@fre4x/gemini 1.0.58 → 1.0.61
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 +5 -3
- package/dist/index.js +1640 -119
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -11,9 +11,9 @@ Google's Gemini is not a chatbot. It is a multimodal reasoning engine. This B1TE
|
|
|
11
11
|
| Tool | Capability |
|
|
12
12
|
|------|-----------|
|
|
13
13
|
| `analyze_media` | Analyze an image or audio file via URL or `file://` path. Prompt is optional. |
|
|
14
|
-
| `list_models` | List
|
|
14
|
+
| `list_models` | List supported models for `analyze_media`, `generate_image`, and `generate_video`. Filter by `analyze`, `image`, `video`, or `all`. |
|
|
15
15
|
| `generate_image` | Image synthesis via Imagen 4 (`imagen-4.0-generate-001`). Optionally save to `output_dir`. |
|
|
16
|
-
| `generate_video` | Async video generation via Veo (`veo-
|
|
16
|
+
| `generate_video` | Async video generation via Veo (`veo-3.1-generate-preview`). Returns `operation_name` to poll. |
|
|
17
17
|
| `get_video_status` | Poll video generation status. Returns URLs when complete. Optionally saves to `output_dir`. |
|
|
18
18
|
|
|
19
19
|
## Requirements
|
|
@@ -48,8 +48,10 @@ MOCK=true npx @fre4x/gemini
|
|
|
48
48
|
|
|
49
49
|
- **Image generation** requires Imagen access — not available on all free-tier API keys. Check [AI Studio](https://aistudio.google.com/).
|
|
50
50
|
- **Video generation** is async. Call `generate_video` → poll `get_video_status` every ~30s until `done: true`.
|
|
51
|
-
- `analyze_media` accepts `file://` paths for local files and auto-detects MIME type from URL extension (jpg, png, mp4, mp3, wav, pdf, etc.). If you omit `prompt`, it defaults to "Describe this media.".
|
|
51
|
+
- `analyze_media` accepts `file://` paths for local files and auto-detects MIME type from URL extension (jpg, png, mp4, mp3, wav, pdf, etc.). If you omit `prompt`, it defaults to "Describe this media." and uses `gemini-2.5-flash` by default.
|
|
52
|
+
- `analyze_media` rejects retired text-model aliases such as `gemini-1.5-*` and `gemini-2.0-*`. If you override `model`, use a currently supported `generateContent` model.
|
|
52
53
|
- `output_dir` on `generate_image` and `get_video_status` saves files to disk. Directory is created if it doesn't exist.
|
|
54
|
+
- Model defaults are intentionally pinned to the latest verified official Gemini docs for the current date. Do not replace them with older names from stale model knowledge.
|
|
53
55
|
|
|
54
56
|
## Development
|
|
55
57
|
|