Enable caching for Claude models on both bedrock and copilot #2840
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
edmundhighcock
force-pushed
the
feature/cache_on_bedrock
branch
3 times, most recently
from
80892bb to
d9a8671
Compare
This commit adds a lazy loading mechanism for MCP tools to reduce token usage and improve performance. The implementation includes: - A tool summarizer module that extracts concise descriptions - A new load_mcp_tool function to request detailed tool information on demand - Updated system prompt to explain the lazy loading mechanism Benefits: - Reduced token usage in system prompts - More context available for actual conversations - Improved performance by loading tool details only when needed The implementation is compatible with mcphub.nvim and includes documentation for the required integration changes.
edmundhighcock
force-pushed
the
feature/cache_on_bedrock
branch
from
686d124 to
38b3e90
Compare
edmundhighcock
force-pushed
the
feature/cache_on_bedrock
branch
from
b7773e6 to
30aa6f0
Compare
|
This PR is stale because it has been open 14 days with no activity. Remove stale label or comment or this will be closed in 10 days. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
This PR adds labels to the prompts sent to Claude models telling them to cache those parts of your prompts.
DRAFT: Waiting on PR #2838 to be merged