agent-runtime
Owns Upsonic's core agent execution surface: Agent, Task, Direct, graph/runtime primitives, streaming, structured output, and run control.
- License 许可
- MIT
- 最近更新
- 2026-10-08
- Stars
- ★ 11
- Forks
- 3
01 前言 Front Matter
- name
- agent-runtime
- license
- MIT
- metadata
- { "disco-role": "operating" }
- description
- Owns Upsonic's core agent execution surface: Agent, Task, Direct, graph/runtime primitives, streaming, structured output, and run control.
- disable-model-invocation
- true
02 资源文件 2
- 参考文档references/api-reference.md2.6 KB
- 参考文档references/troubleshooting.md1.5 KB
03 SKILL.md 正文
agent-runtime
Use this route for the core execution APIs: Agent, Task, Direct, graph/runtime primitives, streaming, structured output, timeouts, partial results, and run control.
Include
AgentandTaskorchestration.Directfor direct model calls without the full agent pipeline.- Runtime primitives such as
Graph, run state, context handling, streaming, and cancellation/timeout behavior. - Structured-output and cache-related runtime behavior when the question is about a task run rather than the provider or storage backend.
Exclude
- Model/provider selection and credentials → models-and-providers
- Tools, MCP, or agent-as-tool wiring → tools-and-mcp
- Session persistence and chat history → chat-memory-storage
- Policies, reflection, reliability, tracing, or evals → quality-safety-governance
- Teams, autonomous agents, prebuilt agents, Ralph, and simulation loops → teams-autonomous-prebuilt
Start here
04 同仓库更多 Skills
obsidian-clipper-template-creator
Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.
obsidian-clipper-template-creator
Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.
python-api
Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP/mAP semantics, and source-style import diagnostics.
file-evaluation
Folder-based PASCAL VOC AP/mAP evaluation from ground-truth and detection text files.
object-detection-metrics
Guides legacy Object-Detection-Metrics PASCAL VOC AP/mAP evaluation from detection text folders and direct Python API classes.
nx-workspace-patterns
Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.