assets

End-to-end run-image classification with Gemini, including image fetch, prompt control, and JSON output. Use when you need parking or pull-over labels from a run_id.

Find a Gen2 MCAP from a run (or model-derived run), list topics, and extract topic/field values at a specific log time. Use when debugging run-level protobuf signals such as controller_state.

Fetch Buildkite job logs and extract failure lines for debugging CI jobs. Use when a user provides build/job ids or requests failure signal from Buildkite.

Use when forming Spark/SQL queries for Databricks parking evaluation - provides table schemas, PySpark patterns, joins, and filter patterns for PUDO/UNPUDO analysis

Work with Databricks notebooks using the REST API - list, read, modify, and write notebooks back to Databricks workspace

Inspect Flyte execution status and per-node/per-task log URIs from a Flyte Console execution URL. Use when a user asks for workflow status, step status, or logs for flyte.data.wayve.ai/dev executions.

Shared Model Catalogue primitives (resolve model refs, find latest checkpoint, call API helpers) used by model lookup/summary/checkpoint/modelci skills. Use when model references must be normalized before downstream analysis.

Inspect checkpoint-level data for a model, including checkpoint licenses and run history. Use when a user asks for licenses or run-level evidence for a specific model/checkpoint.

Fetch an expanded per-model summary from Model Catalogue by nickname or session id, including commit id and aggregated license info. Use when a user asks for detailed metadata about one specific model.

Inspect Model CI status for a model checkpoint, including failed Buildkite job log extraction, Eval Studio info, and Shadow Gym execution metadata. Use when a user asks to debug CI/eval failures for a model.

Build Datadog Logs Explorer URLs from a raw query or Kubernetes pod/namespace filters. Use when a user asks for Datadog log links scoped to execution, pod, or service failures.

Top-level model diagnostics router. Use when a request spans model lookup, checkpoint inspection, CI/debug, or observability and you need to choose/compose the right lower-level model and observability skills.

Lookup model-catalogue sessions by nickname or author and return basic model identity details. Use when a user asks to find a model, confirm model identity, or list candidate models by nickname/author before deeper inspection.

Resolve BC/RL config migration conflicts and add new migrations by bumping versions, updating migrate_to_v* methods/maps, regenerating sample snapshots, and validating tests.