Lataa MiMoCode 0.1.5

Summary
This release ships a builtin skills system — 14 domain-specific skill bundles (document handling, academic writing, arxiv search, deep research, auto-research, html-to-video, skill authoring, and self-documentation) that auto-load when relevant files are attached or task context matches. Skills show localized descriptions in the TUI dialog and support auto-detection of office file attachments. New built-in research workflows: deep-research and fact-check. The self-extend skill is renamed to evolve with a rewritten SKILL.md framing total self-modification — tools, hooks, knowledge, workflows, and UI are all rewritable.
A new Orchestrator mode (opt-in, MIMOCODE_EXPERIMENTAL_ORCHESTRATOR) introduces a delegating coordinator agent that accomplishes goals by spawning and managing child sessions with git worktree isolation and cross-session permission routing.
The cron + loop scheduling system (opt-in, MIMOCODE_EXPERIMENTAL_CRON) enables recurring or self-paced prompts with 5-field cron expressions, durable persistence, and a TUI fire-time clock row.
Vision-aware image paste now spills images to temp files as @file references for non-vision models (instead of base64 that causes hallucination), with smart cost-aware vision_model auto-selection and an actor models [--vision] discovery command.
The Edit tool defaults to exact string matching — fuzzy matching is now opt-in via MIMOCODE_ENABLE_FUZZY_EDIT. Match failures include closest-match hints to help callers correct their old_string.
Other highlights: first-class Windows native installer (PowerShell one-liner alongside macOS/Linux with working upgrade/uninstall), automatic $schema URL migration from opencode.ai to mimo.xiaomi.com/mimocode/, gpt-5.5 support (encrypted reasoning round-trip fix), and a rewritten repetition detector that eliminates false-positive loop-kills on structured content.

本次发布引入 内置 Skills 体系 —— 14 个领域专用 skill bundle（文档处理、学术写作、arXiv 检索、深度调研、自动科研、HTML 转视频、skill 创作、自文档化），在附加相关文件或任务上下文匹配时自动加载，TUI 对话框展示本地化描述。新增研究型内置 workflow：deep-research 和 fact-check。self-extend 重命名为 evolve，SKILL.md 重写为全面自我修改接口——工具、钩子、知识、工作流、界面均可改写。
新增 Orchestrator 模式（opt-in, MIMOCODE_EXPERIMENTAL_ORCHESTRATOR）—— 委派式协调 agent，通过创建/管理子 session 完成目标，支持 git worktree 隔离和跨 session 权限路由。
Cron + Loop 调度系统（opt-in, MIMOCODE_EXPERIMENTAL_CRON）支持 5 字段 cron 表达式、持久化/会话级调度和自适应循环，TUI 新增触发时间行。
视觉感知图片粘贴 对非视觉模型将图片溢写为临时文件 @file 引用（避免 base64 导致幻觉），自动选择性价比最优的 vision_model，新增 actor models [--vision] 发现命令。
Edit 工具默认切换为精确字符串匹配 —— 模糊匹配改为 opt-in（MIMOCODE_ENABLE_FUZZY_EDIT），匹配失败时提供最近似候选提示。
其他重点：Windows 原生安装器转正（PowerShell 一行命令，upgrade/uninstall 全流程可用）、$schema URL 自动迁移（从 opencode.ai 到 mimo.xiaomi.com/mimocode/）、gpt-5.5 支持（加密 reasoning 往返修复）、重写重复检测器（消除对结构化内容的误杀）。
Features
- skill/builtin: ship 14 builtin skills — docx, pdf, pptx, xlsx document handling; arxiv paper search; research-paper-writing; html-to-video pipeline; skill-creator (replaces compose:new-skill); mimocode self-documentation; frontend-design; modern-python-toolchain; deep-research (parallel sub-agents → reflect → cited report, checkpoint-resumable); auto-research (literature surveys, experiment loops, paper reproduction, citation auditing, zero external deps). Add deep-research and fact-check (adversarial 3-juror verification) as built-in workflows. Office file attachments auto-inject relevant skill context; TUI skill dialog shows localized descriptions across 7 languages; slash visibility gated by MIMOCODE_ENABLE_SLASH_SKILLS (#1557, #1564, #1565, #1555, #1569, #1570, #1572, #1567, #1531, #1583, #1579, #1585, #1587)
- skill/builtin: rename self-extend to evolve — rewrite SKILL.md as proactive total self-modification interface (tools, hooks, knowledge, workflows, UI all rewritable); sync hook-api.md with 7 missing events (session/actor lifecycle); add ctx.ask() to tool-api.md (#1590)
- orchestrator: Orchestrator mode (opt-in, MIMOCODE_EXPERIMENTAL_ORCHESTRATOR) — a primary agent that delegates to child sessions via a session tool with create/switch/list/cancel/ask/approve verbs, git worktree isolation per child, permission-approval forwarding, and a globally-unique workspace (#1529)
- cron: cron + loop scheduling system (opt-in, MIMOCODE_EXPERIMENTAL_CRON) — 5-field cron parser, durable + session-only persistence, self-paced loop with adaptive delay and keepalive, /loop skill, TUI fire-time clock row (#1479)
- tui: vision-aware image paste — non-vision models receive a temp-file @file reference instead of base64 bytes; smart cost-aware vision_model auto-selection (in-house preferred, then cheapest); actor models [--vision] discovery command; <vision-capability> system block injected for non-vision models (#1513, #1546)
- edit: default to exact string matching with closest-match error hints — fuzzy matching moved to opt-in via MIMOCODE_ENABLE_FUZZY_EDIT; match failures now suggest the closest candidate to help callers correct old_string (#1466)
- installer: first-class Windows PowerShell native installer (one-liner alongside macOS/Linux), binary upgrade via in-place rename (avoids Job Object killing detached processes), working mimo upgrade/mimo uninstall, UTF-8 encoding (#1511, #1549, #1551)
- config: automatic $schema URL migration from opencode.ai to mimo.xiaomi.com/mimocode/ — existing config files are auto-modified on first load (#1511)
- bash: token efficiency pipeline (opt-in, MIMOCODE_EXPERIMENTAL_TOKEN_EFFICIENCY_HEURISTIC) — heuristic shape-based filter recognizes common output patterns (git diff, pytest, npm, tsc, stacktrace, kubectl, json, markdown) and strips predictable noise to reduce context usage (#1473, #1519)
- security: secondary permission prompt for irreversible bash deletions (bash_delete permission type, distinct from bash) — intercepts rm, rmdir, shred, git reset --hard, git push --force, etc. Opt-out via MIMOCODE_AUTO_APPROVE_DELETE=true. Known issue: default agent permission "*": "allow" auto-approves bash_delete, making this effectively a no-op without manual config (#1566)
- tui: clickable sidebar toggle button at content edge (▶/◀ icons, mouse click replaces Ctrl+X B) (#1541)
- provider: non-empty provider.<id>.models config now acts as implicit whitelist — only listed models shown in picker, hiding unconfigured catalog entries (#1532)
Bug Fixes
- provider: fix gpt-5.5 empty output and reasoning part rs_… not found errors — request encrypted reasoning content for stateless Responses API round-tripping; bump @ai-sdk/* provider deps (#1530)
- provider: defer vision model resolution to environment() call time — fixes P0 crash where mimo upgrade/mimo uninstall failed without project context (#1546)
- detection: rewrite repetition detector from sliding-window n-gram frequency to consecutive-block repeat algorithm (requires 20 contiguous repetitions of a block with ≥3 distinct tokens) — eliminates false-positive loop-kills on markdown tables and structured content; adds CJK character-level tokenization (#1476)
- tui: patch @opentui/core@0.1.101 to fix CJK paste-highlight drift (UTF-16 length → display width) without upgrading to 0.3.4 which regresses markdown streaming (#1471)
- tui: prevent double session creation on home screen submit — consolidate into submitLock guard (#1497)
- tui: clear alternate screen buffer before spawning interactive commands (fixes stale TUI content behind Go TUI tools etc.) (#1492)
- tui: fix background actor Task component showing "completed · 0ms" while still running — now shows live spinner with contextual labels (#1499)
- session: add HTTP 400 to retryable status codes; exclude Auto Dream/Auto Distill system sessions from mimo -c (#1528)
- effect: two-phase instance disposal — Bus shuts down after other services emit final events, fixing sessions stuck as permanently busy (#1527)
- build: generate ext/_manifest.ts in Node target (fixes broken Node-target builds) (#1501)
Refactor
- Prediction uses side-channel generateText instead of llm.stream — bypasses session-coupled hooks, uses tighter context window (3 recent queries + latest assistant turn) (#1498)
Docs
- Add Builtin Skills and Workflows sections to README (en/zh), document MIMOCODE_DISABLE_BUILTIN_SKILLS and MIMOCODE_DISABLE_OFFICIAL_SKILLS env vars (#1581)
Internal / CI
- Skip flaky tests: cancel-truncation (#1523), cancel-interrupts-loop-queued-behind-shell (#1584)
- Remove unused imports and afterEach in overflow test (#1568)