feat: memorycollection implement by penghuima · Pull Request #32 · Serverless-Devs/agentrun-sdk-python

penghuima · 2026-01-12T10:46:17Z

Change-Id: I096c2a825dac99b411fa69db63cc6693cd67630e
Co-developed-by: Cursor noreply@cursor.com

Thank you for creating a pull request to contribute to Serverless Devs agentrun-sdk-python code! Before you open the request please answer the following questions to help it be more easily integrated. Please check the boxes "[ ]" with "[x]" when done too.
Please select one of the PR types below to complete

Fix bugs

Bug detail

The specific manifestation of the bug or the associated issue.

Pull request tasks

Add test cases for the changes
Passed the CI test

Update docs

Reason for update

Why do you need to update your documentation?

Pull request tasks

Update Chinese documentation
Update English documentation

Add contributor

Contributed content

Code
Document

Content detail

if content_type == 'code' || content_type == 'document':
    please tell us `PR url`，like: https://github.com/Serverless-Devs/agentrun-sdk-python/pull/1
else:
    please describe your contribution in detail

Others

Reason for update

Why do you need to update your documentation?

Copilot

Pull request overview

This pull request implements the MemoryCollection module for managing memory collections in the agentrun SDK, including integration with mem0ai for memory management capabilities.

Changes:

Adds new agentrun.memory_collection module with client, models, high-level API, and control API
Implements mem0ai integration through a to_mem0_memory method that converts MemoryCollection to mem0 Memory client
Adds optional dependency agentrun-mem0ai>=0.0.3 in pyproject.toml
Includes example code demonstrating MemoryCollection usage
Updates build configuration (Makefile) to include memory_collection code generation

Reviewed changes

Copilot reviewed 13 out of 13 changed files in this pull request and generated 13 comments.

Show a summary per file

File	Description
pyproject.toml	Adds mem0 optional dependency for agentrun-mem0ai package
examples/memory_collection_example.py	Provides usage examples for MemoryCollection with client and high-level API
codegen/configs/memory_collection_control_api.yaml	Configuration for code generation of control API
agentrun/memory_collection/model.py	Defines data models for MemoryCollection including configs and input/output types
agentrun/memory_collection/memory_collection.py	High-level API for MemoryCollection with CRUD operations and mem0 integration
agentrun/memory_collection/client.py	Client implementation with async/sync methods for memory collection management
agentrun/memory_collection/api/control.py	Control API layer for making HTTP requests to backend service
agentrun/memory_collection/api/init.py	API module initialization and exports
agentrun/memory_collection/__memory_collection_async_template.py	Template for generating async MemoryCollection implementation
agentrun/memory_collection/init.py	Module initialization and public API exports
agentrun/memory_collection/__client_async_template.py	Template for generating async client implementation
agentrun/init.py	Updates root module to export MemoryCollection types and classes
Makefile	Adds memory_collection to code generation targets

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

examples/memory_collection_example.py

agentrun/memory_collection/client.py

agentrun/memory_collection/api/control.py

Copilot · 2026-01-12T11:04:16Z

agentrun/memory_collection/memory_collection.py

+        if history_db_path:
+            mem0_config["history_db_path"] = history_db_path
+
+        return mem0_config
+
+    @staticmethod
+    async def _resolve_model_service_config_async(
+        model_service_name: str, config: Optional[Config]
+    ) -> Tuple[str, str]:
+        """解析 ModelService 配置获取 baseUrl 和 apiKey（异步）
+
+        Args:
+            model_service_name: ModelService 名称
+            config: AgentRun 配置
+
+        Returns:
+            Tuple[str, str]: (base_url, api_key)
+
+        Raises:
+            ValueError: 如果配置信息不完整
+        """
+        from agentrun.credential import Credential
+        from agentrun.model import ModelService
+
+        # 使用高层 API 获取 ModelService
+        model_service = await ModelService.get_by_name_async(
+            model_service_name, config=config
+        )
+
+        # 获取 provider_settings
+        if not model_service.provider_settings:
+            raise ValueError(
+                f"ModelService {model_service_name} providerSettings is empty"
+            )
+
+        base_url = model_service.provider_settings.base_url or ""
+        api_key = model_service.provider_settings.api_key or ""
+
+        # 如果有 credentialName，使用高层 API 获取 credential secret
+        credential_name = model_service.credential_name
+        if credential_name:
+            credential = await Credential.get_by_name_async(
+                credential_name, config=config
+            )
+            if credential.credential_secret:
+                api_key = credential.credential_secret
+
+        if not base_url:
+            raise ValueError(
+                f"ModelService {model_service_name} baseUrl is empty"
+            )
+
+        return base_url, api_key
+
+    @staticmethod
+    def _resolve_model_service_config(
+        model_service_name: str, config: Optional[Config]
+    ) -> Tuple[str, str]:
+        """解析 ModelService 配置获取 baseUrl 和 apiKey（同步）
+
+        Args:
+            model_service_name: ModelService 名称
+            config: AgentRun 配置
+
+        Returns:
+            Tuple[str, str]: (base_url, api_key)
+
+        Raises:
+            ValueError: 如果配置信息不完整
+        """
+        from agentrun.credential import Credential
+        from agentrun.model import ModelService
+
+        # 使用高层 API 获取 ModelService
+        model_service = ModelService.get_by_name(
+            model_service_name, config=config
+        )
+
+        # 获取 provider_settings
+        if not model_service.provider_settings:
+            raise ValueError(
+                f"ModelService {model_service_name} providerSettings is empty"
+            )
+
+        base_url = model_service.provider_settings.base_url or ""
+        api_key = model_service.provider_settings.api_key or ""
+
+        # 如果有 credentialName，使用高层 API 获取 credential secret
+        credential_name = model_service.credential_name
+        if credential_name:
+            credential = Credential.get_by_name(credential_name, config=config)
+            if credential.credential_secret:
+                api_key = credential.credential_secret
+
+        if not base_url:
+            raise ValueError(
+                f"ModelService {model_service_name} baseUrl is empty"
+            )
+
+        return base_url, api_key


The new MemoryCollection module lacks test coverage. The repository has comprehensive test coverage for other modules (agent_runtime, credential, model, toolset) in the tests/unittests directory, but there are no tests for the memory_collection module. Consider adding unit tests to cover the client, model, and memory_collection classes, especially for critical functionality like the mem0 integration and error handling.

Copilot · 2026-01-12T11:04:17Z

examples/memory_collection_example.py

+    # 方式一：使用 Client
+    # Method 1: Using Client
+    print("=== 使用 MemoryCollectionClient ===")
+    client = MemoryCollectionClient(config)


Variable client is not used.

Copilot · 2026-01-12T11:04:17Z

examples/memory_collection_example.py

+
+    # 创建记忆集合
+    # Create memory collection
+    create_input = MemoryCollectionCreateInput(


Variable create_input is not used.

examples/memory_collection_example.py

Copilot · 2026-01-12T11:04:18Z

agentrun/memory_collection/model.py

+Defines data models and enumerations related to memory collections.
+"""
+
+from typing import Any, Dict, List, Optional


Import of 'Any' is not used.
Import of 'Dict' is not used.

Suggested change

from typing import Any, Dict, List, Optional

from typing import List, Optional

Change-Id: I096c2a825dac99b411fa69db63cc6693cd67630e Co-developed-by: Cursor <noreply@cursor.com> Signed-off-by: 久氢 <mapenghui.mph@alibaba-inc.com>

Change-Id: I187d0e5d54abc79d4ed3d256253bd442988a9ff7 Co-developed-by: Cursor <noreply@cursor.com> Signed-off-by: 久氢 <mapenghui.mph@alibaba-inc.com>

OhYee requested a review from Copilot January 12, 2026 10:54

Copilot started reviewing on behalf of OhYee January 12, 2026 10:54 View session

Copilot AI reviewed Jan 12, 2026

View reviewed changes

久氢 added 2 commits January 13, 2026 12:08

feat: memorycollection implement

fb3645b

Change-Id: I096c2a825dac99b411fa69db63cc6693cd67630e Co-developed-by: Cursor <noreply@cursor.com> Signed-off-by: 久氢 <mapenghui.mph@alibaba-inc.com>

feat: memorycollection implement

61f64dc

Change-Id: I187d0e5d54abc79d4ed3d256253bd442988a9ff7 Co-developed-by: Cursor <noreply@cursor.com> Signed-off-by: 久氢 <mapenghui.mph@alibaba-inc.com>

penghuima force-pushed the dev branch from 03fc42d to 61f64dc Compare January 13, 2026 04:11

OhYee closed this pull request by merging all changes into Serverless-Devs:main in d762343 Jan 13, 2026

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat: memorycollection implement#32

feat: memorycollection implement#32
2 commits merged intoServerless-Devs:mainfrom
penghuima:dev

penghuima commented Jan 12, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI Jan 12, 2026

Uh oh!

Copilot AI Jan 12, 2026

Uh oh!

Copilot AI Jan 12, 2026

Uh oh!

Uh oh!

Copilot AI Jan 12, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

	from typing import Any, Dict, List, Optional
	from typing import List, Optional

Conversation

penghuima commented Jan 12, 2026

Fix bugs

Update docs

Add contributor

Others

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI Jan 12, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 12, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 12, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Copilot AI Jan 12, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants