{ "run_id": "TayHCode--sysone-cpu-gpt-6-luna-1792683877827961506", "date": "2026-10-22T15:50:43.532038+00:00", "repo": "TayHCode/sysone-cpu", "kind": "repo", "source": "https://github.com/TayHCode/sysone-cpu", "commit": "c236055c37fc05a0e3f5e9a2933dd8eb946e4f89", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-1002bc876f0002f622e14f9c5b99f9f66721fccc0356f4d53ed24f2f79a3ac5d", "pass": true, "outcome": "pass", "time_to_working_s": 342.13706823205575, "total_s": 365.70405626296997, "steps": [ "pwd; rg --files -g 'README*' -g 'AGENTS.md' -g 'pyproject.toml' -g 'package.json' -g 'Makefile' -g 'requirements*.txt' -g 'p3-models.md' -g '.github/workflows/*' -g 'SKILL.md' /root/.agents 2>/dev/null | head -100; python3 --version; id -u", "ls -la /; ls -la ; rg --files ", "cat README.md; cat 2>/dev/null; cat /root/.agents/skills/i-have-adhd/SKILL.md /root/.agents/skills/ponytail/SKILL.md /root/.agents/skills/p3-mode/SKILL.md 2>/dev/null; find . -name AGENTS.md -o -name '*.py' -o -name '*.sh'", "command -v vault-search && vault-search 'sysone-cpu Laya CPU inference benchmark setup' || true; find /root/.agents -type f -maxdepth 5 2>/dev/null | head -60; cat docs/setup.md; sed -n '1,240p' scripts/download_model.py; sed -n '1,220p' benchmarks/bench_laya_cpu.py", "mkdir -p .tools .scratch .coldpass; export TMPDIR=\"$PWD/.scratch\" UV_PYTHON_PREFERENCE=only-managed UV_CACHE_DIR=\"$PWD/.cache/uv\" UV_PYTHON_INSTALL_DIR=\"$PWD/.tools/python\" HF_HOME=\"$PWD/.cache/huggingface\"; curl -LsSf https://astral.sh/uv/install.sh -o .scratch/install-uv.sh && UV_INSTALL_DIR=\"$PWD/.tools\" UV_NO_MODIFY_PATH=1 sh .scratch/install-uv.sh && export PATH=\"$PWD/.tools:$PATH\" && uv venv --python 3.12 && uv pip install --python .venv --only-binary :all: torch==2.14.0 --index-url https://download.pytorch.org/whl/cpu && uv pip install --python .venv --only-binary :all: laya==0.3.4 transformers==5.17.0 tokenizers==0.23.3 safetensors==0.8.0 huggingface_hub==1.32.0 numpy==2.5.3 psutil==7.2.2", "export TMPDIR=\"$PWD/.scratch\" UV_CACHE_DIR=\"$PWD/.cache/uv\" UV_PYTHON_INSTALL_DIR=\"$PWD/.tools/python\" HF_HOME=\"$PWD/.cache/huggingface\" PATH=\"$PWD/.tools:$PATH\"; uv run --no-project --python .venv python scripts/download_model.py", "export TMPDIR=\"$PWD/.scratch\" UV_CACHE_DIR=\"$PWD/.cache/uv\" UV_PYTHON_INSTALL_DIR=\"$PWD/.tools/python\" HF_HOME=\"$PWD/.cache/huggingface\" PATH=\"$PWD/.tools:$PATH\"; uv run --no-project --python .venv python benchmarks/bench_laya_cpu.py --model .cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output .cache/first-run.json; cat .cache/first-run.json", "cat scripts/parity.py | sed -n '1,260p'; cat formal/README.md; ls -la .coldpass; ls /inputs 2>/dev/null", "mkdir -p .coldpass; cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\".tools/uv\",\"run\",\"--no-project\",\"--python\",\".venv\",\"python\",\"benchmarks/bench_laya_cpu.py\",\"--model\",\".cache/model/typed-decisions\",\"--threads\",\"4\",\"--warmup\",\"1\",\"--repeats\",\"1\",\"--counts\",\"1,3\",\"--output\",\".cache/replay-run.json\"],\"cwd\":\"\",\"env\":{\"TMPDIR\":\"\",\"UV_CACHE_DIR\":\"\",\"UV_PYTHON_INSTALL_DIR\":\"\",\"HF_HOME\":\"\"},\"expected_file\":\".cache/replay-run.json\",\"expected_text\":\"\\\"device\\\": \\\"cpu\\\"\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[\n {\"kind\":\"claim\",\"claim\":\"The benchmark reports CPU execution and batch equivalence for its synthetic workload.\",\"source\":\"Expect `meta.device` to be `\\\"cpu\\\"`, finite probabilities and passing batch checks.\",\"input\":\"README PyTorch quickstart workload at counts 1 and 3\",\"expected\":\"meta.device is cpu and batch_equivalence.same_public_answers is true\",\"probe_kind\":\"cli\",\"argv\":[\".tools/uv\",\"run\",\"--no-project\",\"--python\",\".venv\",\"python\",\"benchmarks/bench_laya_cpu.py\",\"--model\",\".cache/model/typed-decisions\",\"--threads\",\"4\",\"--warmup\",\"1\",\"--repeats\",\"1\",\"--counts\",\"1,3\",\"--output\",\".cache/claim-run.json\"],\"expected_file\":\".cache/claim-run.json\",\"expected_text\":\"\\\"device\\\": \\\"cpu\\\"\",\"cwd\":\"\",\"env\":{\"TMPDIR\":\"\",\"UV_CACHE_DIR\":\"\",\"UV_PYTHON_INSTALL_DIR\":\"\",\"HF_HOME\":\"\"}}\n]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[\n {\"kind\":\"example\",\"claim\":\"Run README PyTorch FP32 quickstart benchmark\",\"source\":\"README.md, Quickstart: PyTorch FP32\",\"input\":\"--threads 4 --warmup 1 --repeats 1 --counts 1,3\",\"expected\":\"CPU inference results are written to JSON with batch equivalence\",\"argv\":[\".tools/uv\",\"run\",\"--no-project\",\"--python\",\".venv\",\"python\",\"benchmarks/bench_laya_cpu.py\",\"--model\",\".cache/model/typed-decisions\",\"--threads\",\"4\",\"--warmup\",\"1\",\"--repeats\",\"1\",\"--counts\",\"1,3\",\"--output\",\".cache/example-run.json\"],\"cwd\":\"\",\"env\":{\"TMPDIR\":\"\",\"UV_CACHE_DIR\":\"\",\"UV_PYTHON_INSTALL_DIR\":\"\",\"HF_HOME\":\"\"},\"expected_text\":\"wrote .cache/example-run.json\"},\n {\"kind\":\"example\",\"claim\":\"Run local standard library checks documented in README\",\"source\":\"README.md, Local checks\",\"input\":\"python3 -m unittest discover -s tests -q\",\"expected\":\"documented checks complete\",\"argv\":[\"python3\",\"-m\",\"unittest\",\"discover\",\"-s\",\"tests\",\"-q\"],\"cwd\":\"\"},\n {\"kind\":\"example\",\"claim\":\"Run documented syntax check\",\"source\":\"README.md, Local checks\",\"input\":\"python3 scripts/check_syntax.py\",\"expected\":\"syntax check completes\",\"argv\":[\"python3\",\"scripts/check_syntax.py\"],\"cwd\":\"\"}\n]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Inspected README entry points, scripts, and benchmark harnesses. The product downloads a checkpoint and runs an explicitly invoked benchmark; no product scheduler, recurring loop, or webhook cycle exists.\",\"checks\":[]}\nEOF\nrm -f .cache/replay-run.json .cache/claim-run.json .cache/example-run.json\nCOLDPASS_WORKSPACE= python3 -I --validate --replay", "python3 - <<'PY'\np='README.md'\ns=open(p).read()\nfor line in s.splitlines():\n if 'Expect `meta.device`' in line or 'finite probabilities' in line or 'passing batch checks' in line: print(repr(line))\nPY", "python3 - <<'PY'\np='.coldpass/claims.json'\ns=open(p).read().replace('Expect `meta.device` to be `\\\\\"cpu\\\\\"`, finite probabilities and passing batch checks.','One timed repeat is a functionality probe; use at least ten for measurements.')\nopen(p,'w').write(s)\nPY\nCOLDPASS_WORKSPACE= python3 -I --validate --replay", "cat .coldpass/claims.json", "python3 - <<'PY'\np='.coldpass/claims.json'; s=open(p).read().replace('One timed repeat is a functionality probe; use at least ten for measurements.','The final command uses synthetic ticket questions and saves answers, package versions, latency and sampled memory to `.cache/first-run.json`.'); open(p,'w').write(s)\nPY\nCOLDPASS_WORKSPACE= python3 -I --validate --replay", "python3 - <<'PY'\np='.coldpass/claims.json'; s=open(p).read().replace('The final command uses synthetic ticket questions and saves answers, package versions, latency and sampled memory to `.cache/first-run.json`.','The final command uses synthetic ticket questions'); open(p,'w').write(s)\nPY\nCOLDPASS_WORKSPACE= python3 -I --validate --replay", "python3 - <<'PY'\np='.coldpass/claims.json'; s=open(p).read().replace('The final command uses synthetic ticket questions','Expect `meta.device` to be `\"cpu\"`'); open(p,'w').write(s)\nPY\nCOLDPASS_WORKSPACE= python3 -I --validate --replay", "python3 - <<'PY'\nimport json\np='.coldpass/claims.json'; d=json.load(open(p)); d[0]['source']='Expect `meta.device` to be `\"cpu\"`'; open(p,'w').write(json.dumps(d,indent=2))\nPY\nCOLDPASS_WORKSPACE= python3 -I --validate --replay", "cat > .coldpass/claims.json <<'EOF'\n[\n {\"kind\":\"claim\",\"claim\":\"Benchmark runs the synthetic workload and records inference results.\",\"source\":\"Expect `meta.device` to be `\\\"cpu\\\"`\",\"input\":\"Synthetic README quickstart ticket questions at counts 1 and 3\",\"expected\":\"CPU metadata and equivalent batched answers are present in the JSON result\",\"probe_kind\":\"cli\",\"argv\":[\".tools/uv\",\"run\",\"--no-project\",\"--python\",\".venv\",\"python\",\"benchmarks/bench_laya_cpu.py\",\"--model\",\".cache/model/typed-decisions\",\"--threads\",\"4\",\"--warmup\",\"1\",\"--repeats\",\"1\",\"--counts\",\"1,3\",\"--output\",\".cache/claim-run.json\"],\"expected_file\":\".cache/claim-run.json\",\"expected_text\":\"\\\"device\\\": \\\"cpu\\\"\",\"cwd\":\"\",\"env\":{\"TMPDIR\":\"\",\"UV_CACHE_DIR\":\"\",\"UV_PYTHON_INSTALL_DIR\":\"\",\"HF_HOME\":\"\"}}\n]\nEOF\npython3 -m json.tool .coldpass/claims.json >/dev/null; COLDPASS_WORKSPACE= python3 -I --validate --replay", "cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Run pinned Laya typed-decisions inference and CPU benchmark\",\"operation_scope\":\"README PyTorch FP32 quickstart on Python 3.12, Linux x86-64 CPU\",\"steps\":[\"Installed uv with the README installer in .tools.\",\"Created a Python 3.12 venv and installed the README's pinned CPU PyTorch and Laya dependencies.\",\"Ran scripts/download_model.py; the pinned public checkpoint passed size and SHA-256 validation.\",\"Ran benchmarks/bench_laya_cpu.py with the README's one-repeat counts 1,3 quickstart settings.\",\"Ran README local unittest and syntax checks; checker replay passed.\"],\"deviations\":[],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF\n" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Run pinned Laya typed-decisions inference and CPU benchmark", "suggested_fix": null, "tokens_in": 443235, "tokens_out": 3770, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ ".tools/uv", "run", "--no-project", "--python", ".venv", "python", "benchmarks/bench_laya_cpu.py", "--model", ".cache/model/typed-decisions", "--threads", "4", "--warmup", "1", "--repeats", "1", "--counts", "1,3", "--output", ".cache/replay-run.json-checker-816b4bc112054695ac5a0bff5a114001" ], "kind": "cli", "returncode": 0, "stdout": "timing 1 questions ...\n p50=677.9 ms p95=677.9 ms 1.48 q/s RSS=2052.8 MiB CPU=109.0%\ntiming 3 questions ...\n p50=1584.7 ms p95=1584.7 ms 1.89 q/s RSS=2056.8 MiB CPU=128.0%\nwrote .cache/replay-run.json-checker-816b4bc112054695ac5a0bff5a114001", "stderr": "", "expected_file": ".cache/replay-run.json-checker-816b4bc112054695ac5a0bff5a114001", "file_checked": true, "file_excerpt": "\"device\": \"cpu\",\n \"model_path\": \"\",\n \"model_config\": {\n \"encoder\": \"answerdotai/ModernBERT-large\",\n \"head_layers\": 2,\n \"max_len\": 1024,\n \"head_max_len\": 256,\n \"max_prefixes\": 6,\n \"act_costs\": {\n \"escalate\": 0.5\n },\n \"cost_wrong_act\": 3.0,\n \"amp_dtype\": \"bf16\",\n \"model_name\": \"laya-typed-decisions\",\n \"training\": {\n \"updates\": 7313,\n \"epochs_completed\": 1,\n \"hours\": 1.96,\n \"world_size\": 1,\n \"fine_tuned_from_checkpoint\": true\n },\n \"gradient_checkpointing\": true,\n \"max_tokens_per_batch\": 4096,\n \"fine_tuned\": true\n },\n \"calibration_source\": \"pinned upstream rl_agent_config.json\",\n \"cold_load_ms\": 24687.351,\n \"rss_before_mib\": 222.05,\n \"rss_after_load_mib\": 2036.53\n },\n \"workloads\": {\n \"1\": {\n \"p50_ms\": 677.864,\n \"p95_ms\": 677.864,\n \"min_ms\": 677.864,\n \"max_ms\": 677.864,\n \"mean_ms\": 677.864,\n \"questions\": 1,\n \"questions_per_second_p50\": 1.475,\n \"rss_peak_mib\": 2052.75,\n \"cpu_percent_mean_sampled\": 109.0,\n \"output_sha256_first\": \"615045d6d0cc8bcc75c059903638b8198377b74f90ab179d89f8f006b21cecdf\",\n \"output_sha256_last\": \"615045d6d0cc8bcc75c059903638b8198377b74f90ab179d89f8f006b21cecdf\",\n \"deterministic_repeated_output\": true,\n \"sample_ms\": [\n 677.864\n ]\n },\n \"3\": {\n \"p50_ms\": 1584.688,\n \"p95_ms\": 1584.688,\n \"min_ms\": 1584.688,\n \"max_ms\": 1584.688,\n \"mean_ms\": 1584.688,\n \"questions\": 3,\n \"questions_per_second_p50\": 1.893,\n \"rss_peak_mib\": 2056.77,\n \"cpu_percent_mean_sampled\": 128.0,\n \"output_sha256_first\": \"62e8e2041019b6894716c30d3050e0beec1e70ea2b9c0e0405e80fb01a4e3aa4\",\n \"output_sha256_last\": \"62e8e2041019b6894716c30d3050e0beec1e70ea2b9c0e0405e80fb01a4e3aa4\",\n \"deterministic_repeated_output\": true,\n \"sample_ms\": [\n 1584.688\n ]\n }\n },\n \"batch_equivalence\": {\n \"same_public_answers\": true,\n \"batched_digest\": \"9b003fbe3501b995d7d9255fe97b2044dec65b44825b40302b949c40eb2ed62d\",\n \"singles_digest\": \"9b003fbe3501b995d7d9255fe97b2044dec65b44825b40302b949c40eb2ed62d\",\n \"batched_answers\": {\n \"department\": {\n \"type\": \"choice\",\n \"choice\": \"billing\",\n \"probabilities\": {\n \"billing\": 0.6989,\n \"technical\": 0.0814,\n \"sales\": 0.1338,\n \"other\": 0.086\n },\n \"confidence\": 0.3258,\n \"action\": {\n \"act_probability\": 1.0\n }\n },\n \"urgency\": {\n \"type\": \"score\",\n \"score\": 1.6111,\n \"legend\": {\n \"0\": \"not urgent\",\n \"1\": \"soon\",\n \"2\": \"critical or blocking\"\n },\n \"probabilities\": {\n \"0\": 0.0408,\n \"1\": 0.3073,\n \"2\": 0.6519\n },\n \"confidence\": 0.2972,\n \"action\": {\n \"act_probability\": 1.0\n }\n },\n \"refund\": {\n \"type\": \"noul\",\n \"noul\": 0.68,\n \"confidence\": 0.68,\n \"action\": {\n \"act_probability\": 1.0\n }\n }\n },\n \"single_answers\": {\n \"department\": {\n \"type\": \"choice\",\n \"choice\": \"billing\",\n \"probabilities\": {\n \"billing\": 0.6989,\n \"technical\": 0.0814,\n \"sales\": 0.1338,\n \"other\": 0.086\n },\n \"confidence\": 0.3258,\n \"action\": {\n \"act_probability\": 1.0\n }\n },\n \"urgency\": {\n \"type\": \"score\",\n \"score\": 1.6111,\n \"legend\": {\n \"0\": \"not urgent\",\n \"1\": \"soon\",\n \"2\": \"critical or blocking\"\n },\n \"probabilities\": {\n \"0\": 0.0408,\n \"1\": 0.3073,\n \"2\": 0.6519\n },\n \"confidence\": 0.2972,\n \"action\": {\n \"act_probability\": 1.0\n }\n },\n \"refund\": {\n \"type\": \"noul\",\n \"noul\": 0.68,\n \"confidence\": 0.68,\n \"action\": {\n \"act_probability\": 1.0\n }\n }\n }\n },\n \"fixture\": {\n \"state\": {\n \"ticket\": {\n \"subject\": \"Duplicate charge\",\n \"body\": \"The customer was billed twice for invoice 4411 and asks for a refund today. They say the duplicate charge is blocking month-end close.\"\n }\n },\n \"questions\": {\n \"department\": {\n \"type\": \"choice\",\n \"instructions\": \"Which team should handle this ticket?\",\n \"criteria\": {\n \"billing\": \"invoices, payments, refunds\",\n \"technical\": \"bugs, outages, integrations\",\n \"sales\": \"pricing, demos, new purchases\",\n \"other\": \"everything else\"\n }\n },\n \"urgency\": {\n \"type\": \"score\",\n \"instructions\": \"How urgent is this ticket?\",\n \"criteria\": [\n \"not urgent\",\n \"soon\",\n \"critical or blocking\"\n ]\n },\n \"refund\": {\n \"type\": \"noul\",\n \"instructions\": \"Does the customer ask for money back?\"\n }\n },\n \"answers\": {\n \"department\": {\n \"type\": \"choice\",\n \"choice\": \"billing\",\n \"probabilities\": {\n \"billing\": 0.6989,\n \"technical\": 0.0814,\n \"sales\": 0.1338,\n \"other\": 0.086\n },\n \"confidence\": 0.3258,\n \"action\": {\n \"act_probability\": 1.0\n }\n },\n \"urgency\": {\n \"type\": \"score\",\n \"score\": 1.6111,\n \"legend\": {\n \"0\": \"not urgent\",\n \"1\": \"soon\",\n \"2\": \"critical or blocking\"\n },\n \"probabilities\": {\n \"0\": 0.0408,\n \"1\": 0.3073,\n \"2\": 0.6519\n },\n \"confidence\": 0.2972,\n \"action\": {\n \"act_probability\": 1.0\n }\n },\n \"refund\": {\n \"type\": \"noul\",\n \"noul\": 0.68,\n \"confidence\": 0.68,\n \"action\": {\n \"act_probability\": 1.0\n }\n }\n }\n }\n}\n", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 1 connection review, 1 outside write.", "findings": [ { "kind": "connection-review", "count": 1, "note": "Repository processes attempted these non-loopback connections; proxies can hide the final hostname.", "location_count": 57, "process_count": 25 }, { "kind": "outside-write", "count": 1, "note": "Repository processes attempted these writes outside documented output/cache paths.", "location_count": 26, "process_count": 1, "processes": [ { "executable": "", "owner": "repo", "path": "/archive-v0/3WDCtWylv6C1xoBh", "pid": "2231", "source": "" } ] } ], "context": [], "limitations": [ "A short run cannot establish that code is safe.", "Connections show IP addresses; proxies can hide the final hostname.", "Tracing covers dispatched commands and their children, not the whole OS; guest root can interfere with tracing." ], "static": { "dependency_note": "OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check." }, "evidence_url": "/safety/?run=TayHCode--sysone-cpu-gpt-6-luna-1792683877827961506", "evidence_file": "/data/safety/TayHCode--sysone-cpu-gpt-6-luna-1792683877827961506.json.gz" }, "agent_execution": "native_agent", "agent_runtime": "codex", "agent_runtime_version": "codex-cli 0.163.0", "tool_transport": "mcp-assigned-vm", "platform": "linux", "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "native_tool_calls": 18, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "c236055c37fc05a0e3f5e9a2933dd8eb946e4f89", "url": "https://github.com/TayHCode/sysone-cpu" }, "purpose": "initial", "profile": { "model": "gpt-6-luna", "reasoning": "low" }, "fault": { "owner": null, "status": "resolved", "reason": null }, "fix_id": null, "verifies_run_id": null, "hosting": null, "operation_scope": "product operation", "tool_calls": 18, "guest_setup": null, "runtime": null, "runtime_version": null, "runtime_revision": null, "source_revision": null, "evidence_version": null, "failure_origin": null, "evidence_strength": "readme_checked", "works": "yes", "install_s": null, "first_use_s": null, "mcp": "none", "needs": [], "needs_which": null, "agent_interface": [ "cli" ], "license": "MIT", "repo_url": "https://github.com/TayHCode/sysone-cpu", "cost_to_try": "free", "hardware": "GPU", "what_failed": null, "local_or_hosted": "local", "cycle_checks": [ { "kind": "cycle", "claim": "Scheduled or looping main behavior", "source": "repository entry points", "input": "source inspection", "expected": "identify the product trigger", "verdict": "yes", "outcome": "Inspected README entry points, scripts, and benchmark harnesses. The product downloads a checkpoint and runs an explicitly invoked benchmark; no product scheduler, recurring loop, or webhook cycle exists.", "evidence": "Inspected README entry points, scripts, and benchmark harnesses. The product downloads a checkpoint and runs an explicitly invoked benchmark; no product scheduler, recurring loop, or webhook cycle exists.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Benchmark runs the synthetic workload and records inference results.", "source": "Expect `meta.device` to be `\"cpu\"`", "input": "Synthetic README quickstart ticket questions at counts 1 and 3", "expected": "CPU metadata and equivalent batched answers are present in the JSON result", "command": ".tools/uv run --no-project --python .venv python benchmarks/bench_laya_cpu.py --model .cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output .cache/claim-run.json-checker-bcf933f28d0848b8ba6a144eb5554a2c", "verdict": "yes", "outcome": "Real input produced the expected result: \"device\": \"cpu\"", "evidence": "\"device\": \"cpu\",\n \"model_path\": \"\",\n \"model_config\": {\n \"encoder\": \"answerdotai/ModernBERT-large\",\n \"head_layers\": 2,\n \"max_len\": 1024,\n \"head_max_len\": 256,\n \"max_prefixes\": 6,\n \"act_costs\": {\n \"escalate\": 0.5\n },\n \"cost_wrong_act\": 3.0,\n \"amp_dtype\": \"bf16\",\n \"model_name\": \"laya-typed-decisions\",\n \"training\": {\n \"updates\": 7313,\n \"epochs_completed\": 1,\n \"hours\": 1.96,\n \"world_size\": 1,\n \"fine_tuned_from_checkpoint\": true\n },\n \"gradient_checkpointi", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Run README PyTorch FP32 quickstart benchmark", "source": "README.md, Quickstart: PyTorch FP32", "input": "--threads 4 --warmup 1 --repeats 1 --counts 1,3", "command": ".tools/uv run --no-project --python .venv python benchmarks/bench_laya_cpu.py --model .cache/model/typed-decisions --threads 4 --warmup 1 --repeats 1 --counts 1,3 --output .cache/example-run.json", "evidence": "timing 1 questions ...\n p50=685.3 ms p95=685.3 ms 1.46 q/s RSS=2051.2 MiB CPU=107.8%\ntiming 3 questions ...\n p50=1595.0 ms p95=1595.0 ms 1.88 q/s RSS=2055.2 MiB CPU=126.6%\nwrote .cache/example-run.json", "deferred": false, "expected": "CPU inference results are written to JSON with batch equivalence", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Run local standard library checks documented in README", "source": "README.md, Local checks", "input": "python3 -m unittest discover -s tests -q", "command": "python3 -m unittest discover -s tests -q", "evidence": "----------------------------------------------------------------------\nRan 19 tests in 0.020s\n\nOK", "deferred": false, "expected": "documented checks complete", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Run documented syntax check", "source": "README.md, Local checks", "input": "python3 scripts/check_syntax.py", "command": "python3 scripts/check_syntax.py", "evidence": "Python syntax checked.", "deferred": false, "expected": "syntax check completes", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "archived": false, "commits_90d": 4, "last_commit_at": "2026-10-19T01:31:51Z", "last_release_at": null, "median_reply_hours": null, "merged_prs_90d": 3, "note": "actively maintained: last commit 3 days ago; 4 commits and 3 merged PRs in 90 days; 0 open issues, 0 open PRs; no releases", "open_issues": 0, "open_prs": 0, "reply_share": null, "reply_threads": 0, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 3 days ago; 4 commits and 3 merged PRs in 90 days; 0 open issues, 0 open PRs; no releases", "maintained": "active", "maintained_note": "last commit 3 days ago", "last_commit_at": "2026-10-19T01:38:00Z", "last_release_at": null, "open_issues": null, "answered_issues": null, "platforms_claimed": [ "linux", "mac", "windows" ], "topic": "other", "agent_interfaces": [ { "interface": "cli", "evidence": "independent checker", "observed": true, "operation_checked": true } ], "agent_interfaces_note": "README metadata is a discovery hint, not pinned documentation proof. Observed interfaces were exercised in this run. An empty list means unknown.", "mcp_context": null, "tested_at": "2026-10-22T15:50:43.532038+00:00", "tested_commit": "c236055c37fc05a0e3f5e9a2933dd8eb946e4f89", "tested_with": { "agent": "codex", "agent_version": "codex-cli 0.163.0", "model": "gpt-6-luna", "model_route": "gpt-6-luna", "reasoning": "low", "os": "linux", "backend": "hyperv", "transport": "mcp-assigned-vm" }, "setup_identity": { "repo": "TayHCode/sysone-cpu", "source": "https://github.com/TayHCode/sysone-cpu", "commit": "c236055c37fc05a0e3f5e9a2933dd8eb946e4f89", "source_revision": null, "os": "linux", "architecture": null, "backend": "hyperv", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "agent_execution": "native_agent", "agent_runtime": "codex", "agent_runtime_version": "codex-cli 0.163.0", "tool_transport": "mcp-assigned-vm", "runtime": null, "runtime_version": null, "runtime_revision": null, "sandbox_source": null, "guest_setup": null, "source_pin": { "commit": "c236055c37fc05a0e3f5e9a2933dd8eb946e4f89", "url": "https://github.com/TayHCode/sysone-cpu" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Run pinned Laya typed-decisions inference and CPU benchmark", "operation_scope": "product operation", "hosting": null, "kind": "repo", "test_version": "readme-1002bc876f0002f622e14f9c5b99f9f66721fccc0356f4d53ed24f2f79a3ac5d", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": "/transcripts/TayHCode--sysone-cpu-gpt-6-luna-1792683877827961506.txt", "report_url": "/reports/TayHCode--sysone-cpu-gpt-6-luna-1792683877827961506.json" }