Lock the shared sweeps, and run two pods
Every @Scheduled sweep here whose effect is shared now takes a named distributed lease through SingletonTaskRunner before it does anything, so it runs once acro...
Unreviewed-response counts and a mark-read
Keyed by session guid, which is what a tool window carries. Not audited as a disclosure: it returns counts and never a word of a transcript, and recording a bad...
Point at YugabyteDB and use PostgreSQLDialect
CockroachDB has been replaced by YugabyteDB. Connection strings move from cockroachdb-public:26257 to yb-tserver-service:5433, and the Hibernate dialect from **...
Persist AI conversation PHI access trail to phi_access_log
Stored assistant conversations are the reads least able to afford a 14-day, unqueryable log stream: the module sits outside the compliance boundary, so prompts ...
Record PHI access on every read of stored AI conversation history
Wires the shared §164.312(b) spine into the paths that read persisted prompts and completions. The assistant is the module the compliance assessment put OUTSIDE...
Per-agent scorecard
What each agent actually did: conversations, how often a person had to take over and why, outreach outcomes including the ones held back, and what it cost. Eve...
Model pricing catalog, write path and backfill
Cost accounting could never work: AiModel has price columns, AiModelController reads them and ChatOrchestrationService reads them to compute costEstimate - but ...
Agent-initiated handoff to a human, with context
The AI could not previously ask for a person: escalation rules reached the model via the compiled prompt, but there was no machine-readable signal back, so the ...
Outbound triggers, scheduler and web-chat dispatch
Makes the outreach spine actually fire. The gate, contact state, consent and audit already existed; nothing caused a touch to be evaluated. - NATS enabled for ...
Persist org-wide required text and apply it immediately
AiOrgSettings gained forcedPreamble/forcedFooter and SalesAgentCompiler already folds them into every agent, but the settings controller neither read nor wrote ...
Sales-agent compiler, versioning, outreach gate; fix tool replay
Structured agent config compiles to the system prompt, freezes per published version, and gains the gate an agent must pass before initiating contact. Compiler...
Sales-agent CRUD, mortgage template, and agent-driven chat prompt
- AiSalesAgentController (/api/ai/sales-agents): org-scoped CRUD + GET /templates - SalesAgentTemplateRegistry: built-in starter templates, beginning with a m...
Inline image vision + tier fallback that prefers stronger over weaker
Two limits made org-configured vision unusable for whole classes of caller. 1. Vision was URL-ONLY. Every caller had to stand up public, provider-fetchable ser...
Per-integration public AI prompt + session attribution
Upgrade the public-chat system-prompt waterfall from per-org to per-integration: PublicAiChatController now reads the X-Public-Chat-Key-Hash header (nullable) f...
Per-org public prompt, human-handoff on no provider, anon daily message cap
Tier-aware internal text completion (POST /api/ai/internal/text)
Mirrors the vision path: selectTextProvider picks the org's active provider tagged with the requested cost tier (LIGHT/MEDIUM/HEAVY), falling back by priority; ...
Provider cost-tier/vision passthrough + internal one-shot vision endpoint
AiProviderController reads/echoes costTier + supportsVision. ProviderRoutingService gains selectVisionProvider(orgId, tier). **************** runs a one-shot vi...
Add public AI chat endpoints with RAG integration for anonymous visitors
Adds /api/ai/public/sessions endpoints for anonymous AI chat on marketing sites. Bypasses OTK auth filter for public paths. Uses public-facing system prompt and...
Pass memberType through RAG search for audience-scoped KB results
Resolve member type from MemberRepository and include it in RAG search requests so the vector DB can filter KB articles by audience visibility.
Structured citation post-processing ensures RAG sources are always cited
Wire ConversationContextService for sliding window context management
Trims conversation history to fit model's context window before sending to LLM. Keeps recent messages verbatim, summarizes older ones.
Include clickable source links in RAG context for AI chat
Update RagClient to embed markdown links in the context sent to the AI model. KB articles link to /kb/{guid}, notes link to /notes?id={noteId}. Instructs the mo...
Pass memberId to RAG for note-aware AI chat
Add extractMemberId to SessionHelper. Update RagClient to send memberId in search requests so RAG returns both org KB articles and the member's own AI-enabled n...
Add RAG context injection for Knowledge Base in AI chat
- New RagClient service for calling RAGService semantic search - ChatOrchestrationService injects KB context before AI responds - Configurable via AiOrgSettings...
Support enabling/disabling models via PUT /api/ai/providers/{id}
When the frontend sends a 'models' array of model IDs in the provider update request, models in the array are set active and models not in the array (belonging ...
Add POST **************** endpoint for sending chat messages
Receives user message, sends to AI provider via ChatOrchestrationService, returns complete response. Supports REST-based chat flow.
Add Hugging Face as dedicated provider type with custom adapter
- HuggingFaceAdapter handles HF's URL structure **************** - Model discovery via HF API (warm text-generation models) - Registered in ProviderAdapterFacto...
Add manual model creation, handle 410/404 in test, use discovered model for CUSTOM providers
- POST /api/ai/models endpoint for manually adding models - DELETE /api/ai/models/{id} endpoint - CUSTOM providers use first discovered model for chat test inst...
Implement model auto-discovery on provider test connection
Each provider adapter discovers available models from the provider API. Models are automatically saved to the database when Test Connection succeeds.
Scaffold AIService project with providers, services, websocket, and controllers
AI chat orchestration service on port 4205 with: - WebSocket streaming with session auth via ***/Redis - Chat orchestration with auto-routing, usage tracking, a...
Like what you see shipping?
Every one of these updates lands in your workspace automatically. Start free and watch it grow week after week.