feat: refactor agent initialization and enhance API proxy configuration in nginx

backend/app.py

@@ -11,7 +11,10 @@ from uvicorn.logging import DefaultFormatter
 
 from backend.core.config import Settings
 from backend.core.database import close_engine, close_valkey, init_db
-from backend.core.dependencies import get_agent_service
+from backend.core.agent import AgentService, set_service
+from backend.repositories.memory_repository import MemoryRepository
+from backend.services.agent_factory import build_agent
+from backend.services.rag_service import RagService
 from backend.routes.admin import router as admin_router
 from backend.routes.auth import router as auth_router
 from backend.routes.chat import router as chat_router
@@ -60,7 +63,9 @@ class AppBuilder:
     """Builds and configures the FastAPI application with DI wiring.
 
     Accepts a ``Settings`` instance so tests can supply custom config.
-    The ``AgentService`` is lazily initialised inside the lifespan.
+    The ``AgentService`` is built inside the lifespan hook, which wires
+    ``MemoryRepository``, ``RagService``, and the agent factory together
+    and registers the result as a module-level singleton.
     """
 
     def __init__(self, settings: Settings | None = None) -> None:
@@ -110,9 +115,12 @@ class AppBuilder:
         # Create database tables if they don't exist.
         await init_db()
 
-        # Initialise the agent service on startup.
-        agent_service = await get_agent_service()
-        agent_service.initialize()
+        # Build agent with full dependency injection via the factory.
+        memory_repo = MemoryRepository()
+        rag_service = RagService()
+        agent = build_agent(self._settings, memory_repo, rag_service)
+        agent_service = AgentService(agent=agent, memory_repo=memory_repo)
+        set_service(agent_service)
 
         yield
 

backend/core/agent.py

@@ -27,41 +27,28 @@ from __future__ import annotations
 
 import time
 from dataclasses import dataclass
+from typing import Any
 
 from pydantic_ai import Agent
-from pydantic_ai.tools import Tool
-from pydantic_ai_harness import CodeMode
 
-from backend.core.config import Settings
 from backend.repositories.memory_repository import MemoryRepository
-from backend.services.agent_factory import build_agent
-from backend.services.rag_service import RagService
 from pydantic_deep.deps import DeepAgentDeps
 
-class AgentService:
-    """Encapsulates agent construction, execution, and teardown.
 
-    Uses lazy initialization so the agent is not built at import time.
-    Accepts a ``Settings`` instance for testability (dependency injection).
+class AgentService:
+    """Thin orchestrator for agent execution.
+
+    Receives a pre-built ``Agent`` and its ``MemoryRepository`` via
+    constructor injection so the lifespan (or tests) control wiring.
+    No lazy initialisation — the agent is ready to run immediately.
     """
 
-    def __init__(self, settings: Settings) -> None:
-        self._settings = settings
-        self._agent: Agent[any, str] | None = None
+    def __init__(self, agent: Agent[Any, str], memory_repo: MemoryRepository) -> None:
+        self._agent = agent
+        self._memory_repo = memory_repo
 
     # ── Lifecycle ──────────────────────────────────────────────────────────
 
-    def initialize(self) -> None:
-        """Build the agent. Idempotent — safe to call multiple times."""
-        if self._agent is not None:
-            return
-
-        memory_repo = MemoryRepository()
-        rag_service = RagService()
-
-        # The factory handles all complex initialization logic
-        self._agent = build_agent(self._settings, memory_repo, rag_service)
-
     async def shutdown(self) -> None:
         """Release agent resources."""
         self._agent = None
@@ -70,17 +57,13 @@ class AgentService:
 
     async def ask(self, prompt: str, session_id: str | None = None) -> AskResult:
         """Send a prompt to the agent and return the text output with usage stats."""
-        self.initialize()
-        assert self._agent is not None
-
-        # Dependency injection using the repository's backend
-        memory_repo = MemoryRepository()
-        deps = DeepAgentDeps(backend=memory_repo.backend)
+        di = DeepAgentDeps(backend=self._memory_repo.backend)
 
         t0 = time.monotonic()
-        result = await self._agent.run(prompt, deps=deps)
+        result = await self._agent.run(prompt, deps=di)
         elapsed = time.monotonic() - t0
         usage = result.usage
+
         return AskResult(
             output=result.output,
             input_tokens=usage.input_tokens,
@@ -89,6 +72,7 @@ class AgentService:
             elapsed_seconds=round(elapsed, 2),
         )
 
+
 @dataclass
 class AskResult:
     """Result of a single agent ``ask()`` call with token usage information."""
@@ -108,20 +92,22 @@ class AskResult:
     elapsed_seconds: float = 0.0
     """Wall-clock time in seconds the agent took to respond."""
 
+
 # ---------------------------------------------------------------------------
-# Singleton — lazy-initialised on the first call to ``ask()``.
-# Keeps the existing module-level ``ask`` facade so downstream imports in
-# ``chat.py`` continue to work unchanged.
+# Singleton — wired once at startup by the lifespan hook in ``app.py``.
+# Routes access it through ``get_service()``.
 # ---------------------------------------------------------------------------
 
-from backend.core.config import settings as _settings  # noqa: E402
+_service: AgentService | None = None
 
-_service = AgentService(_settings)
 
 def get_service() -> AgentService:
     """Return the singleton AgentService instance."""
+    assert _service is not None, "AgentService has not been initialised — did the lifespan run?"
     return _service
 
-async def ask(prompt: str, session_id: str | None = None) -> AskResult:
-    """Send a prompt to the agent and return the text output with usage stats."""
-    return await _service.ask(prompt, session_id=session_id)
+
+def set_service(service: AgentService) -> None:
+    """Set the module-level singleton (called by the lifespan hook)."""
+    global _service
+    _service = service

frontend/nginx.conf

@@ -12,8 +12,11 @@ server {
 
     # ── API proxy ─────────────────────────────────────────────────
     # Container runtime (Docker/Podman) resolves backend:8000 via
-    # its built-in DNS.  nginx caches the resolved IP at startup, so
-    # restarting the backend container needs a frontend restart too.
+    # its built-in DNS (127.0.0.11).  Without a resolver, nginx caches
+    # the resolved IP at startup and returns 502 when the backend
+    # container is recreated.  The resolver + valid=5s forces periodic
+    # re-resolution so the frontend survives backend restarts.
+    resolver 127.0.0.11 valid=5s;
     location /api/ {
         proxy_pass http://backend:8000;
         proxy_set_header Host $host;