fix(evidence): enforce active vector generations

This commit is contained in:
2026-07-12 04:33:07 +02:00
parent b96d4f13b9
commit 981b149249
15 changed files with 261 additions and 23 deletions
+38
View File
@@ -3,6 +3,44 @@
from tht.corpus.store import CorpusStore
class ActiveEvidenceSearcher:
"""Searcher facade that enforces ACTIVE generation predicates before LIMIT."""
def __init__(self, corpus: CorpusStore, delegate):
self.corpus = corpus
self.delegate = delegate
def search(self, embedding, top_n=10, kinds=None, metadata_filter=None):
if kinds != ["evidence"]:
return self.delegate.search(embedding, top_n=top_n, kinds=kinds)
manifest = self.corpus.active_manifest()
if manifest is None:
return []
by_generation: dict[str, list[str]] = {}
mapping = dict(manifest.metadata.get("document_generations", {}))
for document in manifest.documents:
generation = mapping.get(document.document_id, manifest.vector_generation)
if generation:
by_generation.setdefault(generation, []).append(document.document_id)
hits = []
for generation, document_ids in by_generation.items():
hits.extend(self.delegate.search(
embedding, top_n=top_n, kinds=["evidence"],
metadata_filter={
"vector_generation": generation,
"document_ids": document_ids,
},
))
return sorted(hits, key=lambda hit: (-hit.similarity, hit.id))[:top_n]
def active_searcher(cfg, delegate):
corpus_root = cfg.paths.artifacts.parent / "corpus"
if not corpus_root.exists():
return delegate
return ActiveEvidenceSearcher(CorpusStore(corpus_root), delegate)
def active_evidence_hits(store: CorpusStore, vector_store, embedding, *, limit: int):
manifest = store.active_manifest()
if manifest is None or manifest.vector_generation is None: