Add reraise parameter to AgentHook so hooks can opt out of exception
swallowing in CompositeHook._for_each_hook_safe. _LoopHook sets
reraise=True to let its exceptions propagate. _LoopHookChain is removed
and replaced with CompositeHook([loop_hook] + extra_hooks).
Signed-off-by: Lingao Meng <menglingao@xiaomi.com>
When the Consolidator compresses old session messages into history.jsonl,
those messages are immediately removed from the LLM's context. Dream
processes history.jsonl into long-term memory (memory.md) on a cron
schedule (default every 2h), creating a window where compressed content
is invisible to the LLM.
This change closes the gap by injecting unprocessed history entries
(history.jsonl entries not yet consumed by Dream) directly into the
system prompt as "# Recent History".
Key design notes:
- Uses read_unprocessed_history(since_cursor=last_dream_cursor) so only
entries not yet reflected in long-term memory are included, avoiding
duplication with memory.md
- No overlap with session messages: Consolidator advances
last_consolidated before returning, so archived messages are already
removed from get_history() output
- Token-safe: Consolidator's estimate_session_prompt_tokens calls
build_system_prompt via the same build_messages function, so the
injected entries are included in token budget calculations and will
trigger further consolidation if needed
Signed-off-by: Lingao Meng <menglingao@xiaomi.com>
When an agent task is cancelled (e.g. via /stop), the ExecTool was only
handling TimeoutError but not CancelledError. This left the child process
running as an orphan. Now CancelledError also triggers process.kill() and
waitpid cleanup before re-raising.
The test test_openai_compat_strips_message_level_reasoning_fields was
added in fbedf7a and incorrectly asserted that reasoning_content and
extra_content should be stripped from messages. This contradicts the
intent of b5302b6 which explicitly added these fields to _ALLOWED_MSG_KEYS
to preserve them through sanitization.
Rename the test and fix assertions to match the original design intent:
reasoning_content and extra_content at message level should be preserved,
and extra_content inside tool_calls should also be preserved.
Signed-off-by: Lingao Meng <menglingao@xiaomi.com>
reasoning_content and extra_content were accidentally dropped from
_ALLOWED_MSG_KEYS.
Also fix session/manager.py to include reasoning_content when building
LLM messages from session history, so the field is not lost across
turns.
Without this fix, providers such as Kimi, emit reasoning_content in
assistant messages will have it stripped on the next request, breaking
multi-turn thinking mode.
Fixes: https://github.com/HKUDS/nanobot/issues/2777
Signed-off-by: Lingao Meng <menglingao@xiaomi.com>
Add regression tests for the non-streaming (_parse dict branch) and
streaming (_parse_chunks dict and SDK-object branches) paths that extract
reasoning_content, ensuring the field is populated when present and None
when absent.
Signed-off-by: Lingao Meng <menglingao@xiaomi.com>
Extract reasoning_content from both non-streaming and streaming responses
in OpenAICompatProvider. Accumulate chunks during streaming and merge into
LLMResponse, enabling reasoning chain display for models like MiMo and DeepSeek-R1.
Signed-off-by: Lingao Meng <menglingao@xiaomi.com>
Register xiaomi_mimo as an OpenAI-compatible provider with its API base URL,
add xiaomi_mimo to the provider config schema, and document it in README.
Signed-off-by: Lingao Meng <menglingao@xiaomi.com>
Lingao MengandXubin Ren