gateway: debounce queued text follow-ups

This commit is contained in:
Paulo Nascimento
2026-05-23 21:32:19 -04:00
committed by Teknium
parent 21db250034
commit 7abd62719b
10 changed files with 607 additions and 89 deletions

View File

@@ -15,6 +15,7 @@ import re
import socket as _socket
import subprocess
import sys
import time
import uuid
from abc import ABC, abstractmethod
from urllib.parse import urlsplit
@@ -40,6 +41,16 @@ def _platform_name(platform) -> str:
return str(value or "").lower()
def _float_env(name: str, default: float) -> float:
raw = os.environ.get(name, "").strip()
if not raw:
return default
try:
return float(raw)
except (TypeError, ValueError):
return default
def _thread_metadata_for_source(source, reply_to_message_id: str | None = None) -> dict | None:
"""Build platform-aware thread metadata for adapter sends.
@@ -1103,6 +1114,14 @@ class MessageEvent:
return args
@dataclass
class TextDebounceState:
event: MessageEvent
task: asyncio.Task | None
first_ts: float
last_ts: float
_PLAINTEXT_GATEWAY_RESTART_PATTERNS: tuple[re.Pattern[str], ...] = (
re.compile(r"^(?:please\s+)?restart\s+(?:the\s+)?gateway[.!?\s]*$", re.IGNORECASE),
re.compile(r"^(?:please\s+)?restart\s+(?:the\s+)?hermes\s+gateway[.!?\s]*$", re.IGNORECASE),
@@ -1398,6 +1417,17 @@ class BasePlatformAdapter(ABC):
self._active_sessions: Dict[str, asyncio.Event] = {}
self._pending_messages: Dict[str, MessageEvent] = {}
self._session_tasks: Dict[str, asyncio.Task] = {}
self._busy_text_mode: str = (
os.environ.get("HERMES_GATEWAY_BUSY_TEXT_MODE", "queue").strip().lower()
or "queue"
)
self._busy_text_debounce_seconds: float = _float_env(
"HERMES_GATEWAY_BUSY_TEXT_DEBOUNCE_SECONDS", 0.35
)
self._busy_text_hard_cap_seconds: float = _float_env(
"HERMES_GATEWAY_BUSY_TEXT_HARD_CAP_SECONDS", 1.0
)
self._text_debounce: dict[str, TextDebounceState] = {}
# Background message-processing tasks spawned by handle_message().
# Gateway shutdown cancels these so an old gateway instance doesn't keep
# working on a task after --replace or manual restarts.
@@ -2725,6 +2755,161 @@ class BasePlatformAdapter(ABC):
return f"{existing_text}\n\n{new_text}".strip()
return existing_text
def _text_debounce_store(self) -> dict[str, TextDebounceState]:
store = getattr(self, "_text_debounce", None)
if store is None:
store = {}
self._text_debounce = store
return store
def _is_queue_text_debounce_candidate(self, event: MessageEvent) -> bool:
"""Return True for normal text eligible for queue-mode debounce."""
result = (
getattr(self, "_busy_text_mode", "queue") == "queue"
and event.message_type == MessageType.TEXT
and not getattr(event, "internal", False)
and not event.is_command()
and bool((event.text or "").strip())
)
if result:
logger.debug(
"[%s] Queue-text debounce candidate accepted: session=%s text=%.60s",
self.name,
getattr(event, "session_key", "?"),
(event.text or "")[:60],
)
return result
def _can_merge_text_debounce_events(self, existing: MessageEvent, event: MessageEvent) -> bool:
"""Return True when two text debounce events came from the same sender."""
def _identity(candidate: MessageEvent) -> tuple[str, ...] | None:
source = getattr(candidate, "source", None)
if source is None:
return None
platform = _platform_name(getattr(source, "platform", None))
sender = getattr(source, "user_id_alt", None) or getattr(source, "user_id", None)
if sender:
return (platform, str(sender))
if getattr(source, "chat_type", None) in {"dm", "private"} and getattr(source, "chat_id", None):
return (platform, "dm", str(source.chat_id))
return None
existing_sender = _identity(existing)
incoming_sender = _identity(event)
return existing_sender is not None and existing_sender == incoming_sender
def _text_debounce_delay(self, session_key: str) -> float:
"""Return bounded busy-text debounce delay for ``session_key``."""
state = self._text_debounce_store().get(session_key)
if state is None:
return 0.0
now = time.monotonic()
window_deadline = state.last_ts + self._busy_text_debounce_seconds
hard_cap_deadline = state.first_ts + self._busy_text_hard_cap_seconds
return max(0.0, min(window_deadline, hard_cap_deadline) - now)
async def _queue_text_debounce(self, session_key: str, event: MessageEvent) -> None:
"""Buffer normal queue-mode busy text and schedule a bounded flush."""
store = self._text_debounce_store()
state = store.get(session_key)
if state is not None and not self._can_merge_text_debounce_events(state.event, event):
# Preserve sender attribution in shared sessions. The current
# buffer becomes the next pending turn; the new sender starts a
# fresh debounce burst when the pending slot allows it.
await self._flush_text_debounce_now(session_key)
state = store.get(session_key)
if state is not None and not self._can_merge_text_debounce_events(state.event, event):
existing_pending = self._pending_messages.get(session_key)
if existing_pending is not None and self._can_merge_text_debounce_events(existing_pending, event):
merge_pending_message_event(
self._pending_messages,
session_key,
event,
merge_text=True,
)
return
now = time.monotonic()
if state is None:
state = TextDebounceState(
event=event,
task=None,
first_ts=now,
last_ts=now,
)
store[session_key] = state
else:
if event.text:
state.event.text = (
f"{state.event.text}\n{event.text}"
if state.event.text
else event.text
)
latest_message_id = getattr(event, "message_id", None)
latest_anchor = latest_message_id or getattr(event, "reply_to_message_id", None)
if latest_message_id is not None:
state.event.message_id = str(latest_message_id)
if latest_anchor is not None and hasattr(state.event, "reply_to_message_id"):
state.event.reply_to_message_id = str(latest_anchor)
state.last_ts = now
if state.task is not None and not state.task.done():
state.task.cancel()
delay = self._text_debounce_delay(session_key)
state.task = asyncio.create_task(self._flush_text_debounce(session_key, delay))
async def _flush_text_debounce(self, session_key: str, delay: float) -> None:
"""Timer task that flushes the debounced text buffer."""
try:
await asyncio.sleep(delay)
await self._flush_text_debounce_now(session_key)
except asyncio.CancelledError:
return
finally:
current = asyncio.current_task()
state = self._text_debounce_store().get(session_key)
if state is not None and state.task is current:
state.task = None
async def _flush_text_debounce_now(self, session_key: str) -> bool:
"""Force-flush one debounced busy-text burst into the pending slot."""
store = self._text_debounce_store()
state = store.get(session_key)
if state is None:
return False
current = asyncio.current_task()
if state.task is not None and state.task is not current and not state.task.done():
state.task.cancel()
state.task = None
existing_pending = self._pending_messages.get(session_key)
if (
existing_pending is not None
and not self._can_merge_text_debounce_events(existing_pending, state.event)
):
return False
state = store.pop(session_key, None)
if state is None:
return False
merge_pending_message_event(
self._pending_messages,
session_key,
state.event,
merge_text=True,
)
return True
def _discard_text_debounce(self, session_key: str) -> None:
"""Cancel and drop pending text debounce state for control commands."""
state = self._text_debounce_store().pop(session_key, None)
if state is not None and state.task is not None and not state.task.done():
state.task.cancel()
# ------------------------------------------------------------------
# Session task + guard ownership helpers
# ------------------------------------------------------------------
@@ -2794,6 +2979,7 @@ class BasePlatformAdapter(ABC):
self._active_sessions.pop(session_key, None)
self._pending_messages.pop(session_key, None)
self._session_tasks.pop(session_key, None)
self._discard_text_debounce(session_key)
return True
def _start_session_processing(
@@ -2875,6 +3061,7 @@ class BasePlatformAdapter(ABC):
)
if discard_pending:
self._pending_messages.pop(session_key, None)
self._discard_text_debounce(session_key)
if release_guard:
self._release_session_guard(session_key)
@@ -2889,6 +3076,7 @@ class BasePlatformAdapter(ABC):
command-scoped guard, then — if a follow-up message landed while the
command was running — spawns a fresh processing task for it.
"""
await self._flush_text_debounce_now(session_key)
pending_event = self._pending_messages.pop(session_key, None)
self._release_session_guard(session_key, guard=command_guard)
if pending_event is None:
@@ -3020,6 +3208,7 @@ class BasePlatformAdapter(ABC):
# through the dedicated handoff path that serializes
# cancellation + runner response + pending drain.
if cmd in {"stop", "new", "reset"}:
self._discard_text_debounce(session_key)
try:
await self._dispatch_active_session_command(event, session_key, cmd)
except Exception as e:
@@ -3064,8 +3253,9 @@ class BasePlatformAdapter(ABC):
# clarify-intercept can resolve it and unblock the agent.
#
# Without this bypass: the message gets queued in
# _pending_messages AND triggers an interrupt, killing the
# agent run mid-clarify and discarding the user's answer.
# _pending_messages as a follow-up turn instead of reaching the
# clarify resolver, leaving the agent blocked and discarding the
# user's answer.
# Same shape as the /approve deadlock fix (PR #4926) — both
# cases are "agent thread blocked on Event.wait, message must
# reach the resolver before being treated as a new turn."
@@ -3124,27 +3314,28 @@ class BasePlatformAdapter(ABC):
merge_pending_message_event(self._pending_messages, session_key, event)
return # Don't interrupt now - will run after current task completes
# Default behavior for non-photo follow-ups: interrupt the running agent.
#
# Use merge_text=True so rapid TEXT follow-ups (#4469) accumulate
# into the single pending slot instead of clobbering each other.
# Without merging, three rapid messages "A", "B", "C" land like:
# _pending_messages[k] = A (interrupts)
# _pending_messages[k] = B (replaces A before consumer reads)
# _pending_messages[k] = C (replaces B)
# ...and only "C" reaches the next turn. merge_pending_message_event
# already does the right thing for photo/media bursts; the
# ``merge_text=True`` flag extends that to plain TEXT events.
# Same shape as the Telegram bursty-grace path in gateway/run.py.
logger.debug("[%s] New message while session %s is active — triggering interrupt", self.name, session_key)
merge_pending_message_event(
self._pending_messages,
session_key,
event,
merge_text=True,
)
# Signal the interrupt (the processing task checks this)
self._active_sessions[session_key].set()
if self._is_queue_text_debounce_candidate(event):
logger.debug(
"[%s] New text message while session %s is active — "
"debouncing follow-up (busy_text_mode=queue, window=%.2fs)",
self.name,
session_key,
self._busy_text_debounce_seconds,
)
await self._queue_text_debounce(session_key, event)
else:
logger.debug(
"[%s] New message while session %s is active — queuing follow-up "
"(no interrupt, will cascade after current turn)",
self.name,
session_key,
)
merge_pending_message_event(
self._pending_messages,
session_key,
event,
merge_text=event.message_type == MessageType.TEXT,
)
return # Don't process now - will be handled after current task finishes
# Mark session as active BEFORE spawning background task to close
@@ -3498,10 +3689,15 @@ class BasePlatformAdapter(ABC):
ProcessingOutcome.SUCCESS if processing_ok else ProcessingOutcome.FAILURE,
)
# The active drain owns debounce state. If a queue-mode timer has
# not fired yet, force-flush into _pending_messages here and let
# this task hand off the follow-up.
await self._flush_text_debounce_now(session_key)
# Check if there's a pending message that was queued during our processing
if session_key in self._pending_messages:
pending_event = self._pending_messages.pop(session_key)
logger.debug("[%s] Processing queued message from interrupt", self.name)
logger.debug("[%s] Processing queued follow-up message", self.name)
# Keep the _active_sessions entry live across the turn chain
# and only CLEAR the interrupt Event — do NOT delete the entry.
# If we deleted here, a concurrent inbound message arriving
@@ -3510,7 +3706,7 @@ class BasePlatformAdapter(ABC):
# with the recursive drain below. Two agents on one
# session_key = duplicate responses, duplicate tool calls.
# Clearing the Event keeps the guard live so follow-ups take
# the busy-handler path (queue + interrupt) as intended.
# the busy-handler path as intended.
_active = self._active_sessions.get(session_key)
if _active is not None:
_active.clear()
@@ -3603,6 +3799,9 @@ class BasePlatformAdapter(ABC):
await self.stop_typing(event.source.chat_id)
except Exception:
pass
# Final drain/release boundary: force-flush any timer that missed
# the in-band drain before deciding whether the guard can clear.
await self._flush_text_debounce_now(session_key)
# Late-arrival drain: a message may have arrived during the
# cleanup awaits above (typing_task cancel, stop_typing). Such
# messages passed the Level-1 guard (entry still live, Event
@@ -3722,6 +3921,10 @@ class BasePlatformAdapter(ABC):
self._session_tasks.clear()
self._pending_messages.clear()
self._active_sessions.clear()
for state in list(self._text_debounce_store().values()):
if state.task is not None and not state.task.done():
state.task.cancel()
self._text_debounce_store().clear()
def has_pending_interrupt(self, session_key: str) -> bool:
"""Check if there's a pending interrupt for a session."""

View File

@@ -839,6 +839,8 @@ if _config_path.exists():
if _display_cfg and isinstance(_display_cfg, dict):
if "busy_input_mode" in _display_cfg:
os.environ["HERMES_GATEWAY_BUSY_INPUT_MODE"] = str(_display_cfg["busy_input_mode"])
if "busy_text_mode" in _display_cfg:
os.environ["HERMES_GATEWAY_BUSY_TEXT_MODE"] = str(_display_cfg["busy_text_mode"])
if "busy_ack_enabled" in _display_cfg:
os.environ["HERMES_GATEWAY_BUSY_ACK_ENABLED"] = str(_display_cfg["busy_ack_enabled"])
# Timezone: bridge config.yaml → HERMES_TIMEZONE env var.
@@ -1554,6 +1556,7 @@ class GatewayRunner:
# blow up on attribute access.
_running_agents_ts: Dict[str, float] = {}
_busy_input_mode: str = "interrupt"
_busy_text_mode: str = "interrupt"
_restart_drain_timeout: float = DEFAULT_GATEWAY_RESTART_DRAIN_TIMEOUT
_exit_code: Optional[int] = None
_draining: bool = False
@@ -1580,6 +1583,7 @@ class GatewayRunner:
self._service_tier = self._load_service_tier()
self._show_reasoning = self._load_show_reasoning()
self._busy_input_mode = self._load_busy_input_mode()
self._busy_text_mode = self._load_busy_text_mode()
self._restart_drain_timeout = self._load_restart_drain_timeout()
self._provider_routing = self._load_provider_routing()
self._fallback_model = self._load_fallback_model()
@@ -2826,6 +2830,17 @@ class GatewayRunner:
return "steer"
return "interrupt"
@staticmethod
def _load_busy_text_mode() -> str:
"""Load normal busy TEXT follow-up behavior from config/env."""
mode = os.getenv("HERMES_GATEWAY_BUSY_TEXT_MODE", "").strip().lower()
if not mode:
cfg = _load_gateway_runtime_config()
mode = str(cfg_get(cfg, "display", "busy_text_mode", default="") or "").strip().lower()
if mode == "interrupt":
return "interrupt"
return "queue"
@staticmethod
def _load_restart_drain_timeout() -> float:
"""Load graceful gateway restart/stop drain timeout in seconds."""
@@ -2973,11 +2988,19 @@ class GatewayRunner:
running_agent = self._running_agents.get(session_key)
effective_mode = self._busy_input_mode
busy_text_mode = getattr(self, "_busy_text_mode", "queue")
if (
event.message_type == MessageType.TEXT
and busy_text_mode == "queue"
and effective_mode != "steer"
):
return False
# Steer mode: inject mid-run via running_agent.steer() instead of
# queueing + interrupting. If the agent isn't running yet
# (sentinel) or lacks steer(), or the payload is empty, fall back
# to queue semantics so nothing is lost.
effective_mode = self._busy_input_mode
steered = False
if effective_mode == "steer":
steer_text = (event.text or "").strip()
@@ -3002,7 +3025,12 @@ class GatewayRunner:
# successful steer — the text already landed inside the run and
# must NOT also be replayed as a next-turn user message.
if not steered:
merge_pending_message_event(adapter._pending_messages, session_key, event)
merge_pending_message_event(
adapter._pending_messages,
session_key,
event,
merge_text=event.message_type == MessageType.TEXT,
)
is_queue_mode = effective_mode == "queue"
is_steer_mode = effective_mode == "steer"
@@ -3934,6 +3962,7 @@ class GatewayRunner:
adapter.set_fatal_error_handler(self._handle_adapter_fatal_error)
adapter.set_session_store(self.session_store)
adapter.set_busy_session_handler(self._handle_active_session_busy_message)
adapter._busy_text_mode = self._busy_text_mode
# Try to connect
logger.info("Connecting to %s...", platform.value)
@@ -5546,6 +5575,7 @@ class GatewayRunner:
adapter.set_fatal_error_handler(self._handle_adapter_fatal_error)
adapter.set_session_store(self.session_store)
adapter.set_busy_session_handler(self._handle_active_session_busy_message)
adapter._busy_text_mode = self._busy_text_mode
success = await self._connect_adapter_with_timeout(adapter, platform)
if success: