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).

tasks/rewrite-vram-detection-python/IMPLEMENTATION.md

@@ -0,0 +1,26 @@
+# Implementation: Rewrite VRAM Detection as Python Script
+
+## Summary
+Replaced `scripts/vram_detect.sh` with `scripts/vram_detect.py`, a testable Python implementation that produces the same JSON output and fixes several bugs.
+
+## Files Changed
+- `scripts/vram_detect.py` (new)
+- `scripts/vram_detect.sh` (deleted)
+- `scripts/install.sh` — updated to run Python script and parse JSON with Python
+- `README.md` — updated references
+- `prompts/onboarding.md` — updated references and invocation
+- `prompts/decompose.md` — updated references
+- `prompts/orchestrate.md` — updated references
+
+## Bugs Fixed
+- Undefined `$headroom_pct` in manual mode.
+- Hardcoded `"headroom": 0.25` in JSON output.
+- Code-block values in `config.md` being parsed as live config.
+- GPU-counting/output ordering bug.
+- 10KB file-read limit now enforced for API config files.
+
+## Verification
+- `python scripts/vram_detect.py` runs and emits valid JSON.
+- `python scripts/vram_detect.py gpt-4o` detects 128k context.
+- `python scripts/vram_detect.py --model claude-3-5-sonnet` detects 200k context.
+- `rg "vram_detect\.sh" README.md scripts/install.sh prompts/` returns no matches.