{ "run_id": "denizsafak--abogen-gpt-6-luna-1792797281598588448", "date": "2026-10-23T23:26:12.981945+00:00", "repo": "denizsafak/abogen", "kind": "repo", "source": "https://github.com/denizsafak/abogen", "commit": "654ec6d6fd35ae55db427dde2b570cfe06114e90", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "pass": false, "outcome": "blocked", "time_to_working_s": null, "total_s": 691.383332490921, "steps": [ "pwd; rg --files -g 'README*' -g 'AGENTS.md' -g 'pyproject.toml' -g 'requirements*.txt' -g 'package.json' | head -80; vault-search 'abogen README setup run' 2>&1 | head -60; cat 2>&1 | head -80", "ls -la; find .. -name AGENTS.md -o -iname 'README*' | head -80; python3 --version; id -u", "cat AGENTS.md; sed -n '1,240p' README.md; cat pyproject.toml", "sudo -n apt-get update && sudo -n apt-get install -y espeak-ng curl; curl -LsSf https://astral.sh/uv/install.sh | sh; . \"$HOME/.local/bin/env\" 2>/dev/null || true; command -v uv || true", "export NODE_USE_ENV_PROXY=1; tool install --python 3.12 abogen", "sed -n '1,120p' abogen/webui/app.py; rg -n 'app.run|Flask\\(|host=|port=' abogen/webui/app.py | tail -20; sed -n '1,30p' README.md", "sed -n '1,200p' abogen/webui/app.py | tail -35; grep -n 'def main\\|app.run\\|host=' abogen/webui/app.py", "mkdir -p .coldpass; cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"\"],\"cwd\":\"\",\"env\":{\"ABOGEN_HOST\":\"127.0.0.1\",\"ABOGEN_PORT\":\"8808\"},\"stays_running\":true,\"expected_text\":\"Serving Flask app\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"The Web UI provides the Flask web interface.\",\"source\":\"| `abogen-web` | Flask Web UI | Core features + **Supertonic TTS**, **LLM Normalization**, **Audiobookshelf Integration** and more! |\",\"input\":\"GET /\",\"expected\":\"Web UI responds with its page\",\"probe_kind\":\"cli\",\"argv\":[\"\"],\"expected_text\":\"Serving Flask app\",\"cwd\":\"\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Launch the documented Web UI\",\"source\":\"README.md, Interfaces\",\"input\":\"Start web server\",\"expected\":\"Flask Web UI starts\",\"argv\":[\"\"],\"cwd\":\"\",\"expected_text\":\"Serving Flask app\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"README/project entrypoints expose interactive conversion and a Flask UI; no product scheduler or cycle trigger was found in entry points inspected.\",\"checks\":[]}\nEOF\n= python3 -I --validate --replay", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"\"],\"cwd\":\"\",\"env\":{\"QT_QPA_PLATFORM\":\"offscreen\"},\"stays_running\":true,\"expected_text\":\"\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Abogen offers two interfaces.\",\"source\":\"Abogen offers **two interfaces**, but currently they have different feature sets.\",\"testable\":false,\"reason\":\"GUI operation requires an interactive display; available environment is headless.\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"README Web UI launch\",\"source\":\"README.md, Interfaces\",\"reason\":\"Launch was tried; startup stalls while fetching model voice assets and exceeded the replay window.\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"README entrypoints provide interactive conversion and a Flask UI; no product scheduler or cycle trigger was identified.\",\"checks\":[]}\nEOF\ncat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"needs_credentials\",\"fault_owner\":\"prerequisite\",\"operation\":\"Launch Abogen Web UI\",\"operation_scope\":\"Linux install with Python 3.12, espeak-ng and uv; Web UI startup also fetches voice assets.\",\"steps\":[\"sudo apt-get update && sudo apt-get install -y espeak-ng curl\",\"curl -LsSf https://astral.sh/uv/install.sh | sh\",\"uv tool install --python 3.12 abogen\",\"abogen-web (README Interfaces command)\"],\"deviations\":[\"README UI startup attempted; voice asset downloads continued beyond the 120 second checker window. HF Hub emitted an unauthenticated-request warning.\"],\"stuck_step\":\"Complete Web UI startup and useful page request\",\"main_blocker\":\"Web UI startup fetches voice assets and exceeds the replay window in this environment.\",\"plain_failure\":\"Installation completed, but the Web UI did not finish initializing within the available replay time.\",\"suggested_fix\":\"Provide a warmed voice cache or higher HF Hub download allowance, then replay the Web UI startup and request its page.\"}\nEOF\n= python3 -I --validate --replay", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"\"],\"cwd\":\"\",\"env\":{\"QT_QPA_PLATFORM\":\"offscreen\"},\"checks\":[{\"check\":\"start\",\"argv\":[\"\"],\"cwd\":\"\",\"env\":{\"QT_QPA_PLATFORM\":\"offscreen\"}}]}\nEOF\n= python3 -I --validate --replay" ], "stuck_step": "Complete Web UI startup and useful page request", "error_excerpt": "Web UI startup fetches voice assets and exceeds the replay window in this environment.", "what_it_did": "Launch Abogen Web UI", "suggested_fix": "Provide a warmed voice cache or higher HF Hub download allowance, then replay the Web UI startup and request its page.", "tokens_in": 283134, "tokens_out": 1905, "cost_usd": null, "usage_complete": true, "checks": [ { "status": "FAIL", "details": { "working": false, "argv": [ "" ], "kind": "cli", "returncode": 1, "stdout": "QT_QPA_PLATFORM_PLUGIN_PATH set to: ", "stderr": "Traceback (most recent call last):\n File \"\", line 4, in \n from abogen.pyqt.main import main\n File \"\", line 81, in \n from PyQt6.QtWidgets import QApplication\nImportError: libGL.so.1: cannot open shared object file: No such file or directory", "needs_credentials": false, "needs_browser": false, "blocker": "product invocation failed: {\"argv\": [\"\"], \"returncode\": 1, \"stdout\": \"QT_QPA_PLATFORM_PLUGIN_PATH set to: \\n\", \"stderr\": \"Traceback (most recent call last):\\n File \\\"\\\", line 4, in \\n from abogen.pyqt.main import main\\n File \\\"\\\", line 81, in \\n from PyQt6.QtWidgets import QApplication\\nImportError: libGL.so.1: cannot open shared object file: No such file or directory\\n\", \"needs_credentials\": false, \"needs_browser\": false}" }, "check": "start", "optional": false } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 1 connection review, 1 hardcoded secret, 1 outside write.", "expected": "Reviewed as expected for a test run: resolver address lookups that send no data.", "findings": [ { "kind": "connection-review", "count": 1, "note": "Repository processes attempted these non-loopback connections; proxies can hide the final hostname.", "location_count": 17, "process_count": 6 }, { "kind": "hardcoded-secret", "count": 1, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 1, "path": "README.md" }, { "kind": "outside-write", "count": 1, "note": "Repository processes attempted these writes outside documented output/cache paths.", "location_count": 54, "process_count": 1, "processes": [ { "executable": "", "owner": "repo", "path": "/blobs/c03bd1a4c3716c2d8eaa3d50022f62d5c31cfbd6e15933a00b17fefe13841cc4", "pid": "3153", "source": "abogen-web" } ] } ], "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=denizsafak--abogen-gpt-6-luna-1792797281598588448", "evidence_file": "/data/safety/denizsafak--abogen-gpt-6-luna-1792797281598588448.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": 10, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "654ec6d6fd35ae55db427dde2b570cfe06114e90", "url": "https://github.com/denizsafak/abogen" }, "purpose": "initial", "profile": { "model": "gpt-6-luna", "reasoning": "low" }, "fault": { "owner": "prerequisite", "status": "diagnosed", "reason": "Web UI startup fetches voice assets and exceeds the replay window in this environment." }, "fix_id": "fix-5244617bf8d80fea2ac5", "verifies_run_id": null, "hosting": null, "operation_scope": "partial checks", "tool_calls": 10, "guest_setup": null, "runtime": null, "runtime_version": null, "runtime_revision": null, "source_revision": null, "evidence_version": null, "failure_origin": "task", "evidence_strength": "nothing_checked", "works": "no", "install_s": null, "first_use_s": null, "mcp": "none", "needs": [], "needs_which": null, "agent_interface": [], "license": "MIT", "repo_url": "https://github.com/denizsafak/abogen", "cost_to_try": null, "hardware": "GPU", "what_failed": "Web UI startup fetches voice assets and exceeds the replay window in this environment.", "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 entrypoints provide interactive conversion and a Flask UI; no product scheduler or cycle trigger was identified.", "evidence": "README entrypoints provide interactive conversion and a Flask UI; no product scheduler or cycle trigger was identified.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Abogen offers two interfaces.", "source": "Abogen offers **two interfaces**, but currently they have different feature sets.", "input": "", "expected": "", "command": "", "verdict": "blocked", "outcome": "GUI operation requires an interactive display; available environment is headless.", "evidence": "GUI operation requires an interactive display; available environment is headless.", "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "README Web UI launch", "source": "README.md, Interfaces", "input": "", "command": "", "evidence": "Launch was tried; startup stalls while fetching model voice assets and exceeded the replay window.", "deferred": false, "expected": "documented command completes successfully", "verdict": "blocked", "outcome": "Launch was tried; startup stalls while fetching model voice assets and exceeded the replay window." } ], "does_what_it_says": null, "maintenance": { "archived": false, "commits_90d": 46, "last_commit_at": "2026-10-17T15:41:21Z", "last_release_at": "2026-02-06T21:04:50Z", "median_reply_hours": 301.0, "merged_prs_90d": 6, "note": "actively maintained: last commit 6 days ago; 46 commits and 6 merged PRs in 90 days; 45 open issues, 3 open PRs; 8 of 29 recent threads got a maintainer reply, median first reply 301.0h; latest release 2026-02-06", "open_issues": 45, "open_prs": 3, "reply_share": 0.28, "reply_threads": 29, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 6 days ago; 46 commits and 6 merged PRs in 90 days; 45 open issues, 3 open PRs; 8 of 29 recent threads got a maintainer reply, median first reply 301.0h; latest release 2026-02-06", "maintained": "active", "maintained_note": "last commit 6 days ago; 9 open issues, 7 answered or closed", "last_commit_at": "2026-10-17T15:41:21Z", "last_release_at": "2026-02-06T21:04:50Z", "open_issues": 9, "answered_issues": 7, "platforms_claimed": [ "linux", "windows" ], "topic": "agent-harness", "agent_interfaces": [ { "interface": "cli", "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": "2026-10-23T23:26:12.981945+00:00", "tested_commit": "654ec6d6fd35ae55db427dde2b570cfe06114e90", "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": "denizsafak/abogen", "source": "https://github.com/denizsafak/abogen", "commit": "654ec6d6fd35ae55db427dde2b570cfe06114e90", "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": "654ec6d6fd35ae55db427dde2b570cfe06114e90", "url": "https://github.com/denizsafak/abogen" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Launch Abogen Web UI", "operation_scope": "partial checks", "hosting": null, "kind": "repo", "test_version": "readme-f72312298d35d84837d4fc5f6f22b138d54d456600b5ed431e36e8f5db931dbf", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": null, "report_url": "/reports/denizsafak--abogen-gpt-6-luna-1792797281598588448.json" }