## TypeScript SDK v0.2.1
Published simstudio-ts-sdk@0.2.1 to npm.
### Installation
```bash
npm install simstudio-ts-sdk@0.2.1
```
### Documentation
See the [README](https://github.com/simstudioai/sim/tree/main/packages/ts-sdk) or the [docs](https://docs.sim.ai/sdks/typescript) for more information.
## Python SDK v0.2.1
Published simstudio-sdk==0.2.1 to PyPI.
### Installation
```bash
pip install simstudio-sdk==0.2.1
```
### Documentation
See the [README](https://github.com/simstudioai/sim/tree/main/packages/python-sdk) or the [docs](https://docs.sim.ai/sdks/python) for more information.
## Improvements
- improvement(audits): enforce console, helper, render-path, persist, and deployment-flag rules (#8559)
## Bug Fixes
- fix(deps): bump mammoth to 1.12.3 (#8568)
- fix(logging): name the driver cause and redact bound params in logged errors (#8565)
- fix(files): resolve chat uploads whose names are not in VFS form (#8566)
- fix(search): reuse managed MCP sessions within operations (#8567)
## Other Changes
- docs(agents): accurate guidance, guardrail map, and check:guidance-refs (#8557)
## Contributors
- @waleedlatif1
[View changes on GitHub](https://github.com/simstudioai/sim/compare/v0.9.10...v0.9.11)
## What's Changed
### Features
* feat(web): show error id in tRPC error toast and include it in issue reports by @niklassemmler in https://github.com/langfuse/langfuse/pull/17427
* feat(evals): add facet type, built-in protection, and rule idle time by @LysanderKie in https://github.com/langfuse/langfuse/pull/18144
### Fixes / Improvements
* feat(evals): show seven-day execution health in evaluator status by @wochinge in https://github.com/langfuse/langfuse/pull/18113
* feat(web): show view owner name or email on avatar hover by @nimarb in https://github.com/langfuse/langfuse/pull/18032
* fix(web): show full metadata JSONPath values in the modern session header by @nimarb in https://github.com/langfuse/langfuse/pull/18117
* fix(api): type read-side metadata on traces, observations and scores as objects by @niklassemmler in https://github.com/langfuse/langfuse/pull/18122
* fix(evals): preserve page header while loading by @wochinge in https://github.com/langfuse/langfuse/pu
## Features
- feat(workflows): compare deployment versions across UI and API (#8455)
- feat(files): render diff fences and theme mermaid diagrams (#8543)
- feat(dashboards): embed live dashboard panels in markdown (#8527)
- feat(chat): cycle available composer modes with Shift+Tab (#8511)
## Improvements
- improvement(audits): ratchet unused exports, explicit any, and file names (#8550)
- improvement(lint): strip comment noise and add check:comment-hygiene (#8551)
- improvement(cron): run stale execution and file version cleanup off the request path (#8535)
## Bug Fixes
- fix(db): pin the primary-key plan in the search retirement read-bound test (#8556)
- fix(cli): report authentication accurately and preserve file text (#8555)
- fix(files): align workbench reads with provenance policy (#8553)
- fix(accounts): report managed OAuth failures accurately (#8552)
- fix(slack): honor implicit Search approval during authorization (#8548)
- fix(mothership): bound stream recovery with a pe
## Features
- feat(library): What are the best marketing automation platforms for AI workflows in 2026? (#8520)
- feat(library): AI Agent Marketplace vs Building From Scratch: Where Sim Fits (#8519)
## Improvements
- improvement(search): run Search retirement as an operator command instead of a deploy step (#8522)
## Bug Fixes
- fix(chat): keep mention searches open and align resource menus (#8507)
- fix(seo): GEO hygiene — indexing, canonical URLs, llms.txt, docs redirects, library consolidation (#8508)
## Other Changes
- docs(library): update best-ai-agent-platforms-2026 (#8518)
- docs(library): update best-ai-agents-sales-crm-automation (#8517)
- docs(library): update best-ai-workflow-builders (#8516)
- chore(deps): update Next.js to 16.3.6 (#8510)
## Contributors
- @icecrasher321
- @waleedlatif1
[View changes on GitHub](https://github.com/simstudioai/sim/compare/v0.9.8...v0.9.9)
## What's Changed
### Features
* feat(web): add org-level ingestion overview tRPC route by @hassiebp in https://github.com/langfuse/langfuse/pull/18069
* feat(evals): track the evaluator onboarding funnel in PostHog by @Steffen911 in https://github.com/langfuse/langfuse/pull/18075
* feat(web): Org-level analytics view by @bezbac in https://github.com/langfuse/langfuse/pull/18082
* feat(web): add feature activation counts to org ingestion overview by @hassiebp in https://github.com/langfuse/langfuse/pull/18084
* feat(web): Improve org-level analytics view by @bezbac in https://github.com/langfuse/langfuse/pull/18090
* feat(sessions): Add tool filters to session table by @bezbac in https://github.com/langfuse/langfuse/pull/17884
### Fixes / Improvements
* fix(org-ingestion-stats): drop ingress sources by @hassiebp in https://github.com/langfuse/langfuse/pull/18083
* fix(web): add feature counts to org overview graph stories by @hassiebp in https://github.com/langfuse/langfu
## 🐞 Bug Fixes
* fix(engine): remove per-sandbox piece LRU (#15786) @amrdb
This restores the piece-loading fix from 0.91.3, which 0.92.0 was missing.
> 📌 **Upgrading a self-hosted instance?** Review the [Breaking Changes](https://www.activepieces.com/docs/install/reference/breaking-changes) page for any actions required before you upgrade.
## Thanks ❤️
@amrdb
## What's Changed
### Features
* feat(seeder): add incident-session scenario for the session timeline by @nkabardin in https://github.com/langfuse/langfuse/pull/18061
* feat(skills): track draft changes and fetch file contents by hash by @tobi12345 in https://github.com/langfuse/langfuse/pull/18062
### Fixes / Improvements
* fix(web): reword AI features data notice to "used to train models" by @nimarb in https://github.com/langfuse/langfuse/pull/18031
* fix(web): prevent metadata badge descenders from clipping by @wochinge in https://github.com/langfuse/langfuse/pull/18033
* fix(web): collapsed sidebar rows hide their label fully by @nmtrang29 in https://github.com/langfuse/langfuse/pull/18035
* fix(web): unify chevrons icon size by @nmtrang29 in https://github.com/langfuse/langfuse/pull/18003
* fix(ui): mark copy ClickHouse query as internal by @marcklingen in https://github.com/langfuse/langfuse/pull/18054
### Chores
* chore(pricing): add Claude Sonnet 5.5 default
# OpenBB V5 Changelog
OpenBB V5 is the new major-version line of the kept packages under `openbb_platform/` and `cli/`.
The `openbb` metapackage is now 5.0.0; the core, CLI, API, MCP server, routers and most providers are 2.0.0; exceptions include openbb-devtools (1.6.8 -> 2.0.1), openbb-charting (3.0.0 -> 4.0.0) and openbb-imf (2.1.3 -> 2.1.2 -> 3.0.0).
The repository license changed from AGPL-3.0-only to Apache-2.0 in [#7677](https://github.com/OpenBB-finance/OpenBB/pull/7677), in the root `LICENSE`, every `pyproject.toml` and the desktop app.
Eighteen directories present on develop are absent on v5 (sixteen provider packages, the openbb-regulators extension and the test-only `extensions/famafrench` tree); one provider, openbb-jodi 2.0.0, is new.
Headline changes: hatchling/uv packaging, the `openbb-core[pandas]` extra, ruff and ty, layered `openbb.toml` config, `OBBStream` streaming, decoupled charting, CLI 2.0 with `.spec` files and codegen, spec-driven platform-api
**This is the latest stable release (v2.0.0)**
This release always points to the most recent stable version.
For version-specific details and release notes, see: [ODP Desktop v2.0.0](https://github.com/OpenBB-finance/OpenBB/releases/tag/Open-Data-Platform-v2.0.0)
The `latest.json` file in this release is used by the auto-updater to check for new versions.
## Clef decision models
Ollama now supports [Clef](https://ollama.com/library/clef) and [Clef Flash](https://ollama.com/library/clef), Cloudflare's new open-source decision models, through `/v1/systemone`.
Clef (27B) and Clef Flash (9B) are multimodal: requests can now include images alongside the text state, shared by all questions and scored jointly with it.
```sh
curl http://localhost:11434/v1/systemone -d '{
"model": "clef-flash",
"state": "The user took this screenshot.",
"images": ["<base64-encoded image>"],
"questions": {
"has_ollama": {"type": "noul", "instructions": "Does this image contain Ollama?"}
}
}'
```
```
{
"model": "clef-flash",
"answers": {
"has_ollama": {
"type": "noul",
"noul": 0.958
}
},
"usage": {
"input_tokens": 548,
"output_tokens": 0
}
}
```
## What's Changed
* Models using web search can now perform up to ten searches per response, up from three
* Modelfiles now support
## Features
- feat(library): Best ChatGPT alternatives for building AI agents and automating workflows (#8414)
- feat(library): Best AI Workflow Builders for Small Teams in 2026 (#8413)
- feat(forks): opt-in fork sync for new workflows (#8318)
## Improvements
- improvement(search): accept several same-kind native queries per account and cap oversized read limits (#8407)
- refactor: remove dead code and enforce code quality gates (#8395)
## Bug Fixes
- fix(tables): settle a resume whose pause cannot be saved as failed, and never fail a completed run (#8417)
- fix(forks): route new workflows through one row builder and harden lineage locking (#8406)
- fix(logs): keep compacted child span trees shaped as trees (#8403)
- fix(knowledge): name embedding quota, key, and deadline failures in knowledge search (#8405)
- fix(knowledge): shrink the member lifecycle budget tests so they stop timing out in CI (#8404)
- fix(function): report code-placeholder compiler invariants as server failure
## What's Changed
### Features
* feat(topics): render and measure dedicated trace transcripts by @LysanderKie in https://github.com/langfuse/langfuse/pull/17925
* feat(native): prepare JS events and encode batches through NAPI by @sumerman in https://github.com/langfuse/langfuse/pull/17938
* feat(observability): label experiment query outcomes for SLOs by @marliessophie in https://github.com/langfuse/langfuse/pull/17996
* feat(worker): add the ClickHouse Native write strategy by @sumerman in https://github.com/langfuse/langfuse/pull/17939
* feat(ai-gateway): set trace environment from langfuse-environment header by @hassiebp in https://github.com/langfuse/langfuse/pull/17956
* feat(ai-gateway): capture full-mode inputs up to 5 MiB and mark omitted inputs by @hassiebp in https://github.com/langfuse/langfuse/pull/17960
* feat(transcript): expose current turn nesting level by @marliessophie in https://github.com/langfuse/langfuse/pull/18011
### Fixes / Improvements
* fix(exp
## Features
- feat(providers): add Kie provider for Claude, GPT, Grok, and Kimi models (#8391)
- feat(search): add HubSpot CRM member search (#8387)
- feat(providers): add Claude Sonnet 5.5 and make it the default model (#8385)
- feat(docs): OAuth scopes section on each integration page (#8382)
- feat(otter): add Otter.ai integration with triggers and knowledge base connector (#8381)
- feat(emails): introduce Desktop, CLI, and MCP newsletter (#8379)
- feat(search): read Drive documents and Gmail conversations (#8352)
- feat(library): AI Agent Workflow Builders for Multi-Step Tasks: 6-Platform Comparison (#8372)
- feat(library): How do you build an AI Slackbot without code? (#8371)
## Improvements
- improvement(chat): reuse shared overflow fades on scroll edges (#8390)
- improvement(tables): bump rows version once at commit and serialize same-value unique writes (#8335)
## Bug Fixes
- fix(chats): align organization shift-click selection with workspaces (#8389)
- fix(search): preser
## Decision models
Ollama now supports decision models through `/v1/systemone`, based on [TypeSafe’s Jev API](https://typesafe.ai).
Decision models return choices, probabilities, and scores instead of text. Use them for tasks such as ticket triage, model routing, and content classification.
Available models:
- [**Nimble**](https://ollama.com/library/nimble) from Bespoke Labs
- [**Tev1**](https://ollama.com/library/tev1) from Together AI
```sh
ollama pull nimble
```
Send context and one or more questions:
```sh
curl http://localhost:11434/v1/systemone \
-H 'Content-Type: application/json' \
-d '{
"model": "nimble",
"state": "Our checkout has returned 500 errors since 9am.",
"questions": {
"label": {
"type": "choice",
"instructions": "Which label fits this ticket?",
"criteria": {
"billing": "Payments and refunds",
"bug": "Software errors",
"account": "Login and account access"
## What's Changed
### Features
- Add support for native Gemini 3.8 Flash
- Implement evaluation of the last traced run through AMP in crewai eval
- Record the last traced run for crewai eval instead of printing it
- Improve platform integration setup UX
- Prioritize popular platform integrations
- Enhance tracing task spans to include declared output format and results
### Bug Fixes
- Fix visibility of the panel for viewing traces
- Resolve issue with turning tracing on and add an Evaluate button in the TUI
- Retry throttled provider calls in LLM
- Fall back to synchronous calls from acall in Bedrock
- Print areas graded by the evaluation in CLI
- Ensure link is shown after finalizing traces
- Keep Selenium driver reusable
- Close S3 response bodies properly
- Collapse multimodal content with shared helper
- Match roles in LLM overlay that differ only by surrounding whitespace
- Close SQLite connections in flow persistence and SQLite provider
- Preserve directory listing paths
### D
## Features
- feat(chat): add shared find menu (#8351)
- feat(search): expand live providers and discussion reads (#8340)
- feat(snowflake): add Cortex Analyst operations to the Snowflake block (#8347)
- feat(databricks): add Genie agent operations to the Databricks block (#8343)
## Improvements
- refactor(db): require a transaction for advisory lock helpers (#8364)
- improvement(knowledge): walk connector reconciliation by id so seen stamps stay off the index (#8334)
- improvement(knowledge): serve date tag filters from an index (#8348)
- improvement(db): drop unusable date slot and redundant prefix indexes (#8332)
- improvement(billing): share the enterprise reporting usage read across processes (#8325)
- improvement(db): tag advisory lock statements by caller (#8331)
- improvement(knowledge): maintain keyword projections only for search indexes (#8333)
- improvement(chat): stop reloading the full transcript on every turn and event (#8328)
- improvement(knowledge): scan processing
## Bug Fixes
- fix(search): read Confluence pages through the v2 API the Search grant allows (#8321)
- fix(tabs): preserve readable labels in crowded tab strips (#8319)
- fix(search): align landing layout and history rows with Home (#8317)
## Other Changes
- docs(library): update best-ai-agent-platforms-for-enterprise-teams-2026 (#8324)
- docs(library): update byok-multi-model-ai-agent-builder (#8323)
- chore(flags): drop leftover references to the retired async projection flag (#8320)
## Contributors
- @icecrasher321
- @waleedlatif1
[View changes on GitHub](https://github.com/simstudioai/sim/compare/v0.9.2...v0.9.3)