Paul Kompfner
12979293ad
Add thinking examples to eval suite
2025-12-11 15:58:48 -05:00
Paul Kompfner
28248e9b00
Split up thinking examples so that there isn't an llm command-line arg for controlling which LLM to use. This change is preparation for adding these examples to our suite of evals.
2025-12-11 15:07:35 -05:00
Paul Kompfner
0e88ad672e
Add ThoughtTranscriptionMessage.role, which is always "assistant"
2025-12-11 14:41:16 -05:00
Paul Kompfner
c5ff5cc219
Update CHANGELOG
2025-12-08 16:09:59 -05:00
Paul Kompfner
229ff794d6
Better handle Gemini non-function thought signatures
2025-12-08 15:56:40 -05:00
Paul Kompfner
1249ee3de3
Better handle Gemini non-function thought signatures
2025-12-08 13:07:25 -05:00
Paul Kompfner
aa0529ff82
Update comments for accuracy
2025-12-08 11:47:06 -05:00
Paul Kompfner
7e92597c0e
Remove LLMThoughtSignatureFrame in favor of using the more generic LLMMessagesAppendFrame
2025-12-08 11:10:05 -05:00
Paul Kompfner
17203ba3e6
Change FunctionInProgressFrame.llm_specific_extra to a more generic FunctionInProgressFrame.append_extra_context_messages.
2025-12-08 10:50:19 -05:00
Paul Kompfner
61674d7758
Add process_thought constructor argument to TranscriptProcessor to control whether to handle thoughts in addition to assistant utterances. Defaults to False.
2025-12-08 10:27:36 -05:00
Paul Kompfner
8ccc2cbf31
Add unit tests for ThoughtTranscriptProcessor
2025-12-08 10:14:31 -05:00
Paul Kompfner
ef703e9d16
Get rid of ThoughtTranscriptProcessor, moving its logic into AssistantTranscriptProcessor instead
2025-12-08 09:59:32 -05:00
Paul Kompfner
44aa11737b
Minor docstring update for accuracy
2025-12-08 09:29:10 -05:00
Paul Kompfner
49f1f7d6a2
Added CHANGELOG entry describing new thinking-related functionality
2025-12-08 09:29:10 -05:00
Paul Kompfner
4ea51ff67c
Slight refactor of handling thought-signature-containing special context messages in the Gemini adapter
2025-12-08 09:29:10 -05:00
Paul Kompfner
747bd4f737
Tweak the prompt of the thinking + functions example to not confuse Gemini as much (Gemini found the original prompt a bit ambiguous, it seems)
2025-12-08 09:29:10 -05:00
Paul Kompfner
15f5583fd2
Simplify, at the expense of a bit of not-yet-needed flexibility: rather than associating a loose thought_metadata with each thought, use a signature. Thought signatures are the only "thought metadata" we use today.
2025-12-08 09:29:10 -05:00
Paul Kompfner
c8c6f424cd
Add support for Gemini 3 Pro non-function-call-related thought signatures
2025-12-08 09:29:10 -05:00
Paul Kompfner
0cdf0c4504
Bump Google GenAI library version to at least 1.51.0, as that's the version where thinking_level—required for controlling Gemini 3 Pro thinking—is introduced
2025-12-08 09:29:10 -05:00
Paul Kompfner
217f03b9cc
Add additional functionality related to "thinking", for Google and Anthropic LLMs.
...
Thinking, sometimes called "extended thinking" or "reasoning", is an LLM process where the model takes some additional time before giving an answer. It's useful for complex tasks that may require some level of planning and structured, step-by-step reasoning. The model can output its thoughts (or thought summaries, depending on the model) in addition to the answer. The thoughts are usually pretty granular and not really suitable for being spoken out loud in a conversation, but can be useful for logging or prompt debugging.
Here's what's added:
1. New typed input parameters for Google and Anthropic LLMs that control the models' thinking behavior (like how much thinking to do, and whether to output thoughts or thought summaries).
2. New frames for representing thoughts output by LLMs.
3. A generic mechanism for associating extra LLM-specific data with a function call in context, used specifically to support Google's function-call-related "thought signatures", which are necessary to ensure thinking continuity between function calls in a chain (where the model thinks, makes a function call, thinks some more, etc.)
4. A generic mechanism for recording LLM thoughts to context, used specifically to support Anthropic, whose thought signatures are expected to appear alongside the text of the thoughts within assistant context messages.
5. An expansion of `TranscriptProcessor` to process LLM thoughts in addition to user and assistant utterances.
2025-12-08 09:29:01 -05:00
Mark Backman
4517475db7
Merge pull request #3197 from pipecat-ai/mb/cartesia-stt-cleanup
...
Clean up CartesiaSTTService
2025-12-08 08:53:40 -05:00
Aleix Conchillo Flaqué
92b6e8d66b
Merge pull request #3189 from pipecat-ai/aleix/introduce-uninterruptible-frames
...
introduce uninterruptible frames
2025-12-07 14:02:35 -08:00
Aleix Conchillo Flaqué
3be1a7afaa
Merge pull request #3202 from pipecat-ai/aleix/remove-manta
...
README: remove manta badge
2025-12-07 14:00:13 -08:00
Aleix Conchillo Flaqué
f0af0a6b96
README: remove manta badge
2025-12-05 16:16:19 -08:00
Mark Backman
4cefe1357c
Merge pull request #3201 from pipecat-ai/changelog-0.0.97
...
Release 0.0.97 - Changelog Update
2025-12-05 18:49:15 -05:00
markbackman
4df0a9bf73
Update changelog for version 0.0.97
2025-12-05 18:47:21 -05:00
Mark Backman
9ef139d020
Merge pull request #3200 from pipecat-ai/mb/improve-changelog-template
...
Fix newlines between sections in changlelog template
2025-12-05 18:42:52 -05:00
Mark Backman
9103d4ae05
Fix newlines between sections in changlelog template
2025-12-05 18:40:49 -05:00
Aleix Conchillo Flaqué
bd63b6cefa
Merge pull request #3198 from pipecat-ai/aleix/examples-14i-new-model
...
examples(foundational): update 14i-fireworks with new serverless model
2025-12-05 15:33:12 -08:00
Aleix Conchillo Flaqué
4d03270bc3
examples(foundational): update 14i-fireworks with new serverless model
2025-12-05 15:31:29 -08:00
Mark Backman
0debcee761
Clean up CartesiaSTTService
2025-12-05 18:12:11 -05:00
Mark Backman
6aee72c5b4
Merge pull request #3196 from pipecat-ai/mb/docs-cleanup-prep-0.0.97
...
Docs cleanup before 0.0.97 release
2025-12-05 15:16:36 -05:00
Mark Backman
8d62cfb1b6
Merge pull request #3195 from ivaaan/add-hume-header
...
Add tracking headers to Hume service
2025-12-05 14:50:18 -05:00
ivaaan
41214236ab
add changelog
2025-12-05 20:47:04 +01:00
Mark Backman
b25963a63b
Docs cleanup before 0.0.97 release
2025-12-05 14:19:26 -05:00
ivaaan
8c6ef21d84
add stop, cancel
2025-12-05 20:13:58 +01:00
ivaaan
0ffaa09c95
add tracking headers to Hume service
2025-12-05 19:00:47 +01:00
Aleix Conchillo Flaqué
f6e31b7e89
Merge pull request #3185 from pipecat-ai/fix/websocket-service-cancelled-error-handling
...
fix(websocket): handle CancelledError to prevent reconnection on shutdown
2025-12-05 09:25:49 -08:00
Aleix Conchillo Flaqué
49b2b12e04
frames: change function call frame base types
2025-12-05 09:22:29 -08:00
Aleix Conchillo Flaqué
7ad3969690
introduce UninterruptibleFrame frames
2025-12-05 09:21:36 -08:00
Aleix Conchillo Flaqué
48422dd442
WebsocketService: avoid reconnection on shutdown
2025-12-05 09:03:04 -08:00
Vanessa Pyne
fed6a8b669
Merge pull request #3187 from pipecat-ai/vp-mcp-filter-followup
...
add mcp filter example and changelog
2025-12-05 10:58:19 -06:00
vipyne
82e0253a62
add mcp filter example and changelog
2025-12-05 10:56:59 -06:00
Vanessa Pyne
a7f26dca60
Merge pull request #3152 from RuiDaniel/mcp_client_filters
...
Add filters to MCP Client
2025-12-05 10:50:27 -06:00
Vanessa Pyne
459ef27f3f
Merge pull request #3079 from pipecat-ai/vp-add-exact-model-version-function
...
set full model name for base openai models
2025-12-05 10:48:53 -06:00
Mark Backman
464cfa5ccb
Merge pull request #3188 from pipecat-ai/mb/improve-changelog-process
...
Auto-generate changelog from fragments
2025-12-05 11:42:25 -05:00
Mark Backman
9289881a80
Remove 3120.added.md
2025-12-05 11:35:50 -05:00
Mark Backman
34033cd454
Add new changelog entries
2025-12-05 11:35:50 -05:00
Mark Backman
47c21c9579
Delete README.md in changelog
2025-12-05 11:35:50 -05:00
Mark Backman
3b0bcf0b66
Validate fragment types match the expected types
2025-12-05 11:35:50 -05:00
