[bot] Bedrock Converse `reasoningContent` blocks not normalized — extended thinking traces break UI schema
Nobody has claimed this yet.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 82/100
Research direction
Start in braintrust-sdk/src/main/java/dev/braintrust/instrumentation/InstrumentationSemConv.java, reading tagBedrockRequest, tagBedrockResponse, and normalizeBedrockMessage around lines 339–501. Then inspect BraintrustAWSBedrockTest.java and add coverage for a Bedrock reasoningContent block. Done means reasoningContent is normalized with the expected type while preserving its content and existing block handling remains intact.
Written by the indexing model from the issue text.
Description
<!-- provider-gap-audit: bedrock-reasoningcontent-not-normalized -->
Summary
InstrumentationSemConv.normalizeBedrockMessage() — the function that normalizes Bedrock Converse content blocks so they carry an explicit "type" field the Braintrust UI schema requires — recognizes text, toolUse, toolResult, and image blocks, but does not recognize reasoningContent, the official Bedrock Converse block type for extended thinking / Chain-of-Thought output (Claude 3.7+ and Amazon Nova reasoning models via additionalModelRequestFields.reasoning_config).
This is the same code path issue #85 describes as working correctly for tool use ("Non-streaming Converse calls handle tool use correctly — normalizeBedrockMessage() ... already recognizes toolUse, toolResult, and image"), but that issue is scoped to the streaming (ConverseStream) tool-use path and does not mention reasoningContent at all — this is a distinct gap in the shared, non-streaming-safe normalization helper used by both request and response tagging.
What is missing
In braintrust-sdk/src/main/java/dev/braintrust/instrumentation/InstrumentationSemConv.java, normalizeBedrockMessage() (lines 467–501):
if (block.has("text")) {
normalized.put("type", "text");
changed = true;
} else if (block.has("toolUse")) {
normalized.put("type", "tool_use");
changed = true;
} else if (block.has("toolResult")) {
normalized.put("type", "tool_result");
changed = true;
} else if (block.has("image")) {
normalized.put("type", "image");
changed = true;
}
There is no else if (block.has("reasoningContent")) branch. When a Bedrock Converse (or ConverseStream, once #85 is fixed) response contains a reasoningContent block ({"reasoningContent": {"reasoningText": {"text": "...", "signature": "..."}}}), it is left without a type field — unlike every sibling content-block type in the same array — so it doesn't match the schema the UI validates against for thread rendering (per this same method's own doc comment: "both the OpenAI and Anthropic schemas the UI validates against require an explicit type field").
This function is shared by both:
tagBedrockRequest()(line 389:inputArray.add(normalizeBedrockMessage(msg))) — affects multi-turn conversations that echo back a prior assistantreasoningContentblock (required by some models to preserve the reasoning trace across turns)tagBedrockResponse()(line 408:outputArray.add(normalizeBedrockMessage(message))) — affects the model's own reasoning output on the current turn
Braintrust docs status
unclear — the Braintrust docs list Bedrock as a supported provider (https://www.braintrust.dev/docs/integrations/ai-providers) but do not specifically document extended-thinking/reasoning content handling for Bedrock Converse.
Upstream sources
- AWS Bedrock Converse API —
reasoningContentblock, part of theContentBlockunion: https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ContentBlock.html - Amazon Nova extended reasoning guide (documents
reasoningContent/reasoningTextresponse shape): https://docs.aws.amazon.com/nova/latest/userguide/extended-thinking.html - Using Claude 3.7 Sonnet extended thinking via the Bedrock Converse API (
additionalModelRequestFields.reasoning_config, responsereasoningContent): https://seobs.medium.com/using-sonnet-3-7-reasoning-with-the-converse-api-on-aws-bedrock-6c838c685ad9
Local files inspected
braintrust-sdk/src/main/java/dev/braintrust/instrumentation/InstrumentationSemConv.java— lines 339–429 (tagBedrockRequest/tagBedrockResponse), lines 460–501 (normalizeBedrockMessage: onlytext/toolUse/toolResult/imagehandled)braintrust-sdk/instrumentation/aws_bedrock_2_30_0/src/test/java/dev/braintrust/instrumentation/awsbedrock/v2_30_0/BraintrustAWSBedrockTest.java— no test exercises a reasoning/extended-thinking model response- Confirmed via issue #85 that this shared helper is treated as the "correct" reference implementation for non-streaming content-block normalization, but it does not cover
reasoningContent
- Dominant language
- Java
- Stars
- 21
- Forks
- 5
- Avg merge
- 2d 7h
- Merged PRs (30d)
- 8
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from braintrustdata/braintrust-sdk-java
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
Difficulty 5/5 Over a week Newbie friendliness 35/100
All issues in braintrustdata/braintrust-sdk-java
Similar issues
-
certification
Difficulty 1/5 Under an hour Newbie friendliness 80/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
-
[BUG] ECR GetAuthorizationToken returns a proxyEndpoint for the default region, not the request's Openbug ecr
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
-
Needs: Triage Type: Feature request
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
AntennaPod/AntennaPod#8794 ·
-
agentic-workflows
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
github/copilot-sdk#2760 ·