{
  "context": {
    "cap_tokens": 129984,
    "max_model_len": 131072,
    "targets": []
  },
  "failures": [
    {
      "error": "python-stdlib; bounded-retention; external-evidence; degraded-capability",
      "eval_id": "low-overhead-dashboard-architecture",
      "suite": "milestone-execution"
    },
    {
      "error": "ordered-chain",
      "eval_id": "milestone-dependency-order",
      "suite": "milestone-execution"
    },
    {
      "error": "reject-incomplete; capture-proof; strict-reapply",
      "eval_id": "proof-buffer-recovery",
      "suite": "milestone-execution"
    },
    {
      "error": "timeout-alignment",
      "eval_id": "resumable-ci-monitor",
      "suite": "milestone-execution"
    },
    {
      "error": "backup-first",
      "eval_id": "local-remote-main-reconciliation",
      "suite": "milestone-execution"
    }
  ],
  "identity": {
    "base_url": "http://127.0.0.1:39026/v1",
    "candidate_id": "nemotron3-puzzle-75b",
    "config_id": "vllm-0.23.1-mtp3-131k-pinned",
    "model": "nemotron3-puzzle-75b-nvfp4",
    "started_at": "2026-07-12T07:25:23Z"
  },
  "intelligence": {
    "checks": [],
    "status": "not_run"
  },
  "run_id": "fast-bakeoff-20260712T072523Z",
  "schema": "anvil-serving.fast-tier-bakeoff/v1",
  "score_inputs": {
    "e2e_p50_ms": 0.0,
    "intelligence_pass_rate": null,
    "operational_fit_notes": [
      "endpoint was already loaded; benchmark did not start or stop serves"
    ],
    "session_recall_passed": false,
    "thinking_mode": "disabled",
    "tool_call_passed": false,
    "ttft_p50_ms": 0.0,
    "usable_context_tokens": null,
    "voice_latency_ms": null
  },
  "selection": {
    "context_targets": [
      32768
    ],
    "endpoint_already_loaded": true,
    "requests_per_context": 1,
    "suites": []
  },
  "session": {
    "checks": [],
    "status": "not_run"
  },
  "source_recipe": {
    "ref": "examples/primary-node/docker-compose.experiment.yml",
    "serve_command": "anvil-serving serves up --manifest examples/primary-node/serves.toml cand-nemotron3-puzzle-75b --confirm"
  },
  "suites": {
    "milestone-execution": {
      "checks": [
        {
          "content_excerpt": "**Design: Low-Overhead Local Observability Dashboard for a Single Developer (Windows GPU Workstation + Mac Mini)**  \n*Goal: One webpage showing host, VM/container, GPU, shared-memory, service, and ben",
          "error": "python-stdlib; bounded-retention; external-evidence; degraded-capability",
          "id": "low-overhead-dashboard-architecture",
          "latency_ms": 3117.6838874816895,
          "status": "failed",
          "text_checks": [
            {
              "name": "python-stdlib",
              "passed": false
            },
            {
              "name": "bounded-retention",
              "passed": false
            },
            {
              "name": "external-evidence",
              "passed": false
            },
            {
              "name": "degraded-capability",
              "passed": false
            }
          ],
          "validator": "deterministic_text_checks"
        },
        {
          "content_excerpt": "programmatic capture lifecycle -> compressed external artifact plus sanitized manifest -> retained-session comparison -> complete-path overhead measurement\n\nDependency logic:  \n- **Programmatic captur",
          "error": "ordered-chain",
          "id": "milestone-dependency-order",
          "latency_ms": 1893.4571743011475,
          "status": "failed",
          "text_checks": [
            {
              "name": "ordered-chain",
              "passed": false
            },
            {
              "name": "artifact-boundary",
              "passed": true
            }
          ],
          "validator": "deterministic_text_checks"
        },
        {
          "content_excerpt": "The scenario describes a situation where:\n\n- A task\u2019s required `pytest` command **exited with code 0** (success),\n- But **strict review** reports that the **command proof is missing** because the **sh",
          "error": "reject-incomplete; capture-proof; strict-reapply",
          "id": "proof-buffer-recovery",
          "latency_ms": 2392.103672027588,
          "status": "failed",
          "text_checks": [
            {
              "name": "reject-incomplete",
              "passed": false
            },
            {
              "name": "capture-proof",
              "passed": false
            },
            {
              "name": "strict-reapply",
              "passed": false
            }
          ],
          "validator": "deterministic_text_checks"
        },
        {
          "content_excerpt": "To design a **safe, resumable workflow** that avoids duplicate pull requests (PRs), remains **fail-closed on CI failures**, and gracefully handles the constraint that the outer process runner kills th",
          "error": "timeout-alignment",
          "id": "resumable-ci-monitor",
          "latency_ms": 2414.547920227051,
          "status": "failed",
          "text_checks": [
            {
              "name": "timeout-alignment",
              "passed": false
            },
            {
              "name": "persist-resume",
              "passed": true
            },
            {
              "name": "reuse-pr",
              "passed": true
            },
            {
              "name": "no-ci-bypass",
              "passed": true
            }
          ],
          "validator": "deterministic_text_checks"
        },
        {
          "content_excerpt": "This is a nuanced Git reconciliation scenario. Let\u2019s break it down carefully and then provide a **safe, step-by-step plan** that satisfies all your constraints:\n\n---\n\n### \u2705 **Problem Summary**\n\nYou ha",
          "error": "backup-first",
          "id": "local-remote-main-reconciliation",
          "latency_ms": 2222.43070602417,
          "status": "failed",
          "text_checks": [
            {
              "name": "backup-first",
              "passed": false
            },
            {
              "name": "remote-target",
              "passed": true
            },
            {
              "name": "preserve-untracked",
              "passed": true
            },
            {
              "name": "verify-identical",
              "passed": true
            }
          ],
          "validator": "deterministic_text_checks"
        }
      ],
      "date": "2026-07-12",
      "source": "docs/findings/2026-07-12-qwen35-122b-mxfp4-evidence/planning-milestone-execution.suite.json",
      "status": "failed",
      "work_class": "planning"
    }
  },
  "thinking": {
    "chat_template_kwargs": {
      "enable_thinking": false
    },
    "mode": "disabled",
    "unsupported": false
  },
  "timing": {
    "chat": {
      "e2e_p50_ms": 0.0,
      "e2e_p95_ms": 0.0,
      "output_tokens": 0,
      "ttft_p50_ms": 0.0,
      "ttft_p95_ms": 0.0
    },
    "wall_ms": 12077.249765396118
  },
  "tool": {
    "checks": [],
    "status": "not_run"
  },
  "voice": {
    "llm_latency_ms": null,
    "status": "not_run",
    "stt_latency_ms": null,
    "total_turn_latency_ms": null,
    "tts_latency_ms": null
  }
}