Developer
0bd4369ae9
Build & Deploy (Nix) / build-and-deploy (backend) (push) Successful in 3m2s
Build & Deploy (Nix) / build-and-deploy (discord-gateway) (push) Successful in 2m20s
Build & Deploy (Nix) / build-and-deploy (proxy) (push) Successful in 2m26s
Delete fastClassifier.ts (manual regex patterns for phone/email/IP/crypto/ spam/toxicity) and simpleFallback.ts. These hardcoded patterns were the source of false positives (Discord emoji snowflakes matched phone_number, URL digits matched phone, etc.) and produced heuristic verdicts whenever the LLM failed. New flow: Message → LLM (with conversation context, media evidence, user reputation) → verdict. On LLM failure the message is marked 'error' and retried by the recovery worker — no heuristic verdicts, ever. Discord markdown tokens (custom emoji/mentions/timestamps) are normalized to readable placeholders ([emoji:name], @user, @role, #channel, [time]) before reaching the LLM via discordTokens.ts.