GitLab

对称参照 Claude BetaPolicy 的 fast-mode 过滤实现，新增针对 OpenAI 上游
service_tier 字段（priority / flex，含客户端 "fast" → "priority" 归一化）的
pass / filter / block 三态策略，覆盖全部 OpenAI 入口 + admin 配置入口。

后端核心
- 新增 SettingKeyOpenAIFastPolicySettings、OpenAIFastPolicyRule、
  OpenAIFastPolicySettings 配置模型，含规则的 service_tier × action × scope
  × 模型白名单 × fallback action 维度。
- SettingService.Get/SetOpenAIFastPolicySettings；缺失时返回内置默认策略
  （所有模型的 priority 走 filter，whitelist 为空，fallback=pass）。设计
  依据：service_tier=fast 是用户级开关，与 model 字段正交，默认锁定特定
  model slug 会留下"用 gpt-4 + fast 透传 priority 上游"的绕过路径。JSON
  解析失败不再静默 fallback，slog.Warn 记录脏数据，便于运维定位。
- service_tier 归一化（trim + ToLower + fast→priority + 白名单 priority/flex）
  与策略评估（evaluateOpenAIFastPolicy）作为唯一真实来源，HTTP / WS 共用。
  抽出纯函数 evaluateOpenAIFastPolicyWithSettings，配合 ctx-bound settings
  快照（withOpenAIFastPolicyContext / openAIFastPolicySettingsFromContext），
  WS 长会话入口预取一次后所有帧复用，避免每帧打到 settingService。

HTTP 入口（4 个）
- Chat Completions、Anthropic 兼容（Messages，含 BetaFastMode→priority 二次
  命中）、原生 Responses、Passthrough Responses 全部接入
  applyOpenAIFastPolicyToBody，filter 走 sjson 顶层删除 service_tier，block
  返回 403 forbidden_error JSON。
- 4 入口统一使用 upstream 视角的 model（GetMappedModel +
  normalizeOpenAIModelForUpstream + Codex OAuth normalize 后的 slug），
  避免 chat/messages/native /responses/passthrough 因为 model 维度不同
  造成 whitelist 命中差异。
- 在 pass 路径也把客户端 "fast" 别名归一化为 "priority" 写回 body，
  否则 native /responses 与 passthrough 入口会把 "fast" 原样透传给上游
  导致 400/拒绝（chat-completions 入口的 normalizeResponsesBodyServiceTier
  此前已具备同等行为）。

WebSocket 入口
- 新增 applyOpenAIFastPolicyToWSResponseCreate：严格匹配
  type="response.create"，仅处理顶层 service_tier；filter 用 sjson 删字段，
  block 返回 typed *OpenAIFastBlockedError。
- ingress 路径在 parseClientPayload 内调用，block 命中先 Write Realtime
  风格 error event 再返回 OpenAIWSClientCloseError(StatusPolicyViolation
  =1008)，依赖底层 WebSocket Conn.Write 的同步 flush 保证 error 先于
  close。
- passthrough 路径在 RunEntry 前对 firstClientMessage 应用策略，并通过
  openAIWSPolicyEnforcingFrameConn 包装 ReadFrame 对每个 client→upstream
  帧执行策略；后续帧无 model 字段时回退到 capturedSessionModel。
  filter 闭包内同时侦测 session.update / session.created 帧的 session.model
  字段刷新 capturedSessionModel，封堵"首帧 model=gpt-4o（pass）→
  session.update 改为 gpt-5.5 → 不带 model 的 response.create fallback
  到 gpt-4o"的 mid-session 绕过路径。
- passthrough billing：requestServiceTier 在策略 filter 之后再从
  firstClientMessage 提取，filter 命中时 OpenAIForwardResult.ServiceTier
  上报 nil（default tier），与 HTTP 入口（reqBody 来自 post-filter map）
  / WS ingress（payload 来自 post-filter bytes）的语义一致。
- 错误事件 schema：{event_id: "evt_<32hex>", type: "error",
  error: {type: "forbidden_error", code: "policy_violation", message}}，
  与 OpenAI codex 客户端 error event 解析兼容。

Admin / Frontend
- dto.SystemSettings / UpdateSettingsRequest 新增
  openai_fast_policy_settings 字段（omitempty），bulk GET/PUT 接入。
- Settings 页 Gateway 页签新增 Fast/Flex Policy 表单卡片：
  service_tier × action × scope × 模型白名单 × fallback action 全字段配置。
- 前端守门：openaiFastPolicyLoaded 标志仅在 GET 真带回字段时才允许回写，
  避免 rollout/错误把默认规则覆盖成空；saveSettings 回写循环 skip 该字段，
  由专用刷新逻辑处理；仅 action=block 时发送 error_message，匹配后端
  omitempty 行为。

测试
- HTTP 路径：openai_fast_policy_test.go 覆盖默认配置（whitelist=[]，所有
  模型 priority filter）/ block 自定义错误 / scope 区分 / filter 删字段 /
  block 不改 body / block 短路上游 / Anthropic BetaFastMode 触发 OpenAI
  fast policy 等场景。
- WebSocket 路径：openai_fast_policy_ws_test.go 覆盖
    helper 单元（filter / fast→priority 归一化 / flex 透传 / block typed
    error / 无 service_tier 字节不变 / 非 response.create 帧不动 / 空 type
    帧不动 / event_id+code 字段断言 / 非字符串 service_tier 容错）+
    pass 路径 fast 别名归一化回归 +
    ingress 端到端（filter 后上游不含 service_tier / block 后客户端先收
    error event 再收 close 1008 且上游 0 写）+
    passthrough capturedSessionModel fallback 用例（whitelist 策略下首帧
    建立、缺 model 命中 fallback、缺少 fallback 时的 leak 文档化）+
    passthrough session.update / session.created 旋转 capturedSessionModel
    的 mid-session 绕过回归 +
    passthrough billing post-filter ServiceTier 与 idempotent filter 回归。
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

将 vansour/sub2api#1555 的 OpenAI compact 能力建模手工移植到当前 main：账号
级 compact 状态/auto-force_on-force_off 模式、compact-only 模型映射、调度器
tier 分层（已支持 > 未知 > 已知不支持）、管理后台 compact 主动探测，以及对应
i18n/状态徽章。普通 /responses 流量行为不变，无数据库迁移。

The hardcoded codex CLI version (0.104.0) causes upstream rejection
when using gpt-5.5 with compact, as the server treats the request
as an outdated client and returns 400/502.

Update codexCLIVersion, codexCLIUserAgent, and openAICodexProbeVersion
to 0.125.0 to match the current Codex CLI release.

Fixes #1933, #1887, #1865
Related: #1609, #1298, #849

In reconstructResponseOutputFromSSE, text content Marshal/Unmarshal
failure previously caused an early return that silently discarded
already-extracted image_generation_call outputs. Now serialization
errors are tolerated so image results still reach the client.

Revert payment/wechat, sora/claude-max cleanup, fork-only migrations,
and cosmetic changes that were brought in by the release sync commit.
Keep only channel-monitor related improvements:
- PublicSettingsInjectionPayload named struct with drift test
- ChannelMonitorRunner graceful shutdown in wire
- image_output_price in SupportedModelChip
- Simplified buildSelfNavItems in AppSidebar
- Gateway WARN logs for 503 branches

- Extract PublicSettingsInjectionPayload named struct with drift test
- Add channel_monitor_default_interval_seconds to SSR injection
- Add image_output_price to SupportedModelChip
- Simplify AppSidebar buildSelfNavItems (admins see available channels)
- Add gateway WARN logs for 503 no-available-accounts branches
- Wire ChannelMonitorRunner into provideCleanup for graceful shutdown
- Add migrations 130/131 (CC template userid fix + mimicry field cleanup)
- Clean up fork-only features (sora, claude max simulation, client affinity)
- Remove ~320 obsolete i18n keys
- Add codexUsage utility, WechatServiceButton, BulkEditAccountModal
- Tidy go.sum

- 同步 OpenAI 图片生成与编辑接口
- 接入图片请求解析、账号调度、转发与用量记录
- 接入图片计费与图片用量落库
- 限制 OAuth 生图仅支持无显式模型和尺寸的基础请求

refactor: extract ReadUpstreamResponseBody to deduplicate upstream response read + too-large error handling

Consolidates 9 call sites of resolveUpstreamResponseReadLimit + readUpstreamResponseBodyLimited + ErrUpstreamResponseBodyTooLarge error handling into a single ReadUpstreamResponseBody function with TooLargeWriter callback for API-format-specific error responses (Anthropic, OpenAI, countTokens).

Backend:
- gateway_handler: pass subject.UserID instead of int64(0) for user-level routing
- setting_handler: add missing BalanceLowNotifyRechargeURL to UpdateSettings response
- openai_gateway_service: use applyAccountStatsCost for account stats pricing integration
- embed_on: add local file override (data/public/) for embedded frontend assets

Frontend:
- useTableSelection: add batchUpdate method for batch operations
- AccountsView: virtual scrolling params, Set-based isSelected, swipe virtualization
- ProxiesView: add batchUpdate to selection and swipe-select
- BulkEditAccountModal: fix submit handler to prevent event object as argument
- SettingsView: move payload construction outside try block
- i18n: add general translation keys (saved, deleted, view, validation, allowUserRefund)
- api/client: reorder error fields for consistency
- stores/payment: clarify pollOrderStatus JSDoc

Priority was wrong:
- Before: custom rules → LiteLLM (when ApplyPricingToAccountStats) → nil
- After:  custom rules → totalCost (when ApplyPricingToAccountStats) → LiteLLM → nil

When ApplyPricingToAccountStats is enabled, use the request's actual
client billing cost (before multiplier) as account_stats_cost, instead
of recalculating from LiteLLM per-token prices which produced incorrect
values for per-request billing mode.

LiteLLM model pricing is now the final fallback (priority 3), used only
when neither custom rules nor ApplyPricingToAccountStats apply.

WebSearch tri-state switch:
- Account-level web_search_emulation changed from bool to tri-state
  string: "default" (follow channel) / "enabled" / "disabled"
- shouldEmulateWebSearch checks channel config when account is "default"
- SQL migration converts old bool values
- Frontend select replaces toggle in Edit/CreateAccountModal

Account stats pricing:
- resolveAccountStatsCost uses upstream model (post-mapping) for matching
- Priority: custom rules → model pricing file (when toggle on) → default
- Custom rules always configurable, independent of toggle
- Account ID field changed to searchable selector filtered by platform
- Description updated to reflect new behavior

Quota notification cache fix:
- CheckAccountQuotaAfterIncrement fetches real-time account from DB
- Reconstructs pre-increment usage for accurate threshold crossing detection
- New AccountQuotaReader interface (minimal: GetByID only)

Usage tooltip:
- Per-request/image billing shows per-request price instead of $0 token price
- Token billing continues to show input/output price per million tokens

- resolveAccountStatsCost now uses the final upstream model (after
  account-level mapping) to match custom pricing rules, fixing the
  issue where requested model (e.g. claude-sonnet-4-5) didn't match
  rules configured for upstream model (e.g. claude-opus-4-6)
- Remove tryChannelPricing fallback — only custom rules are applied,
  unmatched requests use default formula (total_cost × rate)
- Remove unused billingService and serviceTier parameters
- Update description: "启用后将支持自定义账号统计的模型价格"

- User balance low notification: email alert when balance drops below
  configurable threshold (user email + verified extra emails)
- Account quota notification: broadcast email to admin-configured
  recipients when daily/weekly/total quota usage exceeds alert threshold
- Admin settings: global enable/disable, default threshold, quota
  notification email list (Email Settings tab)
- User profile: enable/disable, custom threshold, add/remove extra
  notification emails with verification code flow
- Account quota: per-dimension alert toggle and threshold in quota
  control card
- Trigger logic: first-crossing only (old >= threshold && new < threshold
  for balance; old < threshold && new >= threshold for quota), naturally
  prevents duplicate notifications without Redis dedup

Allow channels to configure independent model pricing for account
statistics cost calculation, decoupled from user billing.

Backend:
- Migration 101: channels.apply_pricing_to_account_stats toggle,
  channel_account_stats_pricing_rules/model_pricing tables,
  usage_logs.account_stats_cost column
- resolveAccountStatsCost: match rules by group/account, then channel
  pricing, fallback to original formula when unconfigured
- Integrate into both GatewayService.recordUsageCore and
  OpenAIGatewayService.RecordUsage
- Update 8 account stats SQL queries to use
  COALESCE(account_stats_cost, total_cost) * account_rate_multiplier
- 23 unit tests for matching, pricing lookup, and cost calculation

Frontend:
- Channel edit dialog: toggle + custom rules UI with group/account
  multi-select and pricing entry cards
- API types and i18n (zh/en)

当上游返回SSE格式响应(如sub2api链路)时，API Key账号的非流式路径
未检测SSE，导致终态事件中空output直接透传给客户端。

- 将Content-Type SSE检测从仅OAuth扩展至所有账号类型
- 重命名handleOAuthSSEToJSON为handleSSEToJSON（无OAuth专属逻辑）
- 为透传路径新增handlePassthroughSSEToJSON，支持SSE转JSON及空output重建
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

上游API近期更新后，response.completed终态SSE事件的output字段可能为空，
实际内容仅通过response.output_text.delta等增量事件下发。流式路径不受影响，
但chat_completions非流式路径和responses OAuth非流式路径只依赖终态事件的
output，导致返回空响应。

新增BufferedResponseAccumulator累积器，在SSE扫描过程中收集delta事件内容
（文本、function_call、reasoning），当终态output为空时补充重建。

同时修复handleChatBufferedStreamingResponse遗漏response.done事件类型的问题。

When a channel has no model mapping for the requested model, ChannelMappedModel
equals OriginalModel (the user's arbitrary input). Combined with the default
BillingModelSource="channel_mapped", this incorrectly overrides the BillingModel
set by the OpenAI format conversion layer (e.g., gpt-5.4 from DefaultMappedModel)
back to the unmapped original model (e.g., glm) which has no pricing — resulting
in zero-cost billing.

Add guard condition so the channel_mapped override only fires when the channel
actually changed the model (ChannelMappedModel != OriginalModel).

Eliminates unnecessary indirection layer. The wrapper function only
called normalizeCodexModel with a special case for "gpt 5.3 codex spark"
(space-separated variant) that is no longer needed.

All call sites now use normalizeCodexModel directly.

- Change channel cache TTL from 60s to 10min (reduce unnecessary DB queries)
- Actively rebuild cache after CRUD instead of lazy invalidation
- Add slog.Warn logging for channel pricing restriction blocks (4 places)

P0-1: Credits degraded response retry + fail-open
- Add isAntigravityDegradedResponse() to detect transient API failures
- Retry up to 3 times with exponential backoff (500ms/1s/2s)
- Invalidate singleflight cache between retries
- Fail-open after exhausting retries instead of 5h circuit break

P1-1: Fix channel restriction pre-check timing conflict
- Swap checkClaudeCodeRestriction before checkChannelPricingRestriction
- Ensures channel restriction is checked against final fallback groupID

P1-2: Add interval pricing validation (frontend + backend)
- Backend: ValidateIntervals() with boundary, price, overlap checks
- Frontend: validateIntervals() with Chinese error messages
- Rules: MinTokens>=0, MaxTokens>MinTokens, prices>=0, no overlap

P2: Fix cross-platform same-model pricing/mapping override
- Store cache keys using original platform instead of group platform
- Lookup across matching platforms (antigravity→anthropic→gemini)
- Prevents anthropic/gemini same-name models from overwriting each other

- Fix 7 stale comments still mentioning "限制检查" in handlers/services
- Make billingModelForRestriction explicitly list channel_mapped case
- Add slog.Warn for error swallowing in ResolveChannelMapping and
  needsUpstreamChannelRestrictionCheck
- Document sticky session upstream check exemption

- PricingSourceChannel/LiteLLM/Fallback for resolver source
- MediaTypeImage/Video/Prompt for result.MediaType
- Reuse BillingModeToken/BillingModeImage for billing mode
- Reuse BillingModelSourceChannelMapped/PlatformAnthropic in handler

- clearCreditsExhausted: sync Redis scheduler cache after DB update
- Image billing mode UI: write to per_request_price instead of image_output_price
- OpenAI RecordUsage: use BillingModelSourceRequested constant, add s.cfg nil guard
- Fix i18n key path: admin.channels.perRequestPriceRequired → admin.channels.form.perRequestPriceRequired

- Fix errcheck: defer rows.Close() with nolint
- Fix errcheck: type assertion with ok check in channel cache
- Fix staticcheck ST1005: lowercase error string
- Fix staticcheck SA5011: nil check cost before use in openai gateway
- Fix gofmt: format chatcompletions_to_responses.go

- Parse candidatesTokensDetails from Gemini API to separate image/text output tokens
- Add image_output_tokens and image_output_cost to usage_log (migration 089)
- Support per-image-token pricing via output_cost_per_image_token from model pricing data
- Channel pricing ImageOutputPrice override works in token billing mode
- Auto-fill image_output_price in channel pricing form from model defaults
- Add "channel_mapped" billing model source as new default (migration 088)
- Bills by model name after channel mapping, before account mapping
- Fix channel cache error TTL sign error (115s → 5s)
- Fix Update channel only invalidating new groups, not removed groups
- Fix frontend model_mapping clearing sending undefined instead of {}
- Credits balance precheck via shared AccountUsageService cache before injection
- Skip credits injection for accounts with insufficient balance
- Don't mark credits exhausted for "exhausted your capacity on this model" 429s