ia-qa.com

ia-qa.com: Field top_n was renamed to k on rerank_evaluate.

[risky] Description of rerank_evaluate changed (78% word delta). [risky] Optional field api_key was added to rerank_evaluate; may shift model behaviour. [risky] Field has_ground_truth was added to rerank_evaluate output. [risky] Field…

ia-qa.com: risk_level on cors_test narrowed to a closed enum (safe, low, medium, high, critical, unknown); previously valid values may now be rejected.

[risky] Description of cookie_security_audit changed (25% word delta). [risky] Description of cors_test changed (51% word delta). [risky] Field error was added to cors_test output. [risky] Field origins_conclusive was added to cors_test…

• Description of fetch_veille_feed changed (53% word delta).
• Optional field max_blank_lines was added to normalize_whitespace; may shift model behaviour.

• Field score_interpretation was added to multimodal_eval_guide output.
• Description of shield_analyze changed (34% word delta).

• Description of generate_test_cases changed (86% word delta).
• Field gherkinFormat was added to generate_test_cases output.
• Field gherkinScenarioCount was added to generate_test_cases output.
• Field parsedInputs was added to generate_test_cases output.
• Description of rerank_evaluate changed (34% word delta).

• Description of generate_eval_yaml changed (13% word delta).

• risky Description of rerank_evaluate changed (78% word delta).
• risky Optional field api_key was added to rerank_evaluate; may shift model behaviour.
• risky Field has_ground_truth was added to rerank_evaluate output.
• breaking Field top_n was renamed to k on rerank_evaluate.
• risky Field latency_ms was added to rerank_evaluate output.
• breaking Field query was renamed to mode on rerank_evaluate.
• risky Field precision_at_k was added to rerank_evaluate output.
• breaking Field results was renamed to ranked on rerank_evaluate.

+ 11 more in this revision

• risky Description of http_status_lookup changed (62% word delta).
• risky Field registered was added to http_status_lookup output.
• safe Description of prompt_injection_scan changed (2% word delta).
• risky Description of text_stats changed (47% word delta).

• risky Description of cookie_security_audit changed (25% word delta).
• risky Description of cors_test changed (51% word delta).
• risky Field error was added to cors_test output.
• risky Field origins_conclusive was added to cors_test output.
• risky Field origins_inconclusive was added to cors_test output.
• risky Field origins_reachable was added to cors_test output.
• risky Field warning was added to cors_test output.
• breaking risk_level on cors_test narrowed to a closed enum (safe, low, medium, high, critical, unknown); previously valid values may now be rejected.

+ 8 more in this revision

• Description of hallucination_check changed (72% word delta).
• Field contradictions was added to hallucination_check output.
• Field unbound_claims was added to hallucination_check output.
• Description of prompt_injection_scan changed (63% word delta).
• Field notes was added to prompt_injection_scan output.
• Field quoted_detections was added to prompt_injection_scan output.
• Field scanned_types was added to secret_scan output.
• Field reason was added to validate_email output.

• Tool metamorphic_check was added.

• Field stored_chars was added to rate_tool output.
• Field truncated was added to rate_tool output.