LangChain Deep Agents 0.10.5 Returns Tool Errors to the Model Instead of Failing the Run
LangChain · x · 2026-11-20
LangChain's caspar shares a small reliability win in Managed Deep Agents 0.10.5: instead of terminating the run on tool errors, most errors are returned to the model with a status flag so it can recover and retry.
Most tool errors are recoverable, so this change makes agents noticeably more resilient for long-running work. The accompanying diagram shows the before/after: previously the agent ended with "An error occurred"; now the model sees the error, adjusts, and re-executes successfully.
More from coding & agent
- Watching an AI agent click through Plotzy's UI: a temporary pattern, says dev — NathanSRobinson · 2026-11-20
- Building an Email Routing Agent with DSPy Weight-Space Programming on 600M/2B Local Models — lateinteraction · 2026-11-20
- Gemini 4 Neon codes a Chamonix ski sim from scratch: ~10k lines, zero assets — flngr · 2026-11-20
- Personal agent platforms are the new note-taking apps: no tool fixes a missing system — evielync · 2026-11-20
- Consultant runs Gemini as a coworker for 3 months: email triage, lead capture, pair programming — McDonaghMatthew · 2026-11-20
- OpenAI healthcare case study: Assort's Codex agent closes referrals via computer use in Athena — krishnan · 2026-11-20