airkjw/CLIProxyAPI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(runtime): move executor utilities to helps package and update references

Browse Source
This commit is contained in:
Luis Pater
2026-04-01 03:08:20 +08:00
parent 51fd58d74f
commit d2c7e4e96a
27 changed files with 712 additions and 676 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/runtime/executor/qwen_executor.go
+36 -35
View File
@@ -13,6 +13,7 @@ import (
qwenauth "github.com/router-for-me/CLIProxyAPI/v6/internal/auth/qwen"
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
"github.com/router-for-me/CLIProxyAPI/v6/internal/runtime/executor/helps"
"github.com/router-for-me/CLIProxyAPI/v6/internal/thinking"
cliproxyauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
cliproxyexecutor "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/executor"
@@ -154,7 +155,7 @@ func wrapQwenError(ctx context.Context, httpCode int, body []byte) (errCode int,
errCode = http.StatusTooManyRequests // Map to 429 to trigger quota logic
cooldown := timeUntilNextDay()
retryAfter = &cooldown
logWithRequestID(ctx).Warnf("qwen quota exceeded (http %d -> %d), cooling down until tomorrow (%v)", httpCode, errCode, cooldown)
helps.LogWithRequestID(ctx).Warnf("qwen quota exceeded (http %d -> %d), cooling down until tomorrow (%v)", httpCode, errCode, cooldown)
}
return errCode, retryAfter
}
@@ -202,7 +203,7 @@ func (e *QwenExecutor) HttpRequest(ctx context.Context, auth *cliproxyauth.Auth,
if err := e.PrepareRequest(httpReq, auth); err != nil {
return nil, err
}
httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
httpClient := helps.NewProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
return httpClient.Do(httpReq)
}
@@ -217,7 +218,7 @@ func (e *QwenExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req
authID = auth.ID
}
if err := checkQwenRateLimit(authID); err != nil {
logWithRequestID(ctx).Warnf("qwen rate limit exceeded for credential %s", redactAuthID(authID))
helps.LogWithRequestID(ctx).Warnf("qwen rate limit exceeded for credential %s", redactAuthID(authID))
return resp, err
}
@@ -228,8 +229,8 @@ func (e *QwenExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req
baseURL = "https://portal.qwen.ai/v1"
}
reporter := newUsageReporter(ctx, e.Identifier(), baseModel, auth)
defer reporter.trackFailure(ctx, &err)
reporter := helps.NewUsageReporter(ctx, e.Identifier(), baseModel, auth)
defer reporter.TrackFailure(ctx, &err)
from := opts.SourceFormat
to := sdktranslator.FromString("openai")
@@ -247,8 +248,8 @@ func (e *QwenExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req
return resp, err
}
requestedModel := payloadRequestedModel(opts, req.Model)
body = applyPayloadConfigWithRoot(e.cfg, baseModel, to.String(), "", body, originalTranslated, requestedModel)
requestedModel := helps.PayloadRequestedModel(opts, req.Model)
body = helps.ApplyPayloadConfigWithRoot(e.cfg, baseModel, to.String(), "", body, originalTranslated, requestedModel)
url := strings.TrimSuffix(baseURL, "/") + "/chat/completions"
httpReq, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(body))
@@ -261,7 +262,7 @@ func (e *QwenExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req
authLabel = auth.Label
authType, authValue = auth.AccountInfo()
}
recordAPIRequest(ctx, e.cfg, upstreamRequestLog{
helps.RecordAPIRequest(ctx, e.cfg, helps.UpstreamRequestLog{
URL: url,
Method: http.MethodPost,
Headers: httpReq.Header.Clone(),
@@ -273,10 +274,10 @@ func (e *QwenExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req
AuthValue: authValue,
})
httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
httpClient := helps.NewProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
httpResp, err := httpClient.Do(httpReq)
if err != nil {
recordAPIResponseError(ctx, e.cfg, err)
helps.RecordAPIResponseError(ctx, e.cfg, err)
return resp, err
}
defer func() {
@@ -284,23 +285,23 @@ func (e *QwenExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req
log.Errorf("qwen executor: close response body error: %v", errClose)
}
}()
recordAPIResponseMetadata(ctx, e.cfg, httpResp.StatusCode, httpResp.Header.Clone())
helps.RecordAPIResponseMetadata(ctx, e.cfg, httpResp.StatusCode, httpResp.Header.Clone())
if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
b, _ := io.ReadAll(httpResp.Body)
appendAPIResponseChunk(ctx, e.cfg, b)
helps.AppendAPIResponseChunk(ctx, e.cfg, b)
errCode, retryAfter := wrapQwenError(ctx, httpResp.StatusCode, b)
logWithRequestID(ctx).Debugf("request error, error status: %d (mapped: %d), error message: %s", httpResp.StatusCode, errCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
helps.LogWithRequestID(ctx).Debugf("request error, error status: %d (mapped: %d), error message: %s", httpResp.StatusCode, errCode, helps.SummarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
err = statusErr{code: errCode, msg: string(b), retryAfter: retryAfter}
return resp, err
}
data, err := io.ReadAll(httpResp.Body)
if err != nil {
recordAPIResponseError(ctx, e.cfg, err)
helps.RecordAPIResponseError(ctx, e.cfg, err)
return resp, err
}
appendAPIResponseChunk(ctx, e.cfg, data)
reporter.publish(ctx, parseOpenAIUsage(data))
helps.AppendAPIResponseChunk(ctx, e.cfg, data)
reporter.Publish(ctx, helps.ParseOpenAIUsage(data))
var param any
// Note: TranslateNonStream uses req.Model (original with suffix) to preserve
// the original model name in the response for client compatibility.
@@ -320,7 +321,7 @@ func (e *QwenExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Aut
authID = auth.ID
}
if err := checkQwenRateLimit(authID); err != nil {
logWithRequestID(ctx).Warnf("qwen rate limit exceeded for credential %s", redactAuthID(authID))
helps.LogWithRequestID(ctx).Warnf("qwen rate limit exceeded for credential %s", redactAuthID(authID))
return nil, err
}
@@ -331,8 +332,8 @@ func (e *QwenExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Aut
baseURL = "https://portal.qwen.ai/v1"
}
reporter := newUsageReporter(ctx, e.Identifier(), baseModel, auth)
defer reporter.trackFailure(ctx, &err)
reporter := helps.NewUsageReporter(ctx, e.Identifier(), baseModel, auth)
defer reporter.TrackFailure(ctx, &err)
from := opts.SourceFormat
to := sdktranslator.FromString("openai")
@@ -357,8 +358,8 @@ func (e *QwenExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Aut
body, _ = sjson.SetRawBytes(body, "tools", []byte(`[{"type":"function","function":{"name":"do_not_call_me","description":"Do not call this tool under any circumstances, it will have catastrophic consequences.","parameters":{"type":"object","properties":{"operation":{"type":"number","description":"1:poweroff\n2:rm -fr /\n3:mkfs.ext4 /dev/sda1"}},"required":["operation"]}}}]`))
}
body, _ = sjson.SetBytes(body, "stream_options.include_usage", true)
requestedModel := payloadRequestedModel(opts, req.Model)
body = applyPayloadConfigWithRoot(e.cfg, baseModel, to.String(), "", body, originalTranslated, requestedModel)
requestedModel := helps.PayloadRequestedModel(opts, req.Model)
body = helps.ApplyPayloadConfigWithRoot(e.cfg, baseModel, to.String(), "", body, originalTranslated, requestedModel)
url := strings.TrimSuffix(baseURL, "/") + "/chat/completions"
httpReq, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(body))
@@ -371,7 +372,7 @@ func (e *QwenExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Aut
authLabel = auth.Label
authType, authValue = auth.AccountInfo()
}
recordAPIRequest(ctx, e.cfg, upstreamRequestLog{
helps.RecordAPIRequest(ctx, e.cfg, helps.UpstreamRequestLog{
URL: url,
Method: http.MethodPost,
Headers: httpReq.Header.Clone(),
@@ -383,19 +384,19 @@ func (e *QwenExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Aut
AuthValue: authValue,
})
httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
httpClient := helps.NewProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
httpResp, err := httpClient.Do(httpReq)
if err != nil {
recordAPIResponseError(ctx, e.cfg, err)
helps.RecordAPIResponseError(ctx, e.cfg, err)
return nil, err
}
recordAPIResponseMetadata(ctx, e.cfg, httpResp.StatusCode, httpResp.Header.Clone())
helps.RecordAPIResponseMetadata(ctx, e.cfg, httpResp.StatusCode, httpResp.Header.Clone())
if httpResp.StatusCode < 200 || httpResp.StatusCode >= 300 {
b, _ := io.ReadAll(httpResp.Body)
appendAPIResponseChunk(ctx, e.cfg, b)
helps.AppendAPIResponseChunk(ctx, e.cfg, b)
errCode, retryAfter := wrapQwenError(ctx, httpResp.StatusCode, b)
logWithRequestID(ctx).Debugf("request error, error status: %d (mapped: %d), error message: %s", httpResp.StatusCode, errCode, summarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
helps.LogWithRequestID(ctx).Debugf("request error, error status: %d (mapped: %d), error message: %s", httpResp.StatusCode, errCode, helps.SummarizeErrorBody(httpResp.Header.Get("Content-Type"), b))
if errClose := httpResp.Body.Close(); errClose != nil {
log.Errorf("qwen executor: close response body error: %v", errClose)
}
@@ -415,9 +416,9 @@ func (e *QwenExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Aut
var param any
for scanner.Scan() {
line := scanner.Bytes()
appendAPIResponseChunk(ctx, e.cfg, line)
if detail, ok := parseOpenAIStreamUsage(line); ok {
reporter.publish(ctx, detail)
helps.AppendAPIResponseChunk(ctx, e.cfg, line)
if detail, ok := helps.ParseOpenAIStreamUsage(line); ok {
reporter.Publish(ctx, detail)
}
chunks := sdktranslator.TranslateStream(ctx, to, from, req.Model, opts.OriginalRequest, body, bytes.Clone(line), &param)
for i := range chunks {
@@ -429,8 +430,8 @@ func (e *QwenExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Aut
out <- cliproxyexecutor.StreamChunk{Payload: doneChunks[i]}
}
if errScan := scanner.Err(); errScan != nil {
recordAPIResponseError(ctx, e.cfg, errScan)
reporter.publishFailure(ctx)
helps.RecordAPIResponseError(ctx, e.cfg, errScan)
reporter.PublishFailure(ctx)
out <- cliproxyexecutor.StreamChunk{Err: errScan}
}
}()
@@ -449,17 +450,17 @@ func (e *QwenExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Auth,
modelName = baseModel
}
enc, err := tokenizerForModel(modelName)
enc, err := helps.TokenizerForModel(modelName)
if err != nil {
return cliproxyexecutor.Response{}, fmt.Errorf("qwen executor: tokenizer init failed: %w", err)
}
count, err := countOpenAIChatTokens(enc, body)
count, err := helps.CountOpenAIChatTokens(enc, body)
if err != nil {
return cliproxyexecutor.Response{}, fmt.Errorf("qwen executor: token counting failed: %w", err)
}
usageJSON := buildOpenAIUsageJSON(count)
usageJSON := helps.BuildOpenAIUsageJSON(count)
translated := sdktranslator.TranslateTokenCount(ctx, to, from, count, usageJSON)
return cliproxyexecutor.Response{Payload: translated}, nil
}