Commit 0209ad5 moved `import lark_oapi as lark` inside the start()
method (lazy import) to suppress DeprecationWarnings. This had an
unintended side effect: the import now happens after the main asyncio
loop is already running, so lark_oapi's module-level
loop = asyncio.get_event_loop()
captures the running main loop. When the WebSocket thread then calls
loop.run_until_complete() inside Client.start(), Python raises:
RuntimeError: This event loop is already running
and the _connect/_disconnect coroutines are never awaited.
Fix: in run_ws(), create a fresh event loop with asyncio.new_event_loop(),
set it as the thread's current loop, and patch lark_oapi.ws.client.loop
to point to this dedicated loop before calling Client.start(). The loop
is closed on thread exit.
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Feishu's GetMessageResource API only accepts 'image' or 'file' as the
type parameter. When downloading voice messages, nanobot was passing
'audio' which caused the API to reject the request with an error.
This fix converts 'audio' to 'file' in _download_file_sync method
before making the API call, allowing voice messages to be downloaded
and transcribed successfully.
Fixes voice message download failure in Feishu channel.
- test_context_prompt_cache: Update test to reflect merged runtime
context and user message (commit ad99d5a merged them into one)
- Remove test_cron_commands.py: cron add CLI command was removed
in commit c05cb2e (unified scheduling via cron tool)
The OpenAI Codex provider accepts reasoning_effort but silently
discards it. Wire it through as {"reasoning": {"effort": ...}} in
the request body so the config option actually takes effect.
- test_context_prompt_cache: Update test to reflect merged runtime
context and user message (commit ad99d5a merged them into one)
- Remove test_cron_commands.py: cron add CLI command was removed
in commit c05cb2e (unified scheduling via cron tool)
ReadFileTool had no file size check — reading a multi-GB file would
load everything into memory and crash the process. Now:
- Rejects files over ~512KB at the byte level (fast stat check)
- Truncates at 128K chars with a notice if content is too long
- Guides the agent to use exec with head/tail/grep for large files
This matches the protection already in ExecTool (10KB) and
WebFetchTool (50KB).
datetime.fromisoformat(at) raises ValueError for malformed strings,
which propagated uncaught and crashed the tool execution. Now catches
ValueError and returns a user-friendly error message instead.
When the LLM returns malformed tool arguments (e.g. a list or string
instead of a dict), validate_params would crash with AttributeError
in _validate() when calling val.items(). Now returns a clear
validation error instead of crashing.
When a cron job fires, the agent processes the scheduled message and
has access to the cron tool. If the original message resembles a
scheduling instruction (e.g. "remind me in 10 seconds"), the agent
would call cron.add again, creating an infinite feedback loop.
Add a cron-context flag to CronTool that blocks add operations during
cron job execution. The flag is set before process_direct() and cleared
in a finally block to ensure cleanup even on errors.
Fixes#1441
Some LLM providers (Minimax, Dashscope) strictly reject consecutive
messages with the same role. build_messages() was emitting two separate
user messages back-to-back: the runtime context and the actual user
content.
Merge them into a single user message, handling both plain text and
multimodal (image) content. Update _save_turn() to strip the runtime
context prefix from the merged message when persisting to session
history.
Fixes#1414Fixes#1344
