Merge pull request #1 from thepeterstone/claude/local-oss-model-agents-MEBqj

Local OSS models as a third runner (epic)

1 files changed, 152 insertions, 0 deletions

diff --git a/internal/executor/local_test.go b/internal/executor/local_test.go
new file mode 100644
index 0000000..d8ab678
--- /dev/null
+++ b/internal/executor/local_test.go
@@ -0,0 +1,152 @@
+package executor
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"log/slog"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/google/uuid"
+	"github.com/thepeterstone/claudomator/internal/llm"
+	"github.com/thepeterstone/claudomator/internal/storage"
+	"github.com/thepeterstone/claudomator/internal/task"
+)
+
+// fakeOpenAIServer returns an httptest.Server that replies with a streaming
+// chat completion containing the supplied content (split into chunks) plus a
+// usage record.
+func fakeOpenAIServer(t *testing.T, chunks []string, promptTok, outTok int) *httptest.Server {
+	t.Helper()
+	return httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "text/event-stream")
+		flusher, _ := w.(http.Flusher)
+		for _, c := range chunks {
+			payload := map[string]any{
+				"model":   "fake",
+				"choices": []map[string]any{{"delta": map[string]string{"content": c}}},
+			}
+			b, _ := json.Marshal(payload)
+			fmt.Fprintf(w, "data: %s\n\n", b)
+			if flusher != nil {
+				flusher.Flush()
+			}
+		}
+		final := map[string]any{
+			"model":   "fake",
+			"choices": []map[string]any{{"delta": map[string]string{}, "finish_reason": "stop"}},
+			"usage":   map[string]int{"prompt_tokens": promptTok, "completion_tokens": outTok},
+		}
+		fb, _ := json.Marshal(final)
+		fmt.Fprintf(w, "data: %s\n\ndata: [DONE]\n\n", fb)
+	}))
+}
+
+func TestLocalRunner_Run_WritesStreamJSON(t *testing.T) {
+	srv := fakeOpenAIServer(t,
+		[]string{"## Summary\n", "All ", "good."},
+		11, 22,
+	)
+	defer srv.Close()
+
+	logRoot := t.TempDir()
+	r := &LocalRunner{
+		Client: &llm.Client{Endpoint: srv.URL + "/v1", Model: "fake"},
+		Logger: slog.New(slog.NewTextHandler(io.Discard, nil)),
+		LogDir: logRoot,
+	}
+	tt := &task.Task{
+		ID:   "task-1",
+		Name: "test",
+		Agent: task.AgentConfig{
+			Type:         "local",
+			Model:        "fake",
+			Instructions: "Do a thing.",
+		},
+	}
+	exec := &storage.Execution{ID: uuid.New().String(), TaskID: tt.ID}
+
+	if err := r.Run(context.Background(), tt, exec); err != nil {
+		t.Fatalf("Run: %v", err)
+	}
+
+	if exec.CostUSD != 0 {
+		t.Errorf("CostUSD should be 0 for local runner, got %v", exec.CostUSD)
+	}
+	if exec.TokensIn != 11 || exec.TokensOut != 22 {
+		t.Errorf("tokens: want 11/22 got %d/%d", exec.TokensIn, exec.TokensOut)
+	}
+
+	// Verify stdout.log contains stream-json envelopes that extractSummary can parse.
+	stdoutPath := filepath.Join(r.ExecLogDir(exec.ID), "stdout.log")
+	data, err := os.ReadFile(stdoutPath)
+	if err != nil {
+		t.Fatalf("read stdout: %v", err)
+	}
+	lines := strings.Split(strings.TrimSpace(string(data)), "\n")
+	if len(lines) < 4 {
+		t.Fatalf("expected at least 4 lines (3 deltas + 1 result), got %d:\n%s", len(lines), data)
+	}
+	for i, line := range lines[:3] {
+		var env struct {
+			Type    string `json:"type"`
+			Message struct {
+				Content []struct {
+					Type string `json:"type"`
+					Text string `json:"text"`
+				}
+			}
+		}
+		if err := json.Unmarshal([]byte(line), &env); err != nil {
+			t.Fatalf("line %d not JSON: %v: %s", i, err, line)
+		}
+		if env.Type != "assistant" {
+			t.Errorf("line %d: want type=assistant, got %q", i, env.Type)
+		}
+	}
+
+	summary := extractSummary(stdoutPath)
+	if !strings.Contains(summary, "All good.") {
+		t.Errorf("extractSummary should find 'All good.', got %q", summary)
+	}
+}
+
+func TestLocalRunner_Run_NoClient_Errors(t *testing.T) {
+	r := &LocalRunner{LogDir: t.TempDir()}
+	tt := &task.Task{ID: "x", Agent: task.AgentConfig{Instructions: "hi"}}
+	exec := &storage.Execution{ID: "exec-x"}
+	err := r.Run(context.Background(), tt, exec)
+	if err == nil || !strings.Contains(err.Error(), "no LLM client") {
+		t.Errorf("expected 'no LLM client' error, got %v", err)
+	}
+}
+
+func TestLocalRunner_Run_EmptyInstructions_Errors(t *testing.T) {
+	r := &LocalRunner{
+		Client: &llm.Client{Endpoint: "http://unused", Model: "x"},
+		LogDir: t.TempDir(),
+	}
+	tt := &task.Task{ID: "x", Agent: task.AgentConfig{}}
+	exec := &storage.Execution{ID: "exec-x"}
+	err := r.Run(context.Background(), tt, exec)
+	if err == nil || !strings.Contains(err.Error(), "empty instructions") {
+		t.Errorf("expected empty-instructions error, got %v", err)
+	}
+}
+
+func TestLocalRunner_ExecLogDir(t *testing.T) {
+	r := &LocalRunner{LogDir: "/tmp/logs"}
+	if got := r.ExecLogDir("abc"); got != "/tmp/logs/abc" {
+		t.Errorf("ExecLogDir: got %q", got)
+	}
+	r.LogDir = ""
+	if got := r.ExecLogDir("abc"); got != "" {
+		t.Errorf("ExecLogDir empty LogDir: got %q", got)
+	}
+}