// Model capabilities — what each model can read/do beyond plain text.
//
// Fallback order (first match wins), result merged over DEFAULT_CAPABILITIES:
//   1. PROVIDER_CAPABILITIES[provider][model]  — provider-specific override
//   2. MODEL_CAPABILITIES[model]               — canonical exact id (handles exceptions)
//   3. PATTERN_CAPABILITIES                     — glob match, ordered specific -> generic
//   4. DEFAULT_CAPABILITIES                     — safe floor (always returned)
//
// ── HOW TO ADD / UPDATE A MODEL ──────────────────────────────────────
// Authoritative data source: https://models.dev/api.json (145 providers, 4000+
// models, MIT). Each model exposes the exact fields we map below:
//   modalities.input  ["text","image","pdf","audio","video"] -> vision / pdf / audioInput / videoInput
//   modalities.output ["text","image","audio"]               -> imageOutput / audioOutput
//   reasoning   -> reasoning      tool_call    -> tools
//   limit.context -> contextWindow   limit.output -> maxOutput
// Look up the model id, then:
//   • If a PATTERN below already covers it correctly -> nothing to do.
//   • If it is an exception (pattern would mis-match) -> add an exact entry to
//     MODEL_CAPABILITIES (only the fields that differ from DEFAULT).
//   • If a whole new family -> add an ordered PATTERN (specific before generic).
// NOTE: models.dev has NO "search" flag (web search is a runtime tool, not a
// model spec); set `search` from vendor docs (Claude 4.x+, GPT-5.x/4o, Gemini
// 2.0+, Grok, Perplexity). Verify with: curl -s https://models.dev/api.json

import { matchPattern } from "./pricing.js";

/**
 * Safe floor — every resolved result is merged over this so consumers
 * never need null-checks. Most modern LLMs meet these limits.
 */
export const DEFAULT_CAPABILITIES = {
  // input modalities
  vision: false,        // read images
  pdf: false,           // read PDF / documents
  audioInput: false,    // read audio
  videoInput: false,    // read video
  // output modalities
  imageOutput: false,   // generate images
  audioOutput: false,   // generate audio
  // features
  search: false,        // built-in web search tool / grounding
  tools: true,          // function / tool calling
  reasoning: false,     // thinking / reasoning
  // thinking wire format (only meaningful when reasoning:true). null → derive from transport.format.
  // enum: openai|claude-adaptive|claude-budget|gemini-level|gemini-budget|zai|qwen|deepseek|kimi|minimax|hunyuan|step
  thinkingFormat: null,
  thinkingCanDisable: true,  // false → model cannot turn thinking off (clamp to min instead of disable)
  thinkingRange: null,       // { min, max } for budget formats; null = no clamp
  // limits (tokens)
  contextWindow: 200000,
  maxOutput: 64000,
};

// User-added model metadata can carry dashboard service kinds instead of the
// runtime capability names used here. Map those typed model kinds into input /
// output capabilities so custom vision models are not treated as text-only.
const SERVICE_KIND_CAPABILITIES = {
  imageToText: { vision: true },
  image: { imageOutput: true },
  stt: { audioInput: true },
  tts: { audioOutput: true },
  embedding: { tools: false },
};

export function capabilitiesFromServiceKind(kind) {
  return SERVICE_KIND_CAPABILITIES[kind] || null;
}

/**
 * Canonical exact-id overrides — used for exceptions that patterns would
 * otherwise mis-match. Only declare deltas vs DEFAULT.
 */
export const MODEL_CAPABILITIES = {
  // Claude 4.6/4.7 have 1M context + adaptive thinking (override generic claude pattern)
  "claude-opus-4.6":   { vision: true, reasoning: true, search: true, thinkingFormat: "claude-adaptive", contextWindow: 1000000, maxOutput: 128000 },
  "claude-opus-4.7":   { vision: true, reasoning: true, search: true, thinkingFormat: "claude-adaptive", contextWindow: 1000000, maxOutput: 128000 },
  "claude-opus-4-6":   { vision: true, reasoning: true, search: true, thinkingFormat: "claude-adaptive", contextWindow: 1000000, maxOutput: 128000 },
  "claude-sonnet-4.6": { vision: true, reasoning: true, search: true, thinkingFormat: "claude-adaptive", contextWindow: 1000000, maxOutput: 64000 },
  "claude-sonnet-4-6": { vision: true, reasoning: true, search: true, thinkingFormat: "claude-adaptive", contextWindow: 1000000, maxOutput: 64000 },

  // Gemini image-gen / OpenAI image / xai image variants
  "gpt-image-1":       { imageOutput: true, tools: false },

  // GLM vision variant (text GLM has no vision)
  "glm-4.6v":          { vision: true, reasoning: true, thinkingFormat: "zai", contextWindow: 128000 },

  // Qwen plain coder/text (no vision) — registry "vision-model" / "coder-model" aliases
  "vision-model":      { vision: true, reasoning: true, thinkingFormat: "qwen", contextWindow: 1000000 },
  "coder-model":       { reasoning: true, thinkingFormat: "qwen", contextWindow: 1000000 },
};

/**
 * Provider-specific capability overrides. Keyed by provider alias/id.
 */
export const PROVIDER_CAPABILITIES = {
  // CodeBuddy.cn — authoritative per-model metadata from the gateway's model
  // config (contextWindow=maxInputTokens, maxOutput=maxOutputTokens, vision=
  // supportsImages). Every model reasons via OpenAI-style reasoning_effort
  // (see registry thinkingFormat). `onlyReasoning` models can't turn thinking
  // off → thinkingCanDisable:false (clamped to minimal instead of disabled).
  "codebuddy-cn": {
    "glm-5.2":            { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 48000 },
    "glm-5.1":            { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 48000 },
    "glm-5.0":            { reasoning: true, thinkingFormat: "openai", contextWindow: 200000, maxOutput: 48000 },
    "glm-5.0-turbo":      { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 48000 },
    "glm-5v-turbo":       { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 38000 },
    "glm-4.7":            { reasoning: true, thinkingFormat: "openai", contextWindow: 200000, maxOutput: 48000 },
    "minimax-m3":         { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 512000, maxOutput: 48000 },
    "minimax-m2.7":       { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 48000 },
    "kimi-k2.7":          { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 256000, maxOutput: 32000 },
    "kimi-k2.6":          { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 256000, maxOutput: 32000 },
    "kimi-k2.5":          { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 164000, maxOutput: 32000 },
    "hy3-preview":        { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 192000, maxOutput: 64000 },
    "deepseek-v4-pro":    { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 50000 },
    "deepseek-v4-flash":  { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 50000 },
    "deepseek-v3-2-volc": { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 96000, maxOutput: 32000 },
  },
};

/**
 * Pattern fallback — glob (* = wildcard), matched case-insensitively and
 * anchored (^...$) so a pattern must match the full model id. ORDER MATTERS:
 * vision/specific variants first, text-only/generic families last, to avoid
 * a broad family pattern swallowing an exception (e.g. glm-4.6v vs glm-5).
 */
export const PATTERN_CAPABILITIES = [
  // ── Claude (4.6+ = adaptive thinking; older/haiku = budget) ──────
  { pattern: "*claude*opus-4.6*",   caps: { vision: true, reasoning: true, search: true, thinkingFormat: "claude-adaptive" } },
  { pattern: "*claude*opus-4.7*",   caps: { vision: true, reasoning: true, search: true, thinkingFormat: "claude-adaptive" } },
  { pattern: "*claude*opus-4.8*",   caps: { vision: true, reasoning: true, search: true, thinkingFormat: "claude-adaptive" } },
  { pattern: "*claude*sonnet-4.6*", caps: { vision: true, reasoning: true, search: true, thinkingFormat: "claude-adaptive" } },
  { pattern: "*claude*sonnet-4.7*", caps: { vision: true, reasoning: true, search: true, thinkingFormat: "claude-adaptive" } },
  { pattern: "*claude*haiku*",  caps: { vision: true, reasoning: true, search: true, thinkingFormat: "claude-budget" } },
  { pattern: "*claude*opus*",   caps: { vision: true, reasoning: true, search: true, thinkingFormat: "claude-budget" } },
  { pattern: "*claude*sonnet*", caps: { vision: true, reasoning: true, search: true, thinkingFormat: "claude-budget" } },
  { pattern: "*claude*fable*",  caps: { vision: true, reasoning: true, search: true, thinkingFormat: "claude-budget", contextWindow: 1000000, maxOutput: 128000 } },
  { pattern: "*claude*mythos*", caps: { vision: true, reasoning: true, search: true, thinkingFormat: "claude-budget", contextWindow: 1000000, maxOutput: 128000 } },
  { pattern: "*claude-3*",      caps: { vision: true } },
  { pattern: "*claude*",        caps: { vision: true, reasoning: true, search: true, thinkingFormat: "claude-budget" } },

  // ── Gemini (all 2.0+ multimodal + google_search grounding, 1M ctx) ─
  { pattern: "*gemini*image*",  caps: { vision: true, imageOutput: true, contextWindow: 1048576 } },
  { pattern: "*gemini-3*pro*",  caps: { vision: true, audioInput: true, videoInput: true, reasoning: true, search: true, thinkingFormat: "gemini-level", thinkingCanDisable: false, contextWindow: 1048576, maxOutput: 65535 } },
  { pattern: "*gemini-3*",      caps: { vision: true, audioInput: true, videoInput: true, reasoning: true, search: true, thinkingFormat: "gemini-level", thinkingCanDisable: false, contextWindow: 1048576, maxOutput: 65536 } },
  { pattern: "*gemini-2.5*",    caps: { vision: true, audioInput: true, videoInput: true, reasoning: true, search: true, thinkingFormat: "gemini-budget", thinkingRange: { min: 0, max: 24576 }, contextWindow: 1048576, maxOutput: 65536 } },
  { pattern: "*gemini-2*",      caps: { vision: true, audioInput: true, videoInput: true, search: true, contextWindow: 1048576, maxOutput: 65536 } },
  { pattern: "*gemini*",        caps: { vision: true, search: true, contextWindow: 1048576 } },
  { pattern: "*gemma*",         caps: { vision: true, contextWindow: 128000 } },
  { pattern: "*nanobanana*",    caps: { vision: true, imageOutput: true } },

  // ── OpenAI GPT-5.x (vision + thinking + web search) ──────────────
  { pattern: "*gpt-5*image*",   caps: { imageOutput: true } },
  { pattern: "*gpt-5*codex*",   caps: { reasoning: true, search: true, thinkingFormat: "openai", contextWindow: 400000, maxOutput: 128000 } },
  { pattern: "*gpt-5*",         caps: { vision: true, reasoning: true, search: true, thinkingFormat: "openai", contextWindow: 400000, maxOutput: 128000 } },
  { pattern: "*gpt-4o*",        caps: { vision: true, search: true, contextWindow: 128000, maxOutput: 16384 } },
  { pattern: "*gpt-4.1*",       caps: { vision: true, contextWindow: 1000000, maxOutput: 32768 } },
  { pattern: "*gpt-4-turbo*",   caps: { vision: true, contextWindow: 128000 } },
  { pattern: "*gpt-4*",         caps: { contextWindow: 128000 } },
  { pattern: "*gpt-3.5*",       caps: { contextWindow: 16385, maxOutput: 4096 } },
  { pattern: "*gpt-oss*",       caps: { reasoning: true, thinkingFormat: "openai", contextWindow: 128000 } },

  // ── OpenAI o-series (reasoning, vision) ──────────────────────────
  { pattern: "*o1-mini*",       caps: { reasoning: true, thinkingFormat: "openai", contextWindow: 128000 } },
  { pattern: "*o1*",            caps: { vision: true, reasoning: true, thinkingFormat: "openai", contextWindow: 200000, maxOutput: 100000 } },
  { pattern: "*o3*",            caps: { vision: true, reasoning: true, thinkingFormat: "openai", contextWindow: 200000, maxOutput: 100000 } },
  { pattern: "*o4*",            caps: { vision: true, reasoning: true, thinkingFormat: "openai", contextWindow: 200000, maxOutput: 100000 } },

  // ── Grok (vision + Live Search) ──────────────────────────────────
  { pattern: "*grok*image*",    caps: { imageOutput: true } },
  { pattern: "*grok-code*",     caps: { reasoning: true, thinkingFormat: "openai", contextWindow: 256000 } },
  { pattern: "*grok-4*",        caps: { vision: true, reasoning: true, search: true, thinkingFormat: "openai", contextWindow: 256000 } },
  { pattern: "*grok-3*",        caps: { vision: true, reasoning: true, search: true, thinkingFormat: "openai", contextWindow: 131072 } },
  { pattern: "*grok*",          caps: { vision: true, reasoning: true, search: true, thinkingFormat: "openai", contextWindow: 256000 } },

  // ── Qwen (enable_thinking + thinking_budget; QwQ = thinking-only) ─
  { pattern: "*qwen*vl*",       caps: { vision: true, reasoning: true, thinkingFormat: "qwen", contextWindow: 262144 } },
  { pattern: "*qwen*max*",      caps: { vision: true, reasoning: true, thinkingFormat: "qwen", contextWindow: 1000000, maxOutput: 65536 } },
  { pattern: "*qwen*plus*",     caps: { vision: true, reasoning: true, thinkingFormat: "qwen", contextWindow: 1000000, maxOutput: 65536 } },
  { pattern: "*qwen*235b*",     caps: { reasoning: true, thinkingFormat: "qwen", contextWindow: 262144 } },
  { pattern: "*qwen*coder*",    caps: { reasoning: true, thinkingFormat: "qwen", contextWindow: 1000000 } },
  { pattern: "*qwq*",           caps: { reasoning: true, thinkingFormat: "qwen", thinkingCanDisable: false, contextWindow: 131072 } },
  { pattern: "*qwen*",          caps: { reasoning: true, thinkingFormat: "qwen", contextWindow: 262144 } },

  // ── Kimi (enabled→reasoning_effort; K2.7-code cannot disable) ─────
  { pattern: "*kimi*k2.7*code*", caps: { vision: true, reasoning: true, thinkingFormat: "kimi", thinkingCanDisable: false, contextWindow: 262144, maxOutput: 262144 } },
  { pattern: "*kimi*k2*",       caps: { vision: true, reasoning: true, thinkingFormat: "kimi", contextWindow: 262144, maxOutput: 262144 } },
  { pattern: "*kimi*",          caps: { reasoning: true, thinkingFormat: "kimi", contextWindow: 262144 } },

  // ── GLM / Z.ai (thinking.enabled; disable via enable_thinking:false) ─
  { pattern: "*glm-5*",         caps: { reasoning: true, thinkingFormat: "zai", contextWindow: 200000, maxOutput: 128000 } },
  { pattern: "*glm-4.7*",       caps: { reasoning: true, thinkingFormat: "zai", contextWindow: 200000, maxOutput: 128000 } },
  { pattern: "*glm-4*",         caps: { reasoning: true, thinkingFormat: "zai", contextWindow: 200000 } },
  { pattern: "*glm*",           caps: { reasoning: true, thinkingFormat: "zai", contextWindow: 200000 } },

  // ── DeepSeek (thinking.enabled + reasoning_effort; r1 = thinking-only) ─
  { pattern: "*deepseek-v4*",   caps: { reasoning: true, thinkingFormat: "deepseek", contextWindow: 1000000, maxOutput: 384000 } },
  { pattern: "*reasoner*",      caps: { reasoning: true, thinkingFormat: "deepseek", thinkingCanDisable: false, contextWindow: 128000 } },
  { pattern: "*deepseek-r*",    caps: { reasoning: true, thinkingFormat: "deepseek", thinkingCanDisable: false, contextWindow: 128000 } },
  { pattern: "*deepseek-chat*", caps: { contextWindow: 128000 } },
  { pattern: "*deepseek*",      caps: { reasoning: true, thinkingFormat: "deepseek", contextWindow: 128000 } },

  // ── MiniMax (M3 = adaptive; M2.x cannot disable) ─────────────────
  { pattern: "*minimax*image*", caps: { imageOutput: true } },
  { pattern: "*minimax-m3*",    caps: { vision: true, reasoning: true, thinkingFormat: "minimax", contextWindow: 1048576, maxOutput: 512000 } },
  { pattern: "*minimax-m2.7*",  caps: { reasoning: true, thinkingFormat: "minimax", thinkingCanDisable: false, contextWindow: 204800, maxOutput: 131072 } },
  { pattern: "*minimax*",       caps: { reasoning: true, thinkingFormat: "minimax", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 131072 } },

  // ── Xiaomi MiMo (vision, 1M / 262K ctx) ──────────────────────────
  { pattern: "*mimo*v2.5*",     caps: { vision: true, contextWindow: 1048576, maxOutput: 131072 } },
  { pattern: "*mimo*omni*",     caps: { vision: true, audioInput: true, contextWindow: 262144, maxOutput: 131072 } },
  { pattern: "*mimo*",          caps: { vision: true, contextWindow: 262144, maxOutput: 131072 } },

  // ── Llama (4 = vision/1M; 3.x = text-only/128K) ──────────────────
  { pattern: "*llama-4*",       caps: { vision: true, contextWindow: 1000000 } },
  { pattern: "*llama*",         caps: { contextWindow: 128000 } },

  // ── Mistral (Large 3 = vision/256K; codestral text) ──────────────
  { pattern: "*codestral*",     caps: { contextWindow: 256000 } },
  { pattern: "*mistral-large*", caps: { vision: true, contextWindow: 256000 } },
  { pattern: "*mistral*",       caps: { contextWindow: 128000 } },

  // ── Cohere (Command A Vision = vision; others text) ──────────────
  { pattern: "*command-a-vision*", caps: { vision: true, contextWindow: 128000 } },
  { pattern: "*command*",       caps: { contextWindow: 128000 } },

  // ── Perplexity (web search native) ───────────────────────────────
  { pattern: "*sonar*",         caps: { search: true, contextWindow: 128000 } },
  { pattern: "*pplx*",          caps: { search: true, contextWindow: 128000 } },
  { pattern: "*perplexity*",    caps: { search: true, contextWindow: 128000 } },

  // ── Others ───────────────────────────────────────────────────────
  { pattern: "*hunyuan*",       caps: { reasoning: true, thinkingFormat: "hunyuan", contextWindow: 262144, maxOutput: 262144 } },
  { pattern: "hy3*",            caps: { reasoning: true, thinkingFormat: "hunyuan", contextWindow: 262144, maxOutput: 262144 } },
  { pattern: "*step-*",         caps: { reasoning: true, thinkingFormat: "step", contextWindow: 128000 } },
  { pattern: "*nemotron*",      caps: { reasoning: true, contextWindow: 128000 } },
  { pattern: "*ling-*",         caps: { reasoning: true, contextWindow: 128000 } },
];

/**
 * Resolve capabilities for a model using the 4-step fallback chain,
 * merged over DEFAULT_CAPABILITIES so the result is always complete.
 *
 * @param {string} provider
 * @param {string} model
 * @returns {object} full capabilities object
 */
export function getCapabilitiesForModel(provider, model) {
  if (!model) return { ...DEFAULT_CAPABILITIES };

  // 1. Provider-specific override
  if (provider && PROVIDER_CAPABILITIES[provider]?.[model]) {
    return { ...DEFAULT_CAPABILITIES, ...PROVIDER_CAPABILITIES[provider][model] };
  }

  // 2. Canonical exact (strip vendor prefix: "anthropic/claude-opus-4.7" -> "claude-opus-4.7")
  const baseModel = model.includes("/") ? model.split("/").pop() : model;
  if (MODEL_CAPABILITIES[baseModel]) return { ...DEFAULT_CAPABILITIES, ...MODEL_CAPABILITIES[baseModel] };
  if (MODEL_CAPABILITIES[model]) return { ...DEFAULT_CAPABILITIES, ...MODEL_CAPABILITIES[model] };

  // 3. Pattern match (first match wins)
  for (const { pattern, caps } of PATTERN_CAPABILITIES) {
    if (matchPattern(pattern, baseModel) || matchPattern(pattern, model)) {
      return { ...DEFAULT_CAPABILITIES, ...caps };
    }
  }

  // 4. Floor
  return { ...DEFAULT_CAPABILITIES };
}