feat(inbox): C2.5 — inbox hardening + SDK version guard (closes C-F7, C-N3, R-6)

- File-layer decision vocabulary (§4.2 set) with SKIP semantics — an unknown
  decision never reaches the store (C-F7, the review's run proof is the fixture)
- Fail-fast caps (max_files / max_rationale_chars) via InboxLimitError raised
  OUTSIDE the tolerant try — a cap breach is never swallowed as a skip
- R-6 id grammar (mirrors ingest _ID_RE) as a pydantic pattern on
  VerdictDocument.id AND re-checked in write_verdict, since model_copy(update=)
  bypasses model validation — traversal ids can no longer write outside the inbox
- promotion._filename_token: any sanitised id maps to a content hash — 'e/vil'
  can no longer clobber the distinct id 'evil' (restarbeid-funn 2)
- SDK pinned >=0.2.111,<0.3 + version guard test naming the sdk_client.py
  attribute premises; resolved 0.2.120, all premises re-verified against it
- sdk_client read loop bound offline with REAL SDK message types (R-4/R-5):
  text aggregation, error fail-paths, usage/cost extraction, _total_tokens
  fail-closed, non-positive budget guard
- test_sdk_isolation comment no longer claims the --system-prompt ""
  serialization the test body does not bind (honesty rule §1)

Guard-G2 assessment (guard-plan §4): the allowlist + caps + id grammar landed
here are G2's necessary part; an optional scan_output depth pass over
rationale (still a verbatim prose channel into the fold prompt, R-9) remains
relevant as a later additive session — the trigger picture is unchanged.

4 detach proofs red → restored green. Full gate: 389 passed (365→389),
ruff+format+mypy clean; golden + shared/ + runs/s10/ byte-untouched.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-07-16 20:26:41 +02:00
commit 80a2fa1a77
9 changed files with 441 additions and 35 deletions

View file

@ -203,6 +203,18 @@ class TestPathSafety:
assert not (tmp_path / "evil").exists()
assert "/" not in path.name and "\\" not in path.name
def test_sanitised_ids_never_collide_with_a_distinct_id_owning_the_name(
self, bundle: Path
) -> None:
# C2.5 restarbeid-funn 2: 'e/vil' used to sanitise to 'evil' — the
# SAME promoted filename as the distinct id 'evil', so the second
# promotion silently overwrote the first curated verdict.
first = _promote(_document(verdict_id="e/vil", rationale=f"one ({MARKER})"), bundle)
second = _promote(_document(verdict_id="evil", rationale=f"two ({MARKER})"), bundle)
assert first != second
assert parse_concept_file(first).frontmatter["verdict_id"] == "e/vil"
assert parse_concept_file(second).frontmatter["verdict_id"] == "evil"
def test_degenerate_token_falls_back_to_a_content_hash(self, bundle: Path) -> None:
path = _promote(_document(verdict_id="///"), bundle)
assert path.parent == bundle