chore: import upstream snapshot with attribution
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
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
This commit is contained in:
@@ -0,0 +1,40 @@
|
||||
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
||||
description: Codex skill trace eval
|
||||
|
||||
prompts:
|
||||
- 'Use the token-skill skill. Return only the token.'
|
||||
|
||||
providers:
|
||||
- id: openai:codex-sdk
|
||||
config:
|
||||
model: gpt-5.2
|
||||
# Relative working_dir values resolve from this config file's directory.
|
||||
# Codex resolves CODEX_HOME itself; set CODEX_HOME_OVERRIDE when running this config from another cwd.
|
||||
# sample-codex-home has no auth state; use an API key or point CODEX_HOME_OVERRIDE at ~/.codex.
|
||||
working_dir: '{{ env.CODEX_SKILLS_WORKING_DIR | default("./sample-project") }}'
|
||||
skip_git_repo_check: true
|
||||
enable_streaming: true
|
||||
deep_tracing: true
|
||||
cli_env:
|
||||
CODEX_HOME: '{{ env.CODEX_HOME_OVERRIDE | default("./sample-codex-home") }}'
|
||||
|
||||
tests:
|
||||
- assert:
|
||||
- type: contains
|
||||
value: 'CERULEAN-FALCON-SKILL'
|
||||
- type: trajectory:step-count
|
||||
value:
|
||||
type: command
|
||||
pattern: '*token-skill/SKILL.md*'
|
||||
min: 1
|
||||
- type: skill-used
|
||||
value: token-skill
|
||||
|
||||
tracing:
|
||||
enabled: true
|
||||
otlp:
|
||||
http:
|
||||
enabled: true
|
||||
port: 4318
|
||||
host: '127.0.0.1'
|
||||
acceptFormats: ['json']
|
||||
@@ -0,0 +1,25 @@
|
||||
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
||||
description: Codex skill eval
|
||||
|
||||
prompts:
|
||||
- 'Use the token-skill skill. Return only the token.'
|
||||
|
||||
providers:
|
||||
- id: openai:codex-sdk
|
||||
config:
|
||||
model: gpt-5.2
|
||||
# Relative working_dir values resolve from this config file's directory.
|
||||
# Codex resolves CODEX_HOME itself; set CODEX_HOME_OVERRIDE when running this config from another cwd.
|
||||
# sample-codex-home has no auth state; use an API key or point CODEX_HOME_OVERRIDE at ~/.codex.
|
||||
working_dir: '{{ env.CODEX_SKILLS_WORKING_DIR | default("./sample-project") }}'
|
||||
skip_git_repo_check: true
|
||||
enable_streaming: true
|
||||
cli_env:
|
||||
CODEX_HOME: '{{ env.CODEX_HOME_OVERRIDE | default("./sample-codex-home") }}'
|
||||
|
||||
tests:
|
||||
- assert:
|
||||
- type: equals
|
||||
value: 'CERULEAN-FALCON-SKILL'
|
||||
- type: skill-used
|
||||
value: token-skill
|
||||
@@ -0,0 +1,10 @@
|
||||
logs_*.sqlite
|
||||
logs_*.sqlite-shm
|
||||
logs_*.sqlite-wal
|
||||
sessions/
|
||||
skills/
|
||||
state_*.sqlite
|
||||
state_*.sqlite-shm
|
||||
state_*.sqlite-wal
|
||||
.tmp/
|
||||
tmp/
|
||||
@@ -0,0 +1 @@
|
||||
|
||||
@@ -0,0 +1,8 @@
|
||||
---
|
||||
name: token-skill
|
||||
description: Use this skill when the user explicitly asks to use token-skill and wants the special token.
|
||||
---
|
||||
|
||||
When this skill is used, respond with exactly `CERULEAN-FALCON-SKILL`.
|
||||
|
||||
Do not add extra words, punctuation, or explanation.
|
||||
Reference in New Issue
Block a user