refactor: simplify post-WP-0002 cleanup

- Remove redundant async_execute_prompt overrides from OpenAI/Gemini/OpenRouter
  adapters (identical to base class default — asyncio import also removed)
- Cache prompt.split() result in MockLLMAdapter to avoid double evaluation
- Promote deferred LLMBudgetExceededError imports to module level in
  models.py and adapter.py (no circular dependency)
- Auto-populate context dict in LLMBudgetExceededError.__init__ so callers
  need not pass redundant context= kwarg

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

llm_connect/adapter.py

@@ -10,6 +10,7 @@ from abc import ABC, abstractmethod
 from typing import Dict, Any
 
 from llm_connect.models import RunConfig, LLMResponse, BudgetTracker
+from llm_connect.exceptions import LLMBudgetExceededError
 
 
 class LLMAdapter(ABC):
@@ -79,14 +80,12 @@ class LLMAdapter(ABC):
     def _preflight_budget(self, config: RunConfig) -> None:
         """Raise ``LLMBudgetExceededError`` if the budget is already exhausted."""
         if config.budget_tracker is not None and config.budget_tracker.remaining() == 0:
-            from llm_connect.exceptions import LLMBudgetExceededError
             tracker = config.budget_tracker
             raise LLMBudgetExceededError(
                 "Token budget exhausted before making request",
                 total=tracker.total,
                 spent=tracker.spent,
                 requested=0,
-                context={"total": tracker.total, "spent": tracker.spent},
             )
 
     def _consume_budget(self, config: RunConfig, response: LLMResponse) -> None:
@@ -135,13 +134,15 @@ class MockLLMAdapter(LLMAdapter):
         self.last_prompt = prompt
         self.last_config = config
 
+        prompt_tokens = len(prompt.split())
+        completion_tokens = len(self.mock_response.split())
         response = LLMResponse(
             content=self.mock_response,
             model=config.model_name,
             usage={
-                "prompt_tokens": len(prompt.split()),
-                "completion_tokens": len(self.mock_response.split()),
-                "total_tokens": len(prompt.split()) + len(self.mock_response.split()),
+                "prompt_tokens": prompt_tokens,
+                "completion_tokens": completion_tokens,
+                "total_tokens": prompt_tokens + completion_tokens,
             },
             finish_reason="stop",
             metadata={"mock": True},

llm_connect/exceptions.py

@@ -82,6 +82,8 @@ class LLMBudgetExceededError(LLMError):
         cause: Optional[Exception] = None,
         context: Optional[Dict[str, Any]] = None,
     ):
+        if context is None:
+            context = {"total": total, "spent": spent, "requested": requested}
         super().__init__(message, cause=cause, context=context)
         self.total = total
         self.spent = spent

llm_connect/gemini.py

@@ -2,7 +2,6 @@
 Google Gemini adapter — calls the Generative Language REST API directly.
 """
 
-import asyncio
 import time
 from typing import Optional, Dict, Any
 
@@ -111,10 +110,6 @@ class GeminiAdapter(LLMAdapter):
         self._consume_budget(config, response)
         return response
 
-    async def async_execute_prompt(self, prompt: str, config: RunConfig) -> LLMResponse:
-        """Async wrapper — runs execute_prompt in a thread executor."""
-        return await asyncio.to_thread(self.execute_prompt, prompt, config)
-
     def validate_config(self, config: RunConfig) -> bool:
         if not self._api_key:
             return False

llm_connect/models.py

@@ -9,6 +9,8 @@ import threading
 from dataclasses import dataclass, field
 from typing import Dict, Any, Optional
 
+from llm_connect.exceptions import LLMBudgetExceededError
+
 
 class BudgetTracker:
     """Shared token budget for a call or delegation chain.
@@ -36,8 +38,6 @@ class BudgetTracker:
 
     def consume(self, tokens: int) -> None:
         """Record *tokens* as spent. Raises ``LLMBudgetExceededError`` if cap exceeded."""
-        from llm_connect.exceptions import LLMBudgetExceededError  # avoid circular at module load
-
         with self._lock:
             new_spent = self.spent + tokens
             if new_spent > self.total:
@@ -46,7 +46,6 @@ class BudgetTracker:
                     total=self.total,
                     spent=self.spent,
                     requested=tokens,
-                    context={"total": self.total, "spent": self.spent, "requested": tokens},
                 )
             self.spent = new_spent
 

llm_connect/openai.py

@@ -2,7 +2,6 @@
 OpenAI (ChatGPT) adapter — calls the OpenAI chat completions API.
 """
 
-import asyncio
 import time
 from typing import Optional, Dict, Any
 
@@ -100,10 +99,6 @@ class OpenAIAdapter(LLMAdapter):
         self._consume_budget(config, response)
         return response
 
-    async def async_execute_prompt(self, prompt: str, config: RunConfig) -> LLMResponse:
-        """Async wrapper — runs execute_prompt in a thread executor."""
-        return await asyncio.to_thread(self.execute_prompt, prompt, config)
-
     def validate_config(self, config: RunConfig) -> bool:
         if not self._api_key:
             return False

llm_connect/openrouter.py

@@ -2,7 +2,6 @@
 OpenRouter adapter — calls the OpenAI-compatible chat completions API.
 """
 
-import asyncio
 import time
 from typing import Optional, Dict, Any
 
@@ -108,10 +107,6 @@ class OpenRouterAdapter(LLMAdapter):
         self._consume_budget(config, response)
         return response
 
-    async def async_execute_prompt(self, prompt: str, config: RunConfig) -> LLMResponse:
-        """Async wrapper — runs execute_prompt in a thread executor."""
-        return await asyncio.to_thread(self.execute_prompt, prompt, config)
-
     def validate_config(self, config: RunConfig) -> bool:
         if not self._api_key:
             return False