Server-side AG-UI streaming protocol implementation: StreamChunk event types (RUN_STARTED, TEXT_MESSAGE_START/CONTENT/END, TOOL_CALL_START/ARGS/END, RUN_FINISHED, RUN_ERROR, STEP_STARTED/STEP_FINISHED, STATE_SNAPSHOT/DELTA, CUSTOM), toServerSentEventsStream() for SSE format, toHttpStream() for NDJSON format. For backends serving AG-UI events without client packages.

Run harness adapters (Claude Code, Codex, OpenCode) INSIDE isolated sandboxes via defineSandbox + withSandbox + a provider (localProcessSandbox / dockerSandbox). Covers declarative provisioning: createSecrets + secret/bearer, skills (agentSkill/gitSkill/mcpSkill/ fileSkill), plugins, instructions → canonical AGENTS.md + symlinks projected per harness; shallow-clone default with depth opt-out; serial/parallel setup callback over a persistent shell; snapshot-after-setup default with snapshotMaxAge TTL; defineWorkspace (git/setup/scripts/skills/secrets/ instructions/plugins), defineSandboxPolicy (allow/ask/deny), lifecycle/resume, the SandboxHandle (fs/git/process/ports), capability tokens, defineSandbox hooks (onFile/onFileCreate/onFileChange/onFileDelete/onReady/onError/ onDestroy) + fileEvents flag, chat middleware sandbox group (defineChatMiddleware sandbox hooks), the sandbox debug category, watchWorkspace as a low-level building block, the file.changed / sandbox.file / claude-code.session-id events, and the run journal (spawnNdjson journal option, runId uniqueness, follow vs bounded-poll reading, alignToStoredLog replay alignment, chunkFingerprint, createRunScopedIdGen), and takeover of detached runs (withSandbox runs+durability as one opt-in, detach vs cancel via requestRunCancel / RUN_CANCEL_REASON, sandboxRunDriver on the resume path, single-writer fencing of BOTH the event log and the run record, replay-from-zero with JournalReplayDivergedError, the distributed LockStore requirement). Use whenever a harness adapter needs a sandbox or when building sandbox providers.

Server chat state with withPersistence from @tanstack/ai-persistence. Authoritative transcript, run lifecycle, durable interrupts/approvals, chatParamsFromRequest, reconstructChat, snapshotStreaming. Use when the server owns history, multi-device, or durable tool approvals. NOT client localStorage (see ai-core/client-persistence in @tanstack/ai) and NOT stream reconnect alone.

Use when an app already runs Prisma and needs TanStack AI chat persistence — writes a chat-persistence.ts into the app against its existing PrismaClient and schema.prisma. Covers the four models, BigInt timestamps, JSON-as-string columns, upsert-with-empty-update idempotency, and model renaming.

Use when an app already runs Drizzle ORM and needs TanStack AI chat persistence — writes a chat-persistence.ts into the app against its existing db handle, schema file, and drizzle-kit journal. Covers the four tables (SQLite/Postgres/MySQL), the onConflict idempotency rules, JSON columns, and per-request bindings like D1.

Use when an app needs TanStack AI chat persistence on a database with no dedicated recipe — raw Postgres (pg/postgres.js), Kysely, node:sqlite, MongoDB, Supabase, Redis. Writes a chat-persistence.ts against the app's existing client, covering the four stores, the idempotency invariants, and the conformance gate. Route to the Drizzle, Prisma, or Cloudflare skills instead when one of those matches.

Use when a Cloudflare Worker needs TanStack AI chat persistence — writes a chat-persistence.ts into the app against its D1 binding (raw or via Drizzle), plus a Durable Object LockStore. Covers per-request bindings, wrangler config, D1 migrations, and lease-based locks.

AI becomes provocative and mocks the opponent during gameplay

WeWrite 写作模块：在公众号选题明确后完成文章任务书、主张与证据、素材和初稿。由主流程调用， 或响应“就这个选题写正文”。通用写作、博客和短视频文案不触发。

WeWrite 视觉模块：为公众号文章生成封面和必要的内文配图，或只交付提示词。触发词： 封面图、公众号配图、给文章配图、换封面。通用绘图和 logo 设计不触发。

WeWrite 选题模块：抓取全网热点 + 垂类高频需求 + 历史表现分析 + 搜索需求，为公众号 生成 10 个评分排序的选题（含高频角度与常青选题）。 触发关键词：公众号选题、找几个选题、今天写什么、热点选题、热搜选题、爆款选题、选题建议。 需要公众号/微信上下文；不应被抖音/短视频/网站的选题需求触发。

WeWrite 风格设置模块：首次使用引导（onboard）+ 重设公众号写作风格配置（style.yaml）。 触发关键词：重新设置风格、修改风格配置、设置公众号风格、公众号首次设置、换写作人格、 改排版主题偏好。也由主入口 wewrite 在缺 style.yaml 时自动激活。 不应被通用的"改文风"、"润色"触发——那是编辑动作，不是配置动作。

WeWrite 数据复盘模块：拉取微信公众号文章的阅读/分享/点赞数据，回填历史记录并给出 选题、标题、框架的调整建议。 触发关键词：看看文章数据、文章数据怎么样、效果复盘、看看表现、阅读量怎么样。 需要公众号/WeWrite 上下文；不应被通用的"数据分析"触发。

微信公众号内容主入口：完成选题、素材、写作和审稿，并按用户要求独立追加配图、排版或草稿箱发布。 也负责把风格设置、学习修改、数据复盘和多平台改写分发给对应 wewrite-* 模块。 触发关键词：公众号、微信文章、微信推文、草稿箱、微信排版、写公众号、写一篇。 通用文章、博客、邮件、短视频和网站 SEO 不触发。

WeWrite 多平台改写模块：把一篇公众号文章（或指定源稿）内容级真改写成其他平台版本， 当前支持小红书（图文笔记）、抖音（口播脚本），检查编辑质量与源稿相似度。 触发关键词：改写成小红书、小红书版、抖音版、口播稿、多平台分发、一稿多发、平台改写。 不应被"翻译"、"缩写"、"换个标题"触发——那些是单平台编辑动作。

WeWrite 编辑审稿模块：核对任务、事实来源、观点和实用性，必要时直接改稿，只有通过编辑门槛 才生成公众号成稿。也响应“检查这篇文章”。通用代码 review 和网站 SEO 不触发。

WeWrite 排版发布模块：把 Markdown 做成微信预览，或在用户明确授权后推入公众号草稿箱； 也支持主题画廊和图片帖。只处理微信公众号。

WeWrite 自学习模块：从用户的人工修改中学习写作偏好（playbook 飞轮）、导入范文建风格库、 从公众号文章学习排版主题。 触发关键词：学习我的修改、我改了学习一下、导入范文、学习这篇文章、查看范文库、 学习排版、学排版。 不应被通用的"学习"、"总结这篇文章"触发——需要公众号/WeWrite 上下文。

共享规范知识库。包含数学建模竞赛的写作规范、题型防错速查、图表规范等参考内容。其他 skills 在执行过程中按需读取，无需单独触发。

HAR: Execute Plans.md tasks from single task to full parallel team run. Trigger: implement, execute, do everything, breezing, team run, parallel, composer, composer 2.5. Do NOT load for: planning, review, release, setup.