14 OctClaude Code just added idle compaction, and this could save a LOT of usage. Imagine you have a session with 500K tokens of context. You come back 90 minutes later, your prompt cache has expired, and Claude has to process all 500K tokens again without the cache. That’s insanely…ClaudeAnthropicClaude CodeContext managementPrompt caching
19 SepI castrated Claude Code. Ripped almost everything out and left only the bare minimum: read, inspect, write. Startup context is now under 2k tokens. I also capped the context window at 200k tokens so it compacts earlier instead of chewing through my limits with bloated context.…ClaudeAnthropicClaude CodeContext managementAgent harnesses
15 Aug⚡️ Codex is getting 94% faster This applies to long sessions. Previously, opening a huge chat meant Codex loaded almost the entire history at once. Now it will load only the part you actually need, and fetch the rest when needed. In OpenAI’s internal test, load time dropped…OpenAICodexContext management
13 JulCODEX NEWS • GPT-5.6 Sol now uses 10% fewer tokens. • The context window was rolled back from 372K to 272K. They’re investigating why the larger window became more resource-hungry. • Subagent launches have been fixed. 🎁 Expect a little gift today: a banked reset.GPT-5.6 SolOpenAICodexContext managementSubagents
