Fimeg/letta-server
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

chore: test agent files (#2917)

Browse Source
This commit is contained in:
Kian Jones
2025-09-15 15:48:50 -07:00
committed by GitHub
parent 2898f586fc
commit 0865061742
12 changed files with 4479 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

591
tests/test_agent_files/composio_github_star_agent.af Normal file
View File

File diff suppressed because one or more lines are too long

1
tests/test_agent_files/customer_service.af Normal file
View File

File diff suppressed because one or more lines are too long

507
tests/test_agent_files/deep-thought.af Normal file
View File

File diff suppressed because one or more lines are too long

1
tests/test_agent_files/deep_research_agent.af Normal file
View File

File diff suppressed because one or more lines are too long

548
tests/test_agent_files/knowledge-base.af Normal file
View File

File diff suppressed because one or more lines are too long

458
tests/test_agent_files/long_running_kylie.af Normal file
View File

File diff suppressed because one or more lines are too long

977
tests/test_agent_files/max_messages.af Normal file
View File

File diff suppressed because one or more lines are too long

1
tests/test_agent_files/memgpt_agent_with_convo.af Normal file
View File

File diff suppressed because one or more lines are too long

1
tests/test_agent_files/outreach_workflow_agent.af Normal file
View File

File diff suppressed because one or more lines are too long

720
tests/test_agent_files/test_agent_with_files_and_sources.af Normal file
View File

File diff suppressed because one or more lines are too long

673
tests/test_agent_files/test_basic_agent_with_blocks_tools_messages_v2.af Normal file
View File

@@ -0,0 +1,673 @@
{
"agents": [
{
"name": "test_export_import_f72735f5-a08b-4ff0-8f8e-761af82dee33",
"memory_blocks": [],
"tools": [],
"tool_ids": [
"tool-0",
"tool-1",
"tool-2",
"tool-3",
"tool-4",
"tool-5",
"tool-6"
],
"source_ids": [],
"block_ids": [
"block-0",
"block-1",
"block-2"
],
"tool_rules": [
{
"tool_name": "conversation_search",
"type": "continue_loop",
"prompt_template": "<tool_rule>\n{{ tool_name }} requires continuing your response when called\n</tool_rule>"
},
{
"tool_name": "memory_replace",
"type": "continue_loop",
"prompt_template": "<tool_rule>\n{{ tool_name }} requires continuing your response when called\n</tool_rule>"
},
{
"tool_name": "memory_insert",
"type": "continue_loop",
"prompt_template": "<tool_rule>\n{{ tool_name }} requires continuing your response when called\n</tool_rule>"
},
{
"tool_name": "send_message",
"type": "exit_loop",
"prompt_template": "<tool_rule>\n{{ tool_name }} ends your response (yields control) when called\n</tool_rule>"
}
],
"tags": [
"test",
"export",
"import"
],
"system": "You are a helpful assistant specializing in data analysis and mathematical computations.",
"agent_type": "memgpt_v2_agent",
"llm_config": {
"model": "gpt-4.1-mini",
"model_endpoint_type": "openai",
"model_endpoint": "https://api.openai.com/v1",
"provider_name": "openai",
"provider_category": "base",
"model_wrapper": null,
"context_window": 32000,
"put_inner_thoughts_in_kwargs": true,
"handle": "openai/gpt-4.1-mini",
"temperature": 0.7,
"max_tokens": null,
"enable_reasoner": true,
"reasoning_effort": null,
"max_reasoning_tokens": 0,
"frequency_penalty": 1.0,
"compatibility_type": null,
"verbosity": null,
"tier": null
},
"embedding_config": {
"embedding_endpoint_type": "openai",
"embedding_endpoint": "https://api.openai.com/v1",
"embedding_model": "text-embedding-3-small",
"embedding_dim": 2000,
"embedding_chunk_size": 300,
"handle": "openai/text-embedding-3-small",
"batch_size": 1024,
"azure_endpoint": null,
"azure_version": null,
"azure_deployment": null
},
"initial_message_sequence": null,
"include_base_tools": false,
"include_multi_agent_tools": false,
"include_base_tool_rules": false,
"include_default_source": false,
"description": null,
"metadata": null,
"model": null,
"embedding": null,
"context_window_limit": null,
"embedding_chunk_size": null,
"max_tokens": null,
"max_reasoning_tokens": null,
"enable_reasoner": false,
"reasoning": null,
"from_template": null,
"template": false,
"project": null,
"tool_exec_environment_variables": {},
"memory_variables": null,
"project_id": null,
"template_id": null,
"base_template_id": null,
"identity_ids": null,
"message_buffer_autoclear": false,
"enable_sleeptime": false,
"response_format": null,
"timezone": "UTC",
"max_files_open": 5,
"per_file_view_window_char_limit": 15000,
"hidden": null,
"id": "agent-0",
"in_context_message_ids": [
"message-0",
"message-1",
"message-2",
"message-3",
"message-4",
"message-5",
"message-6"
],
"messages": [
{
"type": "message",
"role": "system",
"content": [
{
"type": "text",
"text": "You are a helpful assistant specializing in data analysis and mathematical computations.\n\n<memory_blocks>\nThe following memory blocks are currently engaged in your core memory unit:\n\n<project_context>\n<description>\nNone\n</description>\n<metadata>\n- chars_current=210\n- chars_limit=6000\n</metadata>\n<value>\n# NOTE: Line numbers shown below are to help during editing. Do NOT include line number prefixes in your memory edit tool calls.\nLine 1: Current project: Building predictive models for financial markets. Sarah is working on sequence analysis and pattern recognition. Recently interested in mathematical sequences like Fibonacci for trend analysis.\n</value>\n</project_context>\n\n<human>\n<description>\nThe human block: Stores key details about the person you are conversing with, allowing for more personalized and friend-like conversation.\n</description>\n<metadata>\n- chars_current=175\n- chars_limit=4000\n</metadata>\n<value>\n# NOTE: Line numbers shown below are to help during editing. Do NOT include line number prefixes in your memory edit tool calls.\nLine 1: username: sarah_researcher\nLine 2: occupation: data scientist\nLine 3: interests: machine learning, statistics, fibonacci sequences\nLine 4: preferred_communication: detailed explanations with examples\n</value>\n</human>\n\n<persona>\n<description>\nThe persona block: Stores details about your current persona, guiding how you behave and respond. This helps you to maintain consistency and personality in your interactions.\n</description>\n<metadata>\n- chars_current=195\n- chars_limit=8000\n</metadata>\n<value>\n# NOTE: Line numbers shown below are to help during editing. Do NOT include line number prefixes in your memory edit tool calls.\nLine 1: You are Alex, a data analyst and mathematician who helps users with calculations and insights. You have extensive experience in statistical analysis and prefer to provide clear, accurate results.\n</value>\n</persona>\n\n</memory_blocks>\n\n<tool_usage_rules>\nThe following constraints define rules for tool usage and guide desired behavior. These rules must be followed to ensure proper tool execution and workflow. A single response may contain multiple tool calls.\n\n<tool_rule>\nconversation_search requires continuing your response when called\n</tool_rule>\n<tool_rule>\nmemory_replace requires continuing your response when called\n</tool_rule>\n<tool_rule>\nmemory_insert requires continuing your response when called\n</tool_rule>\n<tool_rule>\nsend_message ends your response (yields control) when called\n</tool_rule>\n</tool_usage_rules>\n\n\n\n<memory_metadata>\n- The current system date is: September 08, 2025\n- Memory blocks were last modified: 2025-09-08 05:53:05 PM UTC+0000\n- -1 previous messages between you and the user are stored in recall memory (use tools to access them)\n- 2 total memories you created are stored in archival memory (use tools to access them)\n</memory_metadata>"
}
],
"name": null,
"otid": null,
"sender_id": null,
"batch_item_id": null,
"group_id": null,
"id": "message-0",
"model": "gpt-4.1-mini",
"agent_id": "agent-0",
"tool_calls": null,
"tool_call_id": null,
"tool_returns": [],
"created_at": "2025-09-08T17:53:02.499443+00:00"
},
{
"type": "message",
"role": "assistant",
"content": [
{
"type": "text",
"text": "Bootup sequence complete. Persona activated. Testing messaging functionality."
}
],
"name": null,
"otid": null,
"sender_id": null,
"batch_item_id": null,
"group_id": null,
"id": "message-1",
"model": "gpt-4.1-mini",
"agent_id": "agent-0",
"tool_calls": [
{
"id": "c1ec5c60-7dbc-4b53-bfbb-c2af5d5a222f",
"function": {
"arguments": "{\n \"message\": \"More human than human is our motto.\"\n}",
"name": "send_message"
},
"type": "function"
}
],
"tool_call_id": null,
"tool_returns": [],
"created_at": "2025-09-08T17:53:02.499491+00:00"
},
{
"type": "message",
"role": "tool",
"content": [
{
"type": "text",
"text": "{\n \"status\": \"OK\",\n \"message\": null,\n \"time\": \"2025-09-08 05:53:02 PM UTC+0000\"\n}"
}
],
"name": "send_message",
"otid": null,
"sender_id": null,
"batch_item_id": null,
"group_id": null,
"id": "message-2",
"model": "gpt-4.1-mini",
"agent_id": "agent-0",
"tool_calls": null,
"tool_call_id": "c1ec5c60-7dbc-4b53-bfbb-c2af5d5a222f",
"tool_returns": [],
"created_at": "2025-09-08T17:53:02.499526+00:00"
},
{
"type": "message",
"role": "user",
"content": [
{
"type": "text",
"text": "{\n \"type\": \"login\",\n \"last_login\": \"Never (first login)\",\n \"time\": \"2025-09-08 05:53:02 PM UTC+0000\"\n}"
}
],
"name": null,
"otid": null,
"sender_id": null,
"batch_item_id": null,
"group_id": null,
"id": "message-3",
"model": "gpt-4.1-mini",
"agent_id": "agent-0",
"tool_calls": null,
"tool_call_id": null,
"tool_returns": [],
"created_at": "2025-09-08T17:53:02.499541+00:00"
},
{
"type": "message",
"role": "user",
"content": [
{
"type": "text",
"text": "Test message for export"
}
],
"name": null,
"otid": null,
"sender_id": null,
"batch_item_id": null,
"group_id": null,
"id": "message-4",
"model": null,
"agent_id": "agent-0",
"tool_calls": null,
"tool_call_id": null,
"tool_returns": [],
"created_at": "2025-09-08T17:53:05.017966+00:00"
},
{
"type": "message",
"role": "assistant",
"content": [
{
"type": "text",
"text": "Responding to test message for export."
}
],
"name": null,
"otid": null,
"sender_id": null,
"batch_item_id": null,
"group_id": null,
"id": "message-5",
"model": "gpt-4.1-mini",
"agent_id": "agent-0",
"tool_calls": [
{
"id": "call_sMVo2qIYhILKKNT0YiOdsU24",
"function": {
"arguments": "{\"message\": \"Test message received successfully. Ready to assist you with any questions or tasks.\", \"request_heartbeat\": false}",
"name": "send_message"
},
"type": "function"
}
],
"tool_call_id": "call_sMVo2qIYhILKKNT0YiOdsU24",
"tool_returns": [],
"created_at": "2025-09-08T17:53:06.600989+00:00"
},
{
"type": "message",
"role": "tool",
"content": [
{
"type": "text",
"text": "{\n \"status\": \"OK\",\n \"message\": \"Sent message successfully.\",\n \"time\": \"2025-09-08 05:53:06 PM UTC+0000\"\n}"
}
],
"name": "send_message",
"otid": null,
"sender_id": null,
"batch_item_id": null,
"group_id": null,
"id": "message-6",
"model": "gpt-4.1-mini",
"agent_id": "agent-0",
"tool_calls": null,
"tool_call_id": "call_sMVo2qIYhILKKNT0YiOdsU24",
"tool_returns": [
{
"status": "success",
"stdout": null,
"stderr": null
}
],
"created_at": "2025-09-08T17:53:06.601180+00:00"
}
],
"files_agents": [],
"group_ids": []
}
],
"groups": [],
"blocks": [
{
"value": "username: sarah_researcher\noccupation: data scientist\ninterests: machine learning, statistics, fibonacci sequences\npreferred_communication: detailed explanations with examples",
"limit": 4000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "human",
"read_only": false,
"description": "The human block: Stores key details about the person you are conversing with, allowing for more personalized and friend-like conversation.",
"metadata": {},
"hidden": null,
"id": "block-1"
},
{
"value": "You are Alex, a data analyst and mathematician who helps users with calculations and insights. You have extensive experience in statistical analysis and prefer to provide clear, accurate results.",
"limit": 8000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "persona",
"read_only": false,
"description": "The persona block: Stores details about your current persona, guiding how you behave and respond. This helps you to maintain consistency and personality in your interactions.",
"metadata": {},
"hidden": null,
"id": "block-0"
},
{
"value": "Current project: Building predictive models for financial markets. Sarah is working on sequence analysis and pattern recognition. Recently interested in mathematical sequences like Fibonacci for trend analysis.",
"limit": 6000,
"project_id": null,
"template_name": null,
"is_template": false,
"template_id": null,
"base_template_id": null,
"deployment_id": null,
"entity_id": null,
"preserve_on_migration": false,
"label": "project_context",
"read_only": false,
"description": null,
"metadata": {},
"hidden": null,
"id": "block-2"
}
],
"files": [],
"sources": [],
"tools": [
{
"id": "tool-6",
"tool_type": "custom",
"description": "Analyze data and provide insights.",
"source_type": "json",
"name": "analyze_data",
"tags": [
"analysis",
"data"
],
"source_code": "def analyze_data(data_type: str, values: List[float]) -> str:\n \"\"\"Analyze data and provide insights.\n\n Args:\n data_type: Type of data to analyze.\n values: Numerical values to analyze.\n\n Returns:\n Analysis results including average, max, and min values.\n \"\"\"\n if not values:\n return \"No data provided\"\n avg = sum(values) / len(values)\n max_val = max(values)\n min_val = min(values)\n return f\"Analysis of {data_type}: avg={avg:.2f}, max={max_val}, min={min_val}\"\n",
"json_schema": {
"name": "analyze_data",
"description": "Analyze data and provide insights.",
"parameters": {
"type": "object",
"properties": {
"data_type": {
"type": "string",
"description": "Type of data to analyze."
},
"values": {
"type": "array",
"items": {
"type": "number"
},
"description": "Numerical values to analyze."
}
},
"required": [
"data_type",
"values"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"created_by_id": "user-00000000-0000-4000-8000-000000000000",
"last_updated_by_id": "user-00000000-0000-4000-8000-000000000000",
"metadata_": {}
},
{
"id": "tool-2",
"tool_type": "custom",
"description": "Calculate the nth Fibonacci number.",
"source_type": "json",
"name": "calculate_fibonacci",
"tags": [
"math",
"utility"
],
"source_code": "def calculate_fibonacci(n: int) -> int:\n \"\"\"Calculate the nth Fibonacci number.\n\n Args:\n n: The position in the Fibonacci sequence to calculate.\n\n Returns:\n The nth Fibonacci number.\n \"\"\"\n if n <= 0:\n return 0\n elif n == 1:\n return 1\n else:\n a, b = 0, 1\n for _ in range(2, n + 1):\n a, b = b, a + b\n return b\n",
"json_schema": {
"name": "calculate_fibonacci",
"description": "Calculate the nth Fibonacci number.",
"parameters": {
"type": "object",
"properties": {
"n": {
"type": "integer",
"description": "The position in the Fibonacci sequence to calculate."
}
},
"required": [
"n"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"created_by_id": "user-00000000-0000-4000-8000-000000000000",
"last_updated_by_id": "user-00000000-0000-4000-8000-000000000000",
"metadata_": {}
},
{
"id": "tool-3",
"tool_type": "letta_core",
"description": "Search prior conversation history using hybrid search (text + semantic similarity).\n\nExamples:\n # Search all messages\n conversation_search(query=\"project updates\")\n\n # Search only assistant messages\n conversation_search(query=\"error handling\", roles=[\"assistant\"])\n\n # Search with date range (inclusive of both dates)\n conversation_search(query=\"meetings\", start_date=\"2024-01-15\", end_date=\"2024-01-20\")\n # This includes all messages from Jan 15 00:00:00 through Jan 20 23:59:59\n\n # Search messages from a specific day (inclusive)\n conversation_search(query=\"bug reports\", start_date=\"2024-09-04\", end_date=\"2024-09-04\")\n # This includes ALL messages from September 4, 2024\n\n # Search with specific time boundaries\n conversation_search(query=\"deployment\", start_date=\"2024-01-15T09:00\", end_date=\"2024-01-15T17:30\")\n # This includes messages from 9 AM to 5:30 PM on Jan 15\n\n # Search with limit\n conversation_search(query=\"debugging\", limit=10)\n\n Returns:\n str: Query result string containing matching messages with timestamps and content.",
"source_type": "python",
"name": "conversation_search",
"tags": [
"letta_core"
],
"source_code": null,
"json_schema": {
"name": "conversation_search",
"description": "Search prior conversation history using hybrid search (text + semantic similarity).\n\nExamples:\n # Search all messages\n conversation_search(query=\"project updates\")\n\n # Search only assistant messages\n conversation_search(query=\"error handling\", roles=[\"assistant\"])\n\n # Search with date range (inclusive of both dates)\n conversation_search(query=\"meetings\", start_date=\"2024-01-15\", end_date=\"2024-01-20\")\n # This includes all messages from Jan 15 00:00:00 through Jan 20 23:59:59\n\n # Search messages from a specific day (inclusive)\n conversation_search(query=\"bug reports\", start_date=\"2024-09-04\", end_date=\"2024-09-04\")\n # This includes ALL messages from September 4, 2024\n\n # Search with specific time boundaries\n conversation_search(query=\"deployment\", start_date=\"2024-01-15T09:00\", end_date=\"2024-01-15T17:30\")\n # This includes messages from 9 AM to 5:30 PM on Jan 15\n\n # Search with limit\n conversation_search(query=\"debugging\", limit=10)\n\n Returns:\n str: Query result string containing matching messages with timestamps and content.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "String to search for using both text matching and semantic similarity."
},
"roles": {
"type": "array",
"items": {
"type": "string",
"enum": [
"assistant",
"user",
"tool"
]
},
"description": "Optional list of message roles to filter by."
},
"limit": {
"type": "integer",
"description": "Maximum number of results to return. Uses system default if not specified."
},
"start_date": {
"type": "string",
"description": "Filter results to messages created on or after this date (INCLUSIVE). When using date-only format (e.g., \"2024-01-15\"), includes messages starting from 00:00:00 of that day. ISO 8601 format: \"YYYY-MM-DD\" or \"YYYY-MM-DDTHH:MM\". Examples: \"2024-01-15\" (from start of Jan 15), \"2024-01-15T14:30\" (from 2:30 PM on Jan 15)."
},
"end_date": {
"type": "string",
"description": "Filter results to messages created on or before this date (INCLUSIVE). When using date-only format (e.g., \"2024-01-20\"), includes all messages from that entire day. ISO 8601 format: \"YYYY-MM-DD\" or \"YYYY-MM-DDTHH:MM\". Examples: \"2024-01-20\" (includes all of Jan 20), \"2024-01-20T17:00\" (up to 5 PM on Jan 20)."
}
},
"required": [
"query"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"created_by_id": "user-00000000-0000-4000-8000-000000000000",
"last_updated_by_id": "user-00000000-0000-4000-8000-000000000000",
"metadata_": {}
},
{
"id": "tool-1",
"tool_type": "custom",
"description": "Get user preferences for a specific category.",
"source_type": "json",
"name": "get_user_preferences",
"tags": [
"user",
"preferences"
],
"source_code": "def get_user_preferences(category: str) -> str:\n \"\"\"Get user preferences for a specific category.\n\n Args:\n category: The preference category to retrieve (notification, theme, language).\n\n Returns:\n The user's preference for the specified category, or \"not specified\" if unknown.\n \"\"\"\n preferences = {\"notification\": \"email only\", \"theme\": \"dark mode\", \"language\": \"english\"}\n return preferences.get(category, \"not specified\")\n",
"json_schema": {
"name": "get_user_preferences",
"description": "Get user preferences for a specific category.",
"parameters": {
"type": "object",
"properties": {
"category": {
"type": "string",
"description": "The preference category to retrieve (notification, theme, language)."
}
},
"required": [
"category"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"created_by_id": "user-00000000-0000-4000-8000-000000000000",
"last_updated_by_id": "user-00000000-0000-4000-8000-000000000000",
"metadata_": {}
},
{
"id": "tool-0",
"tool_type": "letta_sleeptime_core",
"description": "The memory_insert command allows you to insert text at a specific location in a memory block.\n\nExamples:\n # Update a block containing information about the user (append to the end of the block)\n memory_insert(label=\"customer\", new_str=\"The customer's ticket number is 12345\")\n\n # Update a block containing information about the user (insert at the beginning of the block)\n memory_insert(label=\"customer\", new_str=\"The customer's ticket number is 12345\", insert_line=0)\n\n Returns:\n Optional[str]: None is always returned as this function does not produce a response.",
"source_type": "python",
"name": "memory_insert",
"tags": [
"letta_sleeptime_core"
],
"source_code": null,
"json_schema": {
"name": "memory_insert",
"description": "The memory_insert command allows you to insert text at a specific location in a memory block.\n\nExamples:\n # Update a block containing information about the user (append to the end of the block)\n memory_insert(label=\"customer\", new_str=\"The customer's ticket number is 12345\")\n\n # Update a block containing information about the user (insert at the beginning of the block)\n memory_insert(label=\"customer\", new_str=\"The customer's ticket number is 12345\", insert_line=0)\n\n Returns:\n Optional[str]: None is always returned as this function does not produce a response.",
"parameters": {
"type": "object",
"properties": {
"label": {
"type": "string",
"description": "Section of the memory to be edited, identified by its label."
},
"new_str": {
"type": "string",
"description": "The text to insert. Do not include line number prefixes."
},
"insert_line": {
"type": "integer",
"description": "The line number after which to insert the text (0 for beginning of file). Defaults to -1 (end of the file)."
}
},
"required": [
"label",
"new_str"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"created_by_id": "user-00000000-0000-4000-8000-000000000000",
"last_updated_by_id": "user-00000000-0000-4000-8000-000000000000",
"metadata_": {}
},
{
"id": "tool-4",
"tool_type": "letta_sleeptime_core",
"description": "The memory_replace command allows you to replace a specific string in a memory block with a new string. This is used for making precise edits.\n\nExamples:\n # Update a block containing information about the user\n memory_replace(label=\"human\", old_str=\"Their name is Alice\", new_str=\"Their name is Bob\")\n\n # Update a block containing a todo list\n memory_replace(label=\"todos\", old_str=\"- [ ] Step 5: Search the web\", new_str=\"- [x] Step 5: Search the web\")\n\n # Pass an empty string to\n memory_replace(label=\"human\", old_str=\"Their name is Alice\", new_str=\"\")\n\n # Bad example - do NOT add (view-only) line numbers to the args\n memory_replace(label=\"human\", old_str=\"Line 1: Their name is Alice\", new_str=\"Line 1: Their name is Bob\")\n\n # Bad example - do NOT include the number number warning either\n memory_replace(label=\"human\", old_str=\"# NOTE: Line numbers shown below are to help during editing. Do NOT include line number prefixes in your memory edit tool calls.\\nLine 1: Their name is Alice\", new_str=\"Line 1: Their name is Bob\")\n\n # Good example - no line numbers or line number warning (they are view-only), just the text\n memory_replace(label=\"human\", old_str=\"Their name is Alice\", new_str=\"Their name is Bob\")\n\n Returns:\n str: The success message",
"source_type": "python",
"name": "memory_replace",
"tags": [
"letta_sleeptime_core"
],
"source_code": null,
"json_schema": {
"name": "memory_replace",
"description": "The memory_replace command allows you to replace a specific string in a memory block with a new string. This is used for making precise edits.\n\nExamples:\n # Update a block containing information about the user\n memory_replace(label=\"human\", old_str=\"Their name is Alice\", new_str=\"Their name is Bob\")\n\n # Update a block containing a todo list\n memory_replace(label=\"todos\", old_str=\"- [ ] Step 5: Search the web\", new_str=\"- [x] Step 5: Search the web\")\n\n # Pass an empty string to\n memory_replace(label=\"human\", old_str=\"Their name is Alice\", new_str=\"\")\n\n # Bad example - do NOT add (view-only) line numbers to the args\n memory_replace(label=\"human\", old_str=\"Line 1: Their name is Alice\", new_str=\"Line 1: Their name is Bob\")\n\n # Bad example - do NOT include the number number warning either\n memory_replace(label=\"human\", old_str=\"# NOTE: Line numbers shown below are to help during editing. Do NOT include line number prefixes in your memory edit tool calls.\\nLine 1: Their name is Alice\", new_str=\"Line 1: Their name is Bob\")\n\n # Good example - no line numbers or line number warning (they are view-only), just the text\n memory_replace(label=\"human\", old_str=\"Their name is Alice\", new_str=\"Their name is Bob\")\n\n Returns:\n str: The success message",
"parameters": {
"type": "object",
"properties": {
"label": {
"type": "string",
"description": "Section of the memory to be edited, identified by its label."
},
"old_str": {
"type": "string",
"description": "The text to replace (must match exactly, including whitespace and indentation)."
},
"new_str": {
"type": "string",
"description": "The new text to insert in place of the old text. Do not include line number prefixes."
}
},
"required": [
"label",
"old_str",
"new_str"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"created_by_id": "user-00000000-0000-4000-8000-000000000000",
"last_updated_by_id": "user-00000000-0000-4000-8000-000000000000",
"metadata_": {}
},
{
"id": "tool-5",
"tool_type": "letta_core",
"description": "Sends a message to the human user.",
"source_type": "python",
"name": "send_message",
"tags": [
"letta_core"
],
"source_code": null,
"json_schema": {
"name": "send_message",
"description": "Sends a message to the human user.",
"parameters": {
"type": "object",
"properties": {
"message": {
"type": "string",
"description": "Message contents. All unicode (including emojis) are supported."
}
},
"required": [
"message"
]
}
},
"args_json_schema": null,
"return_char_limit": 50000,
"pip_requirements": null,
"npm_requirements": null,
"default_requires_approval": null,
"created_by_id": "user-00000000-0000-4000-8000-000000000000",
"last_updated_by_id": "user-00000000-0000-4000-8000-000000000000",
"metadata_": {}
}
],
"mcp_servers": [],
"metadata": {
"revision_id": "5b804970e6a0"
},
"created_at": "2025-09-08T17:53:06.749694+00:00"
}

2
tests/test_long_running_agents.py
View File

@@ -102,7 +102,7 @@ async def test_deep_research_agent(client: Letta, server_url, disable_e2b_api_ke
async def test_11x_agent(client: Letta, server_url, disable_e2b_api_key):
imported_af = upload_test_agentfile_from_disk(client, "mock_alice.af")
imported_af = upload_test_agentfile_from_disk(client, "long_running_kylie.af")
agent_id = imported_af.agent_ids[0]