mem-deep-research 0.1.0__tar.gz

mem_deep_research-0.1.0/.gitignore

@@ -0,0 +1,147 @@
+# =============================================================================
+# mem_deep_research Framework .gitignore
+# =============================================================================
+
+# -----------------------------------------------------------------------------
+# Logs and Output
+# -----------------------------------------------------------------------------
+logs/
+*.log
+*.json.log
+outputs/
+task_logs/
+
+# -----------------------------------------------------------------------------
+# Environment and Secrets
+# -----------------------------------------------------------------------------
+.env
+.env.local
+.env.*.local
+*.pem
+*.key
+secrets/
+credentials.json
+
+# -----------------------------------------------------------------------------
+# Python
+# -----------------------------------------------------------------------------
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Virtual environments
+.venv/
+venv/
+ENV/
+env/
+.conda/
+
+# -----------------------------------------------------------------------------
+# IDE and Editor
+# -----------------------------------------------------------------------------
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+.project
+.pydevproject
+.settings/
+*.sublime-workspace
+*.sublime-project
+
+# -----------------------------------------------------------------------------
+# OS Generated
+# -----------------------------------------------------------------------------
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# -----------------------------------------------------------------------------
+# Testing and Coverage
+# -----------------------------------------------------------------------------
+.coverage
+.pytest_cache/
+htmlcov/
+.tox/
+.nox/
+coverage.xml
+*.cover
+*.coverage
+.hypothesis/
+pytest_cache/
+
+# -----------------------------------------------------------------------------
+# Jupyter Notebook
+# -----------------------------------------------------------------------------
+.ipynb_checkpoints/
+*.ipynb_checkpoints
+
+# -----------------------------------------------------------------------------
+# Type Checking
+# -----------------------------------------------------------------------------
+.mypy_cache/
+.dmypy.json
+dmypy.json
+.pyre/
+.pytype/
+
+# -----------------------------------------------------------------------------
+# Documentation
+# -----------------------------------------------------------------------------
+docs/_build/
+site/
+
+# -----------------------------------------------------------------------------
+# Package Management
+# -----------------------------------------------------------------------------
+*.lock
+!poetry.lock
+!uv.lock
+pip-log.txt
+pip-delete-this-directory.txt
+
+# -----------------------------------------------------------------------------
+# Hydra
+# -----------------------------------------------------------------------------
+outputs/
+multirun/
+.hydra/
+
+# -----------------------------------------------------------------------------
+# Temporary files
+# -----------------------------------------------------------------------------
+*.tmp
+*.temp
+*.bak
+tmp/
+temp/
+*.cache
+
+# -----------------------------------------------------------------------------
+# MCP Server artifacts
+# -----------------------------------------------------------------------------
+.mcp/
+mcp_cache/

mem_deep_research-0.1.0/CHANGELOG.md

@@ -0,0 +1,16 @@
+# Changelog
+
+## [0.1.0] - 2026-03-11
+
+### Added
+- MCP-native tool integration with stdio, SSE, and streamable-http transports
+- Three-tier context management: Observation Masking, LLM summarization, emergency pruning
+- Tool call deduplication with hit-count tracking and progressive escalation
+- Execution monitoring with stall/loop detection and three-level escalation
+- Skill system with rules, LLM, and inline selection modes
+- Hook system for lifecycle events (agent, turn, tool)
+- SecureContext for automatic sensitive data isolation
+- Streaming output with structured tag extraction
+- Deep research mode with reflection checkpoints and auto task planning
+- CLI for project initialization, execution, and testing
+- Pydantic-based configuration validation

mem_deep_research-0.1.0/CLAUDE.md

@@ -0,0 +1,274 @@
+# Mem Deep Research Framework
+
+可扩展的 AI Agent 框架，专注于深度研究任务。基于 MCP 工具协议，支持多 LLM 提供商。
+
+## 项目结构
+
+```
+mem_deep_research_core/              # 框架核心代码
+├── deep_research.py                 # 主入口 (DeepResearch 类)
+├── config_schema.py                 # Pydantic 配置验证
+├── exceptions.py                    # 异常定义
+├── core/                            # 核心模块
+│   ├── orchestrator.py              # Agent 编排器（主循环 _run_main_loop）
+│   ├── context_manager.py           # 上下文管理（masking + dedup + source registry）
+│   ├── window_strategy.py           # 窗口压缩策略（ObservationMasking/LLMSummarize/BinaryReduction）
+│   ├── hooks.py                     # 钩子系统（HookRegistry, HookContext）
+│   ├── secure_context.py            # 隐私数据保护（_secure 字段 → 占位符）
+│   ├── tool_executor.py             # 工具执行器
+│   ├── llm_call_handler.py          # LLM 调用 + 重试
+│   ├── sub_agent_runner.py          # 子 Agent 生命周期
+│   ├── stream_handler.py            # SSE 流式输出
+│   ├── monitoring.py                # 执行监控 + 循环检测
+│   ├── user_context.py              # 用户上下文构建
+│   ├── task_planner.py              # LLM 任务分解
+│   ├── message_interceptor.py       # 消息拦截
+│   └── answer_handler.py            # 最终答案提取
+├── llm/                             # LLM 客户端
+│   ├── provider_client_base.py      # Provider 基类
+│   └── providers/                   # 8 个 Provider 实现
+├── prompts/                         # Prompt 系统
+│   ├── agent_prompt.py              # AgentPrompt 统一类
+│   ├── template_loader.py           # 模板加载器
+│   └── templates/                   # Markdown 模板（base/presets/extraction/...）
+├── tool/                            # 工具模块
+│   ├── manager.py                   # ToolManager（MCP 工具管理）
+│   └── mcp_servers/                 # 内置 MCP 服务器
+├── skills/                          # Skill 系统
+│   ├── matcher.py                   # 规则匹配 + 注入
+│   ├── llm_selector.py              # LLM Skill 选择
+│   └── inline_selector.py           # Inline Skill 选择（零额外开销）
+└── utils/
+    ├── external_loader.py           # 配置加载器（全局 config_loader/external_loader）
+    ├── tool_utils.py                # 工具辅助
+    └── stream_parsing_utils.py      # 流式解析（StructuredTagExtractor, TextInterceptor）
+config/                              # 框架默认配置
+├── agent_example.yaml               # Agent 配置示例
+├── tool/                            # 内置工具配置 YAML
+└── skills/definitions/              # Skill 定义
+tests/                               # 单元测试
+```
+
+## 核心概念
+
+### 执行流程
+
+```
+DeepResearch.run(query)
+  → Pipeline.run()
+    → AgentFactory 创建 Orchestrator + LLM Client + ToolManager
+      → Orchestrator._run_main_loop():
+          while turn < max_turns:
+            1. Monitor.pre_turn_check()
+            2. LLM 调用
+            3. Monitor.post_turn_check() (循环检测)
+            4. Inline Skill: 解析 <next_skills>
+            5. 解析工具调用 + 跨轮次去重
+            6. 执行工具（SecureContext 自动解占位符）
+            7. Context 管理（ObservationMasking → LLMSummarize → BinaryReduction）
+            8. Hook: on_turn_end
+            9. 反思检查点
+  → 生成最终摘要 → ResearchResult
+```
+
+### 使用方式
+
+```python
+from mem_deep_research import DeepResearch
+
+# 方式 1: 从项目目录加载
+dr = DeepResearch.from_project("./my_project")
+result = await dr.run("研究任务")
+
+# 方式 2: 代码配置
+dr = DeepResearch(
+    llm_provider="anthropic",
+    model="claude-sonnet-4-20250514",
+    api_key="your-key",
+)
+result = await dr.run("任务")
+
+# 同步
+result = dr.run_sync("任务")
+```
+
+### 项目目录结构
+
+用户项目通过 `DeepResearch.from_project()` 加载：
+
+```
+my_project/
+├── config/
+│   ├── agent.yaml              # Agent 配置（LLM、工具、参数）
+│   ├── tool/                   # 项目级工具配置（覆盖框架默认）
+│   ├── skills/definitions/     # 项目级 Skill 定义
+│   └── prompts/                # 自定义 Prompt 模板
+├── hooks.py                    # 项目钩子（自动加载）
+├── .env                        # API 密钥
+└── run.py                      # 入口脚本
+```
+
+## 关键系统详解
+
+### 1. 钩子系统 (`core/hooks.py`)
+
+全局注册表 `hooks = HookRegistry()`，支持的钩子：
+
+| 钩子 | 时机 | 可修改 |
+|------|------|--------|
+| `on_agent_start` | Agent 开始 | — |
+| `on_agent_end` | Agent 结束 | — |
+| `on_turn_start` | 每轮开始 | — |
+| `on_turn_end` | 每轮结束 | — |
+| `on_tool_start` | 工具调用前 | arguments |
+| `on_tool_end` | 工具调用后 | tool_result |
+| `on_tool_result_format` | 结果格式化 | 返回值 |
+| `on_thinking_generate` | thinking 描述 | 返回值 |
+| `on_env_inject` | MCP 环境变量 | server_params |
+
+用法：
+```python
+from mem_deep_research_core.core.hooks import hooks, HookContext
+
+@hooks.register("on_tool_end", priority=10)
+def my_hook(ctx: HookContext, original_fn):
+    result = original_fn(ctx)   # 调用原逻辑
+    return modified_result      # 或完全替换
+```
+
+### 2. SecureContext (`core/secure_context.py`)
+
+context dict 中的 `_secure` 字段自动在 system prompt 中显示为 `[SECURE:xxx]` 占位符，工具调用前自动替换回真实值。
+
+```python
+context = {
+    "user_name": "张三",          # 正常显示
+    "_secure": {
+        "user_id": "real-123",    # system prompt 中显示 [SECURE:user_id]
+        "org_id": "org-456",      # 工具调用时自动替换回 "org-456"
+    }
+}
+```
+
+关键函数：
+- `get_display_value(ctx, field)` — system prompt 用，_secure 字段返回占位符
+- `get_real_value(ctx, field)` — 工具执行用，始终返回真实值
+- `resolve_placeholders_in_args(args, ctx)` — 递归替换工具参数中的占位符
+
+### 3. 上下文管理 (`core/context_manager.py` + `core/window_strategy.py`)
+
+三级窗口压缩策略，通过 `WindowStrategyPipeline` 组合：
+
+| 级别 | 策略 | 触发条件 | LLM 成本 |
+|------|------|---------|---------|
+| L1 | ObservationMasking | token 占比 > 60% | 零 |
+| L2 | LLMSummarize | token 占比 > 80% | 一次 LLM 调用 |
+| L3 | BinaryReduction | token 占比 > 95% | 零 |
+
+支持自定义策略：继承 `WindowStrategy` ABC，实现 `should_trigger()` + `apply()`。
+
+### 4. Skill 系统 (`skills/`)
+
+三种选择方式（配置 `skill_selection.method`）：
+
+| method | 说明 | 开销 |
+|--------|------|------|
+| `rules` | 基于 keywords/tools/context 打分 | 零 |
+| `llm` | 额外 LLM 调用选择 | 一次轻量 LLM |
+| `inline` | LLM 在回复中声明 `<next_skills>` | 零 |
+
+Skill 定义格式（`config/skills/definitions/*.md`）：
+```markdown
+---
+name: search_strategy
+type: knowledge
+description: "搜索策略指南"
+triggers:
+  keywords: ["搜索", "查找"]
+  tools_mentioned: ["semantic_search"]
+metadata:
+  priority: 10
+---
+# Skill 内容（注入 system prompt）
+```
+
+### 5. 工具系统 (`tool/manager.py`)
+
+基于 MCP 协议，支持三种传输：
+- **stdio**: 本地进程（`npx`, `python` 脚本）
+- **streamable-http**: HTTP 远程服务
+- **sse**: Server-Sent Events
+
+工具配置 YAML 示例：
+```yaml
+name: tool-searching
+tool_command: npx
+args: ["-y", "@anthropic/tool-searching"]
+env:
+  SERPER_API_KEY: "${oc.env:SERPER_API_KEY,}"
+```
+
+### 6. Prompt 系统 (`prompts/`)
+
+`AgentPrompt` 统一类，通过配置组合模板：
+
+```yaml
+prompt:
+  agent_type: main           # main | worker
+  tool_format: xml           # xml | native
+  presets: [research, time_sensitive]  # 可选预设
+  custom_system_template: my_prompt    # 自定义模板
+```
+
+模板位于 `prompts/templates/`，用 `{{variable}}` 占位符，`PromptTemplateLoader` 加载渲染。
+
+### 7. LLM 客户端 (`llm/`)
+
+所有 provider 继承 `LLMProviderClientBase`，关键方法：
+- `call_llm(system_prompt, messages, tool_definitions)` — 调用 LLM
+- `update_message_history(history, tool_results, exceeded)` — 更新消息历史
+- `_estimate_tokens(text)` — token 估算
+
+## 配置说明 (`config_schema.py`)
+
+```yaml
+main_agent:
+  prompt:
+    agent_type: main
+    tool_format: xml
+    presets: []
+  llm:
+    provider_class: "ClaudeOpenRouterClient"
+    model_name: "anthropic/claude-sonnet-4"
+    temperature: 0.3
+    max_tokens: 32000
+    max_context_length: 128000    # -1 = 不限制
+    keep_tool_result: 5           # -1 全部保留, N 保留最近 N 个
+  tool_config: [tool-reading, tool-searching]
+  max_turns: 20
+  max_tool_calls_per_turn: 10
+  chinese_context: false
+  skill_selection:
+    enabled: true
+    method: inline               # rules | llm | inline
+    max_skills: 3
+  context_manager:
+    enable_dedup: true
+    enable_compact: true
+    compact_at_ratio: 0.6
+    summarize_at_ratio: 0.8
+    compact_keep_recent: 3
+  deep_research:
+    enabled: false
+    reflection_interval: 5
+    auto_planning: false
+```
+
+## 开发规范
+
+- Python 3.12+，全异步设计
+- 测试运行：`python -m pytest tests/ -v`
+- 配置验证用 Pydantic，运行时配置用 OmegaConf (Hydra)
+- 工具遵循 MCP (Model Context Protocol) 规范
+- 框架无状态，所有定制通过项目级 config + hooks.py 注入
+- 新增核心功能需在 `config_schema.py` 添加配置项并设合理默认值

mem_deep_research-0.1.0/CONTRIBUTING.md

@@ -0,0 +1,46 @@
+# Contributing to Mem Deep Research
+
+Thank you for your interest in contributing!
+
+## Development Setup
+
+```bash
+git clone https://github.com/cjhyy/mem-deep-research.git
+cd mem-deep-research
+python -m venv .venv
+source .venv/bin/activate
+pip install -e ".[dev]"
+```
+
+## Running Tests
+
+```bash
+python -m pytest tests/ -v
+```
+
+## Code Style
+
+This project uses [Ruff](https://docs.astral.sh/ruff/) for linting and formatting:
+
+```bash
+ruff check .
+ruff format .
+```
+
+## Pull Request Process
+
+1. Fork the repository and create your branch from `main`
+2. Add tests for any new functionality
+3. Ensure all tests pass
+4. Update documentation if needed
+5. Submit a pull request
+
+## Reporting Issues
+
+- Use GitHub Issues for bug reports and feature requests
+- Include reproduction steps, expected behavior, and actual behavior
+- For security vulnerabilities, please email chenjunhong54321@163.com directly
+
+## License
+
+By contributing, you agree that your contributions will be licensed under the Apache License 2.0.

mem_deep_research-0.1.0/LICENSE

@@ -0,0 +1,190 @@
+                                 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 the 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 the 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 any 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
+
+   Copyright 2026 Mem Deep Research Contributors
+
+   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.