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
* feat(deepseek): add vision mode support
DeepSeek added a third model "识图模式" (Vision Mode) that accepts
image uploads for visual understanding. Add vision to the --model
choices, update selectModel to use explicit index mapping for all
three models, skip the search toggle in vision mode (not available),
and extend waitForFilePreview to detect image thumbnails via send
button state since vision mode shows a preview image instead of a
filename label.
Also catch "Not allowed" errors from setFileInput (Cloudflare may
block CDP file operations) so the DataTransfer fallback can run.
Closes#1215
* fix(deepseek): harden vision upload mode
---------
Co-authored-by: jackwener <jakevingoo@gmail.com>
|`--file`| Attach a file (PDF, image, text) with the prompt (max 100 MB) |
@@ -76,5 +79,6 @@ opencli deepseek history --limit 10
76
79
77
80
- This adapter drives the DeepSeek web UI in the browser, not an API
78
81
- Default mode is Instant with DeepThink and Search disabled; each flag (`--model`, `--think`, `--search`) is synced on every invocation so omitting a flag resets it
82
+
- Vision mode does not support `--search`; use `--model instant` or `--model expert` for web search
79
83
- Long responses (code, essays) may need a higher `--timeout`
80
-
- File upload reads the file into memory and passes it via base64 to the browser; files over 100 MB are rejected
84
+
- File upload prefers the browser file-input path, falls back to base64 injection when needed, and rejects files over 100 MB
0 commit comments