{ "run_id": "wimglenn--oyaml-claude-haiku-5-5-1793090454562619348", "date": "2026-10-27T08:42:49.672821+00:00", "repo": "wimglenn/oyaml", "kind": "repo", "source": "https://github.com/wimglenn/oyaml", "commit": "37c20f3d838fd177d0128b9d03a20f5587f7445a", "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": 115.11016869544983, "steps": [ "cd && pwd && ls -la && id -u && python3 --version && (git -C . status 2>&1 | head -3) && cat README.md 2>/dev/null | head -150", "ls -la /inputs 2>&1; echo \"CDP_URL=$CDP_URL\"; echo \"=$\"", "cd && cat README.rst && echo ---- && cat setup.py setup.cfg && echo ---- && cat oyaml.py && ls -la .coldpass .github && ls ", "cd && cat .github/workflows/* && echo ---- && head -40 test_oyaml.py && cat MANIFEST.in", "python3 -m venv --help >/dev/null 2>&1 && echo venv_ok || echo venv_missing; pip --version 2>&1; curl -s -m 5 -o /dev/null -w \"%{http_code}\\n\" $CDP_URL/json/version; echo; curl -s -m 5 $CDP_URL/json/version; echo \" rc=$?\"", "python3 -m venv /tmp/oy-venv && /tmp/oy-venv/bin/pip install -q --upgrade pip 2>&1 | tail -3; /tmp/oy-venv/bin/pip install oyaml 2>&1 | tail -5; /tmp/oy-venv/bin/pip show oyaml pyyaml 2>&1 | grep -E \"Name|Version\"", "cd && /tmp/oy-venv/bin/pip install -q pytest 2>&1 | tail -2; /tmp/oy-venv/bin/python -m pytest -p no:cacheprovider -q 2>&1 | tail -25; echo rc=$?", "cd && /tmp/oy-venv/bin/python -m pytest -p no:cacheprovider -q -rs 2>&1 | grep -i skip; cd /tmp && /tmp/oy-venv/bin/python -c \"import oyaml,sys;print(oyaml.__file__)\"; wc -c ; grep -n \"def \\|kind\\|\\\"checks\\\"\\|'checks'\\|install\" | head -80", "cd && cat > claims.json <<'EOF'\n[\n{\"kind\":\"claim\",\"claim\":\"oyaml installs with pip install oyaml as documented\",\"source\":\"Just ``pip install oyaml``, and import as shown below:\",\"input\":\"pip install oyaml\",\"expected\":\"oyaml is installed (already satisfied in the guest)\",\"probe_kind\":\"cli\",\"argv\":[\"/tmp/oy-venv/bin/pip\",\"install\",\"oyaml\"],\"expected_text\":\"Requirement already satisfied: oyaml\",\"cwd\":\"\"},\n{\"kind\":\"claim\",\"claim\":\"oyaml preserves dict ordering when dumping/loading\",\"source\":\"You'll no longer be annoyed by screwed-up mappings when dumping/loading.\",\"testable\":false,\"reason\":\"oyaml is a Python library with no CLI, MCP, or HTTP entry point; the ordering behaviour can only be exercised via agent-written import code, which is not a documented product command. The repo's own pytest suite (test_dump asserts {x: 1, z: 3, y: 2}) covers it, but that is not counted as a probe.\"}\n]\nEOF\ncat > probe.json <<'EOF'\n{\"checks\":[{\"check\":\"install\",\"kind\":\"cli\",\"argv\":[\"/tmp/oy-venv/bin/pip\",\"install\",\"oyaml\"],\"cwd\":\"\",\"expected_text\":\"Requirement already satisfied: oyaml\"}]}\nEOF\ncat > examples.json <<'EOF'\n[\n{\"kind\":\"example\",\"claim\":\"repo test suite runs the oyaml checks\",\"source\":\".github/workflows/tests.yml (Run tests step: python -m pytest)\",\"input\":\"python -m pytest in the checkout\",\"expected\":\"tests pass\",\"argv\":[\"/tmp/oy-venv/bin/python\",\"-m\",\"pytest\",\"-q\"],\"cwd\":\"\",\"expected_text\":\"18 passed, 2 skipped\"}\n]\nEOF\ncat > cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"oyaml is a library with no scheduler, loop, cron, webhook, --once or --now entry point; inspected README.rst, setup.py, oyaml.py and .github/workflows/tests.yml (CI schedules are not product cycles).\",\"checks\":[]}\nEOF\nfor f in claims probe examples cycles; do /tmp/oy-venv/bin/python -I -c \"import json,sys;json.load(open('$f.json'));print('$f ok')\"; done", "cd && = python3 -I --validate --replay 2>&1 | tail -60; echo rc=${PIPESTATUS[0]}", "cd && cat > claims.json <<'EOF'\n[\n{\"kind\":\"claim\",\"claim\":\"oyaml installs with pip install oyaml as documented\",\"source\":\"Just ``pip install oyaml``, and import as shown below:\",\"source_file\":\"README.rst\",\"input\":\"pip install oyaml\",\"expected\":\"oyaml is installed (already satisfied in the guest)\",\"probe_kind\":\"cli\",\"argv\":[\"/tmp/oy-venv/bin/pip\",\"install\",\"oyaml\"],\"expected_text\":\"Requirement already satisfied: oyaml\",\"cwd\":\"\"},\n{\"kind\":\"claim\",\"claim\":\"oyaml preserves dict ordering when dumping/loading\",\"source\":\"You'll no longer be annoyed by screwed-up mappings when dumping/loading.\",\"source_file\":\"README.rst\",\"testable\":false,\"reason\":\"oyaml is a Python library with no CLI, MCP, or HTTP entry point; the ordering behaviour can only be exercised via agent-written import code, which is not a documented product command. The repo's own pytest suite (test_dump asserts {x: 1, z: 3, y: 2}) covers it, but that is not counted as a probe.\"}\n]\nEOF\ncd && = python3 -I --validate --replay 2>&1 | tail -80; echo rc=${PIPESTATUS[0]}", "cd && cat > report.json <<'EOF'\n{\"outcome\":\"unsupported\",\"fault_owner\":\"test\",\"operation\":\"Install oyaml and use it as a drop-in PyYAML replacement that preserves dict ordering\",\"operation_scope\":\"Python library only (no CLI, MCP or HTTP entry point). Guest: Ubuntu, Python 3.12.3 in /tmp/oy-venv, PyYAML 6.0.3, pytest. Browser endpoint http://:9226/json/version returned HTTP 200 (Chrome/155); not needed by this product.\",\"steps\":[\"pip install oyaml (README.rst: Just ``pip install oyaml``) - installed oyaml-1.0 and pyyaml-6.0.3 from PyPI\",\"python -m pytest in the checkout (.github/workflows/tests.yml Run tests step, without the coverage flags) - 18 passed, 2 skipped (skips are for the old dict implementation)\",\"= python3 -I --validate --replay - valid, replay PASS, evidence_strength partly_checked\"],\"deviations\":[\"/inputs/coldpass-preflight.py does not exist in this guest; used instead\",\"README is README.rst, not README.md; claims set source_file to README.rst\",\"Coverage flags (--cov-branch --cov=oyaml) from CI omitted because pytest-cov was not installed; plain python -m pytest run instead\",\"Source was not git-initialised; pip install used the PyPI release of oyaml 1.0 (same version as the pinned checkout's setup.py) rather than installing from the pinned commit\",\"The ordering promise could not be probed: oyaml has no CLI, so the only exercise path is agent-written import code, which the checker does not count as a product operation\"],\"stuck_step\":null,\"main_blocker\":\"oyaml is a library with no runnable product command; the README's only usage is a Python import snippet, so the checker has no documented entry point to call for the dict-ordering behaviour.\",\"plain_failure\":\"Nothing failed. The package installs and its own test suite passes, but the checker could only confirm the install, not the ordering behaviour the README describes.\",\"suggested_fix\":\"Give the README a documented CLI or runnable example script (for example a small oyaml dump/load command) so the ordering claim can be run through a real entry point.\"}\nEOF\n/tmp/oy-venv/bin/python -I -c \"import json;d=json.load(open('report.json'));print(d['outcome'],d['fault_owner'])\"; ls -la " ], "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 && cat > report.json <<'\"'\"'\"'\"'\"'\"'\"'\"'EOF'\"'\"'\"'\"'\"'\"'\"'\"'\n{\"outcome\":\"unsupported\",\"fault_owner\":\"test\",\"operation\":\"Install oyaml and use it as a drop-in PyYAML replacement that preserves dict ordering\",\"operation_scope\":\"Python library only (no CLI, MCP or HTTP entry point). Guest: Ubuntu, Python 3.12.3 in /tmp/oy-venv, PyYAML 6.0.3, pytest. Browser endpoint http://:9226/json/version returned HTTP 200 (Chrome/155); not needed by this product.\",\"steps\":[\"pip install oyaml (README.rst: Just ``pip install oyaml``) - installed oyaml-1.0 and pyyaml-6.0.3 from PyPI\",\"python -m pytest in the checkout (.github/workflows/tests.yml Run tests step, without the coverage flags) - 18 passed, 2 skipped (skips are for the old dict implementation)\",\"= python3 -I --validate --replay - valid, replay PASS, evidence_strength partly_checked\"],\"deviations\":[\"/inputs/coldpass-preflight.py does not exist in this guest; used instead\",\"README is README.rst, not README.md; claims set source_file to README.rst\",\"Coverage flags (--cov-branch --cov=oyaml) from CI omitted because pytest-cov was not installed; plain python -m pytest run instead\",\"Source was not git-initialised; pip install used the PyPI release of oyaml 1.0 (same version as the pinned checkout'\"'\"'\"'\"'\"'\"'\"'\"'s setup.py) rather than installing from the pinned commit\",\"The ordering promise could not be probed: oyaml has no CLI, so the only exercise path is agent-written import code, which the checker does not count as a product operation\"],\"stuck_step\":null,\"main_blocker\":\"oyaml is a library with no runnable product command; the README'\"'\"'\"'\"'\"'\"'\"'\"'s only usage is a Python import snippet, so the checker has no documented entry point to call for the dict-ordering behaviour.\",\"plain_failure\":\"Nothing failed. The package installs and its own test suite passes, but the checker could only confirm the install, not the ordering behaviour the README describes.\",\"suggested_fix\":\"Give the README a documented CLI or runnable example script (for example a small oyaml dump/load command) so the ordering claim can be run through a real entry point.\"}\nEOF\n/tmp/oy-venv/bin/python -I -c \"import json;d=json.load(open('\"'\"'\"'\"'\"'\"'\"'\"'report.json'\"'\"'\"'\"'\"'\"'\"'\"'));print(d['\"'\"'\"'\"'\"'\"'\"'\"'outcome'\"'\"'\"'\"'\"'\"'\"'\"'],d['\"'\"'\"'\"'\"'\"'\"'\"'fault_owner'\"'\"'\"'\"'\"'\"'\"'\"'])\"; ls -la '\"'\"''", "error_excerpt": "oyaml is a library with no runnable product command; the README's only usage is a Python import snippet, so the checker has no documented entry point to call for the dict-ordering behaviour.", "what_it_did": "Install oyaml and use it as a drop-in PyYAML replacement that preserves dict ordering", "suggested_fix": "Give the README a documented CLI or runnable example script (for example a small oyaml dump/load command) so the ordering claim can be run through a real entry point.", "tokens_in": 180274, "tokens_out": 10129, "cost_usd": 0.01072451, "usage_complete": true, "checks": [ { "status": "PASS", "details": { "working": false, "argv": [ "/tmp/oy-venv/bin/pip", "install", "oyaml" ], "kind": "cli", "returncode": 0, "stdout": "Requirement already satisfied: oyaml in /tmp/oy-venv/lib/python3.12/site-packages (1.0)\nRequirement already satisfied: pyyaml in /tmp/oy-venv/lib/python3.12/site-packages (from oyaml) (6.0.3)", "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=wimglenn--oyaml-claude-haiku-5-5-1793090454562619348", "evidence_file": "/data/safety/wimglenn--oyaml-claude-haiku-5-5-1793090454562619348.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": 12, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "37c20f3d838fd177d0128b9d03a20f5587f7445a", "url": "https://github.com/wimglenn/oyaml" }, "purpose": "test_rerun", "profile": { "model": "claude-haiku-5-5", "reasoning": "low" }, "fault": { "owner": "test", "status": "diagnosed", "reason": "oyaml is a library with no runnable product command; the README's only usage is a Python import snippet, so the checker has no documented entry point to call for the dict-ordering behaviour." }, "fix_id": null, "verifies_run_id": "wimglenn--oyaml-claude-haiku-5-5-1793089638890424387", "hosting": null, "operation_scope": "partial checks", "tool_calls": 12, "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": [], "license": "MIT", "repo_url": "https://github.com/wimglenn/oyaml", "cost_to_try": null, "hardware": null, "what_failed": "oyaml is a library with no runnable product command; the README's only usage is a Python import snippet, so the checker has no documented entry point to call for the dict-ordering behaviour.", "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": "oyaml is a library with no scheduler, loop, cron, webhook, --once or --now entry point; inspected README.rst, setup.py, oyaml.py and .github/workflows/tests.yml (CI schedules are not product cycles).", "evidence": "oyaml is a library with no scheduler, loop, cron, webhook, --once or --now entry point; inspected README.rst, setup.py, oyaml.py and .github/workflows/tests.yml (CI schedules are not product cycles).", "command": "" } ], "claims": [ { "kind": "claim", "claim": "oyaml installs with pip install oyaml as documented", "source": "Just ``pip install oyaml``, and import as shown below:", "input": "pip install oyaml", "expected": "oyaml is installed (already satisfied in the guest)", "command": "/tmp/oy-venv/bin/pip install oyaml", "verdict": "yes", "outcome": "Real input produced the expected result: Requirement already satisfied: oyaml", "evidence": "Requirement already satisfied: oyaml in /tmp/oy-venv/lib/python3.12/site-packages (1.0)\nRequirement already satisfied: pyyaml in /tmp/oy-venv/lib/python3.12/site-packages (from oyaml) (6.0.3)\n", "returncode": 0, "source_checked": true, "source_file": "README.rst" }, { "kind": "claim", "claim": "oyaml preserves dict ordering when dumping/loading", "source": "You'll no longer be annoyed by screwed-up mappings when dumping/loading.", "input": "", "expected": "", "command": "", "verdict": "blocked", "outcome": "oyaml is a Python library with no CLI, MCP, or HTTP entry point; the ordering behaviour can only be exercised via agent-written import code, which is not a documented product command. The repo's own pytest suite (test_dump asserts {x: 1, z: 3, y: 2}) covers it, but that is not counted as a probe.", "evidence": "oyaml is a Python library with no CLI, MCP, or HTTP entry point; the ordering behaviour can only be exercised via agent-written import code, which is not a documented product command. The repo's own pytest suite (test_dump asserts {x: 1, z: 3, y: 2}) covers it, but that is not counted as a probe.", "source_checked": true, "source_file": "README.rst" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "repo test suite runs the oyaml checks", "source": ".github/workflows/tests.yml (Run tests step: python -m pytest)", "input": "python -m pytest in the checkout", "command": "/tmp/oy-venv/bin/python -m pytest -q", "evidence": "........s.s......... [100%]\n18 passed, 2 skipped in 0.16s", "deferred": false, "expected": "tests pass", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "partly", "maintenance": { "archived": false, "commits_90d": 0, "last_commit_at": "2024-11-05T02:26:02Z", "last_release_at": "2023-05-07T16:18:18Z", "median_reply_hours": 6.9, "merged_prs_90d": 0, "note": "abandoned: last commit 721 days ago; 0 commits and 0 merged PRs in 90 days; 0 open issues, 0 open PRs; 15 of 17 recent threads got a maintainer reply, median first reply 6.9h; latest release 2023-05-07", "open_issues": 0, "open_prs": 0, "reply_share": 0.88, "reply_threads": 17, "verdict": "abandoned" }, "maintenance_verdict": "abandoned", "maintenance_note": "abandoned: last commit 721 days ago; 0 commits and 0 merged PRs in 90 days; 0 open issues, 0 open PRs; 15 of 17 recent threads got a maintainer reply, median first reply 6.9h; latest release 2023-05-07", "maintained": "dormant", "maintained_note": "last commit 721 days ago; 0 open issues, 15 answered or closed", "last_commit_at": "2024-11-05T02:26:08Z", "last_release_at": "2023-05-07T16:18:18Z", "open_issues": 0, "answered_issues": 15, "platforms_claimed": [ "linux" ], "topic": "creative", "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": "2026-10-27T08:42:49.672821+00:00", "tested_commit": "37c20f3d838fd177d0128b9d03a20f5587f7445a", "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": "wimglenn/oyaml", "source": "https://github.com/wimglenn/oyaml", "commit": "37c20f3d838fd177d0128b9d03a20f5587f7445a", "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": "37c20f3d838fd177d0128b9d03a20f5587f7445a", "url": "https://github.com/wimglenn/oyaml" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": null, "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Install oyaml and use it as a drop-in PyYAML replacement that preserves dict ordering", "operation_scope": "partial checks", "hosting": null, "kind": "repo", "test_version": "readme-d5b140d3c0f8b95c2dd6fe6fc381a303cacb92679582c22317d8e78b572f0cf2", "evidence_version": null }, "transcript_url": "/transcripts/wimglenn--oyaml-claude-haiku-5-5-1793090454562619348.txt", "report_url": "/reports/wimglenn--oyaml-claude-haiku-5-5-1793090454562619348.json" }