Set recommended temperature to 1.0 for all workloads

README.md

@@ -150,7 +150,7 @@ curl https://apihub.agnes-ai.com/v1/chat/completions \
         "content": "Review this API handler for security issues and provide a corrected version."
       }
     ],
-    "temperature": 0.2,
+    "temperature": 1.0,
     "max_tokens": 2000
   }'
 ```
@@ -178,7 +178,7 @@ response = client.chat.completions.create(
             "content": "Design a fault-tolerant event processing architecture.",
         }
     ],
-    temperature=0.3,
+    temperature=1.0,
     max_tokens=2000,
 )
 
@@ -222,15 +222,15 @@ curl https://apihub.agnes-ai.com/v1/responses \
 
 Use sampling rather than greedy decoding. Leave enough `max_tokens` / `max_output_tokens` for extended reasoning.
 
-| Setting | Default | Coding and tool use |
-|---|---|---|
-| `temperature` | 1.0 | 0.2–0.3 |
-| `top_p` | 0.95 | 0.95 |
-| `top_k` | 20 | 20 |
-| `repetition_penalty` | 1.05 | 1.05 |
-| `max_tokens` | 2000 or higher | 2000 or higher |
+| Setting | Recommended |
+|---|---|
+| `temperature` | 1.0 |
+| `top_p` | 0.95 |
+| `top_k` | 20 |
+| `repetition_penalty` | 1.05 |
+| `max_tokens` | 2000 or higher |
 
-The coding examples in Quickstart use `temperature` 0.2 (Chat Completions) and 0.3 (Python). Raise `max_tokens` if a response stops early.
+Raise `max_tokens` if a response stops early.
 
 ## Model Capabilities