Add comprehensive GitHub Copilot instructions with AGENTS.md symlink

[Copilot]

This PR adds a comprehensive .github/copilot-instructions.md file that provides GitHub Copilot with detailed guidance on working with the ChatGPTBox codebase. The instructions are designed to help AI agents understand and work effectively with this browser extension project.

Key Features

Comprehensive Architecture Documentation:

• Detailed breakdown of all major components (content script, background service worker, popup, independent panel)
• Site adapters and selection tools architecture explanation
• Cross-browser compatibility notes with manifest version details (MV3 vs MV2)

Thoroughly Validated Build Process:

• All commands tested and timing measured in dedicated "Time Expectations" section
• Proportional timeout recommendations (5-10 minutes for 33-second builds)
• Expected build output structure with flexible file size guidance for validation
• Safari-specific build requirements with exact artifact names (Fission - ChatBox.app and safari.dmg)
• Cross-references between build commands and troubleshooting sections

Enhanced Manual Testing Strategy:

• Improved browser extension loading instructions that prevent common misloading errors
• Clear guidance for Chrome (select folder containing manifest.json) and Firefox (prefer .xpi files)
• Core functionality test scenarios including keyboard shortcuts (Ctrl+B, Ctrl+Shift+H)
• Site integration testing for major platforms (YouTube, Reddit, GitHub, Google)
• Configuration interface testing across all settings tabs

Cross-Platform Development Support:

• Platform-specific cache clearing commands for both Unix (macOS/Linux) and Windows PowerShell
• Inclusive troubleshooting steps that work across different development environments
• Code quality tools setup (ESLint, Prettier) with pre-commit hooks

Enhanced Technical Documentation:

• Detailed verify script validation explanation with success criteria and expected failure modes
• Extension requires proper browser extension context (cannot be tested via HTTP server)
• No automated test infrastructure - all validation must be manual
• Accurate AI provider list matching actual codebase integrations (ChatGPT, Claude.ai, Kimi.Moonshot, etc.)

Improved Document Structure:

• Eliminated redundant information across sections for better maintainability
• Single sources of truth for build processes, timing expectations, and platform requirements
• Streamlined troubleshooting with unified cache clearing and dependency instructions
• Flexible file size guidance to reduce brittleness and false alarms

The instructions follow best practices with imperative tone, exhaustive validation of commands, and comprehensive manual testing scenarios. This significantly improves AI agent effectiveness when working on ChatGPTBox development tasks across different platforms.

Fixes #880.

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.

---

PR Type

Documentation

---

Description

• Add comprehensive GitHub Copilot instructions file

• Document architecture, build process, and testing procedures

• Provide development workflow and troubleshooting guidance

• Include platform-specific instructions and time expectations

---

Diagram Walkthrough

flowchart LR
  A["GitHub Copilot"] --> B["copilot-instructions.md"]
  B --> C["Architecture Guide"]
  B --> D["Build Process"]
  B --> E["Testing Strategy"]
  B --> F["Development Workflow"]
  C --> G["Components & Manifests"]
  D --> H["Commands & Validation"]
  E --> I["Manual Browser Testing"]
  F --> J["Code Quality & Troubleshooting"]

Loading

File Walkthrough

Relevant files

Documentation

copilot-instructions.md Add comprehensive GitHub Copilot development instructions .github/copilot-instructions.md Create comprehensive 175-line instruction file for GitHub Copilot Document complete architecture with content script, background worker, popup components Provide detailed build commands with timing and validation steps Include manual testing procedures for browser extension functionality Add development workflow guidelines and troubleshooting section +175/-0

---

Summary by CodeRabbit

• Documentation
  • Added a comprehensive developer guide covering setup, build, release, and platform-specific build steps for Chromium, Firefox, and Safari.
  • Includes architecture overview, packaging expectations, manual testing/checklists, build validation, troubleshooting, lint/format hooks, and time estimates for common tasks.
  • Clarifies cross-browser compatibility and AI model support options.
  • Confirms no user-facing behavior changes.

[PeterDaveHello]

@copilot check this review comment, please:

Consider clarifying what specific validation the verify script performs on these search engines. The current explanation mentions 'validate site adapters' but doesn't specify what constitutes successful validation versus expected failure modes.

This review suggests applying this section to "### Verify Script Limitations":

- `npm run verify` tests search engine configurations by attempting to fetch search results from external search engines (Bing, Yahoo, Baidu, Naver) to validate that the site adapters can parse and handle real responses.
- **Successful validation**: For each search engine, the script expects to receive a valid HTTP response (status 200) and to successfully extract and parse search results using the corresponding site adapter. If the adapter can parse the expected data structure from the response, the test is considered a pass.
- **Expected failure modes**: In sandboxed or CI environments, the script may fail due to network restrictions (e.g., DNS errors, timeouts, connection refused), HTTP errors (e.g., 403, 429, 503), or changes in the search engine's response format. These failures are expected and do **not** indicate build problems.
- If you see network or HTTP errors during `npm run verify`, you can safely ignore them unless you are specifically testing or updating site adapter logic.

[Copilot]

@copilot check this review comment, please:

Consider clarifying what specific validation the verify script performs on these search engines. The current explanation mentions 'validate site adapte...

Enhanced the verify script limitations section with detailed explanation of validation process, successful validation criteria, and expected failure modes. The section now clearly explains what constitutes successful validation (HTTP 200 + successful parsing) vs expected failures (network restrictions, HTTP errors, format changes) and when these can be safely ignored.

Commit: 5c8d3f7

[PeterDaveHello]

@copilot check this review comment, and see if it's correct:

The description of Safari build output is unclear. Consider specifying the exact names or patterns of the generated files (e.g., 'ChatGPTBox.app' and 'ChatGPTBox.dmg') to help developers identify successful build artifacts.

-- Creates `.app` bundle and `.dmg` installer
+- Creates `ChatGPTBox.app` bundle and `ChatGPTBox.dmg` installer

[Copilot]

@copilot check this review comment, and see if it's correct:

The description of Safari build output is unclear. Consider specifying the exact names or patterns of the generated files (e.g., 'ChatGP...

Updated Safari build section with exact artifact names based on the actual build script. The correct names are Fission - ChatBox.app and safari.dmg (not ChatGPTBox.* as suggested) since the Safari version uses "Fission - ChatBox" as the app name.

Commit: 4f28ac4

[Copilot]

Pull Request Overview

This PR adds comprehensive GitHub Copilot instructions to guide AI agents when working with the ChatGPTBox browser extension codebase. The instructions provide detailed architectural documentation, validated build processes, and manual testing strategies to help AI agents understand and effectively develop this complex cross-browser extension.

• Comprehensive architecture documentation covering all major components and cross-browser compatibility requirements
• Thoroughly validated build process with measured timing and explicit timeout warnings
• Detailed manual testing strategy since the project lacks automated test infrastructure

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[PeterDaveHello]

@copilot Check the review comment below, confirm if it's correct or not, and decide whether to make some follow-up changes or not:

The timeout recommendation of 90+ minutes for a 33-second build is inconsistent and potentially confusing. Consider clarifying why such a large buffer is needed or adjust the timeout recommendation to be more proportional to the actual build time.

[Copilot]

@copilot Check the review comment below, confirm if it's correct or not, and decide whether to make some follow-up changes or not:

The timeout recommendation of 90+ minutes for a 33-second build ...

The comment is correct - the 90+ minute timeout for a 33-second build was inconsistent and confusing. Updated both timeout recommendations to 5-10 minutes, which provides a reasonable buffer for system variations while being proportional to the actual build time.

Commit: 7210f28

[coderabbitai]

Note

Other AI code review bot(s) detected

CodeRabbit has detected other AI code review bot(s) in this pull request and will avoid duplicating their findings in the review comments. This may lead to a less comprehensive review.

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Walkthrough

Adds a new repository documentation file at .github/copilot-instructions.md documenting build/bootstrap commands, architecture overview, manual testing and validation steps, platform-specific build notes (Chromium/Firefox/Safari), troubleshooting, and release workflow. No code or public API changes.

Changes

Cohort / File(s)

Summary

Repository Copilot instructions .github/copilot-instructions.md

Adds a comprehensive developer guide covering bootstrap/build commands (npm ci, npm run dev, npm run build, npm run lint, npm run pretty, npm run build:safari), expected build outputs and ZIP packaging, architecture (Content Script, Background Script, Popup, Independent Panel, Site Adapters, Selection Tools), MV3/MV2 manifests, manual testing and validation steps, Safari build notes, cross-browser compatibility guidance, AI model/API modes, troubleshooting, lint/pretty hooks, development workflow and release validation checklist. No code or exported/public declarations changed.

Sequence Diagram(s)

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Assessment against linked issues

Objective	Addressed	Explanation
Set up Copilot instructions [#880]	✅

"In my burrow I pen the guide so bright,
Steps for builds by moonbeam light.
Chromium, Firefox, Safari in tune,
Lint, package, ship beneath the moon.
Hop forward, devs—your docs take flight! 🐇✨"

---

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

• Review comments: Directly reply to a review comment made by CodeRabbit. Example:
  • I pushed a fix in commit <commit_id>, please review it.
  • Open a follow-up GitHub issue for this discussion.
• Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query.
• PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
  • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
  • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Support

Need help? Join our Discord community for assistance with any issues or questions.

CodeRabbit Commands (Invoked using PR/Issue comments)

Type @coderabbitai help to get the list of available commands.

Other keywords and placeholders

• Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
• Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
• Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

• You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
• Please see the configuration documentation for more information.
• If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Status, Documentation and Community

• Visit our Status Page to check the current availability of CodeRabbit.
• Visit our Documentation for detailed information on how to use CodeRabbit.
• Join our Discord Community to get help, request features, and share feedback.
• Follow us on X/Twitter for updates and announcements.

[PeterDaveHello]

@copilot, please review the updated comments from Qodo Merge and decide whether to revise.

I don't see any specific updated comments from Qodo Merge in the provided context. Could you please share the specific review comments that need to be addressed? I've already addressed the previous coderabbitai review feedback in commit fd76a40.
Help improve Copilot by leaving feedback using the 👍 or 👎 buttons

@copilot, It's interesting that you can only see normal comments, not the "review" comments?

I've manually pasted Qodo Merge's suggestion here to see if it's reasonable to follow.

Suggestion: Prevent extension misloading instructions

   - Chrome: Go to `chrome://extensions/`, enable Developer Mode, click "Load unpacked", then select the folder `build/chromium/` (the folder must contain `manifest.json`).
   - Firefox: Go to `about:debugging#/runtime/this-firefox`, click "Load Temporary Add-on", then choose the generated `.xpi` file from `build/` (recommended). To load unpacked instead, select the `manifest.json` file inside `build/firefox/` (do not select the folder directly). Note: Temporary add-ons are removed on browser restart.
   - **Important**: Extension files cannot be tested by serving them via HTTP server — they must be loaded as a proper browser extension.

Suggestion: Provide cross-platform cleanup steps

- Build failures: Check Node.js version (requires Node 20+), clear caches and rebuild.
  - macOS/Linux: `rm -rf node_modules && npm ci && rm -rf node_modules/.cache build/ dist/`
  - Windows (PowerShell): `Remove-Item -Recurse -Force node_modules, build, dist; if (Test-Path node_modules\.cache) { Remove-Item -Recurse -Force node_modules\.cache }; npm ci`

[Copilot]

@copilot, please review the updated comments from Qodo Merge and decide whether to revise.

I don't see any specific updated comments from Qodo Merge in the provided context. Could you pleas...

Both Qodo Merge suggestions were reasonable improvements:

1. Extension loading instructions: Added clarification for Chrome to select the folder containing manifest.json, improved Firefox instructions to recommend .xpi files first, and enhanced formatting with proper em dashes.

2. Cross-platform cleanup steps: Added Windows PowerShell commands alongside Unix commands to make the documentation more inclusive for Windows developers.

These changes prevent common extension loading errors and improve cross-platform accessibility without changing core functionality.

Commit: b8fcc48

[PeterDaveHello]

@coderabbitai review

[coderabbitai]

✅ Actions performed

Review triggered.

Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.

[coderabbitai]

Actionable comments posted: 2

♻️ Duplicate comments (2)

.github/copilot-instructions.md (2)

30-31: Safari artifact names look inconsistent with project branding; verify exact product names and update both places together.

The doc says “Fission - ChatBox.app” and “safari.dmg”, which don’t match the repository/product name “ChatGPTBox”. Please confirm the actual names emitted by safari/build.sh/Xcode and make the two sections consistent.

Proposed edit (assuming the app is branded ChatGPTBox in Xcode; if not, adjust to the verified names):

-  - Safari: `Fission - ChatBox.app` and `safari.dmg` (see Safari Build section for details)
+  - Safari: `ChatGPTBox.app` and `ChatGPTBox.dmg` (see Safari Build section for details)

-- Creates `Fission - ChatBox.app` bundle and `safari.dmg` installer
+- Creates `ChatGPTBox.app` bundle and `ChatGPTBox.dmg` installer

Would you like me to open a follow-up to auto-derive these names from safari/build.sh so the doc can’t drift again?

Also applies to: 149-151

---

96-102: Verify script behavior is now explicit and actionable.

The success criteria and expected failure modes for npm run verify are clear, reducing false alarms in CI/sandboxes.

🧹 Nitpick comments (3)

.github/copilot-instructions.md (3)

45-47: Time-stamp the Firefox MV2 note to avoid future staleness.

Mozilla’s MV2/MV3 policy changes over time. Add an “as of” date so readers can evaluate freshness.

-- `src/manifest.v2.json` - Manifest v2 for Firefox (current status; future MV3 migration may change this)
+- `src/manifest.v2.json` - Manifest v2 for Firefox (current status as of August 2025; future MV3 migration may change this)

---

12-16: Hung-build policy is consistent; small style polish for time ranges.

Great that the “NEVER CANCEL” wording was removed and the policy is unified. For consistency, consider using an en dash in time ranges.

-- `npm run build`: ~35 seconds (measured). Set timeout to 5-10 minutes; if it exceeds this and appears hung, see "Build Issues" for recovery steps.
+- `npm run build`: ~35 seconds (measured). Set timeout to 5–10 minutes; if it exceeds this and appears hung, see "Build Issues" for recovery steps.
-- `npm run dev`: ~15 seconds initial build, then watches for changes; use Ctrl+C to stop when switching branches or after config/dependency changes.
+- `npm run dev`: ~15 seconds initial build, then watches for changes; use Ctrl+C to stop when switching branches or after config/dependency changes.

Also applies to: 188-194

---

169-171: Add npm cache reset as a last resort troubleshooting step.

When deep cache corruption occurs, resetting npm’s cache helps.

   - macOS/Linux: `rm -rf node_modules && npm ci && rm -rf node_modules/.cache build/ dist/`
-  - Windows (PowerShell): `Remove-Item -Recurse -Force node_modules, build, dist; if (Test-Path node_modules\.cache) { Remove-Item -Recurse -Force node_modules\.cache }; npm ci`
+  - Windows (PowerShell): `Remove-Item -Recurse -Force node_modules, build, dist; if (Test-Path node_modules\.cache) { Remove-Item -Recurse -Force node_modules\.cache }; npm ci`
+  - If issues persist: `npm cache clean --force && npm ci` (use sparingly)

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

💡 Knowledge Base configuration:

• MCP integration is disabled by default for public repositories
• Jira integration is disabled by default for public repositories
• Linear integration is disabled by default for public repositories

You can enable these sources in your CodeRabbit configuration.

📥 Commits

Reviewing files that changed from the base of the PR and between a105950 and c12bd35.

📒 Files selected for processing (1)

• .github/copilot-instructions.md (1 hunks)

🧰 Additional context used

🪛 LanguageTool

.github/copilot-instructions.md

[grammar] ~26-~26: There might be a mistake here.
Context: ...ithout math rendering and token encoding - Distribution artifacts: - Chromium: `b...

(QB_NEW_EN)

---

[grammar] ~27-~27: There might be a mistake here.
Context: ...token encoding - Distribution artifacts: - Chromium: build/chromium-*.zip (e.g., ...

(QB_NEW_EN)

---

[grammar] ~28-~28: There might be a mistake here.
Context: ...(e.g.,build/chromium-.zip) - Firefox: build/firefox-*.xpi(e.g.,b...

(QB_NEW_EN)

---

[grammar] ~29-~29: There might be a mistake here.
Context: ...i(e.g.,build/firefox-.xpi) - Safari: Fission - ChatBox.appandsaf...

(QB_NEW_EN)

---

[grammar] ~46-~46: There might be a mistake here.
Context: ...s; future MV3 migration may change this) - Background runs as service worker (MV3) ...

(QB_NEW_EN)

---

[grammar] ~56-~56: There might be a mistake here.
Context: ...nality: 1. Load Extension in Browser: - Chrome: Go to chrome://extensions/, en...

(QB_NEW_EN)

---

[grammar] ~57-~57: There might be a mistake here.
Context: ...he folder must contain manifest.json). - Firefox: Go to `about:debugging#/runtime...

(QB_NEW_EN)

---

[grammar] ~59-~59: There might be a mistake here.
Context: ... files cannot be tested by serving them via HTTP server - they must be loaded as a ...

(QB_NEW_EN)

---

[grammar] ~61-~61: There might be a mistake here.
Context: ...tension. 2. Core Functionality Tests: - Press Ctrl+B (Windows/Linux) or ⌘+B ...

(QB_NEW_EN)

---

[grammar] ~65-~65: There might be a mistake here.
Context: ...nu appears - Click extension icon to open popup - Press Ctrl+Shift+H (Window...

(QB_NEW_EN)

---

[grammar] ~68-~68: There might be a mistake here.
Context: ...ation page 3. Site Integration Tests: - Visit YouTube.com, verify video summary ...

(QB_NEW_EN)

---

[grammar] ~70-~70: There might be a mistake here.
Context: ...com, verify ChatGPT integration appears in sidebar - Visit github.com, verify c...

(QB_NEW_EN)

---

[grammar] ~74-~74: There might be a mistake here.
Context: ...ponses appear 4. Configuration Tests: - Open extension popup, navigate through t...

(QB_NEW_EN)

---

[grammar] ~75-~75: There might be a mistake here.
Context: ...:** - Open extension popup, navigate through tabs (General, Feature Pages, Modules >...

(QB_NEW_EN)

---

[grammar] ~82-~82: There might be a mistake here.
Context: ... these files exist in build/chromium/ after successful build: - manifest.json (c...

(QB_NEW_EN)

---

[grammar] ~98-~98: There might be a mistake here.
Context: ...ers can parse and handle real responses. - Successful validation: For each search...

(QB_NEW_EN)

---

[grammar] ~162-~162: There might be a mistake here.
Context: ...ylaidwanderer (API), Kimi.Moonshot (API) - Custom/self-hosted: Alternative endpoi...

(QB_NEW_EN)

---

[grammar] ~169-~169: There might be a mistake here.
Context: ...res Node 20+), clear caches and rebuild. - macOS/Linux: `rm -rf node_modules && npm...

(QB_NEW_EN)

---

[grammar] ~170-~170: There might be a mistake here.
Context: ...ar caches and rebuild. - macOS/Linux: rm -rf node_modules && npm ci && rm -rf node_modules/.cache build/ dist/ - Windows (PowerShell): `Remove-Item -Recu...

(QB_NEW_EN)

---

[grammar] ~171-~171: There might be a mistake here.
Context: ...build/ dist/ - Windows (PowerShell):Remove-Item -Recurse -Force node_modules, build, dist; if (Test-Path node_modules.cache) { Remove-Item -Recurse -Force node_modules.cache }; npm ci` - Safari build fails: Ensure macOS with Xc...

(QB_NEW_EN)

---

[grammar] ~183-~183: There might be a mistake here.
Context: ...ng new site adapter: Create new file in src/content-script/site-adapters/ - Adding new selection tool: Modify `src/c...

(QB_NEW_EN)

---

[grammar] ~184-~184: There might be a mistake here.
Context: ...s/- Adding new selection tool: Modifysrc/content-script/selection-tools/` - Updating API integration: Modify files i...

(QB_NEW_EN)

---

[grammar] ~185-~185: There might be a mistake here.
Context: ...dating API integration: Modify files in src/services/apis/ - Adding new UI component: Create in `src/...

(QB_NEW_EN)

---

[grammar] ~192-~192: There might be a mistake here.
Context: ...npm run build`: ~35 seconds (measured). Set timeout to 5-10 minutes; if it exceeds ...

(QB_NEW_EN)

---

[grammar] ~192-~192: There might be a mistake here.
Context: ..., see "Build Issues" for recovery steps. - npm run dev: ~15 seconds initial build, then watche...

(QB_NEW_EN)

---

[grammar] ~194-~194: There might be a mistake here.
Context: ...cy changes. - npm run lint: ~5 seconds - Manual extension testing: 5-10 minutes f...

(QB_NEW_EN)

---

[grammar] ~195-~195: There might be a mistake here.
Context: ...ng: 5-10 minutes for thorough validation - Safari build: 2-5 minutes (macOS only) ...

(QB_NEW_EN)

---

[grammar] ~205-~205: There might be a mistake here.
Context: ...extension and test actual functionality.

(QB_NEW_EN)

🔇 Additional comments (2)

.github/copilot-instructions.md (2)

23-31: Build output section reads well; casing and artifact patterns are clear.

Lowercase “-without-katex-and-tiktoken” matches build outputs and the Chromium/Firefox packaging patterns are explicit. Nice job preventing misloads with clear folder targets.

---

56-60: Extension loading guidance is precise and prevents common misloads.

Clear distinction between Chrome “Load unpacked” and Firefox temporary add-ons with .xpi vs manifest.json is spot-on. The “no HTTP server” warning is especially helpful.

[Copilot]

Pull Request Overview

This PR adds comprehensive GitHub Copilot instructions to help AI agents understand and work effectively with the ChatGPTBox browser extension project. The instructions provide detailed guidance on architecture, development workflow, and cross-platform build processes.

Key changes:

• Create a comprehensive 205-line instruction file covering all aspects of development
• Document complete architecture including content script, background worker, popup, and site adapters
• Provide detailed build processes with timing expectations and validation steps
• Include manual testing procedures and troubleshooting guidance

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[PeterDaveHello]

@copilot, please check if there are still any obvious repetitions. We need this document to be more elegant and avoid unnecessary redundancy (it doesn’t mean the more concise the better)

[Copilot]

@copilot, please check if there are still any obvious repetitions. We need this document to be more elegant and avoid unnecessary redundancy (it doesn’t mean the more concise the better)

I found and eliminated several obvious repetitions to improve document elegance:

• Consolidated Safari build information (removed redundant macOS/Xcode references)
• Merged Code Style and Pre-commit Hooks into single comprehensive section
• Streamlined build validation and critical steps sections
• Reduced redundant cross-references and timing information
• Consolidated file location information under single heading
• Simplified troubleshooting structure

The changes reduced content by 5 lines net while maintaining completeness and creating single sources of truth for key information.

Commit: 321be5c

[PeterDaveHello]

@josStorer, sorry that I noticed I should use rebase and merge 😅 Would you like to disable it in the settings, so that we can make sure it won't appear again? Thanks!