docs: refresh model references to current models

docs/features/experimental/concurrent-file-edits.md

@@ -91,7 +91,7 @@ This feature leverages the [`apply_diff`](/advanced-usage/available-tools/apply-
 ## Best Practices
 
 ### When to Enable
-- Using capable AI models (Claude 3.5 Sonnet, GPT-4, etc.)
+- Using capable AI models (Claude Sonnet 4 or Claude 3.7 Sonnet, GPT-4.1/GPT-4o, GPT-5 family)
 - Comfortable reviewing multiple changes at once
 
 ### When to Keep Disabled

docs/providers/claude-code.md

@@ -99,11 +99,15 @@ export CLAUDE_CODE_MAX_OUTPUT_TOKENS=32768  # Set to 32k tokens
 The Claude Code provider supports these Claude models:
 
 - **Claude Opus 4.1** (Most capable)
-- **Claude Opus 4** 
+- **Claude Opus 4**
 - **Claude Sonnet 4** (Latest, recommended)
 - **Claude 3.7 Sonnet**
-- **Claude 3.5 Sonnet**
-- **Claude 3.5 Haiku** (Fast responses)
+
+:::note Legacy models
+These older models may still be available via the Claude CLI depending on your subscription, but are no longer recommended in new setups:
+- Claude 3.5 Sonnet
+- Claude 3.5 Haiku
+:::
 
 The specific models available depend on your Claude CLI subscription and plan.
 

docs/providers/litellm.md

@@ -133,7 +133,7 @@ When you configure the LiteLLM provider, Roo Code interacts with your LiteLLM se
     *   `supportsImages`: Determined from `model_info.supports_vision` provided by LiteLLM.
     *   `supportsPromptCache`: Determined from `model_info.supports_prompt_caching` provided by LiteLLM.
     *   `inputPrice` / `outputPrice`: Calculated from `model_info.input_cost_per_token` and `model_info.output_cost_per_token` from LiteLLM.
-    *   `supportsComputerUse`: This flag is set to `true` if the underlying model identifier (from `litellm_params.model`, e.g., `openrouter/anthropic/claude-3.5-sonnet`) matches one of the Anthropic models predefined in Roo Code as suitable for "computer use" (see `COMPUTER_USE_MODELS` in technical details).
+    *   `supportsComputerUse`: This flag is set to `true` if the underlying model identifier (from `litellm_params.model`, e.g., `openrouter/anthropic/claude-3.7-sonnet-20250219`) matches one of the Anthropic models predefined in Roo Code as suitable for "computer use" (see `COMPUTER_USE_MODELS` in technical details).
 
 Roo Code uses default values for some of these properties if they are not explicitly provided by your LiteLLM server's `/model/info` endpoint for a given model. The defaults are:
 *   `maxTokens`: 8192

docs/providers/openai-compatible.md

@@ -59,7 +59,6 @@ While this provider type allows connecting to various endpoints, if you are conn
 *   `o1`
 *   `o1-preview`
 *   `o1-mini`
-*   `gpt-4.5-preview`
 *   `gpt-4o`
 *   `gpt-4o-mini`
 

docs/providers/openai.md

@@ -84,7 +84,6 @@ Original reasoning models:
 ### GPT-4o Family
 Optimized GPT-4 models:
 
-* `gpt-4.5-preview`
 * `gpt-4o` - Optimized GPT-4
 * `gpt-4o-mini` - Smaller optimized variant
 

docs/providers/vscode-lm.md

@@ -37,7 +37,7 @@ Roo Code includes *experimental* support for the [VS Code Language Model API](ht
 1.  **Open Roo Code Settings:** Click the gear icon (<Codicon name="gear" />) in the Roo Code panel.
 2.  **Select Provider:** Choose "VS Code LM API" from the "API Provider" dropdown.
 3.  **Select Model:**  The "Language Model" dropdown will (eventually) list available models. The format is `vendor/family`. For example, if you have Copilot, you might see options like:
-    *   `copilot - claude-3.5-sonnet`
+    *   `copilot - claude-3.7-sonnet`
     *   `copilot - o3-mini`
     *   `copilot - o1-ga`
     *   `copilot - gemini-2.0-flash`