Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your strongest model for the hard parts.
Rust ai-agentsai-gatewayclaude-codecodexcoding-agentcost-optimizationdeepseekllm-gatewayllm-routerlocal-firstmodel-routingrusttask-routingtauri
---
import { posts, newsRoute } from '../lib/news.mjs';
import SiteLayout from '../layouts/SiteLayout.astro';
import { artifactUrl, formatBytes, latestRelease } from '../lib/releases.mjs';
const { language = 'zh' } = Astro.props;
const en = language === 'en';
const t = (zh, english) => en ? english : zh;
const path = en ? '/en/' : '/';
const alternatePath = en ? '/' : '/en/';
const featuredPost = posts[0];
const release = latestRelease('stable');
const preferredArtifact = release?.artifacts.find(item => item.kind === 'desktop' && item.platform === 'macOS' && item.architecture === 'arm64')
?? release?.artifacts.find(item => item.kind === 'desktop' && item.platform === 'macOS');
const windowsArtifact = release?.artifacts.find(item => item.kind === 'desktop' && item.platform === 'Windows');
const linuxArtifact = release?.artifacts.find(item => item.kind === 'standalone' && item.platform === 'Linux');
const releaseKinds = [preferredArtifact && t('macOS 桌面应用', 'macOS Desktop'), windowsArtifact && t('Windows 桌面应用', 'Windows Desktop'), linuxArtifact && t('Linux 无界面版', 'Linux headless')].filter(Boolean).join(' / ');
---
<SiteLayout language={language}
title={t('HiRoute · 长程 Agent 智能路由引擎', 'HiRoute · Intelligent routing for long-horizon agents')}
description={t('面向长程 Agent 的智能路由。连接决策模型,按任务类别与处理程度选择模型,并保留阶段执行证据。', 'Intelligent routing for long-horizon agents. Connect decision models, match models to task categories and difficulty, and retain stage execution evidence.')}
path={path} alternatePath={alternatePath} fullWidth>
<section class="hero wrap">
<div>
{featuredPost ? <a class="hero-article" href={newsRoute(featuredPost.slug, language)} title={featuredPost.title[language]}>
<span class="hero-article-label">{t('最新文章', 'Latest article')}</span>
<span class="hero-article-copy">{featuredPost.shortTitle?.[language] ?? featuredPost.title[language]}</span>
<span class="hero-article-arrow" aria-hidden="true">→</span>
</a> : <div class="eyebrow section-label">{t('面向长程 Agent 的智能路由', 'Intelligent routing for long-horizon agents.')}</div>}
<h1>{en ? <><span>Intelligent routing</span><span>for long-horizon agents.</span></> : <><span>为长程 Agent 而生的</span><span>智能路由引擎。</span></>}</h1>
<p class="intro">{t('一段长任务,不必始终依赖同一个模型。按任务选择 Agent,再根据执行表现与后续工作的需要,决定继续使用还是切换模型。', 'A long task need not rely on one model from start to finish. Match the agent to the task, then choose the right model for each stage—guided by past performance and the work ahead.')}</p>
<a class="jev-callout" href="#how"><strong>{t('决策模型', 'Decision models')}</strong><span>{t('内置接入 · 判断任务,回看表现', 'Built-in connections · Judge the task, assess prior work')}</span><span aria-hidden="true">↗</span></a>
<div class="actions"><a class="button" href={en ? '/en/download/' : '/download/'}>{t('下载 HiRoute', 'Download HiRoute')} <span>↗</span></a><a class="button outline" href="#boundaries">{t('了解路由机制', 'Explore routing')} <span>↓</span></a><a class="button outline" href="#tour">{t('观看介绍', 'Watch the tour')} <span>▶</span></a></div>
<p class="small-note">{t('开发、研究、分析与自动化。保留惯用工作流,按需投入算力。', 'Code, research, analysis, and automation. Keep your workflow and spend compute where it counts.')}</p>
</div>
<div class="journey-art" aria-label={t('一个长任务中的模型路由示意', 'Model routing across one long task')}>
<div class="journey-goal"><span>{t('长程任务 · 阶段式模型路由', 'LONG-HORIZON TASKS · STAGE-BASED MODEL ROUTING')}</span><strong>{t('任务持续推进,模型按需选择。', 'One ongoing task. Model choices that adapt.')}</strong></div>
<div class="journey-stage economy"><span class="journey-dot"></span><div><small>{t('阶段 01 · 明确、局部的工作', 'STAGE 01 · BOUNDED WORK')}</small><h3>{t('常规模型,持续推进', 'Regular model, steady progress')}</h3><p>{t('理解问题 → 调用工具 → 验证结果', 'Understand → Use tools → Verify')}</p><div class="prefix-bars" aria-hidden="true"><i></i><i></i><i></i><i></i><i></i><i></i><i></i></div><span class="journey-cache">{t('阶段内尽量复用 KV Cache', 'Favor KV Cache reuse within the stage')}</span></div></div>
<a class="journey-pivot" href="#how"><span>↻</span><div><strong>{t('新用户请求 · 重新判断', 'New user turn · Reassess')}</strong><small>{t('回看执行表现,判断后续工作', 'Assess past performance and the work ahead')}</small></div><b>↗</b></a>
<div class="journey-stage primary"><span class="journey-dot"></span><div><small>{t('阶段 02 · 更深入的推理', 'STAGE 02 · DEEPER REASONING')}</small><h3>{t('主力模型,接续完成', 'Primary model, take it further')}</h3><p>{t('分析难点 → 完成实现 → 检查交付', 'Reason → Implement → Check the result')}</p><div class="prefix-bars" aria-hidden="true"><i></i><i></i><i></i><i></i></div><span class="journey-cache">{t('切换后建立新的 KV Cache', 'Build a new KV Cache after switching')}</span></div></div>
<p class="journey-footnote">{t('机制示例 · 重新判断也可以继续原模型', 'Illustration · Reassessment can also keep the same model')}</p>
</div>
</section>
<div class="trust-line wrap"><span><b>{t('更省', 'Efficient')}</b> · {t('按需投入算力', 'Compute where it counts')}</span><span><b>{t('更稳', 'Reliable')}</b> · {t('有边界地接力', 'Bounded failover')}</span><span><b>{t('更懂', 'Adaptive')}</b> · {t('用执行事实改进选择', 'Decisions grounded in execution')}</span></div>
<section class="section wrap tour-section" id="tour">
<div class="section-title"><div><div class="eyebrow section-label">{t('产品介绍', 'Product tour')}</div><h2>{t('一分钟了解 HiRoute', 'HiRoute in one minute')}</h2></div><p>{t('从接入模型与 Agent,到按阶段选择模型、守住质量和查看执行证据。', 'From connecting models and agents to stage-based model choice, quality guards, and execution evidence.')}</p></div>
<figure class="product-shot tour-video"><video controls playsinline preload="none" poster={`/media/hiroute-promo-${en ? 'en' : 'zh'}-poster.jpg`} aria-label={t('HiRoute 一分钟产品介绍视频', 'HiRoute one-minute product tour video')}><source src={`/media/hiroute-promo-${en ? 'en' : 'zh'}.mp4`} type="video/mp4"></video></figure>
<p class="caption">{t('真实桌面端界面 · 演示数据,非模型评测。', 'Real desktop UI · Demo data, not a model benchmark.')}</p>
</section>
<section class="section wrap lifecycle-section" id="boundaries">
<div class="section-title"><div><div class="eyebrow section-label">{t('长任务持续推进,判断有明确边界', 'Keep long tasks moving with clear decision boundaries')}</div><h2>{t('阶段内保持稳定,', 'Stay stable within a stage.')}<br>{t('新一轮重新判断。', 'Judge each new turn.')}</h2></div><p>{t('新用户请求重新判断任务与模型组,同轮工具续接沿用冻结决策。模型可以持续完成工具往返,再根据新的工作需要和适用的阶段评分选择。', 'A new user turn gets a fresh task and model-group decision. Tool continuations inherit that turn’s frozen decision, letting the model work through tool round-trips before judging new work and applicable stage evidence.')}</p></div>
<div class="timeline-legend"><span class="legend-economy">{t('常规模型', 'Regular model')}</span><span class="legend-primary">{t('主力模型', 'Primary model')}</span><span>{t('选择节点查看接续方式 · 机制示例', 'Select a point to inspect how routing continues · Illustration')}</span></div>
<div class="timeline-grid">
<div class="turn-caption turn-one">{t('用户提出目标 → Agent 自主推进', 'User sets the goal → Agent works autonomously')}<span>{t('同一轮内,工具往返沿用已选决策', 'Tool round-trips inherit the decision within this turn')}</span></div>
<div class="turn-caption turn-two">{t('用户补充反馈 → 继续推进', 'User feedback → Continue')}<span>{t('新输入带来新的决策机会', 'New input creates another decision point')}</span></div>
<article class="execution-window first-window"><span class="eyebrow">{t('执行轮次 01', 'ROUTING TURN 01')}</span><h3>{t('常规模型 A', 'Regular model A')}</h3><p>{t('处理明确、局部的工作', 'Handles bounded, local work')}</p><div class="tool-steps"><span>{t('回答', 'Answer')}</span><i>→</i><span>{t('工具', 'Tools')}</span><i>→</i><span>{t('继续', 'Continue')}</span></div><div class="cache-ribbon cache-a"><b>{t('尽量复用 A 的 KV Cache', 'Reuse A’s KV Cache when available')}</b><span>{t('连续工具往返,保持模型稳定', 'Tool round-trips keep the model stable')}</span></div></article>
<button class="decision-boundary compact-boundary" type="button" data-boundary="continuation" aria-pressed="true" aria-controls="boundary-detail"><span class="boundary-symbol" aria-hidden="true">↻</span><strong>{t('工具返回', 'Tool continuation')}</strong><span class="boundary-status">{t('继承决策', 'KEEP DECISION')}</span><small>{t('沿用本轮判断', 'Keep this turn’s choice')}<br>{t('持续推进任务', 'Continue the task')}</small></button>
<article class="execution-window second-window"><span class="eyebrow">{t('轮次 01 · 工具续接', 'TURN 01 · CONTINUATION')}</span><h3>{t('继续使用模型 A', 'Continue with model A')}</h3><p>{t('示例:根据工具结果完成当前工作', 'Example: use tool results to finish the current work')}</p><div class="tool-steps"><span>{t('回答', 'Answer')}</span><i>→</i><span>{t('工具', 'Tools')}</span><i>→</i><span>{t('继续', 'Continue')}</span></div><div class="cache-ribbon cache-a"><b>{t('继续复用 A 的 KV Cache', 'Reuse A’s KV Cache when available')}</b><span>{t('同轮续接保持判断,继续复用上下文', 'Keep the decision and reuse the context')}</span></div></article>
<button class="decision-boundary human-boundary" type="button" data-boundary="human" aria-pressed="false" aria-controls="boundary-detail"><span class="boundary-symbol" aria-hidden="true">+</span><strong>{t('用户补充反馈', 'User feedback')}</strong><span class="boundary-status">{t('重新决策', 'DECIDE AGAIN')}</span><small>{t('新问题或新要求', 'New question or requirement')}<br>{t('也可以继续原模型', 'The same model may continue')}</small></button>
<article class="execution-window third-window"><span class="eyebrow">{t('执行轮次 02', 'ROUTING TURN 02')}</span><h3>{t('转交主力模型 B', 'Hand off to primary B')}</h3><p>{t('示例:新要求需要更深入的推理', 'Example: the new request needs deeper reasoning')}</p><div class="tool-steps"><span>{t('回答', 'Answer')}</span><i>→</i><span>{t('工具', 'Tools')}</span><i>→</i><span>{t('继续', 'Continue')}</span></div><div class="cache-ribbon cache-b"><b>{t('在 B 上建立 KV Cache', 'Build B’s KV Cache')}</b><span>{t('新一轮选定后,同轮继续保持', 'Keep the new decision through this turn')}</span></div></article>
</div>
<div class="boundary-detail" id="boundary-detail" aria-live="polite"><div><span class="detail-kicker" id="boundary-kicker">{t('同一轮中的工具续接', 'Tool continuation within one turn')}</span><h3 id="boundary-title">{t('工具返回后,继续本轮工作。', 'After a tool returns, continue this turn’s work.')}</h3><p id="boundary-copy">{t('工具结果仍属于当前任务,HiRoute 沿用本轮冻结的决策,优先使用同组内合格的当前模型,以便复用 KV Cache。候选故障可以按计划接力,工具返回本身不会重新判断任务。', 'Tool results still belong to the current task. HiRoute inherits this turn’s frozen decision and prefers the eligible current model within its group, helping reuse the KV Cache. Candidate failures may use bounded failover; a tool result itself does not trigger another judgment.')}</p></div><div class="boundary-outcome"><span>{t('这一节点的示例', 'At this point')}</span><p><b>{t('路由判断', 'Routing decision')}</b><span id="boundary-assessment">{t('沿用本轮已冻结的任务与模型组判断', 'Inherit this turn’s frozen task and model-group decision')}</span></p><p><b>{t('模型接续', 'Model execution')}</b><span id="boundary-choice">{t('示例中模型 A 继续处理工具结果', 'Model A continues with the tool results in this example')}</span></p></div></div>
</section>
<section class="night" id="how"><div class="section wrap jev-section">
<div class="jev-heading"><div><span class="jev-extension-label">{t('模型 → 决策模型', 'Models → Decision models')}</span><h2>{t('决策模型,一次判断。', 'Decision models. One call.')}<br><em>{t('回看表现,也看向下一步。', 'Look back. Choose what comes next.')}</em></h2></div><div><p class="explain">{t('连接百炼、OpenRouter Jev、TypeSafe 或兼容接入点。内置判断在一次请求中返回任务选择、程度概率与可选上一阶段评分,无需自行部署 Jev。', 'Connect Bailian, OpenRouter Jev, TypeSafe, or a compatible endpoint. Built-in judgment returns the task choice, degree probabilities, and optional prior-stage assessment in one call, with no self-hosted Jev service.')}</p><a class="text-link" href={en ? '/en/docs/decision-extensions/' : '/docs/decision-extensions/'}>{t('决策模型与路由机制', 'Decision models and routing mechanism')} ↗</a></div></div>
<p class="diagram-mobile-hint">{t('左右滑动查看完整机制图', 'Swipe to explore the full diagram')}</p><figure class="jev-diagram" tabindex="0" aria-label={t('决策模型与路由机制图,可横向滚动', 'Decision model and routing diagram, horizontally scrollable')}><img src={`/decision-assets/jev-decision-${en ? 'en' : 'zh-CN'}.svg`} alt={t('HiRoute 提供当前输入、执行历史与冻结条件;决策模型返回任务类别选择、程度概率和可选上一阶段胜任度;HiRoute 应用阈值,选择模型组并执行记录。', 'HiRoute supplies current input, history, and frozen criteria. The decision model returns a task-category choice, degree probabilities, and optional prior-stage competence. HiRoute applies thresholds, selects a model group, executes, and records.')} loading="lazy"></figure>
<div class="jev-modes"><article><span>{t('程度 · 寻找降本机会', 'DEGREE · FIND ROOM TO SAVE')}</span><h3>{t('接下来的任务,常规模型能做吗?', 'Can a regular model handle what comes next?')}</h3><p>{t('按难度分流只有一个任务范围,配置常规与主力模型组。HiRoute 应用本轮简单概率与阈值,达到门槛且没有适用低分时才用常规组,其余使用主力组。', 'Difficulty routing has one task scope with regular and primary groups. HiRoute uses this turn’s simple probability and your threshold: regular requires the threshold to be met with no applicable low score; otherwise it selects primary.')}</p></article><article><span>{t('胜任度 · 守住执行质量', 'COMPETENCE · PROTECT QUALITY')}</span><h3>{t('此前的表现,是否支持继续使用?', 'Does prior performance support continued use?')}</h3><p>{t('本次完整低分只有与当前类别、发布版本和评分标准匹配才触发主力保护。缺失或部分评分不当成零分,旧低分不跨轮锁定;每轮重新判断,也不自动回到常规组。', 'A complete low score applies only to the same category, published revision, and rubric. Missing or partial scores stay unrated. Old low scores do not lock future turns, and a new turn does not automatically return to regular: it is judged again.')}</p></article></div>
<div class="jev-bottom"><p>{t('自定义分支先分写稿、审稿等任务类别,再判断所选类别内的简单/复杂程度,使用常规或可选主力组。单组类别无需程度判断,写稿低分不会推动审稿升级。', 'Custom branches first distinguish categories such as drafting and review, then use the selected category’s simple/complex degree to choose regular or optional primary. Single-group categories need no degree judgment; a low drafting score does not upgrade review.')}</p><small>{t('HiRoute 负责阈值、选组与执行 · 决策模型负责判断与评分 · 自定义扩展可选', 'HiRoute owns thresholds, group selection, and execution · Decision models judge and assess · Custom extensions are optional')}</small></div>
</div></section>
<section class="section wrap" id="performance">
<div class="section-title"><div><div class="eyebrow section-label">{t('为下一次决策保留证据', 'Evidence for the next decision')}</div><h2>{t('不只知道选了谁,', 'See more than who was chosen.')}<br>{t('也看得见做得怎样。', 'See how the work went.')}</h2></div><p>{t('查看模型在具体任务中的阶段评分,结合执行记录与用户反馈,为下一次模型选择和任务委派提供依据。', 'Review model performance within a task, alongside execution records and user feedback, to inform the next model choice and task delegation.')}</p></div>
<figure class="product-shot"><img src={`/decision-assets/quality-native-${en ? 'en' : 'zh-CN'}.png`} alt={t('HiRoute 桌面端会话:阶段胜任度与模型路由', 'HiRoute desktop session: stage competence and model routing')} width="1200" height="1050" loading="lazy"></figure>
<p class="caption">{t('每个分数都对应具体执行阶段,可以继续查看决策依据与执行记录。', 'Each score is linked to an execution stage, with its routing decision and execution record available for review.')}</p>
<div class="proof-bottom"><article><h3>{t('分数始终带着范围', 'A score keeps its scope')}</h3><p>{t('评分属于具体计划、版本、模型和执行阶段;旧评分不会假装覆盖新增轮次。', 'A score belongs to a plan, revision, model, and execution stage; new turns are not silently covered by an older assessment.')}</p></article><article><h3>{t('证据可以帮助细分计划', 'Evidence can refine work plans')}</h3><p>{t('主 Agent 可查询高低分任务,结合证据判断是否需要建立更聚焦的工作场景。', 'A main agent can query high- and low-scoring tasks, inspect evidence, and propose a narrower work plan.')}</p></article></div>
</section>
<section class="section wrap" id="product"><div class="section-title"><div><div class="eyebrow section-label">{t('先选择任务路径,再配置算力', 'Route the task. Then the compute.')}</div><h2>{t('按任务选择 Agent,', 'Choose the agent for the task.')}<br>{t('按需要配置模型与算力。', 'Then configure models and compute.')}</h2></div><p>{t('面向开发、研究、复杂分析与通用自动化,不把产品定义绑定在某个 Agent 上。', 'Designed for coding, research, deep analysis, and general automation—not around one hard-coded agent.')}</p></div><div class="features">
<article class="feature"><span class="num">01—</span><h3>{t('按用途选择执行 Agent', 'Choose an agent by purpose')}</h3><p>{t('主 Agent 发现开放的工作计划,按目标委派任务并取得结果。任务委派与模型路由可独立启用。', 'A main agent discovers allowed work plans, delegates a goal, and retrieves the result. Delegation and model routing remain independent.')}</p></article>
<article class="feature"><span class="num">02—</span><h3>{t('按需要配置模型与算力', 'Configure models and compute')}</h3><p>{t('组合模型来源、思考档位和候选顺序;可以按难度分流、自定义任务分支、固定模型或免费优先。', 'Compose model sources, reasoning profiles, and ordered candidates; use difficulty routing, custom task branches, fixed, or free-first routing.')}</p></article>
<article class="feature"><span class="num">03—</span><h3>{t('让接力有边界', 'Keep failover bounded')}</h3><p>{t('候选满足工具、图像和上下文要求;候选耗尽时明确停止,开始交付后不透明换模。', 'Candidates satisfy tool, image, and context requirements; exhaustion stops explicitly and delivery is not silently switched.')}</p></article>
</div></section>
<section class="section wrap ecosystem-section" id="ecosystem">
<div class="section-title"><div><div class="eyebrow section-label">{t('Agent 生态', 'Agent ecosystem')}</div><h2>{t('不绑定一种 Agent,', 'Not tied to one agent.')}<br>{t('也不局限于编程。', 'Not limited to coding.')}</h2></div><p>{t('集成状态按真实支持范围开放;当前可用与规划方向明确分开。', 'Integration status follows real support; available and planned paths stay visibly separate.')}</p></div>
<div class="ecosystem-groups"><article><h3>{t('当前适配', 'Available now')}</h3><div class="agent-names"><span>Codex</span><span>Claude Code</span><span>Qoder</span><span>Pi</span><span>DeepSeek Harness</span></div></article><article class="ecosystem-planned"><h3>{t('后续方向', 'Planned')}</h3><div class="agent-names"><span>OpenCode</span><span>Hermes Agent</span><span>OpenClaw</span></div><p>{t('具体顺序按真实适配和验证推进。', 'Order depends on real integration and validation.')}</p></article></div>
</section>
<section class="section wrap extension-section" id="extensions">
<div><div class="eyebrow section-label">{t('自定义扩展 · 按需接入', 'Custom extensions · When you need them')}</div><h2>{t('把你的判断方式,', 'Your decision policy.')}<br>{t('接入 HiRoute。', 'One HiRoute interface.')}</h2><p>{t('需要自有模型或处理逻辑时,再部署自定义扩展。HiRoute 传入已发布的任务类别、可用模型组与安全历史;扩展直接返回类别和常规或主力组,可选上一阶段评分仅用于观察。HiRoute 保持模型选择与执行边界。', 'Deploy a custom extension for your own decision policy. HiRoute supplies published categories, available groups and safe history. The extension returns a category and regular or primary group; optional prior-stage scores are observation only. HiRoute retains model selection and execution.')}</p><a class="text-link" href={en ? '/en/docs/decision-api/' : '/docs/decision-api/'}>{t('自定义扩展 API', 'Custom extension API')} →</a><br><a class="text-link" href="/api/decision.openapi.json" download>{t('下载 OpenAPI', 'Download OpenAPI')} ↓</a></div>
<div class="code-box"><div class="code-heading">{t('自定义扩展 API / 首次响应示例', 'CUSTOM EXTENSION API / FIRST RESPONSE')}</div><pre><code><span class="accent">POST</span> /v1/decisions
{
"group": "regular"
}</code></pre><span class="muted">{t('按难度分流的首次决策 · 无历史评分目标,不返回 assessment', 'First difficulty-routing decision · No history target, so no assessment')}</span></div>
</section>
<section class="section wrap" id="start">
<div class="download-row"><div><div class="eyebrow section-label">{t('从 HiRoute 开始', 'Start with HiRoute')}</div><h2>{t('保留工作流,', 'Keep your workflow.')}<br>{t('重新安排算力。', 'Rearrange the compute.')}</h2><p>{release ? t(`稳定版本 ${release.version} 现已提供 ${releaseKinds}。`, `Stable ${release.version} is available for ${releaseKinds}.`) : t('公开版本正在准备中。macOS 使用桌面应用,Linux 可通过一条命令安装完整的无界面管理端。', 'The first public release is being prepared. Use Desktop on macOS or install the complete headless management surface on Linux with one command.')}</p><div class="actions"><a class="button" href={en ? '/en/download/' : '/download/'}>{t('选择安装方式', 'Choose an install path')} ↗</a><a class="button outline" href={en ? '/en/docs/' : '/docs/'}>{t('阅读快速开始', 'Read the Quickstart')} ↗</a></div></div>
<div class="download-state">{release && linuxArtifact ? <><b>{t('Linux 无界面版', 'Linux headless')} · {release.version}</b><p>{linuxArtifact.architecture} · {formatBytes(linuxArtifact.size, language)}</p><code>curl -fsSL https://hiroute.ai/install.sh | sh</code><a class="text-link" href={en ? '/en/docs/install-linux/' : '/docs/install-linux/'}>{t('查看安装与启动步骤', 'Installation and startup')} →</a><span class="tag">SHA256 {linuxArtifact.sha256.slice(0, 12)}…</span></> : release && preferredArtifact ? <><b>HiRoute {release.version}</b><p>macOS {preferredArtifact.architecture} · {formatBytes(preferredArtifact.size, language)}</p><a class="button download-button" href={artifactUrl(release, preferredArtifact)}>{t('下载桌面应用', 'Download Desktop')}</a><span class="tag">{preferredArtifact.distribution === 'self-signed' ? t('自签名', 'SELF-SIGNED') : 'DEVELOPER ID'} · SHA256 {preferredArtifact.sha256.slice(0, 12)}…</span></> : <><b>{t('桌面应用 + 无界面版', 'Desktop + headless')}</b><p>{t('发布前先完成完整性检查、安装走查和发布审核。', 'Integrity checks, installation review, and release approval come first.')}</p><span class="tag">{t('准备中', 'IN PREPARATION')}</span></>}</div>
</div>
</section>
<section class="section wrap faq-section" id="faq"><div class="eyebrow section-label">{t('常见问题', 'Questions')}</div><h2>{t('常见问题', 'Frequently asked questions')}</h2>
<details><summary>{t('切换模型会影响 KV Cache 吗?', 'How does model switching affect KV Cache?')}</summary><p>{t('会。HiRoute 在同一轮正常的连续工具调用中沿用路由决策,并优先保持所选组内的当前模型,让增长中的前缀持续复用缓存。新用户消息会重新判断任务;若发生切换,首次请求可能损失旧缓存,后续连续调用则可以复用新缓存。', 'Yes. During normal consecutive tool calls in the same turn, HiRoute reuses the routing decision and prefers the current model within the selected group, preserving reuse of the growing prefix. A new user message triggers reassessment; a switch may lose the old cache on the first request, while later calls can reuse the new cache.')}</p><p>{t('上下文压缩或重建后,部分缓存本来就需要重建,这时重新选模的额外损失可能更小。HiRoute 通过保持连续执行减少不必要的缓存开销,最终比较包含缓存重建、路由判断和重试的整单成本。具体影响与 Astra × Qwen 实验测算见下文。', 'After compaction or a history rebuild, some cache entries already need rebuilding, so reassessment at that boundary may incur a smaller additional loss. HiRoute preserves continuous execution to reduce unnecessary cache overhead. Whole-task costs include rebuilding, routing decisions, and retries; the article below explains the effects and Astra × Qwen calculations.')}</p><p><a class="text-link" href={en ? '/en/news/routing-cache-cost/' : '/news/routing-cache-cost/'}>{t('阅读缓存影响与成本分析:Astra × Qwen 3.8 Flash', 'Read the cache and cost analysis: Astra × Qwen 3.8 Flash')} →</a></p></details>
<details><summary>{t('上下文压缩一定会重新选模吗?', 'Does context compaction always trigger a new model choice?')}</summary><p>{t('要看是否仍能识别为同轮续接、此前冻结决策是否可复用。能够继承时保持本轮决策;历史重建使续接关系或决策无法复用时才再次判断。重新判断也可以选择原模型,客户端无需单独上报压缩事件。', 'It depends on whether HiRoute can still recognize the same-turn continuation and reuse the frozen decision. A reusable continuation inherits that decision. If a history rebuild breaks continuity or the decision cannot be reused, HiRoute judges again. The new choice can keep the same model; clients need no separate compaction event.')}</p></details>
<details id="history-faq"><summary>{t('决策模型能看到哪些执行历史?', 'What execution history can a decision model see?')}</summary><p>{t('HiRoute 提供简化的 Agent 轮次历史:用户问题、接受的回答、工具名称与粗粒度状态。内部任务类别、模型组与执行身份由 HiRoute 绑定,不要求模型猜测。历史被裁剪、淘汰或重启后可能不完整;评分目标阶段的证据完整性单独判断,缺失或部分评分不会视为零分。', 'HiRoute supplies simplified Agent-turn history: user input, accepted output, tool names, and coarse outcomes. HiRoute binds internal task categories, groups, and execution identities itself. Trimming, eviction, or restart may leave history incomplete; completeness of the assessed stage is tracked separately. Missing or partial assessments are not zero scores.')}</p></details>
<details><summary>{t('一定要部署 Jev 吗?', 'Must I deploy Jev?')}</summary><p>{t('不需要。在模型 → 决策模型中连接百炼、OpenRouter Jev、TypeSafe 或兼容接入点,就能使用内置判断。按难度分流也支持启发式规则;需要自有处理逻辑时才选择自定义扩展。', 'No. Connect Bailian, OpenRouter Jev, TypeSafe, or a compatible endpoint in Models → Decision models to use built-in judgment. Difficulty routing also supports heuristic rules. Choose a custom extension when you need your own processing logic.')}</p></details>
<details><summary>{t('胜任度评分是不是成功率?', 'Is competence a success rate?')}</summary><p>{t('不是。它表达模型对具体执行阶段的胜任程度,必须结合计划、版本、评分覆盖范围和部分证据状态理解。', 'No. It represents competence for a specific execution stage and must be interpreted with plan, revision, assessment coverage, and partial-evidence state.')}</p></details>
</section>
<script is:inline src="/scripts/home.js" defer></script>
</SiteLayout>