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。
ingest-l0【开发与工程】L0 bootstrap of the abap_wiki knowledge base: creates stubs for all custom objects from the TADIR. Use this skill to initialize the repo from scratch or to ingest a new TADIR export. Deterministic operations (no LLM sub-agent), idempotent.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Creates (or updates) the L0 stub for every custom object in the TADIR. Everything is
deterministic: no sub-agents, parallelism via devclass partitioning.
State lives in state/abap_wiki.db (see core/docs/01-pipeline-l0-l1.md).
raw/tadir/TADIR_Z_<YYYYMMDD>.XLSX.Shortcut:
python core/src/tools/pipeline.py l0-runruns steps 1-6 as a single deterministic command (newest TADIR inraw/tadir/or--file). The step-by-step procedure below remains the reference for diagnostics.
All commands must be run from the repo root with the venv active.
python core/src/tools/pipeline.py init-db
python core/src/tools/pipeline.py import-tadir --file raw/tadir/<most recent TADIR>.XLSX
python core/src/tools/pipeline.py resolve-sources
python core/src/tools/pipeline.py ingest-l0 # all
python core/src/tools/pipeline.py ingest-l0 --partition ZPACKAGE # one package
Idempotent: re-running on an already-processed package is a no-op.python core/src/tools/pipeline.py enqueue-l1
python core/src/tools/pipeline.py progress
python core/src/tools/pipeline.py export-excel
python core/src/tools/pipeline.py git-commit --message "ingest L0: <export>"
raw/ (only the user stages it when updating the export).abap_wiki/_packages/, abap_wiki/index.md) are regenerated from queries: do not edit them manually.tadir-<x> and listed
in output/reports/unknown-tadir-types.md (non-blocking).