feat(qa): add "all" taxonomy profile (#95947)

* qa: add all maturity profile

* test: update qa coverage profile expectations

.github/workflows/qa-profile-evidence.yml

@@ -16,7 +16,7 @@ on:
         default: ""
         type: string
       qa_profile:
-        description: Taxonomy QA profile id to run
+        description: Taxonomy QA profile id to run (for example release or all)
         required: true
         default: release
         type: string
@@ -47,7 +47,7 @@ on:
         type: boolean
     secrets:
       OPENAI_API_KEY:
-        description: OpenAI API key used by release QA profile scenarios
+        description: OpenAI API key used by live QA profile scenarios
         required: true
     outputs:
       artifact_name:

docs/concepts/qa-e2e-automation.md

@@ -31,7 +31,7 @@ script aliases; both forms are supported.
 
 | Command                                             | Purpose                                                                                                                                                                                                                                                                 |
 | --------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `qa run`                                            | Bundled QA self-check without `--qa-profile`; taxonomy-backed maturity profile runner with `--qa-profile smoke-ci` or `--qa-profile release`.                                                                                                                           |
+| `qa run`                                            | Bundled QA self-check without `--qa-profile`; taxonomy-backed maturity profile runner with `--qa-profile smoke-ci`, `--qa-profile release`, or `--qa-profile all`.                                                                                                      |
 | `qa suite`                                          | Run repo-backed scenarios against the QA gateway lane. Aliases: `pnpm openclaw qa suite --runner multipass` for a disposable Linux VM.                                                                                                                                  |
 | `qa coverage`                                       | Print the YAML scenario-coverage inventory (`--json` for machine output).                                                                                                                                                                                               |
 | `qa parity-report`                                  | Compare two `qa-suite-summary.json` files and write the agentic parity report, or use `--runtime-axis --token-efficiency` to write Codex-vs-OpenClaw runtime parity and token-efficiency reports from one runtime-pair summary.                                         |
@@ -75,8 +75,10 @@ pnpm openclaw qa run \
 
 Use `smoke-ci` for deterministic profile proof with mock model providers and
 Crabline fake provider servers. Use `release` for Stable/LTS proof against live
-channels. When a command also needs an OpenClaw root profile, put the root
-profile before the QA command:
+channels. Use `all` only for explicit full-taxonomy evidence runs; it selects
+every active maturity category and can be dispatched through the `QA Profile
+Evidence` workflow with `qa_profile=all`. When a command also needs an OpenClaw
+root profile, put the root profile before the QA command:
 
 ```bash
 pnpm openclaw --profile work qa run --qa-profile smoke-ci

docs/help/testing.md

@@ -190,7 +190,10 @@ inside every shard.
   - When dispatched by `pnpm openclaw qa run --qa-profile <profile>`, embeds the
     selected taxonomy profile scorecard in the same `qa-evidence.json`.
     `smoke-ci` writes slim evidence, which sets `evidenceMode: "slim"` and omits
-    per-entry `execution`.
+    per-entry `execution`. `release` covers the curated release-readiness slice;
+    `all` selects every active maturity category and is intended for explicit QA
+    Profile Evidence workflow dispatches when a full scorecard artifact is
+    needed.
   - Runs multiple selected scenarios in parallel by default with isolated
     gateway workers. `qa-channel` defaults to concurrency 4 (bounded by the
     selected scenario count). Use `--concurrency <count>` to tune the worker

extensions/qa-lab/src/cli.runtime.test.ts

@@ -514,6 +514,24 @@ describe("qa cli runtime", () => {
     expect(suiteArgs.channelDriverSelection).toBeUndefined();
   });
 
+  it("runs the all profile through the live taxonomy profile path", async () => {
+    await runQaProfileCommand({
+      repoRoot: "/tmp/openclaw-repo",
+      profile: "all",
+      surface: "agent-runtime-and-provider-execution",
+      category: "agent-runtime-and-provider-execution.agent-turn-execution",
+      providerMode: "mock-openai",
+    });
+
+    const suiteArgs = mockFirstObjectArg(runQaSuite);
+    expectFields(suiteArgs, {
+      providerMode: "mock-openai",
+      channelDriver: "live",
+    });
+    expect(suiteArgs.channelDriverSelection).toBeUndefined();
+    expectWriteContains(stdoutWrite, "QA run profile: all; categories: 1; scenarios:");
+  });
+
   it("filters QA-channel-pinned scenarios from the Crabline smoke profile", async () => {
     runQaSuite.mockImplementationOnce(async () => {
       await fs.writeFile(suiteEvidencePath, JSON.stringify(makeQaEvidence()), "utf8");
@@ -592,7 +610,7 @@ describe("qa cli runtime", () => {
         repoRoot: "/tmp/openclaw-repo",
         profile: "nightly",
       }),
-    ).rejects.toThrow('--qa-profile must be one of smoke-ci, release, got "nightly".');
+    ).rejects.toThrow('--qa-profile must be one of smoke-ci, release, all, got "nightly".');
     expect(runQaSuite).not.toHaveBeenCalled();
   });
 

extensions/qa-lab/src/coverage-report.test.ts

@@ -135,7 +135,7 @@ describe("qa coverage report", () => {
       "telegram",
       "whatsapp",
     ]);
-    expect(inventory.scorecardTaxonomy.profileCount).toBe(2);
+    expect(inventory.scorecardTaxonomy.profileCount).toBe(3);
     expect(
       inventory.scorecardTaxonomy.profiles.find((profile) => profile.id === "smoke-ci"),
     ).toMatchObject({
@@ -147,6 +147,14 @@ describe("qa coverage report", () => {
     ).toMatchObject({
       channelDriver: "live",
     });
+    expect(
+      inventory.scorecardTaxonomy.profiles.find((profile) => profile.id === "all"),
+    ).toMatchObject({
+      channelDriver: "live",
+      categoryIds: expect.arrayContaining([
+        "browser-automation-and-exec-sandbox-tools.tool-invocation-and-execution",
+      ]),
+    });
     expect(inventory.scorecardTaxonomy.categoryCount).toBeGreaterThan(200);
     expect(inventory.scorecardTaxonomy.requiredCategoryCount).toBeGreaterThan(0);
     expect(inventory.scorecardTaxonomy.requiredCategoryCount).toBeLessThanOrEqual(
@@ -233,7 +241,7 @@ describe("qa coverage report", () => {
     expect(report).toContain("- Evidence refs:");
     expect(report).toContain("- Scenario coverage IDs:");
     expect(report).toContain(
-      "- browser-automation-and-exec-sandbox-tools.tool-invocation-and-execution (browser-automation-and-exec-sandbox-tools / Tool Invocation and Execution; partial): profiles: release, smoke-ci; coverage IDs:",
+      "- browser-automation-and-exec-sandbox-tools.tool-invocation-and-execution (browser-automation-and-exec-sandbox-tools / Tool Invocation and Execution; partial): profiles: all, release, smoke-ci; coverage IDs:",
     );
     expect(report).toContain("primary:playwright:ui/src/ui/e2e/chat-flow.e2e.test.ts (ui.control)");
     expect(report).not.toContain("### Unknown Scenario Coverage IDs");

taxonomy.yaml

@@ -219,6 +219,12 @@ profiles:
       - browser-automation-and-exec-sandbox-tools.browser-automation
       - browser-automation-and-exec-sandbox-tools.tool-invocation-and-execution
       - browser-automation-and-exec-sandbox-tools.sandbox-and-tool-policy
+  - id: all
+    description: Full taxonomy scorecard selector for generated maturity coverage evidence across
+      every active category. Intended for explicit QA evidence workflow dispatches rather than the
+      default release gate.
+    channelDriver: live
+    includeAllCategories: true
 levels:
   - id: planned
     code: M0

test/scripts/ci-workflow-guards.test.ts

@@ -588,6 +588,15 @@ describe("ci workflow guards", () => {
       default: false,
       type: "boolean",
     });
+    expect(qaEvidenceWorkflow.on.workflow_dispatch.inputs.qa_profile).not.toHaveProperty("options");
+    expect(qaEvidenceWorkflow.on.workflow_call.inputs.qa_profile.type).toBe("string");
+    const validateProfileStep = qaRunJob.steps.find(
+      (step) => step.name === "Validate QA profile input",
+    );
+    expect(validateProfileStep.run).toContain(
+      "taxonomy.profiles.find((entry) => entry.id === requested)",
+    );
+    expect(validateProfileStep.run).toContain("profile=${profile.id}");
     expect(generateJob.if).toBe("${{ inputs.qa_evidence_run_id == '' }}");
     expect(generateJob.uses).toBe("./.github/workflows/qa-profile-evidence.yml");
     expect(generateJob.with).toMatchObject({