aleksey
a2d238d92e
Make Zed Agent closer to Cursor: deterministic DevOps path index, live Traefik port probe before blind edits, stop-after-edit, and quieter Russian progress.
104 lines
4.0 KiB
Bash
104 lines
4.0 KiB
Bash
#!/usr/bin/env bash
|
|
# Deploy Cursor-parity AiRouter (Max plan / Coder routine / DeepSeek hard) to IFT
|
|
set -euo pipefail
|
|
AIR=/mnt/c/Users/alexc/IdeaProjects/eventHub/EventHubAiRouter
|
|
cd "$AIR"
|
|
|
|
echo "== Local unit + compile =="
|
|
python3 -m py_compile \
|
|
router/agent_hier.py router/router.py router/hierarchical.py router/orchestrator.py
|
|
python3 -m unittest discover -s test/unit -q
|
|
PRIMARY_PROVIDER=hybrid python3 scripts/gen-litellm-config.py
|
|
|
|
echo "== Sync to eventhub-ift =="
|
|
scp \
|
|
router/agent_hier.py \
|
|
router/router.py \
|
|
router/hierarchical.py \
|
|
router/orchestrator.py \
|
|
eventhub-ift:/opt/ai-router-stack/router/
|
|
scp \
|
|
config/orchestration.yaml \
|
|
config/providers.yaml \
|
|
config/routing_rules.yaml \
|
|
eventhub-ift:/opt/ai-router-stack/config/
|
|
scp litellm_config.yaml eventhub-ift:/opt/ai-router-stack/litellm_config.yaml
|
|
scp README.md AGENTS.md eventhub-ift:/opt/ai-router-stack/ 2>/dev/null || true
|
|
|
|
ssh -o BatchMode=yes eventhub-ift bash -s <<'REMOTE'
|
|
set -euo pipefail
|
|
cd /opt/ai-router-stack
|
|
set -a; source .env; set +a
|
|
export PRIMARY_PROVIDER="${PRIMARY_PROVIDER:-hybrid}"
|
|
|
|
sed -i 's/\r$//' \
|
|
router/agent_hier.py router/router.py router/hierarchical.py router/orchestrator.py \
|
|
config/orchestration.yaml config/providers.yaml config/routing_rules.yaml \
|
|
litellm_config.yaml || true
|
|
|
|
echo "== Build gateway image =="
|
|
docker build -f router/Dockerfile -t "${ROUTER_IMAGE:-git.sabilin.com/eventhub/ai-router-gateway:ift}" .
|
|
|
|
TS=$(date +%Y%m%d%H%M%S)
|
|
ORCH="orchestration_config_${TS}"
|
|
LITC="litellm_config_${TS}"
|
|
docker config create "$ORCH" ./config/orchestration.yaml
|
|
docker config create "$LITC" ./litellm_config.yaml
|
|
|
|
OLD_ORCH=$(docker service inspect ai-router_router --format '{{range .Spec.TaskTemplate.ContainerSpec.Configs}}{{println .ConfigName}}{{end}}' | grep orchestration | tail -1 || true)
|
|
OLD_LIT=$(docker service inspect ai-router_litellm --format '{{range .Spec.TaskTemplate.ContainerSpec.Configs}}{{println .ConfigName}}{{end}}' | grep litellm_config | grep -v entrypoint | tail -1 || true)
|
|
|
|
echo "== Update ai-router_router =="
|
|
RARGS=(--image "${ROUTER_IMAGE:-git.sabilin.com/eventhub/ai-router-gateway:ift}" --force)
|
|
RARGS+=(--config-add "source=${ORCH},target=/app/config/orchestration.yaml")
|
|
if [ -n "${OLD_ORCH:-}" ]; then
|
|
RARGS+=(--config-rm "$OLD_ORCH")
|
|
fi
|
|
docker service update "${RARGS[@]}" ai-router_router >/dev/null
|
|
|
|
echo "== Update ai-router_litellm =="
|
|
LARGS=(--force)
|
|
LARGS+=(--config-add "source=${LITC},target=/app/config.yaml")
|
|
if [ -n "${OLD_LIT:-}" ]; then
|
|
LARGS+=(--config-rm "$OLD_LIT")
|
|
fi
|
|
docker service update "${LARGS[@]}" ai-router_litellm >/dev/null
|
|
|
|
echo "== Wait health =="
|
|
ok=0
|
|
for i in $(seq 1 60); do
|
|
if curl -sf --max-time 5 https://ai-router.ift.calentiq.com/health >/dev/null \
|
|
&& curl -sf --max-time 5 https://litellm.ift.calentiq.com/health/liveliness >/dev/null; then
|
|
ok=1
|
|
break
|
|
fi
|
|
sleep 3
|
|
done
|
|
if [ "$ok" != 1 ]; then
|
|
echo "ERROR: health not ready" >&2
|
|
docker service ps ai-router_router --no-trunc | head -8
|
|
docker service ps ai-router_litellm --no-trunc | head -8
|
|
exit 1
|
|
fi
|
|
|
|
RID=$(docker ps -q -f name=ai-router_router | head -1)
|
|
LID=$(docker ps -q -f name=ai-router_litellm | head -1)
|
|
echo "== Verify orchestration =="
|
|
docker exec "$RID" grep -E 'planner_model:|verifier_model:|agent_executor_model:|executor_synthetic_mode:|worker_map:|hard:' /app/config/orchestration.yaml
|
|
echo "== Verify litellm novita-planner =="
|
|
docker exec "$LID" sh -c 'grep -A6 "model_name: novita-planner" /app/config.yaml | head -8'
|
|
|
|
echo "== Smoke classify + chat =="
|
|
curl -sf --max-time 30 -H "Authorization: Bearer ${ROUTER_API_KEY}" \
|
|
-H "Content-Type: application/json" \
|
|
-d '{"text":"поправь timeout в router.py"}' \
|
|
https://ai-router.ift.calentiq.com/classify | head -c 400
|
|
echo
|
|
curl -sf --max-time 90 -H "Authorization: Bearer ${ROUTER_API_KEY}" \
|
|
-H "Content-Type: application/json" \
|
|
-d '{"model":"smart-router","messages":[{"role":"user","content":"ping"}],"max_tokens":8}' \
|
|
https://ai-router.ift.calentiq.com/v1/chat/completions | head -c 500
|
|
echo
|
|
echo CURSOR_PARITY_DEPLOY_OK
|
|
REMOTE
|