Pr 49 #55
Closed
Pr 49 #55
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
Implements a new client.getResponse() method that provides flexible ways to consume streaming responses: - await response.text - Get complete text - await response.message - Get complete AssistantMessage - response.textStream - Stream text deltas - response.newMessagesStream - Stream incremental AssistantMessage updates - response.reasoningStream - Stream reasoning deltas - response.toolStream - Stream tool call deltas - response.fullResponsesStream - Stream all raw events - response.fullChatStream - Stream in chat-compatible format All consumption patterns support both concurrent and sequential access, allowing users to mix and match approaches as needed. Key implementation details: - ReusableReadableStream enables multiple concurrent consumers without blocking - ResponseWrapper provides lazy initialization with cached promises - Stream transformers convert ResponsesAPI events to different formats - Returns AssistantMessage type for consistency with chat API Tests: 19 passing, 1 skipped (model unavailable)
Convert all getter properties that return promises/iterators into explicit methods with get*() naming for better API clarity and consistency. Changes: - response.text → response.getText() - response.message → response.getMessage() - response.textStream → response.getTextStream() - response.newMessagesStream → response.getNewMessagesStream() - response.fullResponsesStream → response.getFullResponsesStream() - response.reasoningStream → response.getReasoningStream() - response.toolStream → response.getToolStream() - response.fullChatStream → response.getFullChatStream() Updated all test files, examples, and JSDoc documentation to reflect the new API. All 20 e2e tests pass successfully.
- Added TurnContext type with numberOfTurns (1-indexed), messageHistory, model/models - Updated tool execute function signatures to accept optional context parameter - Context is built in response-wrapper.ts during tool execution loop - Updated all tests and examples to demonstrate context usage - Context parameter is optional for backward compatibility - Exported TurnContext type in public API This allows tools to access conversation state including turn number, message history, and model information during execution. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
- Changed MaxToolRounds type to accept (context: TurnContext) => boolean - Removed old 3-parameter function signature for simplicity - Function receives full TurnContext with numberOfTurns, messageHistory, model/models - Returns true to allow another turn, false to stop execution - Updated examples to demonstrate the new function signature - Simplified implementation logic in response-wrapper.ts This provides more context to the maxToolRounds function and makes the API more consistent with tool execute functions. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
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.
No description provided.