From 4e9c66ee25ed77858985765382f41d0cf22ea588 Mon Sep 17 00:00:00 2001 From: tanaka takashi Date: Tue, 20 Oct 2026 02:03:54 +0900 Subject: Improve web search region selection and normalize provider results Update ddgs to 9.16.0 and keep backend="auto" while preserving the LLM-facing query/max_results inputs and title/href/body result schema. Implementation: - Add OLLAMA_WEB_SEARCH_REGION with auto/us-en/jp-jp values, normalized configuration input, and a clear startup error for unsupported values. - In auto mode, detect kana after NFKC normalization and exclusion of URLs and site:/filetype: tokens. Select jp-jp for kana and us-en otherwise, without modifying the original query or sharing per-call region state. - Preserve href/url and body/snippet fallbacks and normalize None values. - Reject malformed HTTP(S) URLs without DNS lookups or extra requests. - Unwrap known Yahoo redirect URLs before excluding Bing aclick ads. - Represent missing and URL-only titles as empty strings rather than inventing titles from snippets. Preserve remaining provider order and allow fewer results after filtering, without additional searches. - Preserve provider exception propagation and identify ddgs in error logs. Coverage and documentation: - Add 72 regression cases for configuration, region routing, concurrency, public schemas, title/URL/ad boundaries, limits, and search_and_fetch continuation. Update existing provider mocks and log assertions. - Document the region environment setting and result semantics in both READMEs and tools-schema.md; update the changelog. - Keep only a short backend availability caveat in tools-schema.md and remove the temporary backend comparison, design, and validation docs. Validation: - pytest: 222 passed; ruff check . and mypy src/ passed. - uv lock --check and git diff --check passed. - Initial live acceptance: 56 searches plus 3 registry smoke checks; default-region auto succeeded 8/18 times and real ad filtering removed two ads. Stable relevance/title quality targets remain unmet because provider acquisition is unreliable. - Follow-up backend study: 234 comparative searches plus 3 Yahoo response diagnostics. Yahoo led individual backends at 9/18; restricted multi- backend combinations did not outperform the contemporaneous auto control. Authentication, access restrictions, temporary upstream failures, and Yahoo HTML/parser mismatches were observed. Do not claim search reliability is fixed or add backend configuration, custom retries, ranking changes, or challenge bypasses. Running app processes were not restarted; restart is needed to load the changes. --- tests/test_logging.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tests/test_logging.py') diff --git a/tests/test_logging.py b/tests/test_logging.py index ef6fbd2..68aeb97 100644 --- a/tests/test_logging.py +++ b/tests/test_logging.py @@ -73,7 +73,7 @@ def test_web_search_provider_error_is_written_to_server_log( def __exit__(self, *args): return None - def text(self, query, max_results=5): + def text(self, query, max_results=5, *, region, backend): raise RuntimeError("403 Forbidden") with patch("ollama_web.tools.search.DDGS", FailingDDGS), TestClient(create_app()): @@ -83,6 +83,6 @@ def test_web_search_provider_error_is_written_to_server_log( assert result == {"error": "RuntimeError: 403 Forbidden"} content = (data_dir / "server.log").read_text(encoding="utf-8") - assert "DuckDuckGo web search failed" in content + assert "ddgs web search failed" in content assert "RuntimeError: 403 Forbidden" in content assert "private search terms" not in content -- cgit v1.2.3