{ "run_id": "awebai--aweb-claude-haiku-5-5-1793152981061634799", "date": "2026-10-28T02:10:25.240657+00:00", "repo": "awebai/aweb", "kind": "repo", "source": "https://github.com/awebai/aweb", "commit": "b3dc90a50babbc1cbc7558d7704518bf355317c5", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "test_version": "readme-c03644542c69939a9374958136a8b3431f7456269d3fb4b3c433785f59cfd637", "pass": true, "outcome": "pass", "time_to_working_s": 385.3144510349957, "total_s": 444.1787405014038, "steps": [ "cd && ls -la && git status 2>&1 | head -3; id -u; python3 --version; cat README.md 2>/dev/null | head -c 6000", "echo $CDP_URL; curl -s -m 10 -i $CDP_URL/json/version; echo; echo EXIT=$?", "cd && tail -c +6000 README.md | head -c 9500", "for c in node npm docker openssl go curl git; do printf \"%s: \" $c; command -v $c || echo MISSING; done; node -v 2>&1; npm -v 2>&1; docker --version 2>&1; docker compose version 2>&1; sudo -n true && echo SUDO_OK; cat /etc/os-release | head -2", "export NODE_USE_ENV_PROXY=1; sudo npm install -g @awebai/aw 2>&1 | tail -5; command -v aw && aw version 2>&1 | head -3", "sudo apt-get -o DPkg::Lock::Timeout=300 update 2>&1 | tail -2; sudo apt-get -o DPkg::Lock::Timeout=300 install -y docker.io docker-compose-v2 2>&1 | tail -5; docker --version 2>&1; docker compose version 2>&1", "sudo systemctl start docker 2>&1 | tail -2; sleep 3; sudo docker info 2>&1 | head -5 || true; sudo docker ps 2>&1 | head -3", "cd && cp .env.example .env && echo \"AWID_SERVICE_TOKEN=$(openssl rand -hex 32)\" >> .env && grep -c . .env && ls ../docker-compose.e2e.yml && cd && sed -n 1,80p docker-compose.e2e.yml | head -c 1500; ls server; grep -n \"ports\" -A3 docker-compose.e2e.yml | head", "cd && timeout 900 sudo docker compose up --build -d > /tmp/compose_up.log 2>&1; echo EXIT=$?; tail -15 /tmp/compose_up.log", "sleep 5; curl -s -m 10 -w \" HTTP=%{http_code}\\n\" http://localhost:8000/health; curl -s -m 10 -w \" HTTP=%{http_code}\\n\" http://localhost:8010/health", "mkdir -p && cd && export AWEB_URL=http://localhost:8000 AWID_REGISTRY_URL=http://localhost:8010 && aw init --new-team --name alice 2>&1 | tail -20; echo \"EXIT=$?\"; aw check 2>&1 | tail -10", "cd && export AWEB_URL=http://localhost:8000 AWID_REGISTRY_URL=http://localhost:8010 && aw check 2>&1 | head -40; echo; ls -la .aw 2>&1 | head", "cd && export AWEB_URL=http://localhost:8000 AWID_REGISTRY_URL=http://localhost:8010 && aw check --online 2>&1 | grep -E \"Doctor|server\\.|messaging\\.server|skipped|fail\" | head -30; echo ---; aw team invite 2>&1 | tail -15", "mkdir -p && cd && export AWEB_URL=http://localhost:8000 AWID_REGISTRY_URL=http://localhost:8010 && aw team join eyJpIjoiNzllZDFhYjEtMzBiNi00MmMwLThiOTYtNjBlZTQxMDFkMTJkIiwiZCI6ImxvY2FsIiwidCI6ImRlZmF1bHQiLCJzIjoiSURjZVlZVENKQmhFTS1tQWlEclhydjB6bWFvck53UmgiLCJyIjoiaHR0cDovL2xvY2FsaG9zdDo4MDEwIiwiYSI6Imh0dHA6Ly9sb2NhbGhvc3Q6ODAwMCJ9 --name bob 2>&1 | tail -8; echo \"EXIT=${PIPESTATUS[0]}\"; aw check --online 2>&1 | head -3", "export AWEB_URL=http://localhost:8000 AWID_REGISTRY_URL=http://localhost:8010; cd && aw mail send --to bob --subject \"review requested\" --body \"Please review this branch and reply in the same conversation.\" 2>&1 | tail -8; echo \"EXIT=${PIPESTATUS[0]}\"; sleep 2; cd && aw mail inbox 2>&1 | tail -10; echo \"EXIT=${PIPESTATUS[0]}\"", "cd && export AWEB_URL=http://localhost:8000 AWID_REGISTRY_URL=http://localhost:8010; aw events stream --help 2>&1 | head -30; echo ----; cd && cat CONTRIBUTING.md | head -c 1400", "export AWEB_URL=http://localhost:8000 AWID_REGISTRY_URL=http://localhost:8010; cd && aw mail send --to bob --subject \"cycle check\" --body \"wake test\" 2>&1 | tail -2; cd && timeout 60 aw events stream --json --timeout 6 2>&1 | head -c 1500; echo; echo \"EXIT=${PIPESTATUS[0]}\"", "cd && grep -nF 'Please review this branch and reply in the same conversation.' README.md; grep -nF '`Doctor: ok`.' README.md; grep -nF 'Bob receives an `actionable_mail` event containing a `message_id`.' README.md; export AWEB_URL=http://localhost:8000 AWID_REGISTRY_URL=http://localhost:8010; cd && aw mail show --message-id 25e83edf-d615-47c1-976a-25534187ab37 2>&1 | head -12", "cd && ENVJ='{\"AWEB_URL\":\"http://localhost:8000\",\"AWID_REGISTRY_URL\":\"http://localhost:8010\"}' && BOB= && ALICE= && cat > probe.json < claims.json <&1; cat claims.json | head -c 600", "ls 2>&1; grep -n \"source_file\\|\\\"source\\\"\\|'source'\\|\\\"quote\\\"\\|source_quote\" 2>/dev/null | head -20", "cd && ENVJ='{\"AWEB_URL\":\"http://localhost:8000\",\"AWID_REGISTRY_URL\":\"http://localhost:8010\"}' && BOB= && ALICE= && cat > claims.json < cycles.json < examples.json </dev/null && echo \"$f ok\"; done", "cd && = timeout 900 python3 -I --validate --replay > /tmp/coldpass_validate.out 2>&1; echo EXIT=$?; head -c 5000 /tmp/coldpass_validate.out", "export AWEB_URL=http://localhost:8000 AWID_REGISTRY_URL=http://localhost:8010; cd && aw mail show --conversation-id b9d8dceb-33fd-41c9-ad53-d22c65c07ff9 2>&1 | head -8; echo ---; cd && aw mail send --to bob --subject \"wake probe\" --body \"wake probe body\" | tail -1; cd && timeout 30 aw events stream --json --timeout 4 2>&1 | grep -o '\"type\":\"actionable_mail\"' | head -2", "mkdir -p && cat > <<'EOF'\n#!/bin/bash\n# Manual cycle: Alice sends fresh mail (README \"aw mail send\"), then Bob's\n# documented wake consumer \"aw events stream --json\" runs bounded by --timeout.\nset -e\nexport AWEB_URL=http://localhost:8000 AWID_REGISTRY_URL=http://localhost:8010\ncd \naw mail send --to bob --subject \"cycle check\" --body \"wake test\"\ncd \nexec aw events stream --json --timeout 6\nEOF\nchmod +x && 2>&1 | grep -c actionable_mail; echo EXIT=${PIPESTATUS[0]}", "cd && ENVJ='{\"AWEB_URL\":\"http://localhost:8000\",\"AWID_REGISTRY_URL\":\"http://localhost:8010\"}' && BOB= && ALICE= && WAKE= && CID=b9d8dceb-33fd-41c9-ad53-d22c65c07ff9 && cat > probe.json < claims.json < cycles.json < alice aw mail send then bob aw events stream --json --timeout 6 (no source edits; local SSE only)\",\"input\":\"fresh mail from alice to bob\",\"expected\":\"actionable_mail event emitted with message_id\",\"kind\":\"cli\",\"argv\":[\"$WAKE\"],\"env\":$ENVJ,\"cwd\":\"$BOB\",\"expected_text\":\"actionable_mail\"}]}\nEOF\ncat > examples.json </dev/null && echo \"$f ok\"; done", "cd && = timeout 900 python3 -I --validate --replay > /tmp/coldpass_validate.out 2>&1; echo EXIT=$?; python3 -I -c '\nimport json,sys\nd=json.load(open(\"/tmp/coldpass_validate.out\")) if False else None' ; tail -c 3000 /tmp/coldpass_validate.out", "grep -o '\"valid\": [a-z]*' /tmp/coldpass_validate.out; grep -o '\"problems\": \\[[^]]*\\]' /tmp/coldpass_validate.out | head -c 600; echo; grep -o '\"verdict\\\\\\?\": \\\\\\?\"[a-z]*' /tmp/coldpass_validate.out | sort | uniq -c", "cd && cat > report.json <<'EOF'\n{\n \"outcome\": \"working\",\n \"fault_owner\": null,\n \"operation\": \"Run the local aweb OSS stack from the README and exchange a durable mail round trip between two agents (alice and bob) through the aw CLI, including a wake-up event.\",\n \"operation_scope\": \"Local OSS path only (README 'Local OSS stack'): docker compose stack for aweb (port 8000) and AWID (port 8010), local team 'default:local'. Hosted aweb.ai path, Claude Code/Pi channel plugins, and browser/CDP were not used. Node v22.23.4, Python 3.12.3, Docker 29.1.3, Compose 2.40.3.\",\n \"steps\": [\n \"npm install -g @awebai/aw\",\n \"aw version\",\n \"cd server && cp .env.example .env && echo \\\"AWID_SERVICE_TOKEN=$(openssl rand -hex 32)\\\" >> .env\",\n \"docker compose up --build -d\",\n \"curl http://localhost:8000/health ; curl http://localhost:8010/health\",\n \"export AWEB_URL=http://localhost:8000 AWID_REGISTRY_URL=http://localhost:8010; aw init --new-team --name alice\",\n \"aw check ; aw check --online\",\n \"aw team invite\",\n \"aw team join --name bob ; aw check\",\n \"aw mail send --to bob --subject \\\"review requested\\\" --body \\\"Please review this branch and reply in the same conversation.\\\"\",\n \"aw mail inbox ; aw mail show --message-id ; aw mail show --conversation-id \",\n \"aw events stream --json --timeout 6 (wake-up actionable_mail event)\"\n ],\n \"deviations\": [\n \"Docker was not installed in the guest. Ran: sudo apt-get -o DPkg::Lock::Timeout=300 install -y docker.io docker-compose-v2 (succeeded), then sudo systemctl start docker. Docker commands run with sudo because the ubuntu user is not in the docker group.\",\n \"npm global install ran with sudo (sudo npm install -g @awebai/aw) to place aw in /usr/local/bin.\",\n \"The workspace is not a git repository and no git fetch/reset was needed; the source snapshot was used as-is.\",\n \"Bob's team join used the invite token from alice's aw team invite on the local stack (no DNS, no hosted account).\",\n \"The validation run first failed on two claims because aw mail show marks mail as read, so inbox and the wake stream no longer returned the earlier message. Fixed by using the durable conversation view (aw mail show --conversation-id) for the delivery claim and a guest wrapper that sends fresh mail from alice and then runs bob's aw events stream --json --timeout 6. The wrapper only sequences the two documented aw commands; it is a substitute trigger, not a product scheduler.\",\n \"The compose stack (aweb, awid, postgres, redis) was left running until guest teardown, as required for the CLI probes.\"\n ],\n \"stuck_step\": null,\n \"main_blocker\": null,\n \"plain_failure\": null,\n \"suggested_fix\": \"None for the working path. Note: aw mail show marks mail as read, which changes what aw mail inbox and aw events stream return later; tests that depend on unread state need fresh mail per run.\"\n}\nEOF\npython3 -I -m json.tool report.json >/dev/null && echo REPORT_OK; ls -la ; ls 2>&1" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Run the local aweb OSS stack from the README and exchange a durable mail round trip between two agents (alice and bob) through the aw CLI, including a wake-up event.", "suggested_fix": null, "tokens_in": 796239, "tokens_out": 20628, "cost_usd": 0.027761680000000004, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "aw", "mail", "show", "--conversation-id", "b9d8dceb-33fd-41c9-ad53-d22c65c07ff9" ], "kind": "cli", "returncode": 0, "stdout": "Mail conversation b9d8dceb-33fd-41c9-ad53-d22c65c07ff9 (6 messages):\n\n- local/alice \u2014 review requested: Please review this branch and reply in the same conversation.\n- local/alice \u2014 cycle check: wake test\n- local/alice \u2014 wake probe: wake probe body\n- local/alice \u2014 cycle check: wake test\n- local/alice \u2014 cycle check: wake test\n- local/alice \u2014 cycle check: wake test", "stderr": "", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 2 download and execute, 99 hardcoded secret, 98 known vulnerability, 1 outside write. 137 static matches retained as context.", "findings": [ { "kind": "download-and-execute", "count": 2, "note": "Source contains download and execute; review its purpose.", "location_count": 1, "path": "cli/go/install.sh" }, { "kind": "hardcoded-secret", "count": 98, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 17 }, { "kind": "known-vulnerability", "count": 98, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 20 }, { "kind": "outside-write", "count": 1, "note": "Repository processes attempted these writes outside documented output/cache paths.", "location_count": 3, "process_count": 1, "processes": [ { "executable": "/usr/local/bin/node", "flags": "", "owner": "repo", "path": "/usr/local/lib/node_modules/@awebai/aw/bin/aw", "pid": "2056", "source": "npm lifecycle", "succeeded": true, "syscall": "rename" } ] } ], "context": [ { "kind": "hardcoded-secret", "count": 136, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 65 } ], "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.", "Only 200 of 2570 findings are stored; the summary counts all of them." ], "static": { "dependency_note": "OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check." }, "evidence_url": "/safety/?run=awebai--aweb-claude-haiku-5-5-1793152981061634799", "evidence_file": "/data/safety/awebai--aweb-claude-haiku-5-5-1793152981061634799.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": 28, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "b3dc90a50babbc1cbc7558d7704518bf355317c5", "url": "https://github.com/awebai/aweb" }, "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/awebai/aweb", "cost_to_try": "free", "hardware": null, "what_failed": null, "local_or_hosted": "both", "cycle_checks": [ { "kind": "cycle", "claim": "Bob's event stream wakes on mail delivered by Alice", "source": "README.md", "input": "fresh mail from alice to bob", "expected": "actionable_mail event emitted with message_id", "command": "", "schedule": "event-stream connection; no cron, no loop in the product", "method": "run-once wrapper alice aw mail send then bob aw events stream --json --timeout 6 (no source edits; local SSE only)", "verdict": "yes", "outcome": "Triggered one cycle by hand (run-once wrapper alice aw mail send then bob aw events stream --json --timeout 6 (no source edits; local SSE only); normal trigger: event-stream connection; no cron, no loop in the product): Sent mail in conversation b9d8dceb-33fd-41c9-ad53-d22c65c07ff9 (message_id=bde2d4e4-cd77-47b7-9977-e361e0a1fbed)\n{\"type\":\"connected\",\"raw\":{\"agent_id\":\"5ce895f9-d829-4c1f-9ad6-a1e57822309d\",\"team_id\":\"default:local\"},\"agent_id\":\"5ce895f9-d829-4c1f-9ad6-a1e57822309d\",\"team_id\":\"default:local\"}\n{\"type\":\"actionable_mail\",\"raw\":{\"type\":\"actionable_mail\",\"message_id\":\"103e0bc3-7502-4acb-912d-016ad3fef038\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_stable_id\":\"\",\"from_address\":\"local/alice\",\"subject\":\"wake probe\",\"priority\":\"normal\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"encrypted\":false,\"unread_count\":6,\"wake_mode\":\"idle\",\"created_at\":\"2026-10-28T02:08:56.533879+00:00\"},\"wake_mode\":\"idle\",\"channel\":\"mail\",\"message_id\":\"103e0bc3-7502-4acb-912d-016ad3fef038\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_address\":\"local/alice\",\"subject\":\"wake probe\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"unread_count\":6}\n{\"type\":\"actionable_mail\",\"raw\":{\"type\":\"actionable_mail\",\"message_id\":\"9ae7133c-4ca0-400b-af9d-1c776d89ed06\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_stable_id\":\"\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"priority\":\"normal\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"encrypted\":false,\"unread_count\":6,\"wake_mode\":\"idle\",\"created_at\":\"2026-10-28T02:09:06.212380+00:00\"},\"wake_mode\":\"idle\",\"channel\":\"mail\",\"message_id\":\"9ae7133c-4ca0-400b-af9d-1c776d89ed06\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"unread_count\":6}\n{\"type\":\"actionable_mail\",\"raw\":{\"type\":\"actionable_mail\",\"message_id\":\"d3032407-da3d-4955-99b9-a14d7bb900a5\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_stable_id\":\"\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"priority\":\"normal\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"encrypted\":false,\"unread_count\":6,\"wake_mode\":\"idle\",\"created_at\":\"2026-10-28T02:09:22.757282+00:00\"},\"wake_mode\":\"idle\",\"channel\":\"mail\",\"message_id\":\"d3032407-da3d-4955-99b9-a14d7bb900a5\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"unread_count\":6}\n{\"type\":\"actionable_mail\",\"raw\":{\"type\":\"actionable_mail\",\"message_id\":\"bde160b9-e613-420e-a205-8533f29c6ca7\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_stable_id\":\"\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"priority\":\"normal\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"encrypted\":false,\"unread_count\":6,\"wake_mode\":\"idle\",\"created_at\":\"2026-10-28T02:09:29.102758+00:00\"},\"wake_mode\":\"idle\",\"channel\":\"mail\",\"message_id\":\"bde160b9-e613-420e-a205-8533f29c6ca7\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"unread_count\":6}\n{\"type\":\"actionable_mail\",\"raw\":{\"type\":\"actionable_mail\",\"message_id\":\"013f80c2-7d39-4fa5-badc-8248465a4d8d\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_stable_id\":\"\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"priority\":\"normal\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"encrypted\":false,\"unread_count\":6,\"wake_mode\":\"idle\",\"created_at\":\"2026-10-28T02:09:54.983442+00:00\"},\"wake_mode\":\"idle\",\"channel\":\"mail\",\"message_id\":\"013f80c2-7d39-4fa5-badc-8248465a4d8d\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"unread_count\":6}\n{\"type\":\"actionable_mail\",\"raw\":{\"type\":\"actionable_mail\",\"message_id\":\"bde2d4e4-cd77-47b7-9977-e361e0a1fbed\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_stable_id\":\"\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"priority\":\"normal\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"encrypted\":false,\"unread_count\":6,\"wake_mode\":\"idle\",\"created_at\":\"2026-10-28T02:10:01.296320+00:00\"},\"wake_mode\":\"idle\",\"channel\":\"mail\",\"message_id\":\"bde2d4e4-cd77-47b7-9977-e361e0a1fbed\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"unread_count\":6}", "evidence": "Sent mail in conversation b9d8dceb-33fd-41c9-ad53-d22c65c07ff9 (message_id=bde2d4e4-cd77-47b7-9977-e361e0a1fbed)\n{\"type\":\"connected\",\"raw\":{\"agent_id\":\"5ce895f9-d829-4c1f-9ad6-a1e57822309d\",\"team_id\":\"default:local\"},\"agent_id\":\"5ce895f9-d829-4c1f-9ad6-a1e57822309d\",\"team_id\":\"default:local\"}\n{\"type\":\"actionable_mail\",\"raw\":{\"type\":\"actionable_mail\",\"message_id\":\"103e0bc3-7502-4acb-912d-016ad3fef038\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_stable_id\":\"\",\"from_address\":\"local/alice\",\"subject\":\"wake probe\",\"priority\":\"normal\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"encrypted\":false,\"unread_count\":6,\"wake_mode\":\"idle\",\"created_at\":\"2026-10-28T02:08:56.533879+00:00\"},\"wake_mode\":\"idle\",\"channel\":\"mail\",\"message_id\":\"103e0bc3-7502-4acb-912d-016ad3fef038\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_address\":\"local/alice\",\"subject\":\"wake probe\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"unread_count\":6}\n{\"type\":\"actionable_mail\",\"raw\":{\"type\":\"actionable_mail\",\"message_id\":\"9ae7133c-4ca0-400b-af9d-1c776d89ed06\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_stable_id\":\"\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"priority\":\"normal\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"encrypted\":false,\"unread_count\":6,\"wake_mode\":\"idle\",\"created_at\":\"2026-10-28T02:09:06.212380+00:00\"},\"wake_mode\":\"idle\",\"channel\":\"mail\",\"message_id\":\"9ae7133c-4ca0-400b-af9d-1c776d89ed06\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"unread_count\":6}\n{\"type\":\"actionable_mail\",\"raw\":{\"type\":\"actionable_mail\",\"message_id\":\"d3032407-da3d-4955-99b9-a14d7bb900a5\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_stable_id\":\"\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"priority\":\"normal\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"encrypted\":false,\"unread_count\":6,\"wake_mode\":\"idle\",\"created_at\":\"2026-10-28T02:09:22.757282+00:00\"},\"wake_mode\":\"idle\",\"channel\":\"mail\",\"message_id\":\"d3032407-da3d-4955-99b9-a14d7bb900a5\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"unread_count\":6}\n{\"type\":\"actionable_mail\",\"raw\":{\"type\":\"actionable_mail\",\"message_id\":\"bde160b9-e613-420e-a205-8533f29c6ca7\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_stable_id\":\"\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"priority\":\"normal\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"encrypted\":false,\"unread_count\":6,\"wake_mode\":\"idle\",\"created_at\":\"2026-10-28T02:09:29.102758+00:00\"},\"wake_mode\":\"idle\",\"channel\":\"mail\",\"message_id\":\"bde160b9-e613-420e-a205-8533f29c6ca7\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"unread_count\":6}\n{\"type\":\"actionable_mail\",\"raw\":{\"type\":\"actionable_mail\",\"message_id\":\"013f80c2-7d39-4fa5-badc-8248465a4d8d\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_stable_id\":\"\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"priority\":\"normal\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"encrypted\":false,\"unread_count\":6,\"wake_mode\":\"idle\",\"created_at\":\"2026-10-28T02:09:54.983442+00:00\"},\"wake_mode\":\"idle\",\"channel\":\"mail\",\"message_id\":\"013f80c2-7d39-4fa5-badc-8248465a4d8d\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"unread_count\":6}\n{\"type\":\"actionable_mail\",\"raw\":{\"type\":\"actionable_mail\",\"message_id\":\"bde2d4e4-cd77-47b7-9977-e361e0a1fbed\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_stable_id\":\"\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"priority\":\"normal\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"encrypted\":false,\"unread_count\":6,\"wake_mode\":\"idle\",\"created_at\":\"2026-10-28T02:10:01.296320+00:00\"},\"wake_mode\":\"idle\",\"channel\":\"mail\",\"message_id\":\"bde2d4e4-cd77-47b7-9977-e361e0a1fbed\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_address\":\"local/alice\",\"subject\":\"cycle check\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"unread_count\":6}", "returncode": 0 } ], "claims": [ { "kind": "claim", "claim": "Mail sent by Alice is delivered to Bob and readable in the conversation", "source": "Please review this branch and reply in the same conversation.", "input": "alice's review request in the shared conversation", "expected": "conversation shows the message body", "command": "aw mail show --conversation-id b9d8dceb-33fd-41c9-ad53-d22c65c07ff9", "verdict": "yes", "outcome": "Real input produced the expected result: Please review this branch and reply in the same conversation.", "evidence": "\u2026Please review this branch and reply in the same conversation.\n- local/alice \u2014 cycle check: wake test\n- local/alice \u2014 wake probe: wake probe body\n- local/alice \u2014 cycle check: wake test\n- local/alice \u2014 cycle check: wake test\n- local/alice \u2014 cycle check: wake test\n", "returncode": 0, "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "A healthy setup reports Doctor ok", "source": "`Doctor: ok`.", "input": "aw check in alice workspace", "expected": "Doctor: ok", "command": "aw check", "verdict": "yes", "outcome": "Real input produced the expected result: Doctor: ok", "evidence": "Doctor: ok\nMode: auto\nNote: 21 online check(s) were skipped and do not affect the verdict; run `aw check --online` to include them.\nPath: ~/agents/alice\nChecks:\n [info] doctor.contract.v1 \u2014 Doctor output contract is available.\n [ok] local.workspace_yaml.exists \u2014 Local workspace binding file is present.\n [ok] local.workspace_yaml.parse \u2014 Local workspace binding parsed successfully.\n [ok] local.workspace.aweb_url_syntax \u2014 Workspace aweb_url is present and syntactically valid.\n [ok] local.teams.active_team \u2014 teams.yaml active_team is present.\n [ok] local.workspace.active_membership \u2014 ", "returncode": 0, "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "Bob receives an actionable_mail wake event for new mail from Alice", "source": "Bob receives an `actionable_mail` event containing a `message_id`.", "input": "alice sends fresh mail via wrapper, bob runs aw events stream", "expected": "actionable_mail event", "command": "", "verdict": "yes", "outcome": "Real input produced the expected result: actionable_mail", "evidence": "\u2026actionable_mail\",\"raw\":{\"type\":\"actionable_mail\",\"message_id\":\"103e0bc3-7502-4acb-912d-016ad3fef038\",\"conversation_id\":\"b9d8dceb-33fd-41c9-ad53-d22c65c07ff9\",\"from_alias\":\"alice\",\"from_did\":\"did:key:z6MkmWQx7LE72bY6fvXA8ANPtVbR4hKUNBNLCPUQDUeUx7tr\",\"from_stable_id\":\"\",\"from_address\":\"local/alice\",\"subject\":\"wake probe\",\"priority\":\"normal\",\"content_mode\":\"legacy_plaintext_v1\",\"message_version\":1,\"encrypted\":false,\"unread_count\":5,\"wake_mode\":\"idle\",\"created_at\":\"2026-10-28T02:08:56.533879+00:00\"},\"wake_mode\":\"idle\",\"channel\":\"mail\",\"message_id\":\"103e0bc3-7502-4acb-912d-016ad3fef038\",\"conversati", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Bob fetches the durable message content by message id", "source": "README.md", "input": "message id of alice's review request", "command": "aw mail show --message-id 25e83edf-d615-47c1-976a-25534187ab37", "evidence": "Mail conversation b9d8dceb-33fd-41c9-ad53-d22c65c07ff9 (1 messages):\n\n- local/alice \u2014 review requested: Please review this branch and reply in the same conversation.", "deferred": false, "expected": "message body shown", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "last_commit_at": "2026-10-27T23:04:46Z", "commits_90d": 3945, "merged_prs_90d": 25, "open_issues": 19, "open_prs": 4, "reply_share": 0.03, "reply_threads": 31, "median_reply_hours": 342.1, "last_release_at": "2026-08-19T00:35:23Z", "archived": false, "verdict": "maintained", "note": "actively maintained: last commit 0 days ago; 3945 commits and 25 merged PRs in 90 days; 19 open issues, 4 open PRs; 1 of 31 recent threads got a maintainer reply, median first reply 342.1h; latest release 2026-08-19" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 0 days ago; 3945 commits and 25 merged PRs in 90 days; 19 open issues, 4 open PRs; 1 of 31 recent threads got a maintainer reply, median first reply 342.1h; latest release 2026-08-19", "maintained": "active", "maintained_note": "last commit 0 days ago; 7 open issues, 2 answered or closed", "last_commit_at": "2026-10-28T01:58:27Z", "last_release_at": "2026-08-19T00:35:23Z", "open_issues": 7, "answered_issues": 2, "platforms_claimed": [ "linux" ], "topic": "mcp-server", "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": "2026-10-28T02:10:25.240657+00:00", "tested_commit": "b3dc90a50babbc1cbc7558d7704518bf355317c5", "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": "awebai/aweb", "source": "https://github.com/awebai/aweb", "commit": "b3dc90a50babbc1cbc7558d7704518bf355317c5", "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": "b3dc90a50babbc1cbc7558d7704518bf355317c5", "url": "https://github.com/awebai/aweb" }, "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 the local aweb OSS stack from the README and exchange a durable mail round trip between two agents (alice and bob) through the aw CLI, including a wake-up event.", "operation_scope": "product operation", "hosting": null, "kind": "repo", "test_version": "readme-c03644542c69939a9374958136a8b3431f7456269d3fb4b3c433785f59cfd637", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": "/transcripts/awebai--aweb-claude-haiku-5-5-1793152981061634799.txt", "report_url": "/reports/awebai--aweb-claude-haiku-5-5-1793152981061634799.json" }