{ "checker": { "claims": [ { "claim": "demo runs offline on synthetic sessions", "command": " demo", "evidence": "DEMO complete: temporary sessions removed; nothing sent.\n", "expected": "synthetic demo completes with nothing sent", "input": "sidecarwatch demo", "kind": "claim", "outcome": "Real input produced the expected result: DEMO complete: temporary sessions removed; nothing sent.", "returncode": 0, "source": "`demo` uses temporary synthetic sessions, calls no agent CLI or model, and removes its data.", "source_checked": true, "source_file": "README.md", "verdict": "yes" }, { "claim": "status shows cross-vendor review state", "command": " status", "evidence": "Cross-vendor review: OFF\nConfig: \nKill switch: off\nNeeds you: 0 open; run open to inspect.\n", "expected": "reports cross-vendor review OFF by default", "input": "sidecarwatch status", "kind": "claim", "outcome": "Real input produced the expected result: Cross-vendor review: OFF", "returncode": 0, "source": "- `status` shows whether cross-vendor review is ON or OFF.", "source_checked": true, "source_file": "README.md", "verdict": "yes" }, { "claim": "watch without interval makes one pass", "command": " watch --only --dry-run", "evidence": "0 in scope \u00b7 0 reviewed \u00b7 0 sent \u00b7 0 would send \u00b7 0 need you\n", "expected": "single pass summary printed, then exit", "input": "watch --only --dry-run", "kind": "claim", "outcome": "Real input produced the expected result: 0 in scope", "returncode": 0, "source": "Without `--interval`, a run makes one pass.", "source_checked": true, "source_file": "README.md", "verdict": "yes" } ], "cycle_checks": [ { "claim": "watch runs one pass and stops when no interval is set", "command": " watch --only --dry-run", "evidence": "03:46 0 in scope \u00b7 0 reviewed \u00b7 0 sent \u00b7 0 would send \u00b7 0 need you", "expected": "one pass summary line, then process exits 0", "input": "watch --only --dry-run (no --interval)", "kind": "cycle", "method": "run-once: invoke the watch command by hand once, no interval, dry-run, no source edits", "outcome": "Triggered one cycle by hand (run-once: invoke the watch command by hand once, no interval, dry-run, no source edits; normal trigger: README: Without --interval, a run makes one pass. Interval loops are not used here (no timer installed).): 03:46 0 in scope \u00b7 0 reviewed \u00b7 0 sent \u00b7 0 would send \u00b7 0 need you", "returncode": 0, "schedule": "README: Without --interval, a run makes one pass. Interval loops are not used here (no timer installed).", "source": "sidecarwatch/watch.py", "verdict": "yes" } ], "details": { "argv": [ "", "demo" ], "kind": "cli", "needs_browser": false, "needs_credentials": false, "returncode": 0, "scope": "product operation", "stderr": "", "stdout": "DEMO: synthetic sessions; no CLI calls.\ncodex session aaaaaaaa (idle)\nWhat it is doing\nAdding CSV export to the reading list and checking a small export test.\n\nOn task: ok\nIn scope: ok\nSimple: ok\nReuse: ok\nRoot cause: ok\nHonest: ok\n\n[excerpt truncated]", "working": true }, "evidence_strength": "readme_checked", "example_checks": [ { "claim": "synthetic demo quickstart with system Python 3.14", "command": "/opt/homebrew/bin/python3 -B -m sidecarwatch demo", "deferred": false, "evidence": "DEMO: synthetic sessions; no CLI calls.\ncodex session aaaaaaaa (idle)\nWhat it is doing\nAdding CSV export to the reading list and checking a small export test.\n\nOn task: ok\nIn scope: ok\nSimple: ok\nReuse: ok\nRoot cause: ok\nHonest: ok\n\nShould you correct it? no\n\nLabel: WORKING\nSuggested message (not sent)\nReport the export test results when they are available.\nDEMO complete: temporary sessions removed; nothing sent.", "expected": "offline demo output", "input": "python3 -B -m sidecarwatch demo", "kind": "example", "outcome": "command completed successfully", "returncode": 0, "source": "README.md Quickstart: Linux", "verdict": "yes" }, { "claim": "doctor reports local setup and review OFF", "command": " doctor --shapes", "deferred": false, "evidence": "y\n Scanned: ~/.claude/projects/*/*.jsonl\n Login: unverified; CLI executable unavailable or --help failed; check the configured command (or use --reviewer with the same CLI)\n Reviewer flags: \n Shapes: (none)\n Unknown lines: 0; mostly unknown sessions: 0\ncodex: review unavailable \n Home: ~/.codex; sessions: 0; delivery: print only\n Scanned: ~/.codex/sessions/**/rollout-*.jsonl\n Login: unverified; CLI executable unavailable or --help failed; check the configured command (or use --reviewer with the same CLI)\n Reviewer flags: \n Shapes: (none)\n Unknown lines: 0; mostly unknown sessions: 0", "expected": "local setup report", "input": "doctor --shapes", "kind": "example", "outcome": "command completed successfully", "returncode": 0, "source": "README.md Check your own setup", "verdict": "yes" }, { "claim": "documented unit test suite passes", "command": " -B -m unittest discover -s tests -t . -q", "deferred": false, "evidence": "----------------------------------------------------------------------\nRan 215 tests in 83.246s\n\nOK (skipped=1)", "expected": "all tests pass", "input": "python3 -B -m unittest discover -s tests -t . -q", "kind": "example", "outcome": "command completed successfully", "returncode": 0, "source": "README.md Check your own setup (To run the test suite from source)", "verdict": "yes" } ], "status": "PASS" }, "deviations": [ "Guest is macOS, not Linux; used the README's macOS guidance where it applies.", "uv is not installed in the guest. Used the README's documented `python3 -m venv .venv` route with Homebrew Python 3.14 (>=3.11) instead of `uv venv --python 3.12`. The README's macOS table lists uv 3.12 as the tested route; 3.14 was not the tested interpreter.", "`timeout` is not available on macOS, so the first git fetch command failed with `timeout: command not found`; re-ran the same fetch without it and it succeeded.", "`sidecarwatch init` was not run, so no config or profile was created and review stays OFF.", "No real Claude Code or Codex sessions exist in this VM, so `sessions` is empty and `doctor` reports both CLIs unavailable; this is expected and not a product fault.", "Unit test suite ran with `.venv/bin/python3` (absolute venv path) rather than an activated `python3`. Same command otherwise." ], "fault_owner": null, "main_blocker": null, "operation": "Run the sidecarwatch offline synthetic demo (`sidecarwatch demo`), plus status, one-pass watch, doctor, and the unit test suite", "operation_scope": "macOS arm64 guest (Darwin 24.6), Python 3.14.8 from Homebrew (README requires 3.11+), venv at .venv, no agent CLIs, no login, cross-vendor review OFF, no network calls to reviewers. Pinned commit 8ddf4cf.", "outcome": "working", "plain_failure": null, "steps": [ "git init; git remote add origin https://github.com/TayHCode/sidecarwatch; git fetch --depth 1 origin 8ddf4cfed6d91ad621ad9b0fcc7bf4c4c39901fe; git reset --mixed FETCH_HEAD", "python3 -B -m sidecarwatch demo (from source folder; README Quickstart)", "/opt/homebrew/bin/python3 -m venv .venv (README alternative to uv)", "source .venv/bin/activate && python3 -m pip install .", "sidecarwatch --version", "python3 -B -m unittest discover -s tests -t . -q (README: Check your own setup)", "sidecarwatch doctor --shapes; sidecarwatch sessions; sidecarwatch status", "sidecarwatch watch --only --dry-run" ], "stuck_step": null, "suggested_fix": null }