[WIP] Update prompt wording to align with Copilot guide#127
Conversation
…ehavior Agent-Logs-Url: https://github.com/Bryan-Roe/Aria/sessions/7c58f8b9-3482-4a89-9739-fb771082a16c Co-authored-by: Bryan-Roe <74067792+Bryan-Roe@users.noreply.github.com>
github-actions
Bot
added
the
documentation
🔴 Coverage —
|
| Metric | Value |
|---|---|
| Total coverage | 59.6% |
▼ vs main |
-0.1% |
| Minimum threshold | 60% |
Updated on every push · 2026-05-09
There was a problem hiding this comment.
Pull request overview
Updates Copilot documentation wording to describe agi.prompt.md/agi-reasoning in terms of “internal/hidden reasoning” to address drift with the repo’s Copilot guide.
Changes:
- Adjusts the
agi-reasoning.agent.mddescription line in.github/copilot-instructions.mdto mention “internal chain-of-thought”. - Updates
.github/copilot-instructions.mdand.github/COPILOT_SETUP_GUIDE.mdprompt tables/examples to describeagi.prompt.mdas autonomous long-running work with internal reasoning.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
.github/copilot-instructions.md |
Rewords agi-reasoning agent + agi.prompt.md descriptions to emphasize internal/hidden reasoning. |
.github/COPILOT_SETUP_GUIDE.md |
Rewords agi.prompt.md purpose and the explicit-reference example to emphasize internal reasoning/autonomous work. |
![sourcery-ai[bot]](https://avatars.githubusercontent.com/in/48477?s=60&v=4){kind=small}
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 ✨
There was a problem hiding this comment.
Pull request overview
Updates Copilot documentation wording around the AGI prompt/agent to reduce ambiguity about chain-of-thought handling and better reflect intended usage guidance.
Changes:
- Refines the
agi-reasoning.agent.mddescription in the Copilot quick guide to emphasize “internal” reasoning. - Updates the Copilot quick guide and setup guide prompt tables to describe
agi.prompt.mdas “autonomous long-running work with internal reasoning” rather than “chain-of-thought AGI reasoning”.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
.github/copilot-instructions.md |
Adjusts agent/prompt descriptions to reference internal/hidden reasoning. |
.github/COPILOT_SETUP_GUIDE.md |
Updates prompt table and example text to match the new “internal reasoning” wording. |
| | `ai.agent.md` | Primary autonomous agent — task decomposition, multi-step execution | | ||
| | `my-agent.agent.md` | QAI specialist — quantum-AI/ML development | | ||
| | `agi-reasoning.agent.md` | Chain-of-thought reasoning, self-reflection | | ||
| | `agi-reasoning.agent.md` | Structured reasoning with internal chain-of-thought, self-reflection | |
|
|
||
| **Prompts** (`.github/prompts/`): | ||
| - `agi.prompt.md` — AGI reasoning with chain-of-thought | ||
| - `agi.prompt.md` — Autonomous long-running work with internal reasoning (hidden chain-of-thought) |
| **Prompts** (`.github/prompts/`): | ||
| - `agi.prompt.md` — AGI reasoning with chain-of-thought | ||
| - `agi.prompt.md` — Autonomous long-running work with internal reasoning (hidden chain-of-thought) |
There was a problem hiding this comment.
Done in de9f43c. Updated both .github/prompts/agi.prompt.md and .github/agents/agi-reasoning.agent.md to explicitly instruct that chain-of-thought is internal and must not be exposed — only the final answer is returned. Also updated the agi-reasoning entry in copilot-instructions.md to accurately reflect this behavior.
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>
…nal chain-of-thought Agent-Logs-Url: https://github.com/Bryan-Roe/Aria/sessions/382dfb64-2813-4424-9bb2-b80df22b31ac Co-authored-by: Bryan-Roe <74067792+Bryan-Roe@users.noreply.github.com>
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: de9f43c6ba
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
|
|
||
| You are an advanced autonomous reasoning agent built on Aria's AGI provider system. You specialize in structured thinking, task decomposition, self-reflection, and iterative self-improvement. | ||
|
|
||
| **Do not expose your internal chain-of-thought in responses.** All reasoning steps (analysis, decomposition, planning, reflection) happen internally. Return only the final answer, decision, or output to the user. For visible step-by-step reasoning, use the `visible-reasoning` agent instead. |
There was a problem hiding this comment.
When someone wants visible step-by-step reasoning, this instruction points them to visible-reasoning, but there is no .github/agents/visible-reasoning.agent.md or name: visible-reasoning in .github (I checked the agents directory and rg "visible-reasoning|name:.*reason" .github). The prompt metadata in this same change instead points to reason.prompt, so following the new agent instruction would send users/Copilot to a nonexistent agent rather than the available visible-reasoning workflow.
Useful? React with 👍 / 👎.
Signed-off-by: Bryan <74067792+Bryan-Roe@users.noreply.github.com>
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 |
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.