@cup319/mmpl 2.8.1 → 3.0.0

package/dist/auto-context-NUQFETSY.js

@@ -1,248 +0,0 @@
-#!/usr/bin/env node
-import {
-  OffloadEngine
-} from "./chunk-JL66S7P7.js";
-import {
-  estimateTokens
-} from "./chunk-CHVFXR24.js";
-import "./chunk-2H7UOFLK.js";
-
-// src/auto-context.ts
-var EMPTY_RESULT = {
-  contextText: "",
-  tokenCount: 0,
-  memoryCount: 0,
-  hasPersona: false,
-  sceneCount: 0,
-  offloadStrategy: "none",
-  pendingL0: 0
-};
-var AutoContextGenerator = class {
-  opts;
-  offloadEngine;
-  constructor(opts) {
-    this.opts = opts;
-    this.offloadEngine = opts.offloadEngine ?? new OffloadEngine({ tokenBudget: opts.tokenBudget ?? 2e3 });
-  }
-  /**
-   * 根据用户查询生成完整的记忆上下文。
-   *
-   * 全程 try-catch，任何子步骤失败都会被吞掉并跳过；整体失败返回空上下文。
-   */
-  async generate(query) {
-    if (!query || !query.trim()) {
-      return { ...EMPTY_RESULT };
-    }
-    try {
-      const topK = this.opts.topK ?? 5;
-      const relevanceThreshold = this.opts.relevanceThreshold ?? 0.5;
-      const scanLimit = this.opts.scanLimit ?? 50;
-      const personaTokenLimit = this.opts.personaTokenLimit ?? 500;
-      const snippetLen = this.opts.memorySnippetLength ?? 120;
-      const entries = [];
-      await this.collectVectorHits(
-        query,
-        entries,
-        relevanceThreshold,
-        scanLimit
-      );
-      await this.collectKeywordHits(query, entries, topK);
-      await this.collectSceneHits(query, entries);
-      const offloadResult = this.offloadEngine.compress(entries);
-      let contextText = "";
-      if (offloadResult.retained.length > 0) {
-        contextText += "## \u76F8\u5173\u8BB0\u5FC6\n";
-        for (const e of offloadResult.retained) {
-          const snippet = e.content.length > snippetLen ? e.content.substring(0, snippetLen) + "\u2026" : e.content;
-          contextText += `- ${snippet}
-`;
-        }
-        if (offloadResult.summary) {
-          contextText += `
-> ${offloadResult.summary}
-`;
-        }
-      }
-      const personaOut = await this.injectPersona(
-        contextText,
-        personaTokenLimit
-      );
-      contextText = personaOut.text;
-      const hasPersona = personaOut.injected;
-      let hasMermaid = false;
-      if (this.opts.mermaidInjector && this.opts.sessionId) {
-        try {
-          const mmdResult = await this.opts.mermaidInjector.injectExisting(this.opts.sessionId);
-          if (mmdResult.injectText) {
-            contextText = mmdResult.injectText + "\n\n" + contextText;
-            hasMermaid = true;
-          }
-        } catch {
-        }
-      }
-      let pendingL0 = 0;
-      try {
-        const raw = await this.opts.storage.getUnconsumedRaw(100);
-        pendingL0 = Array.isArray(raw) ? raw.length : 0;
-      } catch {
-      }
-      const tokenCount = estimateTokens(contextText);
-      return {
-        contextText,
-        tokenCount,
-        memoryCount: offloadResult.retained.filter((e) => e.layer === 1).length,
-        hasPersona,
-        sceneCount: offloadResult.retained.filter((e) => e.layer === 2).length,
-        offloadStrategy: offloadResult.strategy,
-        pendingL0
-      };
-    } catch (err) {
-      console.error(
-        "[auto-context] generate failed:",
-        err instanceof Error ? err.message : err
-      );
-      return { ...EMPTY_RESULT };
-    }
-  }
-  /**
-   * 步骤 1: 向量检索 L1 active memories。
-   * 用 cosine 相似度过滤，命中阈值则加入 entries。
-   */
-  async collectVectorHits(query, entries, relevanceThreshold, scanLimit) {
-    try {
-      if (!this.opts.embeddingService?.available) return;
-      const emb = await this.opts.embeddingService.embed(query);
-      if (!emb || emb.length === 0) return;
-      const memories = await this.opts.storage.getActiveMemories();
-      if (!Array.isArray(memories)) return;
-      for (const m of memories.slice(0, scanLimit)) {
-        let mEmb = m.embedding;
-        if (typeof mEmb === "string") {
-          try {
-            mEmb = JSON.parse(mEmb);
-          } catch {
-            mEmb = null;
-          }
-        }
-        if (!Array.isArray(mEmb) || mEmb.length === 0) continue;
-        const sim = this.cosineSim(emb, mEmb);
-        if (sim >= relevanceThreshold) {
-          entries.push({
-            id: m.id,
-            content: m.content,
-            score: sim,
-            layer: 1,
-            importance: typeof m.importance === "number" ? m.importance : 0.5,
-            strength: typeof m.strength === "number" ? m.strength : 0.5,
-            source: "vector"
-          });
-        }
-      }
-    } catch {
-    }
-  }
-  /**
-   * 步骤 2: BM25 关键词检索补充 L1。
-   * 只加入尚未被向量召回命中的记忆。
-   */
-  async collectKeywordHits(query, entries, topK) {
-    try {
-      const results = await this.opts.storage.searchByKeywords(
-        query,
-        topK,
-        "active"
-      );
-      if (!Array.isArray(results)) return;
-      for (const m of results) {
-        if (entries.find((e) => e.id === m.id)) continue;
-        entries.push({
-          id: m.id,
-          content: m.content,
-          score: 0.7,
-          layer: 1,
-          importance: typeof m.importance === "number" ? m.importance : 0.5,
-          strength: typeof m.strength === "number" ? m.strength : 0.5,
-          source: "bm25"
-        });
-      }
-    } catch {
-    }
-  }
-  /**
-   * 步骤 3: 场景匹配 L2。
-   * 用 label / summary 子串匹配（大小写不敏感）。
-   */
-  async collectSceneHits(query, entries) {
-    try {
-      const scenes = await this.opts.storage.getAllScenes();
-      if (!Array.isArray(scenes)) return;
-      const qLower = query.toLowerCase();
-      for (const s of scenes) {
-        const label = (s.label ?? "").toLowerCase();
-        const summary = (s.summary ?? "").toLowerCase();
-        if (label.includes(qLower) || summary.includes(qLower)) {
-          entries.push({
-            id: s.id,
-            content: `[\u573A\u666F] ${s.label ?? s.id}: ${(s.summary ?? "").substring(
-              0,
-              80
-            )}`,
-            score: 0.6,
-            layer: 2,
-            importance: 0.7,
-            strength: 1,
-            source: "scene"
-          });
-        }
-      }
-    } catch {
-    }
-  }
-  /**
-   * 步骤 6: 注入 L3 用户画像。
-   * 画像内容不参与 offload 压缩，但有自己的 token 上限保护。
-   * 返回更新后的文本和是否注入标志。
-   */
-  async injectPersona(contextText, personaTokenLimit) {
-    try {
-      const persona = await this.opts.storage.getLatestPersona();
-      if (!persona || !persona.content) {
-        return { text: contextText, injected: false };
-      }
-      const personaTokens = estimateTokens(persona.content);
-      if (personaTokens >= personaTokenLimit) {
-        return { text: contextText, injected: false };
-      }
-      const text = contextText + `
-## \u7528\u6237\u753B\u50CF
-${persona.content.substring(0, 300)}
-`;
-      return { text, injected: true };
-    } catch {
-      return { text: contextText, injected: false };
-    }
-  }
-  /**
-   * 余弦相似度（内联实现，不依赖 retrieval.ts）
-   * 不等长或空向量返回 0。
-   */
-  cosineSim(a, b) {
-    if (!a || !b || a.length === 0 || b.length === 0 || a.length !== b.length) {
-      return 0;
-    }
-    let dot = 0;
-    let magA = 0;
-    let magB = 0;
-    for (let i = 0; i < a.length; i++) {
-      dot += a[i] * b[i];
-      magA += a[i] * a[i];
-      magB += b[i] * b[i];
-    }
-    const denom = Math.sqrt(magA) * Math.sqrt(magB);
-    return denom > 0 ? dot / denom : 0;
-  }
-};
-export {
-  AutoContextGenerator
-};
-//# sourceMappingURL=auto-context-NUQFETSY.js.map

package/dist/auto-context-NUQFETSY.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/auto-context.ts"],"sourcesContent":["/**\n * 自动召回上下文生成器 (Auto-Context Generator)\n *\n * 背景:\n *   MCP Server 无法 Hook agent 的生命周期（不像 OpenClaw 这类插件框架可以\n *   拦截 before_prompt_build），因此这里实现一个\"一站式\"工具: agent 在每轮\n *   对话开始时调用一次 generate(query)，即可拿到该轮所需的全部记忆上下文。\n *\n *   这相当于 TencentDB AgentMemory 的 before_prompt_build Hook 的 MCP 版本。\n *\n * 流程:\n *   1. 向量检索 L1 active memories（语义相似）\n *   2. BM25 关键词检索 L1 补充（覆盖向量召回遗漏）\n *   3. 场景匹配 L2（label / summary 子串匹配）\n *   4. L3 用户画像固定注入（不参与压缩）\n *   5. 检查 L0 待处理计数（提示 agent 是否需要 consolidate）\n *   6. 用 OffloadEngine 把 L1+L2 压缩到 token 预算内\n *   7. 格式化为可读 Markdown 文本\n *\n * 全程 try-catch，任何子步骤失败都不会抛出，最坏返回空上下文。\n * 不依赖任何外部库。\n */\n\nimport { OffloadEngine, OffloadEntry } from \"./offload-engine.js\";\nimport { estimateTokens } from \"./token-counter.js\";\n\n/** AutoContextGenerator 配置选项 */\nexport interface AutoContextOptions {\n  /** 存储层（鸭子类型，提供 getActiveMemories / getAllScenes / getLatestPersona / searchByKeywords / getUnconsumedRaw 等） */\n  storage: any;\n  /** Embedding 服务（提供 available / embed） */\n  embeddingService: any;\n  /** 可选的 OffloadEngine，不传则按 tokenBudget 自动创建 */\n  offloadEngine?: OffloadEngine;\n  /** 可选的 MermaidInjector，提供时自动注入任务符号图 */\n  mermaidInjector?: any;\n  /** 可选的 session_id，用于注入已有 Mermaid 会话图 */\n  sessionId?: string;\n  /** 上下文 token 预算，默认 2000 */\n  tokenBudget?: number;\n  /** 每层取 top-k，默认 5 */\n  topK?: number;\n  /** 相关性阈值，默认 0.5 */\n  relevanceThreshold?: number;\n  /** 向量扫描上限（性能保护），默认 50 */\n  scanLimit?: number;\n  /** 画像内容 token 上限，超过则不注入，默认 500 */\n  personaTokenLimit?: number;\n  /** 单条记忆输出截断长度，默认 120 */\n  memorySnippetLength?: number;\n}\n\n/** generate() 返回结果 */\nexport interface AutoContextResult {\n  /** 注入到 prompt 前面的记忆上下文文本 */\n  contextText: string;\n  /** 上下文 token 数 */\n  tokenCount: number;\n  /** 命中的记忆条数（L1 retained） */\n  memoryCount: number;\n  /** 是否包含用户画像 */\n  hasPersona: boolean;\n  /** 命中的场景数（L2 retained） */\n  sceneCount: number;\n  /** 压缩策略名称 */\n  offloadStrategy: string;\n  /** 未消费的 L0 计数 */\n  pendingL0: number;\n}\n\n/** 空结果常量，失败时统一返回 */\nconst EMPTY_RESULT: AutoContextResult = {\n  contextText: \"\",\n  tokenCount: 0,\n  memoryCount: 0,\n  hasPersona: false,\n  sceneCount: 0,\n  offloadStrategy: \"none\",\n  pendingL0: 0,\n};\n\n/**\n * 自动召回上下文生成器\n */\nexport class AutoContextGenerator {\n  private opts: AutoContextOptions;\n  private offloadEngine: OffloadEngine;\n\n  constructor(opts: AutoContextOptions) {\n    this.opts = opts;\n    // 若未提供 offloadEngine，按 tokenBudget 自动创建一个\n    this.offloadEngine =\n      opts.offloadEngine ??\n      new OffloadEngine({ tokenBudget: opts.tokenBudget ?? 2000 });\n  }\n\n  /**\n   * 根据用户查询生成完整的记忆上下文。\n   *\n   * 全程 try-catch，任何子步骤失败都会被吞掉并跳过；整体失败返回空上下文。\n   */\n  async generate(query: string): Promise<AutoContextResult> {\n    // 防御：空 query 直接返回空上下文\n    if (!query || !query.trim()) {\n      return { ...EMPTY_RESULT };\n    }\n\n    try {\n      const topK = this.opts.topK ?? 5;\n      const relevanceThreshold = this.opts.relevanceThreshold ?? 0.5;\n      const scanLimit = this.opts.scanLimit ?? 50;\n      const personaTokenLimit = this.opts.personaTokenLimit ?? 500;\n      const snippetLen = this.opts.memorySnippetLength ?? 120;\n\n      const entries: OffloadEntry[] = [];\n\n      // ===== 1. 向量检索 L1 active memories =====\n      await this.collectVectorHits(\n        query,\n        entries,\n        relevanceThreshold,\n        scanLimit\n      );\n\n      // ===== 2. BM25 关键词检索补充 L1 =====\n      await this.collectKeywordHits(query, entries, topK);\n\n      // ===== 3. 场景匹配 L2 =====\n      await this.collectSceneHits(query, entries);\n\n      // ===== 4. 用 OffloadEngine 压缩到 token 预算 =====\n      const offloadResult = this.offloadEngine.compress(entries);\n\n      // ===== 5. 格式化记忆 + 场景文本 =====\n      let contextText = \"\";\n      if (offloadResult.retained.length > 0) {\n        contextText += \"## 相关记忆\\n\";\n        for (const e of offloadResult.retained) {\n          const snippet =\n            e.content.length > snippetLen\n              ? e.content.substring(0, snippetLen) + \"…\"\n              : e.content;\n          contextText += `- ${snippet}\\n`;\n        }\n        if (offloadResult.summary) {\n          contextText += `\\n> ${offloadResult.summary}\\n`;\n        }\n      }\n\n      // ===== 6. L3 用户画像（固定注入，不参与压缩） =====\n      const personaOut = await this.injectPersona(\n        contextText,\n        personaTokenLimit\n      );\n      contextText = personaOut.text;\n      const hasPersona = personaOut.injected;\n\n      // ===== 6.5 Mermaid 任务符号图注入 =====\n      let hasMermaid = false;\n      if (this.opts.mermaidInjector && this.opts.sessionId) {\n        try {\n          const mmdResult = await this.opts.mermaidInjector.injectExisting(this.opts.sessionId);\n          if (mmdResult.injectText) {\n            contextText = mmdResult.injectText + \"\\n\\n\" + contextText;\n            hasMermaid = true;\n          }\n        } catch {\n          /* ignore mermaid injection failure */\n        }\n      }\n\n      // ===== 7. L0 待处理计数 =====\n      let pendingL0 = 0;\n      try {\n        const raw = await this.opts.storage.getUnconsumedRaw(100);\n        pendingL0 = Array.isArray(raw) ? raw.length : 0;\n      } catch {\n        /* ignore */\n      }\n\n      const tokenCount = estimateTokens(contextText);\n\n      return {\n        contextText,\n        tokenCount,\n        memoryCount: offloadResult.retained.filter((e) => e.layer === 1).length,\n        hasPersona,\n        sceneCount: offloadResult.retained.filter((e) => e.layer === 2).length,\n        offloadStrategy: offloadResult.strategy,\n        pendingL0,\n      };\n    } catch (err) {\n      // 任何意外错误都返回空上下文，绝不抛出\n      console.error(\n        \"[auto-context] generate failed:\",\n        err instanceof Error ? err.message : err\n      );\n      return { ...EMPTY_RESULT };\n    }\n  }\n\n  /**\n   * 步骤 1: 向量检索 L1 active memories。\n   * 用 cosine 相似度过滤，命中阈值则加入 entries。\n   */\n  private async collectVectorHits(\n    query: string,\n    entries: OffloadEntry[],\n    relevanceThreshold: number,\n    scanLimit: number\n  ): Promise<void> {\n    try {\n      if (!this.opts.embeddingService?.available) return;\n      const emb = await this.opts.embeddingService.embed(query);\n      if (!emb || emb.length === 0) return;\n\n      const memories = await this.opts.storage.getActiveMemories();\n      if (!Array.isArray(memories)) return;\n\n      for (const m of memories.slice(0, scanLimit)) {\n        // embedding 可能存成 JSON 字符串\n        let mEmb: any = m.embedding;\n        if (typeof mEmb === \"string\") {\n          try {\n            mEmb = JSON.parse(mEmb);\n          } catch {\n            mEmb = null;\n          }\n        }\n        if (!Array.isArray(mEmb) || mEmb.length === 0) continue;\n\n        const sim = this.cosineSim(emb, mEmb);\n        if (sim >= relevanceThreshold) {\n          entries.push({\n            id: m.id,\n            content: m.content,\n            score: sim,\n            layer: 1,\n            importance: typeof m.importance === \"number\" ? m.importance : 0.5,\n            strength: typeof m.strength === \"number\" ? m.strength : 0.5,\n            source: \"vector\",\n          });\n        }\n      }\n    } catch {\n      /* ignore — 向量检索失败不影响后续步骤 */\n    }\n  }\n\n  /**\n   * 步骤 2: BM25 关键词检索补充 L1。\n   * 只加入尚未被向量召回命中的记忆。\n   */\n  private async collectKeywordHits(\n    query: string,\n    entries: OffloadEntry[],\n    topK: number\n  ): Promise<void> {\n    try {\n      const results = await this.opts.storage.searchByKeywords(\n        query,\n        topK,\n        \"active\"\n      );\n      if (!Array.isArray(results)) return;\n      for (const m of results) {\n        if (entries.find((e) => e.id === m.id)) continue;\n        entries.push({\n          id: m.id,\n          content: m.content,\n          score: 0.7,\n          layer: 1,\n          importance: typeof m.importance === \"number\" ? m.importance : 0.5,\n          strength: typeof m.strength === \"number\" ? m.strength : 0.5,\n          source: \"bm25\",\n        });\n      }\n    } catch {\n      /* ignore */\n    }\n  }\n\n  /**\n   * 步骤 3: 场景匹配 L2。\n   * 用 label / summary 子串匹配（大小写不敏感）。\n   */\n  private async collectSceneHits(\n    query: string,\n    entries: OffloadEntry[]\n  ): Promise<void> {\n    try {\n      const scenes = await this.opts.storage.getAllScenes();\n      if (!Array.isArray(scenes)) return;\n      const qLower = query.toLowerCase();\n      for (const s of scenes) {\n        const label = (s.label ?? \"\").toLowerCase();\n        const summary = (s.summary ?? \"\").toLowerCase();\n        if (label.includes(qLower) || summary.includes(qLower)) {\n          entries.push({\n            id: s.id,\n            content: `[场景] ${s.label ?? s.id}: ${(s.summary ?? \"\").substring(\n              0,\n              80\n            )}`,\n            score: 0.6,\n            layer: 2,\n            importance: 0.7,\n            strength: 1.0,\n            source: \"scene\",\n          });\n        }\n      }\n    } catch {\n      /* ignore */\n    }\n  }\n\n  /**\n   * 步骤 6: 注入 L3 用户画像。\n   * 画像内容不参与 offload 压缩，但有自己的 token 上限保护。\n   * 返回更新后的文本和是否注入标志。\n   */\n  private async injectPersona(\n    contextText: string,\n    personaTokenLimit: number\n  ): Promise<{ text: string; injected: boolean }> {\n    try {\n      const persona = await this.opts.storage.getLatestPersona();\n      if (!persona || !persona.content) {\n        return { text: contextText, injected: false };\n      }\n      const personaTokens = estimateTokens(persona.content);\n      if (personaTokens >= personaTokenLimit) {\n        return { text: contextText, injected: false };\n      }\n      const text =\n        contextText +\n        `\\n## 用户画像\\n${persona.content.substring(0, 300)}\\n`;\n      return { text, injected: true };\n    } catch {\n      return { text: contextText, injected: false };\n    }\n  }\n\n  /**\n   * 余弦相似度（内联实现，不依赖 retrieval.ts）\n   * 不等长或空向量返回 0。\n   */\n  private cosineSim(a: number[], b: number[]): number {\n    if (\n      !a ||\n      !b ||\n      a.length === 0 ||\n      b.length === 0 ||\n      a.length !== b.length\n    ) {\n      return 0;\n    }\n    let dot = 0;\n    let magA = 0;\n    let magB = 0;\n    for (let i = 0; i < a.length; i++) {\n      dot += a[i] * b[i];\n      magA += a[i] * a[i];\n      magB += b[i] * b[i];\n    }\n    const denom = Math.sqrt(magA) * Math.sqrt(magB);\n    return denom > 0 ? dot / denom : 0;\n  }\n}\n"],"mappings":";;;;;;;;;;AAuEA,IAAM,eAAkC;AAAA,EACtC,aAAa;AAAA,EACb,YAAY;AAAA,EACZ,aAAa;AAAA,EACb,YAAY;AAAA,EACZ,YAAY;AAAA,EACZ,iBAAiB;AAAA,EACjB,WAAW;AACb;AAKO,IAAM,uBAAN,MAA2B;AAAA,EACxB;AAAA,EACA;AAAA,EAER,YAAY,MAA0B;AACpC,SAAK,OAAO;AAEZ,SAAK,gBACH,KAAK,iBACL,IAAI,cAAc,EAAE,aAAa,KAAK,eAAe,IAAK,CAAC;AAAA,EAC/D;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOA,MAAM,SAAS,OAA2C;AAExD,QAAI,CAAC,SAAS,CAAC,MAAM,KAAK,GAAG;AAC3B,aAAO,EAAE,GAAG,aAAa;AAAA,IAC3B;AAEA,QAAI;AACF,YAAM,OAAO,KAAK,KAAK,QAAQ;AAC/B,YAAM,qBAAqB,KAAK,KAAK,sBAAsB;AAC3D,YAAM,YAAY,KAAK,KAAK,aAAa;AACzC,YAAM,oBAAoB,KAAK,KAAK,qBAAqB;AACzD,YAAM,aAAa,KAAK,KAAK,uBAAuB;AAEpD,YAAM,UAA0B,CAAC;AAGjC,YAAM,KAAK;AAAA,QACT;AAAA,QACA;AAAA,QACA;AAAA,QACA;AAAA,MACF;AAGA,YAAM,KAAK,mBAAmB,OAAO,SAAS,IAAI;AAGlD,YAAM,KAAK,iBAAiB,OAAO,OAAO;AAG1C,YAAM,gBAAgB,KAAK,cAAc,SAAS,OAAO;AAGzD,UAAI,cAAc;AAClB,UAAI,cAAc,SAAS,SAAS,GAAG;AACrC,uBAAe;AACf,mBAAW,KAAK,cAAc,UAAU;AACtC,gBAAM,UACJ,EAAE,QAAQ,SAAS,aACf,EAAE,QAAQ,UAAU,GAAG,UAAU,IAAI,WACrC,EAAE;AACR,yBAAe,KAAK,OAAO;AAAA;AAAA,QAC7B;AACA,YAAI,cAAc,SAAS;AACzB,yBAAe;AAAA,IAAO,cAAc,OAAO;AAAA;AAAA,QAC7C;AAAA,MACF;AAGA,YAAM,aAAa,MAAM,KAAK;AAAA,QAC5B;AAAA,QACA;AAAA,MACF;AACA,oBAAc,WAAW;AACzB,YAAM,aAAa,WAAW;AAG9B,UAAI,aAAa;AACjB,UAAI,KAAK,KAAK,mBAAmB,KAAK,KAAK,WAAW;AACpD,YAAI;AACF,gBAAM,YAAY,MAAM,KAAK,KAAK,gBAAgB,eAAe,KAAK,KAAK,SAAS;AACpF,cAAI,UAAU,YAAY;AACxB,0BAAc,UAAU,aAAa,SAAS;AAC9C,yBAAa;AAAA,UACf;AAAA,QACF,QAAQ;AAAA,QAER;AAAA,MACF;AAGA,UAAI,YAAY;AAChB,UAAI;AACF,cAAM,MAAM,MAAM,KAAK,KAAK,QAAQ,iBAAiB,GAAG;AACxD,oBAAY,MAAM,QAAQ,GAAG,IAAI,IAAI,SAAS;AAAA,MAChD,QAAQ;AAAA,MAER;AAEA,YAAM,aAAa,eAAe,WAAW;AAE7C,aAAO;AAAA,QACL;AAAA,QACA;AAAA,QACA,aAAa,cAAc,SAAS,OAAO,CAAC,MAAM,EAAE,UAAU,CAAC,EAAE;AAAA,QACjE;AAAA,QACA,YAAY,cAAc,SAAS,OAAO,CAAC,MAAM,EAAE,UAAU,CAAC,EAAE;AAAA,QAChE,iBAAiB,cAAc;AAAA,QAC/B;AAAA,MACF;AAAA,IACF,SAAS,KAAK;AAEZ,cAAQ;AAAA,QACN;AAAA,QACA,eAAe,QAAQ,IAAI,UAAU;AAAA,MACvC;AACA,aAAO,EAAE,GAAG,aAAa;AAAA,IAC3B;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,MAAc,kBACZ,OACA,SACA,oBACA,WACe;AACf,QAAI;AACF,UAAI,CAAC,KAAK,KAAK,kBAAkB,UAAW;AAC5C,YAAM,MAAM,MAAM,KAAK,KAAK,iBAAiB,MAAM,KAAK;AACxD,UAAI,CAAC,OAAO,IAAI,WAAW,EAAG;AAE9B,YAAM,WAAW,MAAM,KAAK,KAAK,QAAQ,kBAAkB;AAC3D,UAAI,CAAC,MAAM,QAAQ,QAAQ,EAAG;AAE9B,iBAAW,KAAK,SAAS,MAAM,GAAG,SAAS,GAAG;AAE5C,YAAI,OAAY,EAAE;AAClB,YAAI,OAAO,SAAS,UAAU;AAC5B,cAAI;AACF,mBAAO,KAAK,MAAM,IAAI;AAAA,UACxB,QAAQ;AACN,mBAAO;AAAA,UACT;AAAA,QACF;AACA,YAAI,CAAC,MAAM,QAAQ,IAAI,KAAK,KAAK,WAAW,EAAG;AAE/C,cAAM,MAAM,KAAK,UAAU,KAAK,IAAI;AACpC,YAAI,OAAO,oBAAoB;AAC7B,kBAAQ,KAAK;AAAA,YACX,IAAI,EAAE;AAAA,YACN,SAAS,EAAE;AAAA,YACX,OAAO;AAAA,YACP,OAAO;AAAA,YACP,YAAY,OAAO,EAAE,eAAe,WAAW,EAAE,aAAa;AAAA,YAC9D,UAAU,OAAO,EAAE,aAAa,WAAW,EAAE,WAAW;AAAA,YACxD,QAAQ;AAAA,UACV,CAAC;AAAA,QACH;AAAA,MACF;AAAA,IACF,QAAQ;AAAA,IAER;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,MAAc,mBACZ,OACA,SACA,MACe;AACf,QAAI;AACF,YAAM,UAAU,MAAM,KAAK,KAAK,QAAQ;AAAA,QACtC;AAAA,QACA;AAAA,QACA;AAAA,MACF;AACA,UAAI,CAAC,MAAM,QAAQ,OAAO,EAAG;AAC7B,iBAAW,KAAK,SAAS;AACvB,YAAI,QAAQ,KAAK,CAAC,MAAM,EAAE,OAAO,EAAE,EAAE,EAAG;AACxC,gBAAQ,KAAK;AAAA,UACX,IAAI,EAAE;AAAA,UACN,SAAS,EAAE;AAAA,UACX,OAAO;AAAA,UACP,OAAO;AAAA,UACP,YAAY,OAAO,EAAE,eAAe,WAAW,EAAE,aAAa;AAAA,UAC9D,UAAU,OAAO,EAAE,aAAa,WAAW,EAAE,WAAW;AAAA,UACxD,QAAQ;AAAA,QACV,CAAC;AAAA,MACH;AAAA,IACF,QAAQ;AAAA,IAER;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,MAAc,iBACZ,OACA,SACe;AACf,QAAI;AACF,YAAM,SAAS,MAAM,KAAK,KAAK,QAAQ,aAAa;AACpD,UAAI,CAAC,MAAM,QAAQ,MAAM,EAAG;AAC5B,YAAM,SAAS,MAAM,YAAY;AACjC,iBAAW,KAAK,QAAQ;AACtB,cAAM,SAAS,EAAE,SAAS,IAAI,YAAY;AAC1C,cAAM,WAAW,EAAE,WAAW,IAAI,YAAY;AAC9C,YAAI,MAAM,SAAS,MAAM,KAAK,QAAQ,SAAS,MAAM,GAAG;AACtD,kBAAQ,KAAK;AAAA,YACX,IAAI,EAAE;AAAA,YACN,SAAS,kBAAQ,EAAE,SAAS,EAAE,EAAE,MAAM,EAAE,WAAW,IAAI;AAAA,cACrD;AAAA,cACA;AAAA,YACF,CAAC;AAAA,YACD,OAAO;AAAA,YACP,OAAO;AAAA,YACP,YAAY;AAAA,YACZ,UAAU;AAAA,YACV,QAAQ;AAAA,UACV,CAAC;AAAA,QACH;AAAA,MACF;AAAA,IACF,QAAQ;AAAA,IAER;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOA,MAAc,cACZ,aACA,mBAC8C;AAC9C,QAAI;AACF,YAAM,UAAU,MAAM,KAAK,KAAK,QAAQ,iBAAiB;AACzD,UAAI,CAAC,WAAW,CAAC,QAAQ,SAAS;AAChC,eAAO,EAAE,MAAM,aAAa,UAAU,MAAM;AAAA,MAC9C;AACA,YAAM,gBAAgB,eAAe,QAAQ,OAAO;AACpD,UAAI,iBAAiB,mBAAmB;AACtC,eAAO,EAAE,MAAM,aAAa,UAAU,MAAM;AAAA,MAC9C;AACA,YAAM,OACJ,cACA;AAAA;AAAA,EAAc,QAAQ,QAAQ,UAAU,GAAG,GAAG,CAAC;AAAA;AACjD,aAAO,EAAE,MAAM,UAAU,KAAK;AAAA,IAChC,QAAQ;AACN,aAAO,EAAE,MAAM,aAAa,UAAU,MAAM;AAAA,IAC9C;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA,EAMQ,UAAU,GAAa,GAAqB;AAClD,QACE,CAAC,KACD,CAAC,KACD,EAAE,WAAW,KACb,EAAE,WAAW,KACb,EAAE,WAAW,EAAE,QACf;AACA,aAAO;AAAA,IACT;AACA,QAAI,MAAM;AACV,QAAI,OAAO;AACX,QAAI,OAAO;AACX,aAAS,IAAI,GAAG,IAAI,EAAE,QAAQ,KAAK;AACjC,aAAO,EAAE,CAAC,IAAI,EAAE,CAAC;AACjB,cAAQ,EAAE,CAAC,IAAI,EAAE,CAAC;AAClB,cAAQ,EAAE,CAAC,IAAI,EAAE,CAAC;AAAA,IACpB;AACA,UAAM,QAAQ,KAAK,KAAK,IAAI,IAAI,KAAK,KAAK,IAAI;AAC9C,WAAO,QAAQ,IAAI,MAAM,QAAQ;AAAA,EACnC;AACF;","names":[]}

package/dist/checkpoint-ABRNCBCA.js

@@ -1,68 +0,0 @@
-#!/usr/bin/env node
-import "./chunk-2H7UOFLK.js";
-
-// src/checkpoint.ts
-import { promises as fs } from "fs";
-import path from "path";
-var CheckpointManager = class {
-  checkpointPath;
-  checkpoint;
-  dirty = false;
-  constructor(dataDir) {
-    this.checkpointPath = path.join(dataDir, ".metadata", "pipeline_checkpoint.json");
-    this.checkpoint = {
-      lastL1ProcessedRawId: null,
-      lastL1Time: 0,
-      lastL2Time: 0,
-      lastL3Time: 0,
-      totalL0Processed: 0,
-      totalL1Extracted: 0,
-      totalL2Built: 0,
-      totalL3Versions: 0,
-      updatedAt: 0
-    };
-  }
-  async init() {
-    try {
-      const raw = await fs.readFile(this.checkpointPath, "utf-8");
-      const parsed = JSON.parse(raw);
-      this.checkpoint = { ...this.checkpoint, ...parsed };
-    } catch {
-    }
-  }
-  recordL1(rawId, extracted) {
-    this.checkpoint.lastL1ProcessedRawId = rawId;
-    this.checkpoint.lastL1Time = Date.now();
-    this.checkpoint.totalL0Processed++;
-    this.checkpoint.totalL1Extracted += extracted;
-    this.dirty = true;
-  }
-  recordL2(sceneCount) {
-    this.checkpoint.lastL2Time = Date.now();
-    this.checkpoint.totalL2Built += sceneCount;
-    this.dirty = true;
-  }
-  recordL3() {
-    this.checkpoint.lastL3Time = Date.now();
-    this.checkpoint.totalL3Versions++;
-    this.dirty = true;
-  }
-  getCheckpoint() {
-    return { ...this.checkpoint };
-  }
-  /** 持久化到磁盘（原子写入：tmp + rename） */
-  async flush() {
-    if (!this.dirty) return;
-    this.checkpoint.updatedAt = Date.now();
-    const dir = path.dirname(this.checkpointPath);
-    await fs.mkdir(dir, { recursive: true });
-    const tmpPath = this.checkpointPath + ".tmp";
-    await fs.writeFile(tmpPath, JSON.stringify(this.checkpoint, null, 2), "utf-8");
-    await fs.rename(tmpPath, this.checkpointPath);
-    this.dirty = false;
-  }
-};
-export {
-  CheckpointManager
-};
-//# sourceMappingURL=checkpoint-ABRNCBCA.js.map

package/dist/checkpoint-ABRNCBCA.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/checkpoint.ts"],"sourcesContent":["import { promises as fs } from \"node:fs\";\nimport path from \"node:path\";\n\n/**\n * 管道检查点 — 追踪记忆处理进度，支持崩溃恢复\n *\n * 灵感: TencentDB Agent Memory 的 checkpoint.ts\n */\n\nexport interface PipelineCheckpoint {\n  /** 最后一次 L1 提取处理的 L0 记录 ID */\n  lastL1ProcessedRawId: string | null;\n  /** 最后一次 L1 提取时间 */\n  lastL1Time: number;\n  /** 最后一次 L2 场景构建时间 */\n  lastL2Time: number;\n  /** 最后一次 L3 画像生成时间 */\n  lastL3Time: number;\n  /** 已处理的 L0 记录总数 */\n  totalL0Processed: number;\n  /** 已提取的 L1 记忆总数 */\n  totalL1Extracted: number;\n  /** 已构建的 L2 场景总数 */\n  totalL2Built: number;\n  /** 已生成的 L3 画像版本数 */\n  totalL3Versions: number;\n  /** 检查点最后更新时间 */\n  updatedAt: number;\n}\n\nexport class CheckpointManager {\n  private checkpointPath: string;\n  private checkpoint: PipelineCheckpoint;\n  private dirty: boolean = false;\n\n  constructor(dataDir: string) {\n    this.checkpointPath = path.join(dataDir, \".metadata\", \"pipeline_checkpoint.json\");\n    this.checkpoint = {\n      lastL1ProcessedRawId: null,\n      lastL1Time: 0, lastL2Time: 0, lastL3Time: 0,\n      totalL0Processed: 0, totalL1Extracted: 0, totalL2Built: 0, totalL3Versions: 0,\n      updatedAt: 0,\n    };\n  }\n\n  async init(): Promise<void> {\n    try {\n      const raw = await fs.readFile(this.checkpointPath, \"utf-8\");\n      const parsed = JSON.parse(raw);\n      this.checkpoint = { ...this.checkpoint, ...parsed };\n    } catch { /* first run */ }\n  }\n\n  recordL1(rawId: string, extracted: number): void {\n    this.checkpoint.lastL1ProcessedRawId = rawId;\n    this.checkpoint.lastL1Time = Date.now();\n    this.checkpoint.totalL0Processed++;\n    this.checkpoint.totalL1Extracted += extracted;\n    this.dirty = true;\n  }\n\n  recordL2(sceneCount: number): void {\n    this.checkpoint.lastL2Time = Date.now();\n    this.checkpoint.totalL2Built += sceneCount;\n    this.dirty = true;\n  }\n\n  recordL3(): void {\n    this.checkpoint.lastL3Time = Date.now();\n    this.checkpoint.totalL3Versions++;\n    this.dirty = true;\n  }\n\n  getCheckpoint(): PipelineCheckpoint { return { ...this.checkpoint }; }\n\n  /** 持久化到磁盘（原子写入：tmp + rename） */\n  async flush(): Promise<void> {\n    if (!this.dirty) return;\n    this.checkpoint.updatedAt = Date.now();\n    const dir = path.dirname(this.checkpointPath);\n    await fs.mkdir(dir, { recursive: true });\n    const tmpPath = this.checkpointPath + \".tmp\";\n    await fs.writeFile(tmpPath, JSON.stringify(this.checkpoint, null, 2), \"utf-8\");\n    await fs.rename(tmpPath, this.checkpointPath);\n    this.dirty = false;\n  }\n}\n"],"mappings":";;;;AAAA,SAAS,YAAY,UAAU;AAC/B,OAAO,UAAU;AA6BV,IAAM,oBAAN,MAAwB;AAAA,EACrB;AAAA,EACA;AAAA,EACA,QAAiB;AAAA,EAEzB,YAAY,SAAiB;AAC3B,SAAK,iBAAiB,KAAK,KAAK,SAAS,aAAa,0BAA0B;AAChF,SAAK,aAAa;AAAA,MAChB,sBAAsB;AAAA,MACtB,YAAY;AAAA,MAAG,YAAY;AAAA,MAAG,YAAY;AAAA,MAC1C,kBAAkB;AAAA,MAAG,kBAAkB;AAAA,MAAG,cAAc;AAAA,MAAG,iBAAiB;AAAA,MAC5E,WAAW;AAAA,IACb;AAAA,EACF;AAAA,EAEA,MAAM,OAAsB;AAC1B,QAAI;AACF,YAAM,MAAM,MAAM,GAAG,SAAS,KAAK,gBAAgB,OAAO;AAC1D,YAAM,SAAS,KAAK,MAAM,GAAG;AAC7B,WAAK,aAAa,EAAE,GAAG,KAAK,YAAY,GAAG,OAAO;AAAA,IACpD,QAAQ;AAAA,IAAkB;AAAA,EAC5B;AAAA,EAEA,SAAS,OAAe,WAAyB;AAC/C,SAAK,WAAW,uBAAuB;AACvC,SAAK,WAAW,aAAa,KAAK,IAAI;AACtC,SAAK,WAAW;AAChB,SAAK,WAAW,oBAAoB;AACpC,SAAK,QAAQ;AAAA,EACf;AAAA,EAEA,SAAS,YAA0B;AACjC,SAAK,WAAW,aAAa,KAAK,IAAI;AACtC,SAAK,WAAW,gBAAgB;AAChC,SAAK,QAAQ;AAAA,EACf;AAAA,EAEA,WAAiB;AACf,SAAK,WAAW,aAAa,KAAK,IAAI;AACtC,SAAK,WAAW;AAChB,SAAK,QAAQ;AAAA,EACf;AAAA,EAEA,gBAAoC;AAAE,WAAO,EAAE,GAAG,KAAK,WAAW;AAAA,EAAG;AAAA;AAAA,EAGrE,MAAM,QAAuB;AAC3B,QAAI,CAAC,KAAK,MAAO;AACjB,SAAK,WAAW,YAAY,KAAK,IAAI;AACrC,UAAM,MAAM,KAAK,QAAQ,KAAK,cAAc;AAC5C,UAAM,GAAG,MAAM,KAAK,EAAE,WAAW,KAAK,CAAC;AACvC,UAAM,UAAU,KAAK,iBAAiB;AACtC,UAAM,GAAG,UAAU,SAAS,KAAK,UAAU,KAAK,YAAY,MAAM,CAAC,GAAG,OAAO;AAC7E,UAAM,GAAG,OAAO,SAAS,KAAK,cAAc;AAC5C,SAAK,QAAQ;AAAA,EACf;AACF;","names":[]}

package/dist/chunk-2H7UOFLK.js

@@ -1,11 +0,0 @@
-#!/usr/bin/env node
-var __defProp = Object.defineProperty;
-var __export = (target, all) => {
-  for (var name in all)
-    __defProp(target, name, { get: all[name], enumerable: true });
-};
-
-export {
-  __export
-};
-//# sourceMappingURL=chunk-2H7UOFLK.js.map

package/dist/chunk-2H7UOFLK.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":[],"sourcesContent":[],"mappings":"","names":[]}

package/dist/chunk-CHVFXR24.js

@@ -1,19 +0,0 @@
-#!/usr/bin/env node
-
-// src/token-counter.ts
-function estimateTokens(text) {
-  if (!text) return 0;
-  let count = 0;
-  for (const char of text) {
-    if (/[\u4e00-\u9fff\u3040-\u30ff\uac00-\ud7af]/.test(char)) count += 1;
-    else if (/[a-zA-Z0-9]/.test(char)) count += 0.25;
-    else if (/\s/.test(char)) count += 0.1;
-    else count += 0.5;
-  }
-  return Math.ceil(count);
-}
-
-export {
-  estimateTokens
-};
-//# sourceMappingURL=chunk-CHVFXR24.js.map

package/dist/chunk-CHVFXR24.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/token-counter.ts"],"sourcesContent":["/**\n * 轻量 token 估算器 — 无需 tiktoken 依赖\n *\n * 估算公式:\n *   中文/CJK ~1 token/字\n *   英文字母数字 ~0.25 token/字符 (≈0.75 token/单词)\n *   空格 ~0.1 token\n *   标点符号 ~0.5 token\n *\n * 用于 Context Offload 压缩引擎的 token 预算计算。\n * 纯字符级估算，无外部依赖，开销极低。\n */\n\n/**\n * 估算文本的 token 数\n *\n * @param text 待估算的文本\n * @returns 估算的 token 数（向上取整）\n */\nexport function estimateTokens(text: string): number {\n  if (!text) return 0;\n  let count = 0;\n  for (const char of text) {\n    // CJK 字符（中日韩）: ~1 token each\n    if (/[\\u4e00-\\u9fff\\u3040-\\u30ff\\uac00-\\ud7af]/.test(char)) count += 1;\n    // ASCII 字母数字: ~0.25 token (4 个字符约 1 token)\n    else if (/[a-zA-Z0-9]/.test(char)) count += 0.25;\n    // 空白字符: 0.1 token\n    else if (/\\s/.test(char)) count += 0.1;\n    // 标点及其他符号: 0.5 token\n    else count += 0.5;\n  }\n  return Math.ceil(count);\n}\n\n/**\n * 估算消息数组的总 token 数（含结构开销）\n *\n * @param messages 消息列表，每条含 role 和 content\n * @returns 估算的总 token 数\n */\nexport function estimateMessagesTokens(\n  messages: Array<{ role: string; content: string }>\n): number {\n  let total = 0;\n  for (const msg of messages) {\n    total += estimateTokens(msg.content);\n    total += 4; // role + structural overhead per message\n  }\n  return total + 2; // primer overhead\n}\n"],"mappings":";;;AAmBO,SAAS,eAAe,MAAsB;AACnD,MAAI,CAAC,KAAM,QAAO;AAClB,MAAI,QAAQ;AACZ,aAAW,QAAQ,MAAM;AAEvB,QAAI,4CAA4C,KAAK,IAAI,EAAG,UAAS;AAAA,aAE5D,cAAc,KAAK,IAAI,EAAG,UAAS;AAAA,aAEnC,KAAK,KAAK,IAAI,EAAG,UAAS;AAAA,QAE9B,UAAS;AAAA,EAChB;AACA,SAAO,KAAK,KAAK,KAAK;AACxB;","names":[]}

package/dist/chunk-JL66S7P7.js

@@ -1,151 +0,0 @@
-#!/usr/bin/env node
-import {
-  estimateTokens
-} from "./chunk-CHVFXR24.js";
-
-// src/offload-engine.ts
-var DEFAULT_OPTIONS = {
-  tokenBudget: 2e3,
-  cascadeThreshold: 0.8,
-  aggressiveThreshold: 0.95,
-  emergencyMinKeep: 3
-};
-var OffloadEngine = class {
-  opts;
-  constructor(opts) {
-    this.opts = { ...DEFAULT_OPTIONS, ...opts };
-  }
-  /**
-   * 压缩记忆列表到 token 预算内
-   *
-   * 策略（逐级升级）:
-   *   1. 正常: 总 token < cascade 阈值 → 不压缩
-   *   2. 级联: cascade ≤ 总 token < aggressive → 按最低 score 逐条卸载
-   *   3. 激进: aggressive ≤ 总 token < budget → 按最低 importance×strength 批量卸载
-   *   4. 紧急: 总 token ≥ budget → 只保留 emergencyMinKeep 条最高分条目，其余浓缩为摘要
-   *
-   * @param entries 待压缩的记忆条目列表（不会被修改）
-   * @returns 压缩结果
-   */
-  compress(entries) {
-    const tokensBefore = entries.reduce(
-      (sum, e) => sum + estimateTokens(e.content),
-      0
-    );
-    const cascade = this.opts.tokenBudget * this.opts.cascadeThreshold;
-    const aggressive = this.opts.tokenBudget * this.opts.aggressiveThreshold;
-    if (tokensBefore <= cascade) {
-      return {
-        retained: entries,
-        offloaded: [],
-        tokensBefore,
-        tokensAfter: tokensBefore,
-        strategy: "none",
-        summary: null
-      };
-    }
-    if (tokensBefore <= aggressive) {
-      return this.cascadeCompress(entries, cascade, tokensBefore);
-    }
-    if (tokensBefore <= this.opts.tokenBudget) {
-      return this.aggressiveCompress(entries, cascade, tokensBefore);
-    }
-    return this.emergencyCompress(entries, tokensBefore);
-  }
-  /**
-   * 级联压缩: 按 score 升序排列，从最低分开始逐条卸载，直到降到目标 token 数
-   */
-  cascadeCompress(entries, targetTokens, tokensBefore) {
-    const sorted = [...entries].sort((a, b) => a.score - b.score);
-    const offloaded = [];
-    let currentTokens = tokensBefore;
-    for (const entry of sorted) {
-      if (currentTokens <= targetTokens) break;
-      offloaded.push(entry.id);
-      currentTokens -= estimateTokens(entry.content);
-    }
-    const offloadedSet = new Set(offloaded);
-    const retained = entries.filter((e) => !offloadedSet.has(e.id));
-    return {
-      retained,
-      offloaded,
-      tokensBefore,
-      tokensAfter: currentTokens,
-      strategy: "cascade",
-      summary: null
-    };
-  }
-  /**
-   * 激进压缩: 按 importance × strength 升序批量卸载，直到降到目标 token 数；
-   * 对被卸载条目生成简短摘要。
-   */
-  aggressiveCompress(entries, targetTokens, tokensBefore) {
-    const sorted = [...entries].sort(
-      (a, b) => a.importance * a.strength - b.importance * b.strength
-    );
-    const offloaded = [];
-    let currentTokens = tokensBefore;
-    for (const entry of sorted) {
-      if (currentTokens <= targetTokens) break;
-      offloaded.push(entry.id);
-      currentTokens -= estimateTokens(entry.content);
-    }
-    const offloadedSet = new Set(offloaded);
-    const retained = entries.filter((e) => !offloadedSet.has(e.id));
-    const offloadedEntries = entries.filter((e) => offloadedSet.has(e.id));
-    const summary = this.generateSummary(offloadedEntries);
-    return {
-      retained,
-      offloaded,
-      tokensBefore,
-      tokensAfter: currentTokens,
-      strategy: "aggressive",
-      summary
-    };
-  }
-  /**
-   * 紧急压缩: 按 score 降序，只保留 top emergencyMinKeep 条；
-   * 其余条目浓缩为摘要。保证最少保留 emergencyMinKeep 条。
-   */
-  emergencyCompress(entries, tokensBefore) {
-    const sorted = [...entries].sort((a, b) => b.score - a.score);
-    const keepCount = Math.min(this.opts.emergencyMinKeep, sorted.length);
-    const retained = sorted.slice(0, keepCount);
-    const retainedIds = new Set(retained.map((e) => e.id));
-    const offloadedEntries = entries.filter((e) => !retainedIds.has(e.id));
-    const offloaded = offloadedEntries.map((e) => e.id);
-    const tokensAfter = retained.reduce(
-      (sum, e) => sum + estimateTokens(e.content),
-      0
-    );
-    const summary = this.generateSummary(offloadedEntries);
-    return {
-      retained,
-      offloaded,
-      tokensBefore,
-      tokensAfter,
-      strategy: "emergency",
-      summary
-    };
-  }
-  /**
-   * 把被卸载的条目浓缩为一句话摘要
-   *
-   * @param entries 被卸载的条目
-   * @returns 浓缩摘要字符串（无条目时返回空字符串）
-   */
-  generateSummary(entries) {
-    if (!entries || entries.length === 0) return "";
-    const labels = entries.map((e) => e.content.substring(0, 30));
-    return `[\u5DF2\u538B\u7F29 ${entries.length} \u6761\u4F4E\u4F18\u5148\u8BB0\u5FC6: ${labels.join("; ")}...]`;
-  }
-  /** 获取引擎当前配置（返回副本，避免外部篡改） */
-  getOptions() {
-    return { ...this.opts };
-  }
-};
-
-export {
-  OffloadEngine
-};
-//# sourceMappingURL=chunk-JL66S7P7.js.map

package/dist/chunk-JL66S7P7.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/offload-engine.ts"],"sourcesContent":["/**\n * Context Offload 压缩引擎\n *\n * 灵感来自 TencentDB Agent Memory 的多级压缩策略:\n *   - score-cascade (级联压缩)\n *   - aggressive compress (激进压缩)\n *   - emergency compress (紧急压缩)\n *\n * 将大量记忆条目压缩到 token 预算内，按以下四级策略逐级升级:\n *\n *   1. none      — 总 token < cascade 阈值 → 不压缩\n *   2. cascade   — cascade ≤ token < aggressive → 按最低 score 逐条卸载\n *   3. aggressive— aggressive ≤ token < budget → 按最低 importance×strength 批量卸载\n *   4. emergency — token ≥ budget → 只保留 top-N 最高分条目，其余浓缩为摘要\n *\n * compress() 是纯函数式的，不修改输入数组。\n */\n\nimport { estimateTokens } from \"./token-counter.js\";\n\n// ===== 数据类型 =====\n\n/** 待压缩的记忆条目 */\nexport interface OffloadEntry {\n  /** 记忆 ID */\n  id: string;\n  /** 记忆内容文本 */\n  content: string;\n  /** 相关性分数 (0-1) */\n  score: number;\n  /** 记忆层级 L0-L3 */\n  layer: number;\n  /** 重要性 (0-1) */\n  importance: number;\n  /** 强度 (0-1) */\n  strength: number;\n  /** 来源标识 */\n  source: string;\n}\n\n/** 压缩策略类型 */\nexport type OffloadStrategy = \"none\" | \"cascade\" | \"aggressive\" | \"emergency\";\n\n/** 压缩结果 */\nexport interface OffloadResult {\n  /** 压缩后保留的条目 */\n  retained: OffloadEntry[];\n  /** 被卸载的条目（ID 列表） */\n  offloaded: string[];\n  /** 压缩前的 token 数 */\n  tokensBefore: number;\n  /** 压缩后的 token 数 */\n  tokensAfter: number;\n  /** 压缩策略 */\n  strategy: OffloadStrategy;\n  /** 压缩摘要（被卸载条目的浓缩），无卸载时为 null */\n  summary: string | null;\n}\n\n/** 引擎配置选项 */\nexport interface OffloadEngineOptions {\n  /** token 预算上限（默认 2000） */\n  tokenBudget: number;\n  /** 级联压缩触发阈值，相对 budget 的比例（默认 0.8） */\n  cascadeThreshold: number;\n  /** 激进压缩触发阈值，相对 budget 的比例（默认 0.95） */\n  aggressiveThreshold: number;\n  /** 紧急压缩最少保留条目数（默认 3） */\n  emergencyMinKeep: number;\n}\n\n/** 默认配置 */\nconst DEFAULT_OPTIONS: OffloadEngineOptions = {\n  tokenBudget: 2000,\n  cascadeThreshold: 0.8,\n  aggressiveThreshold: 0.95,\n  emergencyMinKeep: 3,\n};\n\n/**\n * Context Offload 压缩引擎\n */\nexport class OffloadEngine {\n  private opts: OffloadEngineOptions;\n\n  constructor(opts?: Partial<OffloadEngineOptions>) {\n    this.opts = { ...DEFAULT_OPTIONS, ...opts };\n  }\n\n  /**\n   * 压缩记忆列表到 token 预算内\n   *\n   * 策略（逐级升级）:\n   *   1. 正常: 总 token < cascade 阈值 → 不压缩\n   *   2. 级联: cascade ≤ 总 token < aggressive → 按最低 score 逐条卸载\n   *   3. 激进: aggressive ≤ 总 token < budget → 按最低 importance×strength 批量卸载\n   *   4. 紧急: 总 token ≥ budget → 只保留 emergencyMinKeep 条最高分条目，其余浓缩为摘要\n   *\n   * @param entries 待压缩的记忆条目列表（不会被修改）\n   * @returns 压缩结果\n   */\n  compress(entries: OffloadEntry[]): OffloadResult {\n    const tokensBefore = entries.reduce(\n      (sum, e) => sum + estimateTokens(e.content),\n      0\n    );\n    const cascade = this.opts.tokenBudget * this.opts.cascadeThreshold;\n    const aggressive = this.opts.tokenBudget * this.opts.aggressiveThreshold;\n\n    // 1. 正常 — 无需压缩\n    if (tokensBefore <= cascade) {\n      return {\n        retained: entries,\n        offloaded: [],\n        tokensBefore,\n        tokensAfter: tokensBefore,\n        strategy: \"none\",\n        summary: null,\n      };\n    }\n\n    // 2. 级联压缩 — 按 score 从低到高逐条卸载\n    if (tokensBefore <= aggressive) {\n      return this.cascadeCompress(entries, cascade, tokensBefore);\n    }\n\n    // 3. 激进压缩 — 按 importance×strength 批量卸载\n    if (tokensBefore <= this.opts.tokenBudget) {\n      return this.aggressiveCompress(entries, cascade, tokensBefore);\n    }\n\n    // 4. 紧急压缩 — 只保留 top-N，其余浓缩\n    return this.emergencyCompress(entries, tokensBefore);\n  }\n\n  /**\n   * 级联压缩: 按 score 升序排列，从最低分开始逐条卸载，直到降到目标 token 数\n   */\n  private cascadeCompress(\n    entries: OffloadEntry[],\n    targetTokens: number,\n    tokensBefore: number\n  ): OffloadResult {\n    // 按 score 升序排列，从最低分开始卸载\n    const sorted = [...entries].sort((a, b) => a.score - b.score);\n    const offloaded: string[] = [];\n    let currentTokens = tokensBefore;\n\n    for (const entry of sorted) {\n      if (currentTokens <= targetTokens) break;\n      offloaded.push(entry.id);\n      currentTokens -= estimateTokens(entry.content);\n    }\n\n    const offloadedSet = new Set(offloaded);\n    const retained = entries.filter((e) => !offloadedSet.has(e.id));\n    return {\n      retained,\n      offloaded,\n      tokensBefore,\n      tokensAfter: currentTokens,\n      strategy: \"cascade\",\n      summary: null,\n    };\n  }\n\n  /**\n   * 激进压缩: 按 importance × strength 升序批量卸载，直到降到目标 token 数；\n   * 对被卸载条目生成简短摘要。\n   */\n  private aggressiveCompress(\n    entries: OffloadEntry[],\n    targetTokens: number,\n    tokensBefore: number\n  ): OffloadResult {\n    // 按 importance × strength 升序排列\n    const sorted = [...entries].sort(\n      (a, b) => a.importance * a.strength - b.importance * b.strength\n    );\n    const offloaded: string[] = [];\n    let currentTokens = tokensBefore;\n\n    for (const entry of sorted) {\n      if (currentTokens <= targetTokens) break;\n      offloaded.push(entry.id);\n      currentTokens -= estimateTokens(entry.content);\n    }\n\n    const offloadedSet = new Set(offloaded);\n    const retained = entries.filter((e) => !offloadedSet.has(e.id));\n    // 生成简短摘要\n    const offloadedEntries = entries.filter((e) => offloadedSet.has(e.id));\n    const summary = this.generateSummary(offloadedEntries);\n    return {\n      retained,\n      offloaded,\n      tokensBefore,\n      tokensAfter: currentTokens,\n      strategy: \"aggressive\",\n      summary,\n    };\n  }\n\n  /**\n   * 紧急压缩: 按 score 降序，只保留 top emergencyMinKeep 条；\n   * 其余条目浓缩为摘要。保证最少保留 emergencyMinKeep 条。\n   */\n  private emergencyCompress(\n    entries: OffloadEntry[],\n    tokensBefore: number\n  ): OffloadResult {\n    // 按 score 降序，只保留 top emergencyMinKeep\n    const sorted = [...entries].sort((a, b) => b.score - a.score);\n    const keepCount = Math.min(this.opts.emergencyMinKeep, sorted.length);\n    const retained = sorted.slice(0, keepCount);\n    const retainedIds = new Set(retained.map((e) => e.id));\n    const offloadedEntries = entries.filter((e) => !retainedIds.has(e.id));\n    const offloaded = offloadedEntries.map((e) => e.id);\n    const tokensAfter = retained.reduce(\n      (sum, e) => sum + estimateTokens(e.content),\n      0\n    );\n    const summary = this.generateSummary(offloadedEntries);\n    return {\n      retained,\n      offloaded,\n      tokensBefore,\n      tokensAfter,\n      strategy: \"emergency\",\n      summary,\n    };\n  }\n\n  /**\n   * 把被卸载的条目浓缩为一句话摘要\n   *\n   * @param entries 被卸载的条目\n   * @returns 浓缩摘要字符串（无条目时返回空字符串）\n   */\n  private generateSummary(entries: OffloadEntry[]): string {\n    if (!entries || entries.length === 0) return \"\";\n    const labels = entries.map((e) => e.content.substring(0, 30));\n    return `[已压缩 ${entries.length} 条低优先记忆: ${labels.join(\"; \")}...]`;\n  }\n\n  /** 获取引擎当前配置（返回副本，避免外部篡改） */\n  getOptions(): OffloadEngineOptions {\n    return { ...this.opts };\n  }\n}\n"],"mappings":";;;;;;AAwEA,IAAM,kBAAwC;AAAA,EAC5C,aAAa;AAAA,EACb,kBAAkB;AAAA,EAClB,qBAAqB;AAAA,EACrB,kBAAkB;AACpB;AAKO,IAAM,gBAAN,MAAoB;AAAA,EACjB;AAAA,EAER,YAAY,MAAsC;AAChD,SAAK,OAAO,EAAE,GAAG,iBAAiB,GAAG,KAAK;AAAA,EAC5C;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAcA,SAAS,SAAwC;AAC/C,UAAM,eAAe,QAAQ;AAAA,MAC3B,CAAC,KAAK,MAAM,MAAM,eAAe,EAAE,OAAO;AAAA,MAC1C;AAAA,IACF;AACA,UAAM,UAAU,KAAK,KAAK,cAAc,KAAK,KAAK;AAClD,UAAM,aAAa,KAAK,KAAK,cAAc,KAAK,KAAK;AAGrD,QAAI,gBAAgB,SAAS;AAC3B,aAAO;AAAA,QACL,UAAU;AAAA,QACV,WAAW,CAAC;AAAA,QACZ;AAAA,QACA,aAAa;AAAA,QACb,UAAU;AAAA,QACV,SAAS;AAAA,MACX;AAAA,IACF;AAGA,QAAI,gBAAgB,YAAY;AAC9B,aAAO,KAAK,gBAAgB,SAAS,SAAS,YAAY;AAAA,IAC5D;AAGA,QAAI,gBAAgB,KAAK,KAAK,aAAa;AACzC,aAAO,KAAK,mBAAmB,SAAS,SAAS,YAAY;AAAA,IAC/D;AAGA,WAAO,KAAK,kBAAkB,SAAS,YAAY;AAAA,EACrD;AAAA;AAAA;AAAA;AAAA,EAKQ,gBACN,SACA,cACA,cACe;AAEf,UAAM,SAAS,CAAC,GAAG,OAAO,EAAE,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK;AAC5D,UAAM,YAAsB,CAAC;AAC7B,QAAI,gBAAgB;AAEpB,eAAW,SAAS,QAAQ;AAC1B,UAAI,iBAAiB,aAAc;AACnC,gBAAU,KAAK,MAAM,EAAE;AACvB,uBAAiB,eAAe,MAAM,OAAO;AAAA,IAC/C;AAEA,UAAM,eAAe,IAAI,IAAI,SAAS;AACtC,UAAM,WAAW,QAAQ,OAAO,CAAC,MAAM,CAAC,aAAa,IAAI,EAAE,EAAE,CAAC;AAC9D,WAAO;AAAA,MACL;AAAA,MACA;AAAA,MACA;AAAA,MACA,aAAa;AAAA,MACb,UAAU;AAAA,MACV,SAAS;AAAA,IACX;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA,EAMQ,mBACN,SACA,cACA,cACe;AAEf,UAAM,SAAS,CAAC,GAAG,OAAO,EAAE;AAAA,MAC1B,CAAC,GAAG,MAAM,EAAE,aAAa,EAAE,WAAW,EAAE,aAAa,EAAE;AAAA,IACzD;AACA,UAAM,YAAsB,CAAC;AAC7B,QAAI,gBAAgB;AAEpB,eAAW,SAAS,QAAQ;AAC1B,UAAI,iBAAiB,aAAc;AACnC,gBAAU,KAAK,MAAM,EAAE;AACvB,uBAAiB,eAAe,MAAM,OAAO;AAAA,IAC/C;AAEA,UAAM,eAAe,IAAI,IAAI,SAAS;AACtC,UAAM,WAAW,QAAQ,OAAO,CAAC,MAAM,CAAC,aAAa,IAAI,EAAE,EAAE,CAAC;AAE9D,UAAM,mBAAmB,QAAQ,OAAO,CAAC,MAAM,aAAa,IAAI,EAAE,EAAE,CAAC;AACrE,UAAM,UAAU,KAAK,gBAAgB,gBAAgB;AACrD,WAAO;AAAA,MACL;AAAA,MACA;AAAA,MACA;AAAA,MACA,aAAa;AAAA,MACb,UAAU;AAAA,MACV;AAAA,IACF;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA,EAMQ,kBACN,SACA,cACe;AAEf,UAAM,SAAS,CAAC,GAAG,OAAO,EAAE,KAAK,CAAC,GAAG,MAAM,EAAE,QAAQ,EAAE,KAAK;AAC5D,UAAM,YAAY,KAAK,IAAI,KAAK,KAAK,kBAAkB,OAAO,MAAM;AACpE,UAAM,WAAW,OAAO,MAAM,GAAG,SAAS;AAC1C,UAAM,cAAc,IAAI,IAAI,SAAS,IAAI,CAAC,MAAM,EAAE,EAAE,CAAC;AACrD,UAAM,mBAAmB,QAAQ,OAAO,CAAC,MAAM,CAAC,YAAY,IAAI,EAAE,EAAE,CAAC;AACrE,UAAM,YAAY,iBAAiB,IAAI,CAAC,MAAM,EAAE,EAAE;AAClD,UAAM,cAAc,SAAS;AAAA,MAC3B,CAAC,KAAK,MAAM,MAAM,eAAe,EAAE,OAAO;AAAA,MAC1C;AAAA,IACF;AACA,UAAM,UAAU,KAAK,gBAAgB,gBAAgB;AACrD,WAAO;AAAA,MACL;AAAA,MACA;AAAA,MACA;AAAA,MACA;AAAA,MACA,UAAU;AAAA,MACV;AAAA,IACF;AAAA,EACF;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAQQ,gBAAgB,SAAiC;AACvD,QAAI,CAAC,WAAW,QAAQ,WAAW,EAAG,QAAO;AAC7C,UAAM,SAAS,QAAQ,IAAI,CAAC,MAAM,EAAE,QAAQ,UAAU,GAAG,EAAE,CAAC;AAC5D,WAAO,uBAAQ,QAAQ,MAAM,0CAAY,OAAO,KAAK,IAAI,CAAC;AAAA,EAC5D;AAAA;AAAA,EAGA,aAAmC;AACjC,WAAO,EAAE,GAAG,KAAK,KAAK;AAAA,EACxB;AACF;","names":[]}

package/dist/chunk-SSDURI3I.js

@@ -1,46 +0,0 @@
-#!/usr/bin/env node
-
-// src/llm-lock.ts
-var _chain = Promise.resolve();
-function withLlmLock(fn) {
-  const run = _chain.then(fn, fn);
-  _chain = run.then(() => void 0, () => void 0);
-  return run;
-}
-async function fetchWithRetry(url, options, maxRetries = 3) {
-  let lastError = null;
-  for (let attempt = 0; attempt <= maxRetries; attempt++) {
-    try {
-      const response = await fetch(url, options);
-      if (response.status === 429 || response.status >= 500) {
-        if (attempt < maxRetries) {
-          const delay = Math.pow(2, attempt + 1) * 1e3;
-          console.warn(
-            `[llm-lock] ${response.status} \u91CD\u8BD5 ${attempt + 1}/${maxRetries}\uFF0C\u7B49\u5F85 ${delay}ms`
-          );
-          await new Promise((r) => setTimeout(r, delay));
-          continue;
-        }
-      }
-      return response;
-    } catch (err) {
-      lastError = err;
-      if (attempt < maxRetries) {
-        const delay = Math.pow(2, attempt + 1) * 1e3;
-        console.warn(
-          `[llm-lock] \u7F51\u7EDC\u9519\u8BEF\u91CD\u8BD5 ${attempt + 1}/${maxRetries}\uFF0C\u7B49\u5F85 ${delay}ms:`,
-          err.message
-        );
-        await new Promise((r) => setTimeout(r, delay));
-        continue;
-      }
-    }
-  }
-  throw lastError ?? new Error("fetchWithRetry exhausted");
-}
-
-export {
-  withLlmLock,
-  fetchWithRetry
-};
-//# sourceMappingURL=chunk-SSDURI3I.js.map

package/dist/chunk-SSDURI3I.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/llm-lock.ts"],"sourcesContent":["/**\n * LLM 并发控制器 — 确保同时只有一个 LLM API 请求在执行\n *\n * GLM-4.7-Flash 免费模型并发数为 1，多个模块共享此锁。\n */\n\n// 全局二值信号量：同一进程内所有 LLM 调用串行\nlet _chain: Promise<any> = Promise.resolve();\n\n/**\n * 用信号量包装一个异步 LLM 调用，确保串行执行\n */\nexport function withLlmLock<T>(fn: () => Promise<T>): Promise<T> {\n  const run = _chain.then(fn, fn); // 无论前一个成功或失败都继续\n  // 链尾推进，但不让后续 catch 影响调用者\n  _chain = run.then(() => undefined, () => undefined);\n  return run;\n}\n\n/**\n * 带重试的 fetch（用于 429 限流和 5xx 临时错误）\n */\nexport async function fetchWithRetry(\n  url: string,\n  options: RequestInit,\n  maxRetries = 3\n): Promise<Response> {\n  let lastError: Error | null = null;\n\n  for (let attempt = 0; attempt <= maxRetries; attempt++) {\n    try {\n      const response = await fetch(url, options);\n\n      // 429 或 5xx → 重试\n      if (response.status === 429 || response.status >= 500) {\n        if (attempt < maxRetries) {\n          // 指数退避：2s, 4s, 8s\n          const delay = Math.pow(2, attempt + 1) * 1000;\n          console.warn(\n            `[llm-lock] ${response.status} 重试 ${attempt + 1}/${maxRetries}，等待 ${delay}ms`\n          );\n          await new Promise((r) => setTimeout(r, delay));\n          continue;\n        }\n      }\n\n      return response;\n    } catch (err) {\n      lastError = err as Error;\n      if (attempt < maxRetries) {\n        const delay = Math.pow(2, attempt + 1) * 1000;\n        console.warn(\n          `[llm-lock] 网络错误重试 ${attempt + 1}/${maxRetries}，等待 ${delay}ms:`,\n          (err as Error).message\n        );\n        await new Promise((r) => setTimeout(r, delay));\n        continue;\n      }\n    }\n  }\n\n  throw lastError ?? new Error(\"fetchWithRetry exhausted\");\n}\n"],"mappings":";;;AAOA,IAAI,SAAuB,QAAQ,QAAQ;AAKpC,SAAS,YAAe,IAAkC;AAC/D,QAAM,MAAM,OAAO,KAAK,IAAI,EAAE;AAE9B,WAAS,IAAI,KAAK,MAAM,QAAW,MAAM,MAAS;AAClD,SAAO;AACT;AAKA,eAAsB,eACpB,KACA,SACA,aAAa,GACM;AACnB,MAAI,YAA0B;AAE9B,WAAS,UAAU,GAAG,WAAW,YAAY,WAAW;AACtD,QAAI;AACF,YAAM,WAAW,MAAM,MAAM,KAAK,OAAO;AAGzC,UAAI,SAAS,WAAW,OAAO,SAAS,UAAU,KAAK;AACrD,YAAI,UAAU,YAAY;AAExB,gBAAM,QAAQ,KAAK,IAAI,GAAG,UAAU,CAAC,IAAI;AACzC,kBAAQ;AAAA,YACN,cAAc,SAAS,MAAM,iBAAO,UAAU,CAAC,IAAI,UAAU,sBAAO,KAAK;AAAA,UAC3E;AACA,gBAAM,IAAI,QAAQ,CAAC,MAAM,WAAW,GAAG,KAAK,CAAC;AAC7C;AAAA,QACF;AAAA,MACF;AAEA,aAAO;AAAA,IACT,SAAS,KAAK;AACZ,kBAAY;AACZ,UAAI,UAAU,YAAY;AACxB,cAAM,QAAQ,KAAK,IAAI,GAAG,UAAU,CAAC,IAAI;AACzC,gBAAQ;AAAA,UACN,mDAAqB,UAAU,CAAC,IAAI,UAAU,sBAAO,KAAK;AAAA,UACzD,IAAc;AAAA,QACjB;AACA,cAAM,IAAI,QAAQ,CAAC,MAAM,WAAW,GAAG,KAAK,CAAC;AAC7C;AAAA,MACF;AAAA,IACF;AAAA,EACF;AAEA,QAAM,aAAa,IAAI,MAAM,0BAA0B;AACzD;","names":[]}