ext/new-api
2
0
Fork 0
mirror of https://github.com/QuantumNous/new-api.git synced 2026-09-07 01:56:53 +00:00
Code Activity

feat: support Responses to Chat (#5787)

Browse Source 
* fix(openai): harden Chat-to-Responses compatibility

Add a shared Responses-to-Chat stream state machine and use it from the OpenAI relay path. Preserve assistant text alongside tool calls, bind tool argument deltas by output_index, map incomplete finish reasons, support reasoning/custom tool events, and buffer upstream SSE for non-stream Chat clients.

Add deterministic service tests and relay SSE tests for the conversion path.

Related to #5745.

* refactor: rename openaicompat to relayconvert for improved clarity

* feat(gemini): support responses request conversion

* feat: add responses to chat conversion support

* fix: harden responses chat conversion edge cases
This commit is contained in:
Calcium-Ion
2026-06-28 14:25:47 +08:00
committed by GitHub
parent 3a506f50f0
commit 2d5a041639
35 changed files with 2731 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
service/openai_chat_responses_mode.go
+3 -3
View File
@@ -1,14 +1,14 @@
package service
import (
"github.com/QuantumNous/new-api/service/openaicompat"
"github.com/QuantumNous/new-api/service/relayconvert"
"github.com/QuantumNous/new-api/setting/model_setting"
)
func ShouldChatCompletionsUseResponsesPolicy(policy model_setting.ChatCompletionsToResponsesPolicy, channelID int, channelType int, model string) bool {
return openaicompat.ShouldChatCompletionsUseResponsesPolicy(policy, channelID, channelType, model)
return relayconvert.ShouldChatCompletionsUseResponsesPolicy(policy, channelID, channelType, model)
}
func ShouldChatCompletionsUseResponsesGlobal(channelID int, channelType int, model string) bool {
return openaicompat.ShouldChatCompletionsUseResponsesGlobal(channelID, channelType, model)
return relayconvert.ShouldChatCompletionsUseResponsesGlobal(channelID, channelType, model)
}