Vendor OpenClaw source as Adolf fork baseline

Adolf is a fork/vendored clone of github.com/openclaw/openclaw (v2026.6.11),
free to diverge. Tree copied sans upstream .git; upstream remote added for
future syncs. Node pinned to 24 (.nvmrc); engines already require >=22.19.
Preserves docs/ARCHITECTURE.md.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LeqyaxJF2nbRXJtae2kNB2

qa/scenarios/workspace/lobster-invaders-build.yaml

@@ -0,0 +1,64 @@
+title: Build Lobster Invaders
+
+scenario:
+  id: lobster-invaders-build
+  surface: workspace
+  coverage:
+    primary:
+      - workspace.artifacts
+    secondary:
+      - workspace.builds
+  objective: Verify the agent can read the repo, create a tiny playable artifact, and report what changed.
+  successCriteria:
+    - Agent inspects source before coding.
+    - Agent builds a tiny playable Lobster Invaders artifact.
+    - Agent explains how to run or view the artifact.
+  docsRefs:
+    - docs/help/testing.md
+    - docs/web/dashboard.md
+  codeRefs:
+    - extensions/qa-lab/src/report.ts
+    - extensions/qa-lab/web/src/app.ts
+  execution:
+    kind: flow
+    summary: Verify the agent can read the repo, create a tiny playable artifact, and report what changed.
+    config:
+      prompt: Read the QA kickoff context first, then build a tiny Lobster Invaders HTML game at ./lobster-invaders.html in this workspace and tell me where it is.
+
+flow:
+  steps:
+    - name: creates the artifact after reading context
+      actions:
+        - call: reset
+        - call: runAgentPrompt
+          args:
+            - ref: env
+            - sessionKey: agent:qa:lobster-invaders
+              message:
+                expr: config.prompt
+              timeoutMs:
+                expr: liveTurnTimeoutMs(env, 30000)
+        - call: waitForOutboundMessage
+          args:
+            - ref: state
+            - lambda:
+                params: [candidate]
+                expr: "candidate.conversation.id === 'qa-operator'"
+        - set: artifactPath
+          value:
+            expr: "path.join(env.gateway.workspaceDir, 'lobster-invaders.html')"
+        - call: waitForCondition
+          saveAs: artifact
+          args:
+            - lambda:
+                async: true
+                expr: "((await fs.readFile(artifactPath, 'utf8').catch(() => null))?.includes('Lobster Invaders') ? await fs.readFile(artifactPath, 'utf8').catch(() => null) : undefined)"
+            - expr: liveTurnTimeoutMs(env, 20000)
+            - 250
+        - assert:
+            expr: "artifact.includes('Lobster Invaders')"
+            message: missing Lobster Invaders artifact
+        - assert:
+            expr: "!env.mock || (await fetchJson(`${env.mock.baseUrl}/debug/requests`)).some((request) => (request.toolOutput ?? '').includes('QA mission'))"
+            message: expected pre-write read evidence
+      detailsExpr: "'lobster-invaders.html'"

qa/scenarios/workspace/long-running-release-audit.yaml

@@ -0,0 +1,251 @@
+title: Long-running release audit
+
+scenario:
+  id: long-running-release-audit
+  surface: workspace
+  coverage:
+    primary:
+      - workspace.long-running-task
+    secondary:
+      - workspace.repo-discovery
+      - workspace.artifacts
+  objective: Verify a model can complete a sustained repo audit that requires reading several scattered files, ignoring stale decoys, writing artifacts, and checking its own output.
+  successCriteria:
+    - Agent starts from the seeded project README instead of guessing.
+    - Agent inspects docs and source files across multiple directories.
+    - Agent writes a JSON audit and a Markdown handoff with all required findings.
+    - Each JSON finding carries a boolean verified field; missing current source evidence is verified false.
+    - Agent verifies the generated JSON before finalizing.
+  docsRefs:
+    - docs/help/testing.md
+    - qa/scenarios/index.yaml
+  codeRefs:
+    - extensions/qa-lab/src/suite.ts
+    - extensions/qa-lab/src/scenario-flow-runner.ts
+  execution:
+    kind: flow
+    summary: Verify sustained repo-style auditing with scattered evidence and artifact verification.
+    config:
+      reportFile: audit-fixture/release-audit.json
+      handoffFile: audit-fixture/release-handoff.md
+      expectedFindings:
+        - REL-GATEWAY-417
+        - REL-CHANNEL-238
+        - REL-CRON-904
+        - REL-MEMORY-552
+        - REL-PLUGIN-319
+        - REL-INSTALL-846
+        - REL-DOCS-611
+      workspaceFiles:
+        audit-fixture/README.md: |-
+          # Finch Relay
+
+          Release readiness task:
+
+          The release checklist was renamed during docs cleanup.
+          Find the current checklist under `docs/`, then inspect the referenced
+          source and notes. Produce:
+
+          - `release-audit.json`
+          - `release-handoff.md`
+
+          Do not use `docs/archive/old-release-notes.md` as current evidence.
+          Historical path that may appear in stale notes: `docs/release-checklist.md`.
+        audit-fixture/docs/current-readiness-checklist.md: |-
+          # Release Checklist
+
+          Current release readiness requires checking eight areas:
+
+          1. gateway reconnect handling
+          2. channel delivery ordering
+          3. cron duplicate prevention
+          4. memory recall fallback
+          5. plugin runtime loading
+          6. control UI status copy
+          7. installer update path
+          8. docs update status
+
+          Useful current sources:
+
+          - `src/gateway/reconnect.ts`
+          - `src/channels/delivery.ts`
+          - `src/scheduling/cron.ts`
+          - `src/memory/recall.ts`
+          - `src/plugins/runtime.ts`
+          - `ui/control-panel.ts`
+          - `install/update.ts`
+          - `docs/operator-notes.md`
+
+          The archive folder contains stale notes and should not be treated as
+          current release evidence.
+        audit-fixture/docs/operator-notes.md: |-
+          # Operator Notes
+
+          Current docs update status:
+
+          Finding id: REL-DOCS-611
+          Status: docs mention reconnect, cron, memory, plugin, and installer checks,
+          but the channel ordering and UI notes still need maintainer handoff.
+        audit-fixture/docs/archive/old-release-notes.md: |-
+          # Old Release Notes
+
+          Stale finding id: REL-STALE-000
+          This file is from a previous release and should not appear in the new
+          release audit.
+        audit-fixture/src/gateway/reconnect.ts: |-
+          export const gatewayReconnectReleaseFinding = {
+            id: "REL-GATEWAY-417",
+            area: "gateway reconnect handling",
+            status: "retry jitter verified, resume token fallback still needs manual spot check",
+          };
+        audit-fixture/src/channels/delivery.ts: |-
+          export const channelDeliveryReleaseFinding = {
+            id: "REL-CHANNEL-238",
+            area: "channel delivery ordering",
+            status: "thread replies preserve ordering, root-channel fallback needs handoff note",
+          };
+        audit-fixture/src/scheduling/cron.ts: |-
+          export const cronDuplicateReleaseFinding = {
+            id: "REL-CRON-904",
+            area: "cron duplicate prevention",
+            status: "single-run lock verified for restart wakeups",
+          };
+        audit-fixture/src/memory/recall.ts: |-
+          export const memoryRecallReleaseFinding = {
+            id: "REL-MEMORY-552",
+            area: "memory recall fallback",
+            status: "fallback summary survives empty memory search, but ranking sample needs second reviewer",
+          };
+        audit-fixture/src/plugins/runtime.ts: |-
+          export const pluginRuntimeReleaseFinding = {
+            id: "REL-PLUGIN-319",
+            area: "plugin runtime loading",
+            status: "bundled runtime manifest loads cleanly after restart",
+          };
+        audit-fixture/install/update.ts: |-
+          export const installerUpdateReleaseFinding = {
+            id: "REL-INSTALL-846",
+            area: "installer update path",
+            status: "update smoke passed from previous stable tag",
+          };
+      prompt: |-
+        Do a release readiness audit for the small project under `audit-fixture/`.
+        Start from `audit-fixture/README.md`, find the current checklist, inspect the referenced docs/source, then create `audit-fixture/release-audit.json` and `audit-fixture/release-handoff.md`.
+
+        The JSON should include current finding ids, source files, statuses, and a boolean `verified` on each finding.
+        If a current checklist source is referenced but missing from the fixture, include that source as a finding with `verified: false`.
+        The Markdown handoff should summarize what is ready and what needs follow-up.
+        Check your generated JSON before finalizing.
+        Final reply exactly: RELEASE-AUDIT-COMPLETE
+
+flow:
+  steps:
+    - name: completes the sustained release audit with verified artifacts
+      actions:
+        - call: waitForGatewayHealthy
+          args:
+            - ref: env
+            - 60000
+        - call: reset
+        - forEach:
+            items:
+              expr: "Object.entries(config.workspaceFiles ?? {})"
+            item: workspaceFile
+            actions:
+              - set: seededPath
+                value:
+                  expr: "path.join(env.gateway.workspaceDir, String(workspaceFile[0]))"
+              - call: fs.mkdir
+                args:
+                  - expr: "path.dirname(seededPath)"
+                  - recursive: true
+              - call: fs.writeFile
+                args:
+                  - ref: seededPath
+                  - expr: "`${String(workspaceFile[1] ?? '').trimEnd()}\\n`"
+                  - utf8
+        - set: sessionKey
+          value:
+            expr: "`agent:qa:release-audit:${randomUUID().slice(0, 8)}`"
+        - call: runAgentPrompt
+          args:
+            - ref: env
+            - sessionKey:
+                ref: sessionKey
+              message:
+                expr: config.prompt
+              timeoutMs:
+                expr: liveTurnTimeoutMs(env, 120000)
+        - set: reportPath
+          value:
+            expr: "path.join(env.gateway.workspaceDir, config.reportFile)"
+        - set: handoffPath
+          value:
+            expr: "path.join(env.gateway.workspaceDir, config.handoffFile)"
+        - call: waitForCondition
+          saveAs: reportText
+          args:
+            - lambda:
+                async: true
+                expr: "fs.readFile(reportPath, 'utf8').then((value) => config.expectedFindings.every((finding) => value.includes(finding)) ? value : undefined).catch(() => undefined)"
+            - expr: liveTurnTimeoutMs(env, 60000)
+            - expr: "env.providerMode === 'mock-openai' ? 100 : 250"
+        - call: waitForCondition
+          saveAs: handoffText
+          args:
+            - lambda:
+                async: true
+                expr: "fs.readFile(handoffPath, 'utf8').then((value) => config.expectedFindings.every((finding) => value.includes(finding)) && !value.includes('REL-STALE-000') ? value : undefined).catch(() => undefined)"
+            - expr: liveTurnTimeoutMs(env, 30000)
+            - expr: "env.providerMode === 'mock-openai' ? 100 : 250"
+        - set: report
+          value:
+            expr: "JSON.parse(reportText)"
+        - assert:
+            expr: "['src/gateway/reconnect.ts', 'src/channels/delivery.ts', 'src/scheduling/cron.ts', 'src/memory/recall.ts', 'src/plugins/runtime.ts', 'install/update.ts', 'docs/operator-notes.md'].every((file) => JSON.stringify(report).includes(file))"
+            message:
+              expr: "`report missing expected source refs: ${reportText}`"
+        - assert:
+            expr: "config.expectedFindings.every((finding) => JSON.stringify(report).includes(finding))"
+            message:
+              expr: "`report missing expected finding ids: ${reportText}`"
+        - assert:
+            expr: "!JSON.stringify(Array.isArray(report.findings) ? report.findings : report).includes('REL-STALE-000') && !handoffText.includes('REL-STALE-000')"
+            message:
+              expr: "`stale archive finding leaked into audit: report=${reportText}\\nhandoff=${handoffText}`"
+        - set: reportFindings
+          value:
+            expr: "Array.isArray(report) ? report : (Array.isArray(report.findings) ? report.findings : [])"
+        - set: uiFinding
+          value:
+            expr: "reportFindings.find((finding) => JSON.stringify(finding).includes('ui/control-panel.ts'))"
+        - assert:
+            expr: "uiFinding && uiFinding.verified === false"
+            message:
+              expr: "`missing UI evidence was not marked unverified: report=${reportText}\\nhandoff=${handoffText}`"
+        - assert:
+            expr: "reportFindings.length > 0 && reportFindings.every((finding) => typeof finding?.verified === 'boolean')"
+            message:
+              expr: "`each report finding must include a boolean verified field: ${reportText}`"
+        - call: waitForAgentHistoryReply
+          saveAs: outbound
+          args:
+            - ref: env
+            - ref: sessionKey
+            - lambda:
+                params: [text]
+                expr: "text.trim() === 'RELEASE-AUDIT-COMPLETE'"
+            - expr: liveTurnTimeoutMs(env, 45000)
+            - expr: "env.providerMode === 'mock-openai' ? 100 : 250"
+        - call: readRawQaSessionStore
+          saveAs: store
+          args:
+            - ref: env
+        - set: sessionEntry
+          value:
+            expr: "store[sessionKey]"
+        - assert:
+            expr: "Boolean(sessionEntry)"
+            message:
+              expr: "`missing QA session entry for ${sessionKey}`"
+      detailsExpr: "`${outbound.text}\\n${reportText}\\n\\n${handoffText}`"

qa/scenarios/workspace/medium-game-plan-codex-harness.yaml

@@ -0,0 +1,156 @@
+title: Medium game plan Codex harness
+
+scenario:
+  id: medium-game-plan-codex-harness
+  surface: workspace
+  coverage:
+    primary:
+      - workspace.planning
+    secondary:
+      - models.codex-cli
+  objective: Verify the Codex app-server harness can plan and build a medium-complex self-contained browser game.
+  successCriteria:
+    - A live-frontier run fails fast unless the selected primary model is openai/gpt-5.5 with the Codex harness forced.
+    - The scenario forces the Codex embedded harness.
+    - The prompt explicitly asks the agent to enter plan mode before editing.
+    - The agent writes a self-contained HTML game with a canvas loop, controls, scoring, waves, pause, and restart.
+  docsRefs:
+    - docs/plugins/sdk-agent-harness.md
+    - docs/gateway/configuration-reference.md
+    - docs/help/testing.md
+  codeRefs:
+    - extensions/codex/harness.ts
+    - src/agents/harness/selection.ts
+    - extensions/qa-lab/src/suite.ts
+  execution:
+    kind: flow
+    summary: Run with `pnpm openclaw qa suite --provider-mode live-frontier --model openai/gpt-5.5 --alt-model openai/gpt-5.5 --fast --thinking medium --scenario medium-game-plan-codex-harness`.
+    config:
+      requiredProvider: codex
+      requiredModel: gpt-5.5
+      harnessRuntime: codex
+      artifactFile: star-garden-defenders-codex.html
+      gameTitle: Star Garden Defenders
+      minBytes: 5000
+      buildPrompt: |-
+        Enter plan mode first and write a short implementation plan before editing.
+
+        Then build a medium-complex, self-contained browser game at ./star-garden-defenders-codex.html.
+
+        Game: Star Garden Defenders.
+        Requirements:
+        - one HTML file only; no external assets, fonts, scripts, or network calls
+        - canvas-based arcade loop with requestAnimationFrame
+        - keyboard controls and mouse or pointer support
+        - player movement, enemy waves, collectibles or power-ups, collision handling
+        - score, lives or health, wave number, pause, restart, and game-over state
+        - polished inline CSS and clear on-screen controls
+        - after writing the file, reply with the filename and the main systems implemented
+
+flow:
+  steps:
+    - name: confirms GPT-5.5 Codex harness target
+      actions:
+        - set: selected
+          value:
+            expr: splitModelRef(env.primaryModel)
+        - assert:
+            expr: "env.providerMode !== 'live-frontier' || selected?.provider === config.requiredProvider"
+            message:
+              expr: "`expected live primary provider ${config.requiredProvider}, got ${env.primaryModel}`"
+        - assert:
+            expr: "env.providerMode !== 'live-frontier' || selected?.model === config.requiredModel"
+            message:
+              expr: "`expected live primary model ${config.requiredModel}, got ${env.primaryModel}`"
+        - if:
+            expr: "env.providerMode !== 'live-frontier'"
+            then:
+              - assert: "true"
+            else:
+              - call: patchConfig
+                saveAs: patchResult
+                args:
+                  - env:
+                      ref: env
+                    patch:
+                      agents:
+                        defaults:
+                          models:
+                            expr: "({ [env.primaryModel]: { agentRuntime: { id: config.harnessRuntime } } })"
+              - call: waitForGatewayHealthy
+                args:
+                  - ref: env
+                  - 60000
+              - call: waitForQaChannelReady
+                args:
+                  - ref: env
+                  - 60000
+              - call: readConfigSnapshot
+                saveAs: snapshot
+                args:
+                  - ref: env
+              - assert:
+                  expr: "snapshot.config.agents?.defaults?.models?.[env.primaryModel]?.agentRuntime?.id === config.harnessRuntime"
+                  message:
+                    expr: "`expected ${env.primaryModel} agentRuntime.id=${config.harnessRuntime}, got ${JSON.stringify(snapshot.config.agents?.defaults?.models?.[env.primaryModel]?.agentRuntime)}`"
+      detailsExpr: "env.providerMode === 'live-frontier' ? `provider=${selected?.provider} model=${selected?.model} runtime=${snapshot.config.agents?.defaults?.models?.[env.primaryModel]?.agentRuntime?.id}` : `mock mode: parsed ${scenario.id}`"
+    - name: builds the medium game artifact
+      actions:
+        - if:
+            expr: "env.providerMode !== 'live-frontier'"
+            then:
+              - assert: "true"
+            else:
+              - call: reset
+              - call: runAgentPrompt
+                args:
+                  - ref: env
+                  - sessionKey: agent:qa:medium-game-codex
+                    message:
+                      expr: config.buildPrompt
+                    provider:
+                      expr: selected?.provider
+                    model:
+                      expr: selected?.model
+                    timeoutMs:
+                      expr: resolveQaLiveTurnTimeoutMs(env, 420000, env.primaryModel)
+              - call: waitForOutboundMessage
+                saveAs: outbound
+                args:
+                  - ref: state
+                  - lambda:
+                      params: [candidate]
+                      expr: "candidate.conversation.id === 'qa-operator' && candidate.text.includes(config.artifactFile)"
+                  - expr: resolveQaLiveTurnTimeoutMs(env, 60000, env.primaryModel)
+              - set: artifactPath
+                value:
+                  expr: "path.join(env.gateway.workspaceDir, config.artifactFile)"
+              - call: waitForCondition
+                saveAs: artifact
+                args:
+                  - lambda:
+                      async: true
+                      expr: "((await fs.readFile(artifactPath, 'utf8').catch(() => '')).includes(config.gameTitle) ? await fs.readFile(artifactPath, 'utf8').catch(() => '') : undefined)"
+                  - expr: resolveQaLiveTurnTimeoutMs(env, 60000, env.primaryModel)
+                  - 500
+              - set: artifactLower
+                value:
+                  expr: normalizeLowercaseStringOrEmpty(artifact)
+              - assert:
+                  expr: "artifact.length >= config.minBytes"
+                  message:
+                    expr: "`expected medium game artifact >= ${config.minBytes} bytes, got ${artifact.length}`"
+              - assert:
+                  expr: "artifactLower.includes('star garden defenders') && artifactLower.includes('<canvas') && artifactLower.includes('requestanimationframe')"
+                  message: missing title, canvas, or animation loop
+              - assert:
+                  expr: "artifactLower.includes('keydown') || artifactLower.includes('keyup')"
+                  message: missing keyboard controls
+              - assert:
+                  expr: "artifactLower.includes('score') && artifactLower.includes('wave') && artifactLower.includes('pause') && artifactLower.includes('restart')"
+                  message: missing score, wave, pause, or restart systems
+              - assert:
+                  expr: "outbound.text.includes(config.artifactFile)"
+                  message:
+                    expr: "`final reply did not mention ${config.artifactFile}: ${outbound.text}`"
+      detailsExpr: "env.providerMode !== 'live-frontier' ? 'mock mode: skipped live medium-game build' : `${config.artifactFile} bytes=${artifact.length}`"

qa/scenarios/workspace/medium-game-plan-openclaw-harness.yaml

@@ -0,0 +1,156 @@
+title: Medium game plan OpenClaw harness
+
+scenario:
+  id: medium-game-plan-openclaw-harness
+  surface: workspace
+  coverage:
+    primary:
+      - workspace.planning
+    secondary:
+      - agents.openclaw-harness
+  objective: Verify GPT-5.5 can use the OpenClaw harness to plan and build a medium-complex self-contained browser game.
+  successCriteria:
+    - A live-frontier run fails fast unless the selected primary model is openai/gpt-5.5.
+    - The scenario forces the embedded OpenClaw harness before the build turn.
+    - The prompt explicitly asks the agent to enter plan mode before editing.
+    - The agent writes a self-contained HTML game with a canvas loop, controls, scoring, waves, pause, and restart.
+  docsRefs:
+    - docs/plugins/sdk-agent-harness.md
+    - docs/gateway/configuration-reference.md
+    - docs/help/testing.md
+  codeRefs:
+    - src/agents/harness/selection.ts
+    - src/agents/harness/builtin-openclaw.ts
+    - extensions/qa-lab/src/suite.ts
+  execution:
+    kind: flow
+    summary: Run with `pnpm openclaw qa suite --provider-mode live-frontier --model openai/gpt-5.5 --alt-model openai/gpt-5.5 --fast --thinking medium --scenario medium-game-plan-openclaw-harness`.
+    config:
+      requiredProvider: openai
+      requiredModel: gpt-5.5
+      harnessRuntime: openclaw
+      artifactFile: star-garden-defenders-openclaw.html
+      gameTitle: Star Garden Defenders
+      minBytes: 5000
+      buildPrompt: |-
+        Enter plan mode first and write a short implementation plan before editing.
+
+        Then build a medium-complex, self-contained browser game at ./star-garden-defenders-openclaw.html.
+
+        Game: Star Garden Defenders.
+        Requirements:
+        - one HTML file only; no external assets, fonts, scripts, or network calls
+        - canvas-based arcade loop with requestAnimationFrame
+        - keyboard controls and mouse or pointer support
+        - player movement, enemy waves, collectibles or power-ups, collision handling
+        - score, lives or health, wave number, pause, restart, and game-over state
+        - polished inline CSS and clear on-screen controls
+        - after writing the file, reply with the filename and the main systems implemented
+
+flow:
+  steps:
+    - name: confirms GPT-5.5 OpenClaw harness target
+      actions:
+        - set: selected
+          value:
+            expr: splitModelRef(env.primaryModel)
+        - assert:
+            expr: "env.providerMode !== 'live-frontier' || selected?.provider === config.requiredProvider"
+            message:
+              expr: "`expected live primary provider ${config.requiredProvider}, got ${env.primaryModel}`"
+        - assert:
+            expr: "env.providerMode !== 'live-frontier' || selected?.model === config.requiredModel"
+            message:
+              expr: "`expected live primary model ${config.requiredModel}, got ${env.primaryModel}`"
+        - if:
+            expr: "env.providerMode !== 'live-frontier'"
+            then:
+              - assert: "true"
+            else:
+              - call: patchConfig
+                saveAs: patchResult
+                args:
+                  - env:
+                      ref: env
+                    patch:
+                      agents:
+                        defaults:
+                          models:
+                            expr: "({ [env.primaryModel]: { agentRuntime: { id: config.harnessRuntime } } })"
+              - call: waitForGatewayHealthy
+                args:
+                  - ref: env
+                  - 60000
+              - call: waitForQaChannelReady
+                args:
+                  - ref: env
+                  - 60000
+              - call: readConfigSnapshot
+                saveAs: snapshot
+                args:
+                  - ref: env
+              - assert:
+                  expr: "snapshot.config.agents?.defaults?.models?.[env.primaryModel]?.agentRuntime?.id === config.harnessRuntime"
+                  message:
+                    expr: "`expected ${env.primaryModel} agentRuntime.id=${config.harnessRuntime}, got ${JSON.stringify(snapshot.config.agents?.defaults?.models?.[env.primaryModel]?.agentRuntime)}`"
+      detailsExpr: "env.providerMode === 'live-frontier' ? `provider=${selected?.provider} model=${selected?.model} runtime=${snapshot.config.agents?.defaults?.models?.[env.primaryModel]?.agentRuntime?.id}` : `mock mode: parsed ${scenario.id}`"
+    - name: builds the medium game artifact
+      actions:
+        - if:
+            expr: "env.providerMode !== 'live-frontier'"
+            then:
+              - assert: "true"
+            else:
+              - call: reset
+              - call: runAgentPrompt
+                args:
+                  - ref: env
+                  - sessionKey: agent:qa:medium-game-openclaw
+                    message:
+                      expr: config.buildPrompt
+                    provider:
+                      expr: selected?.provider
+                    model:
+                      expr: selected?.model
+                    timeoutMs:
+                      expr: resolveQaLiveTurnTimeoutMs(env, 420000, env.primaryModel)
+              - call: waitForOutboundMessage
+                saveAs: outbound
+                args:
+                  - ref: state
+                  - lambda:
+                      params: [candidate]
+                      expr: "candidate.conversation.id === 'qa-operator' && candidate.text.includes(config.artifactFile)"
+                  - expr: resolveQaLiveTurnTimeoutMs(env, 60000, env.primaryModel)
+              - set: artifactPath
+                value:
+                  expr: "path.join(env.gateway.workspaceDir, config.artifactFile)"
+              - call: waitForCondition
+                saveAs: artifact
+                args:
+                  - lambda:
+                      async: true
+                      expr: "((await fs.readFile(artifactPath, 'utf8').catch(() => '')).includes(config.gameTitle) ? await fs.readFile(artifactPath, 'utf8').catch(() => '') : undefined)"
+                  - expr: resolveQaLiveTurnTimeoutMs(env, 60000, env.primaryModel)
+                  - 500
+              - set: artifactLower
+                value:
+                  expr: normalizeLowercaseStringOrEmpty(artifact)
+              - assert:
+                  expr: "artifact.length >= config.minBytes"
+                  message:
+                    expr: "`expected medium game artifact >= ${config.minBytes} bytes, got ${artifact.length}`"
+              - assert:
+                  expr: "artifactLower.includes('star garden defenders') && artifactLower.includes('<canvas') && artifactLower.includes('requestanimationframe')"
+                  message: missing title, canvas, or animation loop
+              - assert:
+                  expr: "artifactLower.includes('keydown') || artifactLower.includes('keyup')"
+                  message: missing keyboard controls
+              - assert:
+                  expr: "artifactLower.includes('score') && artifactLower.includes('wave') && artifactLower.includes('pause') && artifactLower.includes('restart')"
+                  message: missing score, wave, pause, or restart systems
+              - assert:
+                  expr: "outbound.text.includes(config.artifactFile)"
+                  message:
+                    expr: "`final reply did not mention ${config.artifactFile}: ${outbound.text}`"
+      detailsExpr: "env.providerMode !== 'live-frontier' ? 'mock mode: skipped live medium-game build' : `${config.artifactFile} bytes=${artifact.length}`"

qa/scenarios/workspace/source-docs-discovery-report.yaml

@@ -0,0 +1,77 @@
+title: Source and docs discovery report
+
+scenario:
+  id: source-docs-discovery-report
+  surface: discovery
+  coverage:
+    primary:
+      - workspace.repo-discovery
+    secondary:
+      - docs.discovery
+  objective: Verify the agent can read repo docs and source, expand the QA plan, and publish a worked or did-not-work report.
+  successCriteria:
+    - Agent reads docs and source before proposing more tests.
+    - Agent identifies extra candidate scenarios beyond the seed list.
+    - Agent ends with a worked or failed QA report.
+  docsRefs:
+    - docs/help/testing.md
+    - docs/web/dashboard.md
+    - docs/channels/qa-channel.md
+  codeRefs:
+    - extensions/qa-lab/src/report.ts
+    - extensions/qa-lab/src/self-check.ts
+    - src/agents/system-prompt.ts
+  execution:
+    kind: flow
+    summary: Verify the agent can read repo docs and source, expand the QA plan, and publish a worked or did-not-work report.
+    config:
+      requiredFiles:
+        - repo/qa/scenarios/index.yaml
+        - repo/extensions/qa-lab/src/suite.ts
+        - repo/docs/help/testing.md
+      prompt: Read the seeded docs and source plan. The full repo is mounted under ./repo/. Explicitly inspect repo/qa/scenarios/index.yaml, repo/extensions/qa-lab/src/suite.ts, and repo/docs/help/testing.md, then report grouped into Worked, Failed, Blocked, and Follow-up. Mention at least two extra QA scenarios beyond the seed list.
+
+flow:
+  steps:
+    - name: reads seeded material and emits a protocol report
+      actions:
+        - call: reset
+        - call: runAgentPrompt
+          args:
+            - ref: env
+            - sessionKey: agent:qa:discovery
+              message:
+                expr: config.prompt
+              timeoutMs:
+                expr: liveTurnTimeoutMs(env, 30000)
+        - call: waitForCondition
+          saveAs: outbound
+          args:
+            - lambda:
+                expr: "state.getSnapshot().messages.filter((candidate) => candidate.direction === 'outbound' && candidate.conversation.id === 'qa-operator' && hasDiscoveryLabels(candidate.text)).at(-1)"
+            - expr: liveTurnTimeoutMs(env, 20000)
+            - expr: "env.providerMode === 'mock-openai' ? 100 : 250"
+        - assert:
+            expr: "!reportsMissingDiscoveryFiles(outbound.text)"
+            message:
+              expr: "`discovery report still missed repo files: ${outbound.text}`"
+        - assert:
+            expr: "!reportsDiscoveryScopeLeak(outbound.text)"
+            message:
+              expr: "`discovery report drifted beyond scope: ${outbound.text}`"
+        # Parity gate criterion 2 (no fake progress / fake tool completion):
+        # require an actual read tool call before the prose report. Without this,
+        # a model could fabricate a plausible Worked/Failed/Blocked/Follow-up
+        # report without ever touching the repo files the prompt names. The
+        # debug request log is fetched once and reused for both the assertion
+        # and its failure-message diagnostic. Each request's allInputText is
+        # lowercased inline at match time (the real prompt writes it as
+        # "Worked, Failed, Blocked") so the contains check is case-insensitive.
+        - set: discoveryDebugRequests
+          value:
+            expr: "env.mock ? [...(await fetchJson(`${env.mock.baseUrl}/debug/requests`))] : []"
+        - assert:
+            expr: "!env.mock || discoveryDebugRequests.some((request) => String(request.allInputText ?? '').toLowerCase().includes('worked, failed, blocked') && request.plannedToolName === 'read')"
+            message:
+              expr: "`expected at least one read tool call during discovery report scenario, saw plannedToolNames=${JSON.stringify(discoveryDebugRequests.map((request) => request.plannedToolName ?? null))}`"
+      detailsExpr: outbound.text