ci: tighten maturity artifact inputs

Merged via squash.

Prepared head SHA: 32c61da44d
Co-authored-by: Alix-007 <267018309+Alix-007@users.noreply.github.com>
Co-authored-by: steipete <58493+steipete@users.noreply.github.com>
Reviewed-by: @steipete

.github/workflows/maturity-scorecard.yml

@@ -0,0 +1,124 @@
+name: Maturity scorecard
+
+on:
+  workflow_dispatch:
+    inputs:
+      source_run_id:
+        description: Optional workflow run id containing qa-evidence.json artifacts
+        required: false
+        type: string
+      artifact_pattern:
+        description: Artifact name pattern to download from source_run_id
+        required: false
+        default: "*qa*"
+        type: string
+      strict_inputs:
+        description: Fail when score or QA evidence inputs have non-fatal drift
+        required: false
+        default: false
+        type: boolean
+  push:
+    branches: [main]
+    paths:
+      - "taxonomy.yaml"
+      - "docs/maturity-scores.yaml"
+      - "docs/maturity-scorecard.md"
+      - "docs/taxonomy.md"
+      - "docs/taxonomy-outline.md"
+      - "scripts/render-maturity-docs.ts"
+      - "package.json"
+      - ".github/workflows/maturity-scorecard.yml"
+  pull_request:
+    paths:
+      - "taxonomy.yaml"
+      - "docs/maturity-scores.yaml"
+      - "docs/maturity-scorecard.md"
+      - "docs/taxonomy.md"
+      - "docs/taxonomy-outline.md"
+      - "scripts/render-maturity-docs.ts"
+      - "package.json"
+      - ".github/workflows/maturity-scorecard.yml"
+
+permissions:
+  actions: read
+  contents: read
+
+concurrency:
+  group: ${{ format('{0}-{1}', github.workflow, github.ref) }}
+  cancel-in-progress: true
+
+env:
+  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
+  NODE_VERSION: "24.x"
+
+jobs:
+  render:
+    name: Render maturity docs
+    runs-on: ubuntu-24.04
+    timeout-minutes: 20
+    steps:
+      - name: Checkout
+        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6
+        with:
+          fetch-depth: 1
+          fetch-tags: false
+          persist-credentials: false
+          submodules: false
+
+      - name: Setup Node environment
+        uses: ./.github/actions/setup-node-env
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+          install-bun: "false"
+
+      - name: Check committed maturity docs
+        run: pnpm maturity:check
+
+      - name: Download QA evidence artifacts
+        if: ${{ github.event_name == 'workflow_dispatch' && inputs.source_run_id != '' }}
+        env:
+          GH_TOKEN: ${{ github.token }}
+          SOURCE_RUN_ID: ${{ inputs.source_run_id }}
+          ARTIFACT_PATTERN: ${{ inputs.artifact_pattern }}
+        run: |
+          set -euo pipefail
+          mkdir -p .artifacts/maturity-evidence
+          gh run download "$SOURCE_RUN_ID" \
+            --repo "$GITHUB_REPOSITORY" \
+            --pattern "$ARTIFACT_PATTERN" \
+            --dir .artifacts/maturity-evidence
+          find .artifacts/maturity-evidence -name qa-evidence.json -print
+
+      - name: Render artifact docs
+        env:
+          STRICT_INPUTS: ${{ github.event_name == 'workflow_dispatch' && inputs.strict_inputs }}
+        run: |
+          set -euo pipefail
+          args=(--output-dir .artifacts/maturity-docs --static-assets-dir .artifacts/maturity-docs/assets/maturity)
+          if [[ "$STRICT_INPUTS" == "true" ]]; then
+            args+=(--strict-inputs)
+          fi
+          if find .artifacts/maturity-evidence -name qa-evidence.json -print -quit 2>/dev/null | grep -q .; then
+            args+=(--evidence-dir .artifacts/maturity-evidence)
+          fi
+          pnpm maturity:render -- "${args[@]}"
+          {
+            echo "### Maturity scorecard docs"
+            echo
+            echo "- Committed docs check: passed"
+            echo "- Artifact docs: \`.artifacts/maturity-docs\`"
+            echo "- Strict inputs: \`${STRICT_INPUTS:-false}\`"
+            if find .artifacts/maturity-evidence -name qa-evidence.json -print -quit 2>/dev/null | grep -q .; then
+              echo "- QA evidence: included"
+            else
+              echo "- QA evidence: none downloaded"
+            fi
+          } >> "$GITHUB_STEP_SUMMARY"
+
+      - name: Upload maturity docs artifact
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: maturity-scorecard-docs-${{ github.run_id }}-${{ github.run_attempt }}
+          path: .artifacts/maturity-docs/
+          retention-days: 30
+          if-no-files-found: error

.github/workflows/openclaw-release-checks.yml

@@ -768,6 +768,122 @@ jobs:
       OPENCLAW_QA_CONVEX_SITE_URL: ${{ secrets.OPENCLAW_QA_CONVEX_SITE_URL }}
       OPENCLAW_QA_CONVEX_SECRET_CI: ${{ secrets.OPENCLAW_QA_CONVEX_SECRET_CI }}
 
+  qa_profile_release_evidence_release_checks:
+    name: Generate QA profile release evidence
+    needs: [resolve_target]
+    if: contains(fromJSON('["all","qa"]'), needs.resolve_target.outputs.rerun_group)
+    continue-on-error: true
+    runs-on: blacksmith-8vcpu-ubuntu-2404
+    timeout-minutes: 60
+    permissions:
+      contents: read
+    environment: qa-live-shared
+    env:
+      OPENCLAW_BUILD_PRIVATE_QA: "1"
+      OPENCLAW_ENABLE_PRIVATE_QA_CLI: "1"
+      OPENCLAW_QA_TRANSPORT_READY_TIMEOUT_MS: "180000"
+      OPENCLAW_QA_REDACT_PUBLIC_METADATA: "1"
+    steps:
+      - name: Checkout selected ref
+        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6
+        with:
+          persist-credentials: true
+          ref: ${{ needs.resolve_target.outputs.revision }}
+          fetch-depth: 1
+
+      - name: Setup Node environment
+        uses: ./.github/actions/setup-node-env
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+          install-bun: "true"
+
+      - name: Validate required QA credential env
+        env:
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        shell: bash
+        run: |
+          set -euo pipefail
+
+          if [[ -z "${OPENAI_API_KEY:-}" ]]; then
+            echo "Missing required OPENAI_API_KEY." >&2
+            exit 1
+          fi
+
+      - name: Build private QA runtime
+        env:
+          NODE_OPTIONS: --max-old-space-size=8192
+        run: node scripts/build-all.mjs qaRuntime
+
+      - name: Run release QA profile
+        id: run_profile
+        shell: bash
+        env:
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        run: |
+          set -euo pipefail
+
+          output_dir=".artifacts/qa-e2e/release-profile-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}"
+          echo "output_dir=${output_dir}" >> "$GITHUB_OUTPUT"
+
+          pnpm openclaw qa run \
+            --repo-root . \
+            --qa-profile release \
+            --output-dir "${output_dir}"
+
+      - name: Upload release QA profile evidence
+        id: upload_profile_evidence
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: release-qa-profile-release-${{ needs.resolve_target.outputs.revision }}
+          path: ${{ steps.run_profile.outputs.output_dir || '.artifacts/qa-e2e/' }}
+          retention-days: 30
+          if-no-files-found: warn
+
+      - name: Record advisory status
+        if: always()
+        shell: bash
+        env:
+          RELEASE_CHECK_JOB: qa_profile_release_evidence_release_checks
+          JOB_STATUS: ${{ job.status }}
+          RELEASE_CHECK_STEP_OUTCOMES: ${{ steps.run_profile.outcome }} ${{ steps.upload_profile_evidence.outcome }}
+        run: |
+          set -euo pipefail
+          status="success"
+          mark_status() {
+            case "$1" in
+              failure) status="failure" ;;
+              cancelled)
+                if [[ "$status" != "failure" ]]; then
+                  status="cancelled"
+                fi
+                ;;
+              success|skipped|"") ;;
+              *) status="failure" ;;
+            esac
+          }
+          mark_status "${JOB_STATUS:-}"
+          for outcome in ${RELEASE_CHECK_STEP_OUTCOMES:-}; do
+            mark_status "$outcome"
+          done
+          mkdir -p .artifacts/release-check-status
+          status_path=".artifacts/release-check-status/${RELEASE_CHECK_JOB}.env"
+          {
+            printf 'job=%s\n' "$RELEASE_CHECK_JOB"
+            printf 'status=%s\n' "$status"
+            printf 'job_status=%s\n' "${JOB_STATUS:-}"
+            printf 'step_outcomes=%s\n' "${RELEASE_CHECK_STEP_OUTCOMES:-}"
+          } > "$status_path"
+
+      - name: Upload advisory status
+        if: always()
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
+        with:
+          name: release-check-status-qa-profile-release-${{ needs.resolve_target.outputs.revision }}
+          path: .artifacts/release-check-status/qa_profile_release_evidence_release_checks.env
+          retention-days: 14
+          if-no-files-found: error
+
   qa_lab_parity_lane_release_checks:
     name: Run QA Lab parity lane (${{ matrix.lane }})
     needs: [resolve_target]
@@ -1947,6 +2063,7 @@ jobs:
       - docker_e2e_release_checks
       - package_acceptance_release_checks
       - qa_lab_parity_lane_release_checks
+      - qa_profile_release_evidence_release_checks
       - qa_lab_parity_report_release_checks
       - qa_lab_runtime_parity_release_checks
       - runtime_tool_coverage_release_checks
@@ -2016,7 +2133,7 @@ jobs:
           }
           advisory_status_override_allowed() {
             case "$1" in
-              qa_lab_parity_lane_release_checks|qa_lab_parity_report_release_checks|qa_lab_runtime_parity_release_checks|qa_live_matrix_release_checks|qa_live_telegram_release_checks|qa_live_discord_release_checks|qa_live_whatsapp_release_checks|qa_live_slack_release_checks)
+              qa_lab_parity_lane_release_checks|qa_profile_release_evidence_release_checks|qa_lab_parity_report_release_checks|qa_lab_runtime_parity_release_checks|qa_live_matrix_release_checks|qa_live_telegram_release_checks|qa_live_discord_release_checks|qa_live_whatsapp_release_checks|qa_live_slack_release_checks)
                 return 0
                 ;;
               *)
@@ -2032,6 +2149,7 @@ jobs:
             "docker_e2e_release_checks=${{ needs.docker_e2e_release_checks.result }}" \
             "package_acceptance_release_checks=${{ needs.package_acceptance_release_checks.result }}" \
             "qa_lab_parity_lane_release_checks=${{ needs.qa_lab_parity_lane_release_checks.result }}" \
+            "qa_profile_release_evidence_release_checks=${{ needs.qa_profile_release_evidence_release_checks.result }}" \
             "qa_lab_parity_report_release_checks=${{ needs.qa_lab_parity_report_release_checks.result }}" \
             "qa_lab_runtime_parity_release_checks=${{ needs.qa_lab_runtime_parity_release_checks.result }}" \
             "runtime_tool_coverage_release_checks=${{ needs.runtime_tool_coverage_release_checks.result }}" \

docs/concepts/multi-agent.md

@@ -37,7 +37,7 @@ that agent; if you copy credentials manually, copy only portable static
 `api_key` or `token` profiles.
 </Warning>
 
-Skills are loaded from each agent workspace plus shared roots such as `~/.openclaw/skills`, then filtered by the effective agent skill allowlist when configured. Use `agents.defaults.skills` for a shared baseline and `agents.list[].skills` for per-agent replacement. See [Skills: per-agent vs shared](/tools/skills#per-agent-vs-shared-skills) and [Skills: agent skill allowlists](/tools/skills#agent-skill-allowlists).
+Skills are loaded from each agent workspace plus shared roots such as `~/.openclaw/skills`, then filtered by the effective agent skill allowlist when configured. Use `agents.defaults.skills` for a shared baseline and `agents.list[].skills` for per-agent replacement. See [Skills: per-agent vs shared](/tools/skills#per-agent-vs-shared-skills) and [Skills: agent skill allowlists](/tools/skills#agent-allowlists).
 
 The Gateway can host **one agent** (default) or **many agents** side-by-side.
 

docs/gateway/troubleshooting.md

@@ -160,7 +160,7 @@ it disabled for read-only shared skill roots.
 
 Related:
 
-- [Skills config](/tools/skills-config#symlinked-sibling-repos)
+- [Skills config](/tools/skills-config#symlinked-skill-roots)
 - [Configuration examples](/gateway/configuration-examples#symlinked-sibling-skill-repo)
 
 ## Anthropic 429 extra usage required for long context

extensions/qa-lab/src/harness-parity.ts

@@ -98,16 +98,6 @@ export type HarnessParityResult = {
   firstDriftTurn?: number;
 };
 
-export type HarnessParityReport = {
-  generatedAt: string;
-  providerMode: string;
-  left: HarnessVariant;
-  right: HarnessVariant;
-  results: HarnessParityResult[];
-  pass: boolean;
-  failures: string[];
-};
-
 function sha256(value: string) {
   return createHash("sha256").update(value).digest("hex");
 }

extensions/qa-lab/src/runtime-tool-metadata.ts

@@ -23,8 +23,6 @@ export type QaRuntimeCapabilityLayer =
   | "optional-profile-or-plugin"
   | "structural-text";
 
-export type QaCodexToolLoading = "direct" | "searchable";
-
 export type RuntimeParityComparisonMode = "default" | "codex-native-workspace" | "outcome-only";
 
 export type QaRuntimeToolCoverageMetadata = {

extensions/qa-lab/src/scenario-catalog.test.ts

@@ -50,19 +50,22 @@ describe("qa scenario catalog", () => {
     expect(
       scenarioIds.filter((scenarioId) => requiredScenarioIds.includes(scenarioId)).toSorted(),
     ).toEqual(requiredScenarioIds);
-    const nativeExecutionScenarios = pack.scenarios.filter(
-      (scenario) => scenario.execution.kind !== "flow",
+    expect(
+      pack.scenarios
+        .filter((scenario) => scenario.execution?.kind !== "flow")
+        .map((scenario) => scenario.id)
+        .toSorted(),
+    ).toStrictEqual(
+      [
+        "channel-message-flows",
+        "control-ui-chat-flow-playwright",
+        "gateway-smoke",
+        "package-openclaw-for-docker",
+        "plugin-lifecycle-probe",
+        "qa-otel-smoke",
+        "ux-matrix-evidence-dashboard",
+      ].toSorted(),
     );
-    expect(nativeExecutionScenarios.length).toBeGreaterThan(0);
-    for (const scenario of nativeExecutionScenarios) {
-      const execution = scenario.execution;
-      if (execution.kind === "flow") {
-        throw new Error(`expected native execution scenario: ${scenario.id}`);
-      }
-      expect(["playwright", "script", "vitest"]).toContain(execution.kind);
-      expect(fs.existsSync(execution.path), `${scenario.id} execution.path exists`).toBe(true);
-      expect(execution.flow).toBeUndefined();
-    }
     expect(
       pack.scenarios
         .filter((scenario) => scenario.execution.kind === "flow")
@@ -173,21 +176,6 @@ describe("qa scenario catalog", () => {
     expect(uxMatrix.coverage?.primary).toContain("qa.artifact-safety");
   });
 
-  it("loads folded HTTP API script scenarios with primary taxonomy coverage", () => {
-    expect(readQaScenarioById("openai-compatible-chat-tools").coverage?.primary).toStrictEqual([
-      "gateway.openai-compatible-apis",
-    ]);
-    expect(readQaScenarioById("openai-web-search-minimal").coverage?.primary).toStrictEqual([
-      "runtime.reasoning-and-cache-controls",
-    ]);
-    expect(
-      readQaScenarioById("openai-web-search-native-assertions").coverage?.primary,
-    ).toStrictEqual(["web-search.openai-native-web-search", "plugins.web-search-and-fetch"]);
-    expect(readQaScenarioById("openwebui-openai-compatible").coverage?.primary).toStrictEqual([
-      "gateway.openai-compatible-apis",
-    ]);
-  });
-
   it("loads runtime parity tier metadata for first-hour and soak lanes", () => {
     const firstHour = readQaScenarioById("runtime-first-hour-20-turn");
     const soak = readQaScenarioById("runtime-soak-100-turn");

package.json

@@ -1573,6 +1573,8 @@
     "docs:list": "node scripts/docs-list.js",
     "docs:spellcheck": "bash scripts/docs-spellcheck.sh",
     "docs:spellcheck:fix": "bash scripts/docs-spellcheck.sh --write",
+    "maturity:check": "node --import tsx scripts/render-maturity-docs.ts --check",
+    "maturity:render": "node --import tsx scripts/render-maturity-docs.ts",
     "dup:check": "node scripts/check-duplicates.mjs",
     "dup:check:coverage": "node scripts/check-duplicates.mjs --coverage",
     "dup:check:json": "node scripts/check-duplicates.mjs --json",

qa/scenarios/runtime/openai-compatible-chat-tools.yaml

@@ -1,29 +0,0 @@
-title: OpenAI-compatible chat tools HTTP API
-
-scenario:
-  id: openai-compatible-chat-tools
-  surface: runtime
-  coverage:
-    primary:
-      - gateway.openai-compatible-apis
-    secondary:
-      - runtime.hosted-tool-use
-  objective: Verify the OpenAI-compatible chat-completions client and Docker lane preserve strict tool-call API behavior.
-  successCriteria:
-    - The Docker lane fails missing or placeholder OpenAI auth before Docker build work starts.
-    - The generated config preserves strict positive gateway port and timeout values.
-    - The chat-completions client posts to `/v1/chat/completions` with the expected gateway token and model header.
-    - Tool-call-only responses are accepted, visible content beside a tool call is rejected, and response bodies remain bounded.
-  docsRefs:
-    - docs/gateway/protocol.md
-    - docs/help/testing.md
-    - docs/concepts/qa-e2e-automation.md
-  codeRefs:
-    - scripts/e2e/lib/openai-chat-tools/client.mjs
-    - scripts/e2e/lib/openai-chat-tools/write-config.mjs
-    - scripts/e2e/openai-chat-tools-docker.sh
-    - test/e2e/qa-lab/runtime/openai-compatible-chat-tools.e2e.test.ts
-  execution:
-    kind: vitest
-    path: test/e2e/qa-lab/runtime/openai-compatible-chat-tools.e2e.test.ts
-    summary: Vitest coverage for OpenAI-compatible chat-completions tool-call API behavior.

qa/scenarios/runtime/openai-web-search-minimal.yaml

@@ -1,29 +0,0 @@
-title: OpenAI web_search minimal reasoning gate
-
-scenario:
-  id: openai-web-search-minimal
-  surface: model-provider
-  coverage:
-    primary:
-      - runtime.reasoning-and-cache-controls
-    secondary:
-      - web-search.openai-native-web-search
-      - tools.web-search
-  objective: Verify the OpenAI web_search minimal-reasoning E2E client distinguishes successful grounded turns from provider schema rejection.
-  successCriteria:
-    - Reject mode accepts the expected raw OpenAI schema rejection and the gateway schema wrapper.
-    - Reject mode fails if the agent run unexpectedly succeeds or fails for unrelated transport reasons.
-    - Success mode requires an `ok` agent result with the expected marker in visible reply payloads.
-    - Gateway ports are parsed strictly before connecting.
-  docsRefs:
-    - docs/tools/web.md
-    - docs/help/testing.md
-    - docs/concepts/qa-e2e-automation.md
-  codeRefs:
-    - scripts/e2e/lib/openai-web-search-minimal/client.mjs
-    - scripts/e2e/openai-web-search-minimal-docker.sh
-    - test/e2e/qa-lab/runtime/openai-web-search-minimal.e2e.test.ts
-  execution:
-    kind: vitest
-    path: test/e2e/qa-lab/runtime/openai-web-search-minimal.e2e.test.ts
-    summary: Vitest coverage for OpenAI web_search minimal-reasoning success and rejection validation.

qa/scenarios/runtime/openai-web-search-native-assertions.yaml

@@ -1,30 +0,0 @@
-title: OpenAI native web_search request assertions
-
-scenario:
-  id: openai-web-search-native-assertions
-  surface: model-provider
-  coverage:
-    primary:
-      - web-search.openai-native-web-search
-      - plugins.web-search-and-fetch
-    secondary:
-      - web-search.model-and-filter-routing
-      - tools.web-search
-  objective: Verify the OpenAI web_search Docker lane assertions require native Responses web_search evidence with bounded diagnostics.
-  successCriteria:
-    - A successful request must hit `/v1/responses` with native `web_search` and non-minimal reasoning.
-    - Large request logs are scanned without missing later success requests.
-    - Failure diagnostics are bounded and do not dump stale or oversized request bodies.
-    - Function-shaped `web_search` is rejected as native Responses proof.
-  docsRefs:
-    - docs/tools/web.md
-    - docs/help/testing.md
-    - docs/concepts/qa-e2e-automation.md
-  codeRefs:
-    - scripts/e2e/lib/openai-web-search-minimal/assertions.mjs
-    - scripts/e2e/lib/openai-web-search-minimal/mock-server.mjs
-    - test/e2e/qa-lab/runtime/openai-web-search-minimal-assertions.e2e.test.ts
-  execution:
-    kind: vitest
-    path: test/e2e/qa-lab/runtime/openai-web-search-minimal-assertions.e2e.test.ts
-    summary: Vitest coverage for native OpenAI web_search request-log assertions.

qa/scenarios/runtime/openwebui-openai-compatible.yaml

@@ -1,28 +0,0 @@
-title: OpenWebUI OpenAI-compatible API probe
-
-scenario:
-  id: openwebui-openai-compatible
-  surface: runtime
-  coverage:
-    primary:
-      - gateway.openai-compatible-apis
-    secondary:
-      - runtime.hosted-provider-turns
-      - runtime.provider-specific-model-options
-  objective: Verify the OpenWebUI E2E probe exercises OpenClaw through OpenWebUI's OpenAI-compatible model and chat APIs.
-  successCriteria:
-    - Probe environment limits are parsed strictly and control-plane requests time out quickly.
-    - Sign-in and model-list error bodies are bounded before diagnostics are emitted.
-    - Models mode authenticates and finds the OpenClaw model exposed by OpenWebUI.
-    - Chat mode posts to `/api/chat/completions`, validates the expected nonce, and fails when the reply omits it.
-  docsRefs:
-    - docs/help/testing.md
-    - docs/concepts/qa-e2e-automation.md
-  codeRefs:
-    - scripts/e2e/openwebui-probe.mjs
-    - scripts/e2e/openwebui-docker.sh
-    - test/e2e/qa-lab/runtime/openwebui-probe.e2e.test.ts
-  execution:
-    kind: vitest
-    path: test/e2e/qa-lab/runtime/openwebui-probe.e2e.test.ts
-    summary: Vitest coverage for OpenWebUI model and chat-completions probe behavior.

scripts/test-projects.test-support.mjs

@@ -1067,70 +1067,28 @@ const TOOLING_SOURCE_TEST_TARGETS = new Map([
       "src/image-generation/openai-compatible-image-provider.test.ts",
     ],
   ],
-  [
-    "scripts/e2e/lib/openai-chat-tools/client.mjs",
-    ["test/e2e/qa-lab/runtime/openai-compatible-chat-tools.e2e.test.ts"],
-  ],
-  [
-    "scripts/e2e/lib/openai-chat-tools/scenario.sh",
-    ["test/e2e/qa-lab/runtime/openai-compatible-chat-tools.e2e.test.ts"],
-  ],
-  [
-    "scripts/e2e/lib/openai-chat-tools/write-config.mjs",
-    ["test/e2e/qa-lab/runtime/openai-compatible-chat-tools.e2e.test.ts"],
-  ],
   [
     "scripts/e2e/openai-chat-tools-docker.sh",
-    [
-      "test/e2e/qa-lab/runtime/openai-compatible-chat-tools.e2e.test.ts",
-      "test/scripts/docker-e2e-plan.test.ts",
-    ],
-  ],
-  [
-    "scripts/e2e/lib/openai-web-search-minimal/assertions.mjs",
-    ["test/e2e/qa-lab/runtime/openai-web-search-minimal-assertions.e2e.test.ts"],
-  ],
-  [
-    "scripts/e2e/lib/openai-web-search-minimal/client.mjs",
-    ["test/e2e/qa-lab/runtime/openai-web-search-minimal.e2e.test.ts"],
-  ],
-  [
-    "scripts/e2e/lib/openai-web-search-minimal/mock-server.mjs",
-    [
-      "test/e2e/qa-lab/runtime/openai-web-search-minimal.e2e.test.ts",
-      "test/e2e/qa-lab/runtime/openai-web-search-minimal-assertions.e2e.test.ts",
-    ],
-  ],
-  [
-    "scripts/e2e/lib/openai-web-search-minimal/scenario.sh",
-    [
-      "test/e2e/qa-lab/runtime/openai-web-search-minimal.e2e.test.ts",
-      "test/e2e/qa-lab/runtime/openai-web-search-minimal-assertions.e2e.test.ts",
-    ],
+    ["test/scripts/openai-chat-tools-client.test.ts", "test/scripts/docker-e2e-plan.test.ts"],
   ],
   [
     "scripts/e2e/openai-web-search-minimal-docker.sh",
     [
       "test/scripts/docker-build-helper.test.ts",
       "test/scripts/docker-e2e-plan.test.ts",
-      "test/e2e/qa-lab/runtime/openai-web-search-minimal.e2e.test.ts",
-      "test/e2e/qa-lab/runtime/openai-web-search-minimal-assertions.e2e.test.ts",
+      "test/scripts/openai-web-search-minimal-client.test.ts",
+      "test/scripts/openai-web-search-minimal-assertions.test.ts",
     ],
   ],
-  [
-    "scripts/e2e/lib/openwebui/http-probe.mjs",
-    ["test/e2e/qa-lab/runtime/openwebui-probe.e2e.test.ts"],
-  ],
   [
     "scripts/e2e/openwebui-docker.sh",
     [
       "test/scripts/docker-build-helper.test.ts",
       "test/scripts/docker-e2e-plan.test.ts",
-      "test/e2e/qa-lab/runtime/openwebui-probe.e2e.test.ts",
+      "test/scripts/openwebui-probe.test.ts",
       "test/scripts/fixture-config.test.ts",
     ],
   ],
-  ["scripts/e2e/openwebui-probe.mjs", ["test/e2e/qa-lab/runtime/openwebui-probe.e2e.test.ts"]],
   [
     "scripts/e2e/plugin-binding-command-escape-docker.sh",
     [

src/scripts/test-projects.test.ts

@@ -885,6 +885,7 @@ describe("test-projects args", () => {
           "test/scripts/ios-team-id.test.ts",
           "test/scripts/ios-version.test.ts",
           "test/scripts/kitchen-sink-rpc-walk.test.ts",
+          "test/scripts/openai-chat-tools-client.test.ts",
           "test/scripts/report-test-temp-creations.test.ts",
           "test/scripts/test-projects.test.ts",
           "test/test-env.test.ts",
@@ -911,7 +912,6 @@ describe("test-projects args", () => {
         config: "test/vitest/vitest.e2e.config.ts",
         forwardedArgs: [
           "test/e2e/qa-lab/plugins/plugin-lifecycle-probe.e2e.test.ts",
-          "test/e2e/qa-lab/runtime/openai-compatible-chat-tools.e2e.test.ts",
           "test/openclaw-launcher.e2e.test.ts",
         ],
         includePatterns: null,

test/scripts/openai-chat-tools-client.test.ts

@@ -1,12 +1,12 @@
-// OpenAI-compatible chat tools tests cover QA Lab HTTP tool-call evidence.
+// Openai Chat Tools Client tests cover openai chat tools client script behavior.
 import { spawn, spawnSync } from "node:child_process";
 import { mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
 import { createServer, type Server } from "node:http";
 import { tmpdir } from "node:os";
 import path from "node:path";
 import { beforeAll, describe, expect, it } from "vitest";
-import { createBoundedChildOutput } from "../../../helpers/bounded-child-output.js";
-import { cleanupTempDirs, makeTempDir } from "../../../helpers/temp-dir.js";
+import { createBoundedChildOutput } from "../helpers/bounded-child-output.js";
+import { cleanupTempDirs, makeTempDir } from "../helpers/temp-dir.js";
 
 const clientPath = path.resolve("scripts/e2e/lib/openai-chat-tools/client.mjs");
 const dockerRunnerPath = path.resolve("scripts/e2e/openai-chat-tools-docker.sh");
@@ -14,6 +14,7 @@ const writeConfigPath = path.resolve("scripts/e2e/lib/openai-chat-tools/write-co
 
 interface ClientResult {
   error?: Error;
+  signal: NodeJS.Signals | null;
   status: number | null;
   stderr: string;
   stdout: string;
@@ -68,12 +69,13 @@ function runClient(
     }, timeout);
     child.on("error", (error) => {
       clearTimeout(timer);
-      resolve({ error, status: null, stderr: stderr.text(), stdout: stdout.text() });
+      resolve({ error, signal: null, status: null, stderr: stderr.text(), stdout: stdout.text() });
     });
-    child.on("exit", (status) => {
+    child.on("exit", (status, signal) => {
       clearTimeout(timer);
       resolve({
         error: timedOut ? new Error(`client timed out after ${timeout}ms`) : undefined,
+        signal,
         status,
         stderr: stderr.text(),
         stdout: stdout.text(),

test/scripts/openai-web-search-minimal-assertions.test.ts

@@ -1,4 +1,4 @@
-// OpenAI web-search minimal assertion tests cover QA Lab native web_search evidence.
+// Openai Web Search Minimal Assertions tests cover openai web search minimal assertions script behavior.
 import { spawnSync } from "node:child_process";
 import { mkdtempSync, rmSync, writeFileSync } from "node:fs";
 import { tmpdir } from "node:os";

test/scripts/openai-web-search-minimal-client.test.ts

@@ -1,6 +1,6 @@
-// OpenAI web-search minimal tests cover QA Lab hosted provider schema evidence.
+// Openai Web Search Minimal Client tests cover openai web search minimal client script behavior.
 import { describe, expect, it } from "vitest";
-import { testing } from "../../../../scripts/e2e/lib/openai-web-search-minimal/client.mjs";
+import { testing } from "../../scripts/e2e/lib/openai-web-search-minimal/client.mjs";
 
 describe("scripts/e2e/lib/openai-web-search-minimal/client.mjs", () => {
   it("accepts only the expected raw schema rejection in reject mode", () => {

test/scripts/openwebui-probe.test.ts

@@ -1,16 +1,17 @@
-// OpenWebUI probe tests cover QA Lab OpenAI-compatible API evidence.
+// Openwebui Probe tests cover openwebui probe script behavior.
 import { spawn } from "node:child_process";
 import { readFileSync } from "node:fs";
 import { createServer, type IncomingMessage, type Server as HttpServer } from "node:http";
 import { createServer as createTcpServer, type Server as TcpServer, type Socket } from "node:net";
 import path from "node:path";
 import { describe, expect, it } from "vitest";
-import { createBoundedChildOutput } from "../../../helpers/bounded-child-output.js";
+import { createBoundedChildOutput } from "../helpers/bounded-child-output.js";
 
 const probePath = path.resolve("scripts/e2e/openwebui-probe.mjs");
 
 interface ProbeResult {
   error?: Error;
+  signal: NodeJS.Signals | null;
   status: number | null;
   stderr: string;
   stdout: string;
@@ -66,12 +67,13 @@ function runProbe(baseUrl: string, env: Record<string, string> = {}, timeout = 3
     }, timeout);
     child.on("error", (error) => {
       clearTimeout(timer);
-      resolve({ error, status: null, stderr: stderr.text(), stdout: stdout.text() });
+      resolve({ error, signal: null, status: null, stderr: stderr.text(), stdout: stdout.text() });
     });
-    child.on("exit", (status) => {
+    child.on("exit", (status, signal) => {
       clearTimeout(timer);
       resolve({
         error: timedOut ? new Error(`probe timed out after ${timeout}ms`) : undefined,
+        signal,
         status,
         stderr: stderr.text(),
         stdout: stdout.text(),

test/scripts/test-projects.test.ts

@@ -294,7 +294,7 @@ describe("scripts/test-projects changed-target routing", () => {
   it("routes nested scripts through conventional owner tests", () => {
     expect(resolveChangedTestTargetPlan(["scripts/e2e/openwebui-probe.mjs"])).toEqual({
       mode: "targets",
-      targets: ["test/e2e/qa-lab/runtime/openwebui-probe.e2e.test.ts"],
+      targets: ["test/scripts/openwebui-probe.test.ts"],
     });
     expect(resolveChangedTestTargetPlan(["scripts/lib/docker-e2e-plan.mjs"])).toEqual({
       mode: "targets",
@@ -374,24 +374,21 @@ describe("scripts/test-projects changed-target routing", () => {
       ],
       [
         "scripts/e2e/lib/openai-chat-tools/write-config.mjs",
-        ["test/e2e/qa-lab/runtime/openai-compatible-chat-tools.e2e.test.ts"],
+        ["test/scripts/openai-chat-tools-client.test.ts"],
       ],
       [
         "scripts/e2e/lib/openai-chat-tools/scenario.sh",
-        ["test/e2e/qa-lab/runtime/openai-compatible-chat-tools.e2e.test.ts"],
+        ["test/scripts/openai-chat-tools-client.test.ts"],
       ],
       [
         "scripts/e2e/openai-chat-tools-docker.sh",
-        [
-          "test/e2e/qa-lab/runtime/openai-compatible-chat-tools.e2e.test.ts",
-          "test/scripts/docker-e2e-plan.test.ts",
-        ],
+        ["test/scripts/openai-chat-tools-client.test.ts", "test/scripts/docker-e2e-plan.test.ts"],
       ],
       [
         "scripts/e2e/lib/openai-web-search-minimal/mock-server.mjs",
         [
-          "test/e2e/qa-lab/runtime/openai-web-search-minimal.e2e.test.ts",
-          "test/e2e/qa-lab/runtime/openai-web-search-minimal-assertions.e2e.test.ts",
+          "test/scripts/openai-web-search-minimal-client.test.ts",
+          "test/scripts/openai-web-search-minimal-assertions.test.ts",
         ],
       ],
       [
@@ -399,8 +396,8 @@ describe("scripts/test-projects changed-target routing", () => {
         [
           "test/scripts/docker-build-helper.test.ts",
           "test/scripts/docker-e2e-plan.test.ts",
-          "test/e2e/qa-lab/runtime/openai-web-search-minimal.e2e.test.ts",
-          "test/e2e/qa-lab/runtime/openai-web-search-minimal-assertions.e2e.test.ts",
+          "test/scripts/openai-web-search-minimal-client.test.ts",
+          "test/scripts/openai-web-search-minimal-assertions.test.ts",
         ],
       ],
       [
@@ -408,14 +405,11 @@ describe("scripts/test-projects changed-target routing", () => {
         [
           "test/scripts/docker-build-helper.test.ts",
           "test/scripts/docker-e2e-plan.test.ts",
-          "test/e2e/qa-lab/runtime/openwebui-probe.e2e.test.ts",
+          "test/scripts/openwebui-probe.test.ts",
           "test/scripts/fixture-config.test.ts",
         ],
       ],
-      [
-        "scripts/e2e/lib/openwebui/http-probe.mjs",
-        ["test/e2e/qa-lab/runtime/openwebui-probe.e2e.test.ts"],
-      ],
+      ["scripts/e2e/lib/openwebui/http-probe.mjs", ["test/scripts/openwebui-probe.test.ts"]],
       [
         "scripts/e2e/lib/plugins/npm-registry-server.mjs",
         ["test/scripts/plugins-assertions.test.ts"],