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>

tests/test_per_tool_model_defaults.py

@@ -291,16 +291,22 @@ class TestFileContentPreparation:
             tool = ThinkDeepTool()
             tool._current_model_name = "auto"
 
+            # Set up model context to simulate normal execution flow
+            from utils.model_context import ModelContext
+
+            tool._model_context = ModelContext("gemini-2.5-pro-preview-06-05")
+
             # Call the method
             content, processed_files = tool._prepare_file_content_for_prompt(["/test/file.py"], None, "test")
 
-            # Check that it logged the correct message
-            debug_calls = [call for call in mock_logger.debug.call_args_list if "Auto mode detected" in str(call)]
+            # Check that it logged the correct message about using model context
+            debug_calls = [call for call in mock_logger.debug.call_args_list if "Using model context" in str(call)]
             assert len(debug_calls) > 0
             debug_message = str(debug_calls[0])
-            # Should use a model suitable for extended reasoning
-            assert "gemini-2.5-pro-preview-06-05" in debug_message or "pro" in debug_message
-            assert "extended_reasoning" in debug_message
+            # Should mention the model being used
+            assert "gemini-2.5-pro-preview-06-05" in debug_message
+            # Should mention file tokens (not content tokens)
+            assert "file tokens" in debug_message
 
 
 class TestProviderHelperMethods: