* draft mcp client
* testing
* fix
* cleaning
* mcp resource in inputtransforms
* cleaning
* big cleaning
* cleaning
* no arc
* add utils file
* refactor tools
* add mcp actions
* draft frontend
* send arguments from backend
* better frontend
* cleaning
* use token for auth
* add logo
* rm
* fix
* fix
* chore: refactor mcp for ai agents (#6829)
* Add Tool enum for AIAgent with backward compatibility
- Created Tool enum that can be either Windmill (FlowModule) or Mcp (resource reference)
- Created McpToolRef struct to hold MCP resource path
- Implemented custom Deserialize for Tool with backward compatibility:
- New format: {type: 'windmill'|'mcp', ...}
- Old format: FlowModule objects (automatically wrapped in Tool::Windmill)
- Updated AIAgent to use Vec<Tool> instead of Vec<FlowModule>
- Updated FlowValue::traverse_leafs to handle Tool enum
- Backward compatible: old flows with Vec<FlowModule> will deserialize correctly
* Refactor AI executor to process Tool enum instead of extracting MCP from input_transforms
- Separate Windmill tools and MCP resource paths from tools list
- Process Windmill FlowModules into Tool definitions
- Load MCP tools from resource paths in Tool::Mcp variants
- Remove old logic that extracted mcp_resources from input_transforms
- Import FlowModule, remove unused InputTransform
- Fix type issues: use .as_str() for path and handle Option<bool> properly
* handle in args
* mcp as flowmodule
* frontend
* config for mcp
* simplify logic
* fix ai executor logic
* cleaning
* clean frontend
* fix
* better resource picker
* fix and styling
* add endpoint to fetch tools
* apply tool filtering
* fix name validation
* better ui
* use cache
* fix
* fix merge
* refactor: Separate MCP tools from FlowModule in AIAgent
- Add new AgentTool, ToolValue, and McpToolValue types
- Update AIAgent to use Vec<AgentTool> instead of Vec<FlowModule>
- Implement From traits for clean conversion between AgentTool and FlowModule
- Add backward compatibility via custom deserializer for AgentTool
- Simplify resolve_module logic by reusing existing resolve_modules function
- Update traverse_leafs to handle AgentTool structure
This refactoring separates MCP tools from FlowModule tools, making the
type system clearer and eliminating the need to treat MCP servers as
a special case of FlowModule.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: Update ai_executor and worker_lockfiles for AgentTool
- Update ai_executor.rs to handle new AgentTool structure
- Separate MCP tools from FlowModule tools using ToolValue enum
- Convert AgentTool to FlowModule for backward compatibility
- Add imports for AgentTool and ToolValue types
- Update worker_lockfiles.rs for lazy loading optimization
- Convert AgentTool <-> FlowModule in insert_flow_modules
- Preserve lazy loading for FlowModule tools via modules_node
- Keep MCP tools inline (lightweight, no need for lazy loading)
- Maintain backward compatibility with existing flows
This enables the lazy loading optimization for FlowModule tools while
keeping MCP tools inline, balancing performance and simplicity.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* cleaning
* adapt frontend
* cleaning
* cleaning
* type fix
* cleaning
* fix back comp
* move mcp button position
* nit
* cleaning
* fix nested removal
* cleaning
* opti
* fix chat markdown display
* fix chat messages layout
* fix back comp frontend
* fix deserializer
* nit
* simpler serializer
* use if else
---------
Co-authored-by: Claude <noreply@anthropic.com>
* refactor: improve usage table behavior to eliminate synchronous row locks
Replace synchronous INSERT...RETURNING with SELECT + async UPDATE pattern:
- Add check_usage_limits() to read current usage without row locks
- Add increment_usage_async() to update usage in background task
- Refactor job push logic to use optimistic validation
- Simplify job completion tracking with better error handling
This eliminates blocking row locks on the usage table during job creation,
significantly improving throughput and reducing contention.
Note: Requires running 'cargo sqlx prepare' with database access to update
the query cache in .sqlx/ directory.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Ruben Fiszel <rubenfiszel@users.noreply.github.com>
* Update SQLx metadata
* refactor: optimize cloud usage checks with caching and conditional queries
- Add 60s cache for superadmin status checks to reduce DB load
- Skip unnecessary user usage query for premium workspaces
- Use existing team plan status cache (already implemented in windmill-common)
- Update check_usage_limits to accept check_user_usage parameter
- Add sqlx query cache for conditional user usage query
This optimization eliminates redundant database queries during job creation,
particularly for premium workspaces where user usage tracking is not needed.
Co-authored-by: Ruben Fiszel <rubenfiszel@users.noreply.github.com>
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Ruben Fiszel <rubenfiszel@users.noreply.github.com>
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
* Revert "feat(backend): use flow nodes opti for ai agent steps (#6808)"
This reverts commit e5ea3e4a57.
* fix(backend): revert flow node opti for ai agents
* keep standard base64
* Improve minio on flake.nix
* Add first asset parsing logic for ansible
* Correct html gt sign
* Decouple s3 file picker from drawer
* Factor duplicate code into snippet
* Update S3FilePickerInner to be compatible
* Fix pane shrinking issue
* Git repo viewer
* Change GitRepoViewer
* Endpoints for git repo visualizer
* Move git repo viewer to its own component
* Add button to populate git repo viewer
* Update parser yaml for new ansisble features (repo viewer)
* Reflect parser changes for ansible
* Add button to add the git repo mode of declaration for ansible
* Factor function
* Playbook + inventories into the drawer
* Add button to add inventories from s3
* Move tests to lib.rs
* Inventory loading from s3
* Move get github app token logic to be reused by ansible
* Update parser and ansible executor
* Use the correct path for inventories
* Add nushell to flake for wasm builds
* Add published parser
* Update hubPaths with clone and upload to s3
* Update ee-repo to the branch ref
* Fix npm run check
* Update cargo.lock
* Change labels on buttons
* Remove debug log
* Update ee-repo-ref
* Fix ee issues
* Update ee-repo ref
* Fix typo
* Fix ee
* Update ee-repo-ref
* Fix missing imports
* Unused var
* Fix typo
* Layout improvents
* Fix typos
* Remove unused function and log
---------
Co-authored-by: Ruben Fiszel <ruben@windmill.dev>
* chore(mcp): display API endpoint tools in MCP URL generation
- Add list of 24 API endpoint tools that are always available via MCP
- Display API endpoints as green badges below scripts/flows list
- Update tooltip to mention 'scripts, flows, and API endpoints'
- Show count of available API endpoints in the UI
API endpoints include operations for variables, resources, scripts, flows,
jobs, schedules, and workers.
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
* better
* nit
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: windmill-internal-app[bot] <windmill-internal-app[bot]@users.noreply.github.com>
