ai: live-chat fixes from first real-model run

Three findings from running Qwen3-1.7B against the docker stack:
the llm image lost libgomp when the build tools were removed
(llama-server needs the OpenMP runtime); the Help prompt let the
small model answer from memory instead of the docs, so it now
requires search_help before any answer; and help search results
called the slug "doc" while get_help_doc's argument is "slug", so
the model invented slugs — the names now match.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

docker/llm/Dockerfile

@@ -6,7 +6,9 @@ RUN apt-get update && apt-get install -y curl ca-certificates
 # Build llama-server from the pinned release (single source of truth with native installs).
 COPY wrolpi/scripts/install_llama_cpp.sh /tmp/install_llama_cpp.sh
 RUN /tmp/install_llama_cpp.sh && rm /tmp/install_llama_cpp.sh \
-    && apt-get remove -y build-essential cmake && apt-get autoremove -y && apt-get clean
+    && apt-get remove -y build-essential cmake && apt-get autoremove -y \
+    # llama-server needs the OpenMP runtime, which the build-tool cleanup just removed.
+    && apt-get install -y libgomp1 && apt-get clean
 
 # The same startup scripts the native install uses.
 COPY scripts/start_llama_server.sh /opt/wrolpi/scripts/start_llama_server.sh

modules/ai/api.py

@@ -396,7 +396,7 @@ async def get_inventory(_: Request, slug: str):
 @openapi.definition(
     summary='Search the WROLPi help documentation',
     description='Search the WROLPi help documentation for how to use and repair WROLPi. Returns matching'
-                ' help pages with a snippet; read a full page with get_help_doc. Links are pages on the'
+                ' help pages with a snippet; read a full page by passing its slug to get_help_doc. Links are pages on the'
                 ' WROLPi help site.',
     body=schema.AIHelpSearchRequest,
 )

modules/ai/help_docs.py

@@ -133,7 +133,7 @@ def search_help(search_str: str, limit: int = 5) -> (List[dict], int):
     results = []
     for score, doc in scored[:limit]:
         result = dict(
-            doc=doc.slug,
+            slug=doc.slug,
             title=doc.title,
             link=help_doc_link(doc.slug),
             snippet=_snippet(doc.body, tokens),

modules/ai/modes.py

@@ -14,7 +14,8 @@ MODES = {
         system_prompt=(
             f'{COMMON_PROMPT}'
             ' Your job is to teach the user how to use WROLPi.'
-            ' Search the help documentation with search_help, read pages with get_help_doc, and answer'
+            ' You do NOT know how WROLPi works from memory: before answering ANY question, you MUST'
+            ' first call search_help, then read the matching page with get_help_doc, and answer only'
             ' from what the docs actually say.  Always include the link of every help page you used.'
             ' If the docs do not cover the question, say so.'
         ),

modules/ai/test/test_help_docs.py

@@ -31,14 +31,14 @@ def test_search_help_scoring(help_corpus):
     """Title matches outrank body matches; snippets show context."""
     results, total = help_docs.search_help('logs')
     assert total == 1
-    assert results[0]['doc'] == 'system/logs'
+    assert results[0]['slug'] == 'system/logs'
     assert results[0]['title'] == 'Logs'
     assert results[0]['link'] == '/system/logs/'
     assert 'journalctl' in results[0]['snippet'] or 'Logs' in results[0]['snippet']
 
     # 'videos' matches the videos doc far better than any other.
     results, _ = help_docs.search_help('downloading videos')
-    assert results[0]['doc'] == 'modules/videos'
+    assert results[0]['slug'] == 'modules/videos'
 
     # No matches.
     results, total = help_docs.search_help('xyzzy')
@@ -48,7 +48,7 @@ def test_search_help_scoring(help_corpus):
 def test_help_doc_cache_invalidation(help_corpus):
     """Edited files are re-parsed; deleted files leave the corpus."""
     results, _ = help_docs.search_help('welcome')
-    assert results[0]['doc'] == 'index'
+    assert results[0]['slug'] == 'index'
     assert results[0]['link'] == '/'
 
     (help_corpus / 'index.md').write_text('# Home\n\nGreetings, traveler.\n')
@@ -57,7 +57,7 @@ def test_help_doc_cache_invalidation(help_corpus):
     results, total = help_docs.search_help('welcome')
     assert total == 0
     results, _ = help_docs.search_help('greetings')
-    assert results[0]['doc'] == 'index'
+    assert results[0]['slug'] == 'index'
 
     (help_corpus / 'system/logs.md').unlink()
     _, total = help_docs.search_help('logs')
@@ -77,9 +77,9 @@ async def test_ai_help_endpoints(async_client, help_corpus):
     assert response.status_code == HTTPStatus.OK
     assert response.json['total'] == 1
     result = response.json['results'][0]
-    assert result['doc'] == 'system/logs'
+    assert result['slug'] == 'system/logs'
 
-    request, response = await async_client.get(f'/api/ai/help/{result["doc"]}')
+    request, response = await async_client.get(f'/api/ai/help/{result["slug"]}')
     assert response.status_code == HTTPStatus.OK
     assert response.json['title'] == 'Logs'
     assert 'journalctl' in response.json['content']