progress 235b

pyinfra/framework/compose/litellm/smoke.sh

@@ -0,0 +1,50 @@
+#!/usr/bin/env bash
+# Smoke-test the LiteLLM proxy. /health/readiness for liveness, /v1/models
+# for the configured backends, then /health (which dials every backend)
+# to surface which ones are actually reachable right now.
+set -euo pipefail
+
+HOST="${LITELLM_HOST:-127.0.0.1:4000}"
+# Read master key from sibling .env if present, otherwise from environment.
+if [[ -z "${LITELLM_MASTER_KEY:-}" && -f "$(dirname "$0")/../.env" ]]; then
+    # shellcheck disable=SC1091
+    source "$(dirname "$0")/../.env"
+fi
+if [[ -z "${LITELLM_MASTER_KEY:-}" ]]; then
+    echo "[smoke] LITELLM_MASTER_KEY not set — export it or populate /srv/docker/litellm/.env" >&2
+    exit 1
+fi
+
+echo "[smoke] GET /health/readiness on $HOST (proxy alive?)"
+curl -fsS "http://$HOST/health/readiness" \
+    -H "Authorization: Bearer $LITELLM_MASTER_KEY" \
+  | python3 -m json.tool
+
+echo
+echo "[smoke] GET /v1/models (configured model_names)"
+curl -fsS "http://$HOST/v1/models" \
+    -H "Authorization: Bearer $LITELLM_MASTER_KEY" \
+  | python3 -c "
+import json, sys
+r = json.load(sys.stdin)
+for m in r.get('data', []):
+    print(f\"  - {m.get('id', '?')}\")"
+
+echo
+echo "[smoke] GET /health (each backend's reachability — slow, ~10s)"
+curl -fsS "http://$HOST/health" \
+    -H "Authorization: Bearer $LITELLM_MASTER_KEY" \
+  | python3 -c "
+import json, sys
+r = json.load(sys.stdin)
+healthy = r.get('healthy_endpoints', [])
+unhealthy = r.get('unhealthy_endpoints', [])
+print(f'  healthy:   {len(healthy)}')
+for e in healthy:
+    print(f'    + {e.get(\"model\", \"?\")}')
+print(f'  unhealthy: {len(unhealthy)}')
+for e in unhealthy:
+    print(f'    - {e.get(\"model\", \"?\")}: {e.get(\"error\", \"?\")[:80]}')"
+
+echo
+echo "[smoke] passed — proxy up, model list populated. Unhealthy backends are expected if their compose stacks are down."