mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
Benjamin Taylor
c8736df6f0
Every starter's .env.example documents INTELLIGENCE_API_URL and INTELLIGENCE_GATEWAY_WS_URL under its Threads-enablement block, with a localhost/local-ws value. Uncommenting (or, in llamaindex/mcp-apps, leaving as shipped) that block is the documented way to enable Threads, but it silently points the channel host at a local Intelligence that is usually not running — so `ready()` burns its 30s timeout and the host exits 1 with no indication why. Adds a short comment next to those two vars in each of the 14 starters that ship an .env.example (mastra has none tracked in this branch) noting they're for a self-hosted or local Intelligence deployment only and should be left unset for managed Intelligence. No values changed, nothing uncommented.
23 lines
951 B
Bash
23 lines
951 B
Bash
# --- Claude Agent SDK (Python) starter ---
|
|
|
|
# Your Anthropic API key (required). Get one at https://console.anthropic.com/
|
|
ANTHROPIC_API_KEY=
|
|
|
|
# Claude model to use (optional; this is the default).
|
|
CLAUDE_MODEL=claude-sonnet-5
|
|
|
|
# URL the Next.js runtime uses to reach the agent (optional; this is the default).
|
|
AGENT_URL=http://localhost:8000
|
|
|
|
# --- CopilotKit Intelligence (optional) ---
|
|
# Set COPILOTKIT_LICENSE_TOKEN to activate the Threads drawer's live thread
|
|
# history (server + UI). Without it the drawer shows a locked state.
|
|
# COPILOTKIT_LICENSE_TOKEN=
|
|
# INTELLIGENCE_API_URL and INTELLIGENCE_GATEWAY_WS_URL point at a self-hosted
|
|
# or local Intelligence deployment only — leave them unset when using managed
|
|
# Intelligence, or the channel host and runtime will try to reach a local
|
|
# stack that usually is not running.
|
|
# INTELLIGENCE_API_URL=http://localhost:4201
|
|
# INTELLIGENCE_GATEWAY_WS_URL=ws://localhost:4401
|
|
# INTELLIGENCE_API_KEY=
|