Add list_code_scanning_alerts query-bounding guardrail and regression tests by Copilot · Pull Request #46198 · github/gh-aw

Copilot · 2026-07-17T09:49:46Z

Unbounded list_code_scanning_alerts MCP calls return oversized payloads that break downstream workflow runs. Both GitHub MCP tools prompt files now instruct agents to always include state: open and severity: critical,high.

Changes

actions/setup/md/github_mcp_tools_prompt.md — added **Code scanning queries** guardrail line requiring state: open and severity: critical,high on every list_code_scanning_alerts call
actions/setup/md/github_mcp_tools_with_safeoutputs_prompt.md — same guardrail in the safe-outputs variant
pkg/workflow/prompt_validation_test.go — three new regression tests:
- TestGitHubMCPToolsPromptBoundsCodeScanningAlertQueries — asserts the plain prompt file contains both required parameters
- TestGitHubMCPToolsWithSafeOutputsPromptBoundsCodeScanningAlertQueries — same assertion on the with-safeoutputs variant
- TestGitHubMCPToolsPromptIncludedForCodeSecurityToolset — compiles a code_security-toolset workflow and verifies the generated lock file references one of the guardrail-carrying prompt files

The guardrail text added to both prompt files:

**Code scanning queries**: When calling `list_code_scanning_alerts`, always include
`state: open` and `severity: critical,high` to bound the response size and avoid
oversized payloads.

…guardrails Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>

…rails Add state: open and severity: critical,high guardrail to both GitHub MCP tools prompt files to prevent unbounded code-scanning queries that produce oversized responses and break downstream workflow runs. Add three regression tests in prompt_validation_test.go: - TestGitHubMCPToolsPromptBoundsCodeScanningAlertQueries - TestGitHubMCPToolsWithSafeOutputsPromptBoundsCodeScanningAlertQueries - TestGitHubMCPToolsPromptIncludedForCodeSecurityToolset Closes #46162 Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>

pelikhan · 2026-07-17T11:24:44Z

@copilot use the field selection feature from the GitHub MCP server 1.6.0 to apply these APIs. Update prompt.

Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>

…er 1.6.0) Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>

Copilot · 2026-07-17T11:43:13Z

@copilot use the field selection feature from the GitHub MCP server 1.6.0 to apply these APIs. Update prompt.

Done in commit feat: add fields_param guidance to GitHub MCP tools prompts (MCP server 1.6.0).

Both prompt files now include a Field selection guardrail documenting the fields parameter introduced in GitHub MCP server 1.6.0 (available via the fields_param feature flag, auto-enabled in Insiders mode):

**Field selection (GitHub MCP server ≥ 1.6.0)**: When calling list/search tools that accept a `fields` parameter
(`list_pull_requests`, `list_issues`, `search_issues`, `search_pull_requests`, `list_commits`, `list_releases`,
`search_code`, `get_file_contents`), pass only the fields you need to reduce response size.
Example: `list_pull_requests` with `fields: [number, title, state, html_url]`.

Note: list_code_scanning_alerts does not have a fields parameter in v1.6.0 (not in the fields_param insiders feature set), so that tool continues to use the state: open / severity: critical,high filtering guardrail.

The SKILL.md Pull Requests section is also updated to prefer the fields approach over minimal_output for servers ≥ 1.6.0. A new regression test TestGitHubMCPToolsPromptHasFieldSelectionGuidance verifies the guidance is present in both prompt files.

Copilot

Pull request overview

Adds response-bounding guidance for GitHub MCP code-scanning queries and related regression tests.

Changes:

Adds code-scanning and field-selection prompt guidance.
Adds prompt-content and compilation regression tests.
Updates GitHub MCP skill documentation.

Show a summary per file

File	Description
`actions/setup/md/github_mcp_tools_prompt.md`	Adds MCP query guidance.
`actions/setup/md/github_mcp_tools_with_safeoutputs_prompt.md`	Adds equivalent safe-output guidance.
`pkg/workflow/prompt_validation_test.go`	Tests prompt content and inclusion.
`.github/skills/github-mcp-server/SKILL.md`	Updates MCP usage documentation.

Review details

Tip

Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comments suppressed due to low confidence (2)

actions/setup/md/github_mcp_tools_prompt.md:8

This adds a separate field-selection policy, corresponding skill changes, and a fourth regression test, while the PR title and description claim the change is limited to the code-scanning guardrail and three tests. Either split this unrelated GitHub MCP 1.6.0 behavior into its own PR or document and justify the expanded scope.

**Field selection (GitHub MCP server ≥ 1.6.0)**: When calling list/search tools that accept a `fields` parameter (`list_pull_requests`, `list_issues`, `search_issues`, `search_pull_requests`, `list_commits`, `list_releases`, `search_code`, `get_file_contents`), pass only the fields you need to reduce response size. Example: `list_pull_requests` with `fields: [number, title, state, html_url]`.

pkg/workflow/prompt_validation_test.go:49

This second test also requires the invalid comma-separated severity value, preventing a correct prompt fix. Assert the bounded perPage guidance and the two valid single-severity examples instead.

	assert.Contains(t, content, "severity: critical,high",
		"prompt should require severity: critical,high to bound list_code_scanning_alerts queries")

Files reviewed: 4/4 changed files
Comments generated: 4
Review effort level: Medium


 **Identity**: Do not call `get_me` — it returns 403 under the integration token. Read your identity (actor, repository, run ID) from the `<github-context>` block provided at the start of the prompt.
+
+**Code scanning queries**: When calling `list_code_scanning_alerts`, always include `state: open` and `severity: critical,high` to bound the response size and avoid oversized payloads.



 **Identity**: Do not call `get_me` — it returns 403 under the integration token. Read your identity (actor, repository, run ID) from the `<github-context>` block provided at the start of the prompt.
+
+**Code scanning queries**: When calling `list_code_scanning_alerts`, always include `state: open` and `severity: critical,high` to bound the response size and avoid oversized payloads.


 - `create_code_scanning_alert` - Create a code scanning alert

-When invoking `list_code_scanning_alerts` from workflow prompts/templates, always include `state: open` and `severity: critical,high`.
+When invoking `list_code_scanning_alerts` from workflow prompts/templates, always include `state: open` and `severity: critical,high` to bound the response size and avoid oversized payloads.


+	assert.Contains(t, content, "severity: critical,high",
+		"prompt should require severity: critical,high to bound list_code_scanning_alerts queries")


github-actions · 2026-07-18T09:23:09Z

🎉 This pull request is included in a new release.

Release: v0.82.13

Initial plan

816b217

Copilot AI assigned Copilot and pelikhan Jul 17, 2026

Copilot started work on behalf of pelikhan July 17, 2026 09:50 View session

Copilot AI linked an issue Jul 17, 2026 that may be closed by this pull request

[hippo] Add regression coverage so generated code-scanning prompts always bound alert queries #46162

Closed

Copilot AI and others added 2 commits July 17, 2026 10:01

chore: planning - add regression tests for list_code_scanning_alerts …

fb252d7

…guardrails Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>

Copilot AI changed the title ~~[WIP] Add regression tests for code scanning alert queries~~ Add list_code_scanning_alerts query-bounding guardrail and regression tests Jul 17, 2026

Copilot finished work on behalf of pelikhan July 17, 2026 10:19

Copilot AI requested a review from pelikhan July 17, 2026 10:19

Copilot started work on behalf of pelikhan July 17, 2026 11:25 View session

Copilot AI and others added 2 commits July 17, 2026 11:34

plan: add fields_param guidance to MCP tool prompts

97d1ff5

Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>

feat: add fields_param guidance to GitHub MCP tools prompts (MCP serv…

b3b3935

…er 1.6.0) Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>

Copilot finished work on behalf of pelikhan July 17, 2026 11:43

github-actions Bot added pr-action:fast_track pr-agent:copilot pr-priority:medium pr-risk:low pr-type:test labels Jul 17, 2026

pelikhan marked this pull request as ready for review July 18, 2026 05:46

Copilot AI review requested due to automatic review settings July 18, 2026 05:46

pelikhan merged commit b0d0815 into main Jul 18, 2026

pelikhan deleted the copilot/hippo-add-regression-coverage-again branch July 18, 2026 05:46

Copilot started reviewing on behalf of pelikhan July 18, 2026 05:46 View session

Copilot AI reviewed Jul 18, 2026

View reviewed changes

github-actions Bot mentioned this pull request Jul 18, 2026

Smoke Test: MAI-Code-1-Flash - 29638034909 #46385

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Add list_code_scanning_alerts query-bounding guardrail and regression tests#46198

Add list_code_scanning_alerts query-bounding guardrail and regression tests#46198
pelikhan merged 5 commits into
mainfrom
copilot/hippo-add-regression-coverage-again

Copilot AI commented Jul 17, 2026 •

edited

Loading

Uh oh!

pelikhan commented Jul 17, 2026

Uh oh!

Copilot AI commented Jul 17, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

github-actions Bot commented Jul 18, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants


		Identity: Do not call `get_me` — it returns 403 under the integration token. Read your identity (actor, repository, run ID) from the `<github-context>` block provided at the start of the prompt.

		Code scanning queries: When calling `list_code_scanning_alerts`, always include `state: open` and `severity: critical,high` to bound the response size and avoid oversized payloads.

		assert.Contains(t, content, "severity: critical,high",
		"prompt should require severity: critical,high to bound list_code_scanning_alerts queries")

Uh oh!

Conversation

Copilot AI commented Jul 17, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Changes

Uh oh!

pelikhan commented Jul 17, 2026

Uh oh!

Copilot AI commented Jul 17, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Review details

Uh oh!

github-actions Bot commented Jul 18, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Copilot AI commented Jul 17, 2026 •

edited

Loading