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
parent fe43b9e1fc
commit bc7daf8590
666 changed files with 15994 additions and 69 deletions
@@ -0,0 +1 @@
+complete
@@ -0,0 +1,3 @@
+research:approved|2026-06-21T18:49:57.561180+00:00|user
+code_review:approved|2026-06-21T19:23:42.696319+00:00|user
+code_review:approved|2026-06-21T22:25:35.675228+00:00|user
@@ -0,0 +1,3 @@
+# ADVERSARIAL_BUG_REPORT
+
+10/10 streak independent checker. No findings.
@@ -0,0 +1,3 @@
+# BUG_REPORT
+
+No bugs. Streak verifier saw no failures.
@@ -0,0 +1,3 @@
+# CODE_REVIEW
+
+10-streak verifier passed on attempt 1. See IMPLEMENTATION.md.
@@ -0,0 +1,3 @@
+# DOC_REVIEW
+
+Doc changes in IMPLEMENTATION.md.
@@ -0,0 +1,46 @@
+# IMPLEMENTATION — vram-detect-cross-platform
+
+**Implementer:** local LLM (gemma-4-26B-A4B-it-uncensored-Q4_K_M.gguf via headroom @ localhost:8787, model id `local-llm`)
+**Orchestrator:** opencode (glm-5.2)
+
+## What changed in `scripts/vram_detect.py`
+
+| Function | Author | Change |
+|---|---|---|
+| `import platform` (new top-level import) | Orchestrator (mechanical) | Added to support `platform.system()` dispatch |
+| `detect_gpu_vram()` | Local LLM | Branched on `platform.system()`. Linux: unchanged. Darwin: `system_profiler SPDisplaysDataType` parser (Apple Silicon → unified memory via `sysctl -n hw.memsize`; Intel Macs → `VRAM (Total):`). Windows: `wmic path win32_VideoController get AdapterRAM,Name /format:list` + PowerShell fallback. |
+| `detect_ram()` + `_detect_ram_linux/_darwin/_windows()` | Local LLM + Orchestrator refactor | Local LLM produced inline branches; Orchestrator extracted private helpers to match subtask-3 test contract (`_detect_ram_linux()`). Linux path byte-identical. macOS: `sysctl hw.memsize` (no available RAM, reports total). Windows: `wmic` + PowerShell fallback. |
+| `MODEL_CONTEXT_WINDOWS` | Local LLM | Added 14 local-LLM entries (llama-3.1, qwen2.5, mistral, deepseek-r1/v3, glm-4/4.5, gemma-2, phi-3/4) with source-cited context sizes. Conservative values where YaRN extends context. |
+| `_probe_ollama_model()` (new) | Local LLM | Calls `ollama list`, parses first non-header row's NAME column, strips `:latest`. Returns None on any error or if ollama not installed. |
+| `detect_model_context()` | Orchestrator (mechanical wire-up) | Calls `_probe_ollama_model()` as last-resort fallback after all config-file probes fail. |
+| `run_command()` | Local LLM | On Windows, if first cmd arg starts with `Get-` or contains `CimInstance`, rewrites cmd to `['powershell', '-NoProfile', '-NoLogo', '-Command', ' '.join(cmd)]` before `shutil.which` check. Preserves Linux behavior. |
+
+## BEFORE vs AFTER on this Darwin arm64 (Apple M5, 32GB)
+
+- **BEFORE:** `gpu_vram_gb: 0` (macOS not supported, falls through to "no GPU")
+- **AFTER:** `gpu_vram_gb: 32`, `GPU: Apple Silicon (unified memory)`, `Total System RAM (Shared VRAM): 32768 MB`
+- Target context correctly jumped 12k → 42k (reflects shared VRAM budget).
+- JSON shape unchanged (same 8 keys, same order, same types).
+
+## Anti-spin rails that fired
+
+- **Signature mismatch on `_detect_ram_linux()`:** subtask-3's test expected a private helper; local LLM's first refactor put Linux path inline in `detect_ram()`. Orchestrator (me) extracted the helper to match the test contract — NOT weakening the test, the opposite: making code more testable per the contract.
+- All other local-LLM output was applied verbatim after passing py_compile.
+
+## Streak verifier result
+
+```
+STREAK_COMPLETE attempt=1 clean=10/10
+```
+
+The independent checker model (the streak verifier, per article #2/#9/#13) ran the full suite 10 consecutive times with no edits between. The worker (local LLM) did not grade its own homework.
+
+## Test count
+
+- 235 passed (was 224; subtask-3 added 11 cross-platform tests).
+- 0 errors, 0 skipped.
+- Suite runtime ~3.5s.
+
+## Files touched (and ONLY this file)
+
+- `scripts/vram_detect.py` (+ 1 new top-level import, +14 dict entries, +1 new helper function `_probe_ollama_model`, refactor of 3 existing functions, +1 new branch in `run_command`, +1 wire-up call in `detect_model_context`)
@@ -0,0 +1,60 @@
+# Parent Task: runnable-test-suite
+
+This is the parent SPEC for the runnable-test-suite task. Each sub-task references
+this for context, scope boundaries, and the parent acceptance contract.
+
+## Parent Goal
+
+Make `python3 -m pytest tests/ -v` pass from a clean checkout of `~/.automaton`,
+with deterministic Python deps pinned and docs that reflect the actual interpreter
+on stock macOS/Windows/Linux. In the same wave, make `scripts/vram_detect.py`
+cross-platform (macOS, Windows, Linux) — the existing version was developed on
+Cachyos and only fully works on Linux.
+
+## Parent Acceptance Contract
+
+1. `pip3 install -r requirements.txt` succeeds on stock macOS CommandLineTools + pip3.
+2. `python3 -m pytest tests/ -v` exits 0 from a clean clone, zero `error` lines.
+3. **Streak verifier:** 10 consecutive clean `python3 -m pytest tests/ -v` runs with
+   no edits between runs. A single failure resets the count. Cap: 5 attempts.
+4. `python3 -m py_compile automaton/**/*.py automaton/dashboard/**/*.py scripts/*.py` exits 0.
+5. `bash -n scripts/*.sh` exits 0.
+6. `rg "^python " AGENTS.md README.md automaton/dashboard/README.md prompts/orchestrate.md`
+   returns zero matches for a bare `python ` command.
+7. `python3 scripts/vram_detect.py` on Darwin prints `gpu_vram_gb > 0` (was 0 before).
+8. `python3 scripts/vram_detect.py` JSON shape identical to before on Linux/Cachyos.
+
+## Sub-tasks
+
+- `make-tests-runnable` — Wave 1, parallel-ok
+- `vram-detect-cross-platform` — Wave 1, parallel-ok
+- `vram-detect-cross-platform-tests` — Wave 2, depends on `vram-detect-cross-platform`
+
+Parent is complete ONLY when ALL three sub-tasks pass and the streak verifier above
+runs 10 consecutive clean passes.
+
+## Anti-spin rails (from the source article)
+
+- The streak verifier IS the independent checker model from Boris's loop. The
+  worker (local LLM) does not grade its own homework.
+- If a test is genuinely broken (not just import-failing due to missing pytest),
+  STOP and report. Do not patch the test to make it pass. An agent that grades
+  itself will delete the failing test and call it done.
+- Unknown model name → fail open with `0`. Wrong-context detection is worse than none.
+- No new third-party deps beyond `pytest`. Pure stdlib for `vram_detect.py`.
+
+## Hardware/VRAM context
+
+- Detected by `vram_detect.py` on this box: **32GB RAM, no GPU, model unknown**
+  (because `vram_detect.py` is broken on macOS — subtask-2 fixes that)
+- Target context: 12k tokens, headroom 25%, max peak per sub-task: 9k tokens.
+- Sub-task peak estimates all fit within 9k. No further decomposition.
+
+## Constraints / non-goals (parent)
+
+- No `psutil`, `wmi`, `pywin32`, `tox`, `pytest-cov`, or other third-party deps.
+- No removal of existing OpenAI/Anthropic entries in `MODEL_CONTEXT_WINDOWS`.
+- No changes to `status.py`, `autopilot.py`, or any other runtime script's behavior.
+- No touching files under `tasks/` (those are state, not source).
+- No Docker, no conda, no `pyenv`. Stock `python3` + `pip3` only.
+- VRAM detection is additive — Linux/Cachyos output must NOT regress.
@@ -0,0 +1,124 @@
+# SPEC — vram-detect-cross-platform
+
+Parent: `runnable-test-suite` (see PARENT_SPEC.md).
+
+## Scope
+
+Make `scripts/vram_detect.py` work on macOS, Windows, and Linux without behavior
+change on Cachyos/Linux. The existing version was developed on Cachyos and only
+fully works on Linux. Pure detection logic — no CLI/JSON-shape changes.
+
+## Files this sub-task touches (and ONLY this)
+
+- `scripts/vram_detect.py` — surgical edits to detection functions only.
+
+## MUST NOT touch
+
+- `tests/test_vram_detect.py` (subtask-3 owns all vram_detect tests)
+- Any other test file
+- Any documentation, prompt, or install script (subtask-1 owns those)
+- CLI args, JSON output shape, main() flow — only detection internals
+
+## Functions to refactor (by current line in `scripts/vram_detect.py`)
+
+### `run_command()` (vram_detect.py:54-70)
+- On Windows, route PowerShell cmdlets via `powershell -NoProfile -NoLogo -Command "..."` wrapper.
+- Keep `shutil.which()` gating so missing tools return None on all OSes.
+- Do not break Linux path.
+
+### `detect_gpu_vram()` (vram_detect.py:73-108)
+Branch on `platform.system()`:
+- **Linux**: keep `nvidia-smi` → `lspci -vnn` path exactly as-is. Regression guard.
+- **Darwin** (macOS): add `system_profiler SPDisplaysDataType` parser.
+  Parse `VRAM (Total):` line for Intel Macs, and for Apple Silicon unified memory,
+  detect `Chipset Model: Apple M*` and treat total RAM as shared VRAM (call
+  `sysctl -n hw.memsize` once and use that number, since Apple Silicon has no
+  dedicated VRAM). Print clearly which kind was detected.
+  Fallback (if `system_profiler` missing): `ioreg -c IOPlatformDevice -r -d 1`.
+- **Windows**: add `wmic path win32_VideoController get AdapterRAM,Name /format:list`
+  (deprecated but ubiquitous; works on Win10/11). Sum `AdapterRAM=` values across
+  GPUs. PowerShell fallback:
+  `powershell -NoProfile -Command "Get-CimInstance Win32_VideoController | Select-Object AdapterRAM"`
+
+### `detect_ram()` (vram_detect.py:137-162)
+Branch on `platform.system()`:
+- **Linux**: keep `/proc/meminfo` path. Parse `MemTotal` + `MemAvailable`. Regression guard.
+- **Darwin**: keep `sysctl -n hw.memsize` path (currently the fallback; promote to
+  the macOS branch as primary). Returns (total_kb, total_kb) because macOS doesn't
+  expose "available RAM" via sysctl directly — leave available == total. Print clear
+  "available RAM detection not supported on macOS, reporting total" message once.
+- **Windows**: add `wmic ComputerSystem get TotalPhysicalMemory /format:list`.
+  Returns bytes — divide by 1024 for KB. PowerShell fallback:
+  `powershell -NoProfile -Command "(Get-CimInstance Win32_ComputerSystem).TotalPhysicalMemory"`
+
+### `MODEL_CONTEXT_WINDOWS` dict (vram_detect.py:24-47)
+Additive only. Add these local-LLM entries with context sizes from public model cards:
+- `llama-3.1-8b`: 128_000
+- `llama-3.3-70b`: 128_000
+- `qwen2.5-7b`: 128_000 (Qwen2.5 supports up to 128k per model card)
+- `qwen2.5-72b`: 128_000
+- `mistral-7b`: 32_000
+- `mistral-large`: 128_000
+- `deepseek-r1`: 64_000 (DeepSeek-R1)
+- `deepseek-v3`: 64_000
+- `glm-4`: 128_000
+- `glm-4.5`: 128_000
+- `gemma-2`: 8_000
+- `gemma-2-27b`: 8_000
+- `phi-3`: 128_000
+- `phi-4`: 16_000
+
+Add a docstring comment above each: `# Source: <model card URL or repo>` — never
+fabricate. If a number is uncertain, use the smaller conservative value and
+leave a comment noting the uncertainty.
+
+### `detect_model_context()` (vram_detect.py:175-228)
+Add an `ollama list` probe when no config file names a model AND the system has
+`ollama` on PATH. Steps:
+1. `ollama list` → parse first non-header row's NAME column (strip `:latest` tag).
+2. Look up the cleaned name in `MODEL_CONTEXT_WINDOWS` via existing `_lookup_model_context`.
+3. If matched, return that context. If not matched, fall through to fail-open `0`.
+
+Do NOT modify any other code path in `detect_model_context`.
+
+## MUST NOT regress
+
+- The existing Linux output of `python3 vram_detect.py` must produce byte-identical
+  stdout (after the equivalent hardware probe) on the original Cachyos box. Subtask-3
+  will write a Linux-fixture test to lock this in.
+- Do not remove or alter any existing OpenAI/Anthropic entry in `MODEL_CONTEXT_WINDOWS`.
+
+## Acceptance criteria
+
+1. `python3 scripts/vram_detect.py` on Darwin prints `gpu_vram_gb > 0` (currently prints 0).
+2. `python3 scripts/vram_detect.py` JSON contains the same keys, same order, same types.
+3. `python3 -m py_compile scripts/vram_detect.py` exits 0.
+4. On a Linux fixture (simulated by subtask-3 tests with patched `platform.system`),
+   stdout matches the pre-refactor output line-by-line for GPU/RAM sections.
+5. `python3 scripts/vram_detect.py` does not crash on Windows stub (subtask-3 sets
+   `monkeypatch.setattr(platform, "system", lambda: "Windows")` and mocks subprocess).
+6. No new third-party imports.
+
+## Anti-spin rails
+
+- Unknown model name → fail open with `0`. NEVER guess a context window.
+- If `platform.system()` returns an unexpected string (e.g. "AIX"), fall through to
+  Linux path or print "Unsupported OS: X" and return 0s. Do not crash.
+- If `system_profiler` output format on the local M-series Mac is different from what
+  you parsed, STOP and report. Don't patch a half-working parser.
+
+## Hardware context (this box)
+
+- Darwin arm64, Python 3.9.6 (stock CommandLineTools).
+- `system_profiler SPDisplaysDataType` is the canonical probe.
+- You can iterate locally by running `python3 scripts/vram_detect.py` after each edit.
+
+## Recommended approach
+
+1. Add the local-LLM entries to `MODEL_CONTEXT_WINDOWS` first (mechanical).
+2. Refactor `detect_ram()` with a `platform.system()` dispatch — easiest, lowest risk.
+3. Refactor `detect_gpu_vram()` — hardest, leave for after RAM is green.
+4. Add the `ollama list` probe.
+5. Wrapping `run_command()` for Windows PowerShell — defer until last.
+6. After each function, run `python3 scripts/vram_detect.py` and confirm no crash + correct output.
+7. Do NOT touch `tests/test_vram_detect.py`. Subtask-3 will write tests against your function signatures.
@@ -0,0 +1,3 @@
+# VERDICT
+
+PASS — 235 passed, 0 errors. 10/10 streak on attempt 1. Implementation by local LLM (gemma-4-26B).