@goondocks/myco 0.4.3 → 0.4.4

package/skills/setup/references/model-recommendations.md

@@ -1,60 +1,79 @@
 # Model Recommendations
 
-Hardware-based guidance for choosing intelligence and embedding models during Myco setup.
+Hardware-based guidance for choosing models during Myco setup. Myco uses three model tiers that load simultaneously in Ollama.
 
-## Intelligence Model (LLM)
+## Three-Tier Architecture
 
-One model handles all intelligence tasks — hooks, extraction, summaries, and digest. Size for digestion, the most demanding task (largest context window). The same model runs at 8192 context for hooks and at the digest context window below for synthesis.
+| Tier | Purpose | Speed vs Quality |
+|------|---------|-----------------|
+| **Embedding** | Vector search, semantic similarity | Dedicated small model, always loaded |
+| **Processor** | Extraction, summarization, titles, classification | Speed matters — fast model, 8K context |
+| **Digest** | Synthesize vault knowledge into tiered extracts | Quality matters — large model, up to 65K context |
 
-| RAM | Recommended Model | Digest Context Window |
-|-----|-------------------|-----------------------|
-| **64GB+** | `qwen3.5:35b` (MoE, recommended) | 65536 |
-| **32–64GB** | `qwen3.5:27b` | 32768 |
-| **16–32GB** | `qwen3.5:latest` (~10B) | 16384 |
-| **8–16GB** | `qwen3.5:4b` | 8192 |
+The processor and digest can be the same model on smaller machines. On larger machines, splitting them gives the best speed/quality balance — processor tasks complete in seconds instead of minutes.
+
+## Recommended Configurations
+
+| RAM | Processor Model | Digest Model | Digest Context | Inject Tier | Est. VRAM |
+|-----|----------------|--------------|----------------|-------------|-----------|
+| **64GB+** | `qwen3.5:latest` (~8B) | `qwen3.5:35b` (MoE) | 65536 | 3000 | ~35GB |
+| **48GB** | `qwen3.5:latest` (~8B) | `qwen3.5:27b` | 32768 | 3000 | ~26GB |
+| **32GB** | `qwen3.5:4b` | `qwen3.5:latest` (~8B) | 16384 | 1500 | ~11GB |
+| **16GB** | `qwen3.5:4b` | `qwen3.5:4b` | 8192 | 1500 | ~6GB |
+
+Embedding model (`bge-m3`, ~1.3GB) is included in all VRAM estimates.
+
+When processor and digest use the same model (16GB tier), Ollama loads it once — no extra VRAM.
 
 ### Why Qwen 3.5?
 
 Qwen 3.5 models offer strong instruction-following and synthesis quality on local hardware. The MoE variant (`35b`) runs efficiently on 64GB+ systems because only a subset of parameters activate per token. Any instruction-tuned model that handles JSON output works — prefer what the user already has loaded, but recommend Qwen 3.5 for new setups.
 
-### Pulling Models
+### Important: Reasoning Token Suppression
+
+Qwen 3.5 models are reasoning models that generate `<think>` tokens before output. Myco automatically suppresses this via `reasoning: 'off'` on all LLM calls. No user configuration needed — this is handled in code via the `LLM_REASONING_MODE` constant.
+
+### Ollama Performance Settings
+
+Recommend users add these to their Ollama service configuration for best performance:
+
+```
+OLLAMA_FLASH_ATTENTION=1    # Required for KV cache quantization
+OLLAMA_KV_CACHE_TYPE=q8_0   # Halves KV cache memory — makes large digest context affordable
+```
+
+These are system-wide Ollama settings (launchd plist on macOS, systemd on Linux), not Myco-controlled.
+
+## Pulling Models
 
 **Ollama:**
 ```bash
-ollama pull qwen3.5         # pulls latest tag (~10B)
 ollama pull qwen3.5:4b      # 4B variant
-ollama pull qwen3.5:27b     # 27B variant
+ollama pull qwen3.5:latest  # latest variant (~8B)
 ollama pull qwen3.5:35b     # 35B MoE variant
+ollama pull bge-m3          # embedding model
 ```
 
-**LM Studio:** Search for `qwen3.5` in the model browser. Download the variant matching the RAM tier above.
+**LM Studio:** Search for `qwen3.5` in the model browser. Download the variants matching the RAM tier above.
 
 ## Embedding Model
 
-Embedding models are separate from the intelligence model. Anthropic does not support embeddings — only Ollama and LM Studio provide embedding models.
+Separate from the intelligence models. Anthropic does not support embeddings — only Ollama and LM Studio provide embedding models.
 
-Recommended embedding models:
+Recommended:
 - `bge-m3` — strong multilingual embeddings, good default
 - `nomic-embed-text` — lightweight alternative
 
-**Ollama:**
-```bash
-ollama pull bge-m3
-ollama pull nomic-embed-text
-```
-
-**LM Studio:** Filter the model list for names containing `text-embedding`. If none are available, search for and download an embedding model through the model browser.
-
 ## Inject Tier
 
-Controls how much pre-computed context the agent receives at session start. Agents can always request a different tier on-demand via the `myco_context` MCP tool.
+Controls how much pre-computed context the agent receives at session start. All tiers are available regardless of local hardware — the local LLM can generate any tier. The default should be based on the **coding agent's context window**, not the local model.
 
-| RAM | Available Tiers | Default |
-|-----|-----------------|---------|
-| **64GB+** | 1500, 3000, 5000, 10000 | 3000 |
-| **32–64GB** | 1500, 3000, 5000 | 3000 |
-| **16–32GB** | 1500, 3000 | 1500 |
-| **8–16GB** | 1500 | 1500 |
+| Agent Context Window | Default Tier | Rationale |
+|---------------------|-------------|-----------|
+| **1M+** (Opus 4.6) | 10000 | Rich context is cheap relative to the window |
+| **200K** (Sonnet 4.6, Gemini) | 5000 | Good depth without crowding the agent's context |
+| **128K** (GPT-4o, smaller models) | 3000 | Balanced — enough for key decisions and recent activity |
+| **32K or less** | 1500 | Executive briefing only — preserve context for the task |
 
 ### Tier Descriptions
 
@@ -62,16 +81,3 @@ Controls how much pre-computed context the agent receives at session start. Agen
 - **3000** — team standup (recommended for most setups)
 - **5000** — deep onboarding
 - **10000** — institutional knowledge (richest, most context)
-
-## Advanced: Separate Digestion Model
-
-The guided setup configures one intelligence model for all tasks. Power users who want a separate, larger model specifically for digest can configure it via CLI:
-
-```bash
-node ${CLAUDE_PLUGIN_ROOT}/dist/src/cli.js setup-digest \
-  --provider lm-studio \
-  --model "qwen/qwen3.5-35b-a3b" \
-  --context-window 65536
-```
-
-This is not exposed in the guided setup to avoid resource exhaustion from running two large models simultaneously.

package/dist/chunk-67R6EMYD.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/intelligence/ollama.ts","../src/intelligence/lm-studio.ts"],"sourcesContent":["import type { LlmProvider, EmbeddingProvider, LlmResponse, EmbeddingResponse, LlmRequestOptions } from './llm.js';\nimport { estimateTokens, 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 contextWindow: number;\n  private defaultMaxTokens: number;\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.contextWindow = config?.context_window ?? 8192;\n    this.defaultMaxTokens = config?.max_tokens ?? 1024;\n  }\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    const promptTokens = estimateTokens(prompt);\n    const numCtx = Math.max(promptTokens + maxTokens, contextLength);\n\n    const body: Record<string, unknown> = {\n      model: this.model,\n      prompt,\n      stream: false,\n      options: {\n        num_ctx: numCtx,\n        num_predict: maxTokens,\n      },\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} ${errorBody.slice(0, 500)}`);\n    }\n\n    const data = await response.json() as { response: string; model: string };\n    return { text: data.response, model: data.model };\n  }\n\n  async embed(text: string): Promise<EmbeddingResponse> {\n    const response = await fetch(`${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_UNLOAD = '/api/v1/models/unload';\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. */\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 loadedInstanceId: 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   * Supports per-request context_length, reasoning control, and system_prompt.\n   */\n  async summarize(prompt: string, opts?: LlmRequestOptions): Promise<LlmResponse> {\n    const maxTokens = opts?.maxTokens ?? this.defaultMaxTokens;\n\n    const body: Record<string, unknown> = {\n      model: this.loadedInstanceId ?? this.model,\n      input: prompt,\n      max_output_tokens: maxTokens,\n      store: false,\n    };\n\n    // Only set context_length if we haven't pre-loaded the model\n    // (pre-loaded models already have the correct context via ensureLoaded)\n    if (!this.loadedInstanceId) {\n      const contextLength = opts?.contextLength ?? this.contextWindow;\n      if (contextLength) {\n        body.context_length = contextLength;\n      }\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      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: ${response.status}`);\n    }\n\n    const data = await response.json() as {\n      data: Array<{ embedding: number[] }>;\n      model: string;\n    };\n    const embedding = data.data[0].embedding;\n    return { embedding, model: data.model, dimensions: embedding.length };\n  }\n\n  /**\n   * Ensure a model instance is loaded with the desired settings.\n   * First checks for an existing compatible instance to reuse (prevents\n   * accumulation across daemon restarts), then loads a new one only if needed.\n   * Unloads incompatible instances of the same model to prevent resource exhaustion.\n   */\n  async ensureLoaded(contextLength?: number, gpuKvCache?: boolean): Promise<void> {\n    const ctx = contextLength ?? this.contextWindow;\n    const kvCache = gpuKvCache ?? false;\n\n    // Query native API for existing loaded instances of this model\n    const instances = await this.getLoadedInstances();\n\n    // Check for a compatible instance we can reuse\n    for (const instance of instances) {\n      const matchesContext = !ctx || instance.config.context_length === ctx;\n      const matchesKvCache = instance.config.offload_kv_cache_to_gpu === kvCache;\n      if (matchesContext && matchesKvCache) {\n        this.loadedInstanceId = instance.id;\n        // Unload any incompatible instances (best effort, don't block on failure)\n        await this.unloadIncompatibleInstances(instances, ctx, kvCache);\n        return;\n      }\n    }\n\n    // Unload incompatible instances before loading to free resources\n    await this.unloadIncompatibleInstances(instances, ctx, kvCache);\n\n    // No compatible instance found — load a new one\n    const body: Record<string, unknown> = {\n      model: this.model,\n      flash_attention: true,\n      offload_kv_cache_to_gpu: kvCache,\n    };\n    if (ctx) {\n      body.context_length = ctx;\n    }\n\n    const response = await fetch(`${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} ${errorBody.slice(0, 200)}`);\n    }\n\n    // Capture instance ID — LM Studio may return it under different field names\n    const loadResult = await response.json() as Record<string, unknown>;\n    const instanceId = (loadResult.id ?? loadResult.instance_id ?? loadResult.model_instance_id) as string | undefined;\n    if (instanceId) {\n      this.loadedInstanceId = instanceId;\n    }\n  }\n\n  /**\n   * Query the LM Studio native API for loaded instances of this model.\n   * Returns an empty array if the API is unavailable or the model has no loaded instances.\n   */\n  private async getLoadedInstances(): Promise<NativeLoadedInstance[]> {\n    try {\n      const response = await fetch(`${this.baseUrl}${ENDPOINT_MODELS_NATIVE}`, {\n        signal: AbortSignal.timeout(DAEMON_CLIENT_TIMEOUT_MS),\n      });\n      if (!response.ok) return [];\n\n      const data = await response.json() as { models: NativeModelEntry[] };\n      const entry = data.models.find((m) => m.key === this.model);\n      return entry?.loaded_instances ?? [];\n    } catch {\n      return [];\n    }\n  }\n\n  /**\n   * Unload instances of this model that don't match the desired settings.\n   * Best-effort — failures are silently ignored to avoid blocking the load path.\n   */\n  private async unloadIncompatibleInstances(\n    instances: NativeLoadedInstance[],\n    contextLength: number | undefined,\n    gpuKvCache: boolean,\n  ): Promise<void> {\n    for (const instance of instances) {\n      const matchesContext = !contextLength || instance.config.context_length === contextLength;\n      const matchesKvCache = instance.config.offload_kv_cache_to_gpu === gpuKvCache;\n      if (!matchesContext || !matchesKvCache) {\n        try {\n          await fetch(`${this.baseUrl}${ENDPOINT_MODELS_UNLOAD}`, {\n            method: 'POST',\n            headers: { 'Content-Type': 'application/json' },\n            body: JSON.stringify({ model: instance.id }),\n            signal: AbortSignal.timeout(DAEMON_CLIENT_TIMEOUT_MS),\n          });\n        } catch {\n          // Best effort — don't fail the load if cleanup fails\n        }\n      }\n    }\n  }\n\n  async isAvailable(): Promise<boolean> {\n    try {\n      const response = await fetch(`${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,gBAAgB,QAAQ,kBAAkB;AAC/C,SAAK,mBAAmB,QAAQ,cAAc;AAAA,EAChD;AAAA,EAEA,MAAM,UAAU,QAAgB,MAAgD;AAC9E,UAAM,YAAY,MAAM,aAAa,KAAK;AAC1C,UAAM,gBAAgB,MAAM,iBAAiB,KAAK;AAClD,UAAM,eAAe,eAAe,MAAM;AAC1C,UAAM,SAAS,KAAK,IAAI,eAAe,WAAW,aAAa;AAE/D,UAAM,OAAgC;AAAA,MACpC,OAAO,KAAK;AAAA,MACZ;AAAA,MACA,QAAQ;AAAA,MACR,SAAS;AAAA,QACP,SAAS;AAAA,QACT,aAAa;AAAA,MACf;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,UAAM,OAAO,MAAM,SAAS,KAAK;AACjC,WAAO,EAAE,MAAM,KAAK,UAAU,OAAO,KAAK,MAAM;AAAA,EAClD;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;;;AC7GA,IAAM,gBAAgB;AACtB,IAAM,uBAAuB;AAC7B,IAAM,yBAAyB;AAC/B,IAAM,uBAAuB;AAC7B,IAAM,yBAAyB;AAC/B,IAAM,sBAAsB;AAmBrB,IAAM,kBAAN,MAAM,iBAA0D;AAAA,EACrE,OAAgB,mBAAmB;AAAA,EAC1B,OAAO;AAAA,EACR;AAAA,EACA;AAAA,EACA,mBAAkC;AAAA,EAClC;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,EAMA,MAAM,UAAU,QAAgB,MAAgD;AAC9E,UAAM,YAAY,MAAM,aAAa,KAAK;AAE1C,UAAM,OAAgC;AAAA,MACpC,OAAO,KAAK,oBAAoB,KAAK;AAAA,MACrC,OAAO;AAAA,MACP,mBAAmB;AAAA,MACnB,OAAO;AAAA,IACT;AAIA,QAAI,CAAC,KAAK,kBAAkB;AAC1B,YAAM,gBAAgB,MAAM,iBAAiB,KAAK;AAClD,UAAI,eAAe;AACjB,aAAK,iBAAiB;AAAA,MACxB;AAAA,IACF;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;AACtD,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,EAQA,MAAM,aAAa,eAAwB,YAAqC;AAC9E,UAAM,MAAM,iBAAiB,KAAK;AAClC,UAAM,UAAU,cAAc;AAG9B,UAAM,YAAY,MAAM,KAAK,mBAAmB;AAGhD,eAAW,YAAY,WAAW;AAChC,YAAM,iBAAiB,CAAC,OAAO,SAAS,OAAO,mBAAmB;AAClE,YAAM,iBAAiB,SAAS,OAAO,4BAA4B;AACnE,UAAI,kBAAkB,gBAAgB;AACpC,aAAK,mBAAmB,SAAS;AAEjC,cAAM,KAAK,4BAA4B,WAAW,KAAK,OAAO;AAC9D;AAAA,MACF;AAAA,IACF;AAGA,UAAM,KAAK,4BAA4B,WAAW,KAAK,OAAO;AAG9D,UAAM,OAAgC;AAAA,MACpC,OAAO,KAAK;AAAA,MACZ,iBAAiB;AAAA,MACjB,yBAAyB;AAAA,IAC3B;AACA,QAAI,KAAK;AACP,WAAK,iBAAiB;AAAA,IACxB;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;AAGA,UAAM,aAAa,MAAM,SAAS,KAAK;AACvC,UAAM,aAAc,WAAW,MAAM,WAAW,eAAe,WAAW;AAC1E,QAAI,YAAY;AACd,WAAK,mBAAmB;AAAA,IAC1B;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;AAAA;AAAA;AAAA;AAAA,EAMA,MAAc,4BACZ,WACA,eACA,YACe;AACf,eAAW,YAAY,WAAW;AAChC,YAAM,iBAAiB,CAAC,iBAAiB,SAAS,OAAO,mBAAmB;AAC5E,YAAM,iBAAiB,SAAS,OAAO,4BAA4B;AACnE,UAAI,CAAC,kBAAkB,CAAC,gBAAgB;AACtC,YAAI;AACF,gBAAM,MAAM,GAAG,KAAK,OAAO,GAAG,sBAAsB,IAAI;AAAA,YACtD,QAAQ;AAAA,YACR,SAAS,EAAE,gBAAgB,mBAAmB;AAAA,YAC9C,MAAM,KAAK,UAAU,EAAE,OAAO,SAAS,GAAG,CAAC;AAAA,YAC3C,QAAQ,YAAY,QAAQ,wBAAwB;AAAA,UACtD,CAAC;AAAA,QACH,QAAQ;AAAA,QAER;AAAA,MACF;AAAA,IACF;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":[]}