@goondocks/myco 0.6.1 → 0.6.3

package/.claude-plugin/marketplace.json

@@ -12,7 +12,7 @@
       "source": {
         "source": "npm",
         "package": "@goondocks/myco",
-        "version": "0.6.0"
+        "version": "0.6.2"
       },
       "description": "Collective agent intelligence — captures session knowledge and serves it back via MCP",
       "license": "MIT",

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "myco",
-  "version": "0.6.1",
+  "version": "0.6.3",
   "description": "Collective agent intelligence — captures session knowledge and serves it back to your team via MCP",
   "author": {
     "name": "goondocks-co",

package/dist/{chunk-QGJ2ZIUZ.js → chunk-25FY74AP.js}

@@ -3,7 +3,7 @@ import {
   DAEMON_CLIENT_TIMEOUT_MS,
   EMBEDDING_REQUEST_TIMEOUT_MS,
   LLM_REQUEST_TIMEOUT_MS
-} from "./chunk-6BSDCZ5Q.js";
+} from "./chunk-WBLTISAK.js";
 
 // src/intelligence/ollama.ts
 var ENDPOINT_GENERATE = "/api/generate";
@@ -32,7 +32,7 @@ var OllamaBackend = class _OllamaBackend {
     const body = {
       model: this.model,
       prompt,
-      stream: false,
+      stream: true,
       options
     };
     if (opts?.systemPrompt) {
@@ -54,8 +54,40 @@ var OllamaBackend = class _OllamaBackend {
       const errorBody = await response.text().catch(() => "");
       throw new Error(`Ollama summarize failed: ${response.status} ${errorBody.slice(0, 500)}`);
     }
-    const data = await response.json();
-    return { text: data.response, model: data.model };
+    return this.readStream(response);
+  }
+  /** Read an Ollama streaming response (newline-delimited JSON) and accumulate the result. */
+  async readStream(response) {
+    const reader = response.body.getReader();
+    const decoder = new TextDecoder();
+    let text = "";
+    let model = this.model;
+    let buffer = "";
+    try {
+      for (; ; ) {
+        const { done, value } = await reader.read();
+        if (done) break;
+        buffer += decoder.decode(value, { stream: true });
+        const lines = buffer.split("\n");
+        buffer = lines.pop() ?? "";
+        for (const line of lines) {
+          if (!line.trim()) continue;
+          const chunk = JSON.parse(line);
+          if (chunk.error) throw new Error(`Ollama stream error: ${chunk.error}`);
+          text += chunk.response ?? "";
+          if (chunk.model) model = chunk.model;
+        }
+      }
+      if (buffer.trim()) {
+        const chunk = JSON.parse(buffer);
+        if (chunk.error) throw new Error(`Ollama stream error: ${chunk.error}`);
+        text += chunk.response ?? "";
+        if (chunk.model) model = chunk.model;
+      }
+    } finally {
+      reader.releaseLock();
+    }
+    return { text, model };
   }
   async embed(text) {
     const response = await fetch(`${this.baseUrl}${ENDPOINT_EMBED}`, {
@@ -183,35 +215,37 @@ var LmStudioBackend = class _LmStudioBackend {
     return { embedding, model: data.model, dimensions: embedding.length };
   }
   /**
-   * Ensure a model instance is loaded with the desired settings.
-   * Called every digest cycle (not cached) so it recovers from idle TTL eviction.
+   * Ensure a model instance is loaded and capture its ID for routing.
+   * Called every digest cycle so it recovers from idle TTL eviction.
    *
-   * The load API is necessary to control offload_kv_cache_to_gpu — a load-time
-   * setting that cannot be set per-request via the chat API.
+   * Strategy: reuse ANY loaded instance of this model. Only load a new one
+   * when zero instances exist. This avoids the previous bug where strict
+   * config matching (context_length, offload_kv_cache_to_gpu) caused new
+   * instances to spawn every cycle — exhausting system resources.
    *
-   * Multi-daemon safe: finds or loads our own compatible instance without
-   * touching instances from other daemons/projects. Routes by instance ID.
+   * context_length is set per-request on /api/v1/chat, so we don't need
+   * to match it at load time. Load-time-only params like
+   * offload_kv_cache_to_gpu are llama.cpp-specific and may not apply to
+   * all models (e.g., glm-4.7-flash has no KV cache setting).
    */
   async ensureLoaded(contextLength, gpuKvCache) {
-    const ctx = contextLength ?? this.contextWindow;
-    const kvCache = gpuKvCache ?? false;
     const instances = await this.getLoadedInstances();
-    for (const instance of instances) {
-      const matchesContext = !ctx || instance.config.context_length === ctx;
-      const matchesKvCache = instance.config.offload_kv_cache_to_gpu === kvCache;
-      if (matchesContext && matchesKvCache) {
-        this.instanceId = instance.id;
-        return;
-      }
+    if (instances.length > 0) {
+      this.instanceId = instances[0].id;
+      return;
     }
+    const ctx = contextLength ?? this.contextWindow;
     const body = {
       model: this.model,
-      flash_attention: true,
-      offload_kv_cache_to_gpu: kvCache
+      // llama.cpp-specific — ignored by other engines (MLX, etc.)
+      flash_attention: true
     };
     if (ctx) {
       body.context_length = ctx;
     }
+    if (gpuKvCache) {
+      body.offload_kv_cache_to_gpu = true;
+    }
     const response = await fetch(`${this.baseUrl}${ENDPOINT_MODELS_LOAD}`, {
       method: "POST",
       headers: { "Content-Type": "application/json" },
@@ -273,4 +307,4 @@ export {
   OllamaBackend,
   LmStudioBackend
 };
-//# sourceMappingURL=chunk-QGJ2ZIUZ.js.map
+//# sourceMappingURL=chunk-25FY74AP.js.map

package/dist/chunk-25FY74AP.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/intelligence/ollama.ts","../src/intelligence/lm-studio.ts"],"sourcesContent":["import type { LlmProvider, EmbeddingProvider, LlmResponse, EmbeddingResponse, LlmRequestOptions } from './llm.js';\nimport { LLM_REQUEST_TIMEOUT_MS, EMBEDDING_REQUEST_TIMEOUT_MS, DAEMON_CLIENT_TIMEOUT_MS } from '../constants.js';\n\ninterface OllamaConfig {\n  model?: string;\n  base_url?: string;\n  context_window?: number;\n  max_tokens?: number;\n  // Legacy fields (ignored, kept for backward compat during migration)\n  embedding_model?: string;\n  summary_model?: string;\n}\n\n// Ollama API endpoints\nconst ENDPOINT_GENERATE = '/api/generate';\nconst ENDPOINT_EMBED = '/api/embed';\nconst ENDPOINT_TAGS = '/api/tags';\n\nexport class OllamaBackend implements LlmProvider, EmbeddingProvider {\n  static readonly DEFAULT_BASE_URL = 'http://localhost:11434';\n  readonly name = 'ollama';\n  private baseUrl: string;\n  private model: string;\n  private defaultMaxTokens: number;\n  private contextWindow: number | undefined;\n\n  constructor(config?: OllamaConfig) {\n    this.baseUrl = config?.base_url ?? OllamaBackend.DEFAULT_BASE_URL;\n    this.model = config?.model ?? config?.summary_model ?? 'llama3.2';\n    this.defaultMaxTokens = config?.max_tokens ?? 1024;\n    this.contextWindow = config?.context_window;\n  }\n\n  async summarize(prompt: string, opts?: LlmRequestOptions): Promise<LlmResponse> {\n    const maxTokens = opts?.maxTokens ?? this.defaultMaxTokens;\n\n    // Send num_ctx from config or per-call override. Ollama reloads the model\n    // on num_ctx changes, but consistent values (same num_ctx every call)\n    // only cause one reload on first use. Without this, Ollama falls back to\n    // its model default (often 2048), ignoring the user's configured context.\n    const contextLength = opts?.contextLength ?? this.contextWindow;\n    const options: Record<string, unknown> = { num_predict: maxTokens };\n    if (contextLength) {\n      options.num_ctx = contextLength;\n    }\n\n    const body: Record<string, unknown> = {\n      model: this.model,\n      prompt,\n      stream: true,\n      options,\n    };\n\n    // System prompt — sent as a separate field instead of concatenated into prompt\n    if (opts?.systemPrompt) {\n      body.system = opts.systemPrompt;\n    }\n\n    // Thinking control — false suppresses chain-of-thought for reasoning models\n    if (opts?.reasoning) {\n      body.think = opts.reasoning === 'off' ? false : opts.reasoning;\n    }\n\n    // Keep model loaded between requests (useful for digest cycles)\n    if (opts?.keepAlive) {\n      body.keep_alive = opts.keepAlive;\n    }\n\n    const response = await fetch(`${this.baseUrl}${ENDPOINT_GENERATE}`, {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify(body),\n      signal: AbortSignal.timeout(opts?.timeoutMs ?? LLM_REQUEST_TIMEOUT_MS),\n    });\n\n    if (!response.ok) {\n      const errorBody = await response.text().catch(() => '');\n      throw new Error(`Ollama summarize failed: ${response.status} ${errorBody.slice(0, 500)}`);\n    }\n\n    return this.readStream(response);\n  }\n\n  /** Read an Ollama streaming response (newline-delimited JSON) and accumulate the result. */\n  private async readStream(response: Response): Promise<LlmResponse> {\n    const reader = response.body!.getReader();\n    const decoder = new TextDecoder();\n    let text = '';\n    let model = this.model;\n    let buffer = '';\n\n    try {\n      for (;;) {\n        const { done, value } = await reader.read();\n        if (done) break;\n\n        buffer += decoder.decode(value, { stream: true });\n        const lines = buffer.split('\\n');\n        buffer = lines.pop() ?? '';\n\n        for (const line of lines) {\n          if (!line.trim()) continue;\n          const chunk = JSON.parse(line) as { response?: string; model?: string; error?: string };\n          if (chunk.error) throw new Error(`Ollama stream error: ${chunk.error}`);\n          text += chunk.response ?? '';\n          if (chunk.model) model = chunk.model;\n        }\n      }\n\n      // Process remaining buffer\n      if (buffer.trim()) {\n        const chunk = JSON.parse(buffer) as { response?: string; model?: string; error?: string };\n        if (chunk.error) throw new Error(`Ollama stream error: ${chunk.error}`);\n        text += chunk.response ?? '';\n        if (chunk.model) model = chunk.model;\n      }\n    } finally {\n      reader.releaseLock();\n    }\n\n    return { text, model };\n  }\n\n  async embed(text: string): Promise<EmbeddingResponse> {\n    const response = await fetch(`${this.baseUrl}${ENDPOINT_EMBED}`, {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify({\n        model: this.model,\n        input: text,\n      }),\n      signal: AbortSignal.timeout(EMBEDDING_REQUEST_TIMEOUT_MS),\n    });\n\n    if (!response.ok) {\n      throw new Error(`Ollama embed failed: ${response.status} ${response.statusText}`);\n    }\n\n    const data = await response.json() as { embeddings: number[][]; model: string };\n    const embedding = data.embeddings[0];\n    return { embedding, model: data.model, dimensions: embedding.length };\n  }\n\n  async isAvailable(): Promise<boolean> {\n    try {\n      const response = await fetch(`${this.baseUrl}${ENDPOINT_TAGS}`, {\n        signal: AbortSignal.timeout(DAEMON_CLIENT_TIMEOUT_MS),\n      });\n      return response.ok;\n    } catch {\n      return false;\n    }\n  }\n\n  /** List available models on this Ollama instance. */\n  async listModels(timeoutMs?: number): Promise<string[]> {\n    try {\n      const response = await fetch(`${this.baseUrl}${ENDPOINT_TAGS}`, {\n        signal: AbortSignal.timeout(timeoutMs ?? DAEMON_CLIENT_TIMEOUT_MS),\n      });\n      const data = await response.json() as { models: Array<{ name: string }> };\n      return data.models.map((m) => m.name);\n    } catch {\n      return [];\n    }\n  }\n}\n","import type { LlmProvider, EmbeddingProvider, LlmResponse, EmbeddingResponse, LlmRequestOptions } from './llm.js';\nimport { LLM_REQUEST_TIMEOUT_MS, EMBEDDING_REQUEST_TIMEOUT_MS, DAEMON_CLIENT_TIMEOUT_MS } from '../constants.js';\n\ninterface LmStudioConfig {\n  model?: string;\n  base_url?: string;\n  context_window?: number;\n  max_tokens?: number;\n  // Legacy fields\n  embedding_model?: string;\n  summary_model?: string;\n}\n\n// LM Studio API endpoints\nconst ENDPOINT_CHAT = '/api/v1/chat';\nconst ENDPOINT_MODELS_LOAD = '/api/v1/models/load';\nconst ENDPOINT_MODELS_LIST = '/v1/models';\nconst ENDPOINT_MODELS_NATIVE = '/api/v1/models';\nconst ENDPOINT_EMBEDDINGS = '/v1/embeddings';\n\n/** Shape of a loaded instance from the LM Studio native models API.\n *  Config fields vary by engine — llama.cpp models include flash_attention\n *  and offload_kv_cache_to_gpu, but other engines (MLX, etc.) may omit them. */\ninterface NativeLoadedInstance {\n  id: string;\n  config: {\n    context_length: number;\n    flash_attention?: boolean;\n    offload_kv_cache_to_gpu?: boolean;\n  };\n}\n\n/** Shape of a model entry from the LM Studio native models API. */\ninterface NativeModelEntry {\n  type: string;\n  key: string;\n  loaded_instances: NativeLoadedInstance[];\n}\n\nexport class LmStudioBackend implements LlmProvider, EmbeddingProvider {\n  static readonly DEFAULT_BASE_URL = 'http://localhost:1234';\n  readonly name = 'lm-studio';\n  private baseUrl: string;\n  private model: string;\n  private instanceId: string | null = null;\n  private contextWindow: number | undefined;\n  private defaultMaxTokens: number;\n\n  constructor(config?: LmStudioConfig) {\n    this.baseUrl = config?.base_url ?? LmStudioBackend.DEFAULT_BASE_URL;\n    this.model = config?.model ?? config?.summary_model ?? 'llama3.2';\n    this.contextWindow = config?.context_window;\n    this.defaultMaxTokens = config?.max_tokens ?? 1024;\n  }\n\n  /**\n   * Generate text using LM Studio's native REST API (/api/v1/chat).\n   * Routes to our specific instance by ID when available, with model name +\n   * context_length as fallback. This ensures correct routing when multiple\n   * daemons share the same LM Studio, and graceful degradation when our\n   * instance is evicted by idle TTL.\n   */\n  async summarize(prompt: string, opts?: LlmRequestOptions): Promise<LlmResponse> {\n    const maxTokens = opts?.maxTokens ?? this.defaultMaxTokens;\n    const contextLength = opts?.contextLength ?? this.contextWindow;\n\n    const body: Record<string, unknown> = {\n      model: this.instanceId ?? this.model,\n      input: prompt,\n      max_output_tokens: maxTokens,\n      store: false,\n    };\n\n    // Always send context_length — even when routing by instance ID.\n    // If our instance was evicted and LM Studio auto-loads, this ensures\n    // the replacement gets the correct context window.\n    if (contextLength) {\n      body.context_length = contextLength;\n    }\n\n    // System prompt — sent separately from user content\n    if (opts?.systemPrompt) {\n      body.system_prompt = opts.systemPrompt;\n    }\n\n    // Reasoning control — 'off' suppresses chain-of-thought for reasoning models\n    if (opts?.reasoning) {\n      body.reasoning = opts.reasoning;\n    }\n\n    const response = await fetch(`${this.baseUrl}${ENDPOINT_CHAT}`, {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify(body),\n      signal: AbortSignal.timeout(opts?.timeoutMs ?? LLM_REQUEST_TIMEOUT_MS),\n    });\n\n    if (!response.ok) {\n      const errorBody = await response.text().catch(() => '');\n      // If our instance was evicted, clear the ID so ensureLoaded\n      // reloads on the next cycle instead of hitting a stale ID repeatedly\n      if (response.status === 404 && this.instanceId) {\n        this.instanceId = null;\n      }\n      throw new Error(`LM Studio summarize failed: ${response.status} ${errorBody.slice(0, 500)}`);\n    }\n\n    const data = await response.json() as {\n      model_instance_id: string;\n      output: Array<{ type: string; content: string }>;\n    };\n    const messageOutput = data.output.find((o) => o.type === 'message');\n    const text = messageOutput?.content ?? '';\n    return { text, model: data.model_instance_id };\n  }\n\n  /**\n   * Generate embeddings using LM Studio's OpenAI-compatible endpoint.\n   * (The native API doesn't have an embedding endpoint — OpenAI-compat is fine here.)\n   */\n  async embed(text: string): Promise<EmbeddingResponse> {\n    const response = await fetch(`${this.baseUrl}${ENDPOINT_EMBEDDINGS}`, {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify({\n        model: this.model,\n        input: text,\n      }),\n      signal: AbortSignal.timeout(EMBEDDING_REQUEST_TIMEOUT_MS),\n    });\n\n    if (!response.ok) {\n      throw new Error(`LM Studio embed failed: ${response.status}`);\n    }\n\n    const data = await response.json() as {\n      data: Array<{ embedding: number[] }>;\n      model: string;\n    };\n    const embedding = data.data[0].embedding;\n    return { embedding, model: data.model, dimensions: embedding.length };\n  }\n\n  /**\n   * Ensure a model instance is loaded and capture its ID for routing.\n   * Called every digest cycle so it recovers from idle TTL eviction.\n   *\n   * Strategy: reuse ANY loaded instance of this model. Only load a new one\n   * when zero instances exist. This avoids the previous bug where strict\n   * config matching (context_length, offload_kv_cache_to_gpu) caused new\n   * instances to spawn every cycle — exhausting system resources.\n   *\n   * context_length is set per-request on /api/v1/chat, so we don't need\n   * to match it at load time. Load-time-only params like\n   * offload_kv_cache_to_gpu are llama.cpp-specific and may not apply to\n   * all models (e.g., glm-4.7-flash has no KV cache setting).\n   */\n  async ensureLoaded(contextLength?: number, gpuKvCache?: boolean): Promise<void> {\n    // Query native API for existing loaded instances of this model\n    const instances = await this.getLoadedInstances();\n\n    if (instances.length > 0) {\n      // Reuse the first available instance — don't reject over config differences.\n      // context_length is set per-request; load-time params like kv_cache are\n      // model-dependent and may not even appear in the instance config.\n      this.instanceId = instances[0].id;\n      return;\n    }\n\n    // No instances loaded — load one with our preferred settings.\n    // These are hints; LM Studio silently ignores params that don't apply to the model's engine.\n    const ctx = contextLength ?? this.contextWindow;\n    const body: Record<string, unknown> = {\n      model: this.model,\n      // llama.cpp-specific — ignored by other engines (MLX, etc.)\n      flash_attention: true,\n    };\n    if (ctx) {\n      body.context_length = ctx;\n    }\n    if (gpuKvCache) {\n      body.offload_kv_cache_to_gpu = true;\n    }\n\n    const response = await fetch(`${this.baseUrl}${ENDPOINT_MODELS_LOAD}`, {\n      method: 'POST',\n      headers: { 'Content-Type': 'application/json' },\n      body: JSON.stringify(body),\n      signal: AbortSignal.timeout(LLM_REQUEST_TIMEOUT_MS),\n    });\n\n    if (!response.ok) {\n      const errorBody = await response.text().catch(() => '');\n      throw new Error(`LM Studio model load failed: ${response.status} ${errorBody.slice(0, 200)}`);\n    }\n\n    const loadResult = await response.json() as Record<string, unknown>;\n    const id = (loadResult.instance_id ?? loadResult.id ?? loadResult.model_instance_id) as string | undefined;\n    if (id) {\n      this.instanceId = id;\n    }\n  }\n\n  /**\n   * Query the LM Studio native API for loaded instances of this model.\n   * Returns an empty array if the API is unavailable or the model has no loaded instances.\n   */\n  private async getLoadedInstances(): Promise<NativeLoadedInstance[]> {\n    try {\n      const response = await fetch(`${this.baseUrl}${ENDPOINT_MODELS_NATIVE}`, {\n        signal: AbortSignal.timeout(DAEMON_CLIENT_TIMEOUT_MS),\n      });\n      if (!response.ok) return [];\n\n      const data = await response.json() as { models: NativeModelEntry[] };\n      const entry = data.models.find((m) => m.key === this.model);\n      return entry?.loaded_instances ?? [];\n    } catch {\n      return [];\n    }\n  }\n\n  async isAvailable(): Promise<boolean> {\n    try {\n      const response = await fetch(`${this.baseUrl}${ENDPOINT_MODELS_LIST}`, {\n        signal: AbortSignal.timeout(DAEMON_CLIENT_TIMEOUT_MS),\n      });\n      return response.ok;\n    } catch {\n      return false;\n    }\n  }\n\n  /** List available models on this LM Studio instance. */\n  async listModels(timeoutMs?: number): Promise<string[]> {\n    try {\n      const response = await fetch(`${this.baseUrl}${ENDPOINT_MODELS_LIST}`, {\n        signal: AbortSignal.timeout(timeoutMs ?? DAEMON_CLIENT_TIMEOUT_MS),\n      });\n      const data = await response.json() as { data: Array<{ id: string }> };\n      return data.data.map((m) => m.id);\n    } catch {\n      return [];\n    }\n  }\n}\n"],"mappings":";;;;;;;;AAcA,IAAM,oBAAoB;AAC1B,IAAM,iBAAiB;AACvB,IAAM,gBAAgB;AAEf,IAAM,gBAAN,MAAM,eAAwD;AAAA,EACnE,OAAgB,mBAAmB;AAAA,EAC1B,OAAO;AAAA,EACR;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EAER,YAAY,QAAuB;AACjC,SAAK,UAAU,QAAQ,YAAY,eAAc;AACjD,SAAK,QAAQ,QAAQ,SAAS,QAAQ,iBAAiB;AACvD,SAAK,mBAAmB,QAAQ,cAAc;AAC9C,SAAK,gBAAgB,QAAQ;AAAA,EAC/B;AAAA,EAEA,MAAM,UAAU,QAAgB,MAAgD;AAC9E,UAAM,YAAY,MAAM,aAAa,KAAK;AAM1C,UAAM,gBAAgB,MAAM,iBAAiB,KAAK;AAClD,UAAM,UAAmC,EAAE,aAAa,UAAU;AAClE,QAAI,eAAe;AACjB,cAAQ,UAAU;AAAA,IACpB;AAEA,UAAM,OAAgC;AAAA,MACpC,OAAO,KAAK;AAAA,MACZ;AAAA,MACA,QAAQ;AAAA,MACR;AAAA,IACF;AAGA,QAAI,MAAM,cAAc;AACtB,WAAK,SAAS,KAAK;AAAA,IACrB;AAGA,QAAI,MAAM,WAAW;AACnB,WAAK,QAAQ,KAAK,cAAc,QAAQ,QAAQ,KAAK;AAAA,IACvD;AAGA,QAAI,MAAM,WAAW;AACnB,WAAK,aAAa,KAAK;AAAA,IACzB;AAEA,UAAM,WAAW,MAAM,MAAM,GAAG,KAAK,OAAO,GAAG,iBAAiB,IAAI;AAAA,MAClE,QAAQ;AAAA,MACR,SAAS,EAAE,gBAAgB,mBAAmB;AAAA,MAC9C,MAAM,KAAK,UAAU,IAAI;AAAA,MACzB,QAAQ,YAAY,QAAQ,MAAM,aAAa,sBAAsB;AAAA,IACvE,CAAC;AAED,QAAI,CAAC,SAAS,IAAI;AAChB,YAAM,YAAY,MAAM,SAAS,KAAK,EAAE,MAAM,MAAM,EAAE;AACtD,YAAM,IAAI,MAAM,4BAA4B,SAAS,MAAM,IAAI,UAAU,MAAM,GAAG,GAAG,CAAC,EAAE;AAAA,IAC1F;AAEA,WAAO,KAAK,WAAW,QAAQ;AAAA,EACjC;AAAA;AAAA,EAGA,MAAc,WAAW,UAA0C;AACjE,UAAM,SAAS,SAAS,KAAM,UAAU;AACxC,UAAM,UAAU,IAAI,YAAY;AAChC,QAAI,OAAO;AACX,QAAI,QAAQ,KAAK;AACjB,QAAI,SAAS;AAEb,QAAI;AACF,iBAAS;AACP,cAAM,EAAE,MAAM,MAAM,IAAI,MAAM,OAAO,KAAK;AAC1C,YAAI,KAAM;AAEV,kBAAU,QAAQ,OAAO,OAAO,EAAE,QAAQ,KAAK,CAAC;AAChD,cAAM,QAAQ,OAAO,MAAM,IAAI;AAC/B,iBAAS,MAAM,IAAI,KAAK;AAExB,mBAAW,QAAQ,OAAO;AACxB,cAAI,CAAC,KAAK,KAAK,EAAG;AAClB,gBAAM,QAAQ,KAAK,MAAM,IAAI;AAC7B,cAAI,MAAM,MAAO,OAAM,IAAI,MAAM,wBAAwB,MAAM,KAAK,EAAE;AACtE,kBAAQ,MAAM,YAAY;AAC1B,cAAI,MAAM,MAAO,SAAQ,MAAM;AAAA,QACjC;AAAA,MACF;AAGA,UAAI,OAAO,KAAK,GAAG;AACjB,cAAM,QAAQ,KAAK,MAAM,MAAM;AAC/B,YAAI,MAAM,MAAO,OAAM,IAAI,MAAM,wBAAwB,MAAM,KAAK,EAAE;AACtE,gBAAQ,MAAM,YAAY;AAC1B,YAAI,MAAM,MAAO,SAAQ,MAAM;AAAA,MACjC;AAAA,IACF,UAAE;AACA,aAAO,YAAY;AAAA,IACrB;AAEA,WAAO,EAAE,MAAM,MAAM;AAAA,EACvB;AAAA,EAEA,MAAM,MAAM,MAA0C;AACpD,UAAM,WAAW,MAAM,MAAM,GAAG,KAAK,OAAO,GAAG,cAAc,IAAI;AAAA,MAC/D,QAAQ;AAAA,MACR,SAAS,EAAE,gBAAgB,mBAAmB;AAAA,MAC9C,MAAM,KAAK,UAAU;AAAA,QACnB,OAAO,KAAK;AAAA,QACZ,OAAO;AAAA,MACT,CAAC;AAAA,MACD,QAAQ,YAAY,QAAQ,4BAA4B;AAAA,IAC1D,CAAC;AAED,QAAI,CAAC,SAAS,IAAI;AAChB,YAAM,IAAI,MAAM,wBAAwB,SAAS,MAAM,IAAI,SAAS,UAAU,EAAE;AAAA,IAClF;AAEA,UAAM,OAAO,MAAM,SAAS,KAAK;AACjC,UAAM,YAAY,KAAK,WAAW,CAAC;AACnC,WAAO,EAAE,WAAW,OAAO,KAAK,OAAO,YAAY,UAAU,OAAO;AAAA,EACtE;AAAA,EAEA,MAAM,cAAgC;AACpC,QAAI;AACF,YAAM,WAAW,MAAM,MAAM,GAAG,KAAK,OAAO,GAAG,aAAa,IAAI;AAAA,QAC9D,QAAQ,YAAY,QAAQ,wBAAwB;AAAA,MACtD,CAAC;AACD,aAAO,SAAS;AAAA,IAClB,QAAQ;AACN,aAAO;AAAA,IACT;AAAA,EACF;AAAA;AAAA,EAGA,MAAM,WAAW,WAAuC;AACtD,QAAI;AACF,YAAM,WAAW,MAAM,MAAM,GAAG,KAAK,OAAO,GAAG,aAAa,IAAI;AAAA,QAC9D,QAAQ,YAAY,QAAQ,aAAa,wBAAwB;AAAA,MACnE,CAAC;AACD,YAAM,OAAO,MAAM,SAAS,KAAK;AACjC,aAAO,KAAK,OAAO,IAAI,CAAC,MAAM,EAAE,IAAI;AAAA,IACtC,QAAQ;AACN,aAAO,CAAC;AAAA,IACV;AAAA,EACF;AACF;;;ACxJA,IAAM,gBAAgB;AACtB,IAAM,uBAAuB;AAC7B,IAAM,uBAAuB;AAC7B,IAAM,yBAAyB;AAC/B,IAAM,sBAAsB;AAqBrB,IAAM,kBAAN,MAAM,iBAA0D;AAAA,EACrE,OAAgB,mBAAmB;AAAA,EAC1B,OAAO;AAAA,EACR;AAAA,EACA;AAAA,EACA,aAA4B;AAAA,EAC5B;AAAA,EACA;AAAA,EAER,YAAY,QAAyB;AACnC,SAAK,UAAU,QAAQ,YAAY,iBAAgB;AACnD,SAAK,QAAQ,QAAQ,SAAS,QAAQ,iBAAiB;AACvD,SAAK,gBAAgB,QAAQ;AAC7B,SAAK,mBAAmB,QAAQ,cAAc;AAAA,EAChD;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EASA,MAAM,UAAU,QAAgB,MAAgD;AAC9E,UAAM,YAAY,MAAM,aAAa,KAAK;AAC1C,UAAM,gBAAgB,MAAM,iBAAiB,KAAK;AAElD,UAAM,OAAgC;AAAA,MACpC,OAAO,KAAK,cAAc,KAAK;AAAA,MAC/B,OAAO;AAAA,MACP,mBAAmB;AAAA,MACnB,OAAO;AAAA,IACT;AAKA,QAAI,eAAe;AACjB,WAAK,iBAAiB;AAAA,IACxB;AAGA,QAAI,MAAM,cAAc;AACtB,WAAK,gBAAgB,KAAK;AAAA,IAC5B;AAGA,QAAI,MAAM,WAAW;AACnB,WAAK,YAAY,KAAK;AAAA,IACxB;AAEA,UAAM,WAAW,MAAM,MAAM,GAAG,KAAK,OAAO,GAAG,aAAa,IAAI;AAAA,MAC9D,QAAQ;AAAA,MACR,SAAS,EAAE,gBAAgB,mBAAmB;AAAA,MAC9C,MAAM,KAAK,UAAU,IAAI;AAAA,MACzB,QAAQ,YAAY,QAAQ,MAAM,aAAa,sBAAsB;AAAA,IACvE,CAAC;AAED,QAAI,CAAC,SAAS,IAAI;AAChB,YAAM,YAAY,MAAM,SAAS,KAAK,EAAE,MAAM,MAAM,EAAE;AAGtD,UAAI,SAAS,WAAW,OAAO,KAAK,YAAY;AAC9C,aAAK,aAAa;AAAA,MACpB;AACA,YAAM,IAAI,MAAM,+BAA+B,SAAS,MAAM,IAAI,UAAU,MAAM,GAAG,GAAG,CAAC,EAAE;AAAA,IAC7F;AAEA,UAAM,OAAO,MAAM,SAAS,KAAK;AAIjC,UAAM,gBAAgB,KAAK,OAAO,KAAK,CAAC,MAAM,EAAE,SAAS,SAAS;AAClE,UAAM,OAAO,eAAe,WAAW;AACvC,WAAO,EAAE,MAAM,OAAO,KAAK,kBAAkB;AAAA,EAC/C;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,MAAM,MAAM,MAA0C;AACpD,UAAM,WAAW,MAAM,MAAM,GAAG,KAAK,OAAO,GAAG,mBAAmB,IAAI;AAAA,MACpE,QAAQ;AAAA,MACR,SAAS,EAAE,gBAAgB,mBAAmB;AAAA,MAC9C,MAAM,KAAK,UAAU;AAAA,QACnB,OAAO,KAAK;AAAA,QACZ,OAAO;AAAA,MACT,CAAC;AAAA,MACD,QAAQ,YAAY,QAAQ,4BAA4B;AAAA,IAC1D,CAAC;AAED,QAAI,CAAC,SAAS,IAAI;AAChB,YAAM,IAAI,MAAM,2BAA2B,SAAS,MAAM,EAAE;AAAA,IAC9D;AAEA,UAAM,OAAO,MAAM,SAAS,KAAK;AAIjC,UAAM,YAAY,KAAK,KAAK,CAAC,EAAE;AAC/B,WAAO,EAAE,WAAW,OAAO,KAAK,OAAO,YAAY,UAAU,OAAO;AAAA,EACtE;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAgBA,MAAM,aAAa,eAAwB,YAAqC;AAE9E,UAAM,YAAY,MAAM,KAAK,mBAAmB;AAEhD,QAAI,UAAU,SAAS,GAAG;AAIxB,WAAK,aAAa,UAAU,CAAC,EAAE;AAC/B;AAAA,IACF;AAIA,UAAM,MAAM,iBAAiB,KAAK;AAClC,UAAM,OAAgC;AAAA,MACpC,OAAO,KAAK;AAAA;AAAA,MAEZ,iBAAiB;AAAA,IACnB;AACA,QAAI,KAAK;AACP,WAAK,iBAAiB;AAAA,IACxB;AACA,QAAI,YAAY;AACd,WAAK,0BAA0B;AAAA,IACjC;AAEA,UAAM,WAAW,MAAM,MAAM,GAAG,KAAK,OAAO,GAAG,oBAAoB,IAAI;AAAA,MACrE,QAAQ;AAAA,MACR,SAAS,EAAE,gBAAgB,mBAAmB;AAAA,MAC9C,MAAM,KAAK,UAAU,IAAI;AAAA,MACzB,QAAQ,YAAY,QAAQ,sBAAsB;AAAA,IACpD,CAAC;AAED,QAAI,CAAC,SAAS,IAAI;AAChB,YAAM,YAAY,MAAM,SAAS,KAAK,EAAE,MAAM,MAAM,EAAE;AACtD,YAAM,IAAI,MAAM,gCAAgC,SAAS,MAAM,IAAI,UAAU,MAAM,GAAG,GAAG,CAAC,EAAE;AAAA,IAC9F;AAEA,UAAM,aAAa,MAAM,SAAS,KAAK;AACvC,UAAM,KAAM,WAAW,eAAe,WAAW,MAAM,WAAW;AAClE,QAAI,IAAI;AACN,WAAK,aAAa;AAAA,IACpB;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,MAAc,qBAAsD;AAClE,QAAI;AACF,YAAM,WAAW,MAAM,MAAM,GAAG,KAAK,OAAO,GAAG,sBAAsB,IAAI;AAAA,QACvE,QAAQ,YAAY,QAAQ,wBAAwB;AAAA,MACtD,CAAC;AACD,UAAI,CAAC,SAAS,GAAI,QAAO,CAAC;AAE1B,YAAM,OAAO,MAAM,SAAS,KAAK;AACjC,YAAM,QAAQ,KAAK,OAAO,KAAK,CAAC,MAAM,EAAE,QAAQ,KAAK,KAAK;AAC1D,aAAO,OAAO,oBAAoB,CAAC;AAAA,IACrC,QAAQ;AACN,aAAO,CAAC;AAAA,IACV;AAAA,EACF;AAAA,EAEA,MAAM,cAAgC;AACpC,QAAI;AACF,YAAM,WAAW,MAAM,MAAM,GAAG,KAAK,OAAO,GAAG,oBAAoB,IAAI;AAAA,QACrE,QAAQ,YAAY,QAAQ,wBAAwB;AAAA,MACtD,CAAC;AACD,aAAO,SAAS;AAAA,IAClB,QAAQ;AACN,aAAO;AAAA,IACT;AAAA,EACF;AAAA;AAAA,EAGA,MAAM,WAAW,WAAuC;AACtD,QAAI;AACF,YAAM,WAAW,MAAM,MAAM,GAAG,KAAK,OAAO,GAAG,oBAAoB,IAAI;AAAA,QACrE,QAAQ,YAAY,QAAQ,aAAa,wBAAwB;AAAA,MACnE,CAAC;AACD,YAAM,OAAO,MAAM,SAAS,KAAK;AACjC,aAAO,KAAK,KAAK,IAAI,CAAC,MAAM,EAAE,EAAE;AAAA,IAClC,QAAQ;AACN,aAAO,CAAC;AAAA,IACV;AAAA,EACF;AACF;","names":[]}

package/dist/{chunk-2YBUL3IL.js → chunk-4WL5X7VS.js}

@@ -2,10 +2,10 @@ import { createRequire as __cr } from 'node:module'; const require = __cr(import
 import {
   LmStudioBackend,
   OllamaBackend
-} from "./chunk-QGJ2ZIUZ.js";
+} from "./chunk-25FY74AP.js";
 import {
   AgentRegistry
-} from "./chunk-5QWZT4AB.js";
+} from "./chunk-RNWALAFP.js";
 
 // src/cli/shared.ts
 import fs from "fs";
@@ -83,4 +83,4 @@ export {
   VAULT_GITIGNORE,
   configureVaultEnv
 };
-//# sourceMappingURL=chunk-2YBUL3IL.js.map
+//# sourceMappingURL=chunk-4WL5X7VS.js.map