{ "run_id": "DevMortimer--pi-warden-claude-haiku-5-5-1792790022051680158", "date": "2026-10-23T22:25:11.925820+00:00", "repo": "DevMortimer/pi-warden", "kind": "repo", "source": "https://github.com/DevMortimer/pi-warden", "commit": "f22c15187766e8cd9bfa164625c8225f21e39e77", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "test_version": "readme-bdc1b9b3c0d2673aef87e076d14084a8123ddcf09d520c1ee2e364a37c3f4bb9", "pass": true, "outcome": "pass", "time_to_working_s": 4155.9555054710945, "total_s": 4289.8741092681885, "steps": [ "cd && pwd && ls -la && id -u && python3 --version && cat README.md 2>/dev/null | head -200", "cd && git status 2>&1 | head -3; ls -la ; ls /inputs 2>&1", "cd && which node npm git uv 2>&1; node --version 2>&1; npm --version 2>&1; git --version; sed -n 1,200p package.json; ls -la .coldpass; ls ", "cd && git init -q && git remote add origin https://github.com/DevMortimer/pi-warden && (git fetch --depth 1 origin f22c15187766e8cd9bfa164625c8225f21e39e77 2>&1 | tail -5) && git reset --mixed FETCH_HEAD 2>&1 | tail -3 && git log --oneline -1 && git status --short | head -20; sudo -n true && echo SUDO_OK; cat /etc/os-release | head -2", "export NODE_USE_ENV_PROXY=1; (curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - ) 2>&1 | tail -5; sudo apt-get install -y nodejs 2>&1 | tail -3; node --version; npm --version", "cd && export NODE_USE_ENV_PROXY=1 && npm install 2>&1 | tail -15; echo \"EXIT=$?\"", "cd && export NODE_USE_ENV_PROXY=1 && npm run check 2>&1 | tail -40; echo \"EXIT=${PIPESTATUS[0]}\"", "mkdir -p && cd && export NODE_USE_ENV_PROXY=1 && npm run typecheck > 2>&1; echo TYPECHECK=$?; npm run build > 2>&1; echo BUILD=$?; ls dist | head; timeout 1500 npm test > 2>&1; echo TEST=$?; grep -n \"^not ok\\|^ not ok\\|^ not ok\" | head -40", "cd && sed -n 4750,4775p test.log; echo ----; sed -n 6183,6200p test.log; echo ----; sed -n 6262,6290p test.log; echo ----; sed -n 9908,9925p test.log; echo ---; sed -n 10174,10190p test.log", "cd && echo HOME=$HOME TMPDIR=$TMPDIR USER=$USER; cat tests/setup-env.ts | head -40; echo ----; grep -n \"HOME\\|homedir\\|tmpdir\" src/*.ts | head -30; echo; bash --version | head -1; ls -l /bin/sh", "cd && PWHOME=$(getent passwd $(id -u) | cut -d: -f6); echo PWHOME=$PWHOME; ls -ld \"$PWHOME\" 2>&1; export NODE_USE_ENV_PROXY=1; HOME=\"$PWHOME\" timeout 1500 npm test > 2>&1; echo TEST=$?; grep -n \"^# pass\\|^# fail\" ; grep -n \"^not ok\" | head -30", "cd && sed -n 5694,5712p test2.log; echo ----; sed -n 7769,7800p test2.log", "cd && which make; make --version 2>&1 | head -1; export NODE_USE_ENV_PROXY=1; HOME= node --import tsx --import ./tests/setup-env.ts --test tests/judge-input.test.ts 2>&1 | grep -E \"^# (pass|fail)|^not ok\" ; HOME= node --import tsx --import ./tests/setup-env.ts --test tests/extension.test.ts 2>&1 | grep -E \"^# (pass|fail)|^not ok\"; grep -n \"indented make\" tests/judge-input.test.ts | head", "cd && sudo apt-get install -y make > 2>&1; echo APT=$?; make --version | head -1; export NODE_USE_ENV_PROXY=1; HOME= timeout 1500 npm test > 2>&1; echo TEST=$?; grep -E \"^# (tests|pass|fail)\" ; grep -n \"^not ok\" | head", "cd && sed -n 5391,5405p test3.log; cd && export NODE_USE_ENV_PROXY=1; for i in 1 2; do HOME= node --import tsx --import ./tests/setup-env.ts --test tests/extension.test.ts 2>&1 | grep -E \"^# (pass|fail)|^not ok\"; done", "cd && ls docs examples scripts extensions; echo ----; sed -n 1,80p docs/commands.md; echo ----; cat scripts/dev-pi.mjs | head -60; ls node_modules/.bin | grep -i \"^pi\" ", "cd && ./node_modules/.bin/pi --version 2>&1 | tail -2; ./node_modules/.bin/pi --help 2>&1 | head -60", "export NODE_USE_ENV_PROXY=1; (sudo npm install -g @earendil-works/pi-coding-agent@0.87.0 2>&1 | tail -3); echo NPMG=$?; which pi && pi --version; npm view pi-warden version 2>&1 | tail -2", "export NODE_USE_ENV_PROXY=1; cd /tmp && timeout 600 pi install npm:pi-warden 2>&1 | tail -15; echo INSTALL=$?; pi list 2>&1 | tail -5", "mkdir -p && cd && timeout 120 pi -p --no-session --offline \"/warden status\" 2>&1 | head -40; echo EXIT=${PIPESTATUS[0]}", "cd && cp ./pi-warden.md && (printf '%s\\n' '{\"id\":\"1\",\"type\":\"prompt\",\"message\":\"/warden rules\"}' ; sleep 20) | timeout 60 pi --mode rpc --no-session --offline 2>&1 | head -c 3000; echo; echo EXIT=${PIPESTATUS[1]}", "cd && printf '%s\\n' '{\"id\":\"1\",\"type\":\"prompt\",\"message\":\"/warden rules\"}' > && timeout 60 pi --no-extensions -e --mode rpc --no-session --offline < > 2>; echo EXIT=$?; grep -o 'Rules in force[^\"]*' | head -c 400; echo; cat | head -5; grep -c . ", "cd && printf '%s\\n' '{\"id\":\"1\",\"type\":\"prompt\",\"message\":\"/warden test\"}' > && timeout 90 pi --no-extensions -e --mode rpc --no-session --offline < > 2>; echo EXIT=$?; grep -o '\"message\\\\\\?\":\"[^}]*' | head -c 1500; echo; head -c 400 ", "cd && sed -n 1,40p examples/README.md; echo ----; grep -n -i \"cron\\|--once\\|--now\\|webhook\\|setInterval\\|schedule\" README.md docs/*.md | head; echo ----; grep -n \"setInterval\\|setTimeout\\|cron\" src/*.ts extensions/index.js | head -20; echo ----; grep -c \"^# \" examples/pi-warden.md", "cd && mkdir -p .coldpass && cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"pi\",\"--no-extensions\",\"-e\",\"\",\"--mode\",\"rpc\",\"--no-session\",\"--offline\"],\"cwd\":\"\",\"stdin\":\"{\\\"id\\\":\\\"1\\\",\\\"type\\\":\\\"prompt\\\",\\\"message\\\":\\\"/warden rules\\\"}\\n\",\"expected_text\":\"Rules in force: pi-warden.md (12 rules, 0 dropped)\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[\n{\"kind\":\"claim\",\"claim\":\"Each # heading in pi-warden.md is one rule that the rules guard judges\",\"source\":\"Each `#` heading is one rule.\",\"input\":\"demo project with examples/pi-warden.md copied to pi-warden.md (12 headings)\",\"expected\":\"the rules listing reports 12 rules\",\"probe_kind\":\"cli\",\"argv\":[\"pi\",\"--no-extensions\",\"-e\",\"\",\"--mode\",\"rpc\",\"--no-session\",\"--offline\"],\"stdin\":\"{\\\"id\\\":\\\"1\\\",\\\"type\\\":\\\"prompt\\\",\\\"message\\\":\\\"/warden rules\\\"}\\n\",\"expected_text\":\"Rules in force: pi-warden.md (12 rules, 0 dropped)\",\"cwd\":\"\"},\n{\"kind\":\"claim\",\"claim\":\"Destructive patterns are held with no key and no request\",\"source\":\"Holds destructive patterns (force push, `reset --hard`, `rm -rf` on a path outside scratch, `DROP`) with no key and no request\",\"input\":\"/warden test with no TypeSafe key (synthetic rm -rf demo)\",\"expected\":\"the offline pattern check flags rm-recursive-dangerous-target\",\"probe_kind\":\"cli\",\"argv\":[\"pi\",\"--no-extensions\",\"-e\",\"\",\"--mode\",\"rpc\",\"--no-session\",\"--offline\"],\"stdin\":\"{\\\"id\\\":\\\"1\\\",\\\"type\\\":\\\"prompt\\\",\\\"message\\\":\\\"/warden test\\\"}\\n\",\"expected_text\":\"patterns: rm-recursive-dangerous-target\",\"cwd\":\"\"}\n]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[\n{\"kind\":\"example\",\"claim\":\"Copy pi-warden.md to the project root and /warden rules lists its rules\",\"source\":\"examples/README.md\",\"input\":\"examples/pi-warden.md copied to , then /warden rules over RPC\",\"expected\":\"12 rules listed from pi-warden.md\",\"argv\":[\"pi\",\"--no-extensions\",\"-e\",\"\",\"--mode\",\"rpc\",\"--no-session\",\"--offline\"],\"cwd\":\"\",\"stdin\":\"{\\\"id\\\":\\\"1\\\",\\\"type\\\":\\\"prompt\\\",\\\"message\\\":\\\"/warden rules\\\"}\\n\",\"expected_text\":\"Rules in force: pi-warden.md (12 rules\"},\n{\"kind\":\"example\",\"claim\":\"Type-check the TypeScript sources\",\"source\":\"README.md\",\"input\":\"npm run typecheck (Development section)\",\"expected\":\"tsc exits 0\",\"argv\":[\"npm\",\"run\",\"typecheck\"],\"cwd\":\"\",\"expected_text\":\"> pi-warden@2.0.0 typecheck\"},\n{\"kind\":\"example\",\"claim\":\"Run the offline test suite\",\"source\":\"README.md\",\"input\":\"npm test (Development section)\",\"expected\":\"offline tests pass\",\"deferred\":true,\"reason\":\"Deferred from the replay on purpose: full run is about 13 minutes and has timing-dependent tests that fail intermittently (1 to 24 failures across runs, each passing alone). Full result recorded in the report: 1735 of 1736 on the last run with HOME= and make installed.\"}\n]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Entry points inspected: extensions/index.js, src/extension.ts and the README/docs. pi-warden runs per Pi event (tool calls, prompts, turn ends) and has no cron, scheduler, --once/--now, loop or webhook trigger. The only setTimeout/setInterval uses are per-call timeouts and throttles, so there is no product cycle to trigger by hand.\",\"checks\":[]}\nEOF\nfor f in probe claims examples cycles; do python3 -I -m json.tool .coldpass/$f.json >/dev/null && echo \"$f ok\"; done", "cd && = python3 -I --validate --replay 2>&1 | tail -60; echo EXIT=${PIPESTATUS[0]}", "cd && cat > .coldpass/report.json <<'EOF'\n{\n \"outcome\": \"working\",\n \"fault_owner\": null,\n \"operation\": \"Run pi-warden (pinned commit f22c151) inside the Pi agent over RPC: /warden rules lists the rules from pi-warden.md, and /warden test runs the offline destructive-command check with no TypeSafe key.\",\n \"operation_scope\": \"Offline only. Needs Node >=22.19.0 (installed 22.23.4), the Pi CLI 0.87.0, and the checkout built with npm install and npm run build. No TypeSafe key, no browser, no Jev judgments. The Jev-judged rules guard, /warden enable, and the agent-driven commands (/warden improve, /warden audit) were not exercised.\",\n \"steps\": [\n \"git init; git remote add origin https://github.com/DevMortimer/pi-warden; git fetch --depth 1 origin f22c15187766e8cd9bfa164625c8225f21e39e77; git reset --mixed FETCH_HEAD\",\n \"curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -; sudo apt-get install -y nodejs (Node v22.23.4, npm 10.9.9)\",\n \"npm install (README Development section)\",\n \"npm run typecheck (exit 0)\",\n \"npm run build (exit 0, writes dist/)\",\n \"npm test (README Development section; see deviations for the environment fixes)\",\n \"sudo npm install -g @earendil-works/pi-coding-agent@0.87.0 (Pi CLI, devDependency version)\",\n \"pi install npm:pi-warden (README Install section; installed the published npm package)\",\n \"pi --no-extensions -e --mode rpc --no-session --offline, stdin JSON prompt '/warden rules' (returns 'Rules in force: pi-warden.md (12 rules, 0 dropped)')\",\n \"same command with stdin prompt '/warden test' (returns 'patterns: rm-recursive-dangerous-target', held in steer mode)\"\n ],\n \"deviations\": [\n \"Node was not installed in the guest (the README does not name it; package.json requires node >=22.19.0). Installed Node 22 via the NodeSource setup_22.x script, which is curl|sh with sudo, and apt. Ubuntu 24.04's default node is too old.\",\n \"The pi CLI was not on PATH. Installed it with sudo npm install -g @earendil-works/pi-coding-agent@0.87.0, matching the devDependency.\",\n \"First npm test: 24 failures. Cause is the guest, not the product: HOME was , which is under the temp root /tmp, so guard tests for ~/Library and $HOME/projects were treated as scratch and not held. Reran with HOME= (passwd home): 2 failures.\",\n \"One failure was test 1110 (judge-input), which needs the make command. make was missing; installed it with sudo apt-get install -y make.\",\n \"Remaining full-suite failures vary between runs (1 to 2 per run, e.g. tests 720 and 770). Each passes when its file runs alone (extension.test.ts 299/299 on two reruns). These look like timing-dependent tests under load. The last full run was 1735 of 1736 passing. npm run check was not re-run as one command after the fixes; typecheck and build were run separately and both exited 0.\",\n \"pi -p (print mode) returned nothing for /warden commands. The working route was --mode rpc with JSON prompts on stdin. The README documents these commands inside the Pi TUI, not RPC, so the RPC invocation is my substitute.\",\n \"pi install npm:pi-warden installed the published npm package, not the pinned checkout. The probes and claims load the pinned checkout with --no-extensions -e The npm registry reported the latest published version as 1.14.0, while the pinned package.json says 2.0.0; I did not investigate this further.\",\n \"The README's /warden enable and Jev-judged features need a TypeSafe key, which I did not have, so they were not run. The inline node -e snippet in examples/README.md was not run (inline code is not a probe).\",\n \"No browser was used and no servers were started, so none needed stopping.\"\n ],\n \"stuck_step\": null,\n \"main_blocker\": null,\n \"plain_failure\": null,\n \"suggested_fix\": \"None needed for the product. For the repo: the test suite should not depend on HOME sitting under /tmp, should document make as a prerequisite, and should fix the timing-dependent tests that fail intermittently under load.\"\n}\nEOF\npython3 -I -m json.tool .coldpass/report.json >/dev/null && echo REPORT_OK; ps aux | grep -E \"pi |pi-warden\" | grep -v grep | head -3; ls -la .coldpass", "cd && = python3 -I --validate --replay > 2>&1; echo EXIT=$?; python3 -I -c \"import json;d=json.load(open(''));print(d['valid'],d['problems'],d['replay']['status'])\" 2>&1 | tail -2; pgrep -fa \"rpc|pi-warden\" | grep -v pgrep | head -3; echo servers_checked" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Run pi-warden (pinned commit f22c151) inside the Pi agent over RPC: /warden rules lists the rules from pi-warden.md, and /warden test runs the offline destructive-command check with no TypeSafe key.", "suggested_fix": null, "tokens_in": 982582, "tokens_out": 23575, "cost_usd": 0.03355454000000001, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "pi", "--no-extensions", "-e", "", "--mode", "rpc", "--no-session", "--offline" ], "kind": "cli", "returncode": 0, "stdout": "{\"type\":\"extension_ui_request\",\"id\":\"0fcee715-9473-407c-bc7d-9e2850954b13\",\"method\":\"setWidget\",\"widgetKey\":\"pi-warden\"}\n{\"type\":\"extension_ui_request\",\"id\":\"f63524b9-46e8-4ae5-92b7-254d8718f152\",\"method\":\"notify\",\"message\":\"Rules in force: pi-warden.md (12 rules, 0 dropped)\\n1. no-console-output-in-library-code paths: src/**\\n2. todo-comments-need-a-reference paths: (all)\\n3. no-explicit-any paths: **/*.ts, **/*.tsx\\n4. exported-functions-declare-their-return-type paths: src/**/*.ts\\n5. errors-are-not-swallowed paths: (all)\\n6. switch-statements-have-a-default-case paths: (all)\\n7. no-hardcoded-secrets paths: (all)\\n8. boolean-names-read-as-a-question paths: (all)\\n9. new-exported-functions-get-a-test paths: src/**\\n10. comments-explain-why-not-what paths: (all)\\n11. no-commented-out-code paths: (all)\\n12. migrations-are-reversible paths: **/migrations/**\",\"notifyType\":\"info\"}\n{\"id\":\"1\",\"type\":\"response\",\"command\":\"prompt\",\"success\":true}", "stderr": "", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 1 hardcoded secret, 3 known vulnerability, 1 outside write. 58 static matches retained as context.", "expected": "Reviewed as expected for a test run: npm built the package inside its global install folder.", "findings": [ { "kind": "hardcoded-secret", "count": 1, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 1, "path": "scripts/rules-cases.mjs" }, { "kind": "known-vulnerability", "count": 3, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 1, "path": "brace-expansion" }, { "kind": "outside-write", "count": 1, "note": "Repository processes attempted these writes outside documented output/cache paths.", "location_count": 4, "process_count": 201 } ], "context": [ { "kind": "download-and-execute", "count": 2, "note": "Source contains download and execute; review its purpose.", "location_count": 1, "path": "tests/guard.test.ts" }, { "kind": "hardcoded-secret", "count": 52, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 17 } ], "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=DevMortimer--pi-warden-claude-haiku-5-5-1792790022051680158", "evidence_file": "/data/safety/DevMortimer--pi-warden-claude-haiku-5-5-1792790022051680158.json.gz" }, "agent_execution": "native_agent", "agent_runtime": "claude-code", "agent_runtime_version": "2.1.300 (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": 28, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "f22c15187766e8cd9bfa164625c8225f21e39e77", "url": "https://github.com/DevMortimer/pi-warden" }, "purpose": "initial", "profile": { "model": "claude-haiku-5-5", "reasoning": "low" }, "fault": { "owner": null, "status": "resolved", "reason": null }, "fix_id": null, "verifies_run_id": null, "hosting": null, "operation_scope": "product operation", "tool_calls": 28, "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": "MIT", "repo_url": "https://github.com/DevMortimer/pi-warden", "cost_to_try": "free", "hardware": null, "what_failed": null, "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": "Entry points inspected: extensions/index.js, src/extension.ts and the README/docs. pi-warden runs per Pi event (tool calls, prompts, turn ends) and has no cron, scheduler, --once/--now, loop or webhook trigger. The only setTimeout/setInterval uses are per-call timeouts and throttles, so there is no product cycle to trigger by hand.", "evidence": "Entry points inspected: extensions/index.js, src/extension.ts and the README/docs. pi-warden runs per Pi event (tool calls, prompts, turn ends) and has no cron, scheduler, --once/--now, loop or webhook trigger. The only setTimeout/setInterval uses are per-call timeouts and throttles, so there is no product cycle to trigger by hand.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Each # heading in pi-warden.md is one rule that the rules guard judges", "source": "Each `#` heading is one rule.", "input": "demo project with examples/pi-warden.md copied to pi-warden.md (12 headings)", "expected": "the rules listing reports 12 rules", "command": "pi --no-extensions -e --mode rpc --no-session --offline", "verdict": "yes", "outcome": "Real input produced the expected result: Rules in force: pi-warden.md (12 rules, 0 dropped)", "evidence": "Rules in force: pi-warden.md (12 rules, 0 dropped)\\n1. no-console-output-in-library-code paths: src/**\\n2. todo-comments-need-a-reference paths: (all)\\n3. no-explicit-any paths: **/*.ts, **/*.tsx\\n4. exported-functions-declare-their-return-type paths: src/**/*.ts\\n5. errors-are-not-swallowed paths: (all)\\n6. switch-statements-have-a-default-case paths: (all)\\n7. no-hardcoded-secrets paths: (all)\\n8. boolean-names-read-as-a-question paths: (all)\\n9. new-exported-functions-get-a-test paths: src/**\\n10. comments-explain-why-not-what paths: (all)\\n11. no-commented-out-code paths: (all)\\n12. migrat", "returncode": 0, "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "Destructive patterns are held with no key and no request", "source": "Holds destructive patterns (force push, `reset --hard`, `rm -rf` on a path outside scratch, `DROP`) with no key and no request", "input": "/warden test with no TypeSafe key (synthetic rm -rf demo)", "expected": "the offline pattern check flags rm-recursive-dangerous-target", "command": "pi --no-extensions -e --mode rpc --no-session --offline", "verdict": "yes", "outcome": "Real input produced the expected result: patterns: rm-recursive-dangerous-target", "evidence": "patterns: rm-recursive-dangerous-target \u00b7 confirm \u2014 destructive: recursive rm on an absolute, home, variable, or parent path (pattern checks only: TypeSafe judgments are not enabled or no key is configured)\",\"notifyType\":\"info\"}\n{\"type\":\"extension_ui_request\",\"id\":\"ad09dd56-ebd9-4d52-8d13-51b511d4eb09\",\"method\":\"notify\",\"message\":\"In steer mode a real call would be held and the agent would read: \\\"pi-warden held this bash call before it ran: destructive: recursive rm on an absolute, home, variable, or parent path. Do not retry it unchanged. Either (1) reach the goal with a recoverable alternat", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Copy pi-warden.md to the project root and /warden rules lists its rules", "source": "examples/README.md", "input": "examples/pi-warden.md copied to , then /warden rules over RPC", "command": "pi --no-extensions -e --mode rpc --no-session --offline", "evidence": "reference paths: (all)\\n3. no-explicit-any paths: **/*.ts, **/*.tsx\\n4. exported-functions-declare-their-return-type paths: src/**/*.ts\\n5. errors-are-not-swallowed paths: (all)\\n6. switch-statements-have-a-default-case paths: (all)\\n7. no-hardcoded-secrets paths: (all)\\n8. boolean-names-read-as-a-question paths: (all)\\n9. new-exported-functions-get-a-test paths: src/**\\n10. comments-explain-why-not-what paths: (all)\\n11. no-commented-out-code paths: (all)\\n12. migrations-are-reversible paths: **/migrations/**\",\"notifyType\":\"info\"}\n{\"id\":\"1\",\"type\":\"response\",\"command\":\"prompt\",\"success\":true}", "deferred": false, "expected": "12 rules listed from pi-warden.md", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Type-check the TypeScript sources", "source": "README.md", "input": "npm run typecheck (Development section)", "command": "npm run typecheck", "evidence": "> pi-warden@2.0.0 typecheck\n> tsc --noEmit", "deferred": false, "expected": "tsc exits 0", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Run the offline test suite", "source": "README.md", "input": "npm test (Development section)", "command": "", "evidence": "Deferred from the replay on purpose: full run is about 13 minutes and has timing-dependent tests that fail intermittently (1 to 24 failures across runs, each passing alone). Full result recorded in the report: 1735 of 1736 on the last run with HOME= and make installed.", "deferred": true, "expected": "offline tests pass", "verdict": "deferred", "outcome": "Deferred from the replay on purpose: full run is about 13 minutes and has timing-dependent tests that fail intermittently (1 to 24 failures across runs, each passing alone). Full result recorded in the report: 1735 of 1736 on the last run with HOME= and make installed." } ], "does_what_it_says": "yes", "maintenance": { "last_commit_at": "2026-10-23T07:49:32Z", "commits_90d": 243, "merged_prs_90d": 149, "open_issues": 5, "open_prs": 0, "reply_share": 0.71, "reply_threads": 14, "median_reply_hours": 6.5, "last_release_at": "2026-10-23T08:06:13Z", "archived": false, "verdict": "maintained", "note": "actively maintained: last commit 0 days ago; 243 commits and 149 merged PRs in 90 days; 5 open issues, 0 open PRs; 10 of 14 recent threads got a maintainer reply, median first reply 6.5h; latest release 2026-10-23" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 0 days ago; 243 commits and 149 merged PRs in 90 days; 5 open issues, 0 open PRs; 10 of 14 recent threads got a maintainer reply, median first reply 6.5h; latest release 2026-10-23", "maintained": "active", "maintained_note": "last commit 0 days ago; 1 open issues, 7 answered or closed", "last_commit_at": "2026-10-23T07:50:03Z", "last_release_at": "2026-10-23T08:06:13Z", "open_issues": 1, "answered_issues": 7, "platforms_claimed": [ "linux" ], "topic": "agent-harness", "agent_interfaces": [ { "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": "2026-10-23T22:25:11.925820+00:00", "tested_commit": "f22c15187766e8cd9bfa164625c8225f21e39e77", "tested_with": { "agent": "claude-code", "agent_version": "2.1.300 (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": "DevMortimer/pi-warden", "source": "https://github.com/DevMortimer/pi-warden", "commit": "f22c15187766e8cd9bfa164625c8225f21e39e77", "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": "2.1.300 (Claude Code)", "tool_transport": "mcp-assigned-vm", "runtime": null, "runtime_version": null, "runtime_revision": null, "sandbox_source": null, "guest_setup": null, "source_pin": { "commit": "f22c15187766e8cd9bfa164625c8225f21e39e77", "url": "https://github.com/DevMortimer/pi-warden" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": null, "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Run pi-warden (pinned commit f22c151) inside the Pi agent over RPC: /warden rules lists the rules from pi-warden.md, and /warden test runs the offline destructive-command check with no TypeSafe key.", "operation_scope": "product operation", "hosting": null, "kind": "repo", "test_version": "readme-bdc1b9b3c0d2673aef87e076d14084a8123ddcf09d520c1ee2e364a37c3f4bb9", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": null, "report_url": "/reports/DevMortimer--pi-warden-claude-haiku-5-5-1792790022051680158.json" }