iop/agent-spec/input/openai-compatible-surface.md

spec_doc_type	spec_id	status	source_evidence
spec	input/openai-compatible-surface	구현됨	type path notes contract agent-contract/outer/openai-compatible-api.md Public compatibility behavior type path notes contract agent-contract/outer/anthropic-compatible-api.md Anthropic Messages behavior type path notes code apps/edge/internal/openai/routes.go HTTP routes and authentication type path notes code apps/edge/internal/openai/chat_handler.go Chat validation, routing, and tools type path notes code apps/edge/internal/openai/responses_handler.go Responses validation and normalized execution type path notes test apps/edge/internal/openai/chat_handler_test.go Standard inference and routing regressions

OpenAI-Compatible Input Surface

Current implementation

Edge exposes model discovery, Chat Completions, Responses, legacy Completions, Anthropic Messages, and token-counting compatibility routes. Public model ids resolve to provider-pool candidates or direct provider routes.

Standard streaming, sampling, reasoning, tool definitions, tool choice, structured output, provider passthrough extensions, authentication, and compatible error envelopes are preserved. Provider-native tool calls remain structured; text fallback occurs only after an explicit native-tool rejection.

Caller metadata is a bounded string map. It is never treated as local process control or a filesystem execution context. Correlation values do not resume provider state.

Execution paths

• OpenAI-compatible providers use the raw provider tunnel when selected by the pool.
• Normalized adapters use RunRequest and ordered run events.
• Disconnect and timeout cancellation use the active run id.
• Usage attribution follows the selected provider or configured model group.

Verification

• go test -count=1 ./apps/edge/internal/openai ./apps/node/internal/adapters/...
• make test-e2e