Fix/graceful tool error handling #423 #427
Conversation
Adds the 'gen_ai.conversation.id' attribute to OpenTelemetry spans for LLM calls. This helps link conversation messages together in AI Evals platforms by using the existing session ID. This change is additive and does not remove the existing 'gcp.vertex.agent.session_id' attribute.
…n-id-8998566208331097961 Include gen_ai.conversation.id in OTEL spans
When an LLM calls a tool that is not registered with the current agent, the ADK crashes with a nil pointer dereference instead of gracefully handling the error. The `loopagent` accesses `event.Actions.Escalate` without checking if `event` is nil after an error is returned. This commit fixes the nil pointer dereference in the loopagent by adding a check to ensure `event` is not `nil` before accessing its properties. A new test case has also been added to reproduce the panic and verify the fix.
Removed genAiConversationID from telemetry attributes.
Summary of ChangesHello @sheing-google, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request addresses a critical stability issue in the Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
There was a problem hiding this comment.
Code Review
This pull request addresses a nil pointer dereference in the loopagent by adding proper error and nil-event handling. The changes in agent.go correctly prevent the crash when a sub-agent returns an error. The accompanying test in agent_test.go is well-written, introducing an errorAgent to simulate the failure case and verifying that the loopagent handles it gracefully without panicking.
My review includes one suggestion to slightly refactor the new conditional logic for better conciseness. Overall, this is a good fix that improves the robustness of the agent.
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Addressing issue: #423
This commit fixes a nil pointer dereference in the loopagent that occurred when an LLM called a tool that was not registered with the current agent. The agent now gracefully handles the error and continues execution instead of crashing.
Test: Passed.