Rius changelog

version

0.12.0 → 0.13.0

https://docs.glassflow.ai/llms.txt

− - [TypeScript reference](https://docs.glassflow.ai/rius/sdk/reference/typescript.md): Generated from the `@glassflow-ai/rius` 1.8.2 type declarations, covering the TypeScript SDK's public API surface. Wording fixes happen upstream in the SDK repository, never here.+ - [TypeScript reference](https://docs.glassflow.ai/rius/sdk/reference/typescript.md): Generated from the `@glassflow-ai/rius` 1.8.3 type declarations, covering the TypeScript SDK's public API surface. Wording fixes happen upstream in the SDK repository, never here.+ - [Failure modes](https://docs.glassflow.ai/rius/platform/alerts/failure-modes.md): Rius files every problem it finds in a run under a failure mode, named by a catalog id such as `CF-15`. The id is the same wherever you meet it: on a finding in the trace view, in an alert, and in the `failure_mode` argument of the MCP tools. This page lists every id in the catalog and what each one means.

https://docs.glassflow.ai/llms.txt

− - [Cursor (beta)](https://docs.glassflow.ai/rius/guides/coding-agents/cursor.md): The Rius plugin for Cursor turns each Cursor agent chat into a trace in Rius: your prompts, the agent's answers, every tool call, and the subagents it started. It works with the agent in the Cursor editor and with `cursor-agent` in the terminal. The plugin also brings the Rius MCP server, so you can ask Cursor about those chats.− - [Cursor (beta)](https://docs.glassflow.ai/rius/guides/coding-agents/cursor.md): The Rius plugin for Cursor turns each Cursor agent chat into a trace in Rius: your prompts, the agent's answers, every tool call, and the subagents it started. It works with the agent in the Cursor editor and with `cursor-agent` in the terminal. The plugin also brings the Rius MCP server, so you can ask Cursor about those chats.− - [Installation and configuration](https://docs.glassflow.ai/rius/sdk/installation.md): The Rius SDK for Python is published as `glassflow-rius` and imported as `rius`; it requires Python 3.10 or newer. The TypeScript SDK is published as `@glassflow-ai/rius` and requires Node 18 or newer.− - [Pydantic AI](https://docs.glassflow.ai/rius/sdk/integrations/pydantic-ai.md): Trace agents built with Pydantic AI with Rius: the framework is OpenTelemetry-native and emits its own spans for agent runs, model requests, and tool calls, so the whole structure arrives with no wrappers at all. This guide covers the Python framework; the runnable example behind it lives in agent-observability-examples.− - [Python reference](https://docs.glassflow.ai/rius/sdk/reference/python.md): Generated from the `glassflow-rius` 1.3.1 docstrings, covering the Python SDK's public API surface module by module. Wording fixes happen upstream in the SDK repository, never here.− - [TypeScript reference](https://docs.glassflow.ai/rius/sdk/reference/typescript.md): Generated from the `@glassflow-ai/rius` 1.5.0 type declarations, covering the TypeScript SDK's public API surface. Wording fixes happen upstream in the SDK repository, never here.− - [Upstream keys](https://docs.glassflow.ai/rius/interoperability/registry/upstream.md): The OpenTelemetry keys the Rius SDKs emit or read, referenced from the registries this one pins: core semantic conventions `v1.44.0` and the GenAI semantic conventions at `547934a`. Their definitions, types and stability are upstream's: each key links to it. What is ours is the requirement level Rius gives the key and the note on how Rius uses it.+ - [Cursor (beta)](https://docs.glassflow.ai/rius/guides/coding-agents/cursor.md): The Rius plugin for Cursor turns each Cursor agent chat into a trace in Rius: your prompts, the agent's answers, every tool call, and the subagents it started. It is built for the agent in the Cursor editor and for `cursor-agent` in the terminal. The plugin also brings the Rius MCP server, so you can ask Cursor about those chats.+ - [Cursor (beta)](https://docs.glassflow.ai/rius/guides/coding-agents/cursor.md): The Rius plugin for Cursor turns each Cursor agent chat into a trace in Rius: your prompts, the agent's answers, every tool call, and the subagents it started. It is built for the agent in the Cursor editor and for `cursor-agent` in the terminal. The plugin also brings the Rius MCP server, so you can ask Cursor about those chats.+ - [Installation and configuration](https://docs.glassflow.ai/rius/sdk/installation.md): The Rius SDK for Python is published as `glassflow-rius` and imported as `rius`; it requires Python 3.10 or newer. The TypeScript SDK is published as `@glassflow-ai/rius` and requires Node 18 or newer. Both SDKs are open source under the MIT license, on GitHub: Python and TypeScript.+ - [Pydantic AI](https://docs.glassflow.ai/rius/sdk/integrations/pydantic-ai.md): Trace agents built with Pydantic AI with Rius: the framework is OpenTelemetry-native and emits its own spans for agent runs, model requests, and tool calls, so the whole structure arrives with no wrappers at all. This guide covers the Python framework.+ - [Python reference](https://docs.glassflow.ai/rius/sdk/reference/python.md): Generated from the `glassflow-rius` 1.5.5 docstrings, covering the Python SDK's public API surface module by module. Wording fixes happen upstream in the SDK repository, never here.+ - [TypeScript reference](https://docs.glassflow.ai/rius/sdk/reference/typescript.md): Generated from the `@glassflow-ai/rius` 1.8.2 type declarations, covering the TypeScript SDK's public API surface. Wording fixes happen upstream in the SDK repository, never here.+ - [Context rot](https://docs.glassflow.ai/rius/platform/alerts/context-rot.md): An agent whose context window fills up, or whose history is silently dropped, keeps running and keeps answering. Nothing errors, so nothing tells you the answers got worse. Context rot is the pre-defined alert that finds these runs: it reads the token counts, finish reasons, and compaction markers your agents already send, and raises a finding when the context becomes a problem.+ - [Upstream keys](https://docs.glassflow.ai/rius/interoperability/registry/upstream.md): The OpenTelemetry keys the Rius SDKs emit or read, referenced from the registries this one pins: core semantic conventions `v1.44.0` and the GenAI semantic conventions at `2025935`. Their definitions, types and stability are upstream's: each key links to it. What is ours is the requirement level Rius gives the key and the note on how Rius uses it.+ - [Answers](https://docs.glassflow.ai/rius/answers.md): Short answers to specific questions about observing AI agents with Rius. Each answer stands on its own, and links to the full guide when you want the whole picture. To start from the guides, see Guides.+ - [Help](https://docs.glassflow.ai/rius/help.md): Stuck, found a bug, missing an integration, or have questions or feedback about Rius? Email help@glassflow.ai. We're building against real use cases and reply quickly.

repository_url

— → https://github.com/glassflow/rius-mcp-server

version

0.11.2 → 0.12.0