SDK Compatibility Limits — ML Junction docs

Surface · Implemented · Deliberate limits
OpenAI Chat Completions · Text, async, streaming, tools, strict schema, usage, reasoning telemetry · n > 1 and logprobs are rejected; provider-hosted tools are not emulated
Anthropic Messages · Text, async, streaming, tools, images, schema, thinking preservation · Batches/files/token-count endpoints are not emulated
Native API · Complete ML Junction feature surface · Not wire-compatible with vendor SDK response objects
LangChain · Native chat, tools, schema, multimodal inputs, streams, embeddings, receipts; standard integration suite verified · Structured-output streams are emitted atomically; ML Junction-specific configuration remains intentional

Unknown compatibility request fields are rejected rather than ignored.. Vendor SDK compatibility describes protocol shape, not a promise that every vendor endpoint exists.. A compatibility request may route to another provider unless routing.provider, only_providers, or a provider-bound opaque state restricts it.. Structured streams are buffered until validation succeeds, so first-token latency is intentionally higher than text streaming.. ML Junction extension fields require extra_body/custom request support in strict vendor SDK versions.

Canonical URL: https://mljunction.com/docs/compatibility-limits