feat: update provider model selections

docs/concepts/architecture.mdx

@@ -79,7 +79,7 @@ llm_profiles:
     model: gpt-4o
   fast_agent:
     provider: GoogleGenAI
-    model: gemini-3.1-flash-lite-preview
+    model: gemini-3.1-flash-lite
 agent:
   reasoning: true       # Enable Manager/Executor workflow
   max_steps: 15         # Maximum execution steps (global)

docs/features/structured-output.mdx

@@ -124,7 +124,7 @@ By default, extraction uses the `structured_output` LLM profile. If not configur
 llm_profiles:
   fast_agent:
     provider: GoogleGenAI
-    model: gemini-3.1-flash-lite-preview
+    model: gemini-3.1-flash-lite
     temperature: 0.3
 
   structured_output:
@@ -140,7 +140,7 @@ from mobilerun import load_llm
 config = MobileConfig()
 
 llms = {
-    "fast_agent": load_llm("GoogleGenAI", "gemini-3.1-flash-lite-preview"),
+    "fast_agent": load_llm("GoogleGenAI", "gemini-3.1-flash-lite"),
     "structured_output": load_llm("OpenAI", "gpt-4o-mini"),
 }
 

docs/guides/cli.mdx

@@ -94,7 +94,7 @@ In screenshot-only mode, Mobilerun does not read an accessibility tree. The agen
 export GOOGLE_API_KEY=your-key
 mobilerun run "Archive old emails" \
   --provider GoogleGenAI \
-  --model gemini-3.1-flash-lite-preview
+  --model gemini-3.1-flash-lite
 
 # OpenAI
 export OPENAI_API_KEY=your-key
@@ -384,7 +384,7 @@ trajectories/2025-10-16_14-30-45/
 ```bash Quick Test
 mobilerun run "Turn on dark mode" \
   --provider GoogleGenAI \
-  --model gemini-3.1-flash-lite-preview
+  --model gemini-3.1-flash-lite
 ```
 
 ```bash Debug Task
@@ -405,7 +405,7 @@ mobilerun run "Check Wi-Fi" \
 ```bash Cost Optimization
 mobilerun run "Set alarm" \
   --provider GoogleGenAI \
-  --model gemini-3.1-flash-lite-preview \
+  --model gemini-3.1-flash-lite \
   --no-vision
 ```
 

docs/quickstart.mdx

@@ -122,7 +122,7 @@ mobilerun run "Find a contact named John and send him an email" --reasoning
 
 **Common CLI flags:**
 - `--provider` - LLM provider (GoogleGenAI, OpenAI, Anthropic, etc.)
-- `--model` - Model name (gemini-3.1-flash-lite-preview, gpt-4o, etc.)
+- `--model` - Model name (gemini-3.1-flash-lite, gpt-4o, etc.)
 - `--vision` - Enable screenshot processing
 - `--reasoning` - Enable multi-agent planning mode
 - `--steps N` - Maximum execution steps (default: 15)

docs/sdk/configuration.mdx

@@ -228,7 +228,7 @@ CredentialsConfig(
 ```python
 from llama_index.llms.google_genai import GoogleGenAI
 
-llm = GoogleGenAI(model="gemini-3.1-flash-lite-preview", temperature=0.2)
+llm = GoogleGenAI(model="gemini-3.1-flash-lite", temperature=0.2)
 agent = MobileAgent(goal="...", llms=llm)
 ```
 
@@ -242,10 +242,10 @@ agent = MobileAgent(
     goal="...",
     llms={
         "manager": OpenAI(model="gpt-4o"),                    # Planning
-        "executor": GoogleGenAI(model="gemini-3.1-flash-lite-preview"),  # Action selection
-        "fast_agent": GoogleGenAI(model="gemini-3.1-flash-lite-preview"),   # Fast Agent: Direct execution (XML tool-calling)
+        "executor": GoogleGenAI(model="gemini-3.1-flash-lite"),  # Action selection
+        "fast_agent": GoogleGenAI(model="gemini-3.1-flash-lite"),   # Fast Agent: Direct execution (XML tool-calling)
         "app_opener": OpenAI(model="gpt-4o-mini"),            # App launching
-        "structured_output": GoogleGenAI(model="gemini-3.1-flash-lite-preview"),  # Output extraction
+        "structured_output": GoogleGenAI(model="gemini-3.1-flash-lite"),  # Output extraction
     }
 )
 ```
@@ -429,10 +429,10 @@ agent = MobileAgent(
     # LLMs
     llms={
         "manager": OpenAI(model="gpt-4o"),                    # Planning
-        "executor": GoogleGenAI(model="gemini-3.1-flash-lite-preview"),  # Action selection
-        "fast_agent": GoogleGenAI(model="gemini-3.1-flash-lite-preview"),   # Fast Agent: Direct execution (XML tool-calling)
+        "executor": GoogleGenAI(model="gemini-3.1-flash-lite"),  # Action selection
+        "fast_agent": GoogleGenAI(model="gemini-3.1-flash-lite"),   # Fast Agent: Direct execution (XML tool-calling)
         "app_opener": OpenAI(model="gpt-4o-mini"),            # App launching
-        "structured_output": GoogleGenAI(model="gemini-3.1-flash-lite-preview"),  # Output extraction
+        "structured_output": GoogleGenAI(model="gemini-3.1-flash-lite"),  # Output extraction
     },
 
     # Custom tools
@@ -505,21 +505,21 @@ agent:
 llm_profiles:
   manager:
     provider: GoogleGenAI
-    model: gemini-3.1-flash-lite-preview
+    model: gemini-3.1-flash-lite
     temperature: 0.2
     kwargs:
       max_tokens: 8192
 
   executor:
     provider: GoogleGenAI
-    model: gemini-3.1-flash-lite-preview
+    model: gemini-3.1-flash-lite
     temperature: 0.1
     kwargs:
       max_tokens: 4096
 
   fast_agent:  # Fast Agent: Direct execution (XML tool-calling)
     provider: GoogleGenAI
-    model: gemini-3.1-flash-lite-preview
+    model: gemini-3.1-flash-lite
     temperature: 0.2
     kwargs:
       max_tokens: 8192
@@ -531,7 +531,7 @@ llm_profiles:
 
   structured_output:
     provider: GoogleGenAI
-    model: gemini-3.1-flash-lite-preview
+    model: gemini-3.1-flash-lite
     temperature: 0.0
 
 device:
@@ -585,7 +585,7 @@ mobilerun run "Task" --steps 30 --reasoning --vision
 mobilerun run "Task" --device emulator-5554 --tcp
 
 # Override LLM (applies to ALL agents)
-mobilerun run "Task" --provider GoogleGenAI --model gemini-3.1-flash-lite-preview
+mobilerun run "Task" --provider GoogleGenAI --model gemini-3.1-flash-lite
 
 # Override logging
 mobilerun run "Task" --debug --save-trajectory action --tracing

mobilerun/agent/providers/registry.py

@@ -33,9 +33,10 @@
                 auth_mode="api_key",
                 default_model="gemini-3.1-pro-preview",
                 models=(
+                    "gemini-3.5-flash",
                     "gemini-3-flash-preview",
                     "gemini-3.1-pro-preview",
-                    "gemini-3.1-flash-lite-preview",
+                    "gemini-3.1-flash-lite",
                 ),
                 requires_api_key=True,
             ),
@@ -47,7 +48,7 @@
                 models=(
                     "gemini-3-flash-preview",
                     "gemini-3.1-pro-preview",
-                    "gemini-3.1-flash-lite-preview",
+                    "gemini-3.1-flash-lite",
                 ),
                 credential_path=str(GEMINI_OAUTH_CREDENTIAL_PATH),
             ),
@@ -61,8 +62,9 @@
                 id="OpenAIResponses",
                 runtime_provider_name="OpenAIResponses",
                 auth_mode="api_key",
-                default_model="gpt-5.4",
+                default_model="gpt-5.5",
                 models=(
+                    "gpt-5.5",
                     "gpt-5.4",
                     "gpt-5.4-mini",
                     "gpt-5.4-nano",
@@ -73,11 +75,11 @@
                 id="openai_oauth",
                 runtime_provider_name="openai_oauth",
                 auth_mode="oauth",
-                default_model="gpt-5.4",
+                default_model="gpt-5.5",
                 models=(
+                    "gpt-5.5",
                     "gpt-5.4",
                     "gpt-5.4-mini",
-                    "gpt-5.3-codex",
                 ),
                 credential_path=str(OPENAI_OAUTH_CREDENTIAL_PATH),
             ),
@@ -95,6 +97,7 @@
                 default_model="claude-sonnet-4-6",
                 models=(
                     "claude-sonnet-4-6",
+                    "claude-opus-4-8",
                     "claude-opus-4-6",
                     "claude-haiku-4-5",
                 ),
@@ -107,6 +110,7 @@
                 default_model="claude-opus-4-7",
                 models=(
                     "claude-opus-4-7",
+                    "claude-opus-4-8",
                     "claude-sonnet-4-6",
                     "claude-opus-4-6",
                     "claude-haiku-4-5",

mobilerun/agent/usage.py

@@ -24,6 +24,12 @@
     "Ollama",
 ]
 
+PROVIDER_ALIASES = {
+    "MobilerunAnthropic": "Anthropic",
+    "MobilerunOpenAIResponses": "OpenAIResponses",
+    "openai_responses_llm": "OpenAIResponses",
+}
+
 
 class UsageResult(BaseModel):
     request_tokens: int
@@ -50,7 +56,12 @@ def _usage_field(usage: Any, *names: str) -> int:
     return 0
 
 
+def _normalize_provider_name(provider: str) -> str:
+    return PROVIDER_ALIASES.get(provider, provider)
+
+
 def get_usage_from_response(provider: str, chat_rsp: ChatResponse) -> UsageResult:
+    provider = _normalize_provider_name(provider)
     rsp = chat_rsp.raw
     if not rsp:
         raise ValueError("No raw response in chat response")
@@ -210,7 +221,7 @@ def llm_callback(llm: LLM, *args: List[BaseCallbackHandler]):
 
 
 def create_tracker(llm: LLM) -> TokenCountingHandler:
-    provider = llm.__class__.__name__
+    provider = _normalize_provider_name(llm.__class__.__name__)
     if provider not in SUPPORTED_PROVIDERS:
         raise ValueError(f"Tracking not yet supported for provider: {provider}")
 
@@ -245,7 +256,7 @@ def track_usage(llm: LLM) -> TokenCountingHandler:
         >>> # ... make LLM calls ...
         >>> print(f"Total tokens used: {tracker.usage.total_tokens}")
     """
-    provider = llm.__class__.__name__
+    provider = _normalize_provider_name(llm.__class__.__name__)
     if provider not in SUPPORTED_PROVIDERS:
         raise ValueError(f"Tracking not yet supported for provider: {provider}")