* feat(alibaba): add free-tier routing with console quota and builtin allowlist
Classify DashScope free vs paid models via console quota API, a hardcoded
operator allowlist fallback, and per-connection drained tracking. Wire wildcard
combo expansion, model refresh, combo exhaustion, and audit redaction for
Alibaba console credentials.
* fix(routing): reset forced connection pin and persist Alibaba free-tier drain
Drop session affinity pins when a forced connection is excluded after 429,
and record Alibaba free-tier exhaustion on upstream 403 so per-key drained
lists stay accurate without blocking sibling keys.
* fix(alibaba): prefer live quota sync over static free-tier allowlist
Stop unioning the builtin text allowlist when a console quota snapshot exists,
treat expired quotaValidityPeriod as not_capable, and add a dated JSON pack plus
sync-alibaba-allowlist script for operator refresh without code edits.
* docs(alibaba): document free-tier console path + allowlist env overrides
Adds the 4 ALIBABA_FREE_TIER_*_FE_PATH / ALIBABA_FREE_TIER_ALLOWLIST_PATH
env vars (referenced by alibabaFreeTierQuotaFetcher.ts and
alibabaFreeTierAllowlist.ts) to .env.example and
docs/reference/ENVIRONMENT.md so the env/docs contract check passes.
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
* refactor(open-sse): split alibabaFreeTierQuotaFetcher.ts under file-size cap
Extract pure parsing/classification/eligibility-filtering logic into
alibabaFreeTierQuotaClassify.ts and shared types/primitives into
alibabaFreeTierQuotaTypes.ts, leaving the HTTP/console-fetch flow in the
original file. Public API is unchanged (re-exported), behavior is identical.
Co-authored-by: AndrianBalanescu <AndrianBalanescu@users.noreply.github.com>
* fix: resolve typecheck errors in alibaba-free-tier routing
---------
Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>
Co-authored-by: AndrianBalanescu <AndrianBalanescu@users.noreply.github.com>
Co-authored-by: AndrianBalanescu <andrian@balanescu.dev>
