Skip to content

fix: Simple application model dialogue model error not returned #2514

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
shaohuzhang1 merged 1 commit into from
Mar 7, 2025
Merged

fix: Simple application model dialogue model error not returned #2514

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 10 additions & 6 deletions apps/application/chat_pipeline/step/chat_step/impl/base_chat_step.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -135,16 +135,20 @@ def event_content(response,
add_access_num(client_id, client_type, manage.context.get('application_id'))
except Exception as e:
logging.getLogger("max_kb_error").error(f'{str(e)}:{traceback.format_exc()}')
all_text = '异常' + str(e)
all_text = 'Exception:' + str(e)
write_context(step, manage, 0, 0, all_text)
post_response_handler.handler(chat_id, chat_record_id, paragraph_list, problem_text,
all_text, manage, step, padding_problem_text, client_id)
add_access_num(client_id, client_type, manage.context.get('application_id'))
yield manage.get_base_to_response().to_stream_chunk_response(chat_id, str(chat_record_id), all_text,
'ai-chat-node',
[], True, 0, 0,
{'node_is_end': True, 'view_type': 'many_view',
'node_type': 'ai-chat-node'})
yield manage.get_base_to_response().to_stream_chunk_response(chat_id, str(chat_record_id), 'ai-chat-node',
[], all_text,
False,
0, 0, {'node_is_end': False,
'view_type': 'many_view',
'node_type': 'ai-chat-node',
'real_node_id': 'ai-chat-node',
'reasoning_content': ''})



class BaseChatStep(IChatStep):
Copy link
Copy Markdown
Contributor Author

@shaohuzhang1 shaohuzhang1 Mar 7, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

There are several potential issues and improvements to make:

Issues/Issues:

  1. Logging: The use of logging.getLogger("max_kb_error") could benefit from adding more parameters or context in the log message. It's difficult to determine which logger is being used or why it's named "max_kb_error".

    logging.error(f"Error processing response with chat ID {chat_id} (ID: {chat_record_id}): {e}: {traceback.format_exc()}")

  2. Variable Names:

    • Use meaningful names like response_text, all_error_message, and so on to improve readability.
    • Avoid excessively long variable names that may become confusing.

  3. Stream Response:

    • Ensure that the stream response handles edge cases where there might be multiple errors or no error at all.
    • Consider using exception handling within the stream generation logic to manage unexpected errors gracefully.

  4. Code Duplication: Redundancy exists between writing logs and calling write_context. Refactor these calls into a helper function for clarity and maintainability.

  5. Data Structure: The use of lists for paragraph_list, problem_text, and manage seems inconsistent; ensure they align correctly based on their usage.

  6. Yield Statements:

    • The current yield statement does not include metadata such as node type, real node ID, reasoning content, or other necessary fields. Review the to_stream_chunk_response method to confirm the full set of required data is provided.

  7. Optimization: There are no obvious optimizations needed without additional context or profiling. However, ensuring that operations are performed only when necessary can help optimize performance.

  8. Type Hints: Add appropriate type hints to function arguments, return values, and variables to improve code understanding and catch potential type-related errors during development.

Here’s an updated version of the code incorporating some of these suggestions:

from typing import *
import traceback
import logging

def write_context(step, manage, *args, **kwargs):
    # Implement your context-write logic here
    pass

class AIChatResponseHandler(IChatResponseHandler):
    def handler(self, chat_id, chat_record_id, paragraph_list, problem_text,
               all_text, manage, step, padding_problem_text, client_id):
        try:
            add_access_num(client_id, client_type, manage.context.get('application_id'))
        except Exception as e:
            self.log_exception(chat_id, chat_record_id, e)
            handle_write_context(chat_id, chat_record_id, manage)
            self.stream_response(
                chat_id, chat_record_id, 'ai-chat-node', [],
                f'Exception: {str(e)}{traceback.format_exc()}',
                manage,
                step,
                padding_problem_text,
                client_id
            )
            add_access_num(client_id, client_type, manage.context.get('application_id'))

    @staticmethod
    def log_exception(chat_id, chat_record_id, e):
        logging.error(f"Error processing response with chat ID {chat_id} (ID: {chat_record_id}): {e}: {traceback.format_exc()}")

    def stream_response(self, chat_id, chat_record_id, node_type, nodes, response_text, manage,
                        step, padding_problem_text, client_id, **metadata=None):
        if metadata:
            metadata['node_is_end'] = False
            metadata['view_type'] = 'many_view'
            metadata['node_type'] = node_type
            metadata['real_node_id'] = 'ai-chat-node'
            metadata['reasoning_content'] = ''
        else:
            metadata = {
                'node_is_end': False,
                'view_type': 'many_view',
                'node_type': node_type,
                'real_node_id': 'ai-chat-node',
                'reasoning_content': ''
            }
        yield manage.get_base_to_response().to_stream_chunk_response(chat_id, str(chat_record_id),
                                                                       node_type, nodes, response_text,
                                                                       False,
                                                                       0, 0, metadata)

# Example Usage
def some_function():
    ai_chat_handler = AIChatResponseHandler()
    ai_chat_handler.handler(1, 2, [], '', 'Test Error Message', None, {}, [], 1)

some_function()

By making these changes, you enhance the robustness and maintainability of your codebase.

Expand Down