thermograph/backend/daemon/internal/gateway/reply_test.go
emi 2d3f37c474
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
daemon: move the Discord gateway and scheduler out of the web process into Go (#21)
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.
2026-07-23 22:49:54 +00:00

278 lines
8.3 KiB
Go

// Reply-path tests: a fake Grader plus an httptest server standing in for
// Discord's REST API. No live gateway is involved anywhere.
package gateway
import (
"context"
"encoding/json"
"io"
"net/http"
"net/http/httptest"
"sync"
"sync/atomic"
"testing"
"time"
)
type fakeGrader struct {
mu sync.Mutex
resp json.RawMessage
err error
calls []string
}
func (f *fakeGrader) Grade(_ context.Context, query string) (json.RawMessage, error) {
f.mu.Lock()
defer f.mu.Unlock()
f.calls = append(f.calls, query)
return f.resp, f.err
}
func (f *fakeGrader) callCount() int {
f.mu.Lock()
defer f.mu.Unlock()
return len(f.calls)
}
type captured struct {
method, path, auth string
body []byte
}
// newTestBot wires a Bot to a Grader and an httptest stand-in for Discord.
func newTestBot(t *testing.T, g Grader, handler http.HandlerFunc) *Bot {
t.Helper()
srv := httptest.NewServer(handler)
t.Cleanup(srv.Close)
b := New("tok-123", g)
b.rest = srv.URL
return b
}
// capture records each request and replies 200 {}.
func capture(got chan<- captured) http.HandlerFunc {
return func(w http.ResponseWriter, r *http.Request) {
body, _ := io.ReadAll(r.Body)
got <- captured{r.Method, r.URL.Path, r.Header.Get("Authorization"), body}
_, _ = w.Write([]byte(`{}`))
}
}
func TestGradeReplyIsRelayedVerbatimAsAReply(t *testing.T) {
grade := json.RawMessage(`{"embeds":[{"title":"grade:Phoenix"}]}`)
got := make(chan captured, 1)
b := newTestBot(t, &fakeGrader{resp: grade}, capture(got))
b.handleMessage(context.Background(), testMsg("<@999> Phoenix", mentioning(botID)), botID)
c := <-got
if c.method != http.MethodPost || c.path != "/channels/77/messages" {
t.Fatalf("want POST /channels/77/messages, got %s %s", c.method, c.path)
}
if c.auth != "Bot tok-123" {
t.Fatalf("want bot-token auth, got %q", c.auth)
}
var top map[string]json.RawMessage
if err := json.Unmarshal(c.body, &top); err != nil {
t.Fatalf("reply body not JSON: %v", err)
}
// The embed must be byte-for-byte what Python returned — the verbatim
// relay is the no-drift guarantee.
if string(top["embeds"]) != `[{"title":"grade:Phoenix"}]` {
t.Fatalf("embeds not relayed verbatim: %s", top["embeds"])
}
if string(top["message_reference"]) != `{"message_id":"42"}` {
t.Fatalf("bad message_reference: %s", top["message_reference"])
}
// The locked-down allowed_mentions is the anti-@everyone control; it must
// be present exactly.
if string(top["allowed_mentions"]) != `{"parse":[],"replied_user":true}` {
t.Fatalf("bad allowed_mentions: %s", top["allowed_mentions"])
}
}
func TestEmptyQueryRepliesWithHelpWithoutGrading(t *testing.T) {
got := make(chan captured, 1)
g := &fakeGrader{}
b := newTestBot(t, g, capture(got))
b.handleMessage(context.Background(), testMsg("<@999>", mentioning(botID)), botID)
c := <-got
var body struct {
Content string `json:"content"`
}
if err := json.Unmarshal(c.body, &body); err != nil {
t.Fatalf("help body not JSON: %v", err)
}
if body.Content != helpText {
t.Fatalf("want help text, got %q", body.Content)
}
if g.callCount() != 0 {
t.Fatal("help reply must not hit the grade callback")
}
}
func TestSilentMessagesMakeNoRequests(t *testing.T) {
var hits atomic.Int32
g := &fakeGrader{resp: json.RawMessage(`{}`)}
b := newTestBot(t, g, func(w http.ResponseWriter, r *http.Request) {
hits.Add(1)
})
b.handleMessage(context.Background(), testMsg("just chatting"), botID)
if g.callCount() != 0 || hits.Load() != 0 {
t.Fatalf("silent message leaked: grades=%d posts=%d", g.callCount(), hits.Load())
}
}
func TestGradeFailureStaysSilent(t *testing.T) {
var hits atomic.Int32
g := &fakeGrader{err: context.DeadlineExceeded}
b := newTestBot(t, g, func(w http.ResponseWriter, r *http.Request) {
hits.Add(1)
})
// Must log-and-return, not panic or post a broken reply.
b.handleMessage(context.Background(), testMsg("<@999> Phoenix", mentioning(botID)), botID)
if hits.Load() != 0 {
t.Fatal("failed grade must not produce a reply")
}
}
func TestFailedReplyIsSwallowed(t *testing.T) {
g := &fakeGrader{resp: json.RawMessage(`{"content":"x"}`)}
b := newTestBot(t, g, func(w http.ResponseWriter, r *http.Request) {
http.Error(w, "boom", http.StatusInternalServerError)
})
// A failed reply must never kill the caller (in production: the read
// loop) — returning normally is the assertion.
b.handleMessage(context.Background(), testMsg("<@999> Phoenix", mentioning(botID)), botID)
}
func TestReplyRetriesOnceOn429(t *testing.T) {
var hits atomic.Int32
bodies := make(chan []byte, 2)
g := &fakeGrader{resp: json.RawMessage(`{"content":"x"}`)}
b := newTestBot(t, g, func(w http.ResponseWriter, r *http.Request) {
body, _ := io.ReadAll(r.Body)
bodies <- body
if hits.Add(1) == 1 {
w.WriteHeader(http.StatusTooManyRequests)
_, _ = w.Write([]byte(`{"retry_after":0.01}`))
return
}
_, _ = w.Write([]byte(`{}`))
})
b.handleMessage(context.Background(), testMsg("<@999> Phoenix", mentioning(botID)), botID)
if hits.Load() != 2 {
t.Fatalf("want 1 retry after 429, got %d requests", hits.Load())
}
first, second := <-bodies, <-bodies
if string(first) != string(second) {
t.Fatal("retry must resend the identical payload")
}
}
func TestNoChannelMeansNoPost(t *testing.T) {
var hits atomic.Int32
g := &fakeGrader{resp: json.RawMessage(`{"content":"x"}`)}
b := newTestBot(t, g, func(w http.ResponseWriter, r *http.Request) {
hits.Add(1)
})
b.handleMessage(context.Background(),
testMsg("<@999> Phoenix", mentioning(botID), func(m *gwMessage) { m.ChannelID = "" }), botID)
if hits.Load() != 0 {
t.Fatal("a message without a channel id must not be answered")
}
}
func TestInjectReplyFieldsWithoutMessageIDLeavesBodyAlone(t *testing.T) {
out, err := injectReplyFields([]byte(`{"content":"x"}`), "")
if err != nil {
t.Fatalf("inject: %v", err)
}
var top map[string]json.RawMessage
if err := json.Unmarshal(out, &top); err != nil {
t.Fatalf("out not JSON: %v", err)
}
if _, ok := top["message_reference"]; ok {
t.Fatal("no triggering id => no message_reference")
}
if _, ok := top["allowed_mentions"]; ok {
t.Fatal("no triggering id => no allowed_mentions")
}
}
// --- dispatch: same reply, off the read loop ---------------------------------
func TestDispatchDeliversTheSameReplyViaAGoroutine(t *testing.T) {
// Mirrors the Python test_dispatch_delivers_the_same_reply_via_a_thread:
// the concurrency offload (goroutine + semaphore here, asyncio.to_thread
// there) must not change what gets sent.
grade := json.RawMessage(`{"embeds":[{"title":"grade:Phoenix"}]}`)
got := make(chan captured, 1)
b := newTestBot(t, &fakeGrader{resp: grade}, capture(got))
sess := &session{userID: botID}
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)
select {
case c := <-got:
if c.path != "/channels/77/messages" {
t.Fatalf("want /channels/77/messages, got %s", c.path)
}
var top map[string]json.RawMessage
if err := json.Unmarshal(c.body, &top); err != nil {
t.Fatalf("reply body not JSON: %v", err)
}
if string(top["embeds"]) != `[{"title":"grade:Phoenix"}]` {
t.Fatalf("embeds not relayed verbatim: %s", top["embeds"])
}
if string(top["message_reference"]) != `{"message_id":"42"}` {
t.Fatalf("bad message_reference: %s", top["message_reference"])
}
case <-time.After(2 * time.Second):
t.Fatal("dispatched message never produced a reply")
}
}
func TestMessageFloodIsBoundedWithoutBlockingTheReadLoop(t *testing.T) {
g := &fakeGrader{resp: json.RawMessage(`{}`)}
b := New("tok", g)
b.sem = make(chan struct{}, 1)
b.sem <- struct{}{} // occupy the only slot: simulate a reply in flight
sess := &session{userID: botID}
d, err := json.Marshal(testMsg("<@999> Phoenix", mentioning(botID)))
if err != nil {
t.Fatalf("marshal: %v", err)
}
done := make(chan struct{})
go func() {
b.dispatch(context.Background(), payload{Op: opDispatch, T: "MESSAGE_CREATE", D: d}, sess)
close(done)
}()
select {
case <-done:
// dispatch returned promptly — the read loop would not have stalled
case <-time.After(time.Second):
t.Fatal("dispatch blocked on a full semaphore")
}
time.Sleep(20 * time.Millisecond)
if g.callCount() != 0 {
t.Fatal("over-the-bound message must be dropped, not queued")
}
}