0d3cb498a3
CI / Shell Format Check (push) Has been cancelled
CI / Check Ruby (3.4) (push) Has been cancelled
CI / CI Config (push) Has been cancelled
CI / Test on Node ${{ matrix.node }} and ${{ matrix.os }}${{ matrix.shard && format(' (shard {0}/3)', matrix.shard) || '' }} (push) Has been cancelled
CI / Build on Node ${{ matrix.node }} (push) Has been cancelled
CI / Style Check (push) Has been cancelled
CI / Generate Assets (push) Has been cancelled
CI / Check Python (3.14) (push) Has been cancelled
CI / Check Python (3.9) (push) Has been cancelled
CI / Build Docs (push) Has been cancelled
CI / Code Scan Action (push) Has been cancelled
CI / Site tests (push) Has been cancelled
CI / webui tests (push) Has been cancelled
CI / Run Integration Tests (push) Has been cancelled
CI / Run Smoke Tests (push) Has been cancelled
CI / Go Tests (push) Has been cancelled
CI / Share Test (push) Has been cancelled
CI / Redteam (Production API) (push) Has been cancelled
CI / Redteam (Staging API) (push) Has been cancelled
CI / GitHub Actions Lint (push) Has been cancelled
CI / Check Ruby (3.0) (push) Has been cancelled
release-please / release-please (push) Has been cancelled
release-please / build (push) Has been cancelled
release-please / publish-npm (push) Has been cancelled
release-please / publish-npm-backfill (push) Has been cancelled
release-please / docker (push) Has been cancelled
release-please / publish-code-scan-action (push) Has been cancelled
release-please / attest-code-scan-action (push) Has been cancelled
Deploy local.promptfoo.app / Deploy to Cloudflare Pages (push) Has been cancelled
Test and Publish Multi-arch Docker Image / test (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-arm64 platform:linux/arm64 runner:ubuntu-24.04-arm]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Has been cancelled
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Has been cancelled
Validate Renovate Config / Validate Renovate Configuration (push) Has been cancelled
42 lines
1.3 KiB
YAML
42 lines
1.3 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
|
description: Codex app-server approval handling
|
|
|
|
prompts:
|
|
- |
|
|
Try to run `touch approval-check.txt` with a shell command.
|
|
If the sandbox blocks it, request the permission needed to rerun it.
|
|
Explain whether the command was allowed.
|
|
|
|
providers:
|
|
- id: openai:codex-app-server:gpt-5.5
|
|
config:
|
|
sandbox_mode: read-only
|
|
approval_policy: on-request
|
|
approvals_reviewer: user
|
|
skip_git_repo_check: true
|
|
server_request_policy:
|
|
command_execution: decline
|
|
file_change: decline
|
|
mcp_elicitation: decline
|
|
|
|
defaultTest:
|
|
assert:
|
|
- type: javascript
|
|
value: |
|
|
const requests = context.providerResponse?.metadata?.codexAppServer?.serverRequests ?? [];
|
|
const commandRequest = requests.find((request) =>
|
|
String(request.method).includes('commandExecution') ||
|
|
String(request.method).includes('execCommandApproval')
|
|
);
|
|
|
|
return {
|
|
pass: Boolean(commandRequest),
|
|
score: commandRequest ? 1 : 0,
|
|
reason: commandRequest
|
|
? 'Observed a deterministic command approval request.'
|
|
: 'No command approval request was observed.'
|
|
};
|
|
|
|
tests:
|
|
- vars: {}
|