mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 13:53:15 +00:00
- Root cause: LLM occasionally generates strings like '1, 80' or '170, "limit": 60' for integer fields, causing a Pydantic ValidationError and wasting an LLM turn - Change: add SanitizeToolInputsMiddleware in agent/middleware/sanitize_tool_inputs.py that extracts the leading integer from any string value in offset/limit before the call reaches Pydantic validation; registered before ToolErrorMiddleware in server.py - Verified: 14 unit tests covering all three production trace patterns pass Co-authored-by: LangSmith Forge <forge-agent@langsmith.ai> Co-authored-by: Johannes du Plessis <johannes@langchain.dev> |
||
|---|---|---|
| .. | ||
| test_auth_sources.py | ||
| test_commit_and_open_pr_403.py | ||
| test_commit_and_open_pr_workflow_scope.py | ||
| test_ensure_no_empty_msg.py | ||
| test_get_pr_review_comments.py | ||
| test_github_ci.py | ||
| test_github_comment_prompts.py | ||
| test_github_create_pr.py | ||
| test_github_issue_webhook.py | ||
| test_github_pr_label.py | ||
| test_github_review.py | ||
| test_github_security.py | ||
| test_http_security.py | ||
| test_multimodal.py | ||
| test_notify_step_limit_middleware.py | ||
| test_open_pr_middleware.py | ||
| test_proxy_auth.py | ||
| test_recent_comments.py | ||
| test_repo_extraction.py | ||
| test_sandbox_paths.py | ||
| test_sanitize_tool_inputs.py | ||
| test_slack_context.py | ||