fix(chat): honor effective RAG policy in context building (#7025)

routes/chat_helpers.py

@@ -1276,6 +1276,7 @@ async def build_chat_context(
         message=_ctx_msg,
         session=sess,
         use_web=use_web_val and not skip_web,
+        use_rag=use_rag_val,
         use_memory=mem_enabled,
         time_filter=time_filter,
         preset_system_prompt=preset.system_prompt,
@@ -1286,8 +1287,6 @@ async def build_chat_context(
         incognito=incognito,
         use_skills=skills_enabled,
     )
-    if use_rag is not None or is_research_spinoff or casual_low_signal:
-        _preface_kwargs["use_rag"] = use_rag_val
     preface, rag_sources, web_sources = chat_processor.build_context_preface(**_preface_kwargs)
 
     # Capture used memories immediately

tests/test_c5_rag_disable.py

@@ -0,0 +1,100 @@
+"""Effective RAG policy reaches the real search and context consumer."""
+from types import SimpleNamespace
+from unittest.mock import Mock
+
+import pytest
+
+from src.chat_processor import ChatProcessor
+from tests.test_kv_cache_invalidation_2927 import _build_context_harness
+
+pytestmark = pytest.mark.area_routes
+
+
+@pytest.mark.parametrize('mode', ['chat', 'agent', 'compare'])
+@pytest.mark.parametrize('policy', [
+    'normal', 'incognito', 'preprocessing_disabled', 'research_spinoff', 'low_signal',
+])
+@pytest.mark.parametrize('use_rag', [None, 'true', 'false', True, False])
+async def test_rag_policy_preserves_context_channels(monkeypatch, mode, policy, use_rag):
+    """Exercise effective policy with real preface assembly and synthetic I/O.
+
+    Nonempty results prove permitted retrieval still injects context. Independent
+    memory, skills and web spies ensure a RAG disable cannot disable other channels.
+    """
+    from routes import chat_helpers
+    from src import chat_processor, llm_core, user_time
+
+    sess, request, handler, _ = _build_context_harness(monkeypatch, chat_helpers, history=[])
+    monkeypatch.setattr(chat_helpers, 'load_prefs_for_user', lambda user: {
+        'memory_enabled': True, 'skills_enabled': True})
+    monkeypatch.setattr(user_time, 'current_datetime_context_message', lambda: {
+        'role': 'user', 'content': 'Synthetic current date context'})
+    incognito = policy == 'incognito'
+    preprocessing = policy != 'preprocessing_disabled'
+    if policy == 'research_spinoff':
+        sess.history = [{'role': 'system', 'metadata': {'research_spinoff_from': 'fixture-report'}}]
+    message = 'hi' if policy == 'low_signal' else 'Find the retention policy for archived project documents'
+    search = Mock(return_value=[{
+        'document': 'Synthetic retention document',
+        'metadata': {'filename': 'fixture.txt'}, 'similarity': 0.99,
+    }])
+    memory = Mock(return_value=[{
+        'id': 'fixture-memory', 'text': 'User identity synthetic memory',
+        'category': 'identity', 'pinned': True,
+    }])
+    skills = Mock(return_value=[{'name': 'fixture_skill', 'description': 'Synthetic skill'}])
+    web = Mock(return_value=('Synthetic web context', [{'url': 'https://example.invalid/fixture'}]))
+    query = Mock(return_value='retention policy')
+    monkeypatch.setattr(llm_core, 'llm_call', query)
+    monkeypatch.setattr(chat_processor, 'comprehensive_web_search', web)
+    processor = ChatProcessor(
+        memory_manager=SimpleNamespace(load=memory),
+        personal_docs_manager=SimpleNamespace(rag_manager=SimpleNamespace(search=search)),
+        skills_manager=SimpleNamespace(index_for=skills),
+    )
+    received = []
+    real_preface = processor.build_context_preface
+
+    def capture(**kwargs):
+        received.append(dict(kwargs))
+        return real_preface(**kwargs)
+
+    monkeypatch.setattr(processor, 'build_context_preface', capture)
+    ctx = await chat_helpers.build_chat_context(
+        sess=sess, request=request, chat_handler=handler, chat_processor=processor,
+        message=message, session_id='c5-policy', use_rag=use_rag,
+        incognito=incognito, allow_tool_preprocessing=preprocessing,
+        persist_user_message=False, agent_mode=mode == 'agent',
+        compare_mode=mode == 'compare', use_web='true',
+        search_context='Synthetic prefetched context' if mode == 'compare' else None,
+    )
+    rag_allowed = policy == 'normal' and str(use_rag).lower() != 'false'
+    assert len(received) == 1
+    assert search.call_count == int(rag_allowed)
+    assert received[0]['use_rag'] is rag_allowed
+    if rag_allowed:
+        search.assert_called_once_with(message, k=5, owner='tester')
+        assert ctx.rag_sources == [{
+            'filename': 'fixture.txt', 'snippet': 'Synthetic retention document', 'similarity': 0.99,
+        }]
+    else:
+        assert ctx.rag_sources == []
+    text = '\n'.join(m.get('content', '') for m in ctx.messages)
+    assert ('Synthetic retention document' in text) is rag_allowed
+
+    memory_allowed = policy == 'normal'
+    assert received[0]['use_memory'] is memory_allowed
+    assert memory.call_count == int(memory_allowed)
+    assert ('User identity synthetic memory' in text) is memory_allowed
+    assert bool(ctx.used_memories) is memory_allowed
+    skills_allowed = policy in {'normal', 'research_spinoff'}
+    assert received[0]['use_skills'] is skills_allowed
+    assert skills.call_count == int(skills_allowed and mode == 'agent')
+    assert ('fixture_skill' in text) is (skills_allowed and mode == 'agent')
+    web_allowed = preprocessing and policy != 'low_signal' and mode != 'compare'
+    assert received[0]['use_web'] is web_allowed
+    assert web.call_count == query.call_count == int(web_allowed)
+    assert ('Synthetic web context' in text) is web_allowed
+    assert bool(ctx.web_sources) is web_allowed
+    assert ('Synthetic prefetched context' in text) is (
+        mode == 'compare' and preprocessing and policy != 'low_signal')