@99percentpeople/pi-codex-api 0.3.0 → 0.3.2
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/README.md +4 -4
- package/index.min.js +30 -27
- package/index.min.js.map +9 -6
- package/package.json +1 -5
package/README.md
CHANGED
|
@@ -35,15 +35,15 @@ monitoring — **no OpenAI API key required**.
|
|
|
35
35
|
|
|
36
36
|
Subscription usage, limit-reached state, and reset-card redemption:
|
|
37
37
|
|
|
38
|
-
|
|
39
39
|
|
|
40
40
|
Web search with clean result cards (search → open a result → summarize):
|
|
41
41
|
|
|
42
|
-
|
|
43
43
|
|
|
44
44
|
Image generation with `gpt-image-2` (saved PNG + description):
|
|
45
45
|
|
|
46
|
-
|
|
47
47
|
|
|
48
48
|
## Ask Codex
|
|
49
49
|
|
|
@@ -56,7 +56,7 @@ workspace into the request automatically, so the tool prompt must contain the
|
|
|
56
56
|
necessary context, target language, and output format. Optional controls include:
|
|
57
57
|
|
|
58
58
|
- an exact `openai-codex` model ID from Pi's existing model list (otherwise the
|
|
59
|
-
|
|
59
|
+
current official ChatGPT Codex default is resolved from its live model catalog);
|
|
60
60
|
- reasoning effort and per-call answer detail;
|
|
61
61
|
- up to five workspace images or recent conversation images for vision;
|
|
62
62
|
- an explicit output-token cap when the default 8,192 tokens is unsuitable.
|