@gullabs/google 0.10.0 → 0.10.1

package/README.md

@@ -22,10 +22,8 @@ pnpm add @gullabs/google @gullabs/core @google/genai
 | `isGeminiCapacityError(err)`                                               | Detects Gemini Flex shared-capacity errors for built-in fallback                      |
 | `geminiModelDescriptors`, `gemmaModelDescriptors`, `defaultGeminiRegistry` | Built-in model descriptors + pre-built registry                                       |
 | `geminiPricingSource()`, `GEMINI_PRICING`, `TIER_FACTOR`                   | Built-in Gemini pricing snapshot and tier-factor map                                  |
-
-
-| `GoogleFileStore` | Files API: upload + poll ACTIVE + delete |
-| `FileDeleteOptions` | `{ failClosed?, signal? }` — opt-in fail-closed delete (parity with `@gullabs/xai`) |
+| `GoogleFileStore`                                                          | Files API: upload + poll ACTIVE + delete                                              |
+| `FileDeleteOptions`                                                        | `{ failClosed?, signal? }` — opt-in fail-closed delete (parity with `@gullabs/xai`)   |
 
 ## File store delete modes
 
@@ -67,7 +65,7 @@ const result = await client.generate(
 - `output.jsonSchema` → `responseMimeType: 'application/json'` + verbatim `responseSchema` when native structured output is enabled; the engine returns parsed output and `outputParsed` without validating shape
 - `providerOptions.google.*` → typed provider-extension lane for admitted keys such as `cachedContent`, `safetySettings`, and exact tool declarations
 - Usage: `promptTokenCount`→`inputTokens`, `candidatesTokenCount`+`thoughtsTokenCount`→`outputTokens` (GROSS)
-- Errors: `401/403`→`invalid_auth`, `429`→`rate_limited`, `5xx`→`server`, timeouts, safety blocks
+- Errors: `401` and a bare `403` default to `invalid_auth`; `429`→`rate_limited`; `5xx`→`server`; timeouts; Gemini safety blocks are a 200-path `content_filter` (`promptFeedback.blockReason` / no candidates), not an HTTP 403
 
 ## Strict model-config expectations
 

package/package.json

@@ -1,12 +1,12 @@
 {
   "name": "@gullabs/google",
-  "version": "0.10.0",
+  "version": "0.10.1",
   "description": "Gemini provider adapter for any-llm — Flex tier, thinking capture, structured output, error classification.",
   "type": "module",
   "license": "Apache-2.0",
   "repository": {
     "type": "git",
-    "url": "git+https://github.com/gullabs/any-llm.git",
+    "url": "git+https://github.com/GulLabs/any-llm.git",
     "directory": "packages/google"
   },
   "main": "./dist/index.cjs",
@@ -24,14 +24,14 @@
   ],
   "dependencies": {
     "zod": "^4.4.3",
-    "@gullabs/core": "0.12.0"
+    "@gullabs/core": "0.12.1"
   },
   "peerDependencies": {
     "@google/genai": "^1 || ^2"
   },
   "devDependencies": {
     "@google/genai": "^2.16.0",
-    "@gullabs/testing": "0.6.0"
+    "@gullabs/testing": "0.6.1"
   },
   "engines": {
     "node": ">=20.9.0"
@@ -51,8 +51,8 @@
   "publishConfig": {
     "access": "public"
   },
-  "homepage": "https://github.com/gullabs/any-llm/tree/main/packages/google#readme",
-  "bugs": "https://github.com/gullabs/any-llm/issues",
+  "homepage": "https://github.com/GulLabs/any-llm/tree/main/packages/google#readme",
+  "bugs": "https://github.com/GulLabs/any-llm/issues",
   "scripts": {
     "build": "tsup"
   }