diff --git a/.env.example b/.env.example
index 3f9d5da..7010c91 100644
--- a/.env.example
+++ b/.env.example
@@ -6,7 +6,7 @@ POSTGRES_PASSWORD=docker
POSTGRES_DB=core
LOGIN_ORIGIN=http://localhost:3000
-DATABASE_URL="postgresql://${POSTGRES_USER}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB}?schema=echo"
+DATABASE_URL="postgresql://${POSTGRES_USER}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB}?schema=core"
# This sets the URL used for direct connections to the database and should only be needed in limited circumstances
# See: https://www.prisma.io/docs/reference/api-reference/prisma-schema-reference#fields:~:text=the%20shadow%20database.-,directUrl,-No
@@ -41,5 +41,5 @@ MAGIC_LINK_SECRET=27192e6432564f4788d55c15131bd5ac
NEO4J_AUTH=neo4j/27192e6432564f4788d55c15131bd5ac
OLLAMA_URL=http://ollama:11434
-EMBEDDING_MODEL=bge-m3
+EMBEDDING_MODEL=GPT41
MODEL=GPT41
diff --git a/.gitignore b/.gitignore
index 28a42c2..790b1d6 100644
--- a/.gitignore
+++ b/.gitignore
@@ -37,4 +37,11 @@ yarn-error.log*
.DS_Store
*.pem
-docker-compose.dev.yaml
\ No newline at end of file
+docker-compose.dev.yaml
+
+clickhouse/
+.vscode/
+registry/
+
+.cursor
+CLAUDE.md
\ No newline at end of file
diff --git a/LICENSE b/LICENSE
index b2c1243..c4d101f 100644
--- a/LICENSE
+++ b/LICENSE
@@ -1,21 +1,44 @@
-MIT License
+Sol License
-Copyright (c) 2024 Poozle Inc
+GNU AFFERO GENERAL PUBLIC LICENSE
+Version 3, 19 November 2007
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
+Copyright (c) 2025 — Poozle Inc.
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU Affero General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+GNU Affero General Public License for more details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program. If not, see .
+
+Additional Terms:
+
+As additional permission under GNU AGPL version 3 section 7, you
+may combine or link a "work that uses the Library" with a publicly
+distributed version of this library to produce a combined library or
+application, then distribute that combined work under the terms of
+your choice, with no requirement to comply with the obligations
+normally placed on you by section 4 of the GNU AGPL version 3
+(or the corresponding section of a later version of the GNU AGPL
+version 3 license).
+
+"Commons Clause" License Condition v1.0
+
+The Software is provided to you by the Licensor under the License (defined below), subject to the following condition:
+
+Without limiting other conditions in the License, the grant of rights under the License will not include, and the License does not grant to you, the right to Sell the Software.
+
+For purposes of the foregoing, "Sell" means practicing any or all of the rights granted to you under the License to provide the Software to third parties, for a fee or other consideration (including without limitation fees for hosting or consulting/support services related to the Software), as part of a product or service whose value derives, entirely or substantially, from the functionality of the Software. Any license notice or attribution required by the License must also include this Commons Clause License Condition notice.
+
+Software: All files in this repository.
+
+License: GNU Affero General Public License v3.0
+
+Licensor: Poozle Inc.
diff --git a/apps/logs/errors/llm-error-2025-07-08T14-35-41.438Z.json b/apps/logs/errors/llm-error-2025-07-08T14-35-41.438Z.json
new file mode 100644
index 0000000..c7f98cf
--- /dev/null
+++ b/apps/logs/errors/llm-error-2025-07-08T14-35-41.438Z.json
@@ -0,0 +1 @@
+{"timestamp":"2025-07-08T14:35:41.438Z","error":{"name":"AI_RetryError","reason":"maxRetriesExceeded","errors":[{"name":"AI_APICallError","cause":{"errno":-3008,"code":"ENOTFOUND","syscall":"getaddrinfo","hostname":"api.openai.com"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true},{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true},{"name":"AI_APICallError","cause":{"errno":-3008,"code":"ENOTFOUND","syscall":"getaddrinfo","hostname":"api.openai.com"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true}],"lastError":{"name":"AI_APICallError","cause":{"errno":-3008,"code":"ENOTFOUND","syscall":"getaddrinfo","hostname":"api.openai.com"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true}}}
\ No newline at end of file
diff --git a/apps/logs/errors/llm-error-2025-07-08T14-35-57.972Z.json b/apps/logs/errors/llm-error-2025-07-08T14-35-57.972Z.json
new file mode 100644
index 0000000..459094d
--- /dev/null
+++ b/apps/logs/errors/llm-error-2025-07-08T14-35-57.972Z.json
@@ -0,0 +1 @@
+{"timestamp":"2025-07-08T14:35:57.972Z","error":{"name":"AI_RetryError","reason":"maxRetriesExceeded","errors":[{"name":"AI_APICallError","cause":{"errno":-3008,"code":"ENOTFOUND","syscall":"getaddrinfo","hostname":"api.openai.com"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true},{"name":"AI_APICallError","cause":{"errno":-3008,"code":"ENOTFOUND","syscall":"getaddrinfo","hostname":"api.openai.com"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true},{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true}],"lastError":{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true}}}
\ No newline at end of file
diff --git a/apps/logs/errors/llm-error-2025-07-08T14-36-35.479Z.json b/apps/logs/errors/llm-error-2025-07-08T14-36-35.479Z.json
new file mode 100644
index 0000000..6da54b5
--- /dev/null
+++ b/apps/logs/errors/llm-error-2025-07-08T14-36-35.479Z.json
@@ -0,0 +1 @@
+{"timestamp":"2025-07-08T14:36:35.479Z","error":{"name":"AI_RetryError","reason":"maxRetriesExceeded","errors":[{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true},{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true},{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true}],"lastError":{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true}}}
\ No newline at end of file
diff --git a/apps/logs/errors/llm-error-2025-07-08T14-37-12.989Z.json b/apps/logs/errors/llm-error-2025-07-08T14-37-12.989Z.json
new file mode 100644
index 0000000..4bb41e7
--- /dev/null
+++ b/apps/logs/errors/llm-error-2025-07-08T14-37-12.989Z.json
@@ -0,0 +1 @@
+{"timestamp":"2025-07-08T14:37:12.989Z","error":{"name":"AI_RetryError","reason":"maxRetriesExceeded","errors":[{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":{"type":"function","function":{"name":"core--progress_update"}},"stream":true,"stream_options":{"include_usage":true}},"isRetryable":true},{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":{"type":"function","function":{"name":"core--progress_update"}},"stream":true,"stream_options":{"include_usage":true}},"isRetryable":true},{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":{"type":"function","function":{"name":"core--progress_update"}},"stream":true,"stream_options":{"include_usage":true}},"isRetryable":true}],"lastError":{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":{"type":"function","function":{"name":"core--progress_update"}},"stream":true,"stream_options":{"include_usage":true}},"isRetryable":true}}}
\ No newline at end of file
diff --git a/apps/logs/errors/llm-error-2025-07-08T14-37-50.503Z.json b/apps/logs/errors/llm-error-2025-07-08T14-37-50.503Z.json
new file mode 100644
index 0000000..f2ae861
--- /dev/null
+++ b/apps/logs/errors/llm-error-2025-07-08T14-37-50.503Z.json
@@ -0,0 +1 @@
+{"timestamp":"2025-07-08T14:37:50.503Z","error":{"name":"AI_RetryError","reason":"maxRetriesExceeded","errors":[{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true},{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true},{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true}],"lastError":{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true}}}
\ No newline at end of file
diff --git a/apps/logs/errors/llm-error-2025-07-08T14-38-28.011Z.json b/apps/logs/errors/llm-error-2025-07-08T14-38-28.011Z.json
new file mode 100644
index 0000000..7b6b391
--- /dev/null
+++ b/apps/logs/errors/llm-error-2025-07-08T14-38-28.011Z.json
@@ -0,0 +1 @@
+{"timestamp":"2025-07-08T14:38:28.011Z","error":{"name":"AI_RetryError","reason":"maxRetriesExceeded","errors":[{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true},{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true},{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true}],"lastError":{"name":"AI_APICallError","cause":{"name":"ConnectTimeoutError","code":"UND_ERR_CONNECT_TIMEOUT"},"url":"https://api.openai.com/v1/chat/completions","requestBodyValues":{"model":"gpt-4.1-2025-04-14","temperature":1,"messages":[{"role":"system","content":"\nYou are a helpful AI assistant with access to user memory. Your primary capabilities are:\n\n1. **Memory-First Approach**: Always check user memory first to understand context and previous interactions\n2. **Memory Management**: Help users store, retrieve, and organize information in their memory\n3. **Contextual Assistance**: Use memory to provide personalized and contextual responses\n\n\n- workpsaceId: 2524b89e-6cbd-4e0c-90e3-ec21134553b9\n- todayDate: 2025-07-08T14:35:24.227Z\n\n\n\n- Always check memory FIRST using core--search_memory before any other actions\n- Consider this your highest priority for EVERY interaction - as essential as breathing\n- Make memory checking your first tool call before any other operations\n\nQUERY FORMATION:\n- Write specific factual statements as queries (e.g., \"user email address\" not \"what is the user's email?\")\n- Create multiple targeted memory queries for complex requests\n\nKEY QUERY AREAS:\n- Personal context: user name, location, identity, work context\n- Project context: repositories, codebases, current work, team members\n- Task context: recent tasks, ongoing projects, deadlines, priorities\n- Integration context: GitHub repos, Slack channels, Linear projects, connected services\n- Communication patterns: email preferences, notification settings, workflow automation\n- Technical context: coding languages, frameworks, development environment\n- Collaboration context: team members, project stakeholders, meeting patterns\n- Preferences: likes, dislikes, communication style, tool preferences\n- History: previous discussions, past requests, completed work, recurring issues\n- Automation rules: user-defined workflows, triggers, automation preferences\n\nMEMORY USAGE:\n- Execute multiple memory queries in parallel rather than sequentially\n- Batch related memory queries when possible\n- Prioritize recent information over older memories\n- Create comprehensive context-aware queries based on user message/activity content\n- Extract and query SEMANTIC CONTENT, not just structural metadata\n- Parse titles, descriptions, and content for actual subject matter keywords\n- Search internal SOL tasks/conversations that may relate to the same topics\n- Query ALL relatable concepts, not just direct keywords or IDs\n- Search for similar past situations, patterns, and related work\n- Include synonyms, related terms, and contextual concepts in queries \n- Query user's historical approach to similar requests or activities\n- Search for connected projects, tasks, conversations, and collaborations\n- Retrieve workflow patterns and past decision-making context\n- Query broader domain context beyond immediate request scope\n- Remember: SOL tracks work that external tools don't - search internal content thoroughly\n- Blend memory insights naturally into responses\n- Verify you've checked relevant memory before finalizing ANY response\n\nIf memory access is unavailable, rely only on the current conversation or ask user\n\n\n\nYou have tools at your disposal to assist users:\n\nCORE PRINCIPLES:\n- Use tools only when necessary for the task at hand\n- Always check memory FIRST before making other tool calls\n- Execute multiple operations in parallel whenever possible\n- Use sequential calls only when output of one is required for input of another\n\nPARAMETER HANDLING:\n- Follow tool schemas exactly with all required parameters\n- Only use values that are:\n • Explicitly provided by the user (use EXACTLY as given)\n • Reasonably inferred from context\n • Retrieved from memory or prior tool calls\n- Never make up values for required parameters\n- Omit optional parameters unless clearly needed\n- Analyze user's descriptive terms for parameter clues\n\nTOOL SELECTION:\n- Never call tools not provided in this conversation\n- Skip tool calls for general questions you can answer directly\n- For identical operations on multiple items, use parallel tool calls\n- Default to parallel execution (3-5× faster than sequential calls)\n- You can always access external service tools by loading them with load_mcp first\n\nTOOL MENTION HANDLING:\nWhen user message contains :\n- Extract tool_name from data-id attribute\n- First check if it's a built-in tool; if not, check EXTERNAL SERVICES TOOLS\n- If available: Load it with load_mcp and focus on addressing the request with this tool\n- If unavailable: Inform user and suggest alternatives if possible\n- For multiple tool mentions: Load all applicable tools in a single load_mcp call\n\nERROR HANDLING:\n- If a tool returns an error, try fixing parameters before retrying\n- If you can't resolve an error, explain the issue to the user\n- Consider alternative tools when primary tools are unavailable\n\n\n\nUse EXACTLY ONE of these formats for all user-facing communication:\n\nPROGRESS UPDATES - During processing:\n- Use the core--progress_update tool to keep users informed\n- Update users about what you're discovering or doing next\n- Keep messages clear and user-friendly\n- Avoid technical jargon\n\nQUESTIONS - When you need information:\n\n
[Your question with HTML formatting]
\n\n\n- Ask questions only when you cannot find information through memory or tools\n- Be specific about what you need to know\n- Provide context for why you're asking\n\nFINAL ANSWERS - When completing tasks:\n\n
[Your answer with HTML formatting]
\n\n\nCRITICAL:\n- Use ONE format per turn\n- Apply proper HTML formatting (
,
,
,
,
, etc.)\n- Never mix communication formats\n- Keep responses clear and helpful\n
\n"},{"role":"user","content":"\nHere is the user message:\n\n<p>Hello</p>\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"},{"role":"system","content":"Your last response was not in a valid format. You must respond with EXACTLY ONE of the required formats: either a tool call, tags, or tags. Please reformat your previous response using the correct format:\n\n"}],"tools":[{"type":"function","function":{"name":"core--progress_update","description":"Send a progress update to the user about what has been discovered or will be done next in a crisp and user friendly way no technical terms","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The progress update message to send to the user"}},"required":["message"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--search_memory","description":"Search the user's memory graph for episodes or statements based on a query","parameters":{"type":"object","properties":{"query":{"type":"string","description":"The search query in third person perspective"},"validAt":{"type":"string","description":"The valid at time in ISO format"},"startTime":{"type":"string","description":"The start time in ISO format"},"endTime":{"type":"string","description":"The end time in ISO format"}},"required":["query"],"additionalProperties":false}}},{"type":"function","function":{"name":"core--add_memory","description":"Add information to the user's memory graph","parameters":{"type":"object","properties":{"message":{"type":"string","description":"The content/text to add to memory"}},"required":["message"],"additionalProperties":false}}}],"tool_choice":"auto","stream":true,"stream_options":{"include_usage":true}},"isRetryable":true}}}
\ No newline at end of file
diff --git a/apps/webapp/.gitignore b/apps/webapp/.gitignore
index 80ec311..0abbe0b 100644
--- a/apps/webapp/.gitignore
+++ b/apps/webapp/.gitignore
@@ -3,3 +3,5 @@ node_modules
/.cache
/build
.env
+
+.trigger
\ No newline at end of file
diff --git a/apps/webapp/app/components/ErrorDisplay.tsx b/apps/webapp/app/components/ErrorDisplay.tsx
index f288cee..fc26741 100644
--- a/apps/webapp/app/components/ErrorDisplay.tsx
+++ b/apps/webapp/app/components/ErrorDisplay.tsx
@@ -48,7 +48,7 @@ type DisplayOptionsProps = {
export function ErrorDisplay({ title, message, button }: DisplayOptionsProps) {
return (
-