Changelog

TokenTriage has grown in capability waves. This page summarizes what each wave added, by theme; the authoritative, dated record is docs/CHANGELOG.md in the repository.

The trust dashboard

The embedded, self-contained SPA on the admin plane — the same numbers as the CLI, with honesty on every pixel: the typed Money component with pricing provenance, the EST flag, UNPRICED as an excluded slice, the realtime Live feed, provider-bill reconciliation, budgets and alerting, the robust-seasonal-v1 anomaly detector, and demo mode. See The trust dashboard.

Provider breadth

Providers-as-data: many providers carried as catalog descriptors over four in-code wire dialects, so adding an OpenAI-compatible upstream is N+1-by-config. Azure, Bedrock (SigV4 + binary event-stream), and Gemini/Vertex land here, along with opt-in cross-dialect translation. See Providers.

The routing policy language

A typed, deterministic policy language with a first-class explanation on every decision — five node kinds, a frozen condition language, and the strategy recipes. A legacy routing.rules config desugars to it and decides byte-identically. See The routing policy language.

Response & semantic caching

The first honest LLM-router cache: off by default, shadow-first, byte-faithful, and honestly costed, with air-gapped exact/normalized tiers and an opt-in, bounded semantic tier whose savings are licensed by evidence. See Response caching.

Virtual keys & governance

Minted virtual keys and per-tenant budgets, quotas, rate, and concurrency limits, built so a refusal can never lie — row == wire, fail-open with disclosure, and a shadow-first enablement ladder, with an opt-in distributed tier for multi-replica coordination. See Governance.

---

For the complete, versioned history — including the compatibility guarantees re-proven each release — read the repository CHANGELOG.md.