feat: llamacpp health check client

Add internal/llamacpp package with Client type and Health() method.
Client communicates with llama-server via HTTP; Health checks the
/health endpoint and reports readiness. Foundation type for the
streaming methods (Tasks 2-3).

Co-Authored-By: Virgil <virgil@lethean.io>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

go.mod

@@ -4,4 +4,11 @@ go 1.25.5
 
 require forge.lthn.ai/core/go-inference v0.0.0
 
+require (
+	github.com/davecgh/go-spew v1.1.1 // indirect
+	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/stretchr/testify v1.11.1
+	gopkg.in/yaml.v3 v3.0.1 // indirect
+)
+
 replace forge.lthn.ai/core/go-inference => ../go-inference

go.sum

@@ -0,0 +1,10 @@
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
+github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

internal/llamacpp/health.go

@@ -0,0 +1,52 @@
+package llamacpp
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"strings"
+)
+
+// Client communicates with a llama-server instance.
+type Client struct {
+	baseURL    string
+	httpClient *http.Client
+}
+
+// NewClient creates a client for the llama-server at the given base URL.
+func NewClient(baseURL string) *Client {
+	return &Client{
+		baseURL:    strings.TrimRight(baseURL, "/"),
+		httpClient: &http.Client{},
+	}
+}
+
+type healthResponse struct {
+	Status string `json:"status"`
+}
+
+// Health checks whether the llama-server is ready to accept requests.
+func (c *Client) Health(ctx context.Context) error {
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, c.baseURL+"/health", nil)
+	if err != nil {
+		return err
+	}
+	resp, err := c.httpClient.Do(req)
+	if err != nil {
+		return err
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		return fmt.Errorf("llamacpp: health returned %d", resp.StatusCode)
+	}
+	var h healthResponse
+	if err := json.NewDecoder(resp.Body).Decode(&h); err != nil {
+		return fmt.Errorf("llamacpp: health decode: %w", err)
+	}
+	if h.Status != "ok" {
+		return fmt.Errorf("llamacpp: server not ready (status: %s)", h.Status)
+	}
+	return nil
+}

internal/llamacpp/health_test.go

@@ -0,0 +1,42 @@
+package llamacpp
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestHealth_OK(t *testing.T) {
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		assert.Equal(t, "/health", r.URL.Path)
+		w.Header().Set("Content-Type", "application/json")
+		w.Write([]byte(`{"status":"ok"}`))
+	}))
+	defer ts.Close()
+
+	c := NewClient(ts.URL)
+	err := c.Health(context.Background())
+	require.NoError(t, err)
+}
+
+func TestHealth_NotReady(t *testing.T) {
+	ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		w.Write([]byte(`{"status":"loading model"}`))
+	}))
+	defer ts.Close()
+
+	c := NewClient(ts.URL)
+	err := c.Health(context.Background())
+	assert.ErrorContains(t, err, "not ready")
+}
+
+func TestHealth_ServerDown(t *testing.T) {
+	c := NewClient("http://127.0.0.1:1") // nothing listening
+	err := c.Health(context.Background())
+	assert.Error(t, err)
+}