Better Prompt (#45)

* Enhance report generation and team leader prompts with conditional output rules for empty sections.

* Update .gitignore and configuration for model adjustments; refine query classification prompt

* Enforce max response length in prompts

* Documentazione tool essenziale per il loro utilizzo da parte degli LLM.

* istruzioni chiare sui tool disponibili nei promt degli agenti

* corretto incongruenze nel report generation prompt

* convertito i promt in file markdown

configs.yaml

@@ -37,6 +37,12 @@ models:
       label: Qwen 3 (4B)
     - name: qwen3:1.7b
       label: Qwen 3 (1.7B)
+    - name: qwen3:32b
+      label: Qwen 3 (32B)
+    - name: qwen3:14b
+      label: Qwen 3 (14B)
+    - name: phi4-mini:3.8b
+      label: Phi 4 mini (3.8b)
 
 api:
   retry_attempts: 3
@@ -47,7 +53,7 @@ api:
 
 agents:
   strategy: Conservative
-  team_model: qwen3:1.7b
-  team_leader_model: qwen3:8b
-  query_analyzer_model: qwen3:4b
-  report_generation_model: qwen3:8b
+  team_model: qwen3:14b # the agents
+  team_leader_model: gemini-2.0-flash # the team leader
+  query_analyzer_model: qwen3:14b # query check
+  report_generation_model: qwen3:32b # ex predictor