Merge the latest main branch into the Telegram media filename fix and keep the file_unique_id-based download path on top of the refactored media handling and newer Telegram tests.
Made-with: Cursor
- test_channel_plugins: fix assertion logic for discoverable channels
- test_filesystem_tools: normalize path separators for Windows
- test_tool_validation: use python to generate output, avoid cmd line limits
- Require both history_entry and memory_update, reject null/empty values
- Fallback to tool_choice=auto when provider rejects forced function call
- After 3 consecutive consolidation failures, raw-archive messages to
HISTORY.md without LLM summarization to prevent context window overflow
Some providers (e.g. Dashscope in thinking mode) reject object-style
tool_choice with "does not support being set to required or object".
Retry once with tool_choice="auto" instead of failing silently.
Made-with: Cursor
- nanobot/channels/matrix.py: Add keyword-only parameters restrict_to_workspace/workspace to MatrixChannel.__init__ and assign them to _restrict_to_workspace/_workspace with proper type conversion and path resolution
- tests/test_commands.py: Add _strip_ansi() function to remove ANSI escape codes, use regex assertions for --workspace/--config parameters to allow 1 or 2 dashes
Fix issue #1834: Spawn/subagent tool fails with Deepseek Reasoner
due to missing reasoning_content field when using thinking mode.
The subagent was not including reasoning_content and thinking_blocks
in assistant messages with tool calls, causing the Deepseek API to
reject subsequent requests.
- Add reasoning_content to assistant message when subagent makes tool calls
- Add thinking_blocks to assistant message for Anthropic extended thinking
- Add tests to verify both fields are properly passed
Fixes#1834
Share assistant message construction between the main agent and subagents, and add a regression test to keep reasoning_content and thinking_blocks in follow-up tool rounds.
Move consolidation policy into MemoryConsolidator, keep backward compatibility for legacy config, and compress history by token budget instead of message count.
