Fix DeepSeek tool-calling issues
The three failure modes we actually hit in runs — and the fix for each. Based on real AgentRunDB evidence.
● 由 4 次 AgentRunDB 真实运行支撑 · 成功率 75%
目标: Diagnose and fix failing tool calls with DeepSeek.
- agent
- claude-code
- model
- deepseek
- 最后验证
- 2026-08-16
Failure mode 1 — malformed JSON arguments
Seen with: deepseek-reasoner. Fix: switch to deepseek-chat.
Failure mode 2 — tool not called at all
Cause: base URL typo or trailing slash. Fix: use exactly https://api.deepseek.com.
Failure mode 3 — hangs on parallel tool calls
Fix: reduce parallelism (max 1–2 concurrent tool calls) in agent settings.