v2.1 plan: task 01 cancel-record with its given served_test.go; index for 02/03

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-25 11:12:58 -07:00
parent 481ea12f4c
commit a49a86c0e4
3 changed files with 181 additions and 0 deletions
@@ -0,0 +1,83 @@
+package proxy_test
+
+import (
+	"net/http"
+	"strings"
+	"sync"
+	"testing"
+	"time"
+
+	"git.wntrmute.dev/kyle/crossbar/internal/store"
+)
+
+// A response the proxy delivered in full is recorded with the status the upstream returned, even
+// when the client closes its connection the instant the body ends. Cancellation is what the
+// reverse proxy observed while forwarding (a transport error before any byte, or the client
+// leaving mid-body), never a look at the request context after the forward returned.
+//
+// Each request uses its own connection and closes it as soon as the response is read, which is
+// what a pooled client does when its idle pool is full; the server then cancels the request's
+// context while the handler may still be writing the accounting row.
+func TestServedResponseIsNeverRecordedCancelled(t *testing.T) {
+	alpha := newUpstream(t, "alpha")
+	alpha.delay = 20 * time.Millisecond
+	r := newRig(t, `
+listen = "127.0.0.1:1"
+queue_max = 64
+[hosts.alpha]
+base_url = %q
+models = { "shared" = { parallel = 8 } }
+[routes.r]
+hosts = ["alpha"]
+default_model = "shared"
+`, alpha)
+
+	const n = 32
+	var wg sync.WaitGroup
+	codes := make([]int, n)
+	for i := 0; i < n; i++ {
+		wg.Add(1)
+		go func(i int) {
+			defer wg.Done()
+			client := &http.Client{Transport: &http.Transport{DisableKeepAlives: true}}
+			req, _ := http.NewRequest(http.MethodPost, r.front.URL+"/r/v1/chat/completions", strings.NewReader(conversation(i, 1)))
+			req.Header.Set("Content-Type", "application/json")
+			resp, err := client.Do(req)
+			if err != nil {
+				t.Error(err)
+				return
+			}
+			drain(resp)
+			codes[i] = resp.StatusCode
+		}(i)
+	}
+	wg.Wait()
+	for i, c := range codes {
+		if c != 200 {
+			t.Fatalf("request %d: status %d, want 200", i, c)
+		}
+	}
+
+	// Rows are written after each response completes; allow the store a moment to catch up.
+	var rows []store.UsageRow
+	deadline := time.Now().Add(3 * time.Second)
+	for time.Now().Before(deadline) {
+		rows, _ = r.store.Usage(time.Time{}, store.ByRoute)
+		if len(rows) == 1 && rows[0].Requests == n {
+			break
+		}
+		time.Sleep(20 * time.Millisecond)
+	}
+	if len(rows) != 1 || rows[0].Requests != n {
+		t.Fatalf("usage = %+v, want one row with %d requests", rows, n)
+	}
+	if rows[0].Errors != 0 {
+		t.Errorf("usage = %+v, want 0 errors: every response was delivered with status 200", rows[0])
+	}
+	counts, _ := r.store.StatusCounts(time.Time{})
+	for _, c := range counts {
+		if c.Status != 200 {
+			t.Errorf("status counts %+v: a delivered 200 was recorded as %d", counts, c.Status)
+		}
+	}
+}