[Feature]: opt into Codex client compaction without disabling V2 routing

[cb8010d6]

Area

Multiple areas

What are you trying to accomplish?

Keep OpenCodex V2 subagent routing, including provider-selected plaintext delivery or encrypted task passthrough, while letting Codex perform client-side context compaction. New compacted history should remain replayable after ocx restore or the dashboard Codex OFF action.

What prevents this today?

On an ordinary loopback install, OpenCodex uses Design B and injects only a root openai_base_url. Codex therefore keeps the built-in openai provider identity and selects native remote compaction for every routed model.

For noncanonical providers, OpenCodex converts the compaction turn into a summarizer request and stores the result as type: "compaction" with encrypted_content: "ocx1:<base64>". OpenCodex can decode that envelope while it remains in the path, but native ChatGPT cannot verify it after routing is disabled. This is the forward-looking cause behind the recovery case in #3916.

The V2 task-delivery capability and compaction ownership are independent, but the current loopback injection makes them behave as one choice.

Verified on dev commit 900567af3f (package 2.48.0):

• src/codex/inject.ts selects the root openai_base_url Design B form for authenticated loopback routing.
• The same file already supports a dedicated [model_providers.opencodex] form for non-loopback and authless Desktop routing.
• src/responses/compaction.ts documents and emits the OpenCodeX-owned ocx1: envelope for routed remote compaction V2.
• Codex client compaction uses a bare context_compaction marker followed by ordinary summary history, so it does not require OpenCodeX to decode a provider-private blob.

What should OpenCodex do?

Offer an explicit, default-off Codex client-compaction compatibility mode. When enabled on loopback routing, OpenCodex should use its dedicated opencodex model-provider table with requires_openai_auth = true, rather than overriding the built-in openai provider. This lets Codex select client compaction while retaining the normal ChatGPT sign-in gate and all existing OpenCodex request routing.

The setting should not change provider-level V2 agent-task policy. allowEncryptedV2AgentTasks, plaintext delivery, and recovery/fallback behavior must remain independent.

Observable requirements:

• Default/unset behavior stays byte-compatible with Design B.
• The opt-in generates a noncanonical model_provider = "opencodex" route with requires_openai_auth = true.
• Enabling or disabling it converges the managed Codex configuration through the existing sync path.
• Existing ocx1: history is not silently rewritten; Codex restore leaves ocx1-compacted threads unreplayable on the native backend #3916/fix(codex): recover ocx1-compacted threads for native replay #3920 remain the explicit recovery path.
• The dashboard and CLI explain that this favors native replay portability and may use third-party provider quota for summary generation.

Example usage or interface

ocx system settings --client-compaction on
ocx sync

Equivalent configuration:

{
  "codexClientCompaction": true
}

Expected managed Codex shape:

model_provider = "opencodex"

[model_providers.opencodex]
name = "OpenCodex Proxy"
base_url = "http://127.0.0.1:10100/v1"
wire_api = "responses"
requires_openai_auth = true

Provider configuration remains separate:

{
  "providers": {
    "example": {
      "adapter": "openai-responses",
      "baseUrl": "https://example.invalid/v1",
      "allowEncryptedV2AgentTasks": true
    }
  }
}

Alternatives or workarounds

• Keep Design B and use routed remote compaction. This preserves the built-in provider identity but continues creating OpenCodeX-owned ocx1: state for noncanonical providers.
• Enable codexDesktopAuthless. It already selects the provider-table form, but it also disables the Desktop ChatGPT login gate and is therefore not equivalent.
• Manually maintain a custom model_provider. OpenCodeX intentionally preserves external provider ownership and then does not manage normal routing or catalog convergence.
• Repair each affected thread after the fact. This is necessary for existing history but does not prevent new incompatible compaction state.

Additional context

• Related recovery issue: Codex restore leaves ocx1-compacted threads unreplayable on the native backend #3916
• Existing recovery PR: fix(codex): recover ocx1-compacted threads for native replay #3920
• Earlier remote-compaction compatibility issue: Remote compaction v2 fatals on API-key-based openai-responses providers — passthrough assumes native compaction support #422
• Compaction-provider routing issue: No way to set compaction provider. #2901

This proposal is intentionally limited to selecting the existing Codex provider-table injection form. It does not redesign the Responses relay, V2 task transport, compaction model routing, or history recovery.

Checks

• I searched existing issues and documentation.
• This request describes a concrete OpenCodex workflow rather than merely naming a desired technology.
• I removed secrets and personal data.

[lidge-jun]

리뷰 · 우선순위 61 / 80

이 이슈는 OpenCodex V2 라우팅(플레인텍스트/암호화 task 전달)은 유지한 채, Codex가 클라이언트 쪽 context compaction을 쓰게 하는 opt-in을 요청합니다. 지금 dev HEAD c15662855(package 2.48.0)의 보통 loopback 설치는 Design B입니다. src/codex/inject.ts가 root openai_base_url만 심으면 Codex는 내장 openai provider identity를 유지하고, 모델마다 native remote compaction을 고릅니다. noncanonical provider로 넘어가면 src/responses/compaction.ts가 summarizer 결과를 type: "compaction" + encrypted_content: "ocx1:<base64>"로 저장합니다. 프록시가 붙어 있을 때는 디코드할 수 있지만, ocx restore나 대시보드 Codex OFF 뒤에는 native ChatGPT가 그 blob을 검증하지 못합니다. 이게 #3916 복구 케이스의 앞단 원인으로 이 이슈가 적는 그림이고, HEAD에서도 inject Design B / provider-table([model_providers.opencodex]) / context_compaction 마커 설명이 그대로 있습니다. 제안은 default-off codexClientCompaction(예시 CLI ocx system settings --client-compaction on)으로 loopback에서도 provider-table 폼(requires_openai_auth = true)을 고르게 해, 클라이언트 compaction이 일반 summary history만 남기게 하자는 것입니다. codexDesktopAuthless는 이미 table 폼을 쓰지만 로그인 게이트까지 풀어서 동치가 아닙니다. types/config 분할 캠페인과 직접 충돌하지는 않지만, 새 설정 키를 넣으면 src/types/config.ts / src/config.ts zod / management config-routes / system-command에 같은 패턴으로 슬롯이 필요합니다.

경로 src/codex/inject.ts · Design B vs provider-table - 이 이슈의 핵심 스위치 지점입니다. 이미 authless Desktop이 table 폼을 고르므로, “auth는 유지한 table 폼” 분기만 신중히 추가하면 됩니다.
경로 src/responses/compaction.ts · ocx1 envelope - 기존 remote compaction V2 소유권은 유지하고, 이 모드에서는 새 compaction이 ocx1을 안 만들게 하는 쪽이 목표입니다. 과거 히스토리 자동 재작성은 범위 밖으로 둔 선택이 맞습니다.
경로 #3916 / #3920 - 복구 이슈·PR은 아직 OPEN입니다. 이 이슈는 예방 스위치이고, 복구 레일은 별도로 남겨야 합니다.
경로 설정 표면 - codexDesktopAuthless와 이름이 비슷한 새 플래가라, CLI/대시보드 문구에서 “로그인 게이트는 유지, compaction 소유만 바꾼다”를 분명히 해야 혼선이 없습니다.
경로 기본값 - default-off 제안이 맞습니다. 기존 Design B 사용자 다수에게 ocx1 동작을 갑자기 바꾸면 안 됩니다.

메인테이너의 판단이 필요한 지점

• 설정 키 이름(codexClientCompaction vs 더 명시적인 이름)과 CLI 동사(--client-compaction)를 그대로 갈지
• provider-table 전환 시 catalog/sync/voice sideband(experimental_realtime_ws_base_url) invariant가 Design B와 동일하게 유지되는지 설계 문서를 먼저 받을지
• Codex restore leaves ocx1-compacted threads unreplayable on the native backend #3916/fix(codex): recover ocx1-compacted threads for native replay #3920 복구 레일과 이 예방 스위치를 한 에픽으로 묶을지, 예방 PR을 먼저 받을지
• 서드파티 summarizer quota를 쓰는 부작용을 대시보드에 어느 수준까지 경고할지

너의 추천
needs-design으로 받아 두세요. 방향(독립 스위치로 table 폼 선택, default-off, 기존 ocx1 비재작성)은 HEAD inject/compaction 구조와 맞습니다. 구현 PR은 inject 분기 + types/config/zod/management/CLI 문구 + “OFF 후 native replay” 통합 테스트 없이 받지 마세요. #3916 복구와 닫히 순서를 같이 적어 두는 편이 좋습니다.

이 댓글은 grok-bot이 작성했습니다