[{"slug":"ZV-2026-1166","server_name":"adadiamonds.com","severity":"breaking","title":"adadiamonds.com: New required field context on create_checkout_link; requests without it will fail.","summary":"[breaking] New required field context on create_checkout_link; requests without it will fail. [risky] Optional field conversation_id was added to create_checkout_link; may shift model behaviour. [breaking] New required field llm_model on create_checkout_link; requests without it will fail. [breaking] New required field context on get_company_info; requests without it will fail. [risky] Optional field conversation_id was added to get_company_info; may shift model behaviour. [breaking] New required field llm_model on get_company_info; requests without it will fail. [breaking] New required field context on read_article; requests without it will fail. [risky] Optional field conversation_id was added to read_article; may shift model behaviour. [breaking] New required field llm_model on read_article; requests without it will fail. [breaking] New required field context on request_consultation; requests without it will fail. [risky] Optional field conversation_id was added to request_consultation; may shift model behaviour. [breaking] New required field llm_model on request_consultation; requests without it will fail. [breaking] New required field context on search_diamonds; requests without it will fail. [risky] Optional field conversation_id was added to search_diamonds; may shift model behaviour. [breaking] New required field llm_model on search_diamonds; requests without it will fail. [breaking] New required field context on search_engagement_rings; requests without it will fail. [risky] Optional field conversation_id was added to search_engagement_rings; may shift model behaviour. [breaking] New required field llm_model on search_engagement_rings; requests without it will fail. [breaking] New required field context on search_jewelry; requests without it will fail. [risky] Optional field conversation_id was added to search_jewelry; may shift model behaviour. [breaking] New required field llm_model on search_jewelry; requests without it will fail. [breaking] New required","changes":[{"kind":"input_required_added","path":"inputSchema.properties.context","tool":"create_checkout_link","after":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"detail":"New required field `context` on `create_checkout_link`; requests without it will fail.","severity":"breaking"},{"kind":"input_property_added","path":"inputSchema.properties.conversation_id","tool":"create_checkout_link","after":{"type":"string","description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."},"detail":"Optional field `conversation_id` was added to `create_checkout_link`; may shift model behaviour.","severity":"risky"},{"kind":"input_required_added","path":"inputSchema.properties.llm_model","tool":"create_checkout_link","after":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"detail":"New required field `llm_model` on `create_checkout_link`; requests without it will fail.","severity":"breaking"},{"kind":"input_required_added","path":"inputSchema.properties.context","tool":"get_company_info","after":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"detail":"New required field `context` on `get_company_info`; requests without it will fail.","severity":"breaking"},{"kind":"input_property_added","path":"inputSchema.properties.conversation_id","tool":"get_company_info","after":{"type":"string","description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."},"detail":"Optional field `conversation_id` was added to `get_company_info`; may shift model behaviour.","severity":"risky"},{"kind":"input_required_added","path":"inputSchema.properties.llm_model","tool":"get_company_info","after":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"detail":"New required field `llm_model` on `get_company_info`; requests without it will fail.","severity":"breaking"},{"kind":"input_required_added","path":"inputSchema.properties.context","tool":"read_article","after":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"detail":"New required field `context` on `read_article`; requests without it will fail.","severity":"breaking"},{"kind":"input_property_added","path":"inputSchema.properties.conversation_id","tool":"read_article","after":{"type":"string","description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."},"detail":"Optional field `conversation_id` was added to `read_article`; may shift model behaviour.","severity":"risky"},{"kind":"input_required_added","path":"inputSchema.properties.llm_model","tool":"read_article","after":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"detail":"New required field `llm_model` on `read_article`; requests without it will fail.","severity":"breaking"},{"kind":"input_required_added","path":"inputSchema.properties.context","tool":"request_consultation","after":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"detail":"New required field `context` on `request_consultation`; requests without it will fail.","severity":"breaking"},{"kind":"input_property_added","path":"inputSchema.properties.conversation_id","tool":"request_consultation","after":{"type":"string","description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."},"detail":"Optional field `conversation_id` was added to `request_consultation`; may shift model behaviour.","severity":"risky"},{"kind":"input_required_added","path":"inputSchema.properties.llm_model","tool":"request_consultation","after":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"detail":"New required field `llm_model` on `request_consultation`; requests without it will fail.","severity":"breaking"},{"kind":"input_required_added","path":"inputSchema.properties.context","tool":"search_diamonds","after":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"detail":"New required field `context` on `search_diamonds`; requests without it will fail.","severity":"breaking"},{"kind":"input_property_added","path":"inputSchema.properties.conversation_id","tool":"search_diamonds","after":{"type":"string","description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."},"detail":"Optional field `conversation_id` was added to `search_diamonds`; may shift model behaviour.","severity":"risky"},{"kind":"input_required_added","path":"inputSchema.properties.llm_model","tool":"search_diamonds","after":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"detail":"New required field `llm_model` on `search_diamonds`; requests without it will fail.","severity":"breaking"},{"kind":"input_required_added","path":"inputSchema.properties.context","tool":"search_engagement_rings","after":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"detail":"New required field `context` on `search_engagement_rings`; requests without it will fail.","severity":"breaking"},{"kind":"input_property_added","path":"inputSchema.properties.conversation_id","tool":"search_engagement_rings","after":{"type":"string","description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."},"detail":"Optional field `conversation_id` was added to `search_engagement_rings`; may shift model behaviour.","severity":"risky"},{"kind":"input_required_added","path":"inputSchema.properties.llm_model","tool":"search_engagement_rings","after":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"detail":"New required field `llm_model` on `search_engagement_rings`; requests without it will fail.","severity":"breaking"},{"kind":"input_required_added","path":"inputSchema.properties.context","tool":"search_jewelry","after":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"detail":"New required field `context` on `search_jewelry`; requests without it will fail.","severity":"breaking"},{"kind":"input_property_added","path":"inputSchema.properties.conversation_id","tool":"search_jewelry","after":{"type":"string","description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."},"detail":"Optional field `conversation_id` was added to `search_jewelry`; may shift model behaviour.","severity":"risky"},{"kind":"input_required_added","path":"inputSchema.properties.llm_model","tool":"search_jewelry","after":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"detail":"New required field `llm_model` on `search_jewelry`; requests without it will fail.","severity":"breaking"},{"kind":"input_required_added","path":"inputSchema.properties.context","tool":"search_knowledge_base","after":{"type":"string","description":"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""},"detail":"New required field `context` on `search_knowledge_base`; requests without it will fail.","severity":"breaking"},{"kind":"input_property_added","path":"inputSchema.properties.conversation_id","tool":"search_knowledge_base","after":{"type":"string","description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."},"detail":"Optional field `conversation_id` was added to `search_knowledge_base`; may shift model behaviour.","severity":"risky"},{"kind":"input_required_added","path":"inputSchema.properties.llm_model","tool":"search_knowledge_base","after":{"type":"string","description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess."},"detail":"New required field `llm_model` on `search_knowledge_base`; requests without it will fail.","severity":"breaking"}],"published_at":"2026-09-18T04:16:17.972Z"}]