Repository navigation
Conversation
pengdev
force-pushed
the
fix/verify-hint-hidden-tools
branch
from
October 9, 2026 14:49
25cb0ad to
a40bcfc
Compare
The verify step's hint told the model it MUST call one of assertVisibleBySelector, assertVisibleWithText, or assertWithAI, but the first two are registered with surfaceToLlm = false (one's source comment reads "DO NOT USE GIVE THIS TOOL TO THE LLM"; the other is deprecated). The model can't see or call either one, so it got stuck looking for a nonexistent tool and reported FAILED regardless of what was actually on screen, including on a genuinely correct render. Swap the hint to name the two tools actually surfaced to the LLM today: assertVisible and assertWithAi (also fixes the casing on the latter). Verified against a real Android emulator with claude-sonnet-5 both before and after: before the fix, verify returned exit 1 on both a healthy render and a real negative (Home screen) with a hallucinated-tool confusion in its own reasoning; after the fix, it returns exit 0 on the healthy render and exit 1 on the negative, for the correct reason. Signed-off-by: Peng Liu <liupengking1@gmail.com>
pengdev
force-pushed
the
fix/verify-hint-hidden-tools
branch
from
October 9, 2026 14:51
a40bcfc to
3c9d148
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
trailblaze verify's LLM hint told the model it MUST call one ofassertVisibleBySelector,assertVisibleWithText, orassertWithAIto confirm an assertion — but the first two are registered@TrailblazeToolClass(surfaceToLlm = false, ...)(one's own source comment reads "DO NOT USE GIVE THIS TOOL TO THE LLM"; the other is@Deprecated). The model can never actually see or call either one.Result:
verifyreliably returned exit 1 (FAILED) regardless of what was actually on screen — reproduced on a real Android emulator againstclaude-sonnet-5, where the failure reasoning showed the model hunting for a tool it could never find, even while correctly describing a genuinely healthy render in the same response.This swaps the two unreachable names for the two tools actually surfaced to the LLM today —
assertVisibleandassertWithAi(also fixes a casing typo, "assertWithAI" → "assertWithAi") — and drops the now-stale Oxford comma from the original 3-item list.Verification
@TrailblazeToolClassannotations intrailblaze-commonthatassertVisibleBySelector/assertVisibleWithTextare hidden (surfaceToLlm = false) andassertVisible/assertWithAiare not.assertVisibleis genuinely usable in verify mode and still produces a recordable trail (delegates internally to the recordableassertVisibleBySelector), via existing testsStepToolSetVerifyModeTestandStepToolSetDirectToolsTest.scripts/install-trailblaze-source.sh) and re-ran the sameverifyassertion against a live Android emulator before and after the fix:Test plan
StepToolSetVerifyModeTest,StepToolSetDirectToolsTest) confirmassertVisiblebehaves correctly in verify mode