jianf/ModelRouter
1
0
Fork 0
mirror of https://gitcode.com/JianFeeeee/ModelRouter.git synced 2026-10-03 15:44:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: tool call anchor & wire format, streaming chunk passthrough, WebUI narrow-screen, docs bilingual

Browse Source
This commit is contained in:
root
2026-08-08 11:26:58 +08:00
parent 8e9de95274
commit 5d50b69153
18 changed files with 1119 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
internal/scheduler/scheduler.go
View File

@ -28,6 +28,7 @@ func New(maxRetries int) *Scheduler {
type Provider interface {
Name() string
Available() bool
ModelFor(reqModel string) string
Chat(ctx context.Context, req *types.ChatRequest) (*types.UnifiedResponse, error)
ChatStream(ctx context.Context, req *types.ChatRequest) (<-chan types.UnifiedChunk, error)
Image(ctx context.Context, req *types.ImageGenRequest) (*types.UnifiedResponse, error)
@ -42,13 +43,18 @@ func FromRegistry(ps []*provider.Provider) []Provider {
return out
}
// Chat runs a chat request across cands, falling back on failure.
// Chat runs a chat request across cands, falling back on failure. Each
// candidate receives a request pinned to its own model (ModelFor), so an AUTO
// chain fallback switches the model id per provider instead of reusing the
// first candidate's model name.
func (s *Scheduler) Chat(ctx context.Context, cands []Provider, req *types.ChatRequest) (*types.UnifiedResponse, error) {
attempts := s.MaxRetries + 1
var lastErr error
for i := 0; i < attempts && i < len(cands); i++ {
p := cands[i]
resp, err := p.Chat(ctx, req)
r := *req
r.Model = p.ModelFor(req.Model)
resp, err := p.Chat(ctx, &r)
if ctx.Err() != nil {
return nil, ctx.Err()
}
@ -68,13 +74,16 @@ func (s *Scheduler) Chat(ctx context.Context, cands []Provider, req *types.ChatR
return nil, lastErr
}
// ChatStream runs a streaming chat across cands, falling back early on connect errors.
// ChatStream runs a streaming chat across cands, falling back early on connect
// errors. The request model is pinned per candidate like Chat.
func (s *Scheduler) ChatStream(ctx context.Context, cands []Provider, req *types.ChatRequest) (<-chan types.UnifiedChunk, error) {
attempts := s.MaxRetries + 1
var lastErr error
for i := 0; i < attempts && i < len(cands); i++ {
p := cands[i]
resp, err := p.ChatStream(ctx, req)
r := *req
r.Model = p.ModelFor(req.Model)
resp, err := p.ChatStream(ctx, &r)
if err == nil {
return resp, nil
}