{ "run_id": "intoapex--tas-guard-claude-haiku-5-5-1793207043866476983", "date": "2026-10-28T17:13:01.170318+00:00", "repo": "intoapex/tas-guard", "kind": "mcp", "source": "https://github.com/intoapex/tas-guard", "commit": "0a50a58fba9a4b5733d6502589ba9113998fe5b7", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "test_version": "readme-2d57868128a84902c09a58991c46c5fe288928e55b1de8282ab5003e13159c2f", "pass": true, "outcome": "pass", "time_to_working_s": 503.95257796900114, "total_s": 537.3037271499634, "steps": [ "cd && ls -la && git status 2>&1 | head -3; cat README.md 2>/dev/null | head -c 6000", "python3 --version; echo $CDP_URL; curl -sS -m 10 $CDP_URL/json/version; echo; echo EXIT=$?", "cd && grep -n '^#' README.md; cat package.json; ls src test profiles docs; node --version; npm --version", "cd && sed -n 93,140p README.md; sed -n 464,520p README.md", "cd && grep -n \"demo\\|command ===\\|case '\" src/cli.js | head -60; grep -n \"name:\" src/demo-broker.js | head -20; ls -la .coldpass", "cd && timeout 280 npm test 2>&1 | tail -25", "cd && npm link 2>&1 | tail -3; which tas-guard; tas-guard --help 2>&1 | head -12", "cd /tmp && export HOME=/tmp/tg-home && mkdir -p $HOME && printf '%s\\n' '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"initialize\",\"params\":{\"protocolVersion\":\"2025-06-18\",\"capabilities\":{},\"clientInfo\":{\"name\":\"t\",\"version\":\"1\"}}}' '{\"jsonrpc\":\"2.0\",\"method\":\"notifications/initialized\"}' '{\"jsonrpc\":\"2.0\",\"id\":2,\"method\":\"tools/call\",\"params\":{\"name\":\"get_stock_latest_quote\",\"arguments\":{\"symbol\":\"SPY\"}}}' | timeout 20 node demo 2>/tmp/tg-err.txt; echo EXIT=$?; cat /tmp/tg-err.txt | head -5", "cd && sed -n 14,16p src/demo-broker.js | cut -c1-600; grep -n \"tas_guard_status\" src/*.js | head -3", "cd /tmp && export HOME=/tmp/tg-home && 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\":\"place_stock_order\",\"arguments\":{\"symbol\":\"SPY\",\"side\":\"buy\",\"qty\":\"10\",\"type\":\"limit\",\"limit_price\":\"580\"}}}' '{\"jsonrpc\":\"2.0\",\"id\":3,\"method\":\"tools/call\",\"params\":{\"name\":\"place_stock_order\",\"arguments\":{\"symbol\":\"SPY\",\"side\":\"buy\",\"qty\":\"1\",\"type\":\"limit\",\"limit_price\":\"580\"}}}' | timeout 20 node demo 2>/dev/null | cut -c1-700", "cd && grep -n \"defaultStateDir\" -A4 src/state.js | head -12; sed -n 102,125p src/cli.js | cut -c1-300", "cd && grep -n -i \"setInterval\\|cron\\|--once\\|--now\\|poll\\|webhook\" src/*.js README.md | cut -c1-220 | head -20; sed -n 152,160p README.md | cut -c1-400", "mkdir -p && cat > <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"node\",\"src/cli.js\",\"demo\"],\"cwd\":\"\",\"env\":{\"TAS_GUARD_HOME\":\"/tmp/tg-state-probe\"},\"tool\":\"place_stock_order\",\"arguments\":{\"symbol\":\"SPY\",\"side\":\"buy\",\"qty\":\"1\",\"type\":\"limit\",\"limit_price\":\"580\"},\"expected_text\":\"accepted\"}\nEOF\ncat > <<'EOF'\n[\n{\"kind\":\"claim\",\"claim\":\"demo runs the guard in front of a built-in paper broker with simulated prices\",\"source\":\"`tas-guard demo` runs the guard in front of a built-in paper broker with simulated prices.\",\"input\":\"get_stock_latest_quote SPY\",\"expected\":\"simulated quote\",\"probe_kind\":\"mcp\",\"argv\":[\"node\",\"src/cli.js\",\"demo\"],\"tool\":\"get_stock_latest_quote\",\"arguments\":{\"symbol\":\"SPY\"},\"expected_text\":\"simulated\",\"cwd\":\"\",\"env\":{\"TAS_GUARD_HOME\":\"/tmp/tg-state-claim1\"}},\n{\"kind\":\"claim\",\"claim\":\"1 SPY at $580 is allowed\",\"source\":\"1 SPY at $580 (allowed)\",\"input\":\"place_stock_order qty 1 limit 580\",\"expected\":\"order accepted\",\"probe_kind\":\"mcp\",\"argv\":[\"node\",\"src/cli.js\",\"demo\"],\"tool\":\"place_stock_order\",\"arguments\":{\"symbol\":\"SPY\",\"side\":\"buy\",\"qty\":\"1\",\"type\":\"limit\",\"limit_price\":\"580\"},\"expected_text\":\"accepted\",\"cwd\":\"\",\"env\":{\"TAS_GUARD_HOME\":\"/tmp/tg-state-claim2\"}},\n{\"kind\":\"claim\",\"claim\":\"10 SPY is blocked over the per-order limit\",\"source\":\"10 SPY (blocked: over the $2,000 per-order limit)\",\"input\":\"place_stock_order qty 10 limit 580\",\"expected\":\"blocked by guard\",\"probe_kind\":\"mcp\",\"argv\":[\"node\",\"src/cli.js\",\"demo\"],\"tool\":\"place_stock_order\",\"arguments\":{\"symbol\":\"SPY\",\"side\":\"buy\",\"qty\":\"10\",\"type\":\"limit\",\"limit_price\":\"580\"},\"expected_text\":\"is over the per-order limit of 2,000\",\"cwd\":\"\",\"env\":{\"TAS_GUARD_HOME\":\"/tmp/tg-state-claim3\"}}\n]\nEOF\npython3 -I -c 'import json;json.load(open(\"\"));json.load(open(\"\"));print(\"ok\")'", "cd && export TAS_GUARD_HOME=/tmp/tg-state-ex && timeout 120 node src/cli.js sol-demo 2>&1 | tail -15; echo EXIT=${PIPESTATUS[0]}", "cd && cat > examples.json <<'EOF'\n[\n{\"kind\":\"example\",\"claim\":\"Solana mode demo runs seven agent transactions through the guard\",\"source\":\"README.md Solana mode / Try it: `npx tas-guard sol-demo`\",\"input\":\"sol-demo\",\"expected\":\"guard blocks drainer and over-limit transactions and reports hash chain intact\",\"argv\":[\"node\",\"src/cli.js\",\"sol-demo\"],\"cwd\":\"\",\"env\":{\"TAS_GUARD_HOME\":\"/tmp/tg-state-ex\"},\"expected_text\":\"hash chain intact\"},\n{\"kind\":\"example\",\"claim\":\"Repository offline test suite (README Development section)\",\"source\":\"README.md Development\",\"input\":\"npm test\",\"expected\":\"78 tests pass\",\"argv\":[\"npm\",\"test\"],\"cwd\":\"\",\"env\":{},\"expected_text\":\"# fail 0\"}\n]\nEOF\ncat > cycles.json <<'EOF'\n{\"detected\":false,\"checks\":[],\"reason\":\"Inspected README.md (Quick start, Try it, Phone approvals and kill switch) and src/cli.js, src/telegram.js, src/proxy.js. The only recurring loop is Telegram long-polling (src/telegram.js poll) that talks to an external Telegram Bot API; it cannot be triggered locally without external notifications, which are not allowed. No cron, --once, --now or webhook trigger exists in the product, so no manual cycle was run.\"}\nEOF\npython3 -I -c 'import json;[json.load(open(f)) for f in [\"examples.json\",\"cycles.json\"]];print(\"ok\")'", "cd && = timeout 900 python3 -I --validate --replay 2>&1 | tail -c 5000; echo EXIT=${PIPESTATUS[0]}", "cd && grep -n -i \"isError\\|is_error\" checker/check.py | head -20; grep -n \"def .*expected_text\\|expected_text\" checker/check.py | head -20", "cd && = timeout 900 python3 -I --validate --replay > /tmp/validate.out 2>&1; echo EXIT=$?; python3 -I -c '\nimport json,sys\nt=open(\"/tmp/validate.out\").read()\nprint(t[:1500])' ", "ls -la /tmp/tg-state-* /tmp/tg-home/.tas-guard/guards 2>&1 | head -30; grep -n \"per_minute\\|perMinute\\|minute\" | head; grep -n \"TAS_GUARD_HOME\\|env\" | head -20", "cd && sed -n 1108,1118p checker/check.py; sed -n 1160,1170p checker/check.py; ls -d /tmp/tg-state-* ; cat /tmp/tg-state-probe/audit.jsonl | cut -c1-160 | tail -5", "cd /tmp && 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\":\"tas_guard_status\",\"arguments\":{}}}' | TAS_GUARD_HOME=/tmp/tg-state-status timeout 20 node demo 2>/dev/null | tail -1 | cut -c1-1200", "cd /tmp && 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\":\"tas_guard_status\",\"arguments\":{}}}' | TAS_GUARD_HOME=/tmp/tg-state-status timeout 20 node demo > /tmp/st.out 2>/tmp/st.err; echo EXIT=$?; cut -c1-1500 /tmp/st.out; cat /tmp/st.err | head -5", "cd && cat > probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"node\",\"src/cli.js\",\"demo\"],\"cwd\":\"\",\"env\":{\"TAS_GUARD_HOME\":\"/tmp/tg-state-run2\"},\"tool\":\"place_stock_order\",\"arguments\":{\"symbol\":\"SPY\",\"side\":\"buy\",\"qty\":\"1\",\"type\":\"limit\",\"limit_price\":\"580\"},\"expected_text\":\"accepted\"}\nEOF\ncat > claims.json <<'EOF'\n[\n{\"kind\":\"claim\",\"claim\":\"demo runs the guard in front of a built-in paper broker with simulated prices\",\"source\":\"`tas-guard demo` runs the guard in front of a built-in paper broker with simulated prices.\",\"input\":\"get_stock_latest_quote SPY\",\"expected\":\"simulated quote\",\"probe_kind\":\"mcp\",\"argv\":[\"node\",\"src/cli.js\",\"demo\"],\"tool\":\"get_stock_latest_quote\",\"arguments\":{\"symbol\":\"SPY\"},\"expected_text\":\"simulated\",\"cwd\":\"\",\"env\":{\"TAS_GUARD_HOME\":\"/tmp/tg-state-run2\"}},\n{\"kind\":\"claim\",\"claim\":\"1 SPY at $580 is allowed\",\"source\":\"1 SPY at $580 (allowed)\",\"input\":\"place_stock_order qty 1 limit 580\",\"expected\":\"order accepted\",\"probe_kind\":\"mcp\",\"argv\":[\"node\",\"src/cli.js\",\"demo\"],\"tool\":\"place_stock_order\",\"arguments\":{\"symbol\":\"SPY\",\"side\":\"buy\",\"qty\":\"1\",\"type\":\"limit\",\"limit_price\":\"580\"},\"expected_text\":\"accepted\",\"cwd\":\"\",\"env\":{\"TAS_GUARD_HOME\":\"/tmp/tg-state-run2\"}},\n{\"kind\":\"claim\",\"claim\":\"tas_guard_status shows the limits the guard is working under\",\"source\":\"Ask the agent to call `tas_guard_status` to see the limits it's working under.\",\"input\":\"tas_guard_status\",\"expected\":\"status reports max_order_value 2000\",\"probe_kind\":\"mcp\",\"argv\":[\"node\",\"src/cli.js\",\"demo\"],\"tool\":\"tas_guard_status\",\"arguments\":{},\"expected_text\":\"\\\"max_order_value\\\": 2000\",\"cwd\":\"\",\"env\":{\"TAS_GUARD_HOME\":\"/tmp/tg-state-run2\"}}\n]\nEOF\npython3 -I -c 'import json;json.load(open(\"probe.json\"));json.load(open(\"claims.json\"));print(\"ok\")'", "cd && = timeout 900 python3 -I --validate --replay > /tmp/validate2.out 2>&1; echo EXIT=$?; python3 -I -c '\nimport json\nt=open(\"/tmp/validate2.out\").read()\nprint(t[:900])\nd=json.loads(t[t.index(\"{\"):]) if False else None\nprint(\"valid\" , \"valid\\\": true\" in t, \"problems:\", t.count(\"problems\"))\n' ; grep -o '\"valid\": [a-z]*' /tmp/validate2.out; grep -o '\"problems\": \\[[^]]*\\]' /tmp/validate2.out | cut -c1-600", "cd && sed -n 1266,1274p checker/check.py | cut -c1-260", "cd && python3 -I - <<'EOF'\nimport json\np=\"\"\nc=json.load(open(p))\nc[2][\"expected_text\"]='\\\\\"max_order_value\\\\\": 2000'\njson.dump(c,open(p,\"w\"),indent=1,ensure_ascii=False)\nprint(repr(c[2][\"expected_text\"]))\nEOF\ncd && = timeout 900 python3 -I --validate --replay > /tmp/validate3.out 2>&1; echo EXIT=$?; grep -o '\"valid\": [a-z]*' /tmp/validate3.out; grep -o '\"problems\": \\[[^]]*\\]' /tmp/validate3.out | cut -c1-400", "cd && cat > probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"node\",\"src/cli.js\",\"demo\"],\"cwd\":\"\",\"env\":{\"TAS_GUARD_HOME\":\"/tmp/tg-state-run3\"},\"tool\":\"get_stock_latest_quote\",\"arguments\":{\"symbol\":\"SPY\"},\"expected_text\":\"simulated\"}\nEOF\npython3 -I -c 'import json;json.load(open(\"\"));print(\"ok\")'; sleep 75; cd && = timeout 900 python3 -I --validate --replay > /tmp/validate4.out 2>&1; echo EXIT=$?; grep -o '\"valid\": [a-z]*' /tmp/validate4.out; grep -o '\"problems\": \\[[^]]*\\]' /tmp/validate4.out | cut -c1-400", "cd /tmp && grep -o '\"status\": \"[A-Za-z]*\"' /tmp/validate4.out | sort | uniq -c; grep -o '\"verdict\": \"[a-z]*\"' /tmp/validate4.out | sort | uniq -c; grep -o '\"evidence_strength\": \"[a-z_]*\"' /tmp/validate4.out; TAS_GUARD_HOME=/tmp/tg-state-run3 true; cat /tmp/tg-state-run2/guards/demo.usage.json 2>/dev/null | head -c 300", "cd && python3 -I - <<'EOF'\nimport json\nr = {\n \"outcome\": \"working\",\n \"fault_owner\": None,\n \"operation\": \"Run TAS Guard demo (tas-guard demo) as an MCP stdio server in front of a built-in paper broker, and call its tools: read a simulated quote, place an allowed 1 SPY limit order, and read the guard status\",\n \"operation_scope\": \"Node.js >=18 (engines), tested on Node v22.23.4 / npm 10.9.9; zero npm dependencies; no broker account, no real money; local stdio only; CDP endpoint not used (no browser operation)\",\n \"steps\": [\n \"Read README.md (Try it in 10 seconds; Quick start; Development)\",\n \"node --version / npm --version (v22.23.4 / 10.9.9 present; README requires node >=18 per package.json engines)\",\n \"npm test (README Development: 78 tests) -> 78 pass, 0 fail\",\n \"node src/cli.js demo (stands in for `npx -y tas-guard demo`; see deviations) driven over MCP stdio\",\n \"tools/call get_stock_latest_quote {symbol: SPY} -> simulated bid/ask 579.71/580.29\",\n \"tools/call place_stock_order {SPY, buy, qty 1, limit 580} -> status accepted\",\n \"tools/call place_stock_order {SPY, buy, qty 10, limit 580} -> blocked: 'Order value 5,800 is over the per-order limit of 2,000' (isError true, observed manually)\",\n \"tools/call tas_guard_status {} -> max_order_value 2000, max_daily_value 5000, max_orders_per_minute 3\",\n \"node src/cli.js sol-demo -> exit 0, 'hash chain intact' (README Solana mode example)\",\n \"= python3 -I --validate --replay -> valid true, replay PASS\"\n ],\n \"deviations\": [\n \"`npx -y tas-guard demo` was not used: the repo is the pinned source, so the local bin target src/cli.js was run with node instead. `npm link` to install the tas-guard bin failed with EACCES on the global npm prefix (not writable); no sudo install was attempted.\",\n \"Replacing the README's sequence of 1 SPY allowed / 10 SPY blocked claims: the checker treats any MCP result with isError:true as a failure (check.py line ~1273), and the guard reports blocks with isError:true by design. The blocked-order behavior was observed manually (see steps) but is NOT validated by claims.json; the status claim (tas_guard_status) was used instead.\",\n \"First validation attempt failed for harness reasons, not product reasons: the checker applies each probe/claim env to os.environ globally, so all replays shared one TAS_GUARD_HOME state directory, and the guard's max_orders_per_minute=3 limit tripped when the probe and order claims ran within one minute. Fixed by using one fresh state dir (/tmp/tg-state-run2 for claims, /tmp/tg-state-run3 for the probe), making the probe a read-only quote, and waiting 75s before the final run. The policy was not changed.\",\n \"The demo's stdio server exits with code 1 when stdin closes (`upstream exited (null)`), which is the demo's normal end-of-session behavior; the checker accepted this.\",\n \"Daily state persists in /tmp/tg-state-run2 (3 orders, 1740 of 5000 spent). Repeat replays of the allowed-order claim add 580 each until the daily cap; the per-minute cap of 3 applies to order calls within a rolling minute.\",\n \"cycles: no product cycle detected. The only loop is Telegram long-polling against an external service, which cannot be exercised locally without external notifications.\"\n ],\n \"stuck_step\": None,\n \"main_blocker\": None,\n \"plain_failure\": None,\n \"suggested_fix\": \"None needed for the product. For the checker: treat an MCP isError result that carries an expected blocked message as a valid verdict, and scope env/state per claim so policy counters do not leak between replays.\"\n}\njson.dump(r, open(\"\",\"w\"), indent=1, ensure_ascii=False)\nprint(open(\"\").read()[:400])\nEOF\nls -la ; ls | grep -c '^report.json$'" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Run TAS Guard demo (tas-guard demo) as an MCP stdio server in front of a built-in paper broker, and call its tools: read a simulated quote, place an allowed 1 SPY limit order, and read the guard status", "suggested_fix": null, "tokens_in": 914347, "tokens_out": 28850, "cost_usd": 0.034219009999999994, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "node", "src/cli.js", "demo" ], "kind": "mcp", "serverInfo": { "name": "tas-guard-demo-broker", "version": "1" }, "tools": [ "get_account_info", "get_stock_latest_quote", "get_all_positions", "get_orders", "place_stock_order", "cancel_order_by_id", "cancel_all_orders", "close_all_positions", "tas_guard_status" ], "tool_schema_bytes": 2221, "tool_result": { "content": [ { "type": "text", "text": "{\n \"demo\": true,\n \"symbol\": \"SPY\",\n \"bid\": 579.71,\n \"ask\": 580.29,\n \"note\": \"simulated\"\n}" } ] }, "tool_result_checked": true, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "No problems traced to this repository code in these checks. 4 static matches retained as context.", "expected": "Reviewed as expected for a test run: attempted writes that failed, so nothing was written.", "findings": [], "context": [ { "kind": "encoded-blob", "count": 2, "note": "Source contains encoded blob; review its purpose.", "location_count": 1, "path": "test/evm.test.js" }, { "kind": "hardcoded-secret", "count": 2, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 2 } ], "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=intoapex--tas-guard-claude-haiku-5-5-1793207043866476983", "evidence_file": "/data/safety/intoapex--tas-guard-claude-haiku-5-5-1793207043866476983.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": 29, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "0a50a58fba9a4b5733d6502589ba9113998fe5b7", "url": "https://github.com/intoapex/tas-guard" }, "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": 29, "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/intoapex/tas-guard", "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": "Inspected README.md (Quick start, Try it, Phone approvals and kill switch) and src/cli.js, src/telegram.js, src/proxy.js. The only recurring loop is Telegram long-polling (src/telegram.js poll) that talks to an external Telegram Bot API; it cannot be triggered locally without external notifications, which are not allowed. No cron, --once, --now or webhook trigger exists in the product, so no manual cycle was run.", "evidence": "Inspected README.md (Quick start, Try it, Phone approvals and kill switch) and src/cli.js, src/telegram.js, src/proxy.js. The only recurring loop is Telegram long-polling (src/telegram.js poll) that talks to an external Telegram Bot API; it cannot be triggered locally without external notifications, which are not allowed. No cron, --once, --now or webhook trigger exists in the product, so no manual cycle was run.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "demo runs the guard in front of a built-in paper broker with simulated prices", "source": "`tas-guard demo` runs the guard in front of a built-in paper broker with simulated prices.", "input": "{\"tool\": \"get_stock_latest_quote\", \"arguments\": {\"symbol\": \"SPY\"}}", "expected": "simulated quote", "command": "node src/cli.js demo tools/call {\"tool\": \"get_stock_latest_quote\", \"arguments\": {\"symbol\": \"SPY\"}}", "verdict": "yes", "outcome": "Real input produced the expected result: simulated", "evidence": "\u2026simulated\\\"\\n}\"}]}", "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "1 SPY at $580 is allowed", "source": "1 SPY at $580 (allowed)", "input": "{\"tool\": \"place_stock_order\", \"arguments\": {\"symbol\": \"SPY\", \"side\": \"buy\", \"qty\": \"1\", \"type\": \"limit\", \"limit_price\": \"580\"}}", "expected": "order accepted", "command": "node src/cli.js demo tools/call {\"tool\": \"place_stock_order\", \"arguments\": {\"symbol\": \"SPY\", \"side\": \"buy\", \"qty\": \"1\", \"type\": \"limit\", \"limit_price\": \"580\"}}", "verdict": "yes", "outcome": "Real input produced the expected result: accepted", "evidence": "\u2026accepted\\\"\\n }\\n}\"}]}", "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "tas_guard_status shows the limits the guard is working under", "source": "Ask the agent to call `tas_guard_status` to see the limits it's working under.", "input": "{\"tool\": \"tas_guard_status\", \"arguments\": {}}", "expected": "status reports max_order_value 2000", "command": "node src/cli.js demo tools/call {\"tool\": \"tas_guard_status\", \"arguments\": {}}", "verdict": "yes", "outcome": "Real input produced the expected result: \\\"max_order_value\\\": 2000", "evidence": "\u2026\\\"max_order_value\\\": 2000,\\n \\\"max_daily_value\\\": 5000,\\n \\\"max_orders_per_day\\\": 20,\\n \\\"max_orders_per_minute\\\": 3,\\n \\\"approve_over\\\": 1000,\\n \\\"symbols_allow\\\": [\\n \\\"SPY\\\",\\n \\\"QQQ\\\",\\n \\\"AAPL\\\",\\n \\\"MSFT\\\",\\n \\\"NVDA\\\"\\n ],\\n \\\"symbols_block\\\": [],\\n \\\"live_requires_approval\\\": false\\n },\\n \\\"today\\\": {\\n \\\"day\\\": \\\"2026-10-28\\\",\\n \\\"value_used\\\": 1160,\\n \\\"value_left\\\": 3840,\\n \\\"orders\\\": 2,\\n \\\"orders_left\\\": 18\\n },\\n \\\"pending_approvals\\\": []\\n}\"}]}", "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Solana mode demo runs seven agent transactions through the guard", "source": "README.md Solana mode / Try it: `npx tas-guard sol-demo`", "input": "sol-demo", "command": "node src/cli.js sol-demo", "evidence": " so directly. Blocked by policy.\n\n5. Agent: Approve unlimited USDC spending for a contract\n \ud83d\udeab Blocked: Unlimited token delegation to 52oh\u20263Qx6. Blocked by policy.\n\n6. Agent: Send 150 USDC ($150)\n \ud83d\udeab Blocked: Value $150.00 (0.000005 SOL + 150 USDC (devnet)) is over the per-transaction limit of $100.00.\n\n7. Agent: Pay a 0.14 SOL priority fee\n \ud83d\udeab Blocked: Fee of 0.140005 SOL is over max_fee_sol (0.01 SOL). Priority fee: 100000000 micro-lamports \u00d7 1400000 units.\n\nToday: 2 sent, $45.00 of $300 used. Audit log: 8 entries, hash chain intact.\nUSDC still in the wallet: 500. The drainer got nothing.", "deferred": false, "expected": "guard blocks drainer and over-limit transactions and reports hash chain intact", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Repository offline test suite (README Development section)", "source": "README.md Development", "input": "npm test", "command": "npm test", "evidence": " log is hash-chained, redacts secrets and detects tampering\nok 76 - audit log is hash-chained, redacts secrets and detects tampering\n ---\n duration_ms: 10.221668\n type: 'test'\n ...\n# Subtest: approvals are single-use and expire\nok 77 - approvals are single-use and expire\n ---\n duration_ms: 16.924288\n type: 'test'\n ...\n# Subtest: config files with a Windows UTF-8 BOM are read\nok 78 - config files with a Windows UTF-8 BOM are read\n ---\n duration_ms: 5.288989\n type: 'test'\n ...\n1..78\n# tests 78\n# suites 0\n# pass 78\n# fail 0\n# cancelled 0\n# skipped 0\n# todo 0\n# duration_ms 26672.122397", "deferred": false, "expected": "78 tests pass", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "last_commit_at": "2026-10-28T13:35:20Z", "commits_90d": 21, "merged_prs_90d": 4, "open_issues": 0, "open_prs": 0, "reply_share": null, "reply_threads": 0, "median_reply_hours": null, "last_release_at": null, "archived": false, "verdict": "maintained", "note": "actively maintained: last commit 0 days ago; 21 commits and 4 merged PRs in 90 days; 0 open issues, 0 open PRs; no releases" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 0 days ago; 21 commits and 4 merged PRs in 90 days; 0 open issues, 0 open PRs; no releases", "maintained": "active", "maintained_note": "last commit 0 days ago", "last_commit_at": "2026-10-28T13:35:20Z", "last_release_at": null, "open_issues": null, "answered_issues": null, "platforms_claimed": [ "windows" ], "topic": "mcp-server", "agent_interfaces": [ { "interface": "mcp", "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": { "tool_count": 9, "schema_bytes": 2221, "tokens_approx": 556, "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": "2026-10-28T17:13:01.170318+00:00", "tested_commit": "0a50a58fba9a4b5733d6502589ba9113998fe5b7", "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": "intoapex/tas-guard", "source": "https://github.com/intoapex/tas-guard", "commit": "0a50a58fba9a4b5733d6502589ba9113998fe5b7", "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": "0a50a58fba9a4b5733d6502589ba9113998fe5b7", "url": "https://github.com/intoapex/tas-guard" }, "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 TAS Guard demo (tas-guard demo) as an MCP stdio server in front of a built-in paper broker, and call its tools: read a simulated quote, place an allowed 1 SPY limit order, and read the guard status", "operation_scope": "product operation", "hosting": null, "kind": "mcp", "test_version": "readme-2d57868128a84902c09a58991c46c5fe288928e55b1de8282ab5003e13159c2f", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": "/transcripts/intoapex--tas-guard-claude-haiku-5-5-1793207043866476983.txt", "report_url": "/reports/intoapex--tas-guard-claude-haiku-5-5-1793207043866476983.json" }