perf(e2e): consolidate Hermes dashboard coverage

.github/workflows/e2e.yaml

@@ -203,7 +203,7 @@ jobs:
             fi
             larger_runner="${LARGER_RUNNER_LABEL}"
           fi
-          runner_routing="$(jq -cn --arg standard "ubuntu-latest" --arg larger "${larger_runner}" '{"channels-stop-start-hermes":$larger,"channels-stop-start-openclaw":$standard,"common-egress-agent":$larger,"hermes-dashboard":$larger,"hermes-discord":$larger,"hermes-e2e":$larger,"hermes-inference-switch":$larger,"hermes-shields-config":$larger,"mcp-bridge-deepagents":$larger,"mcp-bridge-hermes":$larger,"mcp-bridge-openclaw":$standard,"rebuild-hermes":$larger,"rebuild-hermes-stale-base":$larger,"security-posture-hermes":$larger,"security-posture-openclaw":$standard}')"
+          runner_routing="$(jq -cn --arg standard "ubuntu-latest" --arg larger "${larger_runner}" '{"channels-stop-start-hermes":$larger,"channels-stop-start-openclaw":$standard,"common-egress-agent":$larger,"hermes-discord":$larger,"hermes-e2e":$larger,"hermes-inference-switch":$larger,"hermes-shields-config":$larger,"mcp-bridge-deepagents":$larger,"mcp-bridge-hermes":$larger,"mcp-bridge-openclaw":$standard,"rebuild-hermes":$larger,"rebuild-hermes-stale-base":$larger,"security-posture-hermes":$larger,"security-posture-openclaw":$standard}')"
           printf 'runner_routing=%s\n' "${runner_routing}" >> "${GITHUB_OUTPUT}"
 
       - name: Authenticate controller dispatch
@@ -2170,6 +2170,7 @@ jobs:
       NEMOCLAW_CLI_BIN: ${{ github.workspace }}/bin/nemoclaw.js
       NEMOCLAW_RUN_LIVE_E2E: "1"
       NEMOCLAW_E2E_INFERENCE_MODE: ${{ inputs.inference_mode || 'mock' }}
+      NEMOCLAW_E2E_HERMES_DASHBOARD: "1"
       NEMOCLAW_ACCEPT_THIRD_PARTY_SOFTWARE: "1"
       NEMOCLAW_AGENT: hermes
       NEMOCLAW_NON_INTERACTIVE: "1"
@@ -2179,7 +2180,7 @@ jobs:
     steps:
       - id: trusted_hermes_swap
         name: Provision trusted Hermes E2E swap
-        if: ${{ github.repository == 'NVIDIA/NemoClaw' && github.ref == 'refs/heads/main' && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && (github.event_name == 'schedule' || inputs.checkout_sha == '' || (github.event_name == 'workflow_dispatch' && inputs.checkout_sha != '' && (contains(format(',{0},', inputs.jobs), ',hermes-e2e,') || contains(format(',{0},', inputs.targets), ',hermes-e2e,')))) }}
+        if: ${{ github.repository == 'NVIDIA/NemoClaw' && github.ref == 'refs/heads/main' && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') && (github.event_name == 'schedule' || inputs.checkout_sha == '' || (github.event_name == 'workflow_dispatch' && inputs.checkout_sha != '' && (contains(format(',{0},', inputs.jobs), ',hermes-e2e,') || contains(format(',{0},', inputs.targets), ',hermes-e2e,') || contains(format(',{0},', inputs.jobs), ',hermes-dashboard,') || contains(format(',{0},', inputs.targets), ',hermes-dashboard,')))) }}
         shell: /bin/bash --noprofile --norc -e -o pipefail {0}
         env:
           BASH_ENV: /dev/null
@@ -2499,85 +2500,6 @@ jobs:
         shell: bash
         run: bash .github/scripts/docker-auth-cleanup.sh
 
-  hermes-dashboard:
-    needs: generate-matrix
-    if: ${{ (github.event_name != 'workflow_dispatch' || (inputs.jobs == '' && inputs.targets == '')) || contains(format(',{0},', inputs.jobs), ',hermes-dashboard,') || contains(format(',{0},', inputs.targets), ',hermes-dashboard,') }}
-    runs-on: ${{ fromJSON(needs.generate-matrix.outputs.runner_routing)['hermes-dashboard'] }}
-    timeout-minutes: 85
-    env:
-      E2E_JOB: "1"
-      E2E_TARGET_ID: "hermes-dashboard"
-      E2E_ARTIFACT_DIR: ${{ github.workspace }}/e2e-artifacts/live/hermes-dashboard
-      NEMOCLAW_CLI_BIN: ${{ github.workspace }}/bin/nemoclaw.js
-      NEMOCLAW_RUN_LIVE_E2E: "1"
-      NEMOCLAW_E2E_USE_HOSTED_INFERENCE: "1"
-      NEMOCLAW_ACCEPT_THIRD_PARTY_SOFTWARE: "1"
-      NEMOCLAW_AGENT: hermes
-      NEMOCLAW_NON_INTERACTIVE: "1"
-      NEMOCLAW_RECREATE_SANDBOX: "1"
-      NEMOCLAW_SANDBOX_NAME: e2e-hermes-dashboard
-      NEMOCLAW_E2E_HERMES_DASHBOARD: "1"
-      NEMOCLAW_ONBOARD_VALIDATION_TIMEOUT_SECONDS: "60"
-    steps:
-      - id: trusted_hermes_swap
-        name: Provision trusted Hermes E2E swap
-        if: ${{ github.repository == 'NVIDIA/NemoClaw' && github.ref == 'refs/heads/main' && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch') }}
-        shell: /bin/bash --noprofile --norc -e -o pipefail {0}
-        env:
-          BASH_ENV: /dev/null
-          CHECKOUT_SHA: ${{ inputs.checkout_sha }}
-          DISPATCH_SHA: ${{ github.sha }}
-          ENV: /dev/null
-          EVENT_NAME: ${{ github.event_name }}
-          EXPECTED_WORKFLOW_SHA: ${{ inputs.workflow_sha }}
-          LC_ALL: C
-          REF: ${{ github.ref }}
-          REPOSITORY: ${{ github.repository }}
-          RUNNER_ARCH_KIND: ${{ runner.arch }}
-          RUNNER_ENVIRONMENT_KIND: ${{ runner.environment }}
-          RUNNER_OS_KIND: ${{ runner.os }}
-          WORKFLOW_SHA: ${{ github.workflow_sha }}
-        run: *trusted-hermes-e2e-swap
-
-      - uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
-        with:
-          repository: ${{ inputs.checkout_repository || github.repository }}
-          ref: ${{ inputs.checkout_sha || github.sha }}
-          persist-credentials: false
-
-      - *dockerhub-auth
-
-      - name: Prepare E2E workspace
-        uses: NVIDIA/NemoClaw/.github/actions/prepare-e2e@f6304bc25fc35bfaa441c8c2fbfee38f72805a75
-
-      - name: Initialize runner comparison telemetry
-        if: ${{ github.repository == 'NVIDIA/NemoClaw' && github.ref == 'refs/heads/main' && inputs.checkout_sha == '' }}
-        continue-on-error: true
-        shell: bash
-        run: npx tsx tools/e2e/runner-comparison.mts initialize
-
-      - name: Run Hermes dashboard live Vitest test
-        env:
-          NVIDIA_INFERENCE_API_KEY: ${{ secrets.NVIDIA_INFERENCE_API_KEY }}
-        run: |
-          set -euo pipefail
-          npx tsx tools/e2e/live-vitest-invocation.mts run --test-path test/e2e/live/hermes-e2e.test.ts
-
-      - name: Finalize runner comparison telemetry
-        if: ${{ always() && github.repository == 'NVIDIA/NemoClaw' && github.ref == 'refs/heads/main' && inputs.checkout_sha == '' }}
-        continue-on-error: true
-        shell: bash
-        run: npx tsx tools/e2e/runner-comparison.mts finalize
-
-      - name: Upload Hermes dashboard live Vitest artifacts
-        if: always()
-        uses: NVIDIA/NemoClaw/.github/actions/upload-e2e-artifacts@7768e15eb90d3ee2d33432f481dfe8747e4f6d57
-
-      - name: Clean up Docker auth
-        if: always()
-        shell: bash
-        run: bash .github/scripts/docker-auth-cleanup.sh
-
   hermes-discord:
     needs: generate-matrix
     if: ${{ (github.event_name != 'workflow_dispatch' || (inputs.jobs == '' && inputs.targets == '')) || contains(format(',{0},', inputs.jobs), ',hermes-discord,') || contains(format(',{0},', inputs.targets), ',hermes-discord,') }}
@@ -5978,7 +5900,6 @@ jobs:
         sessions-agents-cli,
         hermes-e2e,
         hermes-gpu-startup,
-        hermes-dashboard,
         hermes-slack,
         hermes-discord,
         network-policy,
@@ -6046,6 +5967,7 @@ jobs:
           persist-credentials: false
           sparse-checkout: |
             tools/e2e/report-e2e-results.mts
+            tools/e2e/selector-aliases.mts
           sparse-checkout-cone-mode: false
       - name: Post E2E target results to PR
         uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0

test/e2e/README.md

@@ -77,6 +77,12 @@ discovery command locally to inspect the generated test matrix:
 npx tsx tools/e2e/credential-free-tests.mts
 ```
 
+The retired `hermes-dashboard` selector remains a compatibility alias for
+`hermes-e2e` in both selector inputs. Reports use the canonical
+`hermes-e2e` name. That lane always enables dashboard coverage while preserving
+the manually selected `mock`, `internal-nvidia`, or `public-nvidia` inference
+mode.
+
 ## Larger-runner routing
 
 The larger-runner experiment is inactive while the configuration variable
@@ -117,7 +123,7 @@ Successful state is discarded with the ephemeral runner.
 
 The fallback covers agent-turn latency, Hermes inference switch and shields,
 the Hermes Bedrock and stable MCP shards, the Hermes common-egress and channel
-stop/start shards, and the `hermes-e2e`, `hermes-dashboard`, `hermes-discord`,
+stop/start shards, the dashboard-bearing `hermes-e2e` lane, `hermes-discord`,
 and Hermes security-posture tests. Rebuild lanes with workflow-managed swap,
 dedicated-runner lanes, `mcp-bridge-dev`, and non-Hermes shards do not use it.
 Candidate-authored workflow definitions and fork-owned runs cannot reach it.
@@ -135,7 +141,7 @@ The eligible set is limited to the measured or repeatedly interrupted heavy
 lanes:
 
 - `common-egress-agent`;
-- `hermes-e2e`, `hermes-dashboard`, and `hermes-discord`;
+- `hermes-e2e`, including dashboard coverage, and `hermes-discord`;
 - both `hermes-inference-switch` modes;
 - `hermes-shields-config`;
 - the Hermes shards of `security-posture` and `channels-stop-start`;
@@ -260,7 +266,7 @@ window.
 ### Runner comparison telemetry
 
 Trusted `main` runs without an alternate checkout SHA record runner-comparison
-telemetry for 14 routed workflow lane identities / 17
+telemetry for 13 routed workflow lane identities / 16
 concrete job executions.
 
 - `agent-turn-latency`, spanning its sequential OpenClaw and Hermes setup
@@ -272,9 +278,8 @@ concrete job executions.
 - `mcp-bridge` with the `hermes` shard
 - `mcp-bridge` with the `deepagents` shard
 - `channels-stop-start` with the `hermes` shard
-- `hermes-dashboard`
 - `hermes-discord`
-- `hermes-e2e`
+- `hermes-e2e`, including dashboard coverage
 - `hermes-inference-switch` with the `hosted` and `anthropic` modes
 - `hermes-shields-config`
 - `security-posture` with the `hermes` shard

test/e2e/support/e2e-progress-fixture.test.ts

@@ -29,7 +29,7 @@ it.each([
 });
 
 it.each([
-  "hermes-dashboard",
+  "hermes-e2e",
   "hermes-discord",
   "hermes-shields-config",
   null,
@@ -40,7 +40,7 @@ it.each([
 it.each([
   ["rebuild-hermes", 15_000],
   ["rebuild-hermes-stale-base", 15_000],
-  ["hermes-dashboard", 60_000],
+  ["hermes-e2e", 60_000],
 ] as const)("wires the live %s comparison cadence into progress options (#7144)", (targetId, intervalMs) => {
   const samples: Array<{ kind: string; phase: string }> = [];
   const options = runnerComparisonProgressOptions(

test/e2e/support/e2e-report-to-pr-workflow-boundary.test.ts

@@ -398,6 +398,44 @@ it("renders comment content from job evidence without a live GitHub mutation", (
   expect(report.body).toContain("All requested tests passed");
 });
 
+it.each([
+  {
+    env: { JOB_TARGETS: "", JOBS: "hermes-dashboard" },
+    label: "test ID",
+    requestedLine: "**Requested test IDs:** `hermes-e2e`",
+  },
+  {
+    env: { JOB_TARGETS: "hermes-dashboard", JOBS: "" },
+    label: "target",
+    requestedLine: "**Requested targets:** `hermes-e2e`",
+  },
+])("reports the canonical Hermes result for a retired dashboard $label selector", ({
+  env,
+  requestedLine,
+}) => {
+  const report = renderE2eReport({
+    needs: {
+      "generate-matrix": { result: "success" },
+      "hermes-e2e": { result: "success" },
+    },
+    env: {
+      EXPLICIT_ONLY_JOBS: "",
+      TEST_MATRIX: "[]",
+      JOB_PR_NUMBER: "42",
+      ...env,
+    },
+    apiJobs: [{ conclusion: "success", name: "hermes-e2e", status: "completed" }],
+    apiJobsLoaded: true,
+    context: REPORT_CONTEXT,
+  });
+
+  expect(report.fatal).toBeUndefined();
+  expect(report.body).toContain(requestedLine);
+  expect(report.body).toContain("| hermes-e2e | ✅ success | — |");
+  expect(report.body).not.toContain("| hermes-dashboard |");
+  expect(report.body).not.toContain("not reported");
+});
+
 it("fails closed on an invalid test matrix without rendering a comment", () => {
   const report = renderE2eReport({
     needs: {

test/e2e/support/e2e-workflow.test.ts

@@ -645,6 +645,14 @@ describe("e2e workflow boundary", () => {
         selectedFreeStandingJobs: ["network-policy"],
         registryTargets: ["ubuntu-repo-cloud-openclaw"],
       });
+      for (const selectors of [{ jobs: "hermes-dashboard" }, { targets: "hermes-dashboard" }]) {
+        expect(evaluateE2eWorkflowDispatchSelectors(selectors)).toMatchObject({
+          valid: true,
+          liveTargetsRun: false,
+          selectedFreeStandingJobs: ["hermes-e2e"],
+          registryTargets: [],
+        });
+      }
     },
   );
 

test/e2e/support/hermes-dashboard-workflow-boundary.test.ts

@@ -7,73 +7,49 @@ import {
   validateHermesDashboardWorkflow,
   validateHermesDashboardWorkflowBoundary,
 } from "../../../tools/e2e/hermes-dashboard-workflow-boundary.mts";
-import {
-  HERMES_DASHBOARD_JOB_TIMEOUT_MAX_MINUTES,
-  HERMES_DASHBOARD_JOB_TIMEOUT_MINUTES,
-} from "../../../tools/e2e/hermes-timeout-contract.mts";
 
 describe("Hermes dashboard workflow boundary", () => {
-  it("accepts the checked-in workflow and rejects dashboard mode, execution, and reporting drift", () => {
+  it("keeps dashboard coverage in the canonical Hermes lane", () => {
     expect(validateHermesDashboardWorkflowBoundary()).toEqual([]);
-    const dashboardMode = readHermesDashboardWorkflow();
-    const dashboardJob = dashboardMode.jobs["hermes-dashboard"];
-    dashboardJob["timeout-minutes"] = 30;
-    dashboardJob.env!.E2E_ARTIFACT_DIR = "/tmp/hermes-dashboard";
-    dashboardJob.env!.NEMOCLAW_E2E_HERMES_DASHBOARD = "0";
-    dashboardJob.env!.NVIDIA_INFERENCE_API_KEY = "${{ secrets.NVIDIA_INFERENCE_API_KEY }}";
-    const checkout = dashboardJob.steps!.find((step) =>
+
+    const workflow = readHermesDashboardWorkflow();
+    const canonicalJob = workflow.jobs["hermes-e2e"];
+    canonicalJob.env!.NEMOCLAW_E2E_HERMES_DASHBOARD = "0";
+    canonicalJob.env!.NEMOCLAW_E2E_INFERENCE_MODE = "mock";
+    canonicalJob.env!.E2E_TARGET_ID = "hermes-dashboard";
+    canonicalJob.steps!.find((step) => step.name === "Run Hermes live Vitest test")!.run =
+      "echo skipped";
+    workflow.jobs["hermes-dashboard"] = structuredClone(canonicalJob);
+    workflow.jobs["hermes-discord"].env!.NEMOCLAW_E2E_HERMES_DASHBOARD = "1";
+    workflow.jobs["report-to-pr"].needs = ["hermes-dashboard"];
+
+    expect(validateHermesDashboardWorkflow(workflow)).toEqual(
+      expect.arrayContaining([
+        "hermes-dashboard must remain consolidated into hermes-e2e",
+        "only hermes-e2e may enable Hermes dashboard E2E coverage (found on hermes-discord)",
+        "hermes-e2e must enable Hermes dashboard coverage",
+        "hermes-e2e must preserve manual inference-mode selection",
+        "hermes-e2e must publish its canonical selector",
+        "hermes-e2e must run the live Vitest project",
+        "report-to-pr must wait for hermes-e2e",
+        "report-to-pr must not wait for retired hermes-dashboard",
+      ]),
+    );
+  });
+
+  it("keeps the canonical checkout trust boundary", () => {
+    const workflow = readHermesDashboardWorkflow();
+    const checkout = workflow.jobs["hermes-e2e"].steps!.find((step) =>
       step.uses?.startsWith("actions/checkout@"),
     )!;
     checkout.uses = "actions/checkout@v6";
     checkout.with!["persist-credentials"] = true;
-    expect(validateHermesDashboardWorkflow(dashboardMode)).toEqual(
+
+    expect(validateHermesDashboardWorkflow(workflow)).toEqual(
       expect.arrayContaining([
-        `hermes-dashboard timeout must be between ${HERMES_DASHBOARD_JOB_TIMEOUT_MINUTES} and ${HERMES_DASHBOARD_JOB_TIMEOUT_MAX_MINUTES} minutes`,
-        "hermes-dashboard must use its isolated artifact directory",
-        "hermes-dashboard must enable Hermes dashboard coverage",
-        "hermes-dashboard must not expose the inference key at job scope",
-        "hermes-dashboard checkout must pin a full action SHA",
-        "hermes-dashboard checkout must disable persisted credentials",
+        "hermes-e2e checkout must pin a full action SHA",
+        "hermes-e2e checkout must disable persisted credentials",
       ]),
     );
-
-    const misplacedDashboardMode = readHermesDashboardWorkflow();
-    misplacedDashboardMode.jobs["hermes-e2e"].env!.NEMOCLAW_E2E_HERMES_DASHBOARD = "1";
-    expect(validateHermesDashboardWorkflow(misplacedDashboardMode)).toContain(
-      "only hermes-dashboard may enable Hermes dashboard E2E coverage (found on hermes-e2e)",
-    );
-
-    const execution = readHermesDashboardWorkflow();
-    execution.jobs["hermes-dashboard"].steps!.find(
-      (step) => step.name === "Run Hermes dashboard live Vitest test",
-    )!.run = "echo skipped";
-    expect(validateHermesDashboardWorkflow(execution)).toContain(
-      "hermes-dashboard must run the live Vitest project",
-    );
-
-    const reporting = readHermesDashboardWorkflow();
-    reporting.jobs["report-to-pr"].needs = [];
-    expect(validateHermesDashboardWorkflow(reporting)).toContain(
-      "report-to-pr must wait for hermes-dashboard",
-    );
-  });
-
-  it("shares the bounded Hermes timeout headroom contract", () => {
-    const upperBound = readHermesDashboardWorkflow();
-    upperBound.jobs["hermes-dashboard"]["timeout-minutes"] =
-      HERMES_DASHBOARD_JOB_TIMEOUT_MAX_MINUTES;
-    expect(validateHermesDashboardWorkflow(upperBound)).toEqual([]);
-
-    for (const timeoutMinutes of [
-      HERMES_DASHBOARD_JOB_TIMEOUT_MINUTES - 1,
-      HERMES_DASHBOARD_JOB_TIMEOUT_MINUTES + 0.5,
-      HERMES_DASHBOARD_JOB_TIMEOUT_MAX_MINUTES + 1,
-    ]) {
-      const invalid = readHermesDashboardWorkflow();
-      invalid.jobs["hermes-dashboard"]["timeout-minutes"] = timeoutMinutes;
-      expect(validateHermesDashboardWorkflow(invalid)).toContain(
-        `hermes-dashboard timeout must be between ${HERMES_DASHBOARD_JOB_TIMEOUT_MINUTES} and ${HERMES_DASHBOARD_JOB_TIMEOUT_MAX_MINUTES} minutes`,
-      );
-    }
   });
 });

test/e2e/support/larger-runner-routing-workflow-boundary.test.ts

@@ -68,7 +68,6 @@ const standardRouting = {
   "channels-stop-start-hermes": "ubuntu-latest",
   "channels-stop-start-openclaw": "ubuntu-latest",
   "common-egress-agent": "ubuntu-latest",
-  "hermes-dashboard": "ubuntu-latest",
   "hermes-discord": "ubuntu-latest",
   "hermes-e2e": "ubuntu-latest",
   "hermes-inference-switch": "ubuntu-latest",
@@ -139,7 +138,6 @@ describe("larger-runner workflow routing boundary", () => {
       ...standardRouting,
       "channels-stop-start-hermes": largerRunner,
       "common-egress-agent": largerRunner,
-      "hermes-dashboard": largerRunner,
       "hermes-discord": largerRunner,
       "hermes-e2e": largerRunner,
       "hermes-inference-switch": largerRunner,