fix(gateway/discord): add safe startup slash sync policy

Replaces blind tree.sync() on every Discord reconnect with a diff-based
reconcile. In safe mode (default), fetch existing global commands,
compare desired vs existing payloads, skip unchanged, PATCH changed,
recreate when non-patchable metadata differs, POST missing, and delete
stale commands one-by-one. Keeps 'bulk' for legacy behavior and 'off'
to skip startup sync entirely.

Fixes restart-heavy workflows that burn Discord's command write budget
and can surface 429s when iterating on native slash commands.

Env var: DISCORD_COMMAND_SYNC_POLICY (safe|bulk|off), default 'safe'.

Co-authored-by: Codex <codex@openai.invalid>
This commit is contained in:
Magaav 2026-04-23 15:09:04 -07:00 committed by Teknium
parent 4a0c02b7dc
commit a1ff6b45ea
4 changed files with 406 additions and 3 deletions

View file

@ -23,6 +23,7 @@ from typing import Callable, Dict, Optional, Any
logger = logging.getLogger(__name__)
VALID_THREAD_AUTO_ARCHIVE_MINUTES = {60, 1440, 4320, 10080}
_DISCORD_COMMAND_SYNC_POLICIES = {"safe", "bulk", "off"}
try:
import discord
@ -802,8 +803,27 @@ class DiscordAdapter(BasePlatformAdapter):
if not self._client:
return
try:
synced = await asyncio.wait_for(self._client.tree.sync(), timeout=30)
logger.info("[%s] Synced %d slash command(s)", self.name, len(synced))
sync_policy = self._get_discord_command_sync_policy()
if sync_policy == "off":
logger.info("[%s] Skipping Discord slash command sync (policy=off)", self.name)
return
if sync_policy == "bulk":
synced = await asyncio.wait_for(self._client.tree.sync(), timeout=30)
logger.info("[%s] Synced %d slash command(s) via bulk tree sync", self.name, len(synced))
return
summary = await asyncio.wait_for(self._safe_sync_slash_commands(), timeout=30)
logger.info(
"[%s] Safely reconciled %d slash command(s): unchanged=%d updated=%d recreated=%d created=%d deleted=%d",
self.name,
summary["total"],
summary["unchanged"],
summary["updated"],
summary["recreated"],
summary["created"],
summary["deleted"],
)
except asyncio.TimeoutError:
logger.warning("[%s] Slash command sync timed out after 30s", self.name)
except asyncio.CancelledError:
@ -811,6 +831,143 @@ class DiscordAdapter(BasePlatformAdapter):
except Exception as e: # pragma: no cover - defensive logging
logger.warning("[%s] Slash command sync failed: %s", self.name, e, exc_info=True)
def _get_discord_command_sync_policy(self) -> str:
raw = str(os.getenv("DISCORD_COMMAND_SYNC_POLICY", "safe") or "").strip().lower()
if raw in _DISCORD_COMMAND_SYNC_POLICIES:
return raw
if raw:
logger.warning(
"[%s] Invalid DISCORD_COMMAND_SYNC_POLICY=%r; falling back to 'safe'",
self.name,
raw,
)
return "safe"
def _canonicalize_app_command_payload(self, payload: Dict[str, Any]) -> Dict[str, Any]:
"""Reduce command payloads to the semantic fields Hermes manages."""
return {
"type": int(payload.get("type", 1) or 1),
"name": str(payload.get("name", "") or ""),
"description": str(payload.get("description", "") or ""),
"default_member_permissions": payload.get("default_member_permissions"),
"dm_permission": payload.get("dm_permission", True),
"nsfw": bool(payload.get("nsfw", False)),
"options": [
self._canonicalize_app_command_option(item)
for item in payload.get("options", []) or []
if isinstance(item, dict)
],
}
def _canonicalize_app_command_option(self, payload: Dict[str, Any]) -> Dict[str, Any]:
return {
"type": int(payload.get("type", 0) or 0),
"name": str(payload.get("name", "") or ""),
"description": str(payload.get("description", "") or ""),
"required": bool(payload.get("required", False)),
"autocomplete": bool(payload.get("autocomplete", False)),
"choices": [
{
"name": str(choice.get("name", "") or ""),
"value": choice.get("value"),
}
for choice in payload.get("choices", []) or []
if isinstance(choice, dict)
],
"channel_types": list(payload.get("channel_types", []) or []),
"min_value": payload.get("min_value"),
"max_value": payload.get("max_value"),
"min_length": payload.get("min_length"),
"max_length": payload.get("max_length"),
"options": [
self._canonicalize_app_command_option(item)
for item in payload.get("options", []) or []
if isinstance(item, dict)
],
}
def _patchable_app_command_payload(self, payload: Dict[str, Any]) -> Dict[str, Any]:
"""Fields supported by discord.py's edit_global_command route."""
canonical = self._canonicalize_app_command_payload(payload)
return {
"name": canonical["name"],
"description": canonical["description"],
"options": canonical["options"],
}
async def _safe_sync_slash_commands(self) -> Dict[str, int]:
"""Diff existing global commands and only mutate the commands that changed."""
if not self._client:
return {
"total": 0,
"unchanged": 0,
"updated": 0,
"recreated": 0,
"created": 0,
"deleted": 0,
}
tree = self._client.tree
app_id = getattr(self._client, "application_id", None) or getattr(getattr(self._client, "user", None), "id", None)
if not app_id:
raise RuntimeError("Discord application ID is unavailable for slash command sync")
desired_payloads = [command.to_dict(tree) for command in tree.get_commands()]
desired_by_key = {
(int(payload.get("type", 1) or 1), str(payload.get("name", "") or "").lower()): payload
for payload in desired_payloads
}
existing_commands = await tree.fetch_commands()
existing_by_key = {
(
int(getattr(getattr(command, "type", None), "value", getattr(command, "type", 1)) or 1),
str(command.name or "").lower(),
): command
for command in existing_commands
}
unchanged = 0
updated = 0
recreated = 0
created = 0
deleted = 0
http = self._client.http
for key, desired in desired_by_key.items():
current = existing_by_key.pop(key, None)
if current is None:
await http.upsert_global_command(app_id, desired)
created += 1
continue
current_payload = self._canonicalize_app_command_payload(current.to_dict())
desired_payload = self._canonicalize_app_command_payload(desired)
if current_payload == desired_payload:
unchanged += 1
continue
if self._patchable_app_command_payload(current.to_dict()) == self._patchable_app_command_payload(desired):
await http.delete_global_command(app_id, current.id)
await http.upsert_global_command(app_id, desired)
recreated += 1
continue
await http.edit_global_command(app_id, current.id, desired)
updated += 1
for current in existing_by_key.values():
await http.delete_global_command(app_id, current.id)
deleted += 1
return {
"total": len(desired_payloads),
"unchanged": unchanged,
"updated": updated,
"recreated": recreated,
"created": created,
"deleted": deleted,
}
async def _add_reaction(self, message: Any, emoji: str) -> bool:
"""Add an emoji reaction to a Discord message."""
if not message or not hasattr(message, "add_reaction"):