Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 7 additions & 11 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,17 +4,6 @@ All notable changes to this project are documented here. The format follows [Kee

## [Unreleased]

### Added
- Exp. 8 results in the README: base, the paper's checkpoint and the Opus and Astra edits, with thinking on and off.
- `experiments/exp8`: `evaluate.py --no-thinking` and `table.py`.

### Changed
- Faster hot paths, measured with the new `benchmarks/profile_hotpaths.py`: block-parallel `diff`, `patch`, snapshots and restores; exact histogram-based quantiles; sparse checkpoints; content-keyed `describe` cache; cheaper spectrum for large matrices. `describe` on a 151936 x 1024 embedding goes from 6.5 s and 2.4 GB to 1.2 s and 132 MB, and a 30-step agent loop from 9.2 s to 0.4 s. See docs/production.md.

### Fixed
- `apply_patch` silently did nothing on tensors stored as non-contiguous arrays.
- `diff` and `patch` counted untouched NaN weights as edits.

## [0.3.0] - 2026-11-03

### Added
Expand All @@ -27,11 +16,18 @@ All notable changes to this project are documented here. The format follows [Kee
- OpenAI `prompt_cache_key` per run on api.openai.com; `max_retries` / `timeout` on all backends; Anthropic streaming for long requests.
- CLI: `--probe FILE.py:FN`, `--forward-budget`, `--price`, `--max-cost`, `--max-tokens`, `--max-time`, `--events`, `--json`, `--version`; exit code 2 when a run does not finish cleanly.
- `py.typed` marker.
- Exp. 8 results in the README: base, the paper's checkpoint and the Opus and Astra edits, with thinking on and off.
- `experiments/exp8`: `evaluate.py --no-thinking` and `table.py`.

### Changed
- `ws.diff()` and `ws.patch()` run in blocks (about 6x faster and 50x less memory on large tensors); `describe_tensor` is cached and uses a Gram-matrix spectrum for tall/wide matrices.
- The sandbox timeout works off the main thread and without SIGALRM; sandbox code runs under `torch.no_grad()`.
- `agent.py` split into `tools.py`, `result.py`, `events.py` and `usage.py` (same public API).
- Faster hot paths, measured with the new `benchmarks/profile_hotpaths.py`: block-parallel `diff`, `patch`, snapshots and restores; exact histogram-based quantiles; sparse checkpoints; content-keyed `describe` cache; cheaper spectrum for large matrices. `describe` on a 151936 x 1024 embedding goes from 6.5 s and 2.4 GB to 1.2 s and 132 MB, and a 30-step agent loop from 9.2 s to 0.4 s. See docs/production.md.

### Fixed
- `apply_patch` silently did nothing on tensors stored as non-contiguous arrays.
- `diff` and `patch` counted untouched NaN weights as edits.

## [0.2.0] - 2026-11-03

Expand Down
Loading