feat(ai_review): per-PR merge confidence 1-5 in header

tests/pilot/test_ai_review.py

@@ -11,6 +11,7 @@ sys.path.insert(0, os.path.join(ROOT, "pilot"))
 
 import ai_review  # noqa: E402
 from ai_review import (  # noqa: E402
+    _CONFIDENCE_BADGE,
     _SEVERITY_EMOJI,
     _balanced_json_substring,
     _extract_first_json_object,
@@ -24,6 +25,7 @@ from ai_review import (  # noqa: E402
     fmt_tokens,
     format_review_body,
     inline_comment_body,
+    merge_confidence,
     parse_diff_anchors,
     parse_findings,
     parse_repo_config,
@@ -31,6 +33,7 @@ from ai_review import (  # noqa: E402
     parse_text_blocks,
     prior_review_bodies,
     reviewed_shas,
+    REVIEW_HEADER,
     SEVERITIES,
     SEVERITY_RANK,
     split_findings,
@@ -1821,3 +1824,78 @@ def test_parse_repo_config_compare_against_caps_at_12(monkeypatch):
     assert "fake-model-13" not in cfg["compare_against"]
     assert "bogus-extra" not in cfg["compare_against"]
 
+
+# ---------------------------------------------------------------------------
+# Task 6 — merge_confidence + REVIEW_HEADER confidence badge
+# ---------------------------------------------------------------------------
+
+
+def test_merge_confidence_clean_is_five():
+    assert merge_confidence([]) == 5
+
+
+def test_merge_confidence_only_low_is_five():
+    f = {"severity": "low"}
+    assert merge_confidence([f, f, f]) == 5
+
+
+def test_merge_confidence_medium_drops_one():
+    f = {"severity": "medium"}
+    assert merge_confidence([f]) == 4
+
+
+def test_merge_confidence_high_drops_two():
+    f = {"severity": "high"}
+    assert merge_confidence([f]) == 3
+
+
+def test_merge_confidence_critical_drops_to_one():
+    f = {"severity": "critical"}
+    assert merge_confidence([f]) == 1
+
+
+def test_merge_confidence_multi_lens_drops_extra():
+    f = {"severity": "low", "_multi_lens": True}
+    assert merge_confidence([f]) == 4
+
+
+def test_merge_confidence_clamped():
+    # Three critical findings must NOT take the score below 1.
+    f = {"severity": "critical"}
+    assert merge_confidence([f, f, f]) == 1
+
+
+def test_review_header_includes_confidence():
+    # REVIEW_HEADER gains a {confidence} placeholder; verify the format works.
+    h = REVIEW_HEADER.format(model="glm-5.2:cloud", sha="abc1234567", confidence="3/5 🟡")
+    assert "Merge confidence: 3/5 🟡" in h
+
+
+def test_confidence_badge_table_complete():
+    # Sanity-check the badge table the render layer reads from.
+    assert _CONFIDENCE_BADGE == {5: "🟢", 4: "🟢", 3: "🟡", 2: "🟠", 1: "🔴"}
+
+
+def test_format_review_body_default_confidence_is_green():
+    # Default confidence kwarg should produce a green 5/5 badge in the header,
+    # matching the pre-existing "clean PR" semantics.
+    body = format_review_body("- [high] x:1 — bug", "glm-5.2:cloud", "abcdef1234567890")
+    assert "Merge confidence: 5/5 🟢" in body
+
+
+def test_format_review_body_low_confidence_shows_red_badge():
+    body = format_review_body(
+        "- [critical] x:1 — bug", "glm-5.2:cloud", "abcdef1234567890",
+        confidence=1,
+    )
+    assert "Merge confidence: 1/5 🔴" in body
+
+
+def test_format_review_body_confidence_clamps_out_of_range():
+    # Out-of-range confidence is clamped to [1, 5] in the badge string.
+    body_hi = format_review_body("- x", "glm-5.2:cloud", "abcdef1234567890", confidence=99)
+    assert "Merge confidence: 5/5 🟢" in body_hi
+    body_lo = format_review_body("- x", "glm-5.2:cloud", "abcdef1234567890", confidence=0)
+    assert "Merge confidence: 1/5 🔴" in body_lo
+
+