完善 GPT-5.6 三模型元数据与 Fast 兼容 / Complete GPT-5.6 metadata and Fast compatibility#1447
Open
Yuimi-chaya wants to merge 5 commits into
Open
完善 GPT-5.6 三模型元数据与 Fast 兼容 / Complete GPT-5.6 metadata and Fast compatibility#1447Yuimi-chaya wants to merge 5 commits into
Yuimi-chaya wants to merge 5 commits into
Conversation
为什么 / Why: 当前 Codex App 在不同启动路径下对 GPT-5.6 Sol/Terra/Luna 的识别不一致:直启时可能显示为自定义模型,从 Codex++ 启动时虽然能看到三款模型,却会丢失部分推理档位和 Fast capability。 The current Codex App exposes inconsistent GPT-5.6 metadata across launch paths: direct launches may show a custom model, while Codex++ launches can list Sol/Terra/Luna but lose reasoning levels and Fast capability. 改动 / Changes: - Add one bundled structured metadata source for GPT-5.6 Sol, Terra and Luna. - Generate runtime-compatible model catalog entries, including reasoning levels, context window and service-tier capability. - Expose modelMetadata through the Codex++ model catalog bridge. - Generate a managed catalog for known GPT-5.6 models even when no [window] suffix is supplied. - Preserve an explicitly configured external model_catalog_json instead of overwriting it with a generated catalog. 边界 / Scope: This commit only describes model capability. It does not add the Max request override or provider-switch App-state/plugin fixes. 本提交只描述模型能力,不包含 Max 请求覆盖,也不包含供应商切换后的 App 状态或插件修复。
a20a555 to
93ab3f9
Compare
Yuimi-chaya
added a commit
to Yuimi-chaya/CodexPlusPlus
that referenced
this pull request
Jul 12, 2026
# Conflicts: # assets/inject/renderer-inject.js
|
大佬,Fast模式支持最新模型修复了吗? |
|
求合并, 5.6的fast现在用不上 |
Contributor
Author
|
@BigPizzaV3 打扰提醒一下,这个 PR 当前 Windows、macOS x64、macOS arm64 三平台 CI 已全部通过,分支状态为 CLEAN,但暂时还没有收到维护者 review。 该 PR 补充 GPT-5.6 Sol / Luna / Terra 的完整模型元数据,并修复这些模型在 Codex++ 注入后的 Fast 支持判断。目前评论区也已有用户反馈 GPT-5.6 的 Fast 无法正常使用。 这部分改动是独立的模型元数据与兼容性修复,不依赖其他大型 PR。想请您抽空重点看一下:
如果当前上游模型定义已有新的调整,或希望换一种实现方式,也请直接指出,我会按最新主仓结构继续适配。 |
dd3f7ab to
e937451
Compare
|
建议尽快review,fast真的很重要!!Fast 应该也是大多数用户核心需求之一? |
2 tasks
Contributor
|
求合并 求合并 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Important
2026-07-13 官方上下文回滚提醒
官方于 2026-07-13 宣布:GPT-5.6 Sol 的上下文上限已从 372K 临时回滚至 272K,并计划在后续数日重新开放 372K。为避免 Codex++ 在服务端实际上限仍为 272K 时错误声明 372K、延迟压缩并造成上下文超限,本 PR 已同步撤回 372K 元数据,当前三款 GPT-5.6 兼容目录均保守使用 272K。模型识别、推理档位和 Fast 兼容修复不受影响;待官方确认恢复后再单独跟进。
Official context rollback notice (2026-07-13)
OpenAI announced on 2026-07-13 that GPT-5.6 Sol's context limit was temporarily rolled back from 372K to 272K, with 372K planned to return in the following days. To avoid advertising a window larger than the active server limit, delaying compaction, and causing context-limit failures, this PR now withdraws its 372K metadata and conservatively reports 272K for all three GPT-5.6 compatibility entries. Model recognition, reasoning-effort, and Fast compatibility fixes remain unchanged; 372K can be revisited after the official rollout is confirmed.
中文说明
摘要
本 PR 独立完善 GPT-5.6 Sol / Terra / Luna 在 Codex++ 启动链中的模型元数据、推理档位、当前 272K 上下文与 Fast 能力兼容。
本 PR 不再提供自定义 Max 按钮或请求覆盖。Codex App 已通过“设置 → 配置 → 模型功能 → 可用推理强度”开放原生
max;在 API Key / 第三方 Responses 场景中,已真人验证选择“最高”后,新会话第一条请求会直接以reasoning.effort=max到达 NewAPI。为什么仍需要这个 PR
官方原生 Max 解决了推理请求本身,但没有解决第三方供应商经 Codex++ 启动时的模型目录兼容问题:
因此本 PR 只补齐 Codex++ 仍需负责的“模型目录与启动链兼容”,不与官方已经可用的 Max 功能竞争。
实现内容
ultra,Luna 支持至max。priorityservice tier 能力。setting-storage-*与vscode-api-*中的 dispatcher,并支持 singleton 和 class 两种导出形态。model_catalog_json,不会因为检测到 GPT-5.6 就覆盖用户文件。gpt-5.6等未知模型名,不擅自猜测为 Sol / Terra / Luna。原生推理档位说明
当前中文界面存在两个“极高”,内部值并不相同:
高→high极高→xhigh最高→max极高→ultraFast 与上述推理档位相互独立,其请求值为
service_tier=priority。已移除的实验性 Max 补丁
早期版本曾为了绕过 App 隐藏的 Max gate,加入按会话按钮、renderer 状态、helper route、运行时 localhost provider 包装和最终 Responses 改写。官方原生链路经实测可正确发送
max后,这些代码已全部从本 PR 删除,避免双重入口、状态冲突和不必要的本地代理复杂度。验证
node --check assets/inject/renderer-inject.jsnpm run checkcargo fmt --all -- --checkOpenAI.ChatGPT-Desktop_*包;watcher 17/17、core 全套通过。cargo test -q -p codex-plus-core --test cdp_bridge -j 2:69 passedcargo test -q -p codex-plus-core --test model_catalog --test model_suffix --test relay_config -j 2:7 + 14 + 99 passedmax/ultra描述符、新旧 dispatcher 导出,以及自定义 Max 控件和设置字段不存在。max。English
Summary
This PR independently completes model metadata, reasoning-level, current 272K context-window, and Fast capability compatibility for GPT-5.6 Sol, Terra, and Luna in the Codex++ launch path.
It no longer provides a custom Max control or request override. Codex App now exposes native
maxthrough Settings → Configuration → Model features → Available reasoning strengths. Human validation with an API-key/third-party Responses provider confirmed that selecting native Max sendsreasoning.effort=maxon the first request of a fresh thread.Why this PR is still needed
Native Max fixes the reasoning request itself, but it does not solve model-catalog compatibility when third-party providers are launched through Codex++:
This PR therefore keeps only the model-catalog and launch-path compatibility that Codex++ still owns, without competing with the now-working native Max feature.
Implementation
ultra; Luna supports throughmax.priorityservice-tier capability for all three models.setting-storage-*andvscode-api-*, supporting singleton and class export shapes.model_catalog_jsonfiles instead of overwriting user-owned catalogs merely because they contain GPT-5.6.gpt-5.6instead of guessing a Sol/Terra/Luna mapping.Native reasoning labels
The current Chinese locale uses the same visible label for two different effort values:
High→highExtra High→xhighMax→maxExtra Highwith the usage warning →ultraFast is independent from reasoning effort and uses
service_tier=priority.Retired experimental Max patch
An earlier revision added a per-thread control, renderer state, helper route, runtime localhost provider wrapper, and final Responses rewrite to bypass the App's hidden Max gate. Once the native path was verified to send
maxcorrectly, all of that code was removed from this PR to avoid duplicate controls, conflicting state, and unnecessary local-proxy complexity.Validation
node --check assets/inject/renderer-inject.jsnpm run checkcargo fmt --all -- --checkOpenAI.ChatGPT-Desktop_*packages; watcher passed 17/17 and the full core suite passed.cargo test -q -p codex-plus-core --test cdp_bridge -j 2: 69 passedcargo test -q -p codex-plus-core --test model_catalog --test model_suffix --test relay_config -j 2: 7 + 14 + 99 passedmax/ultradescriptors, old and new dispatcher export shapes, and the absence of the custom Max control and setting.maxin NewAPI on the first API-key/Responses request.