Calcium-Ion
86ac0f7745
* test(relayconvert): add golden snapshot matrix and relaykit boundary guard Phase 0 of the relaykit extraction plan: pin byte-level output of every registered (from,to) request/response/stream conversion route, and forbid kit-bound packages from growing host-only imports. * wip(relayconvert): drop gin.Context from converter signatures; add convmeta draft Phase 1 in progress: relayconvert now takes context.Context; host media resolver adapts gin.Context back at the service boundary. * refactor(relayconvert): decouple converters from RelayInfo, gin, and settings Phase 1 of the relaykit extraction plan: - converters now depend on convmeta.Meta (implemented by RelayInfo) instead of *relaycommon.RelayInfo; ClaudeConvertInfo and the format guesser move to convmeta with aliases left behind - host settings reach converters via a convmeta.Options snapshot built in RelayInfo.ConvOptions; no more model_setting/reasoning global reads inside the conversion layer - effort-suffix helpers move to service/relayconvert/reasoning (old package forwards); chat-to-responses upgrade policy moves to service (host routing logic, not conversion) - golden conversion matrix unchanged * test(relayconvert): tighten boundary — kit packages now free of gin/setting imports * refactor(dto): drop gin and logger dependencies Phase 2 (part 1): dto.Request.IsStream now takes *http.Request instead of *gin.Context (Gemini's impl reads query/path off the std request); dto's three logger calls become common.SysError. Boundary test allowlist is now empty — kit-bound packages import no gin/setting/logger/model. * refactor(kit): extract dependency-free kitutil; dto/types/relayconvert stop importing common Phase 2 of the relaykit extraction plan: - new service/relayconvert/kitutil holds the pure helpers the kit needs (JSON wrappers, pointer/string/uuid/timestamp utils, MaskSensitiveInfo, pluggable LogInfo/LogError hooks, Debug flag) - dto, types, and all relayconvert packages now use kitutil; their only remaining internal deps are dto/types/constant - common keeps every original symbol (MaskSensitiveInfo delegates to kitutil) so host code is untouched; main.go routes kit logging into common.SysLog/SysError and mirrors DebugEnabled - golden conversion matrix unchanged * refactor(kit): move EndpointType/FinishReason to types; OpenRouter dialect via Options Kit packages (dto/types/relayconvert/reasonmap) no longer import constant: - EndpointType and finish-reason values live in types; constant re-exports - the OpenRouter special-case in claude->openai request conversion reads Options.OpenRouterDialect, set by the host from the channel type; InitChannelMeta invalidates the cached snapshot on channel switch * refactor: extract relaykit submodule (dto/types/relayconvert/reasonmap) Phase 3 of the relaykit extraction plan: - new go module github.com/QuantumNous/new-api/relaykit containing dto (minus task family), types, relayconvert (with convmeta/kitutil/reasoning), and reasonmap; host consumes it via require + replace, go.work for dev - task-family dto (task/suno/midjourney/video) stays in the host dto package; dual-consumer host files alias it as taskdto - relaykit builds and tests standalone (GOWORK=off): no host imports, no gin, no DB, no settings - golden conversion matrix unchanged * build(docker): copy relaykit/go.mod before go mod download The local-replace submodule's go.mod must exist inside the build context for the main module graph to resolve. * fix: address relaykit extraction regressions * fix: address relaykit review regressions * docs: document Meta nil receiver contract * fix(relaykit): fail OpenAI→Claude conversion without max_tokens; reject negative default_max_tokens The Claude Messages API requires max_tokens (omitting it is a 400 "Field required"), but with a nil Options.Claude.DefaultMaxTokens hook the converters silently emitted a request the upstream is guaranteed to reject. Both OpenAI Chat and Responses → Claude conversions now return sharedclaude.ErrMissingMaxTokens when no path (client value, default hook, thinking-adapter floor) supplied one. Unreachable in the host, which always configures the hook. Host side, claude.default_max_tokens now rejects negative values at the option API before persisting — they would wrap into huge unsigned values during conversion. Zero stays allowed: the current API treats max_tokens: 0 as cache pre-warming. * fix: make Gemini safety settings read path race-free
227 lines
5.9 KiB
JSON
227 lines
5.9 KiB
JSON
{
|
|
"events": [
|
|
{
|
|
"Type": "response.created",
|
|
"Payload": {
|
|
"type": "response.created",
|
|
"response": {
|
|
"id": "stream_fixed",
|
|
"object": "response",
|
|
"created_at": 0,
|
|
"status": "in_progress",
|
|
"instructions": null,
|
|
"max_output_tokens": 0,
|
|
"model": "stream-model",
|
|
"output": [],
|
|
"parallel_tool_calls": false,
|
|
"previous_response_id": null,
|
|
"reasoning": null,
|
|
"store": false,
|
|
"temperature": 0,
|
|
"tool_choice": null,
|
|
"tools": null,
|
|
"top_p": 0,
|
|
"truncation": null,
|
|
"usage": null,
|
|
"user": null,
|
|
"metadata": null
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"Type": "response.output_item.added",
|
|
"Payload": {
|
|
"type": "response.output_item.added",
|
|
"item": {
|
|
"type": "message",
|
|
"id": "stream_fixed_msg_0",
|
|
"status": "in_progress",
|
|
"role": "assistant",
|
|
"content": [],
|
|
"quality": "",
|
|
"size": ""
|
|
},
|
|
"output_index": 0
|
|
}
|
|
},
|
|
{
|
|
"Type": "response.output_text.delta",
|
|
"Payload": {
|
|
"type": "response.output_text.delta",
|
|
"delta": "Hello",
|
|
"output_index": 0,
|
|
"content_index": 0,
|
|
"item_id": "stream_fixed_msg_0"
|
|
}
|
|
},
|
|
{
|
|
"Type": "response.output_text.delta",
|
|
"Payload": {
|
|
"type": "response.output_text.delta",
|
|
"delta": " world",
|
|
"output_index": 0,
|
|
"content_index": 0,
|
|
"item_id": "stream_fixed_msg_0"
|
|
}
|
|
},
|
|
{
|
|
"Type": "response.output_text.done",
|
|
"Payload": {
|
|
"type": "response.output_text.done",
|
|
"output_index": 0,
|
|
"content_index": 0,
|
|
"item_id": "stream_fixed_msg_0"
|
|
}
|
|
},
|
|
{
|
|
"Type": "response.output_item.done",
|
|
"Payload": {
|
|
"type": "response.output_item.done",
|
|
"item": {
|
|
"type": "message",
|
|
"id": "stream_fixed_msg_0",
|
|
"status": "completed",
|
|
"role": "assistant",
|
|
"content": [
|
|
{
|
|
"type": "output_text",
|
|
"text": "Hello world",
|
|
"annotations": []
|
|
}
|
|
],
|
|
"quality": "",
|
|
"size": ""
|
|
},
|
|
"output_index": 0
|
|
}
|
|
},
|
|
{
|
|
"Type": "response.completed",
|
|
"Payload": {
|
|
"type": "response.completed",
|
|
"response": {
|
|
"id": "stream_fixed",
|
|
"object": "response",
|
|
"created_at": 0,
|
|
"status": "completed",
|
|
"instructions": null,
|
|
"max_output_tokens": 0,
|
|
"model": "stream-model",
|
|
"output": [
|
|
{
|
|
"type": "message",
|
|
"id": "stream_fixed_msg_0",
|
|
"status": "completed",
|
|
"role": "assistant",
|
|
"content": [
|
|
{
|
|
"type": "output_text",
|
|
"text": "Hello world",
|
|
"annotations": []
|
|
}
|
|
],
|
|
"quality": "",
|
|
"size": ""
|
|
}
|
|
],
|
|
"parallel_tool_calls": false,
|
|
"previous_response_id": null,
|
|
"reasoning": null,
|
|
"store": false,
|
|
"temperature": 0,
|
|
"tool_choice": null,
|
|
"tools": null,
|
|
"top_p": 0,
|
|
"truncation": null,
|
|
"usage": {
|
|
"prompt_tokens": 4,
|
|
"completion_tokens": 2,
|
|
"total_tokens": 6,
|
|
"billing_usage": {
|
|
"source": "gemini_chat",
|
|
"semantic": "gemini",
|
|
"gemini_usage_metadata": {
|
|
"promptTokenCount": 4,
|
|
"toolUsePromptTokenCount": 0,
|
|
"candidatesTokenCount": 2,
|
|
"totalTokenCount": 6,
|
|
"thoughtsTokenCount": 0,
|
|
"cachedContentTokenCount": 0,
|
|
"promptTokensDetails": [],
|
|
"toolUsePromptTokensDetails": [],
|
|
"candidatesTokensDetails": []
|
|
}
|
|
},
|
|
"prompt_tokens_details": {
|
|
"cached_tokens": 0,
|
|
"text_tokens": 0,
|
|
"audio_tokens": 0,
|
|
"image_tokens": 0
|
|
},
|
|
"completion_tokens_details": {
|
|
"text_tokens": 0,
|
|
"audio_tokens": 0,
|
|
"image_tokens": 0,
|
|
"reasoning_tokens": 0
|
|
},
|
|
"input_tokens": 4,
|
|
"output_tokens": 2,
|
|
"input_tokens_details": {
|
|
"cached_tokens": 0,
|
|
"text_tokens": 4,
|
|
"audio_tokens": 0,
|
|
"image_tokens": 0
|
|
},
|
|
"claude_cache_creation_5_m_tokens": 0,
|
|
"claude_cache_creation_1_h_tokens": 0
|
|
},
|
|
"user": null,
|
|
"metadata": null
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"usage": {
|
|
"prompt_tokens": 4,
|
|
"completion_tokens": 2,
|
|
"total_tokens": 6,
|
|
"billing_usage": {
|
|
"source": "gemini_chat",
|
|
"semantic": "gemini",
|
|
"gemini_usage_metadata": {
|
|
"promptTokenCount": 4,
|
|
"toolUsePromptTokenCount": 0,
|
|
"candidatesTokenCount": 2,
|
|
"totalTokenCount": 6,
|
|
"thoughtsTokenCount": 0,
|
|
"cachedContentTokenCount": 0,
|
|
"promptTokensDetails": [],
|
|
"toolUsePromptTokensDetails": [],
|
|
"candidatesTokensDetails": []
|
|
}
|
|
},
|
|
"prompt_tokens_details": {
|
|
"cached_tokens": 0,
|
|
"text_tokens": 0,
|
|
"audio_tokens": 0,
|
|
"image_tokens": 0
|
|
},
|
|
"completion_tokens_details": {
|
|
"text_tokens": 0,
|
|
"audio_tokens": 0,
|
|
"image_tokens": 0,
|
|
"reasoning_tokens": 0
|
|
},
|
|
"input_tokens": 4,
|
|
"output_tokens": 2,
|
|
"input_tokens_details": {
|
|
"cached_tokens": 0,
|
|
"text_tokens": 4,
|
|
"audio_tokens": 0,
|
|
"image_tokens": 0
|
|
},
|
|
"claude_cache_creation_5_m_tokens": 0,
|
|
"claude_cache_creation_1_h_tokens": 0
|
|
}
|
|
}
|