~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
Python academiaanthropicarxivbravedeep-researchencryptionhome-automationhomeserverlocallocal-deep-researchlocal-llmmistralollamaopenaipubmedresearchresearch-toolretrieval-augmented-generationsearxngself-hosted
test(errors): pin disclosure-table order for mixed-cue strings and the typed-unknown fallthrough (#7339)
LearningCircuitf8e18cd6a5e8
diff --git a/tests/error_handling/test_report_generator_disclosure.py b/tests/error_handling/test_report_generator_disclosure.pyindex ed4d9c3140..20521747e8 100644--- a/tests/error_handling/test_report_generator_disclosure.py+++ b/tests/error_handling/test_report_generator_disclosure.py@@ -107,6 +107,18 @@ def test_report_skips_error_shaped_partial_knowledge():"Wait a few minutes",id="rate-limit",),+ pytest.param(+ "Error: rate limit exceeded (Error type: unknown)",+ "provider's request limit",+ "Wait a few minutes",+ id="rate-limit-typed-unknown-fallthrough",+ ),+ pytest.param(+ "Error: Final answer synthesis failed due to LLM timeout",+ "request took too long",+ "increase the request timeout",+ id="synthesis-failed-mixed-timeout-cue",+ ),pytest.param("Error: connection lost during synthesis","connection to the LLM service failed",