AJ Isaacs 0ff962c95e feat: generate topic drift redirects via LLM with full conversation context ...

Replace static random templates with LLM-generated redirect messages that
reference what the user actually said and why it's off-topic. Sass escalates
with higher strike counts. Falls back to static templates if LLM fails or
use_llm is disabled in config.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-27 15:28:36 -05:00

cogs

feat: generate topic drift redirects via LLM with full conversation context

2026-02-27 15:28:36 -05:00

docs/plans

docs: add conversational memory implementation plan

2026-02-26 12:44:18 -05:00

prompts

feat: generate topic drift redirects via LLM with full conversation context

2026-02-27 15:28:36 -05:00

scripts

fix: use escalation model and fallback to permanent memories in migration

2026-02-26 13:14:38 -05:00

utils

fix: deduplicate memories on save with exact-match check

2026-02-27 10:53:52 -05:00

.env.example

Support hybrid LLM: local Qwen triage + OpenAI escalation

2026-02-23 12:20:07 -05:00

.gitignore

Initial commit: Breehavior Monitor Discord bot

2026-02-20 22:39:40 -05:00

bot.py

chore: remove wordle cog

2026-02-27 10:48:44 -05:00

CLAUDE.md

chore: remove wordle cog

2026-02-27 10:48:44 -05:00

config.yaml

feat: generate topic drift redirects via LLM with full conversation context

2026-02-27 15:28:36 -05:00

docker-compose.yml

Initial commit: Breehavior Monitor Discord bot

2026-02-20 22:39:40 -05:00

Dockerfile

Fix missing libgssapi-krb5-2 dependency in Docker image

2026-02-20 22:48:15 -05:00

requirements.txt

Initial commit: Breehavior Monitor Discord bot

2026-02-20 22:39:40 -05:00

Description

No description provided

1.2 MiB

Languages

Python 98.8%

Shell 0.8%

Dockerfile 0.4%