[Model Routing] claude-sonnet-5 swallows streaming assistant.reasoning_delta; flushes all thinkingContent at completion

Open
#2,346 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
3/5
Estimated time
1-2 days
Newbie friendliness
55/100
Issue type
Bug
Clarity
Mostly clear
Activity status
Active
Tech stack
github, java
Domain
ai, api, performance

Research direction

Start at the implementation behind subscribe('assistant.reasoning_delta') and follow the model-routing path for claude-sonnet-5. Compare its handling with claude-sonnet-4.5 and verify whether upstream reasoning frames are emitted immediately rather than buffered. Done means real-time reasoning_delta events and low TTFT for claude-sonnet-5, without waiting for final completion.

Written by the indexing model from the issue text.

Description

question

Environment Details:

Working Model: claude-sonnet-4.5 (streams perfectly)

Failing Model: claude-sonnet-5

Integration: GitHub Copilot SDK (subscribe('assistant.reasoning_delta'))

Observed Behavior:
When routing requests to claude-sonnet-5, the SDK emits zero assistant.reasoning_delta events during the generation lifecycle. Instead, it accumulates them in the background, resulting in a ~25,000ms Time-to-First-Token (TTFT) and blocking client-side UI rendering. A complete, non-empty thinkingContent block is delivered atomically only when the final text stream buffer flushes or the file completes.

Expected Behavior:
The SDK should map Anthropic's streaming reasoning frames into real-time assistant.reasoning_delta events immediately upon receiving them from the upstream model router, preserving low operational TTFT just as it successfully does for claude-sonnet-4.5.

Dominant language
Java
Stars
10.5k
Forks
1.5k
Avg merge
1d 12h
Merged PRs (30d)
133

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from github/copilot-sdk

All issues in github/copilot-sdk

Similar issues

More Java issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.