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
|
|
@ -38,7 +38,7 @@ import {
|
|||
type TestResult,
|
||||
} from '../types.ts';
|
||||
import { lookupModelDefaults } from './catalog.ts';
|
||||
import { isChatModelId, makeUsage, num, parseArgsStrict, parseToolArguments, runTest, str, TEST_TIMEOUT_MS, withCatalogDefaults } from './common.ts';
|
||||
import { isChatModelId, makeUsage, nearestEffort, num, parseArgsStrict, parseToolArguments, runTest, str, TEST_TIMEOUT_MS, withCatalogDefaults } from './common.ts';
|
||||
import { ensureOk, errorFromProvider, httpRequest, isRecord, requestJson, sseJson, trimBaseUrl, type ErrorContext } from './http.ts';
|
||||
|
||||
type Json = Record<string, unknown>;
|
||||
|
|
@ -120,7 +120,10 @@ export function claudeProfile(model: string): ClaudeProfile {
|
|||
}
|
||||
|
||||
/** Thinking budgets for the legacy `budget_tokens` models. */
|
||||
const LEGACY_BUDGET = { low: 2_048, medium: 8_192, high: 16_384 } as const;
|
||||
const LEGACY_BUDGET = { minimal: 1_024, low: 2_048, medium: 8_192, high: 16_384, xhigh: 24_576, max: 32_000 } as const;
|
||||
|
||||
/** `output_config.effort` levels. "xhigh" exists on the newest models only; a rejection steps it down. */
|
||||
const CLAUDE_EFFORTS = ['low', 'medium', 'high', 'xhigh', 'max'] as const;
|
||||
|
||||
/* ------------------------------------------------------------------ */
|
||||
/* Request building */
|
||||
|
|
@ -133,6 +136,8 @@ interface BuildOptions {
|
|||
useFallbacks: boolean;
|
||||
eagerToolInput: boolean;
|
||||
promptCache: boolean;
|
||||
/** Highest effort level the model accepted, after a rejection. */
|
||||
effortCap?: (typeof CLAUDE_EFFORTS)[number];
|
||||
}
|
||||
|
||||
/** Tool-call ids must match ^[a-zA-Z0-9_-]+$; ids minted by other providers may not. */
|
||||
|
|
@ -268,7 +273,7 @@ function buildBody(req: ChatRequest, profile: ClaudeProfile, opts: BuildOptions)
|
|||
// `display: "summarized"` because these models hide the reasoning text by
|
||||
// default, which would look like a long pause in the UI.
|
||||
body.thinking = adaptive;
|
||||
if (effort) outputConfig.effort = effort;
|
||||
if (effort) outputConfig.effort = opts.effortCap ? nearestEffort(effort, CLAUDE_EFFORTS.filter((e) => CLAUDE_EFFORTS.indexOf(e) <= CLAUDE_EFFORTS.indexOf(opts.effortCap!))) : nearestEffort(effort, CLAUDE_EFFORTS);
|
||||
} else if (effort) {
|
||||
// Forced tool use cannot be combined with thinking on the older generations.
|
||||
if (profile.thinking === 'opt_in' && !forcing) body.thinking = adaptive;
|
||||
|
|
@ -276,7 +281,7 @@ function buildBody(req: ChatRequest, profile: ClaudeProfile, opts: BuildOptions)
|
|||
const budget = Math.min(LEGACY_BUDGET[effort], maxTokens - 1_024); // must be < max_tokens, min 1024
|
||||
if (budget >= 1_024) body.thinking = { type: 'enabled', budget_tokens: budget };
|
||||
}
|
||||
if (profile.effort) outputConfig.effort = effort;
|
||||
if (profile.effort) outputConfig.effort = opts.effortCap ? nearestEffort(effort, CLAUDE_EFFORTS.filter((e) => CLAUDE_EFFORTS.indexOf(e) <= CLAUDE_EFFORTS.indexOf(opts.effortCap!))) : nearestEffort(effort, CLAUDE_EFFORTS);
|
||||
}
|
||||
if (Object.keys(outputConfig).length > 0) body.output_config = outputConfig;
|
||||
}
|
||||
|
|
@ -375,6 +380,7 @@ async function* stream(cfg: ProviderConfig, req: ChatRequest): AsyncGenerator<St
|
|||
else if (opts.useFallbacks && /fallback|anthropic-beta/i.test(detail)) opts.useFallbacks = false;
|
||||
else if (opts.eagerToolInput && /eager_input_streaming/i.test(detail)) opts.eagerToolInput = false;
|
||||
else if (opts.promptCache && /cache_control/i.test(detail)) opts.promptCache = false;
|
||||
else if (/effort/i.test(detail) && opts.effortCap !== 'medium' && req.reasoningEffort && req.reasoningEffort !== 'none') opts.effortCap = opts.effortCap === 'high' ? 'medium' : opts.effortCap === 'xhigh' ? 'high' : 'xhigh';
|
||||
else throw err;
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue