feat: add skill and assistant knowledge bases

This commit is contained in:
Administrator committed 2026-09-02 00:49:13 +08:00
1 parent dd0ee282df
commit fbd8dec48f
45 files changed
+5262 -21

No files matched your search

@@ -1619,3 +1619,27 @@ write, log the exception, complete the rewrite with
`versionSnapshotFailed: true`, and do not emit a user-facing failure or restore
the original. The sandbox uses that signal only to enable its ordinary manual
save fallback.
## Skill/assistant knowledge invariants
Skill distillation is implemented in `deerflow.skill_knowledge` and
`deerflow.persistence.skill_knowledge`; the single native assistant base is in
`deerflow.assistant_knowledge` and
`deerflow.persistence.assistant_knowledge`. Gateway composition, remote adapters,
the lease dispatcher, watcher/scheduler, and APIs remain in `app.gateway` so the
harness-to-app import firewall is preserved.
Never execute a skill or read/upload/summarize its code and script files.
Knowledge fingerprints exclude those files and Markdown code fences. All
resyncs must stage and validate the knowledge digest before activation; the old
snapshot remains authoritative on failure. A binding may have only one active
item (`active_dedupe_key` plus atomic lease claims). Detach/delete operates on
source contributions, not canonical rows, and shared entities/relations are
retired only when their final contribution is gone.
There is exactly one global assistant base (`知识梳理`). Ordinary users have
read/search access and administrators own all mutations. WeKnora direct graph
writes require `llmwiki.weknora.graph.direct_write_enabled`, backend-only
credentials, and the fixed parameterized templates in
`deerflow.skill_knowledge.graph_writer`; never accept Cypher from an API, model,
skill, or frontend.