@gullabs/xai 0.2.0 → 0.2.1
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 +1 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -58,6 +58,7 @@ The default registry ships exactly one model: `grok-4.5` (500k token context win
|
|
|
58
58
|
|
|
59
59
|
- **Reasoning** — level-api (`reasoningApi: 'level'`), mapped to the Responses API `reasoning.effort` field. `admittedReasoningEfforts: ['low', 'high']` — this is deliberately narrower than Gemini's effort vocabulary: `'none'` and `'medium'` are **rejected by the live xAI API**, not merely unsupported by this library. The config schema (`Grok45ConfigSchema`) enforces `reasoning.effort` as `'low' | 'high'` only, and there is no `budgetTokens` field at all (xAI uses level-style reasoning, not token budgets) — passing it throws `bad_request`. The schema does not set a default effort; if `reasoning` is omitted, no `reasoning` field is sent and xAI's own server-side default applies.
|
|
60
60
|
- **Structured output** — native. `output.jsonSchema` maps to the Responses API's `text.format` field with `{ type: 'json_schema', name, schema, strict: true }`, **not** `response_format` — this differs from OpenAI's own convention for the same underlying concept.
|
|
61
|
+
- **`strict: true` performs no OpenAI-style compile-time schema validation, as of the 2026-07-09 live probes.** 2026-07-09 live verification against the real xAI Responses API — 13 single-variant probes plus 1 combined probe (14 calls total, all accepted HTTP 200; the combined probe is recorded as fixture `10-non-strict-schema-accepted.json`) — verified that `text.format` with `strict: true` accepted every one of the following schema shapes that OpenAI's own strict mode rejects at compile time: schemas (root and nested) missing `additionalProperties: false`; properties omitted from `required` (optional properties); `format`, `minLength`, `pattern`, and `default` keywords; `anyOf`; `$defs`/`$ref`; `enum`/`const`; and nullable unions (`type: [T, 'null']`). `strict: false` on the same surface showed no observed behavioral divergence from `strict: true`. This adapter forwards schemas to xAI verbatim — no rewriting, no preflight validation, and no injection of `additionalProperties: false` or `required` completion — so OpenAI-strict schema rewriting (including `@gullabs/codex-cli`'s `toOpenAiStrictOutputSchema` helper) is unnecessary for xai as of that verification date. (Reject-don't-map still applies to genuinely invalid input the xai schema/types layer itself rejects; this note is only about strict-mode compile-time schema-shape enforcement.) `packages/xai/src/__fixtures__/10-non-strict-schema-accepted.json` records one live example combining three of these — missing root `additionalProperties: false`, an optional property, and a `format` keyword — in a single accepted call.
|
|
61
62
|
- **Sampling** — `temperature` and `topP` are forwarded verbatim. No `topK`.
|
|
62
63
|
- **No penalties/stop** — `presence_penalty`, `frequency_penalty`, and `stop` are not in the config schema at all; xAI hard-rejects these on reasoning models, so the schema never admits them (reject-don't-map).
|
|
63
64
|
- **No service tiers** — xAI has no service-tier concept for `grok-4.5`; setting `serviceTier` on the request throws `bad_request`.
|