v0.8.12

## Features

- feat(api): publish agent tool input schema (#7109)
- feat(providers): add GLM-5.3 and GLM-5.3-Flash to Z.ai (#7104)
- feat(credential-groups): add Atlassian OAuth and invite links (#7085)
- feat(integrations): add Microsoft Word (#7069)
- feat(integrations): add Semrush (#7068)
- feat(slack): launch v2 triggers and backfill custom bots (#6873)
- feat(api): make the platform operable headless over v2 (#6912)
- feat(library): Best Multi-Agent Frameworks for Production in 2026 (#7065)

## Improvements

- improvement(cli): clarify npm package readmes (#7121)
- improvement(billing): replace daily refresh credits with weekly refresh (#7113)
- improvement(db): finish workspace file size cutover (#7112)
- improvement(billing): paginate and parallelize the cycle-close sweep (#7103)
- improvement(billing): ledger-only usage + period-advance cycle close (#7078)
- improvement(access-control): wire tool and model permissions into copilot editing (#7080)
- improvement(tools): tell the model which duplicate tool instance is which (#7079)
- improvement(privacy): add Data Privacy Framework disclosures (#7076)
- improvement(workflow): add compact code hover previews (#7074)
- improvement(tools): support duplicate provider instances (#7064)
- refactor: remove dead code, orphan modules, and two unused dependencies (#7063)
- refactor: consolidate three drifted copies, close a gate blind spot, fix stale docs (#7062)
- refactor: remove dead orchestration entry points and no-op tests (#7060)

## Bug Fixes

- fix(db): harden workspace file size cutover (#7123)
- fix(tools): extend the transport-deadline disarm to the Node workers (#7124)
- fix(cli): exit after interactive secret input (#7118)
- fix(landing): restore section heading weight (#7110)
- fix(landing): stabilize platform preview motion (#7108)
- fix(landing): refresh sidebars across landing surface (#7102)
- fix(landing): refresh workspace sidebar preview (#7101)
- fix(chat): conceal a missing deployment the way an unreachable one is (#7100)
- fix(integrations): repair broken endpoints, silent failures, and a path traversal (#7096)
- fix(v2): stop six responses reporting less than the layer beneath them knew (#7097)
- fix(docs): validate generated API navigation (#7099)
- fix(custom-blocks): restore self-host entitlement gate (#7098)
- fix(microsoft-word): make conditional writes service-enforced and return 400 for bad input (#7094)
- fix(chat): prioritize workflows across resource menus (#7086)
- fix(security): require explicit trust for internal tool routes (#7089)
- fix(cli): correct three descriptions the CLI publishes, and restore --no-recursive (#7093)
- fix(docs): correct two statements that contradict what they describe (#7092)
- fix(cli): resolve blockers and majors from a full command-surface audit (#7083)
- fix(knowledge): harden ingestion pipeline (#7077)
- fix(workflow): highlight references in code previews (#7081)
- fix(provenance): classify a latched-but-empty registry's file writes as unrecorded (#7084)
- fix(copilot): name a count-parallel's branch count `count` in the model's read view (#7082)
- fix(tables): prevent truncated sandbox mounts (#7075)
- fix(sse): rotate workspace streams without gaps (#7061)
- fix(sse): bound workspace SSE connection lifetime (#7058)
- fix(ui): unify branded error pages (#7057)
- fix(memory): close app-service leak paths behind the per-task memory ramp (#7056)

## Other Changes

- chore(tools): correct the bindable-subblock rationale (#7091)
- chore(flags): remove released feature gates (#7087)
- chore(skills): drop Cursor Bugbot from the babysit review loop (#7059)

## Contributors

- @TheodoreSpeaks
- @icecrasher321
- @j15z
- @waleedlatif1

[View changes on GitHub](https://github.com/simstudioai/sim/compare/v0.8.11...v0.8.12)