{
  "schemaVersion": 2,
  "date": "2026.07.23",
  "publishedAt": "2026-07-23T15:37:20-07:00",
  "timeZone": "America/Los_Angeles",
  "title": "Router performance telemetry added to Observatory",
  "publicationStatus": "Published",
  "executiveSummary": [
    "Added a Performance tab to Hiro's private Evaluation Observatory so routed development tasks can be reviewed by time, task label, selected model, route, status, duration, and token usage.",
    "The new read-only API aggregates the router's append-only JSONL ledger and reports input, cached-input, output, reasoning, and total input-plus-output tokens without returning prompts or model output.",
    "Restarted only Hiro's API process through its checked-in runner. Both local dashboard listeners returned the new endpoint successfully, while Qwen remained intentionally unloaded and the existing Cloudflare process was left unchanged."
  ],
  "workstreams": [
    {
      "title": "Performance dashboard",
      "status": "Completed",
      "details": [
        "Added a first-class Performance navigation tab with summary cards, a chronological task-attempt table, and token allocation by model.",
        "Each row identifies the safe task label, short task ID, task kind, risk, start time, exact cloud model or active local profile, reasoning level, route, attempt number, token breakdown, duration, and completion status.",
        "The page handles an empty router ledger and refreshes on demand or when its tab is selected."
      ]
    },
    {
      "title": "Prompt-free telemetry API",
      "status": "Completed",
      "details": [
        "Added a read-only performance endpoint backed by the router's append-only ledger with a configurable ledger path.",
        "Total token usage is defined as input plus output tokens. Cached input is shown as a subset of input and is not double-counted; reported reasoning tokens are displayed separately.",
        "Cloud route names resolve to their configured model and reasoning profiles. Local attempts are identified by Hiro's active Qwen profile."
      ]
    },
    {
      "title": "Safe task identity and ledger privacy",
      "status": "Completed",
      "details": [
        "Added an optional safe task label to the router CLI and PowerShell launcher for readable dashboard attribution.",
        "Unlabeled historical or future records fall back to task kind plus a short immutable task identifier.",
        "Removed the truncated final model message from new summary-ledger records; detailed per-task artifacts remain local. The dashboard API never returns prompts or output."
      ]
    },
    {
      "title": "Live service activation",
      "status": "Completed",
      "details": [
        "Verified that the existing dashboard HTML immediately exposed the new tab, then restarted only the exact process owning Hiro's three expected API listeners so the new route module would load.",
        "Used the checked-in blocking API runner with normalized Windows Path state and hidden process startup.",
        "Confirmed the performance endpoint on both HTTP port 8001 and the loopback Observatory port 8765. The current ledger contained one task attempt and 13,525 total input-plus-output tokens."
      ]
    }
  ],
  "decisions": [
    "Do not display task prompts or model output remotely. A safe operator label provides useful identity without expanding the dashboard's sensitive-data surface.",
    "Count input plus output as total tokens and report cached input separately because cached tokens are already part of input usage.",
    "Represent every attempt rather than collapsing escalations so model changes and the cost of failed lower-tier attempts remain visible.",
    "Keep this view read-only and under the Observatory's existing private-access boundary.",
    "Do not restart Cloudflare or load Qwen merely to activate a dashboard API change."
  ],
  "validation": [
    {
      "check": "Focused dashboard, API, router, and operational suite",
      "status": "passed",
      "result": "33 tests passed in 3.95 seconds, covering prompt-free output, exact token aggregation, model mapping, empty-ledger behavior, dashboard presence, existing evaluation APIs, remote access behavior, routing policy, one-escalation resume, output budgets, payloads, and operational boundaries."
    },
    {
      "check": "Python compilation and router launcher startup",
      "status": "passed",
      "result": "The modified server, configuration, performance API, router CLI, and dispatcher compiled successfully. The normalized PowerShell launcher returned a ready self-check with all five routes."
    },
    {
      "check": "Dashboard JavaScript parse",
      "status": "passed",
      "result": "The inline Observatory script was extracted and compiled with Node.js without a syntax error."
    },
    {
      "check": "Live API activation",
      "status": "passed",
      "result": "After the scoped API restart, ports 8001 and 8765 both returned HTTP 200 from the new performance endpoint with one task, one attempt, and 13,525 total tokens."
    },
    {
      "check": "Model shutdown preservation",
      "status": "passed",
      "result": "LM Studio reported that no models were loaded after activation, preserving the user's prior Qwen shutdown request."
    }
  ],
  "currentState": [
    "The Performance tab is active in Hiro's running private Evaluation Observatory and reads the append-only router summary ledger.",
    "New routed tasks can provide a safe label through the documented launcher; historical records remain identifiable through task kind and ID.",
    "The current dataset contains the initial Luna Low router probe. The view will become comparative as real routed tasks accumulate.",
    "The Cloudflare tunnel process and private-access configuration were not modified."
  ],
  "limitations": [
    "The dashboard can only report tasks that enter through Hiro's dedicated router; work performed directly in an existing ChatGPT conversation is outside this ledger.",
    "The initial dataset has one attempt, so model distribution and efficiency comparisons are not yet statistically useful.",
    "Older records created before safe task labels use a generated fallback label.",
    "Token counts are those reported by the model runtime or Codex CLI. They are usage telemetry, not a billing estimate.",
    "Local route records identify the configured active Qwen profile; durable recording of the exact local model identifier at execution time remains a possible future refinement."
  ],
  "nextSteps": [
    "Use a short safe label for each routed task so the Performance table remains readable without exposing prompts.",
    "Accumulate a varied sample before changing route thresholds, then compare validated success, total tokens, cache share, duration, and escalation frequency by model.",
    "Consider adding time-range and model filters once the ledger contains enough tasks to make filtering useful.",
    "Keep per-task prompts, output, credentials, and detailed artifacts local rather than expanding the remote telemetry surface."
  ],
  "disclosureNote": "This public entry omits task prompts, model output, credentials, access-control details, private data, process command lines, and actionable security information."
}