fix(session): warn when context window may be too small for tool calling #7422
+13
−1
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
Contributor
|
Thanks for your contribution! This PR doesn't have a linked issue. All PRs must reference an existing issue. Please:
See CONTRIBUTING.md for details. |
Contributor
|
The following comment was made by an LLM, it may be inaccurate: No duplicate PRs found |
zerone0x
force-pushed
the
fix/vllm-tool-calling-7185
branch
from
07d92d4 to
9a754eb
Compare
Add a warning log when models with context limits below 16K tokens are used with tools. This helps users diagnose tool calling failures with vLLM/Ollama setups that have insufficient context windows. Fixes anomalyco#7185 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
KeyEvent type only has preventDefault(), not stopPropagation(). Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
fwang
force-pushed
the
fix/vllm-tool-calling-7185
branch
from
278fbe6 to
859c17f
Compare
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Outdated suggestions cannot be applied.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.
Summary
Root Cause Analysis
Users with vLLM/Ollama experience tool calling failures because default context windows (2048-8192 tokens) are insufficient for tool
schemas. The minimum recommended is 16,384+ tokens.
Fixes #7185