@x12i/ai-gateway 10.4.0 → 10.4.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +2 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -342,11 +342,12 @@ Every mode requires an explicit **`model`** on the request (concrete catalog id
|
|
|
342
342
|
| `npm test` | All unit/integration tests in `.tests/run-all.js` (tsx, no network) |
|
|
343
343
|
| `npm run test:ai-tools` | ai-tools + cost + trace helper unit tests |
|
|
344
344
|
| `npm run test:ai-tools:live` | Real invoke + dev strict model check (needs API key) |
|
|
345
|
+
| `npm run test:openrouter-live` | OpenRouter runtime + optional server tools (needs `OPENROUTER_API_KEY`) |
|
|
345
346
|
| `npm run test:flex-md-parsing` | flex-md parsing scenarios |
|
|
346
347
|
| `npm run test:flex-md-esm-regression` | ESM build regression for flex-md |
|
|
347
348
|
| `npm run test:prepublish` | `build` + `npm test` |
|
|
348
349
|
|
|
349
|
-
Live tests use `LIVE_TEST_PROVIDER` / `LIVE_TEST_MODEL` (default `openrouter` + `openai/gpt-4o-mini`). Set `LIVE_SKIP_INVOKE=1` to skip the LLM call. Profile alias invokes (`LIVE_TEST_PROFILES=1`) are **no longer supported** — resolve profiles upstream (ai-tasks) before calling the gateway.
|
|
350
|
+
Live tests use `LIVE_TEST_PROVIDER` / `LIVE_TEST_MODEL` (default `openrouter` + `openai/gpt-4o-mini`). Set `LIVE_SKIP_INVOKE=1` to skip the LLM call. `npm run test:openrouter-live` exercises plain OpenRouter calls plus datetime and web search server tools (requires `OPENROUTER_API_KEY`). Profile alias invokes (`LIVE_TEST_PROFILES=1`) are **no longer supported** — resolve profiles upstream (ai-tasks) before calling the gateway.
|
|
350
351
|
|
|
351
352
|
---
|
|
352
353
|
|