revert: remove auto-prefix, user specifies full provider/model

Support both OpenAI-compatible and Anthropic-compatible endpoints.
User must specify full model name with provider prefix.

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

backend/.env.example

@@ -39,25 +39,17 @@
 # LLM_MODEL=ollama/llama2
 
 # =============================================================================
-# Option 7: Custom/Self-hosted (OpenAI-compatible endpoint)
+# Option 7: Custom/Self-hosted endpoint
+# See: https://docs.litellm.ai/docs/providers
 # =============================================================================
 # LLM_API_BASE=http://localhost:8000/v1
 # LLM_API_KEY=your-key
-# LLM_MODEL=qwen2.5
-# Note: When LLM_API_BASE is set, model is auto-prefixed as "openai/qwen2.5"
-
-# =============================================================================
-# Model naming convention (LiteLLM requires provider prefix)
-# See: https://docs.litellm.ai/docs/providers
-# =============================================================================
-# Format: provider/model-name
-# Examples:
-#   openai/gpt-4
-#   anthropic/claude-3-haiku-20240307
-#   gemini/gemini-pro
-#   ollama/llama2
-#   huggingface/starcoder
-#   azure/your-deployment-name
+#
+# For OpenAI-compatible API:
+# LLM_MODEL=openai/your-model-name
+#
+# For Anthropic-compatible API:
+# LLM_MODEL=anthropic/your-model-name
 
 # =============================================================================
 # Force mock mode (no API calls, uses predefined responses)

backend/app/llm.py

@@ -76,13 +76,6 @@ class LLMService:
         self._mock_mode = os.environ.get("LLM_MOCK_MODE", "").lower() == "true"
         self._acompletion = None
 
-        # Auto-add provider prefix for custom endpoints
-        # LiteLLM requires format: provider/model (e.g., openai/gpt-4)
-        # See: https://docs.litellm.ai/docs/providers
-        if self._api_base and "/" not in self._model:
-            self._model = f"openai/{self._model}"
-            logger.info(f"Auto-prefixed model name: {self._model} (custom endpoint detected)")
-
         if self._mock_mode:
             logger.info("LLMService running in MOCK mode (forced by LLM_MOCK_MODE)")
             return