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

pilot/ai_review.py

@@ -58,7 +58,7 @@ import urllib.error
 import urllib.parse
 import urllib.request
 
-REVIEW_HEADER = "🤖 **AI Review** · pragent pilot · {model} · `{sha}`"
+REVIEW_HEADER = "🤖 **AI Review** · pragent pilot · {model} · `{sha}` · Merge confidence: {confidence}"
 # Hidden marker the dedupe pass scans for. Full sha so a re-push (new sha) is
 # never mistaken for an already-reviewed commit, and a label-toggle (same sha)
 # is correctly skipped.
@@ -225,6 +225,44 @@ def _int_env(name: str, default: int) -> int:
         return default
 
 
+# 1-5 merge-verdict score (higher = safer). Buckets:
+#   5 = clean (or low/info/trivial only — nothing worth blocking on)
+#   4 = medium present
+#   3 = high present (operator should at least look)
+#   1 = critical present (block the merge by default)
+# Cross-lens agreement on any finding takes one more off, floored at 1.
+_CONFIDENCE_BADGE = {5: "🟢", 4: "🟢", 3: "🟡", 2: "🟠", 1: "🔴"}
+
+
+def merge_confidence(findings: list[dict]) -> int:
+    """1-5 merge verdict: higher = safer.
+
+    Tier drops driven by the most severe finding present:
+      - critical  → 1
+      - high      → 3
+      - medium    → 4
+      - else      → 5 (low / trivial / info / unknown → no drop)
+
+    An extra -1 when ANY finding carries ``_multi_lens`` (cross-lens agreement
+    bumps confidence in the signal — penalise harder). The final score is
+    clamped to [1, 5] so a critical + multi_lens combo doesn't go negative.
+    """
+    if not findings:
+        return 5
+    max_rank = max(SEVERITY_RANK.get(f.get("severity", "low"), 0) for f in findings)
+    if max_rank >= SEVERITY_RANK["critical"]:
+        score = 1
+    elif max_rank >= SEVERITY_RANK["high"]:
+        score = 3
+    elif max_rank >= SEVERITY_RANK["medium"]:
+        score = 4
+    else:
+        score = 5
+    if any(f.get("_multi_lens") for f in findings):
+        score -= 1
+    return max(1, min(5, score))
+
+
 def format_review_body(
     findings: str,
     model: str,
@@ -236,12 +274,13 @@ def format_review_body(
     risks: list[str] | None = None,
     findings_for_table: list[dict] | None = None,
     inline_count: int = 0,
+    confidence: int = 5,
 ) -> str:
     """Format the posted review summary body.
 
     Layout (per the operator's format guide):
 
-      * Header line (``🤖 AI Review …``).
+      * Header line (``🤖 AI Review …``) including the merge-confidence badge.
       * **Summary of Changes** — 2–4 bullets of what the PR introduces
         (`summary_changes`); falls back to the opencode prose `summary` if
         the agent didn't emit the list.
@@ -255,11 +294,22 @@ def format_review_body(
         the body stays scannable; cost lines stay inside it.
       * Hidden SHA marker — for the dedupe pass.
 
+    `confidence` is a 1-5 merge verdict rendered as `<N>/5 <badge>` in the
+    header. Clamped to [1, 5] so a stray value (e.g. 0 from a missing
+    finding list) doesn't print a broken badge.
+
     Empty `summary_changes` + empty `risks` + empty `summary` collapse into
     a single "Summary of Changes: _no summary provided._" line so the body
     never looks half-rendered.
     """
-    header = REVIEW_HEADER.format(model=model, sha=sha[:8] if sha else "unknown")
+    score = max(1, min(5, confidence))
+    badge = _CONFIDENCE_BADGE.get(score, "🟢")
+    confidence_str = f"{score}/5 {badge}"
+    header = REVIEW_HEADER.format(
+        model=model,
+        sha=sha[:8] if sha else "unknown",
+        confidence=confidence_str,
+    )
     parts: list[str] = [header]
 
     # --- Summary of Changes ---
@@ -2057,6 +2107,11 @@ def review_pr(
         summary_parts = []
         if bullets:
             summary_parts.append("### Unanchored Notes\n\n" + bullets)
+        # 1-5 merge verdict for the header badge. Computed AFTER filtering +
+        # anchoring so the verdict reflects what the operator sees (a critical
+        # finding that fails to anchor is still a critical finding). The
+        # default 5 keeps any failure path (e.g. empty findings) green.
+        confidence = merge_confidence(findings)
         summary_body = format_review_body(
             "\n\n".join(summary_parts), model, sha,
             summary=review_summary,
@@ -2065,6 +2120,7 @@ def review_pr(
             risks=risks,
             findings_for_table=findings,
             inline_count=len(anchored),
+            confidence=confidence,
         )
 
         post_inline_review(api, repo, index, token, summary_body, anchored)

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
+
+