Test / test (ubuntu-latest, 3.14) (push) Has been cancelled
Test / test (windows-latest, 3.10) (push) Has been cancelled
Test / test (windows-latest, 3.11) (push) Has been cancelled
Test / test (windows-latest, 3.12) (push) Has been cancelled
Test / test (windows-latest, 3.13) (push) Has been cancelled
Test / test (windows-latest, 3.14) (push) Has been cancelled
Test / test (macos-latest, 3.10) (push) Has been cancelled
Test / test (macos-latest, 3.11) (push) Has been cancelled
Test / test (macos-latest, 3.12) (push) Has been cancelled
Test / test (macos-latest, 3.13) (push) Has been cancelled
Test / test (macos-latest, 3.14) (push) Has been cancelled
Test / test (ubuntu-latest, 3.10) (push) Has been cancelled
Test / test (ubuntu-latest, 3.11) (push) Has been cancelled
Test / test (ubuntu-latest, 3.12) (push) Has been cancelled
Test / test (ubuntu-latest, 3.13) (push) Has been cancelled
So you can turn off display reasoning and compatible plugins can then
opt not to request reasoning summaries from their models, even as
they do actually run reasoning.
Substantially expanded docs/plugins/advanced-model-plugins.md with
the plugin-author guide to the new machinery. Distilled from the
actual llm-anthropic and llm-gemini implementations so plugin
authors have a recipe that mirrors what real providers do.
New / updated sections (doc grew 317 → 663 lines):
- "Attachments from previous conversations" trimmed to a pointer at
prompt.messages — the old pattern of walking conversation.responses
is replaced by the canonical chain view.
- "Structured messages and streaming events"
- StreamEvent contract, backward compat for plain-str plugins
- Full field reference (type / chunk / part_index / tool_call_id /
provider_metadata / server_executed / tool_name)
- part_index allocation rules with two worked examples:
block-keyed (Anthropic-style content_block_start events) and
kind-tracking (Gemini-style chunk-per-part)
- Reasoning: streamed text + opaque _reasoning_token_count, with
the OpenAI-specific gotcha about reading reasoning_tokens BEFORE
set_usage mutates the dict
- Tool calls — tool_call_name + tool_call_args pattern, reminder
that response.add_tool_call() is separately required for
chain-execution
- Server-side tools — server_executed=True on events, raw payload
in provider_metadata for round-trip, post-stream emission for
providers that don't stream tool-result contents
- Opaque provider_metadata — Anthropic signature, Gemini
thoughtSignature, OpenAI encrypted_content — with namespacing
guidance
- Non-streaming path — one event per content block
- "Consuming prompt.messages in build_messages"
- The invariant: prompt.messages is always the full chain; don't
walk conversation.responses (would double-emit)
- Worked build_messages example that dispatches per Part subtype
- Role mapping across OpenAI / Anthropic / Gemini conventions
- Role-alternation merging
- "Restoring opaque metadata on subsequent requests"
- How to read provider_metadata off prior-turn Parts and fold the
signatures back into the outgoing request body
670 tests still green.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* Docs and shape of register_fragment_loaders hook, refs #863
* Update docs for fragment loaders returning a list of FragmentString
* Support multiple fragments with same content, closes#888
* Call the pm.hook.register_fragment_loaders hook
* Test for register_fragment_loaders hook
* Rename FragmentString to Fragment
Closes#863
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
* New KeyModel and AsyncKeyModel classes for models that taken keys - closes#744
* llm prompt --key now uses new mechanism, including for async
* use new key mechanism in llm chat command
* Python API tests for llm.KeyModel and llm.AsyncKeyModel
* Python API docs for for prompt(... key="")
* Mention await model.prompt() takes other parameters, reorg sections
* Better title for the model tutorial
* Docs on writing model plugins that take a key
Simon Willison