domino-python-sdk

Call Large Language Models through Domino LLM Gateway 2.0, the centrally governed gateway extension an administrator installs in front of external providers and Domino-hosted models. Covers finding and detecting the gateway, authentication with the in-run access token (fresh per call) or a Personal Access Token outside Domino, model aliases and model discovery, the OpenAI-compatible and Anthropic-compatible paths from the OpenAI and Anthropic SDKs, Pydantic AI, LangChain and plain HTTP, streaming, attribution headers, refused calls (login redirect, grants, budgets, guardrails), pointing a coding assistant such as Claude Code or Codex at the gateway, and what the administrator configures. Use when a user mentions LLM Gateway, Gateway 2.0, a gateway alias or URL, asks how to call a model through the Domino gateway, how to run a coding assistant through it, why a gateway call was refused, or what the gateway administrator must set up.

Automate Domino endpoints (Model APIs) and registered models over REST. Covers the /api/modelServing/v1 lifecycle (create an endpoint from a file or a registered model, add versions, poll deployment status, list, update replicas or hardware tier, archive, build and instance logs), registered models v1 vs v2 routes, MLflow tracking vs the registry API, management URL vs prediction URL, and sync Basic vs async Bearer prediction auth. Use when scripting deployments from CI, a Job or a notebook, registering a model version by API, or debugging stop, archive and delete behaviour. For UI publishing, the predict function, scaling and health settings use domino-model-endpoints; for drift and quality monitoring use domino-model-monitoring; for exporting a model out of Domino (image to your registry, NVIDIA Fleet Command, Snowflake UDF, SageMaker) or batch scoring Jobs use domino-model-delivery.

Monitor production models in Domino for data drift and model quality. Covers the two workflows (integrated monitoring for Domino endpoints with prediction capture, and Model Monitor for models served elsewhere), the DataCaptureClient prediction-capture library, registering training sets, prediction data and ground truth with the Monitoring Config JSON, drift tests and thresholds, scheduled checks and notifications, where captured predictions live, remediation, and the Model Monitoring REST API including custom metrics. Use when setting up monitoring for an endpoint, registering an external model, ingesting ground truth, reading drift or quality results by API, or automating retraining on drift.

Publish and call Domino endpoints (model APIs) for synchronous or asynchronous predictions. Covers the prediction function and request JSON, how the endpoint image is built (environment, required packages, no requirements.txt), sync Basic-auth vs async Bearer invocation, versions and routing, instance counts and endpoint hardware tiers, health checks, metrics and logs. Use when deploying a model as an API from the UI, writing predict code, calling an endpoint, or debugging a slow or failing endpoint. For scripted lifecycle automation over REST (create, version, archive, logs) use domino-model-serving; for drift and model-quality monitoring use domino-model-monitoring; for batch scoring Jobs and for exporting a model out of Domino (an image to your registry, NVIDIA Fleet Command, a Snowflake UDF, SageMaker) use domino-model-delivery.

Deliver a Domino model outside a Domino endpoint. Covers batch scoring Jobs (a scoring script run once or on a schedule, results, notifications, the async endpoint alternative), the Model Export API (buildModelImage, exportImageToRegistry, build and export status and logs, .modelignore, running the exported image on your own Kubernetes), and the export targets NVIDIA Fleet Command (exportImageForNvidia) and Snowflake (Snowpark UDF), and SageMaker. Use when the user wants to batch-score a dataset or table with a trained model, run scoring on a schedule, export a model image out of Domino to a container registry from GitHub Actions, Jenkins or another CI/CD pipeline, push a model to NVIDIA Fleet Command or Snowflake, deploy a registered model to a SageMaker external endpoint, or asks about the Exports page. Not for deploying or updating a Domino-hosted endpoint, from CI/CD or otherwise; that belongs to domino-model-serving (REST) and domino-model-endpoints (UI).

Create and run Domino Launchers - self-service web forms that pass text, select, multi-select, date, checkbox and uploaded-file inputs to a script that runs as a Domino Job. Covers the launcher wizard, the command placeholder syntax, how arguments reach the script, result files and email delivery, roles, and finding launcher runs through the Jobs API. Use when building self-service reports, batch scoring forms, or data-product UIs for non-technical users.

Create, run, and manage Domino Jobs - batch executions for scripts, training, and data processing. Covers starting a Job from the UI, CLI or REST API, hardware tiers and environments, scheduled Jobs (Quartz cron, UI or API), status and logs, stopping Jobs, results and notifications. Use when running batch workloads, scheduling recurring tasks, or automating training pipelines. For the CLI itself use domino-cli; for multi-step pipelines domino-flows; for an existing Airflow or Kubeflow domino-airflow-kubeflow; for batch scoring with a model use domino-model-delivery.

Enable AI-assisted model development (vibe modeling) in Domino. The assistant writes the data-analysis, model and training code and uses the bundled Domino MCP server to run it as Domino Jobs, wait for and read their output, and read, upload and sync files (text or binary) for DFS projects, so work stays reproducible, governed and tracked in Experiment Manager. Use when setting up an AI coding assistant to work with Domino, configuring or troubleshooting the Domino MCP server, or when the user asks to analyze a dataset, train or compare models, or run scripts as Domino Jobs from a coding assistant.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model for the user's actual intent — premium vocal hook, cheap background music library, multilingual pop song, repair a bad chorus, lengthen a 30 s draft into a 2 min cut — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate music", "make a song", "AI music", "background music", "instrumental track", "soundtrack", "jingle", "theme music", "royalty-free music", "compose", "music with lyrics", "extend music", "fix this song", "inpaint music", or any explicit ask to generate or edit music.

创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。