Chiusura fase di ristrutturazione e modularizzazione del workflow per favorire sviluppo modulare

harness/tht/evidence/__init__.py

@@ -24,16 +24,15 @@ from tht.evidence.search import (
 from tht.evidence.session import project_session
 from tht.evidence.sources import build_sources
 
-
 __all__ = [
     "AcquiredDocument",
+    "ActiveEvidenceSearcher",
+    "CorpusWorkspaceMismatchError",
+    "EvidenceEmbedder",
     "EvidenceSource",
     "EvidenceSourceError",
     "EvidenceSourceErrorCategory",
-    "EvidenceEmbedder",
     "SourceObject",
-    "ActiveEvidenceSearcher",
-    "CorpusWorkspaceMismatchError",
     "acquire",
     "active_searcher",
     "build_preprocessing_pipeline",

harness/tht/evidence/adapters/s3.py

@@ -7,7 +7,10 @@ from datetime import UTC, datetime
 from urllib.parse import quote, urlsplit
 
 from tht.evidence.contracts import (
-    AcquiredDocument, EvidenceSourceError, EvidenceSourceErrorCategory, SourceObject,
+    AcquiredDocument,
+    EvidenceSourceError,
+    EvidenceSourceErrorCategory,
+    SourceObject,
 )
 
 

harness/tht/evidence/corpus/models.py

@@ -15,7 +15,6 @@ from tht.evidence.contracts import (
     validate_safe_metadata,
 )
 
-
 _NAMESPACED_ID = re.compile(r"^[a-z][a-z0-9_-]*:[A-Za-z0-9._:-]+$")
 _SHA256 = re.compile(r"^sha256:[0-9a-f]{64}$")
 

harness/tht/evidence/corpus/normalize.py

@@ -10,9 +10,8 @@ from pydantic import JsonValue, TypeAdapter, ValidationError
 from yaml.events import AliasEvent
 from yaml.nodes import MappingNode
 
-from tht.evidence.corpus.models import CanonicalDocument
 from tht.evidence.contracts import AcquiredDocument, canonical_provenance_uri
-
+from tht.evidence.corpus.models import CanonicalDocument
 
 MAX_DOCUMENT_BYTES = 10 * 1024 * 1024
 _CHARSET = re.compile(r"(?:^|;)\s*charset\s*=\s*[\"']?([^;\s\"']+)", re.IGNORECASE)

harness/tht/evidence/corpus/pipeline.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import hashlib
 import json
+import logging
 import re
 import uuid
 from collections.abc import Mapping, Sequence
@@ -11,17 +12,16 @@ from dataclasses import asdict, dataclass, field
 from datetime import UTC
 from pathlib import Path
 
+import tht.evidence.acquisition as evidence_acquisition
+from tht.evidence.contracts import EvidenceSource, SourceObject, canonical_provenance_uri
 from tht.evidence.corpus.chunk import ChunkPolicy, chunk
 from tht.evidence.corpus.models import CanonicalChunk, CanonicalDocument, CorpusManifest
 from tht.evidence.corpus.normalize import normalize
 from tht.evidence.corpus.store import CorpusStore
-import tht.evidence.acquisition as evidence_acquisition
-from tht.evidence.contracts import EvidenceSource, SourceObject, canonical_provenance_uri
-from tht.ports.vector import VectorStore, VectorWriteRecord
-from tht.vectorstore.records import VectorRecord
 from tht.jobs.models import JobSpec
 from tht.jobs.runner import JobContext, StageArtifacts, run_job, seal_stage_artifacts
-
+from tht.ports.vector import VectorStore, VectorWriteRecord
+from tht.vectorstore.records import VectorRecord
 
 EVIDENCE_STAGE_IDS = (
     "discover",
@@ -33,6 +33,8 @@ EVIDENCE_STAGE_IDS = (
     "retention_cleanup",
 )
 
+logger = logging.getLogger(__name__)
+
 
 class PipelineError(RuntimeError):
     """Credential-free failure at the preprocessing boundary."""
@@ -212,14 +214,14 @@ class CorpusPipeline:
             if purge_vector:
                 try:
                     self.vector_store.delete_generation("evidence", generation, self.workspace_id)
-                except Exception:
+                except Exception:  # noqa: BLE001 - retention reports per-generation failures
                     failures.append({"generation": generation, "error": "vector cleanup failed"})
                     continue
             try:
                 if purge_filesystem:
                     self.store.discard(generation)
                 evicted.append(generation)
-            except Exception:
+            except Exception:  # noqa: BLE001 - retention reports per-generation failures
                 failures.append({"generation": generation, "error": "filesystem cleanup failed"})
         return {"status": "partial" if failures else "succeeded", "dry_run": dry_run,
                 "active_generation": self.store.active_generation(), "evicted": evicted,
@@ -378,7 +380,7 @@ class CorpusPipeline:
 
         try:
             active_assets_valid = active_assets_are_valid(previous)
-        except Exception:
+        except Exception:  # noqa: BLE001 - any corrupt active asset disables reuse
             active_assets_valid = False
         reusable = (
             active_assets_valid
@@ -538,7 +540,7 @@ class CorpusPipeline:
             try:
                 self.vector_store.delete_generation("evidence", generation, self.workspace_id)
             except Exception:
-                pass
+                logger.debug("Failed to clean the compensated vector generation", exc_info=True)
             write(context, "compensated.json", {"generation": generation})
 
         def rotate_compensated_generation(context: JobContext) -> None:
@@ -786,12 +788,12 @@ class CorpusPipeline:
         try:
             self.store.discard(generation)
         except Exception:
-            pass
+            logger.debug("Failed to discard the unpublished evidence generation", exc_info=True)
         if vector_written:
             try:
                 self.vector_store.delete_generation("evidence", generation, self.workspace_id)
             except Exception:
-                pass
+                logger.debug("Failed to delete the unpublished vector generation", exc_info=True)
 
     @staticmethod
     def _vector_record(

harness/tht/evidence/corpus/store.py

@@ -2,22 +2,21 @@
 
 from __future__ import annotations
 
-import json
 import fcntl
+import hashlib
+import json
 import os
 import re
-import stat
 import shutil
-import uuid
-import hashlib
+import stat
 import threading
+import uuid
+from contextlib import contextmanager
 from datetime import UTC, datetime
 from pathlib import Path
-from contextlib import contextmanager
 
 from tht.evidence.corpus.models import CorpusManifest
 
-
 _GENERATION = re.compile(r"^gen:[0-9a-f]{32}$")
 
 

harness/tht/evidence/formula_store.py

@@ -46,7 +46,7 @@ class ConceptFormula(BaseModel):
         return f"---\n{fm}---\n{self.sql}\n"
 
     @classmethod
-    def parse(cls, text: str) -> "ConceptFormula":
+    def parse(cls, text: str) -> ConceptFormula:
         if not text.startswith("---\n"):
             raise ValueError("frontmatter mancante (atteso '---\\n' iniziale)")
         try:
@@ -55,7 +55,7 @@ class ConceptFormula(BaseModel):
             raise ValueError("frontmatter malformato") from e
         meta = yaml.safe_load(fm)
         if not isinstance(meta, dict):
-            raise ValueError("frontmatter non valido")
+            raise TypeError("frontmatter non valido")
         return cls.model_validate({**meta, "sql": body.strip("\n")})
 
 

harness/tht/evidence/preprocessing.py

@@ -2,10 +2,10 @@
 
 from typing import Protocol
 
+from tht.evidence.contracts import EvidenceSource
 from tht.evidence.corpus.chunk import ChunkPolicy
 from tht.evidence.corpus.pipeline import CorpusPipeline
 from tht.evidence.corpus.store import CorpusStore
-from tht.evidence.contracts import EvidenceSource
 from tht.ports.vector import VectorStore