All checks were successful
Sync infra to hosts / sync-beta (push) Successful in 8s
Sync infra to hosts / sync-prod (push) Successful in 7s
secrets-guard / encrypted (push) Successful in 8s
shell-lint / shellcheck (push) Successful in 10s
Build + push backend image (Forgejo registry) / build-push (push) Successful in 1m14s
Deploy backend to beta VPS / deploy (push) Successful in 2m4s
The gateway bot and APScheduler were long-lived stateful I/O loops running inside the async web app under a leader election. They move into a single Go binary that owns ONLY that I/O -- websocket, RESUME, heartbeat, backoff, timers. It owns no grading logic. Anything needing data calls back over a new internal-only surface (/internal/discord/grade, /internal/jobs/*). Grading depends on polars and the parquet cache; reimplementing it in Go would let the bot's grades drift from the API's. The grade route returns gateway-ready JSON and Go relays the bytes verbatim. The binary ships in the backend image and runs as a second compose service off the same tag, so the two ends of the /internal/* contract can never skew. deploy.sh rolls daemon alongside backend -- without that the service would never be created, since a single-service deploy uses --no-deps. It also probes the image first and skips the daemon when rolling a tag that predates the binary: infra tracks main while image tags are env-staged, so a host can legitimately be asked to roll an older backend image, and creating the service anyway would leave a container crash-looping on a missing binary. replicas: 1 with order: stop-first replaces the leader election -- Discord permits one gateway connection per bot token. THERMOGRAPH_INTERNAL_TOKEN is optional: both ends derive it from THERMOGRAPH_AUTH_SECRET via HMAC under a domain-separation label, so this needs no new vault entry. The derivation is pinned to a shared cross-language test vector asserted on both sides, so drift fails CI instead of 401ing every call. Fail closed when neither secret is set. Improvements over the Python: a close intended for RESUME uses 4000 rather than 1000 (Discord invalidates a session closed 1000, so the old default defeated its own resume); MESSAGE_CREATE runs on a bounded worker pool; and a malformed HELLO returns an error rather than a clean reconnect, which would otherwise reset backoff and hot-loop against the gateway. 365 Python tests pass; Go build/vet/test -race clean; shellcheck 0 findings.
182 lines
5.8 KiB
Go
182 lines
5.8 KiB
Go
// Connection-machinery tests, restricted to the pure parts (backoff, fatal
|
|
// close codes, READY/session bookkeeping, sequence tracking). Deliberately no
|
|
// live-gateway test — that path is exercised in staging, not CI.
|
|
|
|
package gateway
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"net/http"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/coder/websocket"
|
|
)
|
|
|
|
func TestBackoffDoublesAndCaps(t *testing.T) {
|
|
want := []time.Duration{
|
|
2 * time.Second, 4 * time.Second, 8 * time.Second, 16 * time.Second,
|
|
32 * time.Second, 60 * time.Second, 60 * time.Second, 60 * time.Second,
|
|
}
|
|
d := backoffStart
|
|
for i, w := range want {
|
|
d = nextBackoff(d)
|
|
if d != w {
|
|
t.Fatalf("step %d: want %s, got %s", i, w, d)
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestFatalCloseCodes(t *testing.T) {
|
|
for _, c := range []websocket.StatusCode{4004, 4010, 4011, 4012, 4013, 4014} {
|
|
if !isFatalClose(c) {
|
|
t.Errorf("close code %d must be fatal (reconnecting loops forever)", c)
|
|
}
|
|
}
|
|
// 4008 (rate limited) and 4009 (session timed out) are resumable; 4000 is
|
|
// our own zombie close; -1 is CloseStatus's not-a-close-error sentinel.
|
|
for _, c := range []websocket.StatusCode{-1, 1000, 1001, 4000, 4001, 4008, 4009} {
|
|
if isFatalClose(c) {
|
|
t.Errorf("close code %d must not be fatal", c)
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestReadyCapturesResumeState(t *testing.T) {
|
|
b := New("tok", &fakeGrader{})
|
|
sess := &session{}
|
|
d := []byte(`{"session_id":"abc","resume_gateway_url":"wss://resume.example/","user":{"id":"999"}}`)
|
|
|
|
b.dispatch(context.Background(), payload{Op: opDispatch, T: "READY", D: d}, sess)
|
|
|
|
if sess.sessionID != "abc" {
|
|
t.Fatalf("want session id abc, got %q", sess.sessionID)
|
|
}
|
|
// Trailing slash trimmed, gateway query string appended — RESUME must go
|
|
// to the session's own URL with the same v10/json parameters.
|
|
if sess.resumeURL != "wss://resume.example/?v=10&encoding=json" {
|
|
t.Fatalf("bad resume url: %q", sess.resumeURL)
|
|
}
|
|
if sess.userID != botID {
|
|
t.Fatalf("want user id %s, got %q", botID, sess.userID)
|
|
}
|
|
}
|
|
|
|
func TestReadyWithoutResumeURLLeavesItEmpty(t *testing.T) {
|
|
b := New("tok", &fakeGrader{})
|
|
sess := &session{resumeURL: "wss://stale.example/?v=10&encoding=json"}
|
|
d := []byte(`{"session_id":"abc","user":{"id":"999"}}`)
|
|
|
|
b.dispatch(context.Background(), payload{Op: opDispatch, T: "READY", D: d}, sess)
|
|
|
|
if sess.resumeURL != "" {
|
|
t.Fatalf("a READY without resume_gateway_url must clear the stale url, got %q", sess.resumeURL)
|
|
}
|
|
}
|
|
|
|
func TestMessageCreateBeforeReadyIsIgnored(t *testing.T) {
|
|
// Until READY supplies our user id we cannot detect mentions (or guard
|
|
// against answering ourselves), so nothing may be handled.
|
|
g := &fakeGrader{resp: json.RawMessage(`{}`)}
|
|
b := New("tok", g)
|
|
sess := &session{} // no userID yet
|
|
d, err := json.Marshal(testMsg("<@999> Phoenix", mentioning(botID)))
|
|
if err != nil {
|
|
t.Fatalf("marshal: %v", err)
|
|
}
|
|
|
|
b.dispatch(context.Background(), payload{Op: opDispatch, T: "MESSAGE_CREATE", D: d}, sess)
|
|
|
|
time.Sleep(20 * time.Millisecond)
|
|
if g.callCount() != 0 {
|
|
t.Fatal("pre-READY message must be ignored")
|
|
}
|
|
}
|
|
|
|
func TestPayloadSequenceIsNullable(t *testing.T) {
|
|
var withSeq, withoutSeq payload
|
|
if err := json.Unmarshal([]byte(`{"op":0,"t":"X","s":7,"d":{}}`), &withSeq); err != nil {
|
|
t.Fatalf("unmarshal: %v", err)
|
|
}
|
|
if withSeq.S == nil || *withSeq.S != 7 {
|
|
t.Fatalf("want seq 7, got %v", withSeq.S)
|
|
}
|
|
if err := json.Unmarshal([]byte(`{"op":11,"s":null,"d":null}`), &withoutSeq); err != nil {
|
|
t.Fatalf("unmarshal: %v", err)
|
|
}
|
|
if withoutSeq.S != nil {
|
|
t.Fatalf("null seq must stay nil, got %v", *withoutSeq.S)
|
|
}
|
|
}
|
|
|
|
func TestSessionSeqTracking(t *testing.T) {
|
|
sess := &session{}
|
|
if _, ok := sess.lastSeq(); ok {
|
|
t.Fatal("fresh session must have no sequence number")
|
|
}
|
|
sess.setSeq(41)
|
|
sess.setSeq(42)
|
|
if seq, ok := sess.lastSeq(); !ok || seq != 42 {
|
|
t.Fatalf("want seq 42, got %d (ok=%v)", seq, ok)
|
|
}
|
|
}
|
|
|
|
// A malformed HELLO must be an ERROR, not a clean "reidentify". Run treats a
|
|
// clean return as a PLANNED reconnect: backoff resets to 1s and it redials with
|
|
// no sleep at all. So if these ever regress to returning nil, a gateway stuck
|
|
// sending a bad HELLO becomes a tight reconnect loop against Discord.
|
|
func TestParseHelloRejectsMalformedSoBackoffApplies(t *testing.T) {
|
|
for _, tc := range []struct {
|
|
name string
|
|
raw string
|
|
}{
|
|
{"not json", `{`},
|
|
{"wrong op", `{"op":0,"d":{"heartbeat_interval":41250}}`},
|
|
{"missing interval", `{"op":10,"d":{}}`},
|
|
{"zero interval", `{"op":10,"d":{"heartbeat_interval":0}}`},
|
|
{"negative interval", `{"op":10,"d":{"heartbeat_interval":-1}}`},
|
|
{"interval wrong type", `{"op":10,"d":{"heartbeat_interval":"soon"}}`},
|
|
} {
|
|
t.Run(tc.name, func(t *testing.T) {
|
|
got, err := parseHello([]byte(tc.raw))
|
|
if err == nil {
|
|
t.Fatalf("parseHello(%s) = %v, nil; want an error so Run applies backoff", tc.raw, got)
|
|
}
|
|
if got != 0 {
|
|
t.Fatalf("parseHello(%s) interval = %v; want 0 on error", tc.raw, got)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestParseHelloAcceptsValid(t *testing.T) {
|
|
got, err := parseHello([]byte(`{"op":10,"d":{"heartbeat_interval":41250}}`))
|
|
if err != nil {
|
|
t.Fatalf("parseHello: unexpected error %v", err)
|
|
}
|
|
if want := 41250 * time.Millisecond; got != want {
|
|
t.Fatalf("interval = %v; want %v", got, want)
|
|
}
|
|
}
|
|
|
|
// Discord's advertised retry_after is clamped to 5s, matching the Python REST
|
|
// helper's _MAX_BACKOFF_S. Replies run on a small fixed worker pool, so a bogus
|
|
// server value must not park a slot for minutes.
|
|
func TestRetryAfterClamp(t *testing.T) {
|
|
for _, tc := range []struct {
|
|
name string
|
|
body string
|
|
want time.Duration
|
|
}{
|
|
{"honours a sane value", `{"retry_after":2}`, 2 * time.Second},
|
|
{"clamps a hostile value", `{"retry_after":600}`, 5 * time.Second},
|
|
{"defaults when absent", `{}`, 1 * time.Second},
|
|
} {
|
|
t.Run(tc.name, func(t *testing.T) {
|
|
if got := retryAfter(http.Header{}, []byte(tc.body)); got != tc.want {
|
|
t.Fatalf("retryAfter(%s) = %v; want %v", tc.body, got, tc.want)
|
|
}
|
|
})
|
|
}
|
|
}
|