Removed the now-dead node-based pydantic-ai orchestrator/tool-dispatcher stack after switching the request loop to consume tinyagent events directly. This reduces complexity and prevents accidental re-introduction of the legacy execution path.
Refactored RequestOrchestrator._run_stream() into small event-specific handlers to satisfy Ruff complexity gates.
Behavioral Impact
Tool execution and streaming are now exclusively driven by tinyagent event handling.
No backward-compatibility is provided for orchestrator-specific internals/tests.
Related Cards
[[tinyagent-migration]]
1---2name: 2372-2026-02-07-remove-orchestrator-tool-dispatcher-ab61bb203description: Summary4---56## Summary78Removed the now-dead node-based pydantic-ai orchestrator/tool-dispatcher stack after switching the request loop to consume tinyagent events directly. This reduces complexity and prevents accidental re-introduction of the legacy execution path.910## Changes1112- Deleted `src/tunacode/core/agents/agent_components/orchestrator/` (tool dispatcher, usage tracker, node processor).13- Simplified exports:14 - `src/tunacode/core/agents/agent_components/__init__.py`15 - `src/tunacode/core/agents/__init__.py`16- Removed legacy tests that only validated the deleted orchestrator behavior:17 - `tests/integration/tools/test_tool_dispatcher_coverage.py`18 - `tests/integration/core/test_tool_call_lifecycle.py`19 - `tests/unit/core/test_usage_tracker.py`20- Refactored `RequestOrchestrator._run_stream()` into small event-specific handlers to satisfy Ruff complexity gates.2122## Behavioral Impact2324- Tool execution and streaming are now exclusively driven by tinyagent event handling.25- No backward-compatibility is provided for orchestrator-specific internals/tests.2627## Related Cards2829- [[tinyagent-migration]]
Run npx skillmds@latest add tools-only/2372-2026-02-07-remove-orchestrator-tool-dispatcher-ab61bb20 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Summary It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
tools-only (@tools-only) published this skill. Their other Agent Skills are listed on their SkillMD profile.
tools-only