{ "run_id": "MemTether--MemTether-gpt-6-luna-1792968925764333437", "date": "2026-10-25T22:56:36.354293+00:00", "repo": "MemTether/MemTether", "kind": "mcp", "source": "https://github.com/MemTether/MemTether", "commit": "9b46b31ecdb799402983e1c5598bcf21ac9c144b", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-a17389bda4cc696f9601c0c4ff1b2c16e23bfa1d907883b715ccdd9e92ddec56", "pass": true, "outcome": "pass", "time_to_working_s": 49.85242702800315, "total_s": 70.58991074562073, "steps": [ "pwd; git status --short --branch; git rev-parse HEAD; python3 --version; sed -n '1,240p' README.md; rg --files -g 'AGENTS.md' -g 'pyproject.toml' -g 'requirements*.txt' -g 'package.json' -g 'Dockerfile*' -g '*.toml' -g '*.yaml' -g '*.yml' -g '*.json' | head -100", "sed -n '240,520p' README.md; find . -maxdepth 2 -type f | sort | head -150; python3 -m pip --version", "cat pyproject.toml; sed -n '1,200p' examples/audit_chain_demo.py; sed -n '1,180p' memtether.py; sed -n '1,120p' examples/basic_remember.py", "python3 -m venv && -m pip install -e .", "mkdir -p .coldpass ; MEMTETHER_HOME= MEM_DB= MEM_SKIP_VECTOR=1 remember 'Codex probe prefers basalt blue' --source codex; MEMTETHER_HOME= MEM_DB= MEM_SKIP_VECTOR=1 search 'basalt blue' --list; MEMTETHER_HOME= MEM_DB= MEM_SKIP_VECTOR=1 examples/audit_chain_demo.py; cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"\",\"search\",\"basalt blue\",\"--list\"],\"cwd\":\"\",\"env\":{\"MEMTETHER_HOME\":\"\",\"MEM_DB\":\"\",\"MEM_SKIP_VECTOR\":\"1\"},\"expected_text\":\"Codex probe prefers basalt blue\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Remembering and searching stored facts works.\",\"source\":\"memtether remember \\\"User prefers dark theme\\\" --source claude-code\\nmemtether search \\\"theme\\\" --layer L0 # First sentence only\",\"input\":\"Codex probe prefers basalt blue\",\"expected\":\"Codex probe prefers basalt blue\",\"probe_kind\":\"cli\",\"argv\":[\"\",\"search\",\"basalt blue\",\"--list\"],\"expected_text\":\"Codex probe prefers basalt blue\",\"cwd\":\"\",\"env\":{\"MEMTETHER_HOME\":\"\",\"MEM_DB\":\"\",\"MEM_SKIP_VECTOR\":\"1\"}}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Demonstrate tamper evident audit chain.\",\"source\":\"README.md TL;DR\",\"input\":\"synthetic 25 memory audit demo\",\"expected\":\"verify_chain detects tampering\",\"argv\":[\"\",\"examples/audit_chain_demo.py\"],\"cwd\":\"\",\"env\":{\"MEMTETHER_HOME\":\"\",\"MEM_DB\":\"\",\"MEM_SKIP_VECTOR\":\"1\"},\"expected_text\":\"\u6210\u529f\u68c0\u6d4b\u5230\u7be1\u6539\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"README and entry points inspected: MemTether provides direct CLI memory operations and no product scheduler, recurring cycle, or webhook trigger.\"}\nEOF", "= python3 -I --validate --replay", "cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Store and retrieve a memory; demonstrate audit chain tamper detection\",\"operation_scope\":\"CLI with Python 3.12 and editable package install; semantic vector retrieval optional dependency absent, keyword retrieval exercised\",\"steps\":[\"Created Python 3.12 venv and installed package with pip install -e .\",\"Used documented memtether remember and search commands against isolated MEMTETHER_HOME/MEM_DB\",\"Ran documented python examples/audit_chain_demo.py; it passed verification before tampering and detected the changed audit row afterward\",\"Validated and replayed probe, README claim, and example with checker; all passed\"],\"deviations\":[\"Vector retrieval emitted missing chromadb warning and degraded to keyword search, as README describes for skipped optional semantic dependencies.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Store and retrieve a memory; demonstrate audit chain tamper detection", "suggested_fix": null, "tokens_in": 186349, "tokens_out": 1532, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "", "search", "basalt blue", "--list" ], "kind": "cli", "returncode": 0, "stdout": " 1. [fact/codex] Codex probe prefers basalt blue uid=fact-20261025225618-5caf1e9b8d80 0.1976", "stderr": "[warn] \u5411\u91cf\u68c0\u7d22\u5931\u8d25\uff08\u5c06\u964d\u7ea7\u4e3a\u7eaf\u5173\u952e\u8bcd\uff0c\u53ec\u56de\u4f1a\u660e\u663e\u53d8\u5dee\uff09: No module named 'chromadb'\n[warn] \u6b63\u786e\u89e3\u91ca\u5668: ", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "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=MemTether--MemTether-gpt-6-luna-1792968925764333437", "evidence_file": "/data/safety/MemTether--MemTether-gpt-6-luna-1792968925764333437.json.gz" }, "agent_execution": "native_agent", "agent_runtime": "codex", "agent_runtime_version": "codex-cli 0.163.0", "tool_transport": "mcp-assigned-vm", "platform": "linux", "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "native_tool_calls": 7, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "9b46b31ecdb799402983e1c5598bcf21ac9c144b", "url": "https://github.com/MemTether/MemTether" }, "purpose": "initial", "profile": { "model": "gpt-6-luna", "reasoning": "low" }, "fault": { "owner": null, "status": "resolved", "reason": null }, "fix_id": null, "verifies_run_id": null, "hosting": null, "operation_scope": "product operation", "tool_calls": 7, "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": "unknown", "needs": [], "needs_which": null, "agent_interface": [ "cli" ], "license": "Apache-2.0", "repo_url": "https://github.com/MemTether/MemTether", "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": "README and entry points inspected: MemTether provides direct CLI memory operations and no product scheduler, recurring cycle, or webhook trigger.", "evidence": "README and entry points inspected: MemTether provides direct CLI memory operations and no product scheduler, recurring cycle, or webhook trigger.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Remembering and searching stored facts works.", "source": "memtether remember \"User prefers dark theme\" --source claude-code\nmemtether search \"theme\" --layer L0 # First sentence only", "input": "Codex probe prefers basalt blue", "expected": "Codex probe prefers basalt blue", "command": " search 'basalt blue' --list", "verdict": "yes", "outcome": "Real input produced the expected result: Codex probe prefers basalt blue", "evidence": "Codex probe prefers basalt blue uid=fact-20261025225618-5caf1e9b8d80 0.1976\n[warn] \u5411\u91cf\u68c0\u7d22\u5931\u8d25\uff08\u5c06\u964d\u7ea7\u4e3a\u7eaf\u5173\u952e\u8bcd\uff0c\u53ec\u56de\u4f1a\u660e\u663e\u53d8\u5dee\uff09: No module named 'chromadb'\n[warn] \u6b63\u786e\u89e3\u91ca\u5668: \n", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Demonstrate tamper evident audit chain.", "source": "README.md TL;DR", "input": "synthetic 25 memory audit demo", "command": " examples/audit_chain_demo.py", "evidence": "\u5199\u5165 25 \u6761\u8bb0\u5fc6\uff08\u81ea\u52a8\u751f\u6210 2+ \u4e2a\u5ba1\u8ba1\u951a\u70b9\uff09...\n\u7be1\u6539\u524d verify_chain: PASS {'anchors': 2, 'entries_covered': 20, 'unanchored_tail': 5}\n\n\u6a21\u62df\u653b\u51fb\u8005\u76f4\u63a5\u6539\u5e93...\n\u7be1\u6539\u540e verify_chain: FAIL {'anchor_id': 1, 'reason': 'chain hash mismatch \u2014 audit rows edited after anchoring', 'expected': '28671332118673411653d4488e5d7df7e9b767283243aae1f23e6b0be216ec82', 'recomputed': 'fc28ebb9381107cf8e6b6c655167ce1880c3b883031f9df6205265972fa1eae6'}\n\n\u2705 \u54c8\u5e0c\u94fe\u6210\u529f\u68c0\u6d4b\u5230\u7be1\u6539\uff01\u8fd9\u5c31\u662f MemTether \u7684\u6838\u5fc3\u9632\u5fa1\u80fd\u529b\u3002", "deferred": false, "expected": "verify_chain detects tampering", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "archived": false, "commits_90d": 555, "last_commit_at": "2026-10-22T12:09:55Z", "last_release_at": "2026-10-18T03:19:23Z", "median_reply_hours": null, "merged_prs_90d": 0, "note": "slow: last commit 3 days ago; 555 commits and 0 merged PRs in 90 days; 4 open issues, 2 open PRs; 0 of 6 recent threads got a maintainer reply; latest release 2026-10-18", "open_issues": 4, "open_prs": 2, "reply_share": 0.0, "reply_threads": 6, "verdict": "slow" }, "maintenance_verdict": "slow", "maintenance_note": "slow: last commit 3 days ago; 555 commits and 0 merged PRs in 90 days; 4 open issues, 2 open PRs; 0 of 6 recent threads got a maintainer reply; latest release 2026-10-18", "maintained": "active", "maintained_note": "last commit 3 days ago; 4 open issues, 1 answered or closed", "last_commit_at": "2026-10-22T12:10:32Z", "last_release_at": "2026-10-18T03:19:23Z", "open_issues": 4, "answered_issues": 1, "platforms_claimed": [ "linux", "mac", "windows" ], "topic": "mcp-server", "agent_interfaces": [ { "interface": "mcp", "evidence": "README metadata", "observed": false, "operation_checked": false }, { "interface": "cli", "evidence": "independent checker", "observed": true, "operation_checked": true }, { "interface": "api", "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": null, "tested_at": "2026-10-25T22:56:36.354293+00:00", "tested_commit": "9b46b31ecdb799402983e1c5598bcf21ac9c144b", "tested_with": { "agent": "codex", "agent_version": "codex-cli 0.163.0", "model": "gpt-6-luna", "model_route": "gpt-6-luna", "reasoning": "low", "os": "linux", "backend": "hyperv", "transport": "mcp-assigned-vm" }, "setup_identity": { "repo": "MemTether/MemTether", "source": "https://github.com/MemTether/MemTether", "commit": "9b46b31ecdb799402983e1c5598bcf21ac9c144b", "source_revision": null, "os": "linux", "architecture": null, "backend": "hyperv", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "agent_execution": "native_agent", "agent_runtime": "codex", "agent_runtime_version": "codex-cli 0.163.0", "tool_transport": "mcp-assigned-vm", "runtime": null, "runtime_version": null, "runtime_revision": null, "sandbox_source": null, "guest_setup": null, "source_pin": { "commit": "9b46b31ecdb799402983e1c5598bcf21ac9c144b", "url": "https://github.com/MemTether/MemTether" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Store and retrieve a memory; demonstrate audit chain tamper detection", "operation_scope": "product operation", "hosting": null, "kind": "mcp", "test_version": "readme-a17389bda4cc696f9601c0c4ff1b2c16e23bfa1d907883b715ccdd9e92ddec56", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": "/transcripts/MemTether--MemTether-gpt-6-luna-1792968925764333437.txt", "report_url": "/reports/MemTether--MemTether-gpt-6-luna-1792968925764333437.json" }