fix(gateway): wait for systemd restart readiness

gateway/platforms/discord.py

@@ -10,6 +10,8 @@ Uses discord.py library for:
 """
 
 import asyncio
+import hashlib
+import json
 import logging
 import os
 import struct
@@ -24,6 +26,9 @@ logger = logging.getLogger(__name__)
 
 VALID_THREAD_AUTO_ARCHIVE_MINUTES = {60, 1440, 4320, 10080}
 _DISCORD_COMMAND_SYNC_POLICIES = {"safe", "bulk", "off"}
+_DISCORD_COMMAND_SYNC_STATE_FILE = "discord_command_sync_state.json"
+_DISCORD_COMMAND_SYNC_MUTATION_INTERVAL_SECONDS = 4.5
+_DISCORD_COMMAND_SYNC_MAX_RATE_LIMIT_SLEEP_SECONDS = 30.0
 
 try:
     import discord
@@ -45,6 +50,7 @@ from gateway.config import Platform, PlatformConfig
 import re
 
 from gateway.platforms.helpers import MessageDeduplicator, ThreadParticipationTracker
+from utils import atomic_json_write
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -825,6 +831,128 @@ class DiscordAdapter(BasePlatformAdapter):
 
         logger.info("[%s] Disconnected", self.name)
 
+    def _command_sync_state_path(self) -> _Path:
+        from hermes_constants import get_hermes_home
+
+        return get_hermes_home() / _DISCORD_COMMAND_SYNC_STATE_FILE
+
+    def _read_command_sync_state(self) -> dict:
+        try:
+            path = self._command_sync_state_path()
+            if not path.exists():
+                return {}
+            data = json.loads(path.read_text(encoding="utf-8"))
+        except Exception:
+            return {}
+        return data if isinstance(data, dict) else {}
+
+    def _write_command_sync_state(self, state: dict) -> None:
+        atomic_json_write(
+            self._command_sync_state_path(),
+            state,
+            indent=None,
+            separators=(",", ":"),
+        )
+
+    def _command_sync_state_key(self, app_id: Any) -> str:
+        return str(app_id or "unknown")
+
+    def _desired_command_sync_fingerprint(self) -> str:
+        tree = self._client.tree if self._client else None
+        desired = []
+        if tree is not None:
+            desired = [
+                self._canonicalize_app_command_payload(command.to_dict(tree))
+                for command in tree.get_commands()
+            ]
+        desired.sort(key=lambda item: (item.get("type", 1), item.get("name", "")))
+        payload = json.dumps(desired, sort_keys=True, separators=(",", ":"))
+        return hashlib.sha256(payload.encode("utf-8")).hexdigest()
+
+    def _command_sync_skip_reason(self, app_id: Any, fingerprint: str) -> Optional[str]:
+        entry = self._read_command_sync_state().get(self._command_sync_state_key(app_id))
+        if not isinstance(entry, dict):
+            return None
+        now = time.time()
+        retry_after_until = float(entry.get("retry_after_until") or 0)
+        if retry_after_until > now:
+            remaining = max(1, int(retry_after_until - now))
+            return f"Discord asked us to wait before syncing slash commands; retry in {remaining}s"
+        if entry.get("fingerprint") == fingerprint and entry.get("last_success_at"):
+            return "same slash-command fingerprint already synced"
+        return None
+
+    def _record_command_sync_attempt(self, app_id: Any, fingerprint: str) -> None:
+        state = self._read_command_sync_state()
+        state[self._command_sync_state_key(app_id)] = {
+            **(
+                state.get(self._command_sync_state_key(app_id))
+                if isinstance(state.get(self._command_sync_state_key(app_id)), dict)
+                else {}
+            ),
+            "fingerprint": fingerprint,
+            "last_attempt_at": time.time(),
+        }
+        self._write_command_sync_state(state)
+
+    def _record_command_sync_rate_limit(self, app_id: Any, fingerprint: str, retry_after: float) -> None:
+        retry_after = max(1.0, float(retry_after))
+        state = self._read_command_sync_state()
+        state[self._command_sync_state_key(app_id)] = {
+            **(
+                state.get(self._command_sync_state_key(app_id))
+                if isinstance(state.get(self._command_sync_state_key(app_id)), dict)
+                else {}
+            ),
+            "fingerprint": fingerprint,
+            "last_attempt_at": time.time(),
+            "retry_after_until": time.time() + retry_after,
+            "retry_after": retry_after,
+        }
+        self._write_command_sync_state(state)
+
+    def _record_command_sync_success(self, app_id: Any, fingerprint: str, summary: dict) -> None:
+        state = self._read_command_sync_state()
+        state[self._command_sync_state_key(app_id)] = {
+            "fingerprint": fingerprint,
+            "last_attempt_at": time.time(),
+            "last_success_at": time.time(),
+            "summary": summary,
+        }
+        self._write_command_sync_state(state)
+
+    @staticmethod
+    def _extract_discord_retry_after(exc: BaseException) -> Optional[float]:
+        value = getattr(exc, "retry_after", None)
+        if value is not None:
+            try:
+                return max(1.0, float(value))
+            except (TypeError, ValueError):
+                return None
+        response = getattr(exc, "response", None)
+        headers = getattr(response, "headers", None)
+        if headers:
+            for key in ("Retry-After", "X-RateLimit-Reset-After"):
+                try:
+                    raw = headers.get(key)
+                except Exception:
+                    raw = None
+                if raw is None:
+                    continue
+                try:
+                    return max(1.0, float(raw))
+                except (TypeError, ValueError):
+                    continue
+        return None
+
+    def _command_sync_mutation_interval_seconds(self) -> float:
+        return _DISCORD_COMMAND_SYNC_MUTATION_INTERVAL_SECONDS
+
+    async def _sleep_between_command_sync_mutations(self) -> None:
+        interval = self._command_sync_mutation_interval_seconds()
+        if interval > 0:
+            await asyncio.sleep(interval)
+
     async def _run_post_connect_initialization(self) -> None:
         """Finish non-critical startup work after Discord is connected."""
         if not self._client:
@@ -840,14 +968,42 @@ class DiscordAdapter(BasePlatformAdapter):
                 logger.info("[%s] Synced %d slash command(s) via bulk tree sync", self.name, len(synced))
                 return
 
-            # Discord's per-app command-management bucket is ~5 writes / 20 s,
-            # so a mass-prune-plus-upsert reconcile (e.g. 77 orphans + 30
-            # desired = 107 writes) takes several minutes of forced waits.
-            # A flat 30 s budget blew up reliably under bucket pressure and
-            # left slash commands broken for ~60 min until the bucket fully
-            # recovered. Use a wide ceiling; the cap still guards against a
-            # true hang. (#16713)
-            summary = await asyncio.wait_for(self._safe_sync_slash_commands(), timeout=600)
+            app_id = getattr(self._client, "application_id", None) or getattr(getattr(self._client, "user", None), "id", None)
+            fingerprint = self._desired_command_sync_fingerprint()
+            skip_reason = self._command_sync_skip_reason(app_id, fingerprint)
+            if skip_reason:
+                logger.info("[%s] Skipping Discord slash command sync: %s", self.name, skip_reason)
+                return
+            self._record_command_sync_attempt(app_id, fingerprint)
+
+            http = getattr(self._client, "http", None)
+            has_ratelimit_timeout = http is not None and hasattr(http, "max_ratelimit_timeout")
+            previous_ratelimit_timeout = getattr(http, "max_ratelimit_timeout", None) if has_ratelimit_timeout else None
+            if has_ratelimit_timeout:
+                http.max_ratelimit_timeout = _DISCORD_COMMAND_SYNC_MAX_RATE_LIMIT_SLEEP_SECONDS
+
+            try:
+                # Discord's per-app command-management bucket is small, and
+                # discord.py can otherwise sit inside one long retry sleep
+                # before surfacing the 429. Keep the whole sync bounded and
+                # persist Discord's retry-after when it refuses the batch.
+                summary = await asyncio.wait_for(self._safe_sync_slash_commands(), timeout=600)
+            except Exception as e:
+                retry_after = self._extract_discord_retry_after(e)
+                if retry_after is not None:
+                    self._record_command_sync_rate_limit(app_id, fingerprint, retry_after)
+                    logger.warning(
+                        "[%s] Discord rate-limited slash command sync; retrying after %.0fs",
+                        self.name,
+                        retry_after,
+                    )
+                    return
+                raise
+            finally:
+                if has_ratelimit_timeout:
+                    http.max_ratelimit_timeout = previous_ratelimit_timeout
+
+            self._record_command_sync_success(app_id, fingerprint, summary)
             logger.info(
                 "[%s] Safely reconciled %d slash command(s): unchanged=%d updated=%d recreated=%d created=%d deleted=%d",
                 self.name,
@@ -1009,11 +1165,20 @@ class DiscordAdapter(BasePlatformAdapter):
         created = 0
         deleted = 0
         http = self._client.http
+        mutation_count = 0
+
+        async def mutate(call, *args):
+            nonlocal mutation_count
+            if mutation_count:
+                await self._sleep_between_command_sync_mutations()
+            result = await call(*args)
+            mutation_count += 1
+            return result
 
         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)
+                await mutate(http.upsert_global_command, app_id, desired)
                 created += 1
                 continue
 
@@ -1025,16 +1190,16 @@ class DiscordAdapter(BasePlatformAdapter):
                 continue
 
             if self._patchable_app_command_payload(current_existing_payload) == self._patchable_app_command_payload(desired):
-                await http.delete_global_command(app_id, current.id)
-                await http.upsert_global_command(app_id, desired)
+                await mutate(http.delete_global_command, app_id, current.id)
+                await mutate(http.upsert_global_command, app_id, desired)
                 recreated += 1
                 continue
 
-            await http.edit_global_command(app_id, current.id, desired)
+            await mutate(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)
+            await mutate(http.delete_global_command, app_id, current.id)
             deleted += 1
 
         return {