Files

T

CI / build (push) Has been cancelled

Details

Make test suite runnable from clean checkout + cross-platform vram_detect

runnable-test-suite (parent) — complete. Three sub-tasks all complete:

- make-tests-runnable: add requirements.txt pinning pytest==7.4.4, sweep all
  docs/prompts from bare 'python' to 'python3' (stock macOS/Windows ships
  python3), add idempotent .venv install block to scripts/install.sh, and add
  'from __future__ import annotations' to 3 dashboard modules using PEP 604
  union syntax at definition time so they import on Python 3.9+. The
  PEP 604 bug was caught by the streak verifier itself during implementation.

- vram-detect-cross-platform: scripts/vram_detect.py now branches on
  platform.system() for Linux/Darwin/Windows. macOS path uses
  system_profiler SPDisplaysDataType (Apple Silicon unified memory via
  sysctl hw.memsize; Intel Macs via 'VRAM (Total):'). Windows uses wmic
  path win32_VideoController get AdapterRAM with PowerShell fallback. Linux
  /proc/meminfo and nvidia-smi/lspci paths unchanged (regression test locks
  them). Added 14 local-LLM context-window entries (llama-3.1, qwen2.5,
  mistral, deepseek-r1/v3, glm-4/4.5, gemma-2, phi-3/4) with source-cited
  model cards. Added _probe_ollama_model() that runs 'ollama list' as a
  last-resort fallback. run_command() now wraps PowerShell cmdlets on
  Windows (['powershell', '-NoProfile', '-NoLogo', '-Command', ...]).

- vram-detect-cross-platform-tests: 11 new monkeypatched tests in
  tests/test_vram_detect.py covering Linux/Darwin/Windows branches for
  detect_ram and detect_gpu_vram, prefix-match for unknown model names,
  ollama probe, Windows PowerShell wrapper, and a LOCKED regression test
  for _detect_ram_linux(). All external subprocess/sysctl/wmic calls are
  mocked; no live hardware probes. Suite total: 235 passed, 0 errors.

Verified on this box: gpu_vram_gb 0 -> 32 on Apple M5 (32GB unified memory),
target context correctly jumped 12k -> 42k.

Subtask-2 implementation was authored by local LLM (gemma-4-26B-A4B-it
via headroom proxy @ localhost:8787). The 10-consecutive-clean-pass streak
verifier ran as the independent checker model (article #2/#9/#13 in
'WTF Is a Loop? Part 2'). One anti-spin rail fired: local LLM produced
inline branches where subtask-3 tests expected private _detect_ram_linux()
helper; extracted helper to match the test contract without weakening tests.

Parent + all 3 subtasks complete. Prior opencode-subagent implementation
of subtask-2 preserved in git stash for reference.

2026-06-21 18:28:15 -04:00

3.0 KiB

Raw Blame History

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

pip3 install -r requirements.txt succeeds on stock macOS CommandLineTools + pip3.
python3 -m pytest tests/ -v exits 0 from a clean clone, zero error lines.
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.
python3 -m py_compile automaton/**/*.py automaton/dashboard/**/*.py scripts/*.py exits 0.
bash -n scripts/*.sh exits 0.
rg "^python " AGENTS.md README.md automaton/dashboard/README.md prompts/orchestrate.md returns zero matches for a bare python command.
python3 scripts/vram_detect.py on Darwin prints gpu_vram_gb > 0 (was 0 before).
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.

3.0 KiB Raw Blame History