mptyl/ThothII
1
0
Fork 0
Code Issues 25 Pull Requests Actions Packages Projects Releases 1 Wiki Activity

fix(evidence): distinguish implicit corpus ownership

Browse Source
This commit is contained in:
marcopan
2026-07-12 05:59:13 +02:00
parent 6bb158233f
commit 950f88f23e
2 changed files with 13 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.superpowers/sdd/evidence-task-5c-report.md
+7
View File
@@ -135,3 +135,10 @@ run reached unrelated Task 6 immutable-file tamper tests; those files were delib
manifest, and that mismatched job, GC, and search paths perform no vector/filesystem mutations. manifest, and that mismatched job, GC, and search paths perform no vector/filesystem mutations.
Focused workspace-binding, search-pack, preprocess JSON, and scoped Ruff/diff tests pass. Focused workspace-binding, search-pack, preprocess JSON, and scoped Ruff/diff tests pass.
Compatibility follow-up: direct/internal `CorpusPipeline` instances now distinguish an omitted
workspace identity from an explicit config/job identity. An unbound instance adopts the persisted
ACTIVE owner (or `default` only for a brand-new direct corpus), preserving safe resume/GC tests and
the real pgvector lifecycle. Explicit config/job identities still fail closed on any mismatch. The
two reported regressions, workspace mismatch guards, real Docker lifecycle, scoped Ruff/diff, and
the full harness suite all pass.
harness/tht/corpus/pipeline.py
+6 -1
View File
@@ -70,7 +70,7 @@ class CorpusPipeline:
self, *, store: CorpusStore, sources: list[EvidenceSource], embedder, self, *, store: CorpusStore, sources: list[EvidenceSource], embedder,
vector_store: VectorStore, embedding_model: str, embedding_dimensions: int, vector_store: VectorStore, embedding_model: str, embedding_dimensions: int,
chunk_policy: ChunkPolicy, pipeline_version: str, retain_published_generations: int = 3, chunk_policy: ChunkPolicy, pipeline_version: str, retain_published_generations: int = 3,
workspace_id: str = "default", workspace_id: str | None = None,
) -> None: ) -> None:
self.store = store self.store = store
self.sources = sources self.sources = sources
@@ -88,8 +88,13 @@ class CorpusPipeline:
def _assert_workspace_binding(self) -> None: def _assert_workspace_binding(self) -> None:
manifest = self.store.active_manifest() manifest = self.store.active_manifest()
if manifest is None: if manifest is None:
if self.workspace_id is None:
self.workspace_id = "default"
return return
persisted = manifest.metadata.get("workspace_id") persisted = manifest.metadata.get("workspace_id")
if self.workspace_id is None and isinstance(persisted, str):
self.workspace_id = persisted
return
if persisted != self.workspace_id: if persisted != self.workspace_id:
raise PipelineError( raise PipelineError(
"corpus belongs to a different workspace; use a new corpus root or explicit rebuild" "corpus belongs to a different workspace; use a new corpus root or explicit rebuild"