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.

Related event: Even with reasoning effort set to none, compaction still burns reasoning tokens(2 posts)→

Original post →

More from coding & agent

coding & agent channel →