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.
Adds `_validate_schedule_for_add()` to `CronService.add_job` so that
invalid or misplaced `tz` values are rejected before a job is persisted,
regardless of which caller (CLI, tool, etc.) invoked the service.
Surfaces the resulting `ValueError` in `nanobot cron add` via a
`try/except` so the CLI exits cleanly with a readable error message.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Replaces fragile input() hacks with robust prompt_toolkit.PromptSession
- Native support for multiline paste, history, and clean display
- Restores animated spinner in _thinking_ctx (now safe)
- Replaces boxed Panel with clean header for easier copying
- Adds prompt-toolkit dependency
- Adds new unit tests for input layer
