Fix Bedrock Converse streaming and token handling #1763
Closed
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
|
|
||
| DefaultUsage usage = new DefaultUsage(promptTokens, generationTokens, totalTokens); | ||
|
|
||
| Document modelResponseFields = response.additionalModelResponseFields(); |
Member
There was a problem hiding this comment.
We don't seem to use modelResponseFields and metrics. Also, we don't copy all the metadata attributes into the ChatResponse here.
| && this.isToolCall(chatResponse, Set.of("tool_use"))) { | ||
| var toolCallConversation = this.handleToolCalls(prompt, chatResponse); | ||
| return this.call(new Prompt(toolCallConversation, prompt.getOptions())); | ||
| return this.internalCall(new Prompt(toolCallConversation, prompt.getOptions()), chatResponse); |
Member
There was a problem hiding this comment.
We need test coverage to test this flow - especially to verify the final ChatResponse containing the preceding one.
| if (perviousChatResponse != null && perviousChatResponse.getMetadata() != null | ||
| && perviousChatResponse.getMetadata().getUsage() != null) { | ||
|
|
||
| promptTokens += perviousChatResponse.getMetadata().getUsage().getPromptTokens(); |
Member
There was a problem hiding this comment.
I have manually verified this step. Is there an effective way we can add a test to validate this additive operation in our tests?
- Modify stream method to support recursive tool call handling - Update token tracking and metadata merging for streamed responses - Improve token usage calculation for tool use events - Update test cases to handle new response processing Resolves spring-projects#1743
- Modify call method to support recursive tool call handling - Add support for cumulative token tracking across tool call iterations - Introduce internal call method to track and aggregate token usage - Merge previous chat response tokens with current response tokens
tzolov
force-pushed
the
fix-bedrock-converse-tool-usage
branch
from
65936a9 to
625a557
Compare
Member
|
Thanks for updating the tests! LGTM, merging. |
Member
|
Rebased, squashed, fixed check style error and merged as 00ede3f |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Resolves #1743