github-featured/swe-agent--swe-agent
2
0
Fork 0
Code Issues Pull Requests Deployments Models Agent Notes Packages Projects Releases Wiki Activity

docs: fix multimodal disable-image-processing flag hierarchy (#1445)

Browse Source 
The multimodal docs told users to run
`--templates.disable_image_processing=true` to disable image processing.
That flag is rejected by the CLI: `disable_image_processing` lives on
TemplateConfig, which is only reachable under `agent.templates`, and the
top-level run config sets `extra="forbid"`, so the unprefixed flag fails
parsing with `unrecognized arguments`.

Add the missing `agent.` prefix so the documented command matches the
config hierarchy (and the correct YAML shown earlier on the same page):
`--agent.templates.disable_image_processing=true`.
This commit is contained in:
Anas Khan
2026-07-06 21:33:08 +05:30
committed by GitHub
parent 5f40e63360
commit 0363b9ef78
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/usage/multimodal.md
+1 -1
View File
@@ -154,4 +154,4 @@ The `web_browser` bundle provides tools for:
We've enabled multimodal processing when `--instances.type=swe-bench --instances.subset=multimodal` are set.
To disable this behavior, you must set `--templates.disable_image_processing=true`.
To disable this behavior, you must set `--agent.templates.disable_image_processing=true`.