Repo sync

content/copilot/concepts/auto-model-selection.md

@@ -24,7 +24,7 @@ Experience less rate limiting and reduce the mental load of choosing a model by
 * Models excluded by administrator policies. See [AUTOTITLE](/copilot/how-tos/copilot-on-github/set-up-copilot/configure-access-to-ai-models).
 * Models with premium request multipliers greater than one. See [AUTOTITLE](/copilot/reference/ai-models/supported-models#model-multipliers).
 * Models not available in your plan. See [AUTOTITLE](/copilot/reference/ai-models/supported-models#supported-ai-models-per-copilot-plan).
- 
+
 > [!NOTE] Soon {% data variables.copilot.copilot_auto_model_selection %} will choose the best model for you based on your task.
 
 ## {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} in {% data variables.copilot.copilot_chat_short %}
@@ -38,9 +38,9 @@ Experience less rate limiting and reduce the mental load of choosing a model by
   * Eclipse
   * Xcode
 
-When you select **Auto** in {% data variables.copilot.copilot_chat_short %}, {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} chooses from the supported models, subject to your policies and subscription type. Models may change over time. See [AUTOTITLE](/copilot/reference/ai-models/supported-models#supported-ai-models-in-auto-model-selection).
+When you select **Auto** in {% data variables.copilot.copilot_chat_short %} in IDEs, {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} chooses from the supported models, subject to your policies and subscription type. Models may change over time. See [AUTOTITLE](/copilot/reference/ai-models/supported-models#supported-ai-models-in-auto-model-selection).
 
-> [!TIP] To see which model was used for each response, hover over the response in {% data variables.copilot.copilot_chat_short %}.
+> [!TIP] To see which model was used for each response, hover over the response in {% data variables.copilot.copilot_chat_short %} in IDEs.
 
  {% data reusables.copilot.change-the-ai-model %}
 
@@ -52,6 +52,14 @@ When you select **Auto** in {% data variables.copilot.copilot_chat_short %}, {%
 
 During the {% data variables.release-phases.public_preview %}, if you're using a {% data variables.copilot.copilot_business_short %} or {% data variables.copilot.copilot_enterprise_short %} plan, the organization or enterprise that provides your plan must have the **Editor preview features** policy enabled. See [AUTOTITLE](/enterprise-cloud@latest/copilot/managing-copilot/managing-github-copilot-in-your-organization/managing-policies-for-copilot-in-your-organization#enabling-copilot-features-in-your-organization) or [AUTOTITLE](/enterprise-cloud@latest/copilot/managing-copilot/managing-copilot-for-your-enterprise/managing-policies-and-features-for-copilot-in-your-enterprise#copilot-in-githubcom).
 
+## {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} in {% data variables.copilot.copilot_cli %}
+
+When you select **Auto** from the list of available models in {% data variables.copilot.copilot_cli %}, {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} chooses from the supported models, subject to your policies and subscription type. Models may change over time. See [AUTOTITLE](/copilot/reference/ai-models/supported-models#supported-ai-models-in-auto-model-selection).
+
+When using Auto, the model used for each response displays in the terminal.
+
+ {% data reusables.copilot.change-the-ai-model %}
+
 ## {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} in {% data variables.copilot.copilot_cloud_agent %}
 
 When you select **Auto** in {% data variables.copilot.copilot_cloud_agent %}, {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} chooses from the supported list of models, subject to your policies and subscription type. See [AUTOTITLE](/copilot/reference/ai-models/supported-models#supported-ai-models-in-auto-model-selection).

content/copilot/concepts/rate-limits.md

@@ -37,6 +37,7 @@ If you receive a rate limit error when using {% data variables.product.prodname_
 * **Wait and try again.** Rate limits are temporary. Often, waiting a short period and trying again resolves the issue.
 * **Check your usage.** If you’re making frequent or automated requests (for example, rapid-fire completions or large-scale usage), consider adjusting your usage pattern.
 * **Change your model.** Select models may have stricter rate limits due to limited capacity.
+* **Switch to {% data variables.copilot.copilot_auto_model_selection %}.** If you hit a **weekly** rate limit, you can continue using {% data variables.product.prodname_copilot_short %} with {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} until exhausting your premium requests.
 * **Upgrade your plan.** If you are on an individual {% data variables.product.prodname_copilot_short %} plan, upgrading your plan will allow for additional usage. 
 * **Contact Support.** If you’re repeatedly rate limited and believe it’s impacting legitimate use, contact {% data variables.contact.contact_support_page %} for assistance.
 

content/copilot/how-tos/copilot-cli/cli-best-practices.md

@@ -94,12 +94,14 @@ Use `/model` to choose from available models based on your task complexity:
 
 | Model | Best For | Tradeoffs |
 | ----- | -------- | --------- |
+| **Auto** | Reduced rate limiting and lower latency and errors | See [AUTOTITLE](/copilot/concepts/auto-model-selection#auto-model-selection-in-github-copilot-cli)|
 | **Claude Opus 4.5** (default) | Complex architecture, difficult debugging, nuanced refactoring | Most capable but uses more [premium requests](/copilot/concepts/billing/copilot-requests#model-multipliers) |
 | **Claude Sonnet 4.5** | Day-to-day coding, most routine tasks | Fast, cost-effective, handles most work well |
 | **GPT-5.2 Codex** | Code generation, code review, straightforward implementations | Excellent for reviewing code produced by other models |
 
 **Recommendations:**
 
+* **Auto** intelligently chooses models based on real time system health and model performance, reducing rate limiting and providing lower latency and errors.
 * **Opus 4.5** is ideal for tasks requiring deep reasoning, complex system design, subtle bug investigation, or extensive context understanding.
 * **Switch to Sonnet 4.5** for routine tasks where speed and cost efficiency matter—it handles the majority of everyday coding effectively.
 * **Use Codex** for high-volume code generation and as a second opinion for reviewing code produced by other models.

content/copilot/reference/ai-models/supported-models.md

@@ -51,10 +51,10 @@ This table lists the AI models available in {% data variables.copilot.copilot_au
 
 {% rowheaders %}
 
-| Model | {% data variables.copilot.copilot_cloud_agent %} | {% data variables.copilot.copilot_chat_short %} |
-| --- | --- | --- |
+| Model | {% data variables.copilot.copilot_cloud_agent %} | {% data variables.copilot.copilot_chat_short %} | {% data variables.copilot.copilot_cli_short %} |
+| --- | --- | --- | --- |
 | {% for model in tables.copilot.auto-model-selection %} |
-| {{ model.name }} | {% if model.cloud_agent == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} | {% if model.chat == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} |
+| {{ model.name }} | {% if model.cloud_agent == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} | {% if model.chat == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} | {% if model.cli == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} |
 | {% endfor %} |
 
 {% endrowheaders %}

data/tables/copilot/auto-model-selection.yml

@@ -15,43 +15,58 @@
 # - name: The model name.
 # - cloud_agent: Availability for Copilot cloud agent.
 # - chat: Availability for Copilot Chat.
+# - cli: Availability for Copilot CLI.
 
 # OpenAI
 - name: GPT-4.1
   cloud_agent: false
   chat: true
+  cli: false
+
+- name: GPT-5 mini
+  cloud_agent: false
+  chat: false
+  cli: true
 
 - name: GPT-5.3-Codex
   cloud_agent: false
   chat: true
+  cli: true
 
 - name: GPT-5.4
   cloud_agent: false
   chat: true
+  cli: true
 
 - name: GPT-5.4 mini
   cloud_agent: false
   chat: true
+  cli: true
 
 # Anthropic
 - name: Claude Haiku 4.5
   cloud_agent: false
   chat: true
+  cli: true
 
 - name: Claude Sonnet 4.5
   cloud_agent: true
   chat: false
+  cli: false
 
 - name: Claude Sonnet 4.6
   cloud_agent: false
   chat: true
+  cli: true
 
 # xAI
 - name: Grok Code Fast 1
   cloud_agent: false
   chat: true
+  cli: false
 
 # Fine-tuned OAI models
 - name: Raptor mini
   cloud_agent: false
   chat: true
+  cli: false

src/data-directory/lib/data-schemas/tables/copilot/auto-model-selection.ts

@@ -5,7 +5,7 @@ const autoModelSelectionSchema = {
   items: {
     type: 'object',
     additionalProperties: false,
-    required: ['name', 'cloud_agent', 'chat'],
+    required: ['name', 'cloud_agent', 'chat', 'cli'],
     properties: {
       name: {
         type: 'string',
@@ -17,6 +17,9 @@ const autoModelSelectionSchema = {
       chat: {
         type: 'boolean',
       },
+      cli: {
+        type: 'boolean',
+      },
     },
   },
 }