agent/codex
1
0
Fork 0
mirror of https://github.com/pchuan98/codex.git synced 2026-07-01 00:31:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Let models opt into original image detail (#14175)

Browse Source 
## Summary

This PR narrows original image detail handling to a single opt-in
feature:

- `image_detail_original` lets the model request `detail: "original"` on
supported models
- Omitting `detail` preserves the default resized behavior

The model only sees `detail: "original"` guidance when the active model
supports it:

- JS REPL instructions include the guidance and examples only on
supported models
- `view_image` only exposes a `detail` parameter when the feature and
model can use it

The image detail API is intentionally narrow and consistent across both
paths:

- `view_image.detail` supports only `"original"`; otherwise omit the
field
- `codex.emitImage(..., detail)` supports only `"original"`; otherwise
omit the field
- Unsupported explicit values fail clearly at the API boundary instead
of being silently reinterpreted
- Unsupported explicit `detail: "original"` requests fall back to normal
behavior when the feature is disabled or the model does not support
original detail
This commit is contained in:
Curtis 'Fjord' Hawthorne
2026-03-11 15:25:07 -07:00
committed by GitHub
Unverified
parent f548309797
commit 8791f0ab9a
10 changed files with 620 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/js_repl.md
+3 -2
View File
@@ -84,8 +84,9 @@ imported local file. They are not resolved relative to the imported file's locat
- Nested `codex.tool(...)` outputs stay inside JavaScript unless you emit them explicitly.
- `codex.emitImage(...)` accepts a data URL, a single `input_image` item, an object like `{ bytes, mimeType }`, or a raw tool response object that contains exactly one image and no text. Call it multiple times if you want to emit multiple images.
- `codex.emitImage(...)` rejects mixed text-and-image content.
- Example of sharing an in-memory Playwright screenshot: `await codex.emitImage({ bytes: await page.screenshot({ type: "jpeg", quality: 85 }), mimeType: "image/jpeg" })`.
- Example of sharing a local image tool result: `await codex.emitImage(codex.tool("view_image", { path: "/absolute/path" }))`.
- Request full-resolution image processing with `detail: "original"` only when the `view_image` tool schema includes a `detail` argument. The same availability applies to `codex.emitImage(...)`: if `view_image.detail` is present, you may also pass `detail: "original"` there. Use this when high-fidelity image perception or precise localization is needed, especially for CUA agents.
- Example of sharing an in-memory Playwright screenshot: `await codex.emitImage({ bytes: await page.screenshot({ type: "jpeg", quality: 85 }), mimeType: "image/jpeg", detail: "original" })`.
- Example of sharing a local image tool result: `await codex.emitImage(codex.tool("view_image", { path: "/absolute/path", detail: "original" }))`.
- When encoding an image to send with `codex.emitImage(...)` or `view_image`, prefer JPEG at about 85 quality when lossy compression is acceptable; use PNG when transparency or lossless detail matters. Smaller uploads are faster and less likely to hit size limits.
Avoid writing directly to `process.stdout` / `process.stderr` / `process.stdin`; the kernel uses a JSON-line transport over stdio.