feat(llmagent): integrate toolsets and request preprocessing - #23
Merged
Merged
Conversation
Allow applications to configure toolsets directly without manually assembling tools and request instructions. Discover tools once per run and invoke optional request processors before each model call. Cover lifecycle, cancellation, concurrent runs, and the Skills workflow through Runner with offline tests.
ktsoator
added
enhancement
uterflec
approved these changes
Sep 23, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
LLM agents previously accepted only static tools, requiring applications to expand toolsets and inject their instructions manually. Add Toolsets configuration and optional RequestProcessor support to discover tools once per run and prepare each model request in configuration order.
Offline tests cover mixed tools, duplicate names, failures, cancellation, concurrent runs, and the Skills workflow through Runner in streaming and non-streaming modes.
Validation:
go test -race -count=1 -timeout=5m ./...go vet ./...go mod tidy -diffgit diff --check