First revision: DeepSeek, numeric questions, background assistant, UI fixes
All checks were successful
Verify and publish V2 container / build-and-push (push) Successful in 1m2s
All checks were successful
Verify and publish V2 container / build-and-push (push) Successful in 1m2s
Providers and pricing - Add a DeepSeek provider: thinking mode with low/high/max effort, reasoning_content replayed between tool steps, cache-hit usage, /models discovery and catalog prices. - Fix "does not support tool calling": a rejected forced tool_choice (DeepSeek thinking mode) now asks for the call in the prompt; only a genuine no-tools 400 is "unsupported". - Seven reasoning-effort levels (Off to Max) mapped per adapter. - Cached-input price per model, cache-write and DeepSeek off-peak aware cost estimates. - Built-in bge-small embedding model (transformers.js) as the semantic search default. Quizzes - Numeric (type-the-answer) questions: units ignored, optional ± tolerance; editor, runner, importer, templates and generation prompts. - Quiz start screen instead of showing answers; navigator ring no longer clipped and key legend removed; clock only for timed exams; 7-point letter grades. Assistant and generation - Assistant turns run on the server independently of the browser, with re-attach and an explicit stop; drafts tray shows generations in progress. - Per-chat model switcher, @-tagging of class materials, full-width assistant page and a smaller assistant button. - Editable generation instructions and built-in presets, separate from the chatbot import instructions. Other - Dialog footer padding, keyboard hints removed, copy buttons work over plain HTTP, class and folder shares include documents. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
parent
ccdad9728b
commit
f0aabe4d5d
63 changed files with 3892 additions and 488 deletions
|
|
@ -129,10 +129,28 @@ const GEMINI: Record<string, Entry> = {
|
|||
'gemini-2.5-flash-lite': { label: 'Gemini 2.5 Flash-Lite', priceIn: 0.1, priceOut: 0.4, capabilities: GEMINI_CAPS },
|
||||
};
|
||||
|
||||
/* ------------------------------------------------------------------ */
|
||||
/* DeepSeek */
|
||||
/* Prices and limits: https://api-docs.deepseek.com/quick_start/pricing (fetched 2026-11-15)
|
||||
/* Peak-hour list prices are stored. Off-peak hours (everything outside 01:00-04:00 and
|
||||
/* 06:00-10:00 UTC, Monday to Friday) cost half; `priceMultiplier` applies that per call.
|
||||
/* deepseek-v4-flash / deepseek-v4-flash-vision-exp are retired aliases served by
|
||||
/* deepseek-flash at the Flash price.
|
||||
/* ------------------------------------------------------------------ */
|
||||
|
||||
const DS_LIMITS = { contextWindow: 1_048_576, maxOutput: 393_216 };
|
||||
|
||||
const DEEPSEEK: Record<string, Entry> = {
|
||||
'deepseek-flash': { label: 'DeepSeek V4.1 Flash', ...DS_LIMITS, priceIn: 0.3, priceCachedIn: 0.006, priceOut: 1.2, capabilities: { tools: true, vision: true, pdf: false, reasoning: true, temperature: true } },
|
||||
'deepseek-v4-flash': { label: 'DeepSeek V4 Flash (alias of Flash)', ...DS_LIMITS, priceIn: 0.3, priceCachedIn: 0.006, priceOut: 1.2, capabilities: { tools: true, vision: true, pdf: false, reasoning: true, temperature: true } },
|
||||
'deepseek-v4-pro': { label: 'DeepSeek V4 Pro', ...DS_LIMITS, priceIn: 1.32, priceCachedIn: 0.044, priceOut: 3.96, capabilities: { tools: true, vision: false, pdf: false, reasoning: true, temperature: true } },
|
||||
};
|
||||
|
||||
const TABLES: Record<ProviderKind, Record<string, Entry>> = {
|
||||
openai: OPENAI,
|
||||
anthropic: ANTHROPIC,
|
||||
gemini: GEMINI,
|
||||
deepseek: DEEPSEEK,
|
||||
// Aggregators and local servers host arbitrary models at their own prices.
|
||||
openai_compatible: {},
|
||||
ollama: {},
|
||||
|
|
@ -168,6 +186,7 @@ function lookupIn(table: Record<string, Entry>, id: string): Partial<DiscoveredM
|
|||
// capabilities are a fair guess, the price is not.
|
||||
delete out.priceIn;
|
||||
delete out.priceOut;
|
||||
delete out.priceCachedIn;
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
|
@ -185,11 +204,12 @@ export function lookupModelDefaults(kind: ProviderKind, modelId: string): Partia
|
|||
// Routers name models "<vendor>/<model>" (`anthropic/claude-sonnet-5-5`).
|
||||
// Borrow capabilities and limits from the vendor's table, never its prices.
|
||||
const bare = id.slice(id.lastIndexOf('/') + 1).replace(/:[a-z]+$/, '');
|
||||
for (const table of [OPENAI, ANTHROPIC, GEMINI]) {
|
||||
for (const table of [OPENAI, ANTHROPIC, GEMINI, DEEPSEEK]) {
|
||||
const hit = lookupIn(table, bare);
|
||||
if (Object.keys(hit).length > 0) {
|
||||
delete hit.priceIn;
|
||||
delete hit.priceOut;
|
||||
delete hit.priceCachedIn;
|
||||
// Temperature limits are properties of the first-party APIs, not of the router.
|
||||
if (hit.capabilities) delete hit.capabilities.temperature;
|
||||
return hit;
|
||||
|
|
@ -204,3 +224,51 @@ export function lookupModelDefaults(kind: ProviderKind, modelId: string): Partia
|
|||
export function catalogModelIds(kind: ProviderKind): string[] {
|
||||
return Object.keys(TABLES[kind]);
|
||||
}
|
||||
|
||||
/**
|
||||
* What a cache-hit input token costs when a model has no cached price of its own, as a
|
||||
* fraction of the normal input price. These are the providers' published discounts for
|
||||
* their current models: OpenAI GPT-5 and later, Claude cache reads and Gemini 2.5 and later
|
||||
* all bill cached input at 10%. Older OpenAI models (GPT-4.1 25%, GPT-4o / o-series 50%)
|
||||
* discount less. Servers behind the compatible adapter and Ollama have no known discount.
|
||||
*/
|
||||
export function cachedInputRatio(kind: ProviderKind, modelId: string): number {
|
||||
const id = modelId.slice(modelId.lastIndexOf('/') + 1);
|
||||
switch (kind) {
|
||||
case 'openai':
|
||||
if (/^gpt-4\.1/.test(id)) return 0.25;
|
||||
if (/^(gpt-4o|o\d)/.test(id)) return 0.5;
|
||||
return 0.1;
|
||||
case 'anthropic':
|
||||
case 'gemini':
|
||||
return 0.1;
|
||||
case 'deepseek':
|
||||
return 0.02;
|
||||
default:
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
|
||||
/** USD per million cached input tokens: the model's own price when set, otherwise the provider discount. */
|
||||
export function cachedInputPrice(kind: ProviderKind, modelId: string, priceIn: number | null, priceCachedIn: number | null): number {
|
||||
if (priceCachedIn !== null && priceCachedIn !== undefined) return priceCachedIn;
|
||||
return (priceIn ?? 0) * cachedInputRatio(kind, modelId);
|
||||
}
|
||||
|
||||
/** Cache writes: Claude bills writing the (5-minute) prompt cache at 1.25x the input price. */
|
||||
export function cacheWriteRatio(kind: ProviderKind): number {
|
||||
return kind === 'anthropic' ? 1.25 : 1;
|
||||
}
|
||||
|
||||
/**
|
||||
* Time-of-day pricing. DeepSeek charges half its list price outside peak hours
|
||||
* (01:00-04:00 and 06:00-10:00 UTC, Monday to Friday).
|
||||
*/
|
||||
export function priceMultiplier(kind: ProviderKind, at: number = Date.now()): number {
|
||||
if (kind !== 'deepseek') return 1;
|
||||
const d = new Date(at);
|
||||
const day = d.getUTCDay();
|
||||
const hour = d.getUTCHours();
|
||||
const peak = day >= 1 && day <= 5 && ((hour >= 1 && hour < 4) || (hour >= 6 && hour < 10));
|
||||
return peak ? 1 : 0.5;
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue