Centralize system message handling in adapters; add developer message support

Two goals:

1. Centralize system_instruction vs context system message resolution into
   the LLM adapters. This eliminates duplication between in-pipeline and
   out-of-band (run_inference) code paths across ~16 locations in service
   llm.py files.

2. Add support for "developer" role messages in conversation context, which
   is facilitated by the above centralization.

Shared helpers on BaseLLMAdapter:
- _extract_initial_system_or_developer: extracts/converts messages[0]
  based on role and whether system_instruction is provided
- _resolve_system_instruction: warns on conflicts between system_instruction
  and context system messages, returns the effective instruction

Developer message handling (new):
- Non-OpenAI adapters: an initial "developer" message is promoted to the
  system instruction when no system_instruction is provided; otherwise it
  is converted to "user". Subsequent "developer" messages are always
  converted to "user". No conflict warning is emitted for developer
  messages (unlike "system" messages).
- OpenAI adapter: "developer" messages pass through in conversation
  history without triggering conflict warnings.
- OpenAI Responses adapter: "developer" messages are kept as "developer"
  role (same as "system", which is also converted to "developer" for the
  Responses API).

Other behavior changes:
- Gemini: "initial" system message detection now checks messages[0] only
  (previously searched anywhere in the list)
- Bedrock: a lone system message is now converted to "user" instead of
  being extracted to an empty message list (matches existing Anthropic
  behavior)

src/pipecat/services/cerebras/llm.py

@@ -114,15 +114,4 @@ class CerebrasLLMService(OpenAILLMService):
 
         params.update(self._settings.extra)
 
-        # Prepend system instruction if set
-        if self._settings.system_instruction:
-            messages = params.get("messages", [])
-            if messages and messages[0].get("role") == "system":
-                logger.warning(
-                    f"{self}: Both system_instruction and an initial system message in context are set. This may be unintended."
-                )
-            params["messages"] = [
-                {"role": "system", "content": self._settings.system_instruction}
-            ] + messages
-
         return params