Darien Kindlund fca08e8acc fix: escalate to heavy Prisma reconnect after consecutive lightweight failures (#22211) ... When the Prisma query engine process is alive but not accepting connections (e.g., startup race condition in containerized deployments), lightweight reconnects (disconnect + connect) will never succeed. The health watchdog retries indefinitely without escalating to a full Prisma client recreation. Adds a consecutive failure counter that triggers a heavy reconnect (full Prisma client and engine recreation) after 3 consecutive lightweight reconnect failures (configurable via PRISMA_RECONNECT_ESCALATION_THRESHOLD env var). Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>		2026-03-02 19:21:11 +05:30
..
_experimental/mcp_server	Fix/non standard mcp url pattern (#19738)	2026-01-25 23:00:53 -08:00
guardrails	fix Unauthenticated RCE and Sandbox Escape in Custom Code Guardrail	2026-02-25 17:57:32 +05:30
management_endpoints	fix(proxy): skip premium check for empty metadata fields on team/key update	2026-02-06 14:50:24 -05:00
test_claude_code_marketplace.py	Fix/claude code plugin schema (#22271)	2026-02-27 15:59:37 -08:00
test_init_litellm_callbacks.py	fix: prevent double-counting of litellm_proxy_total_requests_metric (#21159)	2026-02-16 09:10:49 -08:00
test_model_based_routing_files_batches.py	fix(proxy): use batch_ prefix for Vertex AI batch IDs in encode_file_id_with_model (#21624)	2026-02-20 08:32:46 -08:00
test_prisma_engine_watchdog.py	fix: escalate to heavy Prisma reconnect after consecutive lightweight failures (#22211)	2026-03-02 19:21:11 +05:30