Metadata-Version: 2.4
Name: llmsurgery
Version: 0.0.6
Summary: LLM Surgery
Author-email: Jeremy Howard <info@fast.ai>
License: Apache-2.0
Project-URL: Repository, https://github.com/AnswerDotAI/llmsurgery
Project-URL: Documentation, https://AnswerDotAI.github.io/llmsurgery/
Keywords: nbdev
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: nbformat
Requires-Dist: fastcore>=2.1.4
Requires-Dist: python-fastllm>=0.0.28
Requires-Dist: aidialog
Provides-Extra: dev
Requires-Dist: exhash; extra == "dev"
Requires-Dist: openai-codex; extra == "dev"
Requires-Dist: claude-agent-sdk; extra == "dev"
Requires-Dist: json5; extra == "dev"
Dynamic: license-file

# llmsurgery


<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->

## Install

``` sh
pip install llmsurgery
```

## What’s here

Dialogs are LLM conversations kept as Jupyter notebooks: notes, runnable code with outputs, and prompt/reply pairs in one editable, diffable document. The dialog data model and toolkit live in [aidialog](https://github.com/AnswerDotAI/aidialog); this library is the surgery layer for provider session files, built on that model:

- `llmsurgery.ant`: Claude Code session transcripts: read, write, search, curate, and build them from dialogs, so `claude --resume` opens an authored conversation.
- `llmsurgery.oai`: Codex threads: read rollouts, and inject authored histories via the `openai-codex` SDK, ready for `codex resume`.

Both sides include DSL-based compaction of long sessions (the document format is `aidialog.compact`’s), and `llmsurgery.antskill` packages the read-only Claude Code session tools as a pyskill.
