refactor: remove unused text analysis module and integrate Qdrant enhancements
Build & Deploy (Nix) / build-and-deploy (backend) (push) Successful in 2m30s
Build & Deploy (Nix) / build-and-deploy (discord-gateway) (push) Successful in 3m7s
Build & Deploy (Nix) / build-and-deploy (proxy) (push) Successful in 3m20s

- Deleted the text analysis prompt constants and helpers as they are no longer needed.
- Added batch search functionality for Qdrant to optimize vector searches.
- Implemented methods for deleting expired Qdrant points and invalidating cache based on content hash.
- Updated text batch processor to use new timeout configurations and modified content building for moderation prompts.
- Enhanced text cache store to support new Qdrant integration and improved cache invalidation logic.
- Introduced a new user reputation model with a more nuanced trust scoring system, including penalties and rewards for user behavior.
- Added unit tests for the new trust model to ensure correctness of penalty and trust gain calculations.
- Updated configuration schema to reflect new timeout settings and removed deprecated OpenAI moderation keys.
This commit is contained in:
Developer
2026-07-31 23:09:00 +07:00
parent fc475dfbb7
commit 6df4f306dd
16 changed files with 893 additions and 802 deletions
@@ -1,11 +0,0 @@
/**
* Text analysis prompt constants and helpers for LLM moderation.
*
* Contains shared types and utilities for text-based analysis scenarios.
*/
export type {
BuildSystemPromptOptions,
PromptMode,
} from "./system.js";
export { buildSystemPrompt, sanitizeAiContent } from "./system.js";