Skip to content

Integration coverage ​

The telemetry reference lists accepted fields. An integration sends only the fields it can observe. Runtime, provider, SDK version, and configuration determine which values arrive.

Choose a collection path ​

SourceAutomatic collectionAdditional instrumentationLimits
Python SDKEnabled library integrations record supported model calls and metadataManual tracking for unsupported calls, feedback, spans, and attachmentsEach adapter covers specific library entry points
iOS / macOS SDKSupported interceptors include ONNX Runtime, ML Kit, and ExecuTorch LLMHandle APIs for other runtimes and application eventsPlatform and interceptor support vary
Android SDKDecorated runtime calls record supported inference telemetryWrap supported runtimes or use model handles and tracking APIsInstalling the dependency does not instrument every call
LiteLLM exportExported provider calls become inference eventsSDK tracking for local calls or application contextCache hits are not exported. Reported cost is estimated
OpenRouter BroadcastExported requests become inference eventsSDK tracking for local calls or application contextRejections before routing and failed fallback attempts are not exported
Bifrost exportExported provider attempts become inference eventsSDK tracking for local calls or application contextReported cost is estimated. Unpriced models have no cost

Gateway exports do not supply the calling device's hardware state or application feedback. SDK and gateway events are not automatically linked into one trace. Disable SDK tracking for cloud calls exported by the gateway if you want one event per call.

Python library examples ​

IntegrationVerified behaviorDetails
OpenAIChat calls, Responses, and embeddings have dedicated instrumentation. Streaming metadata depends on the API and responseStreaming
AnthropicMessage calls and native streaming helpers are instrumentedStreaming
llama.cppCompletion and chat entry points record inference telemetry. Prompts and replies are not attached automaticallyExamples
ONNX RuntimeSupported session calls record inference timing. Input measurements and prediction extraction depend on input and output shapeExample
MLX Whisper and faster-whisperModel loads and transcriptions are tracked. Audio and transcript attachments require manual trackingWhisper guide
Other HTTP clientswildedge.llm_api() records a wrapped call. Supply usage and response metadata through its APIHTTP tracking

These examples cover Python SDK v0.3.0. They are not a complete list of integrations. Check the SDK compatibility guide before enabling an adapter.

Mobile runtime support ​

Use the platform guide for supported entry points and metadata. A runtime name alone does not guarantee hardware, prediction, or content capture support.

  • iOS / macOS SDK: interceptor setup, manual model handles, tracing, and examples.
  • Android SDK: runtime decorators, manual tracking, and examples.

Compare reported device models and accelerators. Do not infer a specific chipset or NPU execution from a generic accelerator value.

Content capture ​

Python automatic integrations do not attach raw inputs or outputs. Enabling attachments_enabled permits uploads explicitly supplied to track_inference(attachments=[...]). Project attachment support must also be enabled.

Other SDKs have their own attachment APIs and settings. Follow the platform guide. Do not assume Python configuration applies to mobile SDKs.

Summaries, attributes, errors, URLs, and custom fields can contain content independently of attachments. See content and identifiers.

WildEdge keeps gateway prompt and response text as event summaries only when the gateway exports it. LiteLLM leaves it out by default, Bifrost with disable_content_logging, and OpenRouter in Privacy Mode.

Buffering and delivery ​

SDK buffering and gateway exporter retries are separate mechanisms.

Collection pathBehavior
Python SDKConfigurable batches, flush interval, memory queue, and event age. Offline persistence is enabled by default. Dead-letter persistence is optional
Mobile SDKsUse the platform guide for queue, persistence, and shutdown behavior. Python defaults do not apply
Gateway exportWildEdge acknowledges after storage. Exporter retry windows are finite, so an extended outage can lose batches
AttachmentsFile upload is separate from event delivery. A recorded inference does not prove its attachment uploaded

For Python settings and defaults, see Configuration. Retryable transmitter failures include HTTP 429, server errors, and network errors. Queue and age limits mean persistence is not an unlimited delivery guarantee.

For retries and known limitations of each gateway, see its setup page: LiteLLM, OpenRouter, or Bifrost.

Verify your setup ​

  1. Run one call through each enabled integration.
  2. Find the event in the intended project.
  3. Check the fields needed for your investigation.
  4. If a field is absent, check adapter support before treating it as a model or device issue.

Next ​