dsh-router-standard

dsh-router-standard 任务感知思维模式路由预设：把 DeepSeek V4 在 persona 轴上"非连续、分相变"的实测特性， 量化到稳定区（spec / react / weak），在首轮注入匹配的 persona 与工具面。 属于 dsh-routing-suite 套装，与 dsh-super-injector （免重启运行时注入）配合开发。 📄 研究史说明：docs/statement.md（勘误声明）｜ docs/apology.md（道歉函） 当前状态（v1.19.1，2026-08-24 · 研发线，尚未发布）

Router Standard 处于「严格 workflow」研发线（以 CHANGELOG 为准，版本线文件 router-bootstrap-v34.mjs）： 严格阶段 workflow：完成信号驱动晋级（0→1 需澄清/计划、1→2 需计划锁定、2→3 需交付自检）， 阶段 0 强制对齐（歧义先 ask_user_question、复杂任务先 todo_write）；"工具名/文本即跳级"已删除。 任务回显：stageText 新增 Task: ——模型每轮都看得清在为什么事工作，不跑题。 渐进披露：阶段化解锁 + 两档预放 + 直达语义 + 交付全量开放；tools_catalog 全量索引 / tools_help 完整 schema； 已删除 all:true（无全量出口，未解锁工具不进入视野）。 标准模式基底：native 直调（无 PTC/run_code 包装，SDK 全量段不存在，工具面注意力税大幅下降）。 页面验证内置：dev_page_check = 截图 + DOM smoke + console/pageerror/title/selector/scale； {js:…} 模式 = 本地 JS 引擎（零外部 node 依赖）；external 证据一等公民。 描述 ⇄ 行为对齐：presentation=native 自检、阶段文案只说真话、平台事实（win32 以 Git Bash 私有 shell seam 为准）。 主动性引导：Proactivity 常驻段（自检信号，不是停手命令）；压力感应器已退役。

配套预设：router-react（v17）/ router-spec（v10）（基于标准模式的两大执行预设，均支持首轮读图）； router-pro 线已退役删除。完整演进：见 CHANGELOG.md 与 docs/STANDARD-PLAN.md。 【历史文档 · v0.3 时代】 Task-aware reasoning-mode router for DeepSeek Harness. One preset, two routing modes (v0.2.0 naming), plus the measured three-band axis behind them: 选择：安装两个预设之一（Router Standard / Router Spec，见 Usage）。 dev_router_status 显示当前路由模式。 This is a research artifact. It encodes a measured property of DeepSeek V4 Pro / V4 Flash: model behavior along the persona axis is not a continuum — it collapses into a few stable regions separated by phase transitions. The router therefore quantizes to the stable regions instead of pretending the axis is continuously tunable. v0.3.0 — real-assembly-chain fixes

v0.2.x shipped routing logic that was validated against bare-API probes but was broken on the REAL DeepSeek Harness assembly chain. v0.3.0 fixes all of it, verified against @deepseek-ai/dsh-agent-loop (0.1.0-rc.7) event ordering: First-turn routing actually works (issue #13): the loop claims the inbox BEFORE assembling the system prompt, and inbox.claim() emits the agent-scoped agent/inbox/claimed event synchronously — the router captures the first REAL user message there (source.kind === 'user' only), so the first request is classified instead of unconditionally falling into weak. (The captured text is CLASSIFIED, not fed to bandOf raw — the old capture path silently mapped every captured message to the spec band.) Near-field guidance moved to agent/pre-step (issues #34/#36/#55): session/event never fires inside agent-plane presets (dsh-scope filters it out of entry-local realms), so the old inbox re-append never delivered guidance — and wherever it did fire, the next-step append forced a SECOND model request per user message (the 2× API-call spike). The guide is now inserted into decision.messages at agent/pre-step: same request as the user message

router-standard: reads the session's first REAL user message, classifies the task (build → react / fix → spec / ambiguous → weak), and on the first model request injects the matching persona while keeping the full prompt sections; the first-turn core tool surface follows the band (spec=read/edit/glob/grep, react=read/write/edit, weak=read/write/edit, each plus the platform shell). Weak-band sessions also get a n