tabbyAPI-ollama/endpoints/OAI
kingbri 5b1db3ad83 API: Don't do a second re-render when tool calling
Re-rendering the template is an expensive operation when it's possible
to just concatenate the prompt and current generation text together.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
2025-07-06 11:32:36 -04:00
..
types API: Add tool_call_id for role = tool 2025-07-05 21:52:58 -04:00
utils API: Don't do a second re-render when tool calling 2025-07-06 11:32:36 -04:00
router.py API: Fix chat completion formatting flow 2024-11-21 17:51:14 -05:00