feat: add deepsearch research system with CLI prune/clear and database schema

Implement a multi-agent deep web research subsystem including CLI commands for pruning expired jobs and clearing all artifacts, database tables for sessions/messages/URL cache with indexes, config paths for chroma storage, and internal embed URL for vector operations.

devplacepy/services/openai_gateway/gateway.py

@@ -12,6 +12,7 @@ from fastapi.responses import JSONResponse, Response, StreamingResponse
 
 from devplacepy.services.openai_gateway import config
 from devplacepy.services.openai_gateway.reliability import CircuitBreaker, retry_send
+from devplacepy.services.openai_gateway.system_message import apply_system_directives
 from devplacepy.services.openai_gateway.usage import (
     GatewayUsageLedger,
     classify_error,
@@ -229,6 +230,8 @@ class GatewayRuntime:
             messages = await augmenter.augment_messages(client, messages)
             self.vision_calls += augmenter.calls
 
+        messages = apply_system_directives(messages, cfg.get("gateway_system_preamble", ""))
+
         requested = body.get("model")
         if cfg["gateway_force_model"] or not requested or requested == "molodetz":
             model = cfg["gateway_model"]
@@ -351,6 +354,25 @@ class GatewayRuntime:
     ):
         log = log or (lambda message: None)
         if not cfg["gateway_embed_enabled"]:
+            from devplacepy.services.audit import record as audit
+            from devplacepy.services.openai_gateway.usage import audit_actor_for
+
+            actor_kind, actor_uid, actor_role = audit_actor_for(owner[0], owner[1])
+            audit.record_system(
+                "ai.gateway.call",
+                actor_kind=actor_kind,
+                actor_uid=actor_uid,
+                actor_role=actor_role,
+                origin="api",
+                result="denied",
+                summary="embeddings disabled",
+                metadata={
+                    "backend": "embed",
+                    "endpoint": "embeddings",
+                    "owner_kind": owner[0],
+                    "owner_id": owner[1],
+                },
+            )
             return JSONResponse(
                 status_code=503,
                 content={