docs(claude): tell agents to let heavy gates queue for machine-wide slots

[devin-ai-integration]

TLDR

Problem this solves:

• Agents don't know heavy gates queue machine-wide
• A quiet queueing make check looks like a hang
• So agents kill, retry, or disable the queue
• Cheap make bootstrap waited behind heavy gates

How it solves it:

• CLAUDE.md now names the slot queue and its message
• Says to wait it out with a long timeout
• Bans LITELLM_GATE_SLOTS=0 and raising the count
• bootstrap no longer takes a slot, being I/O bound

User Flow

Docs and local-tooling change for contributors in this repo, so no end user flow changes

Relevant issues

Linear ticket

Pre-Submission checklist

• I have added meaningful tests
• My PR passes all CI/CD checks (e.g., lint, format, unit tests)
• My PR's scope is as isolated as possible; it only solves 1 specific problem
• I have received a Greptile Confidence Score of at least 4/5 before requesting a maintainer review (Greptile reviews automatically once the PR is opened; only comment @greptileai to re-request a review after pushing changes)

Delays in PR merge?

If you're seeing a delay in your PR being merged, ping the LiteLLM Team on Slack (#pr-review).

Screenshots / Proof of Fix

No proxy code paths change. make -n bootstrap now expands straight to the provisioning commands with no gate_slot_lock.py wrapper, while make -n check still starts with python3 scripts/gate_slot_lock.py make check-inner. The lock behavior itself ships in #36988 and is covered by tests/test_litellm/test_gate_slot_lock.py

Type

📖 Documentation

Caveats (if any)

• Prose rule, so nothing enforces it in CI
• check-inner / lint-inner still work, just discouraged
• bootstrap under make check was already unqueued

Link to Devin session: https://app.devin.ai/sessions/13e9cbbb61e742879faed4d9a1f6c19b
Requested by: @mateo-berri

[devin-ai-integration]

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

• Address comments on this PR. Add '(aside)' to your comment to have me ignore it.
• Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

• Disable automatic comment, CI, and merge conflict monitoring

[greptile-apps]

Greptile Summary

This PR clarifies how machine-wide slots queue heavy contributor checks and removes the I/O-bound bootstrap target from slot management.

• Documents the queue message and instructs agents to wait rather than bypass slot limits
• Runs direct make bootstrap provisioning without the slot-lock wrapper
• Updates Makefile help and slot-lock documentation to list only queued targets

Confidence Score: 5/5

The PR appears safe to merge

No blocking failure remains

Important Files Changed

Filename	Overview
CLAUDE.md	Adds accurate agent guidance for queued heavy gates; the previously reported bypass-list issue is no longer present
Makefile	Makes direct bootstrap execution unqueued while preserving slot locking for check and lint
scripts/gate_slot_lock.py	Updates the module documentation to reflect that bootstrap no longer acquires a machine-wide slot

_{Reviews (4): Last reviewed commit: "chore: make it more concise" | Re-trigger Greptile}

[devin-ai-integration]

@greptileai

[devin-ai-integration]

@greptileai

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[mateo-berri]

bugbot run

[cursor]

Bugbot is paused — on-demand spend limit reached

Bugbot uses usage-based billing for this team and has hit its on-demand spend limit.

A team admin can raise the spend limit in the Cursor dashboard, or wait for the next billing cycle to continue.

[mateo-berri]

@greptileai

[mateo-berri]

LGTM