[codex] Add Syrin v0.12 sandbox execute loop#18
Open
rhein1 wants to merge 9 commits into
Open
Conversation
|
Warning Rate limit exceeded
You’ve run out of usage credits. Purchase more in the billing tab. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (6)
📝 WalkthroughWalkthroughThis PR introduces Syrin v0.12 native sandbox support to Agoragentic, including a new example module that generates sandbox execute-loop plans with guardrail logic, shared workspace contracts, and resource limits, alongside supporting documentation, schema definitions, and comprehensive tests. ChangesSyrin v0.12 Native Sandbox Integration
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Tip 💬 Introducing Slack Agent: The best way for teams to turn conversations into code.Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.
Built for teams:
One agent for your entire SDLC. Right inside Slack. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🧹 Nitpick comments (1)
tests/test_agoragentic_autonomous_lifecycle.py (1)
226-284: ⚡ Quick winAdd a regression for “safe action while live mode is off.”
Current additions don’t assert the default
live_enabled=Falsepath for non-sensitive actions. Add one test to verify the payload stays preview-only in that case, so execute preference cannot silently reappear.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@tests/test_agoragentic_autonomous_lifecycle.py` around lines 226 - 284, Add a regression test that verifies non-sensitive actions with the default live flag remain preview-only: call syrin_sandbox.build_guardrail_report with live_enabled=False using a clearly non-sensitive prompt (e.g., "preview route" or "list items"), then call syrin_sandbox.build_execute_payload with that report and check payload["constraints"]["preview_only"] is True and payload["constraints"]["prefer_execute"] is False (also assert report["decision"] == "allow" if helpful); put this new test alongside the other tests (e.g., a new def test_syrin_sandbox_default_live_off_keeps_preview_only(self):) so it covers the default live_enabled=False path for non-sensitive actions.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@agoragentic/examples/syrin_sandbox_execute_loop.py`:
- Around line 171-197: Update build_execute_payload to factor in live-mode when
deciding execution: add a boolean parameter (e.g., run_live or live_mode) and
compute can_execute = (guardrail_report["decision"] == "allow") and run_live so
preview-first is preserved when live mode is off; keep constraints using
prefer_execute = can_execute and preview_only = not can_execute, and update any
callers of build_execute_payload accordingly (refer to function
build_execute_payload, variable can_execute, and the constraints dict).
- Around line 255-284: The builder build_syrin_sandbox_plan currently accepts
max_cost from callers without validation; add input validation at the start of
build_syrin_sandbox_plan to ensure max_cost is a finite non-negative number (not
NaN or ±inf) and raise a clear ValueError (or similar) if it fails, so invalid
values cannot propagate into build_execute_payload or build_resource_limits;
include the check before any calls to
build_execute_payload/build_resource_limits and mention max_cost in the
exception message for easier debugging.
- Around line 221-252: The generated script uses top-level "async with
Sandbox(...)" which is invalid; wrap the async usage in an async function (e.g.,
define async def main(): and move the Sandbox block and calls to sb.exec_bash /
sb.exec_python into it), add "import asyncio" at the top, and invoke
asyncio.run(main()) at module scope so the Sandbox context and awaits run inside
a proper async event loop.
---
Nitpick comments:
In `@tests/test_agoragentic_autonomous_lifecycle.py`:
- Around line 226-284: Add a regression test that verifies non-sensitive actions
with the default live flag remain preview-only: call
syrin_sandbox.build_guardrail_report with live_enabled=False using a clearly
non-sensitive prompt (e.g., "preview route" or "list items"), then call
syrin_sandbox.build_execute_payload with that report and check
payload["constraints"]["preview_only"] is True and
payload["constraints"]["prefer_execute"] is False (also assert
report["decision"] == "allow" if helpful); put this new test alongside the other
tests (e.g., a new def
test_syrin_sandbox_default_live_off_keeps_preview_only(self):) so it covers the
default live_enabled=False path for non-sensitive actions.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 9b5d4062-25cb-45a2-93ba-3e4329125a36
📒 Files selected for processing (7)
README.mdagoragentic/README.mdagoragentic/SANDBOX_AND_DEPLOYMENT.mdagoragentic/WORKFLOW_SCHEMAS.mdagoragentic/examples/README.mdagoragentic/examples/syrin_sandbox_execute_loop.pytests/test_agoragentic_autonomous_lifecycle.py
…yrin-sandbox-v012 # Conflicts: # agoragentic/README.md # agoragentic/examples/README.md # tests/test_agoragentic_autonomous_lifecycle.py
…cy' into codex/agoragentic-syrin-sandbox-v012 # Conflicts: # agoragentic/README.md # agoragentic/WORKFLOW_SCHEMAS.md # agoragentic/examples/README.md # tests/test_agoragentic_autonomous_lifecycle.py
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
2 participants
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.
Summary
Sandboxexecute-loop example for Agoragentic routingSANDBOX_WORKSPACEcontract, resource limits, and approval-gated execute payloadWhy
Syrin v0.12.0 added first-party sandboxed bash/Python execution, package installation, resource pools, and recursive sandbox propagation. This gives the Agoragentic integration a native sandbox path instead of relying only on external sandbox scaffolding.
Validation
python -m compileall -q agoragentic testspython -m unittest tests.test_agoragentic_autonomous_lifecycle -vpython -m unittest discover -s tests -vpython -m ruff check agoragentic\examples\syrin_sandbox_execute_loop.py tests\test_agoragentic_autonomous_lifecycle.pypython agoragentic\examples\syrin_sandbox_execute_loop.py --task "Preview a v0.12 sandbox route" --max-cost 0 --packages pandas --requested-action "deploy live spend"Summary by CodeRabbit
New Features
Documentation
Tests