Prevent redundant LLM queries in success detection #14
Open
divyashreepathihalli wants to merge 1 commit into
Open
Prevent redundant LLM queries in success detection #14divyashreepathihalli wants to merge 1 commit into
divyashreepathihalli wants to merge 1 commit into
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixed Redundant Success Detection API Calls success_detection.py
Previously, the success detection loop checked for success every sd_async_sd_interval_s by spawning an asynchronous query task. If the LLM query took longer than the spawn interval and no new images arrived from the robot, subsequent loops would fire additional identical API calls against the exact same camera timestamps, burning tokens, risking rate limits, and wasting compute.
This PR added an internal tracker (self._last_queried_image_timestamp). The background task now verifies that current_images_timestamp is strictly newer than the last queried state before dispatching the request to the Gemini LLM.