cat-shark/pi-commandcode-provider
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ci(models): open PRs for Command Code catalog updates

Browse Source
This commit is contained in:
Patrick Wozniak
2026-08-25 15:08:29 +02:00
parent 3d8758fe3b
commit c3a383447c
3 changed files with 62 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -144,7 +144,7 @@ The following environment variables are intended for tests, local mocks, and com
## Image input
The provider advertises image input only for models marked with the `image` input modality in the official Command Code CLI model catalog. The capability snapshot currently follows `command-code@1.32.2`; unknown models default to text-only until their upstream metadata is reviewed. A daily GitHub Actions check compares the static image and reasoning metadata with the latest published CLI package and reports any drift.
The provider advertises image input only for models marked with the `image` input modality in the official Command Code CLI model catalog. The capability snapshot currently follows `command-code@1.32.2`; unknown models default to text-only until their upstream metadata is reviewed. A daily GitHub Actions job synchronizes the CLI version, image capabilities, and reasoning efforts with the latest published CLI package and opens or updates a reviewable pull request when they change. Pricing remains manually reviewed because the CLI catalog does not expose every pricing tier and temporary promotion used by the provider.
For vision-capable models, Pi's native provider adapters forward image blocks from user messages and tool results using the documented OpenAI or Anthropic message schema. Unknown and text-only models remain marked text-only in Pi.