curl -sf http://localhost:8500/health
curl -s -X POST http://localhost:8500/orchestrate \
-H "Content-Type: application/json" \
-d '{
"message": "What does my day look like?",
"input_modality": "text",
"output_format": "markdown"
}' | jq .
Pass the returned session_id back on later requests:
curl -s -X POST http://localhost:8500/orchestrate \
-H "Content-Type: application/json" \
-d '{
"message": "Which of those tasks should I do first?",
"session_id": "e7d2a1f9-3b4c-5d6e-7f8a-9b0c1d2e3f4a"
}' | jq .
The deployed runtime currently uses:
ORCH_CLASSIFIER_MODEL=gemma4-26bThe source fallback in app/config.py is still qwen3.5-27b, so if you are debugging source-level defaults, keep that distinction in mind.
If classifier confidence falls below 0.7, the service returns:
clarification_needed: trueintentclarification_messageNo agent dispatch happens in that case.
curl -sf http://localhost:4000/health/liveliness
docker logs --tail 100 haiven-orchestrator
docker logs --tail 100 litellm
docker logs --tail 100 haiven-orchestrator 2>&1 | grep -i "classifier_parse_failed\|classifier_unknown_intent"
Verify the deployed classifier setting:
docker inspect haiven-orchestrator --format '{{range .Config.Env}}{{println .}}{{end}}' | grep ORCH_CLASSIFIER_MODEL
docker exec redis redis-cli -n 1 PING
docker exec redis redis-cli -n 1 KEYS "orch:session:*"
docker logs --tail 50 agent-briefing
docker logs --tail 50 work-hub
docker logs --tail 50 haiven-knowledge
docker logs --tail 50 research-agent
The current runtime taxonomy has 17 intents:
briefing.dailybriefing.weeklydraftemail.composescheduling.queryscheduling.createscheduling.confirmresearch.topictask.createtask.queryapprovevoice_notereview_feedbackopportunity.scancontent.publishpublishsystem.status