{
  "checker": {
    "claims": [
      {
        "claim": "Each piece of work becomes a task with an acceptance criterion",
        "command": "grimoire task show GAO-fix-the-csv-001",
        "evidence": "\u2026Fix the CSV export\n  \u00e9tat    : ready (board : ready)\n  accepte : pytest tests/test_export.py passes\n  v\u00e9rifiabilit\u00e9 : V1 \u2014 Remont\u00e9e de V0 : les crit\u00e8res nomment un verdict \nm\u00e9canique mais aucune commande n'est d\u00e9clar\u00e9e (`checks`) \u2014 rien \u00e0 ex\u00e9cuter, le \nverdict reste \u00e0 rendre par une revue.\n  mod\u00e8le recommand\u00e9 : sonnet (palier : mid)\n    - pytest tests/test_export.py passes \u2192 test\n  usage   : none\n  vers in_progress : context_bundle, provider_policy\n",
        "expected": "task shows its title and acceptance criterion",
        "input": "task show GAO-fix-the-csv-001 in demo project after task add",
        "kind": "claim",
        "outcome": "Real input produced the expected result: Fix the CSV export",
        "returncode": 0,
        "source": "Each piece of work becomes a task with an acceptance criterion.",
        "source_checked": true,
        "source_file": "README.md",
        "verdict": "yes"
      },
      {
        "claim": "Project memory carries decisions across sessions and is searchable",
        "command": "grimoire memory search SQLite",
        "evidence": "\u2026f7d6884c-ab6 \u2502 We keep      \u2502 non v\u00e9rifi\u00e9 \u2502 saisie      \u2502 2026-10-28 \u2502 0.000 \u2502\n\u2502              \u2502 SQLite while \u2502             \u2502 libre       \u2502            \u2502       \u2502\n\u2502              \u2502 the volume   \u2502             \u2502             \u2502            \u2502       \u2502\n\u2502              \u2502 allows it    \u2502             \u2502             \u2502            \u2502       \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2534\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n",
        "expected": "stored memory is returned with its id",
        "input": "memory search SQLite after memory remember -t decisions -a claude",
        "kind": "claim",
        "outcome": "Real input produced the expected result: f7d6884c-ab6",
        "returncode": 0,
        "source": "What the project decided carries over from one session to the next.",
        "source_checked": true,
        "source_file": "README.md",
        "verdict": "yes"
      },
      {
        "claim": "Grimoire checks that a task's evidence exists before it changes state",
        "command": "grimoire standard gate check",
        "evidence": "\u2026evidence gates for task bootstrap (state: proposed)\n",
        "expected": "gate check reports evidence gates for the task",
        "input": "grimoire standard gate check in demo project",
        "kind": "claim",
        "outcome": "Real input produced the expected result: evidence gates for task bootstrap",
        "returncode": 0,
        "source": "Before a task changes state, Grimoire checks that its evidence exists",
        "source_checked": true,
        "source_file": "README.md",
        "verdict": "yes"
      }
    ],
    "cycle_checks": [
      {
        "claim": "scheduled orchestrate tick runs periodically",
        "command": "grimoire orchestrate tick --project-root <guest-path>",
        "evidence": "Plan : 0 r\u00e9colte(s), 0 r\u00e9veil(s), 0 effet(s) constat\u00e9(s), 0 cr\u00e9neau(x) CI \nrendu(s), 0 orphelin(s) lib\u00e9r\u00e9(s), 1 admise(s), 0 diff\u00e9r\u00e9e(s).\nPlan (copie du ledger, rien n'est \u00e9crit) : relancer avec --apply pour \u00e9crire.",
        "expected": "tick prints a plan and writes nothing",
        "input": "--project-root <guest-path>",
        "kind": "cycle",
        "method": "run-once: manual invocation of the same tick in its default --plan mode (no --apply, nothing written)",
        "outcome": "Triggered one cycle by hand (run-once: manual invocation of the same tick in its default --plan mode (no --apply, nothing written); normal trigger: systemd user timer or crontab line from install-timer (default 5m), running orchestrate tick --apply): Plan : 0 r\u00e9colte(s), 0 r\u00e9veil(s), 0 effet(s) constat\u00e9(s), 0 cr\u00e9neau(x) CI \nrendu(s), 0 orphelin(s) lib\u00e9r\u00e9(s), 1 admise(s), 0 diff\u00e9r\u00e9e(s).\nPlan (copie du ledger, rien n'est \u00e9crit) : relancer avec --apply pour \u00e9crire.",
        "returncode": 0,
        "schedule": "systemd user timer or crontab line from install-timer (default 5m), running orchestrate tick --apply",
        "source": "src/grimoire/missions/timer.py",
        "verdict": "yes"
      }
    ],
    "details": {
      "argv": [
        "grimoire",
        "task",
        "show",
        "GAO-fix-the-csv-001"
      ],
      "kind": "cli",
      "needs_browser": false,
      "needs_credentials": false,
      "returncode": 0,
      "scope": "product operation",
      "stderr": "GAO-fix-the-csv-001 \u2014 Fix the CSV export\n  \u00e9tat    : ready (board : ready)\n  accepte : pytest tests/test_export.py passes\n  v\u00e9rifiabilit\u00e9 : V1 \u2014 Remont\u00e9e de V0 : les crit\u00e8res nomment un verdict \nm\u00e9canique mais aucune commande n'est d\u00e9clar\u00e9e (`checks`) \u2014 rien \u00e0 ex\u00e9cuter, le \nverdict reste \u00e0 rendre par une revue.\n  mod\u00e8le recommand\u00e9 : sonnet (palier : mid)\n    - pytest tests/test_export.py passes \u2192 test\n  usage   : none\n  vers in_progress : context_bundle, provider_policy",
      "stdout": "",
      "working": true
    },
    "evidence_strength": "readme_checked",
    "example_checks": [
      {
        "claim": "Set up a project with the governed profile so the evidence check blocks",
        "command": "grimoire standard init . --profile governed",
        "deferred": false,
        "evidence": "already exists; use --force to \noverwrite\n  \u21b7 _grimoire/standard/remediation-plan.yaml already exists; use --force to \noverwrite\n  \u21b7 _grimoire/standard/accepted-risks.yaml already exists; use --force to \noverwrite\n  \u21b7 _grimoire/standard/waivers.yaml already exists; use --force to overwrite\n  \u21b7 _grimoire/standard/observability-policy.yaml already exists; use --force to \noverwrite\n  \u21b7 _grimoire/standard/standard-profile.yaml already exists; use --force to \noverwrite\n  [OK] hook d'activation Claude Code install\u00e9 (SessionStart -> grimoire standard\nactivation-context)\n    [OK] .claude/settings.json",
        "expected": "governed standard files are written",
        "input": "grimoire standard init . --profile governed in demo project",
        "kind": "example",
        "outcome": "command completed successfully",
        "returncode": 0,
        "source": "README.md quickstart: grimoire standard init . --profile governed",
        "verdict": "yes"
      }
    ],
    "status": "PASS"
  },
  "deviations": [
    "The README's memory example `grimoire memory remember \"...\"` fails: the CLI requires --type and --agent. Re-ran with -t decisions -a claude, which succeeded. The README example is incomplete.",
    "Installed from PyPI via the README's uv command rather than from the pinned checkout; the PyPI version 3.72.0 matches version.txt.",
    "Used --lite -y --no-cockpit instead of plain --lite -y to keep the throwaway project out of the cockpit registry; --lite is deprecated and accepted as default.",
    "Did not run the 640+ unit test suite (make test / pytest tests/unit) from CONTRIBUTING.md; it is offline and was not used as evidence.",
    "Scheduled tick was triggered by hand in its default --plan mode, not --apply, so nothing was written or launched."
  ],
  "fault_owner": null,
  "main_blocker": null,
  "operation": "Install grimoire-kit with the README's uv command, set up a project with grimoire init, then create, read back and check tasks, project memory and the evidence gate",
  "operation_scope": "Linux Ubuntu 24.04 guest, Python 3.12.3, uv 0.13.5 preinstalled, grimoire-kit 3.72.0 from PyPI (matches version.txt). Ran in a fresh throwaway project <guest-path> with --no-cockpit so nothing was enrolled in the cockpit registry. Dashboard (grimoire cockpit start) and the complet Docker memory stack were not exercised. No browser or CDP endpoint was needed.",
  "outcome": "working",
  "plain_failure": null,
  "steps": [
    "uv tool install grimoire-kit",
    "grimoire init . --lite -y --no-cockpit (in fresh git-initialised demo project)",
    "grimoire task add \"Fix the CSV export\" -a \"pytest tests/test_export.py passes\" --ready",
    "grimoire memory remember \"We keep SQLite while the volume allows it\" -t decisions -a claude",
    "grimoire memory search SQLite",
    "grimoire standard gate check",
    "grimoire standard init . --profile governed",
    "grimoire orchestrate tick (manual run of the scheduled tick, plan mode)"
  ],
  "stuck_step": null,
  "suggested_fix": "Update the README memory example to include the required --type and --agent options, e.g. grimoire memory remember \"...\" -t decisions -a claude."
}