Update webui to handle reasoning content and include usage stats in server only when requested #791
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
server : include usage statistics only when user request them (#16052) server : only attempt to enable thinking if using jinja (#15967)
firecoperana
force-pushed
the
fcp/webui_reasoning_handle
branch
from
cb93683 to
e5aa602
Compare
ikawrakow
approved these changes
Sep 24, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The following changes are included in this PR:
Change reasoning format's default value to auto and make current webui compatible with this change (
Support streaming delta.reasoning_content in WebUI ggml-org/llama.cpp#15052). This should be fine with most 3rd party front end as they should be updated by now. If not, use --reasoning-format none to start server.
Add config in current webui for reasoning format. When encountering parsing issue for reasoning content, switch between none and auto to see which one fix them.
server : include usage statistics only when user request them (
server : include usage statistics only when user request them ggml-org/llama.cpp#16052). This could be a breaking change, but is compatible with openai API.
server : only attempt to enable thinking if using jinja (
server : only attempt to enable thinking if using jinja ggml-org/llama.cpp#15967)