autoglm-gui 1.4.1__py3-none-any.whl → 1.5.1__py3-none-any.whl

AutoGLM_GUI/static/assets/workflows-Du_de-dt.js

@@ -1 +0,0 @@
-import{c as D,u as S,r as t,l as b,j as e,B as r,d as W,a as F,b as T}from"./index-UYYauTly.js";import{P as E,L as f,C as L,a as P,b as z,c as H,T as I,D as q,d as B,e as M,f as _,g as j,I as O,h as R,i as A}from"./dialog-B3uW4T8V.js";const G=[["path",{d:"M12 3H5a2 2 0 0 0-2 2v14a2 2 0 0 0 2 2h14a2 2 0 0 0 2-2v-7",key:"1m0v6g"}],["path",{d:"M18.375 2.625a1 1 0 0 1 3 3l-9.013 9.014a2 2 0 0 1-.853.505l-2.873.84a.5.5 0 0 1-.62-.62l.84-2.873a2 2 0 0 1 .506-.852z",key:"ohrbg2"}]],J=D("square-pen",G);function U(){const s=S(),[m,g]=t.useState([]),[p,x]=t.useState(!0),[k,o]=t.useState(!1),[c,h]=t.useState(null),[l,i]=t.useState({name:"",text:""}),[w,u]=t.useState(!1);t.useEffect(()=>{d()},[]);const d=async()=>{try{x(!0);const a=await b();g(a.workflows)}catch(a){console.error("Failed to load workflows:",a)}finally{x(!1)}},v=()=>{h(null),i({name:"",text:""}),o(!0)},N=a=>{h(a),i({name:a.name,text:a.text}),o(!0)},C=async()=>{try{u(!0),c?await F(c.uuid,l):await T(l),o(!1),d()}catch(a){console.error("Failed to save workflow:",a)}finally{u(!1)}},y=async a=>{if(window.confirm(s.workflows.deleteConfirm))try{await W(a),d()}catch(n){console.error("Failed to delete workflow:",n)}};return e.jsxs("div",{className:"container mx-auto p-6 max-w-7xl",children:[e.jsxs("div",{className:"flex justify-between items-center mb-6",children:[e.jsx("h1",{className:"text-3xl font-bold",children:s.workflows.title}),e.jsxs(r,{onClick:v,children:[e.jsx(E,{className:"w-4 h-4 mr-2"}),s.workflows.createNew]})]}),p?e.jsx("div",{className:"flex justify-center items-center h-64",children:e.jsx(f,{className:"w-8 h-8 animate-spin text-slate-400"})}):m.length===0?e.jsx("div",{className:"text-center py-12",children:e.jsx("p",{className:"text-slate-500 dark:text-slate-400",children:s.workflows.empty})}):e.jsx("div",{className:"grid gap-4 md:grid-cols-2 lg:grid-cols-3",children:m.map(a=>e.jsxs(L,{className:"hover:shadow-md transition-shadow",children:[e.jsx(P,{children:e.jsx(z,{className:"text-lg",children:a.name})}),e.jsxs(H,{children:[e.jsx("p",{className:"text-sm text-slate-600 dark:text-slate-400 mb-4 line-clamp-3",children:a.text}),e.jsxs("div",{className:"flex gap-2",children:[e.jsxs(r,{variant:"outline",size:"sm",onClick:()=>N(a),children:[e.jsx(J,{className:"w-3 h-3 mr-1"}),s.common.edit]}),e.jsxs(r,{variant:"destructive",size:"sm",onClick:()=>y(a.uuid),children:[e.jsx(I,{className:"w-3 h-3 mr-1"}),s.common.delete]})]})]})]},a.uuid))}),e.jsx(q,{open:k,onOpenChange:o,children:e.jsxs(B,{className:"sm:max-w-[600px]",children:[e.jsx(M,{children:e.jsx(_,{children:c?s.workflows.edit:s.workflows.create})}),e.jsxs("div",{className:"space-y-4 py-4",children:[e.jsxs("div",{className:"space-y-2",children:[e.jsx(j,{htmlFor:"name",children:s.workflows.name}),e.jsx(O,{id:"name",value:l.name,onChange:a=>i(n=>({...n,name:a.target.value})),placeholder:s.workflows.namePlaceholder})]}),e.jsxs("div",{className:"space-y-2",children:[e.jsx(j,{htmlFor:"text",children:s.workflows.text}),e.jsx(R,{id:"text",value:l.text,onChange:a=>i(n=>({...n,text:a.target.value})),placeholder:s.workflows.textPlaceholder,rows:6,className:"resize-none !rounded-lg"})]})]}),e.jsxs(A,{children:[e.jsx(r,{variant:"outline",onClick:()=>o(!1),children:s.common.cancel}),e.jsx(r,{onClick:C,disabled:!l.name.trim()||!l.text.trim()||w,children:w?e.jsxs(e.Fragment,{children:[e.jsx(f,{className:"w-4 h-4 mr-2 animate-spin"}),s.common.loading]}):s.common.save})]})]})})]})}export{U as component};

autoglm_gui-1.4.1.dist-info/RECORD

@@ -1,117 +0,0 @@
-AutoGLM_GUI/__init__.py,sha256=ic002QIj6sw9cyhh7e_60DFIb7omtPcF01-L6M4lllM,2176
-AutoGLM_GUI/__main__.py,sha256=ygs0rleqyOdDOZBVc7eZoPOjrVmAwKptYjeWOwTtvMc,6251
-AutoGLM_GUI/config_manager.py,sha256=Jy10Ka5A-c7Hq94zc3nPUXjV6uqgXW2Dqhip4TG7yz4,23603
-AutoGLM_GUI/device_adapter.py,sha256=eA0bOlU-lzJig9cNCZrS0FqApEVbSOg7oke5P1iJ1rA,9011
-AutoGLM_GUI/device_manager.py,sha256=dAHP29a63H6GY43f715dOlJdwOz1eWa2XnPf2_SbIiY,26923
-AutoGLM_GUI/device_protocol.py,sha256=PyjCckBz8dtU6XUSqLy2epYbIsREoA4xcfOLktYEFNo,6919
-AutoGLM_GUI/exceptions.py,sha256=QXTQzxdbEHDUrtaD1G4zuKZydFJO5ymNvuo8ZvVjUdA,3487
-AutoGLM_GUI/logger.py,sha256=wLzjbRqsHAsOtI9yB0bcUZFVzgGK6qM8330std6FjVw,2553
-AutoGLM_GUI/metrics.py,sha256=L72hzMNzw1eemQLz6Hoth5sRW6OQlI4Np5BIFSFwl1c,8994
-AutoGLM_GUI/phone_agent_manager.py,sha256=6ySHfglvMqXv8lLPAKoTE59Mi_8NLWjlAJ63ejQx0Ms,32573
-AutoGLM_GUI/phone_agent_patches.py,sha256=xbuD7rBVPyCQ7wMb4MNW-cvSDIdtup7pJT_KvB88foM,4948
-AutoGLM_GUI/platform_utils.py,sha256=fAu_3rHYVlIpDxs09eCkJBUI5_qb2_cHu1si6FuuM1U,2448
-AutoGLM_GUI/prompts.py,sha256=lC5UktW0KRpWKij6T0GG1OrNKV9gAfM6dUcp_tjX7mo,4814
-AutoGLM_GUI/schemas.py,sha256=udgl1SY5c3EbklkSQKrLRu257Wf6w4IFC6S1MmN_mp0,17707
-AutoGLM_GUI/scrcpy_protocol.py,sha256=h6AtAGq3zMM30FWM7EYiYKJz7BDikpNCOjcKtFcRx3s,997
-AutoGLM_GUI/scrcpy_stream.py,sha256=LScxoEXDQu-Vn3TeG5y0fJ4Z66kMVOUdCkrgYq_tTlc,16913
-AutoGLM_GUI/server.py,sha256=Fo2Afl6CFT5B6MBggvR0n_savNxqxW22bFdN51NXRJs,299
-AutoGLM_GUI/socketio_server.py,sha256=ekEyyuIR1CwREDhDyGhIu8wxJ9S42Cemrf4fOdRxNKs,3826
-AutoGLM_GUI/state.py,sha256=qGnqZKdWFDpegVBLB4KHDbzfAVWc89C0AiCum_R9LSk,912
-AutoGLM_GUI/types.py,sha256=LEheZvDfeBrR2Hh_bEwRx3x_8qNDlEV7t8-9ymzzjFE,2532
-AutoGLM_GUI/version.py,sha256=z0MPXu-k9UO7RXxVGcAwim2M3yklrRqLwgOq66zSdzo,178
-AutoGLM_GUI/workflow_manager.py,sha256=AZ_zrhSeEvtlF1HTNMNS3f4qBwRuX-bzImdZEVZVXV8,5552
-AutoGLM_GUI/adb_plus/__init__.py,sha256=YwYYbeMrsKv8BGPcD6dv0PB8-wW93Ik9pMHo02i8QoU,945
-AutoGLM_GUI/adb_plus/device.py,sha256=nCMDUd18LPfl5CsJeDjKd9HSt6FFOy2jS1muOSeLO08,1683
-AutoGLM_GUI/adb_plus/ip.py,sha256=dt6ffIjiW_jGoEqUKUDi9fRGbWN1W9LxfT8rWIqgS-0,2200
-AutoGLM_GUI/adb_plus/keyboard_installer.py,sha256=dsQqLgWd2kkTeljdTTT77mFwJpcM-IJecMcJJEutbHo,13541
-AutoGLM_GUI/adb_plus/mdns.py,sha256=AwQ4MQsPKVW1tPjIUpOWvBQGlJxvVrO9eTvxoqsgPUo,5862
-AutoGLM_GUI/adb_plus/pair.py,sha256=3UElG0yjylhmZBtPpDER2BNMZs9CwDeavjuQOwOC4sw,1945
-AutoGLM_GUI/adb_plus/qr_pair.py,sha256=WHvx76q2xfTnJPXf5y_qI9cNuiBC_KeWwqYpuROdPkw,13571
-AutoGLM_GUI/adb_plus/screenshot.py,sha256=pr7BpmUcGZO9rthpDeMRn4D1oAGX9aEEVL3ZnTQzrIo,3211
-AutoGLM_GUI/adb_plus/serial.py,sha256=lDbBXTIoOJ5lbFj50K5X7PZnfpKt1vRpFiWVjolfEhQ,3142
-AutoGLM_GUI/adb_plus/touch.py,sha256=7cyMon9nOd6zQvZdHK7BHWoRLLWkdK-qWfTuSFfFzJA,2301
-AutoGLM_GUI/adb_plus/version.py,sha256=u5u1N40izJceeORN9kFhyz0wq_hZtlwBXaiytfA3px8,2428
-AutoGLM_GUI/agents/__init__.py,sha256=-LiMODXhqyXEcsMLOMGgnAhn8xIGokzWE4RyfZVcx_4,430
-AutoGLM_GUI/agents/factory.py,sha256=3_hmikWufNBHn-eg1rLAWqe9mPBYpzTBeNDADPOMoIY,4969
-AutoGLM_GUI/agents/mai_adapter.py,sha256=rUxw1LtHtKtfhLUDbQdbKWlsDMirNqAwBdpwH7wf2nY,21132
-AutoGLM_GUI/agents/protocols.py,sha256=3x3xutUZpF4BFXj0kwp8ZbGA39IIMSU9ymTtDnuoBfs,559
-AutoGLM_GUI/api/__init__.py,sha256=GtfuNa-G6SdeWD5_Zj99hvkXiKPYOZ3_YTysrtrGpSk,5420
-AutoGLM_GUI/api/agents.py,sha256=GtAwiakLxI3fAOaFmNfYerNw-QsUFmiIVb1INAWrJS8,20661
-AutoGLM_GUI/api/control.py,sha256=G-7hfdqTl5fq-UXOwE2CI_HMbfmRH1Vd589t2FTNZyY,3155
-AutoGLM_GUI/api/devices.py,sha256=Z_DAPrsPo9DhZSZl29yFGF_ml6obZNQDI-p4Co9oXGI,11088
-AutoGLM_GUI/api/dual_model.py,sha256=PYKM9pDcSWpRMwko0aBJ5M8ekkGd9c98YiMoPQ9Jg0k,10648
-AutoGLM_GUI/api/health.py,sha256=ZedFUv-IHst_YUyeQ_MpL5JXOKuOhWVlHBVwAY3MM0I,266
-AutoGLM_GUI/api/layered_agent.py,sha256=Ts8R5i11woTFHHHUlAOATb5xRVy3TY9MSwfte3iUsSI,26297
-AutoGLM_GUI/api/mcp.py,sha256=ppqzBxiS_8tUeJ5P8AszH_4m6q0sNe0oT2SCU_uISks,4625
-AutoGLM_GUI/api/media.py,sha256=Ioncwd68CNkYvqmeTJJ3P5I1rjWfw6PM4WPz5Ixx8vI,1631
-AutoGLM_GUI/api/metrics.py,sha256=2h5MnUiMTRAshD6nvcarLVoSlOjtlyVAGg-LRXq03vQ,941
-AutoGLM_GUI/api/version.py,sha256=DYiSNNykJsxOXO1zvf3w5AcAtQJTs2c-qtA1HRVihx0,6085
-AutoGLM_GUI/api/workflows.py,sha256=waYwlm2HxwkcfZwp7Bm2Z2l_bms6UmOy2xJEU9B_t0s,2431
-AutoGLM_GUI/devices/__init__.py,sha256=3RHDxS3feJ1jGdWbDKeOHSFUogmexcEr9lpcXWhlnjg,1471
-AutoGLM_GUI/devices/adb_device.py,sha256=9xOMQupSdtnr-wxJRcWhzfjisrwUNCrjxoi8LoMuweM,6406
-AutoGLM_GUI/devices/mock_device.py,sha256=Fnf9q-tjdqUZ-jKRf2cGbguAWAQhWr3qwVcFC4E4FCo,5700
-AutoGLM_GUI/devices/remote_device.py,sha256=x5MDsHwYj5YHR9KBPfjntJA8W8jpKoJwZ4vxslZFYUE,5566
-AutoGLM_GUI/dual_model/__init__.py,sha256=EQSMFAZ4NvZZywfnEJtDT9JrBJ4KuKWtGUHX4KcJIyY,1179
-AutoGLM_GUI/dual_model/decision_model.py,sha256=4UPTFikplV1GDnKEJNxNTMEXfgB2wjnstYL-yGXaI2g,21925
-AutoGLM_GUI/dual_model/dual_agent.py,sha256=HIw6Z5Ae9UH5-JEk9IPI2ry4uodvN-qdUQSIYrU0ecc,31574
-AutoGLM_GUI/dual_model/protocols.py,sha256=CZEqXUgsCoBeq7u1Ne43R031BjojGHvsZgvZqVn7Dh0,10534
-AutoGLM_GUI/dual_model/vision_model.py,sha256=Vaj-BVWVZpedUbAVr-dl-eXUQ2IHaQpo0P1AIBuTvdg,14440
-AutoGLM_GUI/mai_ui_adapter/agent_wrapper.py,sha256=6VZqsPlRHthjf0Q5tJzH7RqNc-zdrRryPnKPCyyJVkY,9322
-AutoGLM_GUI/static/favicon.ico,sha256=uB4wrcENiFaF-K4V-FzNp51XLW8GC4-ujpBDHgISfGM,781
-AutoGLM_GUI/static/index.html,sha256=8GRBiZjc-NI6PxboyyZ8QmZrGtGIrb2Y41tbWR3w8TE,761
-AutoGLM_GUI/static/logo-192.png,sha256=FOXgZxFrN0ZleO0VjlCnvD5cDkd1okJPkwPDZqsflNs,35243
-AutoGLM_GUI/static/logo-512.png,sha256=HlwSg09dQ3_Jtb09Ght4l2VK3YNLZlP_941LCdpDkWk,251598
-AutoGLM_GUI/static/assets/about-_XNhzQZX.js,sha256=SmhdB_v2cKcfR7bxET7KdyIAIR7-zR2aAAPrQl-OZgo,155
-AutoGLM_GUI/static/assets/chat-DwJpiAWf.js,sha256=YWM2KdefYkk3dvykyrhN1_kOt5p9aBPdDh2tL9Txs20,321638
-AutoGLM_GUI/static/assets/dialog-B3uW4T8V.js,sha256=ZVyV1aFhZSgX4eNo7QXs1EgPY7zxjnzIY1jLCH491A4,27378
-AutoGLM_GUI/static/assets/index-Cpv2gSF1.css,sha256=k7xMpqu3sXEnofUa3E6k2dI76d3lRRlBZbCBZml3Xos,80508
-AutoGLM_GUI/static/assets/index-Cy8TmmHV.js,sha256=BOHPeP6BPgHKbLar3Q357uWM_mkYSpHXpZrOsGkXijg,229
-AutoGLM_GUI/static/assets/index-UYYauTly.js,sha256=y0cmKh3RwdWH85mKmevbxyr9czFvIYGQLpdODbfOgwY,389521
-AutoGLM_GUI/static/assets/logo-Cyfm06Ym.png,sha256=6GRUFH2KNmB4ZmnrmJ1wxpoIYEmOW-__XlmKImyAMKM,4955675
-AutoGLM_GUI/static/assets/worker-D6BRitjy.js,sha256=RL1NIRIks9dXdDhXOHK1cCg-OELT0uv9a6u_UEHfQ0Q,173494
-AutoGLM_GUI/static/assets/workflows-Du_de-dt.js,sha256=f9FeE4WAt69qNniqvi5i71iU-PbkVxzpoCrTwNYxrys,3459
-phone_agent/__init__.py,sha256=7sCmGiY-ePdb6L08MGG6DkOiu8goop6wq-v2SiM62tE,360
-phone_agent/agent.py,sha256=1SgHpv70_XbujG1ElYRZbvRO5-d4l7gBgiFRBz_FIH8,8157
-phone_agent/agent_ios.py,sha256=R7EBsoHVghEUBtI5TB7M0_btpFcb4NHquMNxktrqrJE,9338
-phone_agent/device_factory.py,sha256=x_zsU2SNk4kh_OQafBoAfvH6nmMLCP-koqUUvcjNBhg,5027
-phone_agent/actions/__init__.py,sha256=YiAMeBMVhRfmDOf0hQ_1FEBSV5ApcnHPQ05gHjA_weQ,160
-phone_agent/actions/handler.py,sha256=QsRWS3RB_CQxdSmoNFNsmSe58j3__D0yDYB52mcmNN8,15640
-phone_agent/actions/handler_ios.py,sha256=YmK-QabWqCTHBemNJFGnEqDZO5Zhu05KBEvuyBNYLB8,10223
-phone_agent/adb/__init__.py,sha256=w3CBSGRv-cQPME-Q-Bx2tbL_WJkpb9RqmT2olNK9TZw,950
-phone_agent/adb/connection.py,sha256=Epmghk079HcDCqOYARIv8u1kb_oit1Y8rxRhBlqr0z0,10344
-phone_agent/adb/device.py,sha256=NRZAT9b8wT1wRJzV6176fMYxgmACkwyl0ASoEs3Id8g,6686
-phone_agent/adb/input.py,sha256=Yr-5oXcYITkPl8humom7k5eakS3OMVPilj-N0veeCQQ,2857
-phone_agent/adb/screenshot.py,sha256=FgPH6WgFBxU7JPgWpaCgQbltcm4LvhIoTmR5X5rm0yM,3161
-phone_agent/config/__init__.py,sha256=mtVL2HYW5r5UrGejCsTDefXTnLvpfxrJouvfqc2JaS8,1322
-phone_agent/config/apps.py,sha256=D9HcsGzqwJL3g1ZRS4_Iq4WjviijDDEtkBJlV4-TSjE,8774
-phone_agent/config/apps_harmonyos.py,sha256=z2QN6O7NPe87ta4EAPs6s4PAC74SPPXlXXz6fTkAXhY,10606
-phone_agent/config/apps_ios.py,sha256=CrOEDnPyG7T2qF_lS3SDlXjhbJPwDKI61_yOrggernc,11481
-phone_agent/config/i18n.py,sha256=-x8yD5ywyK7xwjoI-pOYqPlSeId_W9KkVjmKayr36m0,2501
-phone_agent/config/prompts.py,sha256=0XKS_LrXthPB_bAXUT3ezsyr7UlwJNR2i4FLdEuticQ,8444
-phone_agent/config/prompts_en.py,sha256=t8C9YLailtg8kVlFtYvq3t9EdtMGE8HastTfDh5BAUM,2630
-phone_agent/config/prompts_zh.py,sha256=oOd5wJz-_P9ZF3F8hIPPrwjXdgv0sIgH7aop94eOTKM,8603
-phone_agent/config/timing.py,sha256=bT-5HKGovzY_95wxRGIhmHyrIIPqhWivsXg-0LWc2pM,5793
-phone_agent/hdc/__init__.py,sha256=6Olk6ujXQovtzmRLXk5MIqbwffxleSQnoHYvCO4G1Ww,996
-phone_agent/hdc/connection.py,sha256=TweQ417wU2M35mgddK_Xt92zn5tZ0K7vtsaQjLn_e1o,11326
-phone_agent/hdc/device.py,sha256=-tOXttrO2oGNFWg5dIGDgEEwa_jfesFTzpgTQJqlYik,7598
-phone_agent/hdc/input.py,sha256=28TcK1FK1-4qpqbR3_vdjHc-l75en85EGI3rDpPy4rE,4901
-phone_agent/hdc/screenshot.py,sha256=sD21nGQidt9_S7nMXDZ3qMl8A2m7Q95nkwJD8vD-9Nc,4099
-phone_agent/model/__init__.py,sha256=w6yFkla9VoUvX5vZkTWa7Z5Bg5_lfA9AajrLjZsdL24,149
-phone_agent/model/client.py,sha256=vpkWoqJUETd4a9P2fQHJAMdhVDQoALyByb9bpTgDPfY,9707
-phone_agent/xctest/__init__.py,sha256=AKIwp6UfoaNdDvDveAp_v5h5UQPxU-PQTefMpfayzj0,881
-phone_agent/xctest/connection.py,sha256=m2lT9aNZgknDzItPoA7KOiFaDVOPqx4Imdhl6GcHx20,10833
-phone_agent/xctest/device.py,sha256=sOAPMoliMIabcrtsmzuGDKnZXtitqlc0lo8RSjQta7A,13655
-phone_agent/xctest/input.py,sha256=aMp1YCRGBtGsRMKhA9rrjxuLkri0_k3n6hisi0EBJ2o,8164
-phone_agent/xctest/screenshot.py,sha256=H6dsQGgf38h8dvuSeigiR2Qr8NucPanIgTK8kjlV9hA,6027
-mai_agent/base.py,sha256=hYjGQXe_qguYkGq2qVWVO_xzsLzNqayA-dox_usCCM0,4546
-mai_agent/mai_grounding_agent.py,sha256=d1X6giinaFVnTtKwh7oFktGZCkDjUySLb22toItykxM,8664
-mai_agent/mai_naivigation_agent.py,sha256=7oA_mjxHfUEYEz2-oLdCEIImNQvAK-V4ADIMCqPPM2s,18264
-mai_agent/prompt.py,sha256=Zgnj5JmVhCGjgM0sB-q19q0G76OCcNdffLypmwxRdl8,7111
-mai_agent/unified_memory.py,sha256=AqEux-0I2WUIQOaY_yCRi-MDuU1BuY6dEWgClQETnEk,2194
-mai_agent/utils.py,sha256=oJ50FEOM13-NwPHY4ttQ0tH49GS-w2TEy1_1FMCaxLg,2304
-scrcpy-server-v3.3.3,sha256=fnAyO6fyWWSd1KzOl6xP77roECssbZHi575hP9U1S-A,90164
-autoglm_gui-1.4.1.dist-info/METADATA,sha256=OCTjbmz6oXyvTATdzv7nuSF87wxvZnD3WHUDJhDKkK0,20387
-autoglm_gui-1.4.1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-autoglm_gui-1.4.1.dist-info/entry_points.txt,sha256=sz4rBO_kgrYmOiT0QnhCCv0b9QqBdWyCjugJgY8AEOI,58
-autoglm_gui-1.4.1.dist-info/licenses/LICENSE,sha256=0IkSHDewdtmXnmYzTNq4U47EJYjTuhjQNpT0bZKuqWc,11342
-autoglm_gui-1.4.1.dist-info/RECORD,,

mai_agent/base.py

@@ -1,137 +0,0 @@
-# Copyright (c) 2025, Alibaba Cloud and its affiliates;
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#    http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""Base agent class for mobile GUI automation agents."""
-
-from abc import ABC, abstractmethod
-from typing import Any, Dict, List, Tuple
-
-from unified_memory import TrajMemory
-
-
-class BaseAgent(ABC):
-    """
-    Abstract base class for all GUI automation agents.
-
-    This class provides common functionality for trajectory management
-    and defines the interface that all agents must implement.
-    """
-
-    def __init__(self) -> None:
-        """Initialize the base agent with empty trajectory memory."""
-        self.traj_memory = TrajMemory(
-            task_goal="",
-            task_id="",
-            steps=[],
-        )
-
-    @property
-    def thoughts(self) -> List[str]:
-        """Return list of thoughts from trajectory memory."""
-        return [step.thought if step.thought else "" for step in self.traj_memory.steps]
-
-    @property
-    def actions(self) -> List[Dict[str, Any]]:
-        """Return list of actions from trajectory memory."""
-        return [step.action for step in self.traj_memory.steps]
-
-    @property
-    def conclusions(self) -> List[str]:
-        """Return list of conclusions from trajectory memory."""
-        return [step.conclusion for step in self.traj_memory.steps]
-
-    @property
-    def observations(self) -> List[Dict[str, Any]]:
-        """Return list of observations from trajectory memory."""
-        return [
-            {
-                "screenshot": step.screenshot_bytes,
-                "accessibility_tree": step.accessibility_tree,
-            }
-            for step in self.traj_memory.steps
-        ]
-
-    @property
-    def history_images(self) -> List[bytes]:
-        """Return list of screenshot bytes from trajectory memory."""
-        return [step.screenshot_bytes for step in self.traj_memory.steps]
-
-    @property
-    def history_responses(self) -> List[str]:
-        """Return list of predictions from trajectory memory."""
-        return [step.prediction for step in self.traj_memory.steps]
-
-    @abstractmethod
-    def predict(
-        self,
-        instruction: str,
-        obs: Dict[str, Any],
-        **kwargs: Any,
-    ) -> Tuple[str, Dict[str, Any]]:
-        """
-        Predict the next action based on the current observation.
-
-        Args:
-            instruction: Task instruction/goal.
-            obs: Current observation containing screenshot and optional accessibility tree.
-            **kwargs: Additional keyword arguments.
-
-        Returns:
-            Tuple of (prediction_text, action_dict).
-        """
-        pass
-
-    def reset(self) -> None:
-        """Reset the trajectory memory for a new task."""
-        self.traj_memory = TrajMemory(
-            task_goal="",
-            task_id="",
-            steps=[],
-        )
-
-    def load_traj(self, traj_memory: TrajMemory) -> None:
-        """
-        Load trajectory from existing TrajMemory object.
-
-        Args:
-            traj_memory: TrajMemory object containing trajectory data.
-        """
-        self.traj_memory = traj_memory
-
-    def save_traj(self) -> Dict[str, Any]:
-        """
-        Save current trajectory to a dictionary format.
-
-        Returns:
-            Dictionary containing the trajectory data that can be serialized.
-        """
-        steps_data = []
-        for step in self.traj_memory.steps:
-            step_dict = {
-                "screenshot_bytes": step.screenshot_bytes,
-                "accessibility_tree": step.accessibility_tree,
-                "prediction": step.prediction,
-                "action": step.action,
-                "conclusion": step.conclusion,
-                "thought": step.thought,
-                "step_index": step.step_index,
-                "agent_type": step.agent_type,
-                "model_name": step.model_name,
-            }
-            steps_data.append(step_dict)
-
-        return {
-            "task_goal": self.traj_memory.task_goal,
-            "task_id": self.traj_memory.task_id,
-            "steps": steps_data,
-        }

mai_agent/mai_grounding_agent.py

@@ -1,263 +0,0 @@
-# Copyright (c) 2025, Alibaba Cloud and its affiliates;
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#    http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-"""
-MAI Grounding Agent - A GUI grounding agent for locating UI elements.
-
-This module provides the MAIGroundingAgent class that uses vision-language models
-to locate UI elements based on natural language instructions.
-"""
-
-import json
-import re
-from io import BytesIO
-from typing import Any, Dict, Optional, Tuple, Union
-
-from openai import OpenAI
-from PIL import Image
-
-from prompt import MAI_MOBILE_SYS_PROMPT_GROUNDING
-from utils import pil_to_base64
-
-
-# Constants
-SCALE_FACTOR = 999
-
-
-def parse_grounding_response(text: str) -> Dict[str, Any]:
-    """
-    Parse model output text containing grounding_think and answer tags.
-
-    Args:
-        text: Raw model output containing <grounding_think> and <answer> tags.
-
-    Returns:
-        Dictionary with keys:
-            - "thinking": The model's reasoning process
-            - "coordinate": Normalized [x, y] coordinate
-
-    Raises:
-        ValueError: If parsing fails or JSON is invalid.
-    """
-    text = text.strip()
-
-    result: Dict[str, Any] = {
-        "thinking": None,
-        "coordinate": None,
-    }
-
-    # Extract thinking content
-    think_pattern = r"<grounding_think>(.*?)</grounding_think>"
-    think_match = re.search(think_pattern, text, re.DOTALL)
-    if think_match:
-        result["thinking"] = think_match.group(1).strip()
-
-    # Extract answer content
-    answer_pattern = r"<answer>(.*?)</answer>"
-    answer_match = re.search(answer_pattern, text, re.DOTALL)
-    if answer_match:
-        answer_text = answer_match.group(1).strip()
-        try:
-            answer_json = json.loads(answer_text)
-            coordinates = answer_json.get("coordinate", [])
-            if len(coordinates) == 2:
-                # Normalize coordinates from SCALE_FACTOR range to [0, 1]
-                point_x = coordinates[0] / SCALE_FACTOR
-                point_y = coordinates[1] / SCALE_FACTOR
-                result["coordinate"] = [point_x, point_y]
-            else:
-                raise ValueError(
-                    f"Invalid coordinate format: expected 2 values, got {len(coordinates)}"
-                )
-        except json.JSONDecodeError as e:
-            raise ValueError(f"Invalid JSON in answer: {e}")
-
-    return result
-
-
-class MAIGroundingAgent:
-    """
-    GUI grounding agent using vision-language models.
-
-    This agent processes a screenshot and natural language instruction to
-    locate a specific UI element and return its coordinates.
-
-    Attributes:
-        llm_base_url: Base URL for the LLM API endpoint.
-        model_name: Name of the model to use for predictions.
-        runtime_conf: Configuration dictionary for runtime parameters.
-    """
-
-    def __init__(
-        self,
-        llm_base_url: str,
-        model_name: str,
-        runtime_conf: Optional[Dict[str, Any]] = None,
-    ):
-        """
-        Initialize the MAIGroundingAgent.
-
-        Args:
-            llm_base_url: Base URL for the LLM API endpoint.
-            model_name: Name of the model to use.
-            runtime_conf: Optional configuration dictionary with keys:
-                - max_pixels: Maximum pixels for image processing
-                - min_pixels: Minimum pixels for image processing
-                - temperature: Sampling temperature (default: 0.0)
-                - top_k: Top-k sampling parameter (default: -1)
-                - top_p: Top-p sampling parameter (default: 1.0)
-                - max_tokens: Maximum tokens in response (default: 2048)
-        """
-        # Set default configuration
-        default_conf = {
-            "temperature": 0.0,
-            "top_k": -1,
-            "top_p": 1.0,
-            "max_tokens": 2048,
-        }
-        self.runtime_conf = {**default_conf, **(runtime_conf or {})}
-
-        self.llm_base_url = llm_base_url
-        self.model_name = model_name
-        self.llm = OpenAI(
-            base_url=self.llm_base_url,
-            api_key="empty",
-        )
-
-        # Extract frequently used config values
-        self.temperature = self.runtime_conf["temperature"]
-        self.top_k = self.runtime_conf["top_k"]
-        self.top_p = self.runtime_conf["top_p"]
-        self.max_tokens = self.runtime_conf["max_tokens"]
-
-    @property
-    def system_prompt(self) -> str:
-        """Return the system prompt for grounding tasks."""
-        return MAI_MOBILE_SYS_PROMPT_GROUNDING
-
-    def _build_messages(
-        self,
-        instruction: str,
-        image: Image.Image,
-    ) -> list:
-        """
-        Build the message list for the LLM API call.
-
-        Args:
-            instruction: Grounding instruction from user.
-            image: PIL Image of the screenshot.
-            magic_prompt: Whether to use the magic prompt format.
-
-        Returns:
-            List of message dictionaries for the API.
-        """
-        encoded_string = pil_to_base64(image)
-
-        messages = [
-            {
-                "role": "system",
-                "content": [
-                    {
-                        "type": "text",
-                        "text": self.system_prompt,
-                    }
-                ],
-            }
-        ]
-
-        messages.append(
-            {
-                "role": "user",
-                "content": [
-                    {
-                        "type": "text",
-                        "text": instruction + "\n",
-                    },
-                    {
-                        "type": "image_url",
-                        "image_url": {"url": f"data:image/png;base64,{encoded_string}"},
-                    },
-                ],
-            }
-        )
-
-        return messages
-
-    def predict(
-        self,
-        instruction: str,
-        image: Union[Image.Image, bytes],
-        **kwargs: Any,
-    ) -> Tuple[str, Dict[str, Any]]:
-        """
-        Predict the coordinate of the UI element based on the instruction.
-
-        Args:
-            instruction: Grounding instruction describing the UI element to locate.
-            image: PIL Image or bytes of the screenshot.
-            **kwargs: Additional arguments (unused).
-
-        Returns:
-            Tuple of (prediction_text, result_dict) where:
-                - prediction_text: Raw model response or error message
-                - result_dict: Dictionary containing:
-                    - "thinking": Model's reasoning process
-                    - "coordinate": Normalized [x, y] coordinate
-        """
-        # Convert bytes to PIL Image if necessary
-        if isinstance(image, bytes):
-            image = Image.open(BytesIO(image))
-
-        if image.mode != "RGB":
-            image = image.convert("RGB")
-
-        # Build messages
-        messages = self._build_messages(instruction, image)
-
-        # Make API call with retry logic
-        max_retries = 3
-        prediction = None
-        result = None
-
-        for attempt in range(max_retries):
-            try:
-                response = self.llm.chat.completions.create(
-                    model=self.model_name,
-                    messages=messages,
-                    max_tokens=self.max_tokens,
-                    temperature=self.temperature,
-                    top_p=self.top_p,
-                    frequency_penalty=0.0,
-                    presence_penalty=0.0,
-                    extra_body={"repetition_penalty": 1.0, "top_k": self.top_k},
-                    seed=42,
-                )
-                prediction = response.choices[0].message.content.strip()
-                print(f"Raw response:\n{prediction}")
-
-                # Parse response
-                result = parse_grounding_response(prediction)
-                print(f"Parsed result:\n{result}")
-                break
-
-            except Exception as e:
-                print(f"Error on attempt {attempt + 1}: {e}")
-                prediction = None
-                result = None
-
-        # Return error if all retries failed
-        if prediction is None or result is None:
-            print("Max retry attempts reached, returning error flag.")
-            return "llm client error", {"thinking": None, "coordinate": None}
-
-        return prediction, result