You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.ko.md
+6-3Lines changed: 6 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -179,6 +179,7 @@ opencodex는 두 가지 동작을 분리해서 유지합니다:
179
179
-**알맞은 모델에 위임.** 대시보드나 config에서 최대 5개의 라우팅/네이티브 모델을 Codex 서브에이전트 선택기에 노출해, 복잡한 작업은 reasoning 모델로, 빠른 작업은 저렴한 모델로 보낼 수 있습니다. v2 멀티에이전트 표면(GPT-5.6 Sol/Terra)에서는 프록시가 간결한 위임 가이드를 주입합니다. 선호 서브에이전트 모델·effort(`injectionModel` / `injectionEffort`), 노출된 모델 로스터와 각 모델이 지원하는 effort 사다리, 그리고 크로스모델 `spawn_agent` 호출이 실제로 먹히게 하는 `fork_turns` 규칙까지. 문구를 직접 쓰고 싶다면 `injectionPrompt`에 `{{model}}` / `{{effort}}` / `{{roster}}` 플레이스홀더를 넣으면 됩니다.
Copy file name to clipboardExpand all lines: README.md
+6-4Lines changed: 6 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -184,6 +184,7 @@ next Codex session. opencodex keeps two separate behaviors:
184
184
-**Delegate to the right model.** Feature up to five routed or native models in Codex's subagent picker from the dashboard or config — route complex tasks to a reasoning model, fast tasks to a cheap one. On the v2 multi-agent surface (GPT-5.6 Sol/Terra) the proxy injects compact delegation guidance: a preferred sub-agent model and effort (`injectionModel` / `injectionEffort`), the featured-model roster with the effort ladder each supports, and the `fork_turns` rules that make cross-model `spawn_agent` calls actually stick. Want your own wording? Set `injectionPrompt` with `{{model}}` / `{{effort}}` / `{{roster}}` placeholders.
185
185
-**Prepare for preview-gated OpenAI rollouts.** GPT-5.6 Sol/Terra/Luna entries ship with the exact upstream spec (Sol/Terra reach `ultra`, Luna caps at `max`; 372k usable context) for ChatGPT passthrough, OpenAI API key, and OpenRouter routes when upstream access is available.
186
186
-**Give any model superpowers.** Non-OpenAI models get real web search and image understanding via a `gpt-5.4-mini` sidecar over your ChatGPT login.
187
+
-**Generate images natively.** Codex's standalone `image_gen` tool uses `POST /v1/images/generations` for generation and `POST /v1/images/edits` for edits; it is separate from the hosted Responses `image_generation` tool.
187
188
-**See what's happening.** The web dashboard shows providers, OAuth status, model selection, and a live request log, including cached/cache-write token counts when upstream reports them — no more guessing why a request failed.
188
189
-**Runs in the background.** Install as a system service (launchd / systemd / Task Scheduler) and forget about it. The proxy starts on boot and stays out of your way.
189
190
-**Clean exit, zero residue.**`ocx stop` (or the dashboard's Stop button) shuts down the proxy, stops the background service if one is installed, and restores Codex to its original configuration. Plain `codex` works exactly as it did before — no leftover config, no orphaned processes.
@@ -341,7 +342,8 @@ WebSocket transport is off by default. Set `"websockets": true` only if you want
341
342
342
343
By default opencodex binds to `127.0.0.1` (loopback) and requires no extra authentication.
343
344
If you set `"hostname": "0.0.0.0"` to expose the proxy on the LAN, opencodex requires a bearer token
344
-
to protect both the management API (`/api/*`) and the data-plane (`/v1/responses`):
345
+
to protect both the management API (`/api/*`) and the data-plane (`/v1/responses`,
346
+
`/v1/images/generations`, and `/v1/images/edits`):
|`routedModelStallTimeoutMs?`|`number`|`200000`| 설정 파일에서만 지정할 수 있는 라우팅 모델 반복별 원시 응답 byte 연속 무활동 deadline. `1`부터 `2147483647`까지의 정수여야 하며, 비어 있지 않은 응답 body chunk가 올 때마다 다시 시작됩니다. |
249
+
|`timeoutMs?`|`number`|`200000`| 호스팅 웹 검색 요청 하나를 제한하는 별도 deadline. |
250
+
251
+
웹 검색 경로에는 네 가지 clock이 있습니다. 기본 bridge event stall 예산(`stallTimeoutSec`),
252
+
DNS/TCP/TLS/최종 header 예산(`connectTimeoutMs`), 라우팅 모델의 원시 byte 무활동
253
+
(`routedModelStallTimeoutMs`), 호스팅 검색 하나의 제한(`timeoutMs`)입니다. 실제 bridge watchdog은
254
+
`max(기본 stall, connect timeout, 라우팅 모델 stall, 사이드카 timeout) + 30초`입니다. 라우팅 모델
0 commit comments