Fix agent empty-response in prod: workdir mount, image freshness, error surfacing
- Pin codex@0.142.0 + opencode-ai@1.17.9 in the job image (was @latest, causing dev/prod drift) - Worker now s the job image once per process so prod stops running a stale Codex - Surface Codex error/turn.failed events instead of swallowing them, so the real failure reason is reported rather than 'no assistant response' - Harden the Codex JSON parser to also handle the legacy msg-wrapped shape - Fix the docker-in-docker workdir: bind-mount identical host:container path and set SPOON_AGENT_HOST_WORKDIR (named volume can't be mounted by sibling job containers) - Add docs/compose.prod.yml as a documented reference deployment
This commit is contained in:
@@ -17,7 +17,7 @@ RUN apt-get update \
|
||||
&& corepack enable \
|
||||
&& corepack prepare pnpm@latest --activate \
|
||||
&& corepack prepare yarn@stable --activate \
|
||||
&& npm install -g bun@1.3.10 opencode-ai@latest @openai/codex@latest \
|
||||
&& npm install -g bun@1.3.10 opencode-ai@1.17.9 @openai/codex@0.142.0 \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
WORKDIR /workspace
|
||||
|
||||
Reference in New Issue
Block a user