Refactoring post PRs (#61)

* - File configs.yaml.example impostato con modelli ollama piccoli di default (come in fasi iniziali progetto). Eliminati altri provider con chiavi a pagamento. Eliminato GPT-OSS poiché modello problematico e incompatibile con metodi standard ollama. Gemini 2.5 sembra funzionare ma è sempre intasato e non ne abbiamo assoluta conferma.
- Eliminati documenti inutili e datati

* doc esame reintrodotto

* configs.yaml.example riaggiunto dati completi

* fix

* Add ReasoningTools for enhanced decision-making and analysis processes

---------

Co-authored-by: Berack96 <giacomobertolazzi7@gmail.com>

configs.yaml.example

@@ -27,18 +27,16 @@ models:
     - name: mistral-large-latest
       label: Mistral
   ollama:
-    - name: gpt-oss:latest
-      label: Ollama GPT
-    - name: qwen3:8b
-      label: Qwen 3 (8B)
-    - name: qwen3:4b
-      label: Qwen 3 (4B)
     - name: qwen3:1.7b
       label: Qwen 3 (1.7B)
-    - name: qwen3:32b
-      label: Qwen 3 (32B)
+    - name: qwen3:4b
+      label: Qwen 3 (4B)
+    - name: qwen3:8b
+      label: Qwen 3 (8B)
     - name: qwen3:14b
       label: Qwen 3 (14B)
+    - name: qwen3:32b
+      label: Qwen 3 (32B)
     - name: phi4-mini:3.8b
       label: Phi 4 mini (3.8b)
 
@@ -51,7 +49,7 @@ api:
 
 agents:
   strategy: Conservative
-  team_model: qwen3:14b # the agents
+  team_model: qwen3:8b # 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
+  query_analyzer_model: qwen3:1.7b # query check
+  report_generation_model: qwen3:8b # ex predictor