leubeem b6f265588d feat(pm): LLM routing endpoint, usage capture, and admin review view ...

Backend counterpart to the Python engine's semantic router.

- POST /api/decision/route: service-secret-guarded endpoint the Python
  backend calls on regex-miss. Calls gpt-5-mini (ROUTER_LLM_MODEL),
  validates the chosen id against the candidate set, and writes both a
  UsageEvent (central cost ledger) and a routing-review record — including
  timeouts, with timeoutMs + actual latencyMs — so the budget can be tuned
- LlmRoutingDecision model + GET /api/admin/llm-routing (paginated,
  status-filtered, per-status counts)
- admin "LLM Routing" tab: transcript vs expected phrase, candidate chips
  with the chosen one highlighted, latency/budget chip, model reason
- serviceAuth util (mirrors CRON_SECRET pattern)
- .env.example: ROUTER_LLM_MODEL, SERVICE_SECRET

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-29 10:27:57 +02:00

..

api

feat(pm): LLM routing endpoint, usage capture, and admin review view

2026-06-29 10:27:57 +02:00

data

Add roadmap sim-control idea and update classroom news date

2026-02-15 15:41:02 +01:00

middleware

feat(server): per-user AI usage tracking, cost alerting, and endpoint hardening

2026-06-10 23:17:03 +02:00

models

feat(pm): LLM routing endpoint, usage capture, and admin review view

2026-06-29 10:27:57 +02:00

plugins

fix(security): mandatory cron secret + reject placeholder JWT secrets (SEC-07, OPS-02, SEC-09)

2026-06-17 11:07:27 +02:00

services

fix typescript errors and update dependencies

2026-02-17 18:13:04 +01:00

utils

feat(pm): LLM routing endpoint, usage capture, and admin review view

2026-06-29 10:27:57 +02:00