test(tools): gated live test — agent invokes read_file end-to-end - #18
Merged
Conversation
Adds LLMProviderKitOllama to the SwiftAgentKitToolsTests target and a gated (SAK_LIVE_TESTS=1) test proving a real model picks up and calls a framework tool: registers read_file + a temp file with a sentinel and asserts the agent reads it back. Passed 2/2 vs glm-5.2:cloud. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
Caution The consumer version of Gemini Code Assist on GitHub has been sunset. All code review activity has officially ceased. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds a gated (
SAK_LIVE_TESTS=1) live test toSwiftAgentKitToolsTestsproving a real model actually uses the new framework tools, not just that they exist: it registersread_file, writes a temp file with a sentinel, and asks the agent to read it back.Requires adding
LLMProviderKitOllamato that test target (test-only; no change to the shipped library).Passed 2/2 vs
glm-5.2:cloud(~4–5s). Gated, so CI stays hermetic. 12 hermetic tools tests pass.🤖 Generated with Claude Code