01 / Start with a bounded outcome
Fixing a particular failing test is easier to evaluate than optimizing an entire project. Specify the permitted scope and a concrete definition of success before starting the agent.
02 / Budget for useful work
Set appropriate limits for retries, tool output, and total usage. Keep error details and supporting evidence. Summarize or paginate long outputs instead of repeatedly including the full result.
03 / Detect repeated failure
Identical tool calls, repeated failed commands, and rewrites without new evidence suggest a stalled loop. Inspect recent actions and change the approach before continuing.
04 / Reserve resources for checks
The task is not finished when an edit is generated. Keep enough budget to run relevant checks, review the change, and report what remains unverified.
Sources and further reading
DS-V4-HUUB · DeepSeek OpenCode Setup & Model Selection ↗api-docs.deepseek.com · Official documentation ↗api-docs.deepseek.com · Official documentation ↗Adapted from the source guide, last updated 2026-06-17. Savings depend on your workload and must be measured.