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/deepsearch/llm.py

@@ -0,0 +1,44 @@
+# retoor <retoor@molodetz.nl>
+
+from __future__ import annotations
+
+import logging
+
+import httpx
+
+from devplacepy.config import INTERNAL_GATEWAY_URL, INTERNAL_MODEL
+
+logger = logging.getLogger(__name__)
+
+CHAT_TIMEOUT_SECONDS = 120.0
+DEFAULT_MAX_TOKENS = 1200
+
+
+async def complete_chat(
+    messages: list[dict],
+    api_key: str,
+    *,
+    gateway_url: str = INTERNAL_GATEWAY_URL,
+    model: str = INTERNAL_MODEL,
+    max_tokens: int = DEFAULT_MAX_TOKENS,
+    temperature: float = 0.2,
+) -> str:
+    payload = {
+        "model": model,
+        "messages": messages,
+        "max_tokens": max_tokens,
+        "temperature": temperature,
+    }
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json",
+    }
+    async with httpx.AsyncClient(timeout=CHAT_TIMEOUT_SECONDS) as client:
+        response = await client.post(gateway_url, json=payload, headers=headers)
+    if response.status_code >= 400:
+        raise RuntimeError(f"chat gateway returned {response.status_code}")
+    data = response.json()
+    choices = data.get("choices") or []
+    if not choices:
+        raise RuntimeError("chat gateway returned no choices")
+    return (choices[0].get("message", {}).get("content") or "").strip()