feat: OpenAI agents sdk instrumentation #2564
Open
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
dosubot
bot
added
the
size:XXL
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
| } | ||
|
|
||
| this._enabled = true; | ||
| } |
There was a problem hiding this comment.
State flag prevents second instrumentation method call
The createProcessor() method sets _enabled = true, which causes instrument() to return early. This prevents using createProcessor() followed by manual registration, defeating the purpose of having two separate APIs. The _enabled flag should only be set when actually registering with the SDK via instrument(), not when merely creating a processor instance.
Additional Locations (1)
@arizeai/openinference-core
@arizeai/openinference-genai
@arizeai/openinference-instrumentation-anthropic
@arizeai/openinference-instrumentation-bedrock
@arizeai/openinference-instrumentation-bedrock-agent-runtime
@arizeai/openinference-instrumentation-beeai
@arizeai/openinference-instrumentation-langchain
@arizeai/openinference-instrumentation-langchain-v0
@arizeai/openinference-instrumentation-mcp
@arizeai/openinference-instrumentation-openai
@arizeai/openinference-instrumentation-openai-agents
@arizeai/openinference-mastra
@arizeai/openinference-semantic-conventions
@arizeai/openinference-vercel
commit: |
Dwij1704
changed the title
| } | ||
| } | ||
| } | ||
| } |
There was a problem hiding this comment.
Off-by-one in handoff tracking memory cap
The reverseHandoffsDict size limit check occurs after adding a new entry and only removes one entry when the limit is exceeded. This allows the map to grow to MAX_HANDOFFS_IN_FLIGHT + 1 before cleanup, and when handoffs arrive faster than agent spans consume them, the cleanup rate becomes insufficient. The condition should check the size before adding or remove enough entries to stay under the limit.
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.
Note
Introduces OpenInference instrumentation for the OpenAI Agents SDK with a processor that maps SDK traces/spans to OpenTelemetry using OpenInference semantics.
@arizeai/openinference-instrumentation-openai-agentspackage exportingOpenAIAgentsInstrumentationandOpenInferenceTracingProcessorto register viasdk.addTraceProcessor()and emitAGENT/LLM/TOOLspans with attributes (messages, tools, usage, handoffs)basic-usage,guardrails,handoffs,lifecycle-hooks,multi-turn,streaming,structured-output) and sharedinstrumentation.tssetupgraph.node.id/parent_id), errors, and instrumentation wiringpackage.json,tsconfig*.json,vitest.config.ts) and updates lockfilesWritten by Cursor Bugbot for commit af3d98d. This will update automatically on new commits. Configure here.