# Web app: Document ingestion reliability fixes and Nova improvements

[Changelog](https://supermemory.ai/changelog)

Web appMarch 28, 2026

## Document ingestion reliability fixes and Nova improvements[#](https://supermemory.ai/changelog/2026-03-28-improvements-and-fixes)

Document ingestion can run up to three targeted searches to retrieve related memories as context, Nova explains region-unavailable models and offers alternatives, and the open-source LLM Bridge library supports OpenAI Responses and cross-provider streaming.

### Improvements

* During document ingestion, Supermemory can now generate up to three targeted searches to retrieve related existing memories as context.
* When Gemini is unavailable in your region, Nova now explains why and offers other models to switch to.
* [The open-source LLM Bridge library now supports OpenAI Responses, cross-provider streaming, reasoning, and structured output.](https://github.com/supermemoryai/llm-bridge)
* Nova chat now shows the active space beside the model selector and in chat history.

### Fixes

* Documents no longer remain permanently stuck in processing after a workflow stops; Supermemory retries them once and marks a second failure clearly.
* When scheduling a batch document upload fails, only the affected batch is marked failed instead of every queued document.
* API and MCP quota errors now name the limit reached and explain how to continue with overage.
* Truncated model output during ingestion no longer discards every generated memory when only relation data is incomplete.
* Updating a document with the same custom ID no longer creates duplicate memories from facts already extracted.
* Supermemory context loads correctly again in OpenCode 1.2.25 and later.
* Console onboarding now advances after you choose a plugin and shows its installation steps instead of No integration selected.
* Web links that return an authentication, paywall, or rate-limit response during metadata lookup no longer fail the entire import.
* Search requests with an empty query or an out-of-range limit now return a clear client error instead of a server error.
* Invitation links now explain when you're signed into the wrong account and let you sign out to continue with the invited email.

## Start building with supermemory.

Memory and continual learning for any model, any harness. Available through our API, plugins, and MCP.

[Build with supermemory ](https://console.supermemory.ai/)