Files
slate/app/lib/modules/llm/manager.ts
Stijnus b7ef2247b8 feat: add Cerebras and Fireworks AI LLM providers (#2113)
* 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>
2026-02-07 15:26:46 +01:00

213 lines
6.9 KiB
TypeScript

import type { IProviderSetting } from '~/types/model';
import { BaseProvider } from './base-provider';
import type { ModelInfo, ProviderInfo } from './types';
import * as providers from './registry';
import { createScopedLogger } from '~/utils/logger';
const logger = createScopedLogger('LLMManager');
export class LLMManager {
private static _instance: LLMManager;
private _providers: Map<string, BaseProvider> = new Map();
private _modelList: ModelInfo[] = [];
private _env: Record<string, string> = {};
private constructor(_env: Record<string, string>) {
this._registerProvidersFromDirectory();
this._env = _env;
}
static getInstance(env: Record<string, string> = {}): LLMManager {
if (!LLMManager._instance) {
LLMManager._instance = new LLMManager(env);
} else if (Object.keys(env).length > 0) {
// Update env on subsequent calls so Cloudflare Workers get fresh bindings
LLMManager._instance._env = env;
}
return LLMManager._instance;
}
get env() {
return this._env;
}
private async _registerProvidersFromDirectory() {
try {
/*
* Dynamically import all files from the providers directory
* const providerModules = import.meta.glob('./providers/*.ts', { eager: true });
*/
// Look for exported classes that extend BaseProvider
for (const exportedItem of Object.values(providers)) {
if (typeof exportedItem === 'function' && exportedItem.prototype instanceof BaseProvider) {
const provider = new exportedItem();
try {
this.registerProvider(provider);
} catch (error: any) {
logger.warn('Failed To Register Provider: ', provider.name, 'error:', error.message);
}
}
}
} catch (error) {
logger.error('Error registering providers:', error);
}
}
registerProvider(provider: BaseProvider) {
if (this._providers.has(provider.name)) {
logger.warn(`Provider ${provider.name} is already registered. Skipping.`);
return;
}
logger.info('Registering Provider: ', provider.name);
this._providers.set(provider.name, provider);
this._modelList = [...this._modelList, ...provider.staticModels];
}
getProvider(name: string): BaseProvider | undefined {
return this._providers.get(name);
}
getAllProviders(): BaseProvider[] {
return Array.from(this._providers.values());
}
getModelList(): ModelInfo[] {
return this._modelList;
}
async updateModelList(options: {
apiKeys?: Record<string, string>;
providerSettings?: Record<string, IProviderSetting>;
serverEnv?: Record<string, string>;
}): Promise<ModelInfo[]> {
const { apiKeys, providerSettings, serverEnv } = options;
let enabledProviders = Array.from(this._providers.values()).map((p) => p.name);
if (providerSettings && Object.keys(providerSettings).length > 0) {
enabledProviders = enabledProviders.filter((p) => providerSettings[p].enabled);
}
// Get dynamic models from all providers that support them
const dynamicModels = await Promise.all(
Array.from(this._providers.values())
.filter((provider) => enabledProviders.includes(provider.name))
.filter(
(provider): provider is BaseProvider & Required<Pick<ProviderInfo, 'getDynamicModels'>> =>
!!provider.getDynamicModels,
)
.map(async (provider) => {
const cachedModels = provider.getModelsFromCache(options);
if (cachedModels) {
return cachedModels;
}
const dynamicModels = await provider
.getDynamicModels(apiKeys, providerSettings?.[provider.name], serverEnv)
.then((models) => {
logger.info(`Caching ${models.length} dynamic models for ${provider.name}`);
provider.storeDynamicModels(options, models);
return models;
})
.catch((err) => {
logger.error(`Error getting dynamic models ${provider.name} :`, err);
return [];
});
return dynamicModels;
}),
);
const staticModels = Array.from(this._providers.values()).flatMap((p) => p.staticModels || []);
const dynamicModelsFlat = dynamicModels.flat();
const dynamicModelKeys = dynamicModelsFlat.map((d) => `${d.name}-${d.provider}`);
const filteredStaticModels = staticModels.filter((m) => !dynamicModelKeys.includes(`${m.name}-${m.provider}`));
// Combine static and dynamic models
const modelList = [...dynamicModelsFlat, ...filteredStaticModels];
modelList.sort((a, b) => a.name.localeCompare(b.name));
this._modelList = modelList;
return modelList;
}
getStaticModelList() {
return [...this._providers.values()].flatMap((p) => p.staticModels || []);
}
async getModelListFromProvider(
providerArg: BaseProvider,
options: {
apiKeys?: Record<string, string>;
providerSettings?: Record<string, IProviderSetting>;
serverEnv?: Record<string, string>;
},
): Promise<ModelInfo[]> {
const provider = this._providers.get(providerArg.name);
if (!provider) {
throw new Error(`Provider ${providerArg.name} not found`);
}
const staticModels = provider.staticModels || [];
if (!provider.getDynamicModels) {
return staticModels;
}
const { apiKeys, providerSettings, serverEnv } = options;
const cachedModels = provider.getModelsFromCache({
apiKeys,
providerSettings,
serverEnv,
});
if (cachedModels) {
logger.info(`Found ${cachedModels.length} cached models for ${provider.name}`);
return [...cachedModels, ...staticModels];
}
logger.info(`Getting dynamic models for ${provider.name}`);
const dynamicModels = await provider
.getDynamicModels?.(apiKeys, providerSettings?.[provider.name], serverEnv)
.then((models) => {
logger.info(`Got ${models.length} dynamic models for ${provider.name}`);
provider.storeDynamicModels(options, models);
return models;
})
.catch((err) => {
logger.error(`Error getting dynamic models ${provider.name} :`, err);
return [];
});
const dynamicModelsName = dynamicModels.map((d) => d.name);
const filteredStaticList = staticModels.filter((m) => !dynamicModelsName.includes(m.name));
const modelList = [...dynamicModels, ...filteredStaticList];
modelList.sort((a, b) => a.name.localeCompare(b.name));
return modelList;
}
getStaticModelListFromProvider(providerArg: BaseProvider) {
const provider = this._providers.get(providerArg.name);
if (!provider) {
throw new Error(`Provider ${providerArg.name} not found`);
}
return [...(provider.staticModels || [])];
}
getDefaultProvider(): BaseProvider {
const firstProvider = this._providers.values().next().value;
if (!firstProvider) {
throw new Error('No providers registered');
}
return firstProvider;
}
}