Features

• feat(demo): auto-confirm demo bookings that came through the verified form and decline the rest (#9976)

Improvements

• improvement(desktop-browser): let a page finish rendering before observing an action (#9985)
• improvement(search): shorter Jira any-term budget and a shared batched read budget (#9984)
• improvement(executor): run the Agent block on the shared model-fallback walk (#9982)
• improvement(computer-use): allow every app by default, protect sensitive apps, and make per-app approval optional (#9980)
• improvement(credentials): resolve agent fallback credentials once, Vanta 401 grace, true refusal codes, headless client-credential modes, and registry cleanups (#9977)

Bug Fixes

• fix(credentials): replay remembered refusals as credential errors, derive the delegable Google services list, and correct a fallback TSDoc (#9993)
• fix(credentials): offer keyless Google delegation only for services that can be delegated (#9992)
• fix(aws-marketplace): confirm a container license lapse on a second re-check before switching Enterprise off (#9991)
• fix(computer-use): refuse Script Editor, Automator and Shortcuts, which run shell commands outside the Terminal control (#9990)
• fix(search): check the last shortened read window against its budget (#9987)
• fix(pii): mask texts over spaCy's length limit and drop encoded files from logs (#9979)
• fix(aws-marketplace): check the container license with CheckoutLicense so AWS's standard buyer policy works (#9981)
• fix(docker): ship the realtime and migrations images with runtime dependencies only (#9983)
• fix(desktop): weak-link ScreenCaptureKit so the Computer Use helper loads on macOS 14 and 15 (#9978)
• fix(docs): copy section permalinks and polish outline navigation (#9972)
• fix(api): match pause points with jsonb_path_exists so a status-filtered run list stays fast (#9971)

Other Changes

• chore(pii): drop the over-long text example from the mask client's outage comment (#9989)
• chore(upgrade): drop the stale Cal.com comment on the sales demo link (#9988)
• chore(analytics): remove Freebuff ad tracking and the Beluga short-link rewrite (#9974)

Contributors

• @waleedlatif1

View changes on GitHub

Features

• feat(credentials): configurable audience for keyless AWS, Databricks, Snowflake, Microsoft, and Google credentials (#9962)
• feat(gitlab): add permission CSV exporter (#9955)
• feat(computer-use): enable computer use by default, governed by a permission-group restriction (#9944)
• feat(library): How to Build a Shopify AI Agent for Orders and Inventory (#9940)
• feat(library): AI Agent Platform Vendor Viability: Funding, Adoption, and Staying Power Compared (#9941)
• feat(aws-marketplace): bill a listing's LLM usage to AWS through a per-period metering tally (#9921)
• feat(credentials): saved PostgreSQL, MySQL, and SQL Server connections (#9929)
• feat(credentials): second auth modes for ServiceNow, Snowflake, Infisical, and Google Ads (#9928)
• feat(knowledge): let the S3 connector sync with a saved AWS credential (#9934)
• feat(credentials): saved credentials for Amplitude, Kalshi, Splunk, CB Insights, Railway, and Qdrant; fix Kalshi Ed25519 signing (#9927)
• feat(credentials): Microsoft app credentials for Power BI and Azure Data Explorer, with national clouds (#9931)
• feat(credentials): keyless Google Workspace domain-wide delegation via IAM signJwt (#9933)
• feat(credentials): record, show, and explain saved token expiry (#9930)
• feat(bedrock): run Bedrock models with a saved AWS credential (#9932)
• feat(credentials): regional and instance hosts for saved LaunchDarkly, LangSmith, New Relic, Square, SendGrid, Hex, and Sentry credentials (#9926)
• feat(apollo): add optional OAuth connections (#9922)
• feat(aws-marketplace): sell several listings from one integration through a product catalog (#9920)

Improvements

• improvement(desktop-browser): click through a nested control that fills the whole target (#9956)
• improvement(desktop-browser): stable element refs, wait observations, and fewer false refusals (#9953)
• improvement(aws-marketplace): close billing gaps and simplify the license write paths (#9946)
• improvement(credentials): keep valid client-credential tokens through refresh outages and pace token retries by failure kind (#9925)
• improvement(changelog): cover meaningful product updates through v0.9.54 (#9809)

Bug Fixes

• fix(credentials): point the AWS keyless hint at the policy audience, quote the docs client ID, and correct a stale comment (#9970)
• fix(aws): round-trip typed DynamoDB cursors and allow percentile-only CloudWatch statistics (#9967)
• fix(desktop-browser): give a wait's closing snapshot a full budget and confirm ref reuse names the same element (#9966)
• fix(executor): resolve saved model credentials inside each fallback attempt in Router and Evaluator (#9968)
• fix(integrations): return the Dataverse page size and correct Contacts search outputs (#9965)
• fix(tests): close three integration-test races that flaked CI (#9964)
• fix(integrations): final review pass for the Atlassian and AWS sweeps (#9961)
• fix(integrations): close stale and empty value leaks from the Google and Microsoft sweeps (#9960)
• fix(desktop-browser): refuse reissued earlier refs and recover from uncommitted ref reuse (#9959)
• fix(gitlab): require confirmed emails in permission exports (#9958)
• fix(aws): validate AWS integrations against SDK and API docs (#9952)
• fix(atlassian): validate Jira, Confluence, JSM, Bitbucket, Trello against vendor docs (#9950)
• fix(microsoft): validate Microsoft integrations, return dropped fields and expose missing params (#9949)
• fix(google): close post-merge verification gaps from the Workspace sweep (#9954)
• fix(google): validate Workspace integrations, return dropped fields and expose missing params (#9947)
• fix(mothership): back off the transport poll instead of retrying every second (#9945)
• fix(credentials): Splunk password sign-in, Snowflake key pair in the CLI, Apollo OAuth people search, and one short SailPoint throttle wait (#9943)
• fix(api): report a finished run's real status once its pauses have settled; show the request id in the CLI (#9924)

Other Changes

• chore(integrations): tidy two comments left by the Google/Microsoft sweep (#9969)
• chore(api): describe the settled-pause rule in the run status overlay TSDoc (#9957)
• revert(library): restore orchestration and governance posts to before #9938 and #9939 (#9951)
• docs(library): remove duplicate questions in orchestration and governance posts (#9948)
• docs(library): update govern-ai-agents-multiple-teams-enterprise-workspace (#9939)
• docs(library): update ai-agent-orchestration-frameworks-explained (#9938)
• docs(library): update enterprise-ai-agent-compliance-deployment-guide (#9937)

Contributors

• @waleedlatif1

View changes on GitHub

A Helm chart for Sim - the open-source AI workspace where teams build, deploy, and manage AI agents

A Helm chart for Sim - the open-source AI workspace where teams build, deploy, and manage AI agents

Features

• feat(aws-marketplace): gate Enterprise on the AWS Marketplace container license and add the EKS install profile (#9917)
• feat(credentials): audit fixes and non-OAuth auth for CrowdStrike, Datadog, Gong, PlanetScale, SailPoint, ServiceNow, Zendesk, ZoomInfo, Shopify, Atlassian, Linear and Twilio (#9911)
• feat(api): failing block on polled runs, deployed input schema, paused-runs list, and applied limits (#9906)
• feat(api): workflow outline, workspace schedules list, clearer v2 errors, and catalog value types (#9905)
• feat(api): agent identity on v2 meta, scoped CLI pairing keys, and v2 workspace rename (#9904)
• feat(table): add Columns to Return to the legacy Table block's Query Rows (#9887)
• feat(library): Best AI Agents for Spreadsheet Analysis in Excel and Google Sheets (#9886)
• feat(library): Best AI Agents for GitHub Pull Requests, Issue Triage, and Code Review (#9884)
• feat(library): Best AI Agent Platforms for HR Teams Answering Employee Questions (#9883)

Improvements

• refactor(credentials): resolve Vanta tokens through the coordinated client-token resolver (#9919)
• improvement(table): document that a column selection matching no column returns empty row data (#9915)

Bug Fixes

• fix(credentials): age-gate 403 token eviction and tidy the client-credential paths (#9918)
• fix(api): attribute a polled run's failure only to the block that caused it (#9916)
• fix(credentials): match JSON 403s case-insensitively and refuse a malformed ZoomInfo access token (#9914)
• fix(security): refuse an extra slash after https:// in typed base URLs (#9913)
• fix(api): release-audit follow-ups for the agent API work (#9910)
• fix(http): keep unwrapping legacy success envelopes for existing workflows (#9909)
• fix(selectors): redact email path segments from provider failure logs; correct table timeout guidance (#9908)
• fix(workflows): refuse operation edits that would overwrite a concurrent change (#9902)
• fix(chat): bring a restored workflow's chat back online when it is relaunched (#9888)
• fix(http): stop treating 200 bodies with status and data keys as proxy responses (#9889)
• fix(tables): show rejected filter errors in the grid and fill imports to the row limit (#9881)
• fix(errors): actionable table read timeouts, 409 for duplicate custom tools, Instagram revocation, selector failure logs (#9880)

Other Changes

• chore(deps): tidy comments and override order from the dependency sweep (#9907)
• docs(api): guide for building and running workflows with the API (#9901)
• chore(deps): update minor and patch dependencies past the release-age gate (#9894)
• chore(deps): bump turbo to 2.11.10 (#9903)
• chore(deps): bump AWS SDK to 3.1162.0, OpenTelemetry to 0.223.0/2.12.0, and @daytona/sdk to 0.227.3 (#9900)
• chore(deps): upgrade docx to 9.15.2 (#9895)
• chore(deps): bump mdast-util-to-markdown to 2.2.2 (#9899)
• chore(deps): bump tiptap to 3.32.2 and keep headings that open a list item (#9898)
• chore(deps): bump knip to 6.44.1 (#9896)
• chore(deps): bump streamdown to 2.7.1 (#9897)
• chore(deps): bump electron-builder to 26.18.0 (#9893)
• chore(deps): upgrade monaco-editor to 0.57.0 (#9892)
• chore(deps): upgrade cronstrue to 3.38.0 (#9891)
• docs(library): update postgres-mcp-server-ai-agents (#9885)
• docs(library): update best-ai-agents-sales-crm-automation (#9882)
• chore(api-keys): remove the api-key-read-only flag now that read-only keys are live (#9879)

Contributors

• @waleedlatif1

View changes on GitHub

A Helm chart for Sim - the open-source AI workspace where teams build, deploy, and manage AI agents

Features

• feat(credentials): set up keyless credentials from the v2 API, CLI and Sim MCP (#9875)
• feat(credentials): keyless Snowflake, Microsoft app-only and Google keyless, GitHub and Bitbucket tokens, DocuSign JWT (#9869)
• feat(mistral): extract PDF images as files and expose table format in Mistral Parser (#9856)
• feat(api): run a pinned deployment version and expose paused run points in v2 (#9854)
• feat(api-keys): read-only API keys and expiry at creation (#9855)
• feat(api): workflow trigger health and enablement through the v2 API (#9853)
• feat(network): honor HTTP_PROXY, HTTPS_PROXY and NO_PROXY for guarded requests, AWS SDK clients and OTLP export (#9851)
• feat(credentials): saved credentials for 21 token-and-host blocks on one host-aware check factory (#9849)
• feat(api): manage workspace members through the v2 API (#9852)
• feat(credentials): saved credentials for 17 more blocks, GitLab tokens, and keyless hardening (#9840)
• feat(search): manage source permissions through a shared API and CLI (#9845)
• feat(search): update GitLab permission CSVs through the API (#9841)
• feat(library): AI Agent Development Company vs Building In House: How to Decide (#9844)
• feat(library): Best AI Agent Platforms That Support the A2A Protocol in 2026 (#9843)
• feat(library): AI Agent Builders With Built-In Web Search and Research Tools in 2026 (#9842)
• feat(credentials): saved credentials and credential-only block versions, with keyless AWS/Databricks OIDC (#9763)

Improvements

• improvement(api): release audit follow-ups for v2 member analytics, workflow access middleware and docs (#9858)
• improvement(search): return a longer live read window when an MCP client asks for more chunks (#9823)

Bug Fixes

• fix(credentials): correct keyless setup instructions and enforce the saved-credential contract on every credential block (#9878)
• fix(mistral): say V3 parses an uploaded or referenced PDF, and bound Max Images at 100 (#9872)
• fix(release): host_not_allowed for refused hosts, internal-JWT-only secret release, and final release-audit cleanups (#9870)
• fix(sim-setup): stop doctor --fix from turning ${VAR} references into literals (#9868)
• fix(credentials): report a refused host as the user's input, persist normalized account ids, cap Databricks reads (#9859)
• fix(release): keyless subject uniqueness, NO_PROXY IPv6/CIDR, proxied boot secret, and remaining audit follow-ups (#9866)
• fix(release): small release-audit cleanups (#9863)
• fix(release): reuse only full-access delegation keys and treat a blank crawl depth as unset (#9857)
• fix(security): harden saved-credential, proxy egress, and keyless-mint paths from the release audit (#9865)
• fix(release): redact deploy keys, check operation-backed tools in the saved-credential contract, and drop SDK copy (#9864)
• fix(release): run pinned async versions on their own variables, map CLI key-creation errors, show GitLab tokens as the current block (#9862)
• fix(sim-setup): quote env values containing $ so dotenv, Bun, and Compose don't expand them (#9861)
• fix(release): cap proxied plain-http responses, count Firecrawl depth from the start URL, and drop stale route cache on upgrade (#9860)
• fix(firecrawl): complete v2 response and depth compatibility (#9847)
• fix(cli): bind sim-setup's containers to loopback, fix reset and env quoting, retire the legacy simstudio CLI (#9830)
• fix(docker): keep ISR and suffix-list caches writable on a read-only root (#9829)

Other Changes

• test(api-keys): use a neutral database role name in the internal-error fixture (#9877)
• test(credentials): use a non-token-shaped GitHub fixture so secret scanning stays quiet (#9876)
• docs(release): correct the Discord allowlist note, Mistral image naming, and the NO_PROXY reference (#9874)
• docs(skills): name refuseUnsafeTypedUrl in the add-integration token-credential steps (#9873)
• chore(sdk): use a live release family as the desktop feed's unrelated-release fixture (#9850)
• chore(sdk): remove the TypeScript and Python SDKs (#9848)
• chore(deps): take vitest 5.1, shiki 4.6, react-hook-form 7.91, MCP SDK 2.4, and small in-range updates (#9846)
• chore(deps): upgrade pi to 1.5.0 (#9826)
• ci: bump the actions group across 2 directories with 7 updates (#9839)

Contributors

• @dependabot[bot]
• @waleedlatif1

View changes on GitHub

A Helm chart for Sim - the open-source AI workspace where teams build, deploy, and manage AI agents

Bug Fixes

• fix(docs): polish code rendering and keyboard navigation (#9827)
• fix(next): align with route-handler framing in 16.4.5 and hash Bun patches into turbo tasks (#9822)
• fix(trigger): keep each worker's egress gateway address out of the env sync (#9821)

Other Changes

• chore(deps): move e2b to 2.62.1 and drizzle-kit to 0.31.11 (#9825)
• test(e2e): stop requiring Content-Length on streamed Route Handler downloads (#9824)
• chore(deps): take the Next.js 16.4.5 security release, patch node-gyp's undici, and refresh in-range patches (#9819)
• chore(deps): drop the expired Trigger.dev release-age exemption (#9818)

Contributors

• @waleedlatif1

View changes on GitHub

Features

• feat(models): add Claude Fable 5.2 (#9816)
• feat(library): Moving AI Agent Prototypes Into Production: A Practical Guide (#9813)
• feat(library): 10 Self Hosted AI Agent Use Cases for Engineering Teams (#9812)
• feat(library): AI Agent Platforms for Running Your Own Fine Tuned Models Compared (#9811)

Improvements

• improvement(search): run Search MCP calls whose arguments have one reading, and log rejected ones (#9814)
• improvement(search): tell clients a Gmail result shows only its message's opening (#9807)
• improvement(landing): surface enterprise identity and audit controls where agents read (#9806)
• improvement(search): refuse a live chunk index before the provider read (#9805)

Bug Fixes

• fix(landing): render the Enterprise plan note in llms.txt as its own paragraph (#9817)

Other Changes

• docs(library): update slack-ai-agent-security-permissions-guide (#9810)

Contributors

• @waleedlatif1

View changes on GitHub