Chat2API HAR Tool Fixture

Use this skill when a recorded client HAR should become reusable test input.

Rules

• Treat HAR parsing as generic.
• Put client-specific expectations in replay profiles, not in HAR extraction.
• Remove secrets and volatile headers from generated fixtures.
• Output fixtures are safe to replay and must not contain Authorization values.

Commands

node skills/chat2api-har-tool-fixture/scripts/extract-har-fixtures.mjs \
  --har backup/har/Cherry-Studio.har \
  --client cherry-studio \
  --out backup/har/cherry-studio-fixture.json

Use --har for the source HAR, --client for the fixture client profile, and --out for the output fixture path. If omitted, --har can come from CHAT2API_HAR, --client can come from CHAT2API_CLIENT_PROFILE, and output defaults to backup/har/<client>-tool-fixtures-<timestamp>.json.

Chat2API Management API

Use this skill before live proxy testing that needs /v0/management/*.

Rules

• Never print full management secrets, API keys, or account credentials.
• Create disposable API keys for tests and delete only keys created by the current run.
• Snapshot config before mutation and restore it in cleanup.
• Do not clear sessions unless the user explicitly asks for cleanup.

Script

Use scripts/management-api.mjs for repeatable management API setup, observation, and cleanup commands.

Commands

CHAT2API_MGMT_SECRET=mgmt_xxx node skills/chat2api-management-api/scripts/management-api.mjs snapshot
CHAT2API_MGMT_SECRET=mgmt_xxx node skills/chat2api-management-api/scripts/management-api.mjs create-api-key --name codex-live-test
CHAT2API_MGMT_SECRET=mgmt_xxx node skills/chat2api-management-api/scripts/management-api.mjs delete-api-key --id key-id
CHAT2API_MGMT_SECRET=mgmt_xxx node skills/chat2api-management-api/scripts/management-api.mjs restore-tool-config --file /private/tmp/toolCallingConfig.json

Use --dry-run to verify command shape without network calls.

create-api-key prints a one-time API key to stdout. Do not write this output to durable logs, transcripts, or shared artifacts.

snapshot omits request logs by default. Use snapshot --include-logs only when logs are intentionally needed; included snapshot data is locally redacted before printing.

Chat2API Provider Model Matrix

Use this skill when model coverage must follow the live /v1/models surface.

Rules

• Use GET /v1/models as the primary model source.
• Use management API data for attribution and cleanup.
• Keep provider fail-fast opt-in.

Commands

CHAT2API_BASE_URL=http://127.0.0.1:8080 \
CHAT2API_MGMT_SECRET=mgmt_xxx \
CHAT2API_API_KEY=sk_xxx \
node skills/chat2api-provider-model-matrix/scripts/run-model-matrix.mjs \
  --fixture backup/har/cherry-studio-fixture.json \
  --profile cherry-studio

The default model source is GET /v1/models. Use --provider, --model, and --fail-fast-provider N to narrow live runs.

Chat2API Proxy Testing

Use this as the orchestration entry point.

Focused Skills

• Use chat2api-management-api for management API setup, observation, and cleanup.
• Use chat2api-har-tool-fixture to extract reusable fixtures from HAR files.
• Use chat2api-tool-client-replay to replay one client fixture against one or more models.
• Use chat2api-provider-model-matrix to discover /v1/models and run matrix coverage.

Default Order

1. Run source regressions when code changed.
2. Snapshot health and config through management API.
3. Extract or select a fixture.
4. Discover models through /v1/models.
5. Replay scenarios.
6. Inspect logs and sessions.
7. Restore config and delete temporary test assets.

Source Of Truth

The versioned source of truth is this skills/chat2api-proxy-testing directory plus the focused sibling skills. ignored .codex copies are local working copies only and must not be the only place where testing behavior is documented.

Chat2API Tool Client Replay

Use this skill to replay fixture scenarios for clients such as Cherry Studio, generic OpenAI tools, or unknown HAR-derived clients.

Rules

• Preserve exact tool names.
• Validate stream and non-stream behavior separately.
• Use profiles for client-specific prompt-protocol expectations.

Commands

CHAT2API_API_KEY=sk_xxx \
node skills/chat2api-tool-client-replay/scripts/replay-client-fixture.mjs \
  --fixture backup/har/cherry-studio-fixture.json \
  --profile cherry-studio \
  --model deepseek-v4-flash

Use --dry-run to check profile, model, and fixture selection without live requests. If the fixture file exists, dry-run parses the fixture schema and reports fixtureExists plus scenarioCount; if it is missing, dry-run still exits successfully with fixtureExists: false.

Profiles

• cherry-studio: Cherry Studio headers and visible prompt-tool-use expectations.
• openai-tools: generic OpenAI-compatible tool-calling expectations.
• custom-har: empty client headers for replaying sanitized HAR-derived fixtures.