deerflow2/backend/packages/harness/deerflow/config
Xinmin Zeng 30d619de08
feat(subagents): support per-subagent skill loading and custom subagent types (#2253)
* feat(subagents): support per-subagent skill loading and custom subagent types (#2230)

Add per-subagent skill configuration and custom subagent type registration,
aligned with Codex's role-based config layering and per-session skill injection.

Backend:
- SubagentConfig gains `skills` field (None=all, []=none, list=whitelist)
- New CustomSubagentConfig for user-defined subagent types in config.yaml
- SubagentsAppConfig gains `custom_agents` section and `get_skills_for()`
- Registry resolves custom agents with three-layer config precedence
- SubagentExecutor loads skills per-session as conversation items (Codex pattern)
- task_tool no longer appends skills to system_prompt
- Lead agent system prompt dynamically lists all registered subagent types
- setup_agent tool accepts optional skills parameter
- Gateway agents API transparently passes skills in CRUD operations

Frontend:
- Agent/CreateAgentRequest/UpdateAgentRequest types include skills field
- Agent card displays skills as badges alongside tool_groups

Config:
- config.example.yaml documents custom_agents and per-agent skills override

Tests:
- 40 new tests covering all skill config, custom agents, and registry logic
- Existing tests updated for new get_skills_prompt_section signature

Closes #2230

* fix: address review feedback on skills PR

- Remove stale get_skills_prompt_section monkeypatches from test_task_tool_core_logic.py
  (task_tool no longer imports this function after skill injection moved to executor)
- Add key prefixes (tg:/sk:) to agent-card badges to prevent React key collisions
  between tool_groups and skills

* fix(ci): resolve lint and test failures

- Format agent-card.tsx with prettier (lint-frontend)
- Remove stale "Skills Appendix" system_prompt assertion — skills are now
  loaded per-session by SubagentExecutor, not appended to system_prompt

* fix(ci): sort imports in test_subagent_skills_config.py (ruff I001)

* fix(ci): use nullish coalescing in agent-card badge condition (eslint)

* fix: address review feedback on skills PR

- Use model_fields_set in AgentUpdateRequest to distinguish "field omitted"
  from "explicitly set to null" — fixes skills=None ambiguity where None
  means "inherit all" but was treated as "don't change"
- Move lazy import of get_subagent_config outside loop in
  _build_available_subagents_description to avoid repeated import overhead

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-04-23 23:59:47 +08:00
..
__init__.py Implement skill self-evolution and skill_manage flow (#1874) 2026-04-06 22:07:11 +08:00
acp_config.py feat(acp): add env field to ACPAgentConfig for subprocess env injection (#1447) 2026-03-27 20:03:30 +08:00
agents_api_config.py fix: disable custom-agent management API by default (#2161) 2026-04-14 00:03:38 +08:00
agents_config.py fix: validate bootstrap agent names before filesystem writes (#2274) 2026-04-16 08:36:42 +08:00
app_config.py fix: disable custom-agent management API by default (#2161) 2026-04-14 00:03:38 +08:00
checkpointer_config.py refactor: split backend into harness (deerflow.*) and app (app.*) (#1131) 2026-03-14 22:55:52 +08:00
extensions_config.py fix: unblock concurrent threads and workspace hydration (#1839) 2026-04-04 21:19:35 +08:00
guardrails_config.py feat(guardrails): add pre-tool-call authorization middleware with pluggable providers (#1240) 2026-03-23 18:07:33 +08:00
memory_config.py feat(memory): Introduce configurable memory storage abstraction (#1353) 2026-03-27 07:41:06 +08:00
model_config.py feat(config): add when_thinking_disabled support for model configs (#1970) 2026-04-09 18:49:00 +08:00
paths.py fix: unblock concurrent threads and workspace hydration (#1839) 2026-04-04 21:19:35 +08:00
sandbox_config.py fix: add output truncation to ls_tool to prevent context window overflow (#1896) 2026-04-06 15:09:57 +08:00
skill_evolution_config.py Implement skill self-evolution and skill_manage flow (#1874) 2026-04-06 22:07:11 +08:00
skills_config.py fix: unblock concurrent threads and workspace hydration (#1839) 2026-04-04 21:19:35 +08:00
stream_bridge_config.py feat(gateway): implement LangGraph Platform API in Gateway, replace langgraph-cli (#1403) 2026-03-30 16:02:23 +08:00
subagents_config.py feat(subagents): support per-subagent skill loading and custom subagent types (#2253) 2026-04-23 23:59:47 +08:00
summarization_config.py refactor: split backend into harness (deerflow.*) and app (app.*) (#1131) 2026-03-14 22:55:52 +08:00
title_config.py refactor: split backend into harness (deerflow.*) and app (app.*) (#1131) 2026-03-14 22:55:52 +08:00
token_usage_config.py feat: add configurable log level and token usage tracking (#1301) 2026-03-25 08:13:26 +08:00
tool_config.py refactor: split backend into harness (deerflow.*) and app (app.*) (#1131) 2026-03-14 22:55:52 +08:00
tool_search_config.py feat(tools): add tool_search for deferred MCP tool loading (#1176) 2026-03-17 20:43:55 +08:00
tracing_config.py feat(tracing): add optional Langfuse support (#1717) 2026-04-02 13:06:10 +08:00