Rewrites m023 in place to the DAG-shaped message store from
plans/dag-schema.md:
- messages: id, parent_id, content_hash, role, provider_metadata_json,
created_at. Chain roots point at a self-referencing sentinel row
("root") so the unique (parent_id, content_hash) index works at
every chain position — NULL-parent uniqueness footgun avoided.
- message_parts: structurally unchanged.
- calls: one row per LLM call, anchoring head_input/head_output
message ids and recording model + timing + usage.
- conversations.head_message_id: advances each turn; history is
reconstructed by walking parent_id from the head.
New llm/storage.py provides MessageStore.save_chain (with dedup),
load_chain, and find_longest_existing_prefix (for the stateless-API
case wired in phase 3).
Response.log_to_db now writes the DAG + a calls row alongside the
existing responses-table writes (kept for llm logs compatibility
until phase 5). Response._load_messages_from_db walks the chain
using calls pointers.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* add vscode and uv artifacts to gitignore
* !fragment feature
* Update fragment command to accept multiple fragments
* Add support for multiple fragments in !fragment command, factor out fragment processing
* Add support for fragment/system fragment arguments in chat command
* update docs
---------
Co-authored-by: Simon Willison <swillison@gmail.com>
Refs #776
* Implemented new llm prompt --schema and model.prompt(schema=)
* Log schema to responses.schema_id and schemas table
* Include schema in llm logs Markdown output
* Test for schema=pydantic_model
* Initial --schema CLI documentation
* Python docs for schema=
* Advanced plugin docs on schemas
- https://github.com/simonw/llm/issues/507#issuecomment-2458639308
* register_model is now async aware
Refs https://github.com/simonw/llm/issues/507#issuecomment-2458658134
* Refactor Chat and AsyncChat to use _Shared base class
Refs https://github.com/simonw/llm/issues/507#issuecomment-2458692338
* fixed function name
* Fix for infinite loop
* Applied Black
* Ran cog
* Applied Black
* Add Response.from_row() classmethod back again
It does not matter that this is a blocking call, since it is a classmethod
* Made mypy happy with llm/models.py
* mypy fixes for openai_models.py
I am unhappy with this, had to duplicate some code.
* First test for AsyncModel
* Still have not quite got this working
* Fix for not loading plugins during tests, refs #626
* audio/wav not audio/wave, refs #603
* Black and mypy and ruff all happy
* Refactor to avoid generics
* Removed obsolete response() method
* Support text = await async_mock_model.prompt("hello")
* Initial docs for llm.get_async_model() and await model.prompt()
Refs #507
* Initial async model plugin creation docs
* duration_ms ANY to pass test
* llm models --async option
Refs https://github.com/simonw/llm/pull/613#issuecomment-2474724406
* Removed obsolete TypeVars
* Expanded register_models() docs for async
* await model.prompt() now returns AsyncResponse
Refs https://github.com/simonw/llm/pull/613#issuecomment-2475157822
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Test / test (macos-latest, >=2.0.0, 3.10) (push) Has been cancelled
Test / test (macos-latest, ==1.10.2, 3.9) (push) Has been cancelled
Test / test (macos-latest, >=2.0.0, 3.11) (push) Has been cancelled
Test / test (macos-latest, >=2.0.0, 3.12) (push) Has been cancelled
Test / test (macos-latest, >=2.0.0, 3.8) (push) Has been cancelled
Test / test (macos-latest, >=2.0.0, 3.9) (push) Has been cancelled
Test / test (ubuntu-latest, ==1.10.2, 3.10) (push) Has been cancelled
Test / test (ubuntu-latest, ==1.10.2, 3.11) (push) Has been cancelled
Test / test (ubuntu-latest, ==1.10.2, 3.12) (push) Has been cancelled
Test / test (ubuntu-latest, ==1.10.2, 3.8) (push) Has been cancelled
Test / test (ubuntu-latest, ==1.10.2, 3.9) (push) Has been cancelled
Test / test (ubuntu-latest, >=2.0.0, 3.10) (push) Has been cancelled
Test / test (ubuntu-latest, >=2.0.0, 3.11) (push) Has been cancelled
Test / test (ubuntu-latest, >=2.0.0, 3.12) (push) Has been cancelled
Test / test (ubuntu-latest, >=2.0.0, 3.8) (push) Has been cancelled
Test / test (ubuntu-latest, >=2.0.0, 3.9) (push) Has been cancelled
Test / test (macos-latest, ==1.10.2, 3.10) (push) Has been cancelled
Test / test (macos-latest, ==1.10.2, 3.11) (push) Has been cancelled
Test / test (macos-latest, ==1.10.2, 3.12) (push) Has been cancelled
Test / test (macos-latest, ==1.10.2, 3.8) (push) Has been cancelled
Test / test (windows-latest, ==1.10.2, 3.10) (push) Has been cancelled
Test / test (windows-latest, ==1.10.2, 3.11) (push) Has been cancelled
Test / test (windows-latest, ==1.10.2, 3.12) (push) Has been cancelled
Test / test (windows-latest, ==1.10.2, 3.8) (push) Has been cancelled
Test / test (windows-latest, ==1.10.2, 3.9) (push) Has been cancelled
Test / test (windows-latest, >=2.0.0, 3.10) (push) Has been cancelled
Test / test (windows-latest, >=2.0.0, 3.11) (push) Has been cancelled
Test / test (windows-latest, >=2.0.0, 3.12) (push) Has been cancelled
Test / test (windows-latest, >=2.0.0, 3.8) (push) Has been cancelled
Test / test (windows-latest, >=2.0.0, 3.9) (push) Has been cancelled
* Run CI on Windows and macOS as well as Ubuntu, refs #407
* Use pyreadline3 on win32
* Back to fail-fast since we have a bigger matrix now
* Mark some tests as xfail on windows
Simon Willison