Skip to content

Commit f7f1a98

Browse files
saritaiCopilotdihydroJenoxide
authored
add GitHub Copilot app support for auto model selection (#62075)
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> Co-authored-by: Jenni C <97056108+dihydroJenoxide@users.noreply.github.com>
1 parent 5fe8e5c commit f7f1a98

6 files changed

Lines changed: 24 additions & 12 deletions

File tree

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

Lines changed: 5 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ More than just a model picker, {% data variables.copilot.copilot_auto_model_sele
1919

2020
### Auto with task optimization
2121

22-
> [!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 %}, and in {% data variables.copilot.copilot_cli_short %}.
22+
> [!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 %}.
2323
2424
{% 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.
2525

@@ -60,22 +60,23 @@ When you select **Auto**, {% data variables.copilot.copilot_auto_model_selection
6060

6161
## {% data variables.copilot.copilot_auto_model_selection_short_cap_a %} in {% data variables.product.prodname_copilot_short %}
6262

63-
{% data variables.copilot.copilot_auto_model_selection_short_cap_a %}, optimized for model reliability and availability, is available in these {% data variables.product.prodname_copilot_short %} products:
63+
{% data variables.copilot.copilot_auto_model_selection_short_cap_a %}, with task optimization, is generally available in these {% data variables.product.prodname_copilot_short %} products:
6464
* {% data variables.copilot.copilot_chat_short %}, on the {% data variables.product.github %} website and supported IDEs
6565
* {% data variables.copilot.copilot_cli_short %}
6666
* {% data variables.copilot.copilot_cloud_agent %}
67+
* {% data variables.copilot.github_copilot_app %}
6768

6869
> [!TIP]
6970
> You can see which model was used for each {% data variables.product.prodname_copilot_short %} response.
7071
> * In **{% data variables.copilot.copilot_chat_short %}**, hover over the response.
7172
> * In **{% data variables.copilot.copilot_cli_short %}**, the model used for each response displays in the terminal.
7273
> * In **{% data variables.copilot.copilot_cloud_agent %}**, the model used for each response displays at the end of the response.
74+
> * In **{% data variables.copilot.github_copilot_app %}**, the model used for each response is shown by the model picker next to **Auto**.
7375
74-
### {% data variables.copilot.copilot_chat_short %} on {% data variables.product.github %} and in IDEs
76+
### {% data variables.copilot.copilot_chat_short %} in IDEs
7577

7678
{% data variables.copilot.copilot_auto_model_selection_short_cap_a %}, with task optimization, is generally available in the following IDEs:
7779
* {% data variables.product.prodname_vscode_shortname %}
78-
* {% data variables.product.github %} website
7980

8081
{% data variables.copilot.copilot_auto_model_selection_short_cap_a %}, optimized for model reliability and availability, is generally available in the following IDEs:
8182
* JetBrains IDEs

content/copilot/how-tos/github-copilot-app/agent-sessions.md

Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -19,8 +19,8 @@ Each session in the {% data variables.copilot.github_copilot_app %} runs in its
1919

2020
1. In the sidebar next to **Sessions**, click **+** to start a new session.
2121
1. Choose a repository—you can use a local folder, choose from {% data variables.product.github %}, or clone from a URL.
22-
1. From the dropdown under the prompt box, choose where the session should run: in a new working tree, in your local repository, or in a cloud sandbox. Cloud sandboxes for {% data variables.product.prodname_copilot_short %} (public preview) are fully isolated environments hosted by {% data variables.product.github %}. For more information, see [AUTOTITLE](/copilot/concepts/about-cloud-and-local-sandboxes).
23-
1. Select a session mode, model, and reasoning effort from the dropdowns below the prompt field.
22+
1. From the dropdown under the prompt box, choose where the session should run: in a new working tree, in your local repository, or in a cloud sandbox. Cloud sandboxes for {% data variables.product.prodname_copilot_short %} (public preview) are fully isolated environments hosted by {% data variables.product.github %}.
23+
1. Select a session mode, model, and reasoning effort from the dropdowns below the prompt field. If you choose **Auto** for the model, the app selects the optimal model for your task based on task complexity.
2424
1. Describe the task in the prompt field. You can reference issues with `#`, add files with `@`, or use `/` for commands.
2525

2626
The agent starts working. Your active sessions appear in the sidebar grouped by repository—click any session to switch to it.
@@ -35,7 +35,9 @@ The session mode controls how much autonomy the agent has. You can set the mode
3535

3636
## Choosing a model
3737

38-
You can select a model and reasoning effort from the dropdowns above the prompt field. Higher reasoning effort gives the agent more time to think through complex problems but may take longer. You can change both settings at any time during a session.
38+
You can select a model and reasoning effort from the dropdowns below the prompt field. Higher reasoning effort gives the agent more time to think through complex problems but may take longer. You can change both settings at any time during a session.
39+
40+
If you choose **Auto** in the model picker, the app automatically selects the optimal model for your task based on task complexity. After the session starts, the picker next to **Auto** shows which model handled each response. For more information, see [AUTOTITLE](/copilot/concepts/auto-model-selection).
3941

4042
If you configured your own model provider in the app, those models also appear in the picker. For setup steps, see [AUTOTITLE](/copilot/how-tos/github-copilot-app/use-byok-models).
4143

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

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -52,10 +52,10 @@ This table lists the supported AI models for {% data variables.copilot.copilot_a
5252

5353
{% rowheaders %}
5454

55-
| Model | {% data variables.copilot.copilot_cloud_agent %} | {% data variables.copilot.copilot_chat_short %} | {% data variables.copilot.copilot_cli_short %} |
56-
| --- | --- | --- | --- |
55+
| Model | {% data variables.copilot.copilot_cloud_agent %} | {% data variables.copilot.copilot_chat_short %} | {% data variables.copilot.copilot_cli_short %} | {% data variables.copilot.github_copilot_app %} |
56+
| --- | --- | --- | --- | --- |
5757
| {% for model in tables.copilot.auto-model-selection %} |
58-
| {{ 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 %} |
58+
| {{ 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 %} | {% if model.app == true %}{% octicon "check" aria-label="Included" %}{% else %}{% octicon "x" aria-label="Not included" %}{% endif %} |
5959
| {% endfor %} |
6060

6161
{% endrowheaders %}

content/copilot/reference/copilot-billing/request-based-billing-legacy/model-multipliers-for-annual-plans.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@ The following table shows the model multipliers per supported model.
3737
> * {% data variables.copilot.copilot_gpt_54_mini %}
3838
> * The multiplier for {% data variables.copilot.copilot_mai_code_1_flash %} is a promotional rate.
3939
>
40-
> If you use {% data variables.copilot.copilot_auto_model_selection_short %} in {% data variables.copilot.copilot_chat_short %}, {% data variables.copilot.copilot_cli_short %}, or {% data variables.copilot.copilot_cloud_agent %}, you qualify for a 10% discount. For example, if a model has a multiplier of 1x you'll be billed at 0.9x instead.
40+
> If you use {% data variables.copilot.copilot_auto_model_selection_short %} in {% data variables.copilot.copilot_chat_short %}, {% data variables.copilot.copilot_cli_short %}, {% data variables.copilot.github_copilot_app %}, or {% data variables.copilot.copilot_cloud_agent %}, you qualify for a 10% discount. For example, if a model has a multiplier of 1x you'll be billed at 0.9x instead.
4141
4242
| Model | Multiplier |
4343
| --- | ---: |
Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1 @@
1-
If you are on a paid {% data variables.product.prodname_copilot_short %} plan, you qualify for a 10% discount on model costs while using {% data variables.copilot.copilot_auto_model_selection_short %} in {% data variables.copilot.copilot_chat_short %}, {% data variables.copilot.copilot_cli_short %}, or {% data variables.copilot.copilot_cloud_agent %}.
1+
If you are on a paid {% data variables.product.prodname_copilot_short %} plan, you qualify for a 10% discount on model costs while using {% data variables.copilot.copilot_auto_model_selection_short %} in {% data variables.copilot.copilot_chat_short %}, {% data variables.copilot.copilot_cli_short %}, {% data variables.copilot.github_copilot_app %}, or {% data variables.copilot.copilot_cloud_agent %}.

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

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -16,47 +16,56 @@
1616
# - cloud_agent: Availability for Copilot cloud agent.
1717
# - chat: Availability for Copilot Chat.
1818
# - cli: Availability for Copilot CLI.
19+
# - app: Availability for GitHub Copilot app.
1920

2021
# OpenAI
2122
- name: GPT-5 mini
2223
cloud_agent: false
2324
chat: true
2425
cli: true
26+
app: true
2527

2628
- name: GPT-5.3-Codex
2729
cloud_agent: true
2830
chat: true
2931
cli: true
32+
app: true
3033

3134
- name: GPT-5.4
3235
cloud_agent: true
3336
chat: true
3437
cli: true
38+
app: true
3539

3640
- name: GPT-5.4 mini
3741
cloud_agent: false
3842
chat: true
3943
cli: true
44+
app: true
4045

4146
# Anthropic
4247
- name: Claude Haiku 4.5
4348
cloud_agent: false
4449
chat: true
4550
cli: true
51+
app: true
4652

4753
- name: Claude Sonnet 4.6
4854
cloud_agent: true
4955
chat: true
5056
cli: true
57+
app: true
5158

5259
# Microsoft
5360
- name: MAI-Code-1-Flash
5461
cloud_agent: true
5562
chat: true
5663
cli: true
64+
app: true
5765

5866
# Fine-tuned OAI models
5967
- name: Raptor mini
6068
cloud_agent: false
6169
chat: true
6270
cli: false
71+
app: false

0 commit comments

Comments
 (0)