Fix uncaught pydantic ValidationError crash on malformed LLM response

[Ruanyuxi1337]

Fixes #250. Wraps the per-batch LLM request and parse loop in a try-except guard. If a parsing or network validation failure occurs, it warns, retries exactly once, and falls back gracefully, preventing the entire scan from crashing and losing all report progress.

[koriyoshi2041]

Thanks for taking this on. One gap worth covering before merge: this only wraps the async arun_batches() path, but semantic_security_discovery still calls analyzer.run_batches(batches).

In that sync loop, a malformed structured response from one batch still raises out of run_batches; the outer node catch then returns zero findings for the whole semantic analyzer, including any earlier batches that parsed successfully. A focused regression would be: three sync batches, middle one raises a Pydantic ValidationError from LLMAnalysisResult.model_validate(...), and the first/third batch results are still returned.

So I think the same per-batch isolation should be added to run_batches() too, otherwise #250 can still reproduce through that analyzer path.