@juspay/neurolink 9.54.9 → 9.55.1
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 +8 -0
- package/README.md +17 -15
- package/dist/browser/neurolink.min.js +273 -272
- package/dist/cli/commands/proxy.js +1 -1
- package/dist/core/redisConversationMemoryManager.js +17 -1
- package/dist/lib/core/redisConversationMemoryManager.js +17 -1
- package/dist/lib/neurolink.js +10 -2
- package/dist/lib/providers/googleNativeGemini3.d.ts +5 -0
- package/dist/lib/providers/googleNativeGemini3.js +18 -0
- package/dist/lib/providers/googleVertex.js +168 -11
- package/dist/lib/services/server/ai/observability/instrumentation.d.ts +2 -3
- package/dist/lib/services/server/ai/observability/instrumentation.js +22 -18
- package/dist/lib/types/conversation.d.ts +4 -0
- package/dist/lib/types/generate.d.ts +2 -0
- package/dist/lib/types/providers.d.ts +15 -0
- package/dist/lib/types/tools.d.ts +4 -0
- package/dist/lib/utils/conversationMemory.js +1 -0
- package/dist/neurolink.js +10 -2
- package/dist/providers/googleNativeGemini3.d.ts +5 -0
- package/dist/providers/googleNativeGemini3.js +18 -0
- package/dist/providers/googleVertex.js +168 -11
- package/dist/services/server/ai/observability/instrumentation.d.ts +2 -3
- package/dist/services/server/ai/observability/instrumentation.js +22 -18
- package/dist/types/conversation.d.ts +4 -0
- package/dist/types/generate.d.ts +2 -0
- package/dist/types/providers.d.ts +15 -0
- package/dist/types/tools.d.ts +4 -0
- package/dist/utils/conversationMemory.js +1 -0
- package/package.json +2 -2
- package/dist/lib/utils/imageCompressor.d.ts +0 -25
- package/dist/lib/utils/imageCompressor.js +0 -141
- package/dist/utils/imageCompressor.d.ts +0 -25
- package/dist/utils/imageCompressor.js +0 -140
package/CHANGELOG.md
CHANGED
|
@@ -1,3 +1,11 @@
|
|
|
1
|
+
## [9.55.1](https://github.com/juspay/neurolink/compare/v9.55.0...v9.55.1) (2026-04-18)
|
|
2
|
+
|
|
3
|
+
## [9.55.0](https://github.com/juspay/neurolink/compare/v9.54.9...v9.55.0) (2026-04-18)
|
|
4
|
+
|
|
5
|
+
### Features
|
|
6
|
+
|
|
7
|
+
- **(gemini3):** add support for conversation memory for gemini 3 models ([0459627](https://github.com/juspay/neurolink/commit/0459627c7612343ad3fc462cea4036c993ace0fd))
|
|
8
|
+
|
|
1
9
|
## [9.54.9](https://github.com/juspay/neurolink/compare/v9.54.8...v9.54.9) (2026-04-18)
|
|
2
10
|
|
|
3
11
|
## [9.54.8](https://github.com/juspay/neurolink/compare/v9.54.7...v9.54.8) (2026-04-18)
|
package/README.md
CHANGED
|
@@ -40,21 +40,22 @@ Extracted from production systems at Juspay and battle-tested at enterprise scal
|
|
|
40
40
|
|
|
41
41
|
## What's New (Q1 2026)
|
|
42
42
|
|
|
43
|
-
| Feature | Version | Description
|
|
44
|
-
| ----------------------------------- | ------- |
|
|
45
|
-
| **
|
|
46
|
-
| **
|
|
47
|
-
| **
|
|
48
|
-
| **
|
|
49
|
-
| **
|
|
50
|
-
| **
|
|
51
|
-
| **
|
|
52
|
-
| **
|
|
53
|
-
| **
|
|
54
|
-
| **
|
|
55
|
-
| **
|
|
56
|
-
| **
|
|
57
|
-
| **
|
|
43
|
+
| Feature | Version | Description | Guide |
|
|
44
|
+
| ----------------------------------- | ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------- |
|
|
45
|
+
| **Gemini 3 Multi-turn Tool Fix** | v9.49.0 | Fixed multi-step agentic tool calling on Vertex AI Gemini 3 models. Correct `thoughtSignature` replay, `stepIndex` parallel-call grouping, `executionId` session isolation, 5-min timeout, silent-timeout surfacing. | [Vertex AI Guide](docs/getting-started/providers/google-vertex.md) |
|
|
46
|
+
| **AutoResearch** | v9.17.0 | Autonomous AI experiment engine: proposes code changes, runs experiments, evaluates metrics, keeps improvements — unattended for hours. | [AutoResearch Guide](docs/features/autoresearch.md) |
|
|
47
|
+
| **MCP Enhancements** | v9.16.0 | Advanced MCP features: tool routing, result caching, request batching, annotations, elicitation, custom server base, multi-server management | [MCP Enhancements Guide](docs/features/mcp-enhancements.md) |
|
|
48
|
+
| **Memory** | v9.12.0 | Per-user condensed memory that persists across conversations. LLM-powered condensation with S3, Redis, or SQLite backends. | [Memory Guide](docs/features/memory.md) |
|
|
49
|
+
| **Context Window Management** | v9.2.0 | 4-stage compaction pipeline with auto-detection, budget gate at 80% usage, per-provider token estimation | [Context Compaction Guide](docs/features/context-compaction.md) |
|
|
50
|
+
| **Tool Execution Control** | v9.3.0 | `prepareStep` and `toolChoice` support for per-step tool enforcement in multi-step agentic loops. API-level control over tool calls. | [API Reference](docs/api/type-aliases/GenerateOptions.md#preparestep) |
|
|
51
|
+
| **File Processor System** | v9.1.0 | 17+ file type processors with ProcessorRegistry, security sanitization, SVG text injection | [File Processors Guide](docs/features/file-processors.md) |
|
|
52
|
+
| **RAG with generate()/stream()** | v9.2.0 | Pass `rag: { files }` to generate/stream for automatic document chunking, embedding, and AI-powered search. 10 chunking strategies, hybrid search, reranking. | [RAG Guide](docs/features/rag.md) |
|
|
53
|
+
| **External TracerProvider Support** | v8.43.0 | Integrate NeuroLink with existing OpenTelemetry instrumentation. Prevents duplicate registration conflicts. | [Observability Guide](docs/features/observability.md) |
|
|
54
|
+
| **Server Adapters** | v8.43.0 | Multi-framework HTTP server with Hono, Express, Fastify, Koa support. Full CLI for server management with foreground/background modes. | [Server Adapters Guide](docs/guides/server-adapters/index.md) |
|
|
55
|
+
| **Title Generation Events** | v8.38.0 | Emit `conversation:titleGenerated` event when conversation title is generated. Supports custom title prompts via `NEUROLINK_TITLE_PROMPT`. | [Conversation Memory Guide](docs/conversation-memory.md) |
|
|
56
|
+
| **Video Generation with Veo** | v8.32.0 | Video generation using Veo 3.1 (`veo-3.1`). Realistic video generation with many parameter options | [Video Generation Guide](docs/features/video-generation.md) |
|
|
57
|
+
| **Image Generation with Gemini** | v8.31.0 | Native image generation using Gemini 2.0 Flash Experimental (`imagen-3.0-generate-002`). High-quality image synthesis directly from Google AI. | [Image Generation Guide](docs/image-generation-streaming.md) |
|
|
58
|
+
| **HTTP/Streamable HTTP Transport** | v8.29.0 | Connect to remote MCP servers via HTTP with authentication headers, automatic retry with exponential backoff, and configurable rate limiting. | [HTTP Transport Guide](docs/mcp-http-transport.md) |
|
|
58
59
|
|
|
59
60
|
- **AutoResearch** – Autonomous AI experiment engine inspired by Karpathy's autoresearch. Phase-gated tool access, git-backed safety, deterministic metric evaluation, and TaskManager integration for continuous unattended research. 12 research tools, 10 typed events, 9 CLI subcommands. → [AutoResearch Guide](docs/features/autoresearch.md)
|
|
60
61
|
- **Memory** – Per-user condensed memory that persists across all conversations. Automatically retrieves and stores memory on each `generate()`/`stream()` call. Supports S3, Redis, and SQLite storage with LLM-powered condensation. → [Memory Guide](docs/features/memory.md)
|
|
@@ -68,6 +69,7 @@ Extracted from production systems at Juspay and battle-tested at enterprise scal
|
|
|
68
69
|
- **Image Generation** – Generate images from text prompts using Gemini models via Vertex AI or Google AI Studio. Supports streaming mode with automatic file saving. → [Image Generation Guide](docs/image-generation-streaming.md)
|
|
69
70
|
- **RAG with generate()/stream()** – Just pass `rag: { files: ["./docs/guide.md"] }` to `generate()` or `stream()`. NeuroLink auto-chunks, embeds, and creates a search tool the AI can invoke. 10 chunking strategies, hybrid search, 5 reranker types. → [RAG Guide](docs/features/rag.md)
|
|
70
71
|
- **HTTP/Streamable HTTP Transport for MCP** – Connect to remote MCP servers via HTTP with authentication headers, retry logic, and rate limiting. → [HTTP Transport Guide](docs/mcp-http-transport.md)
|
|
72
|
+
- 🧠 **Gemini 3 Native Multi-turn Tool Calling** — Fixed multi-step agentic tool calling for Gemini 3 models on Vertex AI. The native `@google/genai` path now correctly replays `thoughtSignature` as a sibling field on each `functionCall` part, groups parallel tool calls by `stepIndex`, enforces a 5-minute default timeout on the generate path, and surfaces silent timeouts as proper `TimeoutError` instead of empty responses. Multi-execution session overlap (where `continueOrchestratorWorkflow` restarts the loop on the same `sessionId`) is addressed by an `executionId` per invocation as a composite grouping key — this prevents tool calls from two different executions colliding into the same Gemini model turn and causing the model to return 0 function calls.
|
|
71
73
|
- 🧠 **Gemini 3 Preview Support** - Full support for gemini-3-flash-preview and gemini-3-pro-preview with extended thinking capabilities
|
|
72
74
|
- 🎯 **Tool Execution Control** – Use `prepareStep` to enforce specific tool calls, change the LLM models per step in multi-step agentic executions. Prevents LLMs from skipping required tools. Use `toolChoice` for static control, or `prepareStep` for dynamic per-step logic. → [GenerateOptions Reference](docs/api/type-aliases/GenerateOptions.md#preparestep)
|
|
73
75
|
- **Structured Output with Zod Schemas** – Type-safe JSON generation with automatic validation using `schema` + `output.format: "json"` in `generate()`. → [Structured Output Guide](docs/features/structured-output.md)
|