fix(litellm): default max_tokens=4096 for the reasoning model #20

Merged

haylan merged 1 commits from fix/litellm-reasoning-max-tokens into main

2026-09-02 18:58:12 +00:00

Author	SHA1	Message	Date
haylanandClaude-Bot	100fed4274	fix(litellm): default max_tokens=4096 for the reasoning model Qwen3 spends output tokens on reasoning_content before writing content. Open WebUI's default chat request doesn't set max_tokens, so it fell through to llama.cpp's low default and the model ran out mid-thought, returning finish_reason=length with empty content — no reply shown in Open WebUI. Confirmed via a manual /v1/chat/completions call: works with max_tokens=2000, fails without it. litellm_params.max_tokens is a default, not a cap — any caller (or Open WebUI's per-model Advanced Params) that sets its own max_tokens still overrides it. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Q2CR8yawSf7pwAVYnjwFea	2026-09-02 20:55:39 +02:00

Author

SHA1

Message

Date

haylanandClaude-Bot

100fed4274

fix(litellm): default max_tokens=4096 for the reasoning model

Qwen3 spends output tokens on reasoning_content before writing content.
Open WebUI's default chat request doesn't set max_tokens, so it fell
through to llama.cpp's low default and the model ran out mid-thought,
returning finish_reason=length with empty content — no reply shown in
Open WebUI. Confirmed via a manual /v1/chat/completions call: works with
max_tokens=2000, fails without it.

litellm_params.max_tokens is a default, not a cap — any caller (or Open
WebUI's per-model Advanced Params) that sets its own max_tokens still
overrides it.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Q2CR8yawSf7pwAVYnjwFea

2026-09-02 20:55:39 +02:00