Manmohan Sharma ba727cb4d5 fix(serve): match tool markers on token-id sequences not decoded text ... Previous text-stream approach lost markers because BPE partial-byte tokens decode to empty strings, so assistant_text never accumulated the full marker. Switch to matching the ordinary-token id sequence directly (python_start = [60,124,25145,95,17104,124,62]).		2026-04-22 14:42:07 -07:00
..
_model.py	feat: deploy d24 SFT + polished UI redesign with dark mode (#39)	2026-04-16 19:55:16 -04:00
_tokenizer.py	feat: deploy d24 SFT + polished UI redesign with dark mode (#39)	2026-04-16 19:55:16 -04:00
_tools.py	fix(tools): enable Tavily include_answer and fix UI overflow	2026-04-22 14:20:47 -07:00
serve.py	fix(serve): match tool markers on token-id sequences not decoded text	2026-04-22 14:42:07 -07:00