Repository navigation
feat(inference): support workload identity federation - #306
Merged
Merged
Conversation
![kit-code-agent[bot]](https://avatars.githubusercontent.com/in/4797102?s=60&v=4){kind=small}
danielkov
commented
Oct 23, 2026
danielkov
commented
Oct 23, 2026
danielkov
force-pushed
the
feat/inference-workload-federation
branch
from
October 24, 2026 09:19
ee050e2 to
7589544
Compare
danielkov
dismissed
kit-code-agent[bot]鈥檚 stale review
October 24, 2026 09:19
The base branch was changed.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Add provider-scoped workload identity authentication for OpenRouter and Speakeasy inference. CLI configuration selects an explicit completion endpoint and an RFC 7523 JWT-bearer or RFC 8693 token-exchange grant backed by a rotating assertion file.
Technical details
Configured providers use the shared workload-token session through asynchronous request authentication, without API-key or browser fallback. Streaming and nonstreaming inference disable automatic replay and redact upstream refusal details; legacy API-key behavior is preserved. Runtime sessions, model changes, and forks retain the provider-specific authentication configuration.
Speakeasy's ordinary-workload inference path requires speakeasy-api/gram#8012; this does not replace managed assistant credentials.