9a5c24e20c
Release 0.32a1
...
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
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
Refs #1426
Refs https://github.com/simonw/llm-anthropic/issues/68
2026-04-29 16:52:09 -07:00
cce6ed956a
Ran cog
2026-04-29 12:02:36 -07:00
35c35dac43
Release 0.32a0
...
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
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
Closes #1314 , #506 , #1278 , #894 , #813 , #468 , #346 , #716 , #770 , #867 , #938 , #1033 , #937
Refs #1067 , #1080
2026-04-29 11:55:20 -07:00
926394aecd
Tweaked some overly-promotional language
Test / test (ubuntu-latest, 3.13) (push) Has been cancelled
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
2026-04-28 17:46:07 -07:00
02c9af048f
A bunch of documentation edits
2026-04-28 17:07:51 -07:00
5789bc9e36
It's actually the 0.32 alpha
2026-04-28 16:59:11 -07:00
35c7533c18
Edited the changelog for 0.32a0
2026-04-28 16:49:05 -07:00
29e3787be5
Draft changelog for 0.32a0
2026-04-28 16:32:52 -07:00
b97a6902f5
Persist visible reasoning to logs and render in markdown
...
Adds a `reasoning` column to the responses table (migration m022)
populated from concatenated visible-reasoning text in the assembled
message. `llm logs --md` renders it under a `## Reasoning` heading
above the response when present.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-28 14:27:22 -07:00
842ab2a93f
response.messages is a method, matching .text() / .json() / .tool_calls()
...
Sync: response.messages() forces execution if not drained, so callers
no longer have to remember to call .text() first. Async: `await
response.messages()` awaits the force.
Internal sync paths (_response_to_dict, _chain_for_tool_results,
_build_full_chain, Response.reply, AsyncResponse.reply) use a new
private _messages_now() helper that assumes the response is already
drained, so they don't have to await on async responses.
Drops the now-obsolete "accessing .messages on un-awaited
AsyncResponse raises" parity test — that constraint goes away with
the method form.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-28 14:04:35 -07:00
f3a0962162
response.reply() auto-executes pending tool calls
...
Zero-arg sugar: when a response made tool calls and tool_results= is
not passed, reply() runs self.execute_tool_calls() and threads the
results into the next turn. Pass tool_results= explicitly to skip
the auto-execute path (e.g. for mutated or synthetic results). Also
forwards self.prompt.tools to the next turn so the model can call
the same tools again, mirroring Conversation.prompt's tools-or-self
rule.
AsyncResponse.reply() is now an awaitable coroutine — `await
response.reply(...)` — so the auto-execute path can `await
self.execute_tool_calls()` internally. This is a non-shipped API
break: existing async-reply callers in the test suite updated.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-28 13:51:13 -07:00
3b0d0fa0a5
part_index is now (mostly) automatically assigned
2026-04-28 09:35:53 -07:00
6567b60005
Merge remote-tracking branch 'origin/messages-refactor' into messages-refactor
...
# Conflicts:
# docs/fragments.md
# llm/default_plugins/openai_models.py
# pyproject.toml
2026-04-28 07:34:02 -07:00
13b10e097c
Merge remote-tracking branch 'origin/main' into messages-refactor
...
# Conflicts:
# llm/default_plugins/openai_models.py
2026-04-28 07:31:55 -07:00
5ce40fd703
Release 0.31
...
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
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
Refs #1418
2026-04-24 16:33:05 -07:00
706852ecea
New image_detail low/high/auto/original option
...
Refs https://github.com/simonw/llm/issues/1418#issuecomment-4316983472
2026-04-24 16:22:43 -07:00
021a29d61a
OpenAI verbosity option
...
Refs https://github.com/simonw/llm/issues/1418#issuecomment-4316867527
2026-04-24 16:08:26 -07:00
c9a3ac9fe0
New model: gpt-5.5 - refs #1418
2026-04-24 15:41:12 -07:00
eb45de6bfc
Ran cog
2026-04-22 17:18:08 +00:00
d11b9a01c5
More documentation tweaks
2026-04-22 08:43:15 -07:00
8c48dccc94
docs: advanced-model-plugins.md covers StreamEvent / prompt.messages / provider_metadata
...
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 >
2026-04-21 21:54:01 -07:00
92f9359ba3
Documentation improvements
2026-04-21 21:24:50 -07:00
d4f3f242ce
Unwrap wrapped text in docs
2026-04-21 20:17:39 -07:00
1c317ab3fe
Ran cog
2026-04-22 00:08:41 +00:00
063564d34d
Phase 6: client-side serialization round-trip test + docs
...
Lock in the "application does its own persistence without SQLite"
story with:
- Five integration tests covering: Message.to_dict / from_dict
round-trip, re-inflating messages and continuing a conversation,
tool calls + results round-trip, redacted reasoning Parts
round-trip, and provider_metadata round-trip.
- A new "Structured messages and streaming events" section in
docs/python-api.md walking users through messages=[...],
stream_events(), response.messages, and the JSON round-trip
pattern.
No new code — the machinery landed in Phases 1-3. This phase is
validation + documentation.
580 tests passing overall.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-04-20 09:45:50 -07:00
f2c7a2a807
Link to #1389 from changelog
2026-03-31 13:45:24 -07:00
7169fe9085
Add Usage to llm/__init__ __all__ (to fix Ruff)
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
Test / test (ubuntu-latest, 3.14) (push) Has been cancelled
2026-03-31 13:33:56 -07:00
62b8864fda
Release 0.30
2026-03-31 13:32:04 -07:00
946e433698
More docstrings and autoclass embeds in docs
2026-03-31 13:12:32 -07:00
1562a8f444
Added some more autoclass docs, with new doctrings
2026-03-31 12:54:00 -07:00
49d4e54639
register_models() model_aliases parameter
2026-03-31 12:45:38 -07:00
40f7b8f2fa
Ran cog
2026-03-31 11:53:25 -07:00
c7cf7e506e
Changelog for 0.29
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
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
2026-03-17 12:23:43 -07:00
07dccc00ef
GPT-5.4, 5.4-mini, 5.4-nano
...
Closes #1376
2026-03-17 11:24:52 -07:00
4766f47946
Note about just cog in release process
...
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
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
See 8002325600
2025-12-12 12:01:37 -08:00
8002325600
Cog for 0.28 release
2025-12-12 12:00:22 -08:00
3a4f639536
Release 0.28
...
Refs #1300 , #1308 , #1309 , #1313 , #1315 , #1316 , #1317 , #1318
2025-12-12 11:58:35 -08:00
abf77e40d8
Fix for cog
2025-12-11 13:20:06 -08:00
1e3c7f0cfd
uv and dependency-groups, refs #1318
2025-12-11 13:18:20 -08:00
1753eb74ee
gpt-5.2, gpt-5.2-chat-latest - refs #1317
2025-12-11 11:50:08 -08:00
a0ac68c452
Custom HTTP user-agent for llm -f URL, closes #1309
2025-11-25 22:07:11 -08:00
921fae9a0a
Release 0.27.1
...
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, 3.9) (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
Test / test (ubuntu-latest, 3.9) (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, 3.9) (push) Has been cancelled
Refs #1237 , #1238 , #1239 . #1240
2025-08-11 22:14:55 -07:00
e15e1ad717
Credit James Sanford in changelog, refs #1218 , #1232
Test / test (macos-latest, 3.9) (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
Test / test (ubuntu-latest, 3.9) (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 (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 (windows-latest, 3.9) (push) Has been cancelled
2025-08-11 14:29:35 -07:00
4292fe9d21
Relase 0.27
...
Refs #1009 , #1014 , #1049 , #1053 , #1088 , #1104 , #1110 , #1111 , #1114 , #1117 , #1134 , #1137 , #1148 , #1150 , #1177 , #1228 , #1229 , #1232
2025-08-11 13:55:05 -07:00
cbd3aab511
GPT-5 model IDs, refs #1229
2025-08-11 13:23:36 -07:00
08094082f2
Toolbox.add_tool(), prepare() and prepare_async() methods
...
Closes #1111
2025-08-11 13:19:31 -07:00
ef3192b44d
Better docs for OpenAI model options
...
!stable-docs
Closes #1228
2025-08-03 15:31:25 -07:00
24f32fe7b4
Grant models the ability to execute tools
2025-06-19 13:21:03 -07:00
0863ed460e
llm logs -l/--latest -q option, closes #1177
2025-06-17 23:23:45 -07:00
12b6ea6977
Fix grammar in attachments docs
2025-06-03 15:48:07 -07:00
Simon Willison