The Merge - initial changes

fix: synchronize job loop with development instance

Create search_engine.py

extensions update

default models

default models and settings

Update code_execution_tool.py

stabilizing fixes

fix: mcp get_tools_prompt fix for tools with optional arguments

Update code_execution_tool.py

dec's updates

input tool terminals

Merge remote-tracking branch 'my_fork/feature-mcp-integration' into feature/mcps-integration

fixes and improvements

Edit: Cleaned up MCP logs and check attempts.

Added: I've made sure that the user_message_text variable is explicitly cast to a string before any length checks or slicing operations are performed on it. I also renamed the variable from user_message_context to user_message_text for better clarity, as it primarily holds the textual part of the user's message.

Added: Contextual reminder for mcps with multi-step-processes for agent to not get distracted, to continue process.

Update: Improved MCP setup and config, async handling for sessions, auto mcp install if present in settings config (on compose)

Edit: Changed mcp.py to mcp_handler.py to prevent potential import confusion between 'mcp' package and 'mcp.py'. Edited dockerfile to 'latest' so it doesnt spin up old builds after image creation. Also edited preinstall to ensure the mcp related dependencies can load non-interactive.

fix: mcp server tool discovery

fix: mcp tool call error because of erroneous await()

fix: startup error missing module

feat: MCP initial support for sse servers (Part 2)

feat: Implement support for MCP Servers (Claude Tools) - Part 1 Stdio Servers

feat: embedded MCP server for messaging with agent-zero

image_get fix, history bulk compression fix

Scheduler wait_for_task and find_task_by_name (#388)

fix: make browser agent compatible with PlayWright 1.50 (#381)

feat: Deduplicate and optimize memory similarity threshold (#389)

llms and api keys reorder

chutes llm provider (#390)

tunnel ports fix

persistent tunnel

feat: Tunnel Manager

Implement tunnel API endpoints

Edit: Cleaned up MCP logs and check attempts.

Added: I've made sure that the user_message_text variable is explicitly cast to a string before any length checks or slicing operations are performed on it. I also renamed the variable from user_message_context to user_message_text for better clarity, as it primarily holds the textual part of the user's message.

Added: Contextual reminder for mcps with multi-step-processes for agent to not get distracted, to continue process.

Update: Improved MCP setup and config, async handling for sessions, auto mcp install if present in settings config (on compose)

Edit: Changed mcp.py to mcp_handler.py to prevent potential import confusion between 'mcp' package and 'mcp.py'. Edited dockerfile to 'latest' so it doesnt spin up old builds after image creation. Also edited preinstall to ensure the mcp related dependencies can load non-interactive.

fix: mcp server tool discovery

fix: mcp tool call error because of erroneous await()

fix: startup error missing module

feat: MCP initial support for sse servers (Part 2)

feat: Implement support for MCP Servers (Claude Tools) - Part 1 Stdio Servers

Edit: Encourage cat > EOF multiline edits for code and documentation

Edit: Loop detection now trunacates the looped info so we flood the LLM with less repeated context.

Fix: Input tool session management

Edit: Team Agent System Prompts

Edit: Code Exe Tool - The get_terminal_output function will now detect if the last 128 characters repeat 5 times consecutively and will stop execution if this pattern occurs, indicating a likely infinite loop.