9d9ecd0a73
Handle tool calls with empty arguments better, closes #1521
2026-07-09 09:02:50 -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
cad03fb4f4
Register async models for extra-openai-models.yaml, closes #1395
...
Note that Completion models do not have an async class so will not be registered as async.
2026-04-04 07:07:14 -07:00
c8889e0a76
Ran black
2026-03-17 11:25:12 -07:00
683ca204b2
Ensure -x/--xl work with -t
2026-03-17 11:22:34 -07:00
5d237ce6ce
Show options in Markdown logs output, closes #1322
2025-12-17 22:19:33 -08:00
e0b44bc5ab
Fix some test warnings, refs #1312
2025-12-11 14:37:47 -08:00
f7934c5c26
Fix some descriptor leaks ( #1313 )
...
Refs #1312
2025-12-11 14:20:58 -08:00
a0ac68c452
Custom HTTP user-agent for llm -f URL, closes #1309
2025-11-25 22:07:11 -08:00
a04a6afa74
AsyncModel in llm.__all__, closes #1308
2025-11-25 13:44:42 -08:00
c41c122239
Use tools in templates with llm chat, closes #1239
2025-08-11 22:11:17 -07:00
2f206d0e26
Fix for duplicated prompts in llm chat with templates, closes #1240
...
Also includes a bug fix for system fragments, see https://github.com/simonw/llm/issues/1240#issuecomment-3177684518
2025-08-11 21:52:54 -07:00
c6e158071a
Ran black
2025-08-11 21:47:11 -07:00
e6ac18fbcb
Fix for confusing error, closes #1238
2025-08-11 16:52:16 -07:00
9f1417f6e8
Fix for enum options and --save, refs #1237
2025-08-11 16:16:27 -07:00
e4c1a46d90
Fix test failure caused by version bump, refs #1218
2025-08-11 14:27:16 -07:00
2a54939951
Fix streaming tool calls with tests for many variants. ( #1218 )
...
* Recorded instance of streaming tool response variant "a".
This is the typical response, where "arguments":"" arrives
first in the stream, followed by "arguments":"{}"
The response data is a real capture from the OpenRouter API,
however some request and header data may be from other test fixtures.
* Recorded instance of streaming tool response variant "b".
This is a streaming response where the first arguments
you get is a fully formed "arguments":"{}"
The response data is a real capture from the OpenRouter API,
however some request and header data may be from other test fixtures.
* Test cases for streaming tool responses.
Note that the replays are marked as "read-only", as they are variants
seen in the wild where the streaming tool call argument fragments
arrive in a specific order.
* Fix streaming tool response variant "b", where "arguments":"{}" is what arrives first.
The previous code erroneously caused the first "arguments" to be duplicated,
by using "+=" even when being initially set.
This went unnoticed as many models stream "arguments":"" first.
When a more fully formed "arguments" fragment arrived first, it was causing
"Error: Extra data: line 1 column 3 (char 2)"
* Recorded instance of streaming tool response variant "c".
This was failing with "Error: unsupported operand type(s) for +=: 'NoneType' and 'str'"
The response data is a real capture from the OpenRouter API,
however some request and header data may be from other test fixtures.
* Test case for streaming tool response variant "c".
* Fix streaming tool response variant "c".
However, I'm not sure why arguments was initially not present or seen as None.
2025-08-11 14:17:52 -07:00
5204a11f33
Allow -o option when calling tools, closes #1233
2025-08-11 13:44:26 -07:00
08094082f2
Toolbox.add_tool(), prepare() and prepare_async() methods
...
Closes #1111
2025-08-11 13:19:31 -07:00
0863ed460e
llm logs -l/--latest -q option, closes #1177
2025-06-17 23:23:45 -07:00
544ce17c1d
Tests to confirm responses FTS triggers
...
Refs https://github.com/simonw/llm/issues/1177#issuecomment-2982832935
2025-06-17 23:18:22 -07:00
3a96d52895
Better handling of before_call cancellation, closes #1148
2025-06-01 18:36:55 -07:00
d96ae4ed8d
Fix --async logging to database, closes #1150
2025-06-01 17:38:26 -07:00
30e0c4abe8
ToolResult.exception for tool errors, now logged to DB
...
Closes #1104
2025-06-01 17:01:40 -07:00
ed64fc3362
chain_limit/before_call/after_call for conversations
...
* chain_limit/before_call/after_call for conversations, closes #1088
* Docs for before_call/after_call including for model.conversation
2025-06-01 12:00:29 -07:00
b5d1c5ee90
Tools can now return attachments
...
Closes #1014
- llm.ToolOutput(output='...', attachments=[...]) for tools to return attachments
- New table: `tool_results_attachments`
- Table is populated when tools return attachments
- llm --tools-debug shows attachments returned by tools
- llm logs shows attachments returned by tools
2025-06-01 10:08:36 -07:00
330a568683
Raise error if a non-Toolbox subclass is passed to register(), closes #1114
2025-05-30 21:37:41 -07:00
a3a2996fed
Tools in templates ( #1138 )
...
Closes #1009
2025-05-30 17:44:52 -07:00
b858b0083e
set_resolved_model() for async models, closes #1117
2025-05-28 07:39:57 -07:00
301db6d76c
responses.resolved_model column and response.set_resolved_model(model_id) method, closes #1117
2025-05-28 07:17:03 -07:00
6bab712cdd
Fix for module 'builtins' has no attribute 'instance_id, closes #1107
2025-05-27 13:13:28 -07:00
dbb02d65b9
Fix for llm_time plugin test
2025-05-27 10:26:08 -07:00
9e25055765
Turn incorrect tool names into errors, closes #1104
2025-05-27 09:29:05 -07:00
2bc6d7679c
New default tool, llm_time, closes #1103
2025-05-26 23:00:18 -07:00
d1c5c688e2
Error on llm -c with a Toolbox, closes #1101
...
Refs #1092
2025-05-26 21:51:16 -07:00
e4ecb86421
Log tool_instances to database ( #1098 )
...
* Log tool_instances to database, closes #1089
* Tested for both sync and async models
2025-05-26 21:01:55 -07:00
c9e8593095
Assert specific order again thanks to monotonic ULIDs, refs #1099
2025-05-26 20:03:22 -07:00
1dc7a1d1f9
Monotonic ULIDs, refs #1099
2025-05-26 19:49:42 -07:00
57459c0a6e
Fix the tests I broke in #1096
2025-05-26 19:02:14 -07:00
9bbb37fae0
New default llm_version tool, closes #1096
...
Refs https://github.com/simonw/llm/issues/1095#issuecomment-2910574597
2025-05-26 13:30:47 -07:00
e23e13e6c7
Test for async toolbox, docs for toolboxes in general
...
Closes #1090 , refs #997
2025-05-26 10:23:03 -07:00
00f44a848a
Test that async def methods work on Toolbox
2025-05-26 10:08:31 -07:00
7eb8acb767
llm.get_key() is now a documented utility, closes #1094
...
Refs #1093 , https://github.com/simonw/llm-tools-datasette/issues/2
2025-05-26 09:39:40 -07:00
bb336d33a0
Toolbox class for class-based tool collections ( #1086 )
...
* Toolbox class for class-based tool collections
Refs #1059 , #1058 , #1057
2025-05-25 22:42:52 -07:00
abc4f473f4
--td now pretty-prints JSON if possible, closes #1083
2025-05-25 12:59:48 -07:00
7837335eea
Remove colon in Token usage header for consistency
...
More consistent with other headings in logs now.
2025-05-24 16:55:05 -07:00
fc44fd6a0d
llm chat now respects default model options ( #985 )
2025-05-24 14:24:53 -07:00
713ee9b032
Ignore order in test, refs #1073 , #1079
2025-05-24 13:18:09 -07:00
3d25708acd
Instantiate from spec utility function, refs #1059
...
Code by o3, docstring by Claude Sonnet 4
2025-05-24 08:21:33 -07:00
Simon Willison