- 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)
- 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)
Feishu rejects interactive cards that contain more than one table element
(API error 11310: card table number over limit).
Add FeishuChannel._split_elements_by_table_limit() which partitions the flat
card-elements list into groups of at most one table each. The send() method
now iterates over these groups and sends each as its own card message, so all
tables are delivered to the user instead of the entire message being dropped.
Single-table and table-free messages are unaffected (one card, same as before).
Fixes#1382
A refactoring in commit 132807a introduced a regression where the final
response was silently discarded whenever the message tool was used,
regardless of the target. This restored the original logic from PR #832
that only suppresses the final reply when the message tool sends to the
same (channel, chat_id) as the original message.
Changes:
- message.py: Replace _sent_in_turn: bool with _turn_sends: list[tuple]
to track actual send targets, add get_turn_sends() method
- loop.py: Check if (msg.channel, msg.chat_id) is in sent_targets before
suppressing final reply. Also move the "Response to" log after the
suppress check to avoid misleading logs.
- Add unit tests for the suppress logic
This ensures:
- Email sent via message tool → Feishu still gets confirmation
- Message tool sends to same Feishu chat → No duplicate (suppressed)
HeartbeatService was refactored from free-text HEARTBEAT_OK token
matching to a structured two-phase design (LLM tool call for
skip/run decision, then execution). The tests still used the old
on_heartbeat callback constructor and HEARTBEAT_OK_TOKEN import.
- Remove obsolete test_heartbeat_ok_detection test
- Update test_start_is_idempotent to use new provider+model constructor
- Add tests for _decide() skip path, trigger_now() run/skip paths
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- SubagentManager tracks _session_tasks: session_key -> {task_id, ...}
- cancel_by_session() cancels all subagents for a session
- SpawnTool passes session_key through to SubagentManager
- /stop response reports subagent cancellation count
- Cleanup callback removes from both _running_tasks and _session_tasks
Builds on #1179
- Add commands.py with CommandDef registry, parse_command(), get_help_text()
- Refactor run() to dispatch messages as asyncio tasks (non-blocking)
- /stop is an 'immediate' command: handled inline, cancels active task
- Global processing lock serializes message handling (safe for shared state)
- _pending_tasks set prevents GC of dispatched tasks before lock acquisition
- _dispatch() registers/clears active tasks, catches CancelledError gracefully
- /help now auto-generated from COMMANDS registry
Closes#849
Previously, `autoReplyEnabled=false` would block ALL email sends,
including proactive emails triggered from other channels (e.g., asking
nanobot on Feishu to send an email).
Now `autoReplyEnabled` only controls automatic replies to incoming
emails, not proactive sends. This allows users to disable auto-replies
while still being able to ask nanobot to send emails on demand.
Changes:
- Check if recipient is in `_last_subject_by_chat` to determine if
it's a reply
- Only skip sending when it's a reply AND auto_reply_enabled is false
- Add test for proactive send with auto_reply_enabled=false
- Update existing test to verify reply behavior
Fixes#1042. When the LLM returns tool call arguments as a dict or
JSON string instead of parsed values, memory consolidation would fail
with "TypeError: data must be str, not dict".
Changes:
- Add type guard in MemoryStore.consolidate() to parse string arguments
and reject unexpected types gracefully
- Add regression tests covering dict args, string args, and edge cases
Propagate Matrix thread metadata from inbound events and attach
m.relates_to
(rel_type=m.thread, m.in_reply_to, is_falling_back=true) to outbound
messages
including attachments. Add tests for thread metadata and thread replies.
- extend message tool with optional media paths for channel delivery
- switch Matrix uploads to stream providers and handle encrypted-room payloads
- add/expand tests for message tool media forwarding and Matrix upload edge cases
- Replaces the explicit media event tuple with MATRIX_MEDIA_EVENT_FILTER
based on
media base classes: (RoomMessageMedia, RoomEncryptedMedia).
- Keeps MatrixMediaEvent as the static typing alias for media-specific
handlers.
- Removes MatrixInboundEvent and uses RoomMessage in mention-related
logic.
- Adds regression tests for:
- callback registration using MATRIX_MEDIA_EVENT_FILTER
- ensuring RoomMessageText is not matched by the media filter.
