docs: fix spec accuracy (line numbers and test counts)

SPEC_01: Line reference 112 → 110 (actual location of .with_standard_manager)
SPEC_02: Test count 142 → 140 (verified with pytest --collect-only)

Both specs now match codebase exactly per audit verification.

docs/specs/SPEC_01_DEMO_TERMINATION.md

@@ -16,7 +16,7 @@ Advanced (Magentic) mode runs indefinitely from user perspective. The demo was m
 ### Question 1: Does max_round_count actually work?
 
 ```python
-# Current code (src/orchestrator_magentic.py:112)
+# Current code (src/orchestrator_magentic.py:110)
 .with_standard_manager(
     chat_client=manager_client,
     max_round_count=self._max_rounds,  # Default: 10

docs/specs/SPEC_02_E2E_TESTING.md

@@ -4,7 +4,7 @@
 
 ## Problem Statement
 
-We have 142 unit tests that verify individual components work, but **no test that proves the full pipeline produces useful research output**.
+We have 140 unit tests that verify individual components work, but **no test that proves the full pipeline produces useful research output**.
 
 We don't know if:
 1. Simple mode produces a valid report
@@ -122,7 +122,7 @@ async def test_real_pubmed_search():
 
 ```
 tests/
-├── unit/           # Existing 142 tests
+├── unit/           # Existing 140 tests
 ├── integration/    # Real API tests (existing)
 └── e2e/            # NEW: Full pipeline tests
     ├── conftest.py         # E2E fixtures