Ed Zynda 5a3d3fdd7d fix: properly handle tags from Qwen/DeepSeek models ...

Models like Qwen and DeepSeek wrap reasoning content in  ...  XML-like
tags within the regular content field. This was causing the reasoning
text to appear twice - once as a reasoning block and once as regular text.

Changes:

1. Provider hooks (providers.go):
   - Extract reasoning from  tags and emit proper reasoning events
   - Use openai provider directly with custom ExtraContentFunc and
     StreamExtraFunc hooks to parse thinking content

2. Stream filtering (stream.go):
   - Filter out all text content between  and  tags at the
     streaming level to prevent duplicate rendering
   - Track state with inThinkTag flag across stream chunks

3. Message conversion (content.go):
   - Strip any remaining  tags from text content when converting
     from fantasy messages

The regex patterns use string concatenation to avoid XML tag corruption:
  regexp.MustCompile( +  +  +  +  +  +  + )

Fixes duplicate reasoning text when using custom provider with models
that wrap thinking in  tags.

2026-03-30 16:31:58 +03:00

..

content_test.go

feat: make /new create a new session file like Pi

2026-03-26 15:41:01 +03:00

content.go

fix: properly handle tags from Qwen/DeepSeek models

2026-03-30 16:31:58 +03:00