Skip to content

feat(mini_swe_agent_2): opt-in reuse of the shared verifier (#1249) [3/3] - #1679

Closed
adil-a wants to merge 1 commit into
stack/2-swe-agents-openhandsfrom
stack/3-mini-swe-agent-reuse
Closed

feat(mini_swe_agent_2): opt-in reuse of the shared verifier (#1249) [3/3]#1679
adil-a wants to merge 1 commit into
stack/2-swe-agents-openhandsfrom
stack/3-mini-swe-agent-reuse

Conversation

@adil-a

@adil-a adil-a commented Jun 23, 2026

Copy link
Copy Markdown
Contributor

Opt-in verifier reuse for mini-swe-agent-2 (#1249)

Stacked PR 3 of 3 · base: stack/2-swe-agents-openhands

Builds on PR 1 (library + verifier) and PR 2 (OpenHands cutover). This PR proves the verifier is genuinely agent-agnostic by wiring a second, independent agent to it.

What changes

mini_swe_agent_2 gains an opt-in path that scores its patch through the shared swe_env verifier over HTTP — the exact same contract the OpenHands agent uses in PR 2. It emits the normalized unified-diff patch field and POSTs a standard verify request.

  • Off by default. In-process grading remains the default; the verifier path is enabled via config, so this PR changes no existing behavior.
  • Demonstrates the core Decouple SWE environment infrastructure from agent harnesses #1249 outcome: one verifier, reachable by any agent that emits the normalized patch field — no SWE-bench-specific code duplicated into the agent.

Tests

responses_api_agents/mini_swe_agent_2/tests/test_app.py   20 passed

ruff clean. The full stack (PR1+PR2+PR3) reconstructs the verified tree exactly and all suites pass together (swe_env 168, verifier 14, swe_agents 82, mini 20).

Review notes

  • Smallest PR in the stack; the additions are the opt-in verify path plus its cross-agent reuse tests.
  • Review after PR 2.

🤖 Generated with Claude Code


Stack created with GitHub Stacks CLIGive Feedback 💬

…1249)

Adds an opt-in path to mini-swe-agent-2 that scores its patch through the shared
swe_env verifier over HTTP (the same contract the OpenHands agent uses), proving the
verifier is agent-agnostic. Off by default; in-process grading remains the default.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Signed-off-by: adil-a <adil.asif2000@hotmail.com>
@copy-pr-bot

copy-pr-bot Bot commented Jun 23, 2026

Copy link
Copy Markdown

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@adil-a adil-a changed the title feat(mini_swe_agent_2): opt-in reuse of the shared swe_env verifier (#1249) feat(mini_swe_agent_2): opt-in reuse of the shared verifier (#1249) [3/3] Jun 23, 2026
adil-a pushed a commit to adil-a/Gym that referenced this pull request Jun 26, 2026
…b + verifier + docker provider; drop openclaw)

Self-contained anyswe-on-swe_env on top of cmunley1/anyswe (now merged with latest main):
- add swe_env library (responses_api_agents/swe_env/) + inline verifier (resources_servers/swe_env/)
- add the docker sandbox provider + register it (main has apptainer/opensandbox, not docker)
- replace anyswe_agent with the swe_env-based version: docker + apptainer backends, local-.sif
  support, --writable-tmpfs, claude_code anthropic_base_url=null (real Anthropic by default)
- drop openclaw + orphaned dataset setup scripts + unused example_rollouts (out of scope)

Supersedes the NVIDIA-NeMo#1677 stack (NVIDIA-NeMo#1677/NVIDIA-NeMo#1678/NVIDIA-NeMo#1679) and the prior NVIDIA-NeMo#1738 base (stack/3).
Unit tests: anyswe 16, swe_env lib 134 (+1 skip), verifier 14 (+2 skip) = 164 passed.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@adil-a adil-a closed this Jun 26, 2026
@adil-a

adil-a commented Jun 26, 2026

Copy link
Copy Markdown
Contributor Author

Superseded — content converged into #1738 on top of #1572.

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant