feat: add --sender parameter to chat commands

[chenjw]

• Add --sender option to Python CLI chat command
• Add --sender option to Rust CLI chat command
• Pass sender ID through to channels
• Display sender in interactive mode header
• Update langfuse integration for compatibility

Description

Related Issue

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Refactoring (no functional changes)
• Performance improvement
• Test update

Changes Made

Testing

• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I have tested this on the following platforms:
  • Linux
  • macOS
  • Windows

Checklist

• My code follows the project's coding style
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• Any dependent changes have been merged and published

Screenshots (if applicable)

Additional Notes

[github-actions]

PR Reviewer Guide 🔍

Here are some key observations to aid the review process:

⏱️ Estimated effort to review: 3 🔵🔵🔵⚪⚪

🧪 No relevant tests

🔒 No security concerns identified

⚡ Recommended focus areas for review Type Mismatch Bug The --sender option is annotated as str but has a default value of None, causing a type mismatch. This will result in type checking errors and potential runtime issues. sender: str = typer.Option( None, "--sender", help="Sender ID, same usage as feishu channel sender" ) Inconsistent Fallback The fallback sender_id values are inconsistent between ChatChannel ("user") and SingleTurnChannel ("default"). Unifying these would improve consistency. sender_id = self.sender or "user" Code Duplication The litellm_provider now directly calls langfuse client methods instead of using the existing langfuse.generation() context manager, leading to duplicated logic. Consider using the context manager for consistency. # Langfuse integration # Note: session_id is set via propagate_attributes in loop.py, not here langfuse_observation = None try: if self.langfuse.enabled and self.langfuse._client: metadata = {"has_tools": tools is not None} client = self.langfuse._client # Use start_observation with generation type if hasattr(client, "start_observation"): langfuse_observation = client.start_observation( name="llm-chat", as_type="generation", model=model, input=messages, metadata=metadata, ) response = await acompletion(**kwargs) llm_response = self._parse_response(response) # Update and end Langfuse observation if langfuse_observation: output_text = llm_response.content or "" if llm_response.tool_calls: output_text = ( output_text or f"[Tool calls: {[tc.name for tc in llm_response.tool_calls]}]" ) # Update observation with output and usage update_kwargs: dict[str, Any] = { "output": output_text, "metadata": {"finish_reason": llm_response.finish_reason}, } if llm_response.usage: # Add usage data using usage_details format usage_details: dict[str, Any] = { "input": llm_response.usage.get("prompt_tokens", 0), "output": llm_response.usage.get("completion_tokens", 0), } # Add cache read tokens if available cache_read_tokens = llm_response.usage.get( "cache_read_input_tokens" ) or llm_response.usage.get("prompt_tokens_details", {}).get("cached_tokens") if cache_read_tokens: usage_details["cache_read_input_tokens"] = cache_read_tokens update_kwargs["usage_details"] = usage_details # Update the observation if hasattr(langfuse_observation, "update"): try: langfuse_observation.update(**update_kwargs) except Exception as e: logger.debug(f"[LANGFUSE] Failed to update observation: {e}") # End the observation if hasattr(langfuse_observation, "end"): try: langfuse_observation.end() except Exception as e: logger.debug(f"[LANGFUSE] Failed to end observation: {e}") self.langfuse.flush() return llm_response except Exception as e: # End Langfuse observation with error if langfuse_observation: try: if hasattr(langfuse_observation, "update"): langfuse_observation.update( output=f"Error: {str(e)}", metadata={"error": str(e)}, ) if hasattr(langfuse_observation, "end"): langfuse_observation.end() self.langfuse.flush() except Exception: pass

[github-actions]

PR Code Suggestions ✨

Explore these optional code suggestions:

Category	Suggestion	Impact
Possible issue	Align default sender ID to "user" The default sender ID in SingleTurnChannel is "default", which is inconsistent with ChatChannel's default of "user". This could lead to inconsistent sender identification across interactive and single-turn chat modes. Let's align the default to "user" for consistency. bot/vikingbot/channels/single_turn.py [64] async def start(self) -> None: """Start the single-turn channel - send message and wait for response.""" self._running = True # Send the message - sender_id = self.sender or "default" + sender_id = self.sender or "user" msg = InboundMessage( Suggestion importance[1-10]: 5 __ Why: Aligning the default sender ID between SingleTurnChannel and ChatChannel improves consistency across chat modes. This is a minor quality improvement with no critical impact.	Low