What shipped, versioned honestly.

1. v2.3.0

   minor Jul 8, 2026

   Guardrail dry-run mode and policy diffs

   • + New dry-run enforcement mode: policies evaluate and log verdicts without blocking, separately from observe (which skips enforcement telemetry).
   • + Policy diff view: compare two policy versions and see which past runs each would have blocked.
   • + Console: the would-have-blocked report exports as CSV.

2. v2.2.0

   minor Jun 16, 2026

   Eval gates in CI

   • + trellis eval --gate exits non-zero when a candidate regresses beyond per-suite thresholds. Add it to any CI as a test step.
   • + Per-suite regression thresholds in trellis.yaml (absolute or relative).
   • + CI examples for the common hosted runners in the docs.

3. v2.1.1

   patch Jun 2, 2026

   Trace ingestion fixes

   • + Fixed a backpressure condition where bursty fleets (over 2k spans/s from one workspace) could delay trace availability by up to 90 s.
   • + Span deduplication for at-least-once SDK delivery: replayed checkpoints no longer double-count tokens in rollups.

4. v2.1.0

   minor May 19, 2026

   Forensic retention tier

   • + New observability tier: 90-day retention with full request and response payloads and eval snapshots.
   • + Payload encryption at rest with customer-managed keys (CMK) on the forensic tier.
   • + Retention is configured per workspace; changes are audit-logged.

5. v2.0.0

   major Apr 28, 2026

   Runs API v2

   • + BREAKING: step objects are now span objects across the API and SDKs, aligning our trace model with OpenTelemetry semantics.
   • + BREAKING: run.cost moves from cents (integer) to a decimal-string USD amount with a per-span breakdown.
   • + v1 endpoints keep working until 2026-11-01; the migration guide maps every renamed field.

6. v1.9.0

   minor Apr 7, 2026

   Human-approval steps

   • + Runs can pause on an approval span. Parked runs hold no compute and cost nothing while waiting.
   • + Approve in the console, by API, or from chat; the approver's identity and timestamp land in the trace.
   • + Configurable timeout with a fallback branch (auto-reject, escalate, or continue).

7. v1.8.0

   minor Mar 17, 2026

   Cost attribution rollups

   • + Tag runs with any metadata (tenant, feature, experiment) and get cost, latency, and outcome rollups per key.
   • + Monthly invoice line items can be split by one metadata key. Finance teams asked, we shipped.

8. v1.7.1

   patch Mar 2, 2026

   Python SDK retry fix

   • + Fixed a retry storm where a 429 on checkpoint write could trigger immediate retries with no backoff in trellis-python 1.7.0.
   • + SDKs now honor Retry-After on all control-plane endpoints.

9. v1.7.0

   minor Feb 18, 2026

   OpenTelemetry export

   • + Native OTel export: every Trellis span forwards to your collector with standard GenAI semantic-convention attributes.
   • + Prebuilt dashboards for Datadog and Grafana in the integrations gallery.

10. v1.6.0

    minor Feb 4, 2026

    Cache-aware token accounting

    • + Cache reads are now metered separately from fresh input tokens in traces and invoices. Multi-step agents typically see 60% to 90% of input tokens served from provider prompt caches.
    • + Cost projections in the console use your workspace's actual trailing cache-hit rate.

Older releases (v1.0.0 to v1.5.x) live in the console's release archive.