Align copilot-instructions.md descriptions with actual prompt behavior

[Copilot]

The guide had two mismatches with the actual prompt files: agi-reasoning.agent.md was labeled "Chain-of-thought reasoning, self-reflection" — implying exposed CoT — while agi.prompt.md explicitly hides it. reason.prompt.md was labeled "Structured analysis", obscuring that it's the prompt that exposes chain-of-thought steps to the user.

Changes

• agi-reasoning.agent.md table entry: Chain-of-thought reasoning, self-reflection → Autonomous multi-step reasoning with internal self-reflection (chain-of-thought is not exposed in output) — matches agi.prompt.md constraint: "Do not expose hidden chain-of-thought in responses"
• reason.prompt.md prompt entry: Structured analysis → Exposed chain-of-thought analysis with structured reasoning steps and confidence scores — reflects that this is the correct prompt to use when visible reasoning steps are desired

No changes to the prompt files themselves; both were already correctly authored.

Summary by Sourcery

Align Copilot instructions with actual behavior of AGI reasoning and reasoning prompts, clarifying when chain-of-thought is internal vs exposed.

Documentation:

• Update AGI reasoning agent description to state that chain-of-thought remains internal and not exposed in responses.
• Clarify that the reasoning prompt exposes chain-of-thought with structured reasoning steps and confidence scores.

[sourcery-ai]

Hi @Copilot! 👋

Your private repo does not have access to Sourcery.

Please upgrade to continue using Sourcery ✨

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

Updates .github/copilot-instructions.md so that the documented behavior of the AGI reasoning agent and the reasoning prompt accurately reflects whether chain-of-thought is internal-only or exposed in responses, without changing any actual prompt behavior.

Flow diagram for choosing AGI reasoning agent vs reasoning prompt

flowchart TD
  Start([Start])
  Decide["Need visible reasoning steps in output?"]
  Hidden["Use agi.prompt.md and agi-reasoning.agent.md (chain-of-thought is internal, not exposed)"]
  Exposed["Use reason.prompt.md (exposed chain-of-thought with structured steps and confidence scores)"]
  End([End])

  Start --> Decide
  Decide -->|Yes| Exposed
  Decide -->|No| Hidden
  Hidden --> End
  Exposed --> End

Loading

File-Level Changes

Change	Details	Files
Clarified documentation of AGI reasoning agent and reasoning prompt to accurately describe internal vs exposed chain-of-thought behavior.	Updated the agi-reasoning.agent.md row in the agents table to describe autonomous multi-step reasoning with internal self-reflection and explicitly note that chain-of-thought is not exposed in output. Updated the reason.prompt.md description in the prompts list to indicate that it provides exposed chain-of-thought analysis with structured reasoning steps and confidence scores.	.github/copilot-instructions.md

Assessment against linked issues

Issue	Objective	Addressed	Explanation
#167	Align the copilot-instructions.md prompt/agent table descriptions with the actual behavior of the prompt files, specifically that agi.prompt.md keeps chain-of-thought internal and reason.prompt.md is the prompt to use when exposing reasoning steps.	✅
#167	Update the later example text in copilot-instructions.md so it no longer tells readers to use agi.prompt.md for visible chain-of-thought reasoning, instead reflecting the actual behavior and correct prompt choice.	❌	The diff only changes the table descriptions for agi-reasoning.agent.md and reason.prompt.md. There is no modification to any later example text in copilot-instructions.md, so the guidance that instructs using agi.prompt for chain-of-thought reasoning appears unchanged.

Possibly linked issues

• [WIP] Update prompt wording to align with Copilot documentation #128: The PR updates copilot-instructions descriptions to match actual CoT behavior, resolving the documented guide–prompt mismatch.
• [WIP] Update prompt wording to align with Copilot documentation #128: PR changes copilot-instructions descriptions so agi/reason prompts’ documented chain-of-thought behavior matches the actual prompts.

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[sourcery-ai]

Hey - I've reviewed your changes and they look great!

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[Copilot]

Pull request overview

Updates .github/copilot-instructions.md documentation so the “Agents” and “Prompts” tables better reflect the intended behavior of the AGI reasoning-related prompt/agent entries.

Changes:

• Refines the agi-reasoning.agent.md table description to clarify chain-of-thought handling.
• Updates the reason.prompt.md table description to indicate it is intended for visible/structured reasoning output (including confidence scoring).

[Copilot]

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated 1 comment.

[github-actions]

⚠️ Deprecation Warning: The deny-licenses option is deprecated for possible removal in the next major release. For more information, see issue 997.

Dependency Review

✅ No vulnerabilities or license issues or OpenSSF Scorecard issues found.

Scanned Files

None

[github-actions]

🔴 Coverage — 982d375

Metric	Value
Total coverage	59.7%
→ vs main	0.0%
Minimum threshold	60%

Updated on every push · 2026-05-09