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
|
|
@ -10,11 +10,12 @@ import type { DB } from '../db.ts';
|
|||
import { HttpError, notFound, type AppContext } from '../http.ts';
|
||||
import { getSetting, setSetting } from '../settings.ts';
|
||||
import { newId, now, parseJson } from '../util.ts';
|
||||
import { getAdapter, lookupModelDefaults } from './providers/index.ts';
|
||||
import { cachedInputPrice, cacheWriteRatio, getAdapter, lookupModelDefaults, priceMultiplier } from './providers/index.ts';
|
||||
import {
|
||||
AIError,
|
||||
DEFAULT_CAPABILITIES,
|
||||
PROVIDER_KINDS,
|
||||
REASONING_EFFORTS,
|
||||
type ChatMessage,
|
||||
type ChatRequest,
|
||||
type DiscoveredModel,
|
||||
|
|
@ -57,6 +58,7 @@ interface ModelRow {
|
|||
max_output: number | null;
|
||||
price_in: number | null;
|
||||
price_out: number | null;
|
||||
price_cached_in: number | null;
|
||||
}
|
||||
|
||||
export const TASKS = ['chat', 'generate', 'vision', 'quick'] as const;
|
||||
|
|
@ -82,7 +84,7 @@ const EMPTY_TASK: TaskConfig = { modelId: null, temperature: null, reasoningEffo
|
|||
export const taskConfigSchema = z.object({
|
||||
modelId: z.string().nullable(),
|
||||
temperature: z.number().min(0).max(2).nullable(),
|
||||
reasoningEffort: z.enum(['none', 'low', 'medium', 'high']).nullable(),
|
||||
reasoningEffort: z.enum(REASONING_EFFORTS).nullable(),
|
||||
maxOutputTokens: z.number().int().min(256).max(200000).nullable(),
|
||||
});
|
||||
|
||||
|
|
@ -122,6 +124,8 @@ function mapModel(row: ModelRow & { provider_name?: string; provider_kind?: stri
|
|||
maxOutput: row.max_output,
|
||||
priceIn: row.price_in,
|
||||
priceOut: row.price_out,
|
||||
/** Null = not set; costs then use the provider's usual cache discount. */
|
||||
priceCachedIn: row.price_cached_in,
|
||||
};
|
||||
}
|
||||
export type ModelDto = ReturnType<typeof mapModel>;
|
||||
|
|
@ -249,11 +253,12 @@ export async function discoverModels(app: AppContext, id: string): Promise<{ add
|
|||
if (current) {
|
||||
// Refresh facts the provider reports, but never overwrite prices or flags the user may have edited.
|
||||
app.db.run(
|
||||
'UPDATE ai_models SET context_window = COALESCE(?, context_window), max_output = COALESCE(?, max_output), price_in = COALESCE(price_in, ?), price_out = COALESCE(price_out, ?), updated_at = ? WHERE id = ?',
|
||||
'UPDATE ai_models SET context_window = COALESCE(?, context_window), max_output = COALESCE(?, max_output), price_in = COALESCE(price_in, ?), price_out = COALESCE(price_out, ?), price_cached_in = COALESCE(price_cached_in, ?), updated_at = ? WHERE id = ?',
|
||||
m.contextWindow ?? null,
|
||||
m.maxOutput ?? null,
|
||||
m.priceIn ?? null,
|
||||
m.priceOut ?? null,
|
||||
m.priceCachedIn ?? null,
|
||||
at,
|
||||
current.id,
|
||||
);
|
||||
|
|
@ -270,8 +275,8 @@ function insertModel(db: DB, providerId: string, m: DiscoveredModel, source: str
|
|||
const id = newId();
|
||||
const at = now();
|
||||
db.run(
|
||||
`INSERT INTO ai_models (id, provider_id, model, label, source, enabled, capabilities, context_window, max_output, price_in, price_out, created_at, updated_at)
|
||||
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)`,
|
||||
`INSERT INTO ai_models (id, provider_id, model, label, source, enabled, capabilities, context_window, max_output, price_in, price_out, price_cached_in, created_at, updated_at)
|
||||
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)`,
|
||||
id,
|
||||
providerId,
|
||||
m.id,
|
||||
|
|
@ -283,6 +288,7 @@ function insertModel(db: DB, providerId: string, m: DiscoveredModel, source: str
|
|||
m.maxOutput ?? null,
|
||||
m.priceIn ?? null,
|
||||
m.priceOut ?? null,
|
||||
m.priceCachedIn ?? null,
|
||||
at,
|
||||
at,
|
||||
);
|
||||
|
|
@ -331,6 +337,7 @@ export const modelPatchSchema = z.object({
|
|||
maxOutput: z.number().int().min(16).max(10_000_000).nullable().optional(),
|
||||
priceIn: z.number().min(0).max(100000).nullable().optional(),
|
||||
priceOut: z.number().min(0).max(100000).nullable().optional(),
|
||||
priceCachedIn: z.number().min(0).max(100000).nullable().optional(),
|
||||
});
|
||||
|
||||
export function patchModel(db: DB, id: string, input: z.input<typeof modelPatchSchema>): ModelDto {
|
||||
|
|
@ -339,7 +346,7 @@ export function patchModel(db: DB, id: string, input: z.input<typeof modelPatchS
|
|||
if (!row) throw notFound('Model');
|
||||
const caps = { ...parseJson<Partial<ModelCapabilities>>(row.capabilities, {}), ...patch.capabilities };
|
||||
db.run(
|
||||
'UPDATE ai_models SET enabled = ?, label = ?, capabilities = ?, context_window = ?, max_output = ?, price_in = ?, price_out = ?, updated_at = ? WHERE id = ?',
|
||||
'UPDATE ai_models SET enabled = ?, label = ?, capabilities = ?, context_window = ?, max_output = ?, price_in = ?, price_out = ?, price_cached_in = ?, updated_at = ? WHERE id = ?',
|
||||
patch.enabled === undefined ? row.enabled : patch.enabled ? 1 : 0,
|
||||
patch.label ?? row.label,
|
||||
JSON.stringify(caps),
|
||||
|
|
@ -347,6 +354,7 @@ export function patchModel(db: DB, id: string, input: z.input<typeof modelPatchS
|
|||
patch.maxOutput === undefined ? row.max_output : patch.maxOutput,
|
||||
patch.priceIn === undefined ? row.price_in : patch.priceIn,
|
||||
patch.priceOut === undefined ? row.price_out : patch.priceOut,
|
||||
patch.priceCachedIn === undefined ? row.price_cached_in : patch.priceCachedIn,
|
||||
now(),
|
||||
id,
|
||||
);
|
||||
|
|
@ -423,19 +431,33 @@ export function resolveModel(app: AppContext, task: TaskName, overrideModelId?:
|
|||
|
||||
/* ------------------------------ usage ------------------------------ */
|
||||
|
||||
export function estimateCost(model: Pick<ModelDto, 'priceIn' | 'priceOut'>, usage: Usage): number | null {
|
||||
/**
|
||||
* Estimated USD cost of one call. Input tokens are split into fresh, cache-hit and
|
||||
* cache-write tokens, each at its own rate: the model's cached price when set, otherwise
|
||||
* the provider's published cache discount; Claude's cache writes cost 1.25x. Providers
|
||||
* with time-of-day pricing (DeepSeek off-peak) are adjusted for when the call was made.
|
||||
*/
|
||||
export function estimateCost(
|
||||
model: Pick<ModelDto, 'priceIn' | 'priceOut' | 'model'> & { priceCachedIn?: number | null; providerKind?: ProviderKind | '' },
|
||||
usage: Usage,
|
||||
at: number = Date.now(),
|
||||
): number | null {
|
||||
if (model.priceIn === null && model.priceOut === null) return null;
|
||||
// Cached input is billed at a fraction of the list price by every provider; 10% is a close, conservative stand-in.
|
||||
const cached = usage.cacheReadTokens ?? 0;
|
||||
const fresh = Math.max(0, usage.inputTokens - cached);
|
||||
return ((fresh + cached * 0.1) * (model.priceIn ?? 0) + usage.outputTokens * (model.priceOut ?? 0)) / 1_000_000;
|
||||
const kind = (model.providerKind || 'openai_compatible') as ProviderKind;
|
||||
const priceIn = model.priceIn ?? 0;
|
||||
const cachedRate = cachedInputPrice(kind, model.model, model.priceIn, model.priceCachedIn ?? null);
|
||||
const cached = Math.min(usage.inputTokens, usage.cacheReadTokens ?? 0);
|
||||
const written = Math.min(usage.inputTokens - cached, usage.cacheWriteTokens ?? 0);
|
||||
const fresh = Math.max(0, usage.inputTokens - cached - written);
|
||||
const input = fresh * priceIn + cached * cachedRate + written * priceIn * cacheWriteRatio(kind);
|
||||
return ((input + usage.outputTokens * (model.priceOut ?? 0)) * priceMultiplier(kind, at)) / 1_000_000;
|
||||
}
|
||||
|
||||
function recordUsage(app: AppContext, r: ResolvedModel, task: string, usage: Usage | null, started: number, error?: string): void {
|
||||
try {
|
||||
app.db.run(
|
||||
`INSERT INTO ai_usage (at, provider_id, provider_name, model, task, input_tokens, output_tokens, cache_read_tokens, cost, ok, error, duration_ms)
|
||||
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)`,
|
||||
`INSERT INTO ai_usage (at, provider_id, provider_name, model, task, input_tokens, output_tokens, cache_read_tokens, cache_write_tokens, cost, ok, error, duration_ms)
|
||||
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)`,
|
||||
now(),
|
||||
r.provider.id,
|
||||
r.provider.name,
|
||||
|
|
@ -444,6 +466,7 @@ function recordUsage(app: AppContext, r: ResolvedModel, task: string, usage: Usa
|
|||
usage?.inputTokens ?? 0,
|
||||
usage?.outputTokens ?? 0,
|
||||
usage?.cacheReadTokens ?? 0,
|
||||
usage?.cacheWriteTokens ?? 0,
|
||||
usage ? estimateCost(r.model, usage) : null,
|
||||
error ? 0 : 1,
|
||||
(error ?? '').slice(0, 300),
|
||||
|
|
@ -597,7 +620,7 @@ export async function generateStructured(app: AppContext, opts: StructuredOption
|
|||
export function usageSummary(db: DB, days: number) {
|
||||
const since = now() - days * 86_400_000;
|
||||
const byModel = db.all<Record<string, any>>(
|
||||
`SELECT provider_name AS provider, model, COUNT(*) AS calls, SUM(input_tokens) AS input, SUM(output_tokens) AS output, SUM(cost) AS cost,
|
||||
`SELECT provider_name AS provider, model, COUNT(*) AS calls, SUM(input_tokens) AS input, SUM(cache_read_tokens) AS cached, SUM(output_tokens) AS output, SUM(cost) AS cost,
|
||||
SUM(CASE WHEN ok = 0 THEN 1 ELSE 0 END) AS errors, SUM(CASE WHEN cost IS NULL AND ok = 1 THEN 1 ELSE 0 END) AS unpriced
|
||||
FROM ai_usage WHERE at >= ? GROUP BY provider_name, model ORDER BY cost DESC, calls DESC`,
|
||||
since,
|
||||
|
|
@ -607,7 +630,7 @@ export function usageSummary(db: DB, days: number) {
|
|||
since,
|
||||
);
|
||||
const total = db.get<Record<string, any>>(
|
||||
`SELECT COUNT(*) AS calls, COALESCE(SUM(input_tokens), 0) AS input, COALESCE(SUM(output_tokens), 0) AS output, COALESCE(SUM(cost), 0) AS cost FROM ai_usage WHERE at >= ?`,
|
||||
`SELECT COUNT(*) AS calls, COALESCE(SUM(input_tokens), 0) AS input, COALESCE(SUM(cache_read_tokens), 0) AS cached, COALESCE(SUM(output_tokens), 0) AS output, COALESCE(SUM(cost), 0) AS cost FROM ai_usage WHERE at >= ?`,
|
||||
since,
|
||||
)!;
|
||||
const recentErrors = db.all<Record<string, any>>(`SELECT at, provider_name AS provider, model, task, error FROM ai_usage WHERE ok = 0 AND at >= ? ORDER BY at DESC LIMIT 10`, since);
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue