Add endpoint_status tool with cached Globus Compute health checks (#47)#47
Merged
Conversation
Adds a process-level Client cache and a short-TTL per-endpoint health cache to health.py so polling on every chat turn is effectively free (10 s TTL healthy / 3 s TTL unhealthy). Exposes a new endpoint_status MCP tool that returns status rows for all configured endpoints (or a named one) along with mode and default_endpoint. Invalidates the cache on set_execution_mode. Wires the tool into server.py and tools/__init__.py. Tests cover caching, force-bypass, TTL expiry, invalidation, named-endpoint scoping, and mode-change invalidation.
…gitignore - Add CONTRIBUTING.md with dev setup, PR process, and code style guide - Remove personal name/email from CLAUDE.md; keep only the tooling rules - CHANGELOG.md: promote Unreleased to 0.1.0 (2026-05-29); drop dead scaffold entry - pyproject.toml: fix Documentation URL to point to ReadTheDocs - Fix endpoint_status docstring indentation that was breaking Sphinx -W CI build - Remove .claude/launch.json from tracking; gitignore .claude/, .DS_Store, root *.png
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a process-level Client cache and a short-TTL per-endpoint health
cache to health.py so polling on every chat turn is effectively free
(10 s TTL healthy / 3 s TTL unhealthy). Exposes a new endpoint_status
MCP tool that returns status rows for all configured endpoints (or a
named one) along with mode and default_endpoint. Invalidates the cache
on set_execution_mode. Wires the tool into server.py and tools/init.py.
Tests cover caching, force-bypass, TTL expiry, invalidation, named-endpoint
scoping, and mode-change invalidation.