* 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>
148 lines
4.2 KiB
TypeScript
148 lines
4.2 KiB
TypeScript
import { BaseProvider } from '~/lib/modules/llm/base-provider';
|
|
import type { ModelInfo } from '~/lib/modules/llm/types';
|
|
import type { IProviderSetting } from '~/types/model';
|
|
import type { LanguageModelV1 } from 'ai';
|
|
import { createFireworks } from '@ai-sdk/fireworks';
|
|
|
|
export default class FireworksProvider extends BaseProvider {
|
|
name = 'Fireworks';
|
|
getApiKeyLink = 'https://fireworks.ai/api-keys';
|
|
|
|
config = {
|
|
apiTokenKey: 'FIREWORKS_API_KEY',
|
|
};
|
|
|
|
staticModels: ModelInfo[] = [
|
|
{
|
|
name: 'accounts/fireworks/models/qwen3-coder-480b-a35b-instruct',
|
|
label: 'Qwen3-Coder 480B (Best for Coding)',
|
|
provider: 'Fireworks',
|
|
maxTokenAllowed: 262000,
|
|
},
|
|
{
|
|
name: 'accounts/fireworks/models/qwen3-coder-30b-a3b-instruct',
|
|
label: 'Qwen3-Coder 30B (Fast Coding)',
|
|
provider: 'Fireworks',
|
|
maxTokenAllowed: 262000,
|
|
},
|
|
{
|
|
name: 'accounts/fireworks/models/llama-v3p1-405b-instruct',
|
|
label: 'Llama 3.1 405B Instruct',
|
|
provider: 'Fireworks',
|
|
maxTokenAllowed: 128000,
|
|
},
|
|
{
|
|
name: 'accounts/fireworks/models/llama-v3p1-70b-instruct',
|
|
label: 'Llama 3.1 70B Instruct',
|
|
provider: 'Fireworks',
|
|
maxTokenAllowed: 128000,
|
|
},
|
|
{
|
|
name: 'accounts/fireworks/models/llama-v3p1-8b-instruct',
|
|
label: 'Llama 3.1 8B Instruct',
|
|
provider: 'Fireworks',
|
|
maxTokenAllowed: 128000,
|
|
},
|
|
{
|
|
name: 'accounts/fireworks/models/deepseek-r1',
|
|
label: 'DeepSeek R1 (Reasoning)',
|
|
provider: 'Fireworks',
|
|
maxTokenAllowed: 64000,
|
|
},
|
|
{
|
|
name: 'accounts/fireworks/models/qwen2p5-72b-instruct',
|
|
label: 'Qwen 2.5 72B Instruct',
|
|
provider: 'Fireworks',
|
|
maxTokenAllowed: 128000,
|
|
},
|
|
{
|
|
name: 'accounts/fireworks/models/firefunction-v2',
|
|
label: 'FireFunction V2',
|
|
provider: 'Fireworks',
|
|
maxTokenAllowed: 8000,
|
|
},
|
|
];
|
|
|
|
async getDynamicModels(
|
|
apiKeys?: Record<string, string>,
|
|
settings?: IProviderSetting,
|
|
serverEnv?: Record<string, string>,
|
|
): Promise<ModelInfo[]> {
|
|
const { apiKey } = this.getProviderBaseUrlAndKey({
|
|
apiKeys,
|
|
providerSettings: settings,
|
|
serverEnv: serverEnv as any,
|
|
defaultBaseUrlKey: '',
|
|
defaultApiTokenKey: 'FIREWORKS_API_KEY',
|
|
});
|
|
|
|
if (!apiKey) {
|
|
return [];
|
|
}
|
|
|
|
try {
|
|
// Try the accounts/fireworks/models endpoint which lists public models
|
|
const response = await fetch('https://api.fireworks.ai/v1/accounts/fireworks/models?page_size=100', {
|
|
headers: {
|
|
Authorization: `Bearer ${apiKey}`,
|
|
},
|
|
signal: this.createTimeoutSignal(5000),
|
|
});
|
|
|
|
if (!response.ok) {
|
|
console.error(`Fireworks API error: ${response.statusText}`);
|
|
return [];
|
|
}
|
|
|
|
const data = (await response.json()) as any;
|
|
const staticModelIds = this.staticModels.map((m) => m.name);
|
|
|
|
// Filter out models we already have in staticModels
|
|
const dynamicModels =
|
|
data.data
|
|
?.filter((model: any) => {
|
|
const modelPath = `accounts/fireworks/models/${model.id}`;
|
|
return !staticModelIds.includes(modelPath) && !staticModelIds.includes(model.id);
|
|
})
|
|
.map((m: any) => ({
|
|
name: `accounts/fireworks/models/${m.id}`,
|
|
label: `${m.id} (Dynamic)`,
|
|
provider: this.name,
|
|
maxTokenAllowed: m.context_length || 128000,
|
|
})) || [];
|
|
|
|
return dynamicModels;
|
|
} catch (error) {
|
|
console.error(`Failed to fetch Fireworks models:`, error);
|
|
return [];
|
|
}
|
|
}
|
|
|
|
getModelInstance(options: {
|
|
model: string;
|
|
serverEnv: Env;
|
|
apiKeys?: Record<string, string>;
|
|
providerSettings?: Record<string, IProviderSetting>;
|
|
}): LanguageModelV1 {
|
|
const { model, serverEnv, apiKeys, providerSettings } = options;
|
|
|
|
const { apiKey } = this.getProviderBaseUrlAndKey({
|
|
apiKeys,
|
|
providerSettings: providerSettings?.[this.name],
|
|
serverEnv: serverEnv as any,
|
|
defaultBaseUrlKey: '',
|
|
defaultApiTokenKey: 'FIREWORKS_API_KEY',
|
|
});
|
|
|
|
if (!apiKey) {
|
|
throw new Error(`Missing API key for ${this.name} provider`);
|
|
}
|
|
|
|
const fireworks = createFireworks({
|
|
apiKey,
|
|
});
|
|
|
|
return fireworks(model);
|
|
}
|
|
}
|