week_3: address CodeRabbit review on #937

Resolve the CodeRabbit review comments on the Module C PR:
- schemas.py: enforce RFC format parity — AnyUrl for url fields,
  datetime for committed_at/filtered_at/classified_at/created_at
- section_validator.py: replace assert with a typed
  MalformedKnowledgeItemError guard (survives python -O)
- knowledge_source.py: skip+log malformed JSONL rows instead of
  aborting the whole iteration on ValidationError
- config_loader_test.py: isolate os.environ and assert the specific
  FrozenInstanceError
- dataset_test.py: add a timeout to the determinism subprocess call
- build_golden_dataset.py: rename unused loop var node_id -> _node_id
- section_validator_test.py: assert committed_at as the typed datetime

Author: PRAteek-singHWY

application/tests/librarian/config_loader_test.py

@@ -1,5 +1,6 @@
 import os
 import unittest
+from dataclasses import FrozenInstanceError
 from unittest import mock
 
 from application.utils.librarian.config_loader import LibrarianConfig, load_config
@@ -18,8 +19,9 @@ def test_defaults_when_env_unset(self):
         self.assertEqual(cfg.conformal_alpha, 0.10)
 
     def test_config_is_frozen(self):
-        cfg = load_config()
-        with self.assertRaises(Exception):
+        with mock.patch.dict(os.environ, {}, clear=True):
+            cfg = load_config()
+        with self.assertRaises(FrozenInstanceError):
             cfg.link_threshold = 0.5  # type: ignore[misc]
 
 

application/tests/librarian/dataset_test.py

@@ -111,6 +111,7 @@ def test_build_check_matches_committed_dataset(self):
             [sys.executable, _BUILD_SCRIPT, "--check"],
             capture_output=True,
             text=True,
+            timeout=120,
         )
         self.assertEqual(
             result.returncode,

application/tests/librarian/section_validator_test.py

@@ -6,6 +6,7 @@
 """
 
 import unittest
+from datetime import datetime, timezone
 
 from pydantic import ValidationError
 
@@ -86,7 +87,10 @@ def test_valid_row_builds_section_with_synthesized_identity(self) -> None:
             section.artifact_id, "art:OWASP/ASVS:4.0/en/0x11-V2-Authentication.md"
         )
         self.assertEqual(section.source.repo, "OWASP/ASVS")
-        self.assertEqual(section.source.committed_at, "2026-05-25T02:25:00Z")
+        self.assertEqual(
+            section.source.committed_at,
+            datetime(2026, 5, 25, 2, 25, tzinfo=timezone.utc),
+        )
         self.assertEqual(section.locator.path, "4.0/en/0x11-V2-Authentication.md")
         self.assertEqual(section.language, "en")
 

application/utils/librarian/knowledge_source.py

@@ -7,11 +7,16 @@
 """
 
 import json
+import logging
 from abc import ABC, abstractmethod
 from typing import Iterator
 
+from pydantic import ValidationError
+
 from application.utils.librarian.schemas import KnowledgeQueueItem
 
+logger = logging.getLogger(__name__)
+
 
 class KnowledgeSource(ABC):
     @abstractmethod
@@ -28,7 +33,15 @@ def __init__(self, jsonl_path: str) -> None:
 
     def items(self) -> Iterator[KnowledgeQueueItem]:
         with open(self._path, encoding="utf-8") as fh:
-            for line in fh:
+            for line_no, line in enumerate(fh, start=1):
                 line = line.strip()
                 if line:
-                    yield KnowledgeQueueItem.model_validate_json(line)
+                    try:
+                        yield KnowledgeQueueItem.model_validate_json(line)
+                    except ValidationError as exc:
+                        logger.warning(
+                            "Skipping malformed knowledge_queue row at line %d: %s",
+                            line_no,
+                            exc,
+                        )
+                        continue

application/utils/librarian/schemas.py

@@ -12,10 +12,11 @@
 from __future__ import annotations
 
 import re
+from datetime import datetime
 from enum import Enum
 from typing import List, Literal, Optional
 
-from pydantic import BaseModel, ConfigDict, Field, model_validator
+from pydantic import AnyUrl, BaseModel, ConfigDict, Field, model_validator
 
 SCHEMA_VERSION = "0.2.0"
 _SCHEMA_VERSION_RE = re.compile(r"^0\.\d+\.\d+$")
@@ -64,10 +65,10 @@ class SourceRef(BaseModel):
     model_config = ConfigDict(extra="forbid")
     type: SourceType
     repo: Optional[str] = None
-    url: Optional[str] = None
+    url: Optional[AnyUrl] = None
     commit_sha: Optional[str] = Field(default=None, min_length=7)
     commit_message: Optional[str] = None
-    committed_at: str
+    committed_at: datetime
     author_login: Optional[str] = None
 
     @model_validator(mode="after")
@@ -84,7 +85,7 @@ class Locator(BaseModel):
     kind: LocatorKind
     id: str = Field(min_length=1)
     path: Optional[str] = None
-    url: Optional[str] = None
+    url: Optional[AnyUrl] = None
     title: Optional[str] = None
 
     @model_validator(mode="after")
@@ -201,7 +202,7 @@ class KnowledgeItem(BaseModel):
     artifact_id: str
     event_id: str
     pipeline_run_id: str
-    filtered_at: str
+    filtered_at: datetime
     status: KnowledgeStatus
     source: SourceRef
     locator: Locator
@@ -228,7 +229,7 @@ class LinkProposal(BaseModel):
     chunk_id: str
     artifact_id: str
     pipeline_run_id: str
-    classified_at: str
+    classified_at: datetime
     status: Literal["linked"] = "linked"
     knowledge: KnowledgeSnapshot
     retrieval: RetrievalAudit
@@ -251,7 +252,7 @@ class ReviewItem(BaseModel):
     chunk_id: str
     artifact_id: str
     pipeline_run_id: str
-    created_at: str
+    created_at: datetime
     status: Literal["review_required"] = "review_required"
     reason_code: ReasonCode
     knowledge: KnowledgeSnapshot

application/utils/librarian/section_validator.py

@@ -160,8 +160,9 @@ def section_from_knowledge_item(
         raise NotKnowledgeError(
             f"status={item.status.value!r}; only 'accepted' items may be linked"
         )
-    # status=accepted guarantees content (enforced by the KnowledgeItem model).
-    assert item.content is not None
+    # Keep boundary behavior typed even for pre-built/mutated model instances.
+    if item.content is None:
+        raise MalformedKnowledgeItemError("status='accepted' requires content")
     _require_text(item.content.text)
     language = _require_language(item.content.language)
 

scripts/build_golden_dataset.py

@@ -258,7 +258,7 @@ def build_positive_multilink(conn: sqlite3.Connection) -> List[Dict]:
         """
     ).fetchall()
     out = []
-    for node_id, name, section_id, text, cre_concat in rows:
+    for _node_id, name, section_id, text, cre_concat in rows:
         cre_ids = sorted(set(cre_concat.split("|")))
         std = "OTHER"
         if "Top 10" in name: