Skip to main content
This matrix describes the current releases: TypeScript 0.1.4 and Python 0.1.2. Tested combinations establish the paths below; accepting standard OTLP is broader than testing every instrumentation library.

​
Existing dependencies

The current @hue-run/sdk package cannot be installed alongside ai@6: npm enforces the optional ai@^7.0.99 peer even if the application only imports the core client. Do not bypass the resolver with --force or --legacy-peer-deps, or upgrade an application’s framework solely to add tracing. An existing OTel application can send records with its standard exporter using the OTLP integration guide. Python’s exact OTel pins can conflict with applications that require a different version. Resolve the dependency set before changing the application. A lockfile records what was tested; it does not certify every compatible-looking version.

​
Content and delivery

Neither SDK estimates unavailable token usage or cost. Queues are bounded and in memory; a successful model response does not establish telemetry delivery.

​
Evaluation coverage

Both SDKs support dataset/scorer creation, frozen versions, local experiments, built-in/custom scorers, resumable result uploads and historical rescoring. Hosted judge job/budget methods are available, but credential resolution is not proof of a successful provider call. Activation belongs to the platform environment. The clients do not yet expose every platform REST operation. Dataset editing/archival, case replacement/deletion, promotion from a trace, copying published scorers, experiment/run listing and frozen-trace snapshot reads are not convenience methods in the current clients. There is no general service-key trace-search client. Open pull requests are not released functionality. API responses are limited to 4 MiB by the clients. Full dataset pages can exceed this limit when cases contain large values. Use smaller explicit page limits when listing full cases; the local experiment runner separately reads summaries and individual cases. A response-size failure does not establish that the server rejected the request.

​
Hue-managed runs

The TypeScript and Python managed target adapters use the same versioned HTTP contract. Hue starts runs against a registered public HTTPS endpoint; the existing agent remains in its own environment. This release supports synchronous targets, verified file transfer, stored outcome recovery and deterministic platform scoring. Hosted AI judges, arbitrary hosted code, manual evaluators and asynchronous targets are outside this managed-run release. See managed runs.