noosphere 0.1.3 → 0.2.1

package/dist/index.cjs

@@ -280,6 +280,105 @@ var UsageTracker = class {
 var import_pi_ai = require("@mariozechner/pi-ai");
 var KNOWN_PROVIDERS = ["anthropic", "google", "openai", "xai", "groq", "cerebras", "openrouter", "zai"];
 var LOCAL_PROVIDERS = /* @__PURE__ */ new Set(["ollama"]);
+var FETCH_TIMEOUT_MS = 8e3;
+var OPENAI_CHAT_PREFIXES = ["gpt-", "o1", "o3", "o4", "chatgpt-", "codex-"];
+var OPENAI_REASONING_PREFIXES = ["o1", "o3", "o4"];
+var GOOGLE_GENERATIVE_PREFIXES = ["gemini-", "gemma-"];
+var ANTHROPIC_CHAT_PREFIXES = ["claude-"];
+var PROVIDER_APIS = {
+  openai: () => ({
+    url: "https://api.openai.com/v1/models",
+    headers: (key) => ({ Authorization: `Bearer ${key}` }),
+    piApiType: "openai-responses",
+    piBaseUrl: "https://api.openai.com/v1",
+    providerName: "openai",
+    filterChat: (id) => OPENAI_CHAT_PREFIXES.some((p) => id.startsWith(p)),
+    isReasoning: (id) => OPENAI_REASONING_PREFIXES.some((p) => id.startsWith(p)),
+    extractEntries: (data) => (data?.data ?? []).map((e) => ({ id: e.id, name: e.id }))
+  }),
+  anthropic: () => ({
+    url: "https://api.anthropic.com/v1/models?limit=100",
+    headers: (key) => ({ "x-api-key": key, "anthropic-version": "2023-06-01" }),
+    piApiType: "anthropic-messages",
+    piBaseUrl: "https://api.anthropic.com/v1",
+    providerName: "anthropic",
+    filterChat: (id) => ANTHROPIC_CHAT_PREFIXES.some((p) => id.startsWith(p)),
+    isReasoning: (id) => id.includes("opus") || id.includes("sonnet"),
+    extractEntries: (data) => (data?.data ?? []).map((e) => ({ id: e.id, name: e.display_name ?? e.id }))
+  }),
+  google: (key) => ({
+    url: `https://generativelanguage.googleapis.com/v1beta/models?key=${key}`,
+    headers: () => ({}),
+    piApiType: "google-generative-ai",
+    piBaseUrl: "https://generativelanguage.googleapis.com/v1beta",
+    providerName: "google",
+    filterChat: (id) => GOOGLE_GENERATIVE_PREFIXES.some((p) => id.startsWith(p)),
+    isReasoning: (id) => id.includes("thinking") || id.includes("2.5"),
+    extractEntries: (data) => (data?.models ?? []).filter((e) => !e.supportedGenerationMethods || e.supportedGenerationMethods.includes("generateContent")).map((e) => ({
+      id: e.name.replace(/^models\//, ""),
+      name: e.displayName ?? e.name.replace(/^models\//, ""),
+      contextWindow: e.inputTokenLimit,
+      maxTokens: e.outputTokenLimit
+    }))
+  }),
+  groq: () => ({
+    url: "https://api.groq.com/openai/v1/models",
+    headers: (key) => ({ Authorization: `Bearer ${key}` }),
+    piApiType: "openai-completions",
+    piBaseUrl: "https://api.groq.com/openai/v1",
+    providerName: "groq",
+    filterChat: () => true,
+    // Groq only serves chat models
+    isReasoning: (id) => id.includes("deepseek-r1"),
+    extractEntries: (data) => (data?.data ?? []).map((e) => ({ id: e.id, name: e.id }))
+  }),
+  mistral: () => ({
+    url: "https://api.mistral.ai/v1/models",
+    headers: (key) => ({ Authorization: `Bearer ${key}` }),
+    piApiType: "openai-completions",
+    piBaseUrl: "https://api.mistral.ai/v1",
+    providerName: "mistral",
+    filterChat: (id) => !id.includes("embed"),
+    isReasoning: (id) => id.includes("large") || id.includes("codestral"),
+    extractEntries: (data) => (data?.data ?? []).map((e) => ({ id: e.id, name: e.id }))
+  }),
+  xai: () => ({
+    url: "https://api.x.ai/v1/models",
+    headers: (key) => ({ Authorization: `Bearer ${key}` }),
+    piApiType: "openai-completions",
+    piBaseUrl: "https://api.x.ai/v1",
+    providerName: "xai",
+    filterChat: (id) => id.startsWith("grok"),
+    isReasoning: (id) => id.includes("think"),
+    extractEntries: (data) => (data?.data ?? []).map((e) => ({ id: e.id, name: e.id }))
+  }),
+  openrouter: () => ({
+    url: "https://openrouter.ai/api/v1/models",
+    headers: (key) => ({ Authorization: `Bearer ${key}` }),
+    piApiType: "openai-completions",
+    piBaseUrl: "https://openrouter.ai/api/v1",
+    providerName: "openrouter",
+    filterChat: () => true,
+    // OpenRouter only lists usable models
+    isReasoning: (id) => id.includes("o1") || id.includes("o3") || id.includes("thinking") || id.includes("deepseek-r1"),
+    extractEntries: (data) => (data?.data ?? []).map((e) => ({
+      id: e.id,
+      name: e.name ?? e.id,
+      contextWindow: e.context_length,
+      maxTokens: e.max_completion_tokens ?? e.top_provider?.max_completion_tokens
+    }))
+  }),
+  cerebras: () => ({
+    url: "https://api.cerebras.ai/v1/models",
+    headers: (key) => ({ Authorization: `Bearer ${key}` }),
+    piApiType: "openai-completions",
+    piBaseUrl: "https://api.cerebras.ai/v1",
+    providerName: "cerebras",
+    filterChat: () => true,
+    isReasoning: () => false,
+    extractEntries: (data) => (data?.data ?? []).map((e) => ({ id: e.id, name: e.id }))
+  })
+};
 function extractText(msg) {
   return msg.content.filter((c) => c.type === "text").map((c) => c.text).join("");
 }
@@ -293,6 +392,9 @@ var PiAiProvider = class {
   modalities = ["llm"];
   isLocal = false;
   keys;
+  // Dynamically discovered models not in pi-ai's static catalog
+  dynamicModels = /* @__PURE__ */ new Map();
+  dynamicModelsFetched = false;
   constructor(keys) {
     this.keys = {};
     for (const [k, v] of Object.entries(keys)) {
@@ -316,11 +418,14 @@ var PiAiProvider = class {
   }
   async listModels(modality) {
     if (modality && modality !== "llm") return [];
+    await this.ensureDynamicModels();
     const models = [];
+    const seenIds = /* @__PURE__ */ new Set();
     for (const provider of KNOWN_PROVIDERS) {
       try {
         const providerModels = (0, import_pi_ai.getModels)(provider);
         for (const m of providerModels) {
+          seenIds.add(m.id);
           models.push({
             id: m.id,
             provider: "pi-ai",
@@ -342,10 +447,31 @@ var PiAiProvider = class {
       } catch {
       }
     }
+    for (const [id, m] of this.dynamicModels) {
+      if (seenIds.has(id)) continue;
+      models.push({
+        id: m.id,
+        provider: "pi-ai",
+        name: m.name || m.id,
+        modality: "llm",
+        local: false,
+        cost: {
+          price: m.cost.input ?? 0,
+          unit: m.cost.input > 0 ? "per_1m_tokens" : "free"
+        },
+        capabilities: {
+          contextWindow: m.contextWindow,
+          maxTokens: m.maxTokens,
+          supportsVision: m.input.includes("image"),
+          supportsStreaming: true
+        }
+      });
+    }
     return models;
   }
   async chat(options) {
     const start = Date.now();
+    await this.ensureDynamicModels();
     const { model, provider } = this.findModel(options.model);
     if (!model || !provider) {
       throw new Error(`Model not found: ${options.model ?? "default"}`);
@@ -378,20 +504,9 @@ var PiAiProvider = class {
   }
   stream(options) {
     const start = Date.now();
-    const { model, provider } = this.findModel(options.model);
-    if (!model || !provider) {
-      throw new Error(`Model not found: ${options.model ?? "default"}`);
-    }
-    const context = {
-      systemPrompt: options.messages.find((m) => m.role === "system")?.content,
-      messages: options.messages.filter((m) => m.role !== "system").map((m) => ({
-        role: m.role,
-        content: m.content,
-        timestamp: Date.now()
-      }))
-    };
-    const piStream = (0, import_pi_ai.stream)(model, context);
     const self = this;
+    let innerStream;
+    let providerModel;
     let aborted = false;
     let resolveResult = null;
     let rejectResult = null;
@@ -399,10 +514,30 @@ var PiAiProvider = class {
       resolveResult = resolve;
       rejectResult = reject;
     });
+    const ensureModel = async () => {
+      if (!providerModel) {
+        await self.ensureDynamicModels();
+        const found = self.findModel(options.model);
+        if (!found.model || !found.provider) {
+          throw new Error(`Model not found: ${options.model ?? "default"}`);
+        }
+        providerModel = { model: found.model, provider: found.provider };
+        const context = {
+          systemPrompt: options.messages.find((m) => m.role === "system")?.content,
+          messages: options.messages.filter((m) => m.role !== "system").map((m) => ({
+            role: m.role,
+            content: m.content,
+            timestamp: Date.now()
+          }))
+        };
+        innerStream = (0, import_pi_ai.stream)(providerModel.model, context);
+      }
+    };
     const asyncIterator = {
       async *[Symbol.asyncIterator]() {
         try {
-          for await (const chunk of piStream) {
+          await ensureModel();
+          for await (const chunk of innerStream) {
             if (aborted) break;
             if (chunk.type === "text_delta") {
               yield { type: "text_delta", delta: chunk.delta };
@@ -410,7 +545,7 @@ var PiAiProvider = class {
               yield { type: "thinking_delta", delta: chunk.delta };
             }
           }
-          const final = await piStream.result();
+          const final = await innerStream.result();
           const inputTokens = final.usage?.input ?? 0;
           const outputTokens = final.usage?.output ?? 0;
           const result = {
@@ -444,6 +579,78 @@ var PiAiProvider = class {
       }
     };
   }
+  // --- Dynamic Model Discovery (ALL providers) ---
+  async ensureDynamicModels() {
+    if (this.dynamicModelsFetched) return;
+    this.dynamicModelsFetched = true;
+    const staticIds = /* @__PURE__ */ new Set();
+    for (const provider of KNOWN_PROVIDERS) {
+      try {
+        for (const m of (0, import_pi_ai.getModels)(provider)) {
+          staticIds.add(m.id);
+        }
+      } catch {
+      }
+    }
+    const fetchPromises = [];
+    for (const [providerKey, configFactory] of Object.entries(PROVIDER_APIS)) {
+      const apiKey = this.keys[providerKey];
+      if (!apiKey) continue;
+      fetchPromises.push(this.fetchProviderModels(configFactory(apiKey), apiKey, staticIds));
+    }
+    await Promise.allSettled(fetchPromises);
+  }
+  async fetchProviderModels(config, apiKey, staticIds) {
+    try {
+      const controller = new AbortController();
+      const timer = setTimeout(() => controller.abort(), FETCH_TIMEOUT_MS);
+      try {
+        const headers = config.headers(apiKey);
+        const res = await fetch(config.url, {
+          headers: Object.keys(headers).length > 0 ? headers : void 0,
+          signal: controller.signal
+        });
+        if (!res.ok) return;
+        const data = await res.json();
+        const entries = config.extractEntries(data);
+        const templateModel = this.findStaticTemplate(config.providerName);
+        for (const entry of entries) {
+          const id = entry.id;
+          if (!config.filterChat(id)) continue;
+          if (staticIds.has(id)) continue;
+          this.dynamicModels.set(id, {
+            id,
+            name: entry.name ?? id,
+            api: config.piApiType,
+            provider: config.providerName,
+            baseUrl: config.piBaseUrl,
+            reasoning: config.isReasoning(id),
+            input: ["text", "image"],
+            cost: templateModel?.cost ?? { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+            contextWindow: entry.contextWindow ?? templateModel?.contextWindow ?? 128e3,
+            maxTokens: entry.maxTokens ?? templateModel?.maxTokens ?? 16384
+          });
+        }
+      } finally {
+        clearTimeout(timer);
+      }
+    } catch {
+    }
+  }
+  findStaticTemplate(providerName) {
+    try {
+      const models = (0, import_pi_ai.getModels)(providerName);
+      return models[0] ?? null;
+    } catch {
+      return null;
+    }
+  }
+  /** Force re-fetch of dynamic models from provider APIs */
+  async refreshDynamicModels() {
+    this.dynamicModelsFetched = false;
+    this.dynamicModels.clear();
+    await this.ensureDynamicModels();
+  }
   findModel(modelId) {
     for (const provider of KNOWN_PROVIDERS) {
       try {
@@ -453,6 +660,10 @@ var PiAiProvider = class {
       } catch {
       }
     }
+    if (modelId) {
+      const dynamic = this.dynamicModels.get(modelId);
+      if (dynamic) return { model: dynamic, provider: String(dynamic.provider) };
+    }
     return { model: null, provider: null };
   }
 };
@@ -826,51 +1037,111 @@ var LocalTTSProvider = class {
 
 // src/providers/huggingface.ts
 var import_inference = require("@huggingface/inference");
+var HF_HUB_API = "https://huggingface.co/api/models";
+var FETCH_TIMEOUT_MS2 = 1e4;
+var PIPELINE_TAG_MAP = {
+  "text-generation": { modality: "llm", limit: 50 },
+  "text-to-image": { modality: "image", limit: 50 },
+  "text-to-speech": { modality: "tts", limit: 30 }
+};
+var DEFAULT_MODELS = [
+  { id: "stabilityai/stable-diffusion-xl-base-1.0", provider: "huggingface", name: "SDXL Base", modality: "image", local: false, cost: { price: 0, unit: "free" } },
+  { id: "facebook/mms-tts-eng", provider: "huggingface", name: "MMS TTS English", modality: "tts", local: false, cost: { price: 0, unit: "free" } },
+  { id: "meta-llama/Llama-3.1-8B-Instruct", provider: "huggingface", name: "Llama 3.1 8B", modality: "llm", local: false, cost: { price: 0, unit: "free" } }
+];
 var HuggingFaceProvider = class {
   id = "huggingface";
   name = "HuggingFace Inference";
   modalities = ["image", "tts", "llm"];
   isLocal = false;
   client;
+  token;
+  dynamicModels = null;
   constructor(token) {
+    this.token = token;
     this.client = new import_inference.HfInference(token);
   }
   async ping() {
     return true;
   }
   async listModels(modality) {
+    if (!this.dynamicModels) {
+      await this.fetchHubModels();
+    }
+    const all = this.dynamicModels ?? DEFAULT_MODELS;
+    if (modality) return all.filter((m) => m.modality === modality);
+    return all;
+  }
+  async fetchHubModels() {
+    const seenIds = /* @__PURE__ */ new Set();
     const models = [];
-    if (!modality || modality === "image") {
-      models.push({
-        id: "stabilityai/stable-diffusion-xl-base-1.0",
-        provider: "huggingface",
-        name: "SDXL Base",
-        modality: "image",
-        local: false,
-        cost: { price: 0, unit: "free" }
-      });
+    for (const d of DEFAULT_MODELS) {
+      seenIds.add(d.id);
+      models.push(d);
     }
-    if (!modality || modality === "tts") {
-      models.push({
-        id: "facebook/mms-tts-eng",
-        provider: "huggingface",
-        name: "MMS TTS English",
-        modality: "tts",
-        local: false,
-        cost: { price: 0, unit: "free" }
-      });
+    const fetches = Object.entries(PIPELINE_TAG_MAP).map(
+      ([tag, { modality, limit }]) => this.fetchByPipelineTag(tag, modality, limit)
+    );
+    const results = await Promise.allSettled(fetches);
+    for (const result of results) {
+      if (result.status !== "fulfilled") continue;
+      for (const model of result.value) {
+        if (seenIds.has(model.id)) continue;
+        seenIds.add(model.id);
+        models.push(model);
+      }
     }
-    if (!modality || modality === "llm") {
-      models.push({
-        id: "meta-llama/Llama-3.1-8B-Instruct",
-        provider: "huggingface",
-        name: "Llama 3.1 8B",
-        modality: "llm",
-        local: false,
-        cost: { price: 0, unit: "free" }
-      });
+    this.dynamicModels = models;
+  }
+  async fetchByPipelineTag(pipelineTag, modality, limit) {
+    try {
+      const controller = new AbortController();
+      const timer = setTimeout(() => controller.abort(), FETCH_TIMEOUT_MS2);
+      try {
+        const params = new URLSearchParams({
+          pipeline_tag: pipelineTag,
+          inference_provider: "all",
+          sort: "trendingScore",
+          limit: String(limit),
+          "expand[]": "inferenceProviderMapping"
+        });
+        const res = await fetch(`${HF_HUB_API}?${params}`, {
+          headers: this.token ? { Authorization: `Bearer ${this.token}` } : {},
+          signal: controller.signal
+        });
+        if (!res.ok) return [];
+        const data = await res.json();
+        return data.filter((entry) => entry.id || entry.modelId).map((entry) => {
+          const id = entry.id ?? entry.modelId;
+          const providers = (entry.inferenceProviderMapping ?? []).filter((p) => p.status === "live").map((p) => p.provider);
+          const pricingProvider = (entry.inferenceProviderMapping ?? []).find((p) => p.providerDetails?.pricing);
+          const pricing = pricingProvider?.providerDetails?.pricing;
+          const contextLength = (entry.inferenceProviderMapping ?? []).find((p) => p.providerDetails?.context_length)?.providerDetails?.context_length;
+          return {
+            id,
+            provider: "huggingface",
+            name: id.split("/").pop() ?? id,
+            modality,
+            local: false,
+            cost: {
+              price: pricing?.input ?? 0,
+              unit: pricing ? "per_1m_tokens" : "free"
+            },
+            capabilities: {
+              ...modality === "llm" ? {
+                contextWindow: contextLength,
+                supportsStreaming: true
+              } : {},
+              ...providers.length > 0 ? { inferenceProviders: providers } : {}
+            }
+          };
+        });
+      } finally {
+        clearTimeout(timer);
+      }
+    } catch {
+      return [];
     }
-    return models;
   }
   async chat(options) {
     const start = Date.now();