{ "run_id": "gleanwork--glean-indexing-sdk-gpt-6-luna-1793156162727469187", "date": "2026-10-28T02:58:16.587688+00:00", "repo": "gleanwork/glean-indexing-sdk", "kind": "repo", "source": "https://github.com/gleanwork/glean-indexing-sdk", "commit": "8b6a809814922ca77bf21f80d9b5bbbc6e1f457f", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-3be879002729975eaa9c9bc49f02188330eb783b8fc02944604e0325529353be", "pass": true, "outcome": "pass", "time_to_working_s": 109.14433744599955, "total_s": 133.86018180847168, "steps": [ "pwd && id -u && python3 --version && rg --files -g 'README*' -g 'pyproject.toml' -g 'package.json' -g 'Cargo.toml' -g 'go.mod' -g '.github/workflows/**' | head -80", "ls -la; find . -maxdepth 3 -type f | head -100", "cat README.md", "cat .python-version; cat package.json; cat pyproject.toml | head -100; cat CONTRIBUTING.md | head -100; command -v uv; command -v node; command -v npm", "uv --version && node --version && npm --version && sed -n '1,160p' mise.toml && find src/glean/indexing -maxdepth 3 -type f | head -60", "IGNORE", "NODE_USE_ENV_PROXY=1 npm ci", "uv sync --locked --extra dev --extra test --extra lint --extra typing", "uv run glean-idx --help", "uv run glean-idx schema document | head -12; sed -n '1,100p' snippets/non_streaming/complete.py", "uv run python - <<'PY'\nfrom glean.indexing.connectors import BaseDataClient, BaseDatasourceConnector\nfrom glean.indexing.models import ContentDefinition, CustomDatasourceConfig, DocumentDefinition\nfrom glean.indexing.testing import StaticDataClient, run_connector\nclass Connector(BaseDatasourceConnector):\n configuration = CustomDatasourceConfig(name='sample', display_name='Sample', url_regex=r'https://example\\.com/.*')\n def transform(self, data):\n return [DocumentDefinition(id=x['id'], title=x['title'], datasource=self.name, view_url=x['url'], body=ContentDefinition(mime_type='text/plain', text_content=x['body'])) for x in data]\nresult = run_connector(Connector('sample', StaticDataClient([{'id':'doc-1','title':'Hello','url':'https://example.com/hello','body':'sample body'}])))\nprint(result)\nPY", "NODE_USE_ENV_PROXY=1 npm run test:plugins", "sed -n '1,220p' src/glean/indexing/testing/mock_client.py; sed -n '1,150p' src/glean/indexing/testing/__init__.py; sed -n '1,100p' src/glean/indexing/cli/commands/schema.py", "grep -n -E 'def run_connector|assert_documents' src/glean/indexing/testing/runner.py; mkdir -p .coldpass", "sed -n '1,74p' src/glean/indexing/testing/runner.py", "cat > /tmp/quickstart_probe.py <<'PY'\nfrom datetime import datetime\nfrom typing import List, Sequence\nfrom glean.indexing.connectors import BaseDataClient, BaseDatasourceConnector\nfrom glean.indexing.models import ContentDefinition, CustomDatasourceConfig, DocumentDefinition, UserReferenceDefinition\nfrom glean.indexing.testing import StaticDataClient, run_connector\nclass Connector(BaseDatasourceConnector):\n configuration = CustomDatasourceConfig(name='companywiki', display_name='Company Wiki', url_regex=r'https://wiki\\\\.company\\\\.com/.*', is_user_referenced_by_email=True)\n def transform(self, data: Sequence[dict]) -> List[DocumentDefinition]:\n return [DocumentDefinition(id=p['id'], title=p['title'], datasource=self.name, view_url=p['url'], body=ContentDefinition(mime_type='text/plain', text_content=p['content']), author=UserReferenceDefinition(email=p['author']), updated_at=int(datetime.fromisoformat(p['updated_at'].replace('Z','+00:00')).timestamp())) for p in data]\nresult = run_connector(Connector('companywiki', StaticDataClient([{'id':'page_123','title':'Engineering Onboarding Guide','content':'Welcome','author':','updated_at':'2026-02-01T14:30:00Z','url':'https://wiki.company.com/pages/123'}])))\nresult.assert_documents_posted(count=1, datasource='companywiki')\nprint('Engineering Onboarding Guide')\nPY\nuv run python /tmp/quickstart_probe.py", "cat > .coldpass/probe.json <<'JSON'\n{\"kind\":\"cli\",\"argv\":[\"uv\",\"run\",\"python\",\"/tmp/quickstart_probe.py\"],\"cwd\":\"\",\"expected_text\":\"Engineering Onboarding Guide\"}\nJSON\ncat > .coldpass/claims.json <<'JSON'\n[{\"kind\":\"claim\",\"claim\":\"The SDK runs a connector against mocked data and supports an assertion that one document was posted.\",\"source\":\"result.assert_documents_posted(count=1, datasource=\\\"companywiki\\\")\",\"input\":\"A sample wiki page with id page_123.\",\"expected\":\"One document is recorded for datasource companywiki.\",\"probe_kind\":\"cli\",\"argv\":[\"uv\",\"run\",\"python\",\"/tmp/quickstart_probe.py\"],\"expected_text\":\"Engineering Onboarding Guide\",\"cwd\":\"\"}]\nJSON\ncat > .coldpass/cycles.json <<'JSON'\n{\"detected\":false,\"reason\":\"README and SDK entry points inspected: indexing is explicitly invoked with connector.index_data(mode=IndexingMode.FULL or INCREMENTAL); no SDK scheduler or automatic cycle trigger is documented.\",\"checks\":[]}\nJSON", "cat > .coldpass/examples.json <<'JSON'\n[{\"kind\":\"example\",\"claim\":\"README connector testing helper runs a connector against fake records and records indexed documents.\",\"source\":\"README.md, Quickstart; documented testing helper\",\"input\":\"One page_123 wiki document passed to StaticDataClient.\",\"expected\":\"The connector run succeeds and emits the sample document title.\",\"argv\":[\"uv\",\"run\",\"python\",\"/tmp/quickstart_probe.py\"],\"cwd\":\"\",\"expected_text\":\"Engineering Onboarding Guide\"},{\"kind\":\"example\",\"claim\":\"Build and validate the bundled plugin targets.\",\"source\":\"package.json scripts.test:plugins\",\"input\":\"Repository plugin sources.\",\"expected\":\"Build succeeds and all target validations pass.\",\"argv\":[\"npm\",\"run\",\"test:plugins\"],\"cwd\":\"\",\"env\":{\"NODE_USE_ENV_PROXY\":\"1\"},\"expected_text\":\"Validation passed.\"}]\nJSON\ncat > .coldpass/report.json <<'JSON'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Run a sample connector with the SDK testing helper and build/validate agent plugins.\",\"operation_scope\":\"Python 3.10 virtual environment with locked dev/test/lint/typing dependencies; Node 22.23.4 used for plugin validation despite package engine requiring >=24.15.0.\",\"steps\":[\"uv sync --locked --extra dev --extra test --extra lint --extra typing\",\"uv run glean-idx schema document\",\"npm ci\",\"npm run test:plugins\",\"uv run python /tmp/quickstart_probe.py\"],\"deviations\":[\"Plugin build and all validations passed under Node 22.23.4, while package.json declares >=24.15.0; npm ci emitted EBADENGINE warning.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nJSON", "= python3 -I --validate --replay", "grep -n -E 'test --phase|StaticDataClient|run_connector|schema document|quickstart' README.md", "cat src/glean/indexing/cli/commands/test.py | head -140", "python3 - <<'PY'\nimport json\np='.coldpass/probe.json'; d=json.load(open(p)); d['argv']=['uv','run','glean-idx','schema','document']; d['expected_text']='\"name\": \"document\"'; open(p,'w').write(json.dumps(d))\np='.coldpass/claims.json'; c=json.load(open(p)); c[0].update(claim='`glean-idx schema document` prints the JSON Schema your `transform()` has to produce.',source='`glean-idx schema document` prints the JSON Schema your `transform()` has to\\nproduce.',input='document schema request',expected='JSON schema output identifies DocumentDefinition.',probe_kind='cli',argv=['uv','run','glean-idx','schema','document'],expected_text='\"name\": \"document\"'); open(p,'w').write(json.dumps(c))\np='.coldpass/examples.json'; e=json.load(open(p)); e[0].update(source='README.md, The CLI',argv=['uv','run','glean-idx','schema','document'],input='document schema request',expected='JSON schema output identifies document.',expected_text='\"name\": \"document\"'); open(p,'w').write(json.dumps(e))\nPY", "= python3 -I --validate --replay", "python3 - <<'PY'\nimport json\np='.coldpass/claims.json'; c=json.load(open(p)); c[0]['source']='`glean-idx schema document` prints the JSON Schema your `transform()` has to\\nproduce.'; open(p,'w').write(json.dumps(c))\nPY", "= python3 -I --validate --replay", "python3 - <<'PY'\nimport json\np='.coldpass/claims.json'; c=json.load(open(p)); c[0]['source']='`glean-idx schema document` prints the JSON Schema your `transform()` has to'; c[0]['claim']='`glean-idx schema document` prints the JSON Schema your `transform()` has to'; open(p,'w').write(json.dumps(c))\nPY", "= python3 -I --validate --replay" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Run a sample connector with the SDK testing helper and build/validate agent plugins.", "suggested_fix": null, "tokens_in": 660145, "tokens_out": 3090, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "uv", "run", "glean-idx", "schema", "document" ], "kind": "cli", "returncode": 0, "stdout": "\u2026tion\": \"Describes the custom properties of the object.\",\n \"properties\": {\n \"name\": {\n \"anyOf\": [\n {\n \"type\": \"string\"\n },\n {\n \"type\": \"null\"\n }\n ],\n \"default\": null,\n[excerpt truncated]", "stderr": "", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 31 known vulnerability.", "findings": [ { "kind": "known-vulnerability", "count": 31, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 8 } ], "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=gleanwork--glean-indexing-sdk-gpt-6-luna-1793156162727469187", "evidence_file": "/data/safety/gleanwork--glean-indexing-sdk-gpt-6-luna-1793156162727469187.json.gz" }, "agent_execution": "native_agent", "agent_runtime": "codex", "agent_runtime_version": "codex-cli 0.164.0", "tool_transport": "mcp-assigned-vm", "platform": "linux", "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "native_tool_calls": 27, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "8b6a809814922ca77bf21f80d9b5bbbc6e1f457f", "url": "https://github.com/gleanwork/glean-indexing-sdk" }, "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": 27, "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/gleanwork/glean-indexing-sdk", "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 SDK entry points inspected: indexing is explicitly invoked with connector.index_data(mode=IndexingMode.FULL or INCREMENTAL); no SDK scheduler or automatic cycle trigger is documented.", "evidence": "README and SDK entry points inspected: indexing is explicitly invoked with connector.index_data(mode=IndexingMode.FULL or INCREMENTAL); no SDK scheduler or automatic cycle trigger is documented.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "`glean-idx schema document` prints the JSON Schema your `transform()` has to", "source": "`glean-idx schema document` prints the JSON Schema your `transform()` has to", "input": "document schema request", "expected": "JSON schema output identifies DocumentDefinition.", "command": "uv run glean-idx schema document", "verdict": "yes", "outcome": "Real input produced the expected result: \"name\": \"document\"", "evidence": "\u2026\"name\": \"document\",\n \"model\": \"DocumentDefinition\",\n \"schema\": {\n \"$defs\": {\n \"CommentDefinition\": {\n \"description\": \"Describes a comment on a document\",\n \"properties\": {\n \"id\": {\n \"title\": \"Id\",\n \"type\": \"string\"\n },\n \"author\": {\n \"anyOf\": [\n {\n \"$ref\": \"#/$defs/UserReferenceDefinition\"\n },\n {\n \"type\": \"null\"\n }\n ],\n \"default\": null\n },\n \"content\"", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "README connector testing helper runs a connector against fake records and records indexed documents.", "source": "README.md, The CLI", "input": "document schema request", "command": "uv run glean-idx schema document", "evidence": " \"type\": \"null\"\n }\n ],\n \"default\": null,\n \"title\": \"Comments\"\n },\n \"customProperties\": {\n \"anyOf\": [\n {\n \"items\": {\n \"$ref\": \"#/$defs/CustomProperty\"\n },\n \"type\": \"array\"\n },\n {\n \"type\": \"null\"\n }\n ],\n \"default\": null,\n \"title\": \"Customproperties\"\n }\n },\n \"required\": [\n \"datasource\"\n ],\n \"title\": \"DocumentDefinition\",\n \"type\": \"object\"\n }\n }\n}", "deferred": false, "expected": "JSON schema output identifies document.", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" }, { "kind": "example", "claim": "Build and validate the bundled plugin targets.", "source": "package.json scripts.test:plugins", "input": "Repository plugin sources.", "command": "npm run test:plugins", "evidence": " test:plugins\n> npm run build:plugins && npm run validate:plugins\n\n\n> @gleanwork/glean-indexing-sdk-agent-plugin@1.2.2 build:plugins\n> pluginpack build\n\nWrote 10 managed files for cursor -> \nWrote 10 managed files for claude -> \nWrote 10 managed files for codex -> \n\n> @gleanwork/glean-indexing-sdk-agent-plugin@1.2.2 validate:plugins\n> pluginpack validate --target claude --dir . && pluginpack validate --target cursor --dir . && pluginpack validate --target codex --dir .\n\nValidation passed.\nValidation passed.\nValidation passed.", "deferred": false, "expected": "Build succeeds and all target validations pass.", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "archived": false, "commits_90d": 83, "last_commit_at": "2026-10-28T00:19:29Z", "last_release_at": "2026-10-28T00:21:42Z", "median_reply_hours": null, "merged_prs_90d": 75, "note": "slow: last commit 0 days ago; 83 commits and 75 merged PRs in 90 days; 2 open issues, 2 open PRs; 0 of 41 recent threads got a maintainer reply; latest release 2026-10-28", "open_issues": 2, "open_prs": 2, "reply_share": 0.0, "reply_threads": 41, "verdict": "slow" }, "maintenance_verdict": "slow", "maintenance_note": "slow: last commit 0 days ago; 83 commits and 75 merged PRs in 90 days; 2 open issues, 2 open PRs; 0 of 41 recent threads got a maintainer reply; latest release 2026-10-28", "maintained": "active", "maintained_note": "last commit 0 days ago; 1 open issues, 0 answered or closed", "last_commit_at": "2026-10-28T00:19:43Z", "last_release_at": "2026-10-28T00:21:42Z", "open_issues": 1, "answered_issues": 0, "platforms_claimed": [ "linux" ], "topic": "data", "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": "2026-10-28T02:58:16.587688+00:00", "tested_commit": "8b6a809814922ca77bf21f80d9b5bbbc6e1f457f", "tested_with": { "agent": "codex", "agent_version": "codex-cli 0.164.0", "model": "gpt-6-luna", "model_route": "gpt-6-luna", "reasoning": "low", "os": "linux", "backend": "hyperv", "transport": "mcp-assigned-vm" }, "setup_identity": { "repo": "gleanwork/glean-indexing-sdk", "source": "https://github.com/gleanwork/glean-indexing-sdk", "commit": "8b6a809814922ca77bf21f80d9b5bbbc6e1f457f", "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 0.164.0", "tool_transport": "mcp-assigned-vm", "runtime": null, "runtime_version": null, "runtime_revision": null, "sandbox_source": null, "guest_setup": null, "source_pin": { "commit": "8b6a809814922ca77bf21f80d9b5bbbc6e1f457f", "url": "https://github.com/gleanwork/glean-indexing-sdk" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Run a sample connector with the SDK testing helper and build/validate agent plugins.", "operation_scope": "product operation", "hosting": null, "kind": "repo", "test_version": "readme-3be879002729975eaa9c9bc49f02188330eb783b8fc02944604e0325529353be", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": "/transcripts/gleanwork--glean-indexing-sdk-gpt-6-luna-1793156162727469187.txt", "report_url": "/reports/gleanwork--glean-indexing-sdk-gpt-6-luna-1793156162727469187.json" }