feat(rag): summarize single-document folders (MIN_DOCS_PER_FOLDER 2 → 1)
Relax the phase-94 folder-summary scope rule from ≥ 2 documents to ≥ 1: a folder (or source root) is a candidate while ANY document lives under it, so single-file folders and single-file source roots get their own lite-written description. A row is now pruned only when its folder loses its last document (vanishes from the catalogue). The constant is the single source of truth, so the flip propagates to the generator's candidate set, the prune pass, the missing_folder_summaries gap probe (the next sync self-heals the new gaps), and the KB-tree summary_pending markers (1-doc folders / sources now read "Summary pending" until their row lands). Docstrings/comments across app/, scripts/import_docs.py, and the E2E fixtures updated to the ≥ 1 wording. Unit + integration tests updated to the new semantics (the pruned-below-minimum scenario is now a folder losing its LAST doc; single-doc folders are pinned as candidates/pending). Full suite: 2314 passed, app coverage 99%; ruff + pyright clean; folder-summary E2E stories pass in isolation (ls_tree_drilldown, sync_summary_visibility, kb_tree, kb_tree_nav, document_dates, oneshot_llm_retry).
This commit is contained in:
+10
-8
@@ -576,7 +576,7 @@ def build_kb_tree(
|
||||
* **Pending** — ``summary_pending`` on the SOURCE and every FOLDER
|
||||
node (phase 98, decision D3 — ONE concept): true iff the node's
|
||||
recursive ``documents`` count ≥
|
||||
:data:`app.rag.folder_summaries.MIN_DOCS_PER_FOLDER` (2) AND it
|
||||
:data:`app.rag.folder_summaries.MIN_DOCS_PER_FOLDER` (1) AND it
|
||||
has NO stored ``folder_summaries`` row (AI or manual — any row;
|
||||
the builder sees stored rows only). That is EXACTLY
|
||||
:func:`app.rag.folder_summaries.missing_folder_summaries`'s
|
||||
@@ -584,9 +584,10 @@ def build_kb_tree(
|
||||
keys on the next sync — the marker is honest: "waiting to
|
||||
generate", and the integration cross-check pins the tree's
|
||||
pending set to that function so the marker can never drift from
|
||||
the gap-fill). A < 2-document folder is NEVER pending (it never
|
||||
gets a summary — its one file line IS its description), and a
|
||||
registered 0-document source never is.
|
||||
the gap-fill). A 0-document folder cannot exist (a folder is a
|
||||
catalogue prefix only) — every existing folder with no row is
|
||||
pending, single-file folders included — and a registered
|
||||
0-document source never is.
|
||||
|
||||
ONE concept end to end: the builder reuses
|
||||
:func:`app.rag.folder_summaries.folder_of` and the phase-94
|
||||
@@ -674,10 +675,11 @@ def list_kb_tree(
|
||||
exactly as ``app/api/chat.py`` does) + the SAME outerjoin/grouped
|
||||
catalogue query ``GET /api/docs`` runs (the document ``id``
|
||||
excluded — the tree has no document ids) + ALL stored
|
||||
``folder_summaries`` rows (a bounded select — one row per ≥ 2-doc
|
||||
folder; rows for sources the tree does not list are never
|
||||
referenced by the builder) — through the pure
|
||||
:func:`build_kb_tree`. ``GET /api/docs`` itself is untouched.
|
||||
``folder_summaries`` rows (a bounded select — one row per
|
||||
existing folder at the ≥ 1-doc rule; rows for sources the tree
|
||||
does not list are never referenced by the builder) — through the
|
||||
pure :func:`build_kb_tree`. ``GET /api/docs`` itself is
|
||||
untouched.
|
||||
"""
|
||||
names = list_source_names(db)
|
||||
rows = db.execute(
|
||||
|
||||
Reference in New Issue
Block a user