mirror of
https://github.com/discourse/discourse.git
synced 2026-08-09 21:45:25 +08:00
cc14e6e402Previously, AI agents had no way to suspend or silence users, and approving any moderation tool action meant leaving the conversation for the `/review` queue. This change adds `suspend_user`/`silence_user` tools that always require moderator approval, and lets moderators approve or reject those actions from an inline review card right in the bot conversation — credited to the approving moderator (not the bot) in the staff action log — instead of switching to the `/review` queue. Demo of this feature: https://github.com/user-attachments/assets/b9605511-e53d-483d-b435-b212694cdf53 https://github.com/user-attachments/assets/383bda5d-93ee-4758-a51e-6162ea0d57ee --------- Co-authored-by: Penar Musaraj <pmusaraj@gmail.com> |
||
|---|---|---|
| .. | ||
| discourse_ai/ai_bot | ||
| ai_agent_mcp_server_spec.rb | ||
| ai_agent_multisite_spec.rb | ||
| ai_agent_spec.rb | ||
| ai_api_request_stat_spec.rb | ||
| ai_artifact_key_value_spec.rb | ||
| ai_mcp_server_spec.rb | ||
| ai_secret_spec.rb | ||
| ai_tool_action_spec.rb | ||
| ai_tool_spec.rb | ||
| embedding_definition_spec.rb | ||
| inferred_concept_spec.rb | ||
| llm_credit_allocation_spec.rb | ||
| llm_credit_daily_usage_spec.rb | ||
| llm_feature_credit_cost_spec.rb | ||
| llm_model_spec.rb | ||
| llm_quota_spec.rb | ||
| llm_quota_usage_spec.rb | ||
| model_accuracy_spec.rb | ||
| rag_document_fragment_spec.rb | ||
| reviewable_ai_chat_message_spec.rb | ||
| reviewable_ai_post_spec.rb | ||
| reviewable_ai_tool_action_spec.rb | ||
| shared_ai_conversation_spec.rb | ||
| user_option_spec.rb | ||
