The go-sdk fires notifications/tools/list_changed and
notifications/resources/list_changed with 10ms delay after AddTool/AddResource.
Since all registration happens before server.Run(), these hit stdout
before the client sends initialize, breaking the MCP handshake.
Co-Authored-By: Virgil <virgil@lethean.io>
Metrics, RAG, and webview tools only register when CORE_MCP_FULL=1.
Process and WS tools always register (used by factory).
Reduces default tool count by 15.
Co-Authored-By: Virgil <virgil@lethean.io>
- Fix TestBridgeToAPI_Good_EndToEnd: POST with empty JSON body instead of nil
- Add local replace for go-process to resolve API drift with core v0.8.0
Co-Authored-By: Virgil <virgil@lethean.io>
Make the func-based channel wiring contract explicit instead of relying on an anonymous interface inside New(). This keeps the extension point discoverable and aligned with the repository's AX-style API clarity.
Co-Authored-By: Virgil <virgil@lethean.io>
Align the IDE bridge and brain subsystem public types with the repo's AX-style comment convention by adding concrete usage examples for bridge messages, DTOs, and helper callbacks.
Co-Authored-By: Virgil <virgil@lethean.io>
Return copies from service accessors and ignore nil subsystems during construction to keep the MCP service API stable and AX-friendly.
Co-Authored-By: Virgil <virgil@lethean.io>
Reorder subsystem notification wiring so channel callbacks are available before tool registration, and add usage-example comments to the public notification DTOs and helpers.
Co-Authored-By: Virgil <virgil@lethean.io>
Remove the duplicate brain-local notifier interface and use the shared pkg/mcp Notifier type directly. Also align stale test comments with the current Options constructor API.
Co-Authored-By: Virgil <virgil@lethean.io>
Make notification broadcasting tolerant of a nil context and make TCP transport fall back to DefaultTCPAddr when no address is supplied.
Co-Authored-By: Virgil <virgil@lethean.io>
Guard the notification broadcast helpers against nil Service and nil server values so they degrade to no-ops instead of panicking. Add coverage for zero-value and nil-server use.
Co-Authored-By: Virgil <virgil@lethean.io>
