GH-600 無料問題集「Microsoft GitHub Agentic AI Developer」
Hotspot Question
You have the following agent logs.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
You have the following agent logs.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
正解：
Explanation:
Box 1: Yes
Yes, the agent did respond with messages.
Markdown Message: The log ccreq:XXX.copilotmd | markdown message 0 returned: finish reason: [stop] indicates that a text-based markdown response was successfully generated and completed.
Language Model Output: The log ccreq:XXX.copilotmd shows the core language model (gpt-4o- mini) completed its request, delivering the main content of the message.
Box 2: Yes
Based on the log entries provided, yes, the agent can edit files in the repository.
Evidence from the LogsTargeted Component: The final three log entries explicitly target the component [panel/editAgent].
Model Selection: For these specific tasks, the system switches from standard conversational models (gpt-4o-mini) to a specialized code-generation model: gpt-5.3-codex.
Processing Time: These operations take significantly longer than standard chat generation, which is characteristic of complex code-parsing and file-modification tasks.
Box 3: Yes
Based on the log entries provided, yes, the agent analyzed files in the repository.
Action Type: The final three entries explicitly call the [panel/editAgent] capability.
Model Used: These actions utilized the gpt-5.3-codex model, which is specialized for codebases.
Operation Duration: The execution times were significantly longer.
Implied Task: Code-generation and editing agents require repository file analysis to perform edits.
Reference:
https://learn.microsoft.com/en-us/troubleshoot/power-platform/copilot-studio/authoring/error-codes
Hotspot Question
Your company uses Microsoft Visual Studio Code and GitHub Copilot Chat.
You have a GitHub repository that uses main as the default branch. The repository contains a workspace custom agent stored at .github/agents/release-notes.agent.md.
A developer switches to a branch named branch1 where the agent file does NOT exist. In the same session, the developer switches to a user profile named profile1.profile1 contains a custom agent file named release-notes.agent.md that has user-invokable set to false.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Your company uses Microsoft Visual Studio Code and GitHub Copilot Chat.
You have a GitHub repository that uses main as the default branch. The repository contains a workspace custom agent stored at .github/agents/release-notes.agent.md.
A developer switches to a branch named branch1 where the agent file does NOT exist. In the same session, the developer switches to a user profile named profile1.profile1 contains a custom agent file named release-notes.agent.md that has user-invokable set to false.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
正解：
Explanation:
Box 1: No
The agent will not appear in the agents dropdown with a display name of release-notes because the developer is currently on branch1 and profile1, which effectively hides it.
Box 2: No
The workspace version of the release-notes agent will not be available in the agents dropdown when the developer is on branch2.
Box 3: No
The user profile agent will not appear in the agents dropdown, nor will it override a workspace agent in this scenario.
Reference:
https://code.visualstudio.com/docs/agent-customization/custom-agents
Case Study 2
Existing Environment
GitHub Environment
The GitHub environment contains the following:
- Three repositories named product-api, billing-service, and infra-terraform.
- Branch protection on the main branch in all repositories that requires at least one pull request review before merging
- GitHub Actions runners used across all workflows
- A GitHub team named SG_Dev that contains developers
- A GitHub team named SG_Review that contains senior engineers and a security team
- A .github/copilot-instructions.md file that includes general coding conventions for all features Agent environment The product-api repository uses a GitHub Copilot coding agent named agent1 that has the following configurations:
- No custom agent profile is defined.
- A Model Context Protocol (MCP) server named MCP1 is deployed to
https://mcp.litwareinc.internal and provides access to internal ticketing and deployment APIs.
MCP1 requires an API key for authentication.
A second Copilot coding agent named agent2 handles changes in infra-terraform and runs in parallel with agent1 when both agents have open assigned issues.
Copilot memory is NOT enabled for the organization.
Problem Statements
Litware identifies the following issues:
- During two recent sessions, agent1 accessed files in billing-service, which is outside the agent's intended scope.
- agent1 makes code changes immediately after receiving a task.
- A developer named Ben, who is on the SG_Dev team, reports that agent1 completed a session with a successful status and opened a pull request, but the pull request contains no file changes.
Other developers report this intermittently as well.
- Both agent1 and agent2 modified shared/config.yaml in a parallel test run, generating conflicting outputs.
agent1 consistently uses raw try-catch blocks for error handling, which violates the defined implementation guidelines of SG_Dev.
Requirements
Planned Changes
Litware plans to make the following changes:
- Ensure that agent1 can access all the tools in the environment.
- Provide product-api with specific instructions to agent1 without affecting Copilot Chat or Copilot code review.
- Configure MCP1 as a tool for agent1 by modifying the product-api repository MCP configuration.
- Ensure that Copilot retains details that it has learned and uses that knowledge for future work.
This must be applied to all licensed members of the organization.
Implementation guidelines
The development team at Litware identifies the following implementation guidelines:
- Agent workflows must be able to run in parallel.
- Application error handling must use the repository ErrorHandler class.
- agent1 and agent2 must run on isolated branches during parallel execution. File-level conflicts must be detected before merges, and both agents must be able to run concurrently.
Security requirements
Litware identifies the following security requirements:
- Only the members of SG_Review must be able to approve agent1 plan outputs.
- All API keys must be stored and accessed securely.
- The developers must NOT be able to self-approve.
Agent configuration
Hotspot Question
You are evaluating how agent1 will behave after you implement the planned changes.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
Existing Environment
GitHub Environment
The GitHub environment contains the following:
- Three repositories named product-api, billing-service, and infra-terraform.
- Branch protection on the main branch in all repositories that requires at least one pull request review before merging
- GitHub Actions runners used across all workflows
- A GitHub team named SG_Dev that contains developers
- A GitHub team named SG_Review that contains senior engineers and a security team
- A .github/copilot-instructions.md file that includes general coding conventions for all features Agent environment The product-api repository uses a GitHub Copilot coding agent named agent1 that has the following configurations:
- No custom agent profile is defined.
- A Model Context Protocol (MCP) server named MCP1 is deployed to
https://mcp.litwareinc.internal and provides access to internal ticketing and deployment APIs.
MCP1 requires an API key for authentication.
A second Copilot coding agent named agent2 handles changes in infra-terraform and runs in parallel with agent1 when both agents have open assigned issues.
Copilot memory is NOT enabled for the organization.
Problem Statements
Litware identifies the following issues:
- During two recent sessions, agent1 accessed files in billing-service, which is outside the agent's intended scope.
- agent1 makes code changes immediately after receiving a task.
- A developer named Ben, who is on the SG_Dev team, reports that agent1 completed a session with a successful status and opened a pull request, but the pull request contains no file changes.
Other developers report this intermittently as well.
- Both agent1 and agent2 modified shared/config.yaml in a parallel test run, generating conflicting outputs.
agent1 consistently uses raw try-catch blocks for error handling, which violates the defined implementation guidelines of SG_Dev.
Requirements
Planned Changes
Litware plans to make the following changes:
- Ensure that agent1 can access all the tools in the environment.
- Provide product-api with specific instructions to agent1 without affecting Copilot Chat or Copilot code review.
- Configure MCP1 as a tool for agent1 by modifying the product-api repository MCP configuration.
- Ensure that Copilot retains details that it has learned and uses that knowledge for future work.
This must be applied to all licensed members of the organization.
Implementation guidelines
The development team at Litware identifies the following implementation guidelines:
- Agent workflows must be able to run in parallel.
- Application error handling must use the repository ErrorHandler class.
- agent1 and agent2 must run on isolated branches during parallel execution. File-level conflicts must be detected before merges, and both agents must be able to run concurrently.
Security requirements
Litware identifies the following security requirements:
- Only the members of SG_Review must be able to approve agent1 plan outputs.
- All API keys must be stored and accessed securely.
- The developers must NOT be able to self-approve.
Agent configuration
Hotspot Question
You are evaluating how agent1 will behave after you implement the planned changes.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
正解：
Explanation:
Scenario:
Planned Changes
Litware plans to make the following changes:
Ensure that agent1 can access all the tools in the environment.
Provide product-api with specific instructions to agent1 without affecting Copilot Chat or Copilot code review.
Configure MCP1 as a tool for agent1 by modifying the product-api repository MCP configuration.
Box 1: Yes
Box 2: Yes
Box 3: Yes
-[Related to another question in this scenario]
The correct action to take is to delete the line with tools: ['read','cearch','edit'] from the agent configuration.
Enabling All Tools: In GitHub Copilot Agent configuration specifications, omitting the tools key entirely or deleting it allows the agent to automatically inherit and utilize all available tools in the runtime environment. Explicitly hardcoding a restricted array limits its capabilities.
Targeted Instructions: Modifying the repository's configuration for the agent ensures that the specific product-api guidelines apply strictly to that custom agent without bleeding into general Copilot Chat or standard Copilot code reviews.
Reference:
https://docs.github.com/en/copilot/how-tos/copilot-sdk/features/mcp
Case Study 2
Existing Environment
GitHub Environment
The GitHub environment contains the following:
- Three repositories named product-api, billing-service, and infra-terraform.
- Branch protection on the main branch in all repositories that requires at least one pull request review before merging
- GitHub Actions runners used across all workflows
- A GitHub team named SG_Dev that contains developers
- A GitHub team named SG_Review that contains senior engineers and a security team
- A .github/copilot-instructions.md file that includes general coding conventions for all features Agent environment The product-api repository uses a GitHub Copilot coding agent named agent1 that has the following configurations:
- No custom agent profile is defined.
- A Model Context Protocol (MCP) server named MCP1 is deployed to
https://mcp.litwareinc.internal and provides access to internal ticketing and deployment APIs.
MCP1 requires an API key for authentication.
A second Copilot coding agent named agent2 handles changes in infra-terraform and runs in parallel with agent1 when both agents have open assigned issues.
Copilot memory is NOT enabled for the organization.
Problem Statements
Litware identifies the following issues:
- During two recent sessions, agent1 accessed files in billing-service, which is outside the agent's intended scope.
- agent1 makes code changes immediately after receiving a task.
- A developer named Ben, who is on the SG_Dev team, reports that agent1 completed a session with a successful status and opened a pull request, but the pull request contains no file changes.
Other developers report this intermittently as well.
- Both agent1 and agent2 modified shared/config.yaml in a parallel test run, generating conflicting outputs.
agent1 consistently uses raw try-catch blocks for error handling, which violates the defined implementation guidelines of SG_Dev.
Requirements
Planned Changes
Litware plans to make the following changes:
- Ensure that agent1 can access all the tools in the environment.
- Provide product-api with specific instructions to agent1 without affecting Copilot Chat or Copilot code review.
- Configure MCP1 as a tool for agent1 by modifying the product-api repository MCP configuration.
- Ensure that Copilot retains details that it has learned and uses that knowledge for future work.
This must be applied to all licensed members of the organization.
Implementation guidelines
The development team at Litware identifies the following implementation guidelines:
- Agent workflows must be able to run in parallel.
- Application error handling must use the repository ErrorHandler class.
- agent1 and agent2 must run on isolated branches during parallel execution. File-level conflicts must be detected before merges, and both agents must be able to run concurrently.
Security requirements
Litware identifies the following security requirements:
- Only the members of SG_Review must be able to approve agent1 plan outputs.
- All API keys must be stored and accessed securely.
- The developers must NOT be able to self-approve.
Agent configuration
Drag and Drop Question
You need to implement the security requirements for agent1.
Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Existing Environment
GitHub Environment
The GitHub environment contains the following:
- Three repositories named product-api, billing-service, and infra-terraform.
- Branch protection on the main branch in all repositories that requires at least one pull request review before merging
- GitHub Actions runners used across all workflows
- A GitHub team named SG_Dev that contains developers
- A GitHub team named SG_Review that contains senior engineers and a security team
- A .github/copilot-instructions.md file that includes general coding conventions for all features Agent environment The product-api repository uses a GitHub Copilot coding agent named agent1 that has the following configurations:
- No custom agent profile is defined.
- A Model Context Protocol (MCP) server named MCP1 is deployed to
https://mcp.litwareinc.internal and provides access to internal ticketing and deployment APIs.
MCP1 requires an API key for authentication.
A second Copilot coding agent named agent2 handles changes in infra-terraform and runs in parallel with agent1 when both agents have open assigned issues.
Copilot memory is NOT enabled for the organization.
Problem Statements
Litware identifies the following issues:
- During two recent sessions, agent1 accessed files in billing-service, which is outside the agent's intended scope.
- agent1 makes code changes immediately after receiving a task.
- A developer named Ben, who is on the SG_Dev team, reports that agent1 completed a session with a successful status and opened a pull request, but the pull request contains no file changes.
Other developers report this intermittently as well.
- Both agent1 and agent2 modified shared/config.yaml in a parallel test run, generating conflicting outputs.
agent1 consistently uses raw try-catch blocks for error handling, which violates the defined implementation guidelines of SG_Dev.
Requirements
Planned Changes
Litware plans to make the following changes:
- Ensure that agent1 can access all the tools in the environment.
- Provide product-api with specific instructions to agent1 without affecting Copilot Chat or Copilot code review.
- Configure MCP1 as a tool for agent1 by modifying the product-api repository MCP configuration.
- Ensure that Copilot retains details that it has learned and uses that knowledge for future work.
This must be applied to all licensed members of the organization.
Implementation guidelines
The development team at Litware identifies the following implementation guidelines:
- Agent workflows must be able to run in parallel.
- Application error handling must use the repository ErrorHandler class.
- agent1 and agent2 must run on isolated branches during parallel execution. File-level conflicts must be detected before merges, and both agents must be able to run concurrently.
Security requirements
Litware identifies the following security requirements:
- Only the members of SG_Review must be able to approve agent1 plan outputs.
- All API keys must be stored and accessed securely.
- The developers must NOT be able to self-approve.
Agent configuration
Drag and Drop Question
You need to implement the security requirements for agent1.
Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
正解：
Explanation:
Scenario:
Security requirements, Litware identifies the following security requirements: Only the members of SG_Review must be able to approve agent1 plan outputs.
Agent environment: The product-api repository uses a GitHub Copilot coding agent named agent1 Step 1: In the product-api repositary settings,..
Create a new environment and add SG_review as the required reviewers.
Step 2: To the agent1 workflow,..
Create a new workflow related to the plan outoput.
Step 3: Add an execute job...
Create a job referencing the plan and the environment.
Hotspot Question
You have a GitHub repository that contains the following custom agent files:
- A file named planner.agent.md that includes YAML frontmatter with a
handoffs entry that has label: Start Implementation, agent:
implementer, and prompt: Now implement the plan outlined above
- A file named implementer.agent.md that is in the same directory as
planner.agent.md and includes YAML frontmatter that has name:
IMPLEMENTER
You add a third agent file named review.agent.md.review.agent.md includes YAML frontmatter that has name: code-review.
You make the following changes to planner.agent.md:
- Update the existing handoff to include send: true and model: GPT-5.2
(copilot).
- Add a second handoff that has label: Run Review, agent: code-review,
and prompt: Review the code changes made in the previous step.
No other agent files are modified.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
You have a GitHub repository that contains the following custom agent files:
- A file named planner.agent.md that includes YAML frontmatter with a
handoffs entry that has label: Start Implementation, agent:
implementer, and prompt: Now implement the plan outlined above
- A file named implementer.agent.md that is in the same directory as
planner.agent.md and includes YAML frontmatter that has name:
IMPLEMENTER
You add a third agent file named review.agent.md.review.agent.md includes YAML frontmatter that has name: code-review.
You make the following changes to planner.agent.md:
- Update the existing handoff to include send: true and model: GPT-5.2
(copilot).
- Add a second handoff that has label: Run Review, agent: code-review,
and prompt: Review the code changes made in the previous step.
No other agent files are modified.
For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
正解：
Explanation:
Box 1: Yes
GitHub Copilot Extensions and agent frameworks route handoffs by matching the agent identifier in the YAML frontmatter to the filename or the name property defined within that repository.
Box 2: Yes
The failure happens because the agent target pointer in the handoff configuration does not match the actual target agent's declaration or file name due to a mismatch introduced by your changes.
Box 3: Yes
Yes, selecting "Start Implementation" will switch the chat to the implementer agent and automatically submit the prompt using the specified model.
The updates made to your GitHub agent repository configure a seamless workflow transition.
Here is how your new settings process that action:
Trigger action: Clicking Start Implementation activates the specific handoff block you modified.
Agent switch: The agent: implementer property targets the file with name: IMPLEMENTER, routing the conversation there.Automated submission: Setting send: true forces the interface to submit the text immediately instead of leaving it in the text box.
Model override: The model: GPT-5.2 (copilot) line forces the system to process that automated submission using that specific model version.
Reference:
https://arinco.com.au/blog/github-copilot-multi-repo-instructions/
https://aminrj.com/posts/building-a-multi-agents-coding-workflow/
Drag and Drop Question
You have a GitHub repository that uses GitHub Actions for CI on pull requests.
You have a GitHub Copilot coding agent that opens pull requests for backlog items, and your company requires automated checks for agent-generated changes.
You plan to standardize success criteria so that pull requests created by agents only succeed when unit tests pass and CodeQL analysis completes.
You need to configure a GitHub Actions workflow that runs on pull requests, executes unit tests, and performs CodeQL analysis.
How should you complete the workflow? To answer, drag the appropriate values to the correct targets. Each value may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.
You have a GitHub repository that uses GitHub Actions for CI on pull requests.
You have a GitHub Copilot coding agent that opens pull requests for backlog items, and your company requires automated checks for agent-generated changes.
You plan to standardize success criteria so that pull requests created by agents only succeed when unit tests pass and CodeQL analysis completes.
You need to configure a GitHub Actions workflow that runs on pull requests, executes unit tests, and performs CodeQL analysis.
How should you complete the workflow? To answer, drag the appropriate values to the correct targets. Each value may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.
正解：
Explanation:
Box 1: npm test
npm test (or mvn test, pytest, dotnet test depending on your language stack).
The run keyword requires a shell command to execute your test runner.
Box 2: init
The CodeQL workflow must initialize its database and environment before building code. The official action for this is github/codeql-action/init.
Box 3: analyze
After the code is prepared (and built if using a compiled language), the final step scans the codebase and uploads the SARIF results to GitHub Security. The official action is github/codeql- action/analyze.
Reference:
https://gitprotect.io/blog/github-actions-how-to-use-it-for-security-and-compliance-needs/
You have a repository on github.com that uses the GitHub Copilot coding agent.
You also use the GitHub Copilot CLI locally to reproduce failures and continue the same work from your terminal.
You need to verify the current token usage.
Which Copilot CLI slash command should you run?
You also use the GitHub Copilot CLI locally to reproduce failures and continue the same work from your terminal.
You need to verify the current token usage.
Which Copilot CLI slash command should you run?
正解：A
解答を投票する
解説: (JPNTest メンバーにのみ表示されます)