Skip to content

[pull] main from inclusionAI:main#68

Merged
pull[bot] merged 1 commit into
axistore80-coder:mainfrom
areal-project:main
May 9, 2026
Merged

[pull] main from inclusionAI:main#68
pull[bot] merged 1 commit into
axistore80-coder:mainfrom
areal-project:main

Conversation

@pull
Copy link
Copy Markdown

@pull pull Bot commented May 9, 2026

See Commits and Changes for more details.


Created by pull[bot] (v2.0.0-alpha.4)

Can you help keep this open source service alive? 💖 Please sponsor : )

…e service (#1318)

* refactor(archon): remove redundant capacity grant from inference service

StalenessManager in the controller already gates episode execution,
making the Router's CapacityManager a no-op intermediary that adds
two HTTP round-trips per episode for zero value.

Key changes:
- Remove _grant_capacity call and method from InferenceServiceWorkflow
- Remove grant_capacity_in_router helper from gateway streaming
- Remove /grant_capacity endpoint from both gateway and router
- Delete CapacityManager class and CapacityResponse model from router
- Remove try_acquire gate from /register_session endpoint
- Drop capacity field from router HealthResponse
- Update all test files to remove capacity-related tests and setup

* chore: modify commit convention scope
@pull pull Bot locked and limited conversation to collaborators May 9, 2026
@pull pull Bot added the ⤵️ pull label May 9, 2026
@pull pull Bot merged commit 6d253e8 into axistore80-coder:main May 9, 2026
5 checks passed
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant