Skip to content

docs(agent): document processing limits #36

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
nkavian merged 1 commit into from
Sep 15, 2026
Merged

docs(agent): document processing limits #36

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions agent/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,6 +154,11 @@ of Service credentials. Attribute Schemas use a 24-hour fallback freshness, whil
require explicit HTTP freshness metadata. Cross-document schema composition uses `$ref`;
`$dynamicRef` accepts only a fragment reference such as `#node`.

Attribute Schema processing is limited to 256 KiB per document, 16 documents, eight reference
levels, and one MiB for the complete graph. OpenAPI documents are limited to one MiB and 32 JSON
nesting levels. These are SDK safety ceilings. Callers can impose a shorter processing deadline
through the operation's `context.Context` but cannot raise the ceilings.

## Discover Offerings across Services

`Agent` searches Services through the canonical directory, then queries each selected Service with
Expand Down