From 2e735508bc8787c05ed3d2efcfc32cfa34bbcf05 Mon Sep 17 00:00:00 2001
From: kigland <shuaizhicheng336@gmail.com>
Date: Tue, 7 Jul 2026 10:42:29 +0800
Subject: [PATCH] isolate malformed LLM batch responses

Signed-off-by: kigland <shuaizhicheng336@gmail.com>
---
 src/skillspector/llm_analyzer_base.py | 32 ++++++++++++++++---
 tests/nodes/test_llm_analyzer_base.py | 44 +++++++++++++++++++++++++++
 2 files changed, 72 insertions(+), 4 deletions(-)

diff --git a/src/skillspector/llm_analyzer_base.py b/src/skillspector/llm_analyzer_base.py
index c5ab9dce..b2c97d16 100644
--- a/src/skillspector/llm_analyzer_base.py
+++ b/src/skillspector/llm_analyzer_base.py
@@ -33,7 +33,7 @@
 from typing import Literal
 
 from langchain_core.messages import BaseMessage
-from pydantic import BaseModel, Field, field_validator
+from pydantic import BaseModel, Field, ValidationError, field_validator
 
 from skillspector.llm_utils import get_chat_model
 from skillspector.logging_config import get_logger
@@ -386,11 +386,35 @@ def run_batches(
                 len(batch.findings),
             )
             if self._structured_llm:
-                response = self._structured_llm.invoke(prompt)
+                try:
+                    response = self._structured_llm.invoke(prompt)
+                except ValidationError as exc:
+                    logger.warning("LLM batch failed for %s: %s", batch.file_label, exc)
+                    continue
+                except (ValueError, NotImplementedError):
+                    raise
+                except Exception as exc:
+                    logger.warning("LLM batch failed for %s: %s", batch.file_label, exc)
+                    continue
             else:
-                response = _message_text(self._llm.invoke(prompt))
+                try:
+                    response = _message_text(self._llm.invoke(prompt))
+                except (ValueError, NotImplementedError):
+                    raise
+                except Exception as exc:
+                    logger.warning("LLM batch failed for %s: %s", batch.file_label, exc)
+                    continue
             logger.debug("LLM response for %s", batch.file_label)
-            parsed = self.parse_response(response, batch)
+            try:
+                parsed = self.parse_response(response, batch)
+            except ValidationError as exc:
+                logger.warning("LLM batch parse failed for %s: %s", batch.file_label, exc)
+                continue
+            except (ValueError, NotImplementedError):
+                raise
+            except Exception as exc:
+                logger.warning("LLM batch parse failed for %s: %s", batch.file_label, exc)
+                continue
             results.append((batch, parsed))
         return results
 
diff --git a/tests/nodes/test_llm_analyzer_base.py b/tests/nodes/test_llm_analyzer_base.py
index e344e654..70a0f471 100644
--- a/tests/nodes/test_llm_analyzer_base.py
+++ b/tests/nodes/test_llm_analyzer_base.py
@@ -388,6 +388,50 @@ async def test_arun_batches_uses_message_text_for_content_blocks(self) -> None:
         assert results[0][1] == ["async chunk"]
 
 
+# ---------------------------------------------------------------------------
+# LLMAnalyzerBase.run_batches (sync execution)
+# ---------------------------------------------------------------------------
+
+
+class TestRunBatches:
+    MODEL = "nvidia/openai/gpt-oss-120b"
+
+    @patch(MOCK_PATCH_TARGET, _mock_get_chat_model)
+    def test_malformed_structured_batch_does_not_abort_the_others(self) -> None:
+        """A malformed structured response costs only its own batch."""
+
+        def _invoke(prompt: str) -> LLMAnalysisResult:
+            if "b.py" in prompt:
+                return LLMAnalysisResult.model_validate({"findings": 'We{"findings":[]}'})
+            return LLMAnalysisResult(
+                findings=[
+                    LLMFinding(rule_id="T-1", message="hit", severity="LOW", start_line=1),
+                ]
+            )
+
+        analyzer = LLMAnalyzerBase(base_prompt="test", model=self.MODEL)
+        analyzer._structured_llm.invoke.side_effect = _invoke
+
+        batches = [
+            Batch(file_path="a.py", content="code a"),
+            Batch(file_path="b.py", content="code b"),
+            Batch(file_path="c.py", content="code c"),
+        ]
+        results = analyzer.run_batches(batches)
+
+        assert {batch.file_path for batch, _ in results} == {"a.py", "c.py"}
+        assert [items[0].rule_id for _, items in results] == ["T-1", "T-1"]
+
+    @patch(MOCK_PATCH_TARGET, _mock_get_chat_model)
+    def test_value_error_still_propagates(self) -> None:
+        """ValueError signals misconfiguration, not a malformed model response."""
+        analyzer = LLMAnalyzerBase(base_prompt="test", model=self.MODEL)
+        analyzer._structured_llm.invoke.side_effect = ValueError("no API key")
+
+        with pytest.raises(ValueError, match="no API key"):
+            analyzer.run_batches([Batch(file_path="a.py", content="code")])
+
+
 # ---------------------------------------------------------------------------
 # LLMAnalyzerBase.arun_batches (async parallel execution)
 # ---------------------------------------------------------------------------