問題修復
派小助手做事時，現在可以設定小助手數量的建議值、省下大筆額度
為了省去你手動重打一長串舊指令的力氣，系統現在修復了 Ctrl+R 歷史搜尋（Ctrl+R history search，在終端機裡按 Ctrl+R 鍵來快速搜尋你以前打過哪些指令的功能）功能。以前用這功能找舊指令時，系統偶爾會因為字串比對錯誤直接崩潰閃退，逼你整台重新啟動；現在修好了，隨你怎麼搜都能穩定運作。這就像圖書館的舊書檢索電腦以前打字打太快會當機，現在修好系統後，隨便你怎麼翻查卡片檢索都不會當機。
繁體中文
新功能
AI 碰到問題會乖乖等你回答，不會自作主張繼續做下去
為了避免 AI 在你離開座位時自作主張做錯事，對話框現在預設會等待人工。以前 AI 遇到需要你同意的 AskUserQuestion（AI 遇到疑惑停下來彈出對話框問你該怎麼辦的機制）時，如果你放著一段時間沒理它，它會自動繼續往下執行，可能不小心做錯；現在它會老老實實等到你回來點頭，如果你需要人不在時也能自動執行，可以在 /config 裡自己開啟閒置逾時（idle timeout，放著不理時會自動按預設流程繼續執行的計時器）。這就像以前的工程助理問你「這段程式要刪嗎？」，你沒回答他就自己動手刪了；現在他會站著等到你給指示，除非你交代「十分鐘沒回就照舊」。
新功能
派小助手做事時，現在可以控制小助手的數量上限、省下大筆額度
為了控制你的 API 帳單花費，系統在 /config 裡新增了設定項目，讓你控制 workflowSizeGuideline（用來限制 AI 遇到大型工作時自動分派出去的小助手數量的指導方針）。你可以自由選擇小、中、大三種規模，這只是小／中／大代理數的建議值，不保證限制或成本上限，但能引導 AI 不要輕易分工給幾十個子代理人同時運作，導致你的用量額度在一瞬間被燒光。這就像你把裝潢外包給工頭，以前工頭會默默叫來三十個工人一天做完然後找你收大筆工錢；現在你可以給他建議值，不保證限制，但能引導預算在控制範圍內。
問題修復
子助手如果被呼叫次數限制擋住，現在會老實報錯，不會裝沒事回傳空資料
為了讓主要 AI 不被錯誤的空資料誤導，系統現在修復了子代理人被擋時的回報機制。以前 subagents（主要 AI 為了分工而派出去幫忙跑分支任務的子代理人）遇到 API 頻率限制（rate limit，雲端伺服器限制你一分鐘內只能發送幾次請求的規則）時，會默默裝作沒事、回傳一個空結果，導致主要 AI 誤以為資料真的不存在而胡亂分析；現在它被限制時會清清楚楚報錯，讓主要 AI 明確收到失敗的結果。這就像你派人去郵局領信，以前他因為郵局關門沒領到信，回來卻對你說「今天沒有信」；現在他會老實坦白「郵局關門了我進不去」，你才不會被誤導。
問題修復
修復丟到背景跑的代理人因為重啟而失效、或突然卡在背景罷工的 bug
為了讓你在背後跑的長任務能順利執行完成，系統修復了背景程式重啟時的驗證錯誤。以前把任務交給背景的 daemons（在背景默默幫你做事的常駐程式）時，如果遇到連線重置，系統在重啟背景程式的過程中，會不小心把安全連線驗證的金鑰（socket auth token，用來與主程式進行安全加密連線的憑證金鑰）洗掉，導致背景任務直接失效或變成卡死在記憶體裡的幽靈程式；現在重啟時金鑰會被妥善保留，孤立的幽靈程式也會被乾淨清空。這就像你去遊樂園玩到一半，工作人員重啟排隊通道時把你的快速通關票收走了、讓你只能傻站著；現在重啟後車票依舊有效，你可以順利玩完。
English
BUGFIX
Set advisory guidelines for helper agent counts, saving your quota
To save you the effort of manually retyping long command strings from scratch, the system has patched the Ctrl+R history search (Ctrl+R history search, a feature that lets you press Ctrl+R to quickly search through commands you typed earlier) tool. Previously, searching for old commands this way could trigger a string-matching bug that crashed the terminal, forcing you to restart the session; now it is resolved so searches run stably. It's like a library catalog search terminal that used to freeze if you typed too fast; now the database search is patched and never locks up.
FEATURE
AI now patiently waits for your answers instead of auto-continuing on its own
To prevent the AI from taking risky actions behind your back when you step away from your desk, dialogs now wait for a human by default. Previously, when the AI asked a question via AskUserQuestion ( the dialog prompt where the AI pauses to ask for your feedback before acting), if you left the terminal unattended, it would auto-continue by itself and potentially break things. Now it waits indefinitely until a human responds, unless you manually configure an idle timeout (idle timeout, a timer that lets the AI take action after you've been away for a set time) in /config. It's like a junior builder who used to knock down a wall if you didn't answer his question; now he stands with his hammer waiting for your nod, unless you tell him 'if I'm away for ten minutes, proceed.'
FEATURE
Control how many helper agents are spawned for complex tasks, saving your quota
A new configuration allows you to guide the workflowSizeGuideline ( a guideline setting that controls how many sub-helper agents the AI is allowed to summon when breaking down a massive task) in /config. By selecting small, medium, or large sizes, this serves as an advisory guideline for small/medium/large agent counts, not a strict limit or cost cap, but helps guide the AI against spawning dozens of subagents to tackle a complex task, which used to burn through your quota in seconds. It's like hiring a contractor who used to show up with thirty assistants and bill you for all of them; now you can give them an advisory guideline, which is not a strict limit, to keep your budget under control.
BUGFIX
Helper agents blocked by rate limits now report errors instead of silently returning empty data
Subagents ( smaller assistant AIs spawned by the main agent to work on subtasks) now fail cleanly when rate-limited. Previously, if they hit a rate limit (rate limit, the speed limit rules that prevent calling an API too many times in a minute) they would return empty results instead of an error, causing the main AI to assume the target file or data was empty; now they throw a clear error so the main agent clearly receives the failure. It's like sending an errand boy to get letters, and because the post office was closed, he returns and tells you 'you have no mail'; now he tells you 'the post office was closed so I couldn't get in,' saving you from being misinformed.
BUGFIX
Background agents no longer lose authentication tokens or get stuck during service restarts
System now preserves authentication credentials during daemon restarts. Previously, when tasks ran under background daemons (daemons, background server programs that run tasks quietly in the background), any connection reset caused the restart sequence to lose the secure connection key (socket auth token, the security credential used to communicate securely with the main application), leaving the agent frozen or orphaned in memory; now the token is preserved, and orphans are swept away. It's like an amusement park ride that broke down, and during the queue restart the ride operator took away your fast-pass ticket, leaving you stranded; now the ticket remains valid through restarts so you can finish the ride.
原始 CHANGELOG
Original changelog派小助手做事時，現在可以設定小助手數量的建議值、省下大筆額度
Fixed crashes during inline history searches (Ctrl+R).Original changelogAI 碰到問題會乖乖等你回答，不會自作主張繼續做下去
Dialogs no longer auto-continue by default and will wait for a human; users can opt into an idle timeout via /config.Original changelog派小助手做事時，現在可以控制小助手的數量上限、省下大筆額度
Added a setting in /config to control the scale of dynamic workflows (small/medium/large agent counts) as an advisory guideline.Original changelog子助手如果被呼叫次數限制擋住，現在會老實報錯，不會裝沒事回傳空資料
Fixed subagents cut off by rate limits returning empty results instead of failing cleanly.Original changelog修復丟到背景跑的代理人因為重啟而失效、或突然卡在背景罷工的 bug
Fixed socket auth tokens being stripped during daemon restarts and resolving orphan background agents.