langsmith-forge[bot] 48965a82a6 fix: coerce malformed integer strings in read_file offset/limit params (#1216) ... - 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>		2026-05-01 14:29:48 -07:00
..
integrations	fix: lower default LangSmith sandbox size to fit "large" tier (#1226)	2026-04-30 13:24:15 -07:00
middleware	fix: coerce malformed integer strings in read_file offset/limit params (#1216)	2026-05-01 14:29:48 -07:00
tools	fix: warn against using http_request for GitHub PR creation (#1203)	2026-05-01 14:14:44 -07:00
utils	fix: update existing PR title and body when create returns 422 (#1163)	2026-05-01 14:02:39 -07:00
encryption.py	chore: Drop monorepo (#1029)	2026-03-06 16:10:34 -08:00
prompt.py	fix: warn against using http_request for GitHub PR creation (#1203)	2026-05-01 14:14:44 -07:00
server.py	fix: coerce malformed integer strings in read_file offset/limit params (#1216)	2026-05-01 14:29:48 -07:00
webapp.py	feat: give agent ability to read cross-posted Slack message links [closes OPE-37] (#1200)	2026-04-29 17:42:27 -07:00