Release v0.5.5 · r1n7aro/Locus

English

Per-file revert. The changes panel, the diff review window, and a new row context menu can restore a single file to its snapshot from before the current round, without popping the undo stack. If the file has later edits, Locus asks before rolling them back. (#100)
Automatic retry for model requests. Connection errors, timeouts, HTTP 5xx, and 429 rate limits retry automatically, honoring Retry-After on 429. Retries only happen before any output has streamed; the attempt cap is adjustable in General settings (default 3, 0 disables). (#101)
Inline <think> tags routed to the thinking channel. On the chat-completions and OpenRouter paths, inline <think>…</think> segments in streamed replies are stripped from the message body and shown as thinking instead (enabled by default).
Subagent limits. General settings now cap task subagent nesting depth and per-session concurrency (default depth 1). Calls over the limit return an error explaining the current caps.
/dream memory consolidation skill. A built-in skill that merges duplicate memories, fixes stale facts, and prunes the Memory index.

Auto-compaction scales its retention and request budgets to the model's context window and recognizes more provider "prompt too long" errors, so compaction converges on small-context models.
Replayed tool-call arguments are normalized before being resent to chat-completions/OpenRouter providers — empty or malformed JSON becomes {}; Codex replays stay verbatim. (#94)
Workspace file paths resolve lexically, so symlinked files open and reveal correctly. (#100)
Smoother streaming of long replies: finished markdown blocks are frozen and only the tail re-parses during streaming.
Context token estimates no longer undercount CJK text.
Auth re-checks no longer tear down open tabs, and views preload to avoid a flash on first visit.

按文件撤回。 变更面板、diff 审查窗口及新增的行右键菜单支持把单个文件恢复到本轮修改前的快照，不影响撤销栈；若该文件之后还有编辑，会先询问再回滚。(#100)
模型请求自动重试。 连接错误、超时、HTTP 5xx 与 429 限流自动重试，429 遵循 Retry-After；仅在尚未流式产出任何内容前重试；次数可在通用设置调整（默认 3，设 0 关闭）。(#101)
内联 <think> 标签转入思考通道。 chat-completions 与 OpenRouter 路径上，流式正文中的 <think>…</think> 片段会从消息正文剥离并作为思考过程展示（默认开启）。
子代理限制。 通用设置新增 task 子代理最大嵌套深度与单会话最大并发（默认深度 1）；超限调用会返回错误并说明当前限制。
/dream 记忆整理技能。 内置技能：合并重复记忆、修正过期事实、精简记忆索引。

自动压缩的保留与请求预算按模型上下文窗口缩放，并识别更多供应商的「prompt 过长」报错，小上下文模型上的压缩现在能收敛。
回放历史工具调用时规范化 arguments：空或非法 JSON 变为 {} 再发给 chat-completions/OpenRouter 供应商；Codex 路径保持逐字不变。(#94)
工作区文件路径改为词法解析，符号链接文件现在能正常打开与定位。(#100)
更流畅的长回复流式渲染：已完成的 markdown 块被冻结，流式期间仅重解析尾部。
上下文 token 估算不再低估中日韩文本。
登录态复查不再重建已打开的标签页；视图预加载，消除首次切换时的闪烁。