Initial implementation of IRC LLM bot

Full implementation from spec: ZNC/IRC client with TLS, Ollama LLM backend,
per-user SQLite conversation memory, and Flask web admin portal with 7 pages.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

bot/llm_client.py

@@ -0,0 +1,70 @@
+import httpx
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+def generate(prompt: str, system: str, config: dict) -> str:
+    host = config.get("ollama_host", "192.168.2.10")
+    port = config.get("ollama_port", 11434)
+    model = config.get("ollama_model", "llama3.1")
+    timeout = config.get("response_timeout_seconds", 30)
+    num_predict = config.get("ollama_num_predict", 120)
+    num_ctx = config.get("ollama_num_ctx", 2048)
+    temperature = config.get("ollama_temperature", 0.7)
+    max_length = config.get("max_response_length", 400)
+
+    url = f"http://{host}:{port}/api/generate"
+    payload = {
+        "model": model,
+        "system": system,
+        "prompt": prompt,
+        "stream": False,
+        "options": {
+            "temperature": temperature,
+            "num_predict": num_predict,
+            "num_ctx": num_ctx,
+        },
+    }
+
+    logger.debug(f"[LLM] POST {url} model={model} prompt_len={len(prompt)}")
+
+    try:
+        response = httpx.post(url, json=payload, timeout=timeout)
+        response.raise_for_status()
+        text = response.json().get("response", "").strip()
+        if len(text) > max_length:
+            text = text[:max_length].rsplit(" ", 1)[0] + "…"
+        logger.debug(f"[LLM] Response ({len(text)} chars): {text[:80]}")
+        return text
+    except httpx.TimeoutException:
+        logger.error(f"[LLM] Timeout after {timeout}s")
+        raise TimeoutError(f"Ollama did not respond within {timeout}s")
+    except Exception as e:
+        logger.error(f"[LLM] Request failed: {e}")
+        raise
+
+
+def build_prompt(
+    user_message: str,
+    nick: str,
+    persistent_history: list[dict],
+    context_buffer: list[str],
+) -> str:
+    parts = []
+
+    if persistent_history:
+        parts.append("--- Past conversation with this user ---")
+        for ex in persistent_history:
+            parts.append(f"User: {ex['user']}")
+            parts.append(f"Assistant: {ex['assistant']}")
+        parts.append("--- End of past conversation ---")
+
+    if context_buffer:
+        parts.append("--- Recent channel activity ---")
+        parts.extend(context_buffer)
+        parts.append("--- End of channel activity ---")
+
+    parts.append(f"{nick} asks: {user_message}")
+
+    return "\n".join(parts)