--- title: "Langfuse October Update" description: "Skill management, redesigned session view, scoped API keys, Python SDK v5 and JS/TS SDK v6, Langfuse Government and more" ogImage: /images/blog/2026-10-31-langfuse-october-update/skill-management.png tag: update date: 2026/10/31 author: "Marc" --- October brought skill management to Langfuse: store, version, and trace agent skills the way you already manage prompts. Alongside it, a new session view and API keys you can scope and expire. 🥁 Join us on Thursday, November 12, for the Langfuse Community Town Hall. We'll talk about a big release coming next week and the updated roadmap we're finalizing right now. As always, we'll also demo all the new capabilities we've shipped since the last Town Hall. → [Sign up for the Town Hall](https://luma.com/lvp5fx33) ## Skill management ![Skill management](/images/blog/2026-10-31-langfuse-october-update/skill-management.png) Next to prompts, you can now store and version agent skills in Langfuse. A skill is a `SKILL.md` with task instructions plus optional supporting files. Create skills in the UI, push a local folder, or publish through the API, CLI, MCP, and SDKs. Each version saves the complete set of files, and labels let you promote or roll back a version without changing application code. With skill tracing configured, generations show which skills have been used. The skill's usage tab combines usage counts, file loads, and linked observations. → [Read more](/docs/skill-management/overview) ## Redesigned session view ![Redesigned session view](/images/blog/2026-10-31-langfuse-october-update/session-view.png) The session view now shows user and assistant messages across traces as one continuous conversation. A sidebar navigates messages, traces, and tool usage, so you can follow where an interaction went off track and jump to the trace behind it. → [Read more](/changelog/2026-10-13-redesigned-session-view) → [Post feedback here](https://github.com/orgs/langfuse/discussions/18687) ## Scoped API keys and expiration dates ![Scoped API keys and expiration dates](/images/blog/2026-10-31-langfuse-october-update/scoped-api-keys.png) Project API keys now carry permissions: Full access, Viewer, Ingestion, or Scores ingestion. Instrument an application with a key that can send traces but cannot read your prompts or datasets, or collect user feedback from a web app with a key that can only submit scores. You can also now set an expiration date for your keys. Existing keys keep working as they are. → [Read more](/changelog/2026-10-16-project-api-key-permissions) ## More decision models: OpenAI and System One ![More decision models: OpenAI and System One](/images/blog/2026-10-31-langfuse-october-update/decision-models.png) Decision-model evaluators now run on OpenAI's gpt-6-luna through the Decisions API, and on any model that serves TypeSafe's System One API, such as Subquadratic's SubQ Snap or the open-weights Strands Decider you host yourself. Choice, Score, and Yes/no questions work unchanged, so you can use whichever model fits your cost and latency budget. The Langfuse MCP server also supports decision-model evaluators (API/CLI coming soon). → [Read more](/docs/evaluation/evaluation-methods/decision-models) ## Python SDK v5 and JS/TS SDK v6 ![Python SDK v5 and JS/TS SDK v6](/images/blog/2026-10-31-langfuse-october-update/sdk-majors.png) Both majors are built for Langfuse v4 and mostly remove APIs that were already deprecated, so for most users the upgrade is a version bump. New: `experiment_url` / `experimentUrl` links straight to the comparison view, nested metadata becomes filterable dotted paths, span batches are gzip-compressed, and scores are created in batches. If you self-host, both need Langfuse v4.59.0 or later. → [Read more](/changelog/2026-10-14-python-sdk-v5-js-sdk-v6) ## Langfuse Government For government and other highly regulated environments, Langfuse Self-Hosted Government offers a FIPS mode that runs on FIPS 140-3 validated cryptographic modules and hardened images built on Iron Bank's Red Hat UBI 9. → [Read more](/self-hosting/configuration/hardening) → [Talk to us](/talk-to-us) ## New integrations - Claude Platform: trace the Messages API and Managed Agents with native OpenTelemetry export ([docs](/integrations/model-providers/claude-platform)) - Cursor: trace Cursor agent sessions, including prompts, tool calls, subagents, and token usage ([docs](/integrations/developer-tools/cursor)) - Slack: The Langfuse Slack app is now listed in the Slack Marketplace and lets you get notified for alerts or prompt changes ([changelog](/changelog/2026-10-30-slack-marketplace)) ## Fixes & improvements - Feat: The Experiments page now shows the trade-off between quality, cost, and latency across your runs ([changelog](/changelog/2026-10-19-experiments)) - Feat: Configure LLM connections once at the organization level and share them with every project; a project connection with the same name takes precedence ([changelog](/changelog/2026-10-14-organization-llm-connections)) - Feat: Usage breakdown chart by project or type with CSV export, on the Billing page on Cloud and a new Usage page when self-hosting ([changelog](/changelog/2026-10-06-organization-usage-breakdown)) - Data: Scheduled blob storage exports can include score metadata and provenance, such as the evaluator, annotation queue, and execution trace behind each score ([changelog](/changelog/2026-10-22-blob-storage-score-field-groups)) - Data: Google Cloud Storage as an export target, with a service account key or ADC ([docs](/docs/api-and-data-platform/features/export-to-blob-storage)) - Cost: Prompt cache hit rate shown on traces ([v4.60.0](https://github.com/langfuse/langfuse/releases/tag/v4.60.0)) - UX: Cmd+K jumps to prompts, datasets, annotation queues, and evaluators, and offers create actions and recent picks ([v4.70.0](https://github.com/langfuse/langfuse/releases/tag/v4.70.0)) - API: `POST /api/public/scores` accepts batches ([v4.55.0](https://github.com/langfuse/langfuse/releases/tag/v4.55.0)) - Evals: Evaluator gallery restyled with score previews; evaluator status shows seven-day execution health ([v4.60.0](https://github.com/langfuse/langfuse/releases/tag/v4.60.0)) - Self-hosting: Outbound host allowlists for LLM connections, webhooks, media, and blob storage endpoints ([docs](/self-hosting/configuration/hardening#outbound-url-allowlists)) - Self-hosting: Guide to export application logs to ClickStack ([docs](/guides/export-self-hosted-langfuse-logs-to-clickstack)) - and many more! ## Blog - [How we built Halo](/blog/2026-10-21-building-the-langfuse-assistant): Ben on building our in-app assistant on the MCP server, why the agent runs outside its sandbox, and how background runs work - [Customer story: DKB](/users/dkb): how DKB keeps an AI banking assistant for around 6 million customers accurate and compliant with self-hosted Langfuse, with engineers and customer service experts working in the same place - Two guides for platform teams: [Provisioning and governing Langfuse across teams](/blog/2026-10-22-provisioning-and-governing-langfuse-across-teams) and [Operating Langfuse as an internal service](/blog/2026-10-22-operating-langfuse-as-an-internal-service) ## Reminder: Langfuse v4 cutover on November 16 Langfuse Cloud becomes v4-only on November 16, 2026. Open the Migration Assistant in the sidebar; if it lists required actions for your project, finish them before the cutover. → [Upgrade guide](/faq/all/upgrade-to-langfuse-v4) --- ## Agent Instructions This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/blog/2026-10-31-langfuse-october-update.md`. ### Querying these docs If the answer is not on this page, query the documentation instead of guessing: - **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question: ```bash curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?" ``` - **Index of every page**: , with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt). ### Before writing Langfuse code - **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results. - **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application. - **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples. - **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx @langfuse/cli api `) to read or write traces, prompts, datasets, and scores from the terminal. Found an error in these docs? Please open an issue at .