knowledge-governance/internal/httpapi/library_capture_test.go

package httpapi

import (
	"encoding/json"
	"net/http"
	"net/http/httptest"
	"strings"
	"testing"
	"time"

	"knowledge-governance/internal/jobs"
)

func captureRequest(body string) *http.Request {
	request := httptest.NewRequest(http.MethodPost, "/api/v1/library/captures", strings.NewReader(body))
	request.Header.Set("Content-Type", "application/json")
	return request
}

// An unwired agent must refuse clearly instead of queueing a job nobody can run.
func TestLibraryCaptureRefusedWhenAgentUnwired(t *testing.T) {
	store := &fakeJobStore{}
	recorder := httptest.NewRecorder()
	libraryCaptureEnqueue(recorder, captureRequest(`{"scope":"internal"}`), Config{Store: store})
	if recorder.Code != http.StatusServiceUnavailable {
		t.Fatalf("status=%d body=%s", recorder.Code, recorder.Body.String())
	}
	var body map[string]any
	if err := json.Unmarshal(recorder.Body.Bytes(), &body); err != nil {
		t.Fatal(err)
	}
	if body["code"] != "library_capture_unwired" || body["reason"] == "" {
		t.Fatalf("unexpected body %v", body)
	}
	if store.enqueued.Type != "" {
		t.Fatal("unwired agent still enqueued a job")
	}
}

func TestLibraryCaptureEnqueuesFixedJobShape(t *testing.T) {
	store := &fakeJobStore{enqueueEchoRequestedID: true}
	recorder := httptest.NewRecorder()
	libraryCaptureEnqueue(recorder, captureRequest(`{"scope":"external","job":"lib-external-review"}`),
		Config{Store: store, LibraryAgentSocket: "/run/library-agent/agent.sock"})
	if recorder.Code != http.StatusAccepted {
		t.Fatalf("status=%d body=%s", recorder.Code, recorder.Body.String())
	}
	enqueued := store.enqueued
	if enqueued.Type != libraryCaptureJobType {
		t.Fatalf("job type %q", enqueued.Type)
	}
	if enqueued.IdempotencyKey != "library.capture:lib-external-review" {
		t.Fatalf("idempotency key %q", enqueued.IdempotencyKey)
	}
	var payload map[string]string
	if err := json.Unmarshal(enqueued.Payload, &payload); err != nil {
		t.Fatal(err)
	}
	if payload["scope"] != "external" || payload["capture_job"] != "lib-external-review" {
		t.Fatalf("payload %v", payload)
	}
	var body map[string]any
	if err := json.Unmarshal(recorder.Body.Bytes(), &body); err != nil {
		t.Fatal(err)
	}
	if body["capture_job"] != "lib-external-review" || body["scope"] != "external" {
		t.Fatalf("response %v", body)
	}
}

func TestLibraryCaptureRejectsInvalidRequest(t *testing.T) {
	for _, body := range []string{
		`{"scope":"production"}`,
		`{"scope":"internal","job":"bad job; rm -rf /"}`,
		`not json`,
	} {
		store := &fakeJobStore{}
		recorder := httptest.NewRecorder()
		libraryCaptureEnqueue(recorder, captureRequest(body), Config{Store: store, LibraryAgentSocket: "/tmp/agent.sock"})
		if recorder.Code != http.StatusBadRequest {
			t.Fatalf("body %q status=%d", body, recorder.Code)
		}
		if store.enqueued.Type != "" {
			t.Fatalf("invalid request %q still enqueued", body)
		}
	}
}

func TestLibraryCaptureQueueIDFitsTheColumn(t *testing.T) {
	// jobs.id 是 varchar(36)：拼长的 id 会在真实 PG 上 500（value too long）。
	// 页面长期停在"未接线"，这条从没被真实请求覆盖过，所以用测试锁住列宽。
	for _, scope := range []string{"internal", "external"} {
		store := &fakeJobStore{enqueueEchoRequestedID: true}
		recorder := httptest.NewRecorder()
		libraryCaptureEnqueue(recorder, captureRequest(`{"scope":"`+scope+`"}`),
			Config{Store: store, LibraryAgentSocket: "/tmp/agent.sock"})
		if recorder.Code != http.StatusAccepted {
			t.Fatalf("%s status=%d body=%s", scope, recorder.Code, recorder.Body.String())
		}
		enqueued := store.enqueued
		if len(enqueued.ID) > 36 {
			t.Fatalf("%s 队列作业 id 超长（%d）：%q", scope, len(enqueued.ID), enqueued.ID)
		}
		if !strings.HasPrefix(enqueued.ID, "libcap-"+scope+"-") {
			t.Fatalf("%s 队列作业 id 形状变了：%q", scope, enqueued.ID)
		}
	}
}

func TestLibraryCaptureJobsAsksStoreForItsOwnType(t *testing.T) {
	// The global queue is busy with unrelated traffic; the capture job must still
	// be visible because the query is type-scoped, not filtered after the fact.
	store := &fakeJobStore{
		listResult: []jobs.Job{{ID: "busy", Type: "artifact.fetch", State: "running"}},
		listByTypeResult: []jobs.Job{
			{ID: "a", Type: libraryCaptureJobType, State: "completed",
				Payload:   json.RawMessage(`{"scope":"internal","capture_job":"lib-internal-1","requested_by":"yaozhanghao"}`),
				CreatedAt: time.Date(2026, 10, 28, 3, 0, 0, 0, time.UTC)},
		},
	}
	recorder := httptest.NewRecorder()
	libraryCaptureJobs(recorder, httptest.NewRequest(http.MethodGet, "/api/v1/library/captures", nil), Config{Store: store})
	if recorder.Code != http.StatusOK {
		t.Fatalf("status=%d", recorder.Code)
	}
	if store.listType != libraryCaptureJobType {
		t.Fatalf("store queried with type %q", store.listType)
	}
	var body struct {
		Available bool             `json:"available"`
		Jobs      []map[string]any `json:"jobs"`
	}
	if err := json.Unmarshal(recorder.Body.Bytes(), &body); err != nil {
		t.Fatal(err)
	}
	if !body.Available || len(body.Jobs) != 1 || body.Jobs[0]["capture_job"] != "lib-internal-1" {
		t.Fatalf("unexpected body %+v", body)
	}
}

// Reusing a capture job id with another scope must be refused, and the response
// must report the scope that was actually stored.
func TestLibraryCaptureRejectsScopeConflictForReusedJob(t *testing.T) {
	store := &fakeJobStore{enqueueResult: &jobs.Job{ID: "existing-job", Type: libraryCaptureJobType,
		State:   jobs.StateCompleted,
		Payload: json.RawMessage(`{"scope":"internal","capture_job":"lib-shared","requested_by":"yaozhanghao"}`)}}
	recorder := httptest.NewRecorder()
	libraryCaptureEnqueue(recorder, captureRequest(`{"scope":"external","job":"lib-shared"}`),
		Config{Store: store, LibraryAgentSocket: "/run/library-agent/agent.sock"})
	if recorder.Code != http.StatusConflict {
		t.Fatalf("status=%d body=%s", recorder.Code, recorder.Body.String())
	}
	var body map[string]any
	if err := json.Unmarshal(recorder.Body.Bytes(), &body); err != nil {
		t.Fatal(err)
	}
	if body["code"] != "library_capture_scope_conflict" || body["existing_scope"] != "internal" || body["requested_scope"] != "external" {
		t.Fatalf("unexpected conflict body %v", body)
	}
}

// A reused job id with an identical request is answered from the stored row.
func TestLibraryCaptureReplayReportsStoredJob(t *testing.T) {
	store := &fakeJobStore{enqueueResult: &jobs.Job{ID: "existing-job", Type: libraryCaptureJobType,
		State:   jobs.StateCompleted,
		Payload: json.RawMessage(`{"scope":"internal","capture_job":"lib-shared","requested_by":"yaozhanghao"}`)}}
	recorder := httptest.NewRecorder()
	libraryCaptureEnqueue(recorder, captureRequest(`{"scope":"internal","job":"lib-shared"}`),
		Config{Store: store, LibraryAgentSocket: "/run/library-agent/agent.sock"})
	if recorder.Code != http.StatusAccepted {
		t.Fatalf("status=%d body=%s", recorder.Code, recorder.Body.String())
	}
	var body map[string]any
	if err := json.Unmarshal(recorder.Body.Bytes(), &body); err != nil {
		t.Fatal(err)
	}
	if body["scope"] != "internal" || body["capture_job"] != "lib-shared" || body["reused"] != true || body["job_id"] != "existing-job" {
		t.Fatalf("unexpected replay body %v", body)
	}
}