{ "run_id": "TheoLeeCJ--SemIf-OpenJev-gpt-6-luna-1792853761015836982", "date": "2026-10-24T15:20:47.475276+00:00", "repo": "TheoLeeCJ/SemIf-OpenJev", "kind": "repo", "source": "https://github.com/TheoLeeCJ/SemIf-OpenJev", "commit": "23cf1f39fc9534fe81437200959b6dfc7106e45a", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-20cd1bc4ab0be6730266a08d7400e342dd7d403c08aabf42aab2e51dc9b34ce0", "pass": null, "outcome": "unsupported", "time_to_working_s": null, "total_s": 1486.4594073295593, "steps": [ "pwd; rg --files -g 'README*' -g 'AGENTS.md' -g 'pyproject.toml' -g 'package.json' -g 'Makefile' -g 'requirements*.txt' -g 'Dockerfile' -g '.github/workflows/**' | head -80; python3 --version; id -u", "ls -la; find .. -name AGENTS.md -o -name 'README*' | head -80; command -v vault-search || true;", "cat AGENTS.md; cat README.md", "cat 2>/dev/null; vault-search 'SemIf model scoring CPU GGUF' 2>/dev/null; sed -n '1,220p' pyproject.toml; sed -n '1,200p' docs/REPRODUCE.md; sed -n '1,160p' src/semif/cli.py", "python3 -m venv /tmp/semif-venv && /tmp/semif-venv/bin/pip install -e '.[test]'", "sudo -n apt-get update && sudo -n apt-get install -y python3.12-venv", "python3 -m venv /tmp/semif-venv && /tmp/semif-venv/bin/pip install -e '.[test]'", "find src -type f; sed -n '1,220p' src/semif_phase1/cli.py; nvidia-smi || true; ls -lh /tmp/inputs/coldpass-preflight.py 2>/dev/null", "python3 -m venv /tmp/semif-llama && /tmp/semif-llama/bin/pip install -e '.[test,llamacpp]'", "sudo -n apt-get install -y build-essential cmake", "CMAKE_ARGS='-DGGML_NATIVE=OFF' /tmp/semif-venv/bin/pip install llama-cpp-python==0.3.35", "find .coldpass -maxdepth 2 -type f -print; head -1 examples/decisions.jsonl; mkdir -p /tmp/semif-model; HF_HUB_DISABLE_XET=1 /tmp/semif-venv/bin/python -c 'from huggingface_hub import hf_hub_download; print(hf_hub_download(\"bartowski/Qwen_Qwen3.5-4B-GGUF\", \"Qwen_Qwen3.5-4B-Q4_K_M.gguf\", local_dir=\"/tmp/semif-model\"))'", "mkdir -p .coldpass; cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"/tmp/semif-venv/bin/semif-score\",\"--mode\",\"direct\",\"--backend\",\"llamacpp\",\"--gguf\",\"/tmp/semif-model/Qwen_Qwen3.5-4B-Q4_K_M.gguf\",\"--model\",\"Qwen/Qwen3.5-4B\",\"--revision\",\"851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a\",\"--input\",\"examples/decisions.jsonl\",\"--output\",\"/tmp/semif-coldpass-probe.jsonl\"],\"cwd\":\"\",\"expected_file\":\"/tmp/semif-coldpass-probe.jsonl\",\"expected_text\":\"support-1\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Score owned examples and produce typed option scores.\",\"source\":\"Run the owned examples:\",\"input\":\"examples/decisions.jsonl\",\"expected\":\"support-1 result includes typed scores\",\"probe_kind\":\"cli\",\"argv\":[\"/tmp/semif-venv/bin/semif-score\",\"--mode\",\"direct\",\"--backend\",\"llamacpp\",\"--gguf\",\"/tmp/semif-model/Qwen_Qwen3.5-4B-Q4_K_M.gguf\",\"--model\",\"Qwen/Qwen3.5-4B\",\"--revision\",\"851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a\",\"--input\",\"examples/decisions.jsonl\",\"--output\",\"/tmp/semif-coldpass-claim.jsonl\"],\"expected_file\":\"/tmp/semif-coldpass-claim.jsonl\",\"expected_text\":\"support-1\",\"cwd\":\"\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Score owned decisions with CPU GGUF backend\",\"source\":\"README.md / Quick start / CPU only\",\"input\":\"examples/decisions.jsonl\",\"expected\":\"one scored JSONL record per decision\",\"argv\":[\"/tmp/semif-venv/bin/semif-score\",\"--mode\",\"direct\",\"--backend\",\"llamacpp\",\"--gguf\",\"/tmp/semif-model/Qwen_Qwen3.5-4B-Q4_K_M.gguf\",\"--model\",\"Qwen/Qwen3.5-4B\",\"--revision\",\"851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a\",\"--input\",\"examples/decisions.jsonl\",\"--output\",\"/tmp/semif-coldpass-example.jsonl\"],\"cwd\":\"\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"README and src entry points describe command-driven scoring; no scheduler or recurring cycle was found.\",\"checks\":[]}\nEOF", "/tmp/semif-venv/bin/semif-score --mode direct --backend llamacpp --gguf /tmp/semif-model/Qwen_Qwen3.5-4B-Q4_K_M.gguf --model Qwen/Qwen3.5-4B --revision 851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a --input examples/decisions.jsonl --output /tmp/semif-manual.jsonl; head -c 500 /tmp/semif-manual.jsonl", "cat /tmp/semif-manual.jsonl", "python3 - <<'PY'\nimport json\np='.coldpass/probe.json'; d=json.load(open(p)); d['expected_text']='\"id\": \"support-1\"'; json.dump(d,open(p,'w'))\np='.coldpass/claims.json'; d=json.load(open(p)); d[0]['source']='Each result contains typed option scores, timing, the exact model revision, and a prompt hash.'; d[0]['source_file']='README.md'; d[0]['expected_text']='\"id\": \"support-1\"'; json.dump(d,open(p,'w'))\np='.coldpass/examples.json'; d=json.load(open(p)); d[0]['expected_text']='\"id\": \"support-1\"'; json.dump(d,open(p,'w'))\nPY\n= python3 -I --validate --replay", "cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Score the owned decision JSONL with the documented CPU llama.cpp backend\",\"operation_scope\":\"Python 3.12.3 venv, pinned package install, downloaded Q4_K_M GGUF, CPU-only execution\",\"steps\":[\"Read README.md and repository AGENTS.md\",\"Installed python3.12-venv and created /tmp/semif-venv\",\"Installed pip install -e '.[test]'\",\"Installed build-essential and cmake after the llama.cpp extension initially failed to compile because x86_64-linux-gnu-gcc was missing\",\"Installed llama-cpp-python==0.3.35\",\"Downloaded the README example GGUF and ran semif-score against examples/decisions.jsonl\",\"Validated and replayed probe, README claim, example, and cycle record successfully\"],\"deviations\":[\"The GPU focused Torch path was unavailable because nvidia-smi was not installed; used the README documented CPU-only llama.cpp backend.\",\"The first llama.cpp optional install failed with CMake error 'Could not find the compiler specified in the environment variable CC: x86_64-linux-gnu-gcc'; installed compiler toolchain and retried successfully.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF" ], "stuck_step": "/tmp/semif-venv/bin/semif-score --mode direct --backend llamacpp --gguf /tmp/semif-model/Qwen_Qwen3.5-4B-Q4_K_M.gguf --model Qwen/Qwen3.5-4B --revision 851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a --input examples/decisions.jsonl --output /tmp/semif-coldpass-probe.jsonl-checker-3da80f9bff8a4a78b285b7df31f1e776", "error_excerpt": "The saved checks do not fully confirm documented product behavior.", "what_it_did": "Score the owned decision JSONL with the documented CPU llama.cpp backend", "suggested_fix": "Keep the partial evidence and check the documented behavior with real input and expected output.", "tokens_in": 866134, "tokens_out": 2972, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": false, "argv": [ "/tmp/semif-venv/bin/semif-score", "--mode", "direct", "--backend", "llamacpp", "--gguf", "/tmp/semif-model/Qwen_Qwen3.5-4B-Q4_K_M.gguf", "--model", "Qwen/Qwen3.5-4B", "--revision", "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a", "--input", "examples/decisions.jsonl", "--output", "/tmp/semif-coldpass-probe.jsonl-checker-3da80f9bff8a4a78b285b7df31f1e776" ], "kind": "cli", "returncode": 0, "stdout": "", "stderr": " dev = CPU\nllama_kv_cache: layer 32: filtered\nllama_kv_cache: CPU KV buffer size = 136.00 MiB\nllama_kv_cache: size = 136.00 MiB ( 4352 cells, 8 layers, 1/1 seqs), K (f16): 68.00 MiB, V (f16): 68.00 MiB\nllama_kv_cache: attn_rot_k = 0, n_embd_head_k_all = 256\nllama_kv_cache: attn_rot_v = 0, n_embd_head_k_all = 256\nllama_memory_recurrent, layer 0: dev = CPU\nllama_memory_recurrent, layer 1: dev = CPU\nllama_memory_recurrent, layer 2: dev = CPU\nllama_memory_recurrent: layer 3: skipped\nllama_memory_recurrent, layer 4: dev = CPU\nllama_memory_recurrent, layer 5: dev = CPU\n[excerpt truncated]", "expected_file": "/tmp/semif-coldpass-probe.jsonl-checker-3da80f9bff8a4a78b285b7df31f1e776", "file_checked": true, "file_excerpt": "\"id\": \"support-1\", \"option_ids\": [\"yes\", \"no\", \"insufficient\"], \"probabilities\": [0.9994890719602687, 0.00013567599535170604, 0.00037525204437965866], \"option_logits\": [28.294504165649414, 19.389774322509766, 20.407102584838867], \"answer_token_ids\": [32, 33, 34], \"input_tokens\": 142, \"allowed_token_mass\": 0.9998756442730353, \"full_vocab_argmax_id\": 32, \"prompt_sha256\": \"7ac35785358f0c656eeb741ca0a51f03e0133753a71e2879a18ad0ab56d0c024\", \"prompt_version\": \"direct-options-v1\", \"model\": {\"source\": \"Qwen/Qwen3.5-4B\", \"revision\": \"851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a\", \"backend\": \"llamacpp\", \"dtype\": \"gguf-quantized\", \"gguf\": {\"file\": \"Qwen_Qwen3.5-4B-Q4_K_M.gguf\", \"bytes\": 3013027808, \"sha256\": \"13c16f426047e2de38cd075bdade4a7bcbc8c774384876f677740cda65f8a983\"}, \"vocab_size\": 248320, \"threads\": 2, \"n_gpu_layers\": 0, \"max_prompt_tokens\": 4096, \"context_tokens\": 4352, \"decode_chunk\": 512, \"llama_cpp_python_version\": \"0.3.35\", \"transformers_version\": \"5.17.0\", \"serving_config\": \"llamacpp-direct-v1\"}, \"readout\": \"quantized last-position logits restricted to declared answer slots; no generated tokens\", \"probability_status\": \"conditional option score over quantized weights; uncalibrated as decision confidence\", \"forward_seconds\": 5.932923989000074, \"total_seconds\": 5.935320555999851}\n{\"id\": \"route-1\", \"option_ids\": [\"account_access\", \"billing\", \"sales\"], \"probabilities\": [0.9999628974085876, 2.6670441244641933e-05, 1.0432150167767386e-05], \"option_logits\": [28.321033477783203, 17.78911590576172, 16.850452423095703], \"answer_token_ids\": [32, 33, 34], \"input_tokens\": 130, \"allowed_token_mass\": 0.999870232621057, \"full_vocab_argmax_id\": 32, \"prompt_sha256\": \"016267542103ab91422c425d2234ec7e1b9aef77f9d3e481b96db2de7cca470a\", \"prompt_version\": \"direct-options-v1\", \"model\": {\"source\": \"Qwen/Qwen3.5-4B\", \"revision\": \"851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a\", \"backend\": \"llamacpp\", \"dtype\": \"gguf-quantized\", \"gguf\": {\"file\": \"Qwen_Qwen3.5-4B-Q4_K_M.gguf\", \"bytes\": 3013027808, \"sha256\": \"13c16f426047e2de38cd075bdade4a7bcbc8c774384876f677740cda65f8a983\"}, \"vocab_size\": 248320, \"threads\": 2, \"n_gpu_layers\": 0, \"max_prompt_tokens\": 4096, \"context_tokens\": 4352, \"decode_chunk\": 512, \"llama_cpp_python_version\": \"0.3.35\", \"transformers_version\": \"5.17.0\", \"serving_config\": \"llamacpp-direct-v1\"}, \"readout\": \"quantized last-position logits restricted to declared answer slots; no generated tokens\", \"probability_status\": \"conditional option score over quantized weights; uncalibrated as decision confidence\", \"forward_seconds\": 4.423341889000085, \"total_seconds\": 4.426572518000057}\n{\"id\": \"policy-1\", \"option_ids\": [\"required\", \"not_required\", \"insufficient\"], \"probabilities\": [0.06092024663437009, 0.935643051777468, 0.0034367015881619045], \"option_logits\": [23.35482406616211, 26.08649253845215, 20.47977066040039], \"answer_token_ids\": [32, 33, 34], \"input_tokens\": 154, \"allowed_token_mass\": 0.9996553685559919, \"full_vocab_argmax_id\": 33, \"prompt_sha256\": \"6884fc4a9117b63369dd79e3042b92f92678f1e08dba2600e93d1da6754b1787\", \"prompt_version\": \"direct-options-v1\", \"model\": {\"source\": \"Qwen/Qwen3.5-4B\", \"revision\": \"851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a\", \"backend\": \"llamacpp\", \"dtype\": \"gguf-quantized\", \"gguf\": {\"file\": \"Qwen_Qwen3.5-4B-Q4_K_M.gguf\", \"bytes\": 3013027808, \"sha256\": \"13c16f426047e2de38cd075bdade4a7bcbc8c774384876f677740cda65f8a983\"}, \"vocab_size\": 248320, \"threads\": 2, \"n_gpu_layers\": 0, \"max_prompt_tokens\": 4096, \"context_tokens\": 4352, \"decode_chunk\": 512, \"llama_cpp_python_version\": \"0.3.35\", \"transformers_version\": \"5.17.0\", \"serving_config\": \"llamacpp-direct-v1\"}, \"readout\": \"quantized last-position logits restricted to declared answer slots; no generated tokens\", \"probability_status\": \"conditional option score over quantized weights; uncalibrated as decision confidence\", \"forward_seconds\": 4.969243106000022, \"total_seconds\": 4.970980280999811}\n", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 1 connection review, 30 hardcoded secret, 6 known vulnerability. 3 static matches retained as context.", "expected": "Reviewed as expected for a test run: resolver address lookups that send no data.", "findings": [ { "kind": "connection-review", "count": 1, "note": "Repository processes attempted these non-loopback connections; proxies can hide the final hostname.", "location_count": 42, "process_count": 8 }, { "kind": "hardcoded-secret", "count": 18, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 7 }, { "kind": "known-vulnerability", "count": 6, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 3 } ], "context": [ { "kind": "encoded-blob", "count": 2, "note": "Source contains encoded blob; review its purpose.", "location_count": 1, "path": "webgpu-demo/vendor/wllama/index.js" }, { "kind": "encoded-execution", "count": 1, "note": "Source contains encoded execution; review its purpose.", "location_count": 1, "path": "webgpu-demo/vendor/wllama/index.js" } ], "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=TheoLeeCJ--SemIf-OpenJev-gpt-6-luna-1792853761015836982", "evidence_file": "/data/safety/TheoLeeCJ--SemIf-OpenJev-gpt-6-luna-1792853761015836982.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": 17, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "23cf1f39fc9534fe81437200959b6dfc7106e45a", "url": "https://github.com/TheoLeeCJ/SemIf-OpenJev" }, "purpose": "test_rerun", "profile": { "model": "gpt-6-luna", "reasoning": "low" }, "fault": { "owner": "unknown", "status": "pending", "reason": "The saved checks do not fully confirm documented product behavior." }, "fix_id": null, "verifies_run_id": "TheoLeeCJ--SemIf-OpenJev-gpt-6-luna-1792844579520237451", "hosting": null, "operation_scope": "product operation", "tool_calls": 17, "guest_setup": null, "runtime": null, "runtime_version": null, "runtime_revision": null, "source_revision": null, "evidence_version": null, "failure_origin": null, "evidence_strength": "partly_checked", "works": "untested", "install_s": null, "first_use_s": null, "mcp": "none", "needs": [], "needs_which": null, "agent_interface": [ "cli" ], "license": "MIT", "repo_url": "https://github.com/TheoLeeCJ/SemIf-OpenJev", "cost_to_try": null, "hardware": null, "what_failed": "The saved checks do not fully confirm documented product behavior.", "local_or_hosted": "both", "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": "README and src entry points describe command-driven scoring; no scheduler or recurring cycle was found.", "evidence": "README and src entry points describe command-driven scoring; no scheduler or recurring cycle was found.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Score owned examples and produce typed option scores.", "source": "Each result contains typed option scores, timing, the exact model revision, and a prompt hash.", "input": "examples/decisions.jsonl", "expected": "support-1 result includes typed scores", "command": "/tmp/semif-venv/bin/semif-score --mode direct --backend llamacpp --gguf /tmp/semif-model/Qwen_Qwen3.5-4B-Q4_K_M.gguf --model Qwen/Qwen3.5-4B --revision 851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a --input examples/decisions.jsonl --output /tmp/semif-coldpass-claim.jsonl-checker-4076f1046d5c44899785f2aa5a138461", "verdict": "yes", "outcome": "Real input produced the expected result: \"id\": \"support-1\"", "evidence": "\"id\": \"support-1\", \"option_ids\": [\"yes\", \"no\", \"insufficient\"], \"probabilities\": [0.9994890719602687, 0.00013567599535170604, 0.00037525204437965866], \"option_logits\": [28.294504165649414, 19.389774322509766, 20.407102584838867], \"answer_token_ids\": [32, 33, 34], \"input_tokens\": 142, \"allowed_token_mass\": 0.9998756442730353, \"full_vocab_argmax_id\": 32, \"prompt_sha256\": \"7ac35785358f0c656eeb741ca0a51f03e0133753a71e2879a18ad0ab56d0c024\", \"prompt_version\": \"direct-options-v1\", \"model\": {\"source\": \"Qwen/Qwen3.5-4B\", \"revision\": \"851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a\", \"backend\": \"llamacpp\", \"dt", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Score owned decisions with CPU GGUF backend", "source": "README.md / Quick start / CPU only", "input": "examples/decisions.jsonl", "command": "/tmp/semif-venv/bin/semif-score --mode direct --backend llamacpp --gguf /tmp/semif-model/Qwen_Qwen3.5-4B-Q4_K_M.gguf --model Qwen/Qwen3.5-4B --revision 851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a --input examples/decisions.jsonl --output /tmp/semif-coldpass-example.jsonl", "evidence": "usage: semif-score [-h] --mode {direct,serial,shared,reranker}\n [--backend {torch,mlx,llamacpp}] [--mlx-bits {4,8}]\n [--mlx-cache-limit-mib MLX_CACHE_LIMIT_MIB] [--gguf GGUF]\n [--llama-threads LLAMA_THREADS] --model MODEL --revision\n REVISION --input INPUT --output OUTPUT\n [--max-tokens MAX_TOKENS] [--device {auto,cuda,mps,cpu}]\n [--dtype {bfloat16,float16,float32}]\nsemif-score: error: Output must be new and max-tokens must be positive", "deferred": false, "expected": "one scored JSONL record per decision", "returncode": 2, "verdict": "no", "outcome": "command exited with code 2" } ], "does_what_it_says": "yes", "maintenance": { "archived": false, "commits_90d": 25, "last_commit_at": "2026-09-23T18:47:59Z", "last_release_at": null, "median_reply_hours": 12.9, "merged_prs_90d": 5, "note": "actively maintained: last commit 30 days ago; 25 commits and 5 merged PRs in 90 days; 23 open issues, 25 open PRs; 1 of 47 recent threads got a maintainer reply, median first reply 12.9h; no releases", "open_issues": 23, "open_prs": 25, "reply_share": 0.02, "reply_threads": 47, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 30 days ago; 25 commits and 5 merged PRs in 90 days; 23 open issues, 25 open PRs; 1 of 47 recent threads got a maintainer reply, median first reply 12.9h; no releases", "maintained": "active", "maintained_note": "last commit 30 days ago; 12 open issues, 2 answered or closed", "last_commit_at": "2026-09-23T18:48:22Z", "last_release_at": null, "open_issues": 12, "answered_issues": 2, "platforms_claimed": [ "mac" ], "topic": "other", "agent_interfaces": [ { "interface": "cli", "evidence": "independent checker", "observed": true, "operation_checked": false } ], "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": "2026-10-24T15:20:47.475276+00:00", "tested_commit": "23cf1f39fc9534fe81437200959b6dfc7106e45a", "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": "TheoLeeCJ/SemIf-OpenJev", "source": "https://github.com/TheoLeeCJ/SemIf-OpenJev", "commit": "23cf1f39fc9534fe81437200959b6dfc7106e45a", "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": "23cf1f39fc9534fe81437200959b6dfc7106e45a", "url": "https://github.com/TheoLeeCJ/SemIf-OpenJev" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Score the owned decision JSONL with the documented CPU llama.cpp backend", "operation_scope": "product operation", "hosting": null, "kind": "repo", "test_version": "readme-20cd1bc4ab0be6730266a08d7400e342dd7d403c08aabf42aab2e51dc9b34ce0", "evidence_version": null }, "transcript_url": null, "report_url": "/reports/TheoLeeCJ--SemIf-OpenJev-gpt-6-luna-1792853761015836982.json" }