feat(pair-corpus-honesty): deterministic provenance fingerprint at scan time

Task 6.1.

- provenance.py: classify a checkout as human / agent / mixed / unknown
  from deterministic signals only (.claude/, AGENTS.md, Lovable meta,
  agent git trailers on a bounded commit sample); no model involved.
- cli scan runs a `provenance` stage; the manifest records the result.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
Claude-Session: https://claude.ai/code/session_01T7XD7x5KonMdmGRkp63EQG
This commit is contained in:
Marius Ciepluch
2026-09-05 10:45:43 +02:00
co-authored by Claude Fable 5.1
parent c0b9e41000
commit 25fa7aa7e1
4 changed files with 180 additions and 0 deletions
+3
View File
@@ -173,6 +173,7 @@ def write_manifest(
stages: dict[str, object] | None = None,
complexity: dict[str, object] | None = None,
worth_fixing: dict[str, object] | None = None,
provenance: dict[str, object] | None = None,
) -> None:
path.parent.mkdir(parents=True, exist_ok=True)
verification_by_id = _verification_by_id(verifications)
@@ -207,6 +208,8 @@ def write_manifest(
payload["complexity"] = complexity
if worth_fixing is not None:
payload["worth_fixing"] = worth_fixing
if provenance is not None:
payload["provenance"] = provenance
path.write_text(json.dumps(payload, indent=2, sort_keys=True) + "\n")