Hacktoberfest 2026: những issue maintainer đã đánh dấu cho tháng Mười, đang mở và phù hợp người mới. Xem issue Hacktoberfest

[bot] OpenAI-compatible chat completions streaming drops `reasoning_content` (affects DeepSeek and other providers using the plain OpenAI SDK)

Đang mở
#2,511 1 bình luận 0 reaction 0 người được giao Xem trên GitHub

Maintainer thường phản hồi trong vòng 2 ngày

Chưa có ai nhận issue này.

Đánh giá

Độ khó
3/5
Thời gian dự kiến
1-2 ngày
Mức phù hợp với người mới
65/100
Loại issue
Lỗi
Độ rõ ràng
Đặc tả rõ ràng
Mức độ hoạt động
Sôi nổi
Công nghệ
javascript, typescript

Hướng nghiên cứu

The issue is in js/src/instrumentation/plugins/openai-plugin.ts. Start by examining the aggregateChatCompletionChunks function and the AggregatedChatChoice and toChatChoice types. Compare with the fixed implementations in groq-plugin.ts and openrouter-plugin.ts to understand the pattern for adding reasoning content aggregation. The goal is to modify the shared function to read delta.reasoning, delta.reasoning_content, or delta.reasoning_details and include them in the aggregated output. Test by simulating a streaming response from an OpenAI-compatible provider like DeepSeek.

Do mô hình lập chỉ mục viết ra từ nội dung của issue.

Mô tả

Summary

The shared streaming aggregation function used by the plain OpenAI plugin (aggregateChatCompletionChunks in js/src/instrumentation/plugins/openai-plugin.ts) does not capture reasoning/reasoning_content/reasoning_details fields from chat-completions streaming deltas. This function is the base implementation used directly by the OpenAI chat.completions.create channel — the exact code path exercised whenever a user points the vanilla openai npm package at a custom baseURL, which is DeepSeek's own documented integration method (and a common pattern for other OpenAI-compatible inference providers/self-hosted reasoning models). Reasoning content emitted during streaming by these providers is silently dropped from spans.

This is the same class of bug already found and fixed three times in sibling/downstream plugins — Mistral (#1857, fixed), OpenRouter (#1883, fixed), and Groq (#1911, fixed) — but in each of those fixes, the shared base function itself was left untouched, so the gap persists for any consumer that reaches it directly (i.e. the plain OpenAI SDK against a third-party OpenAI-compatible endpoint).

What instrumentation is missing

Streaming aggregation never reads reasoning fields

In js/src/instrumentation/plugins/openai-plugin.ts:

  • AggregatedChatChoice (lines 408–420) has fields for role, content, refusal, audio, toolCallsByIndex, logprobs, and finish_reason — no field for reasoning content.
  • aggregateChatCompletionChunks (lines 459 onward) reads delta.finish_reason, delta.role, delta.content, delta.refusal, and delta.audio (lines 505–534+) — there is no branch reading delta.reasoning or delta.reasoning_content.
  • toChatChoice (lines 435–452) builds the final aggregated message from role, content, refusal, audio, tool_calls only.

A repo-wide check confirms this: js/src/instrumentation/plugins/openai-plugin.ts has zero occurrences of "reasoning" (case-insensitive). By contrast, js/src/instrumentation/plugins/groq-plugin.ts (lines 680–720) wraps this exact shared function with an additional aggregateGroqReasoning post-processing step specifically because the shared function doesn't handle it — direct proof the underlying gap was deliberately routed around for Groq's fix rather than fixed at the source, leaving it open for every other consumer of the shared function.

Vendor types have no typed reasoning field either

js/src/vendor-sdk-types/openai-common.ts, OpenAIChatDelta (lines 135–143):

interface OpenAIChatDelta {
  role?: string;
  content?: string;
  refusal?: string;
  audio?: OpenAIChatAudio | null;
  tool_calls?: OpenAIChatToolCallDelta[];
  finish_reason?: string | null;
  [key: string]: unknown;
}

The [key: string]: unknown index signature means the runtime value is present on delta when a provider sends it, but the aggregation code never reads it.

Non-streaming path is unaffected

The non-streaming chatCompletionsCreate handler (openai-plugin.ts lines 89–109) uses extractOutput: (result) => result?.choices, a full passthrough — so message.reasoning_content survives for non-streaming calls. The gap is specific to streaming aggregation.

Upstream API format

DeepSeek's chat completions API (OpenAI-compatible, accessed via the plain openai SDK with a custom baseURL per DeepSeek's own quickstart) returns chain-of-thought content in thinking-enabled models via a reasoning_content field at the same level as content. In streaming responses this is delta.reasoning_content, a nullable string emitted incrementally in chat.completion.chunk objects, analogous to how delta.content streams the final answer.

This same non-standard reasoning/reasoning_content/reasoning_details extension pattern is also what OpenRouter (#1883) and Groq (#1911) needed dedicated fixes for — it is a broadly used convention among OpenAI-compatible providers, not unique to one vendor.

Comparison with other providers in this repo

Provider Reasoning content captured in streaming
Anthropic thinking_delta aggregated
Google GenAI thought parts handled
AI SDK reasoning-delta chunks aggregated
Cohere thinking content blocks aggregated
Mistral thinking chunks aggregated — fixed in #1857
OpenRouter reasoning/reasoning_content/reasoning_details aggregated — fixed in #1883
Groq reasoning aggregated via dedicated wrapper — fixed in #1911
OpenAI base plugin (chat.completions.create) Silently dropped — this issue

Braintrust docs status

not_found — checked https://www.braintrust.dev/docs/integrations/ai-providers/openai. The page documents metrics like completion_reasoning_tokens (a token count) and covers pointing the OpenAI client at a custom API base URL/endpoint path, but does not mention reasoning_content capture or DeepSeek/OpenAI-compatible reasoning-content streaming at all.

Local files inspected

  • js/src/instrumentation/plugins/openai-plugin.ts (lines 89–109: non-streaming passthrough is fine; lines 408–452: AggregatedChatChoice/toChatChoice have no reasoning field; lines 459–534+: aggregateChatCompletionChunks never reads delta.reasoning/delta.reasoning_content)
  • js/src/instrumentation/plugins/openai-channels.ts (chatCompletionsCreate channel definition)
  • js/src/vendor-sdk-types/openai-common.ts (lines 135–143: OpenAIChatDelta has no typed reasoning field)
  • js/src/instrumentation/plugins/groq-plugin.ts (lines 680–720: proof pattern — Groq wraps the shared function with its own aggregateGroqReasoning rather than the shared function being fixed)
  • js/src/instrumentation/plugins/openrouter-plugin.ts (confirmed sibling plugin's own separate aggregateOpenRouterChatChunks has equivalent handling, unrelated to the shared OpenAI function)
Ngôn ngữ chính
TypeScript
Star
27
Fork
13
Merge trung bình
2 ngày 20 giờ
Pull request đã merge (30 ngày)
66

Chuẩn bị môi trường

Chúng tôi chưa kiểm tra các tệp thiết lập môi trường của dự án này. Hãy bắt đầu từ README và xem hướng dẫn đóng góp lần đầu của chúng tôi để biết các bước chung.

Bắt đầu từ đâu

  1. Đọc hết issue, rồi đọc hướng dẫn đóng góp của dự án.
  2. Bình luận trên issue rằng bạn sẽ nhận — tránh hai người làm cùng một việc.
  3. Fork repository và làm thay đổi trên một nhánh.
  4. Mở pull request có tham chiếu số hiệu của issue.

Issue khác của braintrustdata/braintrust-sdk-javascript

Tất cả issue của braintrustdata/braintrust-sdk-javascript

Issue tương tự

Thêm issue về TypeScript

Nhận issue mới trong hộp thư của bạn

Bản tóm tắt ngắn những issue GitHub phù hợp với người mới.