highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-10 20:27:27 +01:00
Code Issues Packages Projects Releases Wiki Activity

Reapply "add truncate and shift parameters" (#12582)

Browse Source
This commit is contained in:
Jeffrey Morgan
2025-10-11 16:06:14 -07:00
committed by GitHub
parent 5db8a818a1
commit 6544e14735
8 changed files with 298 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

101
server/routes_generate_test.go
View File

@@ -609,6 +609,58 @@ func TestGenerateChat(t *testing.T) {
t.Errorf("final tool call mismatch (-got +want):\n%s", diff)
}
})
t.Run("status error non-streaming", func(t *testing.T) {
mock.CompletionFn = func(ctx context.Context, r llm.CompletionRequest, fn func(r llm.CompletionResponse)) error {
return api.StatusError{
StatusCode: http.StatusServiceUnavailable,
Status: "Service Unavailable",
ErrorMessage: "model is overloaded",
}
}
stream := false
w := createRequest(t, s.ChatHandler, api.ChatRequest{
Model: "test",
Messages: []api.Message{
{Role: "user", Content: "Hello!"},
},
Stream: &stream,
})
if w.Code != http.StatusServiceUnavailable {
t.Errorf("expected status 503, got %d", w.Code)
}
if diff := cmp.Diff(w.Body.String(), `{"error":"model is overloaded"}`); diff != "" {
t.Errorf("mismatch (-got +want):\n%s", diff)
}
})
t.Run("status error streaming", func(t *testing.T) {
mock.CompletionFn = func(ctx context.Context, r llm.CompletionRequest, fn func(r llm.CompletionResponse)) error {
return api.StatusError{
StatusCode: http.StatusTooManyRequests,
Status: "Too Many Requests",
ErrorMessage: "rate limit exceeded",
}
}
w := createRequest(t, s.ChatHandler, api.ChatRequest{
Model: "test",
Messages: []api.Message{
{Role: "user", Content: "Hello!"},
},
})
if w.Code != http.StatusTooManyRequests {
t.Errorf("expected status 429, got %d", w.Code)
}
if diff := cmp.Diff(w.Body.String(), `{"error":"rate limit exceeded"}`); diff != "" {
t.Errorf("mismatch (-got +want):\n%s", diff)
}
})
}
func TestGenerate(t *testing.T) {
@@ -983,6 +1035,55 @@ func TestGenerate(t *testing.T) {
t.Errorf("mismatch (-got +want):\n%s", diff)
}
})
t.Run("status error non-streaming", func(t *testing.T) {
mock.CompletionFn = func(ctx context.Context, r llm.CompletionRequest, fn func(r llm.CompletionResponse)) error {
return api.StatusError{
StatusCode: http.StatusServiceUnavailable,
Status: "Service Unavailable",
ErrorMessage: "model is overloaded",
}
}
streamRequest := false
w := createRequest(t, s.GenerateHandler, api.GenerateRequest{
Model: "test",
Prompt: "Hello!",
Stream: &streamRequest,
})
if w.Code != http.StatusServiceUnavailable {
t.Errorf("expected status 503, got %d", w.Code)
}
if diff := cmp.Diff(w.Body.String(), `{"error":"model is overloaded"}`); diff != "" {
t.Errorf("mismatch (-got +want):\n%s", diff)
}
})
t.Run("status error streaming", func(t *testing.T) {
mock.CompletionFn = func(ctx context.Context, r llm.CompletionRequest, fn func(r llm.CompletionResponse)) error {
return api.StatusError{
StatusCode: http.StatusTooManyRequests,
Status: "Too Many Requests",
ErrorMessage: "rate limit exceeded",
}
}
w := createRequest(t, s.GenerateHandler, api.GenerateRequest{
Model: "test",
Prompt: "Hello!",
Stream: &stream,
})
if w.Code != http.StatusTooManyRequests {
t.Errorf("expected status 429, got %d", w.Code)
}
if diff := cmp.Diff(w.Body.String(), `{"error":"rate limit exceeded"}`); diff != "" {
t.Errorf("mismatch (-got +want):\n%s", diff)
}
})
}
func TestChatWithPromptEndingInThinkTag(t *testing.T) {