[claude] Add timmy learn autoresearch entry point (#907) #1240

claude · 2026-03-23T23:06:58Z

claude commented

2026-03-23 23:06:58 +00:00

Fixes #907

What

Implements the python -m timmy.cli learn autoresearch entry point.

Changes

`src/timmy/autoresearch.py`

Added SystemExperiment class encapsulating the full hypothesis → edit → tox → evaluate → commit/revert loop
Added _extract_pass_rate() and _extract_coverage() helpers for built-in metric extraction
Handles higher-is-better metrics (unit_pass_rate, coverage) and lower-is-better (val_bpb, custom)

`src/timmy/cli.py`

Added learn subcommand with flags: --target, --metric, --budget, --max-experiments, --dry-run, --tox-env, --model
Reads program.md for research direction; degrades gracefully if file is absent
Uses Aider (existing toolkit integration) for code edits; skips silently if Aider is not installed

`program.md`

Starter research direction file for timmy learn

Tests

tests/timmy/test_autoresearch.py — 16 new tests covering SystemExperiment methods and helper functions
tests/timmy/test_cli_learn.py — 5 tests covering CLI flags, dry-run behaviour, and help text

All 400 unit tests pass

Fixes #907 ## What Implements the `python -m timmy.cli learn` autoresearch entry point. ## Changes ### `src/timmy/autoresearch.py` - Added `SystemExperiment` class encapsulating the full hypothesis → edit → tox → evaluate → commit/revert loop - Added `_extract_pass_rate()` and `_extract_coverage()` helpers for built-in metric extraction - Handles higher-is-better metrics (`unit_pass_rate`, `coverage`) and lower-is-better (`val_bpb`, custom) ### `src/timmy/cli.py` - Added `learn` subcommand with flags: `--target`, `--metric`, `--budget`, `--max-experiments`, `--dry-run`, `--tox-env`, `--model` - Reads `program.md` for research direction; degrades gracefully if file is absent - Uses Aider (existing toolkit integration) for code edits; skips silently if Aider is not installed ### `program.md` - Starter research direction file for `timmy learn` ### Tests - `tests/timmy/test_autoresearch.py` — 16 new tests covering `SystemExperiment` methods and helper functions - `tests/timmy/test_cli_learn.py` — 5 tests covering CLI flags, dry-run behaviour, and help text ## All 400 unit tests pass

claude added 1 commit 2026-03-23 23:06:58 +00:00

feat: add timmy learn CLI command and SystemExperiment class

Tests / lint (pull_request) Failing after 17s

Details

Tests / test (pull_request) Has been skipped

Details

f0657000ab

Implements the autoresearch entry point requested in #907:

- `SystemExperiment` class in autoresearch.py encapsulates the
  hypothesis → edit → tox → evaluate → commit/revert loop with
  configurable target, metric, and budget
- `timmy learn` CLI command with --target, --metric, --budget,
  --max-experiments, --dry-run, --tox-env, and --model flags
- Helper functions _extract_pass_rate() and _extract_coverage()
  for built-in metric extraction from tox/pytest output
- program.md template in repo root for research direction
- Unit tests for SystemExperiment and the learn CLI command

Fixes #907

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

claude referenced this pull request

2026-03-23 23:07:07 +00:00

[Autoresearch H1] Implement `python -m timmy.cli learn` Entry Point #907

Rockachopa merged commit 6691f4d1f3 into main

2026-03-23 23:14:11 +00:00

Rockachopa deleted branch claude/issue-907

2026-03-23 23:14:11 +00:00

Rockachopa referenced this issue from a commit

2026-03-23 23:14:12 +00:00

[claude] Add timmy learn autoresearch entry point (#907) (#1240)

Sign in to join this conversation.