mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
fix(matrix): harden e2ee access-token handling (#3562)
* fix(matrix): harden e2ee access-token handling * fix: patch nio mock in e2ee maintenance sync loop test The sync_loop now imports nio for SyncError checking (from PR #3280), so the test needs to inject a fake nio module via sys.modules. --------- Co-authored-by: Cortana <andrew+cortana@chalkley.org>
This commit is contained in:
Teknium
GitHub
parent
be39292633
commit
be322efdf2
2 changed files with 320 additions and 20 deletions
|
|
@ -161,22 +161,49 @@ class MatrixAdapter(BasePlatformAdapter):
|
|||
# Authenticate.
|
||||
if self._access_token:
|
||||
client.access_token = self._access_token
|
||||
# Resolve user_id if not set.
|
||||
if not self._user_id:
|
||||
resp = await client.whoami()
|
||||
if isinstance(resp, nio.WhoamiResponse):
|
||||
self._user_id = resp.user_id
|
||||
client.user_id = resp.user_id
|
||||
logger.info("Matrix: authenticated as %s", self._user_id)
|
||||
else:
|
||||
logger.error(
|
||||
"Matrix: whoami failed — check MATRIX_ACCESS_TOKEN and MATRIX_HOMESERVER"
|
||||
|
||||
# With access-token auth, always resolve whoami so we validate the
|
||||
# token and learn the device_id. The device_id matters for E2EE:
|
||||
# without it, matrix-nio can send plain messages but may fail to
|
||||
# decrypt inbound encrypted events or encrypt outbound room sends.
|
||||
resp = await client.whoami()
|
||||
if isinstance(resp, nio.WhoamiResponse):
|
||||
resolved_user_id = getattr(resp, "user_id", "") or self._user_id
|
||||
resolved_device_id = getattr(resp, "device_id", "")
|
||||
if resolved_user_id:
|
||||
self._user_id = resolved_user_id
|
||||
|
||||
# restore_login() is the matrix-nio path that binds the access
|
||||
# token to a specific device and loads the crypto store.
|
||||
if resolved_device_id and hasattr(client, "restore_login"):
|
||||
client.restore_login(
|
||||
self._user_id or resolved_user_id,
|
||||
resolved_device_id,
|
||||
self._access_token,
|
||||
)
|
||||
await client.close()
|
||||
return False
|
||||
else:
|
||||
if self._user_id:
|
||||
client.user_id = self._user_id
|
||||
if resolved_device_id:
|
||||
client.device_id = resolved_device_id
|
||||
client.access_token = self._access_token
|
||||
if self._encryption:
|
||||
logger.warning(
|
||||
"Matrix: access-token login did not restore E2EE state; "
|
||||
"encrypted rooms may fail until a device_id is available"
|
||||
)
|
||||
|
||||
logger.info(
|
||||
"Matrix: using access token for %s%s",
|
||||
self._user_id or "(unknown user)",
|
||||
f" (device {resolved_device_id})" if resolved_device_id else "",
|
||||
)
|
||||
else:
|
||||
client.user_id = self._user_id
|
||||
logger.info("Matrix: using access token for %s", self._user_id)
|
||||
logger.error(
|
||||
"Matrix: whoami failed — check MATRIX_ACCESS_TOKEN and MATRIX_HOMESERVER"
|
||||
)
|
||||
await client.close()
|
||||
return False
|
||||
elif self._password and self._user_id:
|
||||
resp = await client.login(
|
||||
self._password,
|
||||
|
|
@ -194,13 +221,18 @@ class MatrixAdapter(BasePlatformAdapter):
|
|||
return False
|
||||
|
||||
# If E2EE is enabled, load the crypto store.
|
||||
if self._encryption and hasattr(client, "olm"):
|
||||
if self._encryption and getattr(client, "olm", None):
|
||||
try:
|
||||
if client.should_upload_keys:
|
||||
await client.keys_upload()
|
||||
logger.info("Matrix: E2EE crypto initialized")
|
||||
except Exception as exc:
|
||||
logger.warning("Matrix: crypto init issue: %s", exc)
|
||||
elif self._encryption:
|
||||
logger.warning(
|
||||
"Matrix: E2EE requested but crypto store is not loaded; "
|
||||
"encrypted rooms may fail"
|
||||
)
|
||||
|
||||
# Register event callbacks.
|
||||
client.add_event_callback(self._on_room_message, nio.RoomMessageText)
|
||||
|
|
@ -230,6 +262,7 @@ class MatrixAdapter(BasePlatformAdapter):
|
|||
)
|
||||
# Build DM room cache from m.direct account data.
|
||||
await self._refresh_dm_cache()
|
||||
await self._run_e2ee_maintenance()
|
||||
else:
|
||||
logger.warning("Matrix: initial sync returned %s", type(resp).__name__)
|
||||
|
||||
|
|
@ -301,13 +334,48 @@ class MatrixAdapter(BasePlatformAdapter):
|
|||
relates_to["m.in_reply_to"] = {"event_id": reply_to}
|
||||
msg_content["m.relates_to"] = relates_to
|
||||
|
||||
resp = await self._client.room_send(
|
||||
chat_id,
|
||||
"m.room.message",
|
||||
msg_content,
|
||||
)
|
||||
async def _room_send_once(*, ignore_unverified_devices: bool = False):
|
||||
return await asyncio.wait_for(
|
||||
self._client.room_send(
|
||||
chat_id,
|
||||
"m.room.message",
|
||||
msg_content,
|
||||
ignore_unverified_devices=ignore_unverified_devices,
|
||||
),
|
||||
timeout=45,
|
||||
)
|
||||
|
||||
try:
|
||||
resp = await _room_send_once(ignore_unverified_devices=False)
|
||||
except Exception as exc:
|
||||
retryable = isinstance(exc, asyncio.TimeoutError)
|
||||
olm_unverified = getattr(nio, "OlmUnverifiedDeviceError", None)
|
||||
send_retry = getattr(nio, "SendRetryError", None)
|
||||
if isinstance(olm_unverified, type) and isinstance(exc, olm_unverified):
|
||||
retryable = True
|
||||
if isinstance(send_retry, type) and isinstance(exc, send_retry):
|
||||
retryable = True
|
||||
|
||||
if not retryable:
|
||||
logger.error("Matrix: failed to send to %s: %s", chat_id, exc)
|
||||
return SendResult(success=False, error=str(exc))
|
||||
|
||||
logger.warning(
|
||||
"Matrix: initial encrypted send to %s failed (%s); "
|
||||
"retrying after E2EE maintenance with ignored unverified devices",
|
||||
chat_id,
|
||||
exc,
|
||||
)
|
||||
await self._run_e2ee_maintenance()
|
||||
try:
|
||||
resp = await _room_send_once(ignore_unverified_devices=True)
|
||||
except Exception as retry_exc:
|
||||
logger.error("Matrix: failed to send to %s after retry: %s", chat_id, retry_exc)
|
||||
return SendResult(success=False, error=str(retry_exc))
|
||||
|
||||
if isinstance(resp, nio.RoomSendResponse):
|
||||
last_event_id = resp.event_id
|
||||
logger.info("Matrix: sent event %s to %s", last_event_id, chat_id)
|
||||
else:
|
||||
err = getattr(resp, "message", str(resp))
|
||||
logger.error("Matrix: failed to send to %s: %s", chat_id, err)
|
||||
|
|
@ -565,6 +633,9 @@ class MatrixAdapter(BasePlatformAdapter):
|
|||
getattr(resp, "message", resp),
|
||||
)
|
||||
await asyncio.sleep(5)
|
||||
continue
|
||||
|
||||
await self._run_e2ee_maintenance()
|
||||
except asyncio.CancelledError:
|
||||
return
|
||||
except Exception as exc:
|
||||
|
|
@ -573,6 +644,38 @@ class MatrixAdapter(BasePlatformAdapter):
|
|||
logger.warning("Matrix: sync error: %s — retrying in 5s", exc)
|
||||
await asyncio.sleep(5)
|
||||
|
||||
async def _run_e2ee_maintenance(self) -> None:
|
||||
"""Run matrix-nio E2EE housekeeping between syncs.
|
||||
|
||||
Hermes uses a custom sync loop instead of matrix-nio's sync_forever(),
|
||||
so we need to explicitly drive the key management work that sync_forever()
|
||||
normally handles for encrypted rooms.
|
||||
"""
|
||||
client = self._client
|
||||
if not client or not self._encryption or not getattr(client, "olm", None):
|
||||
return
|
||||
|
||||
tasks = [asyncio.create_task(client.send_to_device_messages())]
|
||||
|
||||
if client.should_upload_keys:
|
||||
tasks.append(asyncio.create_task(client.keys_upload()))
|
||||
|
||||
if client.should_query_keys:
|
||||
tasks.append(asyncio.create_task(client.keys_query()))
|
||||
|
||||
if client.should_claim_keys:
|
||||
users = client.get_users_for_key_claiming()
|
||||
if users:
|
||||
tasks.append(asyncio.create_task(client.keys_claim(users)))
|
||||
|
||||
for task in asyncio.as_completed(tasks):
|
||||
try:
|
||||
await task
|
||||
except asyncio.CancelledError:
|
||||
raise
|
||||
except Exception as exc:
|
||||
logger.warning("Matrix: E2EE maintenance task failed: %s", exc)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Event callbacks
|
||||
# ------------------------------------------------------------------
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue