[AZ-231] Add anchor verification gates

Co-authored-by: Cursor <cursoragent@cursor.com>

_docs/03_implementation/batch_08_cycle1_report.md

@@ -0,0 +1,35 @@
+# Batch Report
+
+**Batch**: 8
+**Tasks**: AZ-231_anchor_verification_matching
+**Date**: 2026-05-03
+
+## Task Results
+
+| Task | Status | Files Modified | Tests | AC Coverage | Issues |
+|------|--------|----------------|-------|-------------|--------|
+| AZ-231_anchor_verification_matching | Done | 4 files | Pass | 3/3 ACs covered | None |
+
+## AC Test Coverage: All covered
+
+| AC Ref | Coverage |
+|--------|----------|
+| AZ-231 AC-1 | `test_candidate_verification_emits_acceptance_evidence` verifies accepted decisions include MRE, inliers, homography, and reason metadata. |
+| AZ-231 AC-2 | `test_unsafe_candidate_is_rejected_with_reason` verifies unsafe/stale candidates are rejected without estimated pose. |
+| AZ-231 AC-3 | `test_matcher_benchmark_reports_profile_runtime_and_quality_metrics` verifies matcher profile runtime and quality metrics are reportable. |
+
+## Code Review Verdict: PASS
+
+Review report: `_docs/03_implementation/reviews/batch_08_review.md`
+
+## Auto-Fix Attempts: 0
+
+## Stuck Agents: None
+
+## Verification
+
+- `.venv/bin/python -m black --check src tests e2e/replay` passed.
+- `.venv/bin/python -m ruff check src tests e2e/replay` passed.
+- `.venv/bin/python -m pytest` passed: 45 tests.
+
+## Next Batch: AZ-232_safety_anchor_state_machine

_docs/03_implementation/reviews/batch_08_review.md

@@ -0,0 +1,53 @@
+# Code Review Report
+
+**Batch**: AZ-231_anchor_verification_matching
+**Date**: 2026-05-03
+**Verdict**: PASS
+
+## Findings
+
+No findings.
+
+## Review Scope
+
+- Task spec:
+  - `_docs/02_tasks/todo/AZ-231_anchor_verification_matching.md`
+- Changed files:
+  - `src/anchor_verification/__init__.py`
+  - `src/anchor_verification/interfaces.py`
+  - `src/anchor_verification/types.py`
+  - `tests/unit/test_anchor_verification.py`
+
+## Phase Notes
+
+### Spec Compliance
+
+- AZ-231 AC-1 is covered by `test_candidate_verification_emits_acceptance_evidence`.
+- AZ-231 AC-2 is covered by `test_unsafe_candidate_is_rejected_with_reason`.
+- AZ-231 AC-3 is covered by `test_matcher_benchmark_reports_profile_runtime_and_quality_metrics`.
+
+### Code Quality
+
+The implementation keeps evidence/result models in `types.py`, gate behavior in `interfaces.py`, and public exports in `__init__.py`. The benchmark path computes each verification result once and reports runtime/quality metrics per matcher profile.
+
+### Security Quick-Scan
+
+No network calls, shell execution, dynamic code execution, hardcoded secrets, or credential logging were introduced.
+
+### Performance Scan
+
+Anchor verification is request/trigger oriented and does not add a per-frame learned matcher loop. Benchmark reporting is bounded by the provided evidence tuple.
+
+### Cross-Task Consistency
+
+The verifier consumes `VprCandidate` outputs from Satellite Service and emits shared `AnchorDecision` DTOs for the later safety wrapper task.
+
+### Architecture Compliance
+
+Imports respect `_docs/02_document/module-layout.md`: Anchor Verification imports shared contracts only and does not reach into Satellite Service or Tile Manager internals.
+
+## Verification
+
+- `.venv/bin/python -m black --check src tests e2e/replay`
+- `.venv/bin/python -m ruff check src tests e2e/replay`
+- `.venv/bin/python -m pytest`

_docs/_autodev_state.md

@@ -9,6 +9,6 @@ tracker: jira
 sub_step:
   phase: 1
   name: batch-loop
-  detail: "batch 7: AZ-230_satellite_service_vpr_retrieval"
+  detail: "batch 8: AZ-231_anchor_verification_matching"
 retry_count: 0
 cycle: 1