Use when you want to offload bounded, read-only analysis to a persistent OpenCode sidecar to save primary-agent context and coordination overhead. Best for repo search summaries, log triage, docs/API lookup, and implementation mapping. Do not use for file edits, destructive commands, or tightly coupled coding loops.
Use this sidecar for bounded read-only analysis that is cheaper to isolate than to carry in the main agent context.
./start-opencode-sidecar.sh
Defaults:
127.0.0.14096./opencode-sidecar-run.sh /path/to/repo "Search for auth config loading and summarize the entrypoints."
The runner already constrains the prompt. Expect output to be:
Design your task prompt so the answer can stay short.
Good prompt shapes:
Find the entrypoints for X and summarize them in 5 bullets.Read these logs and identify the first failing step.Compare these two payload shapes and list material mismatches only.Bad prompt shapes:
Fix this bug.Refactor this subsystem.Investigate everything related to auth../state/../state/ is only local sidecar session state. It is not repo data../start-opencode-sidecar.sh starts the headless OpenCode server./opencode-sidecar-run.sh sends bounded read-only tasks to the server