LOCALAI_MODERATION_DISABLED switched off OpenAI moderation for every model (ASB-405) 76a5d9ca
Moderation of service: openai models runs again when LOCALAI_MODERATION_DISABLED=true is set, which is the Helm default (localaiModerationDisabled: true). Since 4.8.0 that switch disabled the input check, the output check and the text-to-speech check for every OpenAI-compatible service instead of LocalAI only. LocalAI models stay unmoderated; moderationDisabled is the only global switch.
Deployments that point service: openai at a self-hosted endpoint without /v1/moderations now send moderation requests and fail on them. Use service: localai for self-hosted models, or set moderationDisabled: true.
Embeddings endpoint answers with 500 on every App Suite start without a vector store (ASB-432) 7787230e
Load the Smart Search embeddings state on first use instead of at App Suite start, so users without Smart Search no longer call the embeddings endpoints
Return an empty list from GET /api/embeddings/ when no vector store is configured instead of an error
Missing resource requests and limits on cleanupdb and migratedb jobs (ASB-219)
Set resource requests and limits from .Values.resources on the cleanupdb CronJob and the migratedb Job, so clusters that enforce resource specs no longer reject these pods
AI chat fails with an error for every message after a broken tool call (ASB-164) 8dcb0891
Fix streamed tool call arguments being prefixed with "NaN" when a model's first delta omits the arguments field, which permanently broke the affected chat
Ignore malformed tool calls when replaying a chat history instead of failing the whole request
Ai-chat broken in plain text mode (ASB-144) 62b88986
Bad contrast of code blocks and user messages in ai chat in Dark theme (ASB-136) 4c81caec
Chat input no longer collapses to auto height while typing 5d6f2670