@juspay/neurolink 12.2.6 → 12.3.0

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.
Files changed (22) hide show
  1. package/CHANGELOG.md +3 -3
  2. package/README.md +1 -0
  3. package/dist/adapters/providerImageAdapter.js +3 -0
  4. package/dist/browser/neurolink.min.js +364 -364
  5. package/dist/cli/commands/setup.js +2 -1
  6. package/dist/constants/contextWindows.js +11 -0
  7. package/dist/constants/enums.d.ts +26 -0
  8. package/dist/constants/enums.js +27 -0
  9. package/dist/factories/providerDescriptors.js +16 -1
  10. package/dist/models/manifestRegistry.js +2 -0
  11. package/dist/models/manifests/sambanova.d.ts +11 -0
  12. package/dist/models/manifests/sambanova.js +42 -0
  13. package/dist/providers/openaiChatCompletionsClient.d.ts +1 -1
  14. package/dist/providers/openaiChatCompletionsClient.js +20 -3
  15. package/dist/providers/openaiCompatCatalog.d.ts +1 -1
  16. package/dist/providers/openaiCompatCatalog.js +43 -3
  17. package/dist/types/providers.d.ts +4 -0
  18. package/dist/utils/modelChoices.js +29 -1
  19. package/dist/utils/pricing.js +16 -0
  20. package/dist/utils/providerConfig.d.ts +1 -0
  21. package/dist/utils/providerConfig.js +14 -0
  22. package/package.json +1 -1
package/CHANGELOG.md CHANGED
@@ -1,8 +1,8 @@
1
- ## [12.2.6](https://github.com/juspay/neurolink/compare/v12.2.5...v12.2.6) (2026-08-27)
1
+ ## [12.3.0](https://github.com/juspay/neurolink/compare/v12.2.6...v12.3.0) (2026-08-28)
2
2
 
3
- ### Bug Fixes
3
+ ### Features
4
4
 
5
- - **(localUsage):** a window longer than history means everything, not nothing ([396553c](https://github.com/juspay/neurolink/commit/396553c073b31f07c30773221d45ed09a0965a10))
5
+ - **(providers):** onboard SambaNova as the second post-gate catalog provider ([4184700](https://github.com/juspay/neurolink/commit/4184700e5c4fa6c7001e97a8d06eacdbed834724)), closes [#33](https://github.com/juspay/neurolink/issues/33) [1583/#1584](https://github.com/1583/neurolink/issues/1584)
6
6
 
7
7
  ## [11.2.3](https://github.com/juspay/neurolink/compare/v11.2.2...v11.2.3) (2026-08-19)
8
8
 
package/README.md CHANGED
@@ -48,6 +48,7 @@ Extracted from production systems at Juspay, NeuroLink provides a practical, Typ
48
48
 
49
49
  | Feature | Version | Description | Guide |
50
50
  | -------------------------------------------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------- |
51
+ | **SambaNova Provider** | next | RDU-accelerated open-weight flagships: Llama 3.3 70B (default), GPT-OSS 120B, DeepSeek V3.x, MiniMax, Gemma 4 (vision) — OpenAI-compatible Tier 2 catalog entry. Note: new SambaNova accounts require purchased credits. | [SambaNova Guide](docs/getting-started/providers/sambanova.md) |
51
52
  | **Cerebras Provider** | next | Wafer-scale inference at ~3000 tok/s: GPT-OSS 120B (default) + Gemma 4 31B, OpenAI-compatible Tier 2 catalog entry, live-verified end to end (generate, stream, tools, structured output). | [Cerebras Guide](docs/getting-started/providers/cerebras.md) |
52
53
  | **Avatar / Music Modalities + 12 Providers** | next | New `output: { mode: "avatar" \| "music" }` dispatch with handlers for D-ID, HeyGen, Replicate-MuseTalk (avatar) and Beatoven, ElevenLabs Music, Lyria, Replicate-MusicGen (music). Plus Fish Audio TTS, Kling/Runway/Replicate video, xAI/Groq/Cohere/Together/Fireworks/Perplexity/Cloudflare LLMs, Voyage/Jina embeddings, Stability/Ideogram/Recraft/Replicate image-gen. | [Provider Integration](docs/provider-integration/) |
53
54
  | **Multi-Provider Voice (TTS/STT)** | v9.62.0 | 6 TTS providers (OpenAI TTS, ElevenLabs, Google TTS, Azure TTS, Fish Audio, Cartesia) + 4 STT providers (Whisper, Deepgram, Azure STT, Google STT) + 2 realtime APIs (OpenAI Realtime, Gemini Live). | [TTS Guide](docs/features/tts.md) \| [STT Guide](docs/features/audio-input.md) \| [Realtime Guide](docs/features/real-time-services.md) |
package/dist/adapters/providerImageAdapter.js CHANGED
@@ -98,6 +98,9 @@ function normalizeVisionProvider(provider) {
98
98
  * Vision capability definitions for each provider
99
99
  */
100
100
  const VISION_CAPABILITIES = {
101
+ // SambaNova: vendor model-spec page (2026-08-27) lists gemma-4-31B-it as
102
+ // text+image+video; the dashboard also marks MiniMax-M3 as Vision.
103
+ sambanova: ["gemma-4-31B-it", "MiniMax-M3"],
101
104
  openai: [
102
105
  // GPT-5.4 family (released Mar 2026) - Latest flagship models
103
106
  "gpt-5.4",