visual-ai-assertions 0.5.0 → 0.7.0
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 +23 -16
- package/dist/index.cjs +293 -127
- package/dist/index.cjs.map +1 -1
- package/dist/index.d.cts +48 -3
- package/dist/index.d.ts +48 -3
- package/dist/index.js +292 -127
- package/dist/index.js.map +1 -1
- package/package.json +3 -2
package/README.md
CHANGED
|
@@ -387,11 +387,13 @@ The `VisualAIKnownError` union and `isVisualAIKnownError()` helper are useful wh
|
|
|
387
387
|
|
|
388
388
|
### Optional Configuration
|
|
389
389
|
|
|
390
|
-
| Variable
|
|
391
|
-
|
|
|
392
|
-
| `VISUAL_AI_MODEL`
|
|
393
|
-
| `VISUAL_AI_DEBUG`
|
|
394
|
-
| `
|
|
390
|
+
| Variable | Description |
|
|
391
|
+
| -------------------------- | -------------------------------------------------------------------------------------------------------------- |
|
|
392
|
+
| `VISUAL_AI_MODEL` | Default model when `model` is not set in config. Overrides the provider's default model. |
|
|
393
|
+
| `VISUAL_AI_DEBUG` | Enable error diagnostic logging to stderr. Does **not** enable prompt/response logging. Use `"true"` or `"1"`. |
|
|
394
|
+
| `VISUAL_AI_DEBUG_PROMPT` | Enable prompt-only debug logging to stderr. Use `"true"` or `"1"`. |
|
|
395
|
+
| `VISUAL_AI_DEBUG_RESPONSE` | Enable response-only debug logging to stderr. Use `"true"` or `"1"`. |
|
|
396
|
+
| `VISUAL_AI_TRACK_USAGE` | Enable usage tracking (token counts and cost) to stderr. Use `"true"` or `"1"`. |
|
|
395
397
|
|
|
396
398
|
## Configuration
|
|
397
399
|
|
|
@@ -399,7 +401,9 @@ The `VisualAIKnownError` union and `isVisualAIKnownError()` helper are useful wh
|
|
|
399
401
|
| ----------------- | ------- | ---------------- | ----------------------------------------------------------------------------- |
|
|
400
402
|
| `apiKey` | string | env var | API key for the provider |
|
|
401
403
|
| `model` | string | provider default | Model to use |
|
|
402
|
-
| `debug` | boolean | `false` |
|
|
404
|
+
| `debug` | boolean | `false` | Enable error diagnostic logging to stderr |
|
|
405
|
+
| `debugPrompt` | boolean | `false` | Log prompts to stderr |
|
|
406
|
+
| `debugResponse` | boolean | `false` | Log responses to stderr |
|
|
403
407
|
| `maxTokens` | number | `4096` | Max tokens for AI response |
|
|
404
408
|
| `reasoningEffort` | string | `undefined` | `"low"` `"medium"` `"high"` `"xhigh"` — controls how deeply the model reasons |
|
|
405
409
|
| `trackUsage` | boolean | `false` | Log token usage and estimated cost to stderr |
|
|
@@ -463,19 +467,22 @@ All listed models support image/vision input. Pass any model ID to the `model` c
|
|
|
463
467
|
|
|
464
468
|
### OpenAI
|
|
465
469
|
|
|
466
|
-
| Model
|
|
467
|
-
|
|
|
468
|
-
| GPT-5.4 Pro
|
|
469
|
-
| GPT-5.4
|
|
470
|
-
| GPT-5.2
|
|
471
|
-
| GPT-5 mini
|
|
470
|
+
| Model | Model ID | Input $/MTok | Output $/MTok | Notes |
|
|
471
|
+
| ------------ | -------------- | ------------ | ------------- | ------------------------------ |
|
|
472
|
+
| GPT-5.4 Pro | `gpt-5.4-pro` | $30 | $180 | Most capable, extended context |
|
|
473
|
+
| GPT-5.4 | `gpt-5.4` | $2.50 | $15 | Best vision quality |
|
|
474
|
+
| GPT-5.2 | `gpt-5.2` | $1.75 | $14 | Balanced quality and cost |
|
|
475
|
+
| GPT-5.4 mini | `gpt-5.4-mini` | $0.75 | $4.50 | Fast and affordable |
|
|
476
|
+
| GPT-5.4 nano | `gpt-5.4-nano` | $0.20 | $1.25 | Cheapest OpenAI option |
|
|
477
|
+
| GPT-5 mini | `gpt-5-mini` | $0.25 | $2 | **Default** — fast and cheap |
|
|
472
478
|
|
|
473
479
|
### Google
|
|
474
480
|
|
|
475
|
-
| Model
|
|
476
|
-
|
|
|
477
|
-
| Gemini 3.1 Pro
|
|
478
|
-
| Gemini 3 Flash | `gemini-3-flash-preview` | $0.
|
|
481
|
+
| Model | Model ID | Input $/MTok | Output $/MTok | Notes |
|
|
482
|
+
| --------------------- | ------------------------------- | ------------ | ------------- | --------------------------------- |
|
|
483
|
+
| Gemini 3.1 Pro | `gemini-3.1-pro-preview` | $2 | $12 | Preview — most advanced reasoning |
|
|
484
|
+
| Gemini 3.1 Flash Lite | `gemini-3.1-flash-lite-preview` | $0.25 | $1.50 | Preview — lightweight and cheap |
|
|
485
|
+
| Gemini 3 Flash | `gemini-3-flash-preview` | $0.50 | $3 | **Default** — fast and capable |
|
|
479
486
|
|
|
480
487
|
## License
|
|
481
488
|
|