Implement support for OpenRouter sticky routing via a session_id variable
This commit is contained in:
@@ -12,6 +12,7 @@ import (
|
||||
"os"
|
||||
"strings"
|
||||
"time"
|
||||
"unicode/utf8"
|
||||
|
||||
"gitea.maximumdirect.net/eric/scriptorium/internal/defaults"
|
||||
"gitea.maximumdirect.net/eric/scriptorium/internal/domain"
|
||||
@@ -169,6 +170,12 @@ func openAIChatRequestFromGenerateRequest(req domain.GenerateRequest, defaultMod
|
||||
wireReq := openAIChatRequest{
|
||||
Model: model,
|
||||
}
|
||||
if sessionID := strings.TrimSpace(req.Prompt.SessionID); sessionID != "" {
|
||||
if n := utf8.RuneCountInString(sessionID); n > domain.SessionIDMaxLength {
|
||||
return openAIChatRequest{}, fmt.Errorf("session_id length %d exceeds maximum %d", n, domain.SessionIDMaxLength)
|
||||
}
|
||||
wireReq.SessionID = sessionID
|
||||
}
|
||||
|
||||
wireReq.Messages = make([]openAIChatRequestMessage, 0, len(req.Prompt.Messages))
|
||||
for _, msg := range req.Prompt.Messages {
|
||||
@@ -200,6 +207,7 @@ func openAIChatRequestFromGenerateRequest(req domain.GenerateRequest, defaultMod
|
||||
|
||||
type openAIChatRequest struct {
|
||||
Model string `json:"model"`
|
||||
SessionID string `json:"session_id,omitempty"`
|
||||
Messages []openAIChatRequestMessage `json:"messages"`
|
||||
Temperature *float64 `json:"temperature,omitempty"`
|
||||
MaxTokens *int `json:"max_tokens,omitempty"`
|
||||
|
||||
@@ -181,7 +181,7 @@ func TestOpenAICompatibleClientSerializesCacheControlledMessageAsContentBlock(t
|
||||
t.Fatalf("expected no error, got %v", err)
|
||||
}
|
||||
|
||||
for _, forbidden := range []string{"cache_control", "session_id", "extra_params"} {
|
||||
for _, forbidden := range []string{"cache_control", "extra_params"} {
|
||||
if _, exists := observedBody[forbidden]; exists {
|
||||
t.Fatalf("expected top-level %s to be omitted, got %#v", forbidden, observedBody[forbidden])
|
||||
}
|
||||
@@ -262,6 +262,96 @@ func TestOpenAICompatibleClientOmitsEmptyCacheControlTTL(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestOpenAICompatibleClientSerializesSessionID(t *testing.T) {
|
||||
var observedBody map[string]any
|
||||
var observedSessionHeader string
|
||||
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
observedSessionHeader = r.Header.Get("x-session-id")
|
||||
defer r.Body.Close()
|
||||
if err := json.NewDecoder(r.Body).Decode(&observedBody); err != nil {
|
||||
t.Fatalf("failed to decode request body: %v", err)
|
||||
}
|
||||
_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"ok"}}]}`))
|
||||
}))
|
||||
defer ts.Close()
|
||||
|
||||
client, err := NewOpenAICompatibleClient(OpenAICompatibleConfig{BaseURL: ts.URL + "/v1"})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
_, err = client.Generate(context.Background(), domain.GenerateRequest{
|
||||
Prompt: domain.RenderedPrompt{
|
||||
SessionID: " session-123 ",
|
||||
Messages: []domain.RenderedMessage{{Role: "user", Content: "hi"}},
|
||||
},
|
||||
Target: domain.ExecutionTarget{Model: "model"},
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("expected no error, got %v", err)
|
||||
}
|
||||
if observedBody["session_id"] != "session-123" {
|
||||
t.Fatalf("expected top-level session_id, got %#v", observedBody["session_id"])
|
||||
}
|
||||
if observedSessionHeader != "" {
|
||||
t.Fatalf("did not expect x-session-id header, got %q", observedSessionHeader)
|
||||
}
|
||||
}
|
||||
|
||||
func TestOpenAICompatibleClientOmitsEmptySessionID(t *testing.T) {
|
||||
var observedBody map[string]any
|
||||
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
defer r.Body.Close()
|
||||
if err := json.NewDecoder(r.Body).Decode(&observedBody); err != nil {
|
||||
t.Fatalf("failed to decode request body: %v", err)
|
||||
}
|
||||
_, _ = w.Write([]byte(`{"choices":[{"message":{"content":"ok"}}]}`))
|
||||
}))
|
||||
defer ts.Close()
|
||||
|
||||
client, err := NewOpenAICompatibleClient(OpenAICompatibleConfig{BaseURL: ts.URL + "/v1"})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
_, err = client.Generate(context.Background(), domain.GenerateRequest{
|
||||
Prompt: domain.RenderedPrompt{
|
||||
SessionID: " ",
|
||||
Messages: []domain.RenderedMessage{{Role: "user", Content: "hi"}},
|
||||
},
|
||||
Target: domain.ExecutionTarget{Model: "model"},
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("expected no error, got %v", err)
|
||||
}
|
||||
if _, exists := observedBody["session_id"]; exists {
|
||||
t.Fatalf("expected empty session_id to be omitted, got %#v", observedBody["session_id"])
|
||||
}
|
||||
}
|
||||
|
||||
func TestOpenAICompatibleClientRejectsTooLongSessionID(t *testing.T) {
|
||||
client, err := NewOpenAICompatibleClient(OpenAICompatibleConfig{
|
||||
BaseURL: "http://example.com/v1",
|
||||
Model: "model",
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
_, err = client.Generate(context.Background(), domain.GenerateRequest{
|
||||
Prompt: domain.RenderedPrompt{
|
||||
SessionID: strings.Repeat("x", domain.SessionIDMaxLength+1),
|
||||
Messages: []domain.RenderedMessage{{Role: "user", Content: "hi"}},
|
||||
},
|
||||
})
|
||||
if err == nil {
|
||||
t.Fatal("expected invalid request error")
|
||||
}
|
||||
if !errors.Is(err, ErrInvalidRequest) {
|
||||
t.Fatalf("expected ErrInvalidRequest, got %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
func TestOpenAICompatibleClientParsesCacheUsage(t *testing.T) {
|
||||
ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
||||
_, _ = w.Write([]byte(`{
|
||||
|
||||
Reference in New Issue
Block a user