mirror of
https://github.com/Nezumi-2711/9router.git
synced 2026-09-22 20:00:47 +00:00
decolua
b10b807063
## Features - **Thinking**: per-model thinking level picker on provider page — appends `(level)` suffix to copied model names for forced reasoning effort across all formats (openai, claude, gemini, deepseek, kimi, qwen, zai, minimax, hunyuan, step) - **RTK**: add JS-native git-log filter (#2423) - **Caveman**: add targeted upstream-aligned style rules (#2424) - **i18n**: add Farsi (fa) language support (#2385) ## Fixes - **Thinking**: strip `(level)` suffix from upstream `body.model` so providers no longer reject requests - **Translator**: preserve developer instructions in openai-responses conversion (#2434) - **count_tokens**: count structured Anthropic blocks (#2419) - **Volcengine-ark**: clamp GLM-5 max_tokens to model output ceiling (#2428) - **Kimi**: normalize reasoning_effort to backend enum (#2427) - **Claude**: reconcile max_tokens vs thinking budget and lift per-model ceiling (#2381) - **Kiro**: deliver system prompt natively, add Opus 4.5/4.7/4.8, tolerate dash version ids (#2366) - **Headroom**: proxy dashboard through app (#2372) - **MITM**: recover from stale lock file on server start
47 lines
2.2 KiB
JavaScript
47 lines
2.2 KiB
JavaScript
// Resolve valid thinking levels per model — drives UI level picker (suffix "model(level)").
|
|
// Reuses capabilities.js (thinkingFormat/canDisable) so this file only maps format→levels (DRY).
|
|
import { getCapabilitiesForModel } from "./capabilities.js";
|
|
import { matchPattern } from "./pricing.js";
|
|
|
|
// Shared level sets (deduped) — verified against provider docs + wire in thinkingUnified.applyFormat.
|
|
const L = {
|
|
base: ["none", "low", "medium", "high"], // qwen, step, hunyuan, gemini-budget
|
|
onOff: ["none", "thinking"], // zai (binary), minimax (adaptive)
|
|
openai: ["none", "minimal", "low", "medium", "high", "xhigh"], // GPT-5.x / o-series (no "max")
|
|
levelMax: ["none", "low", "medium", "high", "max"], // claude-adaptive, kimi
|
|
budgetX: ["none", "low", "medium", "high", "xhigh", "max"], // claude-budget
|
|
gemini: ["minimal", "low", "medium", "high"], // gemini-3 thinkingLevel (no disable)
|
|
hiMax: ["none", "high", "max"], // deepseek (low/med→high, xhigh→max)
|
|
};
|
|
|
|
// thinkingFormat → valid selectable levels (source of truth for UI options).
|
|
const FORMAT_LEVELS = {
|
|
openai: L.openai,
|
|
"claude-adaptive": L.levelMax,
|
|
"claude-budget": L.budgetX,
|
|
"gemini-level": L.gemini,
|
|
"gemini-budget": L.base,
|
|
zai: L.onOff,
|
|
qwen: L.base,
|
|
kimi: L.levelMax,
|
|
deepseek: L.hiMax,
|
|
minimax: L.onOff,
|
|
hunyuan: L.base,
|
|
step: L.base,
|
|
};
|
|
|
|
// Model-name pattern overrides (glob, first match wins) — more precise than format default.
|
|
const PATTERN_THINKING = [
|
|
{ pattern: "*codex*", levels: ["low", "medium", "high", "xhigh"] }, // codex cannot disable thinking
|
|
];
|
|
|
|
// Returns valid thinking levels for a model, or null when the model has no reasoning.
|
|
export function getThinkingLevels(provider, model) {
|
|
const caps = getCapabilitiesForModel(provider, model);
|
|
if (!caps.reasoning) return null;
|
|
const hit = PATTERN_THINKING.find((p) => matchPattern(p.pattern, model));
|
|
let levels = hit?.levels || FORMAT_LEVELS[caps.thinkingFormat] || L.base;
|
|
if (caps.thinkingCanDisable === false) levels = levels.filter((l) => l !== "none");
|
|
return levels;
|
|
}
|