feat: support multimodal tool results and improve tool message handling #6816
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Outdated suggestions cannot be applied.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.
Describe Your Changes
ToolResulttype that mirrors the structure returned by tools (text, image data, URLs, errors).convertToolPartToApiContentPartto translate each tool output part into the format expected by the OpenAI chat completion API.CompletionMessagesBuilder.addToolMessageto accept a fullToolResultinstead of a plain string and to:contentarray.anytype for thetoolrole as required by the API.postMessageProcessingto pass the raw tool result (result as ToolResult) toaddToolMessage, avoiding premature extraction of only the first text part.These changes enable the chat system to handle richer tool outputs (e.g., images, mixed content) and provide more robust error handling.
Fixes Issues
Self Checklist