Add web auth, infinite-scroll, agent admission and review fixes across agent/server/web

agent/internal/client/client.go

@@ -4,6 +4,7 @@ import (
 	"bytes"
 	"context"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"io"
 	"net/http"
@@ -15,6 +16,7 @@ import (
 
 const (
 	MaxBatchEvents = 200
+	MaxBatchBytes  = 1 << 20
 )
 
 type Client struct {
@@ -68,18 +70,81 @@ func (c *Client) SendEvents(ctx context.Context, events []scheduler.Event) (*Eve
 		return &EventBatchResponse{}, nil
 	}
 	if len(events) > MaxBatchEvents {
-		return nil, fmt.Errorf("batch exceeds %d events", MaxBatchEvents)
+		return nil, nonRetryablef("batch exceeds %d events", MaxBatchEvents)
 	}
 	wireEvents := make([]scheduler.Event, len(events))
 	for i, ev := range events {
 		wireEvents[i] = ev.WireEvent()
 	}
 	req := EventBatchRequest{AgentID: c.agentID, Events: wireEvents}
-	var resp EventBatchResponse
-	if err := c.post(ctx, "/api/v1/events", req, &resp); err != nil {
+	batches, err := c.splitEventBatches(req.Events)
+	if err != nil {
 		return nil, err
 	}
-	return &resp, nil
+	var total EventBatchResponse
+	for _, batch := range batches {
+		var resp EventBatchResponse
+		if err := c.post(ctx, "/api/v1/events", EventBatchRequest{AgentID: c.agentID, Events: batch}, &resp); err != nil {
+			return nil, err
+		}
+		total.Accepted += resp.Accepted
+		total.Deduplicated += resp.Deduplicated
+	}
+	return &total, nil
+}
+
+func (c *Client) splitEventBatches(events []scheduler.Event) ([][]scheduler.Event, error) {
+	overhead, err := c.eventBatchOverhead()
+	if err != nil {
+		return nil, err
+	}
+	batches := make([][]scheduler.Event, 0, 1)
+	current := make([]scheduler.Event, 0, len(events))
+	currentSize := overhead
+	for _, ev := range events {
+		eventSize, err := jsonSize(ev)
+		if err != nil {
+			return nil, err
+		}
+		nextSize := currentSize + eventSize
+		if len(current) > 0 {
+			nextSize++
+		}
+		if nextSize <= MaxBatchBytes {
+			current = append(current, ev)
+			currentSize = nextSize
+			continue
+		}
+		if len(current) == 0 {
+			return nil, nonRetryablef("single event batch exceeds %d bytes", MaxBatchBytes)
+		}
+		batches = append(batches, current)
+		current = []scheduler.Event{ev}
+		currentSize = overhead + eventSize
+		if currentSize > MaxBatchBytes {
+			return nil, nonRetryablef("single event batch exceeds %d bytes", MaxBatchBytes)
+		}
+	}
+	if len(current) > 0 {
+		batches = append(batches, current)
+	}
+	return batches, nil
+}
+
+func (c *Client) eventBatchOverhead() (int, error) {
+	size, err := jsonSize(EventBatchRequest{AgentID: c.agentID, Events: []scheduler.Event{}})
+	if err != nil {
+		return 0, err
+	}
+	return size, nil
+}
+
+func jsonSize(v any) (int, error) {
+	b, err := json.Marshal(v)
+	if err != nil {
+		return 0, err
+	}
+	return len(b), nil
 }
 
 func (c *Client) post(ctx context.Context, path string, body any, out any) error {
@@ -115,30 +180,28 @@ type HTTPError struct {
 
 func (e *HTTPError) Error() string { return fmt.Sprintf("http %d: %s", e.Status, e.Body) }
 
+type NonRetryableError struct{ Err error }
+
+func (e *NonRetryableError) Error() string { return e.Err.Error() }
+func (e *NonRetryableError) Unwrap() error { return e.Err }
+
+func nonRetryablef(format string, args ...any) error {
+	return &NonRetryableError{Err: fmt.Errorf(format, args...)}
+}
+
 // Retryable reports whether the error should trigger a retry (network errors
 // and 5xx are retryable; 4xx are dropped to avoid hot-loop on bad payload).
 func Retryable(err error) bool {
 	if err == nil {
 		return false
 	}
+	var ne *NonRetryableError
+	if errors.As(err, &ne) {
+		return false
+	}
 	var he *HTTPError
-	if asErr(err, &he) {
+	if errors.As(err, &he) {
 		return he.Status >= 500
 	}
 	return true
 }
-
-func asErr(err error, target **HTTPError) bool {
-	for e := err; e != nil; {
-		if h, ok := e.(*HTTPError); ok {
-			*target = h
-			return true
-		}
-		u, ok := e.(interface{ Unwrap() error })
-		if !ok {
-			return false
-		}
-		e = u.Unwrap()
-	}
-	return false
-}

agent/internal/client/client_test.go

@@ -6,6 +6,7 @@ import (
 	"io"
 	"net/http"
 	"net/http/httptest"
+	"strings"
 	"testing"
 	"time"
 
@@ -57,6 +58,59 @@ func TestSendEventsBatch(t *testing.T) {
 	}
 }
 
+func TestSendEventsSplitsByJSONSize(t *testing.T) {
+	var (
+		requests int
+		total    int
+	)
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		body, err := io.ReadAll(r.Body)
+		if err != nil {
+			t.Error(err)
+			http.Error(w, "read body", http.StatusInternalServerError)
+			return
+		}
+		if len(body) > MaxBatchBytes {
+			t.Errorf("body size %d exceeds %d", len(body), MaxBatchBytes)
+			http.Error(w, "too large", http.StatusRequestEntityTooLarge)
+			return
+		}
+		var got EventBatchRequest
+		if err := json.Unmarshal(body, &got); err != nil {
+			t.Error(err)
+			http.Error(w, "bad json", http.StatusBadRequest)
+			return
+		}
+		requests++
+		total += len(got.Events)
+		w.WriteHeader(http.StatusAccepted)
+		_ = json.NewEncoder(w).Encode(EventBatchResponse{Accepted: len(got.Events)})
+	}))
+	defer srv.Close()
+
+	events := make([]scheduler.Event, MaxBatchEvents)
+	for i := range events {
+		events[i] = scheduler.Event{
+			EventID:    "event-" + time.Unix(int64(i), 0).UTC().Format("20060102150405"),
+			CheckID:    "check",
+			ObservedAt: time.Unix(int64(i), 0).UTC(),
+			Status:     "ok",
+			Output:     strings.Repeat("x", 8192),
+		}
+	}
+	c := New(srv.URL, "tok", "a1")
+	resp, err := c.SendEvents(context.Background(), events)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if requests < 2 {
+		t.Fatalf("expected split batch, got %d request", requests)
+	}
+	if total != MaxBatchEvents || resp.Accepted != MaxBatchEvents {
+		t.Fatalf("total=%d resp=%+v", total, resp)
+	}
+}
+
 func TestSendEventsTooBig(t *testing.T) {
 	c := New("http://x", "t", "a1")
 	big := make([]scheduler.Event, MaxBatchEvents+1)
@@ -64,6 +118,24 @@ func TestSendEventsTooBig(t *testing.T) {
 	if err == nil {
 		t.Fatal("expected error")
 	}
+	if Retryable(err) {
+		t.Fatal("oversized batch should not retry")
+	}
+}
+
+func TestSendEventsSingleEventTooLargeIsNotRetryable(t *testing.T) {
+	c := New("http://x", "t", "a1")
+	_, err := c.SendEvents(context.Background(), []scheduler.Event{{
+		EventID: "x",
+		CheckID: strings.Repeat("c", MaxBatchBytes),
+		Status:  "ok",
+	}})
+	if err == nil {
+		t.Fatal("expected error")
+	}
+	if Retryable(err) {
+		t.Fatal("oversized single event should not retry")
+	}
 }
 
 func TestRetryableClassification(t *testing.T) {