29 Commits
Author SHA1 Message Date
Wesley Liddick 53c21fed25 Merge pull request #8006 from feeeei/feat/gemini-explicit-cache
feat(gemini): 支持显式上下文缓存,并完善 Vertex 与第三方 API Key 账号
2026-10-13 14:51:11 +08:00
feeeei 4426593e9d fix(gemini): 3.6 Flash 兜底价改为官方优惠价
- 内置兜底价与本地价格表快照的 gemini-3.6-flash 改为 $0.75 输入 / $3.75 输出 /
  $0.075 缓存读取(Priority 档 $1.35 / $6.75 / $0.135),有效期至 2026-12-31,
  2027-01-01 起恢复 $1.50 / $7.50 / $0.15,与 3.7 / 3.8 Flash 及远程价格目录一致
2026-10-11 11:22:48 +08:00
xcrong d56f5e7879 feat(gateway): adapt Claude Haiku 5.5
Closes #7919. Wire claude-haiku-5-5 (released 2026-10-07) across model
registry, effort catalog, pricing, billing, validation and Codex
descriptors, following the opus-5-5/sonnet-5-5 template and the official
migration guide + overview specs.

- registry: DefaultModels entry (fixed ID, no date suffix per guide)
- effort: full low/medium/high/xhigh/max family + IsHaiku55 +
  claude-haiku-5.5 dotted normalization (official default: medium)
- pricing catalog: 1M/128k limits, base (<=100k) prices and
  *_above_100k_tokens absolute prices; the existing ladder derivation
  yields threshold=100000 with uniform 5x multipliers, matching the
  official two-tier table exactly (cache tiers follow input x5)
- billing/pricing fallbacks carry the same tier so a missing catalog
  entry can never silently bill >100k prompts at base rate
- validation: adaptive-only thinking (enabled always 400; disabled 400
  at xhigh/max), sonnet-style sampling locks, temp+top_p combo rejected,
  forced tool_choice explicitly allowed (differs from opus/sonnet)
- oauth mimicry: skip temperature:1 top-up when top_p is present on
  sampling-locked models (sonnet-5-5 included), otherwise the gateway
  manufactures the temp+top_p 400 itself
- toolset beta filter + Codex 1M context cover haiku-5-5
- Bedrock/Antigravity mappings intentionally left out (no 5.5 entries
  exist there at all, same as opus-5-5); Vertex passes the fixed ID
  through untouched
2026-10-09 10:07:36 +08:00
lyy0709 9688571a83 feat(models): support GPT-6.1 Sol 2026-09-29 11:49:26 -07:00
haruka 8490a81867 feat: support Claude Sonnet 5.5 2026-09-29 04:55:07 +08:00
lyy0709 c4c2e66070 feat(models): support GPT-6 Sol, Luna and Claude Opus 5.5 2026-09-23 11:27:49 +08:00
nagi330 935db68517 feat(grok):add grok 4.7 support 2026-09-22 10:30:01 +08:00
alfadb ab9bd9e877 fix(billing): 适配 DeepSeek V4.1-Flash 新价与 pro→Flash 切换
- flash 低谷价更新为 $0.15/$0.60/$0.003 per MTok(2026-09-10 官方降价)
- deepseek-v4-pro 自 2026-09-14 04:00 UTC 起按 Flash 价计费(上游路由变更)
- 计费时点显式驱动 pro→Flash 切换,定价展示与计费两条路径同源
- deepseek-flash 保留 reasoning_effort=max;补 Codex 模型清单与前端白名单
- 价表 JSON 新增 deepseek-flash 条目并同步 flash 系价格
2026-09-10 22:10:29 +08:00
hansnow 7ccc8a6f50 fix(openai): 支持 Image 2.5 并修复 OAuth 生图主控模型 2026-09-09 11:04:59 +08:00
feeeei e2cfaa46e7 fix(pricing): 目录 cache 侧字段契约哨兵与 Gemini pro 缓存写入价修正
阶梯计价数据驱动后,目录条目的字段缺失或版本拼接会直接变成计费偏差,
解析层补两道数据契约哨兵,并修正出厂快照中 Gemini pro 系的缓存写入价:

- orphanCacheTierFields / warnOrphanCacheTierFields:条目带 cache 侧
  above 档(含 _priority/_flex 变体与 above_1hr 形态)却没有基础价时打
  WARN——cache 侧 above 档不参与计费取值,按"基础价 × 输入倍率"计,基础价
  缺失即该分项按 0 计;变体缺自身基础价时沿 变体→1h→标准 回落链任一存在
  即不算孤儿,与计费回落一致
- isLopsidedLongContextLadder / warnLopsidedLongContextLadders:above 档
  折算出只有一侧带附加费的阶梯时打 WARN(基础价与 above 档来自不同价格
  版本的形态),显式 long_context_* 字段不告警
- deriveLongContextFromAboveTierFields 注释改为陈述契约:cache above 档
  须恰为基础价 × 输入倍率
- 出厂快照 6 个 Gemini pro 条目补 cache_creation_input_token_cost(= 标准
  输入价,Google 对缓存写入不另收费)、above_200k 改为输入 above 价、带
  priority 输入价的 4 条补 priority 孪生,与 model-price-repo 数据修正同值

测试:
- 解析层:孤儿字段 WARN(含 priority/1h 孤儿正例、1h 回落 5m 反例)、单侧
  阶梯 WARN、出厂快照契约(全条目无孤儿字段、无单侧阶梯、Gemini pro 缓存
  写入价 = 输入价)
- 用量契约:extractGeminiUsage 与 Antigravity 非流式/流式转换均不产生
  cache_creation token(Gemini usageMetadata 无该类别)
- 计费:gemini-2.5-pro 阶梯对 cache_read / cache_creation 分项生效,阈值
  计入缓存写入 token;阶梯表场景与夹具同步为现行目录值
2026-09-01 01:26:55 +08:00
alfadb b5827cfd54 fix(pricing): align DeepSeek billing with official peak/off-peak rates
同步 DeepSeek 官方峰谷价格与模型定价。
2026-08-29 17:30:23 +08:00
alfadb f06bf181d2 feat(openai): support Fast mode service_tier across responses/chat/WS paths
- Accept fast|priority (canonical priority), flex|auto|default|scale on
  /v1/responses and /v1/chat/completions; reject unknown/empty/non-string
  with HTTP 400; omitted and null stay compatible.
- Propagate service_tier through JSON/SSE, Responses<->Chat conversions,
  fallback paths and HTTP->upstream WebSocket bridge.
- Billing prefers the upstream terminal tier; the outbound (policy-
  transformed) tier is used only when upstream omits the field.
  Explicit upstream default bills Standard even when Fast was requested.
- Pricing: Fast premium 2x Standard for gpt-5.6-sol/terra/luna and
  gpt-5.4; 2.5x for gpt-5.5; channel FastMultiplier stays authoritative.
- Live verification (official Codex 0.149.0 + gateway, HTTP & WS):
  upstream ChatGPT backend may return terminal default even when the
  account catalog advertises priority; billing follows the actual tier.
2026-08-24 11:52:48 +08:00
Zven 698547418f fix(pricing): keep Auto-review rates evidence-based 2026-07-31 21:20:32 +08:00
Zven f54e9827a0 fix(pricing): update Codex Auto-review rates 2026-07-31 21:16:06 +08:00
Zven b2d895fb8d fix(pricing): update GPT-5.6 Luna and Terra rates 2026-07-31 09:42:46 +08:00
haruka 6c7625800a fix(billing): price Antigravity Gemini 3.6 Flash 2026-07-26 01:56:10 +08:00
shaw 6c9b84cc7a feat: 适配 Anthropic 新模型 claude-opus-5
模型登记:/v1/models 清单、Bedrock 默认映射(us.anthropic.claude-opus-5-v1)、
定价条目($5/$25 per MTok、1M 上下文、128K 输出)、前端模型清单与
Anthropic/Bedrock 预设映射、限流 scope 简称。

同时修复两个会静默出错的问题:

- 定价家族兜底 3 倍超收:定价数据缺 claude-opus-5 时,matchByModelFamily
  的 Phase 2 关键字兜底会落到 opus-4 系列、getFallbackPricing 会落到
  claude-3-opus,两条路都按 $15/$75 计费(官方 $5/$25),输入输出双双
  3 倍超收且无任何报错。两处补 opus-5 家族并回退到同价的 4.8;判断用
  opus-5/opus5 子串而非裸 "5",避免误伤 claude-opus-4-5。顺带补齐兜底表
  缺失的 claude-opus-4.8(此前同样会掉到 claude-3-opus)。

- Bedrock 版本闸门降级:claudeVersionRe 强制要求 major-minor 两段版本号,
  只有主版本号的 claude-opus-5 / claude-sonnet-5 完全不匹配,被当成旧模型:
  isBedrockOpus47OrNewer 假导致 thinking.enabled 不转 adaptive(Opus 5 上游
  已移除 budget_tokens,透传直接 400)、isBedrockClaude45OrNewer 假导致
  cache_control.ttl 被剥离、bedrockModelSupportsToolSearch 假导致 tool search
  被过滤。改为 minor 可选(缺省 minor=0),claude-sonnet-5 的同一问题一并修复。

Vertex 无需改动:normalizeVertexAnthropicModelID 只处理 -YYYYMMDD→@YYYYMMDD,
无日期后缀的裸 ID 原样透传即正确。context-1m-2025-08-07 白名单不动:Opus 系
上游不接受该 beta,且 Opus 5 的 1M 上下文是默认能力。

Antigravity 暂不接入:无上游支持证据,mapAntigravityModel 对未映射模型返回
空字符串即"该账号不支持",fails closed 安全。

回归测试 internal/service/claude_opus5_test.go 覆盖定价两层兜底、Bedrock
三个闸门、thinking 转换与模型清单;逐个回退上述修复已确认测试会红。
2026-07-25 11:22:42 +08:00
superman2003 de28eba3c8 fix(openai): harden GPT-5.6 billing and usage 2026-07-10 15:13:11 +08:00
benjamin 383f61d0e9 fix(openai): align GPT-5.6 billing with official pricing 2026-07-10 09:42:31 +08:00
Turtle_Li 1b07fe821a merge: sync batch image branch with origin main 2026-07-07 03:27:11 +08:00
shaw 6cea1c35bb feat: 适配 OpenAI 新模型 gpt-5.6-sol/terra/luna 2026-07-06 17:34:22 +08:00
Turtle_Li 8fab636998 feat: complete batch image workflow 2026-07-06 12:22:04 +08:00
shaw 68901cbfff chore(pricing): update model pricing metadata 2026-05-29 16:29:29 +08:00
gaoren002 32a79be962 fix(openai): add codex auto review model pricing 2026-05-12 09:26:53 +00:00
Remx 42d73118fd feat(openai): 增加 gpt-5.4-mini/nano 模型支持与定价配置
- 接入 gpt-5.4-mini/nano 模型识别与规范化,补充默认模型列表
- 增加 gpt-5.4-mini/nano 输入/缓存命中/输出价格与计费兜底逻辑
- 同步前端模型白名单与 OpenCode 配置
- 补充 service tier(priority/flex) 计费回归测试
2026-03-19 19:03:13 +08:00
yangjianbo 1a0d4ed668 feat(openai): 增加 gpt-5.4 模型支持与定价配置
- 接入 gpt-5.4 模型识别与规范化,补充默认模型列表
- 增加 gpt-5.4 输入/缓存命中/输出价格与计费兜底逻辑
- 同步前端模型白名单与 OpenCode 上下文窗口(1050000/128000)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
(cherry picked from commit 924476dcac6181cd0f3ee731ec7b73672ff03793)
2026-03-06 10:16:23 +08:00
shaw 15f3ffb165 chore: 调整模型定价文件仓库 2026-02-25 13:50:21 +08:00
yangjianbo 9e1535e203 feat(模型): 添加 gpt-5.3 Codex 映射与价格配置 2026-02-06 07:14:46 +08:00
shaw 642842c29e First commit 2025-12-18 13:50:39 +08:00