Fix Bedrock model IDs for on-demand inference (remove :0 suffix)

llm.py

@@ -362,7 +362,7 @@ def check_credentials():
             bedrock_runtime = get_bedrock_client()
             # Try a simple test invocation to verify credentials
             test_response = bedrock_runtime.invoke_model(
-                modelId="anthropic.claude-3-haiku-20240307-v1:0",
+                modelId="anthropic.claude-3-haiku-20240307-v1",
                 contentType="application/json",
                 accept="application/json",
                 body=json.dumps({

model_config.py

@@ -5,8 +5,8 @@ PROVIDER_MODEL_MAP = {
         "gpt-5-nano",
     ],
     "anthropic": [
-        "anthropic.claude-3-5-sonnet-20241022-v2:0",
-        "anthropic.claude-3-haiku-20240307-v1:0",
+        "anthropic.claude-3-5-sonnet-20241022-v2",
+        "anthropic.claude-3-haiku-20240307-v1",
     ],
 }
 
@@ -22,8 +22,8 @@ MODEL_DISPLAY_NAMES = {
     "gpt-4.1-mini": "OpenAI - GPT-4.1 Mini",
     "gpt-5-mini": "OpenAI - GPT-5 Mini",
     "gpt-5-nano": "OpenAI - GPT-5 Nano",
-    "anthropic.claude-3-5-sonnet-20241022-v2:0": "AWS Bedrock - Anthropic - Claude 3.5 Sonnet",
-    "anthropic.claude-3-haiku-20240307-v1:0": "AWS Bedrock - Anthropic - Claude 3 Haiku",
+    "anthropic.claude-3-5-sonnet-20241022-v2": "AWS Bedrock - Anthropic - Claude 3.5 Sonnet",
+    "anthropic.claude-3-haiku-20240307-v1": "AWS Bedrock - Anthropic - Claude 3 Haiku",
 }
 
 MODEL_CHOICES = [model for models in PROVIDER_MODEL_MAP.values() for model in models]