WeKnora/internal/models
lyingbug 1c448bf72c
fix(chat): send one completion-token field per provider (#3082)
* fix(chat): send one completion-token field per provider

Agent dual-wrote max_tokens and max_completion_tokens, which Volcengine Ark
rejects. Collapse them to one budget and pick the wire name the way Pi does.

Fixes #3014

* fix(chat): shrink max_tokens provider whitelist to documented hosts

Only DeepSeek, Zhipu, SiliconFlow, Moonshot, NVIDIA, and self-hosted
vLLM-class runtimes stay on the legacy field. Aliyun DashScope documents
max_completion_tokens for thinking models and must not be forced onto
max_tokens.

* fix(chat): send max_tokens for LKEAP completions

Tencent LKEAP documents max_tokens only. Keep Pi's default of
max_completion_tokens, and classify every AllProviders() host so a new
vendor cannot silently inherit the default.
2026-09-07 19:16:27 +08:00
..
asr fix(security): harden model client redirects 2026-07-02 19:15:46 +08:00
chat fix(chat): send one completion-token field per provider (#3082) 2026-09-07 19:16:27 +08:00
embedding fix(embedding): validate WeKnoraCloud response indexes 2026-08-11 16:59:48 +08:00
limiter feat(system): expose model concurrency stats on runtime queues dashboard 2026-07-11 07:17:28 +08:00
provider feat: add LiteLLM as a model provider (#2923) 2026-09-01 12:21:03 +08:00
rerank feat(memory): add cross-session long-term memory 2026-08-13 18:00:02 +08:00
utils feat: integrate ChatBot provider and docreader 2026-04-13 17:47:24 +08:00
vlm feat(memory): add cross-session long-term memory 2026-08-13 18:00:02 +08:00