feat: final platform plugin parity — webhook delivery, platform hints, docs

Closes remaining functional gaps and adds documentation.

webhook.py: Cross-platform delivery now checks the plugin registry
  for unknown platform names instead of hardcoding 15 names in a tuple.
  Plugin platforms can receive webhook-routed deliveries.

prompt_builder: Platform hints (system prompt LLM guidance) now fall
  back to the plugin registry's platform_hint field. Plugin platforms
  can tell the LLM 'you're on IRC, no markdown.'

PlatformEntry: Added platform_hint field for LLM guidance injection.

IRC adapter: Added acquire_scoped_lock/release_scoped_lock in
  connect/disconnect to prevent two profiles from using the same IRC
  identity. Added platform_hint for IRC-specific LLM guidance.

Removed dead token-empty-warning extension for plugin platforms
  (plugin adapters handle their own env vars via check_fn).

website/docs/developer-guide/adding-platform-adapters.md:
  - Added 'Plugin Path (Recommended)' section with full code examples,
    PLUGIN.yaml template, config.yaml examples, and a table showing all
    18 integration points the plugin system handles automatically
  - Renamed built-in checklist to clarify it's for core contributors

gateway/platforms/ADDING_A_PLATFORM.md:
  - Added Plugin Path section pointing to the reference implementation
    and full docs guide
  - Clarified built-in path is for core contributors only

run_agent.py

@@ -2151,7 +2151,7 @@ class AIAgent:
         # Context engine reset (works for both built-in compressor and plugins)
         if hasattr(self, "context_compressor") and self.context_compressor:
             self.context_compressor.on_session_reset()
-    
+
     def _ensure_lmstudio_runtime_loaded(self, config_context_length: Optional[int] = None) -> None:
         """
         Preload the LM Studio model with at least Hermes' minimum context.
@@ -2935,7 +2935,7 @@ class AIAgent:
 
         # Check if there's any non-whitespace content remaining
         return bool(cleaned.strip())
-    
+
     def _strip_think_blocks(self, content: str) -> str:
         """Remove reasoning/thinking blocks from content, returning only visible text.
 
@@ -3153,8 +3153,8 @@ class AIAgent:
             marker in assistant_text for marker in workspace_markers
         )
         return (user_targets_workspace or assistant_targets_workspace) and assistant_mentions_action
-    
-    
+
+
     def _extract_reasoning(self, assistant_message) -> Optional[str]:
         """
         Extract reasoning/thinking content from an assistant message.
@@ -3727,7 +3727,7 @@ class AIAgent:
         
         # Return everything up to (not including) the last assistant message
         return messages[:last_assistant_idx]
-    
+
     def _format_tools_for_system_message(self) -> str:
         """
         Format tool definitions for the system message in the trajectory format.
@@ -3751,7 +3751,7 @@ class AIAgent:
             formatted_tools.append(formatted_tool)
         
         return json.dumps(formatted_tools, ensure_ascii=False)
-    
+
     def _convert_to_trajectory_format(self, messages: List[Dict[str, Any]], user_query: str, completed: bool) -> List[Dict[str, Any]]:
         """
         Convert internal message format to trajectory format for saving.
@@ -3916,7 +3916,7 @@ class AIAgent:
             i += 1
         
         return trajectory
-    
+
     def _save_trajectory(self, messages: List[Dict[str, Any]], user_query: str, completed: bool):
         """
         Save conversation trajectory to JSONL file.
@@ -3931,7 +3931,7 @@ class AIAgent:
         
         trajectory = self._convert_to_trajectory_format(messages, user_query, completed)
         _save_trajectory_to_file(trajectory, self.model, completed)
-    
+
     @staticmethod
     def _summarize_api_error(error: Exception) -> str:
         """Extract a human-readable one-liner from an API error.
@@ -4243,7 +4243,7 @@ class AIAgent:
         except Exception as e:
             if self.verbose_logging:
                 logging.warning(f"Failed to save session log: {e}")
-    
+
     def interrupt(self, message: str = None) -> None:
         """
         Request the agent to interrupt its current tool-calling loop.
@@ -4311,7 +4311,7 @@ class AIAgent:
                 logger.debug("Failed to propagate interrupt to child agent: %s", e)
         if not self.quiet_mode:
             print("\n⚡ Interrupt requested" + (f": '{message[:40]}...'" if message and len(message) > 40 else f": '{message}'" if message else ""))
-    
+
     def clear_interrupt(self) -> None:
         """Clear any pending interrupt request and the per-thread tool interrupt signal."""
         self._interrupt_requested = False
@@ -4532,7 +4532,7 @@ class AIAgent:
                 )
             except Exception:
                 pass
-    
+
     def commit_memory_session(self, messages: list = None) -> None:
         """Trigger end-of-session extraction without tearing providers down.
         Called when session_id rotates (e.g. /new, context compression);
@@ -4728,7 +4728,7 @@ class AIAgent:
             if not self.quiet_mode:
                 self._vprint(f"{self.log_prefix}📋 Restored {len(last_todo_response)} todo item(s) from history")
         _set_interrupt(False)
-    
+
     @property
     def is_interrupted(self) -> bool:
         """Check if an interrupt has been requested."""
@@ -4912,6 +4912,15 @@ class AIAgent:
         platform_key = (self.platform or "").lower().strip()
         if platform_key in PLATFORM_HINTS:
             prompt_parts.append(PLATFORM_HINTS[platform_key])
+        elif platform_key:
+            # Check plugin registry for platform-specific LLM guidance
+            try:
+                from gateway.platform_registry import platform_registry
+                _entry = platform_registry.get(platform_key)
+                if _entry and _entry.platform_hint:
+                    prompt_parts.append(_entry.platform_hint)
+            except Exception:
+                pass
 
         return "\n\n".join(p.strip() for p in prompt_parts if p.strip())