feat: dashboard login gate for public deployments (#148)

fix: model list not updating at startup — fast-retry on auth race (#149)

feat: usage stats page with time-series token tracking (#147)

feat: account management page with batch operations (#146)

fix: write runtime cache to data/ instead of git-tracked config/ (#138)

feat: detect banned accounts and show status in dashboard (#142)

fix: handle new Responses SSE lifecycle events (#137)

fix: remove isCodexCompatibleId whitelist — trust backend model list (#129)

fix: allow multiple team accounts sharing same chatgpt_account_id (#126) (#127)

fix: prevent quota-exhausted accounts from cycling back to active (#115)

fix: clear quota warnings when account is deleted (#100) (#102)

refactor: decouple AccountPool, split codex-api and web.ts, fix CI (#113)

fix: make instructions optional in /v1/responses for client compatibility (#71) (#112)

feat: add sticky rotation strategy (#107) (#110)

feat: add POST /admin/refresh-models endpoint + plan routing integration tests (#104)

refactor: migrate electron from branch to npm workspace

feat: add quota settings UI to dashboard (#101)

fix: macOS Electron login error -86 (EBADARCH) due to wrong-arch curl binary (#96) (#98)

fix: disable desktop context injection by default (#95) (#97)

feat: auto-refresh quota with tiered warnings (#92) (#93)

feat: bulk account import/export with selective export (#82)

feat: WebSocket transport + previous_response_id for multi-turn (#84)

fix: add Cache-Control headers to prevent stale frontend after update (#79)

feat: tuple schema (prefixItems) support for structured outputs (#77)

feat: model list auto-sync + theme contrast fix

feat: Docker image auto-publish to GHCR + Watchtower support

fix: simplify hardRestart — remove helper script, spawn directly with EADDRINUSE retry

fix: harden extraction pipeline + update Codex Desktop v26.309.31024

fix: review improvements — schema walker, status helper, UI i18n, CI version skip

feat: add Structured Outputs support (response_format → text.format)

docs: add mixed-plan routing fix to changelog (#54)

docs: fix model removal scope — free only, not plus

docs: update model catalog and changelog for 2026-03-10 changes

fix: Electron OAuth login + i18n layout shift + update modal (#53)

Merge pull request #44 from icebear0828/fix/service-tier-and-headers

fix: lock container PORT=8080, revert HEALTHCHECK to hardcoded port

fix: strip service_tier from request body + add OpenAI-Beta header + update gpt-5.4 efforts

fix: expose OAuth callback port 1455 in Docker Compose

fix: Dockerfile HEALTHCHECK respects PORT env var (#40)

feat: /v1/responses passthrough endpoint + missing SSE event types + Docker docs fix (#37, #38)

feat: model name suffix system + service_tier + Docker persistence fix (#35)

feat: proxy assignment management page with bulk operations (#34)

fix: remove wall-clock timeout from streaming SSE to prevent thinking chain cutoff

feat: add proxy pool for per-account proxy routing

feat: GitHub Star badge + check-for-updates in dashboard header

feat: add gpt-5.4 + codex-spark support, matrix model selector, extended reasoning efforts

feat: add reasoning/thinking output support for OpenAI and Anthropic routes

docs: remove external contributor mention from CHANGELOG

fix: Anthropic route thinking blocks validation + context token display

feat: add image input support for all API routes