dual-mem 0.1.0__tar.gz

dual_mem-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

dual_mem-0.1.0/PKG-INFO

@@ -0,0 +1,280 @@
+Metadata-Version: 2.4
+Name: dual-mem
+Version: 0.1.0
+Summary: Dual-system layered memory SDK (Hy-Memory reproduction)
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic>=2.6
+Requires-Dist: pydantic-settings>=2.2
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: openai>=1.30
+Requires-Dist: chromadb>=0.5
+Requires-Dist: kuzu>=0.4
+Requires-Dist: scikit-learn>=1.4
+Requires-Dist: numpy>=1.26
+Requires-Dist: rank-bm25>=0.2.2
+Requires-Dist: jieba>=0.42
+Requires-Dist: fastapi>=0.110
+Requires-Dist: uvicorn>=0.29
+Requires-Dist: typer>=0.12
+Requires-Dist: mcp>=1.2
+Requires-Dist: httpx>=0.27
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.23; extra == "dev"
+Requires-Dist: respx>=0.21; extra == "dev"
+Dynamic: license-file
+
+# dual-mem
+
+> 分层记忆内核 —— 从零复现 [Hy-Memory](https://github.com/) 的演化链 / System1-System2 / 8 层记忆框架，封装成一套干净、可测、契约对齐的 Python 记忆 SDK。
+
+`dual_mem` 是一个面向 LLM 应用 / Agent 的**长期记忆**组件。它把零散的对话沉淀成结构化、可演化、可检索的记忆，并通过 **SDK / REST / MCP / CLI / Skill** 五种方式对外提供能力。
+
+核心能力：
+
+- **演化链**：偏好/事实发生变化时（如「最爱 Java」→「转向 Python」、「住上海」→「搬北京」），写侧显式建立 `supersedes`/`superseded_by` 双向指针；旧版本软删保留，检索命中链头时自动展开整条历史（最新→最旧）。
+- **System1（写侧同步认知）**：一次写入内集中所有 LLM 调用 —— 抽取 identity/facts、更新 L0 结构化画像、生成摘要、协调演化链。
+- **System2（ultra 异步沉淀）**：把同领域事实聚类，升维为高阶认知结构（L6 行为 Schema / L7 意图），并支持跨域升维出「核心 Schema」。
+- **三路召回（零 LLM）**：profile（画像/身份/模式）/ proactive（推断意图）/ normal（普通事实知识），叠加演化链展开、BM25+RRF 重排、中文时间词解析、tag 桥接。
+
+---
+
+## 安装
+
+需要 Python ≥ 3.11。
+
+```bash
+git clone <repo-url> dual-mem
+cd dual-mem
+pip install -e .          # 运行时依赖
+pip install -e ".[dev]"   # 含测试依赖（pytest / pytest-asyncio / respx）
+```
+
+主要依赖：`pydantic` / `pydantic-settings`（配置），`openai`（LLM/Embed 兼容协议），`chromadb`（向量库），`kuzu`（图库），`scikit-learn`+`numpy`（System2 聚类），`rank-bm25`+`jieba`（中文重排），`fastapi`+`uvicorn`（REST），`typer`（CLI），`mcp`（MCP server）。
+
+---
+
+## 快速开始（SDK）
+
+`MemoryClient` 是全异步门面。最小例子：
+
+```python
+import asyncio
+from dual_mem import MemoryClient
+
+
+async def main():
+    client = MemoryClient(mode="pro", storage_dir="./.dual_mem_data")
+
+    await client.add(
+        content="我最爱的编程语言是 Java，已经用了5年。",
+        app_id="my_app",
+        user_id="alice",
+    )
+
+    res = await client.search(
+        query="用户的编程语言偏好",
+        app_ids=["my_app"],
+        user_id="alice",
+    )
+    # res["memories"] = {"profile": [...], "proactive": [...], "normal": [...]}
+    for m in res["memories"]["profile"]:
+        print(m["content"], m.get("evolution_chain"))
+
+
+asyncio.run(main())
+```
+
+### 配置（YAML）
+
+配置主源是 YAML 文件，默认读 `~/.dual_mem/config.yaml`（可用环境变量 `DUAL_MEM_CONFIG_FILE` 指定其它路径）。复制仓库根的 `config.example.yaml` 即可：
+
+```bash
+mkdir -p ~/.dual_mem
+cp config.example.yaml ~/.dual_mem/config.yaml
+```
+
+```yaml
+mode: pro                       # lite | pro | ultra
+storage_dir: ./.dual_mem_data
+llm_base_url: https://api.openai.com/v1
+llm_api_key: sk-your-llm-key
+llm_model: gpt-4o-mini
+embed_base_url: https://api.openai.com/v1
+embed_api_key: sk-your-embed-key
+embed_model: text-embedding-3-small
+embed_dim: 1536
+auth_disabled: true             # REST 本地鉴权开关
+app_whitelist:                  # REST app_id 白名单
+  - default
+system2_trigger_mode: per_write # per_write | manual | scheduled
+```
+
+优先级：显式传参 `MemoryClient(mode=...)` > `DUAL_MEM_` 前缀环境变量（临时覆盖）> YAML 文件 > 默认值。
+
+LLM/Embed 走 OpenAI 兼容协议，`base_url` 可指向任意兼容服务（OpenAI / Hunyuan / 本地推理）。
+
+---
+
+## 三档模式
+
+`mode` 自动派生 `agent_mode` 与 `enable_graph`，决定写入深度、LLM 开销与是否启用图库：
+
+| 维度 | lite | pro | ultra |
+|---|---|---|---|
+| 一次 `add` 的 LLM 次数 | **0**（仅 embed） | 2~3 | pro + 异步 1~N |
+| 写入层 | 仅 L1_RAW | L0 / L1(SHADOW) / L2 / L3 / L4 | + L5 / L6 / L7（图库） |
+| System2 异步沉淀 | 否 | 否 | **是**（队列 + 跨域 sweeper） |
+| 图库（Kuzu） | 关 | 关 | **开** |
+| Writer | MemoryWriter | MemoryWriter | System2Writer（内部仍跑 System1） |
+| 适用 | 纯检索 / 离线写入 | 个性化助手 | 深度画像 / 认知沉淀 |
+
+> lite 与 pro 共用 `MemoryWriter`，差别仅在 `agent_mode`；ultra 用 `System2Writer`，写完 System1 后 fire-and-forget 入 System2 队列，由 `client.digest()` 或调度触发加工。
+
+---
+
+## 五种用法
+
+### 1. SDK
+
+见上「快速开始」。`MemoryClient` 提供 `add / search / get / list / update / delete / delete_bulk / digest`，全异步。
+
+### 2. REST（`dual-mem serve`）
+
+```bash
+dual-mem serve --host 0.0.0.0 --port 8000
+```
+
+契约对齐 hy-api：`POST /v1/memories/`、`POST /v1/memories/search`、`GET /v1/memories/`、`GET|DELETE /v1/memories/{id}`、`DELETE /v1/memories/`（需 `confirm=true`），外加 `/health` `/ping` `/info`。开启鉴权时需 `Authorization: Bearer <appkey>` 且 `app_id` 在白名单内。
+
+```bash
+curl -X POST http://localhost:8000/v1/memories/ \
+  -H "Content-Type: application/json" \
+  -d '{"content": "用户喜欢喝咖啡", "app_id": "default", "user_id": "u1"}'
+```
+
+### 3. MCP（`dual-mem-mcp`）
+
+```bash
+dual-mem-mcp                                            # stdio（供 Cursor/Claude Desktop 经 uvx 拉起）
+dual-mem-mcp --transport streamable-http --port 8765   # HTTP，暴露 /mcp 端点
+```
+
+暴露工具：`memory_add / memory_search / memory_get / memory_list / memory_delete`，可直接接入支持 MCP 的 Agent 客户端。`memory_search` 返回结果按 profile/proactive/normal 三路分组，演化过的记忆带 `evolution_chain`。
+
+Cursor `mcp.json` 最小配置：
+
+```json
+{ "mcpServers": { "dual-mem": { "command": "uvx", "args": ["dual-mem-mcp"] } } }
+```
+
+更多传输模式、uvx、Cursor/Claude Desktop 配置见 [`docs/mcp_integration.md`](docs/mcp_integration.md)；整体分层见 [`docs/architecture.md`](docs/architecture.md)。
+
+### 4. CLI
+
+```bash
+dual-mem add --content "用户喜欢喝咖啡" --app-id default --user-id u1
+dual-mem search "用户的饮品偏好" --app-id default --user-id u1
+dual-mem list --app-id default --user-id u1
+dual-mem get <memory_id>
+dual-mem delete <memory_id>
+dual-mem digest          # 触发 System2 沉淀（ultra）
+```
+
+### 5. Skill
+
+`skills/dual-mem/SKILL.md` 指导 Agent 何时、如何通过 CLI 或 MCP 读写记忆（调用范式、三路分组用法、演化链解读），可直接装入支持 Skill 的 Agent。
+
+---
+
+## 架构
+
+### 8 层记忆框架（L0–L7）
+
+| 层 | 名称 | 含义 |
+|---|---|---|
+| L0 | BASIC_INFO | 结构化画像（name/age/location/occupation/employer），diff-only 演化链 |
+| L1 | RAW | 原始对话（pro/ultra 写后转 SHADOW，避免与 L2/L4 双重命中） |
+| L2 | FACT | 客观事件、经历、计划 |
+| L3 | SUMMARY | 长内容（≥500 字）摘要 |
+| L4 | IDENTITY | 偏好、态度、价值观、人格特质 |
+| L5 | KNOWLEDGE | 领域知识 |
+| L6 | SCHEMA | System2 提炼的行为模式（场景+模式+洞察） |
+| L7 | INTENTION | System2 推断的具体未来意图 |
+
+### 写侧 System1（集中 LLM）
+
+```
+add → 写 L1_RAW → Extractor(identity/facts JSON + L0 tool)
+                → Summarizer(≥500 字才出 L3)
+                → Reconciler(search_query 改写 → 双路检索 → 判 ADD/SUPERSEDE/DELETE)
+                → L1 转 SHADOW
+```
+
+### 异步 System2（仅 ultra）
+
+```
+digest() → 取 fresh facts → 两阶段 DBSCAN 聚类
+        → System2Agent 真 ReAct 循环（OpenAI function-calling 8 工具，tool_choice=auto，
+           上限 system2_max_iters=10 轮，无 tool_calls 即终止）
+           读：search_vdb / search_graph / get_node / expand_node
+           写：create_schema(L6) / create_intention(L7) / add_evidence / add_edge
+        → CrossDomainSweeper：基础 Schema ≥5 → 升维出核心 Schema（CROSS_ABSTRACTS_TO）
+```
+
+### 演化链
+
+Reconciler 在写侧显式建 `supersedes`/`superseded_by` 双向指针；`DELETE` 不真删（`is_latest=False` + `SHADOW`），信息无损。读侧命中链中任一节点 → 回溯到链头（is_latest）→ 附 `evolution_chain`（最新→最旧）。**不依赖相似度聚类。**
+
+### 三路召回（零 LLM）
+
+| 路 | 召回层 | 说明 |
+|---|---|---|
+| profile | L0 / L4 / L6 | 稳定画像；identity 40% / schema 40% / 自由 20% 配额，`profile_limit=-1` 全量 |
+| proactive | L7 | 推断意图；`intention_limit=0` 时恒空（默认关） |
+| normal | L2 / L5 / L3 / L1 | 普通事实知识；受 `limit` 与 `min_score` 约束，BM25+RRF 重排 |
+
+> 返回的 profile/proactive/normal 是**路由分组**，不是层；真实层看每条记忆的 `category` 字段。
+
+---
+
+## 与 Hy-Memory 的差异
+
+本项目复现的是 Hy-Memory 的**能力与行为**，不是源码拷贝。主要差异：
+
+1. **8 层命名对齐代码而非官网**：官网文档 L1–L6 命名相对源码有 ±1 位移，本项目弃用官网命名，采用源码语义的 `L0_BASIC_INFO`…`L7_INTENTION`。
+2. **REST 契约对齐 hy-api 文档**：源码 REST 是无鉴权的 stdlib `HTTPServer` + 自定义 `/api/v1/add` 内部协议；本项目用 FastAPI 重写为文档约定的 `/v1/memories/` 契约 + Bearer/appkey 鉴权 + 统一错误码。
+3. **新增 MCP / CLI / Skill / 鉴权 / 测试**：源码这五块完全没有，本项目全新构建（含 128 单测 + e2e smoke）。
+4. **时间查询解析增强**：源码默认 legacy reader 不解析时间词（横评点名短板，「昨天聊了啥」类几乎全错）；本项目默认给 reader 接入中文相对时间解析（`昨天/上周/X月X日` → `created_after` 区间）。
+5. **System2 工具集对齐**：源码 System2 是 8 工具 ReAct 多轮循环；本项目同样实现为 `chat_with_tools` + `tool_choice=auto` 的真 ReAct 循环（`system2_max_iters=10` 轮上限，无 tool_calls 即终止），早期文档里的「单次 LLM 输出 ops JSON 数组」已废弃。
+6. **配置收敛**：源码几十个分散的 `MEMORY_*` 环境变量收敛为 `DUAL_MEM_` 前缀的 pydantic-settings，`mode` 自动派生其余开关。
+7. **砍掉死代码**：源码 4 套 reader（legacy/hybrid/hybrid_tag/exhaustive）、`rdb.py` 桩、`scorer(V1)`、`emotion_analyzer`、`intention_detector` 等只留一套增强 reader。
+
+---
+
+## 已知短板 / 限制
+
+- **supersedes 不跨层纠错**：演化链是**层内**链路（L4↔L4、L2↔L2）。L0 若被误抽（如一句话误判用户名），不会被 L2/L4 纠正 —— 如实保留源码行为。
+- **tag_index 图桥接为简化版**：跨域升维（CrossDomainSweeper）用「基础 Schema 数 ≥5 触发 + 一次 LLM 归纳」，而非源码的行为升维 embed + 矩阵碰撞 + Union-Find。
+- **L0 抽取依赖 LLM 质量**：结构化画像的准确性取决于 extract 阶段 LLM 的判断，弱模型可能误抽/漏抽。
+- **Kuzu 无原生向量索引**：L6/L7 的向量召回在 Python 侧做 cosine 全量比对，数据量大时性能受限。
+- **摘要触发阈值**：L3 仅在 content ≥ 500 字才生成；单条短文本 add 几乎不产摘要（messages 形态更易触发）。
+
+---
+
+## 测试与开发
+
+```bash
+# 全量单测（已全程 mock LLM/Embed，不真连网络）
+python -m pytest tests/ -q
+
+# 静态检查（__init__ 参数 / 方法名 / 模块路径 / 导出列表一致性）
+python ~/.agents/rules/check_ast.py .
+
+# 端到端 smoke（三档 + REST + MCP + CLI，无需 API key）
+python tmp/m7_e2e_demo.py
+```
+
+测试遵循 TDD，`tests/conftest.py` 注入确定性 `FakeEmbed` + 脚本化 `FakeLLMClient`，绝不真连 LLM/Embed。