chore: publish from main

2026-07-14 01:51:02 +00:00 · 2026-07-02 01:56:18 +00:00
parent cbbe282a54
commit 232aa776d5
5 changed files with 53 additions and 6 deletions
@@ -3,7 +3,7 @@ title: 'Agents and Subagents'
 description: 'Learn how delegated subagents differ from primary agents, when to use them, and how to launch them in VS Code and Copilot CLI.'
 authors:
  - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-06-23
+lastUpdated: 2026-07-01
 estimatedReadingTime: '9 minutes'
 tags:
  - agents
@@ -208,6 +208,10 @@ Yes, when the delegated worker is a custom agent with its own frontmatter.

 No. They can run sequentially when one step depends on another, or in parallel when work items are independent.

+**Can I control how many subagents run simultaneously?**
+
+Yes. In v1.0.66+, usage-based billing users can configure **subagent concurrency and depth limits** directly from `/settings`. The concurrency limit controls how many subagents run in parallel; the depth limit controls how many levels deep delegation can chain (preventing runaway recursive subagent trees). These settings give you predictable control over resource consumption during complex orchestrated tasks.
+
 ## Next steps

 - Read [Building Custom Agents](../building-custom-agents/) to design coordinator and worker agents.
@@ -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.'
 authors:
  - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-06-26
+lastUpdated: 2026-07-01
 estimatedReadingTime: '10 minutes'
 tags:
  - agents
@@ -254,7 +254,8 @@ The agent can then query your database, analyze query plans, and suggest optimiz

 | Scenario | Recommended Model |
 |----------|-------------------|
-| Complex reasoning, security review | Claude Sonnet 4 or higher |
+| Most demanding reasoning, security review | Claude Sonnet 5 *(v1.0.67+)* |
+| Complex reasoning, analysis | Claude Sonnet 4 |
 | Code generation, refactoring | GPT-4.1 |
 | Quick analysis, simple tasks | Claude Haiku or GPT-4.1-mini |
 | Large codebase understanding | Models with larger context windows |
@@ -401,6 +401,7 @@ CLI settings use **camelCase** naming. Key settings added in recent releases:
 | `extension_mode` | Control extensibility (agent tools and plugins) |
 | `continueOnAutoMode` | Automatically switch to the auto model on rate limit instead of pausing |
 | `proxy` | HTTP(S) proxy URL for all outbound CLI requests (e.g., `http://proxy.example.com:8080`) (v1.0.64+) |
+| `sessionLimits` | Restrict credit or turn usage for a session; limits apply across the current conversation and reset on `/clear` (v1.0.66+) |

 > **Note**: Older snake_case names (e.g., `include_gitignored`, `auto_updates_channel`) are still accepted for backward compatibility, but camelCase is now the preferred format.

@@ -3,7 +3,7 @@ title: 'Defining Custom Instructions'
 description: 'Learn how to create persistent, context-aware instructions that guide GitHub Copilot automatically across your codebase.'
 authors:
  - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-03-22
+lastUpdated: 2026-07-01
 estimatedReadingTime: '8 minutes'
 tags:
  - instructions
@@ -142,7 +142,38 @@ applyTo: '**'
 **Expected Result**:
 When you work on a file matching the pattern, Copilot incorporates that instruction's context into suggestions and chat responses automatically.

-## Real Examples from the Repository
+## Composing Instructions with @-style Imports
+
+*(v1.0.66+)* Copilot CLI supports **@-style imports** in instruction files, AGENTS.md, and CLAUDE.md. Use a bare `@path/to/file.md` reference to embed the content of another file at that point:
+
+```markdown
+---
+description: 'Full TypeScript standards for this project'
+applyTo: '**/*.ts, **/*.tsx'
+---
+
+@shared/base-coding-standards.md
+@shared/security-rules.md
+
+## TypeScript-Specific Rules
+
+- Prefer `interface` over `type` for object shapes
+- Always provide return types for public functions
+```
+
+When the instruction file is loaded, the referenced files are read and their content is substituted inline before being sent to the model.
+
+**Why this matters**:
+- **DRY principle**: Maintain a shared `security-rules.md` and import it into every instruction rather than copying it
+- **Modular composition**: Build complex instructions from small, focused files
+- **Easy updates**: Edit the shared file once; every instruction that imports it picks up the change automatically
+
+**Tips**:
+- Paths are resolved relative to the instruction file's location
+- Referenced files do not need to be instruction files themselves — plain Markdown files work
+- Imports can be nested (a file you import can itself import other files)
+
+

 The awesome-copilot-hub repository includes over 120 instruction files demonstrating real-world patterns.

@@ -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.'
 authors:
  - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-06-26
+lastUpdated: 2026-07-01
 estimatedReadingTime: '8 minutes'
 tags:
  - mcp
@@ -122,6 +122,16 @@ This guided flow is the recommended way to add new MCP servers, especially for s

 **deferTools** *(optional, v1.0.63+)*: When set to `false`, the server's tools are always available even when tool search is enabled. By default, tool search can hide rarely-used MCP tools to reduce context noise; setting `deferTools: false` on a server prevents its tools from being deferred, keeping them permanently in the tool list.

+### Allowing MCP Server Instructions
+
+By default, Copilot CLI limits which MCP server instructions are injected into the system prompt, to avoid noisy or unexpected instructions from servers you may not have fully reviewed. You can opt in to include instructions from **all** connected MCP servers with the `--allow-all-mcp-server-instructions` flag *(v1.0.66+)*:
+
+```bash
+copilot --allow-all-mcp-server-instructions
+```
+
+Use this only with servers you fully trust, since their instructions can influence how Copilot responds throughout the entire session. For most projects, the default behavior is sufficient — only enable this if a specific server requires it (for example, an internal tool whose instructions you control).
+
 ### Managing Persistent MCP Configuration via Server RPCs

 In addition to file-based configuration, GitHub Copilot CLI exposes **server RPCs** that let MCP servers and tooling scripts manage the persistent MCP server registry at runtime. This enables programmatic setup — for example, an installer script that registers a server without requiring you to hand-edit a JSON file.