v0.9.22

simstudioai/simv0.9.22Oct 15, 2026by github-actions[bot]

Upgrading?

AI Summary

This release introduces core storage and realtime operations for project files, enhances the Mothership dashboard with benchmarking tools and super-user plans, and expands the library with articles on AI agents and voice platforms. It also standardizes documentation and API scopes while resolving numerous bugs related to file permissions, search, and uploads.

Key Highlights

  • Added core storage and realtime operations for project files
  • Enhanced Mothership with super-user plans, knowledge graph settings, and benchmark tooling
  • Standardized OAuth scopes in OpenAPI and implemented JSON 404s for unknown API paths
  • Expanded library with guides on AI agents for recruiting, IT helpdesk, and voice support

Breaking Changes

  • Renamed 'sandbox-tasks' to 'sandboxes'
  • Unknown API paths now return JSON 404s instead of other statuses

New Features

  • Core storage and realtime operations for project files
  • Establish shared file ownership foundation
  • Super-user Plan and knowledge graph settings with benchmark tooling in Mothership
  • Live Web Search integration using You.com API
  • New library articles: 7 Best AI Agents for Recruiting, 7 Best Voice AI Agent Builders, Best AI Agents for IT Helpdesk

Full Release Notes

## Features

- feat(project-files): add core storage and realtime operations (#9016)
- feat(library): 7 Best AI Agents for Recruiting Teams in 2026: Screening, Scheduling, ATS, and Outreach (#9031)
- feat(library): 7 Best Voice AI Agent Builders for Phone Support in 2026 (#9030)
- feat(library): Best AI Agents for IT Helpdesk Teams: 6 Platforms Compared (#9029)
- feat(library): Best AI Agent Platforms for Agencies and Consultants Managing Multiple Clients (#9028)
- feat: establish shared file ownership foundation (#8609)
- feat(library): How to Give AI Agents Live Web Search with the You.com API in Sim (#9007)
- feat(changelog): cover October 13 product releases (#9004)
- feat(mothership): add super-user Plan and knowledge graph settings with benchmark tooling (#8637)

## Improvements

- improvement(docs): standardize integration copy and generated references (#9039)
- improvement(naming): rename sandbox-tasks to sandboxes and standardize file names (#9044)
- improvement(ci): track flaky checks daily and fix the live flakes (#9038)
- improvement(mcp): advertise server metadata, output schemas, and clearer tool docs (#9037)
- improvement(docs): standardize copy and responsive navigation (#9020)
- refactor(files): unify mutation accounting and retention (#9015)
- improvement(api): declare OAuth scopes in OpenAPI, JSON 404s for unknown API paths, and root MCP resource metadata (#9026)
- improvement(audits): ratchet relative imports, literal text sizes, static inline styles, db access in API routes, and bare route handlers (#9013)
- improvement(seo): fix soft 404s, per-integration freshness, and docs markdown for AI crawlers (#9006)
- improvement(mothership): load chat transcripts as windows from a stored UI projection (#9002)
- improvement(search): rank an overflowing Confluence all-terms match with relevance search (#9001)
- improvement(workflow): scope the editor by props instead of the URL (#8996)

## Bug Fixes

- fix(project-files): hold the Project and permission-group locks shared for non-charging file operations (#9058)
- fix(mothership): drop queued tab adds the server already removed (#9050)
- fix(file-doc): stop the permission resend loop and restore the 10 MB proxy body limit (#9057)
- fix(projects): gate the Project list on the projects rollout flag (#9052)
- fix(mothership): surface actionable workbench file read failures (#9048)
- fix(logging): log expected outcomes below ERROR and acknowledge a lost workflow-result race (#9056)
- fix(byok): preserve credential ownership on lookup failures (#9054)
- fix(appconfig): share the polled snapshot with Trigger.dev runs (#9053)
- fix(api): map MCP reauth redirect, deleted-account visit, and task service outage to non-500 statuses (#9051)
- fix(folders): run reorder lock checks on the reorder transaction (#9055)
- fix(resume): retry automatic resumes after read deadlines and an unreadable usage ledger (#9046)
- fix(uploads): sign transfers for in-process v2 callers that carry no network origin (#9049)
- fix(knowledge): serialize chunk date tags on the internal chunk read (#9045)
- fix(resume): answer a sync v2 resume whose run fails with the failed run, not a 500 (#9047)
- fix(docs): preserve negotiated response cache headers (#9043)
- fix(docs): correct delivery headers and preview details (#9042)
- fix(file-search): send legacy workspace index payloads, isolate realtime test DB, best-effort post-upload Project check (#9041)
- fix(files): cancel resumed runs across replicas, unify anchored file edits, and harden workspace, integration, and presence paths (#9035)
- fix(content): preserve canonical provenance across reads (#9036)
- fix(realtime): share file editor presence across replicas (#9014)
- fix(uploads): drop the stale reconciliation-retry claim from the upload-parts cleanup log (#9032)
- fix(files): keep file search and compiled-doc reads off write locks (#9023)
- fix(projects): fence file writers with a shared Project lock (#9025)
- fix(file-search): find an owner's stale dependencies from its dependency rows (#9024)
- fix(projects): sweep only retired Project prefixes (#9021)
- fix(mothership): admit stored content to Chat per item through one gate (#8941)
- fix(docs): return 404 for unknown docs paths and derive integration counts from the catalog (#9003)
- fix(mothership): grant gated entitlements to organization Build chats (#8998)
- fix(settings): add platform admin tabs to organization view (#8997)
- fix(empty-states): keep const assertions on changelog release constants (#8994)

## Other Changes

- ci: bump the actions group across 2 directories with 5 updates (#9033)
- docs(library): update best-ai-agents-invoice-processing-finance-reconciliation-2026 (#9027)
- chore(files): tighten #8609 follow-ups (#9022)
- docs(library): update what-is-an-ai-agent-definition-how-it-works-and-examples (#9008)
- docs(library): update can-ai-agents-talk-to-each-other-multi-agent-communication-explained (#9009)
- docs(library): update best-ai-agents-for-customer-support-automation (#9010)
- docs(library): update best-ai-agents-for-data-extraction-and-rag-in-2026 (#9011)
- docs(library): update sim-vs-dedicated-chatbot-builders (#9012)
- chore(legal): update privacy and cookie policies (#9005)
- chore(docs): remove the academy (#8995)

## Contributors

- @Sg312
- @TheodoreSpeaks
- @dependabot[bot]
- @icecrasher321
- @mzxchandra
- @waleedlatif1

[View changes on GitHub](https://github.com/simstudioai/sim/compare/v0.9.21...v0.9.22)

Related Repositories