feat: mount MCP server, add bearer auth, and guard outbound calls

The MCP server was created but never mounted — no client could reach
it. Mount it at /mcp/ over streamable HTTP with a combined lifespan,
resolving the gateway lazily so mounting happens at app construction.

Security and safety for the agent surface:
- One static API_TOKEN (SecretStr) enforced across REST (dependency),
  WebSocket (query param/header before accept), and MCP
  (StaticTokenVerifier). Startup refuses tokenless non-loopback binds.
- Emergency numbers (911/9911/112) always refused on make_call, plus a
  MAX_CONCURRENT_CALLS cap; ValueError surfaces as 400/ToolError.
- Safe defaults: debug off, no credential in default DATABASE_URL,
  SIP/LLM/TTS secrets as SecretStr.

Cleanups:
- Delete broken learn_call_flow tool (wrong ctor args, nonexistent
  method) and the never-fed CallAnalytics service; keep
  call_flow_learner for proper wiring later.
- Trim dial_plan to what is actually used (emergency guard, extension
  allocation); delete the unreferenced matcher/normaliser.
- Register call_history before calls so /api/calls/history is no
  longer shadowed by /api/calls/{call_id}.
- fastmcp pinned >=3.0 (http_app + StaticTokenVerifier).

New tests: MCP in-memory client (tool surface, lazy gateway, emergency
refusal, call cap) and API security (401 paths, route order, mount).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

config.py

@@ -4,7 +4,7 @@ Hold Slayer Gateway — Configuration
 All settings loaded from environment variables / .env file.
 """
 
-from pydantic import Field
+from pydantic import Field, SecretStr
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
 
@@ -16,7 +16,7 @@ class SIPTrunkSettings(BaseSettings):
     host: str = "sip.provider.com"
     port: int = 5060
     username: str = ""
-    password: str = ""
+    password: SecretStr = SecretStr("")
     transport: str = "udp"  # udp, tcp, tls
     did: str = ""  # Your phone number (E.164)
 
@@ -58,7 +58,7 @@ class LLMSettings(BaseSettings):
 
     base_url: str = "http://localhost:11434/v1"
     model: str = "llama3"
-    api_key: str = "not-needed"
+    api_key: SecretStr = SecretStr("not-needed")
     timeout: float = 30.0
     max_tokens: int = 1024
     temperature: float = 0.3
@@ -84,7 +84,7 @@ class TTSSettings(BaseSettings):
     base_url: str = "http://localhost:8000"
     model: str = "speaches-ai/Kokoro-82M-v1.0-ONNX"
     voice: str = "af_heart"
-    api_key: str = ""
+    api_key: SecretStr = SecretStr("")
     timeout: float = 30.0
     sample_rate: int = 16000
 
@@ -117,15 +117,22 @@ class Settings(BaseSettings):
         extra="ignore",
     )
 
-    # Database
-    database_url: str = "postgresql+asyncpg://holdslayer:changeme@localhost:5432/holdslayer"
+    # Database — no default credentials; must be set in the environment
+    database_url: str = ""
 
     # Server
     host: str = "0.0.0.0"
     port: int = 8000
-    debug: bool = True
+    debug: bool = False
     log_level: str = "info"
 
+    # Auth — one static bearer token shared by REST, WebSocket, and MCP.
+    # Empty disables auth, which is only permitted on loopback binds.
+    api_token: SecretStr = SecretStr("")
+
+    # Outbound-call safety cap (REST + MCP make_call)
+    max_concurrent_calls: int = 4
+
     # Notifications
     notify_sms_number: str = ""