update openai server #3346

LuoPengcheng12138 · 2025-10-30T02:47:42Z

Description

Feat #3190

Checklist

Go over all the following points, and put an x in all the boxes that apply.

I have read the CONTRIBUTION guide (required)
I have linked this PR to an issue using the Development section on the right sidebar or by adding Fixes #issue-number in the PR description (required)
I have checked if any dependencies need to be added or updated in pyproject.toml and uv lock
I have updated the tests accordingly (required for a bug fix or a new feature)
I have updated the documentation if needed:
I have added examples if this is a new feature

If you are unsure about any of these, don't hesitate to ask. We are here to help!

coderabbitai · 2025-10-30T02:48:01Z

Important

Review skipped

Auto reviews are disabled on this repository.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

✨ Finishing touches

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment
Commit unit tests in branch feat/openai-compatible-server

Tip

📝 Customizable high-level summaries are now available in beta!

You can now customize how CodeRabbit generates the high-level summary in your pull requests — including its content, structure, tone, and formatting.

Provide your own instructions using the high_level_summary_instructions setting.
Format the summary however you like (bullet lists, tables, multi-section layouts, contributor stats, etc.).
Use high_level_summary_in_walkthrough to move the summary from the description to the walkthrough section.

Example instruction:

"Divide the high-level summary into five sections:

📝 Description — Summarize the main change in 50–60 words, explaining what was done.

📓 References — List relevant issues, discussions, documentation, or related PRs.

📦 Dependencies & Requirements — Mention any new/updated dependencies, environment variable changes, or configuration updates.

📊 Contributor Summary — Include a Markdown table showing contributions:
| Contributor | Lines Added | Lines Removed | Files Changed |

✔️ Additional Notes — Add any extra reviewer context.
Keep each section concise (under 200 words) and use bullet or numbered lists for clarity."

Note: This feature is currently in beta for Pro-tier users, and pricing will be announced later.

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

camel/agents/chat_agent.py

fengju0213 · 2025-10-30T06:18:07Z

@LuoPengcheng12138 thanks for this pr! is it a enhance pr based on https://github.com/camel-ai/camel/pull/2311/files？

LuoPengcheng12138 · 2025-10-30T06:39:07Z

@LuoPengcheng12138 thanks for this pr! is it a enhance pr based on https://github.com/camel-ai/camel/pull/2311/files？

Yes, it was copied from PR2311. When I tried merging main into 2311, the operation couldn’t be completed due to numerous conflicts with the main branch(maybe), so I created a new branch instead. Could you help me merge main into 2311 if needed?

fengju0213 · 2025-10-30T06:43:07Z

@LuoPengcheng12138 thanks for this pr! is it a enhance pr based on https://github.com/camel-ai/camel/pull/2311/files？

Yes, it was copied from PR2311. When I tried merging main into 2311, the operation couldn’t be completed due to numerous conflicts with the main branch(maybe), so I created a new branch instead. Could you help me merge main into 2311 if needed?

i see，maybe It's been a while since 2311 last update. will help to merge main to 2311

Wendong-Fan

thanks @LuoPengcheng12138 , left some initial comments below

Wendong-Fan · 2025-11-01T14:51:13Z

camel/agents/chat_agent.py

+                    elif msg_role == "tool":
+                        # Handle tool response messages if needed
+                        pass


should we also support taking system message to align with OpenAI interface?

Wendong-Fan · 2025-11-01T14:53:14Z

camel/schemas/openai_schema.py

seems content in this file is not used in this PR

Wendong-Fan · 2025-11-01T14:55:00Z

camel/agents/chat_agent.py

+                    # Type guard to ensure tools_to_use is not None
+                    if tools_to_use is not None:
+                        for tool in tools_to_use:
+                            self.add_external_tool(tool)


seems here would accumulate the tools added to agent, should we clean after one request ended?

Wendong-Fan

thanks @LuoPengcheng12138 , left some comments below and added one enhance PR:#3380 , feel free to review and leave your comments

Wendong-Fan · 2025-11-05T00:18:51Z

camel/agents/chat_agent.py

+        # Define Pydantic models for request/response
+        class ChatMessage(BaseModel):


seems defined but not used

Wendong-Fan · 2025-11-05T00:21:34Z

camel/agents/chat_agent.py

        if reset_memory:
            self.init_messages()

+    def reset_system_message(


we already has update_system_message, seems no necessary to add this new function

Wendong-Fan · 2025-11-05T00:22:46Z

camel/agents/chat_agent.py

+                    content={"error": f"Internal server error: {e!s}"},
+                )
+
+        async def _stream_response(message: BaseMessage, request_data: dict):


The streaming implementation awaited the full response first, then split it into words and sent them one-by-one with artificial delays. This defeats the purpose of streaming

Wendong-Fan · 2025-11-05T00:24:57Z

camel/agents/chat_agent.py

+                messages = request_data.get("messages", [])
+                model = request_data.get("model", "camel-model")
+                stream = request_data.get("stream", False)
+                functions = request_data.get("functions")
+                tools = request_data.get("tools")


The agent's state persisted across different API requests, which would causing conversations from different clients to mix and memory leaks, would better to add self.reset() and self._external_tool_schemas.clear() at the start of each request?

Wendong-Fan · 2025-11-05T00:35:26Z

camel/agents/chat_agent.py

+                    elif msg_role == "system":
+                        sys_msg = BaseMessage.make_system_message(
+                            role_name="System", content=msg_content
+                        )
+                        self.update_memory(sys_msg, OpenAIBackendRole.SYSTEM)
+                        self.reset_system_message(msg_content, True)


should we update system message without clearing memory to preserve conversation history?

Yes, during the design phase, we considered that multiple GAIA2 tests might have different system_messages. I was concerned about potential interference between these system_messages so the system_message is reset each time. Currently, it is not confirmed whether the ARE environment reuses a single agent instance during testing, and I will continue to investigate this. However, for the function serving as the OpenAI Server interface, it is indeed necessary to not clear memory so as to preserve the conversation history.This may lead to functional contradictions.

I see.My understanding of the chat interface is not thorough enough, and I will update the code!

LuoPengcheng12138 · 2025-11-05T14:33:40Z

thanks @LuoPengcheng12138 , left some comments below and added one enhance PR:#3380 , feel free to review and leave your comments

This PR is still in draft status, and I will revise it later based on your comments.

review-notebook-app · 2025-11-13T16:02:39Z

Check out this pull request on

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB

camel/agents/chat_agent.py

+            except Exception as e:
+                return JSONResponse(
+                    status_code=500,
+                    content={"error": f"Internal server error: {e!s}"},


To fix this issue, the code should avoid including the actual string representation of the exception ({e!s}) in the response sent to the client. Instead, upon catching an exception, the error (including the exception message and ideally the stack trace) should be logged on the server for diagnostic purposes, and a generic error message (e.g., "An internal server error has occurred.") should be returned to the client. This keeps sensitive implementation details from being exposed to a potential attacker while still providing developers the information they need to debug the error. The required changes are as follows:

In the exception handler in the chat_completions route, use logger.error to log the actual exception and stack trace.

Change the frontend-facing response to a generic message, such as {"error": "Internal server error"}.

Ensure the logger is available (already present as logger in the code) and used correctly for logging exceptions.

No new imports are needed, as logger and FastAPI's JSONResponse are already imported.

LuoPengcheng12138 · 2025-11-24T08:45:12Z

Hi, @Wendong-Fan ,I think this PR is finished and need you review again,Please feel free to let me know if you have any questions.（I think the failed check in github actions is not caused by this pr)

update openai server

986abd9

github-actions bot added the Review Required PR need to be reviewed label Oct 30, 2025

github-advanced-security bot found potential problems Oct 30, 2025

View reviewed changes

camel/agents/chat_agent.py Fixed Show fixed Hide fixed

Merge branch 'master' into feat/openai-compatible-server

f175024

Wendong-Fan reviewed Nov 1, 2025

View reviewed changes

Wendong-Fan assigned LuoPengcheng12138 Nov 1, 2025

LuoPengcheng12138 mentioned this pull request Nov 2, 2025

[Fix] Align assistant_message structure in camel with OpenAI Chat API specification #3356

Closed

LuoPengcheng12138 added 3 commits November 2, 2025 22:01

construct tool_message

fff6cf2

update test_openai_function

59f473c

update test_openai_function

1bac929

Wendong-Fan added Waiting for Update PR has been reviewed, need to be updated based on review comment and removed Review Required PR need to be reviewed labels Nov 2, 2025

Merge branch 'master' into feat/openai-compatible-server

7452bb7

Wendong-Fan reviewed Nov 5, 2025

View reviewed changes

LuoPengcheng12138 added 2 commits November 12, 2025 00:41

Merge branch 'master' into feat/openai-compatible-server

041f564

update：support stream openai

bd11420

github-advanced-security bot found potential problems Nov 13, 2025

View reviewed changes

LuoPengcheng12138 and others added 4 commits November 17, 2025 21:09

update stream api

8d69cf8

Merge branch 'master' into feat/openai-compatible-server

ebb6c28

Merge branch 'master' into feat/openai-compatible-server

648661d

Merge branch 'master' into feat/openai-compatible-server

43235f9

		# Define Pydantic models for request/response
		class ChatMessage(BaseModel):

update openai server #3346

Are you sure you want to change the base?

update openai server #3346

Uh oh!

Conversation

LuoPengcheng12138 commented Oct 30, 2025

Description

Checklist

Uh oh!

coderabbitai bot commented Oct 30, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Review skipped

Uh oh!

Uh oh!

fengju0213 commented Oct 30, 2025

Uh oh!

LuoPengcheng12138 commented Oct 30, 2025

Uh oh!

fengju0213 commented Oct 30, 2025

Uh oh!

Wendong-Fan left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Wendong-Fan left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

LuoPengcheng12138 commented Nov 5, 2025

Uh oh!

review-notebook-app bot commented Nov 13, 2025

Uh oh!

Check warning

Uh oh!

Copilot Autofix

LuoPengcheng12138 commented Nov 24, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

coderabbitai bot commented Oct 30, 2025 •

edited

Loading

Wendong-Fan left a comment •

edited

Loading