Add /model list/add/remove/clear so a single provider profile can expose multiple switchable models in the TUI selector. Also add regression coverage for invalid grep regexes in the Python fallback.\n\nFixes #222\nRefs #218
When the LLM returns multiple tool calls in one response, query.py
executes them concurrently via asyncio.gather. If more than one tool
requires user confirmation, each concurrent _ask_permission call emits
its own modal_request event. The React frontend overwrites its modal
state on every modal_request (setModal), so only the last dialog is
ever shown to the user. The earlier futures never receive a response
and time out after 300 s, causing silent "Permission denied" errors.
This edge case was not addressed by the recent deadlock fix (69c85e4).
Fix: add _permission_lock (asyncio.Lock) to ReactBackendHost and wrap
_ask_permission with 'async with self._permission_lock'. Only one
permission dialog is live at a time; the next concurrent caller waits
until the current modal is resolved or timed out.
Add test_concurrent_ask_permission_are_serialised to verify that two
concurrent _ask_permission calls are serialised and both resolve correctly.
Co-authored-by: Copilot
A lightweight open-source Python implementation of the Agent Harness architecture.
44x lighter than Claude Code (11K vs 512K lines), 98% core tool coverage.
- 43 tools with Pydantic validation and parallel execution
- Skills system compatible with anthropics/skills (17+ tested)
- Plugin system compatible with claude-code/plugins (12+ tested)
- API retry with exponential backoff
- Multi-level permissions with path rules
- React/Ink TUI with "Oh my Harness!" branding
- 114 unit tests + 6 E2E test suites
- MIT License
tjb-tech