Files
Lap Tran bc7daf8590 Restore archived tasks, fix dashboard scroll-reset, bind ornith, add Playwright smoke test
- **Restore 82 completed tasks** from tasks/complete/ back to tasks/ top
  level (all <7 days old per the cleanup policy; premature bulk archive
  was fixed).
- **Dashboard: fix scroll-reset on auto-refresh** — renderBoard rebuilds
  the board via innerHTML every 2s, destroying each column-body's
  scrollTop. Now snapshots column-body scrollTop + board.scrollLeft +
  view.scrollTop before rebuild and restores after (matched by
  PHASE_GROUPS index).
- **Dashboard UI additions** (pre-existing unstaged work): approval
  section cards, transition buttons, inline artifact editor (textarea for
  writing missing SPEC/VERDICT/etc from the detail modal).
- **Bind ornith as Implement model** — config.md: Model explicit to
  omlx/Ornith-1.0-35B-4bit-mlx, context window 32768. Interactive
  autopilot already used ornith via opencode default; now explicit.
- **Fix cleanup stub** — automaton-cleanup.sh had a stale --project arg
  pointing at a pytest temp dir (test isolation leak). Rewired to point
  at ~/.automaton.
- **Fix plist-isolation test** — test asserted host plist doesn't exist,
  but a real install creates it. Now snapshots mtime before run, asserts
  unchanged after (only a write during the test counts as bleed).
- **New Playwright smoke test** (tests/test_dashboard_ui.py) — 2 tests:
  board renders tasks, column scroll survives auto-refresh tick.
  Verified the test fails without the scroll fix (scrollTop resets to 0).
  Skipped via importorskip when playwright is absent (main CI stays
  green).
- **Clarify SI loop scope in README** — new-project onboarding section
  documents the framework-scoped self-improvement loop and options
  (leave/pause/create project loop).
- **CHANGELOG** documents all changes including the known model-divergence
  gap (mde tasks marked complete but per-role model binding was never
  implemented).
2026-06-26 10:05:18 -04:00

975 B

SPEC: Upgrade Pre-Commit Hook with Autopilot Awareness

Problem

Agents create throwaway tasks (skip to implement, commit, abandon) to bypass the pre-commit hook. The hook checks for an edit-phase task but doesn't detect hollow/stale tasks or warn about hanging tasks when autopilot is enabled.

Requirements

  1. After a successful pre-commit check, read .agent.md to detect Autopilot: Enabled
  2. If autopilot is enabled, scan all tasks for non-terminal (stuck) tasks
  3. If hanging tasks exist, emit a clear warning in the hook output
  4. Do NOT block the commit — only warn. Blocking would prevent legitimate fixes.
  5. Detect hollow tasks: tasks in implement/doc_review phase with no IMPLEMENTATION.md artifact

Acceptance Criteria

  • Pre-commit hook warns when autopilot is on and non-terminal tasks exist
  • Pre-commit hook warns when the edit task is hollow (no real implementation)
  • Existing blocking behavior (no edit task = DENIED) is preserved unchanged