CMU 11-768's first assignment starts from an empty ReAct loop: a bash-only CodeAgent fixes a bug in a chess app, context compaction is added to solve a SWE-bench task, and the same loop becomes a ChessAgent that runs a two-ply search with simulate_move, run_python, and a skill. All 100 points are graded by replaying submitted patches and trajectories offline.
TurnContext 在 turn 初始化時捕獲所有設定（模型、審批、token budget），後續 step 透過 StepContext 讀取快照；StepActivation 驗證設定變更不違反 legacy 安全約束；ContextManager 用 Arc<Vec> + 版本號實現 Copy-on-Write 歷史共享；壓縮觸發條件為 token_remaining < threshold，支援 remote v1/v2、local、model fallback 四條路徑。
omp doesn't have just one compaction: context-full uses LLM summarization with iterative windows and budget halving retries; snapcompact skips the LLM entirely, rendering history as dense PNG bitmaps for vision models to read — solving no-API-key, low-latency, vision-model-cheaper scenarios; branch summary summarizes the abandoned branch during `/tree` navigation so file ops aren't lost; shake mechanically replaces tool-result text and large fenced/XML blocks with placeholders — an emergency hatch when summary is too heavy and prune isn't enough. Four strategies, distinct failure modes, orchestrated by session maintenance or manual triggers.
Complete Compaction Mechanism: shouldCompact Trigger Conditions (Token Ratio, Message Count), estimateTokens Calculation (Char/Word Approximation), findCutPoint Finding Cut Point (Retain Recent N Turns), generateSummary Generating Summary (LLM Call), prepareCompaction Preparing Context, Branch Summary Generation, Structured Compaction (Extension Custom via fromHook), CompactionEntry Details, fromHook Mechanism, Compaction Settings.
SessionManager core: JSONL append-only storage, id/parentId tree formation, branch() moves leaf pointer without mutating history, buildSessionContext() handles compaction entries, createBranchedSession() forks to new file. Complete Entry types: message, thinking_level_change, model_change, compaction, branch_summary, custom, custom_message, label, session_info. Migration v1→v2→v3 details.
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.
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.
By default every DM lands in one main session, and group activity and background work report back into it. Memory is entirely Markdown on disk — the model only remembers what gets saved, with no hidden state. But if more than one person can DM your agent, DM isolation is something you have to turn on.
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.