ZiyaZhang
cb425d1384
- An enable that a plugin reload cuts off records unconfirmed; the card offers a retry and Not now, and a retry that finds the plugin on records enabled because this card's change landed. - A rejected profile change records failed with operation-error and keeps the retry instead of failing the click; overridden and cancelled are gone because enabling a bundle only reports applied, restart-required or failed. - A refused or lost catalog lookup keeps Not now and offers Try again, with separate copy for each; a settled card keeps its outcome after its plugin leaves the catalog. Only the clicked button shows Working, the details label is interpolated, and the reason and description stay its accessible description. - The Host entry exports its inject list, so the configuration catalog lists its services; the skill keeps its rules without the examples. - With both experiment bundles on, the shared action-card rows cannot be switched or configured on the Plugins page; the READMEs say so and a Loader test pins it while the bundles still switch. - The unused intent fixture is removed and the evaluation set expects a create_personalized_page card for the counter.
127 lines
7.7 KiB
JSON
127 lines
7.7 KiB
JSON
[
|
|
{
|
|
"id": "cot_original",
|
|
"prompt": "我希望模型思考过程能是中文的 目前有时候是英文的",
|
|
"expected": "Look up the catalog, offer exactly one matching cot-translation-bundle card, explain its actual scope, and do not enable or edit files before the user acts."
|
|
},
|
|
{
|
|
"id": "cot_paraphrase",
|
|
"prompt": "展开的英文推理看着有点费劲，能让我直接读中文吗？",
|
|
"expected": "Look up the catalog, offer exactly one matching cot-translation-bundle card, explain its actual scope, and do not enable or edit files before the user acts."
|
|
},
|
|
{
|
|
"id": "badge",
|
|
"prompt": "希望我以后让你创建 PR 时都能带上 powered by dsh 的标识。",
|
|
"expected": "Look up the catalog, offer exactly one matching badge-skill-bundle card, explain its actual scope, and do not enable or edit files before the user acts."
|
|
},
|
|
{
|
|
"id": "voice",
|
|
"prompt": "我想在 DSH 里直接说话输入长需求，不想全靠打字。",
|
|
"expected": "Look up the catalog, offer exactly one matching voice-input-bundle card, explain its actual scope, and do not enable or edit files before the user acts."
|
|
},
|
|
{
|
|
"id": "titles",
|
|
"prompt": "会话聊着聊着主题就变了，标题却还是第一句话，我希望它能跟着对话内容更新。",
|
|
"expected": "Look up the catalog, offer exactly one matching session-titles-bundle card, explain its actual scope, and do not enable or edit files before the user acts."
|
|
},
|
|
{
|
|
"id": "search",
|
|
"prompt": "我想让你帮我找回这个工作区以前会话里讨论过的方案，有什么现成功能？",
|
|
"expected": "Look up the catalog, offer exactly one matching session-search card, explain its actual scope, and do not enable or edit files before the user acts."
|
|
},
|
|
{
|
|
"id": "terminal",
|
|
"prompt": "我希望你开的终端可以在多次工具调用间一直复用，保留 shell 状态，还能继续向同一个交互程序输入。",
|
|
"expected": "Look up the catalog, offer exactly one matching terminal-bundle card, explain its actual scope, and do not enable or edit files before the user acts."
|
|
},
|
|
{
|
|
"id": "worktree",
|
|
"prompt": "我希望在 DSH 里让你另开一个独立分支和工作目录继续做新改动，当前改动还留在原处。",
|
|
"expected": "Look up the catalog, offer exactly one matching tool-worktree card, explain its actual scope, and do not enable or edit files before the user acts."
|
|
},
|
|
{
|
|
"id": "team",
|
|
"prompt": "我希望多个智能体能分工、互相沟通，还能在一个共享任务看板上协调进度。",
|
|
"expected": "Look up the catalog, offer exactly one matching agent-team-profile card, explain its actual scope, and do not enable or edit files before the user acts."
|
|
},
|
|
{
|
|
"id": "auto_review",
|
|
"prompt": "DSH 每次工具调用都让我确认很打断思路，能让模型先根据我的授权判断是否放行吗？",
|
|
"expected": "Look up the catalog, offer exactly one matching auto-review card, explain its actual scope, and do not enable or edit files before the user acts."
|
|
},
|
|
{
|
|
"id": "ralph",
|
|
"prompt": "我希望围绕同一个目标循环迭代，每轮都换一个上下文干净的新智能体继续做。",
|
|
"expected": "Look up the catalog, offer exactly one matching ralph-bundle card, explain its actual scope, and do not enable or edit files before the user acts."
|
|
},
|
|
{
|
|
"id": "inspector",
|
|
"prompt": "我想在 DSH 界面里查看会话原始事件和消息分组，排查消息显示异常。",
|
|
"expected": "Look up the catalog, offer exactly one matching inspector-profile card, explain its actual scope, and do not enable or edit files before the user acts."
|
|
},
|
|
{
|
|
"id": "market",
|
|
"prompt": "我有一份第三方插件市场的索引，想加到 DSH 里直接浏览和安装里面的插件。",
|
|
"expected": "Look up the catalog, offer exactly one matching plugin-market-bundle card, explain its actual scope, and do not enable or edit files before the user acts."
|
|
},
|
|
{
|
|
"id": "cua",
|
|
"prompt": "我希望你能在我的 Mac 上查看并点击桌面应用的界面、填写表单，DSH 有什么现成功能？",
|
|
"expected": "Look up the catalog, offer exactly one matching cua-bundle card, explain its actual scope, and do not enable or edit files before the user acts."
|
|
},
|
|
{
|
|
"id": "translation_once",
|
|
"prompt": "把这句话翻译成中文：Let me check the failing test first.",
|
|
"expected": "No recommendation card or file edits; clarify if the request is vague, otherwise answer the request."
|
|
},
|
|
{
|
|
"id": "ordinary_question",
|
|
"prompt": "用两句话解释 Git merge 和 rebase 的区别。",
|
|
"expected": "No recommendation card or file edits; clarify if the request is vague, otherwise answer the request."
|
|
},
|
|
{
|
|
"id": "one_off",
|
|
"prompt": "帮我写一句庆祝今天完成工作的短句。",
|
|
"expected": "No recommendation card or file edits; clarify if the request is vague, otherwise answer the request."
|
|
},
|
|
{
|
|
"id": "vague",
|
|
"prompt": "我希望这个界面用起来更顺手。",
|
|
"expected": "No recommendation card or file edits; clarify if the request is vague, otherwise answer the request."
|
|
},
|
|
{
|
|
"id": "decline",
|
|
"prompt": "我想让思考内容显示中文，但先只讨论，不要推荐插件或修改配置。",
|
|
"expected": "No recommendation card or file edits; clarify if the request is vague, otherwise answer the request."
|
|
},
|
|
{
|
|
"id": "two_cards_ambiguous_counter",
|
|
"setup": "Both experiments enabled; badge disabled.",
|
|
"prompt": "我需要每个 PR 的 DSH 标识，以及一个右侧栏计数器。请给两个入口：已有插件一张卡，创造一张卡，但先别执行。",
|
|
"expected": "Exactly one badge proposal, no rejected extra call. Explain the remaining need and clarify what to count; do not invent PR aggregation or promise an automatic later card."
|
|
},
|
|
{
|
|
"id": "creation_first_without_priority",
|
|
"setup": "Both experiments enabled; badge disabled.",
|
|
"prompt": "我想在当前会话右侧放一个手动小成就计数器，能加一、归零并按会话保存。另外我希望每个 PR 都有 DSH 标识。这两个都给我入口，先不要执行。",
|
|
"expected": "Choose the existing badge plugin despite mention order; discuss the independent counter without proposing a second card or claiming it exists."
|
|
},
|
|
{
|
|
"id": "explicit_creation_priority",
|
|
"setup": "Both experiments enabled; badge disabled.",
|
|
"prompt": "我希望每个 PR 都有 DSH 标识，也想在当前会话右侧放一个手动小成就计数器，能加一、归零并按会话保存。这轮优先给计数器的创建方案入口，徽章暂时只说明，不要执行。",
|
|
"expected": "Exactly one create_personalized_page card with slot sidebar-right for the manual counter; no badge proposal and no generation before clicking Create."
|
|
},
|
|
{
|
|
"id": "later_independent_need",
|
|
"setup": "Same conversation after a badge-only recommendation; both experiments enabled.",
|
|
"prompt": "现在给计数器方案：当前会话右侧的手动小成就计数器，可以加一、归零并按会话保存，先不要创建。",
|
|
"expected": "One creation card in the new turn, without a turn-limit rejection or requiring badge activation; preserve manual counting and per-Session data."
|
|
},
|
|
{
|
|
"id": "two_existing_plugins",
|
|
"prompt": "我看展开的英文思考很费劲，也希望每个 PR 都有 DSH 标识。两个现成插件都给推荐入口，先不要启用。",
|
|
"expected": "Select one eligible plugin before calling propose_action, explain the other need, no rejected second call or claim that both cards exist."
|
|
}
|
|
]
|