{ "run_id": "SIDDARTHAREDDY8--dhp-claude-haiku-5-5-1792969046672538328", "date": "2026-10-25T23:05:34.029279+00:00", "repo": "SIDDARTHAREDDY8/dhp", "kind": "mcp", "source": "https://github.com/SIDDARTHAREDDY8/dhp", "commit": "b36e78ee427f0df4af9b74d66bd3ebee1aa51c6b", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "test_version": "readme-ca496ea10bb07418d1d8f1c256c2433a55547acc0fb62d8b6d86ae33c976fbfa", "pass": true, "outcome": "pass", "time_to_working_s": 459.343339400948, "total_s": 487.3567109107971, "steps": [ "cd && pwd && ls -la && id -u && python3 --version && cat README.md 2>/dev/null | head -c 6000", "cd && tail -c +6000 README.md | head -c 7000", "cd && cat install.sh; cat pyproject.toml; ls .coldpass dhp scripts tests demo daily; cat .coldpass/* 2>/dev/null | head -c 2000", "cd && grep -n -i \"mcp\\|pytest\\|test\\|venv\\|pip install\\|--root\\|cycle\\|cron\\|daily\" README.md | head -80", "cd && sed -n 340,370p README.md; sed -n 410,425p README.md", "cd && python3 -m venv 2>&1 | tail -3; ls 2>/dev/null | head", "cd && -m pip install -q -e \".[dev]\" 2>&1 | tail -15; echo EXIT=$?; ls | grep dhp", "cd && timeout 900 -m pytest tests/ -q 2>&1 | tail -8; echo; timeout 300 2>&1 | tail -15; echo EXIT=$?", "cd && timeout 300 -m pytest tests/test_adversarial.py::test_kill9_during_writes -q 2>&1 | grep -v Warning | grep -E \"Error|error|assert|FAILED|passed|failed|sqlite\" | head -20", "cd && sed -n 95,130p tests/test_adversarial.py", "cd && grep -n \"sqlite3\\\"\\|\\.sqlite\\|dhp.db\\|\\.db\\\"\" dhp/store.py | head; ls 2>&1 | head -1", "cd && -c \"import sys; sys.path.insert(0, ''); import dhp; from tests.conftest import SCHEMA; print('imports ok')\" 2>&1 | tail -3", "cd && grep -n \"def dhp_\\\\\\|def _tool\\|name=\" dhp/mcp_server.py | head -60", "cd && sed -n 40,100p dhp/mcp_server.py; sed -n 180,192p dhp/mcp_server.py", "mkdir -p && cd && ( printf '%s\\n' '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"initialize\",\"params\":{\"protocolVersion\":\"2025-06-18\",\"capabilities\":{},\"clientInfo\":{\"name\":\"t\",\"version\":\"1\"}}}' '{\"jsonrpc\":\"2.0\",\"method\":\"notifications/initialized\"}' '{\"jsonrpc\":\"2.0\",\"id\":2,\"method\":\"tools/call\",\"params\":{\"name\":\"dhp_dispatch\",\"arguments\":{\"task_kind\":\"demo.count\",\"inputs\":{\"target\":50},\"output_schema\":{\"type\":\"object\"}}}}' ; sleep 2 ) | timeout 60 --root 2> | tail -c 1500; echo; echo EXIT=$?; tail -5 ", "mkdir -p && cd && cat > probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"\",\"--root\",\"\"],\"cwd\":\"\",\"tool\":\"dhp_dispatch\",\"arguments\":{\"task_kind\":\"demo.count\",\"inputs\":{\"target\":50},\"output_schema\":{\"type\":\"object\"}},\"expected_text\":\"cf7ec797ce52cd7b650b090180a804f28ac7cc63864c3c578c3aa2c947f314bf\",\"env\":{}}\nEOF\ncat > claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The MCP server is started with dhp-mcp --root and dispatching work returns a handoff ID\",\"source\":\"run `dhp-mcp --root ` and point any MCP client at it.\",\"input\":\"task_kind demo.count, inputs target 50\",\"expected\":\"ok true with handoff_id cf7ec797ce52cd7b650b090180a804f28ac7cc63864c3c578c3aa2c947f314bf\",\"probe_kind\":\"mcp\",\"argv\":[\"\",\"--root\",\"\"],\"tool\":\"dhp_dispatch\",\"arguments\":{\"task_kind\":\"demo.count\",\"inputs\":{\"target\":50},\"output_schema\":{\"type\":\"object\"}},\"expected_text\":\"cf7ec797ce52cd7b650b090180a804f28ac7cc63864c3c578c3aa2c947f314bf\",\"env\":{},\"cwd\":\"\"}]\nEOF\npython3 -m json.tool probe.json >/dev/null && python3 -m json.tool claims.json >/dev/null && echo OK; grep -n \"run \\`dhp-mcp --root \\` and point any MCP client at it.\" ", "cd && timeout 240 demo/run_mad_demo.py > 2>&1; echo EXIT=$?; tail -25 ", "cd && sed -n 30,50p demo/run_mad_demo.py; grep -n \"home/hatch\" -r demo dhp scripts tests | head; grep -n \"__file__\\|BASE\\|ROOT\" demo/run_mad_demo.py | head", "cd && cat dhp/supervisor3_watch.py | head -60; echo ----; cat scripts/daily_loop.sh | head -30; echo ----; grep -rn \"schedule\\|cron\" .github | head -5", "cd && timeout 60 sup1 2 2>; echo EXIT=$?; tail -3 ; ls 2>&1", "cd && grep -n \"def watch\" -A 12 dhp/supervisor3.py; grep -n \"scan_s\\|SCAN_S\" dhp/config.py dhp/supervisor3.py | head -5", "rm -rf && cd && cat > cycles.json <<'EOF'\n{\"detected\":true,\"checks\":[{\"claim\":\"The supervisor runs a periodic lease scan loop until its duration elapses\",\"source\":\"dhp/supervisor3.py\",\"quote\":\"while time.time() < end and not self._stop.is_set():\",\"schedule\":\"scan every supervisor_scan_s (default 1.0s) for the duration given on the command line\",\"method\":\"run-once: dhp-supervisor with a 2 second duration (manual trigger, no source edits)\",\"input\":\"root , supervisor id sup1, 2 seconds\",\"expected\":\"two scans run, leader elected, JSON summary printed\",\"kind\":\"cli\",\"argv\":[\"\",\"\",\"sup1\",\"2\"],\"cwd\":\"\",\"expected_text\":\"\\\"was_leader\\\": true\"}]}\nEOF\ncat > examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Run the conformance suite (README CONTRIBUTING: dhp-conform reports 10/10)\",\"source\":\"README.md Contributing section\",\"input\":\"no arguments\",\"expected\":\"10 passed, 0 failed\",\"argv\":[\"\"],\"cwd\":\"\",\"env\":{},\"expected_text\":\"10 passed, 0 failed\"},{\"kind\":\"example\",\"claim\":\"Run the pytest suite documented in README Contributing; one test deselected because it hardcodes a missing author path and fails here\",\"source\":\"README.md Contributing section\",\"input\":\"tests/ -q with --deselect of test_kill9_during_writes\",\"expected\":\"all other tests pass\",\"argv\":[\"\",\"-m\",\"pytest\",\"tests/\",\"-q\",\"--deselect\",\"tests/test_adversarial.py::test_kill9_during_writes\"],\"cwd\":\"\",\"env\":{},\"expected_text\":\"passed\"}]\nEOF\npython3 -m json.tool cycles.json >/dev/null && python3 -m json.tool examples.json >/dev/null && echo OK; grep -n \"while time.time() < end and not self._stop.is_set():\" ; grep -n \"dhp-conform # 10/10\" ", "cd && = timeout 900 python3 -I --validate --replay 2>&1 | tail -60; echo EXIT=$?", "cd && timeout 300 -m pytest tests/ -q -p no:warnings --deselect tests/test_adversarial.py::test_kill9_during_writes 2>&1 | tail -6; echo EXIT=$?; grep -n \"accept\" dhp/net.py | head -3", "cd && cat > probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"\",\"--root\",\"\"],\"cwd\":\"\",\"tool\":\"dhp_dispatch\",\"arguments\":{\"task_kind\":\"demo.count\",\"inputs\":{\"target\":50},\"output_schema\":{\"type\":\"object\"}},\"expected_text\":\"\\\"ok\\\": true\",\"env\":{}}\nEOF\ncat > claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The MCP server is started with dhp-mcp --root and dispatching work returns a handoff ID\",\"source\":\"run `dhp-mcp --root ` and point any MCP client at it.\",\"input\":\"task_kind demo.count, inputs target 50\",\"expected\":\"ok true with a handoff_id\",\"probe_kind\":\"mcp\",\"argv\":[\"\",\"--root\",\"\"],\"tool\":\"dhp_dispatch\",\"arguments\":{\"task_kind\":\"demo.count\",\"inputs\":{\"target\":50},\"output_schema\":{\"type\":\"object\"}},\"expected_text\":\"\\\"ok\\\": true\",\"env\":{},\"cwd\":\"\"}]\nEOF\ncat > examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Run the conformance suite (README Contributing: dhp-conform reports 10/10)\",\"source\":\"README.md Contributing section\",\"input\":\"no arguments\",\"expected\":\"10 passed, 0 failed\",\"argv\":[\"\"],\"cwd\":\"\",\"env\":{},\"expected_text\":\"10 passed, 0 failed\"},{\"kind\":\"example\",\"claim\":\"Run the pytest suite documented in README Contributing; warnings plugin disabled and the test that hardcodes a missing author path deselected\",\"source\":\"README.md Contributing section\",\"input\":\"tests/ -q, -p no:warnings, deselect test_kill9_during_writes\",\"expected\":\"59 passed, 1 deselected\",\"argv\":[\"\",\"-m\",\"pytest\",\"tests/\",\"-q\",\"-p\",\"no:warnings\",\"--deselect\",\"tests/test_adversarial.py::test_kill9_during_writes\"],\"cwd\":\"\",\"env\":{},\"expected_text\":\"59 passed, 1 deselected\"}]\nEOF\nfor f in probe claims examples cycles; do python3 -m json.tool $f.json >/dev/null && echo \"$f ok\"; done; rm -rf ", "cd && = timeout 900 python3 -I --validate --replay > 2>&1; echo EXIT=$?; python3 -c \"\nimport json,sys\nd=json.load(open(''))\nprint('valid:',d.get('valid'))\nfor p in d.get('problems',[]): print('PROBLEM:',str(p)[:600])\n\" 2>&1 | head -40", "grep -n \"did not confirm\" -B 25 | head -80", "cd && ( printf '%s\\n' '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"initialize\",\"params\":{\"protocolVersion\":\"2025-06-18\",\"capabilities\":{},\"clientInfo\":{\"name\":\"t\",\"version\":\"1\"}}}' '{\"jsonrpc\":\"2.0\",\"method\":\"notifications/initialized\"}' '{\"jsonrpc\":\"2.0\",\"id\":2,\"method\":\"tools/call\",\"params\":{\"name\":\"dhp_status\",\"arguments\":{\"handoff_id\":\"not-a-handoff\"}}}' ; sleep 1 ) | timeout 60 --root 2>/dev/null | tail -1; rm -rf ", "cd && ( printf '%s\\n' '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"initialize\",\"params\":{\"protocolVersion\":\"2025-06-18\",\"capabilities\":{},\"clientInfo\":{\"name\":\"t\",\"version\":\"1\"}}}' '{\"jsonrpc\":\"2.0\",\"method\":\"notifications/initialized\"}' '{\"jsonrpc\":\"2.0\",\"id\":2,\"method\":\"tools/call\",\"params\":{\"name\":\"dhp_status\",\"arguments\":{\"handoff_id\":\"not-a-handoff\"}}}' ; sleep 3 ) | timeout 60 --root 2> | tail -n 2 | cut -c1-600; echo; tail -3 ; rm -rf ", "cd && cat > probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"\",\"--root\",\"\"],\"cwd\":\"\",\"tool\":\"dhp_status\",\"arguments\":{\"handoff_id\":\"not-a-handoff\"},\"expected_text\":\"malformed handoff_id (want 64 lowercase hex chars)\",\"env\":{}}\nEOF\ncat > claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The MCP server is started with dhp-mcp --root and rejects a malformed handoff ID\",\"source\":\"run `dhp-mcp --root ` and point any MCP client at it.\",\"input\":\"handoff_id not-a-handoff\",\"expected\":\"ValidationError: malformed handoff_id (want 64 lowercase hex chars)\",\"probe_kind\":\"mcp\",\"argv\":[\"\",\"--root\",\"\"],\"tool\":\"dhp_status\",\"arguments\":{\"handoff_id\":\"not-a-handoff\"},\"expected_text\":\"malformed handoff_id (want 64 lowercase hex chars)\",\"env\":{},\"cwd\":\"\"}]\nEOF\nfor f in probe claims; do python3 -m json.tool $f.json >/dev/null && echo \"$f ok\"; done; ls ", "rm -rf && cd && = timeout 900 python3 -I --validate --replay > 2>&1; echo EXIT=$?; python3 -c \"\nimport json\nd=json.load(open(''))\nprint('valid:',d.get('valid'))\nfor p in d.get('problems',[]): print('PROBLEM:',str(p)[:700])\n\" 2>&1 | head -30", "pgrep -af \"dhp-mcp|dhp-supervisor|run_mad_demo|transport\" || echo \"no dhp processes\"; rm -rf /tmp/dhp-mad-demo; ls ; ls ", "cd && cat > report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":\"repo\",\"operation\":\"Start the DHP MCP server (dhp-mcp --root ) and dispatch/validate durable work through its tools\",\"operation_scope\":\"Linux Ubuntu 24.04 guest, Python 3.12.3 in a venv at , pip install -e \\\".[dev]\\\" from the pinned checkout. Local stdio MCP only. Kill demo and network chaos not run (need author-specific paths and internet). A successful dhp_dispatch was observed by hand (handoff id returned with ok true); replay checks a malformed-id rejection because the handoff id contains a nonce and changes every run.\",\"steps\":[\"python3 -m venv \",\" -m pip install -q -e \\\".[dev]\\\"\",\" -m pytest tests/ -q -p no:warnings --deselect tests/test_adversarial.py::test_kill9_during_writes (59 passed, 1 deselected)\",\" (10 passed, 0 failed)\",\" --root (stdio JSON-RPC: tools/call dhp_dispatch -> ok true, handoff_id returned; tools/call dhp_status with malformed id -> ValidationError)\",\" sup1 2 (two scans, leader elected, 0 actions)\"],\"deviations\":[\"Used a venv because Ubuntu 24.04 blocks system-wide pip (PEP 668); README-required Python >=3.10 is satisfied by 3.12.3.\",\"pip install -e \\\".[dev]\\\" created build metadata inside the checkout (egg-info); no product source was edited.\",\"tests/test_adversarial.py::test_kill9_during_writes fails on this VM: the subprocess script hardcodes and the test kills the child after a fixed 0.4s sleep, so the DB file was not created before sqlite3.connect (OperationalError). Deselected for the documented pytest example; not fixed in product source.\",\"Pytest output includes an unhandled thread exception: OSError Bad file descriptor from TransportServer's accept loop (dhp/net.py line 177) during teardown. Suppressed in the replayed example with -p no:warnings; the run itself passed 59 tests. This is a real issue in the repo to investigate.\",\"README test count is stale: it says 45 passed; the suite now has 60 tests (59 pass here).\",\"demo/run_mad_demo.py could not run: it opens (FileNotFoundError). Not worked around; the path is not created in the guest. scripts/daily_loop.sh has the same hardcoded path and is the author's cron/git-push script, not a product cycle.\",\"The README's MCP promise was verified with dhp_status rejecting a malformed handoff ID rather than with dhp_dispatch's returned handoff ID, because the ID is nonce-based and changes every run; the checker cannot match a random value. The successful dispatch was observed manually with ok true.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":\"Remove hardcoded author paths () from demo/run_mad_demo.py, demo/net_chaos.py, demo/crawl_worker.py and tests/test_adversarial.py (use paths relative to the repo or tempdirs); make the kill-9 test wait for the DB file instead of a fixed sleep; close the TransportServer accept socket cleanly on shutdown so no thread exception is raised; update the README test count.\"}\nEOF\npython3 -m json.tool report.json >/dev/null && echo report-ok; cd && = timeout 900 python3 -I --validate --replay > 2>&1; echo EXIT=$?; python3 -c \"\nimport json; d=json.load(open('')); print('valid:',d.get('valid')); [print('PROBLEM:',str(p)[:400]) for p in d.get('problems',[])]\"; rm -rf " ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Start the DHP MCP server (dhp-mcp --root ) and dispatch/validate durable work through its tools", "suggested_fix": null, "tokens_in": 1143473, "tokens_out": 25179, "cost_usd": 0.03599979000000001, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "", "--root", "" ], "kind": "mcp", "serverInfo": { "name": "dhp", "version": "" }, "tools": [ "dhp_dispatch", "dhp_claim", "dhp_checkpoint", "dhp_heartbeat", "dhp_complete", "dhp_recover", "dhp_status", "dhp_last_checkpoint", "dhp_health", "dhp_record_effect", "dhp_effect_done", "dhp_note_spend", "dhp_note_activity", "dhp_request_approval", "dhp_approval_status", "dhp_approve", "dhp_deny", "dhp_require_capability" ], "tool_schema_bytes": 9441, "tool_result": { "content": [ { "text": "{\"ok\": false, \"error\": \"malformed handoff_id (want 64 lowercase hex chars)\", \"code\": \"ValidationError\"}", "type": "text" } ], "isError": false, "structuredContent": { "result": "{\"ok\": false, \"error\": \"malformed handoff_id (want 64 lowercase hex chars)\", \"code\": \"ValidationError\"}" } }, "tool_result_checked": true, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 1 download and execute, 2 known vulnerability.", "expected": "Reviewed as expected for a test run: attempted writes that failed, so nothing was written.", "findings": [ { "kind": "download-and-execute", "count": 1, "note": "Source contains download and execute; review its purpose.", "location_count": 1, "path": "install.sh" }, { "kind": "known-vulnerability", "count": 2, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 1, "path": "certifi" } ], "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=SIDDARTHAREDDY8--dhp-claude-haiku-5-5-1792969046672538328", "evidence_file": "/data/safety/SIDDARTHAREDDY8--dhp-claude-haiku-5-5-1792969046672538328.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": 33, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "b36e78ee427f0df4af9b74d66bd3ebee1aa51c6b", "url": "https://github.com/SIDDARTHAREDDY8/dhp" }, "purpose": "initial", "profile": { "model": "claude-haiku-5-5", "reasoning": "low" }, "fault": { "owner": "repo", "status": "diagnosed", "reason": null }, "fix_id": null, "verifies_run_id": null, "hosting": null, "operation_scope": "product operation", "tool_calls": 33, "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": "local", "needs": [], "needs_which": null, "agent_interface": [ "mcp" ], "license": "MIT", "repo_url": "https://github.com/SIDDARTHAREDDY8/dhp", "cost_to_try": "free", "hardware": null, "what_failed": null, "local_or_hosted": "local", "cycle_checks": [ { "kind": "cycle", "claim": "The supervisor runs a periodic lease scan loop until its duration elapses", "source": "dhp/supervisor3.py", "input": "root , supervisor id sup1, 2 seconds", "expected": "two scans run, leader elected, JSON summary printed", "command": " sup1 2", "schedule": "scan every supervisor_scan_s (default 1.0s) for the duration given on the command line", "method": "run-once: dhp-supervisor with a 2 second duration (manual trigger, no source edits)", "verdict": "yes", "outcome": "Triggered one cycle by hand (run-once: dhp-supervisor with a 2 second duration (manual trigger, no source edits); normal trigger: scan every supervisor_scan_s (default 1.0s) for the duration given on the command line): {\n \"supervisor\": \"sup1\",\n \"was_leader\": true,\n \"actions\": [],\n \"metrics\": {\n \"scans\": 2,\n \"orphans\": 0,\n \"dlq\": 0,\n \"leadership_changes\": 1,\n \"errors\": 0,\n \"uptime_s\": 2.0\n }\n}\n2026-10-25 23:05:00,684 INFO [dhp] store: initialized schema v3 at \n2026-10-25 23:05:00,685 INFO [dhp] supervisor sup1: watching (scan every 1.0s)\n2026-10-25 23:05:00,688 INFO [dhp] supervisor sup1: became leader\n2026-10-25 23:05:02,694 INFO [dhp] supervisor sup1: stopped (0 actions)", "evidence": "{\n \"supervisor\": \"sup1\",\n \"was_leader\": true,\n \"actions\": [],\n \"metrics\": {\n \"scans\": 2,\n \"orphans\": 0,\n \"dlq\": 0,\n \"leadership_changes\": 1,\n \"errors\": 0,\n \"uptime_s\": 2.0\n }\n}\n2026-10-25 23:05:00,684 INFO [dhp] store: initialized schema v3 at \n2026-10-25 23:05:00,685 INFO [dhp] supervisor sup1: watching (scan every 1.0s)\n2026-10-25 23:05:00,688 INFO [dhp] supervisor sup1: became leader\n2026-10-25 23:05:02,694 INFO [dhp] supervisor sup1: stopped (0 actions)", "returncode": 0 } ], "claims": [ { "kind": "claim", "claim": "The MCP server is started with dhp-mcp --root and rejects a malformed handoff ID", "source": "run `dhp-mcp --root ` and point any MCP client at it.", "input": "{\"tool\": \"dhp_status\", \"arguments\": {\"handoff_id\": \"not-a-handoff\"}}", "expected": "ValidationError: malformed handoff_id (want 64 lowercase hex chars)", "command": " --root tools/call {\"tool\": \"dhp_status\", \"arguments\": {\"handoff_id\": \"not-a-handoff\"}}", "verdict": "yes", "outcome": "Real input produced the expected result: malformed handoff_id (want 64 lowercase hex chars)", "evidence": "malformed handoff_id (want 64 lowercase hex chars)\\\", \\\"code\\\": \\\"ValidationError\\\"}\", \"type\": \"text\"}], \"isError\": false, \"structuredContent\": {\"result\": \"{\\\"ok\\\": false, \\\"error\\\": \\\"malformed handoff_id (want 64 lowercase hex chars)\\\", \\\"code\\\": \\\"ValidationError\\\"}\"}}", "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Run the conformance suite (README Contributing: dhp-conform reports 10/10)", "source": "README.md Contributing section", "input": "no arguments", "command": "", "evidence": "nformance suite (v0.4):\n PASS no-lost-results\n PASS no-crossed-inputs\n PASS no-untyped-results\n PASS no-silent-budget-overrun\n PASS no-runner-lock-in\n PASS exactly-one-wins\n PASS fencing\n PASS leader-election\n PASS transport\n PASS dead-letter-queue\n\n10 passed, 0 failed\ncomplete aed2c1c311af: schema failure \u2192 DLQ: result violates output_schema: 'x' is a required property\n\nFailed validating 'required' in schema:\n {'type': 'object',\n 'properties': {'x': {'type': 'integer'}},\n 'required': ['x']}\n\nOn instance:\n {'wrong': 'shape'}\norphan dc32c4cbf057: DLQ (attempt 1 >= max 1)", "deferred": false, "expected": "10 passed, 0 failed", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Run the pytest suite documented in README Contributing; warnings plugin disabled and the test that hardcodes a missing author path deselected", "source": "README.md Contributing section", "input": "tests/ -q, -p no:warnings, deselect test_kill9_during_writes", "command": " -m pytest tests/ -q -p no:warnings --deselect tests/test_adversarial.py::test_kill9_during_writes", "evidence": "........................................................... [100%]\n59 passed, 1 deselected in 22.64s", "deferred": false, "expected": "59 passed, 1 deselected", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "last_commit_at": "2026-10-12T10:19:29Z", "commits_90d": 27, "merged_prs_90d": 1, "open_issues": 0, "open_prs": 4, "reply_share": null, "reply_threads": 0, "median_reply_hours": null, "last_release_at": "2026-10-12T03:39:56Z", "archived": false, "verdict": "maintained", "note": "actively maintained: last commit 13 days ago; 27 commits and 1 merged PRs in 90 days; 0 open issues, 4 open PRs; latest release 2026-10-12" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 13 days ago; 27 commits and 1 merged PRs in 90 days; 0 open issues, 4 open PRs; latest release 2026-10-12", "maintained": "active", "maintained_note": "last commit 1 days ago", "last_commit_at": "2026-10-24T03:23:34Z", "last_release_at": "2026-10-12T03:39:56Z", "open_issues": null, "answered_issues": null, "platforms_claimed": [ "linux" ], "topic": "mcp-server", "agent_interfaces": [ { "interface": "mcp", "evidence": "independent checker", "observed": true, "operation_checked": true }, { "interface": "cli", "evidence": "README metadata", "observed": false, "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": { "tool_count": 18, "schema_bytes": 9441, "tokens_approx": 2361, "estimate_method": "ceil(compact UTF-8 tools/list JSON bytes / 4)", "scope": "returned tools/list page only; excludes client framing and tool results" }, "tested_at": "2026-10-25T23:05:34.029279+00:00", "tested_commit": "b36e78ee427f0df4af9b74d66bd3ebee1aa51c6b", "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": "SIDDARTHAREDDY8/dhp", "source": "https://github.com/SIDDARTHAREDDY8/dhp", "commit": "b36e78ee427f0df4af9b74d66bd3ebee1aa51c6b", "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": "b36e78ee427f0df4af9b74d66bd3ebee1aa51c6b", "url": "https://github.com/SIDDARTHAREDDY8/dhp" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": null, "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Start the DHP MCP server (dhp-mcp --root ) and dispatch/validate durable work through its tools", "operation_scope": "product operation", "hosting": null, "kind": "mcp", "test_version": "readme-ca496ea10bb07418d1d8f1c256c2433a55547acc0fb62d8b6d86ae33c976fbfa", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": "/transcripts/SIDDARTHAREDDY8--dhp-claude-haiku-5-5-1792969046672538328.txt", "report_url": "/reports/SIDDARTHAREDDY8--dhp-claude-haiku-5-5-1792969046672538328.json" }