Overhaul agent quality — prompts, tools, config, compression

- Rewrite system prompt: structured sections, explicit tool descriptions
  with full SKILL.md descriptions, multi-agent awareness
- Add write_file skill for creating/modifying workspace files
- Per-template config passthrough: temperature, num_predict, context_size,
  compress settings, max_tool_rounds, max_response_lines
- Bump defaults: 1024 output tokens (was 512), 500-char deque (was 200),
  250-token summaries (was 150), compress threshold 16 (was 12), keep 8 (was 4)
- Cache compression by content hash — no redundant summarization
- Update all 5 templates with tuned settings per role

agent/tools.py

@@ -72,13 +72,13 @@ def ollama_request(ollama_url, payload):
         return json.loads(resp.read(2_000_000))
 
 
-def query_ollama(messages, runtime, tools, skill_scripts, dispatch_fn, ollama_url, max_rounds):
+def query_ollama(messages, runtime, tools, skill_scripts, dispatch_fn, ollama_url, max_rounds, num_predict=1024, temperature=0.7):
     """Call Ollama chat API with skill-based tool support."""
     payload = {
         "model": runtime["model"],
         "messages": messages,
         "stream": False,
-        "options": {"num_predict": 512},
+        "options": {"num_predict": num_predict, "temperature": temperature},
     }
 
     if tools: