{ "run_id": "langchain-ai--social-media-agent-claude-haiku-5-5-1792801374124435789", "date": "2026-10-24T00:48:03.890065+00:00", "repo": "langchain-ai/social-media-agent", "kind": "repo", "source": "https://github.com/langchain-ai/social-media-agent", "commit": "7c98af38daaa6b2d721dfcdd2307f3acabd7aa60", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "test_version": "readme-bdc1b9b3c0d2673aef87e076d14084a8123ddcf09d520c1ee2e364a37c3f4bb9", "pass": null, "outcome": "unverified", "time_to_working_s": null, "total_s": 1509.7656083106995, "steps": [ "cd && ls -la && cat README.md | head -300 && python3 --version && id -u && git status 2>&1 | head -3", "cd && git init -q 2>&1; git remote add origin https://github.com/langchain-ai/social-media-agent.git && git fetch --depth 1 origin 7c98af38daaa6b2d721dfcdd2307f3acabd7aa60 2>&1 | tail -3; git reset --mixed FETCH_HEAD 2>&1 | tail -2; git log --oneline | head -2; git status --short | head; echo ---; sed -n 300,500p README.md | grep -n -i -E \"cron|yarn|npm|node|python|docker\" | head -60; echo ---; cat package.json | head -60; node --version; npm --version; yarn --version; sudo -n true && echo SUDO_OK", "cd && grep -n -i -E \"node|engines\" README.md package.json | head; grep -n -A3 '\"engines\"' package.json; cat .env.quickstart.example; cat /etc/os-release | head -2; (sudo apt-get update -qq && sudo DEBIAN_FRONTEND=noninteractive apt-get install -y -qq nodejs npm >/tmp/apt.log 2>&1; echo apt=$?); node --version; npm --version", "export NODE_USE_ENV_PROXY=1; cd /tmp && curl -fsSL https://deb.nodesource.com/setup_22.x -o /tmp/ns.sh && sudo -E bash /tmp/ns.sh >/tmp/ns.log 2>&1; echo ns=$?; sudo DEBIAN_FRONTEND=noninteractive apt-get install -y -qq nodejs >/tmp/apt2.log 2>&1; echo apt=$?; node --version; sudo npm i -g yarn@1.22.22 >/tmp/yarn.log 2>&1; echo yarn=$?; yarn --version; tail -3 /tmp/ns.log /tmp/apt2.log 2>/dev/null | tail -8", "export NODE_USE_ENV_PROXY=1; cd && yarn install --frozen-lockfile > /tmp/yarn-install.log 2>&1; echo rc=$?; tail -15 /tmp/yarn-install.log", "cd && cp .env.quickstart.example .env && ls .coldpass; (nohup yarn langgraph:in_mem:up > /tmp/lg.log 2>&1 &); sleep 90; tail -30 /tmp/lg.log", "cd && curl -s -m 10 http://localhost:54367/ok; echo; curl -s -m 10 -X POST http://localhost:54367/assistants/search -H 'content-type: application/json' -d '{\"limit\":20}' | head -c 1500; echo; curl -s -m 10 -X POST http://localhost:54367/threads -H 'content-type: application/json' -d '{}' | head -c 300; echo; cat scripts/generate-post.ts | head -60", "ls /inputs 2>&1; f=; wc -l $f; grep -n -E \"stays_running|method|'http'|\\\"http\\\"|kind ==|expected_file|needs_credentials|credentials_error\" $f | head -60", "f=; sed -n 250,270p $f; sed -n 810,845p $f; grep -n -A12 \"^def http_details\" $f | head -40", "f=; grep -n \"^def http(\" $f; n=$(grep -n \"^def http(\" $f | cut -d: -f1); sed -n \"${n},$((n+30))p\" $f", "cd && curl -s -m 10 http://localhost:54367/assistants/e4ac3461-519e-5766-967f-68a84d44fdc6 | head -c 400; echo; curl -s -m 10 http://localhost:54367/assistants/e4ac3461-519e-5766-967f-68a84d44fdc6 | grep -o '\"graph_id\":\"[^\"]*\"'; echo ---; f=; sed -n 861,900p $f | cut -c1-220; echo ---; ls scripts/crons; sed -n 1,60p scripts/crons/create-cron.ts | cut -c1-200", "cd && export NODE_USE_ENV_PROXY=1; LANGGRAPH_API_URL=http://localhost:54367 timeout 170 yarn -s cron:list 2>&1 | tail -15; echo rc=$?; curl -s -m 10 -X POST http://localhost:54367/runs/crons/search -H 'content-type: application/json' -d '{}' ; echo; curl -s -m 10 -X POST http://localhost:54367/runs/crons -H 'content-type: application/json' -d '{}' | head -c 300; echo; cat scripts/crons/list-crons.ts | head -30 | cut -c1-160", "pkill -f \"langgraph-cli\" ; pkill -f \"langgraph:in_mem\" ; pkill -f \"langgraph dev\"; sleep 3; (ss -ltnp 2>/dev/null | grep 54367) ; echo \"port-check-done\"; cd && export NODE_USE_ENV_PROXY=1 && timeout 900 yarn -s test > /tmp/yarn-test.log 2>&1; echo testrc=$?; grep -E \"^(Tests|Test Suites):\" /tmp/yarn-test.log; tail -5 /tmp/yarn-test.log", "for p in $(pgrep -f \"in_mem:up|langgraph-cli dev\" ); do echo pid $p; done | head; for p in $(pgrep -f \"langgraph-cli dev|in_mem:up\" | grep -v \"^$\"); do kill $p 2>/dev/null; done; sleep 3; curl -s -m 3 http://localhost:54367/ok || echo \"server down\"; pgrep -fa \"langgraph\" | grep -v pgrep | head -5", "ps -eo pid,args | grep '[l]anggraph' | head; for p in $(ps -eo pid,args | grep '[l]anggraph' | awk '{print $1}'); do kill $p 2>/dev/null; done; sleep 3; curl -s -m 3 http://localhost:54367/ok || echo \"server down\"", "cd && export NODE_USE_ENV_PROXY=1 && timeout 900 yarn -s test > /tmp/yarn-test.log 2>&1; echo testrc=$?; grep -E \"^(Tests|Test Suites):\" /tmp/yarn-test.log; tail -4 /tmp/yarn-test.log", "cd && mkdir -p .coldpass && python3 -I - <<'EOF'\nimport json\nW=\"\"\nURL=\"http://localhost:54367/assistants/e4ac3461-519e-5766-967f-68a84d44fdc6\"\nserver=[\"yarn\",\"langgraph:in_mem:up\"]\nprobe={\"kind\":\"http\",\"argv\":server,\"cwd\":W,\"url\":URL,\"expected_text\":\"curated_post_interrupt\"}\nclaims=[\n {\"kind\":\"claim\",\"claim\":\"The LangGraph server starts with the documented script and serves the registered graphs\",\n \"source\":\"To start the LangGraph server, run this script:\",\"input\":\"GET assistant e4ac3461-519e-5766-967f-68a84d44fdc6 after yarn langgraph:in_mem:up\",\n \"expected\":\"assistant record for the curated_post_interrupt graph\",\"probe_kind\":\"http\",\"argv\":server,\n \"url\":URL,\"expected_text\":\"curated_post_interrupt\",\"cwd\":W},\n {\"kind\":\"claim\",\"claim\":\"Generating a post through the running server requires API keys that were not available here\",\n \"source\":\"Once the server is ready, you can execute the following command to generate a post:\",\"testable\":False,\n \"reason\":\"yarn generate_post needs ANTHROPIC_API_KEY and FIRECRAWL_API_KEY (plus ARCADE_API_KEY for the quickstart); none were supplied, so no post was generated.\"},\n]\nexamples=[\n {\"kind\":\"example\",\"claim\":\"Repository's documented offline unit test suite runs\",\n \"source\":\"package.json scripts.test\",\"input\":\"yarn test (jest, *.test.ts, excludes *.int.test.ts)\",\n \"expected\":\"all unit test suites pass\",\"argv\":[\"yarn\",\"-s\",\"test\"],\"cwd\":W,\"env\":{}},\n]\ncycles={\"detected\":True,\"checks\":[\n {\"claim\":\"Scheduled ingest_data cron runs daily at 08:00 UTC\",\n \"source\":\"scripts/crons/create-cron.ts\",\n \"quote\":'schedule: \"0 8 * * *\", // Runs at 8:00 AM UTC every day (1AM PST)',\n \"schedule\":\"0 8 * * * (daily 08:00 UTC)\",\"method\":\"LangGraph cron API (crons.create) on the server\",\n \"input\":\"no trigger was run; the local in-memory dev server cannot run crons\",\n \"expected\":\"ingest_data run started by the cron scheduler\",\n \"reason\":\"Cron search on the in-memory dev server returns 'Not implemented' (yarn cron:list against http://localhost:54367). Cron scheduling needs a deployed LangGraph server, and the create-cron script still has the placeholder slackChannelId ADD_SLACK_CHANNEL_ID_HERE plus a SLACK_BOT_TOKEN, so no cycle was run.\"}\n]}\nfor name,obj in [(\"probe.json\",probe),(\"claims.json\",claims),(\"examples.json\",examples),(\"cycles.json\",cycles)]:\n with open(f\".coldpass/{name}\",\"w\") as f: json.dump(obj,f,indent=2)\nprint(\"ok\")\nEOF\nls -la .coldpass", "cd && python3 -I - <<'EOF'\nimport json\nreport={\n \"outcome\":\"needs_credentials\",\n \"fault_owner\":\"prerequisite\",\n \"operation\":\"Start the LangGraph server with `yarn langgraph:in_mem:up` and call its API (read back the curated_post_interrupt assistant); run the documented unit tests with `yarn test`.\",\n \"operation_scope\":\"Local in-memory LangGraph dev server on port 54367. Post generation (`yarn generate_post`) was NOT run: it needs ANTHROPIC_API_KEY and FIRECRAWL_API_KEY (and ARCADE_API_KEY for the quickstart), none of which were available. Cron scheduling was not run either.\",\n \"steps\":[\n \"git init; git remote add origin https://github.com/langchain-ai/social-media-agent.git; git fetch --depth 1 origin 7c98af38daaa6b2d721dfcdd2307f3acabd7aa60; git reset --mixed FETCH_HEAD\",\n \"Install Node 22 (nodesource setup_22.x, then apt install nodejs) and yarn 1.22.22 (npm i -g yarn@1.22.22)\",\n \"yarn install --frozen-lockfile\",\n \"cp .env.quickstart.example .env\",\n \"yarn langgraph:in_mem:up\",\n \"yarn generate_post (not run: missing API keys)\",\n \"yarn test\"\n ],\n \"deviations\":[\n \"README gives no Node version. Distro Node 18 was installed first, but @types/node ^26 and the toolchain need a newer Node, so Node 22.23.4 was installed from nodesource (curl | sh of setup_22.x, run in the disposable guest).\",\n \"yarn was not installed; it was installed with npm i -g yarn@1.22.22 to match package.json packageManager.\",\n \"Quickstart .env was created from .env.quickstart.example with blank keys. The LangSmith tracing 401 warning at server start is expected without LANGCHAIN_API_KEY.\",\n \"yarn generate_post was not run: no ANTHROPIC/FIRECRAWL/ARCADE keys were available, so no credentials were obtained.\",\n \"Cron scheduling was not run: `yarn cron:list` against the in-memory server returned 'Not implemented'; create-cron.ts also needs a Slack channel ID and token.\",\n \"Probe uses a read-back GET on the assistant record (its ID is stable) instead of a graph run, because the checker's http probe only does GET.\"\n ],\n \"stuck_step\":\"yarn generate_post (README Quickstart 'Once the server is ready...') needs LLM and scraping API keys.\",\n \"main_blocker\":\"Missing API keys for Anthropic, FireCrawl and Arcade; the post-generation graph cannot run without them.\",\n \"plain_failure\":\"The app starts and serves its graphs locally, and its unit tests pass. Actually generating a social media post needs paid API keys that were not available in this test environment, so that step was not run.\",\n \"suggested_fix\":\"Supply ANTHROPIC_API_KEY, FIRECRAWL_API_KEY and ARCADE_API_KEY in .env (LANGCHAIN_API_KEY for tracing), then run `yarn langgraph:in_mem:up` and `yarn generate_post` to verify a full run. Consider stating the Node version (22+) in the README.\"\n}\nimport os\nos.makedirs(\".coldpass\",exist_ok=True)\njson.dump(report,open(\".coldpass/report.json\",\"w\"),indent=2)\nprint(\"written\")\nEOF\n= python3 -I --validate --replay 2>&1 | tail -60", "f=; sed -n 270,300p $f | cut -c1-240; grep -n \"def replay\\|'working'\\] = \\|working=\" $f | head -20", "f=; sed -n 1188,1202p $f | cut -c1-240; grep -n \"^def scope_outcome\\|scope_outcome(\" $f | head", "cd && curl -s -m 3 http://localhost:54367/ok || echo \"54367 free\"; ls report.json 2>/dev/null || echo \"no root report.json\"; ls -la .coldpass; python3 -I -c \"import json;[json.load(open('.coldpass/'+f)) for f in ['probe.json','claims.json','examples.json','cycles.json','report.json']];print('json ok')\"" ], "stuck_step": "yarn generate_post (README Quickstart 'Once the server is ready...') needs LLM and scraping API keys.", "error_excerpt": "Missing API keys for Anthropic, FireCrawl and Arcade; the post-generation graph cannot run without them.", "what_it_did": "Start the LangGraph server with `yarn langgraph:in_mem:up` and call its API (read back the curated_post_interrupt assistant); run the documented unit tests with `yarn test`.", "suggested_fix": "Supply ANTHROPIC_API_KEY, FIRECRAWL_API_KEY and ARCADE_API_KEY in .env (LANGCHAIN_API_KEY for tracing), then run `yarn langgraph:in_mem:up` and `yarn generate_post` to verify a full run. Consider stating the Node version (22+) in the README.", "tokens_in": 675380, "tokens_out": 15207, "cost_usd": 0.02355403, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": false, "argv": [ "yarn", "langgraph:in_mem:up" ], "kind": "http", "status": 200, "bytes": 294, "url": "http://localhost:54367/assistants/e4ac3461-519e-5766-967f-68a84d44fdc6", "response_checked": true, "response_excerpt": "curated_post_interrupt\",\"metadata\":{\"created_by\":\"system\"},\"name\":\"curated_post_interrupt\",\"description\":null}", "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 2 encoded blob, 9 hardcoded secret, 35 known vulnerability, 1 outside write.", "expected": "Reviewed as expected for a test run: npm looked for a config file that did not exist, so nothing was read.", "findings": [ { "kind": "encoded-blob", "count": 2, "note": "Source contains encoded blob; review its purpose.", "location_count": 2 }, { "kind": "hardcoded-secret", "count": 8, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 7 }, { "kind": "known-vulnerability", "count": 35, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 13 }, { "kind": "outside-write", "count": 1, "note": "Repository processes attempted these writes outside documented output/cache paths.", "location_count": 3, "process_count": 3 } ], "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=langchain-ai--social-media-agent-claude-haiku-5-5-1792801374124435789", "evidence_file": "/data/safety/langchain-ai--social-media-agent-claude-haiku-5-5-1792801374124435789.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": 21, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "7c98af38daaa6b2d721dfcdd2307f3acabd7aa60", "url": "https://github.com/langchain-ai/social-media-agent" }, "purpose": "initial", "profile": { "model": "claude-haiku-5-5", "reasoning": "low" }, "fault": { "owner": "prerequisite", "status": "diagnosed", "reason": "Missing API keys for Anthropic, FireCrawl and Arcade; the post-generation graph cannot run without them." }, "fix_id": null, "verifies_run_id": null, "hosting": null, "operation_scope": "product operation", "tool_calls": 21, "guest_setup": null, "runtime": null, "runtime_version": null, "runtime_revision": null, "source_revision": null, "evidence_version": null, "failure_origin": null, "evidence_strength": "partly_checked", "works": "untested", "install_s": null, "first_use_s": null, "mcp": "none", "needs": [], "needs_which": null, "agent_interface": [ "api" ], "license": "MIT", "repo_url": "https://github.com/langchain-ai/social-media-agent", "cost_to_try": null, "hardware": null, "what_failed": "Missing API keys for Anthropic, FireCrawl and Arcade; the post-generation graph cannot run without them.", "local_or_hosted": "local", "cycle_checks": [ { "kind": "cycle", "claim": "Scheduled ingest_data cron runs daily at 08:00 UTC", "source": "scripts/crons/create-cron.ts", "input": "no trigger was run; the local in-memory dev server cannot run crons", "expected": "ingest_data run started by the cron scheduler", "command": "", "schedule": "0 8 * * * (daily 08:00 UTC)", "method": "LangGraph cron API (crons.create) on the server", "verdict": "blocked", "outcome": "Cron search on the in-memory dev server returns 'Not implemented' (yarn cron:list against http://localhost:54367). Cron scheduling needs a deployed LangGraph server, and the create-cron script still has the placeholder slackChannelId ADD_SLACK_CHANNEL_ID_HERE plus a SLACK_BOT_TOKEN, so no cycle was run.", "evidence": "Cron search on the in-memory dev server returns 'Not implemented' (yarn cron:list against http://localhost:54367). Cron scheduling needs a deployed LangGraph server, and the create-cron script still has the placeholder slackChannelId ADD_SLACK_CHANNEL_ID_HERE plus a SLACK_BOT_TOKEN, so no cycle was run." } ], "claims": [ { "kind": "claim", "claim": "The LangGraph server starts with the documented script and serves the registered graphs", "source": "To start the LangGraph server, run this script:", "input": "GET assistant e4ac3461-519e-5766-967f-68a84d44fdc6 after yarn langgraph:in_mem:up", "expected": "assistant record for the curated_post_interrupt graph", "command": "yarn langgraph:in_mem:up", "verdict": "yes", "outcome": "Real input produced the expected result: curated_post_interrupt", "evidence": "curated_post_interrupt\",\"metadata\":{\"created_by\":\"system\"},\"name\":\"curated_post_interrupt\",\"description\":null}", "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "Generating a post through the running server requires API keys that were not available here", "source": "Once the server is ready, you can execute the following command to generate a post:", "input": "", "expected": "", "command": "", "verdict": "blocked", "outcome": "yarn generate_post needs ANTHROPIC_API_KEY and FIRECRAWL_API_KEY (plus ARCADE_API_KEY for the quickstart); none were supplied, so no post was generated.", "evidence": "yarn generate_post needs ANTHROPIC_API_KEY and FIRECRAWL_API_KEY (plus ARCADE_API_KEY for the quickstart); none were supplied, so no post was generated.", "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Repository's documented offline unit test suite runs", "source": "package.json scripts.test", "input": "yarn test (jest, *.test.ts, excludes *.int.test.ts)", "command": "yarn -s test", "evidence": " ^\n 3 |\n 4 | // Mock the timezone to 'America/Los_Angeles'\n 5 | // timezoneMock.register(\"US/Pacific\"); // Alternatively, use 'America/Los_Angeles'\n\n at ie (node_modules/dotenv/dist/index.cjs:7:155)\n at Object.ae [as configDotenv] (node_modules/dotenv/dist/index.cjs:7:1128)\n at Object.le [as config] (node_modules/dotenv/dist/index.cjs:7:1237)\n at Object. (jest.setup.cjs:2:19)\n\n\nTest Suites: 6 passed, 6 total\nTests: 4 skipped, 71 passed, 75 total\nSnapshots: 0 total\nTime: 15.52 s\nRan all test suites matching .test.ts$.", "deferred": false, "expected": "all unit test suites pass", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "partly", "maintenance": { "archived": false, "commits_90d": 101, "last_commit_at": "2026-10-23T15:13:11Z", "last_release_at": null, "median_reply_hours": 10.3, "merged_prs_90d": 69, "note": "actively maintained: last commit 0 days ago; 101 commits and 69 merged PRs in 90 days; 14 open issues, 7 open PRs; 5 of 15 recent threads got a maintainer reply, median first reply 10.3h; no releases", "open_issues": 14, "open_prs": 7, "reply_share": 0.33, "reply_threads": 15, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 0 days ago; 101 commits and 69 merged PRs in 90 days; 14 open issues, 7 open PRs; 5 of 15 recent threads got a maintainer reply, median first reply 10.3h; no releases", "maintained": "active", "maintained_note": "last commit 0 days ago", "last_commit_at": "2026-10-23T17:23:07Z", "last_release_at": null, "open_issues": null, "answered_issues": null, "platforms_claimed": [ "linux" ], "topic": "agent-harness", "agent_interfaces": [ { "interface": "cli", "evidence": "README metadata", "observed": false, "operation_checked": false }, { "interface": "api", "evidence": "independent checker", "observed": true, "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": "2026-10-24T00:48:03.890065+00:00", "tested_commit": "7c98af38daaa6b2d721dfcdd2307f3acabd7aa60", "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": "langchain-ai/social-media-agent", "source": "https://github.com/langchain-ai/social-media-agent", "commit": "7c98af38daaa6b2d721dfcdd2307f3acabd7aa60", "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": "7c98af38daaa6b2d721dfcdd2307f3acabd7aa60", "url": "https://github.com/langchain-ai/social-media-agent" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": null, "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Start the LangGraph server with `yarn langgraph:in_mem:up` and call its API (read back the curated_post_interrupt assistant); run the documented unit tests with `yarn test`.", "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/langchain-ai--social-media-agent-claude-haiku-5-5-1792801374124435789.json" }