Compare commits
15 Commits
2774069f8e
...
314a693793
| Author | SHA1 | Date | |
|---|---|---|---|
|
314a693793 | ||
|
|
044749e2ce | ||
|
|
1321471202 | ||
|
|
05e22391ed | ||
|
|
b33acf9da0 | ||
|
|
ee65d208a8 | ||
|
|
2d82d7c8b6 | ||
|
|
eda54757e6 | ||
|
|
822589eab6 | ||
|
|
709a967537 | ||
|
|
0c985607b5 | ||
|
|
a161e43421 | ||
|
|
deb78a7625 | ||
|
|
0a6ec95518 | ||
| 393d8c7c37 |
@ -108,7 +108,7 @@ workflows:
|
||||
filters:
|
||||
branches:
|
||||
only:
|
||||
- master
|
||||
- dev
|
||||
- deploy:
|
||||
name: deploy-for-test
|
||||
docker-tag: ''
|
||||
@ -120,7 +120,7 @@ workflows:
|
||||
filters:
|
||||
branches:
|
||||
only:
|
||||
- master
|
||||
- dev
|
||||
requires:
|
||||
- build-for-test
|
||||
- build-and-push:
|
||||
@ -183,7 +183,7 @@ workflows:
|
||||
filters:
|
||||
branches:
|
||||
only:
|
||||
- onprem
|
||||
- onprem-release
|
||||
- docker-hub-build-push:
|
||||
name: docker-hub-build-push-arm
|
||||
repo: gptbasesparticle/catalog-agent
|
||||
@ -192,4 +192,31 @@ workflows:
|
||||
filters:
|
||||
branches:
|
||||
only:
|
||||
- onprem
|
||||
- onprem-release
|
||||
# 为 onprem-dev 环境部署
|
||||
- build-and-push:
|
||||
name: build-for-onprem-dev
|
||||
context:
|
||||
- ecr-new
|
||||
path: .
|
||||
dockerfile: Dockerfile
|
||||
repo: catalog-agent
|
||||
docker-tag: ''
|
||||
filters:
|
||||
branches:
|
||||
only:
|
||||
- onprem-dev
|
||||
- deploy:
|
||||
name: deploy-for-onprem-dev
|
||||
docker-tag: ''
|
||||
path: '/home/ubuntu/cluster-for-B/onprem-dev/catalog-agent/deploy.yaml'
|
||||
deploy-name: catalog-agent
|
||||
deploy-namespace: onprem-dev
|
||||
context:
|
||||
- ecr-new
|
||||
filters:
|
||||
branches:
|
||||
only:
|
||||
- onprem-dev
|
||||
requires:
|
||||
- build-for-onprem-dev
|
||||
|
||||
435
docs/file_manage_apis.md
Normal file
435
docs/file_manage_apis.md
Normal file
@ -0,0 +1,435 @@
|
||||
# 文件管理 API 接口文档
|
||||
|
||||
**Base URL:** `/api/v1/file-manager`
|
||||
|
||||
---
|
||||
|
||||
## 1. 列出目录内容
|
||||
|
||||
**GET** `/api/v1/file-manager/list`
|
||||
|
||||
| 参数 | 类型 | 位置 | 必填 | 说明 |
|
||||
|------|------|------|------|------|
|
||||
| path | string | query | 否 | 相对路径，空字符串返回根目录（projects/prompt） |
|
||||
| recursive | bool | query | 否 | 是否递归列出子目录，默认 false |
|
||||
|
||||
```bash
|
||||
curl -X GET "/api/v1/file-manager/list?path=projects&recursive=false"
|
||||
```
|
||||
|
||||
响应示例：
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"path": "projects",
|
||||
"items": [
|
||||
{
|
||||
"name": "report.pdf",
|
||||
"path": "projects/report.pdf",
|
||||
"type": "file",
|
||||
"size": 102400,
|
||||
"modified": 1700000000.0,
|
||||
"created": 1699000000.0
|
||||
}
|
||||
],
|
||||
"total": 1
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 2. 上传文件
|
||||
|
||||
**POST** `/api/v1/file-manager/upload`
|
||||
|
||||
请求方式：表单数据上传（multipart/form-data）
|
||||
|
||||
| 参数 | 类型 | 位置 | 必填 | 说明 |
|
||||
|------|------|------|------|------|
|
||||
| file | file | form | 是 | 上传的文件 |
|
||||
| path | string | form | 否 | 目标目录路径，默认 `projects` |
|
||||
|
||||
```bash
|
||||
curl -X POST "/api/v1/file-manager/upload" \
|
||||
-F "file=@document.pdf" \
|
||||
-F "path=projects/dataset"
|
||||
```
|
||||
|
||||
响应示例：
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"message": "文件上传成功",
|
||||
"filename": "document.pdf",
|
||||
"original_filename": "document.pdf",
|
||||
"path": "projects/dataset/document.pdf",
|
||||
"size": 102400
|
||||
}
|
||||
```
|
||||
|
||||
> 注：文件名中的空格会自动替换为下划线。
|
||||
|
||||
---
|
||||
|
||||
## 3. 下载文件
|
||||
|
||||
**GET** `/api/v1/file-manager/download/{file_path}`
|
||||
|
||||
| 参数 | 类型 | 位置 | 必填 | 说明 |
|
||||
|------|------|------|------|------|
|
||||
| file_path | string | path | 是 | 文件相对路径 |
|
||||
|
||||
```bash
|
||||
curl -X GET "/api/v1/file-manager/download/projects/report.pdf" -o report.pdf
|
||||
```
|
||||
|
||||
响应：文件二进制流，`Content-Type` 根据文件类型自动推断。
|
||||
|
||||
---
|
||||
|
||||
## 4. 删除文件或目录
|
||||
|
||||
**DELETE** `/api/v1/file-manager/delete`
|
||||
|
||||
| 参数 | 类型 | 位置 | 必填 | 说明 |
|
||||
|------|------|------|------|------|
|
||||
| path | string | query | 是 | 要删除的路径 |
|
||||
|
||||
```bash
|
||||
curl -X DELETE "/api/v1/file-manager/delete?path=projects/report.pdf"
|
||||
```
|
||||
|
||||
响应示例：
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"message": "文件删除成功",
|
||||
"path": "projects/report.pdf"
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 5. 创建文件夹
|
||||
|
||||
**POST** `/api/v1/file-manager/create-folder`
|
||||
|
||||
请求方式：JSON
|
||||
|
||||
| 参数 | 类型 | 位置 | 必填 | 说明 |
|
||||
|------|------|------|------|------|
|
||||
| path | string | body | 否 | 父目录路径，默认 `projects` |
|
||||
| name | string | body | 是 | 文件夹名称 |
|
||||
|
||||
```bash
|
||||
curl -X POST "/api/v1/file-manager/create-folder" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"path": "projects", "name": "new-folder"}'
|
||||
```
|
||||
|
||||
响应示例：
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"message": "文件夹创建成功",
|
||||
"path": "projects/new-folder"
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 6. 重命名文件或文件夹
|
||||
|
||||
**POST** `/api/v1/file-manager/rename`
|
||||
|
||||
| 参数 | 类型 | 位置 | 必填 | 说明 |
|
||||
|------|------|------|------|------|
|
||||
| old_path | string | query | 是 | 原路径 |
|
||||
| new_name | string | query | 是 | 新名称 |
|
||||
|
||||
```bash
|
||||
curl -X POST "/api/v1/file-manager/rename?old_path=projects/old-name.pdf&new_name=new-name.pdf"
|
||||
```
|
||||
|
||||
响应示例：
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"message": "重命名成功",
|
||||
"old_path": "projects/old-name.pdf",
|
||||
"new_path": "projects/new-name.pdf"
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 7. 移动文件或文件夹
|
||||
|
||||
**POST** `/api/v1/file-manager/move`
|
||||
|
||||
| 参数 | 类型 | 位置 | 必填 | 说明 |
|
||||
|------|------|------|------|------|
|
||||
| source_path | string | query | 是 | 源路径 |
|
||||
| target_path | string | query | 是 | 目标路径 |
|
||||
|
||||
```bash
|
||||
curl -X POST "/api/v1/file-manager/move?source_path=projects/a.pdf&target_path=projects/sub/a.pdf"
|
||||
```
|
||||
|
||||
响应示例：
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"message": "移动成功",
|
||||
"source_path": "projects/a.pdf",
|
||||
"target_path": "projects/sub/a.pdf"
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 8. 复制文件或文件夹
|
||||
|
||||
**POST** `/api/v1/file-manager/copy`
|
||||
|
||||
| 参数 | 类型 | 位置 | 必填 | 说明 |
|
||||
|------|------|------|------|------|
|
||||
| source_path | string | query | 是 | 源路径 |
|
||||
| target_path | string | query | 是 | 目标路径 |
|
||||
|
||||
```bash
|
||||
curl -X POST "/api/v1/file-manager/copy?source_path=projects/a.pdf&target_path=projects/a-copy.pdf"
|
||||
```
|
||||
|
||||
响应示例：
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"message": "复制成功",
|
||||
"source_path": "projects/a.pdf",
|
||||
"target_path": "projects/a-copy.pdf"
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 9. 搜索文件
|
||||
|
||||
**GET** `/api/v1/file-manager/search`
|
||||
|
||||
| 参数 | 类型 | 位置 | 必填 | 说明 |
|
||||
|------|------|------|------|------|
|
||||
| query | string | query | 是 | 搜索关键词（匹配文件名） |
|
||||
| path | string | query | 否 | 搜索路径，为空则搜索所有支持目录 |
|
||||
| file_type | string | query | 否 | 文件类型过滤（如 `.pdf`） |
|
||||
|
||||
```bash
|
||||
curl -X GET "/api/v1/file-manager/search?query=report&path=projects&file_type=.pdf"
|
||||
```
|
||||
|
||||
响应示例：
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"query": "report",
|
||||
"path": "projects",
|
||||
"results": [
|
||||
{
|
||||
"name": "report.pdf",
|
||||
"path": "projects/report.pdf",
|
||||
"type": "file"
|
||||
}
|
||||
],
|
||||
"total": 1
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 10. 读取文件内容
|
||||
|
||||
**GET** `/api/v1/file-manager/read`
|
||||
|
||||
| 参数 | 类型 | 位置 | 必填 | 说明 |
|
||||
|------|------|------|------|------|
|
||||
| path | string | query | 是 | 文件相对路径 |
|
||||
|
||||
```bash
|
||||
curl -X GET "/api/v1/file-manager/read?path=projects/config.json"
|
||||
```
|
||||
|
||||
响应示例：
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"content": "{\"key\": \"value\"}",
|
||||
"path": "projects/config.json",
|
||||
"size": 16,
|
||||
"modified": 1700000000.0,
|
||||
"encoding": "utf-8",
|
||||
"mime_type": "application/json"
|
||||
}
|
||||
```
|
||||
|
||||
> 限制：最大 10MB。自动尝试 utf-8 / gbk / gb2312 / latin-1 编码。
|
||||
|
||||
---
|
||||
|
||||
## 11. 保存文件内容
|
||||
|
||||
**POST** `/api/v1/file-manager/save`
|
||||
|
||||
请求方式：JSON
|
||||
|
||||
| 参数 | 类型 | 位置 | 必填 | 说明 |
|
||||
|------|------|------|------|------|
|
||||
| path | string | body | 是 | 文件相对路径 |
|
||||
| content | string | body | 是 | 文件内容 |
|
||||
|
||||
```bash
|
||||
curl -X POST "/api/v1/file-manager/save" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"path": "projects/config.json", "content": "{\"key\": \"new-value\"}"}'
|
||||
```
|
||||
|
||||
响应示例：
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"message": "文件保存成功",
|
||||
"path": "projects/config.json",
|
||||
"size": 20,
|
||||
"modified": 1700000000.0,
|
||||
"encoding": "utf-8"
|
||||
}
|
||||
```
|
||||
|
||||
> 限制：最大 5MB。保存前自动创建备份，写入失败时自动回滚。
|
||||
|
||||
---
|
||||
|
||||
## 12. 获取文件/文件夹详细信息
|
||||
|
||||
**GET** `/api/v1/file-manager/info/{file_path}`
|
||||
|
||||
| 参数 | 类型 | 位置 | 必填 | 说明 |
|
||||
|------|------|------|------|------|
|
||||
| file_path | string | path | 是 | 文件或文件夹路径 |
|
||||
|
||||
```bash
|
||||
curl -X GET "/api/v1/file-manager/info/projects/report.pdf"
|
||||
```
|
||||
|
||||
响应示例：
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"info": {
|
||||
"name": "report.pdf",
|
||||
"path": "projects/report.pdf",
|
||||
"type": "file",
|
||||
"size": 102400,
|
||||
"modified": 1700000000.0,
|
||||
"created": 1699000000.0,
|
||||
"permissions": "644",
|
||||
"mime_type": "application/pdf",
|
||||
"preview": "文件前1000字符预览..."
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
> 小于 1MB 的文本文件会包含 `preview` 字段。
|
||||
|
||||
---
|
||||
|
||||
## 13. 下载文件夹为 ZIP
|
||||
|
||||
**POST** `/api/v1/file-manager/download-folder-zip`
|
||||
|
||||
请求方式：JSON
|
||||
|
||||
| 参数 | 类型 | 位置 | 必填 | 说明 |
|
||||
|------|------|------|------|------|
|
||||
| path | string | body | 是 | 文件夹路径 |
|
||||
|
||||
```bash
|
||||
curl -X POST "/api/v1/file-manager/download-folder-zip" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"path": "projects/dataset"}' -o dataset.zip
|
||||
```
|
||||
|
||||
响应：ZIP 文件二进制流（`application/zip`）。
|
||||
|
||||
> 限制：最大 500MB，最多 10000 个文件。
|
||||
|
||||
---
|
||||
|
||||
## 14. 批量下载为 ZIP
|
||||
|
||||
**POST** `/api/v1/file-manager/download-multiple-zip`
|
||||
|
||||
请求方式：JSON
|
||||
|
||||
| 参数 | 类型 | 位置 | 必填 | 说明 |
|
||||
|------|------|------|------|------|
|
||||
| paths | string[] | body | 是 | 文件/文件夹路径数组 |
|
||||
| filename | string | body | 否 | ZIP 文件名，默认 `batch_download.zip` |
|
||||
|
||||
```bash
|
||||
curl -X POST "/api/v1/file-manager/download-multiple-zip" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"paths": ["projects/a.pdf", "projects/sub"], "filename": "export.zip"}' \
|
||||
-o export.zip
|
||||
```
|
||||
|
||||
响应：ZIP 文件二进制流（`application/zip`）。
|
||||
|
||||
> 限制：最大 500MB，最多 10000 个文件。
|
||||
|
||||
---
|
||||
|
||||
## 15. 批量操作
|
||||
|
||||
**POST** `/api/v1/file-manager/batch-operation`
|
||||
|
||||
请求方式：JSON（操作数组）
|
||||
|
||||
支持操作类型：`delete` / `move` / `copy`
|
||||
|
||||
```bash
|
||||
curl -X POST "/api/v1/file-manager/batch-operation" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '[
|
||||
{"type": "delete", "path": "projects/old.pdf"},
|
||||
{"type": "move", "source_path": "projects/a.pdf", "target_path": "projects/archive/a.pdf"},
|
||||
{"type": "copy", "source_path": "projects/b.pdf", "target_path": "projects/backup/b.pdf"}
|
||||
]'
|
||||
```
|
||||
|
||||
响应示例：
|
||||
```json
|
||||
{
|
||||
"success": true,
|
||||
"results": [
|
||||
{"type": "delete", "success": true, "message": "删除成功"},
|
||||
{"type": "move", "success": true, "message": "移动成功"},
|
||||
{"type": "copy", "success": true, "message": "复制成功"}
|
||||
],
|
||||
"total": 3,
|
||||
"successful": 3
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 通用说明
|
||||
|
||||
- **路径约束**：所有路径必须以 `projects` 或 `prompt` 开头，否则返回 400
|
||||
- **安全机制**：路径经过规范化处理，防止目录遍历攻击
|
||||
- **隐藏文件**：以 `.` 开头的文件/目录在列出和搜索时自动跳过
|
||||
- **错误响应格式**：
|
||||
```json
|
||||
{
|
||||
"detail": "错误描述信息"
|
||||
}
|
||||
```
|
||||
@ -148,6 +148,21 @@ Output: {{"facts" : []}}
|
||||
Input: DR1の照明状態を教えて
|
||||
Output: {{"facts" : []}}
|
||||
|
||||
Input: 私は林檎好きです
|
||||
Output: {{"facts" : ["林檎が好き"]}}
|
||||
|
||||
Input: コーヒー飲みたい、毎朝
|
||||
Output: {{"facts" : ["毎朝コーヒーを飲みたい"]}}
|
||||
|
||||
Input: 昨日映画見た、すごくよかった
|
||||
Output: {{"facts" : ["昨日映画を見た", "映画がすごくよかった"]}}
|
||||
|
||||
Input: 我喜欢吃苹果
|
||||
Output: {{"facts" : ["喜欢吃苹果"]}}
|
||||
|
||||
Input: 나는 사과를 좋아해
|
||||
Output: {{"facts" : ["사과를 좋아함"]}}
|
||||
|
||||
Return the facts and preferences in a json format as shown above.
|
||||
|
||||
Remember the following:
|
||||
@ -159,12 +174,15 @@ Remember the following:
|
||||
- If you do not find anything relevant in the below conversation, you can return an empty list corresponding to the "facts" key.
|
||||
- Create the facts based on the user and assistant messages only. Do not pick anything from the system messages.
|
||||
- Make sure to return the response in the format mentioned in the examples. The response should be in json with a key as "facts" and corresponding value will be a list of strings.
|
||||
|
||||
- **CRITICAL - Do NOT memorize actions or operations**: Do not extract facts about queries the user asked you to perform, devices the user asked you to operate, or any one-time transient actions. Only memorize information ABOUT the user (preferences, relationships, personal details, plans), not actions the user asked the assistant to DO. Ask yourself: "Is this a fact about WHO the user IS, or what the user asked me to DO?" Only remember the former.
|
||||
|
||||
- **CRITICAL for Semantic Completeness**:
|
||||
- Each extracted fact MUST preserve the complete semantic meaning. Never truncate or drop key parts of the meaning.
|
||||
- For colloquial or grammatically informal expressions (common in spoken Japanese, Chinese, Korean, etc.), understand the full intended meaning and record it in a clear, semantically complete form.
|
||||
- In Japanese, spoken language often omits particles (e.g., が, を, に). When extracting facts, include the necessary particles to make the meaning unambiguous. For example: "私は林檎好きです" should be understood as "林檎が好き" (likes apples), not literally "私は林檎好き".
|
||||
- When the user expresses a preference or opinion in casual speech, record the core preference/opinion clearly. Remove the subject pronoun (私は/I) since facts are about the user by default, but keep all other semantic components intact.
|
||||
|
||||
- **CRITICAL for People/Relationship Tracking**:
|
||||
- Write people-related facts in plain, natural language. Do NOT use structured formats like "Contact:", "referred as", or "DEFAULT when user says".
|
||||
- Good examples: "Michael Johnson is a colleague, also called Mike", "田中さんは友達", "滨田太郎は「滨田」とも呼ばれている"
|
||||
|
||||
@ -14,7 +14,19 @@ The filesystem backend is currently operating in: `{agent_dir_path}`
|
||||
- Never use relative paths in bash commands - always construct full absolute paths
|
||||
- Use the working directory from <env> to construct absolute paths
|
||||
|
||||
**2. Skill Script Path Conversion**
|
||||
**2. Skills vs Tools - CRITICAL DISTINCTION**
|
||||
|
||||
**Skills are NOT tools.** Do NOT attempt to call a skill as a tool_call/function_call.
|
||||
|
||||
- **Tools** (e.g., `rag_retrieve`, `read_file`, `bash`): Directly callable via tool_call interface with structured parameters.
|
||||
- **Skills** (e.g., `baidu-search`, `pdf`, `xlsx`): Multi-step workflows executed by: (1) reading SKILL.md, (2) extracting the command, (3) running it via the `bash` tool.
|
||||
|
||||
❌ WRONG: Generating a tool_call with `{"name": "baidu-search", "arguments": {...}}`
|
||||
✅ CORRECT: Using `read_file` to read SKILL.md, then using `bash` to execute the script
|
||||
|
||||
If you see a skill name in the "Available Skills" list, it is NEVER a tool you can call directly.
|
||||
|
||||
**3. Skill Script Path Conversion**
|
||||
|
||||
When executing scripts from SKILL.md files, you MUST convert relative paths to absolute paths:
|
||||
|
||||
@ -29,14 +41,14 @@ When executing scripts from SKILL.md files, you MUST convert relative paths to a
|
||||
└── scriptB.py # Actual script B file
|
||||
```
|
||||
|
||||
**3. Workspace Directory Structure**
|
||||
**4. Workspace Directory Structure**
|
||||
|
||||
- **`{agent_dir_path}/skills/`** - Skill packages with embedded scripts
|
||||
- **`{agent_dir_path}/dataset/`** - Store file datasets and document data
|
||||
- **`{agent_dir_path}/executable_code/`** - Place generated executable scripts here (not skill scripts)
|
||||
- **`{agent_dir_path}/download/`** - Store downloaded files and content
|
||||
|
||||
**4. Executable Code Organization**
|
||||
**5. Executable Code Organization**
|
||||
|
||||
When creating scripts in `executable_code/`, follow these organization rules:
|
||||
|
||||
@ -80,3 +92,15 @@ Trace Id: {trace_id}
|
||||
- Even when the user writes in a different language, you MUST still reply in [{language}].
|
||||
- Do NOT mix languages. Do NOT fall back to English or any other language under any circumstances.
|
||||
- Technical terms, code identifiers, file paths, and tool names may remain in their original form, but all surrounding text MUST be in [{language}].
|
||||
|
||||
**Citation Requirement (RAG Only)**: When answering questions based on `rag_retrieve` tool results, you MUST add XML citation tags for factual claims derived from the knowledge base.
|
||||
|
||||
**MANDATORY FORMAT**: `The cited factual claim <CITATION file="file_uuid" page="3" />`
|
||||
|
||||
**Citation Rules**:
|
||||
- The citation tag MUST be placed immediately after the factual claim or paragraph
|
||||
- The `file` attribute MUST use the exact `File ID` from `rag_retrieve` document
|
||||
- The `page` attribute MUST use the exact `Page Number` from `rag_retrieve` document
|
||||
- If multiple sources support the same claim, include separate citation tags for each source
|
||||
- Example: `According to the policy, returns are accepted within 30 days <CITATION file="abc123" page="5" />.`
|
||||
- This requirement ONLY applies when using `rag_retrieve` results to answer questions.
|
||||
|
||||
@ -83,6 +83,18 @@ When using the write_todos tool:
|
||||
|
||||
The todo list is a planning tool - use it judiciously to avoid overwhelming the user with excessive task tracking.
|
||||
|
||||
### Skills vs Tools - CRITICAL DISTINCTION
|
||||
|
||||
**Skills are NOT tools.** Do NOT attempt to call a skill as a tool_call/function_call.
|
||||
|
||||
- **Tools** (e.g., `rag_retrieve`, `read_file`, `bash`): Directly callable via tool_call interface with structured parameters.
|
||||
- **Skills** (e.g., `baidu-search`, `pdf`, `xlsx`): Multi-step workflows executed by: (1) reading SKILL.md, (2) extracting the command, (3) running it via the `bash` tool.
|
||||
|
||||
❌ WRONG: Generating a tool_call with `{"name": "baidu-search", "arguments": {...}}`
|
||||
✅ CORRECT: Using `read_file` to read SKILL.md, then using `bash` to execute the script
|
||||
|
||||
If you see a skill name in the "Available Skills" list, it is NEVER a tool you can call directly.
|
||||
|
||||
### Skill Execution Workflow
|
||||
|
||||
**CRITICAL**: When you need to use a skill, follow this exact workflow:
|
||||
|
||||
112
routes/memory.py
112
routes/memory.py
@ -1,13 +1,13 @@
|
||||
"""
|
||||
Memory 管理 API 路由
|
||||
提供记忆查看和删除功能
|
||||
提供记忆查看、添加和删除功能
|
||||
"""
|
||||
|
||||
import logging
|
||||
from typing import Optional, List, Dict, Any
|
||||
from typing import Literal, Optional, List, Dict, Any
|
||||
from fastapi import APIRouter, HTTPException, Header, Query
|
||||
from fastapi.responses import JSONResponse
|
||||
from pydantic import BaseModel
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
logger = logging.getLogger('app')
|
||||
|
||||
@ -33,6 +33,26 @@ class DeleteAllResponse(BaseModel):
|
||||
deleted_count: int
|
||||
|
||||
|
||||
class ConversationMessage(BaseModel):
|
||||
"""对话消息"""
|
||||
role: Literal["user", "assistant"]
|
||||
content: str = Field(..., min_length=1)
|
||||
|
||||
|
||||
class AddMemoryRequest(BaseModel):
|
||||
"""添加记忆的请求体"""
|
||||
bot_id: str = Field(..., min_length=1)
|
||||
user_id: str = Field(..., min_length=1)
|
||||
messages: List[ConversationMessage] = Field(..., max_length=200)
|
||||
|
||||
|
||||
class AddMemoryResponse(BaseModel):
|
||||
"""添加记忆的响应"""
|
||||
success: bool
|
||||
pairs_processed: int
|
||||
pairs_failed: int = 0
|
||||
|
||||
|
||||
async def get_user_identifier_from_request(
|
||||
authorization: Optional[str],
|
||||
user_id: Optional[str] = None
|
||||
@ -63,6 +83,92 @@ async def get_user_identifier_from_request(
|
||||
)
|
||||
|
||||
|
||||
@router.post("/memory", response_model=AddMemoryResponse)
|
||||
async def add_memory_from_conversation(data: AddMemoryRequest):
|
||||
"""
|
||||
从对话消息中提取并保存记忆
|
||||
|
||||
将用户和助手的对话配对，通过 Mem0 提取关键事实并存储。
|
||||
用于 realtime 语音对话等不经过 Agent 中间件的场景。
|
||||
此端点供内部服务调用（如 felo-mygpt），不暴露给外部用户。
|
||||
"""
|
||||
try:
|
||||
from agent.mem0_manager import get_mem0_manager
|
||||
from utils.settings import MEM0_ENABLED
|
||||
|
||||
if not MEM0_ENABLED:
|
||||
raise HTTPException(
|
||||
status_code=503,
|
||||
detail="Memory feature is not enabled"
|
||||
)
|
||||
|
||||
if not data.messages:
|
||||
return AddMemoryResponse(success=True, pairs_processed=0)
|
||||
|
||||
manager = get_mem0_manager()
|
||||
|
||||
# 将消息配对为 user-assistant 对，然后调用 add_memory
|
||||
pairs_processed = 0
|
||||
pairs_failed = 0
|
||||
i = 0
|
||||
while i < len(data.messages):
|
||||
msg = data.messages[i]
|
||||
if msg.role == 'user':
|
||||
# 收集连续的 user 消息
|
||||
user_contents = [msg.content]
|
||||
j = i + 1
|
||||
while j < len(data.messages) and data.messages[j].role == 'user':
|
||||
user_contents.append(data.messages[j].content)
|
||||
j += 1
|
||||
|
||||
user_text = '\n'.join(user_contents)
|
||||
|
||||
# 检查是否有对应的 assistant 回复
|
||||
assistant_text = ""
|
||||
if j < len(data.messages) and data.messages[j].role == 'assistant':
|
||||
assistant_text = data.messages[j].content or ""
|
||||
j += 1
|
||||
|
||||
if user_text and assistant_text:
|
||||
conversation_text = f"User: {user_text}\nAssistant: {assistant_text}"
|
||||
try:
|
||||
await manager.add_memory(
|
||||
text=conversation_text,
|
||||
user_id=data.user_id,
|
||||
agent_id=data.bot_id,
|
||||
metadata={"type": "realtime_conversation"},
|
||||
)
|
||||
pairs_processed += 1
|
||||
except Exception as pair_error:
|
||||
pairs_failed += 1
|
||||
logger.error(
|
||||
f"Failed to add memory for pair: {pair_error}"
|
||||
)
|
||||
|
||||
i = j
|
||||
else:
|
||||
i += 1
|
||||
|
||||
logger.info(
|
||||
f"Added {pairs_processed} memory pairs (failed={pairs_failed}) "
|
||||
f"for user={data.user_id}, bot={data.bot_id}"
|
||||
)
|
||||
return AddMemoryResponse(
|
||||
success=pairs_failed == 0,
|
||||
pairs_processed=pairs_processed,
|
||||
pairs_failed=pairs_failed,
|
||||
)
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to add memory from conversation: {e}")
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail="Failed to add memory from conversation"
|
||||
)
|
||||
|
||||
|
||||
@router.get("/memory", response_model=MemoryListResponse)
|
||||
async def get_memories(
|
||||
bot_id: str = Query(..., description="Bot ID (对应 agent_id)"),
|
||||
|
||||
Loading…
Reference in New Issue
Block a user