feat: add extended thinking (reasoning) support for Anthropic models#55
Draft
masudahiroto wants to merge 12 commits intomainfrom
Draft
feat: add extended thinking (reasoning) support for Anthropic models#55masudahiroto wants to merge 12 commits intomainfrom
masudahiroto wants to merge 12 commits intomainfrom
Conversation
When a multi-step agent run produces multiple steps each with text AND tool calls, the conversation context was losing per-step boundaries. After page reload, all tool calls were merged into one assistant message and all text was concatenated into a separate message, causing the LLM to misunderstand previous turns. Server: Move hasEmittedTextStart/messageId to StepContext so TEXT_MESSAGE_START/END is emitted per step instead of per run. Client: Add STEP_FINISHED handler to flush per-step messages while maintaining backward compatibility with servers without step events. useServerEvents: Fix extractTurnMessages to preserve assistant content. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
… flash Two UI issues with per-step TEXT_MESSAGE emission: 1. Streaming text cleared at TEXT_MESSAGE_END caused flash between steps. Fix: accumulate text across steps via runTextRef, only clear at RUN_FINISHED. 2. Intermediate assistant messages with text+toolCalls displayed as separate bubbles. Fix: hide all assistant messages with toolCalls from display, combine all step text into the final saved message. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Assistant messages now render with transparent background and minimal padding for a cleaner, less cluttered chat appearance. User messages retain the existing bubble style. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This reverts commit 25e5bdb.
saveAIResponse was using runTextRef (accumulated text from all steps) instead of client.currentMessageContent (last step only). Since intermediate steps' text is already preserved in turnMessages via extractTurnMessages, the final message duplicated that text. Use client.currentMessageContent for the saved message content. runTextRef continues to be used for streaming UI display only. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…ntation Tests were re-implementing extractTurnMessages locally, so bugs in the real function would not be caught. Export extractTurnMessages from useServerEvents.ts and import it in tests. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Tests were re-implementing transformMessagesToClientFormat locally. Export from useChatManagement.ts and import in both persistence test files so bugs in the real function are caught by tests. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Per-step messages are preserved for correct LLM context, but the UI now combines consecutive assistant messages within each turn into a single bubble. Intermediate assistant messages (with toolCalls) have their text merged with the final text-only message using paragraph separators. Add mergeAssistantMessagesForDisplay utility with 8 unit tests. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace 5 scattered test files (~1850 lines) with 2 focused test files (~350 lines) that directly verify the core bug fix: per-step text+tool association is preserved in conversation context sent to LLM on 2nd run. - client.multiStepContext.test.ts: integration test covering message assembly, 2nd run_agent context correctness, and text deduplication - AISDKAgent.perStepEvents.test.ts: server unit test for per-step TEXT_MESSAGE_START/END emission and event ordering Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…sages tests - Replace runTextRef (accumulated string never read) with hasTextFromPriorStepRef boolean for step separator logic - Add unit tests for mergeAssistantMessagesForDisplay (7 cases: simple exchange, multi-step merge, tool filtering, tool-only step, multiple turns, property preservation, ContentPart arrays) - Strengthen extractTurnMessages assertions in integration test Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…ests Replace Date.now() with constituent message IDs to produce stable React keys. Update stale JSDoc in extractTurnMessages to reflect STEP_FINISHED flushing. Add tests for empty input, trailing pending text, and ID determinism. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add support for Anthropic's extended thinking feature across the full stack. When enabled, the server streams reasoning events to the client, which renders them in a collapsible Reasoning component. Server: - AISDKAgent emits REASONING_START/REASONING_DELTA/REASONING_END events - Convert reasoning parts between AI SDK and Anthropic message formats - Preserve reasoning signatures across multi-turn conversations - Add MockReasoningModel under agents/testing/ for dev/test usage Client: - New Reasoning component with shimmer animation during streaming - useServerEvents handles REASONING_* event lifecycle - Reasoning parts persisted in chat history (reasoningParts on messages) - mergeAssistantMessages updated to consolidate reasoning parts Core: - Add REASONING_START, REASONING_DELTA, REASONING_END to AG-UI event types E2E: - Extended thinking tests covering single-turn, multi-turn, and multi-step reasoning scenarios Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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
1 participant
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.
Add support for Anthropic's extended thinking feature across the full stack. When enabled, the server streams reasoning events to the client, which renders them in a collapsible Reasoning component with shimmer animation.
Server: AISDKAgent emits REASONING_START/REASONING_DELTA/REASONING_END events, converts reasoning parts between AI SDK and Anthropic message formats, and preserves reasoning signatures across multi-turn conversations. MockReasoningModel added under agents/testing/ for dev/test usage.
Client: New Reasoning component handles streaming and completed reasoning display. useServerEvents manages REASONING_* event lifecycle. Reasoning parts are persisted in chat history. mergeAssistantMessages updated to consolidate reasoning parts.
Core: REASONING_START, REASONING_DELTA, REASONING_END added to AG-UI event types.
E2E tests cover single-turn, multi-turn, and multi-step reasoning scenarios.
Note: This PR is branched from #54. #54 has to be merged first.