Files
ollama_ollama/cmd/warn_thinking_test.go
T
Devon Rifkin 5f57b0ef42
release / setup-environment (push) Has been cancelled
release / windows-depends (amd64, 11.3, https://developer.download.nvidia.com/compute/cuda/11.3.1/local_installers/cuda_11.3.1_465.89_win10.exe, windows, CUDA 11) (push) Has been cancelled
release / windows-depends (amd64, 12.8, https://developer.download.nvidia.com/compute/cuda/12.8.0/local_installers/cuda_12.8.0_571.96_windows.exe, windows, CUDA 12) (push) Has been cancelled
release / windows-depends (amd64, https://download.amd.com/developer/eula/rocm-hub/AMD-Software-PRO-Edition-24.Q4-WinSvr2022-For-HIP.exe, windows, ROCm 6, 6.2) (push) Has been cancelled
release / windows-depends (amd64, windows, CPU) (push) Has been cancelled
release / darwin-build (amd64, darwin) (push) Has been cancelled
release / darwin-build (arm64, darwin) (push) Has been cancelled
release / darwin-sign (push) Has been cancelled
release / windows-build (amd64, windows) (push) Has been cancelled
release / windows-build (arm64, windows) (push) Has been cancelled
release / windows-sign (push) Has been cancelled
release / linux-build (amd64, linux, archive) (push) Has been cancelled
release / linux-build (amd64, linux, rocm) (push) Has been cancelled
release / linux-build (arm64, linux, archive) (push) Has been cancelled
release / docker-build-push (amd64, CGO_CFLAGS CGO_CXXFLAGS GOFLAGS , linux) (push) Has been cancelled
release / docker-build-push (amd64, CGO_CFLAGS CGO_CXXFLAGS GOFLAGS FLAVOR=rocm , linux, -rocm) (push) Has been cancelled
release / docker-build-push (arm64, CGO_CFLAGS CGO_CXXFLAGS GOFLAGS , linux) (push) Has been cancelled
release / docker-merge-push () (push) Has been cancelled
release / docker-merge-push (-rocm) (push) Has been cancelled
release / trigger (push) Has been cancelled
release / release (push) Has been cancelled
add thinking support to the api and cli (#10584)
- Both `/api/generate` and `/api/chat` now accept a `"think"`
  option that allows specifying whether thinking mode should be on or
  not
- Templates get passed this new option so, e.g., qwen3's template can
  put `/think` or `/no_think` in the system prompt depending on the
  value of the setting
- Models' thinking support is inferred by inspecting model templates.
  The prefix and suffix the parser uses to identify thinking support is
  also automatically inferred from templates
- Thinking control & parsing is opt-in via the API to prevent breaking
  existing API consumers. If the `"think"` option is not specified, the
  behavior is unchanged from previous versions of ollama
- Add parsing for thinking blocks in both streaming/non-streaming mode
  in both `/generate` and `/chat`
- Update the CLI to make use of these changes. Users can pass `--think`
  or `--think=false` to control thinking, or during an interactive
  session they can use the commands `/set think` or `/set nothink`
- A `--hidethinking` option has also been added to the CLI. This makes
  it easy to use thinking in scripting scenarios like
  `ollama run qwen3 --think --hidethinking "my question here"` where you
  just want to see the answer but still want the benefits of thinking
  models
2025-05-28 19:38:52 -07:00

64 lines
1.6 KiB
Go

package cmd
import (
"encoding/json"
"io"
"net/http"
"net/http/httptest"
"os"
"strings"
"testing"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/types/model"
)
// Test that a warning is printed when thinking is requested but not supported.
func TestWarnMissingThinking(t *testing.T) {
cases := []struct {
capabilities []model.Capability
expectWarn bool
}{
{capabilities: []model.Capability{model.CapabilityThinking}, expectWarn: false},
{capabilities: []model.Capability{}, expectWarn: true},
}
for _, tc := range cases {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path != "/api/show" || r.Method != http.MethodPost {
t.Fatalf("unexpected request to %s %s", r.URL.Path, r.Method)
}
var req api.ShowRequest
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
t.Fatalf("decode request: %v", err)
}
resp := api.ShowResponse{Capabilities: tc.capabilities}
if err := json.NewEncoder(w).Encode(resp); err != nil {
t.Fatalf("encode response: %v", err)
}
}))
defer srv.Close()
t.Setenv("OLLAMA_HOST", srv.URL)
client, err := api.ClientFromEnvironment()
if err != nil {
t.Fatal(err)
}
oldStderr := os.Stderr
r, w, _ := os.Pipe()
os.Stderr = w
ensureThinkingSupport(t.Context(), client, "m")
w.Close()
os.Stderr = oldStderr
out, _ := io.ReadAll(r)
warned := strings.Contains(string(out), "warning:")
if tc.expectWarn && !warned {
t.Errorf("expected warning, got none")
}
if !tc.expectWarn && warned {
t.Errorf("did not expect warning, got: %s", string(out))
}
}
}