.opencode/agents/pragent.md

@@ -164,4 +164,7 @@ Rules:
 - If the diff is clean, output `{"summary":"...","findings":[]}`.
 - Do NOT repeat anything in `prior_reviews`.
 - The JSON block must be the LAST thing in your message — the Python shell parses
-  the last ```json fenced block from your output.
+  the last ```json fenced block from your output. If you run out of context/steps
+  before emitting it, your analysis is wasted: ALWAYS reserve the final step for
+  writing the JSON. Stop exploring and write findings at the first sign you've
+  covered the diff (no new findings in the last 2 file reads = stop).

pilot/ai_review.py

@@ -509,14 +509,42 @@ def _normalize_finding(f: dict) -> dict | None:
 
 
 def _last_json_block(text: str) -> str | None:
-    """Return the substring of the last fenced ```json block in text, or None.
+    r"""Return the substring of the last JSON object/array in text, or None.
-    Falls back to _extract_first_json_object when no fence is present."""
+
+    The pragent agent emits ```json fences around its final block, but real
+    outputs drift:
+      * the fence contains nested objects (regex ``\{.*?\}`` only matches the
+        first ``}``, truncating the JSON — the parser then sees
+        ``json.JSONDecodeError``);
+      * the fence is missing or unterminated, but a balanced JSON object sits
+        in the prose tail;
+      * the agent emits a bare array (findings only, no summary wrapper).
+
+    Strategy:
+      1. Find each fenced block, take the last. Inside it, walk a balanced
+         ``{...}``/``[...]`` scanner (not a regex) so nested structures survive.
+      2. Fall back to a balanced scanner over the whole text, picking the LAST
+         balanced object/array (the agent writes its conclusion last).
+    """
     s = text or ""
-    # Find all ```json ... ``` fenced blocks; take the last.
+    if not s:
-    blocks = list(re.finditer(r"```(?:json)?\s*(\{.*?\})\s*```", s, re.DOTALL))
+        return None
-    if blocks:
+    # 1. Fenced blocks: take the last ```json ... ``` or ``` ... ``` region.
-        return blocks[-1].group(1)
+    fences = list(re.finditer(r"```(?:json)?\n", s))
-    return _extract_first_json_object(s)
+    for m in reversed(fences):
+        start = m.end()
+        # Find the matching closing fence.
+        end = s.find("```", start)
+        if end < 0:
+            # Unterminated fence — try to salvage the balanced object inside.
+            end = len(s)
+        inner = s[start:end].strip()
+        obj = _balanced_json_substring(inner)
+        if obj is not None:
+            return obj
+    # 2. No (parseable) fence — scan the whole text for the LAST balanced
+    #    object/array. The agent's conclusion is at the tail.
+    return _last_balanced_json(s)
 
 
 def parse_findings(text: str) -> list[dict]:
@@ -526,11 +554,17 @@ def parse_findings(text: str) -> list[dict]:
     scans for the first balanced `{...}` and extracts its `findings` array.
     Drops findings missing path/line or with an unknown severity (normalised).
     Never raises — returns [] on any parse failure.
+
+    Also accepts a bare JSON array as the outer value: ``[{...}, {...}]`` —
+    some agents skip the ``{"summary":..., "findings":[...]}`` wrapper.
     """
     data = _parse_json_tolerant(text)
-    if not isinstance(data, dict):
+    if isinstance(data, dict):
+        findings = data.get("findings")
+    elif isinstance(data, list):
+        findings = data
+    else:
         return []
-    findings = data.get("findings")
     if not isinstance(findings, list):
         return []
     out = []
@@ -577,10 +611,11 @@ def salvage_summary(text: str, max_chars: int = SALVAGE_MAX_CHARS) -> str:
 def parse_review_output(text: str) -> tuple[str, list[dict]]:
     """Parse the opengine's stdout into (summary, findings).
 
-    Accepts `{"summary": "...", "findings": [...]}` (the opencode pragent agent)
+    Accepts `{"summary": "...", "findings": [...]}` (the opencode pragent agent),
-    or a bare `{"findings": [...]}`. `summary` defaults to "". Uses the LAST
+    `{"findings": [...]}`, or a bare `[...]` of finding dicts. `summary` defaults
-    ```json fenced block (the pragent agent emits JSON as the final block), with
+    to "". Uses the LAST fenced block (the pragent agent emits JSON as the final
-    a tolerant fallback. Never raises.
+    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:
@@ -589,10 +624,15 @@ def parse_review_output(text: str) -> tuple[str, list[dict]]:
         data = json.loads(blob)
     except json.JSONDecodeError:
         return "", []
-    if not isinstance(data, dict):
+    if isinstance(data, dict):
+        summary = str(data.get("summary", "") or "").strip()
+        findings = data.get("findings")
+    elif isinstance(data, list):
+        # Bare array: each item is a finding; no summary.
+        summary = ""
+        findings = data
+    else:
         return "", []
-    summary = str(data.get("summary", "") or "").strip()
-    findings = data.get("findings")
     out = []
     if isinstance(findings, list):
         for f in findings:
@@ -602,16 +642,18 @@ def parse_review_output(text: str) -> tuple[str, list[dict]]:
     return summary, out
 
 
-def _parse_json_tolerant(text: str) -> dict | None:
+def _parse_json_tolerant(text: str) -> dict | list | None:
-    """Parse a JSON object from text: try the last fenced block, then a direct
+    """Parse a JSON object/array from text: try the last fenced block, then a
-    parse, then the first balanced object. Returns None on any failure."""
+    direct parse, then the first balanced object. Returns None on any failure.
+    Accepts both ``{...}`` (the pragent schema) and bare ``[...]`` arrays
+    (agents that skip the wrapper)."""
     if not text:
         return None
     blob = _last_json_block(text)
     if blob is not None:
         try:
             d = json.loads(blob)
-            if isinstance(d, dict):
+            if isinstance(d, (dict, list)):
                 return d
         except json.JSONDecodeError:
             pass
@@ -621,7 +663,7 @@ def _parse_json_tolerant(text: str) -> dict | None:
         s = re.sub(r"\n?```$", "", s).strip()
     try:
         d = json.loads(s)
-        if isinstance(d, dict):
+        if isinstance(d, (dict, list)):
             return d
     except json.JSONDecodeError:
         pass
@@ -629,7 +671,17 @@ def _parse_json_tolerant(text: str) -> dict | None:
     if obj is not None:
         try:
             d = json.loads(obj)
-            if isinstance(d, dict):
+            if isinstance(d, (dict, list)):
+                return d
+        except json.JSONDecodeError:
+            pass
+    # Last resort: the JSON lives at the tail of the prose with no fence.
+    # Walk the whole text for the last balanced object/array.
+    last = _last_balanced_json(text)
+    if last is not None:
+        try:
+            d = json.loads(last)
+            if isinstance(d, (dict, list)):
                 return d
         except json.JSONDecodeError:
             pass
@@ -641,6 +693,62 @@ def _extract_first_json_object(s: str) -> str | None:
     start = s.find("{")
     if start < 0:
         return None
+    end = _scan_balanced(s, start, "{", "}")
+    if end is None:
+        return None
+    return s[start:end + 1]
+
+
+def _last_balanced_json(s: str) -> str | None:
+    """Return the substring of the LAST balanced ``{...}`` or ``[...]`` in s.
+
+    Used when the agent emits no fence: the JSON lives in the prose tail.
+    Picks whichever closer (object or array) appears latest in the text.
+    """
+    if not s:
+        return None
+    last_obj = _find_last_close(s, "{", "}")
+    last_arr = _find_last_close(s, "[", "]")
+    candidates = []
+    if last_obj is not None:
+        candidates.append(last_obj)
+    if last_arr is not None:
+        candidates.append(last_arr)
+    if not candidates:
+        return None
+    end, opener, start = max(candidates, key=lambda t: t[0])
+    return s[start:end + 1]
+
+
+def _balanced_json_substring(s: str) -> str | None:
+    """Return the first balanced ``{...}`` or ``[...]`` substring in ``s``.
+
+    Skips past leading whitespace/non-JSON and returns the full balanced
+    extent (handles nested objects/arrays and string literals with braces).
+    """
+    if not s:
+        return None
+    # Try object first; the pragent schema is an object on the outer level.
+    for i, c in enumerate(s):
+        if c == "{":
+            end = _scan_balanced(s, i, "{", "}")
+            if end is not None:
+                return s[i:end + 1]
+            break
+        if c == "[":
+            end = _scan_balanced(s, i, "[", "]")
+            if end is not None:
+                return s[i:end + 1]
+            break
+    return None
+
+
+def _scan_balanced(s: str, start: int, opener: str, closer: str) -> int | None:
+    """Return the index of the matching ``closer`` for ``s[start] == opener``.
+
+    Tracks string literals (with ``\\`` escapes) so braces inside strings don't
+    fool the depth counter. Returns None if no balance is reached.
+    """
     depth = 0
     in_str = False
     esc = False
@@ -656,12 +764,49 @@ def _extract_first_json_object(s: str) -> str | None:
             continue
         if c == '"':
             in_str = True
-        elif c == "{":
+        elif c == opener:
             depth += 1
-        elif c == "}":
+        elif c == closer:
             depth -= 1
             if depth == 0:
-                return s[start:i + 1]
+                return i
+    return None
+
+
+def _find_last_close(s: str, opener: str, closer: str) -> tuple[int, str, int] | None:
+    """Walk ``s`` backwards from the last ``closer`` to find its matching opener.
+
+    Returns ``(close_idx, opener_char, open_idx)`` for the rightmost balanced
+    structure, or None if no pair exists.
+    """
+    # Find the last `closer` candidate.
+    last = s.rfind(closer)
+    while last >= 0:
+        # Walk left, tracking depth from the perspective of the opener.
+        depth = 1
+        in_str = False
+        esc = False
+        for j in range(last - 1, -1, -1):
+            c = s[j]
+            if in_str:
+                if esc:
+                    esc = False
+                elif c == "\\":
+                    esc = True
+                elif c == '"':
+                    in_str = False
+                continue
+            if c == '"':
+                # Approximation: we don't track quotes perfectly walking
+                # backwards, but strings in agent output are short and rare.
+                in_str = not in_str
+            elif c == closer:
+                depth += 1
+            elif c == opener:
+                depth -= 1
+                if depth == 0:
+                    return (last, opener, j)
+        last = s.rfind(closer, 0, last)
     return None
 
 

pilot/diff_compress.py

@@ -103,7 +103,7 @@ def compress_diff(diff: str, *, context: int = 2) -> tuple[str, int, int]:
 
 
 def _render_hunk_body(body: list[str], *, context: int) -> tuple[list[str], int]:
-    """Trim `body` to `context` unchanged lines around the +/- lines.
+    r"""Trim `body` to `context` unchanged lines around the +/- lines.
 
     Body lines are classified:
       - `+` line → keep

tests/pilot/test_ai_review.py

@@ -11,6 +11,9 @@ sys.path.insert(0, os.path.join(ROOT, "pilot"))
 
 import ai_review  # noqa: E402
 from ai_review import (  # noqa: E402
+    _balanced_json_substring,
+    _extract_first_json_object,
+    _last_balanced_json,
     build_user_prompt,
     compute_attribution,
     format_review_body,
@@ -408,6 +411,108 @@ def test_parse_review_output_uses_last_json_block():
     assert fs[0]["path"] == "y"
 
 
+def test_parse_findings_fenced_json_with_nested_object():
+    # Real-world regression: agent emits a fence whose inner JSON has nested
+    # objects. The old regex `\{.*?\}` matched only the first `}`, truncating
+    # the JSON. Now we balance braces inside the fence.
+    txt = (
+        "```json\n"
+        '{"summary":"x","findings":[{"severity":"high","path":"a.py","line":1,'
+        '"problem":"p","fix":"f","suggestion":"","reference":""}],"meta":{"engine":"opencode"}}\n'
+        "```"
+    )
+    fs = parse_findings(txt)
+    assert len(fs) == 1
+    assert fs[0]["path"] == "a.py"
+
+
+def test_parse_findings_unfenced_at_tail():
+    # No fence at all. Agent wrote the JSON inline at the very end of its
+    # prose. The old first-balanced regex caught the FIRST `{`, not this one.
+    txt = (
+        "I considered the diff carefully. Two findings stand out:\n"
+        "First one is just text.\n"
+        '{"findings":[{"severity":"critical","path":"x","line":1,"problem":"p","fix":"f"}]}'
+    )
+    fs = parse_findings(txt)
+    assert len(fs) == 1
+    assert fs[0]["severity"] == "critical"
+
+
+def test_parse_findings_bare_array():
+    # Some agents skip the `{"summary":..., "findings":[...]}` wrapper and
+    # emit just the array.
+    txt = (
+        "Here are my findings:\n"
+        "```json\n"
+        '[{"severity":"low","path":"a","line":1,"problem":"p","fix":"f","suggestion":"","reference":""}]\n'
+        "```"
+    )
+    fs = parse_findings(txt)
+    assert len(fs) == 1
+    assert fs[0]["path"] == "a"
+
+
+def test_parse_review_output_unfenced_at_tail():
+    # The exact shape canalhandia produced: long prose, JSON at the very end,
+    # no fence. Old parser returned ([], salvage) — now we recover findings.
+    txt = (
+        "Let me refine the fix: should call a dedicated `setPermanent`.\n"
+        "Let me finalize. Let me also double-check the `find` thread-safety.\n"
+        '{"summary":"Adds void protection; one critical race.","findings":['
+        '{"severity":"high","path":"VoidProtection.java","line":162,'
+        '"problem":"drop duplication race","fix":"use ItemMeta","suggestion":"","reference":""}]}'
+    )
+    summary, fs = parse_review_output(txt)
+    assert "void protection" in summary.lower()
+    assert len(fs) == 1
+    assert fs[0]["path"] == "VoidProtection.java"
+
+
+def test_parse_review_output_bare_array_at_tail():
+    txt = (
+        "All wrapped up.\n"
+        '[{"severity":"low","path":"a","line":1,"problem":"p","fix":"","suggestion":"","reference":""}]'
+    )
+    summary, fs = parse_review_output(txt)
+    assert summary == ""
+    assert len(fs) == 1
+
+
+def test_scan_balanced_handles_braces_in_strings():
+    # The JSON scanner must not be fooled by `{` or `}` inside string literals.
+    s = '{"a":"contains { and }","b":1}'
+    obj = _extract_first_json_object(s)
+    assert obj == s
+    d = json.loads(obj)
+    assert d["a"] == "contains { and }"
+
+
+def test_last_balanced_json_picks_latest():
+    s = '{"a":1} some text {"b":2,"nested":{"c":3}} trailing'
+    out = _last_balanced_json(s)
+    assert out is not None
+    d = json.loads(out)
+    assert d == {"b": 2, "nested": {"c": 3}}
+
+
+def test_last_balanced_json_no_json():
+    assert _last_balanced_json("nothing here") is None
+    assert _last_balanced_json("") is None
+
+
+def test_balanced_json_substring_skips_leading_prose():
+    s = 'preamble {"a":1} more prose {"b":2}'
+    out = _balanced_json_substring(s)
+    assert out == '{"a":1}'
+
+
+def test_balanced_json_substring_handles_array():
+    s = '[{"a":1},{"b":2}]'
+    out = _balanced_json_substring(s)
+    assert out == s
+
+
 # ---------------------------------------------------------------------------
 # reference rendering in inline_comment_body + summary_bullets + summary section
 # ---------------------------------------------------------------------------