thermograph/backend/daemon/internal/apiclient/client_test.go

125 lines
3.7 KiB
Go
Raw Normal View History

daemon: move the Discord gateway and scheduler out of the web process into Go web/app.py started two long-lived background jobs under a leader election: the Discord gateway bot and an APScheduler. Both are stateful I/O loops -- reconnect, RESUME, heartbeat, backoff, interval timers -- living inside an async web app that also has to serve requests. This moves them into a single Go binary. Go owns ONLY the stateful I/O. It owns no climate or grading logic: anything needing data calls back into Python over a new internal-only HTTP surface (/internal/discord/grade, /internal/jobs/warm-cities, /internal/jobs/indexnow). Grading depends on polars and the parquet cache; reimplementing it in Go would make the bot's grades drift from the API's, and the slash-command path deliberately shares one grade builder so the two can never disagree. The grade route returns gateway-ready JSON -- including the ephemeral-flag drop that discord_bot.py used to do -- and Go relays those bytes verbatim without parsing the embed. Packaging: the binary is built by a golang:1.26 stage in the backend Dockerfile and shipped in the SAME image, run as a second compose service off the SAME tag. The daemon and backend share the /internal/* contract, so they must never skew versions; one image makes that structural rather than a convention. Its entrypoint bypasses entrypoint.sh -- the backend owns alembic, and two racing migrators is a real hazard. replicas: 1 in the Swarm stack is load-bearing. Discord permits exactly one gateway connection per bot token; the pin replaces core/singleton.claim_leader for this workload. update_config uses order: stop-first, since start-first would briefly run two gateways. autoscale.sh targets ${STACK_NAME}_web only, so it cannot scale this. Security: the internal routes compare the token with hmac.compare_digest and the whole router 404s when THERMOGRAPH_INTERNAL_TOKEN is unset -- fail closed, never default open. Caddy only routes /api/*, /digest and /discord/interactions to the backend, so /internal/* was never publicly reachable; the token is defence in depth. The router mounts before the catch-all frontend proxy so /internal/* cannot fall through to it. The daemon refuses to start without the token. Behaviour preserved from the Python, with the reasoning carried into the Go comments: non-privileged intents (no MESSAGE_CONTENT, so no portal review); fatal close codes 4004/4010-4014 stop rather than loop; the bot-author and self-author mention-loop guard; allowed_mentions locked to {"parse":[], "replied_user":true} so a crafted query cannot turn a reply into an @everyone ping; the first cron tick deferred one full interval rather than firing at boot, since warm-cities already runs at deploy time; and no overlapping warm-cities run, which would double-spend the archive-fetch quota. Two deliberate improvements over the Python. A close intended for RESUME now uses 4000 rather than 1000 -- Discord invalidates a session closed 1000/1001, so the Python's default close silently defeated its own resume. And MESSAGE_CREATE is handled on a bounded worker pool rather than an unbounded thread hand-off, so a flood of mentions cannot spawn unbounded work against the backend. A .dockerignore is added because a disposable backend/.venv was being swallowed by COPY . /app/ and duplicated again by the chown layer, inflating the image to 1.8 GB; it builds at 578 MB. Tests: 29 Go gateway tests covering every behaviour the deleted test_discord_bot.py asserted, plus cron/config/apiclient suites; 10 new Python tests for the internal routes (fail-closed, auth, flag drop, per-job 409 guard). Full suite 359 passed / 7 skipped; go build, vet and test -race clean.
2026-07-23 22:33:11 +00:00
package apiclient
import (
"context"
"encoding/json"
"net/http"
"net/http/httptest"
"strings"
"testing"
"time"
)
func TestGradeHappyPathRelaysBodyVerbatim(t *testing.T) {
// Deliberately odd formatting/key order: Grade must hand back the exact
// bytes, never a re-marshalled reshaping of them.
const body = `{ "content":null, "embeds": [ {"title":"Phoenix"} ] }`
var gotPath, gotToken, gotQuery string
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
gotPath = r.URL.Path
gotToken = r.Header.Get("X-Thermograph-Internal-Token")
var req map[string]string
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
t.Errorf("decode request: %v", err)
}
gotQuery = req["query"]
w.Header().Set("Content-Type", "application/json")
if _, err := w.Write([]byte(body)); err != nil {
t.Errorf("write response: %v", err)
}
}))
defer srv.Close()
c := New(srv.URL, "tok123")
raw, err := c.Grade(context.Background(), "phoenix")
if err != nil {
t.Fatalf("Grade: %v", err)
}
if string(raw) != body {
t.Errorf("body not relayed verbatim:\n got %q\nwant %q", raw, body)
}
if gotPath != "/internal/discord/grade" {
t.Errorf("path = %q", gotPath)
}
if gotToken != "tok123" {
t.Errorf("token header = %q, want %q", gotToken, "tok123")
}
if gotQuery != "phoenix" {
t.Errorf("query = %q", gotQuery)
}
}
func TestJobsSendTokenAndHitRightPaths(t *testing.T) {
paths := map[string]bool{}
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.Method != http.MethodPost {
t.Errorf("method = %s, want POST", r.Method)
}
if r.Header.Get("X-Thermograph-Internal-Token") != "tok" {
t.Errorf("missing/wrong token header on %s", r.URL.Path)
}
paths[r.URL.Path] = true
if _, err := w.Write([]byte(`{"ok":true}`)); err != nil {
t.Errorf("write response: %v", err)
}
}))
defer srv.Close()
c := New(srv.URL+"/", "tok") // trailing slash must not produce "//internal"
if err := c.WarmCities(context.Background()); err != nil {
t.Fatalf("WarmCities: %v", err)
}
if err := c.IndexNow(context.Background()); err != nil {
t.Fatalf("IndexNow: %v", err)
}
for _, p := range []string{"/internal/jobs/warm-cities", "/internal/jobs/indexnow"} {
if !paths[p] {
t.Errorf("path %s was never hit (saw %v)", p, paths)
}
}
}
func TestNon2xxReturnsStatusAndTruncatedBody(t *testing.T) {
long := strings.Repeat("x", 2000)
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
http.Error(w, long, http.StatusBadGateway)
}))
defer srv.Close()
c := New(srv.URL, "tok")
_, err := c.Grade(context.Background(), "phoenix")
if err == nil {
t.Fatal("expected error on 502, got nil")
}
msg := err.Error()
if !strings.Contains(msg, "502") {
t.Errorf("error should include status, got: %s", msg)
}
if !strings.Contains(msg, "truncated") {
t.Errorf("error should mark truncation, got %d chars: %.100s...", len(msg), msg)
}
if len(msg) > 1000 {
t.Errorf("error message not truncated: %d chars", len(msg))
}
}
func TestContextCancellation(t *testing.T) {
block := make(chan struct{})
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
<-block // hold the request open until the test ends
}))
defer srv.Close()
defer close(block)
c := New(srv.URL, "tok")
ctx, cancel := context.WithTimeout(context.Background(), 50*time.Millisecond)
defer cancel()
_, err := c.Grade(ctx, "phoenix")
if err == nil {
t.Fatal("expected error from cancelled context, got nil")
}
if !strings.Contains(err.Error(), "deadline") && !strings.Contains(err.Error(), "cancel") {
t.Errorf("expected a context-shaped error, got: %v", err)
}
}