IanShaw027
b7112d596f
fix(keys): grok-4.5 上下文窗口按 500k 对齐并修正账号测试 i18n mock
...
- UseKeyModal 中 grok-4.5 的 context_window / model_context_window /
OpenCode 模型目录统一改为 500000，与 xAI 实际上下文一致
- UseKeyModal.spec 的 OpenCode 目录断言同步为 500000
- AccountTestModal.spec 补齐 imagePreviewAlt 的 i18n mock，
跟上组件把 alt 文案迁到 i18n 之后的行为
2026-08-08 10:40:40 +08:00
IanShaw027
b717ed9d0d
feat(keys): complete Grok Build sample with endpoints/auth/session/features
...
Expand Use Key Grok CLI config.toml to include production-oriented sections
from working gateway setups: full [endpoints], preferred_method=api_key,
image_description, auto_compact threshold, and Imagine image/video feature
overrides with guided comments.
2026-08-08 10:33:45 +08:00
IanShaw027
f3bac4619e
feat(keys): expand Grok client samples and tune free soft-gate default
...
Ship Use Key templates that match Grok Build / Codex best practice: env
vars + multi-model config.toml with api_backend=responses, env_key over
hardcoded secrets, and clearer shell/path guidance for Claude/Codex/OpenCode.
Also set free_quota_token_limit default to 500k (24h soft-gate), clean up
personal-dev-only comments, and keep billing test fixtures aligned.
2026-08-08 10:26:16 +08:00
Wesley Liddick and GitHub
4d91f39474
Merge pull request #4431 from linyqh/codex/fix-codex-image-handoff
...
fix(openai): 修复 Codex 生图网关侧交接问题
2026-07-16 19:32:33 +08:00
superman2003
174ea22eeb
fix(grok): enable Codex Responses WebSocket v2
2026-07-16 18:30:59 +08:00
viccy and OmX
9d1064badd
澄清 Codex 图片桥接与本地执行器边界
...
配置界面现在区分非 Responses Lite 的 hosted 桥接与客户端本地 image_gen，并准确描述账号 strip 策略。API Key Mode 同时提示完全重启 Codex 后新建 task，以重建客户端工具注册表。
Constraint: 兼容模式继续保持默认，Responses Lite 的本地工具由客户端与账号策略决定
Rejected: 写入 features.image_generation | 当前 Codex 已默认启用且仓库既有配置刻意省略该项
Confidence: high
Scope-risk: narrow
Reversibility: clean
Directive: 图片桥接文案必须区分 hosted 注入、客户端声明和 image-only 路由
Tested: 前端 lint、typecheck、关键套件 93 项、定向套件 43 项
Not-tested: Codex Desktop 真实工具注册表重建
Co-authored-by: OmX <omx@oh-my-codex.dev >
2026-07-16 17:11:17 +08:00
superman2003
e8cc1fe26b
feat(frontend): add Grok key setup templates
2026-07-16 00:16:21 +08:00
feeeei
1acbb12c65
统一gork使用模板中的名称风格
2026-07-15 10:51:08 +08:00
haruka
ad3522e34b
fix(frontend): preserve legacy Codex config mode
2026-07-14 22:41:38 +08:00
haruka
f09d63f54e
fix(frontend): address Codex config review feedback
2026-07-14 18:31:06 +08:00
haruka
e2028a814e
fix(frontend): update Codex API key snippets
2026-07-14 16:41:44 +08:00
Heatherm Huang
ad18ee7c4f
fix(grok): use responses adapter for OpenCode
2026-07-13 10:09:53 +08:00
Heatherm Huang
038b25c0b1
fix(grok): resolve recent integration issues
2026-07-13 10:09:53 +08:00
superman2003
de28eba3c8
fix(openai): harden GPT-5.6 billing and usage
2026-07-10 15:13:11 +08:00
shaw
d662c97302
feat: claude-fable-5
2026-06-10 08:58:06 +08:00
shaw
a391635191
更新 OpenAI 使用密钥配置
2026-05-27 17:29:20 +08:00
erio
bbc4aed3d9
fix(openai): 移除已下线 Codex 模型并修复归一化兜底副作用
...
- backend: 删除 gpt-5 / 5.1 / 5.1-codex / 5.1-codex-max / 5.1-codex-mini / 5.2-codex / 5.4-nano 的内置映射与 DefaultModels 条目
- backend: normalizeCodexModel 默认兜底由 gpt-5.1 改为 gpt-5.4，gpt-5.3-codex-spark 独立保留映射
- backend: 修复 isOpenAIGPT54Model 与 shouldAutoInjectPromptCacheKeyForCompat 对 claude / gpt-4o 的误判（之前依赖 gpt-5.1 作为非 GPT 族的隐式 sentinel，改后需要显式前缀守卫）
- backend: 清理 billing_service 中已不可达的 fallback 价格与 switch 分支
- frontend: 从白名单、OpenCode 配置、预设映射中移除已下线模型
- 同步更新所有相关单测
Refs: #1758 , parallels upstream #1759 but adds downstream guard fixes
2026-04-20 22:01:41 +08:00
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
IanShaw027