Features
- feat(changelog): workspace changelog of releases with markdown bodies and the Sim changelog tool (#8859)
- feat(library): AI Agents for Asana and monday.com Task Automation: Platform and Workflow Guide (#8847)
- feat(sim-cli): publish which CLI commands Mothership is refused, from the route admission rule (#8838)
- feat(shopify): expand operations and refresh expiring credentials (#8833)
- feat(checkr): add Checkr integration with tools, block, and webhook triggers (#8824)
- feat(tests): workflow tests as a workspace resource (#8773)
- feat(library): Enterprise AI Agent Compliance and Deployment Guide: HIPAA, GDPR, Data Residency, On-Prem, and VPC (#8822)
- feat(changelog): publish curated product updates (#8787)
- feat(analytics): attribute sign-ups and demo requests to their acquisition source (#8815)
- feat(dashboards): add empty-state graphic for the dashboard page (#8719)
- feat(oracledb): add Oracle Database integration (#7378)
- feat(library): 6 Best AI Agent Marketplaces and Template Libraries in 2026 (#8806)
- feat(library): How Do You Build a Salesforce AI Lead-Scoring Agent With Sim? (#8804)
- feat(oracle-epm): add validated integration foundation (#7469)
- feat(oracle-fusion): add validated integration foundation (#7427)
- feat(oci): add validated native integration foundation (#7444)
- feat(integrations): add saved Ramp and Vanta credentials (#8802)
Improvements
- improvement(ci): fix the stripe-sync flake, stop helm cancelling a publish, attest via actions/attest (#8873)
- improvement(app): show branded wordmark while loading (#8879)
- improvement(logs): log each execution failure once at its owning boundary (#8872)
- improvement(sim-cli): commands reach the API only through the operations they declare (#8877)
- improvement(changelog): refresh media and released product updates (#8866)
- improvement(logs): cut recurring production log noise and fix the bugs behind it (#8871)
- improvement(diff): refine embedded diff presentation (#8862)
- improvement(editor): refine previews and compact formatting controls (#8860)
- improvement(mobile): refine responsive chat and workspace layouts (#8842)
- improvement(desktop): make file consent clearer and easier to control (#8835)
- improvement(emcn): refine shared menu and picker styling (#8836)
Bug Fixes
- fix(chat): keep composer drafts across hydration (#8892)
- fix(chat): contain mobile composer scrolling (#8889)
- fix(tools): stop provider timeout params from becoming the request deadline (#8878)
- fix(docs): render the FAQ JSON-LD as a native script tag, and forbid data-typed next/script (#8875)
- fix(webhooks): stop admission-refusal retry loops and per-retry log writes (#8870)
- fix(oauth): record revoked refresh tokens durably and surface them as reconnect (#8868)
- fix(billing): let operators resolve billing dead letters and stop re-paging old ones (#8869)
- fix(pii): stop one half-emoji from failing log redaction (#8867)
- fix(sim-cli): the command inventory describes the operation each command runs (#8874)
- fix(files): refuse Chat current-file reads no provenance observer records (#8864)
- fix(deploy): return deployed-version lint as its own field, opt-in and time-bounded (#8863)
- fix(sim-cli): an unknown option on a command with no options says so (#8865)
- fix(mothership): show the copy control for API keys created in organization chat (#8861)
- fix(tests): purge deleted tests, bill their storage, and record versions as loaded (#8858)
- fix(credentials): allow encoded Oracle connection payloads (#8856)
- fix(desktop): open Folder Access from a focused utility window (#8855)
- fix(lint): describe unquoted JSON references as failing only when the text is not itself JSON (#8854)
- fix(sim-cli): an unknown option lists the command's own flags (#8845)
- fix(files): refuse delegated version reads no provenance observer records (#8843)
- fix(mothership): let Chat share credentials and request access as the delegating member (#8840)
- fix(mothership): let Chat read its own permission config and file version history (#8839)
- fix(workflows): stop flagging whole-field references in JSON fields and correct the quoting advice (#8837)
- fix(settings): decouple access settings from usage analytics (#8828)
- fix(invitations): let Chat invite teammates through the workspace invitations command (#8834)
- fix(desktop): require folder permission for native file tools (#8345)
- fix(providers): remove default agent tool-call iteration cap (#8829)
- fix(mcp): add directory verification compatibility (#8825)
- fix(mcp): declare request bodies and annotation titles (#8827)
- fix(desktop-browser): ask the user before a page's alert, confirm, or leave-site prompt is answered (#8432)
- fix(tables): drop the per-table row-order lock from inserts (#8811)
- fix(tables): log row writes to the change log instead of locking the table definition row (#8765)
- fix(google-ads): align reporting with current API access (#8812)
- fix(db): retire unused keyword search projections (#8810)
- fix(billing): acknowledge Stripe webhooks whose subscription references a missing organization (#8809)
- fix(files): support arbitrary uploads and in-document links (#8807)
- fix(workflows): lint unquoted string references in JSON fields and surface lint on deploy (#8803)
Other Changes
- chore(audits): check raw-route parseRequest contracts and enforce surface-neutral application imports (#8883)
- chore(tests): tighten check:test-patterns and shrink its baseline (#8886)
- docs(agents): align agent guidance with code and enforced checks (#8887)
- chore(naming): rename 41 baselined files to the file-name convention (#8884)
- chore(audits): name generated-artifact checks check: so run-audits discovers them (#8882)
- chore(api): give colliding error helpers domain names, drop VFS pass-through wrappers (#8885)
- chore(audits): drop dead ESLint directives and redundant check:dead-code; fix the PPTX blend-group call they hid (#8876)
- chore(google-ads): remove synthetic E2E suite (#8857)
- docs(library): update best-ai-agent-marketplaces-template-libraries (#8846)
- docs(library): update best-ai-automation-tools-2026 (#8848)
- docs(library): update best-ai-agents-for-scheduling-and-calendar-management-in-2026 (#8849)
- docs(library): update ai-agents-vs-rpa (#8850)
- docs(library): update best-ai-agent-platforms-2026 (#8851)
- docs(library): update how-to-create-an-ai-agent (#8852)
- test(credentials): cover Chat's OAuth-only, admin-demotion and integrations guards on credential sharing (#8844)
- docs(library): update best-zapier-alternatives (#8820)
- docs(library): update open-source-ai-agent-platforms (#8821)
- docs(library): update best-ai-agents-sales-crm-automation (#8823)
- chore(integrations): refresh catalog and Microsoft branding (#8816)
- chore(config): retire unused env vars and fully-rolled-out feature flags (#8808)
- docs(library): update best-ai-agents-support-ticket-triage (#8805)