docs: document Homebrew Tap Trust requirements - #1251
Conversation
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
📝 WalkthroughWalkthroughREADME documentation was updated with Homebrew 6+ trust guidance, a Skill Registry link, and formatting alignment for the Hermes supported-agent entry. ChangesREADME updates
Estimated code review effort: 1 (Trivial) | ~3 minutes Possibly related PRs
Suggested reviewers: 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Pull request overview
Updates the main README to document Homebrew “tap trust” behavior (notably on Homebrew 6+) so users can successfully install/upgrade Gentle AI tooling via the Gentleman Programming tap.
Changes:
- Adds a Homebrew 6+ note describing the “untrusted tap” failure mode and how to trust either the whole tap or individual packages.
- Tweaks the install snippet comment and makes minor README table formatting adjustments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| # macOS / Linux | ||
| brew tap Gentleman-Programming/homebrew-tap | ||
| brew trust --formula gentleman-programming/tap/gentle-ai # one-time, for Homebrew tap trust | ||
| brew trust --formula gentleman-programming/tap/gentle-ai # Homebrew +6, one-time, for Homebrew tap trust |
| > Trust the tap once: | ||
| > | ||
| > ```bash | ||
| > brew trust gentleman-programming/tap |
There was a problem hiding this comment.
Thanks! I checked the Homebrew Tap Trust documentation and brew trust gentleman-programming/tap is the documented syntax for trusting an entire tap. There is no --tap flag, so I'll keep the official command and only update the README to make the installation example consistent.
| # macOS / Linux | ||
| brew tap Gentleman-Programming/homebrew-tap | ||
| brew trust --formula gentleman-programming/tap/gentle-ai # one-time, for Homebrew tap trust | ||
| brew trust --formula gentleman-programming/tap/gentle-ai # Homebrew +6, one-time, for Homebrew tap trust |
| > If you encounter this error, trust the tap once: | ||
| > | ||
| > ```bash | ||
| > brew trust gentleman-programming/tap |
|
Thanks! I checked the Homebrew Tap Trust documentation and brew trust gentleman-programming/tap is the documented syntax for trusting an entire tap. There is no --tap flag, so I'll keep the official command and only update the README to make the installation example consistent. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
README.md (1)
124-124: 🎯 Functional Correctness | 🟡 Minor | ⚡ Quick winTrust the whole tap here Replace the formula-scoped trust command with
brew trust gentleman-programming/tapso users don’t have to retrust individual formulas forgga,engram, or future packages.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@README.md` at line 124, Update the Homebrew setup command in the README to trust the entire gentleman-programming/tap repository rather than the individual gentleman-programming/tap/gentle-ai formula, using the tap-scoped trust target so all current and future packages are covered.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In `@README.md`:
- Line 124: Update the Homebrew setup command in the README to trust the entire
gentleman-programming/tap repository rather than the individual
gentleman-programming/tap/gentle-ai formula, using the tap-scoped trust target
so all current and future packages are covered.
| # macOS / Linux | ||
| brew tap Gentleman-Programming/homebrew-tap | ||
| brew trust --formula gentleman-programming/tap/gentle-ai # one-time, for Homebrew tap trust | ||
| brew trust gentleman-programming/tap/gentle-ai # Homebrew +6, one-time, for Homebrew tap trust |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@README.md`:
- Line 124: Update the Homebrew installation example in README.md to trust the
complete tap rather than only the gentle-ai artifact, so related tap artifacts
install and upgrade without trust errors. Also change the wording from “Homebrew
+6” to “Homebrew 6+” while preserving the one-time trust guidance.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
README.md (1)
47-47: 🎯 Functional Correctness | 🟡 Minor | ⚡ Quick winUpdate Hermes to match the canonical delegation model.
The README still labels Hermes as “Detect-only,” while
docs/agents.mddocuments Hermes asFull (delegate_task ephemeral). Update this row to avoid misleading users about supported delegation behavior.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@README.md` at line 47, Update the Hermes row in the README agent capability table to label it as “Full (delegate_task ephemeral)” instead of “Detect-only,” matching the canonical delegation model documented in docs/agents.md while preserving the existing configuration and installation details.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In `@README.md`:
- Line 47: Update the Hermes row in the README agent capability table to label
it as “Full (delegate_task ephemeral)” instead of “Detect-only,” matching the
canonical delegation model documented in docs/agents.md while preserving the
existing configuration and installation details.
| # macOS / Linux | ||
| brew tap Gentleman-Programming/homebrew-tap | ||
| brew trust --formula gentleman-programming/tap/gentle-ai # one-time, for Homebrew tap trust | ||
| brew trust gentleman-programming/tap/gentle-ai # Homebrew 6+, one-time, for Homebrew tap trust |
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
README.md (1)
47-47: 🎯 Functional Correctness | 🟡 Minor | ⚡ Quick winKeep the Hermes capability description consistent with
docs/agents.md.This row says Hermes is “Detect-only,” while
docs/agents.mddocuments Hermes as Full (delegate_task ephemeral). Update the README wording to match the canonical agent documentation, or explicitly reconcile which document is authoritative.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@README.md` at line 47, Update the Hermes row in README.md to match the canonical capability description in docs/agents.md, using “Full (delegate_task ephemeral)” instead of “Detect-only”; do not alter the other Hermes configuration details.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Outside diff comments:
In `@README.md`:
- Line 47: Update the Hermes row in README.md to match the canonical capability
description in docs/agents.md, using “Full (delegate_task ephemeral)” instead of
“Detect-only”; do not alter the other Hermes configuration details.
| # macOS / Linux | ||
| brew tap Gentleman-Programming/homebrew-tap | ||
| brew trust --formula gentleman-programming/tap/gentle-ai # one-time, for Homebrew tap trust | ||
| brew trust gentleman-programming/tap # Homebrew 6+, one-time, for Homebrew tap trust |
|
Thanks for the finding. This appears to be unrelated to the Homebrew Tap Trust documentation changed in this PR and is outside the current diff. I’m keeping this PR focused on issue #832. The Hermes capability discrepancy should be verified separately to determine which document is authoritative, and then addressed in a dedicated issue or PR. |
| # macOS / Linux | ||
| brew tap Gentleman-Programming/homebrew-tap | ||
| brew trust --formula gentleman-programming/tap/gentle-ai # one-time, for Homebrew tap trust | ||
| brew trust gentleman-programming/tap # brew trust gentleman-programming/tap # Homebrew 6+, if required (one-time) |
| > [!NOTE] | ||
| > **Homebrew 6+** | ||
| > | ||
| > Recent versions of Homebrew require third-party taps to be explicitly trusted before formulas or casks can be installed or upgraded. |
| # macOS / Linux | ||
| brew tap Gentleman-Programming/homebrew-tap | ||
| brew trust --formula gentleman-programming/tap/gentle-ai # one-time, for Homebrew tap trust | ||
| brew trust gentleman-programming/tap # Homebrew 6+, if required (one-time) |
🔗 Linked Issue
Closes #832
🏷️ PR Type
What kind of change does this PR introduce?
type:bug— Bug fix (non-breaking change that fixes an issue)type:feature— New feature (non-breaking change that adds functionality)type:docs— Documentation onlytype:refactor— Code refactoring (no functional changes)type:chore— Build, CI, or tooling changestype:breaking-change— Breaking change (fix or feature that changes existing behavior)📝 Summary
Adds documentation for Homebrew Tap Trust requirements.
Recent versions of Homebrew may refuse to load third-party formulas and casks until the Gentleman Programming tap has been explicitly trusted. This can prevent
gentle-ai,gga, andengramfrom being upgraded.The README now explains how users can trust the complete tap or only the required formulas and cask.
📂 Changes
File / Area | What Changed -- | -- README.md | Added Homebrew Tap Trust instructions for installing and upgrading Gentle AI tools✅ Contributor Checklist
PR is linked to an issue with
status:approvedPR stays within 400 changed lines, or I have requested/obtained maintainer-applied
size:exceptionwith rationale documentedI have added the appropriate
type:*label to this PRUnit tests pass (
go test ./...)E2E tests pass (
cd e2e && ./docker-test.sh)I have updated documentation if necessary
My commits follow Conventional Commits format
My commits do not include
Co-Authored-Bytrailers💬 Notes for Reviewers
This is a documentation-only change based on an error encountered when upgrading
gentle-ai,gga, andengramthrough Homebrew.🔗 Linked Issue
Closes #832
🏷️ PR Type
What kind of change does this PR introduce?
type:bug— Bug fix (non-breaking change that fixes an issue)type:feature— New feature (non-breaking change that adds functionality)type:docs— Documentation onlytype:refactor— Code refactoring (no functional changes)type:chore— Build, CI, or tooling changestype:breaking-change— Breaking change (fix or feature that changes existing behavior)📝 Summary
Adds documentation for Homebrew Tap Trust requirements.
Recent versions of Homebrew may refuse to load third-party formulas and casks until the Gentleman Programming tap has been explicitly trusted. This can prevent
gentle-ai,gga, andengramfrom being upgraded.The README now explains how users can trust the complete tap or only the required formulas and cask.
📂 Changes
README.md🧪 Test Plan
Unit Tests
go test ./...E2E Tests (Docker required)
go test ./...)cd e2e && ./docker-test.sh)Documentation-only change. The rendered Markdown, code blocks, and Homebrew commands were reviewed manually.
🤖 Automated Checks
The following checks run automatically on this PR:
additions + deletions) or usesize:exceptionCloses/Fixes/Resolves #Nstatus:approvedtype:*Labeltype:*label must be appliedgo test ./...must passcd e2e && ./docker-test.shmust pass✅ Contributor Checklist
status:approvedsize:exceptionwith rationale documentedtype:*label to this PRgo test ./...)cd e2e && ./docker-test.sh)Co-Authored-Bytrailers💬 Notes for Reviewers
This is a documentation-only change based on an error encountered when upgrading
gentle-ai,gga, andengramthrough Homebrew.Summary by CodeRabbit
brew trustguidance to reference Homebrew 6+.