[WIP] Update prompt wording to align with Copilot documentation

[Codex]

Thanks for asking me to work on this. I will get started on it and keep this PR's description up to date as I form a plan and make progress.

---

This section details on the original issue you should resolve

<issue_title>This prompt now instructs "Do not expose hidden chain-of-thought" but the repo’s Copilot quick guide currently describes agi.prompt.md as "AGI reasoning with chain-of-thought" (see custom-instructions/repo/.github/copilot-instructions.md:332-334). To avoid confusion/drift, consider aligning the prompt wording/description with that documentation (or update the doc in a follow-up PR).</issue_title>
<issue_description>This prompt now instructs "Do not expose hidden chain-of-thought" but the repo’s Copilot quick guide currently describes agi.prompt.md as "AGI reasoning with chain-of-thought" (see custom-instructions/repo/.github/copilot-instructions.md:332-334). To avoid confusion/drift, consider aligning the prompt wording/description with that documentation (or update the doc in a follow-up PR).

Originally posted by @copilot in #99 (comment)</issue_description>

Comments on the Issue (you are @codex[agent] in this section)

[sourcery-ai]

Hi @codex! 👋

Your private repo does not have access to Sourcery.

Please upgrade to continue using Sourcery ✨

[github-actions]

🔴 Coverage — 101e4fd

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

Updated on every push · 2026-05-09

[Copilot]

Pull request overview

Updates Copilot-facing documentation to better describe the intent/usage of agi.prompt.md, and adds a gitignore entry for generated chat-cli logs.

Changes:

• Adjusts .github/copilot-instructions.md prompt listing to describe agi.prompt.md as structured analysis and not exposing hidden chain-of-thought.
• Updates .github/COPILOT_SETUP_GUIDE.md prompt table entry to match the revised agi.prompt.md description.
• Adds ai-projects/chat-cli/logs/ to .gitignore.

Reviewed changes

Copilot reviewed 2 out of 3 changed files in this pull request and generated 2 comments.

File	Description
.gitignore	Ignores generated chat-cli log output directory.
.github/copilot-instructions.md	Updates prompt catalog wording for agi.prompt.md.
.github/COPILOT_SETUP_GUIDE.md	Updates prompt purpose table wording for agi.prompt.md.

[Copilot]

This table row now says agi.prompt.md is "structured analysis" and "do not expose hidden chain-of-thought", but the actual .github/prompts/agi.prompt.md content doesn’t state that restriction and includes enable_chain_of_thought=True. Also, later in this same guide the example text still tells readers to use agi.prompt for chain-of-thought reasoning. Please align the guide with the prompt’s real behavior (or update the prompt).

[Bryan-Roe]

@copilot apply changes based on this feedback

[Copilot]

Fixed in commit 0f5547b. The table entry in COPILOT_SETUP_GUIDE.md now reads "AGI reasoning with structured analysis" — removing the inaccurate "do not expose hidden chain-of-thought" constraint that contradicted agi.prompt.md's actual behavior (enable_chain_of_thought=True). The example text referencing chain-of-thought reasoning was kept as it accurately reflects the prompt's behavior.

[sourcery-ai]

Hi @Bryan-Roe! 👋

Your private repo does not have access to Sourcery.

Please upgrade to continue using Sourcery ✨

[Bryan-Roe]

K

K

[Copilot]

Pull request overview

Copilot reviewed 2 out of 3 changed files in this pull request and generated 2 comments.

[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.

Snapshot Warnings

⚠️: No snapshots were found for the head SHA 959a2ca.

Ensure that dependencies are being submitted on PR branches and consider enabling retry-on-snapshot-warnings. See the documentation for more information and troubleshooting advice.

Scanned Files

None