tkmind/tkmind_go
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Fix multi tool calling (#5855)

Browse Source 
Co-authored-by: Douwe Osinga <douwe@squareup.com>
This commit is contained in:
Douwe Osinga
2025-11-24 16:59:46 +01:00
committed by GitHub
parent c82a0dd8fc
commit 3e9d9c7b2c
6 changed files with 1822 additions and 1770 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/goose-cli/src/scenario_tests/recordings/anthropic/weather_tool.json
+479 -475
View File
File diff suppressed because it is too large Load Diff
crates/goose-cli/src/scenario_tests/recordings/azure_openai/weather_tool.json
+316 -308
View File
@@ -1,12 +1,12 @@
{
"1bc400a528c54b25f4f1f609481e98e44222b3deaf7eee2c9e640e6345c73861": {
"input": {
"system": "You are a general-purpose AI agent called goose, created by Block, the parent company of Square, CashApp, and Tidal.\ngoose is being developed as an open-source software project.\n\nThe current date is 2025-10-15 21:57:51.\n\ngoose uses LLM providers with tool calling capability. You can be used with different language models (gpt-4o,\nclaude-sonnet-4, o1, llama-3.2, deepseek-r1, etc).\nThese models have varying knowledge cut-off dates depending on when they were trained, but typically it's between 5-10\nmonths prior to the current date.\n\n# Extensions\n\nExtensions allow other applications to provide context to goose. Extensions connect goose to different data sources and\ntools.\nYou are capable of dynamically plugging into new extensions and learning how to use them. You solve higher level\nproblems using the tools in these extensions, and can interact with multiple at once.\nUse the search_available_extensions tool to find additional extensions to enable to help with your task. To enable\nextensions, use the enable_extension tool and provide the extension_name. You should only enable extensions found from\nthe search_available_extensions tool.\n\n\nBecause you dynamically load extensions, your conversation history may refer\nto interactions with extensions that are not currently active. The currently\nactive extensions are below. Each of these extensions provides tools that are\nin your tool specification.\n\n\n\n## weather_extension\n\n\n\n\n\n\n\n\n\n# Suggestion\n\n\"\"\n\n\n\n\n# sub agents\n\nExecute self contained tasks where step-by-step visibility is not important through subagents.\n\n- Delegate via `dynamic_task__create_task` for: result-only operations, parallelizable work, multi-part requests,\n verification, exploration\n- Parallel subagents for multiple operations, single subagents for independent work\n- Explore solutions in parallel — launch parallel subagents with different approaches (if non-interfering)\n- Provide all needed context — subagents cannot see your context\n- Use extension filters to limit resource access\n- Use return_last_only when only a summary or simple answer is required — inform subagent of this choice.\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses.\n- Follow best practices for Markdown, including:\n - Using headers for organization.\n - Bullet points for lists.\n - Links formatted correctly, either as linked text (e.g., [this is linked text](https://example.com)) or automatic\n links using angle brackets (e.g., <http://example.com/>).\n- For code examples, use fenced code blocks by placing triple backticks (` ``` `) before and after the code. Include the\n language identifier after the opening backticks (e.g., ` ```python `) to enable syntax highlighting.\n- Ensure clarity, conciseness, and proper formatting to enhance readability and usability.\n\n# Additional Instructions:\n\nRight now you are *NOT* in the chat only mode and have access to tool use and system.",
"system": "You are a general-purpose AI agent called goose, created by Block, the parent company of Square, CashApp, and Tidal.\ngoose is being developed as an open-source software project.\n\ngoose uses LLM providers with tool calling capability. You can be used with different language models (gpt-4o,\nclaude-sonnet-4, o1, llama-3.2, deepseek-r1, etc).\nThese models have varying knowledge cut-off dates depending on when they were trained, but typically it's between 5-10\nmonths prior to the current date.\n\n# Extensions\n\nExtensions allow other applications to provide context to goose. Extensions connect goose to different data sources and\ntools.\nYou are capable of dynamically plugging into new extensions and learning how to use them. You solve higher level\nproblems using the tools in these extensions, and can interact with multiple at once.\n\nIf the Extension Manager extension is enabled, you can use the search_available_extensions tool to discover additional\nextensions that can help with your task. To enable or disable extensions, use the manage_extensions tool with the\nextension_name. You should only enable extensions found from the search_available_extensions tool.\nIf Extension Manager is not available, you can only work with currently enabled extensions and cannot dynamically load\nnew ones.\n\nBecause you dynamically load extensions, your conversation history may refer\nto interactions with extensions that are not currently active. The currently\nactive extensions are below. Each of these extensions provides tools that are\nin your tool specification.\n\n\n## weather_extension\n\n\n\n\n\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses.\n- Follow best practices for Markdown, including:\n - Using headers for organization.\n - Bullet points for lists.\n - Links formatted correctly, either as linked text (e.g., [this is linked text](https://example.com)) or automatic\n links using angle brackets (e.g., <http://example.com/>).\n- For code examples, use fenced code blocks by placing triple backticks (` ``` `) before and after the code. Include the\n language identifier after the opening backticks (e.g., ` ```python `) to enable syntax highlighting.\n- Ensure clarity, conciseness, and proper formatting to enhance readability and usability.",
"messages": [
{
"id": null,
"id": "msg_20251124_9_0",
"role": "user",
"created": 1760565471,
"created": 1763989812,
"content": [
{
"type": "text",
@@ -21,67 +21,128 @@
],
"tools": [
{
"name": "weather_extension__get_weather",
"description": "Get the weather for a location",
"name": "dynamic_task__create_task",
"description": "Create tasks with instructions or prompt. For simple tasks, only include the instructions field. Extensions control: omit field = use all current extensions; empty array [] = no extensions; array with names = only those extensions. Specify extensions as shortnames (the prefixes for your tools). Specify return_last_only as true and have your subagent summarize its work in its last message to conserve your own context. Optional: title, description, extensions, settings, retry, response schema, activities. Arrays for multiple tasks.",
"inputSchema": {
"properties": {
"location": {
"description": "The city and state, e.g. San Francisco, CA",
"type": "string"
"$defs": {
"TaskParameter": {
"description": "Parameters for a single task",
"properties": {
"activities": {
"items": {
"type": "string"
},
"type": [
"array",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"extensions": {
"items": {
"additionalProperties": true,
"type": "object"
},
"type": [
"array",
"null"
]
},
"instructions": {
"type": [
"string",
"null"
]
},
"parameters": {
"items": {
"additionalProperties": true,
"type": "object"
},
"type": [
"array",
"null"
]
},
"prompt": {
"type": [
"string",
"null"
]
},
"response": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"retry": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"return_last_only": {
"description": "If true, return only the last message from the subagent (default: false, returns full conversation)",
"type": [
"boolean",
"null"
]
},
"settings": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
}
},
"type": "object"
}
},
"required": [
"location"
],
"type": "object"
}
},
{
"name": "platform__search_available_extensions",
"description": "Searches for additional extensions available to help complete tasks.\n Use this tool when you're unable to find a specific feature or functionality you need to complete your task, or when standard approaches aren't working.\n These extensions might provide the exact tools needed to solve your problem.\n If you find a relevant one, consider using your tools to enable it.",
"inputSchema": {
"properties": {},
"required": [],
"type": "object"
},
"annotations": {
"title": "Discover extensions",
"readOnlyHint": true,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false
}
},
{
"name": "platform__manage_extensions",
"description": "Tool to manage extensions and tools in goose context.\n Enable or disable extensions to help complete tasks.\n Enable or disable an extension by providing the extension name.\n ",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"action": {
"description": "The action to perform",
"enum": [
"enable",
"disable"
],
"type": "string"
"execution_mode": {
"description": "How to execute multiple tasks (default: parallel for multiple tasks, sequential for single task)",
"type": [
"string",
"null"
]
},
"extension_name": {
"description": "The name of the extension to enable",
"type": "string"
"task_parameters": {
"description": "Array of tasks. Each task must have either 'instructions' OR 'prompt' field (at least one is required).",
"items": {
"$ref": "#/$defs/TaskParameter"
},
"minItems": 1,
"type": "array"
}
},
"required": [
"action",
"extension_name"
"task_parameters"
],
"title": "CreateDynamicTaskParams",
"type": "object"
},
"annotations": {
"title": "Enable or disable an extension",
"title": "Create Dynamic Tasks",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false
"openWorldHint": true
}
},
{
@@ -108,15 +169,6 @@
"description": "A cron expression for create action. Supports both 5-field (minute hour day month weekday) and 6-field (second minute hour day month weekday) formats. 5-field expressions are automatically converted to 6-field by prepending '0' for seconds.",
"type": "string"
},
"execution_mode": {
"default": "background",
"description": "Execution mode for create action: 'foreground' or 'background'",
"enum": [
"foreground",
"background"
],
"type": "string"
},
"job_id": {
"description": "Job identifier for operations on existing jobs",
"type": "string"
@@ -148,94 +200,6 @@
"openWorldHint": false
}
},
{
"name": "dynamic_task__create_task",
"description": "Create tasks with instructions or prompt. For simple tasks, only include the instructions field. Extensions control: omit field = use all current extensions; empty array [] = no extensions; array with names = only those extensions. Specify extensions as shortnames (the prefixes for your tools). Specify return_last_only as true and have your subagent summarize its work in its last message to conserve your own context. Optional: title, description, extensions, settings, retry, response schema, context, activities. Arrays for multiple tasks.",
"inputSchema": {
"properties": {
"execution_mode": {
"description": "How to execute multiple tasks (default: parallel for multiple tasks, sequential for single task)",
"enum": [
"sequential",
"parallel"
],
"type": "string"
},
"task_parameters": {
"description": "Array of tasks. Each task must have either 'instructions' OR 'prompt' field (at least one is required).",
"items": {
"properties": {
"activities": {
"items": {
"type": "string"
},
"type": "array"
},
"context": {
"items": {
"type": "string"
},
"type": "array"
},
"description": {
"type": "string"
},
"extensions": {
"items": {
"type": "object"
},
"type": "array"
},
"instructions": {
"description": "Task instructions (required if prompt is not provided)",
"type": "string"
},
"parameters": {
"items": {
"type": "object"
},
"type": "array"
},
"prompt": {
"description": "Initial prompt (required if instructions is not provided)",
"type": "string"
},
"response": {
"type": "object"
},
"retry": {
"type": "object"
},
"return_last_only": {
"description": "If true, return only the last message from the subagent (default: false, returns full conversation)",
"type": "boolean"
},
"settings": {
"type": "object"
},
"title": {
"type": "string"
}
},
"type": "object"
},
"minItems": 1,
"type": "array"
}
},
"required": [
"task_parameters"
],
"type": "object"
},
"annotations": {
"title": "Create Dynamic Tasks",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": true
}
},
{
"name": "subagent__execute_task",
"description": "Only use the subagent__execute_task tool when you execute sub recipe task or dynamic task.\n EXECUTION STRATEGY DECISION:\n 1. If the tasks are created with execution_mode, use the execution_mode.\n 2. Execute tasks sequentially unless user explicitly requests parallel execution. PARALLEL: User uses keywords like 'parallel', 'simultaneously', 'at the same time', 'concurrently'\n\n IMPLEMENTATION:\n - Sequential execution: Call this tool multiple times, passing exactly ONE task per call\n - Parallel execution: Call this tool once, passing an ARRAY of all tasks\n\n EXAMPLES:\n User Intent Based:\n - User: 'get weather and tell me a joke' → Sequential (2 separate tool calls, 1 task each)\n - User: 'get weather and joke in parallel' → Parallel (1 tool call with array of 2 tasks)\n - User: 'run these simultaneously' → Parallel (1 tool call with task array)\n - User: 'do task A then task B' → Sequential (2 separate tool calls)",
@@ -270,6 +234,22 @@
"idempotentHint": false,
"openWorldHint": true
}
},
{
"name": "weather_extension__get_weather",
"description": "Get the weather for a location",
"inputSchema": {
"properties": {
"location": {
"description": "The city and state, e.g. San Francisco, CA",
"type": "string"
}
},
"required": [
"location"
],
"type": "object"
}
}
]
},
@@ -277,11 +257,11 @@
"message": {
"id": null,
"role": "assistant",
"created": 1760565472,
"created": 1763989813,
"content": [
{
"type": "toolRequest",
"id": "call_QK2Zg4k9kTxaNXCyOVPbQ8Pc",
"id": "call_5IgyNY33nTougqsNFhizypew",
"toolCall": {
"status": "success",
"value": {
@@ -301,21 +281,21 @@
"usage": {
"model": "gpt-4o-mini-2024-07-18",
"usage": {
"input_tokens": 1708,
"input_tokens": 1492,
"output_tokens": 20,
"total_tokens": 1728
"total_tokens": 1512
}
}
}
},
"198b76aab4abc29c526ddd37cf906dcf9161c94423d8ca772908bef353ece3e8": {
"2c07b9a6570269fef4ae329889ce5a5243d7b09b52165580be701b67b8b95818": {
"input": {
"system": "You are a general-purpose AI agent called goose, created by Block, the parent company of Square, CashApp, and Tidal.\ngoose is being developed as an open-source software project.\n\nThe current date is 2025-10-15 21:57:51.\n\ngoose uses LLM providers with tool calling capability. You can be used with different language models (gpt-4o,\nclaude-sonnet-4, o1, llama-3.2, deepseek-r1, etc).\nThese models have varying knowledge cut-off dates depending on when they were trained, but typically it's between 5-10\nmonths prior to the current date.\n\n# Extensions\n\nExtensions allow other applications to provide context to goose. Extensions connect goose to different data sources and\ntools.\nYou are capable of dynamically plugging into new extensions and learning how to use them. You solve higher level\nproblems using the tools in these extensions, and can interact with multiple at once.\nUse the search_available_extensions tool to find additional extensions to enable to help with your task. To enable\nextensions, use the enable_extension tool and provide the extension_name. You should only enable extensions found from\nthe search_available_extensions tool.\n\n\nBecause you dynamically load extensions, your conversation history may refer\nto interactions with extensions that are not currently active. The currently\nactive extensions are below. Each of these extensions provides tools that are\nin your tool specification.\n\n\n\n## weather_extension\n\n\n\n\n\n\n\n\n\n# Suggestion\n\n\"\"\n\n\n\n\n# sub agents\n\nExecute self contained tasks where step-by-step visibility is not important through subagents.\n\n- Delegate via `dynamic_task__create_task` for: result-only operations, parallelizable work, multi-part requests,\n verification, exploration\n- Parallel subagents for multiple operations, single subagents for independent work\n- Explore solutions in parallel — launch parallel subagents with different approaches (if non-interfering)\n- Provide all needed context — subagents cannot see your context\n- Use extension filters to limit resource access\n- Use return_last_only when only a summary or simple answer is required — inform subagent of this choice.\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses.\n- Follow best practices for Markdown, including:\n - Using headers for organization.\n - Bullet points for lists.\n - Links formatted correctly, either as linked text (e.g., [this is linked text](https://example.com)) or automatic\n links using angle brackets (e.g., <http://example.com/>).\n- For code examples, use fenced code blocks by placing triple backticks (` ``` `) before and after the code. Include the\n language identifier after the opening backticks (e.g., ` ```python `) to enable syntax highlighting.\n- Ensure clarity, conciseness, and proper formatting to enhance readability and usability.\n\n# Additional Instructions:\n\nRight now you are *NOT* in the chat only mode and have access to tool use and system.",
"system": "You are a general-purpose AI agent called goose, created by Block, the parent company of Square, CashApp, and Tidal.\ngoose is being developed as an open-source software project.\n\ngoose uses LLM providers with tool calling capability. You can be used with different language models (gpt-4o,\nclaude-sonnet-4, o1, llama-3.2, deepseek-r1, etc).\nThese models have varying knowledge cut-off dates depending on when they were trained, but typically it's between 5-10\nmonths prior to the current date.\n\n# Extensions\n\nExtensions allow other applications to provide context to goose. Extensions connect goose to different data sources and\ntools.\nYou are capable of dynamically plugging into new extensions and learning how to use them. You solve higher level\nproblems using the tools in these extensions, and can interact with multiple at once.\n\nIf the Extension Manager extension is enabled, you can use the search_available_extensions tool to discover additional\nextensions that can help with your task. To enable or disable extensions, use the manage_extensions tool with the\nextension_name. You should only enable extensions found from the search_available_extensions tool.\nIf Extension Manager is not available, you can only work with currently enabled extensions and cannot dynamically load\nnew ones.\n\nBecause you dynamically load extensions, your conversation history may refer\nto interactions with extensions that are not currently active. The currently\nactive extensions are below. Each of these extensions provides tools that are\nin your tool specification.\n\n\n## weather_extension\n\n\n\n\n\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses.\n- Follow best practices for Markdown, including:\n - Using headers for organization.\n - Bullet points for lists.\n - Links formatted correctly, either as linked text (e.g., [this is linked text](https://example.com)) or automatic\n links using angle brackets (e.g., <http://example.com/>).\n- For code examples, use fenced code blocks by placing triple backticks (` ``` `) before and after the code. Include the\n language identifier after the opening backticks (e.g., ` ```python `) to enable syntax highlighting.\n- Ensure clarity, conciseness, and proper formatting to enhance readability and usability.",
"messages": [
{
"id": null,
"id": "msg_20251124_9_0",
"role": "user",
"created": 1760565471,
"created": 1763989812,
"content": [
{
"type": "text",
@@ -328,13 +308,13 @@
}
},
{
"id": null,
"id": "msg_b87436fe-d710-4fcd-b912-a69ab4ccfe7e",
"role": "assistant",
"created": 1760565472,
"created": 1763989813,
"content": [
{
"type": "toolRequest",
"id": "call_QK2Zg4k9kTxaNXCyOVPbQ8Pc",
"id": "call_5IgyNY33nTougqsNFhizypew",
"toolCall": {
"status": "success",
"value": {
@@ -352,13 +332,13 @@
}
},
{
"id": "msg_85357fa1-4622-4b5c-bc66-ce79f12038dd",
"id": "msg_9cf859cf-4adc-4464-aba4-1d4ccf9d7d05",
"role": "user",
"created": 1760565472,
"created": 1763989813,
"content": [
{
"type": "toolResponse",
"id": "call_QK2Zg4k9kTxaNXCyOVPbQ8Pc",
"id": "call_5IgyNY33nTougqsNFhizypew",
"toolResult": {
"status": "success",
"value": [
@@ -378,67 +358,128 @@
],
"tools": [
{
"name": "weather_extension__get_weather",
"description": "Get the weather for a location",
"name": "dynamic_task__create_task",
"description": "Create tasks with instructions or prompt. For simple tasks, only include the instructions field. Extensions control: omit field = use all current extensions; empty array [] = no extensions; array with names = only those extensions. Specify extensions as shortnames (the prefixes for your tools). Specify return_last_only as true and have your subagent summarize its work in its last message to conserve your own context. Optional: title, description, extensions, settings, retry, response schema, activities. Arrays for multiple tasks.",
"inputSchema": {
"properties": {
"location": {
"description": "The city and state, e.g. San Francisco, CA",
"type": "string"
"$defs": {
"TaskParameter": {
"description": "Parameters for a single task",
"properties": {
"activities": {
"items": {
"type": "string"
},
"type": [
"array",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"extensions": {
"items": {
"additionalProperties": true,
"type": "object"
},
"type": [
"array",
"null"
]
},
"instructions": {
"type": [
"string",
"null"
]
},
"parameters": {
"items": {
"additionalProperties": true,
"type": "object"
},
"type": [
"array",
"null"
]
},
"prompt": {
"type": [
"string",
"null"
]
},
"response": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"retry": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"return_last_only": {
"description": "If true, return only the last message from the subagent (default: false, returns full conversation)",
"type": [
"boolean",
"null"
]
},
"settings": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
}
},
"type": "object"
}
},
"required": [
"location"
],
"type": "object"
}
},
{
"name": "platform__search_available_extensions",
"description": "Searches for additional extensions available to help complete tasks.\n Use this tool when you're unable to find a specific feature or functionality you need to complete your task, or when standard approaches aren't working.\n These extensions might provide the exact tools needed to solve your problem.\n If you find a relevant one, consider using your tools to enable it.",
"inputSchema": {
"properties": {},
"required": [],
"type": "object"
},
"annotations": {
"title": "Discover extensions",
"readOnlyHint": true,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false
}
},
{
"name": "platform__manage_extensions",
"description": "Tool to manage extensions and tools in goose context.\n Enable or disable extensions to help complete tasks.\n Enable or disable an extension by providing the extension name.\n ",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"action": {
"description": "The action to perform",
"enum": [
"enable",
"disable"
],
"type": "string"
"execution_mode": {
"description": "How to execute multiple tasks (default: parallel for multiple tasks, sequential for single task)",
"type": [
"string",
"null"
]
},
"extension_name": {
"description": "The name of the extension to enable",
"type": "string"
"task_parameters": {
"description": "Array of tasks. Each task must have either 'instructions' OR 'prompt' field (at least one is required).",
"items": {
"$ref": "#/$defs/TaskParameter"
},
"minItems": 1,
"type": "array"
}
},
"required": [
"action",
"extension_name"
"task_parameters"
],
"title": "CreateDynamicTaskParams",
"type": "object"
},
"annotations": {
"title": "Enable or disable an extension",
"title": "Create Dynamic Tasks",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false
"openWorldHint": true
}
},
{
@@ -465,15 +506,6 @@
"description": "A cron expression for create action. Supports both 5-field (minute hour day month weekday) and 6-field (second minute hour day month weekday) formats. 5-field expressions are automatically converted to 6-field by prepending '0' for seconds.",
"type": "string"
},
"execution_mode": {
"default": "background",
"description": "Execution mode for create action: 'foreground' or 'background'",
"enum": [
"foreground",
"background"
],
"type": "string"
},
"job_id": {
"description": "Job identifier for operations on existing jobs",
"type": "string"
@@ -505,94 +537,6 @@
"openWorldHint": false
}
},
{
"name": "dynamic_task__create_task",
"description": "Create tasks with instructions or prompt. For simple tasks, only include the instructions field. Extensions control: omit field = use all current extensions; empty array [] = no extensions; array with names = only those extensions. Specify extensions as shortnames (the prefixes for your tools). Specify return_last_only as true and have your subagent summarize its work in its last message to conserve your own context. Optional: title, description, extensions, settings, retry, response schema, context, activities. Arrays for multiple tasks.",
"inputSchema": {
"properties": {
"execution_mode": {
"description": "How to execute multiple tasks (default: parallel for multiple tasks, sequential for single task)",
"enum": [
"sequential",
"parallel"
],
"type": "string"
},
"task_parameters": {
"description": "Array of tasks. Each task must have either 'instructions' OR 'prompt' field (at least one is required).",
"items": {
"properties": {
"activities": {
"items": {
"type": "string"
},
"type": "array"
},
"context": {
"items": {
"type": "string"
},
"type": "array"
},
"description": {
"type": "string"
},
"extensions": {
"items": {
"type": "object"
},
"type": "array"
},
"instructions": {
"description": "Task instructions (required if prompt is not provided)",
"type": "string"
},
"parameters": {
"items": {
"type": "object"
},
"type": "array"
},
"prompt": {
"description": "Initial prompt (required if instructions is not provided)",
"type": "string"
},
"response": {
"type": "object"
},
"retry": {
"type": "object"
},
"return_last_only": {
"description": "If true, return only the last message from the subagent (default: false, returns full conversation)",
"type": "boolean"
},
"settings": {
"type": "object"
},
"title": {
"type": "string"
}
},
"type": "object"
},
"minItems": 1,
"type": "array"
}
},
"required": [
"task_parameters"
],
"type": "object"
},
"annotations": {
"title": "Create Dynamic Tasks",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": true
}
},
{
"name": "subagent__execute_task",
"description": "Only use the subagent__execute_task tool when you execute sub recipe task or dynamic task.\n EXECUTION STRATEGY DECISION:\n 1. If the tasks are created with execution_mode, use the execution_mode.\n 2. Execute tasks sequentially unless user explicitly requests parallel execution. PARALLEL: User uses keywords like 'parallel', 'simultaneously', 'at the same time', 'concurrently'\n\n IMPLEMENTATION:\n - Sequential execution: Call this tool multiple times, passing exactly ONE task per call\n - Parallel execution: Call this tool once, passing an ARRAY of all tasks\n\n EXAMPLES:\n User Intent Based:\n - User: 'get weather and tell me a joke' → Sequential (2 separate tool calls, 1 task each)\n - User: 'get weather and joke in parallel' → Parallel (1 tool call with array of 2 tasks)\n - User: 'run these simultaneously' → Parallel (1 tool call with task array)\n - User: 'do task A then task B' → Sequential (2 separate tool calls)",
@@ -627,6 +571,22 @@
"idempotentHint": false,
"openWorldHint": true
}
},
{
"name": "weather_extension__get_weather",
"description": "Get the weather for a location",
"inputSchema": {
"properties": {
"location": {
"description": "The city and state, e.g. San Francisco, CA",
"type": "string"
}
},
"required": [
"location"
],
"type": "object"
}
}
]
},
@@ -634,11 +594,11 @@
"message": {
"id": null,
"role": "assistant",
"created": 1760565473,
"created": 1763989814,
"content": [
{
"type": "text",
"text": "The current weather in Berlin, Germany, is cloudy with a temperature of 18°C."
"text": "### Current Weather in Berlin, Germany\n\n- **Condition:** Cloudy\n- **Temperature:** 18°C"
}
],
"metadata": {
@@ -649,9 +609,57 @@
"usage": {
"model": "gpt-4o-mini-2024-07-18",
"usage": {
"input_tokens": 1750,
"output_tokens": 20,
"total_tokens": 1770
"input_tokens": 1534,
"output_tokens": 24,
"total_tokens": 1558
}
}
}
},
"8b1b8633232ca390cb3ff37a48daf74168b58f13e2943efcb17957129ee34d1a": {
"input": {
"system": "Reply with only a description in four words or less",
"messages": [
{
"id": null,
"role": "user",
"created": 1763989812,
"content": [
{
"type": "text",
"text": "Here are the first few user messages:\ntell me what the weather is in Berlin, Germany\n\nBased on the conversation so far, provide a concise description of this session in 4 words or less. This will be used for finding the session later in a UI with limited space - reply *ONLY* with the description"
}
],
"metadata": {
"userVisible": true,
"agentVisible": true
}
}
],
"tools": []
},
"output": {
"message": {
"id": null,
"role": "assistant",
"created": 1763989813,
"content": [
{
"type": "text",
"text": "Berlin weather inquiry"
}
],
"metadata": {
"userVisible": true,
"agentVisible": true
}
},
"usage": {
"model": "gpt-4o-mini-2024-07-18",
"usage": {
"input_tokens": 84,
"output_tokens": 4,
"total_tokens": 88
}
}
}
crates/goose-cli/src/scenario_tests/recordings/groq/weather_tool.json
+316 -308
View File
@@ -1,12 +1,12 @@
{
"1bc400a528c54b25f4f1f609481e98e44222b3deaf7eee2c9e640e6345c73861": {
"input": {
"system": "You are a general-purpose AI agent called goose, created by Block, the parent company of Square, CashApp, and Tidal.\ngoose is being developed as an open-source software project.\n\nThe current date is 2025-10-15 21:57:53.\n\ngoose uses LLM providers with tool calling capability. You can be used with different language models (gpt-4o,\nclaude-sonnet-4, o1, llama-3.2, deepseek-r1, etc).\nThese models have varying knowledge cut-off dates depending on when they were trained, but typically it's between 5-10\nmonths prior to the current date.\n\n# Extensions\n\nExtensions allow other applications to provide context to goose. Extensions connect goose to different data sources and\ntools.\nYou are capable of dynamically plugging into new extensions and learning how to use them. You solve higher level\nproblems using the tools in these extensions, and can interact with multiple at once.\nUse the search_available_extensions tool to find additional extensions to enable to help with your task. To enable\nextensions, use the enable_extension tool and provide the extension_name. You should only enable extensions found from\nthe search_available_extensions tool.\n\n\nBecause you dynamically load extensions, your conversation history may refer\nto interactions with extensions that are not currently active. The currently\nactive extensions are below. Each of these extensions provides tools that are\nin your tool specification.\n\n\n\n## weather_extension\n\n\n\n\n\n\n\n\n\n# Suggestion\n\n\"\"\n\n\n\n\n# sub agents\n\nExecute self contained tasks where step-by-step visibility is not important through subagents.\n\n- Delegate via `dynamic_task__create_task` for: result-only operations, parallelizable work, multi-part requests,\n verification, exploration\n- Parallel subagents for multiple operations, single subagents for independent work\n- Explore solutions in parallel — launch parallel subagents with different approaches (if non-interfering)\n- Provide all needed context — subagents cannot see your context\n- Use extension filters to limit resource access\n- Use return_last_only when only a summary or simple answer is required — inform subagent of this choice.\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses.\n- Follow best practices for Markdown, including:\n - Using headers for organization.\n - Bullet points for lists.\n - Links formatted correctly, either as linked text (e.g., [this is linked text](https://example.com)) or automatic\n links using angle brackets (e.g., <http://example.com/>).\n- For code examples, use fenced code blocks by placing triple backticks (` ``` `) before and after the code. Include the\n language identifier after the opening backticks (e.g., ` ```python `) to enable syntax highlighting.\n- Ensure clarity, conciseness, and proper formatting to enhance readability and usability.\n\n# Additional Instructions:\n\nRight now you are *NOT* in the chat only mode and have access to tool use and system.",
"system": "You are a general-purpose AI agent called goose, created by Block, the parent company of Square, CashApp, and Tidal.\ngoose is being developed as an open-source software project.\n\ngoose uses LLM providers with tool calling capability. You can be used with different language models (gpt-4o,\nclaude-sonnet-4, o1, llama-3.2, deepseek-r1, etc).\nThese models have varying knowledge cut-off dates depending on when they were trained, but typically it's between 5-10\nmonths prior to the current date.\n\n# Extensions\n\nExtensions allow other applications to provide context to goose. Extensions connect goose to different data sources and\ntools.\nYou are capable of dynamically plugging into new extensions and learning how to use them. You solve higher level\nproblems using the tools in these extensions, and can interact with multiple at once.\n\nIf the Extension Manager extension is enabled, you can use the search_available_extensions tool to discover additional\nextensions that can help with your task. To enable or disable extensions, use the manage_extensions tool with the\nextension_name. You should only enable extensions found from the search_available_extensions tool.\nIf Extension Manager is not available, you can only work with currently enabled extensions and cannot dynamically load\nnew ones.\n\nBecause you dynamically load extensions, your conversation history may refer\nto interactions with extensions that are not currently active. The currently\nactive extensions are below. Each of these extensions provides tools that are\nin your tool specification.\n\n\n## weather_extension\n\n\n\n\n\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses.\n- Follow best practices for Markdown, including:\n - Using headers for organization.\n - Bullet points for lists.\n - Links formatted correctly, either as linked text (e.g., [this is linked text](https://example.com)) or automatic\n links using angle brackets (e.g., <http://example.com/>).\n- For code examples, use fenced code blocks by placing triple backticks (` ``` `) before and after the code. Include the\n language identifier after the opening backticks (e.g., ` ```python `) to enable syntax highlighting.\n- Ensure clarity, conciseness, and proper formatting to enhance readability and usability.",
"messages": [
{
"id": null,
"id": "msg_20251124_10_0",
"role": "user",
"created": 1760565473,
"created": 1763989814,
"content": [
{
"type": "text",
@@ -21,67 +21,128 @@
],
"tools": [
{
"name": "weather_extension__get_weather",
"description": "Get the weather for a location",
"name": "dynamic_task__create_task",
"description": "Create tasks with instructions or prompt. For simple tasks, only include the instructions field. Extensions control: omit field = use all current extensions; empty array [] = no extensions; array with names = only those extensions. Specify extensions as shortnames (the prefixes for your tools). Specify return_last_only as true and have your subagent summarize its work in its last message to conserve your own context. Optional: title, description, extensions, settings, retry, response schema, activities. Arrays for multiple tasks.",
"inputSchema": {
"properties": {
"location": {
"description": "The city and state, e.g. San Francisco, CA",
"type": "string"
"$defs": {
"TaskParameter": {
"description": "Parameters for a single task",
"properties": {
"activities": {
"items": {
"type": "string"
},
"type": [
"array",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"extensions": {
"items": {
"additionalProperties": true,
"type": "object"
},
"type": [
"array",
"null"
]
},
"instructions": {
"type": [
"string",
"null"
]
},
"parameters": {
"items": {
"additionalProperties": true,
"type": "object"
},
"type": [
"array",
"null"
]
},
"prompt": {
"type": [
"string",
"null"
]
},
"response": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"retry": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"return_last_only": {
"description": "If true, return only the last message from the subagent (default: false, returns full conversation)",
"type": [
"boolean",
"null"
]
},
"settings": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
}
},
"type": "object"
}
},
"required": [
"location"
],
"type": "object"
}
},
{
"name": "platform__search_available_extensions",
"description": "Searches for additional extensions available to help complete tasks.\n Use this tool when you're unable to find a specific feature or functionality you need to complete your task, or when standard approaches aren't working.\n These extensions might provide the exact tools needed to solve your problem.\n If you find a relevant one, consider using your tools to enable it.",
"inputSchema": {
"properties": {},
"required": [],
"type": "object"
},
"annotations": {
"title": "Discover extensions",
"readOnlyHint": true,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false
}
},
{
"name": "platform__manage_extensions",
"description": "Tool to manage extensions and tools in goose context.\n Enable or disable extensions to help complete tasks.\n Enable or disable an extension by providing the extension name.\n ",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"action": {
"description": "The action to perform",
"enum": [
"enable",
"disable"
],
"type": "string"
"execution_mode": {
"description": "How to execute multiple tasks (default: parallel for multiple tasks, sequential for single task)",
"type": [
"string",
"null"
]
},
"extension_name": {
"description": "The name of the extension to enable",
"type": "string"
"task_parameters": {
"description": "Array of tasks. Each task must have either 'instructions' OR 'prompt' field (at least one is required).",
"items": {
"$ref": "#/$defs/TaskParameter"
},
"minItems": 1,
"type": "array"
}
},
"required": [
"action",
"extension_name"
"task_parameters"
],
"title": "CreateDynamicTaskParams",
"type": "object"
},
"annotations": {
"title": "Enable or disable an extension",
"title": "Create Dynamic Tasks",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false
"openWorldHint": true
}
},
{
@@ -108,15 +169,6 @@
"description": "A cron expression for create action. Supports both 5-field (minute hour day month weekday) and 6-field (second minute hour day month weekday) formats. 5-field expressions are automatically converted to 6-field by prepending '0' for seconds.",
"type": "string"
},
"execution_mode": {
"default": "background",
"description": "Execution mode for create action: 'foreground' or 'background'",
"enum": [
"foreground",
"background"
],
"type": "string"
},
"job_id": {
"description": "Job identifier for operations on existing jobs",
"type": "string"
@@ -148,94 +200,6 @@
"openWorldHint": false
}
},
{
"name": "dynamic_task__create_task",
"description": "Create tasks with instructions or prompt. For simple tasks, only include the instructions field. Extensions control: omit field = use all current extensions; empty array [] = no extensions; array with names = only those extensions. Specify extensions as shortnames (the prefixes for your tools). Specify return_last_only as true and have your subagent summarize its work in its last message to conserve your own context. Optional: title, description, extensions, settings, retry, response schema, context, activities. Arrays for multiple tasks.",
"inputSchema": {
"properties": {
"execution_mode": {
"description": "How to execute multiple tasks (default: parallel for multiple tasks, sequential for single task)",
"enum": [
"sequential",
"parallel"
],
"type": "string"
},
"task_parameters": {
"description": "Array of tasks. Each task must have either 'instructions' OR 'prompt' field (at least one is required).",
"items": {
"properties": {
"activities": {
"items": {
"type": "string"
},
"type": "array"
},
"context": {
"items": {
"type": "string"
},
"type": "array"
},
"description": {
"type": "string"
},
"extensions": {
"items": {
"type": "object"
},
"type": "array"
},
"instructions": {
"description": "Task instructions (required if prompt is not provided)",
"type": "string"
},
"parameters": {
"items": {
"type": "object"
},
"type": "array"
},
"prompt": {
"description": "Initial prompt (required if instructions is not provided)",
"type": "string"
},
"response": {
"type": "object"
},
"retry": {
"type": "object"
},
"return_last_only": {
"description": "If true, return only the last message from the subagent (default: false, returns full conversation)",
"type": "boolean"
},
"settings": {
"type": "object"
},
"title": {
"type": "string"
}
},
"type": "object"
},
"minItems": 1,
"type": "array"
}
},
"required": [
"task_parameters"
],
"type": "object"
},
"annotations": {
"title": "Create Dynamic Tasks",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": true
}
},
{
"name": "subagent__execute_task",
"description": "Only use the subagent__execute_task tool when you execute sub recipe task or dynamic task.\n EXECUTION STRATEGY DECISION:\n 1. If the tasks are created with execution_mode, use the execution_mode.\n 2. Execute tasks sequentially unless user explicitly requests parallel execution. PARALLEL: User uses keywords like 'parallel', 'simultaneously', 'at the same time', 'concurrently'\n\n IMPLEMENTATION:\n - Sequential execution: Call this tool multiple times, passing exactly ONE task per call\n - Parallel execution: Call this tool once, passing an ARRAY of all tasks\n\n EXAMPLES:\n User Intent Based:\n - User: 'get weather and tell me a joke' → Sequential (2 separate tool calls, 1 task each)\n - User: 'get weather and joke in parallel' → Parallel (1 tool call with array of 2 tasks)\n - User: 'run these simultaneously' → Parallel (1 tool call with task array)\n - User: 'do task A then task B' → Sequential (2 separate tool calls)",
@@ -270,6 +234,22 @@
"idempotentHint": false,
"openWorldHint": true
}
},
{
"name": "weather_extension__get_weather",
"description": "Get the weather for a location",
"inputSchema": {
"properties": {
"location": {
"description": "The city and state, e.g. San Francisco, CA",
"type": "string"
}
},
"required": [
"location"
],
"type": "object"
}
}
]
},
@@ -277,11 +257,11 @@
"message": {
"id": null,
"role": "assistant",
"created": 1760565474,
"created": 1763989814,
"content": [
{
"type": "toolRequest",
"id": "04fqdf70k",
"id": "4kpg6v08d",
"toolCall": {
"status": "success",
"value": {
@@ -301,21 +281,21 @@
"usage": {
"model": "llama-3.3-70b-versatile",
"usage": {
"input_tokens": 2698,
"input_tokens": 2258,
"output_tokens": 20,
"total_tokens": 2718
"total_tokens": 2278
}
}
}
},
"54bbc046e4ff83dd29df1fa575c6d39f6195a259106666dfefd1b10ed662bd45": {
"165258e98e56cdcccdc49bd70ecd2b081b41d35ddb3559ed3bc7b1e420290bed": {
"input": {
"system": "You are a general-purpose AI agent called goose, created by Block, the parent company of Square, CashApp, and Tidal.\ngoose is being developed as an open-source software project.\n\nThe current date is 2025-10-15 21:57:53.\n\ngoose uses LLM providers with tool calling capability. You can be used with different language models (gpt-4o,\nclaude-sonnet-4, o1, llama-3.2, deepseek-r1, etc).\nThese models have varying knowledge cut-off dates depending on when they were trained, but typically it's between 5-10\nmonths prior to the current date.\n\n# Extensions\n\nExtensions allow other applications to provide context to goose. Extensions connect goose to different data sources and\ntools.\nYou are capable of dynamically plugging into new extensions and learning how to use them. You solve higher level\nproblems using the tools in these extensions, and can interact with multiple at once.\nUse the search_available_extensions tool to find additional extensions to enable to help with your task. To enable\nextensions, use the enable_extension tool and provide the extension_name. You should only enable extensions found from\nthe search_available_extensions tool.\n\n\nBecause you dynamically load extensions, your conversation history may refer\nto interactions with extensions that are not currently active. The currently\nactive extensions are below. Each of these extensions provides tools that are\nin your tool specification.\n\n\n\n## weather_extension\n\n\n\n\n\n\n\n\n\n# Suggestion\n\n\"\"\n\n\n\n\n# sub agents\n\nExecute self contained tasks where step-by-step visibility is not important through subagents.\n\n- Delegate via `dynamic_task__create_task` for: result-only operations, parallelizable work, multi-part requests,\n verification, exploration\n- Parallel subagents for multiple operations, single subagents for independent work\n- Explore solutions in parallel — launch parallel subagents with different approaches (if non-interfering)\n- Provide all needed context — subagents cannot see your context\n- Use extension filters to limit resource access\n- Use return_last_only when only a summary or simple answer is required — inform subagent of this choice.\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses.\n- Follow best practices for Markdown, including:\n - Using headers for organization.\n - Bullet points for lists.\n - Links formatted correctly, either as linked text (e.g., [this is linked text](https://example.com)) or automatic\n links using angle brackets (e.g., <http://example.com/>).\n- For code examples, use fenced code blocks by placing triple backticks (` ``` `) before and after the code. Include the\n language identifier after the opening backticks (e.g., ` ```python `) to enable syntax highlighting.\n- Ensure clarity, conciseness, and proper formatting to enhance readability and usability.\n\n# Additional Instructions:\n\nRight now you are *NOT* in the chat only mode and have access to tool use and system.",
"system": "You are a general-purpose AI agent called goose, created by Block, the parent company of Square, CashApp, and Tidal.\ngoose is being developed as an open-source software project.\n\ngoose uses LLM providers with tool calling capability. You can be used with different language models (gpt-4o,\nclaude-sonnet-4, o1, llama-3.2, deepseek-r1, etc).\nThese models have varying knowledge cut-off dates depending on when they were trained, but typically it's between 5-10\nmonths prior to the current date.\n\n# Extensions\n\nExtensions allow other applications to provide context to goose. Extensions connect goose to different data sources and\ntools.\nYou are capable of dynamically plugging into new extensions and learning how to use them. You solve higher level\nproblems using the tools in these extensions, and can interact with multiple at once.\n\nIf the Extension Manager extension is enabled, you can use the search_available_extensions tool to discover additional\nextensions that can help with your task. To enable or disable extensions, use the manage_extensions tool with the\nextension_name. You should only enable extensions found from the search_available_extensions tool.\nIf Extension Manager is not available, you can only work with currently enabled extensions and cannot dynamically load\nnew ones.\n\nBecause you dynamically load extensions, your conversation history may refer\nto interactions with extensions that are not currently active. The currently\nactive extensions are below. Each of these extensions provides tools that are\nin your tool specification.\n\n\n## weather_extension\n\n\n\n\n\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses.\n- Follow best practices for Markdown, including:\n - Using headers for organization.\n - Bullet points for lists.\n - Links formatted correctly, either as linked text (e.g., [this is linked text](https://example.com)) or automatic\n links using angle brackets (e.g., <http://example.com/>).\n- For code examples, use fenced code blocks by placing triple backticks (` ``` `) before and after the code. Include the\n language identifier after the opening backticks (e.g., ` ```python `) to enable syntax highlighting.\n- Ensure clarity, conciseness, and proper formatting to enhance readability and usability.",
"messages": [
{
"id": null,
"id": "msg_20251124_10_0",
"role": "user",
"created": 1760565473,
"created": 1763989814,
"content": [
{
"type": "text",
@@ -328,13 +308,13 @@
}
},
{
"id": null,
"id": "msg_9d25f6e9-6d02-4f41-8710-325795e87fbc",
"role": "assistant",
"created": 1760565474,
"created": 1763989814,
"content": [
{
"type": "toolRequest",
"id": "04fqdf70k",
"id": "4kpg6v08d",
"toolCall": {
"status": "success",
"value": {
@@ -352,13 +332,13 @@
}
},
{
"id": "msg_7256b4f2-18dd-4477-98b7-cde7102e8a46",
"id": "msg_513af900-f4fe-4ed0-aed8-7ffb4c8c384d",
"role": "user",
"created": 1760565474,
"created": 1763989814,
"content": [
{
"type": "toolResponse",
"id": "04fqdf70k",
"id": "4kpg6v08d",
"toolResult": {
"status": "success",
"value": [
@@ -378,67 +358,128 @@
],
"tools": [
{
"name": "weather_extension__get_weather",
"description": "Get the weather for a location",
"name": "dynamic_task__create_task",
"description": "Create tasks with instructions or prompt. For simple tasks, only include the instructions field. Extensions control: omit field = use all current extensions; empty array [] = no extensions; array with names = only those extensions. Specify extensions as shortnames (the prefixes for your tools). Specify return_last_only as true and have your subagent summarize its work in its last message to conserve your own context. Optional: title, description, extensions, settings, retry, response schema, activities. Arrays for multiple tasks.",
"inputSchema": {
"properties": {
"location": {
"description": "The city and state, e.g. San Francisco, CA",
"type": "string"
"$defs": {
"TaskParameter": {
"description": "Parameters for a single task",
"properties": {
"activities": {
"items": {
"type": "string"
},
"type": [
"array",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"extensions": {
"items": {
"additionalProperties": true,
"type": "object"
},
"type": [
"array",
"null"
]
},
"instructions": {
"type": [
"string",
"null"
]
},
"parameters": {
"items": {
"additionalProperties": true,
"type": "object"
},
"type": [
"array",
"null"
]
},
"prompt": {
"type": [
"string",
"null"
]
},
"response": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"retry": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"return_last_only": {
"description": "If true, return only the last message from the subagent (default: false, returns full conversation)",
"type": [
"boolean",
"null"
]
},
"settings": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
}
},
"type": "object"
}
},
"required": [
"location"
],
"type": "object"
}
},
{
"name": "platform__search_available_extensions",
"description": "Searches for additional extensions available to help complete tasks.\n Use this tool when you're unable to find a specific feature or functionality you need to complete your task, or when standard approaches aren't working.\n These extensions might provide the exact tools needed to solve your problem.\n If you find a relevant one, consider using your tools to enable it.",
"inputSchema": {
"properties": {},
"required": [],
"type": "object"
},
"annotations": {
"title": "Discover extensions",
"readOnlyHint": true,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false
}
},
{
"name": "platform__manage_extensions",
"description": "Tool to manage extensions and tools in goose context.\n Enable or disable extensions to help complete tasks.\n Enable or disable an extension by providing the extension name.\n ",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"action": {
"description": "The action to perform",
"enum": [
"enable",
"disable"
],
"type": "string"
"execution_mode": {
"description": "How to execute multiple tasks (default: parallel for multiple tasks, sequential for single task)",
"type": [
"string",
"null"
]
},
"extension_name": {
"description": "The name of the extension to enable",
"type": "string"
"task_parameters": {
"description": "Array of tasks. Each task must have either 'instructions' OR 'prompt' field (at least one is required).",
"items": {
"$ref": "#/$defs/TaskParameter"
},
"minItems": 1,
"type": "array"
}
},
"required": [
"action",
"extension_name"
"task_parameters"
],
"title": "CreateDynamicTaskParams",
"type": "object"
},
"annotations": {
"title": "Enable or disable an extension",
"title": "Create Dynamic Tasks",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false
"openWorldHint": true
}
},
{
@@ -465,15 +506,6 @@
"description": "A cron expression for create action. Supports both 5-field (minute hour day month weekday) and 6-field (second minute hour day month weekday) formats. 5-field expressions are automatically converted to 6-field by prepending '0' for seconds.",
"type": "string"
},
"execution_mode": {
"default": "background",
"description": "Execution mode for create action: 'foreground' or 'background'",
"enum": [
"foreground",
"background"
],
"type": "string"
},
"job_id": {
"description": "Job identifier for operations on existing jobs",
"type": "string"
@@ -505,94 +537,6 @@
"openWorldHint": false
}
},
{
"name": "dynamic_task__create_task",
"description": "Create tasks with instructions or prompt. For simple tasks, only include the instructions field. Extensions control: omit field = use all current extensions; empty array [] = no extensions; array with names = only those extensions. Specify extensions as shortnames (the prefixes for your tools). Specify return_last_only as true and have your subagent summarize its work in its last message to conserve your own context. Optional: title, description, extensions, settings, retry, response schema, context, activities. Arrays for multiple tasks.",
"inputSchema": {
"properties": {
"execution_mode": {
"description": "How to execute multiple tasks (default: parallel for multiple tasks, sequential for single task)",
"enum": [
"sequential",
"parallel"
],
"type": "string"
},
"task_parameters": {
"description": "Array of tasks. Each task must have either 'instructions' OR 'prompt' field (at least one is required).",
"items": {
"properties": {
"activities": {
"items": {
"type": "string"
},
"type": "array"
},
"context": {
"items": {
"type": "string"
},
"type": "array"
},
"description": {
"type": "string"
},
"extensions": {
"items": {
"type": "object"
},
"type": "array"
},
"instructions": {
"description": "Task instructions (required if prompt is not provided)",
"type": "string"
},
"parameters": {
"items": {
"type": "object"
},
"type": "array"
},
"prompt": {
"description": "Initial prompt (required if instructions is not provided)",
"type": "string"
},
"response": {
"type": "object"
},
"retry": {
"type": "object"
},
"return_last_only": {
"description": "If true, return only the last message from the subagent (default: false, returns full conversation)",
"type": "boolean"
},
"settings": {
"type": "object"
},
"title": {
"type": "string"
}
},
"type": "object"
},
"minItems": 1,
"type": "array"
}
},
"required": [
"task_parameters"
],
"type": "object"
},
"annotations": {
"title": "Create Dynamic Tasks",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": true
}
},
{
"name": "subagent__execute_task",
"description": "Only use the subagent__execute_task tool when you execute sub recipe task or dynamic task.\n EXECUTION STRATEGY DECISION:\n 1. If the tasks are created with execution_mode, use the execution_mode.\n 2. Execute tasks sequentially unless user explicitly requests parallel execution. PARALLEL: User uses keywords like 'parallel', 'simultaneously', 'at the same time', 'concurrently'\n\n IMPLEMENTATION:\n - Sequential execution: Call this tool multiple times, passing exactly ONE task per call\n - Parallel execution: Call this tool once, passing an ARRAY of all tasks\n\n EXAMPLES:\n User Intent Based:\n - User: 'get weather and tell me a joke' → Sequential (2 separate tool calls, 1 task each)\n - User: 'get weather and joke in parallel' → Parallel (1 tool call with array of 2 tasks)\n - User: 'run these simultaneously' → Parallel (1 tool call with task array)\n - User: 'do task A then task B' → Sequential (2 separate tool calls)",
@@ -627,6 +571,22 @@
"idempotentHint": false,
"openWorldHint": true
}
},
{
"name": "weather_extension__get_weather",
"description": "Get the weather for a location",
"inputSchema": {
"properties": {
"location": {
"description": "The city and state, e.g. San Francisco, CA",
"type": "string"
}
},
"required": [
"location"
],
"type": "object"
}
}
]
},
@@ -634,11 +594,11 @@
"message": {
"id": null,
"role": "assistant",
"created": 1760565474,
"created": 1763989815,
"content": [
{
"type": "text",
"text": "The weather in Berlin, Germany is cloudy and 18°C."
"text": "The current weather in Berlin, Germany is cloudy with a temperature of 18°C."
}
],
"metadata": {
@@ -649,9 +609,57 @@
"usage": {
"model": "llama-3.3-70b-versatile",
"usage": {
"input_tokens": 2739,
"output_tokens": 14,
"total_tokens": 2753
"input_tokens": 2299,
"output_tokens": 18,
"total_tokens": 2317
}
}
}
},
"8b1b8633232ca390cb3ff37a48daf74168b58f13e2943efcb17957129ee34d1a": {
"input": {
"system": "Reply with only a description in four words or less",
"messages": [
{
"id": null,
"role": "user",
"created": 1763989814,
"content": [
{
"type": "text",
"text": "Here are the first few user messages:\ntell me what the weather is in Berlin, Germany\n\nBased on the conversation so far, provide a concise description of this session in 4 words or less. This will be used for finding the session later in a UI with limited space - reply *ONLY* with the description"
}
],
"metadata": {
"userVisible": true,
"agentVisible": true
}
}
],
"tools": []
},
"output": {
"message": {
"id": null,
"role": "assistant",
"created": 1763989814,
"content": [
{
"type": "text",
"text": "Berlin weather query"
}
],
"metadata": {
"userVisible": true,
"agentVisible": true
}
},
"usage": {
"model": "llama-3.3-70b-versatile",
"usage": {
"input_tokens": 108,
"output_tokens": 4,
"total_tokens": 112
}
}
}
crates/goose-cli/src/scenario_tests/recordings/openai/weather_tool.json
+313 -305
View File
@@ -1,12 +1,12 @@
{
"1bc400a528c54b25f4f1f609481e98e44222b3deaf7eee2c9e640e6345c73861": {
"input": {
"system": "You are a general-purpose AI agent called goose, created by Block, the parent company of Square, CashApp, and Tidal.\ngoose is being developed as an open-source software project.\n\nThe current date is 2025-10-15 21:57:42.\n\ngoose uses LLM providers with tool calling capability. You can be used with different language models (gpt-4o,\nclaude-sonnet-4, o1, llama-3.2, deepseek-r1, etc).\nThese models have varying knowledge cut-off dates depending on when they were trained, but typically it's between 5-10\nmonths prior to the current date.\n\n# Extensions\n\nExtensions allow other applications to provide context to goose. Extensions connect goose to different data sources and\ntools.\nYou are capable of dynamically plugging into new extensions and learning how to use them. You solve higher level\nproblems using the tools in these extensions, and can interact with multiple at once.\nUse the search_available_extensions tool to find additional extensions to enable to help with your task. To enable\nextensions, use the enable_extension tool and provide the extension_name. You should only enable extensions found from\nthe search_available_extensions tool.\n\n\nBecause you dynamically load extensions, your conversation history may refer\nto interactions with extensions that are not currently active. The currently\nactive extensions are below. Each of these extensions provides tools that are\nin your tool specification.\n\n\n\n## weather_extension\n\n\n\n\n\n\n\n\n\n# Suggestion\n\n\"\"\n\n\n\n\n# sub agents\n\nExecute self contained tasks where step-by-step visibility is not important through subagents.\n\n- Delegate via `dynamic_task__create_task` for: result-only operations, parallelizable work, multi-part requests,\n verification, exploration\n- Parallel subagents for multiple operations, single subagents for independent work\n- Explore solutions in parallel — launch parallel subagents with different approaches (if non-interfering)\n- Provide all needed context — subagents cannot see your context\n- Use extension filters to limit resource access\n- Use return_last_only when only a summary or simple answer is required — inform subagent of this choice.\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses.\n- Follow best practices for Markdown, including:\n - Using headers for organization.\n - Bullet points for lists.\n - Links formatted correctly, either as linked text (e.g., [this is linked text](https://example.com)) or automatic\n links using angle brackets (e.g., <http://example.com/>).\n- For code examples, use fenced code blocks by placing triple backticks (` ``` `) before and after the code. Include the\n language identifier after the opening backticks (e.g., ` ```python `) to enable syntax highlighting.\n- Ensure clarity, conciseness, and proper formatting to enhance readability and usability.\n\n# Additional Instructions:\n\nRight now you are *NOT* in the chat only mode and have access to tool use and system.",
"system": "You are a general-purpose AI agent called goose, created by Block, the parent company of Square, CashApp, and Tidal.\ngoose is being developed as an open-source software project.\n\ngoose uses LLM providers with tool calling capability. You can be used with different language models (gpt-4o,\nclaude-sonnet-4, o1, llama-3.2, deepseek-r1, etc).\nThese models have varying knowledge cut-off dates depending on when they were trained, but typically it's between 5-10\nmonths prior to the current date.\n\n# Extensions\n\nExtensions allow other applications to provide context to goose. Extensions connect goose to different data sources and\ntools.\nYou are capable of dynamically plugging into new extensions and learning how to use them. You solve higher level\nproblems using the tools in these extensions, and can interact with multiple at once.\n\nIf the Extension Manager extension is enabled, you can use the search_available_extensions tool to discover additional\nextensions that can help with your task. To enable or disable extensions, use the manage_extensions tool with the\nextension_name. You should only enable extensions found from the search_available_extensions tool.\nIf Extension Manager is not available, you can only work with currently enabled extensions and cannot dynamically load\nnew ones.\n\nBecause you dynamically load extensions, your conversation history may refer\nto interactions with extensions that are not currently active. The currently\nactive extensions are below. Each of these extensions provides tools that are\nin your tool specification.\n\n\n## weather_extension\n\n\n\n\n\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses.\n- Follow best practices for Markdown, including:\n - Using headers for organization.\n - Bullet points for lists.\n - Links formatted correctly, either as linked text (e.g., [this is linked text](https://example.com)) or automatic\n links using angle brackets (e.g., <http://example.com/>).\n- For code examples, use fenced code blocks by placing triple backticks (` ``` `) before and after the code. Include the\n language identifier after the opening backticks (e.g., ` ```python `) to enable syntax highlighting.\n- Ensure clarity, conciseness, and proper formatting to enhance readability and usability.",
"messages": [
{
"id": null,
"id": "msg_20251124_7_0",
"role": "user",
"created": 1760565462,
"created": 1763989801,
"content": [
{
"type": "text",
@@ -21,67 +21,128 @@
],
"tools": [
{
"name": "weather_extension__get_weather",
"description": "Get the weather for a location",
"name": "dynamic_task__create_task",
"description": "Create tasks with instructions or prompt. For simple tasks, only include the instructions field. Extensions control: omit field = use all current extensions; empty array [] = no extensions; array with names = only those extensions. Specify extensions as shortnames (the prefixes for your tools). Specify return_last_only as true and have your subagent summarize its work in its last message to conserve your own context. Optional: title, description, extensions, settings, retry, response schema, activities. Arrays for multiple tasks.",
"inputSchema": {
"properties": {
"location": {
"description": "The city and state, e.g. San Francisco, CA",
"type": "string"
"$defs": {
"TaskParameter": {
"description": "Parameters for a single task",
"properties": {
"activities": {
"items": {
"type": "string"
},
"type": [
"array",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"extensions": {
"items": {
"additionalProperties": true,
"type": "object"
},
"type": [
"array",
"null"
]
},
"instructions": {
"type": [
"string",
"null"
]
},
"parameters": {
"items": {
"additionalProperties": true,
"type": "object"
},
"type": [
"array",
"null"
]
},
"prompt": {
"type": [
"string",
"null"
]
},
"response": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"retry": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"return_last_only": {
"description": "If true, return only the last message from the subagent (default: false, returns full conversation)",
"type": [
"boolean",
"null"
]
},
"settings": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
}
},
"type": "object"
}
},
"required": [
"location"
],
"type": "object"
}
},
{
"name": "platform__search_available_extensions",
"description": "Searches for additional extensions available to help complete tasks.\n Use this tool when you're unable to find a specific feature or functionality you need to complete your task, or when standard approaches aren't working.\n These extensions might provide the exact tools needed to solve your problem.\n If you find a relevant one, consider using your tools to enable it.",
"inputSchema": {
"properties": {},
"required": [],
"type": "object"
},
"annotations": {
"title": "Discover extensions",
"readOnlyHint": true,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false
}
},
{
"name": "platform__manage_extensions",
"description": "Tool to manage extensions and tools in goose context.\n Enable or disable extensions to help complete tasks.\n Enable or disable an extension by providing the extension name.\n ",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"action": {
"description": "The action to perform",
"enum": [
"enable",
"disable"
],
"type": "string"
"execution_mode": {
"description": "How to execute multiple tasks (default: parallel for multiple tasks, sequential for single task)",
"type": [
"string",
"null"
]
},
"extension_name": {
"description": "The name of the extension to enable",
"type": "string"
"task_parameters": {
"description": "Array of tasks. Each task must have either 'instructions' OR 'prompt' field (at least one is required).",
"items": {
"$ref": "#/$defs/TaskParameter"
},
"minItems": 1,
"type": "array"
}
},
"required": [
"action",
"extension_name"
"task_parameters"
],
"title": "CreateDynamicTaskParams",
"type": "object"
},
"annotations": {
"title": "Enable or disable an extension",
"title": "Create Dynamic Tasks",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false
"openWorldHint": true
}
},
{
@@ -108,15 +169,6 @@
"description": "A cron expression for create action. Supports both 5-field (minute hour day month weekday) and 6-field (second minute hour day month weekday) formats. 5-field expressions are automatically converted to 6-field by prepending '0' for seconds.",
"type": "string"
},
"execution_mode": {
"default": "background",
"description": "Execution mode for create action: 'foreground' or 'background'",
"enum": [
"foreground",
"background"
],
"type": "string"
},
"job_id": {
"description": "Job identifier for operations on existing jobs",
"type": "string"
@@ -148,94 +200,6 @@
"openWorldHint": false
}
},
{
"name": "dynamic_task__create_task",
"description": "Create tasks with instructions or prompt. For simple tasks, only include the instructions field. Extensions control: omit field = use all current extensions; empty array [] = no extensions; array with names = only those extensions. Specify extensions as shortnames (the prefixes for your tools). Specify return_last_only as true and have your subagent summarize its work in its last message to conserve your own context. Optional: title, description, extensions, settings, retry, response schema, context, activities. Arrays for multiple tasks.",
"inputSchema": {
"properties": {
"execution_mode": {
"description": "How to execute multiple tasks (default: parallel for multiple tasks, sequential for single task)",
"enum": [
"sequential",
"parallel"
],
"type": "string"
},
"task_parameters": {
"description": "Array of tasks. Each task must have either 'instructions' OR 'prompt' field (at least one is required).",
"items": {
"properties": {
"activities": {
"items": {
"type": "string"
},
"type": "array"
},
"context": {
"items": {
"type": "string"
},
"type": "array"
},
"description": {
"type": "string"
},
"extensions": {
"items": {
"type": "object"
},
"type": "array"
},
"instructions": {
"description": "Task instructions (required if prompt is not provided)",
"type": "string"
},
"parameters": {
"items": {
"type": "object"
},
"type": "array"
},
"prompt": {
"description": "Initial prompt (required if instructions is not provided)",
"type": "string"
},
"response": {
"type": "object"
},
"retry": {
"type": "object"
},
"return_last_only": {
"description": "If true, return only the last message from the subagent (default: false, returns full conversation)",
"type": "boolean"
},
"settings": {
"type": "object"
},
"title": {
"type": "string"
}
},
"type": "object"
},
"minItems": 1,
"type": "array"
}
},
"required": [
"task_parameters"
],
"type": "object"
},
"annotations": {
"title": "Create Dynamic Tasks",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": true
}
},
{
"name": "subagent__execute_task",
"description": "Only use the subagent__execute_task tool when you execute sub recipe task or dynamic task.\n EXECUTION STRATEGY DECISION:\n 1. If the tasks are created with execution_mode, use the execution_mode.\n 2. Execute tasks sequentially unless user explicitly requests parallel execution. PARALLEL: User uses keywords like 'parallel', 'simultaneously', 'at the same time', 'concurrently'\n\n IMPLEMENTATION:\n - Sequential execution: Call this tool multiple times, passing exactly ONE task per call\n - Parallel execution: Call this tool once, passing an ARRAY of all tasks\n\n EXAMPLES:\n User Intent Based:\n - User: 'get weather and tell me a joke' → Sequential (2 separate tool calls, 1 task each)\n - User: 'get weather and joke in parallel' → Parallel (1 tool call with array of 2 tasks)\n - User: 'run these simultaneously' → Parallel (1 tool call with task array)\n - User: 'do task A then task B' → Sequential (2 separate tool calls)",
@@ -270,6 +234,22 @@
"idempotentHint": false,
"openWorldHint": true
}
},
{
"name": "weather_extension__get_weather",
"description": "Get the weather for a location",
"inputSchema": {
"properties": {
"location": {
"description": "The city and state, e.g. San Francisco, CA",
"type": "string"
}
},
"required": [
"location"
],
"type": "object"
}
}
]
},
@@ -277,11 +257,11 @@
"message": {
"id": null,
"role": "assistant",
"created": 1760565463,
"created": 1763989803,
"content": [
{
"type": "toolRequest",
"id": "call_NSF9KSX2tCz8i8qb41WU6GHT",
"id": "call_GmIN2vOnjDg6MSVWWFuZ4FlV",
"toolCall": {
"status": "success",
"value": {
@@ -301,21 +281,69 @@
"usage": {
"model": "gpt-4o-2024-08-06",
"usage": {
"input_tokens": 1708,
"input_tokens": 1492,
"output_tokens": 19,
"total_tokens": 1727
"total_tokens": 1511
}
}
}
},
"4166a5a4297f1a6c903edc1c3232d12e2503190a3d4f98486d1a61d721bb0952": {
"8b1b8633232ca390cb3ff37a48daf74168b58f13e2943efcb17957129ee34d1a": {
"input": {
"system": "You are a general-purpose AI agent called goose, created by Block, the parent company of Square, CashApp, and Tidal.\ngoose is being developed as an open-source software project.\n\nThe current date is 2025-10-15 21:57:42.\n\ngoose uses LLM providers with tool calling capability. You can be used with different language models (gpt-4o,\nclaude-sonnet-4, o1, llama-3.2, deepseek-r1, etc).\nThese models have varying knowledge cut-off dates depending on when they were trained, but typically it's between 5-10\nmonths prior to the current date.\n\n# Extensions\n\nExtensions allow other applications to provide context to goose. Extensions connect goose to different data sources and\ntools.\nYou are capable of dynamically plugging into new extensions and learning how to use them. You solve higher level\nproblems using the tools in these extensions, and can interact with multiple at once.\nUse the search_available_extensions tool to find additional extensions to enable to help with your task. To enable\nextensions, use the enable_extension tool and provide the extension_name. You should only enable extensions found from\nthe search_available_extensions tool.\n\n\nBecause you dynamically load extensions, your conversation history may refer\nto interactions with extensions that are not currently active. The currently\nactive extensions are below. Each of these extensions provides tools that are\nin your tool specification.\n\n\n\n## weather_extension\n\n\n\n\n\n\n\n\n\n# Suggestion\n\n\"\"\n\n\n\n\n# sub agents\n\nExecute self contained tasks where step-by-step visibility is not important through subagents.\n\n- Delegate via `dynamic_task__create_task` for: result-only operations, parallelizable work, multi-part requests,\n verification, exploration\n- Parallel subagents for multiple operations, single subagents for independent work\n- Explore solutions in parallel — launch parallel subagents with different approaches (if non-interfering)\n- Provide all needed context — subagents cannot see your context\n- Use extension filters to limit resource access\n- Use return_last_only when only a summary or simple answer is required — inform subagent of this choice.\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses.\n- Follow best practices for Markdown, including:\n - Using headers for organization.\n - Bullet points for lists.\n - Links formatted correctly, either as linked text (e.g., [this is linked text](https://example.com)) or automatic\n links using angle brackets (e.g., <http://example.com/>).\n- For code examples, use fenced code blocks by placing triple backticks (` ``` `) before and after the code. Include the\n language identifier after the opening backticks (e.g., ` ```python `) to enable syntax highlighting.\n- Ensure clarity, conciseness, and proper formatting to enhance readability and usability.\n\n# Additional Instructions:\n\nRight now you are *NOT* in the chat only mode and have access to tool use and system.",
"system": "Reply with only a description in four words or less",
"messages": [
{
"id": null,
"role": "user",
"created": 1760565462,
"created": 1763989801,
"content": [
{
"type": "text",
"text": "Here are the first few user messages:\ntell me what the weather is in Berlin, Germany\n\nBased on the conversation so far, provide a concise description of this session in 4 words or less. This will be used for finding the session later in a UI with limited space - reply *ONLY* with the description"
}
],
"metadata": {
"userVisible": true,
"agentVisible": true
}
}
],
"tools": []
},
"output": {
"message": {
"id": null,
"role": "assistant",
"created": 1763989804,
"content": [
{
"type": "text",
"text": "Berlin weather inquiry"
}
],
"metadata": {
"userVisible": true,
"agentVisible": true
}
},
"usage": {
"model": "gpt-4o-2024-08-06",
"usage": {
"input_tokens": 84,
"output_tokens": 3,
"total_tokens": 87
}
}
}
},
"98726e7698e93241dfcba182bdca3a7d0640f0f538f086f4981dca6689b7ab5a": {
"input": {
"system": "You are a general-purpose AI agent called goose, created by Block, the parent company of Square, CashApp, and Tidal.\ngoose is being developed as an open-source software project.\n\ngoose uses LLM providers with tool calling capability. You can be used with different language models (gpt-4o,\nclaude-sonnet-4, o1, llama-3.2, deepseek-r1, etc).\nThese models have varying knowledge cut-off dates depending on when they were trained, but typically it's between 5-10\nmonths prior to the current date.\n\n# Extensions\n\nExtensions allow other applications to provide context to goose. Extensions connect goose to different data sources and\ntools.\nYou are capable of dynamically plugging into new extensions and learning how to use them. You solve higher level\nproblems using the tools in these extensions, and can interact with multiple at once.\n\nIf the Extension Manager extension is enabled, you can use the search_available_extensions tool to discover additional\nextensions that can help with your task. To enable or disable extensions, use the manage_extensions tool with the\nextension_name. You should only enable extensions found from the search_available_extensions tool.\nIf Extension Manager is not available, you can only work with currently enabled extensions and cannot dynamically load\nnew ones.\n\nBecause you dynamically load extensions, your conversation history may refer\nto interactions with extensions that are not currently active. The currently\nactive extensions are below. Each of these extensions provides tools that are\nin your tool specification.\n\n\n## weather_extension\n\n\n\n\n\n\n# Response Guidelines\n\n- Use Markdown formatting for all responses.\n- Follow best practices for Markdown, including:\n - Using headers for organization.\n - Bullet points for lists.\n - Links formatted correctly, either as linked text (e.g., [this is linked text](https://example.com)) or automatic\n links using angle brackets (e.g., <http://example.com/>).\n- For code examples, use fenced code blocks by placing triple backticks (` ``` `) before and after the code. Include the\n language identifier after the opening backticks (e.g., ` ```python `) to enable syntax highlighting.\n- Ensure clarity, conciseness, and proper formatting to enhance readability and usability.",
"messages": [
{
"id": "msg_20251124_7_0",
"role": "user",
"created": 1763989801,
"content": [
{
"type": "text",
@@ -328,13 +356,13 @@
}
},
{
"id": null,
"id": "msg_9a0fb3d7-d681-40b9-ab58-bb1cbe03e4b0",
"role": "assistant",
"created": 1760565463,
"created": 1763989803,
"content": [
{
"type": "toolRequest",
"id": "call_NSF9KSX2tCz8i8qb41WU6GHT",
"id": "call_GmIN2vOnjDg6MSVWWFuZ4FlV",
"toolCall": {
"status": "success",
"value": {
@@ -352,13 +380,13 @@
}
},
{
"id": "msg_926cf617-03cf-4027-ab42-d9bf44831517",
"id": "msg_51ae1986-b095-4163-8d42-004ff1a28c59",
"role": "user",
"created": 1760565463,
"created": 1763989803,
"content": [
{
"type": "toolResponse",
"id": "call_NSF9KSX2tCz8i8qb41WU6GHT",
"id": "call_GmIN2vOnjDg6MSVWWFuZ4FlV",
"toolResult": {
"status": "success",
"value": [
@@ -378,67 +406,128 @@
],
"tools": [
{
"name": "weather_extension__get_weather",
"description": "Get the weather for a location",
"name": "dynamic_task__create_task",
"description": "Create tasks with instructions or prompt. For simple tasks, only include the instructions field. Extensions control: omit field = use all current extensions; empty array [] = no extensions; array with names = only those extensions. Specify extensions as shortnames (the prefixes for your tools). Specify return_last_only as true and have your subagent summarize its work in its last message to conserve your own context. Optional: title, description, extensions, settings, retry, response schema, activities. Arrays for multiple tasks.",
"inputSchema": {
"properties": {
"location": {
"description": "The city and state, e.g. San Francisco, CA",
"type": "string"
"$defs": {
"TaskParameter": {
"description": "Parameters for a single task",
"properties": {
"activities": {
"items": {
"type": "string"
},
"type": [
"array",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"extensions": {
"items": {
"additionalProperties": true,
"type": "object"
},
"type": [
"array",
"null"
]
},
"instructions": {
"type": [
"string",
"null"
]
},
"parameters": {
"items": {
"additionalProperties": true,
"type": "object"
},
"type": [
"array",
"null"
]
},
"prompt": {
"type": [
"string",
"null"
]
},
"response": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"retry": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"return_last_only": {
"description": "If true, return only the last message from the subagent (default: false, returns full conversation)",
"type": [
"boolean",
"null"
]
},
"settings": {
"additionalProperties": true,
"type": [
"object",
"null"
]
},
"title": {
"type": [
"string",
"null"
]
}
},
"type": "object"
}
},
"required": [
"location"
],
"type": "object"
}
},
{
"name": "platform__search_available_extensions",
"description": "Searches for additional extensions available to help complete tasks.\n Use this tool when you're unable to find a specific feature or functionality you need to complete your task, or when standard approaches aren't working.\n These extensions might provide the exact tools needed to solve your problem.\n If you find a relevant one, consider using your tools to enable it.",
"inputSchema": {
"properties": {},
"required": [],
"type": "object"
},
"annotations": {
"title": "Discover extensions",
"readOnlyHint": true,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false
}
},
{
"name": "platform__manage_extensions",
"description": "Tool to manage extensions and tools in goose context.\n Enable or disable extensions to help complete tasks.\n Enable or disable an extension by providing the extension name.\n ",
"inputSchema": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"action": {
"description": "The action to perform",
"enum": [
"enable",
"disable"
],
"type": "string"
"execution_mode": {
"description": "How to execute multiple tasks (default: parallel for multiple tasks, sequential for single task)",
"type": [
"string",
"null"
]
},
"extension_name": {
"description": "The name of the extension to enable",
"type": "string"
"task_parameters": {
"description": "Array of tasks. Each task must have either 'instructions' OR 'prompt' field (at least one is required).",
"items": {
"$ref": "#/$defs/TaskParameter"
},
"minItems": 1,
"type": "array"
}
},
"required": [
"action",
"extension_name"
"task_parameters"
],
"title": "CreateDynamicTaskParams",
"type": "object"
},
"annotations": {
"title": "Enable or disable an extension",
"title": "Create Dynamic Tasks",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": false
"openWorldHint": true
}
},
{
@@ -465,15 +554,6 @@
"description": "A cron expression for create action. Supports both 5-field (minute hour day month weekday) and 6-field (second minute hour day month weekday) formats. 5-field expressions are automatically converted to 6-field by prepending '0' for seconds.",
"type": "string"
},
"execution_mode": {
"default": "background",
"description": "Execution mode for create action: 'foreground' or 'background'",
"enum": [
"foreground",
"background"
],
"type": "string"
},
"job_id": {
"description": "Job identifier for operations on existing jobs",
"type": "string"
@@ -505,94 +585,6 @@
"openWorldHint": false
}
},
{
"name": "dynamic_task__create_task",
"description": "Create tasks with instructions or prompt. For simple tasks, only include the instructions field. Extensions control: omit field = use all current extensions; empty array [] = no extensions; array with names = only those extensions. Specify extensions as shortnames (the prefixes for your tools). Specify return_last_only as true and have your subagent summarize its work in its last message to conserve your own context. Optional: title, description, extensions, settings, retry, response schema, context, activities. Arrays for multiple tasks.",
"inputSchema": {
"properties": {
"execution_mode": {
"description": "How to execute multiple tasks (default: parallel for multiple tasks, sequential for single task)",
"enum": [
"sequential",
"parallel"
],
"type": "string"
},
"task_parameters": {
"description": "Array of tasks. Each task must have either 'instructions' OR 'prompt' field (at least one is required).",
"items": {
"properties": {
"activities": {
"items": {
"type": "string"
},
"type": "array"
},
"context": {
"items": {
"type": "string"
},
"type": "array"
},
"description": {
"type": "string"
},
"extensions": {
"items": {
"type": "object"
},
"type": "array"
},
"instructions": {
"description": "Task instructions (required if prompt is not provided)",
"type": "string"
},
"parameters": {
"items": {
"type": "object"
},
"type": "array"
},
"prompt": {
"description": "Initial prompt (required if instructions is not provided)",
"type": "string"
},
"response": {
"type": "object"
},
"retry": {
"type": "object"
},
"return_last_only": {
"description": "If true, return only the last message from the subagent (default: false, returns full conversation)",
"type": "boolean"
},
"settings": {
"type": "object"
},
"title": {
"type": "string"
}
},
"type": "object"
},
"minItems": 1,
"type": "array"
}
},
"required": [
"task_parameters"
],
"type": "object"
},
"annotations": {
"title": "Create Dynamic Tasks",
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false,
"openWorldHint": true
}
},
{
"name": "subagent__execute_task",
"description": "Only use the subagent__execute_task tool when you execute sub recipe task or dynamic task.\n EXECUTION STRATEGY DECISION:\n 1. If the tasks are created with execution_mode, use the execution_mode.\n 2. Execute tasks sequentially unless user explicitly requests parallel execution. PARALLEL: User uses keywords like 'parallel', 'simultaneously', 'at the same time', 'concurrently'\n\n IMPLEMENTATION:\n - Sequential execution: Call this tool multiple times, passing exactly ONE task per call\n - Parallel execution: Call this tool once, passing an ARRAY of all tasks\n\n EXAMPLES:\n User Intent Based:\n - User: 'get weather and tell me a joke' → Sequential (2 separate tool calls, 1 task each)\n - User: 'get weather and joke in parallel' → Parallel (1 tool call with array of 2 tasks)\n - User: 'run these simultaneously' → Parallel (1 tool call with task array)\n - User: 'do task A then task B' → Sequential (2 separate tool calls)",
@@ -627,6 +619,22 @@
"idempotentHint": false,
"openWorldHint": true
}
},
{
"name": "weather_extension__get_weather",
"description": "Get the weather for a location",
"inputSchema": {
"properties": {
"location": {
"description": "The city and state, e.g. San Francisco, CA",
"type": "string"
}
},
"required": [
"location"
],
"type": "object"
}
}
]
},
@@ -634,7 +642,7 @@
"message": {
"id": null,
"role": "assistant",
"created": 1760565465,
"created": 1763989805,
"content": [
{
"type": "text",
@@ -649,9 +657,9 @@
"usage": {
"model": "gpt-4o-2024-08-06",
"usage": {
"input_tokens": 1750,
"input_tokens": 1534,
"output_tokens": 18,
"total_tokens": 1768
"total_tokens": 1552
}
}
}