Correction: OpenAI Compaction Still Uses Reasoning Tokens Even With Effort 'none'
mhmazur · x · 2026-09-05
mhmazur corrected his earlier finding: even with reasoning effort set to none, OpenAI API context compaction still incurs reasoning-related tokens — though they represent the compaction's output tokens, not its reasoning tokens. Discovered while testing the new OpenAI Provider Adapter harness on ARC-AGI-3; compaction uses the same model and reasoning effort as the original request.
More from coding & agent
- Cross-Model Code Review: Having Claude and Copilot CLI Battle Over Refactoring — DanWahlin · 2026-09-05
- Coinbase's x402 protocol replaces 700+ API keys with a single wallet signature for AI agents — kleffew94 · 2026-09-05
- Dev observes GPT-6 Astra skips read/write tool calls, uses bash for everything — lucasmeijer · 2026-09-05
- Astra's touted persistence under scrutiny: no revolutionary leap yet, users say — Benata · 2026-09-05
- Dev builds entire project with Astra: code, demo video, and post all agent-made — daniel_mac8 · 2026-09-05
- astra-advisor: open-source tool lets GPT-6 Astra delegate to smaller models and cut API costs — daniel_mac8 · 2026-09-05