Modernize workflows (#4668)

# External (non-OpenAI) Pull Request Requirements

Before opening this Pull Request, please read the dedicated
"Contributing" markdown file or your PR may be closed:
https://github.com/openai/codex/blob/main/docs/contributing.md

If your PR conforms to our contribution guidelines, replace this text
with a detailed and high quality description of your changes.
This commit is contained in:
pakrym-oai
2025-10-03 09:25:29 -07:00
committed by GitHub
parent 042d4d55d9
commit 3495a7dc37
2 changed files with 82 additions and 17 deletions

View File

@@ -45,10 +45,35 @@ jobs:
uses: openai/codex-action@main
with:
openai_api_key: ${{ secrets.CODEX_OPENAI_API_KEY }}
prompt_file: .github/prompts/issue-deduplicator.txt
require_repo_write: false
codex_version: 0.43.0-alpha.16
codex_args: -m gpt-5
model: gpt-5
prompt: |
You are an assistant that triages new GitHub issues by identifying potential duplicates.
You will receive the following JSON files located in the current working directory:
- `codex-current-issue.json`: JSON object describing the newly created issue (fields: number, title, body).
- `codex-existing-issues.json`: JSON array of recent issues (each element includes number, title, body, createdAt).
Instructions:
- Load both files as JSON and review their contents carefully. The codex-existing-issues.json file is large, ensure you explore all of it.
- Compare the current issue against the existing issues to find up to five that appear to describe the same underlying problem or request.
- When unsure, prefer returning fewer matches.
- Include at most five numbers.
output_schema: |
{
"type": "object",
"properties": {
"issues": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": ["issues"],
"additionalProperties": false
}
comment-on-issue:
name: Comment with potential duplicates
@@ -66,22 +91,25 @@ jobs:
with:
github-token: ${{ github.token }}
script: |
let numbers;
const raw = process.env.CODEX_OUTPUT ?? '';
let parsed;
try {
numbers = JSON.parse(process.env.CODEX_OUTPUT);
parsed = JSON.parse(raw);
} catch (error) {
core.info(`Codex output was not valid JSON. Raw output: ${raw}`);
core.info(`Parse error: ${error.message}`);
return;
}
if (numbers.length === 0) {
const issues = Array.isArray(parsed?.issues) ? parsed.issues : [];
if (issues.length === 0) {
core.info('Codex reported no potential duplicates.');
return;
}
const lines = [
'Potential duplicates detected:',
...numbers.map((value) => `- #${value}`),
...issues.map((value) => `- #${String(value)}`),
'',
'*Powered by [Codex Action](https://github.com/openai/codex-action)*'];

View File

@@ -13,11 +13,6 @@ jobs:
runs-on: ubuntu-latest
permissions:
contents: read
env:
ISSUE_NUMBER: ${{ github.event.issue.number }}
ISSUE_TITLE: ${{ github.event.issue.title }}
ISSUE_BODY: ${{ github.event.issue.body }}
REPO_FULL_NAME: ${{ github.repository }}
outputs:
codex_output: ${{ steps.codex.outputs.final_message }}
steps:
@@ -27,9 +22,51 @@ jobs:
uses: openai/codex-action@main
with:
openai_api_key: ${{ secrets.CODEX_OPENAI_API_KEY }}
prompt_file: .github/prompts/issue-labeler.txt
require_repo_write: false
codex_version: 0.43.0-alpha.16
prompt: |
You are an assistant that reviews GitHub issues for the repository.
Your job is to choose the most appropriate existing labels for the issue described later in this prompt.
Follow these rules:
- Only pick labels out of the list below.
- Prefer a small set of precise labels over many broad ones.
Labels to apply:
1. bug — Reproducible defects in Codex products (CLI, VS Code extension, web, auth).
2. enhancement — Feature requests or usability improvements that ask for new capabilities, better ergonomics, or quality-of-life tweaks.
3. extension — VS Code (or other IDE) extension-specific issues.
4. windows-os — Bugs or friction specific to Windows environments (always when PowerShell is mentioned, path handling, copy/paste, OS-specific auth or tooling failures).
5. mcp — Topics involving Model Context Protocol servers/clients.
6. codex-web — Issues targeting the Codex web UI/Cloud experience.
8. azure — Problems or requests tied to Azure OpenAI deployments.
9. documentation — Updates or corrections needed in docs/README/config references (broken links, missing examples, outdated keys, clarification requests).
10. model-behavior — Undesirable LLM behavior: forgetting goals, refusing work, hallucinating environment details, quota misreports, or other reasoning/performance anomalies.
Issue number: ${{ github.event.issue.number }}
Issue title:
${{ github.event.issue.title }}
Issue body:
${{ github.event.issue.body }}
Repository full name:
${{ github.repository }}
output_schema: |
{
"type": "object",
"properties": {
"labels": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": ["labels"],
"additionalProperties": false
}
apply-labels:
name: Apply labels from Codex output
@@ -53,12 +90,12 @@ jobs:
exit 0
fi
if ! printf '%s' "$json" | jq -e 'type == "array"' >/dev/null 2>&1; then
echo "Codex output was not a JSON array. Raw output: $json"
if ! printf '%s' "$json" | jq -e 'type == "object" and (.labels | type == "array")' >/dev/null 2>&1; then
echo "Codex output did not include a labels array. Raw output: $json"
exit 0
fi
labels=$(printf '%s' "$json" | jq -r '.[] | tostring')
labels=$(printf '%s' "$json" | jq -r '.labels[] | tostring')
if [ -z "$labels" ]; then
echo "Codex returned an empty array. Nothing to do."
exit 0