{ "run_id": "Atrayee-dev--secure-ai-agent-boundary-claude-haiku-5-5-1793058313793756339", "date": "2026-10-26T23:46:22.743303+00:00", "repo": "Atrayee-dev/secure-ai-agent-boundary", "kind": "repo", "source": "https://github.com/Atrayee-dev/secure-ai-agent-boundary", "commit": "410c962288e34d0d3baacc34012cda4af51f0ac9", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "test_version": "readme-ca496ea10bb07418d1d8f1c256c2433a55547acc0fb62d8b6d86ae33c976fbfa", "pass": false, "outcome": "blocked", "time_to_working_s": null, "total_s": 68.94951510429382, "steps": [ "cd && pwd && ls -la && id -u && python3 --version && (git -C . rev-parse 2>/dev/null || echo \"not git\") && ls /inputs 2>/dev/null; ls 2>/dev/null", "cd && cat README.md 2>/dev/null | head -c 7000; echo; echo ---; find . -maxdepth 2 -not -path './.git*' | head -100", "cd && tail -c +7000 README.md | head -c 4500; echo; echo ---; ls -la .github .github/* ; grep -n -i \"install\\|pip\\|npm\\|python\\|run\\|usage\\|\\$ \" README.md | head -40", "cd && cat .github/workflows/UvWBoLBblbqu.yml; echo ---; file .github/feXHEbontYwhhU; head -c 300 .github/feXHEbontYwhhU | cat -v | head -20", "cd && grep -o -i -E \"(pip install|npm |npx |curl [^<\\\"]*|git clone[^<\\\"]*|python[0-9]* [^<\\\"]*|codeboundary [a-z-]*|docker [a-z]*)\" index.html | sort | uniq -c | head -30; echo \"---title:\"; grep -o \"[^<]*\" index.html; echo \"--- find code files:\"; find . -type f \\( -name \"*.py\" -o -name \"*.js\" -o -name \"*.ts\" -o -name \"package.json\" -o -name \"pyproject.toml\" -o -name \"setup.py\" -o -name \"*.yml\" -o -name \"Makefile\" \\) | grep -v \"^./.coldpass\"; echo \"--- pages:\"; grep -o -i \"href=\\\"[^\\\"]*\\\"\" index.html | head -15", "cd <guest-path> && ls -la .coldpass; grep -n -E \"argparse|add_argument|def main|--validate|--replay\" <guest-path> | head -30; echo; sed -n 1,30p index.html | head -c 1200", "mkdir -p <guest-path> && cat > <guest-path> <<'EOF'\n[\n {\"kind\":\"claim\",\"claim\":\"Install-free operation\",\"source\":\"CodeBoundary does not require installing a daemon, patching your kernel, or running a heavyweight control plane.\",\"testable\":false,\"reason\":\"The snapshot contains no installable package, source code, entry point, or install command. README.md, index.html, two SVG files and a scheduled GitHub Actions workflow are the only files present.\"},\n {\"kind\":\"claim\",\"claim\":\"Primary entry point is a config file\",\"source\":\"The primary entry point is a file called `.codeboundary.yml` at the root of your repository.\",\"testable\":false,\"reason\":\"No .codeboundary.yml exists in the snapshot and no program in the snapshot reads one, so there is nothing to run or read back.\"}\n]\nEOF\npython3 -I -c 'import json,sys; json.load(open(sys.argv[1])); print(\"claims ok\")' <guest-path>", "cd <guest-path> && cat > probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"codeboundary\"],\"cwd\":\"<guest-path>\",\"checks\":[]}\nEOF\ncat > cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Inspected README.md, index.html and .github/workflows/UvWBoLBblbqu.yml. The only schedule is a GitHub Actions cron ('0 * * * *') that appends a timestamp line to .github/feXHEbontYwhhU and commits it to main; it is a CI schedule, not a product cycle, and it was not run. No product scheduler, daemon, loop or --once entry point exists in the snapshot.\",\"checks\":[]}\nEOF\ncat > examples.json <<'EOF'\n[\n {\"kind\":\"example\",\"claim\":\"Run the documented CodeBoundary quickstart\",\"source\":\"README.md\",\"reason\":\"README.md has no install, build, run or CLI command section. The only executable-looking material is the GitHub Actions workflow, which is a CI schedule and not product usage.\"},\n {\"kind\":\"example\",\"claim\":\"Run the repository's own test suite\",\"source\":\"README.md\",\"reason\":\"No test files, package manifest, Makefile or test command exist in the snapshot; nothing was run.\"}\n]\nEOF\npython3 -I -c 'import json; [json.load(open(f)) for f in [\"probe.json\",\"cycles.json\",\"examples.json\"]]; print(\"ok\")' 2>&1; ls -la", "cd <guest-path> && cat > report.json <<'EOF'\n{\"outcome\":\"blocked\",\"fault_owner\":\"repo\",\"operation\":\"Install and run CodeBoundary as documented in README.md, then exercise one real product operation\",\"operation_scope\":\"Pinned snapshot Atrayee-dev/secure-ai-agent-boundary at 410c962288e34d0d3baacc34012cda4af51f0ac9, Linux VM, Python 3.12.3 available. No browser or credentials were needed.\",\"steps\":[\"Read README.md in full (concept and configuration description only; no install, build, run or CLI commands).\",\"Listed the snapshot: README.md, index.html, button.svg, preview.svg, .github/workflows/UvWBoLBblbqu.yml and .github/feXHEbontYwhhU (a timestamp log file).\",\"Searched index.html and README.md for install/run commands (pip, npm, npx, curl, git clone, python, docker): none found.\",\"Searched for source or package files (*.py, *.js, *.ts, package.json, pyproject.toml, setup.py, Makefile): none found, apart from the workflow file.\"],\"deviations\":[\"No product install was possible: the snapshot has no installer, package or source code, so the README's installer step does not exist.\",\"probe.json uses argv ['codeboundary'] as a placeholder for a nonexistent executable, with checks [] as the unavailable-executable form. No product operation was run, so no product output was observed.\",\"The GitHub Actions workflow (hourly cron committing to main) was inspected but not run, because it is a CI schedule and not a product entry point.\",\"Did not hand-write product code or substitute a made-up CLI.\"],\"stuck_step\":\"Locating an installable product: README.md has no runnable command, and no source or package exists in the snapshot.\",\"main_blocker\":\"The pinned snapshot contains documentation and a static page only, with no runnable CodeBoundary program.\",\"plain_failure\":\"This repository does not contain the CodeBoundary program. The README describes how the tool is meant to work, but it gives no way to install or start it, and the files here are only a description, a web page and an automated timestamp bot. Nothing could be run, so nothing was confirmed to work.\",\"suggested_fix\":\"Publish the CodeBoundary source or package in the repository (for example a pyproject.toml or package.json, plus the CLI entry point), add install and quickstart commands to README.md, and include a test or example that runs one real operation such as creating a .codeboundary.yml and reading it back.\"}\nEOF\npython3 -I -c 'import json; json.load(open(\"report.json\")); print(\"report ok\")'; cd <guest-path> && <env-var>=<guest-path> python3 -I <guest-path> --validate --replay; echo \"exit=$?\"" ], "stuck_step": "Locating an installable product: README.md has no runnable command, and no source or package exists in the snapshot.", "error_excerpt": "The pinned snapshot contains documentation and a static page only, with no runnable CodeBoundary program.", "what_it_did": "Install and run CodeBoundary as documented in README.md, then exercise one real product operation", "suggested_fix": "Publish the CodeBoundary source or package in the repository (for example a pyproject.toml or package.json, plus the CLI entry point), add install and quickstart commands to README.md, and include a test or example that runs one real operation such as creating a .codeboundary.yml and reading it back.", "tokens_in": 138290, "tokens_out": 6031, "cost_usd": 0.00866685, "usage_complete": true, "checks": [ { "check": "operation", "status": "FAIL", "details": { "working": false, "blocker": "no checks supplied" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "No problems traced to this repository code in these checks.", "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=Atrayee-dev--secure-ai-agent-boundary-claude-haiku-5-5-1793058313793756339", "evidence_file": "/data/safety/Atrayee-dev--secure-ai-agent-boundary-claude-haiku-5-5-1793058313793756339.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": 9, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "410c962288e34d0d3baacc34012cda4af51f0ac9", "url": "https://github.com/Atrayee-dev/secure-ai-agent-boundary" }, "purpose": "initial", "profile": { "model": "claude-haiku-5-5", "reasoning": "low" }, "fault": { "owner": "repo", "status": "diagnosed", "reason": "The pinned snapshot contains documentation and a static page only, with no runnable CodeBoundary program." }, "fix_id": "fix-95e5d2a301c251497174", "verifies_run_id": null, "hosting": null, "operation_scope": "Pinned snapshot Atrayee-dev/secure-ai-agent-boundary at 410c962288e34d0d3baacc34012cda4af51f0ac9, Linux VM, Python 3.12.3 available. No browser or credentials were needed.", "tool_calls": 9, "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": null, "repo_url": "https://github.com/Atrayee-dev/secure-ai-agent-boundary", "cost_to_try": null, "hardware": null, "what_failed": "The pinned snapshot contains documentation and a static page only, with no runnable CodeBoundary program.", "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": "Inspected README.md, index.html and .github/workflows/UvWBoLBblbqu.yml. The only schedule is a GitHub Actions cron ('0 * * * *') that appends a timestamp line to .github/feXHEbontYwhhU and commits it to main; it is a CI schedule, not a product cycle, and it was not run. No product scheduler, daemon, loop or --once entry point exists in the snapshot.", "evidence": "Inspected README.md, index.html and .github/workflows/UvWBoLBblbqu.yml. The only schedule is a GitHub Actions cron ('0 * * * *') that appends a timestamp line to .github/feXHEbontYwhhU and commits it to main; it is a CI schedule, not a product cycle, and it was not run. No product scheduler, daemon, loop or --once entry point exists in the snapshot.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Install-free operation", "source": "CodeBoundary does not require installing a daemon, patching your kernel, or running a heavyweight control plane.", "input": "", "expected": "", "command": "", "verdict": "blocked", "outcome": "The snapshot contains no installable package, source code, entry point, or install command. README.md, index.html, two SVG files and a scheduled GitHub Actions workflow are the only files present.", "evidence": "The snapshot contains no installable package, source code, entry point, or install command. README.md, index.html, two SVG files and a scheduled GitHub Actions workflow are the only files present.", "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "Primary entry point is a config file", "source": "The primary entry point is a file called `.codeboundary.yml` at the root of your repository.", "input": "", "expected": "", "command": "", "verdict": "blocked", "outcome": "No .codeboundary.yml exists in the snapshot and no program in the snapshot reads one, so there is nothing to run or read back.", "evidence": "No .codeboundary.yml exists in the snapshot and no program in the snapshot reads one, so there is nothing to run or read back.", "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Run the documented CodeBoundary quickstart", "source": "README.md", "input": "", "command": "", "evidence": "README.md has no install, build, run or CLI command section. The only executable-looking material is the GitHub Actions workflow, which is a CI schedule and not product usage.", "deferred": false, "expected": "documented command completes successfully", "verdict": "blocked", "outcome": "README.md has no install, build, run or CLI command section. The only executable-looking material is the GitHub Actions workflow, which is a CI schedule and not product usage." }, { "kind": "example", "claim": "Run the repository's own test suite", "source": "README.md", "input": "", "command": "", "evidence": "No test files, package manifest, Makefile or test command exist in the snapshot; nothing was run.", "deferred": false, "expected": "documented command completes successfully", "verdict": "blocked", "outcome": "No test files, package manifest, Makefile or test command exist in the snapshot; nothing was run." } ], "does_what_it_says": null, "maintenance": { "last_commit_at": "2026-10-26T21:26:21Z", "commits_90d": 811, "merged_prs_90d": 0, "open_issues": 0, "open_prs": 0, "reply_share": null, "reply_threads": 0, "median_reply_hours": null, "last_release_at": null, "archived": false, "verdict": "maintained", "note": "actively maintained: last commit 0 days ago; 811 commits and 0 merged PRs in 90 days; 0 open issues, 0 open PRs; no releases" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 0 days ago; 811 commits and 0 merged PRs in 90 days; 0 open issues, 0 open PRs; no releases", "maintained": "active", "maintained_note": "last commit 0 days ago", "last_commit_at": "2026-10-26T21:26:21Z", "last_release_at": null, "open_issues": null, "answered_issues": null, "platforms_claimed": [ "linux" ], "topic": "agent-harness", "agent_interfaces": [], "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": "2026-10-26T23:46:22.743303+00:00", "tested_commit": "410c962288e34d0d3baacc34012cda4af51f0ac9", "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": "Atrayee-dev/secure-ai-agent-boundary", "source": "https://github.com/Atrayee-dev/secure-ai-agent-boundary", "commit": "410c962288e34d0d3baacc34012cda4af51f0ac9", "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": "410c962288e34d0d3baacc34012cda4af51f0ac9", "url": "https://github.com/Atrayee-dev/secure-ai-agent-boundary" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": null, "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Install and run CodeBoundary as documented in README.md, then exercise one real product operation", "operation_scope": "Pinned snapshot Atrayee-dev/secure-ai-agent-boundary at 410c962288e34d0d3baacc34012cda4af51f0ac9, Linux VM, Python 3.12.3 available. No browser or credentials were needed.", "hosting": null, "kind": "repo", "test_version": "readme-ca496ea10bb07418d1d8f1c256c2433a55547acc0fb62d8b6d86ae33c976fbfa", "evidence_version": null }, "other_model": null, "other_run_id": null, "models_agree": null, "furthest_model": null, "transcript_url": "/transcripts/Atrayee-dev--secure-ai-agent-boundary-claude-haiku-5-5-1793058313793756339.txt", "report_url": "/reports/Atrayee-dev--secure-ai-agent-boundary-claude-haiku-5-5-1793058313793756339.json" }