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 operation tool (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">Mouse:</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">Keys:</text>
|
|
<text x="105" y="152" font-family="'Courier New', Courier, monospace" font-size="10" fill="#333333" text-anchor="start" dominant-baseline="central">type (character by character, 12ms interval)</text>
|
|
<text x="105" y="168" font-family="'Courier New', Courier, monospace" font-size="9.5" fill="#333333" text-anchor="start" dominant-baseline="central">key (combination key) · hold_key (long press)</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">Scroll:</text>
|
|
<text x="105" y="190" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">scroll 4 directions + modifier keys</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">Perception actions</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">Screen:</text>
|
|
<text x="470" y="98" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">screenshot → scale to training resolution</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">Cursor:</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">Wait:</text>
|
|
<text x="470" y="142" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">wait → wait for interface to stabilize</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">Command execution (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">Term:</text>
|
|
<text x="470" y="213" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">persistent bash session · 120s timeout</text>
|
|
<text x="470" y="229" font-family="'Courier New', Courier, monospace" font-size="11" fill="#333333" text-anchor="start" dominant-baseline="central">Sentinel string detection complete</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">File editing (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">Ops:</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">Coordinate scaling mechanism</text>
|
|
<text x="572" y="295" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">actual resolution ↔ training resolution (XGA/WXGA/FWXGA)</text>
|
|
<text x="572" y="310" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="9.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">screenshot shrink → model inference → coordinate enlarge → xdotool execute</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">Typical execution flow: fill form</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">Capture page</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 Model inference</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">Find name field</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">Move to (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">Click to get focus</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">Each action interval 2-5s (serial screenshot-recognize-think-click), 1/3 to 1/5 of human speed</text>
|
|
</svg> |
