lisone/ds2api
1
0
Fork 0
mirror of https://github.com/CJackHwang/ds2api.git synced 2026-05-05 00:45:29 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: route OpenAI chat usage through preserved prompt text

Browse Source 
Use the stored full-context prompt text for chat non-stream, stream, and retry accounting so current_input_file no longer shrinks returned prompt token counts.
This commit is contained in:
shern-point
2026-04-30 00:45:30 +08:00
parent 90817cb9e2
commit f702d45a24
3 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
internal/httpapi/openai/chat/chat_stream_runtime.go
View File

@@ -220,7 +220,7 @@ func (s *chatStreamRuntime) finalize(finishReason string, deferEmptyOutput bool)
s.sendFailedChunk(status, message, code)
return true
}
usage := openaifmt.BuildChatUsage(s.finalPrompt, finalThinking, finalText)
usage := openaifmt.BuildChatUsageForModel(s.model, s.finalPrompt, finalThinking, finalText)
s.finalFinishReason = finishReason
s.finalUsage = usage
s.sendChunk(openaifmt.BuildChatStreamChunk(

2
internal/httpapi/openai/chat/empty_retry_runtime.go
View File

@@ -67,7 +67,7 @@ func (h *Handler) handleNonStreamWithRetry(w http.ResponseWriter, ctx context.Co
config.Logger.Warn("[openai_empty_retry] retry request failed", "surface", "chat.completions", "stream", false, "retry_attempt", attempts, "error", err)
return
}
usagePrompt = usagePromptWithEmptyOutputRetry(finalPrompt, attempts)
usagePrompt = usagePromptWithEmptyOutputRetry(usagePrompt, attempts)
currentResp = nextResp
}
}

6
internal/httpapi/openai/chat/handler_chat.go
View File

@@ -109,10 +109,10 @@ func (h *Handler) ChatCompletions(w http.ResponseWriter, r *http.Request) {
return
}
if stdReq.Stream {
h.handleStreamWithRetry(w, r, a, resp, payload, pow, sessionID, stdReq.ResponseModel, stdReq.FinalPrompt, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, historySession)
h.handleStreamWithRetry(w, r, a, resp, payload, pow, sessionID, stdReq.ResponseModel, stdReq.PromptTokenText, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, historySession)
return
}
h.handleNonStreamWithRetry(w, r.Context(), a, resp, payload, pow, sessionID, stdReq.ResponseModel, stdReq.FinalPrompt, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, historySession)
h.handleNonStreamWithRetry(w, r.Context(), a, resp, payload, pow, sessionID, stdReq.ResponseModel, stdReq.PromptTokenText, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, historySession)
}
func (h *Handler) autoDeleteRemoteSession(ctx context.Context, a *auth.RequestAuth, sessionID string) {
@@ -184,7 +184,7 @@ func (h *Handler) handleNonStream(w http.ResponseWriter, resp *http.Response, co
}
}
if historySession != nil {
historySession.success(http.StatusOK, finalThinking, finalText, finishReason, openaifmt.BuildChatUsage(finalPrompt, finalThinking, finalText))
historySession.success(http.StatusOK, finalThinking, finalText, finishReason, openaifmt.BuildChatUsageForModel(model, finalPrompt, finalThinking, finalText))
}
writeJSON(w, http.StatusOK, respBody)
}