# Changelog

All notable changes to sekft, the shell-operator SFT trainer behind the
[posix-sdc](https://huggingface.co/datasets/tiararodney/posix-sdc) experiment,
are documented in this file.

The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
and the project follows [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

## [1.0.3] - 2026-06-18

### Changed
- The README intro now states up front that this is **not tool-calling**: sekft
  trains shell operation, not function-calling; the model is given no typed tool
  API or JSON-schema action list, and writes plain-text commands at a real prompt
  with the whole system as its action space.

## [1.0.2] - 2026-06-18

### Fixed
- The generation operators (`sekft-eval`, `sekft-resident`) passed the
  `BatchEncoding` from `apply_chat_template(..., return_tensors="pt")` straight
  to `model.generate`, which does `inputs.shape[0]` and raised `AttributeError`
  on transformers ≥ 5 — the holdout eval crashed on its first scenario. 1.0.1
  fixed only the trainer's masking; this sweeps the generation path too. A shared
  `_input_ids` helper and a `render_prompt_ids` function now extract the id
  tensor for both operators, with unit tests for the BatchEncoding and bare
  shapes.

## [1.0.1] - 2026-06-18

### Fixed
- `build_masked_example` could not derive the assistant mask on transformers
  ≥ 5: `apply_chat_template` now returns a `BatchEncoding` (`{input_ids: [...]}`)
  where 4.x returned a bare `list[int]`, so the render was treated as a dict and
  the prefix-differencing spuriously raised "chat template is not additive" on
  every real model. The id sequence is now extracted either way; verified the
  assistant-only mask against `mistralai/Mistral-7B-Instruct-v0.2`. The
  fake-tokenizer test gained a `BatchEncoding`-returning variant so this can't
  regress.

## [1.0.0] - 2026-06-18

First release: the training and evaluation pipeline that turns posix-sdc
trajectories into a fine-tuned shell operator.

### Added
- `sekft-train`: LoRA / QLoRA supervised fine-tuning of a base model on
  shell-operation trajectories, with an **assistant-only loss mask** derived by
  token-prefix differencing — the commands and the terminal `exit` / `panic`
  token are trained; the environment turns (orientation, prompts, command
  output) are masked to `-100`. The render uses the tokenizer's own
  `apply_chat_template`, so training matches what the serving harness sends
  (train = serve), with `normalize_for_template` canonicalising trajectories for
  instruct templates that have no system role and require strict user/assistant
  alternation.
- Three sources of training data: a directory of raw rollout `.json`
  (keep-filtered), a curated `.jsonl` corpus, or the published posix-sdc corpus
  over the Hugging Face Hub (`--hub`).
- `--inspect` for mask and token statistics without training, and structured
  stderr logging across every phase (`-v` / `-q`): per-trajectory and progress
  lines while the corpus is tokenized, dataset accounting that warns on dropped
  (over-length / empty-mask) trajectories, and the per-step training curve.
- `sekft-eval`: behavioural evaluation that drops the tuned model into held-out
  scenarios with no scaffold and scores whether it operates and terminates.
- `sekft-resident`: a resident-base harness that loads the base model once and
  fits several adapters without reloading, for paired / STaR-style runs.
- Packaging: the `tiararodney.sekft` namespace package with `sekft-train`,
  `sekft-eval`, and `sekft-resident` console scripts; a typed (`py.typed`),
  mypy-strict codebase; an optional `[gpu]` extra (torch / transformers / peft);
  and a dependency on `posix-sdc[hub]`. Released under GPL-2.0.

[1.0.3]: https://git.code.tiararodney.com/tiara/sekft/compare/v1.0.2...v1.0.3
[1.0.2]: https://git.code.tiararodney.com/tiara/sekft/compare/v1.0.1...v1.0.2
[1.0.1]: https://git.code.tiararodney.com/tiara/sekft/compare/v1.0.0...v1.0.1
[1.0.0]: https://git.code.tiararodney.com/tiara/sekft/releases/tag/v1.0.0