@sogni-ai/sogni-client 4.2.0-alpha.17 → 4.2.0-alpha.18
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/CHANGELOG.md +7 -0
- package/CLAUDE.md +10 -0
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,3 +1,10 @@
|
|
|
1
|
+
# [4.2.0-alpha.18](https://github.com/Sogni-AI/sogni-client/compare/v4.2.0-alpha.17...v4.2.0-alpha.18) (2026-05-09)
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
### Bug Fixes
|
|
5
|
+
|
|
6
|
+
* **examples:** prepare sound-to-video audio uploads ([52e6cc2](https://github.com/Sogni-AI/sogni-client/commit/52e6cc210e67da49742229a9d1ff2d0edd5e14fa))
|
|
7
|
+
|
|
1
8
|
# [4.2.0-alpha.17](https://github.com/Sogni-AI/sogni-client/compare/v4.2.0-alpha.16...v4.2.0-alpha.17) (2026-05-09)
|
|
2
9
|
|
|
3
10
|
|
package/CLAUDE.md
CHANGED
|
@@ -21,6 +21,16 @@ Use secondary LLM calls for semantic planning, creative adaptation, and audit/re
|
|
|
21
21
|
|
|
22
22
|
When SDK examples or generated helpers expose hosted creative workflows, keep them generated from or aligned with shared `@sogni/creative-agent` contracts such as `compileCreativeWorkflowPlanToHostedSequence()`, `validateAndNormalizeHostedToolArguments()`, `getRepairControlDecision()`, and `summarizeGuardTelemetry()`.
|
|
23
23
|
|
|
24
|
+
### Phase 3 (agentic-harness) shared contracts
|
|
25
|
+
|
|
26
|
+
`@sogni/creative-agent` ships several Phase-3 surfaces SDK consumers can import directly when implementing creative workflows:
|
|
27
|
+
|
|
28
|
+
- **Skills**: `ALL_BUILT_IN_SKILLS`, individual manifest exports (`QUALITY_AUDIT_SKILL`, `SKILL_MANAGEMENT_SKILL`, `SESSION_CONTROL_SKILL`, `ASSET_REFERENCE_MANAGEMENT_SKILL`, plus `IMAGE_GENERATION_SKILL`, `IMAGE_EDITING_SKILL`, `VIDEO_GENERATION_SKILL`, `VIDEO_EDITING_SKILL`, `MUSIC_GENERATION_SKILL`, `MEDIA_ANALYSIS_SKILL`, `PERSONA_MANAGEMENT_SKILL`, `APP_SETTINGS_SKILL`).
|
|
29
|
+
- **Asset manifest**: `createAssetManifest`, `addAsset`, `mapAssetsForModel`, `validateAssetReferences`, `formatModelRef` — three-layer asset references (`asset_id` / `user_label` / `model_ref`) so SDK consumers don't hand-format Seedance `@Image1` / GPT-Image-2 `[Image 1]` / LTX-2.3 `context_image_0` tokens.
|
|
30
|
+
- **Storyboard adapters**: `compileForModel`, `storyboardAdapterRegistry`, `SEEDANCE_ADAPTER`, `GPT_IMAGE_2_ADAPTER`, `LTX23_ADAPTER`, `WAN_ADAPTER`. Resolution is liberal (`seedance2-fast` → seedance via prefix).
|
|
31
|
+
- **Tool envelope**: `ToolResult`, `toolOk`, `toolErr`, `isToolResultOk`, `isToolResultErr`, `mapLegacyToolErrorCategory`, plus the canonical `ToolErrorCode` taxonomy.
|
|
32
|
+
- **Constrained decoding (`response_format`)**: llama-server natively accepts OpenAI-standard `{ type: "json_schema", json_schema: { strict, schema } }`. Plumbing through `src/Chat/index.ts` is the right place to land if SDK consumers want to opt in on tool-call rounds. Once added here it auto-flows through `sogni-socket` to the worker.
|
|
33
|
+
|
|
24
34
|
## Overview
|
|
25
35
|
|
|
26
36
|
This is the **Sogni SDK for JavaScript/Node.js** - a TypeScript client library for the Sogni Supernet, a DePIN protocol for creative AI inference. The SDK supports image generation (Stable Diffusion, Flux, etc.), video generation (WAN 2.2 and LTX-2.3 models), audio generation (ACE-Step 1.5), LLM chat with tool calling, and multimodal vision chat (Qwen3.5 VLM) via WebSocket communication.
|
package/package.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
|
3
3
|
"publishConfig": {
|
|
4
4
|
"access": "public"
|
|
5
5
|
},
|
|
6
|
-
"version": "4.2.0-alpha.
|
|
6
|
+
"version": "4.2.0-alpha.18",
|
|
7
7
|
"description": "Sogni SDK - AI image, video & audio generation plus LLM chat with vision via the Sogni Supernet (Stable Diffusion, Flux, WAN 2.2, LTX-2, Seedance, Qwen VLM)",
|
|
8
8
|
"keywords": [
|
|
9
9
|
"ai",
|