{ "run_id": "Edge0-AI--Edge0-claude-haiku-5-5-1792759900902418903", "date": "2026-10-23T13:11:31.939938+00:00", "repo": "Edge0-AI/Edge0", "kind": "repo", "source": "https://github.com/Edge0-AI/Edge0", "commit": "e9cc00cfb44b0fd2abf7195dcbe707b75ea6c3e5", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "test_version": "readme-bdc1b9b3c0d2673aef87e076d14084a8123ddcf09d520c1ee2e364a37c3f4bb9", "pass": true, "outcome": "pass", "time_to_working_s": 1142.1141136039514, "total_s": 1191.0374836921692, "steps": [ "cd && pwd && ls -la && git status 2>&1 | head -3; python3 --version; id -u; cat /etc/os-release | head -2; ls /inputs 2>&1", "cd && find . -maxdepth 2 -not -path './.git*' | head -100; echo ---; cat README.md 2>/dev/null | head -200", "cd && sed -n 200,400p README.md", "cd && git init -q 2>&1; git remote add origin https://github.com/Edge0-AI/Edge0 2>&1; timeout 120 git fetch --depth 1 origin e9cc00cfb44b0fd2abf7195dcbe707b75ea6c3e5 2>&1 | tail -5; git reset --mixed FETCH_HEAD 2>&1 | tail -3; git log --oneline -1 2>&1; git status --short | head -5", "uname -m; nproc; free -g | head -2; cd && grep -n -A12 'requires-python\\|dependencies' pyproject.toml | head -60; echo ---; (python3.12 --version 2>&1); python3 -m venv --help >/dev/null 2>&1 && echo venv_ok || echo venv_missing", "cd && python3.12 -m venv .venv && timeout 900 .venv/bin/pip install -e '.[dev,fetch]' > 2>&1; echo rc=$?; tail -25 ", "cd && rm -rf .venv && (sudo -n apt-get update -qq 2>&1 | tail -2; sudo -n DEBIAN_FRONTEND=noninteractive apt-get install -y -qq python3.12-venv 2>&1 | tail -3); echo apt_rc=$?; python3.12 -m venv .venv && echo VENV_OK", "cd && timeout 1500 .venv/bin/pip install -e '.[dev,fetch]' > 2>&1; echo rc=$?; tail -30 ", "cd && .venv/bin/edge0 --help 2>&1 | head -40; echo ---; ls examples scripts tests; echo ---; timeout 600 .venv/bin/pytest -q 2>&1 | tail -15; echo pytest_rc=$?", "cd && .venv/bin/pip show mlx | head -12; .venv/bin/pip show -f mlx | grep -i 'libmlx\\|\\.so' | head; .venv/bin/pip index versions mlx-cpu 2>&1 | head -3; echo; .venv/bin/pip download --no-deps -d mlx-cpu==0.30.6 2>&1 | tail -2", "cd && .venv/bin/pip install 'mlx-cpu==0.30.6' > 2>&1; echo rc=$?; tail -2 ; .venv/bin/edge0 --help 2>&1 | head -40", "cd && .venv/bin/edge0 models 2>&1 | head -20; echo ---; timeout 120 .venv/bin/edge0 chat edge0-8b --prompt \"Explain streaming inference in one sentence.\" 2>&1 | tail -8; echo chat_rc=$?; echo ---; timeout 20 curl -sS -o /dev/null -w '%{http_code}\\n' https://huggingface.co/Edge0/Edge0-8B-A1B-preview/resolve/main/config.json 2>&1; env | grep -i proxy | sed 's/=.*@/=***@/' | head -3", "df -h /tmp | tail -1; cd && sed -n 1,60p scripts/fetch_models.py | grep -n 'add_argument\\|def \\|HF_\\|token' | head -30", "cd && nohup .venv/bin/python scripts/fetch_models.py --tier edge0-8b --target-dir models > 2>&1 &\nsleep 60; tail -c 600 ; echo; du -sh 2>/dev/null", "cd && ls models/edge0-8b; export EDGE0_8B_MODEL=$PWD/models/edge0-8b; time (timeout 900 .venv/bin/edge0 chat edge0-8b --prompt \"Explain streaming inference in one sentence.\" --max-new 48 > 2>); echo rc=$?; tail -c 1500 ; echo ---ERR; tail -c 1500 ", "sudo -n DEBIAN_FRONTEND=noninteractive apt-get install -y -qq g++ > 2>&1; echo apt_rc=$?; which g++; cd && export EDGE0_8B_MODEL=$PWD/models/edge0-8b; time (timeout 1200 .venv/bin/edge0 chat edge0-8b --prompt \"Explain streaming inference in one sentence.\" --max-new 48 > 2>); echo rc=$?; tail -c 1200 ; echo ---ERR; tail -c 800 ", "grep -m3 -n 'error' | cut -c1-400; g++ --version | head -1; cd && grep -rn 'disable_compile\\|MLX_DISABLE\\|mx.compile' src | head -5", "mkdir -p && printf '#!/bin/sh\\nexec /usr/bin/g++ -fpermissive \"$@\"\\n' > && chmod +x ; cd && export PATH= EDGE0_8B_MODEL=$PWD/models/edge0-8b; time (timeout 1200 .venv/bin/edge0 chat edge0-8b --prompt \"Explain streaming inference in one sentence.\" --max-new 48 > 2>); echo rc=$?; tail -c 1500 ; echo ---ERR; grep -m3 'rror' | cut -c1-300; tail -c 300 ", "cd && export PATH=; timeout 1200 .venv/bin/pytest -q 2>&1 | tail -8; echo pytest_rc=${PIPESTATUS[0]}; echo ---; grep -rniE 'cron|schedul|--once|--now|while True|webhook|interval' src/edge0/cli.py src/edge0/server/*.py 2>/dev/null | head -10; grep -n 'temperature\\|do_sample\\|greedy' src/edge0/cli.py | head -5", "cd && sed -n 196,225p src/edge0/server/app.py; echo ---; grep -rn 'temperature' src/edge0/cli.py src/edge0/server/chat.py | head -6; grep -n 'add_argument' src/edge0/cli.py | head -30 | cut -c1-160", "cd && mkdir -p .coldpass && ls -la .coldpass && cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"cli\",\"argv\":[\"\",\"chat\",\"edge0-8b\",\"--prompt\",\"Explain streaming inference in one sentence.\",\"--max-new\",\"48\"],\"cwd\":\"\",\"env\":{\"PATH\":\"\",\"EDGE0_8B_MODEL\":\"\"},\"expected_text\":\"Streaming inference\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"One-shot chat with the edge0 CLI answers a prompt\",\"source\":\"README.md\",\"input\":\"edge0-8b tier with the prompt 'Explain streaming inference in one sentence.' (edge0-35b is not used: 23 GB checkpoint, 3 GB RAM guest)\",\"expected\":\"A one-sentence answer about streaming inference is printed\",\"probe_kind\":\"cli\",\"argv\":[\"\",\"chat\",\"edge0-8b\",\"--prompt\",\"Explain streaming inference in one sentence.\",\"--max-new\",\"48\"],\"env\":{\"PATH\":\"\",\"EDGE0_8B_MODEL\":\"\"},\"expected_text\":\"Streaming inference\",\"cwd\":\"\"}]\nEOF\necho written", "cd && cat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"One-shot chat with the edge0 CLI answers a prompt\",\"source\":\"edge0 chat edge0-35b --prompt \\\"Explain streaming inference in one sentence.\\\"\",\"input\":\"edge0-8b tier (edge0-35b not used: 23 GB checkpoint, 3 GB RAM guest) with the same prompt\",\"expected\":\"A one-sentence answer about streaming inference is printed\",\"probe_kind\":\"cli\",\"argv\":[\"\",\"chat\",\"edge0-8b\",\"--prompt\",\"Explain streaming inference in one sentence.\",\"--max-new\",\"48\"],\"env\":{\"PATH\":\"\",\"EDGE0_8B_MODEL\":\"\"},\"expected_text\":\"Streaming inference\",\"cwd\":\"\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Repository unit tests run offline (no real weights)\",\"source\":\"python/README.md\",\"input\":\"pytest -q in python/ venv\",\"expected\":\"all collected tests pass\",\"argv\":[\"\",\"-q\"],\"cwd\":\"\",\"env\":{\"PATH\":\"\"},\"expected_text\":\"passed\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Entry points inspected: edge0 CLI (demo/chat/serve/models) and python/src/edge0/server/app.py. The only while-True loop (app.py:208) is a per-request streaming queue consumer, not a schedule. No cron, --once, --now, scheduler or webhook trigger exists in the product; serve is a long-running request server, run on demand.\",\"checks\":[]}\nEOF\nfor f in claims examples cycles probe; do python3 -I -c \"import json,sys;json.load(open('.coldpass/$f.json'));print('$f ok')\"; done; ls -la .coldpass; ps aux | grep -c '[e]dge0 serve'", "ls -la 2>&1; cd && = timeout 1500 python3 -I --validate --replay > 2>&1; echo rc=$?; tail -c 3000 ", "head -c 1200 ; echo; echo ...; grep -oiE '\"(problems|errors|problem)\": [^]]{0,300}' | head -5; grep -ci 'fail' ", "cd && cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Run a one-shot generation with the edge0 CLI: `edge0 chat edge0-8b --prompt \\\"Explain streaming inference in one sentence.\\\"`, using the downloaded edge0-8b checkpoint, on Linux x86_64 CPU.\",\"operation_scope\":\"Linux x86_64 guest (Ubuntu 24.04, 2 vCPU, 3 GB RAM), CPU-only MLX build, edge0-8b tier only. The README documents the Python framework as macOS / Apple Silicon only, so this is an unsupported platform that works with the deviations below. edge0-35b (23 GB, needs more RAM) was not run. Unit tests (pytest) and one chat generation were replayed and passed.\",\"steps\":[\"git init; git remote add origin https://github.com/Edge0-AI/Edge0; git fetch --depth 1 origin e9cc00cfb44b0fd2abf7195dcbe707b75ea6c3e5; git reset --mixed FETCH_HEAD\",\"cd python && python3.12 -m venv .venv && .venv/bin/pip install -e '.[dev,fetch]'\",\"export EDGE0_8B_MODEL=$PWD/models/edge0-8b; .venv/bin/python scripts/fetch_models.py --tier edge0-8b --target-dir models\",\"edge0 chat edge0-8b --prompt \\\"Explain streaming inference in one sentence.\\\" --max-new 48\",\"pytest (unit tests, in python/ venv)\"],\"deviations\":[\"python3.12 -m venv failed: ensurepip not available. Fixed with sudo apt-get install python3.12-venv, then reran the README install command unchanged.\",\"pip install -e '.[dev,fetch]' succeeded but `edge0` failed at import: libmlx.so missing. The mlx 0.30.6 Linux wheel does not include the CPU library. Installed mlx-cpu==0.30.6 (same version, not in README/pyproject) into the venv.\",\"First chat failed: MLX CPU JIT needs g++, which was missing. Fixed with sudo apt-get install g++.\",\"Second chat failed: GCC 13 rejects MLX's generated CPU kernel (redeclaration of built-in type '_Float32'). Worked around by a PATH-first g++ wrapper at that adds -fpermissive. This is an environment-only change outside the repo; no product source was edited. The probe and claim env set PATH to use this wrapper.\",\"Chat generation on CPU is slow: about 90 s for 37-39 tokens with edge0-8b.\",\"Cycles: none. The product has no cron, --once, --now, scheduler or webhook trigger; the while-True loop in server/app.py is a streaming queue consumer. cycles.json is detected:false.\",\"README tier example used edge0-35b; the claim uses edge0-8b because 35b is too large for this guest. Model checkpoint directory python/models (4.3 GB) and python/.venv are left in the checkout.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":\"Documentation/product: state Linux support status explicitly (the README says macOS Apple Silicon only). For Linux CPU, the mlx-cpu package and a -fpermissive or newer-GCC build of the MLX CPU JIT are needed; the README should list these prerequisites (python3.12-venv, g++, mlx-cpu) and the GCC 13 incompatibility should be reported upstream to MLX.\"}\nEOF\npython3 -I -c \"import json;d=json.load(open('.coldpass/report.json'));print(d['outcome'])\"; ps aux | grep -E '[e]dge0|[f]etch_models|[p]ytest' | head -3; echo procs_checked", "cd && = timeout 1500 python3 -I --validate --replay > 2>&1; echo checker_rc=$?; head -c 300 ; echo; grep -o '\"status\": \"[A-Z]*\"' | sort | uniq -c" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Run a one-shot generation with the edge0 CLI: `edge0 chat edge0-8b --prompt \"Explain streaming inference in one sentence.\"`, using the downloaded edge0-8b checkpoint, on Linux x86_64 CPU.", "suggested_fix": null, "tokens_in": 793600, "tokens_out": 17881, "cost_usd": 0.027256330000000002, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "argv": [ "", "chat", "edge0-8b", "--prompt", "Explain streaming inference in one sentence.", "--max-new", "48" ], "kind": "cli", "returncode": 0, "stdout": "[lora] applied=153 not_found=0 skipped=0 scale=2.0\n[edge0-8b] prerouter installed: 16 heads, start=7, K=8\n[edge0-8b] built in 0.9s\nStreaming inference is the technique of processing and sending model responses in real-time as they are generated, rather than waiting for a full computation to complete before outputting results.", "stderr": "# 33 tokens in 83.553s", "needs_credentials": false, "needs_browser": false, "scope": "product operation" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 1 connection review, 61 known vulnerability.", "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": 14, "process_count": 8 }, { "kind": "known-vulnerability", "count": 55, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 19 } ], "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=Edge0-AI--Edge0-claude-haiku-5-5-1792759900902418903", "evidence_file": "/data/safety/Edge0-AI--Edge0-claude-haiku-5-5-1792759900902418903.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": 26, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "e9cc00cfb44b0fd2abf7195dcbe707b75ea6c3e5", "url": "https://github.com/Edge0-AI/Edge0" }, "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": 26, "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": "Apache-2.0", "repo_url": "https://github.com/Edge0-AI/Edge0", "cost_to_try": "free", "hardware": "GPU", "what_failed": null, "local_or_hosted": "both", "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": "Entry points inspected: edge0 CLI (demo/chat/serve/models) and python/src/edge0/server/app.py. The only while-True loop (app.py:208) is a per-request streaming queue consumer, not a schedule. No cron, --once, --now, scheduler or webhook trigger exists in the product; serve is a long-running request server, run on demand.", "evidence": "Entry points inspected: edge0 CLI (demo/chat/serve/models) and python/src/edge0/server/app.py. The only while-True loop (app.py:208) is a per-request streaming queue consumer, not a schedule. No cron, --once, --now, scheduler or webhook trigger exists in the product; serve is a long-running request server, run on demand.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "One-shot chat with the edge0 CLI answers a prompt", "source": "edge0 chat edge0-35b --prompt \"Explain streaming inference in one sentence.\"", "input": "edge0-8b tier (edge0-35b not used: 23 GB checkpoint, 3 GB RAM guest) with the same prompt", "expected": "A one-sentence answer about streaming inference is printed", "command": " chat edge0-8b --prompt 'Explain streaming inference in one sentence.' --max-new 48", "verdict": "yes", "outcome": "Real input produced the expected result: Streaming inference", "evidence": "Streaming inference is the technique of processing and generating responses from an AI model in real-time as data is being streamed, rather than waiting for a complete input to be processed before output begins.\n# 37 tokens in 92.297s\n", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Repository unit tests run offline (no real weights)", "source": "python/README.md", "input": "pytest -q in python/ venv", "command": " -q", "evidence": "........................................................................ [ 39%]\n.......................................................ss..s............ [ 78%]\n....................................... [100%]\n180 passed, 3 skipped, 4 deselected in 16.15s", "deferred": false, "expected": "all collected tests pass", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": "yes", "maintenance": { "last_commit_at": "2026-10-22T07:59:58Z", "commits_90d": 163, "merged_prs_90d": 38, "open_issues": 5, "open_prs": 2, "reply_share": 0.62, "reply_threads": 29, "median_reply_hours": 167.0, "last_release_at": "2026-10-21T07:11:13Z", "archived": false, "verdict": "maintained", "note": "actively maintained: last commit 1 days ago; 163 commits and 38 merged PRs in 90 days; 5 open issues, 2 open PRs; 18 of 29 recent threads got a maintainer reply, median first reply 167.0h; latest release 2026-10-21" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 1 days ago; 163 commits and 38 merged PRs in 90 days; 5 open issues, 2 open PRs; 18 of 29 recent threads got a maintainer reply, median first reply 167.0h; latest release 2026-10-21", "maintained": "active", "maintained_note": "last commit 1 days ago; 2 open issues, 11 answered or closed", "last_commit_at": "2026-10-22T07:59:59Z", "last_release_at": "2026-10-21T07:11:13Z", "open_issues": 2, "answered_issues": 11, "platforms_claimed": [ "mac", "windows" ], "topic": "other", "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": "2026-10-23T13:11:31.939938+00:00", "tested_commit": "e9cc00cfb44b0fd2abf7195dcbe707b75ea6c3e5", "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": "Edge0-AI/Edge0", "source": "https://github.com/Edge0-AI/Edge0", "commit": "e9cc00cfb44b0fd2abf7195dcbe707b75ea6c3e5", "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": "e9cc00cfb44b0fd2abf7195dcbe707b75ea6c3e5", "url": "https://github.com/Edge0-AI/Edge0" }, "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 a one-shot generation with the edge0 CLI: `edge0 chat edge0-8b --prompt \"Explain streaming inference in one sentence.\"`, using the downloaded edge0-8b checkpoint, on Linux x86_64 CPU.", "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/Edge0-AI--Edge0-claude-haiku-5-5-1792759900902418903.json" }