test(tools): gated live multi-stage loop with a real goal verifier - #30
Merged
Conversation
…fier Stresses the full agentic loop end-to-end against glm-5.2:cloud: the agent writes a Python script, runs it, and a goal verifier that ACTUALLY EXECUTES the script requires exact output (FIB10=55) — forcing self-repair if wrong. Combines FileWriteTool + ShellTool + autonomousMode + verifyCompletion. Passed 3/3. 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Exercises the whole loop-engineering surface end-to-end against a real model (
glm-5.2:cloud, gatedSAK_LIVE_TESTS=1):write_file) → run it (run_shell).verifyCompletionactually executes the script and requires exact output (FIB10=55); a wrong attempt returns.unsatisfiedwith the actual output, forcing self-repair until correct.autonomousMode(no confirmation gate) + a persistence prompt +maxVerificationRetries.Passed 3/3 locally. Complements the deterministic verifier unit tests (
testVerifier*) with a live, real-execution proof. 125 hermetic tests pass.