ai: Thinking Shows Twice When a reasoning.text Detail Repeats Streamed reasoning_content

Aperta Adatta ai principianti
#64,723 1 commento 0 reazioni 0 assegnatari Vedi su GitHub

I maintainer di solito rispondono entro 1 giorno

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
2/5
Tempo stimato
1-3 ore
Idoneità per principianti
78/100
Tipo di issue
Bug
Chiarezza
Specificata chiaramente
Stato di attività
Attiva
Stack tecnologico
typescript
Ambito
backend, testing

Direzione di ricerca

Inizia da packages/ai/src/protocols/openai-chat.ts, in particolare da detailText e reasoningTextObserved, poi esamina i test del provider di chat OpenAI in packages/ai/test/provider/openai-chat.test.ts. Riproduci lo stream in cui a reasoning_content seguono dettagli corrispondenti di reasoning.text. Il lavoro è completato quando il blocco Thought contiene il testo una sola volta e il test di regressione passa.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

area/providers platform/macos status/repro-simulated type/bug version/v2
Description

Claude's thinking shows twice in the Thought block when the model is reached through an OpenAI-compatible gateway that streams reasoning_content and then sends the signed thinking block as one reasoning.text entry in reasoning_details. I see it in OpenChamber. The doubled text is also in the stored session, so it does not depend on the interface.

The next request sends the doubled text back as reasoning_content. The signed entry itself is sent back correctly.

The cause is in packages/ai/src/protocols/openai-chat.ts. detailText returns the text of every reasoning.text entry, and OpenCode appends that text as another reasoning delta after the streamed chunks. reasoningTextObserved already stops this for Kimi's summary entries but has no effect on reasoning.text.

The code is the same in v2.2.7, v2.3.2 and dev (ae88eb6a7).

In my local database, 730 of 918 reasoning blocks from Claude Sonnet and 188 of 219 from Claude Haiku are exactly doubled. The GPT model I use (321 blocks) shows no doubling.

I have a two-line fix with a regression test, and it passes the related existing provider tests. I can open a PR if a maintainer wants one.

Plugins

Two local plugins (memory and environment setup). Neither mentions reasoning or thinking.

OpenCode version

2.2.7 (I also read the source of 2.3.2 and dev)

Steps to reproduce
  1. Use a Claude Sonnet or Haiku model through a gateway that streams the chunks below on /v1/chat/completions. OpenCodex does this. OpenRouter sends both fields in one frame and is not affected.

    {"delta":{"reasoning_content":"Think "}}
    {"delta":{"reasoning_content":"hard."}}
    {"delta":{"reasoning_details":[{"type":"reasoning.text","text":"Think hard.","signature":"...","format":"anthropic-claude-v1","index":0}]}}
    {"delta":{"content":"Done"},"finish_reason":"stop"}
    
  2. Ask a question that makes the model think.

  3. Open the Thought block. It reads "Think hard.Think hard." and should read "Think hard."

The same stream as a test in packages/ai/test/provider/openai-chat.test.ts fails with Received: "Think hard.Think hard.".

Screenshot

No response

Operating System

macOS 27.2

Terminal

OpenChamber (web UI)

Lingua principale
TypeScript
Stelle
227k
Fork
30.7k
Merge medio
5h 14m
PR unite (30g)
486

Preparare l'ambiente

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di anomalyco/opencode

Tutte le issue di anomalyco/opencode

Issue simili

Altre issue su TypeScript

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.