mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
Jordan Ritter
b355acd56c
TanStack's chat() engine runs a multi-turn agent loop: after the model returns tool calls, it tries to execute them via processToolCalls(). Frontend-only tools (like render_pie_chart) are unknown to TanStack, so executeToolCalls() treats them as errors and buildToolResultChunks() re-emits TOOL_CALL_END without a preceding TOOL_CALL_START. The ag-ui verify middleware rejects this duplicate. Fix: track a runFinished flag in convertTanStackStream and discard all events after the first RUN_FINISHED, which marks the boundary between the streaming pass and TanStack's internal tool execution loop. Also adds built-in-agent to docker-compose.local.yml and local-ports.json.
21 lines
434 B
JSON
21 lines
434 B
JSON
{
|
|
"langgraph-python": 3100,
|
|
"langgraph-typescript": 3101,
|
|
"langgraph-fastapi": 3102,
|
|
"google-adk": 3103,
|
|
"mastra": 3104,
|
|
"crewai-crews": 3105,
|
|
"pydantic-ai": 3106,
|
|
"claude-sdk-python": 3107,
|
|
"claude-sdk-typescript": 3108,
|
|
"agno": 3109,
|
|
"ag2": 3110,
|
|
"llamaindex": 3111,
|
|
"strands": 3112,
|
|
"langroid": 3113,
|
|
"ms-agent-python": 3114,
|
|
"ms-agent-dotnet": 3115,
|
|
"spring-ai": 3116,
|
|
"built-in-agent": 3117
|
|
}
|