All checks were successful
PR build (required check) / build-frontend (pull_request) Has been skipped
PR build (required check) / validate-observability (pull_request) Has been skipped
secrets-guard / encrypted (pull_request) Successful in 6s
PR build (required check) / changes (pull_request) Successful in 9s
shell-lint / shellcheck (pull_request) Successful in 6s
PR build (required check) / build-backend (pull_request) Successful in 1m10s
PR build (required check) / gate (pull_request) Successful in 2s
THERMOGRAPH_DISCORD_BOT_MENTIONS=0 makes the gateway bot silent on guild mentions. Default on, and unset counts as on, so every env file that predates the knob behaves exactly as before. The reason is a second responder. The operator's desktop now runs a conversational agent that replies as this same bot account (discord-voice-bot, AGENTS.md) and grades through the same API we do, so with both live a single "@Thermograph Phoenix" gets answered twice — once as a card, once as a reply. Only one of us can own that surface, and the agent is the one that can also hold a conversation. Scoped to guild mentions on purpose. DMs stay here: the agent polls guild channels only, so staying silent in a DM would just drop the message. And /grade is a signed HTTP interaction that never touched this path, so it keeps answering from prod while the desktop is asleep — which is what stops this from trading an always-on surface for a sometimes-on one. Claude-Session: https://claude.ai/code/session_015Z1ebLbhUxeZ9ozpNrVTCP
138 lines
4.6 KiB
Go
138 lines
4.6 KiB
Go
// The REST half of answering a message: replies go out over plain HTTP with
|
|
// the bot token, not the gateway socket (the gateway is receive-only for us).
|
|
|
|
package gateway
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"encoding/json"
|
|
"io"
|
|
"log"
|
|
"net/http"
|
|
"strconv"
|
|
"time"
|
|
)
|
|
|
|
const discordAPIBase = "https://discord.com/api/v10"
|
|
|
|
// replyBodyLimit caps how much of a failed reply's response body we echo into
|
|
// logs.
|
|
const replyBodyLimit = 4096
|
|
|
|
// injectReplyFields adds message_reference + allowed_mentions to an otherwise
|
|
// verbatim message body. Only the top level is decoded — every value that
|
|
// came from Python (embeds and all) passes through as raw bytes, unparsed, so
|
|
// the grading/embed contract stays entirely on the Python side.
|
|
//
|
|
// allowed_mentions is a SECURITY control, not decoration: the graded reply
|
|
// echoes the user's query text, so without {"parse":[]} a crafted query could
|
|
// turn our reply into an @everyone/role ping. Only the person who asked is
|
|
// pinged, via the reply reference.
|
|
func injectReplyFields(body []byte, messageID string) ([]byte, error) {
|
|
var top map[string]json.RawMessage
|
|
if err := json.Unmarshal(body, &top); err != nil {
|
|
return nil, err
|
|
}
|
|
if messageID != "" {
|
|
ref, err := json.Marshal(map[string]string{"message_id": messageID})
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
top["message_reference"] = ref
|
|
top["allowed_mentions"] = json.RawMessage(`{"parse":[],"replied_user":true}`)
|
|
}
|
|
return json.Marshal(top)
|
|
}
|
|
|
|
// reply posts body to the triggering message's channel as a proper reply. A
|
|
// failed reply is logged and swallowed — it must never kill the read loop.
|
|
func (b *Bot) reply(ctx context.Context, channelID, messageID string, body json.RawMessage) {
|
|
if channelID == "" {
|
|
return
|
|
}
|
|
payload, err := injectReplyFields(body, messageID)
|
|
if err != nil {
|
|
log.Printf("gateway: reply body is not a JSON object: %v", err)
|
|
return
|
|
}
|
|
url := b.rest + "/channels/" + channelID + "/messages"
|
|
for attempt := 0; ; attempt++ {
|
|
req, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(payload))
|
|
if err != nil {
|
|
log.Printf("gateway: reply failed: %v", err)
|
|
return
|
|
}
|
|
req.Header.Set("Authorization", "Bot "+b.token)
|
|
req.Header.Set("Content-Type", "application/json")
|
|
resp, err := b.http.Do(req)
|
|
if err != nil {
|
|
log.Printf("gateway: reply failed: %v", err)
|
|
return
|
|
}
|
|
raw, _ := io.ReadAll(io.LimitReader(resp.Body, replyBodyLimit))
|
|
resp.Body.Close()
|
|
if resp.StatusCode == http.StatusTooManyRequests && attempt == 0 {
|
|
// One retry honouring the advertised wait — parity with the
|
|
// Python REST helper's 429 handling.
|
|
if !sleepCtx(ctx, retryAfter(resp.Header, raw)) {
|
|
return
|
|
}
|
|
continue
|
|
}
|
|
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
|
|
log.Printf("gateway: reply failed: status %d: %s", resp.StatusCode, raw)
|
|
}
|
|
return
|
|
}
|
|
}
|
|
|
|
// retryAfter extracts Discord's requested wait from a 429 (JSON retry_after
|
|
// in seconds, falling back to the Retry-After header), clamped so a bogus
|
|
// server value can't park the handler for minutes.
|
|
func retryAfter(h http.Header, body []byte) time.Duration {
|
|
seconds := 1.0
|
|
var d struct {
|
|
RetryAfter float64 `json:"retry_after"`
|
|
}
|
|
if err := json.Unmarshal(body, &d); err == nil && d.RetryAfter > 0 {
|
|
seconds = d.RetryAfter
|
|
} else if v, err := strconv.ParseFloat(h.Get("Retry-After"), 64); err == nil && v > 0 {
|
|
seconds = v
|
|
}
|
|
// 5s matches the Python REST helper's _MAX_BACKOFF_S. It also bounds the cost
|
|
// of a bogus/hostile retry_after: replies run on a small fixed worker pool, so
|
|
// a parked handler holds one of very few slots and mentions start being
|
|
// dropped that much sooner.
|
|
if seconds > 5 {
|
|
seconds = 5
|
|
}
|
|
return time.Duration(seconds * float64(time.Second))
|
|
}
|
|
|
|
// handleMessage triages one MESSAGE_CREATE and sends whatever reply it calls
|
|
// for. Runs in its own goroutine (see dispatch) so a slow grade lookup can
|
|
// never stall heartbeats or the read loop.
|
|
func (b *Bot) handleMessage(ctx context.Context, m *gwMessage, botID string) {
|
|
act, query := triage(m, botID, b.guildMentions)
|
|
switch act {
|
|
case actSilent:
|
|
case actHelp:
|
|
body, err := json.Marshal(map[string]string{"content": helpText})
|
|
if err != nil {
|
|
return
|
|
}
|
|
b.reply(ctx, string(m.ChannelID), string(m.ID), body)
|
|
case actGrade:
|
|
// The callback owns all grading; its JSON is relayed VERBATIM (no
|
|
// parsing, no reshaping) so the bot's grades can never drift from
|
|
// the API's. A failed callback stays silent — better no reply than a
|
|
// made-up one.
|
|
raw, err := b.api.Grade(ctx, query)
|
|
if err != nil {
|
|
log.Printf("gateway: grade callback failed for %q: %v", query, err)
|
|
return
|
|
}
|
|
b.reply(ctx, string(m.ChannelID), string(m.ID), raw)
|
|
}
|
|
}
|