Skip to content
All tags

#context-window

5 posts

Learning Design from Mature Coding Agents (26): Context Compression and Compaction — From Gap to Auditable Baseline

Mature-agent compaction must handle triggers, complete-turn cut points, and recovery. looplane now has an 85% high-watermark, automatic compaction, a deterministic native-loop fallback summary, persisted checkpoints, and workspace-context reinjection. Cross-runtime fallback, model-quality summaries, and live-provider long-session validation remain open.

Looplane context pressure, compaction, and workspace reinjection

Near 85% context pressure, Looplane has two distinct paths: the native loop can apply one bounded deterministic history fallback, while a conversation runtime with native compaction can compact after a completed turn. Both paths re-anchor the next request with workspace context.

Tokens, Context Windows, and Inference vs Training: Three Things to Know Before Using AI Models

Models don't read words — they read tokens. A Chinese character is typically 1-2 tokens; an English word is 1-3. The context window is the token limit per request. Inference is using a model; training is teaching one. What you do every day is inference.

ai guide

Inside the Codex Agent Loop: How OpenAI Keeps AI Agents Iterating

A detailed look at OpenAI's Codex agent loop design: how prompts are constructed, how multi-turn conversations are managed, how prompt caching prevents cost explosions, and how context window auto-compaction works.

How to manage Claude Code's context window: startup content, per-feature costs, and the compaction trio

Claude Code loads the system prompt, MEMORY.md, CLAUDE.md, MCP tool names, and skill descriptions before you type your first word. This post breaks down the startup context, what each of six extension features costs, and how to control auto-compaction with /compact, /autocompact, and autoCompactWindow.