docs: Remove prompt caching instructions for Gemini and OpenRouter providers

Author: hannesrudolph

docs/providers/gemini.md

@@ -43,13 +43,6 @@ Refer to the [Gemini documentation](https://ai.google.dev/models/gemini) for mor
 3.  **Enter API Key:** Paste your Gemini API key into the "Gemini API Key" field.
 4.  **Select Model:** Choose your desired Gemini model from the "Model" dropdown.
 
-5.  **(Optional) Enable Prompt Caching (Gemini 2.5 Models):** For supported Gemini 2.5 models, check the "Enable Prompt Caching" box if you wish to activate prompt caching. See the note below for important details specific to this provider.
-    <img src="/img/v3.14.2/v3.14.2.png" alt="Prompt Caching Checkbox for Gemini Provider" width="600" />
 ## Tips and Notes
 
-*   **Prompt Caching (Manual Activation Required):**
-    *   Prompt caching is available for supported Gemini 2.5 models.
-    *   However, for the **Google Gemini provider**, caching is **not enabled by default**.
-    *   You **must manually check** the "Enable Prompt Caching" box in the provider settings to activate it.
-    *   **Reason:** This manual step is a temporary workaround due to potential response delays sometimes observed with Google's caching mechanism when accessed directly via this provider.
 *   **Pricing:**  Gemini API usage is priced based on input and output tokens. Refer to the [Gemini pricing page](https://ai.google.dev/pricing) for detailed information.

docs/providers/openrouter.md

@@ -26,8 +26,6 @@ OpenRouter supports a large and growing number of models.  Roo Code automaticall
 4.  **Select Model:** Choose your desired model from the "Model" dropdown.
 5.  **(Optional) Custom Base URL:** If you need to use a custom base URL for the OpenRouter API, check "Use custom base URL" and enter the URL. Leave this blank for most users.
 
-6.  **(Optional) Enable Prompt Caching (Supported Models):** For models accessed via OpenRouter that support caching (like Gemini 2.5), check the "Enable Prompt Caching" box if you wish to activate it. See the note below for important details specific to this provider.
-    <img src="/img/v3.14.2/v3.14.2.png" alt="Prompt Caching Checkbox for OpenRouter Provider" width="600" />
 ## Supported Transforms
 
 OpenRouter provides an [optional "middle-out" message transform](https://openrouter.ai/docs/features/message-transforms) to help with prompts that exceed the maximum context size of a model. You can enable it by checking the "Compress prompts and message chains to the context size" box.