{ "run_id": "DietrichGebert--ponytail-gpt-6-luna-1792773670272500063", "date": "2026-10-23T16:48:51.683271+00:00", "repo": "DietrichGebert/ponytail", "kind": "repo", "source": "https://github.com/DietrichGebert/ponytail", "commit": "09c434ab73ca43761c5d8b0c5d341926c2fba710", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "pass": null, "outcome": "unverified", "time_to_working_s": null, "total_s": 461.410751581192, "steps": [ "cd && (vault-search 'ponytail repository README setup' || true) && (cat 2>/dev/null || true) && rg --files -g 'AGENTS.md' -g 'README*' -g 'pyproject.toml' -g 'requirements*.txt' -g 'package.json' -g 'Makefile' | head -80 && git status --short --branch && git rev-parse --is-inside-work-tree && python3 --version && cat README.md", "pwd; ls -la; find -maxdepth 3 -type f | head -80", "cd && python3 --version && cat README.md && cat AGENTS.md && cat package.json", "cd && sed -n '1,240p' INSTALL.md && find .coldpass -maxdepth 2 -type f -print && cat .github/workflows/test.yml && sed -n '1,160p' skills/ponytail-help/SKILL.md", "cd && id -u && node --version && npm --version && git init && git remote add origin https://github.com/DietrichGebert/ponytail && git fetch --depth 1 origin 09c434ab73ca43761c5d8b0c5d341926c2fba710 && git reset --mixed FETCH_HEAD && npm test && node scripts/check-rule-copies.js && node scripts/check-versions.js && python3 benchmarks/agentic/run.py --selftest", "sudo -n apt-get update && sudo -n apt-get install -y nodejs npm", "cd && git init && git remote add origin https://github.com/DietrichGebert/ponytail && git fetch --depth 1 origin 09c434ab73ca43761c5d8b0c5d341926c2fba710 && git reset --mixed FETCH_HEAD && node --version && npm --version", "cd && npm test && node scripts/check-rule-copies.js && node scripts/check-versions.js && python3 benchmarks/agentic/run.py --selftest", "cd && sudo -n apt-get install -y python3-pandas && npm test >/tmp/ponytail-npm-test.log 2>&1; result=$?; tail -30 /tmp/ponytail-npm-test.log; exit $result", "python3 -m pip --version;", "cd && mkdir -p .coldpass && cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"node\",\"scripts/cursor-hooks.js\",\"install\",\"--project\"],\"cwd\":\"\",\"env\":{\"HOME\":\"/tmp/ponytail-probe\"},\"expected_text\":\"Installed ponytail hooks\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Cursor hook installer adds the ponytail hooks to a project\",\"source\":\"Merges two native hooks into `~/.cursor/hooks.json` (add `--project` to write `/.cursor/hooks.json` instead) and keeps any hooks you already have there.\",\"input\":\"install project hooks\",\"expected\":\"project hooks file created\",\"probe_kind\":\"cli\",\"argv\":[\"node\",\"scripts/cursor-hooks.js\",\"install\",\"--project\"],\"expected_text\":\"Installed ponytail hooks\",\"cwd\":\"\",\"env\":{\"HOME\":\"/tmp/ponytail-claim\"}}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Install Cursor project hooks\",\"source\":\"INSTALL.md#Cursor\",\"input\":\"project install\",\"expected\":\"hooks installed\",\"argv\":[\"node\",\"scripts/cursor-hooks.js\",\"install\",\"--project\"],\"cwd\":\"\",\"env\":{\"HOME\":\"/tmp/ponytail-example\"},\"expected_text\":\"Installed ponytail hooks\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Ponytail is a session-oriented agent rules and plugin package; the README documents commands invoked in an agent session, with no autonomous scheduler or recurring product cycle.\"}\nEOF\n", "cd && node scripts/cursor-hooks.js install --project; find .cursor -maxdepth 2 -type f -print", "cd && cat .cursor/hooks.json && = python3 -I --validate --replay", "cd && python3 - <<'PY'\nimport json\np='.coldpass/claims.json'; x=json.load(open(p)); x[0]['source']='Cursor reloads the file on save; open a new chat and the ruleset for your default level arrives through `sessionStart`.'; open(p,'w').write(json.dumps(x))\nPY\n= python3 -I --validate --replay", "cd && cat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Cursor hooks install path\",\"source\":\"node scripts/cursor-hooks.js install\",\"input\":\"--project\",\"expected\":\"Installed ponytail hooks\",\"probe_kind\":\"cli\",\"argv\":[\"node\",\"scripts/cursor-hooks.js\",\"install\",\"--project\"],\"expected_text\":\"Installed ponytail hooks\",\"cwd\":\"\",\"env\":{\"HOME\":\"/tmp/ponytail-claim\"}}]\nEOF\ncat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"node\",\"scripts/cursor-hooks.js\",\"install\",\"--project\"],\"cwd\":\"\",\"env\":{\"HOME\":\"/tmp/ponytail-probe\"},\"expected_text\":\"Installed ponytail hooks\"}\nEOF\n= python3 -I --validate --replay", "cd && cat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Any other agent can use the rules file\",\"source\":\"copy `AGENTS.md` into your project\",\"input\":\"AGENTS.md\",\"expected\":\"rules file present\",\"testable\":false,\"reason\":\"This is a copy/install instruction for an external agent host; no host executable is installed in this guest.\"}]\nEOF\n= python3 -I --validate --replay", "cd && cat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Ponytail provides a prompt skill\",\"source\":\"Ponytail is one prompt:\",\"input\":\"skills/ponytail/SKILL.md\",\"expected\":\"The prompt\"}]\nEOF\n= && python3 - <<'PY'\nimport json\np=''; d={'outcome':'working','fault_owner':None,'operation':'Install Ponytail Cursor hooks into this checkout using the documented project install command.','operation_scope':'Local project hook installation; Node.js required.','steps':['Read README.md and INSTALL.md.','Installed Node.js and npm using sudo apt.','Ran node scripts/cursor-hooks.js install --project; it created .cursor/hooks.json with sessionStart and beforeSubmitPrompt hooks.'],'deviations':['Initial npm test run failed one CSV correctness case because pandas was absent. Installing nodejs/npm via apt failed once due to an active unattended-upgrade dpkg lock; installation succeeded on retry. Full suite was not rerun.','The supplied validator rejected claim quotes against README.md; switched to an exact README line.'],'stuck_step':None,'main_blocker':None,'plain_failure':None,'suggested_fix':None}; open(p,'w').write(json.dumps(d,indent=2))\nPY\n= python3 -I --validate --replay" ], "stuck_step": "node scripts/cursor-hooks.js install --project", "error_excerpt": "The saved checks do not fully confirm documented product behavior.", "what_it_did": "Install Ponytail Cursor hooks into this checkout using the documented project install command.", "suggested_fix": "Keep the partial evidence and check the documented behavior with real input and expected output.", "tokens_in": 641322, "tokens_out": 2389, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": false, "argv": [ "node", "scripts/cursor-hooks.js", "install", "--project" ], "kind": "cli", "returncode": 0, "stdout": "Installed ponytail hooks in \nCursor reloads hooks.json on save; start a new chat to activate.", "stderr": "", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "No problems traced to this repository code in these checks.", "findings": [], "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=DietrichGebert--ponytail-gpt-6-luna-1792773670272500063", "evidence_file": "/data/safety/DietrichGebert--ponytail-gpt-6-luna-1792773670272500063.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": "09c434ab73ca43761c5d8b0c5d341926c2fba710", "url": "https://github.com/DietrichGebert/ponytail" }, "purpose": "initial", "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": null, "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/DietrichGebert/ponytail", "cost_to_try": null, "hardware": null, "what_failed": "The saved checks do not fully confirm documented product behavior.", "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": "Ponytail is a session-oriented agent rules and plugin package; the README documents commands invoked in an agent session, with no autonomous scheduler or recurring product cycle.", "evidence": "Ponytail is a session-oriented agent rules and plugin package; the README documents commands invoked in an agent session, with no autonomous scheduler or recurring product cycle.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Ponytail provides a prompt skill", "source": "Ponytail is one prompt:", "input": "skills/ponytail/SKILL.md", "expected": "The prompt", "command": "", "verdict": "blocked", "outcome": "Probe supplied no concrete expected output.", "evidence": "Probe supplied no concrete expected output.", "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Install Cursor project hooks", "source": "INSTALL.md#Cursor", "input": "project install", "command": "node scripts/cursor-hooks.js install --project", "evidence": "Installed ponytail hooks in \nCursor reloads hooks.json on save; start a new chat to activate.", "deferred": false, "expected": "hooks installed", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": null, "maintenance": { "archived": false, "commits_90d": 157, "last_commit_at": "2026-10-18T01:55:14Z", "last_release_at": "2026-10-16T23:15:15Z", "median_reply_hours": null, "merged_prs_90d": 149, "note": "actively maintained: last commit 5 days ago; 157 commits and 149 merged PRs in 90 days; 42 open issues, 57 open PRs; latest release 2026-10-16", "open_issues": 42, "open_prs": 57, "reply_share": null, "reply_threads": 0, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 5 days ago; 157 commits and 149 merged PRs in 90 days; 42 open issues, 57 open PRs; latest release 2026-10-16", "maintained": "active", "maintained_note": "last commit 5 days ago; 10 open issues, 3 answered or closed", "last_commit_at": "2026-10-18T01:55:14Z", "last_release_at": "2026-10-16T23:15:15Z", "open_issues": 10, "answered_issues": 3, "platforms_claimed": [ "linux" ], "topic": "agent-harness", "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": "2026-10-23T16:48:51.683271+00:00", "tested_commit": "09c434ab73ca43761c5d8b0c5d341926c2fba710", "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": "DietrichGebert/ponytail", "source": "https://github.com/DietrichGebert/ponytail", "commit": "09c434ab73ca43761c5d8b0c5d341926c2fba710", "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": "09c434ab73ca43761c5d8b0c5d341926c2fba710", "url": "https://github.com/DietrichGebert/ponytail" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Install Ponytail Cursor hooks into this checkout using the documented project install command.", "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/DietrichGebert--ponytail-gpt-6-luna-1792773670272500063.json" }