fix: add entity input/output to agent spans #840
Merged
+21
−0
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
Contributor
WalkthroughThe change updates transformTelemetryMetadata in the AI SDK transformations to propagate LLM/tool input and output message data into trace entity input/output attributes when a top-level or agent span is detected, using existing conditional logic that sets span kind and entity name. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes
Possibly related PRs
Suggested reviewers
Poem
Pre-merge checks and finishing touches✅ Passed checks (3 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
📜 Recent review detailsConfiguration used: CodeRabbit UI Review profile: CHILL Plan: Pro Disabled knowledge base sources:
📒 Files selected for processing (1)
🧰 Additional context used📓 Path-based instructions (2)packages/{instrumentation-*,traceloop-sdk}/**/*.{ts,tsx}📄 CodeRabbit inference engine (CLAUDE.md)
Files:
packages/traceloop-sdk/**/*.{ts,tsx}📄 CodeRabbit inference engine (CLAUDE.md)
Files:
🧠 Learnings (8)📓 Common learnings📚 Learning: 2025-08-24T22:08:07.023ZApplied to files:
📚 Learning: 2025-08-24T22:08:07.023ZApplied to files:
📚 Learning: 2025-08-24T22:08:07.023ZApplied to files:
📚 Learning: 2025-08-24T22:08:07.023ZApplied to files:
📚 Learning: 2025-08-12T13:57:05.901ZApplied to files:
📚 Learning: 2025-08-12T13:58:25.583ZApplied to files:
📚 Learning: 2025-08-24T22:08:07.023ZApplied to files:
🧬 Code graph analysis (1)packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts (1)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
🔇 Additional comments (1)
Comment |
![ellipsis-dev[bot]](https://avatars.githubusercontent.com/in/64358?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Important
Looks good to me! 👍
Reviewed everything up to 9126d8e in 33 seconds. Click for details.
- Reviewed
21lines of code in1files - Skipped
0files when reviewing. - Skipped posting
2draft comments. View those below. - Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.
1. packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts:496
- Draft comment:
Consider checking explicitly for undefined (e.g. usinginputMessages !== undefined) instead of relying on truthy checks. Empty but valid values might be skipped. - Reason this comment was not posted:
Confidence changes required:50%<= threshold50%None
2. packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts:496
- Draft comment:
The added transformation aligns with similar patterns in the file. Ensure the new entity input/output attributes are consistent with related processing. - Reason this comment was not posted:
Confidence changes required:0%<= threshold50%None
Workflow ID: wflow_cSPJyDVASWAb9tNE
You can customize 
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts (1)
495-504: LGTM! Agent span entity input/output propagation is correct.The logic correctly propagates LLM message data to entity input/output attributes for agent spans. This mirrors the pattern used for tool spans (lines 535-540) and ensures agent spans have the necessary input/output data for tracing.
Consider adding a brief comment explaining the purpose of this propagation:
attributes[SpanAttributes.TRACELOOP_ENTITY_NAME] = agentName; + // Propagate LLM messages to entity input/output for agent span tracing const inputMessages = attributes[SpanAttributes.LLM_INPUT_MESSAGES];
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
Disabled knowledge base sources:
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
packages/{instrumentation-*,traceloop-sdk}/**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
Import AI/LLM semantic attribute constants from @traceloop/ai-semantic-conventions rather than hardcoding strings
Files:
packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts
packages/traceloop-sdk/**/*.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
packages/traceloop-sdk/**/*.{ts,tsx}: Use the provided decorators (@workflow, @task, @agent) for workflow/task/agent spans instead of re-implementing them
For manual LLM operations, use trace.withLLMSpan from @traceloop/node-server-sdk
Files:
packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts
🧠 Learnings (8)
📓 Common learnings
Learnt from: CR
Repo: traceloop/openllmetry-js PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-08-24T22:08:07.023Z
Learning: Applies to packages/traceloop-sdk/**/*.{ts,tsx} : For manual LLM operations, use trace.withLLMSpan from traceloop/node-server-sdk
Learnt from: CR
Repo: traceloop/openllmetry-js PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-08-24T22:08:07.023Z
Learning: Applies to packages/traceloop-sdk/**/*.{ts,tsx} : Use the provided decorators (workflow, task, agent) for workflow/task/agent spans instead of re-implementing them
Learnt from: CR
Repo: traceloop/openllmetry-js PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-08-24T22:08:07.023Z
Learning: Applies to packages/instrumentation-*/**/*.{ts,tsx} : Instrumentations must create spans with appropriate AI/LLM semantic attributes for calls they wrap
Learnt from: CR
Repo: traceloop/openllmetry-js PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-08-24T22:08:07.023Z
Learning: Applies to packages/{instrumentation-*,traceloop-sdk}/**/*.{ts,tsx} : Import AI/LLM semantic attribute constants from traceloop/ai-semantic-conventions rather than hardcoding strings
📚 Learning: 2025-08-24T22:08:07.023Z
Learnt from: CR
Repo: traceloop/openllmetry-js PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-08-24T22:08:07.023Z
Learning: Applies to packages/{instrumentation-*,traceloop-sdk}/**/*.{ts,tsx} : Import AI/LLM semantic attribute constants from traceloop/ai-semantic-conventions rather than hardcoding strings
Applied to files:
packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts
📚 Learning: 2025-08-24T22:08:07.023Z
Learnt from: CR
Repo: traceloop/openllmetry-js PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-08-24T22:08:07.023Z
Learning: Applies to packages/traceloop-sdk/**/*.{ts,tsx} : For manual LLM operations, use trace.withLLMSpan from traceloop/node-server-sdk
Applied to files:
packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts
📚 Learning: 2025-08-24T22:08:07.023Z
Learnt from: CR
Repo: traceloop/openllmetry-js PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-08-24T22:08:07.023Z
Learning: Applies to packages/traceloop-sdk/**/*.{ts,tsx} : Use the provided decorators (workflow, task, agent) for workflow/task/agent spans instead of re-implementing them
Applied to files:
packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts
📚 Learning: 2025-08-24T22:08:07.023Z
Learnt from: CR
Repo: traceloop/openllmetry-js PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-08-24T22:08:07.023Z
Learning: Applies to packages/instrumentation-*/**/*.{ts,tsx} : Instrumentations must create spans with appropriate AI/LLM semantic attributes for calls they wrap
Applied to files:
packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts
📚 Learning: 2025-08-12T13:57:05.901Z
Learnt from: galzilber
Repo: traceloop/openllmetry-js PR: 643
File: packages/traceloop-sdk/test/datasets-final.test.ts:97-105
Timestamp: 2025-08-12T13:57:05.901Z
Learning: The traceloop-sdk uses a response transformer (`transformApiResponse` in `packages/traceloop-sdk/src/lib/utils/response-transformer.ts`) that converts snake_case API responses to camelCase for SDK interfaces. Raw API responses use snake_case but SDK consumers see camelCase fields.
Applied to files:
packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts
📚 Learning: 2025-08-24T22:08:07.023Z
Learnt from: CR
Repo: traceloop/openllmetry-js PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-08-24T22:08:07.023Z
Learning: Applies to packages/ai-semantic-conventions/src/SemanticAttributes.ts : Define all AI/LLM span attribute constants in packages/ai-semantic-conventions/src/SemanticAttributes.ts
Applied to files:
packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts
📚 Learning: 2025-08-24T22:08:07.023Z
Learnt from: CR
Repo: traceloop/openllmetry-js PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-08-24T22:08:07.023Z
Learning: Applies to packages/instrumentation-*/**/*.{ts,tsx} : Do not implement anonymous telemetry collection in instrumentation packages; telemetry is collected only in the SDK
Applied to files:
packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts
🧬 Code graph analysis (1)
packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts (1)
packages/ai-semantic-conventions/src/SemanticAttributes.ts (1)
SpanAttributes(23-79)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Build and test
doronkopit5
approved these changes
Dec 8, 2025
Contributor
There was a problem hiding this comment.
Important
Looks good to me! 👍
Reviewed bc4e703 in 1 minute and 38 seconds. Click for details.
- Reviewed
35lines of code in1files - Skipped
0files when reviewing. - Skipped posting
1draft comments. View those below. - Modify your settings and rules to customize what types of comments Ellipsis leaves. And don't forget to react with 👍 or 👎 to teach Ellipsis.
1. packages/traceloop-sdk/src/lib/tracing/ai-sdk-transformations.ts:496
- Draft comment:
The new logic maps LLM messages if available and falls back to toolCall args/results. Ensure this else-if approach is intended, as a partial presence (e.g. LLM_INPUT_MESSAGES exists but not LLM_OUTPUT_MESSAGES while toolCall.result is provided) will ignore the toolCall value. - Reason this comment was not posted:
Decided after close inspection that this draft comment was likely wrong and/or not actionable: usefulness confidence = 15% vs. threshold = 50% The comment starts with "Ensure this else-if approach is intended" which is asking the PR author to confirm their intention. This violates the rule: "Do NOT ask the PR author to confirm their intention, to explain, to double-check things, to ensure the behavior is intended". The comment is also speculative - it says "as a partial presence...will ignore the toolCall value" which is describing a hypothetical scenario. The rules explicitly state: "Do NOT make speculative comments, such as 'If X, then Y is an issue', Only comment if it is definitely an issue." This comment is describing a potential edge case but not definitively stating it's a bug. The author likely intended this behavior as a priority system (LLM messages take precedence over tool calls). However, the comment does identify a real behavioral consequence of the code change - the else-if structure does create a priority system where LLM messages completely override tool calls. This might be a legitimate code quality concern if the behavior is unintended. The comment could be seen as pointing out a potential bug rather than just being speculative. While the behavioral consequence is real, the comment is phrased as asking the author to verify intent ("Ensure this...is intended") rather than stating a definite problem. The rules are clear that we should not ask authors to confirm intentions or make speculative comments about edge cases. Without strong evidence that this is definitely a bug (rather than intentional priority logic), this comment should be deleted. This comment should be deleted. It asks the PR author to confirm their intention ("Ensure this...is intended") and makes a speculative observation about an edge case without definitively identifying it as a bug. Both of these violate the review rules.
Workflow ID: wflow_hgsI5aKKKJXtJCAs
You can customize
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.
Important
Enhance
transformTelemetryMetadata()to map LLM and tool call messages to trace entity input/output attributes inai-sdk-transformations.ts.transformTelemetryMetadata()inai-sdk-transformations.ts, map LLM input/output messages toTRACELOOP_ENTITY_INPUTandTRACELOOP_ENTITY_OUTPUTattributes.ai.toolCall.argsorai.toolCall.resultare present, mapping them to entity input/output attributes if LLM messages are absent.This description was created by
for bc4e703. You can customize this summary. It will automatically update as commits are pushed.
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.