v1.4.13

npx -y @maximhq/deepintshield --transport-version v1.4.13

docker pull maximhq/deepintshield:v1.4.13
docker run -p 8080:8080 maximhq/deepintshield:v1.4.13

DeepIntShield(HTTP) 1.4.13

✨ Features

Plugin Sequencing — Added plugin execution ordering with placement and priority controls for custom plugins relative to built-in plugins
Groq Speech — Added speech synthesis (TTS) and transcription (STT) support for Groq provider
Gemini Model Metadata — Added support for Gemini metadata endpoint (/v1beta/models/{model}) (thanks @Vaibhav701161!)
Wildcard Header Forwarding — Added wildcard pattern support in header forwarding configuration
Log Metadata Columns — Added metadata columns in logs and filters for richer observability
Prompt Caching Improvements — Preserved JSON key ordering for LLM prompt caching using byte-level operations
Azure GCC Cloud Support — Added Azure cloud environment configuration for GCC High and DoD environments
Connection Pool Management — Added connection lifetime limits and optimized pool behavior to prevent stale connections

MCP Tool Headers — Fixed MCP tools not passing required headers to the MCP server
MCP Tool Call Detection — Fixed tool calls not being detected in MCP agent mode when providers return “stop” finish reason
Gemini Finish Reason — Fixed Gemini models not returning correct “tool_calls” finish reason
Prompt Cascade Deletion — Fixed manual cascade deletion for prompt entities

Container Base Image — Upgraded Node and Alpine base images to include latest security patches

Core 1.4.10

feat: added plugin execution ordering with placement and priority controls
feat: added speech synthesis (TTS) and transcription (STT) support for Groq provider
feat: added support for Gemini metadata endpoint (thanks @Vaibhav701161!)
feat: preserved JSON key ordering for prompt caching using byte-level operations with gjson/sjson
feat: improved fasthttp connection pooling with connection lifetime limits and MaxConnDuration
fix: MCP tools now correctly pass headers to the MCP server
fix: ensure tool calls are always detected in MCP agent mode
fix: Gemini models now correctly return finish_reason “tool_calls” when tool calls are present

Framework 1.2.29

feat: added plugin sequencing with placement and order fields in plugin configuration
feat: added metadata columns in logs and filters
fix: manual cascade deletion for prompt entities
chore: upgraded core to v1.4.9

governance 1.4.29

jsonparser 1.4.28

litellmcompat 0.0.18

logging 1.4.29

maxim 1.5.27

mocker 1.4.28

otel 1.1.28

semanticcache 1.4.27

telemetry 1.4.29