alvis aa4bdd8f09 feat(admin): LLM tip quality dashboard — per-model/prompt/kind breakdowns ...

/admin/reward-analytics now surfaces served count, reaction rate, and avg
reward grouped by llm_model, prompt_version, and tip_kind — closing the
loop so model/prompt iterations in M2 are legible next to the bandit
policy view. Data comes from the tip_scores columns added in ffdf707 and
tip_feedback.reward_milli; bandit-only tips show as "(bandit-only)".

Closes #92.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-04-24 15:24:52 +00:00

..

db

feat: M2 AI tips — LiteLLM gateway, context assembler, end-to-end generation pipeline

2026-04-17 14:09:02 +00:00

events

test: cover NATS bridge + Todoist scheduler; ADR-0010

2026-04-18 07:55:25 +00:00

middleware

feat: ε-greedy v1 as active policy; dwell-time reward inference; offline sim framework

2026-04-16 07:44:37 +00:00

routes

feat(admin): LLM tip quality dashboard — per-model/prompt/kind breakdowns

2026-04-24 15:24:52 +00:00

signals

test: cover NATS bridge + Todoist scheduler; ADR-0010

2026-04-18 07:55:25 +00:00

test

feat(admin): LLM tip quality dashboard — per-model/prompt/kind breakdowns

2026-04-24 15:24:52 +00:00

config.ts

feat: NATS JetStream + Todoist background sync (#21, #22)

2026-04-18 01:18:51 +00:00

index.ts

feat: NATS JetStream + Todoist background sync (#21, #22)

2026-04-18 01:18:51 +00:00