Skip to content

Commit efe9a49

Browse files
authored
Merge pull request #45880 from github/repo-sync
Repo sync
2 parents ffb6901 + 0357b73 commit efe9a49

8 files changed

Lines changed: 5260 additions & 777 deletions

File tree

.github/workflows/readability.yml

Lines changed: 0 additions & 106 deletions
This file was deleted.

content/admin/data-residency/github-copilot-with-data-residency.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -64,6 +64,7 @@ The models available for {% data variables.product.prodname_copilot_short %} var
6464
* {% data variables.copilot.copilot_gpt_56_luna %}
6565
* {% data variables.copilot.copilot_gpt_56_sol %}
6666
* {% data variables.copilot.copilot_gpt_56_terra %}
67+
* {% data variables.copilot.copilot_gpt_6_astra %}
6768
* {% data variables.copilot.copilot_claude_haiku_45 %}
6869
* {% data variables.copilot.copilot_claude_opus_47 %}
6970
* {% data variables.copilot.copilot_claude_opus_48 %}

content/copilot/concepts/context/content-exclusion.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -35,7 +35,7 @@ The {% data variables.copilot.copilot_business_short %} and {% data variables.co
3535
| Tool | Inline suggestions support | Chat and agent support |
3636
|-------------------------------------------------|:---------------------------------------------:|:----------------------------------------------:|
3737
| {% data variables.product.prodname_vs %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
38-
| {% data variables.product.prodname_vscode %} | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
38+
| {% data variables.product.prodname_vscode %} | {% octicon "check" aria-label="Supported" %} | Chat: {% octicon "check" aria-label="Supported" %}<br>Edit: {% octicon "x" aria-label="Not supported" %}<br>Agent: {% octicon "x" aria-label="Not supported" %} |
3939
| JetBrains IDEs | {% octicon "check" aria-label="Supported" %} | {% octicon "check" aria-label="Supported" %} |
4040
| Vim/Neovim | {% octicon "check" aria-label="Supported" %} | Not applicable |
4141
| Xcode | {% octicon "check" aria-label="Supported" %} | {% octicon "x" aria-label="Not supported" %} |

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

Lines changed: 20 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -32,6 +32,23 @@ Benefits of using {% data variables.copilot.copilot_auto_model_selection_short %
3232
* Language invariance: Routing decisions depend on what you are trying to do, not what language you're asking in.
3333
* Improved cost efficiency due to intelligent task routing.
3434

35+
#### Auto tier options
36+
37+
When using auto with task optimization, there are three tiers available. Use these tiers to adjust how {% data variables.copilot.copilot_auto_model_selection_short %} preferentially routes models for each prompt.
38+
39+
| Tier | Priority | Typical use |
40+
| --- | --- | --- |
41+
| **Efficiency** | Cost | Well suited to fast, straightforward tasks. |
42+
| **Balance** | Balances cost, quality and latency | A good fit for everyday work. |
43+
| **Intelligence** | Quality | Built for complex tasks. |
44+
45+
With tiers, {% data variables.copilot.copilot_auto_model_selection_short %} still considers the prompt for each task. The same models remain available in each tier, but tiered routing changes how preferred models are selected for each task. Examples for each tier:
46+
* **Efficiency**: All prompts are routed to the most cost-efficient and appropriately capable model for the task.
47+
* **Balance**: For each prompt, the model is selected by considering cost, quality, and latency, to provide cost effective and efficient performance appropriate to the complexity of each prompt.
48+
* **Intelligence**: Prompts are evaluated for which model would provide the highest quality response. A simple prompt could still be routed to a smaller model, while a complex prompt is routed to the most capable model for that task.
49+
50+
Usage is still charged based on the model auto selects, regardless of tier, alongside the 10% discount for users on paid plans. See [Discount for auto model selection](#discount-for-using-auto-model-selection).
51+
3552
### Auto optimized for model reliability and availability
3653

3754
Experience less rate limiting by letting {% data variables.copilot.copilot_auto_model_selection_short %} choose the best available model on your behalf.
@@ -63,8 +80,10 @@ When you select **Auto**, {% data variables.copilot.copilot_auto_model_selection
6380
{% 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:
6481
* {% data variables.copilot.copilot_chat_short %}, on the {% data variables.product.github %} website and supported IDEs
6582
* {% data variables.copilot.copilot_cli_short %}
66-
* {% data variables.copilot.copilot_cloud_agent %}
6783
* {% data variables.copilot.github_copilot_app %}
84+
* {% data variables.copilot.copilot_cloud_agent %}
85+
86+
> [!NOTE] Auto tiers are only available on {% data variables.product.prodname_vscode_shortname %}, {% data variables.copilot.copilot_cli_short %}, and {% data variables.copilot.github_copilot_app %} .
6887
6988
> [!TIP]
7089
> You can see which model was used for each {% data variables.product.prodname_copilot_short %} response.

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

Lines changed: 12 additions & 23 deletions
Original file line numberDiff line numberDiff line change
@@ -19,11 +19,6 @@
1919
# - app: Availability for GitHub Copilot app.
2020

2121
# OpenAI
22-
- name: GPT-5 mini
23-
cloud_agent: false
24-
chat: true
25-
cli: true
26-
app: true
2722

2823
- name: GPT-5.3-Codex
2924
cloud_agent: true
@@ -33,39 +28,33 @@
3328

3429
- name: GPT-5.4
3530
cloud_agent: true
36-
chat: true
37-
cli: true
38-
app: true
39-
40-
- name: GPT-5.4 mini
41-
cloud_agent: false
42-
chat: true
43-
cli: true
44-
app: true
31+
chat: false
32+
cli: false
33+
app: false
4534

4635
- name: GPT-5.5
4736
cloud_agent: false
4837
chat: true
4938
cli: true
50-
app: false
39+
app: true
5140

5241
- name: GPT-5.6 Luna
5342
cloud_agent: false
5443
chat: true
5544
cli: true
56-
app: false
45+
app: true
5746

5847
- name: GPT-5.6 Sol
5948
cloud_agent: false
6049
chat: true
6150
cli: true
62-
app: false
51+
app: true
6352

6453
- name: GPT-5.6 Terra
6554
cloud_agent: false
6655
chat: true
6756
cli: true
68-
app: false
57+
app: true
6958

7059
# Anthropic
7160
- name: Claude Haiku 4.5
@@ -84,19 +73,19 @@
8473
cloud_agent: false
8574
chat: true
8675
cli: true
87-
app: false
76+
app: true
8877

8978
- name: Claude Sonnet 4.6
9079
cloud_agent: true
91-
chat: true
92-
cli: true
93-
app: true
80+
chat: false
81+
cli: false
82+
app: false
9483

9584
- name: Claude Sonnet 5
9685
cloud_agent: false
9786
chat: true
9887
cli: true
99-
app: false
88+
app: true
10089

10190
# Google
10291
- name: Gemini 3.6 Flash

package.json

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -83,7 +83,6 @@
8383
"purge-fastly": "tsx src/workflows/purge-fastly.ts",
8484
"purge-fastly-changed-content": "tsx src/workflows/purge-fastly-changed-content.ts",
8585
"wait-for-build": "tsx src/workflows/wait-for-build.ts",
86-
"readability-report": "tsx src/workflows/experimental/readability-report.ts",
8786
"ready-for-docs-review": "tsx src/workflows/ready-for-docs-review.ts",
8887
"release-banner": "tsx src/ghes-releases/scripts/release-banner.ts",
8988
"repo-sync": "./src/workflows/local-repo-sync.sh",

0 commit comments

Comments
 (0)