{ "run_id": "python-hyper--rfc3986-claude-haiku-5-5-1793089992992115881", "date": "2026-10-27T08:37:04.239483+00:00", "repo": "python-hyper/rfc3986", "kind": "repo", "source": "https://github.com/python-hyper/rfc3986", "commit": "3bd3832b72eb981d080514a8192046e3177263be", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "test_version": "readme-d5b140d3c0f8b95c2dd6fe6fc381a303cacb92679582c22317d8e78b572f0cf2", "pass": null, "outcome": "unverified", "time_to_working_s": null, "total_s": 231.24733233451843, "steps": [ "cd && pwd && ls -la && id -u && python3 --version && cat README* | head -c 6000", "echo $CDP_URL; curl -sS -m 10 $CDP_URL/json/version; echo \"exit=$?\"; ls /inputs 2>/dev/null; ls 2>/dev/null", "cd && cat setup.cfg pyproject.toml | head -80; ls -la .coldpass; ls src/rfc3986 tests; wc -c ", "cd && python3 -m venv && -m pip install -q --upgrade pip 2>&1 | tail -3; -m pip install 2>&1 | tail -3; echo exit=$?", "cd && cat tox.ini | head -50; ls .github/workflows && grep -n \"run:\" -A3 .github/workflows/*.yml | head -40", "cd && cat dev-requirements.txt && -m pip install -q -r dev-requirements.txt idna 2>&1 | tail -3; -m pytest --version", "cd && -m pytest --cov rfc3986 --cov-fail-under 100 tests/ -q -p no:cacheprovider 2>&1 | tail -25; echo exit=${PIPESTATUS[0]}", "cd && grep -n \"testable\\|\\\"checks\\\"\\|'checks'\\|install\\|def _probe\\|probe_kind\\|kind ==\\|kind in\" check.py | head -80", "cd && sed -n 75,100p check.py; sed -n 760,790p check.py; sed -n 1230,1250p check.py", "cd && grep -rn \"__main__\\|console_scripts\\|entry_points\\|schedul\\|cron\\|webhook\\|argparse\\|sys.argv\" src setup.cfg pyproject.toml setup.py 2>/dev/null | head; echo \"---\"; grep -n \"A Python implementation of\\|Use pip to install\\|Strictly Parsing a URI\\|Replacing \\`\\`urlparse\\`\\`\\|You can also very simply validate a URI\" README.rst; echo \"---\"; ls -la .coldpass; git status 2>/dev/null | head -1; ls -d build *.egg-info src/*.egg-info 2>/dev/null", "cd && rm -rf build src/rfc3986.egg-info && install rfc3986 2>&1 | tail -2; ls | grep -i \"py.test\\|pytest\"; --cov rfc3986 --cov-fail-under 100 tests/ -q 2>&1 | tail -2; echo exit=${PIPESTATUS[0]}", "cd && cat > .coldpass/claims.json <<'EOF'\n[\n{\"kind\":\"claim\",\"claim\":\"Installing rfc3986 with pip works\",\"source\":\"Use pip to install ``rfc3986`` like so::\",\"testable\":false,\"reason\":\"The install command was run and succeeded (see probe.json), but this promise only covers installation, not a product operation; no CLI, server, or MCP surface exists for the checker to drive.\"},\n{\"kind\":\"claim\",\"claim\":\"The library validates URIs (is_valid_uri)\",\"source\":\"You can also very simply validate a URI:\",\"testable\":false,\"reason\":\"rfc3986 is a Python library with no command-line entry point, server, or MCP tool. The documented call is a Python API call (from rfc3986 import is_valid_uri), and the checker only accepts documented CLI, HTTP, or MCP entry points. Covered indirectly by the repository's own test suite (tests/test_api.py etc.), which passed with 100% coverage.\"},\n{\"kind\":\"claim\",\"claim\":\"The library parses URIs into components\",\"source\":\"A Python implementation of `RFC 3986`_ including validation and authority\",\"testable\":false,\"reason\":\"Same gap: the parsing promise is only exposed as a Python API (uri_reference, urlparse) with no CLI, server, or MCP surface. Covered indirectly by the repository's test suite, which passed.\"}\n]\nEOF\ncat > .coldpass/probe.json <<'EOF'\n{\"checks\":[{\"check\":\"install\",\"kind\":\"cli\",\"argv\":[\"\",\"install\",\"rfc3986\"],\"cwd\":\"\",\"expected_text\":\"rfc3986\"}]}\nEOF\n -m json.tool .coldpass/claims.json >/dev/null -- 2>/dev/null; -c \"\" ; python3 -I -c \"import json;json.load(open('.coldpass/claims.json'));json.load(open('.coldpass/probe.json'));print('ok')\"", "cd && cat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"The repository's documented test command runs and enforces 100% coverage\",\"source\":\"tox.ini [testenv] commands\",\"input\":\"py.test --cov rfc3986 --cov-fail-under 100 tests/\",\"expected\":\"all tests pass and coverage reaches 100%\",\"argv\":[\"\",\"--cov\",\"rfc3986\",\"--cov-fail-under\",\"100\",\"tests/\"],\"cwd\":\"\",\"env\":{},\"expected_text\":\"Required test coverage of 100% reached\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Inspected src/rfc3986 and setup.cfg/pyproject.toml/setup.py: no __main__, console_scripts entry point, scheduler, cron, loop, webhook, or --once/--now option. rfc3986 is a passive import-only library, so it has no product cycle to trigger.\",\"checks\":[]}\nEOF\ncat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"unsupported\",\"fault_owner\":\"test\",\"operation\":\"Validate and parse URIs with rfc3986 (README Python API) and run the repository test suite\",\"operation_scope\":\"Python library, installed into a venv at with Python 3.12.3; no CLI, server, or MCP surface exists. Repository tests pass (100% coverage). The README's API calls were not driven through a checker-accepted entry point.\",\"steps\":[\"python3 -m venv \",\" -m pip install \",\" -m pip install -r dev-requirements.txt idna\",\" --cov rfc3986 --cov-fail-under 100 tests/ (tox.ini command; passed, 100% coverage)\",\" install rfc3986 (README install command; already satisfied)\"],\"deviations\":[\"Installed the checkout with python -m pip (the README says pip install rfc3986); the README install was also run and was already satisfied.\",\"Test run used the installed site-packages copy of rfc3986, not src/, so coverage reflects the installed build.\",\"README Python API examples (uri_reference, is_valid_uri, normalize) were not replayed as checker probes: the library has no CLI/server entry point, and python -c code is not accepted as a product entry point. Their behavior is only covered indirectly by the test suite.\",\"Probe records only the documented install step as partial evidence; no product operation could be replayed.\"],\"stuck_step\":null,\"main_blocker\":\"The product is a Python library with no command-line, server, or MCP entry point, so the checker cannot drive its documented API.\",\"plain_failure\":null,\"suggested_fix\":\"Add a documented command-line or example script entry point, or have the checker support library-level example calls, so README API promises can be replayed.\"}\nEOF\npython3 -I -c \"import json;[json.load(open('.coldpass/'+f)) for f in ['examples.json','cycles.json','report.json']];print('ok')\"", "cd && = timeout 900 python3 -I --validate --replay 2>&1 | tail -c 4000; echo exit=${PIPESTATUS[0]}", "cd && sed -i 's/\"kind\":\"claim\",/\"kind\":\"claim\",\"source_file\":\"README.rst\",/' .coldpass/claims.json && python3 -I -c \"import json;print(len(json.load(open('.coldpass/claims.json'))))\" && = timeout 900 python3 -I --validate --replay 2>&1 | tail -c 4000; echo exit=${PIPESTATUS[0]}", "cd && = timeout 900 python3 -I --validate --replay > 2>&1; echo exit=$?; python3 -I -c \"\nimport json,re\nt=open('').read()\ni=t.find('{')\nd=json.loads(t[i:])\nprint({k:(v if not isinstance(v,(dict,list)) else '...') for k,v in d.items()})\nprint(d.get('problems'))\nprint(d.get('probe',{}).get('status') if isinstance(d.get('probe'),dict) else str(d.get('probe'))[:600])\n\" 2>&1 | head -c 3000", "cd && python3 -I -c \"\nimport json\nt=open('').read()\nd=json.loads(t[t.find('{'):])\nr=d['replay']\nprint(list(r.keys()))\nfor k in r:\n v=r[k]\n if isinstance(v,dict): print(k, {x:(str(y)[:120]) for x,y in v.items() if x in ('status','verdict','outcome','working','scope')})\n else: print(k, str(v)[:200])\n\"", "cd && rm -rf .pytest_cache .coverage htmlcov && ls -a && ls -la .coldpass && cat .coldpass/report.json | python3 -I -c \"import json,sys;print(json.load(sys.stdin)['outcome'])\"" ], "stuck_step": "/bin/bash -c 'o=$(mktemp);e=$(mktemp);/bin/bash --noprofile --norc -c \"$1\" \"$o\" 2>\"$e\";c=$?;cat \"$o\";cat \"$e\" >&2;rm -f \"$o\" \"$e\";exit $c' coldpass 'exec /usr/bin/env -i USER=agent LOGNAME=agent USERNAME=agent '\"'\"'GIT_AUTHOR_NAME=Coldpass Cold Agent'\"'\"' '\"'\"'GIT_COMMITTER_NAME=Coldpass Cold Agent'\"'\"' GIT_CONFIG_NOSYSTEM=1 GIT_CONFIG_SYSTEM=/dev/null GIT_CONFIG_GLOBAL=/dev/null GIT_CONFIG_COUNT=4 GIT_CONFIG_KEY_0=user.name '\"'\"'GIT_CONFIG_VALUE_0=Coldpass Cold Agent'\"'\"' GIT_CONFIG_KEY_1=user.email GIT_CONFIG_KEY_2=user.useConfigOnly GIT_CONFIG_VALUE_2=true GIT_CONFIG_KEY_3=credential.helper GIT_CONFIG_VALUE_3= HOME= PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin LANG=C.UTF-8 SHELL=/bin/bash = XDG_CONFIG_HOME= NPM_CONFIG_CACHE=/var PIP_CACHE_DIR=/var CARGO_HOME=/var GOCACHE=/var GOMODCACHE=/var CDP_URL=http://:9226 =http://:9226 /bin/bash --noprofile --norc -c '\"'\"'cd && cd && rm -rf .pytest_cache .coverage htmlcov && ls -a && ls -la .coldpass && cat .coldpass/report.json | python3 -I -c \"import json,sys;print(json.load(sys.stdin)['\"'\"'\"'\"'\"'\"'\"'\"'outcome'\"'\"'\"'\"'\"'\"'\"'\"'])\"'\"'\"''", "error_excerpt": "The product is a Python library with no command-line, server, or MCP entry point, so the checker cannot drive its documented API.", "what_it_did": "Validate and parse URIs with rfc3986 (README Python API) and run the repository test suite", "suggested_fix": "Add a documented command-line or example script entry point, or have the checker support library-level example calls, so README API promises can be replayed.", "tokens_in": 345189, "tokens_out": 11071, "cost_usd": 0.013656290000000001, "usage_complete": true, "checks": [ { "status": "PASS", "details": { "working": false, "argv": [ "", "install", "rfc3986" ], "kind": "cli", "returncode": 0, "stdout": "Requirement already satisfied: rfc3986 in (2.0.0)", "stderr": "", "needs_credentials": false, "needs_browser": false, "scope": "partial: install" }, "check": "install", "optional": false } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "No problems traced to this repository code in these checks.", "expected": "Reviewed as expected for a test run: attempted writes that failed, so nothing was written.", "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=python-hyper--rfc3986-claude-haiku-5-5-1793089992992115881", "evidence_file": "/data/safety/python-hyper--rfc3986-claude-haiku-5-5-1793089992992115881.json.gz" }, "agent_execution": "native_agent", "agent_runtime": "claude-code", "agent_runtime_version": "2.1.310 (Claude Code)", "tool_transport": "mcp-assigned-vm", "platform": "linux", "reasoning": "low", "service_tier": null, "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": "3bd3832b72eb981d080514a8192046e3177263be", "url": "https://github.com/python-hyper/rfc3986" }, "purpose": "test_rerun", "profile": { "model": "claude-haiku-5-5", "reasoning": "low" }, "fault": { "owner": "test", "status": "diagnosed", "reason": "The product is a Python library with no command-line, server, or MCP entry point, so the checker cannot drive its documented API." }, "fix_id": null, "verifies_run_id": "python-hyper--rfc3986-claude-haiku-5-5-1793088194885441219", "hosting": null, "operation_scope": "partial checks", "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": "nothing_checked", "works": "untested", "install_s": null, "first_use_s": null, "mcp": "none", "needs": [], "needs_which": null, "agent_interface": [], "license": "NOASSERTION", "repo_url": "https://github.com/python-hyper/rfc3986", "cost_to_try": null, "hardware": null, "what_failed": "The product is a Python library with no command-line, server, or MCP entry point, so the checker cannot drive its documented API.", "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 src/rfc3986 and setup.cfg/pyproject.toml/setup.py: no __main__, console_scripts entry point, scheduler, cron, loop, webhook, or --once/--now option. rfc3986 is a passive import-only library, so it has no product cycle to trigger.", "evidence": "Inspected src/rfc3986 and setup.cfg/pyproject.toml/setup.py: no __main__, console_scripts entry point, scheduler, cron, loop, webhook, or --once/--now option. rfc3986 is a passive import-only library, so it has no product cycle to trigger.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Installing rfc3986 with pip works", "source": "Use pip to install ``rfc3986`` like so::", "input": "", "expected": "", "command": "", "verdict": "blocked", "outcome": "The install command was run and succeeded (see probe.json), but this promise only covers installation, not a product operation; no CLI, server, or MCP surface exists for the checker to drive.", "evidence": "The install command was run and succeeded (see probe.json), but this promise only covers installation, not a product operation; no CLI, server, or MCP surface exists for the checker to drive.", "source_checked": true, "source_file": "README.rst" }, { "kind": "claim", "claim": "The library validates URIs (is_valid_uri)", "source": "You can also very simply validate a URI:", "input": "", "expected": "", "command": "", "verdict": "blocked", "outcome": "rfc3986 is a Python library with no command-line entry point, server, or MCP tool. The documented call is a Python API call (from rfc3986 import is_valid_uri), and the checker only accepts documented CLI, HTTP, or MCP entry points. Covered indirectly by the repository's own test suite (tests/test_api.py etc.), which passed with 100% coverage.", "evidence": "rfc3986 is a Python library with no command-line entry point, server, or MCP tool. The documented call is a Python API call (from rfc3986 import is_valid_uri), and the checker only accepts documented CLI, HTTP, or MCP entry points. Covered indirectly by the repository's own test suite (tests/test_api.py etc.), which passed with 100% coverage.", "source_checked": true, "source_file": "README.rst" }, { "kind": "claim", "claim": "The library parses URIs into components", "source": "A Python implementation of `RFC 3986`_ including validation and authority", "input": "", "expected": "", "command": "", "verdict": "blocked", "outcome": "Same gap: the parsing promise is only exposed as a Python API (uri_reference, urlparse) with no CLI, server, or MCP surface. Covered indirectly by the repository's test suite, which passed.", "evidence": "Same gap: the parsing promise is only exposed as a Python API (uri_reference, urlparse) with no CLI, server, or MCP surface. Covered indirectly by the repository's test suite, which passed.", "source_checked": true, "source_file": "README.rst" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "The repository's documented test command runs and enforces 100% coverage", "source": "tox.ini [testenv] commands", "input": "py.test --cov rfc3986 --cov-fail-under 100 tests/", "command": " --cov rfc3986 --cov-fail-under 100 tests/", "evidence": " 92 0 100%\n 188 0 100%\n 31 0 100%\n 129 0 100%\n-----------------------------------------------------------------------------------------------\nTOTAL 883 0 100%\nRequired test coverage of 100% reached. Total coverage: 100.00%\n2914 passed, 1517 warnings in 19.51s", "deferred": false, "expected": "all tests pass and coverage reaches 100%", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": null, "maintenance": { "archived": false, "commits_90d": 5, "last_commit_at": "2026-10-06T10:23:54Z", "last_release_at": null, "median_reply_hours": 12.7, "merged_prs_90d": 5, "note": "actively maintained: last commit 20 days ago; 5 commits and 5 merged PRs in 90 days; 21 open issues, 12 open PRs; 8 of 33 recent threads got a maintainer reply, median first reply 12.7h; no releases", "open_issues": 21, "open_prs": 12, "reply_share": 0.24, "reply_threads": 33, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 20 days ago; 5 commits and 5 merged PRs in 90 days; 21 open issues, 12 open PRs; 8 of 33 recent threads got a maintainer reply, median first reply 12.7h; no releases", "maintained": "active", "maintained_note": "last commit 7 days ago; 3 open issues, 1 answered or closed", "last_commit_at": "2026-10-19T22:14:45Z", "last_release_at": null, "open_issues": 3, "answered_issues": 1, "platforms_claimed": [ "linux" ], "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": "2026-10-27T08:37:04.239483+00:00", "tested_commit": "3bd3832b72eb981d080514a8192046e3177263be", "tested_with": { "agent": "claude-code", "agent_version": "2.1.310 (Claude Code)", "model": "claude-haiku-5-5", "model_route": "claude-haiku-5-5", "reasoning": "low", "os": "linux", "backend": "hyperv", "transport": "mcp-assigned-vm" }, "setup_identity": { "repo": "python-hyper/rfc3986", "source": "https://github.com/python-hyper/rfc3986", "commit": "3bd3832b72eb981d080514a8192046e3177263be", "source_revision": null, "os": "linux", "architecture": null, "backend": "hyperv", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "agent_execution": "native_agent", "agent_runtime": "claude-code", "agent_runtime_version": "2.1.310 (Claude Code)", "tool_transport": "mcp-assigned-vm", "runtime": null, "runtime_version": null, "runtime_revision": null, "sandbox_source": null, "guest_setup": null, "source_pin": { "commit": "3bd3832b72eb981d080514a8192046e3177263be", "url": "https://github.com/python-hyper/rfc3986" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": null, "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Validate and parse URIs with rfc3986 (README Python API) and run the repository test suite", "operation_scope": "partial checks", "hosting": null, "kind": "repo", "test_version": "readme-d5b140d3c0f8b95c2dd6fe6fc381a303cacb92679582c22317d8e78b572f0cf2", "evidence_version": null }, "transcript_url": "/transcripts/python-hyper--rfc3986-claude-haiku-5-5-1793089992992115881.txt", "report_url": "/reports/python-hyper--rfc3986-claude-haiku-5-5-1793089992992115881.json" }