* fix: improve local model provider robustness and UX - Extract shared Docker URL rewriting and env conversion into BaseProvider to eliminate 4x duplicated code across Ollama and LMStudio - Add error handling and 5s timeouts to all model-listing fetches so one unreachable provider doesn't block the entire model list - Fix Ollama using createOllama() instead of mutating provider internals - Fix LLMManager singleton ignoring env updates on subsequent requests - Narrow cache key to only include provider-relevant env vars instead of the entire server environment - Fix 'as any' casts in LMStudio and OpenAILike by using shared convertEnvToRecord helper - Replace console.log/error with structured logger in OpenAILike - Fix typo: filteredStaticModesl -> filteredStaticModels in manager - Add connection status indicator (green/red dot) for local providers in the ModelSelector dropdown - Show helpful "is X running?" message when local provider has no models Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: add Cerebras LLM provider - Add Cerebras provider with 8 models (Llama, GPT OSS, Qwen, ZAI GLM) - Integrate @ai-sdk/cerebras@0.2.16 for compatibility - Add CEREBRAS_API_KEY to environment configuration - Register provider in LLMManager registry Models included: - llama3.1-8b, llama-3.3-70b - gpt-oss-120b (reasoning) - qwen-3-32b, qwen-3-235b variants - zai-glm-4.6, zai-glm-4.7 (reasoning) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com> * feat: add Fireworks AI LLM provider - Add Fireworks provider with 6 popular models - Integrate @ai-sdk/fireworks@0.2.16 for compatibility - Add FIREWORKS_API_KEY to environment configuration - Register provider in LLMManager registry Models included: - Llama 3.1 variants (405B, 70B, 8B Instruct) - DeepSeek R1 (reasoning model) - Qwen 2.5 72B Instruct - FireFunction V2 Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com> * feat: add coding-specific models to existing providers Enhanced providers with state-of-the-art coding models: **DeepSeek Provider:** + DeepSeek V3.2 (integrates thinking + tool-use) + DeepSeek V3.2-Speciale (high-compute variant, beats GPT-5) **Fireworks Provider:** + Qwen3-Coder 480B (262K context, best for coding) + Qwen3-Coder 30B (fast coding specialist) **Cerebras Provider:** + Qwen3-Coder 480B (2000 tokens/sec!) - Removed deprecated models (qwen-3-32b, llama-3.3-70b) Total new models: 4 Total coding models across all providers: 12+ Performance highlights: - Qwen3-Coder: State-of-the-art coding performance - DeepSeek V3.2: Integrates thinking directly into tool-use - ZAI GLM 4.6: 73.8% SWE-bench score - Ultra-fast inference: 2000 tok/s on Cerebras Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com> * feat: add dynamic model discovery to providers Implemented getDynamicModels() for automatic model discovery: **DeepSeek Provider:** - Fetches models from https://api.deepseek.com/models - Automatically discovers new models as DeepSeek adds them - Filters out static models to avoid duplicates **Cerebras Provider:** - Fetches models from https://api.cerebras.ai/v1/models - Auto-discovers new Cerebras models - Keeps UI up-to-date with latest offerings **Fireworks Provider:** - Fetches from https://api.fireworks.ai/v1/accounts/fireworks/models - Includes context_length from API response - Discovers new Qwen-Coder and other models automatically **Moonshot Provider:** - Fetches from https://api.moonshot.ai/v1/models - OpenAI-compatible endpoint - Auto-discovers new Kimi models Benefits: - ✅ No manual updates needed when providers add new models - ✅ Users always have access to latest models - ✅ Graceful fallback to static models if API fails - ✅ 5-second timeout prevents hanging - ✅ Caching system built into BaseProvider Technical details: - Uses BaseProvider's built-in caching system - Cache invalidates when API keys change - Failed API calls fallback to static models - All endpoints have 5-second timeout protection Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com> * feat: add Z.AI provider with GLM models and JWT authentication Merged changes from PR #2069 to add Z.AI provider: - Added GLM-4.6 (200K), GLM-4.5 (128K), and GLM-4.5 Flash models - Implemented secure JWT token generation with HMAC-SHA256 signing - Added dynamic model discovery from Z.AI API - Included proper error handling and token validation - GLM-4.6 achieves 73.8% on SWE-bench coding benchmarks Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
194 lines
5.5 KiB
TypeScript
194 lines
5.5 KiB
TypeScript
import { BaseProvider } from '~/lib/modules/llm/base-provider';
|
|
import type { IProviderSetting } from '~/types/model';
|
|
import type { LanguageModelV1 } from 'ai';
|
|
import type { ModelInfo } from '~/lib/modules/llm/types';
|
|
import { createOpenAI } from '@ai-sdk/openai';
|
|
import crypto from 'node:crypto';
|
|
|
|
export default class ZaiProvider extends BaseProvider {
|
|
name = 'Z.ai';
|
|
getApiKeyLink = 'https://open.bigmodel.cn/usercenter/apikeys';
|
|
|
|
config = {
|
|
baseUrlKey: 'ZAI_BASE_URL',
|
|
apiTokenKey: 'ZAI_API_KEY',
|
|
baseUrl: 'https://api.z.ai/api/coding/paas/v4', //Dedicated endpoint for Coding Plan
|
|
};
|
|
|
|
staticModels: ModelInfo[] = [
|
|
{
|
|
name: 'glm-4.6',
|
|
label: 'GLM-4.6 (200K)',
|
|
provider: 'Z.ai',
|
|
maxTokenAllowed: 200000,
|
|
maxCompletionTokens: 65536,
|
|
},
|
|
{
|
|
name: 'glm-4.5',
|
|
label: 'GLM-4.5 (128K)',
|
|
provider: 'Z.ai',
|
|
maxTokenAllowed: 128000,
|
|
maxCompletionTokens: 65536,
|
|
},
|
|
{
|
|
name: 'glm-4.5-flash',
|
|
label: 'GLM-4.5 Flash (128K)',
|
|
provider: 'Z.ai',
|
|
maxTokenAllowed: 128000,
|
|
maxCompletionTokens: 65536,
|
|
},
|
|
];
|
|
|
|
async getDynamicModels(
|
|
apiKeys?: Record<string, string>,
|
|
settings?: IProviderSetting,
|
|
serverEnv?: Record<string, string>,
|
|
): Promise<ModelInfo[]> {
|
|
const { baseUrl, apiKey } = this.getProviderBaseUrlAndKey({
|
|
apiKeys,
|
|
providerSettings: settings,
|
|
serverEnv: serverEnv as any,
|
|
defaultBaseUrlKey: 'ZAI_BASE_URL',
|
|
defaultApiTokenKey: 'ZAI_API_KEY',
|
|
});
|
|
|
|
if (!apiKey) {
|
|
throw new Error(`Missing Api Key configuration for ${this.name} provider`);
|
|
}
|
|
|
|
const token = this._generateToken(apiKey);
|
|
|
|
if (!this._isValidToken(token)) {
|
|
throw new Error(`Invalid API key format for ${this.name} provider`);
|
|
}
|
|
|
|
try {
|
|
const response = await fetch(`${baseUrl}/models`, {
|
|
headers: {
|
|
Authorization: `Bearer ${token}`,
|
|
'Content-Type': 'application/json',
|
|
},
|
|
});
|
|
|
|
if (!response.ok) {
|
|
throw new Error(`Failed to fetch models: ${response.status} ${response.statusText}`);
|
|
}
|
|
|
|
const res = (await response.json()) as any;
|
|
const staticModelIds = this.staticModels.map((m) => m.name);
|
|
|
|
// Filter out static models and only include GLM models
|
|
const data =
|
|
res.data?.filter(
|
|
(model: any) =>
|
|
model.object === 'model' && model.id?.startsWith('glm-') && !staticModelIds.includes(model.id),
|
|
) || [];
|
|
|
|
return data.map((m: any) => {
|
|
let contextWindow = 128000;
|
|
let maxCompletionTokens = 65536;
|
|
|
|
if (m.id?.includes('glm-4.6')) {
|
|
contextWindow = 200000;
|
|
maxCompletionTokens = 65536;
|
|
} else if (m.id?.includes('glm-4.5')) {
|
|
contextWindow = 128000;
|
|
maxCompletionTokens = 65536;
|
|
} else if (m.id?.includes('glm-4')) {
|
|
contextWindow = 128000;
|
|
maxCompletionTokens = 8192;
|
|
} else if (m.id?.includes('glm-3')) {
|
|
contextWindow = 32000;
|
|
maxCompletionTokens = 4096;
|
|
}
|
|
|
|
return {
|
|
name: m.id,
|
|
label: `${m.id} (${Math.floor(contextWindow / 1000)}k context)`,
|
|
provider: this.name,
|
|
maxTokenAllowed: contextWindow,
|
|
maxCompletionTokens,
|
|
};
|
|
});
|
|
} catch (error) {
|
|
console.error(`Failed to fetch dynamic models for ${this.name}:`, error);
|
|
return [];
|
|
}
|
|
}
|
|
|
|
private _generateToken(apiKey: string): string {
|
|
try {
|
|
const [id, secret] = apiKey.split('.');
|
|
|
|
if (!id || !secret) {
|
|
throw new Error(`Invalid API key format for ${this.name}. Expected: id.secret`);
|
|
}
|
|
|
|
const now = Date.now();
|
|
const payload = {
|
|
apiKey: id,
|
|
exp: now + 3600 * 1000,
|
|
timestamp: now,
|
|
};
|
|
|
|
const header = { alg: 'HS256', sign_type: 'SIGN' };
|
|
|
|
const base64Url = (obj: any) =>
|
|
Buffer.from(JSON.stringify(obj)).toString('base64').replace(/=/g, '').replace(/\+/g, '-').replace(/\//g, '_');
|
|
const signature = crypto
|
|
.createHmac('sha256', secret)
|
|
.update(base64Url(header) + '.' + base64Url(payload))
|
|
.digest('base64')
|
|
.replace(/=/g, '')
|
|
.replace(/\+/g, '-')
|
|
.replace(/\//g, '_');
|
|
|
|
return `${base64Url(header)}.${base64Url(payload)}.${signature}`;
|
|
} catch (error) {
|
|
console.error(`Failed to generate JWT token for ${this.name}:`, error);
|
|
throw new Error(`Failed to generate JWT token: ${error instanceof Error ? error.message : 'Unknown error'}`);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Validates JWT token format
|
|
*/
|
|
private _isValidToken(token: string): boolean {
|
|
try {
|
|
const parts = token.split('.');
|
|
return parts.length === 3 && parts.every((part) => part.length > 0);
|
|
} catch {
|
|
return false;
|
|
}
|
|
}
|
|
|
|
getModelInstance(options: {
|
|
model: string;
|
|
serverEnv: Env;
|
|
apiKeys?: Record<string, string>;
|
|
providerSettings?: Record<string, IProviderSetting>;
|
|
}): LanguageModelV1 {
|
|
const { model, serverEnv, apiKeys, providerSettings } = options;
|
|
|
|
const { baseUrl, apiKey } = this.getProviderBaseUrlAndKey({
|
|
apiKeys,
|
|
providerSettings: providerSettings?.[this.name],
|
|
serverEnv: serverEnv as any,
|
|
defaultBaseUrlKey: 'ZAI_BASE_URL',
|
|
defaultApiTokenKey: 'ZAI_API_KEY',
|
|
});
|
|
|
|
if (!apiKey) {
|
|
throw new Error(`Missing API key for ${this.name} provider`);
|
|
}
|
|
|
|
const token = this._generateToken(apiKey);
|
|
const zaiClient = createOpenAI({
|
|
baseURL: baseUrl,
|
|
apiKey: token,
|
|
});
|
|
|
|
return zaiClient(model);
|
|
}
|
|
}
|