feat(tools): enhance code execution sandbox#66
Merged
Conversation
Add LimitedWriter for streaming output truncation (stdout: 50KB, stderr: 10KB), SandboxConfig with resource limits and tool allowlist, file-based RPC for tool call forwarding, and ExecMetrics for execution statistics. Refactor executePython/executeBash to share a unified runSandboxed function that uses the new sandbox primitives. Fixes MLT-OSS#59
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
LimitedWriterthat wrapsbytes.Bufferwith streaming output truncation (stdout: 50KB, stderr: 10KB), appending a truncation notice when exceededSandboxConfigwith configurable resource limits (MaxStdoutBytes,MaxStderrBytes,MaxToolCalls,Timeout), tool allowlist (default:read_file,write_file,search_files,patch,terminal,web_search,web_extract), andRestrictNetworkflag~/.hermes/cache/sandbox_rpc/<id>/withrequest.json/response.jsonexchange and allowlist enforcementExecMetricsstruct capturing wall time, exit code, stdout/stderr sizes, and tool call countexecutePython/executeBashinto a sharedrunSandboxedfunction using the new sandbox primitivesTest plan
LimitedWritertruncation at exact limit, under limit, over limit, and multi-write scenariosSandboxConfigdefaults validation and independent copy safetySetupRPCDir/CleanupRPCDirlifecycleExecMetricsJSON round-tripgo test ./... -count=1passesFixes #59