@@ -49,7 +49,7 @@ The following third-party agents are supported on {% data variables.product.gith
 
 When starting a task with a third-party agent, you can select the AI model used by the agent. You may find that different models perform better, or provide more useful responses, depending on the type of task. For help deciding which model to use, see [AUTOTITLE](/copilot/reference/ai-models/model-comparison).
 
-You can also select **Auto**, which allows {% data variables.copilot.copilot_auto_model_selection %} to choose the best available model on your behalf. See [AUTOTITLE](/copilot/concepts/models/auto-model-selection).
+You can also select **Auto**, which chooses between the supported models below. Choosing **Auto** with third-party agents does **not** leverage {% data variables.copilot.copilot_auto_model_selection %}. See [AUTOTITLE](/copilot/concepts/models/auto-model-selection).
 
 The following models are available for each agent:
 
 
@@ -27,4 +27,4 @@ When starting a task with the {% data variables.product.prodname_anthropic_claud
 * Auto
 {% data reusables.copilot.anthropic-claude-agent-models %}
 
-If you select **Auto**, {% data variables.copilot.copilot_auto_model_selection %} will select the best model based on availability and to help reduce rate limiting. For more information, see [AUTOTITLE](/copilot/concepts/models/auto-model-selection).
+If you select **Auto**, it will choose one of the available models listed above. **Auto** in {% data variables.product.prodname_anthropic_claude %} coding agent does **not** leverage {% data variables.copilot.copilot_auto_model_selection %}.
@@ -30,7 +30,7 @@ When starting a task with the {% data variables.product.prodname_openai_codex %}
 * Auto
 {% data reusables.copilot.openai-codex-agent-models %}
 
-If you select **Auto**, {% data variables.copilot.copilot_auto_model_selection %} will select the best model based on availability and to help reduce rate limiting. For more information, see [AUTOTITLE](/copilot/concepts/models/auto-model-selection).
+If you select **Auto**, it will choose one of the available models listed above. **Auto** in {% data variables.product.prodname_openai_codex %} coding agent does **not** leverage {% data variables.copilot.copilot_auto_model_selection %}.
 
 ## {% data variables.product.prodname_vscode_shortname %} extension
 
 
@@ -19,11 +19,12 @@ More than just a model picker, {% data variables.copilot.copilot_auto_model_sele
 
 ### Auto with task optimization
 
-> [!NOTE] {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} with task optimization is generally available in {% data variables.copilot.copilot_chat_short %} on the {% data variables.product.github %} website, in {% data variables.product.prodname_vscode_shortname %}, in {% data variables.copilot.copilot_cli_short %}, and in {% data variables.copilot.github_copilot_app %}.
+> [!NOTE] {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} with task optimization is generally available in {% data variables.copilot.copilot_chat_short %} on the {% data variables.product.github %} website, in {% data variables.product.prodname_vscode_shortname %}, in {% data variables.copilot.copilot_cli_short %}, in {% data variables.copilot.github_copilot_app %}, and in JetBrains IDEs.
 
 {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} with task optimization combines two systems to provide high quality results and better reliability. One system tracks real-time system health and availability, while the other evaluates task complexity. Putting these together, {% data variables.copilot.copilot_auto_model_selection_short %} routes the task to the optimal model.
 
-Routing occurs along natural cache boundaries to avoid additional cache related costs. Switching models mid-session has shown increased cost without ample improvements in quality.
+Routing occurs along natural cache boundaries and large drifts in conversation complexity to avoid additional cache related costs without quality improvements.
+
 This helps you get more value from {% data variables.product.prodname_copilot_short %} since it matches each task to the model that can solve it most efficiently. That means reserving higher-cost reasoning models for problems that truly need it, while routing straightforward tasks to faster, lower-cost models that still deliver great results.
 
 Benefits of using {% data variables.copilot.copilot_auto_model_selection_short %} include:
@@ -87,38 +88,17 @@ When you select **Auto**, {% data variables.copilot.copilot_auto_model_selection
 
 > [!TIP]
 > You can see which model was used for each {% data variables.product.prodname_copilot_short %} response.
-> * In **{% data variables.copilot.copilot_chat_short %}**, hover over the response.
+> * In **{% data variables.copilot.copilot_chat_short %}** and **{% data variables.copilot.github_copilot_app %}**, hover over the response.
 > * In **{% data variables.copilot.copilot_cli_short %}**, the model used for each response displays in the terminal.
 > * In **{% data variables.copilot.copilot_cloud_agent %}**, the model used for each response displays at the end of the response.
-> * In **{% data variables.copilot.github_copilot_app %}**, the model used for each response is shown by the model picker next to **Auto**.
 
 ### {% data variables.copilot.copilot_chat_short %} in IDEs
 
 {% data variables.copilot.copilot_auto_model_selection_short_cap_a %}, with task optimization, is generally available in the following IDEs:
   * {% data variables.product.prodname_vscode_shortname %}
+  * JetBrains IDEs
 
 {% data variables.copilot.copilot_auto_model_selection_short_cap_a %}, optimized for model reliability and availability, is generally available in the following IDEs:
-  * JetBrains IDEs
   * Eclipse
   * Xcode
   * {% data variables.product.prodname_vs %}
-
-## {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} in third-party agents
-
-When you select **Auto** in the {% data variables.product.prodname_openai_codex %} or {% data variables.product.prodname_anthropic_claude %} coding agents, {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} chooses from the supported list of models, subject to your policies and subscription type.
-
-### {% data variables.product.prodname_openai_codex %} supported models
-
-These models are available for {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} in the {% data variables.product.prodname_openai_codex %} coding agent.
-
-{% data reusables.copilot.openai-codex-agent-models %}
-
-For more information, see [AUTOTITLE](/copilot/concepts/agents/openai-codex).
-
-### {% data variables.product.prodname_anthropic_claude %} supported models
-
-These models are available for {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} in the {% data variables.product.prodname_anthropic_claude %} coding agent.
-
-{% data reusables.copilot.anthropic-claude-agent-models %}
-
-For more information, see [AUTOTITLE](/copilot/concepts/agents/anthropic-claude).
@@ -43,7 +43,7 @@ See [AUTOTITLE](/copilot/reference/ai-models/supported-models#models-with-extend
 
 A small router looks at your prompt and sends it to the model that can **handle it most efficiently**, reserving expensive reasoning models for complex problems. It also avoids models that burn through a token budget quickly.
 
-{% data variables.copilot.copilot_auto_model_selection_short_cap_a %} also **protects your cache**. It only changes models at natural cache boundaries, when a new session starts or after you run `/compact`, never mid-task. To understand more about why this matters, see [4. Preserve the cache](#4-preserve-the-cache).
+{% data variables.copilot.copilot_auto_model_selection_short_cap_a %} also **protects your cache**. It changes models at natural cache boundaries, when a new session starts or after you run `/compact`. As conversations evolve, it will re-route at points where quality improvements outweigh cache loss. To understand more about why this matters, see [4. Preserve the cache](#4-preserve-the-cache).
 
 {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} also routes around degraded or busy models, so you hit fewer rate limits and errors.
 
@@ -198,4 +198,4 @@ Teams that invest in these guardrails see fewer retries, faster task completion,
 Monitor and manage your spending to get the most out of your {% data variables.product.prodname_ai_credits_short %}:
 
 * **Use your dashboard and budget controls**. The "AI usage" page, under https://github.com/settings/billing, breaks down consumption across every feature and model, so you can see where your credits are actually going and adjust accordingly. See [AUTOTITLE](/copilot/how-tos/manage-and-track-spending/monitor-ai-usage).
-* **Upgrade for a larger allowance**. If you regularly approach your monthly limit, a higher plan may be more economical than paying for additional usage, as higher plans have more {% data variables.product.prodname_ai_credit_singular %} allowance. See [AUTOTITLE](/copilot/get-started/plans#github-ai-credits-allowance-by-plan) and [AUTOTITLE](/copilot/how-tos/manage-your-account/view-and-change-your-copilot-plan).
+* **Upgrade for a larger allowance**. If you regularly approach your monthly limit, a higher plan may be more economical than paying for additional usage, as higher plans have more {% data variables.product.prodname_ai_credit_singular %} allowance. See [AUTOTITLE](/copilot/get-started/plans#github-ai-credits-allowance-by-plan) and [AUTOTITLE](/copilot/how-tos/manage-your-account/view-and-change-your-copilot-plan).
@@ -56,6 +56,18 @@
   cli: true
   app: true
 
+- name: GPT-6 Luna
+  cloud_agent: true
+  chat: true
+  cli: true
+  app: true
+
+- name: GPT-6 Sol
+  cloud_agent: true
+  chat: true
+  cli: true
+  app: true
+
 # Anthropic
 - name: Claude Haiku 4.5
   cloud_agent: true
@@ -75,6 +87,12 @@
   cli: true
   app: true
 
+- name: Claude Opus 5.5
+  cloud_agent: true
+  chat: true
+  cli: true
+  app: true
+
 - name: Claude Sonnet 4.6
   cloud_agent: false
   chat: true