Repository navigation
feat: read chat streams one way and share reply parts with the model chat - #3843
Merged
Merged
Conversation
…chat Every chat reads its stream with the SDK's readPixelStreamChunk, which hands text, reasoning, tool deltas, and token usage to their handlers, skips empty text and reasoning, and ignores a kind it does not know. The model chat no longer takes a usage chunk, or the chunk that closes a tool call, for a tool call, and the playground no longer logs usage chunks as unknown. The SDK's stream types include usage. The playground's reasoning toggle, generating line, and loading messages move to @semoss/shared as ChatReasoning, ChatGeneratingIndicator, and useLoadingMessage, beside a display-only ChatToolCallRow, with their words in a transcript namespace. The model chat shows its reasoning, tool calls, and the wait for the first words with them, so a reply reads the same in both chats.
✅ Snyk checks have passed. No issues have been found so far.
💻 Catch issues earlier using the plugins for VS Code, JetBrains IDEs, Visual Studio, and Eclipse. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Every chat reads its stream with the SDK's readPixelStreamChunk, which hands text, reasoning, tool deltas, and token usage to their handlers, skips empty text and reasoning, and ignores a kind it does not know. The model chat no longer takes a usage chunk, or the chunk that closes a tool call, for a tool call, and the playground no longer logs usage chunks as unknown. The SDK's stream types include usage.
The playground's reasoning toggle, generating line, and loading messages move to @semoss/shared as ChatReasoning, ChatGeneratingIndicator, and useLoadingMessage, beside a display-only ChatToolCallRow, with their words in a transcript namespace. The model chat shows its reasoning, tool calls, and the wait for the first words with them, so a reply reads the same in both chats.