fix(claude): separate reasoning summary parts in streamed thinking - #944
Draft
DevMello wants to merge 1 commit into
Draft
fix(claude): separate reasoning summary parts in streamed thinking#944DevMello wants to merge 1 commit into
DevMello wants to merge 1 commit into
Conversation
The streaming translator folded every summary part into one thinking block with no separator, so multi-part summaries rendered as run-on text. The JSON path already joins parts with a blank line; the stream now emits the same separator at part boundaries.
📝 WalkthroughWalkthroughChangesReasoning stream handling
Estimated code review effort: 2 (Simple) | ~10 minutes Suggested reviewers: 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@tests/claude-outbound.test.ts`:
- Around line 242-260: Add coverage in the “same-part deltas and index-free
reasoning frames never get a separator” test for indexed reasoning content by
emitting deltas with content_index 0 and 1. Collect the converted message and
assert its thinking content contains the two parts separated by "\n\n",
exercising the content_index branch while preserving the existing same-part and
index-free assertions.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro Plus
Run ID: 8b37aca0-694d-480d-a5f3-7c2226c9e0ff
📒 Files selected for processing (2)
src/claude/outbound.tstests/claude-outbound.test.ts
Comment on lines
+242
to
+260
| test("same-part deltas and index-free reasoning frames never get a separator", async () => { | ||
| const samePart = [ | ||
| sse("response.created", { response: { id: "resp_1", status: "in_progress" } }), | ||
| sse("response.reasoning_summary_text.delta", { item_id: "rs_1", output_index: 0, summary_index: 0, delta: "Hel" }), | ||
| sse("response.reasoning_summary_text.delta", { item_id: "rs_1", output_index: 0, summary_index: 0, delta: "lo" }), | ||
| sse("response.completed", { response: { status: "completed", usage: { input_tokens: 1, output_tokens: 1 } } }), | ||
| ].join(""); | ||
| const msg1 = await collectAnthropicMessage(responsesSseToAnthropicSse(streamFrom(samePart), "m"), "m") as Record<string, any>; | ||
| expect(msg1.content.find((b: Record<string, unknown>) => b.type === "thinking").thinking).toBe("Hello"); | ||
|
|
||
| const indexFree = [ | ||
| sse("response.created", { response: { id: "resp_1", status: "in_progress" } }), | ||
| sse("response.reasoning_text.delta", { delta: "A" }), | ||
| sse("response.reasoning_text.delta", { delta: "B" }), | ||
| sse("response.completed", { response: { status: "completed", usage: { input_tokens: 1, output_tokens: 1 } } }), | ||
| ].join(""); | ||
| const msg2 = await collectAnthropicMessage(responsesSseToAnthropicSse(streamFrom(indexFree), "m"), "m") as Record<string, any>; | ||
| expect(msg2.content.find((b: Record<string, unknown>) => b.type === "thinking").thinking).toBe("AB"); | ||
| }); |
There was a problem hiding this comment.
📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick win
Cover indexed reasoning content parts.
The new content_index branch is not exercised. The current test only verifies repeated index-free frames. Add deltas with content_index: 0 and content_index: 1, then assert that the result contains "\n\n" between the parts.
Proposed regression case
+ const indexedContent = [
+ sse("response.reasoning_text.delta", {
+ item_id: "rs_1", output_index: 0, content_index: 0, delta: "A",
+ }),
+ sse("response.reasoning_text.delta", {
+ item_id: "rs_1", output_index: 0, content_index: 1, delta: "B",
+ }),
+ sse("response.completed", {
+ response: { status: "completed", usage: { input_tokens: 1, output_tokens: 1 } },
+ }),
+ ].join("");
+ const indexedMsg = await collectAnthropicMessage(
+ responsesSseToAnthropicSse(streamFrom(indexedContent), "m"),
+ "m",
+ ) as Record<string, any>;
+ expect(indexedMsg.content.find((b: Record<string, unknown>) => b.type === "thinking").thinking)
+ .toBe("A\n\nB");📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| test("same-part deltas and index-free reasoning frames never get a separator", async () => { | |
| const samePart = [ | |
| sse("response.created", { response: { id: "resp_1", status: "in_progress" } }), | |
| sse("response.reasoning_summary_text.delta", { item_id: "rs_1", output_index: 0, summary_index: 0, delta: "Hel" }), | |
| sse("response.reasoning_summary_text.delta", { item_id: "rs_1", output_index: 0, summary_index: 0, delta: "lo" }), | |
| sse("response.completed", { response: { status: "completed", usage: { input_tokens: 1, output_tokens: 1 } } }), | |
| ].join(""); | |
| const msg1 = await collectAnthropicMessage(responsesSseToAnthropicSse(streamFrom(samePart), "m"), "m") as Record<string, any>; | |
| expect(msg1.content.find((b: Record<string, unknown>) => b.type === "thinking").thinking).toBe("Hello"); | |
| const indexFree = [ | |
| sse("response.created", { response: { id: "resp_1", status: "in_progress" } }), | |
| sse("response.reasoning_text.delta", { delta: "A" }), | |
| sse("response.reasoning_text.delta", { delta: "B" }), | |
| sse("response.completed", { response: { status: "completed", usage: { input_tokens: 1, output_tokens: 1 } } }), | |
| ].join(""); | |
| const msg2 = await collectAnthropicMessage(responsesSseToAnthropicSse(streamFrom(indexFree), "m"), "m") as Record<string, any>; | |
| expect(msg2.content.find((b: Record<string, unknown>) => b.type === "thinking").thinking).toBe("AB"); | |
| }); | |
| test("same-part deltas and index-free reasoning frames never get a separator", async () => { | |
| const samePart = [ | |
| sse("response.created", { response: { id: "resp_1", status: "in_progress" } }), | |
| sse("response.reasoning_summary_text.delta", { item_id: "rs_1", output_index: 0, summary_index: 0, delta: "Hel" }), | |
| sse("response.reasoning_summary_text.delta", { item_id: "rs_1", output_index: 0, summary_index: 0, delta: "lo" }), | |
| sse("response.completed", { response: { status: "completed", usage: { input_tokens: 1, output_tokens: 1 } } }), | |
| ].join(""); | |
| const msg1 = await collectAnthropicMessage(responsesSseToAnthropicSse(streamFrom(samePart), "m"), "m") as Record<string, any>; | |
| expect(msg1.content.find((b: Record<string, unknown>) => b.type === "thinking").thinking).toBe("Hello"); | |
| const indexFree = [ | |
| sse("response.created", { response: { id: "resp_1", status: "in_progress" } }), | |
| sse("response.reasoning_text.delta", { delta: "A" }), | |
| sse("response.reasoning_text.delta", { delta: "B" }), | |
| sse("response.completed", { response: { status: "completed", usage: { input_tokens: 1, output_tokens: 1 } } }), | |
| ].join(""); | |
| const msg2 = await collectAnthropicMessage(responsesSseToAnthropicSse(streamFrom(indexFree), "m"), "m") as Record<string, any>; | |
| expect(msg2.content.find((b: Record<string, unknown>) => b.type === "thinking").thinking).toBe("AB"); | |
| const indexedContent = [ | |
| sse("response.reasoning_text.delta", { | |
| item_id: "rs_1", output_index: 0, content_index: 0, delta: "A", | |
| }), | |
| sse("response.reasoning_text.delta", { | |
| item_id: "rs_1", output_index: 0, content_index: 1, delta: "B", | |
| }), | |
| sse("response.completed", { | |
| response: { status: "completed", usage: { input_tokens: 1, output_tokens: 1 } }, | |
| }), | |
| ].join(""); | |
| const indexedMsg = await collectAnthropicMessage( | |
| responsesSseToAnthropicSse(streamFrom(indexedContent), "m"), | |
| "m", | |
| ) as Record<string, any>; | |
| expect(indexedMsg.content.find((b: Record<string, unknown>) => b.type === "thinking").thinking) | |
| .toBe("A\n\nB"); | |
| }); |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@tests/claude-outbound.test.ts` around lines 242 - 260, Add coverage in the
“same-part deltas and index-free reasoning frames never get a separator” test
for indexed reasoning content by emitting deltas with content_index 0 and 1.
Collect the converted message and assert its thinking content contains the two
parts separated by "\n\n", exercising the content_index branch while preserving
the existing same-part and index-free assertions.
Owner
|
Carried onto the review stack as #953 (stack 3/3), unmodified. Your commits were taken with Verified on the stack: This PR stays open until #953 lands. If a maintainer prefers to take yours directly instead, that path is unaffected — the stack commits get dropped and this one merges. Once #953 merges I'll close this as carried, with the credit already in the commit history rather than in a comment. Stack: #951 (plan, base Thanks for the fix. |
This was referenced Aug 3, 2026
Wibias
marked this pull request as draft
August 3, 2026 20:51
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
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.
Summary
On the native ChatGPT backend the upstream Responses stream is translated straight into Anthropic SSE. Reasoning summaries arrive there in parts, each its own paragraph with a bold headline. The streaming translator folded every part into one thinking block with no separator, so thinking text rendered as run-on lines like "wants X.Planning the fix". The non-streaming translator in the same file already joins parts with a blank line. The stream now tracks part identity on the delta frames and emits the same blank-line separator at part boundaries. Frames without part indices keep a constant key and behave as before, and a new reasoning item still opens its own block.
Verification
tests/claude-outbound.test.ts: multi-part summaries match the JSON path's joined text, and same-part or index-free deltas never get a separator.bun run test,typecheck,lint:gui,privacy:scan.Checklist
Summary by CodeRabbit
Bug Fixes
Tests