mirrors/pikasTech-unidesk
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: wire web probe sentinel validation (#912)

Browse Source 
Co-authored-by: Codex <codex@noreply.local>
This commit is contained in:
Lyon
2026-06-26 00:46:45 +08:00
committed by GitHub
parent 4bd179e898
commit db3fed012e
6 changed files with 1205 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/src/hwlab-node-help.ts
+12 -2
View File
@@ -58,6 +58,9 @@ export function hwlabNodeHelp(): Record<string, unknown> {
"bun scripts/cli.ts hwlab nodes web-probe sentinel control-plane plan --node D601 --lane v03 --dry-run",
"bun scripts/cli.ts hwlab nodes web-probe sentinel control-plane status --node D601 --lane v03",
"bun scripts/cli.ts hwlab nodes web-probe sentinel control-plane trigger-current --node D601 --lane v03 --dry-run",
"bun scripts/cli.ts hwlab nodes web-probe sentinel validate --node D601 --lane v03",
"bun scripts/cli.ts hwlab nodes web-probe sentinel maintenance stop --node D601 --lane v03 --confirm --wait",
"bun scripts/cli.ts hwlab nodes web-probe sentinel report --node D601 --lane v03 --view turn-summary",
"bun scripts/cli.ts hwlab nodes observability plan --node D601 --lane v03",
"bun scripts/cli.ts hwlab nodes observability status --node D601 --lane v03",
"bun scripts/cli.ts hwlab nodes observability apply --node D601 --lane v03 --dry-run",
@@ -70,6 +73,7 @@ export function hwlabNodeHelp(): Record<string, unknown> {
"`control-plane sync --confirm` syncs the YAML-declared local-k3s postgres bootstrap Secret, terminates a stale running Argo operation, deletes failed Argo hook Jobs, and recreates stale non-ready StatefulSet pods that are still pinned to an old controller revision with pull/backoff errors.",
"`--wait` defaults to 120 seconds. If the PipelineRun is still active after 120 seconds, the CLI returns a warning plus env-reuse and git-mirror inspection commands instead of blocking.",
"`web-probe sentinel image/control-plane` renders the YAML-first image, GitOps and Argo plan from the owning configRefs; unavailable service validation is a structured failure, not an automatic second execution path.",
"`web-probe sentinel validate|maintenance|report` talks to the sentinel through k3s internal Service DNS, records only analyze summaries/views, and never runs a public/fallback validation path.",
"Use `--rerun` for a deliberate YAML-first config-only publish when UniDesk node/lane render inputs changed but the HWLAB source commit did not."
],
};
@@ -112,13 +116,19 @@ export function hwlabNodeWebProbeHelp(): Record<string, unknown> {
"bun scripts/cli.ts hwlab nodes web-probe sentinel control-plane plan --node D601 --lane v03 --dry-run",
"bun scripts/cli.ts hwlab nodes web-probe sentinel control-plane status --node D601 --lane v03",
"bun scripts/cli.ts hwlab nodes web-probe sentinel control-plane trigger-current --node D601 --lane v03 --dry-run",
"bun scripts/cli.ts hwlab nodes web-probe sentinel validate --node D601 --lane v03",
"bun scripts/cli.ts hwlab nodes web-probe sentinel validate --node D601 --lane v03 --quick-verify --confirm --wait",
"bun scripts/cli.ts hwlab nodes web-probe sentinel maintenance start --node D601 --lane v03 --confirm --wait --release-id <id>",
"bun scripts/cli.ts hwlab nodes web-probe sentinel maintenance stop --node D601 --lane v03 --confirm --wait --release-id <id>",
"bun scripts/cli.ts hwlab nodes web-probe sentinel report --node D601 --lane v03 --view summary",
"bun scripts/cli.ts hwlab nodes web-probe sentinel report --node D601 --lane v03 --view trace-frame",
"bun scripts/cli.ts hwlab nodes web-probe script --node D601 --lane v03 <<'JS'\nexport default async ({ waitWorkbenchReady, fetchJson, fetchApiMatrix, recordStep, collectText, safeEvaluate, screenshot }) => {\n const ready = await waitWorkbenchReady();\n const workspace = await fetchJson('/v1/workbench/workspace?projectId=prj_hwpod_workbench');\n const apiMatrix = await fetchApiMatrix(['/v1/workbench/workspace?projectId=prj_hwpod_workbench', '/auth/session']);\n const workspaceText = await collectText('#workspace');\n const evaluated = await safeEvaluate(({ a, b }) => ({ sum: a + b }), { a: 1, b: 2 });\n await screenshot('workbench.png');\n recordStep('workbench-summary', { finalUrl: ready.finalUrl, workspaceOk: workspace.ok, apiMatrixOk: apiMatrix.ok });\n return { finalUrl: ready.finalUrl, workspaceOk: workspace.ok, workspaceText, evaluated };\n};\nJS",
],
actions: {
run: "Run the repo-owned scripts/web-live-dom-probe.mjs helper.",
script: "Run caller-provided Playwright JS after CLI-managed /auth/login; the script receives authenticated browser/context/page plus gotoStable/reloadStable/gotoCurrentStable/safeReload/fetchJson/safeFetchJson/fetchApiMatrix/recordStep/collectText/safeEvaluate/waitWorkbenchReady/screenshotOnError/summarizeWorkspace/summarizeConversation helpers and must not handle secrets itself.",
observe: "Start, inspect, control, stop, collect, and analyze a pure-client long-running Workbench observer on the target host. The observer runs a control page plus a passive observer page in a shared-auth browser context, receives commands through stateDir/commands files, writes JSONL artifacts, and does not expose any inbound service API.",
sentinel: "Render the YAML-first service wrapper configRef graph plus image/GitOps/Argo control-plane plan for the production web-probe sentinel. This reads observability.webProbe.sentinel.enabled/configRefs and validates owning YAML presence, shape, redacted hashes, and cross-ref consistency without starting a browser or reading secret values.",
sentinel: "Render the YAML-first service wrapper configRef graph plus image/GitOps/Argo control-plane plan for the production web-probe sentinel, then validate/maintenance/report through the k3s internal sentinel Service DNS. Quick verify still uses web-probe observe/analyze artifacts as truth and records only redacted report summaries/views.",
},
notes: [
"The default probe URL, browser proxy mode, observe/analyze alert thresholds, and project-management observe behavior come from config/hwlab-node-lanes.yaml webProbe; pass --url only when intentionally overriding the YAML-selected origin.",
@@ -134,7 +144,7 @@ export function hwlabNodeWebProbeHelp(): Record<string, unknown> {
"observe analyze scans every sampled DOM point, extracts Workbench timing text such as 总耗时/total and 最近 N 秒/分前, and writes a sample point vs turn timing report: each Markdown table row starts with the timestamp, followed by each turn's 总耗时(s) and 最近更新(s). Timing series are reported for post-processing/manual analysis instead of auto-judged from status tail output.",
"observe analyze also reports visible “加载中” count, owner attribution, concurrent loading owners, and continuous visible segments; fixes must reduce real loading latency, not reveal incomplete content early to make this metric disappear.",
"script/observe support --browser-proxy-mode auto|direct; use direct for A/B evidence when frontend RUM is slow but OTel server spans are absent or fast, instead of falling back to raw Playwright.",
"sentinel plan/status is a configuration visibility command for the service wrapper; sentinel image/control-plane renders image, GitOps and Argo control-plane state from owning YAML and refuses to report deployment mutation until the remote publish job is wired. observe start/status/command/collect/analyze remain the sampling and analysis truth.",
"sentinel plan/status is a configuration visibility command for the service wrapper; sentinel image/control-plane renders image, GitOps and Argo control-plane state from owning YAML. sentinel validate checks /api/health, /metrics, recent analyze report and publicExposure; maintenance stop can run the configured quick verify and index the observe/analyze report. observe start/status/command/collect/analyze remain the sampling and analysis truth.",
"Use recordStep(name, data) or fetchApiMatrix(paths) to keep structured partial evidence when a later step fails.",
"Use reloadStable(), gotoCurrentStable(), or safeReload() for bounded retries around page reload/current-URL navigation jitter such as ERR_NETWORK_CHANGED.",
"Playwright page.evaluate accepts one serializable argument; use page.evaluate(({ a, b }) => ..., { a, b }) or safeEvaluate(fn, { a, b }).",