Skip to content

Conversation

createthis
Copy link
Owner

just for my own use

- Added COMMON_CHAT_FORMAT_DEEPSEEK_V3_1 enum value
- Created common_chat_params_init_deepseek_v3_1() function (currently uses R1 implementation)
- Created common_chat_parse_deepseek_v3_1() function that handles V3.1 thinking format:
  - Extracts reasoning content before '</think>' tag into reasoning_content
  - Extracts regular content after '</think>' tag into content
  - No opening '<think>' tag in V3.1 format
- Added detection logic for V3.1 templates based on pattern: 'message['prefix'] is defined and message['prefix'] and thinking'
- Added V3.1 case to parsing switch statement

This addresses the issue where V3.1 outputs reasoning content followed by '</think>' and then regular content without the opening '<think>' tag.
@createthis createthis self-assigned this Aug 22, 2025
as to not accidentally introduce regressions.
Tool calls work in thinking and non-thinking modes. However, I've introduced a regression in streaming mode where reasoning content initially comes through as regular content. I need to think about how to deal with this long term.
createthis and others added 20 commits August 26, 2025 14:22
behaviors by adding optional update_cursor argument.
Co-authored-by: Sigbjørn Skjæret <[email protected]>
Co-authored-by: Sigbjørn Skjæret <[email protected]>
Co-authored-by: Sigbjørn Skjæret <[email protected]>
Co-authored-by: Sigbjørn Skjæret <[email protected]>
Co-authored-by: Sigbjørn Skjæret <[email protected]>
Co-authored-by: Sigbjørn Skjæret <[email protected]>
Co-authored-by: Sigbjørn Skjæret <[email protected]>
Co-authored-by: Sigbjørn Skjæret <[email protected]>
Co-authored-by: Sigbjørn Skjæret <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants