llm-ingestion-pipeline-secu.../tests
Kjell Tore Guttormsen 0af8f68cae feat(wiring): §6 bookends (prepare_input/screen_output) + full public API + README v0.1 (TDD)
Module 11 (final) — the top-level wiring. The library never makes the model call
(no SDK imported by the core), so the public surface is the toolkit plus two
library-side bookends around the caller's tool-less transform (Form 1, chosen
with the operator over an export-only toolkit and a full orchestrator — the
bookends fit existing pipelines with least friction, encode the two halves the
library can stand for, and impose no control flow):

- prepare_input(text, source=INPUT) -> PreparedInput(fenced, nonce, report):
  §6 steps 1-2, sanitize THEN fence (carrier can never smuggle a forged
  delimiter). Merged report carries both steps' findings; renders no disposition.
- screen_output(text, policy, *, provenance, transform_failed) -> DispositionResult:
  §6 steps 6-7, scan_output under guard() so a scanner error fails CLOSED
  (FAIL_SECURE, never a silent persist). transform_failed routes the compound
  forced-fallback rule.
- __all__ exports the full framework-agnostic surface: detectors, result types,
  disposition machinery + presets, contract asserters, the grounding seam.

Docs: README refreshed from the stale "brief / pre-implementation" line to a v0.1
alpha status with a Form-1 quickstart, the §6 adopt-this checklist, and an honest
-limitations section (structural unsolvability at the text layer; semantic
poisoning invisible to lexicon+entropy; text-only, no multimodal). CHANGELOG
seeded; CLAUDE.md remote/status lines corrected (remote IS set, no longer
brief-stage).

10 wiring tests (public surface, prepare_input compose, screen_output fail-closed
+ compound). 189 green (showcase + corpora follow).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HyRCQMocjZ6SmSQ6JidJ2k
2026-07-04 23:34:28 +02:00
..
test_contract.py feat(contract): tool-less + credential-allowlist + env-scoping quarantine asserters (TDD) [skip-docs] 2026-07-04 20:44:20 +02:00
test_disposition.py feat(disposition): source-trust + provenance gate — WARN|QUARANTINE|FAIL_SECURE, compound + fail-closed (TDD) [skip-docs] 2026-07-04 20:34:32 +02:00
test_entropy.py feat(entropy): high-entropy/encoded-blob detection with decode-and-rescan (TDD) 2026-07-04 09:43:24 +02:00
test_fence.py feat(fence): randomized unspoofable delimiter + attacker marker-strip (TDD) [skip-docs] 2026-07-04 18:23:35 +02:00
test_grounding.py feat(grounding): SourceGroundingCheck protocol + pass-through default — the semantic-poisoning seam (TDD) [skip-docs] 2026-07-04 22:44:41 +02:00
test_lexicon.py feat(lexicon): JSON injection lexicon + variant-set scan (TDD) [skip-docs] 2026-07-04 17:20:21 +02:00
test_neutralize.py feat(neutralize): opt-in pure defang of active-content output (TDD) [skip-docs] 2026-07-04 18:55:12 +02:00
test_output.py feat(output): report-only OUTPUT gate — compose + secret egress (TDD) [skip-docs] 2026-07-04 20:18:46 +02:00
test_report.py feat: scaffold package + report and sanitize modules (TDD) 2026-07-04 09:24:20 +02:00
test_sanitize.py feat: scaffold package + report and sanitize modules (TDD) 2026-07-04 09:24:20 +02:00
test_wiring.py feat(wiring): §6 bookends (prepare_input/screen_output) + full public API + README v0.1 (TDD) 2026-07-04 23:34:28 +02:00