Add Consensus Tool for Multi-Model Perspective Gathering (#67)

* WIP
Refactor resolving mode_names, should be done once at MCP call boundary
Pass around model context instead
Consensus tool allows one to get a consensus from multiple models, optionally assigning one a 'for' or 'against' stance to find nuanced responses.

* Deduplication of model resolution, model_context should be available before reaching deeper parts of the code
Improved abstraction when building conversations
Throw programmer errors early

* Guardrails
Support for `model:option` format at MCP boundary so future tools can use additional options if needed instead of handling this only for consensus
Model name now supports an optional ":option" for future use

* Simplified async flow

* Improved model for request to support natural language
Simplified async flow

* Improved model for request to support natural language
Simplified async flow

* Fix consensus tool async/sync patterns to match codebase standards

CRITICAL FIXES:
- Converted _get_consensus_responses from async to sync (matches other tools)
- Converted store_conversation_turn from async to sync (add_turn is synchronous)
- Removed unnecessary asyncio imports and sleep calls
- Fixed ClosedResourceError in MCP protocol during long consensus operations

PATTERN ALIGNMENT:
- Consensus tool now follows same sync patterns as all other tools
- Only execute() and prepare_prompt() are async (base class requirement)
- All internal operations are synchronous like analyze, chat, debug, etc.

TESTING:
- MCP simulation test now passes: consensus_stance ✅
- Two-model consensus works correctly in ~35 seconds
- Unknown stance handling defaults to neutral with warnings
- All 9 unit tests pass (100% success rate)

The consensus tool async patterns were anomalous in the codebase.
This fix aligns it with the established synchronous patterns used
by all other tools while maintaining full functionality.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

* Fixed call order and added new test

* Cleanup dead comments
Docs for the new tool
Improved tests

---------

Co-authored-by: Claude <noreply@anthropic.com>

simulator_tests/base_test.py

@@ -136,18 +136,23 @@ class Calculator:
 
             self.logger.debug(f"Calling MCP tool {tool_name} with proper initialization")
 
-            # Execute the command
+            # Execute the command with proper handling for async responses
+            # For consensus tool and other long-running tools, we need to ensure
+            # the subprocess doesn't close prematurely
             result = subprocess.run(
                 docker_cmd,
                 input=input_data,
                 text=True,
                 capture_output=True,
                 timeout=3600,  # 1 hour timeout
+                check=False,  # Don't raise on non-zero exit code
             )
 
             if result.returncode != 0:
-                self.logger.error(f"Docker exec failed: {result.stderr}")
-                return None, None
+                self.logger.error(f"Docker exec failed with return code {result.returncode}")
+                self.logger.error(f"Stderr: {result.stderr}")
+                # Still try to parse stdout as the response might have been written before the error
+                self.logger.debug(f"Attempting to parse stdout despite error: {result.stdout[:500]}")
 
             # Parse the response - look for the tool call response
             response_data = self._parse_mcp_response(result.stdout, expected_id=2)
@@ -191,7 +196,10 @@ class Calculator:
 
             # If we get here, log all responses for debugging
             self.logger.warning(f"No valid tool call response found for ID {expected_id}")
-            self.logger.debug(f"Full stdout: {stdout}")
+            self.logger.warning(f"Full stdout: {stdout}")
+            self.logger.warning(f"Total stdout lines: {len(lines)}")
+            for i, line in enumerate(lines[:10]):  # Log first 10 lines
+                self.logger.warning(f"Line {i}: {line[:100]}...")
             return None
 
         except json.JSONDecodeError as e: