v1.6.0
Release Date: 2026-11-13
Theme: Maximum Provider & Model Compatibility, Modality FinOps, Production Test Suite & K8s Hardening
Model Catalog, Provider Compatibility & Operation Enforcement
- Upstream Catalog Parity & Capability Generalizations (
cmd/catalog-sync/,internal/modelcatalog/): Expandedcmd/catalog-syncandinternal/modelcatalogwith operation-level model support, modality pricing provenance, and explicit inferred capability generalizations (internal/modelcatalog/generalizations.go) without treating unverified catalog rates as verified for budgeted traffic. - Operation-Level Routing Enforcement & Certified OpenAI-Compatible Profiles (
internal/router/,internal/adapter/openaicompat/): AddedSupportedOperationsenforcement across router dispatch (internal/router/reliability.go) and expanded certified provider profiles (internal/adapter/openaicompat/extended_profiles.go,validator.go). - Multimodal Native Adapter & Responses API Extensions (
internal/adapter/): Expanded multimodal content, tool-only streaming, and audio/image/rerank wire handling across native adapters (anthropic,bedrock,cohere,gemini,mistral,ollama,openai,vertex) and/v1/responses.
Storage, FinOps & Security Fixes
- Migration
0012& Modality Persistence (migrations/): Addedmigrations/0012_add_cache_write_and_operations.{up,down}.sqlfor cache-write pricing and per-model operation declarations across PostgreSQL and in-memory repositories. - PostgreSQL
file_uploadsQuery Fix (internal/storage/postgres.go): Removed invalid::uuidcasts onVARCHAR(64)org_id,team_id, anduser_idcolumns inCreateFile,GetFile,ListFiles, andDeleteFile. - In-Memory Spend Outbox & Redis Breaker Fixes (
internal/storage/,internal/cache/): Deleted delivered entries fromMemoryRepository.spendOutboxinMarkSpendEventDeliveredto prevent $O(N^2)$ lock scans under sustained soak load, and treatedredis.Nilcache misses as non-failures inRedisFabriccircuit breakers.
Production Testing, Docker & Kubernetes Hardening
- Hardened Kubernetes Kustomize Manifests (
deployments/k8s/): Addeddeployments/k8s/with a 2-replicagatewaydeployment, non-rootsecurityContext(runAsNonRoot: true,runAsUser: 65532,readOnlyRootFilesystem: true,capabilities.drop: ["ALL"]),/readyz+/healthzprobes, andpostgres+redisservices. See Kubernetes & Kustomize Deployment. - Containerized Production Suite & Load/Canary Harnesses (
deployments/,tests/): Addeddeployments/docker-compose.test.yml,tests/load/(5-minute Go soak +k6_gateway_smoke.js),tests/canary/(//go:build canary),tests/e2e/budget_concurrency_test.go,tests/e2e/modality_compat_test.go,tests/e2e/security_boundaries_test.go, andmake test-prod-containers(gitleaks,trivy,govulncheck,k6,pgbench,redis-benchmark).