Qwen-Code's huge system prompt inflates every turn; no-compaction ipython grows largest late
yb2698 · x · 2026-10-14
Per-turn prompt-size analysis: Qwen-Code is much larger every turn due to its huge system prompt. Turns per trial are fairly homogeneous with a slight edge for opencode. The bare ipython harness has the smallest prompts up to 30% of the trajectory, then grows linearly to become the largest by the last turn — because it implements no history compaction at all, just a pure ipython session.
More from coding & agent
- Creator builds custom GoPro ingestion tool with Codex: 4-camera array with WiFi trickle ingest — OpenAIDevs · 2026-10-15
- HybridAgent reasons in latent space, acts via text — 2x faster, 3x cheaper, open-sourced — zainhas · 2026-10-15
- Claude Code 2.1.300 ships 88 CLI changes, drops AskUserQuestion directive from system prompt — ClaudeCodeLog · 2026-10-15
- Tahoe AI opens Tara, a one-prompt plug-in connecting agents to its Tahoe-100M biology datasets — anshulkundaje · 2026-10-15
- sgrep cuts coding agent LLM costs 21.3% on SWE-bench versus ripgrep, fully local in Rust — udmrzn · 2026-10-15
- 10 GitHub repos that turn Claude Code and Codex into elite UI designers — udmrzn · 2026-10-15