Document multi-model agent lists and MCP CIMD OAuth support (CLI v1.0.83)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
github-actions[bot]
2026-09-06 20:46:59 +00:00
committed by GitHub
co-authored by Copilot
parent 7b1ebe6333
commit afa4ad8d37
2 changed files with 12 additions and 2 deletions
@@ -3,7 +3,7 @@ title: 'Building Custom Agents'
description: 'Learn how to create specialized GitHub Copilot agents with custom personas, tool integrations, and domain expertise.' description: 'Learn how to create specialized GitHub Copilot agents with custom personas, tool integrations, and domain expertise.'
authors: authors:
- GitHub Copilot Learning Hub Team - GitHub Copilot Learning Hub Team
lastUpdated: 2026-08-09 lastUpdated: 2026-09-06
estimatedReadingTime: '10 minutes' estimatedReadingTime: '10 minutes'
tags: tags:
- agents - agents
@@ -73,6 +73,14 @@ tools: ['codebase', 'terminal', 'github']
**model** (recommended): The AI model that powers the agent. Choose based on the complexity of the task—use more capable models for nuanced reasoning. **model** (recommended): The AI model that powers the agent. Choose based on the complexity of the task—use more capable models for nuanced reasoning.
> **New (v1.0.83+)**: `model` can list several models, tried in order until one is available to you (for example, if your account or enterprise policy doesn't have access to the first choice):
>
> ```yaml
> model: [Claude Sonnet 4.5, Claude Sonnet 4, GPT-5]
> ```
>
> Pair this with `model-policy: required` to prevent the model from being changed away from this list mid-session — useful when an agent's behavior depends on a specific model family.
**reasoningEffort** *(v1.0.66+)*: Override the reasoning effort level for this agent. Accepted values are `low`, `medium`, and `high`. This lets you pin specific agents to a cost/quality tradeoff regardless of the user's global setting — for example, a quick code-formatting agent can use `low` effort, while a security reviewer uses `high`: **reasoningEffort** *(v1.0.66+)*: Override the reasoning effort level for this agent. Accepted values are `low`, `medium`, and `high`. This lets you pin specific agents to a cost/quality tradeoff regardless of the user's global setting — for example, a quick code-formatting agent can use `low` effort, while a security reviewer uses `high`:
```yaml ```yaml
@@ -3,7 +3,7 @@ title: 'Understanding MCP Servers'
description: 'Learn how Model Context Protocol servers extend GitHub Copilot with access to external tools, databases, and APIs.' description: 'Learn how Model Context Protocol servers extend GitHub Copilot with access to external tools, databases, and APIs.'
authors: authors:
- GitHub Copilot Learning Hub Team - GitHub Copilot Learning Hub Team
lastUpdated: 2026-08-28 lastUpdated: 2026-09-06
estimatedReadingTime: '8 minutes' estimatedReadingTime: '8 minutes'
tags: tags:
- mcp - mcp
@@ -215,6 +215,8 @@ Some MCP servers require authentication to connect to protected resources. GitHu
> **Tip**: If your MCP server uses OAuth with Dynamic Client Registration but hosts its authorization metadata at a non-standard URL (as some enterprise servers like Atlassian Rovo do), Copilot CLI handles this automatically. > **Tip**: If your MCP server uses OAuth with Dynamic Client Registration but hosts its authorization metadata at a non-standard URL (as some enterprise servers like Atlassian Rovo do), Copilot CLI handles this automatically.
> **New (v1.0.83+)**: Copilot CLI supports **Client ID Metadata Document (CIMD)** for MCP OAuth sign-in. Instead of registering a client dynamically with each server, the CLI can present a metadata document URL as its client identifier, simplifying OAuth setup for MCP servers that support this emerging standard.
## How Agents Use MCP Tools ## How Agents Use MCP Tools
When an agent declares an MCP server in its `tools` array, Copilot can invoke that server's capabilities during conversation: When an agent declares an MCP server in its `tools` array, Copilot can invoke that server's capabilities during conversation: