Skip to content

feat(swe-bench): content-addressed unit plan + durable mkdir-atomic work queue - #469

Open
arekay-nv wants to merge 1 commit into
mainfrom
swe-layer-1
Open

feat(swe-bench): content-addressed unit plan + durable mkdir-atomic work queue#469
arekay-nv wants to merge 1 commit into
mainfrom
swe-layer-1

Conversation

@arekay-nv

Copy link
Copy Markdown
Collaborator

What does this PR do?

Type of change

  • Bug fix
  • New feature
  • Documentation update
  • Refactor/cleanup

Related issues

Testing

  • Tests added/updated
  • All tests pass locally
  • Manual testing completed

Checklist

  • Code follows project style
  • Pre-commit hooks pass
  • Documentation updated (if needed)

Stack created with GitHub Stacks CLIGive Feedback 💬

…ork queue

Adds the two foundations of the distributed SWE-bench harness:

- units.py: shards an instance-id list into immutable, content-addressed
  units. The sha256 digest covers the ordered id list, so a plan cannot be
  silently reused across a different run, instance list, or ordering.
- queue.py: a filesystem work queue whose claim is a bare os.mkdir (never
  makedirs(exist_ok=True), which hands a unit to every caller). available()
  is plan - claims - results, so deleting a result alone does NOT requeue a
  unit; requeue() is the only supported path and removes the result, the
  claim and the attempt records together.

Env faults are ledgered separately from counted attempts, and abandoning a
unit publishes a terminal result AND releases the claim so claims/ and
results/ never disagree.
@arekay-nv
arekay-nv requested a review from a team August 26, 2026 03:32
@github-actions

Copy link
Copy Markdown

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

@github-actions
github-actions Bot requested a review from nvzhihanj August 26, 2026 03:32
@github-actions github-actions Bot added the size/large PR Review Policy: 501-1500 lines or 21-50 files label Aug 26, 2026
@nvzhihanj

Copy link
Copy Markdown
Collaborator

I couldn't find the README and purposes of this PR stack, @arekay-nv is this ready for review?

@arekay-nv

Copy link
Copy Markdown
Collaborator Author

I couldn't find the README and purposes of this PR stack, @arekay-nv is this ready for review?

No, this is just a POC for the PR from @leopck converted to a stack. Will probably close this set once he has his own stack.

@nvzhihanj

Copy link
Copy Markdown
Collaborator

I couldn't find the README and purposes of this PR stack, @arekay-nv is this ready for review?

No, this is just a POC for the PR from @leopck converted to a stack. Will probably close this set once he has his own stack.

I see, it's pretty neat from the github interface.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size/large PR Review Policy: 501-1500 lines or 21-50 files

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants