CalvinBackup/donutbrowser
1
0
Fork 0
mirror of https://github.com/zhom/donutbrowser.git synced 2026-04-22 03:46:43 +02:00
Code Issues Packages Projects Releases Wiki Activity

chore: cleanup triage bot

Browse Source
This commit is contained in:
zhom
2026-03-09 14:41:39 +04:00
parent 12bc4ed08f
commit 3d1471d41d
3 changed files with 36 additions and 347 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/prompts/issue-validation.prompt.yml
-76
View File
@@ -1,76 +0,0 @@
messages:
- role: system
content: |-
You are an issue validation assistant for Donut Browser, an anti-detect browser.
Analyze the provided issue content and determine if it contains sufficient information based on these requirements:
For Bug Reports, the issue should include:
1. Clear description of the problem
2. Steps to reproduce the issue (numbered list preferred)
3. Expected vs actual behavior
4. Environment information (OS, browser version, etc.)
5. Error messages, stack traces, or screenshots if applicable
For Feature Requests, the issue should include:
1. Clear description of the requested feature
2. Use case or problem it solves
3. Proposed solution or how it should work
4. Priority level or importance
General Requirements for all issues:
1. Descriptive title
2. Sufficient detail to understand and act upon
3. Professional tone and clear communication
Constraints:
- Maximum 3 items in missing_info array
- Maximum 3 items in suggestions array
- Each array item must be under 80 characters
- overall_assessment must be under 100 characters
- role: user
content: |-
## Issue Content to Analyze:
**Title:** {{issue_title}}
**Body:**
{{issue_body}}
**Labels:** {{issue_labels}}
model: openai/gpt-4.1
responseFormat: json_schema
jsonSchema: |-
{
"name": "issue_validation",
"strict": true,
"schema": {
"type": "object",
"properties": {
"is_valid": {
"type": "boolean",
"description": "Whether the issue contains sufficient information"
},
"issue_type": {
"type": "string",
"enum": ["bug_report", "feature_request", "other"]
},
"missing_info": {
"type": "array",
"items": { "type": "string" },
"description": "Missing information items (max 3, each under 80 characters)"
},
"suggestions": {
"type": "array",
"items": { "type": "string" },
"description": "Suggestions for improvement (max 3, each under 80 characters)"
},
"overall_assessment": {
"type": "string",
"description": "One sentence assessment under 100 characters"
}
},
"required": ["is_valid", "issue_type", "missing_info", "suggestions", "overall_assessment"],
"additionalProperties": false
}
}
.github/prompts/pr-review.prompt.yml
-67
View File
@@ -1,67 +0,0 @@
messages:
- role: system
content: |-
You are a code review assistant for Donut Browser, an open-source anti-detect browser built with Tauri, Next.js, and Rust.
Review the provided pull request and provide constructive feedback. Focus on:
1. Code quality and best practices
2. Potential bugs or issues
3. Security concerns (especially important for an anti-detect browser)
4. Performance implications
5. Consistency with the project's patterns
Constraints:
- Maximum 4 items in feedback array
- Maximum 3 items in suggestions array
- Maximum 2 items in security_notes array
- Each array item must be under 150 characters
- summary must be under 200 characters
- Be constructive and helpful, not harsh
- role: user
content: |-
## Pull Request to Review:
**Title:** {{pr_title}}
**Description:**
{{pr_body}}
**Diff:**
{{pr_diff}}
model: openai/gpt-4.1
responseFormat: json_schema
jsonSchema: |-
{
"name": "pr_review",
"strict": true,
"schema": {
"type": "object",
"properties": {
"summary": {
"type": "string",
"description": "Brief 1-2 sentence summary under 200 characters"
},
"quality_score": {
"type": "string",
"enum": ["good", "needs_work", "critical_issues"]
},
"feedback": {
"type": "array",
"items": { "type": "string" },
"description": "Feedback points (max 4, each under 150 characters)"
},
"suggestions": {
"type": "array",
"items": { "type": "string" },
"description": "Suggestions (max 3, each under 150 characters)"
},
"security_notes": {
"type": "array",
"items": { "type": "string" },
"description": "Security notes if any (max 2, each under 150 characters)"
}
},
"required": ["summary", "quality_score", "feedback", "suggestions", "security_notes"],
"additionalProperties": false
}
}
.github/workflows/issue-validation.yml
+36 -204
View File
@@ -18,31 +18,13 @@ permissions:
id-token: write
jobs:
validate-issue:
analyze-issue:
if: github.event_name == 'issues'
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 #v6.0.1
- name: Save issue body to file
env:
ISSUE_BODY: ${{ github.event.issue.body }}
run: printf '%s' "${ISSUE_BODY:-}" > issue_body.txt
- name: Validate issue with AI
id: validate
uses: actions/ai-inference@e09e65981758de8b2fdab13c2bfb7c7d5493b0b6 # v2.0.7
with:
prompt-file: .github/prompts/issue-validation.prompt.yml
input: |
issue_title: ${{ github.event.issue.title }}
issue_labels: ${{ join(github.event.issue.labels.*.name, ', ') }}
file_input: |
issue_body: ./issue_body.txt
max-tokens: 1024
- name: Check if first-time contributor
id: check-first-time
env:
@@ -59,101 +41,31 @@ jobs:
echo "is_first_time=false" >> $GITHUB_OUTPUT
fi
- name: Parse validation result and take action
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
RESPONSE_FILE: ${{ steps.validate.outputs.response-file }}
run: |
if [ -n "$RESPONSE_FILE" ] && [ -f "$RESPONSE_FILE" ]; then
RAW_OUTPUT=$(cat "$RESPONSE_FILE")
else
echo "::error::Response file not found: $RESPONSE_FILE"
exit 1
fi
JSON_RESULT=$(printf "%s" "$RAW_OUTPUT" | sed -n '/```json/,/```/p' | sed '1d;$d')
if [ -z "$JSON_RESULT" ]; then
JSON_RESULT="$RAW_OUTPUT"
fi
if ! echo "$JSON_RESULT" | jq empty 2>/dev/null; then
echo "::warning::Invalid JSON in AI response, using fallback"
JSON_RESULT='{"is_valid":true,"issue_type":"other","missing_info":[],"suggestions":[],"overall_assessment":"Unable to validate automatically"}'
fi
IS_VALID=$(echo "$JSON_RESULT" | jq -r '.is_valid // false')
ISSUE_TYPE=$(echo "$JSON_RESULT" | jq -r '.issue_type // "other"')
MISSING_INFO=$(echo "$JSON_RESULT" | jq -r '.missing_info[]? // empty' | sed 's/^/- /')
SUGGESTIONS=$(echo "$JSON_RESULT" | jq -r '.suggestions[]? // empty' | sed 's/^/- /')
ASSESSMENT=$(echo "$JSON_RESULT" | jq -r '.overall_assessment // "No assessment provided"')
IS_FIRST_TIME="${{ steps.check-first-time.outputs.is_first_time }}"
GREETING_SECTION=""
if [ "$IS_FIRST_TIME" = "true" ]; then
GREETING_SECTION="## 👋 Welcome!\n\nThank you for your first issue ❤️ If this is a feature request, please make sure it is clear what you want, why you want it, and how important it is to you. If you posted a bug report, please make sure it includes as much detail as possible.\n\n---\n\n"
fi
if [ "$IS_VALID" = "false" ]; then
{
printf "%b" "$GREETING_SECTION"
printf "## 🤖 Issue Validation\n\n"
printf "Thank you for submitting this issue! However, it appears that some required information might be missing to help the maintainers better understand and address your concern.\n\n"
printf "**Issue Type Detected:** \`%s\`\n\n" "$ISSUE_TYPE"
printf "**Assessment:** %s\n\n" "$ASSESSMENT"
printf "### 📋 Missing Information:\n%s\n\n" "$MISSING_INFO"
printf "### 💡 Suggestions for Improvement:\n%s\n\n" "$SUGGESTIONS"
printf "### 📝 How to Provide Additional Information:\n\n"
printf "Please edit your original issue description to include the missing information. Here are the issue templates for reference:\n\n"
printf -- "- **Bug Report Template:** [View Template](.github/ISSUE_TEMPLATE/01-bug-report.md)\n"
printf -- "- **Feature Request Template:** [View Template](.github/ISSUE_TEMPLATE/02-feature-request.md)\n\n"
printf "### 🔧 Quick Tips:\n"
printf -- "- For **bug reports**: Include step-by-step reproduction instructions, your environment details, and any error messages\n"
printf -- "- For **feature requests**: Describe the use case, expected behavior, and why this feature would be valuable\n"
printf -- "- Add **screenshots** or **logs** when applicable\n\n"
printf "Once you have updated the issue with the missing information, feel free to remove this comment or reply to let the maintainers know the updates have been made.\n\n"
printf -- "---\n*This validation was performed automatically to ensure all the information needed to help effectively is provided.*\n"
} > comment.md
gh issue comment ${{ github.event.issue.number }} --body-file comment.md
gh issue edit ${{ github.event.issue.number }} --add-label "needs-info"
else
SUGGESTIONS_SECTION=""
if [ -n "$SUGGESTIONS" ]; then
SUGGESTIONS_SECTION=$(printf "### 💡 Suggestions:\n%s\n\n" "$SUGGESTIONS")
fi
{
printf "%b" "$GREETING_SECTION"
printf "## 🤖 Issue Validation\n\n"
printf "**Issue Type Detected:** \`%s\`\n\n" "$ISSUE_TYPE"
printf "**Assessment:** %s\n\n" "$ASSESSMENT"
printf "%b" "$SUGGESTIONS_SECTION"
printf -- "---\n*This validation was performed automatically to help triage issues.*\n"
} > comment.md
gh issue comment ${{ github.event.issue.number }} --body-file comment.md
case "$ISSUE_TYPE" in
"bug_report")
gh issue edit ${{ github.event.issue.number }} --add-label "bug"
;;
"feature_request")
gh issue edit ${{ github.event.issue.number }} --add-label "enhancement"
;;
esac
fi
- name: Run opencode analysis
- name: Analyze issue
uses: anomalyco/opencode/github@6c7d968c4423a0cd6c85099c9377a6066313fa0a #v1.2.20
env:
ZHIPU_API_KEY: ${{ secrets.ZHIPU_API_KEY }}
with:
model: zai-coding-plan/glm-4.7
prompt: |
You are a triage bot for Donut Browser (open-source anti-detect browser, Tauri + Next.js + Rust).
- name: Cleanup
run: rm -f issue_body.txt comment.md
${{ steps.check-first-time.outputs.is_first_time == 'true' && 'This is a first-time contributor. Start your comment with: "Thanks for opening your first issue!"' || '' }}
handle-pr:
Analyze this issue and post a single concise comment. Format:
1. One sentence acknowledging what the user wants.
2. A short **Action items** list — what specific info is missing or what the user should do next. Only include items that are actually missing. If the issue is complete, say so and skip this section.
3. Label the issue: add "bug" label for bug reports, "enhancement" label for feature requests.
Rules:
- Be brief. No filler, no generic tips, no templates.
- If it's a bug report, check for: reproduction steps, OS/version, error messages. Only ask for what's actually missing.
- If it's a feature request, check for: clear description of desired behavior, use case. Only ask for what's actually missing.
- If the issue already has everything needed, just acknowledge it and label it.
- Never exceed 6 items total.
analyze-pr:
if: github.event_name == 'pull_request' && github.actor != 'dependabot[bot]'
runs-on: ubuntu-latest
steps:
@@ -178,109 +90,29 @@ jobs:
echo "is_first_time=false" >> $GITHUB_OUTPUT
fi
- name: Get PR diff
id: get-diff
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
gh pr diff ${{ github.event.pull_request.number }} > pr_diff.txt
head -c 10000 pr_diff.txt > pr_diff_truncated.txt
- name: Save PR body to file
env:
PR_BODY: ${{ github.event.pull_request.body }}
run: printf '%s' "${PR_BODY:-No description provided}" > pr_body.txt
- name: Analyze PR with AI
id: analyze
uses: actions/ai-inference@e09e65981758de8b2fdab13c2bfb7c7d5493b0b6 # v2.0.7
with:
prompt-file: .github/prompts/pr-review.prompt.yml
input: |
pr_title: ${{ github.event.pull_request.title }}
file_input: |
pr_body: ./pr_body.txt
pr_diff: ./pr_diff_truncated.txt
max-tokens: 1024
- name: Post PR feedback comment
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
RESPONSE_FILE: ${{ steps.analyze.outputs.response-file }}
run: |
if [ -n "$RESPONSE_FILE" ] && [ -f "$RESPONSE_FILE" ]; then
RAW_OUTPUT=$(cat "$RESPONSE_FILE")
else
echo "::error::Response file not found"
exit 1
fi
JSON_RESULT=$(printf "%s" "$RAW_OUTPUT" | sed -n '/```json/,/```/p' | sed '1d;$d')
if [ -z "$JSON_RESULT" ]; then
JSON_RESULT="$RAW_OUTPUT"
fi
if ! echo "$JSON_RESULT" | jq empty 2>/dev/null; then
echo "::warning::Invalid JSON in AI response, using fallback"
JSON_RESULT='{"summary":"Unable to analyze automatically","quality_score":"good","feedback":[],"suggestions":[],"security_notes":[]}'
fi
SUMMARY=$(echo "$JSON_RESULT" | jq -r '.summary // "No summary"')
QUALITY=$(echo "$JSON_RESULT" | jq -r '.quality_score // "good"')
FEEDBACK=$(echo "$JSON_RESULT" | jq -r '.feedback[]? // empty' | sed 's/^/- /')
SUGGESTIONS=$(echo "$JSON_RESULT" | jq -r '.suggestions[]? // empty' | sed 's/^/- /')
SECURITY=$(echo "$JSON_RESULT" | jq -r '.security_notes[]? // empty' | sed 's/^/- ⚠️ /')
IS_FIRST_TIME="${{ steps.check-first-time.outputs.is_first_time }}"
{
if [ "$IS_FIRST_TIME" = "true" ]; then
printf "## 👋 Welcome!\n\n"
printf "Thank you for your first contribution ❤️ A human will review your PR shortly. Make sure that the pipelines are green, so that the PR is considered ready for review and could be merged.\n\n"
printf -- "---\n\n"
fi
printf "## 🤖 PR Review\n\n"
printf "**Summary:** %s\n\n" "$SUMMARY"
case "$QUALITY" in
"good")
printf "**Status:** ✅ Looking good!\n\n"
;;
"needs_work")
printf "**Status:** 🔧 Some improvements suggested\n\n"
;;
"critical_issues")
printf "**Status:** ⚠️ Please address the issues below\n\n"
;;
esac
if [ -n "$FEEDBACK" ]; then
printf "### 📝 Feedback:\n%s\n\n" "$FEEDBACK"
fi
if [ -n "$SUGGESTIONS" ]; then
printf "### 💡 Suggestions:\n%s\n\n" "$SUGGESTIONS"
fi
if [ -n "$SECURITY" ]; then
printf "### 🔒 Security Notes:\n%s\n\n" "$SECURITY"
fi
printf -- "---\n*This review was performed automatically. A human maintainer will also review your changes.*\n"
} > comment.md
gh pr comment ${{ github.event.pull_request.number }} --body-file comment.md
- name: Run opencode analysis
- name: Analyze PR
uses: anomalyco/opencode/github@6c7d968c4423a0cd6c85099c9377a6066313fa0a #v1.2.20
env:
ZHIPU_API_KEY: ${{ secrets.ZHIPU_API_KEY }}
with:
model: zai-coding-plan/glm-4.7
prompt: |
You are a review bot for Donut Browser (open-source anti-detect browser, Tauri + Next.js + Rust).
- name: Cleanup
run: rm -f pr_diff.txt pr_diff_truncated.txt pr_body.txt comment.md
${{ steps.check-first-time.outputs.is_first_time == 'true' && 'This is a first-time contributor. Start your comment with: "Thanks for your first PR!"' || '' }}
Review this PR and post a single concise comment. Format:
1. One sentence summarizing what this PR does.
2. **Action items** — only list things that actually need to be fixed or addressed. If the PR looks good, say so and skip this section.
Rules:
- Be brief. No filler, no praise padding.
- Focus on: bugs, security issues, missing edge cases, breaking changes.
- If the PR touches UI text or adds new strings, remind to update translation files in src/i18n/locales/.
- If the PR modifies Tauri commands, remind to check the unused-commands test.
- Do not nitpick style or formatting — the project has automated linting.
- Never exceed 8 lines total.
opencode-command:
if: |