{  "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": "reuse-pr",      "eval_id": "resumable-ci-monitor",      "suite": "milestone-execution"    }  ],  "identity": {    "base_url": "http://127.0.0.1:30004/v1",    "candidate_id": "qwen35-122b-a10b-mxfp4",    "config_id": "vllm-marlin-w4a16-131k",    "model": "qwen35-122b-mxfp4",    "started_at": "2026-07-12T06:08:36Z"  },  "intelligence": {    "checks": [],    "status": "not_run"  },  "run_id": "fast-bakeoff-20260712T060836Z",  "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.flexibility.yml",    "serve_command": "anvil-serving serves up --manifest examples/primary-node/serves.toml heavy-qwen35-122b-mxfp4 --confirm"  },  "suites": {    "milestone-execution": {      "checks": [        {          "content_excerpt": "### Recommended Implementation Shape: The \"Sidecar-Snapshot\" Architecture\n\nTo meet the constraints of **low overhead**, **no admin rights**, and **cross-platform (Windows GPU + Mac Mini)** visibility,",          "error": "python-stdlib; bounded-retention; external-evidence; degraded-capability",          "id": "low-overhead-dashboard-architecture",          "latency_ms": 4592.247724533081,          "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": "The logical ordering of these tasks relies on a progression from raw data acquisition to artifact creation, then to validation, and finally to performance analysis.\n\n1.  **Programmatic capture lifecyc",          "error": "ordered-chain",          "id": "milestone-dependency-order",          "latency_ms": 2904.294490814209,          "status": "failed",          "text_checks": [            {              "name": "ordered-chain",              "passed": false            },            {              "name": "artifact-boundary",              "passed": true            }          ],          "validator": "deterministic_text_checks"        },        {          "content_excerpt": "Based on the constraints provided, the core issue is a **state desynchronization**: the command execution succeeded (exit code 0), but the orchestration layer failed to capture the necessary artifacts",          "error": "reject-incomplete; capture-proof; strict-reapply",          "id": "proof-buffer-recovery",          "latency_ms": 3607.667922973633,          "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": "This is a classic distributed systems problem involving **idempotency**, **state reconciliation**, and **timeout mismatch**. The core issue is that the command's internal logic (30-minute poll) is dec",          "error": "reuse-pr",          "id": "resumable-ci-monitor",          "latency_ms": 3648.905038833618,          "status": "failed",          "text_checks": [            {              "name": "timeout-alignment",              "passed": true            },            {              "name": "persist-resume",              "passed": true            },            {              "name": "reuse-pr",              "passed": false            },            {              "name": "no-ci-bypass",              "passed": true            }          ],          "validator": "deterministic_text_checks"        },        {          "content_excerpt": "This is a classic Git divergence scenario involving a \"duplicate merge\" and an untracked file. The goal is to align your local `main` with `origin/main` (which contains the remote merge commit and the",          "id": "local-remote-main-reconciliation",          "latency_ms": 3634.589910507202,          "status": "passed",          "text_checks": [            {              "name": "backup-first",              "passed": true            },            {              "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": 18421.159029006958  },  "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  }}