When /background was sent during an active run, it was not in the
platform adapter's bypass list and fell through to the interrupt path
instead of spawning a parallel background task.

Add "background" to the active-session command bypass in the platform
adapter, and add an early return in the gateway runner's running-agent
guard to route /background to _handle_background_command() before it
reaches the default interrupt logic.

Fixes #6827

Adds a regression test verifying that /background bypasses the
active-session guard in the platform adapter, matching the existing
test pattern for /stop, /new, /approve, /deny, and /status.

…am and Feishu

Python assertions are stripped when running with `python -O` (optimized
mode), making them unsuitable for runtime error handling.

1. `telegram_network.py:113` — After exhausting all fallback IPs, the code
   uses `assert last_error is not None` before `raise last_error`. In
   optimized mode, the assert is skipped; if `last_error` is unexpectedly
   None, `raise None` produces a confusing `TypeError` instead of a
   meaningful error. Replace with an explicit `if` check that raises
   `RuntimeError` with a descriptive message.

2. `feishu.py:975` — The `_configure_with_overrides` closure uses
   `assert original_configure is not None` as a guard. While the outer
   scope only installs this closure when `original_configure` is not None,
   the assert would silently disappear in optimized mode. Replace with an
   explicit `if` check for defensive safety.

- configure Telegram HTTPXRequest pool/timeouts with env-overridable defaults\n- use separate request/get_updates request objects to reduce pool contention\n- skip fallback-IP transport when proxy is configured (or explicitly disabled)\n\nThis mitigates recurrent pool-timeout failures during polling reconnect/bootstrap (delete_webhook).

Platforms that don't return a message_id after the first send (Signal,
GitHub webhooks) were causing GatewayStreamConsumer to re-enter the
"first send" path on every tool boundary, posting one platform message
per tool call (observed as 155 PR comments on a single response).

Fix: treat _message_id == "__no_edit__" as a sentinel meaning "platform
accepted the send but cannot be edited". When a tool boundary arrives
in that state, skip the message_id/accumulated/last_sent_text reset so
all continuation text is delivered once via _send_fallback_final rather
than re-posted per segment.

Also make prompt_toolkit imports in hermes_cli/commands.py optional so
gateway and test environments that lack the package can still import
resolve_command, gateway_help_lines, and COMMAND_REGISTRY.

- test_background_autocompletes: pytest.importorskip("prompt_toolkit")
  so the test skips gracefully where the CLI dep is absent

- test_run_agent_progress_stays_in_originating_topic: update stale emoji
  💻 → ⚙️ to match get_tool_emoji("terminal", default="⚙️") in run.py

- test_internal_event_bypass{_authorization,_pairing}: mock
  _handle_message_with_agent to raise immediately; avoids the 300s
  run_in_executor hang that caused the tests to time out