You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/issue-triage.md
+9-9Lines changed: 9 additions & 9 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,7 +4,7 @@
4
4
5
5
**Automatically triage issues when they are created or reopened**
6
6
7
-
The [Issue Triage workflow](../workflows/issue-triage.md?plain=1) runs when issues are created or reopened to analyze content, check related items, categorize, add labels, and post triage comments.
7
+
The [Issue Triage workflow](../workflows/issue-triage.md?plain=1) runs when issues are created or reopened to analyze content, check related items, set issue type, add labels, detect duplicates, and post structured triage reports.
8
8
9
9
## Installation
10
10
@@ -22,11 +22,11 @@ This walks you through adding the workflow to your repository.
22
22
23
23
```mermaid
24
24
graph LR
25
-
A[Issue Created/Reopened] --> B[Analyze Content]
26
-
B --> C[Check Related Items]
27
-
C --> D[Categorize Issue]
28
-
D --> E[Add Labels]
29
-
E --> F[Post Triage Comment]
25
+
A[Issue Created/Reopened] --> B[Gather Context]
26
+
B --> C[Spam & Quality Check]
27
+
C --> D[Triage: Type, Labels]
28
+
D --> E[Detect Duplicates]
29
+
E --> F[Post Triage Report]
30
30
```
31
31
32
32
The workflow may search for relevant documentation, error messages, or similar issues online to assist with triage.
@@ -41,8 +41,8 @@ This workflow requires no configuration and works out of the box. You can custom
41
41
42
42
After editing run `gh aw compile` to update the workflow and commit all changes to the default branch.
43
43
44
-
### Human in the Loop
44
+
### Human in the loop
45
45
46
-
- Review triage comments for accuracy
47
-
- Validate label assignments and priority assessments
from similar issues, and provides analysis notes including debugging strategies,
6
-
reproduction steps, and resource links. Helps maintainers quickly understand and
7
-
prioritize incoming issues.
4
+
Analyzes issue content, detects spam and incomplete reports, selects appropriate
5
+
labels, sets issue type, detects duplicates, and provides structured
6
+
triage reports with debugging strategies and resource links. Helps maintainers
7
+
quickly understand and prioritize incoming issues.
8
8
9
9
on:
10
10
issues:
@@ -23,11 +23,17 @@ safe-outputs:
23
23
add-labels:
24
24
max: 5
25
25
add-comment:
26
+
set-issue-type:
27
+
max: 1
28
+
close-issue:
29
+
target: "triggering"
30
+
state-reason: "not_planned"
31
+
max: 1
26
32
27
33
tools:
28
34
web-fetch:
29
35
github:
30
-
toolsets: [issues]
36
+
toolsets: [issues, labels]
31
37
min-integrity: none # This workflow is allowed to examine and comment on any issues
32
38
33
39
timeout-minutes: 10
@@ -37,54 +43,108 @@ timeout-minutes: 10
37
43
38
44
<!-- Note - this file can be customized to your needs. Replace this section directly, or add further instructions here. After editing run 'gh aw compile' -->
39
45
40
-
You're a triage assistant for GitHub issues. Your task is to analyze issue #${{ github.event.issue.number }}and perform some initial triage tasks related to that issue.
46
+
You are a triage assistant for GitHub issues. Your task is to analyze issue #${{ github.event.issue.number }}, categorize it with the right metadata, and help maintainers act quickly. Your triage comments are written for maintainers reviewing the triage, not for the issue author.
41
47
42
-
1. Select appropriate labels for the issue from the provided list.
48
+
Do not make assumptions beyond what the issue content supports. Do not invent missing context.
43
49
44
-
2. Retrieve the issue content using the `get_issue` tool. If the issue is obviously spam, or generated by bot, or something else that is not an actual issue to be worked on, then add an issue comment to the issue with a one-sentence analysis and exit the workflow.
50
+
## Step 1: Gather context
45
51
46
-
3. Next, use the GitHub tools to gather additional context about the issue:
52
+
1. Retrieve the issue content using the `get_issue` tool.
53
+
2. Fetch any comments on the issue using the `get_issue_comments` tool.
54
+
3. Fetch the list of labels available in this repository using the `list_label` tool.
55
+
4. Search for similar issues using the `search_issues` tool.
47
56
48
-
- Fetch the list of labels available in this repository. Use 'gh label list' bash command to fetch the labels. This will give you the labels you can use for triaging issues.
49
-
- Fetch any comments on the issue using the `get_issue_comments` tool
50
-
- Find similar issues if needed using the `search_issues` tool
51
-
- List the issues to see other open issues in the repository using the `list_issues` tool
57
+
## Step 2: Spam and quality check
52
58
53
-
4. Analyze the issue content, considering:
59
+
**Spam and invalid issues:** If the issue is obviously spam, bot-generated, gibberish, or a test issue:
60
+
- Apply the `invalid` or `spam` label if one exists in the repository.
61
+
- Close the issue as "not planned" with a one-sentence reason (e.g., "Closing as spam."). No triage report, no assessment table.
62
+
- Do not apply any other metadata. **Stop here; do not continue to Steps 3 or 4.**
54
63
55
-
- The issue title and description
56
-
- The type of issue (bug report, feature request, question, etc.)
57
-
- Technical areas mentioned
58
-
- Severity or priority indicators
59
-
- User impact
60
-
- Components affected
64
+
**Incomplete issues:** If the issue lacks enough detail for meaningful triage, add a comment that politely asks the author to provide the missing information:
65
+
- For bugs: steps to reproduce, expected vs actual behavior, logs/errors, environment details.
66
+
- For other issue types: equivalent details that would make the report actionable.
67
+
- Apply a `needs-info` or `question` label if one exists in the repository.
61
68
62
-
5. Write notes, ideas, nudges, resource links, debugging strategies and/or reproduction steps for the team to consider relevant to the issue.
69
+
Be specific about what is missing and why it is needed. Do not attempt to apply type or other labels to incomplete issues.
63
70
64
-
6. Select appropriate labels from the available labels list provided above:
71
+
If the issue has sufficient detail, proceed to Step 3.
65
72
66
-
- Choose labels that accurately reflect the issue's nature
67
-
- Be specific but comprehensive
68
-
- Select priority labels if you can determine urgency (high-priority, med-priority, or low-priority)
69
-
- Consider platform labels (android, ios) if applicable
70
-
- Search for similar issues, and if you find similar issues consider using a "duplicate" label if appropriate. Only do so if the issue is a duplicate of another OPEN issue.
71
-
- Only select labels from the provided list above
72
-
- It's okay to not add any labels if none are clearly applicable
73
+
## Step 3: Triage
73
74
74
-
7. Apply the selected labels:
75
+
### 3a: Set issue type
75
76
76
-
- Use the `update_issue` tool to apply the labels to the issue
77
-
- DO NOT communicate directly with users
78
-
- If no labels are clearly applicable, do not apply any labels
77
+
- If the issue already has a type set, do not change it.
78
+
- Otherwise, determine the single best issue type (e.g., Bug, Feature, Task).
79
+
- If no type is clearly supported by the issue content, leave it unset and note what is missing.
79
80
80
-
8. If very confident, add an issue comment to the issue with your analysis:
81
-
- Start with "🎯 Agentic Issue Triage"
82
-
- Provide a brief summary of the issue
83
-
- Mention any relevant details that might help the team understand the issue better
84
-
- Include any debugging strategies or reproduction steps if applicable
85
-
- Suggest resources or links that might be helpful for resolving the issue or learning skills related to the issue or the particular area of the codebase affected by it
86
-
- Mention any nudges or ideas that could help the team in addressing the issue
87
-
- If you have possible reproduction steps, include them in the comment
88
-
- If you have any debugging strategies, include them in the comment
89
-
- If appropriate break the issue down to sub-tasks and write a checklist of things to do.
90
-
- Use collapsed-by-default sections in the GitHub markdown to keep the comment tidy. Collapse all sections except the short main summary at the top.
81
+
### 3b: Select labels
82
+
83
+
- Be cautious with labels; they can trigger automation in many repositories.
84
+
- Choose labels that accurately reflect the issue's nature from the repository's available labels.
85
+
- Select priority labels if you can determine urgency (high-priority, med-priority, low-priority).
86
+
- Consider platform labels (android, ios) if applicable.
87
+
- Do not apply labels that do not exist in the repository.
88
+
- If no labels are clearly applicable, do not apply any.
89
+
- It is better to under-label than to speculatively add labels.
90
+
91
+
### 3c: Detect duplicates and related issues
92
+
93
+
- Review the similar issues found in Step 1.
94
+
- Classify matches as:
95
+
-**Duplicate** (high confidence): the issue describes the same problem as an existing open issue. Include up to 3.
96
+
-**Related**: similar domain or adjacent problem, but not a duplicate. Include up to 3.
97
+
- If a high-confidence duplicate is found and the repository has a `duplicate` label, apply it.
98
+
- If no similar issues are found, state that explicitly in your report.
99
+
100
+
### 3e: Assess coding agent suitability
101
+
102
+
Assess whether the issue is suitable for automated coding agent assignment:
0 commit comments