Implement the multi-provider routing system for the OpenAI gateway, including two new database tables (`gateway_providers`, `gateway_models`) ensured at init, a new admin page at `/admin/gateway` with full CRUD for providers and model routes, and a `"gateway"` audit category mapped to `"ai"`. The routing layer sits transparently on top of the existing single-provider default path: unmatched model names fall through unchanged, while matched routes forward to the configured provider with their own pricing economy, vision model, and context window. Cross-worker cache invalidation uses a shared `_ROUTING_CACHE` bumped via `"gateway_routing"` cache version.
Implement a multi-agent deep web research subsystem including CLI commands for pruning expired jobs and clearing all artifacts, database tables for sessions/messages/URL cache with indexes, config paths for chroma storage, and internal embed URL for vector operations.
Add POST /openai/v1/embeddings route in openai_gateway router, new config fields for embedding upstream URL/model/key/enabled toggle with defaults pointing to OpenRouter Qwen3 8B, INTERNAL_EMBED_MODEL constant in config.py, documentation in docs_api.py and README.md describing the molodetz~embed model mapping, and embed-call tracking in gateway metrics alongside existing chat/vision counters.
Split the monolithic test directory into three tiers (unit, api, e2e) with a path-mirroring directory structure. Added corresponding Makefile targets (test-unit, test-api, test-e2e) and updated all documentation references (CLAUDE.md, README.md, testing-cicd.html, testing-framework.html, testing-make.html) to reflect the new layout and naming conventions.
