Files
tradingagents/docker-compose.yml
Yijia-Xiao a420ad0f3b fix(cli): honor env precedence for LLM and run config
Interactive selections and flag defaults overrode TRADINGAGENTS_* env vars.
Rule: an explicit env value or CLI flag wins; otherwise the env-applied
default is kept.

- Research depth: skip the prompt when both round-count env vars are set, and
  stop overwriting them (#977).
- Checkpoint: --checkpoint/--no-checkpoint is tri-state; omitting it keeps
  TRADINGAGENTS_CHECKPOINT_ENABLED (#976).
- Docker ollama: use TRADINGAGENTS_LLM_PROVIDER + OLLAMA_BASE_URL, not a bare
  LLM_PROVIDER the overlay never reads (#975).
- Reasoning/thinking knobs: settable via env; the prompt is skipped when set.
- Effort gating: forward effort only to models that accept it (Anthropic
  Opus 4.5+/Sonnet 4.6+, OpenAI reasoning models); drop it elsewhere.
- Boolean env values: raise a named error on invalid input instead of
  silently becoming False.
2026-06-21 21:03:05 +00:00

37 lines
672 B
YAML

services:
tradingagents:
build: .
env_file:
- .env
volumes:
- tradingagents_data:/home/appuser/.tradingagents
tty: true
stdin_open: true
ollama:
image: ollama/ollama:latest
volumes:
- ollama_data:/root/.ollama
profiles:
- ollama
tradingagents-ollama:
build: .
env_file:
- .env
environment:
- TRADINGAGENTS_LLM_PROVIDER=ollama
- OLLAMA_BASE_URL=http://ollama:11434/v1
volumes:
- tradingagents_data:/home/appuser/.tradingagents
depends_on:
- ollama
tty: true
stdin_open: true
profiles:
- ollama
volumes:
tradingagents_data:
ollama_data: