Remove unjustified 2s sleep after tool execution in run_async (ADK module) #826
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
oracle-contributor-agreement
bot
added
the
OCA Verified
yodeee9
changed the title
There was a problem hiding this comment.
Pull request overview
Removes an unconditional 2-second delay that was applied after each tool-call round in run_async, eliminating unnecessary latency during agent execution.
Changes:
- Removed the fixed
time.sleep(2)call (and its throttle-related comment) from therun_asyncloop.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
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Outdated suggestions cannot be applied.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.
Remove the fixed
time.sleep(2)that ran after handlingrequired_actions(tool execution) and before sending the next chat request inrun_async.Every tool-call round added a fixed 2-second wait for all users. The value 2 seconds is a magic number. It is not specified by the API, not configurable, and not justified by any documented OCI/GenAI requirement or constants.
And retry is already implemented at a lower level:
AgentClientbuildsGenerativeAiAgentRuntimeClientwithretry_strategy=oci.retry.DEFAULT_RETRY_STRATEGY(agent_client.py ~line 116).DEFAULT_RETRY_STRATEGY(src/oci/retry/init.py) retries on HTTP 429 (throttles) with exponential backoff (up to 8 attempts, 600s total)._handle_chat→client.chat()→_rt_client.chat()is called, the runtime client already retries on 429. The fixed 2s sleep does not replace or improve that; it only adds delay when no throttle occurs.