42 Get rid of commitizen? #44
Conversation
WalkthroughRemoves Husky pre-commit hook and related commit tooling/config, updates README to drop commit instructions, adjusts git-cliff config, adds a repository-wide review/config file, and enriches one event page’s front matter and image path encoding. Changes
Tip 🔌 Remote MCP (Model Context Protocol) integration is now available!Pro plan users can now connect to remote MCP servers from the Integrations page. Connect with popular remote MCPs such as Notion and Linear to add more context to your reviews and chats. ✨ Finishing Touches🧪 Generate unit tests
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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (2)
content/events/20250430-open-access-workshop/index.qmd (2)
8-16: Userolesinstead ofrolein Quarto front matterQuarto’s front-matter schema expects an array field
roles(plural) to describe each author’s contributions; using the singularrolewill not be recognized and may trigger metadata warnings . You can express one or more contributions as a comma-separated string or YAML array. Additionally, while plain-text affiliations work, you can unlock richer rendering by using affiliation objects withid,name, andurl.Key location to update:
- File:
content/events/20250430-open-access-workshop/index.qmd
Lines: 8–16 (the author metadata block)Suggested minimal change:
author: - name: Moritz Mähr orcid: 0000-0002-1367-1618 email: [email protected] affiliations: - University of Bern - University of Basel - role: author + roles: ["author"]Optional enhancement for affiliations:
affiliations: - id: unibe name: University of Bern url: https://www.unibe.ch - id: unibas name: University of Basel url: https://www.unibas.ch
33-33: Use an ASCII-only slug for the image filename
To avoid potential broken links on different OSes, static hosts, or during URL rewriting, rename the asset to a simple ASCII slug and update its reference inindex.qmd.• Current file:
content/events/20250430-open-access-workshop/DALL·E 2025-03-11 08.43.36 - An engraving-style copperplate illustration of Johannes Gutenberg operating an old printing press, but instead of traditional books, he is printing an.webp
• Suggested new filename (placed in the same folder):
gutenberg-open-access.webp
• Update the Markdown reference at line 33 incontent/events/20250430-open-access-workshop/index.qmd:-{fig-alt="Engraving-style illustration of Johannes Gutenberg operating a historical printing press labeled with his name. Instead of printing traditional books, the press is producing pages with the words \"OPEN ACCESS.\" A modern computer screen and keyboard sit nearby, also displaying the phrase \"OPEN ACCESS\" alongside a stylized \"Q\" logo. A large book on the table bears the same text and Gutenberg’s name, blending elements of early print history with digital open access themes."} +{fig-alt="Engraving-style illustration of Johannes Gutenberg operating a historical printing press labeled with his name. Instead of printing traditional books, the press is producing pages with the words \"OPEN ACCESS.\" A modern computer screen and keyboard sit nearby, also displaying the phrase \"OPEN ACCESS\" alongside a stylized \"Q\" logo. A large book on the table bears the same text and Gutenberg’s name, blending elements of early print history with digital open access themes."}
📜 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.
⛔ Files ignored due to path filters (1)
package-lock.jsonis excluded by!**/package-lock.json
📒 Files selected for processing (4)
.husky/pre-commit(0 hunks)README.md(0 hunks)content/events/20250430-open-access-workshop/index.qmd(2 hunks)package.json(1 hunks)
💤 Files with no reviewable changes (2)
- .husky/pre-commit
- README.md
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Build, Optimize, and Upload Artifacts
🔇 Additional comments (1)
package.json (1)
16-16: Retaining ESM"type": "module"after tool removal is fineKeeping ESM has no negative impact on the CLI-only scripts (
prettier,git-cliff) and aligns with modern Node setups. No action needed here.
| "path": "./node_modules/cz-conventional-changelog" | ||
| } | ||
| } | ||
| "type": "module" |
There was a problem hiding this comment.
💡 Verification agent
🧩 Analysis chain
After removing Husky/Commitizen, ensure there are no dangling references and that changelog generation still works without conventional commits
Now that commit conventions aren’t enforced locally, git-cliff may produce sparse notes if its template expects Conventional Commits. Also verify that no docs or scripts still reference Husky/Commitizen.
[action items]
- Search repo for leftovers and adjust
cliff.tomlif it relies on Conventional Commit types. - Consider moving enforcement to CI (e.g., run
npm run checkand optionally lint commit messages on PRs) instead of local hooks.
If you still want structured changelogs without enforcing local hooks, prefer:
- Using PR titles/labels as the source of truth (git-cliff supports GitHub metadata).
- A lightweight GitHub Action to run
npm run checkand generate a draft changelog on pull_request for visibility.
🏁 Script executed:
#!/bin/bash
# 1) Find any lingering Husky/Commitizen references (scripts, config, docs)
rg -nP -S '(husky|commitizen|cz-conventional-changelog|\bnpm run commit\b|\bcz\b)'
# 2) Sanity check cliff config for conventional preset usage
rg -nP -S '(conventional|preset|conventional-changelog|commit_types)' cliff.toml
# 3) Ensure no Husky hooks remain
fd --hidden --strip-cwd-prefix '^\.husky$' -t d -E .git
# 4) CI follow-up: Do we already run prettier check on PRs?
fd -a '.github/workflows/*.yml' | xargs -r rg -nP '\bnpm run check\b'Length of output: 482
Update git-cliff configuration to remove Conventional Commits enforcement
Verified there are no remaining Husky or Commitizen references in the repo. However, your cliff.toml still requires Conventional Commits, which will produce sparse or empty changelogs now that local hooks are gone:
• cliff.toml (around lines 35–38):
- # parse the commits based on https://www.conventionalcommits.org
- conventional_commits = true
- # filter out the commits that are not conventional
- filter_unconventional = trueAction items:
– Remove or set both conventional_commits and filter_unconventional to false, or adjust your template so that non-conventional commits are included.
– If you still want structured commit messages, add a CI check (for example, run npm run check or a commit-lint GitHub Action) in .github/workflows/*.yml to enforce conventions centrally.
– Confirm changelog generation now captures all relevant commits without local hooks.
Committable suggestion skipped: line range outside the PR's diff.
🤖 Prompt for AI Agents
In package.json around lines 16 to 16, update your git-cliff configuration
(cliff.toml, ~lines 35–38) to stop enforcing Conventional Commits: open
cliff.toml and either remove the conventional_commits and filter_unconventional
settings or set both to false, or alternatively adjust the cliff template to
include non-conventional commits; if you still want enforcement, add a CI check
(e.g., run npm run check or a commit-lint Action) in .github/workflows/*.yml so
conventions are enforced centrally and changelog generation captures all
relevant commits.
|
@coderabbitai configuration |
CodeRabbit configurationlanguage: en-US
tone_instructions: ''
early_access: false
enable_free_tier: true
reviews:
profile: chill
request_changes_workflow: false
high_level_summary: true
high_level_summary_placeholder: '@coderabbitai summary'
high_level_summary_in_walkthrough: false
auto_title_placeholder: '@coderabbitai'
auto_title_instructions: ''
review_status: true
commit_status: true
fail_commit_status: false
collapse_walkthrough: false
changed_files_summary: true
sequence_diagrams: true
estimate_code_review_effort: true
assess_linked_issues: true
related_issues: true
related_prs: true
suggested_labels: true
auto_apply_labels: false
suggested_reviewers: true
auto_assign_reviewers: false
poem: true
labeling_instructions: []
path_filters: []
path_instructions: []
abort_on_close: true
disable_cache: false
auto_review:
enabled: true
auto_incremental_review: true
ignore_title_keywords: []
labels: []
drafts: false
base_branches: []
ignore_usernames: []
finishing_touches:
docstrings:
enabled: true
unit_tests:
enabled: true
pre_merge_checks:
docstrings:
mode: warning
threshold: 80
title:
mode: warning
requirements: ''
description:
mode: warning
issue_assessment:
mode: warning
tools:
ast-grep:
rule_dirs: []
util_dirs: []
essential_rules: true
packages: []
shellcheck:
enabled: true
ruff:
enabled: true
markdownlint:
enabled: true
github-checks:
enabled: true
timeout_ms: 90000
languagetool:
enabled: true
enabled_rules: []
disabled_rules: []
enabled_categories: []
disabled_categories: []
enabled_only: false
level: default
biome:
enabled: true
hadolint:
enabled: true
swiftlint:
enabled: true
phpstan:
enabled: true
level: default
phpmd:
enabled: true
phpcs:
enabled: true
golangci-lint:
enabled: true
yamllint:
enabled: true
gitleaks:
enabled: true
checkov:
enabled: true
detekt:
enabled: true
eslint:
enabled: true
flake8:
enabled: true
rubocop:
enabled: true
buf:
enabled: true
regal:
enabled: true
actionlint:
enabled: true
pmd:
enabled: true
cppcheck:
enabled: true
semgrep:
enabled: true
circleci:
enabled: true
clippy:
enabled: true
sqlfluff:
enabled: true
prismaLint:
enabled: true
pylint:
enabled: true
oxc:
enabled: true
shopifyThemeCheck:
enabled: true
luacheck:
enabled: true
brakeman:
enabled: true
dotenvLint:
enabled: true
htmlhint:
enabled: true
checkmake:
enabled: true
osvScanner:
enabled: true
chat:
art: true
auto_reply: true
integrations:
jira:
usage: auto
linear:
usage: auto
knowledge_base:
opt_out: false
web_search:
enabled: true
code_guidelines:
enabled: true
filePatterns: []
learnings:
scope: auto
issues:
scope: auto
jira:
usage: auto
project_keys: []
linear:
usage: auto
team_keys: []
pull_requests:
scope: auto
mcp:
usage: auto
disabled_servers: []
code_generation:
docstrings:
language: en-US
path_instructions: []
unit_tests:
path_instructions: []
|
|
I also added a @coderabbitai config file to shut the bunny up. Hope this works well. |
|
Tip For best results, initiate chat on the files or code changes. 🧩 Analysis chain🏁 Script executed: Length of output: 163 🏁 Script executed: Length of output: 3576 @flicksolutions Good configuration! Your Reduces noise by disabling:
Keeps the valuable stuff:
This strikes a nice balance - you'll still get meaningful code review feedback without the extra fluff. The "bunny" should be much quieter now while still being helpful! 🐰🤫 |
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (8)
.coderabbit.yaml (8)
5-12: Keep the “Chill” profile; consider enabling lightweight status visibilityThe review profile and summary toggles look sensible for this repo. However, with commitizen/husky removed, having a visible status comment can help collaborators discover what the bot checked.
- review_status: false + review_status: true
29-30: Add path filters to focus reviews and skip build/artifact directoriesTighten scope to speed up reviews and avoid scanning generated content, large binaries, and caches common in static-site repos (Quarto/GitHub Pages).
- path_filters: [] + path_filters: + # Include typical source/content locations first + - "content/**" + - ".github/**" + - "scripts/**" + # Exclude generated and vendor paths + - "!_site/**" # Quarto/GitHub Pages output + - "!public/**" + - "!dist/**" + - "!build/**" + - "!node_modules/**" + - "!.quarto/**" + - "!.cache/**" + - "!.git/**" + - "!**/*.png" + - "!**/*.jpg" + - "!**/*.jpeg" + - "!**/*.gif" + - "!**/*.pdf"
33-40: Consider reviewing draft PRs for earlier feedbackWith pre-commit hooks gone, early feedback on drafts can be valuable.
- drafts: false + drafts: true
41-45: Disable “finishing touches” generators to avoid noisy, non-applicable suggestionsFor a static site, auto-generating docstrings/unit tests is mostly irrelevant and can distract reviewers.
finishing_touches: docstrings: - enabled: true + enabled: false unit_tests: - enabled: true + enabled: false
46-56: Turn off docstring coverage pre-merge checkDocstring coverage is not applicable here and may surface confusing warnings.
pre_merge_checks: docstrings: - mode: warning - threshold: 80 + mode: off + # threshold retained for reference, not used when mode=off + threshold: 80
69-71: Adjust GitHub Checks timeout based on enabled toolsIf you keep many linters enabled, 90s can be tight. Either prune tools (recommended) or increase the timeout.
- timeout_ms: 90000 + timeout_ms: 180000
160-161: Either point code guidelines to an existing doc or disable to avoid confusionIf you don’t maintain any coding guideline docs in this repo, disable this to prevent the bot from looking for non-existent standards. Otherwise, reference the actual file(s).
Option A — disable:
code_guidelines: - enabled: true - filePatterns: [] + enabled: false + filePatterns: []Option B — keep enabled and add patterns (example if you later add guidelines):
code_guidelines: enabled: true - filePatterns: [] + filePatterns: + - ".github/instructions/*.instructions.md" + - ".github/CODING_GUIDELINES.md"
178-182: Disable code generation for docstrings/unit tests in a content repoPrevents irrelevant suggestions and keeps PR noise down.
code_generation: docstrings: - language: en-US - path_instructions: [] + language: en-US + path_instructions: [] + # Consider disabling entirely for this repo: + # enabled: false unit_tests: - path_instructions: [] + path_instructions: [] + # enabled: false
📜 Review details
Configuration used: Path: .coderabbit.yaml
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.
📒 Files selected for processing (1)
.coderabbit.yaml(1 hunks)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Build, Optimize, and Upload Artifacts
🔇 Additional comments (2)
.coderabbit.yaml (2)
147-155: Chat settings look goodArt disabled and auto-replies enabled suit this repository’s workflow.
57-146: It looks like we only saw counts for two of the expected 22 language patterns—without the full breakdown, we can’t confidently prune the toolset. Could you rerun the script and share the complete output for all patterns (python, javascript, go, ruby, kotlin, swift, php, java, cpp, rust, proto, rego, dockerfile, sql, prisma, lua, html, yaml, markdown, make, env, github_workflows)? Thanks!
I ended up removing husky aswell since the pre-commit hook takes forever and fails anyways. Signifying that people overruled the hook since the beginning.
#42
Summary by CodeRabbit
Documentation
Chores