lisone/ds2api
1
0
Fork 0
mirror of https://github.com/CJackHwang/ds2api.git synced 2026-05-19 15:37:44 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #374 from shern-point/feat/full-context-file-token-accounting

Browse Source 
Feat/full context file token accounting
This commit is contained in:
CJACK.
2026-04-30 02:12:55 +08:00
committed by GitHub
parent 63e62fd1b0 6a778e0d35
commit 7c3ff6ee7e
19 changed files with 185 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
internal/httpapi/openai/chat/handler_chat.go
View File

@@ -108,11 +108,12 @@ func (h *Handler) ChatCompletions(w http.ResponseWriter, r *http.Request) {
writeOpenAIError(w, http.StatusInternalServerError, "Failed to get completion.")
return
}
refFileTokens := stdReq.RefFileTokens
if stdReq.Stream {
h.handleStreamWithRetry(w, r, a, resp, payload, pow, sessionID, stdReq.ResponseModel, stdReq.PromptTokenText, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, historySession)
h.handleStreamWithRetry(w, r, a, resp, payload, pow, sessionID, stdReq.ResponseModel, stdReq.PromptTokenText, refFileTokens, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, historySession)
return
}
h.handleNonStreamWithRetry(w, r.Context(), a, resp, payload, pow, sessionID, stdReq.ResponseModel, stdReq.PromptTokenText, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, historySession)
h.handleNonStreamWithRetry(w, r.Context(), a, resp, payload, pow, sessionID, stdReq.ResponseModel, stdReq.PromptTokenText, refFileTokens, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, historySession)
}
func (h *Handler) autoDeleteRemoteSession(ctx context.Context, a *auth.RequestAuth, sessionID string) {
@@ -148,7 +149,7 @@ func (h *Handler) autoDeleteRemoteSession(ctx context.Context, a *auth.RequestAu
}
}
func (h *Handler) handleNonStream(w http.ResponseWriter, resp *http.Response, completionID, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, historySession *chatHistorySession) {
func (h *Handler) handleNonStream(w http.ResponseWriter, resp *http.Response, completionID, model, finalPrompt string, refFileTokens int, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, historySession *chatHistorySession) {
if resp.StatusCode != http.StatusOK {
defer func() { _ = resp.Body.Close() }()
body, _ := io.ReadAll(resp.Body)
@@ -176,6 +177,9 @@ func (h *Handler) handleNonStream(w http.ResponseWriter, resp *http.Response, co
return
}
respBody := openaifmt.BuildChatCompletionWithToolCalls(completionID, model, finalPrompt, finalThinking, finalText, detected.Calls, toolsRaw)
if refFileTokens > 0 {
addRefFileTokensToUsage(respBody, refFileTokens)
}
finishReason := "stop"
if choices, ok := respBody["choices"].([]map[string]any); ok && len(choices) > 0 {
if fr, _ := choices[0]["finish_reason"].(string); strings.TrimSpace(fr) != "" {
@@ -183,12 +187,12 @@ func (h *Handler) handleNonStream(w http.ResponseWriter, resp *http.Response, co
}
}
if historySession != nil {
historySession.success(http.StatusOK, finalThinking, finalText, finishReason, openaifmt.BuildChatUsageForModel(model, finalPrompt, finalThinking, finalText))
historySession.success(http.StatusOK, finalThinking, finalText, finishReason, openaifmt.BuildChatUsageForModel(model, finalPrompt, finalThinking, finalText, refFileTokens))
}
writeJSON(w, http.StatusOK, respBody)
}
func (h *Handler) handleStream(w http.ResponseWriter, r *http.Request, resp *http.Response, completionID, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, historySession *chatHistorySession) {
func (h *Handler) handleStream(w http.ResponseWriter, r *http.Request, resp *http.Response, completionID, model, finalPrompt string, refFileTokens int, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, historySession *chatHistorySession) {
defer func() { _ = resp.Body.Close() }()
if resp.StatusCode != http.StatusOK {
body, _ := io.ReadAll(resp.Body)
@@ -233,6 +237,7 @@ func (h *Handler) handleStream(w http.ResponseWriter, r *http.Request, resp *htt
bufferToolContent,
emitEarlyToolDeltas,
)
streamRuntime.refFileTokens = refFileTokens
streamengine.ConsumeSSE(streamengine.ConsumeConfig{
Context: r.Context(),