feat(openfeature): server-side EVP flagevaluation emission#4886

Merged

gh-worker-dd-mergequeue-cf854d[bot] merged 39 commits into

mainfrom

workspace/flag-evaluations-cross-sdk

Jun 22, 2026

Commits on Jun 12, 2026

test(01-01): add failing test stubs + signature-only production stubs for EVP flagevaluation
leoromanovsky
committed
feat(01-01): add BenchmarkFlagEvaluationNoop/OTelOnly/OTelPlusEVP benchmark scenarios
leoromanovsky
committed
feat(01-02): implement flagEvaluationAggregator + writer + transport reuse
leoromanovsky
committed
feat(01-02): implement flagEvaluationHook Finally stage + extraction helpers
leoromanovsky
committed
feat(01-02): wire EVP flagevaluation hook + writer into provider (Task 3)
leoromanovsky
committed
feat(01-03): wire real EVP hook in OTelPlusEVP benchmark (no-flush writer)
leoromanovsky
committed
fix(openfeature): deterministic context hash + drop dead targeting_rule field (CR-01, WR-01, WR-02)
leoromanovsky
committed
fix(openfeature): count cancelled-context evaluations in Finally hook (WR-03)
leoromanovsky
committed
fix(openfeature): rotate benchmark targeting key per iteration (WR-04)
leoromanovsky
committed
chore(env): set DD_FLAGGING_EVALUATION_COUNTS_ENABLED type/default and regenerate
leoromanovsky
committed
fix(openfeature): preserve count signal on global-cap overflow; align EVP flagevaluation contract
leoromanovsky
committed
refactor(openfeature): async best-effort EVP flagevaluation recording; benchmark + comment fixes
leoromanovsky
committed
fix(openfeature): correct EVP flagevaluation context hashing, ultra-degraded bound, post-stop record, and error message
leoromanovsky
committed
fix(openfeature): derive runtime-default from absent variant only (PR review)
leoromanovsky
committed
test(openfeature): table-ify EVP flagevaluation tests and benches
leoromanovsky
committed
refactor(openfeature): tighten EVP flagevaluation writer/hook in place
leoromanovsky
committed
feat(openfeature): 2-tier EVP aggregation (full -> degraded -> drop), remove ultra-degraded; resize caps for 2,500-flag scale
leoromanovsky
committed
test(openfeature): add 2,500-flag scale + parallel benchmarks and aggregator scale harness
leoromanovsky
committed
test(openfeature): modernize range-over-int loops in EVP scale harness (lint)
leoromanovsky
committed
fix(openfeature): use comparable canonical-context key for EVP full-tier buckets
leoromanovsky
committed
perf(openfeature): merge flatten+prune into one EVP worker-path traversal
leoromanovsky
committed
feat(openfeature): record EVP eval-time from provider metadata, not hook-fire time (review #3)
leoromanovsky
committed

Commits on Jun 17, 2026