Lap Tran
bc7daf8590
- **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).
56 lines
2.8 KiB
Markdown
56 lines
2.8 KiB
Markdown
# Implementation: Status Script
|
|
|
|
## Changes Made
|
|
|
|
### 1. Core script: `scripts/status.py` (980 lines)
|
|
Full implementation of all commands specified in the SPEC:
|
|
|
|
- `--task {name}` — Shows phase, allowed/forbidden actions, next artifact, next phase, approval status
|
|
- `--list` — Lists all tasks with phase and next step
|
|
- `--create-task {name}` — Creates task folder with `.state`=new, validates kebab-case, refuses duplicates
|
|
- `--transition {phase}` — Validates and writes `.state` transitions, refuses illegal transitions, refuses past `:awaiting_approval` without `--approve`, validates required artifacts and forbidden artifacts
|
|
- `--approve` — Transitions `:awaiting_approval` → `:approved`, records in `.state.approvals`, refuses if not in awaiting_approval sub-state
|
|
- `--validate-folder` — Checks for out-of-order artifacts, flags manually created tasks
|
|
- `--audit` — Four categories: out-of-order artifacts, state-artifact inconsistency, unauthorized git modifications, manually created tasks
|
|
- `--claim / --release` — Multi-agent task claiming with `.state.lock` files, timeout, overclaiming
|
|
- `--next-available / --available` — Work discovery for multi-agent, filters by agent role
|
|
- `--can-edit` — Returns ALLOWED/DENIED based on current phase
|
|
- `--scope-check` — Returns IN_SCOPE/OUT_OF_SCOPE for file paths
|
|
- `--same-session` — Heuristic session check
|
|
|
|
### 2. Approval sub-states
|
|
- Phases with approval: research, decomposition, design, test_design
|
|
- Sub-states: `{phase}:awaiting_approval` and `{phase}:approved`
|
|
- `--transition` refuses past `:awaiting_approval` without `--approve`
|
|
- `--approve` records timestamp and approver in `.state.approvals`
|
|
|
|
### 3. Forbidden artifacts per phase
|
|
- Full mapping from SPEC implemented in FORBIDDEN_ARTIFACTS dict
|
|
- `--validate-folder` checks and reports violations
|
|
- `--transition` refuses if forbidden artifacts exist
|
|
|
|
### 4. Multi-agent support
|
|
- Agent Configuration parsed from `.agent.md`
|
|
- `.state.lock` files with agent ID, phase, claimed timestamp, expiry
|
|
- Configurable lock timeout (default 30 min)
|
|
- `--claim` validates agent is configured for the phase
|
|
- `--next-available` returns highest-priority unclaimed task matching agent phases
|
|
|
|
### 5. Tests: `tests/test_status.py` (25 tests)
|
|
- Create task (valid, invalid names, duplicates)
|
|
- State transitions (legal, illegal, approval gates)
|
|
- Approval gates (approve, refuse wrong phase, record log)
|
|
- Folder validation (valid, no state file, out-of-order artifacts)
|
|
- Artifact validation (missing required, forbidden)
|
|
- Show task (phase display, allowed/forbidden)
|
|
- List tasks
|
|
- Tool hooks (can-edit, scope-check)
|
|
- Audit (manual tasks, clean tasks)
|
|
|
|
## Files Created
|
|
- `scripts/status.py` (980 lines)
|
|
- `tests/test_status.py` (25 test cases)
|
|
|
|
## Test Results
|
|
- 183 tests passing (including all 25 new status.py tests)
|
|
- Python compilation clean |