[bot] Learning Hub: document Copilot CLI v1.0.37–v1.0.40 updates#1610
Merged
aaronpowell merged 1 commit intostagedfrom May 5, 2026
Merged
Conversation
- automating-with-hooks.md: Add prompt mode security gate note (v1.0.40)
— repo hooks and workspace MCP are disabled by default in -p prompt mode;
users must opt in via GITHUB_COPILOT_PROMPT_MODE_REPO_HOOKS and
GITHUB_COPILOT_PROMPT_MODE_WORKSPACE_MCP env vars
- agents-and-subagents.md: Add /research orchestrator/subagent note (v1.0.40)
and prompt mode security cross-reference for /fleet -p examples
- building-custom-agents.md: Document ACP agent list/switch capability (v1.0.40)
— ACP clients can now list and switch custom agents via agent config option
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
aaronpowell
approved these changes
May 5, 2026
Contributor
There was a problem hiding this comment.
Pull request overview
Updates three Learning Hub articles so the docs reflect recent Copilot CLI changes from v1.0.37–v1.0.40, mainly around prompt/programmatic mode security, multi-agent research behavior, and custom-agent selection via ACP.
Changes:
- Added prompt-mode security guidance explaining that repo hooks are disabled by default in
copilot -pand require an opt-in env var. - Expanded the subagents article with a
/fleetprompt-mode note and a/researchorchestrator/subagent explanation. - Extended the custom-agents FAQ to cover ACP-based agent discovery and switching.
Show a summary per file
| File | Description |
|---|---|
website/src/content/docs/learning-hub/building-custom-agents.md |
Updates the custom-agent selection FAQ with Copilot CLI and ACP details. |
website/src/content/docs/learning-hub/automating-with-hooks.md |
Adds a security callout about prompt-mode hook gating and workspace MCP opt-in. |
website/src/content/docs/learning-hub/agents-and-subagents.md |
Adds prompt-mode hook guidance for /fleet and documents /research’s orchestration model. |
Copilot's findings
- Files reviewed: 3/3 changed files
- Comments generated: 3
|
|
||
| A: In VS Code, open Copilot Chat and use the agent picker dropdown at the top of the chat panel. Your custom agents appear alongside built-in options. You can also `@mention` an agent by name. | ||
|
|
||
| In Copilot CLI, custom agents are discoverable via the agent picker inside a session. Clients that integrate with Copilot CLI using the **Agent Coordination Protocol (ACP)** can also list available custom agents and switch between them programmatically via the `agent` session configuration option (v1.0.40+). This allows tools like Zed, Neovim plugins, and CI pipelines driving Copilot via ACP to surface the agent picker and switch agents without requiring a slash command. |
Comment on lines
+276
to
+280
| > **Prompt mode security (v1.0.40+)**: When running the CLI in **prompt mode** (`copilot -p "..."`) — the non-interactive mode commonly used in CI pipelines — repo hooks are **disabled by default** for security. To opt in to repo hooks in prompt mode, set the environment variable `GITHUB_COPILOT_PROMPT_MODE_REPO_HOOKS=true` before running the command: | ||
| > ```bash | ||
| > GITHUB_COPILOT_PROMPT_MODE_REPO_HOOKS=true copilot -p "..." --no-ask-user | ||
| > ``` | ||
| > This is a secure-by-default change: it prevents untrusted repository hooks from firing silently when a user runs a quick prompt command in an unfamiliar repository. Similarly, workspace MCP servers are disabled in prompt mode by default; opt in with `GITHUB_COPILOT_PROMPT_MODE_WORKSPACE_MCP=true`. |
| copilot -p "/fleet Update the auth docs, refactor the auth service, and add related tests." --no-ask-user | ||
| ``` | ||
|
|
||
| > **Prompt mode and repo hooks (v1.0.40+)**: When using `copilot -p "..."` (prompt mode), repository hooks are disabled by default for security. If your `/fleet` workflow relies on hooks (e.g., auto-formatting or lint checks after edits), opt in by setting `GITHUB_COPILOT_PROMPT_MODE_REPO_HOOKS=true` before running. See [Automating with Hooks](../automating-with-hooks/) for details. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What changed
Three new features from the Copilot CLI changelog (versions 1.0.37–1.0.40, released 2026-04-27 through 2026-05-01) were not yet reflected in the Learning Hub.
New features / changes found
-p) now gates repo hooks and workspace MCP behind opt-in env vars (GITHUB_COPILOT_PROMPT_MODE_REPO_HOOKS,GITHUB_COPILOT_PROMPT_MODE_WORKSPACE_MCP) — secure-by-default breaking change for CI users/researchnow uses an orchestrator/subagent model for more thorough, parallel deep-research resultsagentsession configuration optionSections updated
automating-with-hooks.md— Added a callout after the PermissionRequest/CI example explaining the v1.0.40 prompt mode security gate. Users who rely on repo hooks firing incopilot -p "..."pipelines now get clear guidance that they must setGITHUB_COPILOT_PROMPT_MODE_REPO_HOOKS=true.agents-and-subagents.md— Two additions:/fleet -pnon-interactive example cross-referencing the prompt mode security change./researchcommand uses the orchestrator/subagent pattern internally as of v1.0.40.building-custom-agents.md— Expanded the "How do I select a custom agent?" FAQ answer to cover ACP clients, which can now list and switch agents programmatically via session configuration.Source announcements