{ "run_id": "Graphify-Labs--graphify-gpt-6-luna-1792776386984097674", "date": "2026-10-23T17:28:11.655559+00:00", "repo": "Graphify-Labs/graphify", "kind": "repo", "source": "https://github.com/Graphify-Labs/graphify", "commit": "c588b72d936927790a87ad009955078ed40562a3", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "pass": true, "outcome": "pass", "time_to_working_s": 73.59870207402855, "total_s": 104.6714255809784, "steps": [ "cd && pwd && rg --files -g 'README*' -g 'AGENTS.md' -g 'pyproject.toml' -g 'requirements*' -g 'package.json' -g 'Makefile' -g '.github/workflows/**' | head -80 && vault-search 'Graphify graphify repo setup README MCP graph extraction' 2>&1 | head -80 && cat ~/.agents/skills/i-have-adhd/SKILL.md && cat ~/.agents/skills/ponytail/SKILL.md && cat ~/.agents/skills/p3-mode/SKILL.md && cat 2>&1 | head -80", "cd && ls -la && find .. -name AGENTS.md -o -name 'README*' | head -80 && git rev-parse HEAD 2>&1 && python3 --version && id -u && find . -maxdepth 3 -type f | head -100", "cd && cat AGENTS.md && python3 --version; sed -n '1,240p' README.md", "cd && sed -n '240,520p' README.md && find graphify -maxdepth 3 -type f | head -60 && grep -nE 'graphify (map|build|query|path|explain)|/graphify|Output|graph.json|MCP|cycle|schedule' README.md", "cd && git init && git remote add origin https://github.com/Graphify-Labs/graphify && git fetch --depth 1 origin c588b72d936927790a87ad009955078ed40562a3 && git reset --mixed FETCH_HEAD && (uv --version || true) && (pipx --version || true) && ls -la .coldpass && sed -n '1,220p' pyproject.toml", "cd && curl -LsSf https://astral.sh/uv/install.sh | sh && export PATH=\"$HOME/.local/bin:$PATH\" && uv --version && uv tool install --from . graphifyy && uv tool run --from . graphify --help | head -60", "cd && grep -nE '^## |extract |--code-only|--out|--no-viz' graphify/skill.md | head -80 && export PATH=\"$HOME/.local/bin:$PATH\" && graphify extract --help | head -100 && graphify query --help | head -80 && mkdir -p .coldpass/sample && cat > .coldpass/sample/sample.py <<'EOF'\nclass UserService:\n def load_user(self, user_id):\n return DatabasePool.fetch(user_id)\n\nclass DatabasePool:\n @staticmethod\n def fetch(user_id):\n return {\"id\": user_id}\nEOF\n", "cd && export PATH=\"$HOME/.local/bin:$PATH\" && graphify extract .coldpass/sample --help 2>&1 | head -80 && graphify --help | tail -80 && sed -n '1,100p' graphify/__main__.py", "cd && PATH=\"$HOME/.local/bin:$PATH\" GRAPHIFY_BACKEND=none graphify extract .coldpass/sample --code-only --no-viz --out .coldpass/build 2>&1; find .coldpass/build -maxdepth 3 -type f -print; PATH=\"$HOME/.local/bin:$PATH\" graphify explain UserService --graph .coldpass/build/graphify-out/graph.json 2>&1", "cd && grep -nE 'watch|schedule|cron|webhook|loop' graphify/__main__.py | head -60 && find . -maxdepth 2 -type f -path './.github/workflows/*' -print", "cd && cat > .coldpass/claims.json <<'EOF'\n[\n {\n \"kind\": \"claim\",\n \"claim\": \"Code files are processed locally via tree-sitter and require no API key.\",\n \"source\": \"Code files: processed locally via tree-sitter. Nothing leaves your machine. A code-only corpus requires no API key: `graphify extract` runs fully offline.\",\n \"input\": \"A Python sample defining UserService and DatabasePool\",\n \"expected\": \"The code-only extraction creates a graph and explain returns UserService with a connection.\",\n \"probe_kind\": \"cli\",\n \"argv\": [\"\", \"extract\", \".coldpass/sample\", \"--code-only\", \"--no-viz\", \"--out\", \".coldpass/replay-claim\"],\n \"cwd\": \"\",\n \"env\": {\"GRAPHIFY_BACKEND\": \"none\"},\n \"expected_text\": \"5 nodes, 5 edges\"\n }\n]\nEOF\ncat > .coldpass/probe.json <<'EOF'\n{\n \"kind\": \"cli\",\n \"argv\": [\"\", \"extract\", \".coldpass/sample\", \"--code-only\", \"--no-viz\", \"--out\", \".coldpass/replay-probe\"],\n \"cwd\": \"\",\n \"env\": {\"GRAPHIFY_BACKEND\": \"none\"},\n \"expected_text\": \"5 nodes, 5 edges\"\n}\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[\n {\n \"kind\": \"example\",\n \"claim\": \"Build a local code graph using the documented CLI operation.\",\n \"source\": \"README.md / Privacy and Common commands\",\n \"input\": \"Python code-only corpus at .coldpass/sample\",\n \"expected\": \"graph.json with extracted code nodes and edges\",\n \"argv\": [\"\", \"extract\", \".coldpass/sample\", \"--code-only\", \"--no-viz\", \"--out\", \".coldpass/replay-example\"],\n \"cwd\": \"\",\n \"env\": {\"GRAPHIFY_BACKEND\": \"none\"},\n \"expected_text\": \"5 nodes, 5 edges\"\n }\n]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Inspected the README commands and graphify CLI entry point: graphify watch is a user-started filesystem watcher, not a scheduled product cycle. No cron, scheduler, webhook, or --once cycle is documented; a one-shot extraction was exercised instead.\",\"checks\":[]}\nEOF\nmkdir -p .coldpass\n= python3 -I --validate --replay", "cd && python3 - <<'PY'\nfrom pathlib import Path\np=Path('.coldpass/claims.json')\ns=p.read_text()\ns=s.replace('Code files: processed locally via tree-sitter. Nothing leaves your machine. A code-only corpus requires no API key: `graphify extract` runs fully offline.', '- **Code files**: processed locally via tree-sitter. Nothing leaves your machine. A code-only corpus requires no API key: `graphify extract` runs fully offline.')\np.write_text(s)\nPY\n= python3 -I --validate --replay", "cd && cat > .coldpass/report.json <<'EOF'\n{\n \"outcome\": \"working\",\n \"fault_owner\": null,\n \"operation\": \"Build and query a local code knowledge graph\",\n \"operation_scope\": \"Python 3.12.3; uv tool install from the pinned checkout; offline code-only extraction and graph explanation\",\n \"steps\": [\n \"Initialized Git metadata and fetched/reset to c588b72d936927790a87ad009955078ed40562a3.\",\n \"Installed uv with the README installer and installed graphifyy with `uv tool install --from . graphifyy`.\",\n \"Ran `GRAPHIFY_BACKEND=none graphify extract .coldpass/sample --code-only --no-viz --out .coldpass/build`; extraction produced 5 nodes, 5 edges, and 2 communities.\",\n \"Ran `graphify explain UserService --graph .coldpass/build/graphify-out/graph.json`; it returned the node source and connections.\",\n \"Validated and replayed probe, README claim, example, and cycle metadata successfully.\"\n ],\n \"deviations\": [\n \"The README's top-level assistant invocation `/graphify .` requires an AI coding assistant. Exercised its documented local code-only CLI extraction instead.\",\n \"Installed graphify from the pinned local source with the uv tool command rather than installing the published package.\"\n ],\n \"stuck_step\": null,\n \"main_blocker\": null,\n \"plain_failure\": null,\n \"suggested_fix\": null\n}\nEOF\nls -la .coldpass && git rev-parse FETCH_HEAD && cat .coldpass/report.json" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Build and query a local code knowledge graph", "suggested_fix": null, "tokens_in": 351433, "tokens_out": 2804, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "", "extract", ".coldpass/sample", "--code-only", "--no-viz", "--out", ".coldpass/replay-probe-checker-a2562f5b7629411795e7bbc514def48e" ], "kind": "cli", "returncode": 0, "stdout": "[graphify extract] scanning \n[graphify extract] found 1 code, 0 docs, 0 papers, 0 images\n[graphify extract] AST extraction on 1 code files...\n[graphify extract] wrote 5 nodes, 5 edges, 2 communities\n[graphify extract] wrote \n[graphify extract] next: run `graphify cluster-only to generate GRAPH_REPORT.md and name communities", "stderr": "", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 127 known vulnerability. 1 static matches retained as context.", "findings": [ { "kind": "known-vulnerability", "count": 127, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 12 } ], "context": [ { "kind": "hardcoded-secret", "count": 1, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 1, "path": "tests/test_security.py" } ], "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=Graphify-Labs--graphify-gpt-6-luna-1792776386984097674", "evidence_file": "/data/safety/Graphify-Labs--graphify-gpt-6-luna-1792776386984097674.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": 13, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "c588b72d936927790a87ad009955078ed40562a3", "url": "https://github.com/Graphify-Labs/graphify" }, "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": 13, "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": "Apache-2.0", "repo_url": "https://github.com/Graphify-Labs/graphify", "cost_to_try": "free", "hardware": null, "what_failed": null, "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": "Inspected the README commands and graphify CLI entry point: graphify watch is a user-started filesystem watcher, not a scheduled product cycle. No cron, scheduler, webhook, or --once cycle is documented; a one-shot extraction was exercised instead.", "evidence": "Inspected the README commands and graphify CLI entry point: graphify watch is a user-started filesystem watcher, not a scheduled product cycle. No cron, scheduler, webhook, or --once cycle is documented; a one-shot extraction was exercised instead.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Code files are processed locally via tree-sitter and require no API key.", "source": "- **Code files**: processed locally via tree-sitter. Nothing leaves your machine. A code-only corpus requires no API key: `graphify extract` runs fully offline.", "input": "A Python sample defining UserService and DatabasePool", "expected": "The code-only extraction creates a graph and explain returns UserService with a connection.", "command": " extract .coldpass/sample --code-only --no-viz --out .coldpass/replay-claim-checker-74f600b6f9a6419e8f871f0865fd96a3", "verdict": "yes", "outcome": "Real input produced the expected result: 5 nodes, 5 edges", "evidence": "5 nodes, 5 edges, 2 communities\n[graphify extract] wrote \n[graphify extract] next: run `graphify cluster-only to generate GRAPH_REPORT.md and name communities\n", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Build a local code graph using the documented CLI operation.", "source": "README.md / Privacy and Common commands", "input": "Python code-only corpus at .coldpass/sample", "command": " extract .coldpass/sample --code-only --no-viz --out .coldpass/replay-example-checker-23ccc43f4fc5487eb20a32e7902fb95e", "evidence": "ode, 0 docs, 0 papers, 0 images\n[graphify extract] AST extraction on 1 code files...\n[graphify extract] wrote 5 nodes, 5 edges, 2 communities\n[graphify extract] wrote \n[graphify extract] next: run `graphify cluster-only to generate GRAPH_REPORT.md and name communities", "deferred": false, "expected": "graph.json with extracted code nodes and edges", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "archived": false, "commits_90d": 1240, "last_commit_at": "2026-10-22T16:06:40Z", "last_release_at": "2026-10-22T16:19:50Z", "median_reply_hours": null, "merged_prs_90d": 0, "note": "actively maintained: last commit 1 days ago; 1240 commits and 0 merged PRs in 90 days; 719 open issues, 913 open PRs; latest release 2026-10-22", "open_issues": 719, "open_prs": 913, "reply_share": null, "reply_threads": 0, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 1 days ago; 1240 commits and 0 merged PRs in 90 days; 719 open issues, 913 open PRs; latest release 2026-10-22", "maintained": "active", "maintained_note": "last commit 1 days ago; 4 open issues, 5 answered or closed", "last_commit_at": "2026-10-22T16:19:38Z", "last_release_at": "2026-10-22T16:19:50Z", "open_issues": 4, "answered_issues": 5, "platforms_claimed": [ "linux", "mac", "windows" ], "topic": "mcp-server", "agent_interfaces": [ { "interface": "mcp", "evidence": "README metadata", "observed": false, "operation_checked": false }, { "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": "2026-10-23T17:28:11.655559+00:00", "tested_commit": "c588b72d936927790a87ad009955078ed40562a3", "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": "Graphify-Labs/graphify", "source": "https://github.com/Graphify-Labs/graphify", "commit": "c588b72d936927790a87ad009955078ed40562a3", "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": "c588b72d936927790a87ad009955078ed40562a3", "url": "https://github.com/Graphify-Labs/graphify" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Build and query a local code knowledge graph", "operation_scope": "product operation", "hosting": null, "kind": "repo", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": null, "report_url": "/reports/Graphify-Labs--graphify-gpt-6-luna-1792776386984097674.json" }