pi-codex-image-gen 0.1.14 → 0.1.15
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +6 -0
- package/README.md +4 -4
- package/extensions/index.ts +1 -1
- package/package.json +1 -1
- package/skills/imagegen/SKILL.md +1 -0
package/CHANGELOG.md
CHANGED
|
@@ -6,6 +6,12 @@ This project follows the spirit of [Keep a Changelog](https://keepachangelog.com
|
|
|
6
6
|
|
|
7
7
|
## [Unreleased]
|
|
8
8
|
|
|
9
|
+
## [0.1.15] - 2026-10-02
|
|
10
|
+
|
|
11
|
+
### Changed
|
|
12
|
+
|
|
13
|
+
- Use `gpt-6-astra` as the default Codex image-routing model instead of `gpt-5.5`. Preserve explicit tool/configuration overrides and backend-selected image rendering.
|
|
14
|
+
|
|
9
15
|
## [0.1.14] - 2026-10-02
|
|
10
16
|
|
|
11
17
|
### Added
|
package/README.md
CHANGED
|
@@ -100,7 +100,7 @@ Project config overrides global config only when project trust is active. If pro
|
|
|
100
100
|
{
|
|
101
101
|
"save": "global",
|
|
102
102
|
"saveDir": "~/Pictures/generated",
|
|
103
|
-
"model": "gpt-
|
|
103
|
+
"model": "gpt-6-astra"
|
|
104
104
|
}
|
|
105
105
|
```
|
|
106
106
|
|
|
@@ -110,7 +110,7 @@ Project config overrides global config only when project trust is active. If pro
|
|
|
110
110
|
| --------- | ------ | ---------- | ---------------------------------------- |
|
|
111
111
|
| `save` | string | `"global"` | Default save mode (see below). |
|
|
112
112
|
| `saveDir` | string | — | Directory used when `save=custom`. |
|
|
113
|
-
| `model` | string | `"gpt-
|
|
113
|
+
| `model` | string | `"gpt-6-astra"`| Codex routing model, not the backend image model. |
|
|
114
114
|
|
|
115
115
|
### Environment variables
|
|
116
116
|
|
|
@@ -135,7 +135,7 @@ Project config overrides global config only when project trust is active. If pro
|
|
|
135
135
|
| Parameter | Type | Required | Description |
|
|
136
136
|
| -------------- | ------ | -------- | ------------------------------------------------------------------ |
|
|
137
137
|
| `prompt` | string | ✅ | The image generation prompt. |
|
|
138
|
-
| `model` | string | — | Override the Codex model. Defaults to config or `gpt-
|
|
138
|
+
| `model` | string | — | Override the Codex model. Defaults to config or `gpt-6-astra`. |
|
|
139
139
|
| `outputFormat` | string | — | `png` (default), `jpeg`, or `webp`. |
|
|
140
140
|
| `save` | string | — | Override save mode for this call. |
|
|
141
141
|
| `saveDir` | string | — | Directory when `save=custom`. Relative paths resolve under CWD. |
|
|
@@ -145,7 +145,7 @@ Project config overrides global config only when project trust is active. If pro
|
|
|
145
145
|
## How it works
|
|
146
146
|
|
|
147
147
|
1. Resolves package-owned `codex-images` OAuth via Pi, or falls back to available legacy Pi `openai-codex` OAuth.
|
|
148
|
-
2. Sends a request to the Codex Responses endpoint and routing model (default `gpt-
|
|
148
|
+
2. Sends a request to the Codex Responses endpoint and routing model (default `gpt-6-astra`) with the `image_generation` tool enabled.
|
|
149
149
|
3. For edits, attaches the selected local or conversation images to the request.
|
|
150
150
|
4. The backend selects an image model to generate or edit the image.
|
|
151
151
|
5. Parses the SSE stream and strictly validates the returned base64 and image format.
|
package/extensions/index.ts
CHANGED
|
@@ -20,7 +20,7 @@ import { abortable, httpFailure, MAX_IMAGE_BYTES, parseCodexSse, withRequestDead
|
|
|
20
20
|
|
|
21
21
|
const PACKAGE_NAME = "pi-codex-image-gen";
|
|
22
22
|
const LEGACY_PROVIDER = "openai-codex";
|
|
23
|
-
const DEFAULT_MODEL = "gpt-
|
|
23
|
+
const DEFAULT_MODEL = "gpt-6-astra";
|
|
24
24
|
const CODEX_RESPONSES_URL = "https://chatgpt.com/backend-api/codex/responses";
|
|
25
25
|
const DEFAULT_SAVE_MODE = "global";
|
|
26
26
|
const OPENAI_BETA_HEADER = "responses=experimental";
|
package/package.json
CHANGED
package/skills/imagegen/SKILL.md
CHANGED
|
@@ -28,6 +28,7 @@ Rules:
|
|
|
28
28
|
- Use the Pi `codex_generate_image` tool by default for new image generation requests.
|
|
29
29
|
- Image login is separate from chat: use `/login codex-images` and complete the ChatGPT OAuth flow in Pi. The Codex app is not required. Existing legacy Pi `openai-codex` OAuth can be a fallback; new `openai` plan-sharing chat OAuth cannot generate images. Never ask the user to paste login URLs or tokens into chat.
|
|
30
30
|
- The tool's `model` parameter selects a Codex routing model, not Flare or Sunburst. Do not claim a specific served image model unless the response reports it. Read `details.reportedImage` for backend-reported output settings, then inspect the actual image; prompt requests for quality, dimensions, or transparency are not guarantees.
|
|
31
|
+
- The default routing model is `gpt-6-astra`. Explicit tool parameters and configuration values override this default.
|
|
31
32
|
- Do not automatically repeat quota, connection, timeout, or incomplete-stream failures. The remote generation may already have consumed quota.
|
|
32
33
|
- Use `referencedImagePaths` for edits when every target has a local path. Use `numLastImagesToInclude` only when a target is available solely in recent conversation history. Never provide both selectors. Masks and advanced CLI-only controls still require confirmed CLI fallback.
|
|
33
34
|
- Do not switch to CLI fallback for ordinary generation quality, size, or output file-path control.
|