Documentation
¶
Overview ¶
Package openrouter is a reference backend emulator for OpenRouter's API surface. It serves both POST /api/v1/chat/completions and POST /api/v1/responses with JSON or SSE bodies compatible with github.com/openai/openai-go/v3, adding OpenRouter-specific header/body capture for integration test assertions.
Index ¶
Constants ¶
const ChatStreamWithUsageSSE = "data: {\"id\":\"gen-or-refbackend-stream\",\"object\":\"chat.completion.chunk\",\"created\":1715620000,\"model\":\"openai/gpt-4o-mini\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"or-stream-ok\"},\"finish_reason\":null}]}\n\n" +
"data: {\"id\":\"gen-or-refbackend-stream\",\"object\":\"chat.completion.chunk\",\"created\":1715620000,\"model\":\"openai/gpt-4o-mini\",\"choices\":[{\"index\":0,\"delta\":{},\"finish_reason\":\"stop\"}]}\n\n" +
"data: {\"id\":\"gen-or-refbackend-stream\",\"object\":\"chat.completion.chunk\",\"created\":1715620000,\"model\":\"openai/gpt-4o-mini\",\"choices\":[],\"usage\":{\"prompt_tokens\":3,\"completion_tokens\":7,\"total_tokens\":10,\"cost\":0.00014}}\n\n" +
"data: [DONE]\n\n"
ChatStreamWithUsageSSE includes a final usage chunk before [DONE].
const DefaultChatNonStreamJSON = `` /* 339-byte string literal not displayed */
DefaultChatNonStreamJSON is a minimal Chat Completions response with OpenRouter extensions.
const DefaultChatStreamSSE = "data: {\"id\":\"gen-or-refbackend-stream\",\"object\":\"chat.completion.chunk\",\"created\":1715620000,\"model\":\"openai/gpt-4o-mini\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"or-stream-ok\"},\"finish_reason\":null}]}\n\n" +
"data: [DONE]\n\n"
DefaultChatStreamSSE is a minimal streaming Chat Completions response.
const DefaultResponsesNonStreamJSON = `` /* 422-byte string literal not displayed */
DefaultResponsesNonStreamJSON is a minimal Responses API completed response.
const DefaultResponsesStreamSSE = "event: response.completed\n" +
"data: {\"type\":\"response.completed\",\"sequence_number\":1,\"response\":{\"id\":\"resp_or_refbackend_stream\",\"object\":\"response\",\"created_at\":1715620000,\"status\":\"completed\",\"model\":\"openai/gpt-4o-mini\",\"output\":[{\"type\":\"message\",\"id\":\"m1\",\"status\":\"completed\",\"role\":\"assistant\",\"content\":[{\"type\":\"output_text\",\"text\":\"or-stream-ok\"}]}],\"usage\":{\"input_tokens\":3,\"output_tokens\":7,\"total_tokens\":10}}}\n\n" +
"data: [DONE]\n\n"
DefaultResponsesStreamSSE is a minimal Responses SSE stream.
Variables ¶
This section is empty.
Functions ¶
func NewHandler ¶
NewHandler returns an http.Handler that emulates both OpenRouter endpoints: POST /api/v1/chat/completions and POST /api/v1/responses.
Types ¶
type Config ¶
type Config struct {
AllowMissingBearer bool
OnAuthorizedCredential func(secret string)
ForcedHTTPStatus int
ForcedRetryAfter string
ForcedErrorJSON string
OnRequestBody func(body []byte)
OnRequestHeaders func(h http.Header)
// Chat completions overrides.
ChatNonStreamJSON string
ChatStreamSSE string
// Responses overrides.
ResponsesNonStreamJSON string
ResponsesStreamSSE string
}
Config tunes the emulator handler.
Source Files