协作头脑风暴
brainstorming
在实现前澄清需求、探索设计选择,并形成清晰的开发方向。
platform-pipeline-provider【开发与工程】Develop and debug LangBot platform adapters, HTTP Bot callbacks, message aggregation, pipeline stages, provider runners, model managers, local agent tools, and tool-loading workflows.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Use this sub-skill for message flow, IM platform adapters, HTTP Bot and WebSocket chat behavior, pipeline stages, providers/runners, model manager, local agent, and tool manager issues.
RuntimeBot applies routing rules and pushes messages to aggregation.MessageAggregator collapses N-to-1 bursts by session.Controller schedules Query work subject to concurrency.RuntimePipeline executes configured stages.Keep vendor translation inside the adapter. Do not put LLM provider logic or pipeline business rules inside platform code. Add or update manifests, config schemas, icons/assets, i18n strings, docs, and focused adapter tests.
Start with fake provider/tool tests before using real API keys. If plugin,
Box, native, or stdio MCP tools are involved, route deep runtime details to
plugin-box-skills after confirming the provider/tool manager boundary.
Use scripts/http_bot_hmac_helper.py for self-contained HTTP Bot HMAC signing, verification, payload building, and optional signed POSTs. It adapts the public example client into a skill-owned helper and does not depend on the original checkout.
python scripts/select_langbot_checks.py pipeline
uv run pytest tests/smoke/test_fake_message_flow.py -q --tb=short
uv run pytest tests/integration/pipeline/test_full_flow.py -q --tb=short
uv run pytest tests/unit_tests/platform/test_http_bot_tenancy.py -q --tb=short
uv run pytest tests/unit_tests/provider/test_tool_manager.py -q --tb=short