mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
Jordan Ritter
f58615831d
Spring-AI ignores the showcase-wide OPENAI_BASE_URL because its split base-url + completions-path model would produce a double-/v1 against aimock. Introduce SPRING_AI_OPENAI_BASE_URL carrying the host without /v1 (e.g. http://aimock:4010), default to https://api.openai.com. Additionally, pin WebClient's JDK HttpClient to HTTP/1.1 and disable connection pooling: - Without reactor-netty, Spring-AI's auto-configured WebClient sent `Upgrade: h2c` on every cleartext request, which some fixtures (aimock) reject with 404. - Default JDK HttpClient pooling reused half-closed sockets between fixture responses, tripping `Connection reset` on tool-result follow-ups. L3 chat now passes locally against the stack. L4 tool-rendering still needs additional work (tool-execution loop cap WIP in BoundedToolCallingManagerConfig).
22 lines
805 B
Bash
22 lines
805 B
Bash
# Copy to showcase/.env and fill in.
|
|
# Picked up by docker-compose.local.yml via env_file for every showcase package container.
|
|
# Not committed to git.
|
|
|
|
OPENAI_API_KEY=
|
|
ANTHROPIC_API_KEY=
|
|
LANGSMITH_API_KEY=
|
|
|
|
# Optional: route LLM traffic through local aimock on the compose network.
|
|
# Most packages consume OPENAI_BASE_URL / ANTHROPIC_BASE_URL directly.
|
|
# Spring-AI splits base-url (host) + completions-path (/v1/chat/completions),
|
|
# so it needs the host without /v1 via SPRING_AI_OPENAI_BASE_URL.
|
|
# OPENAI_BASE_URL=http://aimock:4010/v1
|
|
# ANTHROPIC_BASE_URL=http://aimock:4010
|
|
# SPRING_AI_OPENAI_BASE_URL=http://aimock:4010
|
|
|
|
# Package-specific (only required for the packages that use them).
|
|
# ms-agent-dotnet: GitHub model provider token.
|
|
GitHubToken=
|
|
# google-adk / gemini-based demos.
|
|
GOOGLE_API_KEY=
|