guard block — executes
- * as an ordinary green test. The pure helpers get direct cases below.
+ * Unit tests for the suite factory, by running it: two synthetic suites over the scripted fake
+ * ACP bin (./fixtures/fake-acp-agent.ts) register real describe/it trees at collection time,
+ * so every factory path — golden and log compares, the per-suite header pin and its uniformity
+ * guard, record-mode fixture write-back, skip semantics, and the fixture guard block —
+ * executes as an ordinary green test.
  *
- * The replay suite runs against the committed fixtures in ./fixtures/suite.
- * The record suite runs against a TEMP COPY of ./fixtures/record-suite
- * (record mode writes session fixtures back into its snapshots dir; a run must
- * never touch the committed tree). To re-bootstrap the record tree's goldens
- * after changing the fake bin's output, run this spec once with
- * `ACP_SNAPSHOT_SPEC_BOOTSTRAP=1` (points the record suite at the committed
- * tree so vitest creates/updates the goldens and the write-back lands there),
- * then commit the result.
+ * Record tests use a temp copy. To intentionally rebuild their committed fixtures, run this
+ * spec once with `ACP_SNAPSHOT_SPEC_BOOTSTRAP=1`, then review and commit the resulting tree.
  */
 
 const AGENT = {
@@ -44,12 +43,7 @@ const AGENT = {
 const REPLAY_DIR = fileURLToPath(new URL('./fixtures/suite', import.meta.url))
 const RECORD_SRC = fileURLToPath(new URL('./fixtures/record-suite', import.meta.url))
 
-// The replay suite doubles as the header-CLASS coverage: every scenario names
-// the same explicit class (the record suite exercises the 'default' fallback),
-// and plain-turn boots through a per-scenario configPath override (the same
-// dummy path the agent default carries — the plumbing, not the composition,
-// is what this suite can exercise; the real overlay boot is the acp-agent
-// example's code-mode scenarios).
+// Replay pins explicit header classes; recording covers the default fallback.
 const REPLAY_SCENARIOS: Scenario[] = [
   { name: 'pin-turn', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderDeltas: 1, headerClass: 'main' },
   { name: 'plain-turn', hasModelTurn: true, recorded: true, childSessions: 1, headerClass: 'main', configPath: AGENT.configPath },
@@ -82,6 +76,7 @@ afterAll(async () => {
 function staleRefreshFixtures(dir: string): void {
   writeFileSync(join(dir, 'plain-turn', 'stdout.golden.jsonl'), 'stale stdout\n')
   writeFileSync(join(dir, 'pin-turn', 'system-prompt.golden.md'), 'STALE PROMPT\n')
+  writeFileSync(join(dir, 'pin-turn', 'tool-schemas.golden.json'), '{"initial":[{"name":"stale"}],"deltas":[]}\n')
 
   const plainBehaviorFile = join(dir, 'plain-turn', 'behavior.json')
   const plainBehavior = JSON.parse(readFileSync(plainBehaviorFile, 'utf8')) as Record<string, unknown>
@@ -137,6 +132,9 @@ describe('defineAcpSnapshotSuite: refresh write-back', () => {
       'NEW PROMPT LINE',
       '',
     ].join('\n'))
+    const schemas = readFileSync(join(refreshDir, 'pin-turn', 'tool-schemas.golden.json'), 'utf8')
+    expect(schemas).toContain('"description": "D1"')
+    expect(schemas).not.toContain('"name":"stale"')
   })
 })
 
@@ -247,6 +245,40 @@ describe('normalizedSystemPrompts', () => {
   })
 })
 
+describe('normalizedToolSchemas', () => {
+  it('extracts normalized schema arrays and omits absent or non-array fields', () => {
+    const log = [
+      '{"type":"session","id":"a","createdAt":5,"cwd":"/w"}',
+      '{"type":"request/header","seq":0,"time":9,"data":{"header":{"tools":[{"name":"read","description":"work in /w"}]}}}',
+      '{"type":"request/header","seq":1,"time":9,"data":{"header":{}}}',
+      '{"type":"request/header","seq":2,"time":9,"data":{"header":{"tools":null}}}',
+      '{"type":"request/header","seq":3,"time":9,"data":{"header":null}}',
+      '{"type":"request/header","seq":4,"time":9,"data":{"header":"invalid"}}',
+      '',
+    ].join('\n')
+    expect(normalizedToolSchemas(log, { sessionIds: [], cwd: '/w' })).toEqual([
+      [{ name: 'read', description: 'work in {{cwd}}' }],
+    ])
+  })
+})
+
+describe('normalizedToolSchemaDeltas', () => {
+  it('extracts and normalizes object-valued schema edits', () => {
+    const log = [
+      '{"type":"request/header-delta","data":{"tools":{"added":[{"name":"read","description":"work in /w"}]}}}',
+      '{"type":"request/header-delta","data":{"tools":null}}',
+      '{"type":"request/header-delta","data":{"tools":"invalid"}}',
+      '{"type":"request/header-delta","data":{"tools":[]}}',
+      '{"type":"request/header-delta","data":{"system":{"insert":[]}}}',
+      '{"type":"request/header","data":{"tools":{"added":[]}}}',
+      '',
+    ].join('\n')
+    expect(normalizedToolSchemaDeltas(log, { sessionIds: [], cwd: '/w' })).toEqual([
+      { added: [{ name: 'read', description: 'work in {{cwd}}' }] },
+    ])
+  })
+})
+
 describe('normalizedSystemPromptDeltas', () => {
   it('extracts and normalizes well-formed system edits', () => {
     const log = [
@@ -281,6 +313,39 @@ describe('formatSystemPromptSnapshot', () => {
   })
 })
 
+describe('tool-schema snapshots', () => {
+  const snapshot = {
+    initial: [{ name: 'read', description: 'Read a file.' }],
+    deltas: [{ added: [{ name: 'grep', description: 'Search files.' }] }],
+  }
+
+  it('formats and parses canonical structured JSON', () => {
+    const formatted = formatToolSchemasSnapshot(snapshot.initial, snapshot.deltas)
+    expect(formatted).toBe(`${JSON.stringify(snapshot, null, 2)}\n`)
+    expect(parseToolSchemasSnapshot(formatted)).toEqual(snapshot)
+  })
+
+  it('rejects invalid top-level and field shapes', () => {
+    expect(() => parseToolSchemasSnapshot('null')).toThrow(/must be an object/)
+    expect(() => parseToolSchemasSnapshot('"invalid"')).toThrow(/must be an object/)
+    expect(() => parseToolSchemasSnapshot('[]')).toThrow(/must be an object/)
+    expect(() => parseToolSchemasSnapshot('{"initial":{},"deltas":[]}')).toThrow(/array-valued/)
+    expect(() => parseToolSchemasSnapshot('{"initial":[],"deltas":{}}')).toThrow(/array-valued/)
+  })
+
+  it('restores initial schemas into the pinned header token', () => {
+    expect(restorePinnedToolSchemas({ system: '{{system}}', tools: '{{tools}}' }, snapshot))
+      .toEqual({ system: '{{system}}', tools: snapshot.initial })
+  })
+
+  it('rejects invalid headers and a missing tool token', () => {
+    expect(() => restorePinnedToolSchemas(null, snapshot)).toThrow(/must be an object/)
+    expect(() => restorePinnedToolSchemas('invalid', snapshot)).toThrow(/must be an object/)
+    expect(() => restorePinnedToolSchemas([], snapshot)).toThrow(/must be an object/)
+    expect(() => restorePinnedToolSchemas({ tools: [] }, snapshot)).toThrow(/must equal/)
+  })
+})
+
 describe('headerDeltaCount', () => {
   it('counts request/header-delta events, ignoring blanks and other lines', () => {
     const delta = JSON.stringify({ type: 'request/header-delta', seq: 2, time: 9, data: {} })
@@ -290,6 +355,27 @@ describe('headerDeltaCount', () => {
   })
 })
 
+describe('unknownToolCallIds', () => {
+  it('returns structured UNKNOWN_TOOL call ids and ignores other results', () => {
+    const log = [
+      '{"type":"tool/result","data":{"callId":"missing","error":{"code":"UNKNOWN_TOOL"}}}',
+      '{"type":"tool/result","data":{"callId":"failed","error":{"code":"EXECUTION_FAILED"}}}',
+      '{"type":"tool/result","data":null}',
+      '{"type":"tool/result","data":"invalid"}',
+      '{"type":"tool/result","data":{"error":null}}',
+      '{"type":"tool/result","data":{"error":"invalid"}}',
+      '{"type":"assistant/message","data":{"error":{"code":"UNKNOWN_TOOL"}}}',
+      '{"type":"tool/result","data":{"error":{"code":"UNKNOWN_TOOL"}}}',
+      '',
+    ].join('\n')
+    expect(unknownToolCallIds(log)).toEqual(['missing', '<missing callId>'])
+  })
+
+  it('returns no failures for ordinary tool results', () => {
+    expect(unknownToolCallIds('{"type":"tool/result","data":{"callId":"ok"}}\n')).toEqual([])
+  })
+})
+
 describe('refreshFixtureReplacements', () => {
   it('maps fresh ids and cwd values to the existing fixture values, skipping non-replacements', () => {
     const log = (content: string): HarvestedLog => ({ id: 'diagnostic', createdAt: 1, content })