From b7685271878ef98875d2c802143031bd66e8efdf Mon Sep 17 00:00:00 2001 From: NanPan <111261006+poijygfdyy@users.noreply.github.com> Date: Sat, 3 Oct 2026 21:55:00 +0800 Subject: [PATCH] fix(channels): retain live SDK workers after stop timeout (#6215) * rebase(channels): replay retained worker fix * rebase(channels): replay retained worker fix * rebase(channels): replay retained worker fix * rebase(channels): replay retained worker fix * rebase(channels): replay stop-timeout classification * rebase(channels): replay retained timeout handling * rebase(channels): replay retained worker guidance * docs(channels): keep lifecycle guidance within CI size limit * docs(channels): fit lifecycle guidance within size budget --------- Co-authored-by: Willem Jiang --- backend/app/channels/AGENTS.md | 6 +++--- backend/app/channels/base.py | 4 ++++ backend/app/channels/dingtalk.py | 10 +++++++--- backend/app/channels/feishu.py | 10 +++++++--- backend/app/channels/service.py | 8 +++++++- backend/tests/test_dingtalk_channel.py | 16 ++++++++++++++++ backend/tests/test_feishu_parser.py | 17 +++++++++++++++++ 7 files changed, 61 insertions(+), 10 deletions(-) diff --git a/backend/app/channels/AGENTS.md b/backend/app/channels/AGENTS.md index 6b84a54932..f4ed5c4e36 100644 --- a/backend/app/channels/AGENTS.md +++ b/backend/app/channels/AGENTS.md @@ -6,13 +6,13 @@ Bridges external messaging platforms (Feishu, Slack, Telegram, Discord, DingTalk **Components**: - `message_bus.py` - Async pub/sub hub (`InboundMessage` → queue → dispatcher; `OutboundMessage` → callbacks → channels) -- `store.py` - JSON-file persistence mapping `channel_name:chat_id[:topic_id]` → `thread_id` (keys are `channel:chat` for root conversations and `channel:chat:topic` for threaded conversations). Every access to `_data` must be protected by `_lock`; `list_entries()` snapshots keys and copied entries under the lock, then formats the result after releasing it so concurrent channel threads cannot resize the dictionary during iteration without extending the critical section. +- `store.py` - JSON persistence for `channel_name:chat_id[:topic_id]` → `thread_id`. Guard every `_data` access with `_lock`; `list_entries()` snapshots under the lock and formats after release so concurrent writers cannot resize the dict during iteration. - `manager.py` - Core dispatcher: creates threads via `client.threads.create()`, routes commands including `/goal` (setting a goal persists it through Gateway and then routes the objective as a chat turn) and `/agent` (`list` is owner-scoped; `use` creates a fresh thread and persists the Custom Agent selection under both the channel restart key and Web's canonical routing metadata so existing checkpoint lineage never changes agent across IM/Web), keeps Slack/Discord on `client.runs.wait()`, uses `client.runs.stream(["messages-tuple", "values"])` for Feishu/Telegram incremental outbound updates, serializes same-thread Feishu turns in-manager when the channel's `ChannelRunPolicy.serialize_thread_runs=True` so rapid follow-ups queue instead of tripping the runtime busy reply, and switches to `client.runs.create()` (fire-and-forget, returns once the run is `pending`) for channels whose `ChannelRunPolicy.fire_and_forget=True` so long autonomous runs do not hit the SDK default 300s `httpx.ReadTimeout` A swallowed streaming failure publishes its final outbound before releasing the inbound dedupe key, so a provider redelivery can retry without overtaking the terminal reply. **What may be published from the stream is an allowlist, not a denylist** (`_accumulate_stream_text`): only assistant message types — LangChain serializes `AIMessage.type` as `"ai"` and `AIMessageChunk.type` as `"AIMessageChunk"`, plus the OpenAI-style `"assistant"` spelling for foreign runtimes — become displayable text. The previous rule rejected only payloads whose `type` contained `"tool"` and therefore published everything else, which leaked DeerFlow's hidden model context to every streaming IM channel: `DynamicContextMiddleware` injects recalled memory as a hidden `HumanMessage` (`type == "human"`) and rewrites the user's own turn into a new `HumanMessage`, `DurableContextMiddleware` injects a hidden `` `HumanMessage`, and LangGraph fans those state writes out on the `messages-tuple` stream. Proved live on a Buzz relay, which published a `` fact block and, in another run, a verbatim echo of the user's own message as the assistant's reply. Matching is by prefix (`ai` / `assistant`), never substring, because ordinary words contain `"ai"` (`chain`, `domain`). The message type is resolved by `_stream_payload_type`, which handles both the `model_dump()` shape DeerFlow's own gateway emits and LangChain's `to_json()` constructor shape (whose top-level `type` is the literal `"constructor"`, with the class name at the tail of the `id` path). A bare `str` payload is no longer accepted at all: it carries no type information, so it cannot be attributed to the assistant, and nothing in DeerFlow produces one (`runtime/serialization.py::serialize_messages_tuple` always emits `[message_dict, metadata]`). - `base.py` - Abstract `Channel` base class (start/stop/send lifecycle). Provider callbacks that submit coroutines from SDK threads must use `_submit_threadsafe_coroutine()` (or `_submit_threadsafe_coroutine_future()` to await the outcome through `asyncio.shield`): it creates and retains the real `asyncio.Task` on the owner loop instead of treating `run_coroutine_threadsafe()`'s proxy Future as a completion signal. Submission is closed atomically with shutdown, and `stop()` must call `_close_and_drain_threadsafe_futures()` before tearing down SDK resources. Blocking SDK teardown in `stop()` (a client `close()`, a thread `join()`) must run off the event loop through `asyncio.to_thread`, since every run and channel on the Gateway shares that loop and `stop()` also serves `POST /api/channels/{name}/restart`; Slack's `SocketModeClient.close()` is a shielded, tracked task so a cancelled stop leaves it running and a retried stop awaits the same close. Anchored by `tests/blocking_io/test_channel_stop_offloop.py`. **Proactive push** (`Channel.send_notification`): used by the scheduled-task notification outbox to push markdown to a bound external identity with no inbound frame. The base default raises `NotImplementedError` (after a `ChannelUnavailable` check when not running) so unsupported providers fail visibly in the outbox. Connectivity failures must raise `ChannelUnavailable` so the delivery worker parks without consuming retries; platform rejections of a well-formed send remain ordinary exceptions. **Only WeCom implements proactive push today** (`wecom.py` via `WSClient.send_message`); the SDK raises `RuntimeError` from that call for a dead socket and for a platform rejection alike, so only the `Reply ack error` prefix counts; other `RuntimeError`s, `ConnectionError`/`TimeoutError`/`OSError` and the `websockets` close exception park. Before sending, the worker re-checks the binding via `resolve_connections` (`ChannelConnectionRepository.list_connections`, owner-scoped, ahead of the channel-liveness check): a target no longer `connected` for the row's owner is finalized with `mark_failed(terminal=True)`; a lookup failure parks. Terminal outbox rows (`sent`/`failed`) ignore later status writes. Scheduler side (`app/scheduler/`): `handle_run_completion` enqueues only after `complete_run` recorded a success or failed outcome; manual triggers, interrupts and recovery-finalized occurrences stay silent. Gateway lifespan wires the enqueue side with the scheduler, then starts `NotificationDeliveryWorker` after the channel service (the scheduler starts first), detaching the enqueue side if delivery cannot start; the worker stops before the channel service. -- `wecom.py` - WeCom WebSocket channel; implements `send_notification` for the outbox worker. Tracks `_ws_transport_up` across disconnect/reconnect so transport failures become `ChannelUnavailable` rather than burning the counted retry budget. -- `service.py` - Manages lifecycle of all configured channels from `config.yaml`. Shutdown closes manager admission first and keeps transports alive until every manager worker/follow-up watcher has exited. A successful manager stop therefore owns no live handler; if the Gateway's outer timeout cancels shutdown, the service retains its channel objects and global singleton so unfinished resources are not detached and cleanup can be retried. +- `wecom.py` - WeCom WebSocket channel with proactive `send_notification`; `_ws_transport_up` maps disconnects to `ChannelUnavailable` without consuming retry budget. +- `service.py` - Owns configured channel lifecycles. Shutdown drains manager work before transports and retains objects on timeout for retry. If a bounded Feishu/DingTalk join leaves the SDK thread alive, `ChannelStopTimeout` retains that instance and defers replacement/restart; log WARNING without traceback. The wedge still reports `is_running`/status false. - `slack.py` / `feishu.py` / `telegram.py` / `discord.py` / `dingtalk.py` - Platform-specific implementations (`feishu.py` tracks the running card `message_id` in memory and patches the same card in place; `telegram.py` accepts inbound text/photos/documents, preserves media captions, hands token-free attachment bytes to the shared upload pipeline, edits the "Working on it..." stream target in place via `editMessageText`, and can optionally send final Markdown replies as Rich Messages through `channels.telegram.rich_messages` — the Rich path only fires when `rich_messages` is on **and** the text contains a rich construct (fenced code, emphasis, a table, a task list, `
`, block math, or a link), so structured command/error replies (none of these) stay plain text and their newlines and `` tokens survive; `discord.py` runs `_on_message` on discord.py's private loop, so connection-repository work (identity lookup with the reservation commit, `/connect` binding) goes to the Gateway loop through `_submit_threadsafe_coroutine` — the SQLAlchemy engine is bound there — and bind replies return through `_run_on_discord_loop`; typing registers before that hand-off settles, and a failed hand-off skips the ack and stops the indicator it started unless another message still relies on it; `discord.py` registers typing loops before inbound handling yields and `_start_typing()` refuses work once `_running` is false; each tick sends the indicator with discord.py 2.x's `await channel.typing()` (`trigger_typing()` was removed in 2.0, and each typing loop logs its first failed tick at WARNING, later ones at DEBUG); because `stop()` runs on the main loop while typing tasks belong to `_discord_loop`, normal cross-thread cancellation, awaiting, and map cleanup are scheduled there with a bounded wait, while `_run_client()` drains tasks in its `finally` block before an exception/disconnect can make that loop unusable; an already-stopped foreign loop must never have its tasks awaited from the main loop; to that end every outbound cross-loop call (`send` / `send_file` / `_get_channel_or_thread`) goes through `_run_on_discord_loop`, which bounds the await (`DISCORD_OUTBOUND_TIMEOUT_SECONDS` 30s; `DISCORD_UPLOAD_TIMEOUT_SECONDS` 120s for file uploads, whose unbounded-size payload needs room for a slow uplink plus 429 retry-after) and fails fast with a `RuntimeError` when the client loop is missing or not running — a dead client becomes a logged send failure instead of a permanently hung `ChannelManager` worker — and `is_running` reports client-thread aliveness (like `feishu.py`) so `ensure_channel_ready` can restart the channel after `_run_client()` exits on a fatal error; `dingtalk.py` optionally uses AI Card streaming for in-place updates when `card_template_id` is configured, and overrides `receive_file` to download inbound images (`picture`/`richText`) and documents (`file`) by `downloadCode` into the thread uploads bucket, mirroring `feishu.py`) - `buzz.py` - Buzz (Nostr relay) implementation: one NIP-42-authenticated websocket, pubkey-allowlist + mention/DM/thread-follow gating, streaming replies via in-place kind-40003 edits; requires the `buzz` dependency extra. Its durable seen-event replay guard uses async `aseen()` / `arecord()` / `aflush()` boundaries: initial JSON reads and coalesced atomic writes run off the Gateway event loop, and `stop()` awaits the final flush before returning. **Subscription model** (operator-facing version in [IM_CHANNEL_CONNECTIONS.md](../../docs/IM_CHANNEL_CONNECTIONS.md#buzz-subscription-model)): the relay fans kind-9 chat events out **only** to channel-scoped subscriptions, proved against a live relay — `REQ {"kinds":[9]}` is accepted and answered with `EOSE` but never receives an event (the connector authenticated and then sat silent forever), `REQ {"kinds":[9],"#h":[uuid]}` works, and a multi-value `#h` matches nothing, so it is strictly one REQ per channel (the same shape as Buzz's own `buzz-acp` harness). Every connection therefore rebuilds three kinds of subscription after NIP-42 auth: `buzz-discovery` (`{"kinds":[39000]}`, a historical query returning exactly the channels this identity belongs to, one stored event each then `EOSE` — adding `#p` returns zero, do not "narrow" it), `buzz-membership` (`{"kinds":[44100,44101],"#p":[us],"since":}`, the relay-signed member-added/member-removed notifications whose `p` tag names the affected member and `h` tag the channel), and one `buzz-chat-` per discovered channel. Chat subscriptions open as each kind-39000 arrives; the discovery `EOSE` is the completeness barrier that retries any that failed and warns when discovery found nothing. A kind-44100 for our pubkey subscribes to the new channel **live** (then re-issues discovery so its name/type reach the DM-detection cache, but only when that channel's metadata is actually missing — an unconditional refresh is how a burst of 44100s multiplied into one discovery pass each); a kind-44101 issues `buzz_nostr.close_frame` for exactly that channel's subscription and drops its metadata. **The membership subscription is scoped to LIVE events** and this is load-bearing: buzz-relay *stores* 44100/44101 and serves history newest-first (default limit 2000), so an unscoped filter replayed the whole membership history on every connect — every stored add read as live, re-running discovery once each (M+1 discovery passes × N stored kind-39000 events per connect, observed live as two `channel discovery complete` lines and one channel logged `` because the 44100 path subscribed before its metadata arrived), re-subscribing channels we have since been removed from, and letting a stored 44101 transiently unsubscribe a channel we are still in. `since` is anchored at the moment the socket opened (`_session_started_at`) minus `MEMBERSHIP_LOOKBACK_SECONDS` (60) of slack, which covers both relay clock skew and a membership change published *during* the connect/auth handshake; the slack can only cost an idempotent replay of the last minute. **A relay `CLOSED` frame is recovered, not merely forgotten** — every subscription on the socket fails silently when dropped, so `_handle_closed` re-issues it, bounded by `MAX_RESUBSCRIBE_ATTEMPTS` (3) per subscription id per connection *and per auth epoch* (`_resubscribe_attempts` is reset on session start, on re-auth, and by `stop()`, so pre-auth rejections — which the auth branch already recovers wholesale — never spend the authenticated session's budget). The first retry is immediate (the common case is a one-off hiccup); later ones back off 1s then 2s, awaited inline in the read loop rather than in a background task that could outlive its own socket. **`auth-required:` before this socket has completed its NIP-42 handshake is the expected bootstrap sequence, not a refusal**, and `_handle_closed` short-circuits it ahead of every recovery path: the connector opens its control REQs immediately in case the relay serves unauthenticated reads, a closed relay answers `auth-required:` plus an `AUTH` challenge, and the auth branch re-opens everything. That case is logged at DEBUG and consumes neither the permanent-refusal branch nor the retry budget (a chat subscription is still dropped from `_chat_subscriptions`, since it genuinely is not subscribed and discovery is what re-opens it). Treating it as permanent produced an operator-facing warning claiming discovery/membership tracking was DOWN in the same run where discovery then completed, every channel was subscribed, and a brand-new channel's kind-44100 was picked up one second later. The boundary is the per-socket `_auth_completed` flag, set once the signed AUTH event has been sent and cleared on session entry, session exit, and `stop()`; the same reason *after* that stays loud, and says the subscription is down until the relay's next AUTH challenge or the next reconnect rather than borrowing the non-auth wording. Then `_is_transient_close` decides whether to retry at all: NIP-01/NIP-42 `auth-required:`/`restricted:`/`blocked:`/`mute:`/`invalid:`/`pow:` prefixes and buzz-relay's own removal/revocation prose are permanent (do not fight the relay over a channel that is no longer ours; a post-auth `auth-required:` is recovered by the AUTH branch, not by re-issuing), `rate-limited:`/`error:`/no-reason-at-all and anything unrecognized are transient — the default resolves toward "keep listening" because going silently deaf is the failure this exists to remove, and the attempt budget bounds a wrong guess. A chat `CLOSED` is only ever recovered for a channel already in `_chat_subscriptions`: a `CLOSED` is relay-supplied, so acting on an unknown one would let a relay induce a subscription just by naming a channel. Every subscription that goes unlistened is logged at WARNING, never INFO. Subscription ids are deterministic per channel precisely so one can be replaced or closed without disturbing the others on the socket, and `_chat_subscriptions` is per-socket state cleared on session end, on re-auth (a pre-auth REQ may have been rejected), and by `stop()`. Three bounds on remote-fed state: `MAX_CACHED_CHANNELS` (512) caps the kind-39000 metadata cache, the watermark map, and the resubscribe-attempt map; `MAX_CHANNEL_SUBSCRIPTIONS` (256, well under buzz-relay's own 1024-per-connection ceiling) caps live chat subscriptions — at the cap new channels are refused and named in a warning rather than evicting a working subscription. **Known bound (documented, not fixed):** the relay caps historical delivery at 2000 events per subscription, newest-first, even with a `since`, so >2000 unread messages in a *single* channel across a disconnect loses the oldest — the relay never sends them and the watermark advances past them. That is the one remaining path that can skip; everything else fails toward replay. **Trust model** (operator-facing version in [IM_CHANNEL_CONNECTIONS.md](../../docs/IM_CHANNEL_CONNECTIONS.md#buzz-trust-model)): every inbound `EVENT` is authenticated at the single `handle_relay_frame` choke point — the NIP-01 id is recomputed from the delivered payload and the BIP-340 Schnorr signature verified against the claimed `pubkey` (`buzz_nostr.verify_event`, pure and total: malformed input returns `False`, never raises) — so `ev["pubkey"]`, the authorization principal for both the allowlist and the `/connect` bind, cannot be forged by a relay the DeerFlow operator does not run. What remains trusted is the *authorship* of kind-39000 channel metadata: any member can sign one, and because per-channel subscriptions are now driven by discovery, a forged kind-39000 has two effects rather than one — it can mark a channel `type: "dm"` (relaxing `require_mention` for that channel) **and** it can induce a chat subscription for a channel of the forger's choosing, since the channels we listen to are exactly the channels we hold metadata for. Neither makes anything be *acted on*: `allowed_users` and per-event signature verification are independent gates, so an induced subscription only means the relay reads its own traffic back to a subscriber that drops it, bounded by `MAX_CHANNEL_SUBSCRIPTIONS` (which refuses rather than evicts, so it cannot displace a real channel). Same for a forged kind-44100, except its `p` tag is re-checked locally so it must at least name us. Closing this needs a configured trusted relay pubkey, which `relay_url` is not. `allowed_users` is deny-by-default (empty = nobody, unlike siblings' empty = everyone), so `start()` logs a WARNING when it is empty and each drop logs at DEBUG. The resubscribe cursor (`since`) is **per channel**, advances only for events that were actually processed, and never past `now + MAX_FUTURE_SKEW_SECONDS`, because it is peer-supplied (`created_at`) and a single future-dated event otherwise made the connector permanently deaf. Per channel rather than global is the safety-critical half: subscriptions are per channel, so one shared cursor is the newest event seen in *any* channel and a busy channel would drag it past a quiet channel's unread messages, skipping them on the next reconnect — measured on a live relay, three channels of one identity sat ~28h apart. Per-channel cursors can only ever cost duplicate delivery (absorbed by the manager's `event_id` dedupe), and an evicted cursor degrades to "no `since`", i.e. the relay's default backlog — both fail toward replay, never toward a miss. Streaming tracks every oversize chunk index (`_stream_targets` for chunk 0, `_stream_tails` for the rest), since the manager republishes cumulative text and reposting `chunks[1:]` per update flooded the channel; all of it is per-connection state cleared by `stop()`, and the remote-fed kind-39000 cache is capped at `MAX_CACHED_CHANNELS`. **`send()` refuses outright to publish text carrying a hidden model-context wrapper** (``, ``, `` — `_HIDDEN_CONTEXT_MARKERS`), logging at ERROR and clearing the stream bookkeeping on a blocked `is_final`. This is defense in depth behind the manager's allowlist, and it lives here rather than in a sibling connector because on Buzz a leak is permanent: every streaming update is an immutable public Nostr event, so a corrective edit only changes what clients render while the original leaked event stays on the relay. Matching is on the literal opening tag, so a reply that merely talks about memory is still published Buzz seen-event shutdown stays bounded and retryable: `aflush()` awaits any in-flight write, attempts at most one final snapshot, leaves a still-changing generation dirty for fail-open replay, and returns without a live persistence timer. A Gateway cancellation does not cancel the underlying worker-thread write; `BuzzChannel.stop()` tracks cleanup completion separately from transport admission so ChannelService can retry the retained channel without racing a second snapshot against that write. The store is quiesced before stop (including the already-stopped guard), so a timed-out relay task that records after stop only marks data dirty and cannot schedule detached file work; a repeated `stop()` still drains that dirty state, while `BuzzChannel.start()` explicitly resumes scheduling and flushes it automatically. diff --git a/backend/app/channels/base.py b/backend/app/channels/base.py index 1d470bf568..68295ef3a8 100644 --- a/backend/app/channels/base.py +++ b/backend/app/channels/base.py @@ -39,6 +39,10 @@ class ChannelUnavailable(Exception): """ +class ChannelStopTimeout(RuntimeError): + """A channel still owns a live provider worker after bounded teardown.""" + + @dataclass(eq=False, slots=True) class _ThreadsafeSubmission: coroutine: Coroutine[Any, Any, Any] diff --git a/backend/app/channels/dingtalk.py b/backend/app/channels/dingtalk.py index f7425c7eaa..016f8b0878 100644 --- a/backend/app/channels/dingtalk.py +++ b/backend/app/channels/dingtalk.py @@ -14,7 +14,7 @@ from typing import Any import httpx -from app.channels.base import Channel +from app.channels.base import Channel, ChannelStopTimeout from app.channels.commands import is_known_channel_command, strip_leading_mentions from app.channels.connection_identity import attach_connection_identity from app.channels.message_bus import InboundMessage, InboundMessageType, InboundReservation, MessageBus, OutboundMessage, ResolvedAttachment @@ -230,8 +230,12 @@ class DingTalkChannel(Channel): if self._thread: # The SDK thread only returns on a fatal error, so this join # normally waits out its full timeout; keep it off the event loop. - await asyncio.to_thread(self._thread.join, timeout=5) - self._thread = None + thread = self._thread + await asyncio.to_thread(thread.join, timeout=5) + if thread.is_alive(): + raise ChannelStopTimeout("DingTalk SDK thread is still running after stop timeout") + if self._thread is thread: + self._thread = None logger.info("DingTalk channel stopped") def _resolve_routing(self, msg: OutboundMessage) -> tuple[str, str, str]: diff --git a/backend/app/channels/feishu.py b/backend/app/channels/feishu.py index df1a1a5ae1..0b5c2bce47 100644 --- a/backend/app/channels/feishu.py +++ b/backend/app/channels/feishu.py @@ -11,7 +11,7 @@ import threading import time from typing import Any, Literal -from app.channels.base import Channel +from app.channels.base import Channel, ChannelStopTimeout from app.channels.commands import is_known_channel_command, strip_leading_mentions from app.channels.connection_identity import attach_connection_identity from app.channels.message_bus import ( @@ -285,8 +285,12 @@ class FeishuChannel(Channel): if self._thread: # The SDK thread only returns on a fatal error, so this join # normally waits out its full timeout; keep it off the event loop. - await asyncio.to_thread(self._thread.join, timeout=5) - self._thread = None + thread = self._thread + await asyncio.to_thread(thread.join, timeout=5) + if thread.is_alive(): + raise ChannelStopTimeout("Feishu SDK thread is still running after stop timeout") + if self._thread is thread: + self._thread = None logger.info("Feishu channel stopped") async def send(self, msg: OutboundMessage, *, _max_retries: int = 3) -> None: diff --git a/backend/app/channels/service.py b/backend/app/channels/service.py index 4a2c6f4f6f..3ad0aa2b95 100644 --- a/backend/app/channels/service.py +++ b/backend/app/channels/service.py @@ -10,7 +10,7 @@ from collections.abc import Callable from pathlib import Path from typing import TYPE_CHECKING, Any -from app.channels.base import Channel +from app.channels.base import Channel, ChannelStopTimeout from app.channels.manager import DEFAULT_CHANNEL_MAX_CONCURRENCY, DEFAULT_CHANNEL_SHUTDOWN_GRACE_PERIOD_SECONDS, DEFAULT_GATEWAY_URL, DEFAULT_LANGGRAPH_URL, ChannelManager from app.channels.message_bus import DEFAULT_INBOUND_QUEUE_MAXSIZE, MessageBus from app.channels.runtime_config_store import merge_runtime_channel_configs @@ -300,6 +300,9 @@ class ChannelService: # The Gateway deadline interrupted shutdown, so detaching them # would hide resources that may still be in use. raise + except ChannelStopTimeout as exc: + logger.warning("Channel %s remains retained after bounded stop timeout: %s", name, exc) + stop_errors.append(exc) except Exception as exc: logger.exception("Error stopping channel") stop_errors.append(exc) @@ -428,6 +431,9 @@ class ChannelService: # interrupted cleanup, so detaching it here would hide resources # that may still be in use (mirrors ChannelService.stop()). raise + except ChannelStopTimeout as exc: + logger.warning("Channel %s remains retained after bounded stop timeout: %s", name, exc) + return except Exception: logger.exception("Error stopping channel %s during discard", name) return diff --git a/backend/tests/test_dingtalk_channel.py b/backend/tests/test_dingtalk_channel.py index 84b18727e7..193cd62cda 100644 --- a/backend/tests/test_dingtalk_channel.py +++ b/backend/tests/test_dingtalk_channel.py @@ -1772,6 +1772,22 @@ class TestCardMode: class TestStop: + def test_stop_retains_live_stream_thread_after_join_timeout(self): + async def go(): + channel = DingTalkChannel(MessageBus(), config={}) + thread = MagicMock() + thread.is_alive.return_value = True + channel._thread = thread + channel._running = True + + with pytest.raises(RuntimeError, match="still running after stop timeout"): + await channel.stop() + + thread.join.assert_called_once_with(timeout=5) + assert channel._thread is thread + + _run(go()) + def test_stop_joins_stream_thread_off_the_event_loop(self): async def go(): channel = DingTalkChannel(MessageBus(), config={}) diff --git a/backend/tests/test_feishu_parser.py b/backend/tests/test_feishu_parser.py index bafc7c6dda..2d8517c40a 100644 --- a/backend/tests/test_feishu_parser.py +++ b/backend/tests/test_feishu_parser.py @@ -190,6 +190,23 @@ def test_feishu_stop_joins_ws_thread_off_the_event_loop(): asyncio.run(go()) +def test_feishu_stop_retains_live_ws_thread_after_join_timeout(): + async def go(): + channel = FeishuChannel(MessageBus(), {"app_id": "test", "app_secret": "test"}) + thread = MagicMock() + thread.is_alive.return_value = True + channel._thread = thread + channel._running = True + + with pytest.raises(RuntimeError, match="still running after stop timeout"): + await channel.stop() + + thread.join.assert_called_once_with(timeout=5) + assert channel._thread is thread + + asyncio.run(go()) + + def test_feishu_event_handler_ignores_non_content_message_events(): import lark_oapi as lark