WeKnora/internal/models
DerrickLinus a9d71038b6
fix(models): stop advertising graded thinking levels the wire format drops (#3552)
* fix(models): stop advertising graded thinking levels the wire format drops

A generic-provider row (relays, self-hosted runtimes — the default for
uncatalogued models) resolves an empty ThinkingLevelMap, whose missing-key
semantics report every graded rung as supported. Capabilities() then hands
minimal/low/medium/high to the frontend, which renders a selector whose
choice applyThinking silently discards: the chat-template-kwargs branch
sends only the enable_thinking boolean and no reasoning_effort is computed.
Same defect class as the two NVIDIA NIM entries fixed in #3489, but there
is no catalog entry to repair here.

Collapse Capabilities() to the levels the wire can actually express for a
boolean-only switch (off/auto) unless the settings opt into
supports_reasoning_effort. The vendor map itself is untouched, so vendors
that do carry effort keep their ladders.

* fix(models): carry reasoning_effort through the chat-template switch when opted in

The Capabilities() guard kept a vendor's ladder when it opts into
supports_reasoning_effort, but applyThinking's chat-template-kwargs branch
wrote only the enable_thinking boolean and dropped the already-computed
effort — so the opt-in combination still sent byte-identical bodies for
every graded rung (#3551's defect, alive in exactly the shape the review
flagged). Mirror the enable_thinking dialect: write reasoning_effort on
top of the switch when one was computed. A golden case pins the opt-in
combination; the no-opt-in guard case keeps asserting the level is
dropped.

* style(models): wrap long Resolve call in thinking-levels test

---------

Co-authored-by: wizardchen <wizardchen@tencent.com>
Co-authored-by: lyingbug <xiayula2014@gmail.com>
2026-09-25 22:23:08 +08:00
..
api fix(models): stop advertising graded thinking levels the wire format drops (#3552) 2026-09-25 22:23:08 +08:00
asr refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
catalog fix(models): serve qwen3-rerank on the native DashScope rerank protocol 2026-09-24 14:18:55 +08:00
chat refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
embedding refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
internal/configcopy refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
limiter feat(system): expose model concurrency stats on runtime queues dashboard 2026-07-11 07:17:28 +08:00
parity fix(models): serve qwen3-rerank on the native DashScope rerank protocol 2026-09-24 14:18:55 +08:00
providers fix(models): serve qwen3-rerank on the native DashScope rerank protocol 2026-09-24 14:18:55 +08:00
rerank fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
runtime fix(models): stop advertising graded thinking levels the wire format drops (#3552) 2026-09-25 22:23:08 +08:00
utils feat: integrate ChatBot provider and docreader 2026-04-13 17:47:24 +08:00
vlm refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
capabilities.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
legacy_keys.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
model.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
model_type.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00