liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
54 lines
10 KiB
XML
54 lines
10 KiB
XML
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 40 780 420" width="780" height="420" style="background:#ffffff">
|
|
<defs><marker id="ah" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#333333"/></marker><marker id="ah-light" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#999999"/></marker></defs>
|
|
|
|
<rect x="35" y="60" width="340" height="180" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="205" y="80" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">GUI 操作工具 (computer)</text>
|
|
<text x="47" y="98" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">鼠标:</text>
|
|
<text x="105" y="98" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">mouse_move · left/right/middle_click</text>
|
|
<text x="105" y="114" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">double/triple_click · left_click_drag</text>
|
|
<text x="105" y="130" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">left_mouse_down/up</text>
|
|
<text x="47" y="152" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">键盘:</text>
|
|
<text x="105" y="152" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">type (逐字符, 12ms间隔)</text>
|
|
<text x="105" y="168" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">key (组合键) · hold_key (长按)</text>
|
|
<text x="47" y="190" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">滚动:</text>
|
|
<text x="105" y="190" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">scroll 四方向 + 修饰键</text>
|
|
<rect x="400" y="60" width="345" height="100" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
|
|
<text x="572" y="80" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">感知动作</text>
|
|
<text x="412" y="98" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">截图:</text>
|
|
<text x="470" y="98" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">screenshot → 缩放到训练分辨率</text>
|
|
<text x="412" y="120" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">光标:</text>
|
|
<text x="470" y="120" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">cursor_position → (x, y)</text>
|
|
<text x="412" y="142" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">等待:</text>
|
|
<text x="470" y="142" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">wait → 等待界面稳定</text>
|
|
<rect x="400" y="175" width="345" height="65" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="572" y="195" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">命令执行 (bash)</text>
|
|
<text x="412" y="213" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">终端:</text>
|
|
<text x="470" y="213" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">持久 bash 会话 · 120s 超时</text>
|
|
<text x="470" y="229" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">哨兵字符串检测完成</text>
|
|
<rect x="35" y="255" width="340" height="65" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="205" y="275" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">文件编辑 (str_replace_editor)</text>
|
|
<text x="47" y="293" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">操作:</text>
|
|
<text x="105" y="293" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">view · create · str_replace</text>
|
|
<text x="105" y="309" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">insert · undo_edit</text>
|
|
<rect x="400" y="255" width="345" height="65" rx="4" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
|
<text x="572" y="275" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">坐标缩放机制</text>
|
|
<text x="572" y="295" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">实际分辨率 ↔ 训练分辨率 (XGA/WXGA/FWXGA)</text>
|
|
<text x="572" y="310" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">截图缩小 → 模型推理 → 坐标放大 → xdotool 执行</text>
|
|
<rect x="35" y="335" width="710" height="110" rx="4" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
|
<text x="390" y="357" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="20" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">典型执行流程：填写表单</text>
|
|
<text x="123" y="385" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">① screenshot</text>
|
|
<text x="123" y="403" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">截取当前页面</text>
|
|
<line x1="186" y1="391" x2="196" y2="391" stroke="#999999" stroke-width="2" marker-end="url(#ah-light)"/>
|
|
<text x="259" y="385" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">② 模型推理</text>
|
|
<text x="259" y="403" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">识别姓名框位置</text>
|
|
<line x1="322" y1="391" x2="332" y2="391" stroke="#999999" stroke-width="2" marker-end="url(#ah-light)"/>
|
|
<text x="387" y="385" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">③ mouse_move</text>
|
|
<text x="387" y="403" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">移动到 (324, 156)</text>
|
|
<line x1="458" y1="391" x2="468" y2="391" stroke="#999999" stroke-width="2" marker-end="url(#ah-light)"/>
|
|
<text x="531" y="385" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">④ left_click</text>
|
|
<text x="531" y="403" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">点击获取焦点</text>
|
|
<line x1="594" y1="391" x2="604" y2="391" stroke="#999999" stroke-width="2" marker-end="url(#ah-light)"/>
|
|
<text x="667" y="385" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">⑤ type</text>
|
|
<text x="667" y="403" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">"John Smith"</text>
|
|
<text x="390" y="430" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">每个动作间隔 2-5s（串行截图-识别-思考-点击），人类速度的 1/3 到 1/5</text>
|
|
</svg> |