rob thijssen
bc74e0e95f
Some checks failed
CI / Format (push) Successful in 38s
CI / CUDA type-check (push) Successful in 1m39s
CI / Clippy (push) Successful in 2m26s
CI / Test (push) Successful in 4m49s
CI / Build cortex SRPM (push) Has been skipped
CI / Build neuron SRPM (push) Has been skipped
CI / Publish cortex to COPR (push) Has been skipped
CI / Publish neuron to COPR (push) Has been skipped
CI / Bump version in source (push) Has been skipped
build-prerelease / Package helexa-bench RPM (push) Blocked by required conditions
build-prerelease / Resolve version stamps + change detection (push) Successful in 32s
build-prerelease / Build neuron-blackwell (push) Successful in 1m40s
build-prerelease / Build neuron-ada (push) Successful in 2m19s
build-prerelease / Build neuron-ampere (push) Successful in 2m22s
build-prerelease / Lint (fmt + clippy) (push) Successful in 2m49s
build-prerelease / Build cortex binary (push) Successful in 3m0s
build-prerelease / Test (push) Successful in 4m25s
build-prerelease / Package cortex RPM (push) Successful in 1m32s
build-prerelease / Package helexa-neuron-ada RPM (push) Successful in 1m50s
build-prerelease / Package helexa-neuron-ampere RPM (push) Successful in 1m49s
build-prerelease / Package helexa-neuron-blackwell RPM (push) Successful in 1m54s
build-prerelease / Build helexa-bench binary (push) Successful in 2m12s
build-prerelease / Publish to rpm.lair.cafe (unstable) (push) Has been cancelled
Stage 1's build seam (#50): the interface auth, metering, and budget enforcement all hang off, with a local/static provider so the A0 amplification fix can land before any upstream clearing house exists. The future helexa-upstream client (#57) is just another impl. - cortex-core::entitlements: Principal {account_id, key_id}, CapWindow (Balance | Rolling{seconds}), Reservation handle, BudgetSnapshot, AuthError/BudgetError, and the async EntitlementProvider trait (resolve / reserve / settle / release / snapshot). BudgetError carries the window semantics so callers pick the #63 code (rate_limit_exceeded + Retry-After vs insufficient_quota) without the provider touching HTTP. - cortex-core::config: [entitlements] section on GatewayConfig (require_auth + [[entitlements.keys]] with account_id, optional key_id, hard_cap, window). Additive + serde(default) — anonymous/uncapped when omitted, so existing setups are unaffected. - cortex-gateway::entitlements_local: LocalEntitlementProvider. Budget math serialized under one Mutex so spent+reserved can never exceed a hard cap under concurrency (the #52 guarantee); rolling windows reset lazily; uncapped keys (no hard_cap) always reserve but still meter. - CortexState gains Arc<dyn EntitlementProvider> + require_auth, built in from_config. Not yet consumed by the request path — auth middleware is 1b (#49), enforcement is 1d (#52). - cortex.example.toml documents the section; test GatewayConfig literals updated for the new field. 6 provider unit tests (resolve, unknown-key, round-trip, balance/rolling over-cap codes, uncapped infra key). Local fmt/clippy/test all green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
14 KiB
14 KiB