feat(review): walkthrough/risk_verdict/test_coverage schema

pilot/ai_review.py

@@ -109,7 +109,10 @@ Output STRICT JSON only — no prose, no markdown fences. Shape:
       "fix": "one line: how to fix it",
       "suggestion": "<exact replacement lines for that location, or empty string if you cannot produce safe replacement code>"
     }
-  ]
+  ],
+  "walkthrough": ["2-6 short bullets, file- or change-grouped, plain prose"],
+  "risk_verdict": "Low|Medium|High|Critical risk: <one-line concrete reason>",
+  "test_coverage": "Tests added" | "Tests changed" | "No tests for behavioral change" | "No test files in repo"
 }
 
 Rules:
@@ -121,6 +124,15 @@ Rules:
   Keep it minimal — just the changed lines, indented as they would appear in the
   file. Leave it empty ("") if a safe textual replacement is not possible (e.g.
   a missing test, an architectural note).
+- `walkthrough`: 2-6 short bullets, file- or change-grouped, plain prose.
+  Default to `[]` when the diff is trivial. Backward compatible: parsers
+  default to `[]` if absent.
+- `risk_verdict`: exactly one line. Lead with "Low|Medium|High|Critical risk:"
+  followed by a concrete reason. Default to `""` when not applicable.
+  Backward compatible: parsers default to `""` if absent.
+- `test_coverage`: short string. One of "Tests added" / "Tests changed" /
+  "No tests for behavioral change" / "No test files in repo". Default to `""`
+  when not applicable. Backward compatible: parsers default to `""` if absent.
 - Skip nitpicks, pure formatting, and praise. At most ~15 findings, highest
   severity first.
 - If the diff is clean, output: {"findings": []}
@@ -728,45 +740,59 @@ def salvage_summary(text: str, max_chars: int = SALVAGE_MAX_CHARS) -> str:
     )
 
 
-def parse_review_output(text: str) -> tuple[str, list[dict], list[str], list[str]]:
-    """Parse the opengine's stdout into (summary, findings, summary_changes, risks).
+def parse_review_output(
+    text: str,
+) -> tuple[str, list[dict], list[str], list[str], list[str], str, str]:
+    """Parse the opengine's stdout into a 7-tuple:
+        (summary, findings, summary_changes, risks,
+         walkthrough, risk_verdict, test_coverage)
 
     Accepts `{"summary": "...", "summary_changes": [...], "risks": [...],
-    "findings": [...]}` (the opencode pragent agent), `{"findings": [...]}`,
-    or a bare `[...]` of finding dicts. `summary_changes` and `risks` default
-    to empty lists; older outputs without them still parse fine. Uses the
-    LAST fenced block (the pragent agent emits JSON as the final block), with
-    a tolerant fallback that scans for the last balanced object/array in the
-    prose tail. Never raises.
+    "walkthrough": [...], "risk_verdict": "...", "test_coverage": "...",
+    "findings": [...]}` (the opencode pragent agent), the legacy 4-field
+    shape, or a bare `[...]` of finding dicts. The three new fields
+    (`walkthrough`, `risk_verdict`, `test_coverage`) default to empty
+    list / empty strings when absent — older outputs and the bare-array
+    shape stay backward compatible.
+
+    Uses the LAST fenced block (the pragent agent emits JSON as the final
+    block), with a tolerant fallback that scans for the last balanced
+    object/array in the prose tail. Never raises.
     """
     blob = _last_json_block(text)
     if blob is None:
-        return "", [], [], []
+        return "", [], [], [], [], "", ""
     try:
         data = json.loads(blob)
     except json.JSONDecodeError:
-        return "", [], [], []
+        return "", [], [], [], [], "", ""
     summary = ""
     summary_changes: list[str] = []
     risks: list[str] = []
+    walkthrough: list[str] = []
+    risk_verdict = ""
+    test_coverage = ""
     findings_raw = None
     if isinstance(data, dict):
         summary = str(data.get("summary", "") or "").strip()
         summary_changes = _string_list(data.get("summary_changes"))
         risks = _string_list(data.get("risks"))
+        walkthrough = _string_list(data.get("walkthrough"))
+        risk_verdict = str(data.get("risk_verdict", "") or "").strip()
+        test_coverage = str(data.get("test_coverage", "") or "").strip()
         findings_raw = data.get("findings")
     elif isinstance(data, list):
         # Bare array: each item is a finding; no summary/sections.
         findings_raw = data
     else:
-        return "", [], [], []
+        return "", [], [], [], [], "", ""
     out = []
     if isinstance(findings_raw, list):
         for f in findings_raw:
             n = _normalize_finding(f)
             if n is not None:
                 out.append(n)
-    return summary, out, summary_changes, risks
+    return summary, out, summary_changes, risks, walkthrough, risk_verdict, test_coverage
 
 
 def _string_list(value) -> list[str]:
@@ -2028,7 +2054,7 @@ def review_pr(
                     compression_note=compression_note,
                     additional_context=additional_context,
                 )
-            review_summary, findings, summary_changes, risks = parse_review_output(stdout)
+            review_summary, findings, summary_changes, risks, _walkthrough, _risk_verdict, _test_coverage = parse_review_output(stdout)
             if not findings and not review_summary:
                 # The findings JSON was missing or malformed. Don't discard the
                 # run: salvage the prose, keep the usage report (the label asked