import fs from "node:fs";
import path from "node:path";
import { fileURLToPath } from "node:url";
import {
  calculateStringSimilarity,
  loadContextTreeDocuments,
  mergeSearchResults,
} from "../utils.js";
import { askOpenAI } from "./llm.js";

const __dirname = path.dirname(fileURLToPath(import.meta.url));

async function fetchJson(url, options = {}) {
  const response = await fetch(url, options);
  const text = await response.text();
  let payload;

  try {
    payload = text ? JSON.parse(text) : undefined;
  } catch (error) {
    throw new Error(`Invalid JSON response from ${url}`);
  }

  if (!response.ok) {
    const message =
      payload?.error?.message ||
      payload?.message ||
      `Request failed with status ${response.status}`;
    const error = new Error(message);
    error.status = response.status;
    error.payload = payload ?? text;
    throw error;
  }

  return payload;
}

function loadConfig() {
  const dataDir = process.env.DATA_DIR || "/data";
  const configPath = path.join(dataDir, "config.json");
  const raw = fs.readFileSync(configPath, "utf8");
  return JSON.parse(raw);
}

function extractEmbedding(payload) {
  if (Array.isArray(payload?.embedding)) {
    return payload.embedding;
  }
  if (Array.isArray(payload?.embeddings)) {
    return payload.embeddings[0];
  }
  if (
    Array.isArray(payload?.data) &&
    Array.isArray(payload.data[0]?.embedding)
  ) {
    return payload.data[0].embedding;
  }
  if (Array.isArray(payload)) {
    return payload[0];
  }
  return undefined;
}

async function getEmbedding(config, input, isQuery = false) {
  const payload = await fetchJson(`${config.EMBEDDER_BASE_URL}/embed`, {
    method: "POST",
    headers: {
      accept: "application/json",
      "x-api-key": config.EMBEDDER_API_KEY,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({ input: [input], is_query: isQuery }),
  });

  const embedding = extractEmbedding(payload);
  if (!Array.isArray(embedding)) {
    throw new Error("Embedding response did not include a vector");
  }

  return embedding;
}

function buildApiUrl(config, apiBase, pathSegment) {
  const base = config.CHROMA_URL.replace(/\/+$/, "");
  const api = apiBase.startsWith("/") ? apiBase : `/${apiBase}`;
  const path = pathSegment.startsWith("/") ? pathSegment : `/${pathSegment}`;
  return `${base}${api}${path}`;
}

async function fetchChroma(config, pathSegment, options = {}) {
  const url = buildApiUrl(config, "/api/v2", pathSegment);
  return fetchJson(url, options);
}

async function ensureDatabase(config) {
  const tenant = config.CHROMA_TENANT || "default";
  const database = config.CHROMA_DATABASE || "default";

  try {
    await fetchChroma(config, `/tenants/${tenant}/databases/${database}`);
  } catch (error) {
    if (error.status === 404) {
      await fetchChroma(config, `/tenants/${tenant}/databases`, {
        method: "POST",
        headers: { "Content-Type": "application/json" },
        body: JSON.stringify({ name: database }),
      });
    } else {
      throw error;
    }
  }
}

async function getOrCreateCollection(config) {
  const tenant = config.CHROMA_TENANT || "default";
  const database = config.CHROMA_DATABASE || "default";

  const collectionPath = `/tenants/${tenant}/databases/${database}/collections?name=${encodeURIComponent(config.CHROMA_COLLECTION)}`;
  const existing = await fetchChroma(config, collectionPath);
  const collection = Array.isArray(existing) ? existing[0] : existing;

  if (collection?.id) {
    return collection.id;
  }

  const createPath = `/tenants/${tenant}/databases/${database}/collections`;
  const created = await fetchChroma(config, createPath, {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ name: config.CHROMA_COLLECTION }),
  });

  return created.id;
}

async function getCollectionId(config) {
  const tenant = config.CHROMA_TENANT || "default";
  const database = config.CHROMA_DATABASE || "default";

  const collectionPath = `/tenants/${tenant}/databases/${database}/collections?name=${encodeURIComponent(config.CHROMA_COLLECTION)}`;
  const existing = await fetchChroma(config, collectionPath);
  const collection = Array.isArray(existing) ? existing[0] : existing;

  if (!collection?.id) {
    throw new Error("Collection not found");
  }

  return collection.id;
}

const addDocumentsToolDefinition = {
  name: "add_documents",
  description: "Add documents into the Chroma collection using the embedder.",
  inputSchema: {
    type: "object",
    properties: {
      documents: {
        type: "array",
        description: "Documents to add to the collection.",
        items: {
          type: "object",
          properties: {
            id: { type: "string", description: "Unique document id." },
            text: { type: "string", description: "Document text." },
            metadata: {
              type: "object",
              description: "Optional metadata for the document.",
            },
          },
          required: ["id", "text"],
          additionalProperties: false,
        },
        minItems: 1,
      },
    },
    required: ["documents"],
    additionalProperties: false,
  },
};

const listCollectionDataToolDefinition = {
  name: "list_collection_data",
  description: "Return all records stored in the Chroma collection.",
  inputSchema: {
    type: "object",
    properties: {
      limit: {
        type: "integer",
        description: "Maximum number of records to return.",
        minimum: 1,
      },
      offset: {
        type: "integer",
        description: "Offset for pagination.",
        minimum: 0,
      },
      includeEmbeddings: {
        type: "boolean",
        description: "Include embedding vectors in the response.",
      },
    },
    additionalProperties: false,
  },
};

const queryCollectionDataToolDefinition = {
  name: "query_collection_data",
  description:
    "Query documents in the Chroma collection using the embedder. Supports 3-tier search (vector → fuzzy → LLM reranking).",
  inputSchema: {
    type: "object",
    properties: {
      query: {
        type: "string",
        description: "Query text for semantic search.",
      },
      nResults: {
        type: "integer",
        description: "Number of results to return (default 5).",
        minimum: 1,
      },
      includeEmbeddings: {
        type: "boolean",
        description: "Include embedding vectors in the response.",
      },
      enhanced: {
        type: "boolean",
        description:
          "Enable 3-tier search (vector + fuzzy matching). Default false.",
      },
      rerank: {
        type: "boolean",
        description:
          "Use LLM to rerank results by relevance. Only works if enhanced=true. Default false.",
      },
    },
    required: ["query"],
    additionalProperties: false,
  },
};

async function addDocuments(args = {}) {
  if (!Array.isArray(args.documents) || args.documents.length === 0) {
    throw new Error("documents must be a non-empty array");
  }

  const config = loadConfig();
  await ensureDatabase(config);
  const collectionId = await getOrCreateCollection(config);
  const tenant = config.CHROMA_TENANT || "default";
  const database = config.CHROMA_DATABASE || "default";
  const embeddings = [];

  for (const doc of args.documents) {
    embeddings.push(await getEmbedding(config, doc.text, false));
  }

  await fetchChroma(
    config,
    `/tenants/${tenant}/databases/${database}/collections/${collectionId}/add`,
    {
      method: "POST",
      headers: { "Content-Type": "application/json" },
      body: JSON.stringify({
        ids: args.documents.map((doc) => doc.id),
        embeddings,
        documents: args.documents.map((doc) => doc.text),
        metadatas: args.documents.map((doc) => doc.metadata ?? null),
      }),
    },
  );

  return { added: args.documents.length, documents: args.documents };
}

async function listCollectionData(args = {}) {
  const config = loadConfig();
  await ensureDatabase(config);
  const collectionId = await getOrCreateCollection(config);
  const tenant = config.CHROMA_TENANT || "default";
  const database = config.CHROMA_DATABASE || "default";
  const include = ["documents", "metadatas"];

  if (args.includeEmbeddings) {
    include.push("embeddings");
  }

  const body = { include };
  if (Number.isInteger(args.limit)) {
    body.limit = args.limit;
  }
  if (Number.isInteger(args.offset)) {
    body.offset = args.offset;
  }

  return fetchChroma(
    config,
    `/tenants/${tenant}/databases/${database}/collections/${collectionId}/get`,
    {
      method: "POST",
      headers: { "Content-Type": "application/json" },
      body: JSON.stringify(body),
    },
  );
}

async function queryCollectionData(args = {}) {
  const config = loadConfig();
  const tenant = config.CHROMA_TENANT || "default";
  const database = config.CHROMA_DATABASE || "default";
  const collectionId = await getCollectionId(config);
  const include = ["documents", "metadatas", "distances"];

  if (args.includeEmbeddings) {
    include.push("embeddings");
  }

  const queryEmbedding = await getEmbedding(config, args.query, true);
  return fetchChroma(
    config,
    `/tenants/${tenant}/databases/${database}/collections/${collectionId}/query`,
    {
      method: "POST",
      headers: { "Content-Type": "application/json" },
      body: JSON.stringify({
        query_embeddings: [queryEmbedding],
        n_results: args.nResults ?? 5,
        include,
      }),
    },
  );
}

async function performFuzzySearch(query, nResults = 5) {
  const dataDir = process.env.DATA_DIR || "/data";
  const docs = await loadContextTreeDocuments(dataDir);

  const scored = docs.map((doc) => ({
    ...doc,
    score: calculateStringSimilarity(
      query.toLowerCase(),
      doc.text.toLowerCase(),
    ),
  }));

  scored.sort((a, b) => b.score - a.score);
  return scored.slice(0, nResults);
}

async function rerankWithLLM(vectorResults, fuzzyResults, query) {
  const allResults = [];

  if (vectorResults?.ids?.[0]) {
    vectorResults.ids[0].forEach((id, idx) => {
      allResults.push({
        id,
        text: vectorResults.documents?.[0]?.[idx] || "",
        source: "vector",
        metadata: vectorResults.metadatas?.[0]?.[idx] || {},
      });
    });
  }

  if (Array.isArray(fuzzyResults)) {
    fuzzyResults.forEach((doc) => {
      if (!allResults.find((r) => r.id === doc.id)) {
        allResults.push({
          id: doc.id,
          text: doc.text,
          source: "fuzzy",
          metadata: doc.metadata || {},
        });
      }
    });
  }

  if (allResults.length === 0) return vectorResults;

  const resultsText = allResults.map((r) => `- [${r.id}] ${r.text}`).join("\n");
  const prompt = `Given these search results and the query "${query}", rank them by relevance to the query. Return ONLY a JSON array of IDs in ranked order, like: ["id1", "id2", "id3"]. Results:\n${resultsText}`;

  try {
    const response = await askOpenAI("", prompt);
    const jsonMatch = response.match(/\[[\s\S]*\]/);
    if (!jsonMatch) return vectorResults;

    const rankedIds = JSON.parse(jsonMatch[0]);
    const rankedResults = {
      ids: [rankedIds],
      documents: [
        rankedIds.map((id) => allResults.find((r) => r.id === id)?.text || ""),
      ],
      metadatas: [
        rankedIds.map(
          (id) => allResults.find((r) => r.id === id)?.metadata || {},
        ),
      ],
      distances: [rankedIds.map((_, idx) => idx / rankedIds.length)],
    };

    return rankedResults;
  } catch (error) {
    console.error("LLM reranking failed:", error.message);
    return vectorResults;
  }
}

async function queryCollectionDataEnhanced(args = {}) {
  if (!args.enhanced) {
    return queryCollectionData(args);
  }

  const nResults = args.nResults ?? 5;
  const vectorResults = await queryCollectionData({ ...args, nResults });
  const fuzzyResults = await performFuzzySearch(args.query, nResults);
  const merged = mergeSearchResults(vectorResults, fuzzyResults, nResults);

  if (args.rerank) {
    return rerankWithLLM(merged, fuzzyResults, args.query);
  }

  return merged;
}

export {
  addDocuments,
  addDocumentsToolDefinition,
  listCollectionData,
  listCollectionDataToolDefinition,
  queryCollectionData,
  queryCollectionDataToolDefinition,
  queryCollectionDataEnhanced,
};