docs: align copilot-instructions.md prompt/agent descriptions with actual agi.prompt.md behavior#164
Merged
Merged
Conversation
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Hi @Copilot! 👋
Your private repo does not have access to Sourcery.
Please upgrade to continue using Sourcery ✨
…tual agi.prompt.md behavior Agent-Logs-Url: https://github.com/Bryan-Roe/Aria/sessions/b53ab83e-20cf-49d6-b2c8-71ada149d720 Co-authored-by: Bryan-Roe <74067792+Bryan-Roe@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Fix guide to align with agi.prompt.md content
docs: align copilot-instructions.md prompt/agent descriptions with actual agi.prompt.md behavior
Apr 30, 2026
…en CoT behavior Agent-Logs-Url: https://github.com/Bryan-Roe/Aria/sessions/02d5805e-beca-4937-913b-dac349a80fd7 Co-authored-by: Bryan-Roe <74067792+Bryan-Roe@users.noreply.github.com>
Contributor
There was a problem hiding this comment.
Hi @Bryan-Roe! 👋
Your private repo does not have access to Sourcery.
Please upgrade to continue using Sourcery ✨
github-actions
Bot
added
the
documentation
Contributor
🔴 Coverage —
|
| Metric | Value |
|---|---|
| Total coverage | 59.7% |
→ vs main |
0.0% |
| Minimum threshold | 60% |
Updated on every push · 2026-05-09
Contributor
There was a problem hiding this comment.
Pull request overview
Updates GitHub Copilot documentation/metadata to align the AGI prompt and agent descriptions with the intended behavior that chain-of-thought is performed internally (final answer only), and clarifies how reason.prompt.md is meant to be used.
Changes:
- Updated
.github/prompts/agi.prompt.mdfront-matter description to explicitly state chain-of-thought is internal and point users toreason.prompt. - Updated
.github/agents/agi-reasoning.agent.mddescription to remove “chain of thought” trigger phrasing and clarify internal-only chain-of-thought. - Updated
.github/copilot-instructions.mdagent table entry and prompt list entry to reflect the above.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| .github/prompts/agi.prompt.md | Clarifies AGI prompt front-matter to state hidden/internal chain-of-thought and redirect to reason.prompt. |
| .github/copilot-instructions.md | Updates agent/prompt summaries to reflect hidden/internal chain-of-thought expectations. |
| .github/agents/agi-reasoning.agent.md | Updates agent description and trigger phrases to avoid implying visible chain-of-thought output. |
This was referenced Apr 30, 2026
Contributor
There was a problem hiding this comment.
Pull request overview
Aligns documentation metadata for the AGI reasoning prompt/agent so that descriptions in .github/copilot-instructions.md and prompt/agent front-matter match the intended “internal (hidden) chain-of-thought” behavior, while directing users to reason.prompt for visible step-by-step reasoning.
Changes:
- Updates
.github/prompts/agi.prompt.mdfront-matter description to explicitly state chain-of-thought is internal and redirect toreason.promptfor visible steps. - Updates
.github/copilot-instructions.mdagent table and prompt list descriptions to reflect hidden vs visible reasoning behavior. - Updates
.github/agents/agi-reasoning.agent.mddescription and trigger phrases to remove “chain of thought” as a trigger and clarify hidden-CoT behavior.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| .github/prompts/agi.prompt.md | Clarifies AGI prompt uses internal/hidden chain-of-thought; redirects to reason.prompt for visible reasoning. |
| .github/copilot-instructions.md | Updates agent/prompt descriptions to match the intended hidden vs visible reasoning split. |
| .github/agents/agi-reasoning.agent.md | Adjusts agent description and trigger phrases to better match hidden-CoT positioning. |
| --- | ||
| name: agi-reasoning | ||
| description: "AGI reasoning and autonomous decision-making agent. Specializes in chain-of-thought reasoning, task decomposition, self-reflection, and multi-step planning using the AGI provider system.\n\nTrigger phrases include:\n- 'reason through this problem'\n- 'break this down step by step'\n- 'think through this autonomously'\n- 'use AGI reasoning'\n- 'chain of thought'\n- 'self-reflection'\n- 'autonomous planning'\n\nExamples:\n- User says 'reason through this architecture decision' → invoke for structured multi-step analysis\n- User asks 'break down this complex feature into tasks' → invoke for task decomposition\n- User says 'autonomously plan and implement this feature' → invoke for planning + execution with self-correction\n\nThis agent leverages the AGI provider's reasoning chains, task decomposition, and self-reflection capabilities." | ||
| description: "AGI reasoning and autonomous decision-making agent. Uses internal chain-of-thought reasoning (not exposed in output) for task decomposition, self-reflection, and multi-step planning — only the final answer is delivered to the user. For visible step-by-step reasoning, use reason.prompt instead.\n\nTrigger phrases include:\n- 'reason through this problem'\n- 'break this down step by step'\n- 'think through this autonomously'\n- 'use AGI reasoning'\n- 'autonomous planning'\n- 'self-reflection'\n\nExamples:\n- User says 'reason through this architecture decision' → invoke for structured multi-step analysis\n- User asks 'break down this complex feature into tasks' → invoke for task decomposition\n- User says 'autonomously plan and implement this feature' → invoke for planning + execution with self-correction\n\nThis agent leverages the AGI provider's reasoning chains, task decomposition, and self-reflection capabilities. Chain-of-thought steps are completed internally; only the final answer is delivered." |
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> Signed-off-by: Bryan <74067792+Bryan-Roe@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> Signed-off-by: Bryan <74067792+Bryan-Roe@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> Signed-off-by: Bryan <74067792+Bryan-Roe@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> Signed-off-by: Bryan <74067792+Bryan-Roe@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> Signed-off-by: Bryan <74067792+Bryan-Roe@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> Signed-off-by: Bryan <74067792+Bryan-Roe@users.noreply.github.com>
Comment on lines
1
to
3
| --- | ||
| description: "Engage autonomous AGI reasoning with multi-step analysis, task decomposition, self-correction, and iterative improvement. For complex problems requiring structured autonomous thinking." | ||
| description: "Engage autonomous AGI reasoning with multi-step analysis, task decomposition, self-correction, and iterative improvement. Chain-of-thought reasoning runs internally — only the final answer is delivered to the user. For visible step-by-step reasoning, use `reason.prompt.md` instead." | ||
| name: "AGI Reasoning" |
Contributor
Author
There was a problem hiding this comment.
Already applied in commit 296b162 — both .github/prompts/agi.prompt.md and .github/agents/agi-reasoning.agent.md now reference `reason.prompt.md` with the .md extension and in backticks.
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> Signed-off-by: Bryan <74067792+Bryan-Roe@users.noreply.github.com>
Signed-off-by: Bryan <74067792+Bryan-Roe@users.noreply.github.com>
Contributor
Dependency Review✅ No vulnerabilities or license issues or OpenSSF Scorecard issues found.Snapshot WarningsEnsure 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 FilesNone |
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.
copilot-instructions.mdagent table and prompt list (previous session)agi-reasoning.agent.mddescription — replaced "Specializes in chain-of-thought reasoning" with "Uses internal chain-of-thought reasoning (not exposed in output)"; added redirect "For visible step-by-step reasoning, use reason.prompt instead"; removed "chain of thought" trigger phrase that would incorrectly route users wanting visible CoTagi.prompt.mdfront-matter description — added "Chain-of-thought reasoning runs internally — only the final answer is delivered to the user. For visible step-by-step reasoning, use reason.prompt instead."