Optimization

Submit an optimization job

Use dn optimize to submit a hosted GEPA optimization job for a capability agent:

dn optimize \
  --server http://127.0.0.1:8000 \
  --api-key "$DREADNODE_API_KEY" \
  --organization dreadnode \
  --workspace localdev \
  --model openai/gpt-4o-mini \
  --capability [email protected] \
  --agent-name assistant \
  --dataset [email protected] \
  --val-dataset [email protected] \
  --reward-recipe exact_match_v1 \
  --objective "Improve instruction quality without increasing verbosity." \
  --max-metric-calls 100 \
  --reflection-lm gpt-5-mini \
  --wait \
  --json

V1 flags to know:

Flag	Description
--capability NAME@VERSION	Capability artifact containing the target agent
--agent-name <name>	Required when the capability exports multiple agents
--dataset NAME@VERSION	Training dataset used during optimization
--val-dataset NAME@VERSION	Optional held-out validation dataset
--reward-recipe <name>	Declarative hosted reward recipe
--reward-params <json>	JSON params passed to the reward recipe
--seed <n>	Deterministic optimization seed
--max-metric-calls <n>	Metric-call budget
--reflection-lm <model>	Reflection model override; defaults to --model
--no-capture-traces	Disable trajectory capture for reflection
--wait	Poll until the hosted job reaches a terminal state
--json	Print the full job payload instead of a compact summary

Current hosted CLI scope matches the hosted API:

• backend: gepa
• target kind: capability_agent
• optimized components: agent instructions

Inspect and manage jobs

dn optimize list
dn optimize get <job-id>
dn optimize wait <job-id> --json
dn optimize logs <job-id>
dn optimize artifacts <job-id>
dn optimize cancel <job-id> --json
dn optimize retry <job-id>

dn optimize wait exits non-zero if the job finishes in failed or cancelled.

dn optimize list supports the same top-level filters as the API, including --status, --backend, --target-kind, --project-ref, --page, and --page-size.

Platform context

Hosted optimization commands require platform credentials plus an active organization and workspace. Pass them explicitly with flags or configure them in your SDK profile first:

dn configure
dn optimize get <job-id>