init: cobol-java migration verification platform v3 (42 tests, JCL module)

orchestrator.py

@@ -10,6 +10,7 @@ from runners.cobol_runner import CobolRunner
 from runners.data_writer import DataWriter
 from agents.agent1_parser import Agent1Parser
 from agents.agent2_data import Agent2Data
+from agents.agent3_diagnostic import Agent3Diagnostic
 from agents.llm import LLMClient
 from comparator.aligner import align_records
 from comparator.field_compare import compare_field
@@ -31,6 +32,9 @@ def run_pipeline(cfg: Config, cpath: str, cbl: str, java: str, map_path: str) ->
         llm = LLMClient(model=cfg.llm_model, timeout=cfg.llm_timeout, cache_dir=cfg.llm_cache_dir)
         tree = Agent1Parser(llm).parse(text)
         vr.llm_cost += 0.002
+        vr.debug["field_tree"] = [{"name":f.name,"level":f.level,"pic":f.pic,"usage":f.usage,
+            "offset":f.offset,"length":f.length,"redefines":f.redefines}
+            for f in tree.flatten().values()]
         if not tree.fields:
             return _done(vr, t0, "BLOCKED", 2)
         if vr.llm_cost > cfg.max_llm_cost:
@@ -38,6 +42,8 @@ def run_pipeline(cfg: Config, cpath: str, cbl: str, java: str, map_path: str) ->
 
         suite = Agent2Data(llm).design(tree, cfg.coverage_default, cfg.runner_mode == "spark")
         vr.llm_cost += 0.002
+        vr.debug["test_cases"] = [{"id":tc.id,"fields":tc.fields,"targets":tc.coverage_targets} for tc in suite.test_cases]
+        vr.debug["spark_config"] = {"records":suite.spark_config.num_records} if suite.has_spark else None
 
         bundle = TestDataBundle(base_path=Path("test-data-bundle"))
         bundle.ensure_dirs()
@@ -51,6 +57,7 @@ def run_pipeline(cfg: Config, cpath: str, cbl: str, java: str, map_path: str) ->
 
         cob = CobolRunner()
         build = cob.compile(cbl, cfg.dialect)
+        vr.debug["cobol_build"] = {"ok": build.success, "log": build.log[-300:]}
         if not build.success:
             return _done(vr, t0, "BLOCKED", 2)
         co = Path("cobol_out.bin")
@@ -61,6 +68,7 @@ def run_pipeline(cfg: Config, cpath: str, cbl: str, java: str, map_path: str) ->
             return _done(vr, t0, "BLOCKED", 2)
         runner: Runner = SparkJavaRunner(cfg.spark_master) if cfg.runner_mode == "spark" else NativeJavaRunner()
         jb = runner.compile(java)
+        vr.debug["java_build"] = {"ok": jb.success, "log": jb.log[-300:]}
         if not jb.success:
             return _done(vr, t0, "BLOCKED", 2)
         inp = str(bundle.spark_input_dir() if cfg.runner_mode == "spark" else bundle.native_input())
@@ -95,6 +103,14 @@ def run_pipeline(cfg: Config, cpath: str, cbl: str, java: str, map_path: str) ->
         vr.status = "PASS" if m == 0 else "MISMATCH"
         vr.exit_code = 0 if m == 0 else 1
 
+        diag = Agent3Diagnostic(llm)
+        for fr in frs:
+            if fr.status in ("MISMATCH", "NOT_SET", "NPE"):
+                try:
+                    fr.suggestion = diag.analyze(fr) or ""
+                except:
+                    pass
+
         rd = Path(f"reports/{vr.program}") / vr.timestamp
         rd.mkdir(parents=True, exist_ok=True)
         g = ReportGenerator()