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>

tools/testgen.py

@@ -290,23 +290,25 @@ class TestGenerationTool(BaseTool):
         continuation_id = getattr(request, "continuation_id", None)
 
         # Get model context for token budget calculation
-        model_name = getattr(self, "_current_model_name", None)
         available_tokens = None
 
-        if model_name:
+        if hasattr(self, "_model_context") and self._model_context:
             try:
-                provider = self.get_model_provider(model_name)
-                capabilities = provider.get_capabilities(model_name)
+                capabilities = self._model_context.capabilities
                 # Use 75% of context for content (code + test examples), 25% for response
                 available_tokens = int(capabilities.context_window * 0.75)
                 logger.debug(
-                    f"[TESTGEN] Token budget calculation: {available_tokens:,} tokens (75% of {capabilities.context_window:,}) for model {model_name}"
+                    f"[TESTGEN] Token budget calculation: {available_tokens:,} tokens (75% of {capabilities.context_window:,}) for model {self._model_context.model_name}"
                 )
             except Exception as e:
                 # Fallback to conservative estimate
-                logger.warning(f"[TESTGEN] Could not get model capabilities for {model_name}: {e}")
+                logger.warning(f"[TESTGEN] Could not get model capabilities: {e}")
                 available_tokens = 120000  # Conservative fallback
                 logger.debug(f"[TESTGEN] Using fallback token budget: {available_tokens:,} tokens")
+        else:
+            # No model context available (shouldn't happen in normal flow)
+            available_tokens = 120000  # Conservative fallback
+            logger.debug(f"[TESTGEN] No model context, using fallback token budget: {available_tokens:,} tokens")
 
         # Process test examples first to determine token allocation
         test_examples_content = ""