Skip to content

Serve with gunicorn (1 worker) and raise the OHTTP request cap to 20 MiB #134

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
adambalogh merged 1 commit into from
Jul 22, 2026
+5 −4
Merged

Serve with gunicorn (1 worker) and raise the OHTTP request cap to 20 MiB #134

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
9 changes: 5 additions & 4 deletions tee_gateway/controllers/ohttp_controller.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,10 +88,11 @@
_SSE_CONTENT_TYPE = "text/event-stream"

# Cap on the encapsulated request size. The inner payload is a chat-completion
# JSON body and may include base64 image attachments; 16 MiB covers roughly a
# 10 MiB raw image after base64/JSON overhead while still bounding enclave
# memory use for malicious or accidentally huge payloads.
_MAX_ENCAPSULATED_REQUEST_BYTES = 16 * 1024 * 1024
# JSON body and may include base64 image attachments; 20 MiB covers roughly a
# 14 MiB raw image — or several attached reference images — after base64/JSON
# overhead while still bounding enclave memory use for malicious or
# accidentally huge payloads.
_MAX_ENCAPSULATED_REQUEST_BYTES = 20 * 1024 * 1024

# Fields that can re-identify a client and have no role in inference. We drop
# them before forwarding to the inner handler — keeping them inside the
Expand Down
Loading