GitLab

- 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

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent

)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

当 API Key 无分组时，调度仅从未分组账号池中选取。
修复 isAccountInGroup 在 groupID==nil 时的逻辑，
同时补全 scheduler_snapshot_service 和 gemini_compat_service
中的 SimpleMode 保护，确保分组隔离在所有调度路径生效。

新增 ListSchedulableUngroupedByPlatform/s 方法，
使用 Ent 的 Not(HasAccountGroups()) 谓词实现未分组账号隔离。
新增 17 个单元和端到端隔离测试，覆盖所有分支和边界条件。

- 将高密度服务与处理器日志迁移到新日志系统（LegacyPrintf/结构化日志）
- 增加 stdlog bridge 与兼容测试，保留旧日志捕获能力
- 将 OpenAI 断流告警改为结构化 Warn 并改造对应测试为 sink 捕获
- 补齐后端相关文件 logger 引用并通过全量 go test

Gemini 2.5 Pro/Flash thinking models return thoughtsTokenCount separately
from candidatesTokenCount in usageMetadata, but this field was not parsed
or included in billing calculations, causing thinking tokens to be
unbilled.

- Add ThoughtsTokenCount field to GeminiUsageMetadata struct
- Include thoughtsTokenCount in OutputTokens across all 3 Gemini usage
  parsing paths (non-streaming, streaming, compat layer)
- Add tests covering thinking token scenarios

Closes #554

将 API 网关热路径中的 json.Unmarshal+json.Marshal 替换为 gjson 零拷贝查询和 sjson 精准写入：
- unwrapV1InternalResponse 性能提升 22x（4009ns→182ns），内存分配减少 28.5x
- unwrapGeminiResponse、extractGeminiUsage、estimateGeminiCountTokens、ParseGeminiRateLimitResetTime 改为接收 []byte 使用 gjson 提取
- ParseGatewayRequest 的 model/stream/metadata/thinking/max_tokens 改用 gjson 类型安全提取
- Handler 层（sora/openai）改用 gjson 提取字段、sjson 注入/修改字段，移除 map[string]any 中间变量
- Sora Client 响应解析改用 gjson ForEach 遍历，减少内存分配
- 新增约 100 个单元测试用例，所有改动函数覆盖率 >85%
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

For retryable transient errors (Google 400 "invalid project resource name"
and empty stream responses), retry on the same account up to 2 times
(with 500ms delay) before switching to another account.

- Add RetryableOnSameAccount field to UpstreamFailoverError
- Add same-account retry loop in both Gemini and Claude/OpenAI handler paths
- Move temp-unschedule from service layer to handler layer (only after
  all same-account retries exhausted)
- Reduce temp-unschedule cooldown from 30 minutes to 1 minute

Google 后端间歇性返回 400 "Invalid project resource name" 错误，
此前该错误直接透传给客户端且不触发账号切换，导致请求失败。

- 在 Antigravity 和 Gemini 两个平台的所有转发路径中，
  精确匹配该错误消息后触发 failover 自动换号重试
- 命中后将账号临时封禁 1 小时，避免反复调度到同一故障账号
- 提取共享函数 isGoogleProjectConfigError / tempUnscheduleGoogleConfigError
  消除跨 Service 的代码重复

Add ShouldHandleErrorCode guard at the entry of handleGeminiUpstreamError
and AntigravityGatewayService.handleUpstreamError so that accounts with
custom error codes (e.g. [599]) are not rate-limited when the upstream
returns a non-matching status (e.g. 429).

When custom error codes are enabled and the upstream error code is NOT
in the configured list, return HTTP 500 to the client instead of
transparently forwarding the original status code.

Also adds integration test TestCustomErrorCode599 verifying that 429,
500, 503, 401, 403 all return 500 without triggering SetRateLimited
or SetError.

Upstream accounts now use the standard APIKey type instead of a dedicated
upstream type. GetBaseURL() and new GetGeminiBaseURL() automatically append
/antigravity for Antigravity platform APIKey accounts, eliminating the need
for separate upstream forwarding methods.

- Remove ForwardUpstream, ForwardUpstreamGemini, testUpstreamConnection
- Remove upstream branch guards in Forward/ForwardGemini/TestConnection
- Add migration 052 to convert existing upstream accounts to apikey
- Update frontend CreateAccountModal to create apikey type
- Add unit tests for GetBaseURL and GetGeminiBaseURL

Key changes:
- Upgrade model mapping: Opus 4.5 → Opus 4.6-thinking with precise matching
- Unified rate limiting: scope-level → model-level with Redis snapshot sync
- Load-balanced scheduling by call count with smart retry mechanism
- Force cache billing support
- Model identity injection in prompts with leak prevention
- Thinking mode auto-handling (max_tokens/budget_tokens fix)
- Frontend: whitelist mode toggle, model mapping validation, status indicators
- Gemini session fallback with Redis Trie O(L) matching
- Ops: enhanced concurrency monitoring, account availability, retry logic
- Migration scripts: 049-051 for model mapping unification

支持管理员配置上游错误如何返回给客户端：
- 新增 ErrorPassthroughRule 数据模型和 Ent Schema
- 实现规则的 CRUD API（/admin/error-passthrough-rules）
- 支持按错误码、关键词匹配，支持 any/all 匹配模式
- 支持按平台过滤（anthropic/openai/gemini/antigravity）
- 支持透传或自定义响应状态码和错误消息
- 实现两级缓存（Redis + 本地内存）和多实例同步
- 集成到 gateway_handler 的错误处理流程
- 新增前端管理界面组件
- 新增单元测试覆盖核心匹配逻辑

优化：
- 移除 refreshLocalCache 中的冗余排序（数据库已排序）
- 后端 Validate() 增加匹配条件非空校验

extractGeminiUsage 函数未提取 cachedContentTokenCount，
导致计费时缓存读取 token 始终为 0。

修复：
- 提取 usageMetadata.cachedContentTokenCount
- 设置 CacheReadInputTokens 字段
- InputTokens 减去缓存 token（与 response_transformer 逻辑一致）

Gemini API 不接受 contents 数组中 parts 为空的消息，会返回 400 INVALID_ARGUMENT 错误。
添加 filterEmptyPartsFromGeminiRequest 函数在转发前过滤这类消息。

影响范围：ForwardGemini (antigravity) 和 ForwardNative (gemini)

对齐 Antigravity 平台的图片计费逻辑：
- 添加 extractImageSize() 方法提取图片尺寸
- Forward() 和 ForwardNative() 返回 ImageCount/ImageSize
- 支持分组自定义图片价格和倍率

对齐 Antigravity 平台的图片计费逻辑：
- 添加 extractImageSize() 方法提取图片尺寸
- Forward() 和 ForwardNative() 返回 ImageCount/ImageSize
- 支持分组自定义图片价格和倍率

Previously, collectGeminiSSE() only returned the last chunk received
from the upstream streaming response when converting to non-streaming.
This caused incomplete responses where only the final text fragment
was returned to clients.

For example, a request asking to "count from 1 to 10" would only
return "\n" (the last chunk) instead of "1\n2\n3\n...\n10\n".

This was especially problematic for JSON structured output where
the opening brace "{" from the first chunk was lost, resulting
in invalid JSON like: colors": ["red", "blue"]}

The fix:
- Collect all text parts from each SSE chunk into a slice
- Merge all collected text parts into the final response
- Reuse the same pattern as handleGeminiStreamToNonStreaming
  in antigravity_gateway_service.go

Fixes: non-streaming responses returning incomplete text
Fixes: structured output (JSON schema) returning invalid JSON

- Update/BulkUpdate 按不可调度字段触发缓存刷新
- GatewayCache 支持多前缀会话键清理
- 模型路由与混合调度优化粘性会话处理
- 补充调度与缓存相关测试覆盖

- Update/BulkUpdate 按不可调度字段触发缓存刷新
- GatewayCache 支持多前缀会话键清理
- 模型路由与混合调度优化粘性会话处理
- 补充调度与缓存相关测试覆盖

- 调度热路径优先读 Redis 快照，保留分组排序语义
- outbox 回放 + 全量重建纠偏，失败重试不推进水位
- 自动 Atlas 基线对齐并同步调度配置示例

**新增功能**:
- 新建ops_upstream_error_events表存储上游服务错误详情
- 支持记录上游429/529/5xx错误的详细上下文信息
- 提供按时间范围查询上游错误事件的API

**后端改动**:
1. 模型层（ops_models.go, ops_port.go）:
   - 新增UpstreamErrorEvent结构体
   - 扩展Repository接口支持上游错误事件CRUD

2. 仓储层（ops_repo.go）:
   - 实现InsertUpstreamErrorEvent写入上游错误
   - 实现GetUpstreamErrorEvents按时间范围查询

3. 服务层（ops_service.go, ops_upstream_context.go）:
   - ops_service: 新增GetUpstreamErrorEvents查询方法
   - ops_upstream_context: 封装上游错误上下文构建逻辑

4. Handler层（ops_error_logger.go）:
   - 新增GetUpstreamErrorsHandler处理上游错误查询请求

5. Gateway层集成:
   - antigravity_gateway_service.go: 429/529错误时记录上游事件
   - gateway_service.go: OpenAI 429/5xx错误时记录
   - gemini_messages_compat_service.go: Gemini 429/5xx错误时记录
   - openai_gateway_service.go: OpenAI 429/5xx错误时记录
   - ratelimit_service.go: 429限流错误时记录

**数据记录字段**:
- request_id: 关联ops_logs主记录
- platform/model: 上游服务标识
- status_code/error_message: 错误详情
- request_headers/response_body: 调试信息（可选）
- created_at: 错误发生时间

- 增加降级链路环检测并拦截配置

- 仅复用合法分组上下文并必要时回退查询

- 标注 GetByIDLite 轻量语义并补充测试

新增 GetByIDLite 并在网关与 Gemini 选择流程复用上下文 group，避免 COUNT 触发
更新 API key 中间件注入 group 上下文，减少重复查库
补充 gateway/gemini 中间件与仓库层回归测试

测试: make test

* fix: 添加 gemini-3-flash 前缀映射支持 gemini-3-flash-preview

* feat(antigravity): 增强请求参数和注入 Antigravity 身份 system prompt

* feat: antigravity 配额域限流

* chore: 调整 SSE 单行上限到 25MB

* chore: 提升 SSE 单行上限到 40MB