interactions:
- request:
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '4851'
      content-type:
      - application/json
      host:
      - localhost:11434
    method: POST
    parsed_body:
      encoding_format: base64
      input:
      - |-
        Jakarta Election Campaigns Heat Up: Here's How to Understand the System
        As election day in Jakarta draws nearer, candidates are out in force using various strategies to woo voters and prepare to exercise their democratic rights. Citizens make their voices heard as the city vibrates with life. This coverage offers valuable insight into campaign activities while offering an in-depth guide for understanding electoral processes in Jakarta.
        Initial Launch of Candidates' Campaign Plans on September 1
        After September 1st, when campaign season officially kicked off, candidates have moved swiftly to engage their bases. Amira Bintang, an upstart candidate with extensive social activism experience and promising urban development and public transportation reform as key platforms of her candidacy speech in Jakarta; incumbent Rizal Harahap relies heavily on his track record and highlights all infrastructure projects completed during his term.
        Campaign Strategies: From Digital Battlegrounds to Door-toDoor Outreach
        Campaign strategies have taken an advanced turn as candidates leverage digital media to reach a wider audience. Hashtags, viral videos, targeted ads and targeted messaging can all play an influential role in changing public opinion with just a tweet or meme. At the grassroots level candidates engage in door-to-door campaigns personalized for individual voters in an attempt to connect.
      - |-
        Bintang's interactive app for gathering real-time feedback from citizens about daily commute challenges was applauded as an innovative form of civic engagement, while Harahap launched a series of webinars featuring experts discussing economic growth under his administration.
        Rallies and Persuasion
        Jakartan politicians know the power of an impassioned speech cannot be underrated, and candidates have been taking full advantage of its effectiveness at rallies. Rallies feature vibrant colors, banners and impassioned discourse in an attempt to win converts over. At one high-spirited rally on October 22, Bintang outlined her policy plans for improving education and healthcare to an appreciative crowd while Harahap's rallies often consist of shows of solidarity from various political allies united behind his plea for continuity and stability.
        Debates: Clashes Between Visions and Policies
      - |-
        Debates are one of the highlights of Jakarta election campaigns, allowing candidates to outline their platforms and discuss critical issues. On November 5th, citizens witnessed an exhilarating debate between candidates Bintang and Harahap over whether the city was prepared for digital transformation in public services; Bintang advocated an aggressive move toward smart city model while Harahap advocated a more measured approach so as not to alienate less tech-savvy residents.
        Voter Engagement: Making Every Vote Count
        Ensuring every eligible voter is engaged and informed remains an ongoing challenge for Jakartans. Civil society groups and independent bodies host workshops and publish voter guides to inform voters of their rights and choices, while an annual democracy festival such as that held on November 20 featured interactive exhibits on Jakarta's electoral history as well as mock voting booths for first-time voters.
        Campaign Financing: Transparency and Accountability
      - |-
        Campaign financing has always been a contentious topic in elections, and this election cycle is no exception. Bintang's campaign, funded largely through crowdfunders online supporters, stands in stark contrast with Harahap's sophisticated machine backed by both private donors and party funds. To protect democratic decision making processes from any
        undue influences on decision-making processes, Jakarta Election Commission mandated strict reporting and transparency measures during campaign financing decisions.
        Before Election Day: Submit Final Appeals Now
        As election day nears, candidates make their last appeals to voters. Bintang plans a visit through key neighborhoods while Harahap plans a final rally scheduled for late November. Both camps are honing their messaging and policy proposals while encouraging supporters to make an appearance at polling booths on November 8th.
        Polling Day: The Final Act of Campaign Activities
        On December 6th, voting booths across Jakarta will open their doors, signalling the culmination of weeks of intense campaigning. Voters will cast their vote and candidates await results that depend on how effective their strategies, speeches and outreach initiatives have been.
      - Jakarta's vibrant election campaign offers an insight into its flourishing democracy. As the city looks ahead to an
        exciting new chapter in its political history, electoral processes demonstrate the significance of people-power in
        shaping our collective futures.
      model: qwen3-embedding:4b
    uri: http://localhost:11434/v1/embeddings
  response:
    headers:
      content-type:
      - application/json
      transfer-encoding:
      - chunked
    parsed_body:
      data:
      - embedding: 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
        index: 0
        object: embedding
      - embedding: ceLHuSxXhrsozj+9uGinPEm1wrqjdhw8Z9mfPTXlvjude1Q67jq5vKKnbj2tVZu8PXOpO91ygzwgxIO8P1nSu4/5Fr3ID+k7sJoKPMeHi7sdU7s6CpnsPBNzrD1yQCg8qj3CPBaMebxuCcy8ncPKvQwydbyU1c28zk7nvLnGfb0dLQi9MgeLPPPwj7qW+Qc9FakDPXL70rpJWXE5CSE1PMqHQ7yLygw9Qu4PPDtEFrxB38w8a/aJPFYmCTwBs4u7GCPbvL906by+13M8wkMePF/bUb2Xd5m8jX6JuxYzPj36l/87qvbju9ytyDyee0S8pvpOPPvqiTxobvI6LiXcvKOMCbzqwY+7Gc/rvNLiDjw5pES68PWUPIIZmryxEV28syeVPJRoXrtLC748jqiJvPrTuruVcF47Ixj7PCHAwDzLXe67Sbs1PdQxODrfVHK8Xng2vJrLbrxFWeU8bHV5vMJczbwp41W6naaAPA2D/TwYbQ48CYw1PdEHSLuESGc8cYMUPJxHBb0cqsS8ft1YPOh1OzziZPG8+yaMPLM0mbtdrOU71Ky6vBtiSLt5Tl48bOmmO8176zwINKu6KMLhO4xcD7zKyOU7Mt4MvNBNwTvnGDm8c+sPPIer1rtiDgq9jkYRPFkLkzsOAgM8GFfEus+Ioby9nHo8VzCQuwvmzzsRLD495olruxznAjz4o2+8V/VBvLN6DLyR0MM87C6EPAxP0LoSKla8VLotPBM3wDxpQxc70wVKvGLeSzxIXxq8+OPovFaxNrwu5rO8PmmsOiYbEjwFoLm5SemEO+UB5rq8++Y7EZPCOznZt7pgoI48ODyvvHrjSDuhjjY72KdxOzpE4TzM+FY8o3NjvKKwxDzQsT68nDWSu4maPDryPaa8ob8au0ohZTz6LCc8TztmO1JUA7wxHWy8fvt4OrW3xDrl81G74iqZuuy03rzLVny9m8KOu3SXP70o1G48QCExvL8xnjshuwW8IjE+vPIfxDsFcqU89O4LPOJzZbxn/ui7A9IRPDt8+DyeYf45q4TnO9lsi7scOoc839DYOx0wEzkXBKg8zk/xu+YENr01bD28R8zQvMaIBrl8z348WHkBvKiOCTzUoSK9okFFvGY/OjwqC268wfeOu9fPeDvBMSk9120zvDT/ULtbL008BUULPU/lrzr8GW25mQ28vBKZSDzbgAm9KB1aPG2rYjwCTbY8tRdVOtFAgrz1uiY9zVHKOl0YNzy5VD+8jRrqPM30o7q+lbw6RwqGuoLezDwkGAi9gzBnvf+Ee7wfzQc8xom/PHEegDttray8JUOwPB8WwTsf/xg8CWWsvBpcKrtolyY8vvPPPFujKzpOIQK9IXdbu5Sz2rx7voW8sa0ZvFi8PjxIio88ukEaPdMot7tY1Q28jDxkO4Cc5LzQ6CI9tCHMOz4N0TsaUju6vRkBu9hhdjxEFeW5ENgkPBCGPb3oAYe8csI9u+lh3zu37Z08qCwavIWaAbvxPxS8tRepu6yROjwCh9u70ooNPZeOujv4P6u7djUEOv+LFDxFCpI86Snlu0goDrxHZiQ7hukePXULirsB7Cw8prVNOzTGC7xP2re81L0VvK5vTLx544E6DrrLvEgSqDxNqFU9UJZsvOdMYrv/Wt2810EdvcU2tbycyIw83lpTPIZVSLms2gA9dYdRvKkONTw1h9c886OqOy/VsLxtoIO86I8zvQm/PDzT2z68opN0uuBOdzwfO5I8/u8lPF78NbtbziY9WSzSPBENv7vXqby8bEX/u0V2gzrJvcO7T8NbvJrmZD0BSYK7tNrpvGA2JDnxrgm8/WInPXn4TrwddXk8zi2CPKf2pLxL9BI8v2WCvfg8AD2+3oy71V0cPFYyN70FHT2859p9u0l/UTy3iEU6BhOLO/s8YjxE0++8iA4bO17WRjpFj4c8REFNPMPrhjxl+Ra6n51yvMIBPjzsgAK9faNGu7IyEjzs/Ku7xAIjPdjzNrtFwaG7WoelO+wl4TwXZw+8Sf+1O+n8rDy6Huw8wSw1PQGCcrrMxPI8xKUAuxURyTwfUai8WRbmvOpQGLzdyJO80wSIOjgMcb1qnWc8uG+XPGVF8rv3Jqk8WhxvPObtKDz7bbG8X88ovb77Q71ct7m8TJ4evcbV8zkFC+Q8tqTyu9UBlbuFyoA8ZdUPPDZkpTz1TdK7gTupuejFojxVloM8bnQjPGuFcrtNcuq6sUGpPC/Q67zVLHW7FySmu7dj3rvd3hO9g+rYO6XZnDwTzCU8tgFAvd7MFTymzKW6iBHcvGjpM7xuJFm8iOBmvSMKljzHC/y5c64jPSd6MTu6Iei7uPmYvAN2I71eei+7FTVCO+asvrwfgK47DL8DvdP+3TvR+gC95HWovFP7xDyruUQ9g8q1vN5CBLsIbee7Mnvzu2QnlDxgyww8R+MtPGFrQzzVhIq7SsFPvFocbzxw11g781E6vVLlkTyMFEO8NT/xvB/VpTsPeWm7P5ZIvKQjqbp+9UG7YP8pPOxwpjxRSBS96C9EOhUgfbyY8g88Hq8NvFzUMj2Gh6w70wRFvPIlvLx+bg+9EX3iuwcZVzy4x8Y5WJEbO8fbdLzq6aM8A/pKPC27gDyixIc8g5y/PKcFnryRMBC81dSkvD953Drgv1M8cw3BO056kzxxWxi9eyO9PLxc/brdol+8EhuUuzok+zuWh1U9Mt3TvIqCIb2vn6a4KYh9PG1ojDvrsRM9iPv5u+kjNLvcMgi9/gQqvBCSk7yNaqo7hgydvIO+Bb2a4B669PGuuwFpHb3lOSG9GfyXPHMJWjwUTFy8HNEMvNBBFjzipuu7jIXzOzlWAz1jtIy8w6B/OwLOFbzRplG9eoAvPVwmiztQwz+6r/E9vGhEBTvGevi6J8v3PILjQD21nt88kWpXvMrCITythR+8D+QHPXVP0jv+mnk8aggLvG1GHDtZAos6lHtaPMN73DtFhbw7yx/lO8p9OrwSUMo7899aPO8/4zzwecg8j/FyvCD9qjsEhy08j7/iPAQSVTzOexG8UrkxvMs2XT3+x9k7ABphPDAibLs1q+C8gD8lvPcl7Tt/19i8KtjnOwQkITsVbLQ8049wvGYGYL1k38K7qFdCvYaY2zyP6YQ8pk4LPX5pLrvS15G8AxfxOyn9xroBlcQ8bVvyPBbh0LxKwAE9lLS+PM89Y7zs97c8bQAEPAVQIjyuCm68nZqKO/HQIju9SkG6x0dGOmz0XTxlPHC8zG2yO4QSmDwtxs68mN+tPONulLvR9Rk8DdeevOUgIzv3Tta7iGsbvRSfSjtIQVw4lM1IvEWCFr2SFha9rkqzvMj3DLu2R8W7KT3RvNyhlbye6UG7K0QTvPA7Yz0iVae8mt8lvLue37yg85y8eR+jPIM0EjzgsIG6PTzKvNi8N7wydAE8JI1CPe9xdrx3QLs6AkW2vAXss7zvwj49R2E9Omu91jwm4WA7zYP9OxFcNDxOgpE7eNV7u9gAHj32uIA8rpO8vKdZ/Tw5PUs8auoAPT9umLyBc4K8ptoLPHIrab0dRTi8LvWJvOqhU7yc9Sk9O0uEPElUpLxfuku8RJ0ovNRYWTz8dSo9vTz+vLrk9TyTsvK7ld28uu93Cb0ot4q8rRB8uuW9TjwUN/E6iSNvPHR/Ar1kXbS70BOjvNCKK7uUV4s89OpRvEYFrrwEJA29Udr9u/8VyDzRc9A8SbBpvPRezruP+Bm9ob3su7mAqLvB/eM8dfxnPBUXJT1Bmg29D/cCvKuduzxdzx88M8abu4Y/nzyvur08rVfCvLbThbyueyA8JmaFvCuI7TwTUaa8t7xYPFgunzuVfGc8fI8NunYMwzxq0jE85vubO+j5zDrhwQO8eBG1PEXYIryp6au8KfOePGaomLqh/O48OsRXveHjizwpHfq8sxfdOwUp/bz0B7O8hQ2CvdmkrTwSSSy8FoYyOkYXCzyp5DG6R5VEPM0i/TwINcQ8nmo7O3+MHzxGs5G8AGkDuzm/nDwFPUY9v3H7u8nxczu+g3c8QioVPCmIHTz0M0C87aBLPPamXroxpvu5yPt5vFUAG73P22w7MhhKPCUZKrzDWM486/o4vTfPJj3P30e8lTxXvDXoXDyM6zy8pVYTPf2eqbvUxk288+/nvJpWBD05FDg8oG3fvAF49Tyi+FA7RoQwvUJhwLq7dB69LIaIvMDsE7x1mxU9cuemPCk/FjzJFzK8SFUdvBSQDzt/cI68zMoBO7sXkDyWhta8cyybPOWCi72nAUY9va1pvE2oH7xpe9E6NcK2Olwm27zZ/qo8t7xpPHkJi7xoqpc8vzCDvLVoDb0y6we9xpMhOnXFIr35yBg8DUL1vLLdrTwIvbw8/U8TvDXe9bs9qoc4wM6DvAdK7TkARQU89O8QvDzy1jyE/Za8AqYjvJxrxjsNDr67NRcVPQ5MJTw2FNE8ppmOvIZhEDzI0668swc7vRzLe7y/T4G7/R3APEu9grza5Wa6eUsevUIJsTxFZwo8djpZvNPoDj0Esyw8YBrcu/HdTryCXhs9CpXBvNK6djycHBu8IdtYOkT+GT2YEy+8miMoPQfmWLwR9MG7rp6FvGEKSry9RRA8CHCqPH38gjeXbW+8hnaPvG12NLzngRS9wCEGPM9D3jwS93M7kwuUO4/nCruOkhk973fPu/DXTDwKP168CGLEPJ/HHz2xSi68uXtIPe3z2TyTG/G7cDBgPHSnATyfFAy7rq8ePLxUqbySiXM8c4Chu8W4PTzAbIM8bE/yPL/pF7x79sK8cW4ivBuD+jy6t4a952avPHP6Fz2jN568ZXNqvIDQDbw2eo67i0MfPDaKF7yaadM7oXyfvDOpt7xZ61c74u5SvLL8pjzW2CO9m3QPvUlGZDuHQ4U8p6tJPIJtqbpj9m67EqtmvBbCmbzJFe87AHeNPCe3VbyiF568cZtrvLCNtLy/oJc80+cCPPwQ/7usjew7PsYuvaiXA700sye63bgkPSdbrLy1TTs7+fP+vPThxLu5Z6a8aa1SPCQ4dDw0b0g8rLpxOwRzj7x57tS7SrfbORFZrDzBWx+8wtTPPCLlLLtRz5c7PzEUvXjwETlsfZK69hiFPNZgIT1PetM82cwAveTC0jyPono8W02GuxOOw7v6Dum8xUn4OpDLzDyl0MM8IUBNurh0XbxQ8YI6AOEXPEiVBLw+HfS7MGUmvFFvOTsc+Lg8WQwAPSsxmzx5yMe7FWx/PMZ/77uh6w87udPovAKN2LwuQEi8ToekOiW2JTvKGJy8tPvVvIQ/O7unELe7FLjnPMcm4jyzcf880JibvG0Gjbtb9Z884Km0OhddnbzYOAM8uw2Pu9asebxh2pe8I2btOwBE7buxs6m8CGNIPUquuDycJhg80e+Euh17iDueW6q7ycX5u6IK5bv3Cq088nRVvAVYQLtTfs28f4SRuk+pebzoGOG89GRavCvyzbq0zsC8PZCrPHGDLjwWqCc9Iu4fu4NZg7yqjgq6xfc3veH9Rbx0xoY737KNvCTK3LymvEk8i5VDvXBPs7z1i1E71WRZOxDtFj2in/u8piy3u0wZdrz71iw78cuFvBDw8rybYYY7FOXSvFgtary8/Hw8boEOPZ4xpjwPNiS9K0p0vPOUfrwIMhc8Ch+DvHlM7rrAzki8YfcGPYNQk7z1/la9upmxO/plDbzHDdm8IbVPvNQ0VL2DG4q8Aaq6vIVzsTwAHxG8mLUHPPvzZjzCINU7JQFbvCs3ZryV3B29rNeWvOq16bpNOz68EJVOPHS50DwR0fO8ovMMO0/wKbyV3GA8sZn+O9yoQDziyIY5WciJvF/ZoTs6vf48xrjCvErfJb2t7No7TNc8O3pLiTyEMIq8lUrKvDVAL72Uqfe5JB+8u41iiLzrj6C7HWT7PBTupTpQP+s6hwOJO//MD73FQkC8slfBuzS7+bz8Hia8YrWGvPPbGzxDvwC87RrOvGplrrrdYAU7OWHlvPxql7zNof48MPozPYSVobxpnhc9fyGMO6kHjTwXd248lfIRPF0dljsBMDS8xG8yvHUNaj05zlI8vnMKPVK10rxAQCC7JYY3PKfl6TyQnQS8NR7NvMCZVLzdOME7WrSlOzNHRLxLXJg8kyZdPMmRk7y2hwQ8rabdulWxUrsyTHM8NN7pPIFeKTxKce48gfKtPDihNr2eMAI8CBngO9iYyzwU8iA9J9EDvTP+uruCHwe65sr0PDYHhjz8dYi7vrjDvEEVijnL+bk8P2EEOzeR+zshvJO7z1givL91nbxWVuu8pPouPXqFTjy6P5O8KLu2vHk/5zvovOi7RW4tO31nbzvcv786i/aVu/0aQ704eg89zX2QPPWpsrtJomU8d6GsO2xDZbwBAKa7ABuvPF0Qm7wGTtm8ZznvPE2U3LyuB408UlANPAk1PLwbv2m85ONrvNw00juljNG8FJ9XPTdrDj1Fh/k78LYHPIe7Fj3rnAq6TQtcvPTGkjxTbHq8LgA7vJxoNDyQvQo8ysnnPGc3u7zjn8a6v2k/vEU6pLyEM0k7BZr1PIU1Srxvzbq8XDuGOUmJtLzLEQy9wAOHPLkug7zm86c8hdOoPBS7J70LQgm83+E5vAKFND1BNAc9vTBJvOr/BjtZgvI6oktMO5SDubvmuJg89nQXPOYmML0B2hM8tlvhu09WdbwVspS8zZFKvDk+gLyoqag866wavSqdWjtv4Yk8KxqAPNZ6tbwTp8K6CJPiO4UbC70fzWI80ic8PfznhrsEAUQ8OCPPvG82hrz/b7m7wm6FOiH/mDxAr6M8rH6kPGnnMT1i3wq9lPG0PH9owTo0HHQ8keYOvGJAeDz1L7U69k6vPGrAxzra6eW8PGidvPgEDL3NB4o7l24CPGs4jjqAJCq8SzyluzIR/DsYXro7oIiLPCNmfTt+YBg9gFCwO4s2GjxR0ns78E1jvCgx0rs41VC86Xtdutq1Nj2f/Do82ooCPPmbobzEmnU6bRemPCEkODwGChQ63rwpPNyLATyXQAA8eBpfu2z1QbyCJ5U87oMCu5QcgTxN6ha8OgezvKqMQrxTRsm8BoJ3vJJ7W7wTNpk843t4vNjWTDyHjXo8l8/2vNk0Yrt3JYI7B3LHOFVCEztZTOI8r51dPMBYQrqR0Q47gz+rvJOmIjw5QXC8KDfVPBWLDj1E/hs8o7vmvOq6Hzy3Lk48L8BZujNNnbzkvXQ8foaHPEz/zbuFV7I8290JvGpptjzWQAM6FpKhPOnpbLx+4JS882a2PJ24SruLGAo8f8Qvu54lLD3o3s882ojDuuChUzx2GgA8v7xAPbS35Tx2c+47txhpPTUm/TzkpIC8PPHJPB8kSTyC4To6mRw4vIQjgzsc1ck8YKrcO6fc/TwaURQ86j+gvPBl+7ii35s7bliWPF/DEzp48xS8KkCwPLax17tJl0C85kSQPLAyrLxImFk76ro9vGIkRjyrVWE8yM5bu7ZHN7xQYY48bua/uz9SkTzjCbe75GtJuz5gczzv0do8b8wmverAsTsKUlu7QpcMvCQ/zjz036e880eMPDjCa7w1cyA8y8jkvAfp0rrqN6w8ZximPMrdGrzfTcc7n22BPK8ufjzHLSS8mMg0PBGIU7xzJ9K8YUB/vJm+1LtfSxG9htPiuYuhgzyEejA8Q0vTPCHsyDzbKZ+8nrXNu2/Ylrz7Z1w83V/mu8e7Lrw8azW8g79aPGzFAL1Ogwi8K8Anve4S5DuVspo7hF2BulDpIr0SAQe97zzzPIy4BD0d5JG8tYVqPClkyLwBSLg8tSW+uVGTurzkXai7850YPWE7vjzX6jC9ZjFOvSwdQ7xY3g+9Wd1YvGlWyrygsjM9VmKBPP+EAb0+cTK8COB/PPDDoLyzRtW8xZjUvIdZQjzSJsS7r57ou9hBFbz+urG895SvPO3wd7ukQ3I8u4PouwMApDzLs1W7i9CQvBJBRLwO4Bw8ePeLvJfzr7u46Da8PQmNO66aF7v6w0487VTYPDcDzbzF3Tk8X3iXPGT5uzxTorO89nqTPDSQGjztgf87/7eevBB6ZDz8grY7zw/yO3vasjwdSvm5CFFoOjKuN7uCsQk84A+du34pwzwlQBG8gLPYvFZd3TtKyhE8YsJQOgqBsLxWak48aY8eO9IV+DvI1rY7ptllOlycwLyrIn+8QS4NPcK0sbxTl8k8ThrYPK/C2TxBjH48cjedu4ZcW70HvS08u82BvL15gjsdEDs7G6divIXmJjuo7oc8eYXSuKOV7rzrw1y8kQM8vKTHlzxTVcO7AElKvUV6xLvGWEy7NOn5O5XoEj3ftjm7h7vOuyzZqjwTEv+83szluZgsET2H3lG8yd0mPHg8wzwYI4s75ZAnO5jDmbwKpYq86PkYvGoqLjw6Zq271TYLPaCnNzu8rve88frHPJPqPzq1wAI9+zffPLX7krzShkA755ieuw3CTrtPZu87KNsMu5nYOTwWwWu7yRSrO5RHjrws8hC8FY7QOvySgLwU8l265xfCO+LgFDzV/1m7ZSLYO2UXLLwazUI4maU5vNQHO7xtK1+80IEnO4gqUTvzJz28zFaVuSHidjzkH7O8sUspvJHS87wmVp+8yDbKvFhJlbwnDOo75S8XO+pEu7vw9lw802KQPFYWljuxYQO85otfPEMcILwgjV87SrUxvKcNDr0HSk67P024vAKh3jzCLL+8xtUhPHuOrLu229W8Jn0LuUY4b7zXfxI8quqTPA8cF7uyhG+8N44XuqxCRrxAcuk89wG7uYVCwjue+5887T2iPCks0zwK4Ai9RIfzOwKWETy1/to8Ys8OPB+f8zuwsa+794c4OymXeLwZEie8M/2NurMsg7tgYAK8+QidPO27iLygsLI7A0cGuzQaobzyeLQ7kQMGvZRrgTuixAa8wuRlvCF1nLzn6wk8hEzKO/GBKL1Mn7G7ei8mPFfM6rzB8zm8pHdrO/Q9VLwkEQw9NsAPPJ57nrwuTvO8Rl+3vEj92TzizuG8TY/KvGzs4DxNN6o7+katPPiALj00I8y7zZXeu+WwCDxT4Sq80lzevH7phTxTSSY71gStPLM9H7y/4gq8DffVukKKZTwZV9e8PbNBu+df7DxFBdQ7odJsOLnRgLxdMeO8/fsuudsBv7ypP087ykU+PMpXAjvfx3I8qnUXPFSzJzwsOQW93gEguoQzrrzvsp+8AjijPN29ibwwOYs7sYSQPK/+s7u1s788TIyLPLXgCzxMNZy8vzLROxuqiLx2SiQ9EJS7PLKbprocXRE91hjEPONxHTvP+T674eqUvEY+urwucz+8EVS6vCgZZDl3yoK61Pc2uolEG7uE5vo6OE41O1GxczzJXKw7pCknvdDuCzzJPOU8i+O7u3jpIz1ZLlM8ifyqu/1LAr02VtS7MqXxvDNa2bwZlZ089uTlOzVVCb2pbFM8SbWQu6u/HrywKhG8XRQMPRt6DTzcULg7c1uBPNRlNbx0M2k6o70dPO3pFbxVZNC8p9g+vWoDXjugPZk8bdrkO1NabrwyNq07Jf4uPIMNq7yLdpW72NlMPaoODbx4vxY7noWdO0piwTzinJK8pcgwPBpMnLxX2zM8GXinPG1Cobtm/vi8XyKWvFuccLw/Ie+8WQ68vMkgMjtfdQO9boJ3OmgIrbzXEg+8OFoYO+QgNjs9oIU8zLUTPH9S2TpHMMQ7r3oIPDwaVLy4eXk7qlAEvRYz1rvekRk9k/LBvIJhoTx581a8KYDZPM0PQb3kZZ48oIK7vLPpkbzu4Di9hSbpPN5Yf7u4C3i8DqGPvN6MAry5RUy8Z2covDDeRLyczU88Vtm2uzMgtbuAbJY8XVm7u2aGFT2Kork76i28vCICGzzZZFu7dXsXvC7sSDulVtO8usbvvLzcIbxjR7U89lw+vEivqTyi68Q8uoXqu9KVpLwYH0S6QcWwPO3U3jwYbHa8ztwjvG+SAjwenuU7VzVWvFNis7xln+q8KiEnvbeQH735R+K7ExaBu+56pztDnoU8enoFvPJwkDoW1CM8Hd7uPMHv1LwNGx09DCCivBhFHDv7pTk8/1SjOWomZrzuloA8XmsIvdjTE7xUgQo7wbtXvNFRJLy0NIa8dUbNvEB3Rz3gD0U8h+enPLmIsbyaaSa8aniavBfRXrzPs5S78Ms6vAkhHr2kDBU8nhFbO3564rmkkQE9ITqQPI40ZDtpk4m8A4fJPBUopTwzeSi7/6gMu3EKtLv4T5W8PQiVO/30w7rp1JQ7JIQqu5Ra+jvX9Bw8YC+BvLZEMLxvJBO5uEeMPGhvVzofz5I6gJLiu2bMLLxSMri843s4vP7gz7zYJyS7asSlPF13jbxPCLW8sL0ivWx9cjuALnm859rnvAQ44Lz1/yi7uB9XPL0EgjvxkhQ8f9+0OhWSzjtN3Ym8RoeKPIHsgjye3UU8TriwvHwigbz2GBk8fcA8ui7X37mEqiK8O8HgO7oRfbwL6DM8cs3ru3+4VzwNQx29WRGQPFRNbDxLxCE9VDq5u/EN/DzJ7wO9IHn2vIYaZjyPfCA8aupQO2oauzzIg4o8EFDtOsRDzruzYqq70HyTvEbrQrtLTAS9fwzDOwImNb2z7NK84RfWPLfMejwGKyI7qZHqOzWhqbxyUhS8XA0JvQwQCzwS0Ug7lgONPL7YpjxvQa28jy8aO7QhADxN9iq7GfC3vNXG0LwfTPu8CJkRPYcqm7w2HAK85KaIvF4FTjy9iZG8TnUIvcdCyLxYAY078qWxPPicozz4nMq870CKu9y4/juu76O89IeCvJ62B706iNa8aJ2svJWonDvvT8s8Jj+YvMwCLT3DMLc7CTNBvOx3hbxcyJu8/+eHu+pMO7vzsxa8WugVPG/eH7rJdnI7WaIGvapPK7zwKRY8dQjDvGCJpjxcg6S8galuOx6nMTzySra8s0jNPM2BZDwIOBS8L3ETPF7oirxQCfu7N/SSPMYJtzyVUgs9XnvdvPuvtLvjg4q9+XfsPPU/ILxqLCW8juBAOqEqH7wTZeQ8P3y0vAXLDrvYcje9qRACvVOzIzx3iEe8H+P/vBUzVDm/LHK6QKzLuxM98LvyIpC8KnuWvNd9C7zCeZk8qdH/usU+iroOLOA7M6ycvJAgTLxyUuA8CXaTvJegFDwkAsA8LQOHPONn8Tywqmw8JNEGvBNApTwDBYM4wm8qPPgL6jxAqqu87XjLvGJksrtPrwC93wXXO211Yrx/mWM8jlZQPLN3/bvwB9C86oPsPDtTBr3W8fO856CVvC/uLj1J69u8yIMBvSIw0ToFOTm8A+XmPBpMHLzl4wE7DgSKvHxs5Tui8KA6p6YDPIQGK72kkPw88VmavK3p6Lsxh1W8yyr9vIydVDz8/YK8VLVpPOvLhzxwVBi9+iJbu68yurk6J8C8ImecPEir4zwc1DW8Ytbhu+ugXbkJDFI4HeFUu3Ncczxk7CM7TU0au+6CHbyAqcu8Hwzlu3KJADuf/Ao9iYsKPfoCP7zcuZY7+2lsOZEeK7xE6aw8ILm3O4xlsjyov9s8XBIHPEzNAbpCCKu8sBW2vLbLpTyATQM80f0HvcM/3TubKRC7rk6LOhXdUrxp2Kc6aZpTO6XYgDwAKbi8FGnePHjlqrlsBUg7NsAtPMbpBTxev/+6h6aFOrQjuruPlM67ihUZvHE6Fj1VzzI9akTAvFVzo7xwf4E8Q9YGuobcr7xVHGk8a2uZPIETyrvGV/i7PlyWPDl0dbzI9vc7VoaivEl7+7u1PDi6XeteveQRTjslOqI82euZPOds07tPblK86JRPvEiQLr1p7sK8CICHOjL6ITvB2Re6PHHpOtS8Fjo0Y7k6VdFtukI6XjwhdAo80fNEvTDJejvlzpi8ef71uxqwkruFOMQ70Eh3OwNygjvQXw68CwvDu9NKw7x6CPc7k7gbvOAV8rvA80Q7OyGUPMsqWjyb0tO8sSsiO7mhjryjpTi7G41TPCyylLsIl9W8d4aePLC45jyXm6681UBuvLjV07xFA9q7ILGyOhrExbud7uu7WIEUO1EF7rtK2Dk9MvT/vLt7Ebuvu7U8Qm7SO6WL8Twp/2Y6/n8yvKcTrDykCs+73K0dO4Fa0ry3OJE8bWrLOqNE8jsO3Ek8R6UxPI1RAbt1jki8iKNqvGVZCDyCjjE8xYwvu0Tgj7z0q7c7pQ7kPNGZHryYd8O8aRBSPFV+BT003da7OZiCOCrrFDvgLjY9oDWTvDfmKT0+yKc7qlGwOpty0jqCJgS8Yv7ZvKCN1DzDr/e6i2P4PK7mozsj+9y83Mg1OvPDsrwpX6u8TQyVPOl94bwAwk47i80TvIlmWjxQKRK9zb2jO28R7buz7W88jGpGvTjYtTzW3MI8y1zUvDzL3rtMH507fSQ5PLoUlzpa+Lo8sWqCvJLNUrxVgxG77eSTvJ7xtDxs8pQ8LuOTvFePhjsvrbI8B47HuY8rwrw4M8K8jEgNvS5XizxEKwU9m2iaPLeSkbrfOVG8mjUWPMbuGbxO3wS8SIyBvPK7L7wcZpi8Ca04PBZLfTwHFvc6Yi57vCl2m7zksx29ggJEvKfxjDyVXg8521kivI53nbyK+bq8e4uePKZ2UzymH4w8YHh4O8f+vjmcCOU8w9Zwunq1IrytVb073cOtOnCWVrttq5e8FkBXOhszSDyRCg28Jh0yPL74hLs9W+A8yXjDPDrU5js17lA9w/i9Otx2fzzBfeU7KoMTvR+YD7tAyVO8YoB9PBj56Dzuxy+83d/Fu8Q7P7y3OKm8Ns0wu+Rdl7xl+vK81ouNvEybLjxiWw29bGwDuwPyxzsbWnO8q5l5O3E2TLxcr2K7VE2UvPW0Xry9dc274oGwuQ0DIbyGLoe7qnaSvC2397tntVm8CPDLu+C0jzx5/pg8Gi0JvBM6g7wwQIQ7CxPXvMVTBrwbRl87XJdfOpzTKbwkqgc8YtDwPMjOnjvGmQa97Z0EPQBwDzyD6lA8g9NnPIDTpDzFHp28Lh+bOxu9oDxs79u8+Pr5PKqapTy6SXu7nmkdPHV5PDxEK587hdcMvcwMfLxRThe7Ti/gOvlVjjy1/0Y8Jc3/Oscc1jxQOuG81P7Zu+e9HjzgWp68daUPuyzyEDwd1366htFDPCec6jy01u68AWDXvKF9LLzVEwY9pxADvIiOiLs9ruG72RHOuzHJwTv/LfI7txYAveVYQTzGXd28TnsIvSjXOD2H7546dIFrO0AvErxg4zQ7Cum1u4ra7bq6TEq8sabOPBWNPjxoya48oempvDJAGju/Psk8OEDXPP3FhDykfB26cmG+PDcApLzuFaq8EMvYu1xWurzFDWc8QQ88PGZT5bu1O/s7mg+2O/RikzljqHa8OXlnvAWpKj3P6547huQAPLkCFT3qSBG8XjHGPPzpiLxiJgS9/402PFOmxDsQddC7wSUJvDplDbsFcMM79b8jvObRjbzrvdq7N6//u5c6ajxF1M+8uX4eu6sUNboO36O8sVmzPJWD5jyzlQa9F+poOxG3CbyYYM267xDwOd0AJTyXcww9gtsYPMbJNzsxsji8WdpUPNV8R7y2ykI8SkjNO33RnTpS26y8T501PFQXmTtbTbK8kVTVvOV0IrwQwK+7TLcBPUyzFz0s3hQ8jh0zvOMF0ztj2J28+Q3VPA==
        index: 1
        object: embedding
      - embedding: 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
        index: 2
        object: embedding
      - embedding: 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
        index: 3
        object: embedding
      - embedding: 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
        index: 4
        object: embedding
      model: qwen3-embedding:4b
      object: list
      usage:
        prompt_tokens: 858
        total_tokens: 858
    status:
      code: 200
      message: OK
- request:
    body: !!binary |
      H4sIABExUGkC/61WzW/cRBRPSGnT2bRJXEJTSsXgCiktrbE3+xmEUCkHWFUqtAUJtZGZtce709hj
      4xkn3UZ7LAghLghxAK6UD6H2T+CKxI0DSKAKTgiJf4ALEm/8setsE9oDuWT8vuf3fu/Nop+X0Hcz
      qI2OCBpvMocajAtJuDq4mo5wu1W1Vk3PrJHVRq1K6m2LWq1u0202nIbltepIR49L6tOAynhgCHfD
      8AnvJaRHtVm0PxrIfsjRM0jbacNJQLV5dCiMKB9p0NNoaafZJo0FC7mKZBmrbcMCk7mi0DTGIppP
      +AYPt7idy9ERVIni0KFCGBHcYd/y3S9nwO+xQhgnXLIg9z+IDjh5kSfR0UmTUv5Vw1o1mugNdHzS
      yKXCiVkklWED1TJDvBIQxs/gyzTCVgtXzWr9DK5W1+rVtdXaKXz1vEIJxIZl1PA6egHNF9cqcp5G
      K/VWreaaTafuAvKm59atNjVbtXq1adVaTrtqEtdqeqSrfaShJbj1wCVQknOWMC3Dy9Q+fAQtTH9G
      Xvz2e+fmwksfkPdnbz+vzfZ+OnjhPT53XJ+9ePv1z/9Y+eHa6YPQMS4xXMqcbr/ybuOXL1ZuLZ8r
      Dp2jCAWhS327QK0XybOhEJ0lhFLPTHEAPZp+dZ5Ei/DfJsxIv42d2idQxQ97HoupEYieVkHj7J2T
      aLHQiYhwWw4iqh1Gc8AUl/GerYSd59CxwqiQRyRWZUDHNbRgTvzdnLo1PTU9NaX9Ob8bHh//9vWn
      b975+0d99tlPvrr3153m4uk5p08kzm8JkLx9of1rCklx6DyFlvIrAotjovqfXXM/2qecO8fQodxA
      DISkgaJR6PskIB2gY66K6TsJFdJI0S0DewIdVpSgsUFcNwbCKZj80CF+PxSyo6FKro7CWGozy9+8
      1fmngpazLuVRFShQkQRKab9X0L3Ktu4l3FGl2jIMfaGv4avbuqoaTrqgJHb6ths6SQBYCv0M1scR
      7OsC3ITTpwEB620d6mIqFPFfixUEklEV0CO+oMqzLNzWoaB4kJ5UR9N0MobG6UOw9VnAZKp0qUcS
      X5154vugInxw0cvqLBwZ7IwejZXnWKjM9eH6UIVT1wduuMotT7wO4sI07F6njkwTl4ZXaS6nCGDZ
      p1gtFZ+6PYq7RFDshTGOYTltwojhEULGNX6NX6IyibkAtYDKBd5iso+dPuwl/OrLAhPuFp4OxcIJ
      wc5QXh4FxoKo8OsOVGIWZ77AZMw4dpikrp1KhKEaEibQjHQqXNtljrQ36GCMlsLUkaUuCMUE2ArE
      Lwk3GFfYjMig4kKTiUskGcdS2w2y5YKhQrCbMF+yEnnWs4qiRNqKeSqo0uljcQ72KGou3oV+HgMq
      2RkaD6Dentya6OcVaGQ6CfAN4MJEbxHVEbFFFT1KnCiRMVPvFS7TYhmmLCmC7xGq3L3dAip+hF7W
      cIETQV0VGLgWpNHzSiAQxAnEXtNTiEgck0GWN+QecxW7JobKMsz7WX9+ZJ3RMyW77LMCKbxinrVO
      pSQhN1iQBKNAAeP5t5l+j4cx6KoB3WMYxyDvMpZK+R+bZZepPTdqCcHZDsNpnvIkxsW4/f9TlDH6
      oWcIuBtEihbFJNAg8omkpZXn++EWyG/I3KaUNNOxAB7MCeWws4GOFK9iaWC0K+jS9i4gT8zQXg/H
      DtIVm3M4fLh3+sTOhx7U5Wf1gc94zSMN+NHj0Ea15XTrTkcfvbmwJqKQC3rfw1k89f8C7zDDPdoK
      AAA=
    headers:
      accept:
      - '*/*'
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-encoding:
      - gzip
      content-length:
      - '1313'
      content-type:
      - application/x-protobuf
    method: POST
    uri: https://logfire-eu.pydantic.dev/v1/traces
  response:
    body:
      string: ''
    headers:
      connection:
      - keep-alive
      content-length:
      - '0'
      nel:
      - '{"report_to":"cf-nel","success_fraction":0.0,"max_age":604800}'
      report-to:
      - '{"group":"cf-nel","max_age":604800,"endpoints":[{"url":"https://a.nel.cloudflare.com/report/v4?s=DtsP84ckWWKajTvY7Wo4UrZQFQp6fgU0c2V1vEKaYDPbRb26xFqj9X1ivmrj%2FUShwi%2FQwenA9mOCZYuSoK6VgQzradVAdqyBeo3dLElDeNO141SF"}]}'
      vary:
      - origin, access-control-request-method, access-control-request-headers
    status:
      code: 200
      message: OK
- request:
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '2742'
      content-type:
      - application/json
      host:
      - localhost:11434
    method: POST
    parsed_body:
      messages:
      - content: |-
          You are a knowledgeable assistant that answers questions using a document knowledge base.

          Process:
          1. Call search_documents with relevant keywords from the question
          2. Review the results and their relevance scores
          3. If needed, perform follow-up searches with different keywords (max 3 total)
          4. Provide a concise answer based strictly on the retrieved content

          The search tool returns results like:
          [chunk_abc123] (score: 0.85)
          Source: "Document Title" > Section > Subsection
          Type: paragraph
          Content:
          The actual text content here...

          [chunk_def456] (score: 0.72)
          Source: "Another Document"
          Type: table
          Content:
          | Column 1 | Column 2 |
          ...

          Each result includes:
          - chunk_id in brackets and relevance score
          - Source: document title and section hierarchy (when available)
          - Type: content type like paragraph, table, code, list_item (when available)
          - Content: the actual text

          In your response, include the chunk IDs you used in cited_chunks.

          Guidelines:
          - Base answers strictly on retrieved content - do not use external knowledge
          - Use the Source and Type metadata to understand context
          - If multiple results are relevant, synthesize them coherently
          - If information is insufficient, say: "I cannot find enough information in the knowledge base to answer this question."
          - Be concise and direct - avoid elaboration unless asked
          - Higher scores indicate more relevant results
        role: system
      - content: What innovative form of civic engagement did Bintang introduce for gathering feedback from citizens during
          Jakarta's election?
        role: user
      model: gpt-oss
      reasoning_effort: high
      stream: false
      tool_choice: auto
      tools:
      - function:
          description: |-
            Search the knowledge base for relevant documents.

            Returns results with chunk IDs and relevance scores.
            Reference results by their chunk_id in cited_chunks.
          name: search_documents
          parameters:
            additionalProperties: false
            properties:
              limit:
                anyOf:
                - type: integer
                - type: 'null'
                default: null
              query:
                type: string
            required:
            - query
            type: object
        type: function
      - function:
          description: Answer to a search query with chunk references.
          name: final_result
          parameters:
            additionalProperties: false
            properties:
              answer:
                description: The answer to the question
                type: string
              cited_chunks:
                description: IDs of chunks used to form the answer
                items:
                  type: string
                type: array
              confidence:
                default: 1.0
                description: Confidence score for this answer (0-1)
                maximum: 1.0
                minimum: 0.0
                type: number
              query:
                description: The question that was answered
                type: string
            required:
            - query
            - answer
            type: object
        type: function
    uri: http://localhost:11434/v1/chat/completions
  response:
    headers:
      content-length:
      - '1272'
      content-type:
      - application/json
    parsed_body:
      choices:
      - finish_reason: tool_calls
        index: 0
        message:
          content: ''
          reasoning: |-
            We need to answer: "What innovative form of civic engagement did Bintang introduce for gathering feedback from citizens during Jakarta's election?" It's a specific question about Bintang, presumably Bintang, presumably "Bintang" might be a brand? Actually, Bintang is an Indonesian "Bintang" probably a local government official. Wait context: "Jakarta's election" - maybe referring to Jakarta's governor election, or maybe a local Jakarta election? Bintang might refer to "Bintang" (meaning "star") or a name? Probably Bintang is a person, maybe a citizen or activist, or a platform called Bintang? Let's search.

            Use keywords: "Bintang innovative form civic engagement gathering feedback citizens Jakarta election"
          role: assistant
          tool_calls:
          - function:
              arguments: '{"limit":10,"query":"Bintang innovative form civic engagement gathering feedback citizens Jakarta
                election"}'
              name: search_documents
            id: call_uw8bfctv
            index: 0
            type: function
      created: 1766863128
      id: chatcmpl-847
      model: gpt-oss
      object: chat.completion
      system_fingerprint: fp_ollama
      usage:
        completion_tokens: 188
        prompt_tokens: 548
        total_tokens: 736
    status:
      code: 200
      message: OK
- request:
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '155'
      content-type:
      - application/json
      host:
      - localhost:11434
    method: POST
    parsed_body:
      encoding_format: base64
      input:
      - Bintang innovative form civic engagement gathering feedback citizens Jakarta election
      model: qwen3-embedding:4b
    uri: http://localhost:11434/v1/embeddings
  response:
    headers:
      content-type:
      - application/json
      transfer-encoding:
      - chunked
    parsed_body:
      data:
      - embedding: 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
        index: 0
        object: embedding
      model: qwen3-embedding:4b
      object: list
      usage:
        prompt_tokens: 13
        total_tokens: 13
    status:
      code: 200
      message: OK
- request:
    body: !!binary |
      H4sIABgxUGkC/8VYS4wcRxn2yCasa/1sx8YmIql0IFmb2c7M7My+gFi2E4FHEXFiR1bksYaa7uqZ
      ynZXD13dux5vVuKSA+IhISSEBEJIgBNBFE6ciBQkLkiQAwcOCAycIqMcOCDECYn/r+ru6ZmdNTkk
      4jLTXfXX//z+RzV5r07e3k/WyAnF403hckdIlTCJD55lE7q22qgv1fxaky0tNxustVbn9dXeirey
      7C7X/dUWscmphAc85Ek8cpS34QRM9lPW59YceWA4SgaRJJ8i1iSNZCG3jpLD0ZDLYoc8Sk5Okm3y
      WIlIIqe6s7Tm1IHkUK6o5nGcHE3lhoy2ZDdbJyfI/DCOXK6UMwQbDpz++Wv74dyD+WKcykSE2fmD
      5KNupuRj5GPTJCX5S059yVkhL5KHpok8rtxYDBMkXCZNQ0gXQiZklV7lQ1pfpY1ao1WljcZ6q7G+
      1DxLb1xCL8GyU3ea9Cb5HDmam5XLPEcWWqvNpldbcVseeL7me636Gq+tNluNlXpz1V1r1JhXX/FZ
      z7rjkJNg9chjoJK7yIRl/FWzfvEEOVb5Hjv/xm/c28cufo19de7OZ6y5T3/n9bvvvbly3J577s7z
      33934bedc4fcAUtof5gsRkrVKmtfenbtTz9ZePX0hYXv/oq9Bg/tR8jJPpddJhyIWszQXuPDB8gB
      PNw+Qw5nBGqkEh6i26IgYCFrg/uzrZh/OeUqccLI4wG6PxPZ/gQ5gi7gscM8LwYHW/PkYBC5LBhE
      KmlbZD7bHkZxYu0//dOX2v+ZJ6c1n27GtTtkMWiUgAutv82Tu/Pbtp9KF1XtJlEUKHud3ti2UWt4
      shVnsTvoepGbhoBDZVepPebQfVnBMeUOeMiAetsGvQSyYsGVGF2QCI4MfRYojifLi9s2KBSP9FMy
      GhpxSSxk394B2kCEItGbHvdZGuCzTIMAtpgcPecbPfODAnKkz2M8OV5Ecnvn5g6yQ/NFzD08lgm+
      Ccs5adR7mbuJFlwCK+5c1R6gyYBTTKKAe31Oe0xx6kcxjSEZNwFStPCQ05Ed+QJP0lgq2FaguaJb
      IhlQdwB5SC8/rSiTXn7S5VS5EdA5eMrnMcel/FxvhIJFbM52hUeFpK5IuNfVK8rBgEQpBKOLpnhd
      T7hJd4OPxt5Cn7pJKQoKkQBZwILS4oaQ6JsCDMgXgsw8lrAxL8xmkJYt7KAHe6kIElECz02j0TBN
      uog8ZIp79ng5c3bBNVueAT9fAJS6xhv/A3p7YmsqntcgkDoT4B2cCxm9xTAiaosjPEqYKIHRbO/F
      zuzSJNIoyZnvwaocvVkMER+RbwKuaKq4h4wBa6HmnmkCjIBPqPbKnnyJxTEbGbmR9IWH6JpKqrpT
      2436SwW1gacGezIQuafoQm2xflaDhN0SYRoWjEIhs/eafh8nY9jDBN0jGcdOnpGWuHmfyjIjay8U
      IWHU1DCq5ZQzMc7T7YPPIoPo951DgN1wiLDIM4GHw4AlvFTygiDagvVbSUZTEmr2RAgDxdTmTvsh
      cjyI+j4421FDJrV52I3wBfrJfL4Zqr51hEx0uPYfK0U7ExK4OiG0HBCirLcr5K0KpGkcBTpMgNI4
      S89ETRZmVNk28EvAXbh0HYUIKaNN6JCb3GAbIS+gu1Mu+yADSyn1oN5dhMqOcwD8xZGXugaJfQa5
      gGCnPudej7kb1AcfYmkUtzkUXi/Vu222ASqxJxSFaqvr2nlsCDfbb8yRU3mr1i4bG/etOfLNuZJx
      TCmB816yl4UDITcw76as5FRyk7wG2Ou08382vWPTywksQEoMuSt8EFlUQtYDP+Qiq3SINTdkvWA0
      c61jZ6vAMhT9QUJ7UJpoL4bOdp5ecJMUQDmqjk3AukEvSy+SXAl4LDMA9Pc0V0b1MEP7EQwxUvsh
      8kFLyDGHXmciodq/txJ05W77gNUiDdmox01qazeA+8eUhjE4MT9SpfBijuTCM+qx1wojjKGaNbIt
      m7AQciZRXAcKBYs79llkzCj2sfP0Sm5g2R0UiphCDXLxWQD1QZC8CaCrGi5YCzRSQD+YP3I25+mz
      HMNp6pueO16EsQTK1lYUe2p9rOEuyO3C2wxUFYCa9kjHnhyzsG93UTXdlXT9w7duurXa891kE5fv
      N0+yuJ+9AMF2x0x+HXu9Xqt2THeAlw/Nlh1bl2CYNIQawKjBlOkgY6ugXLwzTz4+Mbh38Q4Yp5qH
      st6cJz+bv3/ReylKKYsxzsUUCZCA97y6mFnElApV5CVOAGgJKwbMqSlUh/2KuW+td2TdoZdAZzrt
      Z9P3imk1x4gpHeWppSMbDn2Bbwq+pdfzSRRHVjOKTg+uHbnk0Mu+rnbcqyKudVz8CPvSYjrMlOGZ
      Ep7wdd8taQE3wVt0CZIqYcHZjmw6mDKbMH9gWkTSFaoYstBmj5puDBmlZzjUEhb4JuxkLkev4GiW
      9X4MJhJNDOWB2ODgshtmtmY9t95YukkXtFU4vay2QJerURq7HHPp6TwA10QScEj6p+DqqgGAT2lP
      ZYiS1wAF6xRH1X7MhoOOvGR0WjcqMV0dKWIk15YCXrnj6Fhm6sB81mwtl9VZaUyoc0FGCHOaq9Wx
      c8kJAqss9RV6KQrSUNI6LR4b9JWOzEQ+w9xB5hXILjdIYZiCY4sTtw6o7e4GT2ZeXpA216zAaYJu
      0tSZZ+hAwKUYwjGiC1sDqHRsk4kAlT2LDIzyuUcwlXSExo6sGsuqQOPBbwB508UheCa33HozNI9d
      jvZelnQE2qLJQ0gx4JVZrYnH1zQgMgP49KULmXw+BXwGQmauusgKjKoJeO6CJjQpL6IQPeRNQSVo
      SaBckdbIDes46mKcqp2I7qH5NIn9J5UeyEpwL2uLeBISMYQ4imFQyt2YF6lfpWokgbWCeogioH5G
      A52OwSg7LyTmr/56gZ0KKl2quzDXp9kI0XcZepFEG6BuelB8o7Q/mDwoZ12Zi2HI3CXyouMgeMGH
      vJTtHhSKGIAD7mKbEWCQQ3Aj81EFbA+g3kHx3OAenvwCtGZgagoSyIb5HcZnGkYly3N3YD3/d4Wc
      yEff0kXS+muF/LmyPeP6MXW7nDkWT9zFxhev2WPm/YlnNJk9Duz1cWeCPP+6sbPTpuRMJiNFPYwJ
      cPXegO5o7T/94wPtR4tWZyiK23lG8lalbRcXgzyFdn+s+iSxpmmEl98xXLjfLK42V9p18vA01UQn
      VtbRc4fJPDlYtOPb+16t7Kvs22f9vTLru137mV+TL74y+qc9d/fJuPuPfz3VP3c4TqU0s2AU4Ie7
      1+ff0d/rLuQP7UfIR/Smdercg8Qix6bbJxBMXJWOkSM507pm235s1kULrB1yAKPsd/WF60lyJifK
      1yFiIABqrAVimz5bbtXXXL7cWHV7Lbew9d6BWbb+oP+H819fvv68PXfvd/V3//KNb3/23KGyrWDq
      Pev3xtT8of04OZZ5HEnM58lZFj9OTpTp0PUYwKPk8MRw1/5KhRzRwSnGOEuSYDv/fgdDXP4t5sOZ
      4OwdcOtEcCh5uOyF9V3DUPuXe6T/jyrkh+8n/SftnZlq1WyCzGG9F9F0LJBuej3zvd6CFP5AoOZ5
      DX+l0fK577eW+PJKDrX/AnvBlYHuGAAA
    headers:
      accept:
      - '*/*'
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-encoding:
      - gzip
      content-length:
      - '2703'
      content-type:
      - application/x-protobuf
    method: POST
    uri: https://logfire-eu.pydantic.dev/v1/traces
  response:
    body:
      string: ''
    headers:
      connection:
      - keep-alive
      content-length:
      - '0'
      nel:
      - '{"report_to":"cf-nel","success_fraction":0.0,"max_age":604800}'
      report-to:
      - '{"group":"cf-nel","max_age":604800,"endpoints":[{"url":"https://a.nel.cloudflare.com/report/v4?s=xDLApOJqPg%2FzMcxeUVZqDALGBRXUoZynWuvH57cPAX5U2rMdJ5rEdp1EkHEpqNCp%2FjZ4YqLCso2NVnLZQB9%2BZhm8fad5oMpwEuuNgLWJWxELxWtf"}]}'
      vary:
      - origin, access-control-request-method, access-control-request-headers
    status:
      code: 200
      message: OK
- request:
    body: !!binary |
      H4sIABgxUGkC/61ZW6tkx3XWQbYz3qPLuCXZMsZRuY2s0dCn1X0uM+e0kpi5GfuQZJSZkSFIk6Z6
      7+ru0tm7antX7W61xIG8mBBCIJCHBJJAIMEOIRA/CUzAzmPw5SE/wMYvNnozCfgxkG+tqt29z2Vs
      P/ipu+uyatVa3/rWqtXJB19Mvvtkcpg851S10Knqa+O8NPQl63QTcXiwM9wdTAd7cvf63o7cPxyq
      4cHkRnbjenp9OD3YT7rJJ73KVaF8teq77LifSzOr5Ux1LiUfK1d+bk3yctI5vcbIQnWeTZ62pTLr
      meRzyQunly1U5bQ1JGnY3z3sD7HkqUZRlvGJ5NnaHBu7NOM4njyXXC4rmyrn+iXu8JEX//2bT2Lf
      881gVRuvi7j/48lvpVHJzyefOrukdf5uf7jbv5G8mXzm7KJMubTSpaeF15O9sFBcLaQ2PfFAlWJ4
      IHYGO/s9sbMz2t8Z7e69Kt66TVbCcH/Y3xOPkt9Nnm2u1Zx5Lbm6f7C3lw1upPsZLD+YZvvDQzU4
      2NvfuTHcO0gPdwYyG96Yyknnf15PXsCtV5mESum21J1gr0Hn29eSK1t/J7/4b/+Vvnfl1l/IP7/0
      jdc7lz78wfBnP/7Lv/6d7qUfvVaNf/6L35tdewrXMRo6eWvzwdbhh53/lt+8+vUXb86v/bOnL0df
      SK7MlBlL3aclwXyd5IpTskrn48ymdQFnOqx7rr0ulXlOWIK36eu4Xh5MpqlfHP3pVvIMrRjLaha2
      dkySv9/NdaF9dzQc9Lpfq1W16o66t7TxZC9tjF1IrxdKTG1ViFTDZEKZGeBGEsRM+rmq6BpTpbKJ
      TI+xxuv3lHHiSB7LyksBhKXkrO7J0WvJ5dzOprpS/cLNOiL57bYVRuLc3f5jK3mu2fGOswBdOleF
      7PzTVvKPW+93/apU3ZHo2sk7OKPbE12ApVSV18phHAtO3TcMnd5zgk28qlKutMapxy066wtad3Y8
      2p6nTk6OPpN8olHeldKMSWrnY8lH6MfRn30hefrUwZ1fvJz878tv3dhNpzcm2XR7Z5im23vD3cPt
      yf70YDsDJ+wMdzJ5sJs9Elddais1EoP+YPfV5CEEj4RX7/rktkWAGz9KGvPfjeYXt2VRSj2DZ76s
      pBdvliN8qdQr+G2XcIB402SIBTg+E/CqeLByXhVJctOtXSgyuQIo1q7NKrl0wsBrquqJFDt1Jr1y
      AgPC1p7WAjipErUjLy9kpW3thPMVls3gJTp3aa1YWI+zBZ1dVqqk/ZhR76oq1U6RProSmSpsip3A
      YKVnc+/64naDtkIeN8sWFnHtxBxqZUI6vgxQuRILPalYvaX2c5HrqeqLh3PtRGrBAsC0sNMpqbGQ
      eS0nuYL+jg7CJ7RJowGFhDEWmkAmlnOdx210QWmwdDtTJeTPap1x3Ih6bVhaw8a0lcxFZDaI2di0
      nyRfMZCN6d+XtUnnEA7XNZZ9Ze1G8QYozQk4BZwHR01UJYbw1hSGbA8534OWymzUR5QhlEhpneKc
      fCWOdXqsMho55cW5ROAXsE0m3FJPPVaSUzj8o60nEur3xc1CV1JE2uiRGeoSF678RlwwOiAKbxGh
      OEuHR1u6AjMIXK2QCSMKbKEZNHU1gbxMLVRuS2Ydnq8nOXAAIBmEDwzH+KwU8xScfqxWosylp9+O
      bAieapRJV8KVSsG2G7u/ju9gnQnJv6/fg2ZflpWcyxIycx3gtNCwAE4hyOBgkF2lEIYZKzQHUHJG
      pYBNIW1aSeC8Tn0NMOM6xCQEtaLMlYdJs5ohw8JUVcDxa9c+WMfHSHwJhhB39Ex76HRLep+rWWUB
      KY6dO9ZW297Sh7hX+0rJdN4S1Ao0dqZHlBhyj8wWVHQg0uvKkL1abs9VjIYsnlqoTEs6jcULCVcC
      0ELWGfurD1O5uZcz10OIEbAXmLf4BQTM+K4yC7G9HiiAezmj+6ekDQwGZ61C/EzzGl4gcFSWY1Ck
      c8CKFkev21IbcjdD6p3aARLCL5XyAmYokJqASM9xP4MTXGWtD9fK2/eMQIb8LFhxmz7XceIEAIlA
      kTkYJuNA1tiLu9V0xUBYOljTI9pKTyZKrTFwNLwZo+EVWoS1DHRguyxZ1CZzwqj5NlU2mxw6JZ+v
      E6mcEJVmktAH+BQ1ggkWyXNcgCgI3oPUHO5QzHdsxNOJG/g/m7t7kbsamOfMNiQBBFERYrBpqSba
      SNxzipQR8MpxCnNm2qW14whFEBhEawpr2yU8wnzHwJZZAU8xCuEvGOU+1CbZBIY3YMBaUvGVNNnK
      iNLmuDeoARenOpO9WNolBEIfuhq842gTsVKIYvjUWC8mKpxMkM96fMRZMpsowB9BwBVLDdRxHPhA
      /ULjWgpUzp4yQCgcK6qgcV80qgdTqJBNwBapzW0FsIOlTJPD2kqSoWxdOXUeLEvCtjULNijlIMYt
      djGbbLtSV5qipWKWBuDvIXMQq+/s9Bq2pTybazqIGI7MlzLzwX4M2QLUs2AvZXUaWJLpCqjz8zQm
      WlKrROKF3Rk0KRyZnQYIcBxNAVN5xYo7uJYM5+Z2yXhxOD5DkkeyZQw3CT96lfg+iKgNX2yi5pq5
      E0tyJVljyPXa1CSDFEUamWjsXgE9d9SEfDkSKOfdHGJuKQp7I76qydgRVmQCnLFeHqoRwy4mNLWY
      GiNny9RN/PdIWbuMJNXgCNaKFo8pcJNl6PQYFrBgvLB2rib43DPiD+FiTsr7ft7bxDdYjMBGoWcQ
      XjC6pHjBsRlfAFYKt2xp0TifjmwimABEqZ6IZVP0ED3EkiqQWMPqnDpJ8QAKQDGya3wZudc3p2QL
      m0ofNJSzGUpWzuFUG8AgSyq0XMHpno4sbAamPU0vLRGYh0MKVCE16UTAs5RXnCX2okgmRAImhi6f
      Uxx6hPm2k4vFCnTpkF1QzQMPXyUSFnfXnDYSfxBi+y5MsRI0LW4jV/okuWtc5C+eQk6faarwmMfh
      pMiMIZcjB8EuFHiKnpVMqdbMLEOhYV42ZsNbXIqiPuCyRsEGlKPLSAYgJby7SWkxsRknY4vAWdrq
      GJETV7Hx3TwqxMUjgy3o0uSbAGGgroqlBpHcnAvehtDJRcZQjor1MvhgqhziGkOupgRONTGoba7y
      jFhljcudQcNu2amkRaCcEDvadb30imsVsohffFmR4KUiVkU9bpHHoDSZbIL8Ow90hMeQ8yHbhRu1
      y54vIdeYFDtG4iHXdcCsSQMN3ExTcmTkgtamabMJDE+l11KuXOB5yVRCpQRRkEfRkBLKm0B3IUV4
      Ip9N8K9SKjkIhrh1qrjN0BebXN6wQw/5w1DCzamkocp4Do/P5oE6p6Hkh72YKFxdUo2qKE3wO4AL
      ByqQj1lHqhRDMbMhW2dLMqsOQVMgQEgSlQfEmysYFcvLCl4FyDMk4Ob5BO+sWDlg8qGlyhPR49uP
      pww8T3xJjyauqtbvECZtaWBf7K9VU4zRc4pef3Hf9tl9PXH+tYlCRbt4isn4EqgDNDQBGcEYOrKX
      b3s6koJriuP0vJcbJQg5t6jcV5tD78jVSDyoJ4X2DKZc3CxLJDoHiC/Pv2Tp4epOvXhar8icfCLj
      dt+8UNdQiClWogxw2q+9T88OoxCbE1vNrc3cGRpsdk1Zu5DXqaeR1Xmk55z82UQkjiM3kxlCGpvb
      0C5hFTdFNDs+pv7KltaR0uFk2BXVR1i2wSHdiC8bMj8MIfnl5UlM3graNj0c+DmM/kZcwMZ+iDQT
      LZ368FSNHru5fiQnCXLfHZUGIdcp950mBomYcZuG0VKDQqhT2Tz7LddXeIkbGY7m5FbnqC1D7uJK
      VR0zPRJvGRRbDXSwvs+ZoHJBckqObToFXp2tE+VSasKoq3MfeTLQN7/8UJCuK8QoZPPG6sWCNNa3
      Nr7HoBI96GlLqwztr4teBHtTS54rQpqOBNf0rV4EkfE0h2ORMkJURKpHBdnqeOTWwioSxV4WyzyQ
      mmbbG7WkXFZy+jMscFOlRULvXdisoLNMuDWfRI7RU+wjBMEDpbIo5rZD0U48h1M0F6pU3OV5tN60
      pkTj+u898fWtJ7aeeKLzra2LeqdNx7R76d43/ujvf3b1+29fe7rdNXSDrcN/ufzD0Dz9qz/5IDRP
      X0o+ypOdT157Prmoa/rS6VbkleSZRuiQxf7S5t1a5Q+fvUjlu39bLf5h+Tff6V56uxj9/IOXvje9
      9lRKQJqVfhtIh8Y/+el/sqI3my9Q6IXYSqQOZngvcc8XZ9Lmo08nT8cFjjtz1CWHNWUhjz6XPB+n
      KvU1VJu+zyUYddvjkUefTZ6hug6UIrOM6rfO5eTjOUqynGqRo05yOU4TQXSefPFf//jo/y4nL7Kc
      cZQ6Bk1DIwqlzk8uJz+6/H4XeYYBO2Zrd0firfe7sTvaPWtz7s+uJYxb/VzuuUIvTaJk/ka7iTsF
      lanznd3Yqm71aim7mBn3amNLG5OZmkoEMr4bPPcwheR2bxr0bDYSY8xURTs3g7S8e/LohMTR9YED
      6uu+FQ9+RG3j803i1n8TNPOALcBBQm9ZUPxMccuMmb5CcNHrU6wt1H/bvG3uK+rJuDUFcV2Qzmtz
      LL5yJzBL3Ilw4zYw7buvwBPcPWv2TVaRoHjvWGfcSaFn15hHXJ8cApJSFYM7G2fIzmNksI21QsZu
      ecERErg50xpEMUC2WYOB5MLJEoQqN7Ko6MNpceCELDipdQ4y2oDnUdCorP2YkEdCaa67GY7GXkuN
      wxfAj1PsOFjjV0Dvsdg640/KdhwJRNGcGrj5YhyYDvBoYaIFxjD9OHFhlsjZt4Q/RlTbexcJJHxQ
      q4cXiJqelBDM7we/PotkQ07hHhc9zZCsKrkK51ozpUdXqs4E1bA/OI/62+vVAZ4Mdi6z42WvDraH
      rzJI5Lu6qIu1IGoWhd8D/r0JRioduo8Lxo2RLwhLmvwlzHJB1N5cu0TGf6QEn9OOxKoJt998FAVE
      /9oxRI3ykmDRRIIqqCOhWpRHXYwx/TsU17QODXO6wNP3zOTJ0fHF/709TO7/Gv+8PS5xXPj32snJ
      0ecvSrfPJE9R5QVgjvk/s8+eTtqYbqfVo9eSTzfTzTZ+WHiQH/11ujeV1/eHh6m6vnOQTvbTo+46
      5zZ/wp1LnE2q/38lTytNuR8AAA==
    headers:
      accept:
      - '*/*'
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-encoding:
      - gzip
      content-length:
      - '3838'
      content-type:
      - application/x-protobuf
    method: POST
    uri: https://logfire-eu.pydantic.dev/v1/traces
  response:
    body:
      string: ''
    headers:
      connection:
      - keep-alive
      content-length:
      - '0'
      nel:
      - '{"report_to":"cf-nel","success_fraction":0.0,"max_age":604800}'
      report-to:
      - '{"group":"cf-nel","max_age":604800,"endpoints":[{"url":"https://a.nel.cloudflare.com/report/v4?s=hAjchguDwlnZrdktXz3KchT8afuvmDYPOYlrhBO45s6bYoi56ZkynqcF%2B%2BEKRSBQOPvz8y9pn%2BlIT9uFRrilLMFjjBi8MSQpo2yrN4Vf3g%2Fcfsjn"}]}'
      vary:
      - origin, access-control-request-method, access-control-request-headers
    status:
      code: 200
      message: OK
- request:
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '8704'
      content-type:
      - application/json
      host:
      - localhost:11434
    method: POST
    parsed_body:
      messages:
      - content: |-
          You are a knowledgeable assistant that answers questions using a document knowledge base.

          Process:
          1. Call search_documents with relevant keywords from the question
          2. Review the results and their relevance scores
          3. If needed, perform follow-up searches with different keywords (max 3 total)
          4. Provide a concise answer based strictly on the retrieved content

          The search tool returns results like:
          [chunk_abc123] (score: 0.85)
          Source: "Document Title" > Section > Subsection
          Type: paragraph
          Content:
          The actual text content here...

          [chunk_def456] (score: 0.72)
          Source: "Another Document"
          Type: table
          Content:
          | Column 1 | Column 2 |
          ...

          Each result includes:
          - chunk_id in brackets and relevance score
          - Source: document title and section hierarchy (when available)
          - Type: content type like paragraph, table, code, list_item (when available)
          - Content: the actual text

          In your response, include the chunk IDs you used in cited_chunks.

          Guidelines:
          - Base answers strictly on retrieved content - do not use external knowledge
          - Use the Source and Type metadata to understand context
          - If multiple results are relevant, synthesize them coherently
          - If information is insufficient, say: "I cannot find enough information in the knowledge base to answer this question."
          - Be concise and direct - avoid elaboration unless asked
          - Higher scores indicate more relevant results
        role: system
      - content: What innovative form of civic engagement did Bintang introduce for gathering feedback from citizens during
          Jakarta's election?
        role: user
      - content: |-
          <think>
          We need to answer: "What innovative form of civic engagement did Bintang introduce for gathering feedback from citizens during Jakarta's election?" It's a specific question about Bintang, presumably Bintang, presumably "Bintang" might be a brand? Actually, Bintang is an Indonesian "Bintang" probably a local government official. Wait context: "Jakarta's election" - maybe referring to Jakarta's governor election, or maybe a local Jakarta election? Bintang might refer to "Bintang" (meaning "star") or a name? Probably Bintang is a person, maybe a citizen or activist, or a platform called Bintang? Let's search.

          Use keywords: "Bintang innovative form civic engagement gathering feedback citizens Jakarta election"
          </think>
        role: assistant
        tool_calls:
        - function:
            arguments: '{"limit":10,"query":"Bintang innovative form civic engagement gathering feedback citizens Jakarta
              election"}'
            name: search_documents
          id: call_uw8bfctv
          type: function
      - content: |-
          [73cf7bdf-21cc-4139-b5f8-df04212da83d] (score: 0.03)
          Type: text
          Content:
          Jakarta Election Campaigns Heat Up: Here's How to Understand the System

          As election day in Jakarta draws nearer, candidates are out in force using various strategies to woo voters and prepare to exercise their democratic rights. Citizens make their voices heard as the city vibrates with life. This coverage offers valuable insight into campaign activities while offering an in-depth guide for understanding electoral processes in Jakarta.

          Initial Launch of Candidates' Campaign Plans on September 1

          After September 1st, when campaign season officially kicked off, candidates have moved swiftly to engage their bases. Amira Bintang, an upstart candidate with extensive social activism experience and promising urban development and public transportation reform as key platforms of her candidacy speech in Jakarta; incumbent Rizal Harahap relies heavily on his track record and highlights all infrastructure projects completed during his term.

          Campaign Strategies: From Digital Battlegrounds to Door-toDoor Outreach

          Campaign strategies have taken an advanced turn as candidates leverage digital media to reach a wider audience. Hashtags, viral videos, targeted ads and targeted messaging can all play an influential role in changing public opinion with just a tweet or meme. At the grassroots level candidates engage in door-to-door campaigns personalized for individual voters in an attempt to connect.

          Bintang's interactive app for gathering real-time feedback from citizens about daily commute challenges was applauded as an innovative form of civic engagement, while Harahap launched a series of webinars featuring experts discussing economic growth under his administration.

          Rallies and Persuasion

          Jakartan politicians know the power of an impassioned speech cannot be underrated, and candidates have been taking full advantage of its effectiveness at rallies. Rallies feature vibrant colors, banners and impassioned discourse in an attempt to win converts over. At one high-spirited rally on October 22, Bintang outlined her policy plans for improving education and healthcare to an appreciative crowd while Harahap's rallies often consist of shows of solidarity from various political allies united behind his plea for continuity and stability.

          Debates: Clashes Between Visions and Policies

          Debates are one of the highlights of Jakarta election campaigns, allowing candidates to outline their platforms and discuss critical issues. On November 5th, citizens witnessed an exhilarating debate between candidates Bintang and Harahap over whether the city was prepared for digital transformation in public services; Bintang advocated an aggressive move toward smart city model while Harahap advocated a more measured approach so as not to alienate less tech-savvy residents.

          Voter Engagement: Making Every Vote Count

          Ensuring every eligible voter is engaged and informed remains an ongoing challenge for Jakartans. Civil society groups and independent bodies host workshops and publish voter guides to inform voters of their rights and choices, while an annual democracy festival such as that held on November 20 featured interactive exhibits on Jakarta's electoral history as well as mock voting booths for first-time voters.

          Campaign Financing: Transparency and Accountability

          Campaign financing has always been a contentious topic in elections, and this election cycle is no exception. Bintang's campaign, funded largely through crowdfunders online supporters, stands in stark contrast with Harahap's sophisticated machine backed by both private donors and party funds. To protect democratic decision making processes from any

          undue influences on decision-making processes, Jakarta Election Commission mandated strict reporting and transparency measures during campaign financing decisions.

          Before Election Day: Submit Final Appeals Now

          As election day nears, candidates make their last appeals to voters. Bintang plans a visit through key neighborhoods while Harahap plans a final rally scheduled for late November. Both camps are honing their messaging and policy proposals while encouraging supporters to make an appearance at polling booths on November 8th.

          Polling Day: The Final Act of Campaign Activities

          On December 6th, voting booths across Jakarta will open their doors, signalling the culmination of weeks of intense campaigning. Voters will cast their vote and candidates await results that depend on how effective their strategies, speeches and outreach initiatives have been.

          Jakarta's vibrant election campaign offers an insight into its flourishing democracy. As the city looks ahead to an exciting new chapter in its political history, electoral processes demonstrate the significance of people-power in shaping our collective futures.
        role: tool
        tool_call_id: call_uw8bfctv
      model: gpt-oss
      reasoning_effort: high
      stream: false
      tool_choice: auto
      tools:
      - function:
          description: |-
            Search the knowledge base for relevant documents.

            Returns results with chunk IDs and relevance scores.
            Reference results by their chunk_id in cited_chunks.
          name: search_documents
          parameters:
            additionalProperties: false
            properties:
              limit:
                anyOf:
                - type: integer
                - type: 'null'
                default: null
              query:
                type: string
            required:
            - query
            type: object
        type: function
      - function:
          description: Answer to a search query with chunk references.
          name: final_result
          parameters:
            additionalProperties: false
            properties:
              answer:
                description: The answer to the question
                type: string
              cited_chunks:
                description: IDs of chunks used to form the answer
                items:
                  type: string
                type: array
              confidence:
                default: 1.0
                description: Confidence score for this answer (0-1)
                maximum: 1.0
                minimum: 0.0
                type: number
              query:
                description: The question that was answered
                type: string
            required:
            - query
            - answer
            type: object
        type: function
    uri: http://localhost:11434/v1/chat/completions
  response:
    headers:
      content-length:
      - '1260'
      content-type:
      - application/json
    parsed_body:
      choices:
      - finish_reason: stop
        index: 0
        message:
          content: "Bintang launched an **interactive app** that lets citizens give real‑time feedback on their daily commute
            challenges during the Jakarta election.  \n\n- **Chunk used:** 73cf7bdf‑21cc‑4139‑b5f8‑df04212da83d  \n- **Confidence:**
            0.97"
          reasoning: |-
            We have a chunk id 73cf7bdf-21cc-4139-b5f8-df04212da83d. This chunk references Bintang's interactive app for gathering real-time feedback from citizens about daily commute challenges as an innovative form of civic engagement.

            The question: "What innovative form of civic engagement did Bintang introduce for gathering feedback from citizens during Jakarta's election?" So the answer: She introduced an interactive app for gathering real-time feedback from citizens about daily commute challenges. The chunk provides the answer. Let's note the chunk id is 73cf7bdf-21cc-4139-b5f8-df04212da83d.

            Thus answer: An interactive app for real-time feedback on daily commute. Let's craft a concise answer with citation.
          role: assistant
      created: 1766863137
      id: chatcmpl-844
      model: gpt-oss
      object: chat.completion
      system_fingerprint: fp_ollama
      usage:
        completion_tokens: 234
        prompt_tokens: 1628
        total_tokens: 1862
    status:
      code: 200
      message: OK
- request:
    body: !!binary |
      H4sIACExUGkC/+1aXawcyVVea6PgtDfZzSwbdokglUlgbWtmuHN/7Ou7Ita1vWF9FViz9mYV7VhX
      Nd01M7W3u6rp6p7ZWccvSEFCvCP+lMdEAQQSQrwgAY8IBIL3ICKhoAgh8cgTEt85Vd3TM/fejUEJ
      5MEv9tzu6qpT53znOz9V0b+8F/3ls9GN6EWnirmO1UAbV0pDP5JONxI39reHO1uTrV25c213W+7d
      GKrh/vh6cv1afG042d+LutGnSpWqTJXFcuCSk0EqzbSSU9W5GH00X5Yza6KfiTrrY4zMVOf56OM2
      V6Z5E302eml92FwVTltDMw0HOzcGQwx5rhaU5/hk9HxlToxdmOPwPHoxupQXNlbODXLs4SMv//E3
      n8V3P14/LCpT6ix8/7Hox+Ig5Oein9gc0lp/ZzDcGVyP3o4+vTkoUS4udF7SwGvRrh8oLmdSm564
      r3Ix3BfbW9t7PbG9fbC3fbCze0W8e5u0hMeD4WBXPIx+Pnq+3la95tXo8t7+7m6ydT3eS6D5rUmy
      N7yhtvZ397avD3f34xvbWzIZXp/Icefr0+gl7HqZSIgU96XueH1tdX77neiFC78rb/7hX8cfvHDr
      N+SvX/zGa52Lo+zgP/7sM38z6V588xu//Hv/evlvR1efi2eyFNO87Fvnti7c+M53/6r85uWvvXz4
      D0eT3/wWfhx9Jnppqsyx1ANYrZC0X6/Dj0YfoY+PXok+Hga4pStVRmqzaSozeQT1h1eF+pVKuXKQ
      2USlpP6w5NFPRZ8gFahiIJOkgII7l6KPpTaW6cy68qgTXQqvc1uUnWdf/v2vHP3Xpehlnuc4zHqc
      ywISlVBh5zuXon+69Kg7qUxMoh6X1qaueyDefdQlqfGr65Qs4tlxYuMqAw5dtye6qxmO33P4zMUz
      lUmMftSFXJqmkum9glRQakUTTmTqFH3ZfvioC4GKJf8ql7lfriy0mXYfY2yqM13yy0RNZJXSb1Ol
      KV5Js3xz4uWsP9Twkakq6MvVQxreffzwMU1H29eFSuizsPBDPK6H2vF7Ki554RZY6c191oAoZ0qQ
      E6UqmSoxlk6JiS1EAWecA1Ki0dBgZEbmLVVWhXF47SC5EwtdzkQ8gx+Ku3eckCapv4yVcLHFuAF9
      NVGFokf1d+MlLawL/+2xToQ2ItalSo75iRuQQWwFYxzTVpLjRMfl8YlarrRFOo3LlhUcIQFeINPW
      wxNtSDcNGGheGFkmspSrucibsVp48Jg0OK50WuoWeB56ifKqPCbk0aT0rrt6HJTdzBoenwG/iQaU
      jr02vg/0zsXWhj0fwJDsCfgbyoVHLyRZxC0UwaOFiRYY/evzpvNvRWkZJfXk50zVtt5ZExI+7MQb
      3InKqYQmBtYynj1IgokwT+bO8576kSwKufTrWjPRCaFrw6mGg63TqL/djPbwZLCXM11rSlze6g+v
      MEjk+zqrsmaiTJvw9xb/vXLGbEwOeo4zrpR8hlvSyw9hljO89rAxiRSewwSv0/bEona3H7wXeUQ/
      sQ8Bu1lOsKg9QWV5KkvVorw0tQs8f78MY1qL+nc6Q0Kx8fLx0aejT6Z2OoGyBy6XhrdH0Yj+QDy5
      VL/M3LTziWgtwh396rAJZ9pg1kGGkINFXOd7W9F3t+CmhU3ZTEBpEdyzdOvETCJ3PfxKqIsevUOL
      aGPsHBFyrjy2CfIa0V0oM8UaRKUiAd/dArNTHoD/CptUsUfiVMIXCOxiolQylvGJmECHRI36AwXi
      TSp+eyRPIJJ81QmwLfPaTQoIFCRq2aVzmtK58rwNzLQ5Ibfa2IQSRnnf9Lg9EKP/552NuuJuiQdA
      fK5iPcGSDdHJMZBRL9kTOVFqJsfp8sxno254iikzPZ2VYgzmEeMCgeumOIzLCphb9lZbIFoQd01i
      jXIaP9sTANxjnlUKzlXE1CJHMawHO4GUcKGBeEfqUrB+3y9Jlaf3h6n6IpPLsfKey2qA+lcj/cRQ
      Yv1JT+AP/0m9eBi90lqzCb9RnpqmbW/hcqakoeVG4AFZjLpXaGIpKEzdFPfqDbbVIcBRjiSolw8G
      5A+x8hyg6/lZyNUZKZAP6UU9zU3xJUXm9PTFacXbyDrASgtbJO5gJeEpyJ3C2xmoagC1qZFRdz2L
      orB8TKJx0GF6o7+Oq8X+eBKXc3r8YemiLKbhDwx4NPKJ3ah7MNzqjTz5448f2l4ed5lhkUhoN0Mm
      IZ0PEKtdrbHBhzFZ/QXlI7k1Tv0vFRLSGbx99/pOPLk+Tib97WEc93eHOzf6473Jfj9BNbk93E7k
      /k7yUFzmEMwBdefKyDyAQAeCHGVkbntGOhiZeuuvh62L2zLLpZ5CK28o0NLb+QF+FAqIesMuCOFv
      mwQYLSkZpcziPlckBLPDldOJRC4p56xnTwq5cGA+WaiiB8AaMBkCFQCPHIEoBmNhNpBZ5chEc1lo
      WwHEJcohNUXQppUX1oq5pTSOU2EwT07f4416XxWxBsx92puozMZUSMWiIPd0A3G7tnUmT+phc4uy
      0IkZxEoEsjnaDjCxFHM9Llg8DvupnqiBeEBZTExUAUQRA5EYc5lW8GEF+R3zANBosT+vwuCxlHOI
      xUyn4TPaIMhOm36icsw/rZAyMYtXjWppDCvTFmCfUBhjmpVO2bPvGk2phPiSRP49o5hxu9Htq40p
      xT3UxEgPDRXNMBYSKjFki02gzPZDIpfFDHTTbMEx9BvGBV2d6PgEdIMna5acSbheBv0kwi30pMRI
      Mgw7YNA3lT8wxWGmC7kKIFBFlRM/lqvpvOIBVViMXNpZWrxmwAxvwJOa80yPBJtpBk5VjDFfouYq
      tTn7Pb+vximwADAZR0Uul9jE2cQUMDzIsaFTTqPBFLUw8ZLiooJ2V7p/Db9jSkwx/1v6A0j2BiqM
      mcypPNMeUnMNDWAVgg0WjilxhD8mLNAMYEkZmQI6xWyTQgLrFUIkAI3tUP5KcENCh7olqcM3T6aK
      jI3fmPd+4yUH4osU9e/oqS4h1S1ZlqmaFhbAYg+6Y23RLy39J96sSvBaPFubquVwbNAS3mLIRDLh
      qhM+jwqVdNYyPSpS7xVJWDdTiZa0Hi+AWLUAwhGzqoRtNoC63KyUU9eDqxHA53hv8RdQMOX9ysT7
      ePPAJ5Gkg5ikgdJgsKX3o0kaUmpBfMy17gzQosHB8jYHkcMYDKv3KgdYiHKhVMmRHgECqCzZ/6cw
      hCusLf220vY+A5gxf+L12Kf/G19xIXjLFEyTsEMjrwdgk4q26IlLe22WlKuXpCIkLwbGZosGn3iV
      hmE0wx0Iz/ONHA9qTftUEJyX7fm8LZGEQYAoQ41COkGeYKZERlS65lBglShmPlbj980/e4HFarCn
      zDo0A2iiIMzgo4Uao/rGTicIHx617K1QaKJdXDn2U7iCgc/G0LddwCbMfAxvmVApyDikPhi3RSA4
      zU6AuAclVpL6ePQm+KMRuU2xd5AENk/9FrZlbqmYg0y0PdjI0WfET96fYVljOUfl1Qn4SY8X2aS1
      sYITwBU4e0Bl5b2h9IFAaGxNgdjZWshkISgSQi/zQNTCe3UoH1sMJa2pLQB58JWpI1pbSFKWrQqn
      TkNmQQi3Zs5KpYjE6MVXzCt9l+uCugUsA3PQm4gjxO/b26vkGwBJNS1EXEfqi5kDoT8GbgYSmrOl
      UGN4vmTiAvLKWRzCLomVIwxD7wycGMZM1kECLAdVQFWlYsGpciLFuZldMGYclk8Q8hF6Gcd1+A9W
      Jeb3U1SGNzZWqK4Shgv4UbLEVARoU9EcJCgCyljj6yUj6I4akzUPxO0UzIOJbilyfyO+rEndAVqk
      BKzS+sDnJ4bNTIhq8TaebKaNKyboCa6uA13VWILGgtZDQFzFHFo/uAe0GDatnasIQm8a8UswM4fo
      vXLWW/k5+IwARy5o4GZQvCS/wbIJbwCa8vtsSVEDgJasPZlARIGfCGaVBhFNhCTL01nN7xxISXAP
      DMAx8GxotbvXVqskcxRQpZdQTqfUf9YhU4BCFpR6uYyDPy3JTecNmmlNgfcwCMoqV5FMBD5LEcZZ
      YjHyZkIloGJo8yn5YglX7zs5ny+pPUrNqdBs/TIRsni9YbcD8Yvew1+fU8eHXovbiJwlDX7duMBl
      /BJRfqop72NWp8rNs6SP7ohI0A05oKKzCqZXa6aW4VCzMCu05i9OUJExcKKjoAeK2XkgBZBTrgwJ
      LsY24dBs4UAo507gQWEUG8DNgkCcUjLgvCx19PEwBvKKkHwQ2c04Da7JncxkDEWskEWDFybUDkCu
      K1xF4dz5BuhMpQmxS4PN7a2a5ZK1AEbAHBNLWrPZgOD0Fn6MH0uaeKGIXZGlW8Q0CE0qGyMazzwt
      TTTSYx/5/I7WE6EvIvKYGN8ciAec60lq1HlCOIxjMmZghbXPJvVnYHtKyBZy6TznSxF6N0xHJdKI
      mNBeO7zz4YIbnCsSWMaUhBAcsfNYcXNxIFaxvWaJHmKJoQCcUpJD+fIMVp/OPI1OfDEAnTFhuCqn
      zFVRyOAKgVMJSptPWEbKH316syJeZ3NSrfbOk8FRaCZKF4hDl1AshucFLAuoJwjIdWEFCy1ZOODy
      gaV8FF5UtsuqBJxPzEnlFOdZTYXCBC4NaxgzVKpO0KjUosowfNnf/LInTteiSF20C+uYhLfhO6pw
      LVKHDjxWtq0d6KHpecWn7VwL4fFziwoBtVr2jlweiPvVONMlQyoVh3mOwOcA9cVZlS4Vtm6tGmpV
      mSlZRoYJyrqCbQARgq5EYuB02WCAShKj4KVjW8ysTdwGKdZf8VFHiPR0rJFUaSBr6gQ3vonlyNik
      Ch/UZpY7U17EVXLN5g/JQGFz60hovzJ0i3zED1uhkXbEm/W5ABTBh1OgB0yTtty3TRT7pW9M3QtD
      WOF0JBK0HZe+lA12O2zKaPoI0fCOiv1E1ygartOEhPe4VUtnoUEodBhetwYsZ12o1o30i3O4q1Jk
      nT6acQ6rTpgsicUMUrAaQhg/4MhQOD9zTMatuwml2swe5YL6k/WxHLOmJ3OuDJGmNnljmGRVf/VC
      mhryXhuqNYhEJT990kpOB61kGI5f55inEpO6b8H5fqtjQeQ8SWFehBDvH4H6kVm2+iKptdCLRBIY
      OthEcJq1b9SCYlvO4dDwhKvsLRB878yWBq1l/L55JTINdaEZR7BBriySvL5P5onzsIrmBJaSvjQN
      +ptUFHjcgBr1D4/+/WL0qfpMnc82VqcQ/3gx+vuL7/4gOvmsfhmOhXQinqQtVzeSNo6SxP9V6ffE
      xR5Dqn3q+SNxUnHfto4zQdIztZo+8Tv7IWpvwCTlbcf1ESdZjTyD0Ho3NkC5QQYs/kTg8DqvXLPB
      w7N3dMY+OBS1xK6FgRtPSp/IcIc0HMT6A03tW2GDjdb96cO32parkt+Iq1c3RLt61VNcqqh3Vat0
      Sm9J4FG1vTUcnpI68PJ5gA1wIHVu1lsDIUhhfUhymzVNx94HkKLWtV+RFO5/kdb9L1K9/9XWP83H
      szXH2DTb1uDG9XOOA0BrOV4d/d2l6CfXbugc02Uv6udRktH5o0vRH1z68NPNr9iK47JcXRfhxnLD
      Tl613nqucUoXGuayuUmycd3Ex1lPtgcjM0ShQc2zzQMGj4fmWkp9WuS9o309YWS2B+ItNdfK91jq
      2BaOA3Rx6obKyOwMxN0Jn3tSgyVXBdPGxFKJ3K/yIEzdbk/0hFmxJcXlTL4vdhByUHxeGZndAR2e
      kfedxjXtuU4SffPDS4kHinrTQeU1uYVDfjqkoUFrt29SfaKgsnf9JRo5jofbO+1Tlf09yHIfYQgw
      ATfeqQ3wQJepAld9QdwP4fcLlE26cLYUDmLoTsq0kPmsfRrD10L4nJQPamppqUejBgO2ZRAnUZPd
      vWttca5vr4lzCBaiar4Wa9RtjoAIWO1Vv4pEO60yI4ai+bktvjoyYcnXKe/wWqHGd1qB9g7IU9rX
      i8bU41blmbeUaGwtWYPTktTkezVBTTMNNoE5luIyH0LIOUiBhL1CE3jha42QK7GFVors+Z0hD7cJ
      /kU5XB7TbZczZ6t37+l7pXJ/qiKWlF3UB3a9etctUqf7Nhjkb9ps3q6iSX6BSnAq3byqbskGo24N
      nqegKfrQEfcyMDefgRSUFDduTbO97Y+6glJZiaQeUV8boexsdZhUH5DTl3DEDHbUSKlWvluoxvWR
      di4NpnYgb1oCsdHO2B3TZfjetxRC64fyFVfx6RB3iB2l8qPu3bq7OqFGnTJc06x9aM66G9dci/A1
      dU06AwIvdKha3k79soKq0j4sa4FBBeNa3zXG3rn3Ix0qXfryDaS6mNQTEnflqSb23aSG9II6iM//
      80L0Yn3HpXVjrPPPF6JvX3h0xj2jjWtkZ95/Wbt0tbphdXaa+uGDzwgy53xw3i3OteH1NcbHj49E
      9EpYoyI5/BaOS3uCUN559uVvP3f02SbU+RHNNbww5N8uHHWbG0C1C52+lfr5qLM5Rif1ZaI4y9P+
      /u7uUS/66c1Ra0HYdaKrFyO6mYRI/MEzX7vwzIVnnul87/mz7uZ+/nf+5Llf+9O/uNq9mPXvvPbn
      P3vz66fu5u7/1pKv5B7WP57ezX16N/fp3dynd3Of3s19ejf3R+Ru7snZqcmD6K0nSEz+p+nA5866
      CIwgTT1MAPP4SS4E/1z0Sv26/oxb9cjOk04nemF3Iq/tDW/E6tr2fjzei58kfahD/X8DdPosIWY1
      AAA=
    headers:
      accept:
      - '*/*'
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-encoding:
      - gzip
      content-length:
      - '5018'
      content-type:
      - application/x-protobuf
    method: POST
    uri: https://logfire-eu.pydantic.dev/v1/traces
  response:
    body:
      string: ''
    headers:
      connection:
      - keep-alive
      content-length:
      - '0'
      nel:
      - '{"report_to":"cf-nel","success_fraction":0.0,"max_age":604800}'
      report-to:
      - '{"group":"cf-nel","max_age":604800,"endpoints":[{"url":"https://a.nel.cloudflare.com/report/v4?s=mxVz43p3rFdabz9ZPergTGffeEFuK%2FTnGtrWkacQC%2BnIklbs2f%2FW9eNsYeAXxiOZoLpwKg5K8wabXI6fE1YrMw3iwjcoT15PLMf3cOteh6vr83H4"}]}'
      vary:
      - origin, access-control-request-method, access-control-request-headers
    status:
      code: 200
      message: OK
- request:
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '9847'
      content-type:
      - application/json
      host:
      - localhost:11434
    method: POST
    parsed_body:
      messages:
      - content: |-
          You are a knowledgeable assistant that answers questions using a document knowledge base.

          Process:
          1. Call search_documents with relevant keywords from the question
          2. Review the results and their relevance scores
          3. If needed, perform follow-up searches with different keywords (max 3 total)
          4. Provide a concise answer based strictly on the retrieved content

          The search tool returns results like:
          [chunk_abc123] (score: 0.85)
          Source: "Document Title" > Section > Subsection
          Type: paragraph
          Content:
          The actual text content here...

          [chunk_def456] (score: 0.72)
          Source: "Another Document"
          Type: table
          Content:
          | Column 1 | Column 2 |
          ...

          Each result includes:
          - chunk_id in brackets and relevance score
          - Source: document title and section hierarchy (when available)
          - Type: content type like paragraph, table, code, list_item (when available)
          - Content: the actual text

          In your response, include the chunk IDs you used in cited_chunks.

          Guidelines:
          - Base answers strictly on retrieved content - do not use external knowledge
          - Use the Source and Type metadata to understand context
          - If multiple results are relevant, synthesize them coherently
          - If information is insufficient, say: "I cannot find enough information in the knowledge base to answer this question."
          - Be concise and direct - avoid elaboration unless asked
          - Higher scores indicate more relevant results
        role: system
      - content: What innovative form of civic engagement did Bintang introduce for gathering feedback from citizens during
          Jakarta's election?
        role: user
      - content: |-
          <think>
          We need to answer: "What innovative form of civic engagement did Bintang introduce for gathering feedback from citizens during Jakarta's election?" It's a specific question about Bintang, presumably Bintang, presumably "Bintang" might be a brand? Actually, Bintang is an Indonesian "Bintang" probably a local government official. Wait context: "Jakarta's election" - maybe referring to Jakarta's governor election, or maybe a local Jakarta election? Bintang might refer to "Bintang" (meaning "star") or a name? Probably Bintang is a person, maybe a citizen or activist, or a platform called Bintang? Let's search.

          Use keywords: "Bintang innovative form civic engagement gathering feedback citizens Jakarta election"
          </think>
        role: assistant
        tool_calls:
        - function:
            arguments: '{"limit":10,"query":"Bintang innovative form civic engagement gathering feedback citizens Jakarta
              election"}'
            name: search_documents
          id: call_uw8bfctv
          type: function
      - content: |-
          [73cf7bdf-21cc-4139-b5f8-df04212da83d] (score: 0.03)
          Type: text
          Content:
          Jakarta Election Campaigns Heat Up: Here's How to Understand the System

          As election day in Jakarta draws nearer, candidates are out in force using various strategies to woo voters and prepare to exercise their democratic rights. Citizens make their voices heard as the city vibrates with life. This coverage offers valuable insight into campaign activities while offering an in-depth guide for understanding electoral processes in Jakarta.

          Initial Launch of Candidates' Campaign Plans on September 1

          After September 1st, when campaign season officially kicked off, candidates have moved swiftly to engage their bases. Amira Bintang, an upstart candidate with extensive social activism experience and promising urban development and public transportation reform as key platforms of her candidacy speech in Jakarta; incumbent Rizal Harahap relies heavily on his track record and highlights all infrastructure projects completed during his term.

          Campaign Strategies: From Digital Battlegrounds to Door-toDoor Outreach

          Campaign strategies have taken an advanced turn as candidates leverage digital media to reach a wider audience. Hashtags, viral videos, targeted ads and targeted messaging can all play an influential role in changing public opinion with just a tweet or meme. At the grassroots level candidates engage in door-to-door campaigns personalized for individual voters in an attempt to connect.

          Bintang's interactive app for gathering real-time feedback from citizens about daily commute challenges was applauded as an innovative form of civic engagement, while Harahap launched a series of webinars featuring experts discussing economic growth under his administration.

          Rallies and Persuasion

          Jakartan politicians know the power of an impassioned speech cannot be underrated, and candidates have been taking full advantage of its effectiveness at rallies. Rallies feature vibrant colors, banners and impassioned discourse in an attempt to win converts over. At one high-spirited rally on October 22, Bintang outlined her policy plans for improving education and healthcare to an appreciative crowd while Harahap's rallies often consist of shows of solidarity from various political allies united behind his plea for continuity and stability.

          Debates: Clashes Between Visions and Policies

          Debates are one of the highlights of Jakarta election campaigns, allowing candidates to outline their platforms and discuss critical issues. On November 5th, citizens witnessed an exhilarating debate between candidates Bintang and Harahap over whether the city was prepared for digital transformation in public services; Bintang advocated an aggressive move toward smart city model while Harahap advocated a more measured approach so as not to alienate less tech-savvy residents.

          Voter Engagement: Making Every Vote Count

          Ensuring every eligible voter is engaged and informed remains an ongoing challenge for Jakartans. Civil society groups and independent bodies host workshops and publish voter guides to inform voters of their rights and choices, while an annual democracy festival such as that held on November 20 featured interactive exhibits on Jakarta's electoral history as well as mock voting booths for first-time voters.

          Campaign Financing: Transparency and Accountability

          Campaign financing has always been a contentious topic in elections, and this election cycle is no exception. Bintang's campaign, funded largely through crowdfunders online supporters, stands in stark contrast with Harahap's sophisticated machine backed by both private donors and party funds. To protect democratic decision making processes from any

          undue influences on decision-making processes, Jakarta Election Commission mandated strict reporting and transparency measures during campaign financing decisions.

          Before Election Day: Submit Final Appeals Now

          As election day nears, candidates make their last appeals to voters. Bintang plans a visit through key neighborhoods while Harahap plans a final rally scheduled for late November. Both camps are honing their messaging and policy proposals while encouraging supporters to make an appearance at polling booths on November 8th.

          Polling Day: The Final Act of Campaign Activities

          On December 6th, voting booths across Jakarta will open their doors, signalling the culmination of weeks of intense campaigning. Voters will cast their vote and candidates await results that depend on how effective their strategies, speeches and outreach initiatives have been.

          Jakarta's vibrant election campaign offers an insight into its flourishing democracy. As the city looks ahead to an exciting new chapter in its political history, electoral processes demonstrate the significance of people-power in shaping our collective futures.
        role: tool
        tool_call_id: call_uw8bfctv
      - content: "<think>\nWe have a chunk id 73cf7bdf-21cc-4139-b5f8-df04212da83d. This chunk references Bintang's interactive
          app for gathering real-time feedback from citizens about daily commute challenges as an innovative form of civic
          engagement.\n\nThe question: \"What innovative form of civic engagement did Bintang introduce for gathering feedback
          from citizens during Jakarta's election?\" So the answer: She introduced an interactive app for gathering real-time
          feedback from citizens about daily commute challenges. The chunk provides the answer. Let's note the chunk id is
          73cf7bdf-21cc-4139-b5f8-df04212da83d.\n\nThus answer: An interactive app for real-time feedback on daily commute.
          Let's craft a concise answer with citation.\n</think>\n\nBintang launched an **interactive app** that lets citizens
          give real‑time feedback on their daily commute challenges during the Jakarta election.  \n\n- **Chunk used:** 73cf7bdf‑21cc‑4139‑b5f8‑df04212da83d
          \ \n- **Confidence:** 0.97"
        role: assistant
      - content: |-
          Validation feedback:
          Please include your response in a tool call.

          Fix the errors and try again.
        role: user
      model: gpt-oss
      reasoning_effort: high
      stream: false
      tool_choice: auto
      tools:
      - function:
          description: |-
            Search the knowledge base for relevant documents.

            Returns results with chunk IDs and relevance scores.
            Reference results by their chunk_id in cited_chunks.
          name: search_documents
          parameters:
            additionalProperties: false
            properties:
              limit:
                anyOf:
                - type: integer
                - type: 'null'
                default: null
              query:
                type: string
            required:
            - query
            type: object
        type: function
      - function:
          description: Answer to a search query with chunk references.
          name: final_result
          parameters:
            additionalProperties: false
            properties:
              answer:
                description: The answer to the question
                type: string
              cited_chunks:
                description: IDs of chunks used to form the answer
                items:
                  type: string
                type: array
              confidence:
                default: 1.0
                description: Confidence score for this answer (0-1)
                maximum: 1.0
                minimum: 0.0
                type: number
              query:
                description: The question that was answered
                type: string
            required:
            - query
            - answer
            type: object
        type: function
    uri: http://localhost:11434/v1/chat/completions
  response:
    headers:
      content-length:
      - '1781'
      content-type:
      - application/json
    parsed_body:
      choices:
      - finish_reason: tool_calls
        index: 0
        message:
          content: ''
          reasoning: |-
            The user says "Validation feedback: Please include your response in a tool call."

            So as per instructions, we need to provide the answer via a tool call. There is a tool called 'final_result' that we need to call. The final_result requires arguments: answer, cited_chunks, confidence, query.

            So we need to output a JSON via the functions.final_result.

            Hence we need to produce a tool call. We can't just give text. The "functions.final_result" tool is defined and we need to call it. So let's call that tool.

            The required fields:

            - answer: string
            - cited_chunks: [chunk_id(s)]
            - confidence: number between 0 and 1
            - query: string

            We need to include the answer, citing chunk 73cf7bdf-21cc-4139-b5f8-df04212da83d.

            Confidence: high, say 0.99.

            Query: The question "What innovative form of civic engagement did Bintang introduce for gathering feedback from citizens during Jakarta's election?"

            Return the tool call. No additional commentary.
          role: assistant
          tool_calls:
          - function:
              arguments: '{"answer":"Bintang launched an interactive app that allows citizens to give real‑time feedback on
                their daily commute challenges during the Jakarta election.","cited_chunks":["73cf7bdf-21cc-4139-b5f8-df04212da83d"],"confidence":0.99,"query":"What
                innovative form of civic engagement did Bintang introduce for gathering feedback from citizens during Jakarta''s
                election?"}'
              name: final_result
            id: call_2uzvnhea
            index: 0
            type: function
      created: 1766863148
      id: chatcmpl-238
      model: gpt-oss
      object: chat.completion
      system_fingerprint: fp_ollama
      usage:
        completion_tokens: 327
        prompt_tokens: 1887
        total_tokens: 2214
    status:
      code: 200
      message: OK
- request:
    body: !!binary |
      H4sIACwxUGkC/+1dXYwk11X2ep1kXbP+a+PYTgK56QT2Rz3NdM/M7sxY2Kx3ba9H8U+8a1vGvRpu
      V93uLk91VVO3qnvbzkqAFEQUEIKHKFIQioQwSojgBSEsHlAkEIgQnlCQEMggJF6Ah0hIPCAC3zn3
      3qrqnp7dCdixgzoPcXfV/Tn33O9855x7T896f/WtY94fH/e2vfu1Ssehr5phrDMZ04egVvfE9la7
      tb7WW9uQ6+c22nJzu6VaW93zwflz/rlWb2vTq3sfzlSkhipLp00d7DcjGfdz2Ve1E94HR9NskMTe
      j3q12TaxHKraPd5dyUjFxRvvE94Ds83GKtVhEtNIreb6drOFJiedoDzGfd49ebwfJ5N4zz737vdW
      RmniK62bI6zhjod+77ePo98PuYdpHmfh0Pa/0/uQb4X8pPfgfJPK/OvN1nrzvPei99H5RoHSfhqO
      Mmp4ztswDcXpoQzjhriiRqK1Jdpr7c2GaLd3Nts76xtnxKsXSUt43Gw1N8Q17ye8e9yy3JxnvdOb
      Wxsbwdp5fzOA5td6wWZrW61tbWy2z7c2tvzt9poMWud7slv7xb845j2AZU8DCZn8VRnWjMLWat8M
      vHuPfVk+9vU/91+/9/EvyM+fePOR2onh6qVH/ujHHvuN+onn3vzMr//z6W92zp70BzIT/VG2mmi9
      dmx760vTL3719OceunD9T1dqX8eH3Y97D/RVvCfDJrYtlbRgo8QPendQ592HvbtsAz3VmRqS3pIo
      kkO5C/3bV6n6mVzprDlMAhWR/u2Uuz/s3U06UGlTBkEKDddWvDujxJfRINHZbs1bsa9HSZrVjj/0
      tVd2/2vFe4jH2bOj7o1kCoky6LD2Dyve36+8Ue/lsU+i7mVJEun6jnj1jTpJjU91rWTqD/aCxM+H
      AKKuN0S9HGHvNY1u2h+ooUTrN+qQK6ShZPR8SirIQkUD9mSkFfWsPnyjDoHSKX/KpiMzXZaGcb9+
      A22jcBhm/DJQPZlH9DnOowivZDx9rmfkdB1DGElfpdSzfEjN6zeu3aDhaPlhqgLqZie+hseuadJ9
      TfkZT1xBK725whoQ2UAJsqJIBX0lulIr0UtSkcIax4CUKDTU7MSd+AWV5Wms8VpDci0mYTYQ/gCG
      KJ6+pIWMA9fTV0L7Cdo1qVdPpYoeuX7dKU0cpqbvXhiIMBZ+mKlgj5/oJm1IkmMz9mgpwV4Q+tne
      vpqW2iKd+lllFzQhAVYgo8rD/TAm3RRgoHGxyTKQmSzHInPGbPbBDdJgNw+jLKyA55qRaJRne4Q8
      GpTe1cvHVtnFqPbxAvj1QkBpz2jjFtA7FFtz+3kVG8mWgO9QLix6ImlH9EQRPCqYqIDRvD5sOPNW
      ZAmjxA1+yFDV3Vs0IOEj6ZkN1yLXKqCBgbUhj24lwUAYZ6gPsx73SKapnJp5k7gXBoSuOaNqNdcO
      ov5i0drAk8GeDUKnKXF6bbV1hkEir4fDfFgMNAxj+32Nv5fGOOySgR5ijKWSF5glvbwJsyyw2gvF
      lkhhOEzwPFVLTJ25vfNWZBB9ZBsCdocjgoWzBDUcRTJTFcqLomSC59cz26YyqXkXDhFRzL28sftR
      774o6feg7KYeyZiXR96IvsCfrLiXQ92v3e3NeLjd7+wU7iyMMWpzCJeDSXTtb3a8v96BmaZJxNsE
      lKbWPDM9S8wkct3AL4O66NHLNEkYx8kYHnKsDLYJ8iHcu1BxH3MQlYoAfPc4mJ0CAfwnTYLcN0js
      S9gCgV30lAq60t8XPeiQqDF8XYF4g5zf7sp9iCRPaQG2ZV57jBwCOQknu9Q6pHguO2wBgzDeJ7Oa
      W4QSsTK2aXC7Izrv8co6dfF0hgdA/Ej5YQ9TFkQnu0CGm7IhRkSpQ9mNpgufder2KYYchv1BJrpg
      HtFN4bgeExf8LAfmpo1yCUQL4uk4SGKlQ3ysDgBwd3lUKThWEf0EMUrMekh6kBIm1BQvyzATrN/r
      Gany4Pow1KoYymlXGctlNUD9ZUszMJToujQEvpgubnLbutRasQizUB6ahq0u4fRQyZim64AHZNqp
      n6GBpSA39Zh43i2wqg4BjtIkgZvebiB3xMxjgK5hRiFTZ6RAPoQXbpjHxKcVbaehLw4rXkTUAVaa
      JGmgd0oJD0DuAN4WoKoA1LxGOvXZKIrc8h6Jxk6H6Y2+7eWTrW7Pz8b0+Gbhokz79gsavNExgV2n
      vtNaa3QM+ePLu7aWG3VmWAQSoR4gkpDaOIhyVTNscDMmcz0oHhklsVb/S4XYcAZvXz2/7vfOd4Pe
      arvl+6sbrfXt1e5mb2s1QDrZbrUDubUeXBOn2QWzQ10/04mvQqAdQYbSiS8aRtrpxG7pT9ili4ty
      OJJhH1q5rEBLL4528CFVQNTlZEIIfzEOgNGMglGKLK5wRkIwu1AanQjklGJON3qQyokG88lUpQ0A
      NgaTwVEB8IgRiGLQFtsGMss1bdFYpmGSA8QZ0iHVh9OmmSdJIsYJhXEcCoN5RtQfb9R1lfohYG7C
      3kANE58SKV+kZJ66KS66vR7KfddsnCAv1GIAsQKBaI6WA0xMxTjspiweu/0o7KmmuEpRjE9UAUQR
      A5EYYxnlsGEF+TXzANCYYH1GhdZiKeYQk0EY2W60QJBdGK8GaoTx+zlCJmbxvFAttWFlJinYx2bG
      GKbUKVv203FIoYT4tET8PSCfcbHQ7aliK8XzSIoRHsaUNWOzEFCJFu9YD8qsPiRymQxAN8USNEO/
      YFzQ1X7o74Nu8GRmJwcSpjeEfgKhJ2EvQ0vaGDZAq29Kf7AVF4ZhKksHAlXkI+LHrBzOKB5QxY6R
      SeuEJncMOMQb8GTIcaZBQjIMGTh52sV4gRqrKBmx3fP7vBsBCwBTrCnJ5RSbOJuYAhsPcizolMNo
      MIUTxp+SX1TQbqn7R/DZp8AU478Qvg7JLiPDGMgRpWehgdQ4hAYwC8EGE/sUOMIeAxZoALBEjEwB
      nWK0XiqB9RwuEoDGcih+JbghoEPeEjj3zYOpdMibX2zvlcJKdsST5PUvhf0wg1SPyyyLVD9NACy2
      oEtJkq5mCf1HPJdn4DV/MDNUxeB4QzNYS0xbJAPOOmHzyFBJZ5WtR0ZqrCKw8w5VEEqajyeAr5oA
      4fBZecB71oS69CCTfd2AqRHAx3if4BtQ0Of1ysDYePHABJGkA5+kgdKwYVNjR73IhtSC+Jhz3QGg
      RY3tzicjEDk2g2H1Wq4BC5FNlMrY08NBAJUZ238fG6HTJMnMsqLqOi2YMX5g9LhK/y1sRVvnLSMw
      TcAGjbgegA1yWqIhrtBoM6NYPSMVIXiJsdm8o9YmTlEztGa4A+Gj0VyMB7VGq5QQHBbtmbgtkIRB
      gGiIHIV0gjgh7hMZUeo6ggLzQDHzsRpvGX82LIs5sEfMOjQCaCIlzKDTRHWRfWOlPbgPg1q2Vig0
      CLWfa7ZTmEIMm/Wh72SCPWHmY3jLgFJBxiGdg/GxCASn0QkQz0OJuaSDPHpj7TEWoyTC2kESWDyd
      t/BejhJK5iATLQ97pKkb8ZOxZ+xsnHCMyrMT8IMGTzJPa10FI4ApcPSAzMpYQ2YcgQixNAVi591C
      JAtBERAamZvCCW/UoYxviSlojZIUkAdfxc6jVYUkZSV5qtVByEwI4Uk8ZqWSR2L0ohfzyqoehSmd
      FrAMzEHPwY8Qv7fbZfANgEQhTURcR+rzmQOhPwbuECQ05p1CjmH4kokLyMsGvnW7JNYIbhh6Z+D4
      2MxgFiTAslUFVJUpFpwyJ1KcHiQTxozG9AFcPlwv49i5f7urxPxmiDzmhXUVsquA4QJ+lCwxJQFh
      nNMYJCgcSjdE7ykj6JLq0m7uiIsRmAcDPa7I/GPxUkjqttAiJWCWSgcTn8S8zYSoCm/jyXzYWDJB
      Q3B2benKYQkas1q3DrH0OTS/NQ9o0S461DonCD0Xi2exzeyiN7NBo7Rz8BkBjkwwhplB8ZLsBtMG
      vABoyqyzIoUDAE3pLJlARI6fCKYMg4gmbJBl6MzxOztSEtwAA3C0PGvP2vUj5SzBGAlUZiSU/T6d
      P4c2UoBCJhR66SE7f5qSD53naKYyBN5jQ5BW6ZxkIvAl5GF0QixG1kyoBFRiWnxEtpjB1Fe1HI+n
      dDxKh1P2sPUlImTxRMFuO+IZY+FPjOnEh16Li/CcGTV+ItaWy/glvHw/pLiPWZ0yN8OSxrvDI0E3
      ZICKLiuYXpO4nzAcHAuzQh1/cYCKiIEDHQU9kM8eWVIAOY1UTIKLbhKwa05gQEjn9mFBthVvgB5Y
      gTikZMAZWZz3MTAG8lIbfBDZDTgMduRO2xTH5LFsFA1e6NFxAGJdoXNy59ocgA5UFBC7FNhsrzmW
      C2YcGAGzSyyZxPMHEBzewo7xYUoDTxSxK6L0BD4NQpPKuvDGA0NLvRDhsfF8ZkWzgdCT8Dyxjz47
      4irHepIO6gwhXPB92kzLCjPdeq4b2J4CsomcasP5UtizG6ajDGGET2h3Bq+Nu+ADzpIEpj4FIQRH
      rNxXfLjYFKVvdyzRgC+JyQFHFORQvDzArvcHhkZ7JhmAzpgwdD6iyFWRy+AMgUMJCpv3WUaKH014
      UxKvTkak2tAYzxCGQiNRuEAcOoVi0XyUYmcB9QAO2SVW2KEpCwdcXk0oHoUVZdW0KgDnE3NSOsVx
      VpGhMIHLmDWMEXLlAjRKtSgztD1X53s2xMFcFKFLqO08ccDLMCeqMC1SR2h5LKvutqWH4szLP7jP
      TgiDn8cpEVDltJfkdEdcybvDMGNIReLCaATHpwH1yaJMlxJbPZMNVbLMiHZG2gEyl8EWgLBOVyIw
      0GFWYIBSkljBSrtJOkiSQM+RouvFVx3W09O1RpBHlqzpJLiwTUxHm02qME5tkPDJlBGxDK55+20w
      kCajRJPQZmboFvGIaVaikVbEizWxABTBl1OgBwwTVcy3ShRbmTmYet42YYXTlYjVtp+ZVNbu24Ui
      jaZO8IaXlG8GOkfecJYmJKxHl0c6kxCEQrfh7mgg4agL2XoszeTs7vIIUafxZhzDqn0mS2KxGCGY
      gxDaN9kzpNqM7NPmutOETM1Hj3JC55PuWo5Z05A5Z4YIU4u40Q5S5l8NG6bauDex2RpEopSfulSC
      02YlGIbhuxjzQGDizi043q+cWBA59yJsL1yIsQ9L/YgsK+ciUZJALxJBoD3BJoILWfuxmpBvG7E7
      jHnAMnqzBN9YeKRBc8Vm3TwTbQ2dQjOOsAcjlSDIWzXBPHEeZgk5gKWgL4qs/no5OR7dfOcO6lm7
      0t76hIE4yqmbOyeauykS36/M7si5HCOmeqn5vriIuJJUbivBwQNVDh+Ylb2L2msyB5m94/SHY6hC
      nqY9WY8Ti9QCGdjxI4HD6DzXxQIvLF7RgnWwp6mI7YSBlfYyE6fwAai9ZzX3laE56WrOncwfvFtz
      e1lm9LE4e3ZOtLNnDYNFio6mnEr79JYE7uTttVbrgNSWdg8DrIUDqXM+nWoKQQpbhSQXWdN0q70D
      KZyuzYykcPOJtG4+kerNp6r+aTwerbilptHWmtvnDzntB2uNjn7Qf1CtL0nKa5mBnUp24PWQsnJa
      70d5oMSUiMzdDXCyL+jOgK91GDFPhtdZPypNXYSWUbTcR27BdHdt92snvQ+7EiK+yi0vXX/lpPdL
      J1/9P/MhWQYtXmgKjjsLlya+p5XVaW1XOHEbMbObA1ATVk/Ke1JriRVDhH+TM2OR3abKXKAVT9H7
      VLUQ5JQt2yhHLvqKajthywwoTrJXUDt24sZMEU1DlMURDVMn0LRrqkxi9gOC7V557lmWnBbi6mV0
      szo1d7/Mx9qzCmB6nVnxyxSUxKcyc5rJRkgANMvp1BePD4blIULyuj0+/SE0zakEzrtJTBwZgqEn
      rDnqWrgNV4sB1SEN1DvGUh2vmZISelJVGHDmCpJO6zPX+HVpisKUehRHFmssW4tasW7LUTtx5Rrd
      ga2Ehzkf4VybWOPIzFyhBT7oaRDWiR62+fVnjBAzhUDvvcssy8ZYAxWEPAvTKqpfmHohhgRGj3ZP
      285fH8eI9KrXkvN1VfN3tEb/M/eyVY8y7+oYVXxQVvEn2NJ30aV06o3OTC0VhH21Uz8KRjr1a9S3
      AAl6EjZmbqPfazQc4dr62u63VryPzJST7lW5t/a7K97vrNzcr72S5JxEyrK2kW9BC99it5bhoAtz
      0fZ2VxZlj3O1kSYpNJkBGKXVRA4I9pm/DTfRTVFD6UobjJ6qtXSduN0UL6hxqMyFgEvE7N11mB4o
      p+zE603xdI/ZhW4D4Jl4D3sJwXQ1H1lh3N1wEPY4xq9IcXoor4t14DiT0ZlOvNGkSg/2YAeiNFqz
      O9EwJ/VGSjxQdJFqVe4411aksY2nc6WiUbivoDJLsLLrt9rr1RKArc0z5JnylNitU7/kNuBqmEWA
      snhUXLG54qN09KFtIYStGqACyn4qR4Nq6QDXMHJRD7seJy1dKKhmk/fSigNns7F5rirO+faMOBcQ
      U9PRsxOLeM3WKxCwqrN+VlxMonwYi5YoPrbFZzuxnfIJSpKtJ7e+gbC0OlML26ULWZUtLKmltk6y
      AqcZqclcLFg1DUJwGbZjKk7zjbkcg49I2DM0gBHeaYRMiXeoVGTDrIxiiAD/H8Fu9qg0c+FobvXG
      yZUqNyUAs3FWY8YjlsXDaGTKQudLgWmQp+i8mM4ZjaoelwVG9Qw8D0BTrEJHfPCOsfnCPiVvU5g1
      jfaiqcuwSmUlknqEq3Ekyi8rH1w1F/WEIQ6xjyHy/9J2U1WYPjz0NMbQGsxIU4AlkwGbYzS1/c35
      t72noOxb51zKwNeZms6dOvWn3VVgj26VVMwHcDMd40WF3EUNnzkAdqTDkS10qCrWTpc7KR2hIkQa
      J8CgwuYm5ooTa+eLCqn3VUA9LyP2oECbCYmvkOkA11x9FKRn1UF8/h/HvPtdQWalvLn29jHv7469
      saAodq7meWGx5kyFcFkOvDjJuHnjBU7mkA6H/eRgprmrub9xY1d4D9s5cpLDLGEvS/bhJ2vHH3r7
      7t1PFK7OtChqxm2TP7t9t16UqzoTOvgTik95tfk2YeAqX/3hKFptr2/ttrwfmW8144l17Z6zd3kr
      3p2FO379ts8du+3YbbfV/vKnFv2apPgNyZ2QnTY9j9eObV/+hXN/+1v0A5KvPPiw+QHJg55nVOd+
      euPkfsDzuKd58SHvA/xt92PefVZQ/t6cffuR2fpeyFvMfvPC4F877p2shoi1nzvufff2sqj+vS7h
      rVbkv18D1PrBWv9XjxSecgH8TLU+Rae3tpGP39JG/u0Du7962XvI/QiKYYMEoThh+PenvO88tSzr
      XpZ1L8u6l2Xdy7LuZVn3sqx7Wda9LOtelnUvy7qXZd3Lsu5lWfeyrHtZ1r0s616WdS/Lupdl3cuy
      7mVZ97Kse1nWvSzrXpZ1L8u6l2Xdy7LuQ8u63wG6W1ZtL6u2l1Xby6rtZdX2D3jV9jt1K30UfJQ3
      0iZvswTrQvvA/uZoWUa+LCNflpEvy8iXZeT/P8rIv3FIGflXj3lvHqWM/LD60HeqOHzGTS0uCC/K
      qX/5di6n/skHPvb7Z9IvffGn39x66x9rJ17yT4hvP/Mn7fqJ7z7z0iunvvzz/zJbWL32h5/ieuoL
      7sP3sbD6k4sKq+/2TtKpIpzdHhdY/7j3sGvknvPpOGw+qNW8e9fm/lfo4xsnFunj8w82//sLX8n+
      s37iX3/znx5dab319oF/rOBnV9tGJe7D+/AfK/j2HTf5xwreusP7gzsW/WMF7+M/Qk9J2lhGJkoq
      cd7FHErGC/4WeqXDO/Jn0IvkujwHmAxCOETFBUemZI4KFbR0f7L+iH8GHUb+g/NX0PcXE+JV74Uj
      0OH3+luWIxHALf70+q34oac2gs1zm9vt89vdrbbqHuW3L45D/gep6MDi0mYAAA==
    headers:
      accept:
      - '*/*'
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-encoding:
      - gzip
      content-length:
      - '5917'
      content-type:
      - application/x-protobuf
    method: POST
    uri: https://logfire-eu.pydantic.dev/v1/traces
  response:
    body:
      string: ''
    headers:
      connection:
      - keep-alive
      content-length:
      - '0'
      nel:
      - '{"report_to":"cf-nel","success_fraction":0.0,"max_age":604800}'
      report-to:
      - '{"group":"cf-nel","max_age":604800,"endpoints":[{"url":"https://a.nel.cloudflare.com/report/v4?s=34c92eY02KlqEnB6slpRaSa3OHEEm2fCNUUYCN7Rfo9fYjV8sZJmpgjT4VuX237plAIwIhzSFZOCbyU2tL2P5Gr49xt3C%2FoiWZGCZjnbJZCDvV%2Bq"}]}'
      vary:
      - origin, access-control-request-method, access-control-request-headers
    status:
      code: 200
      message: OK
- request:
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '1828'
      content-type:
      - application/json
      host:
      - localhost:11434
    method: POST
    parsed_body:
      messages:
      - content: |
          You are evaluating whether two answers to the same question are semantically equivalent.

          EVALUATION CRITERIA:
          Rate as EQUIVALENT if:
          ✓ Both answers contain the same core factual information
          ✓ Both directly address the question asked
          ✓ The key claims and conclusions are consistent
          ✓ Any additional detail in one answer doesn't contradict the other

          Rate as NOT EQUIVALENT if:
          ✗ Factual contradictions exist between the answers
          ✗ One answer fails to address the core question
          ✗ Key information is missing that changes the meaning
          ✗ The answers lead to different conclusions or implications

          GUIDELINES:
          - Ignore minor differences in phrasing, style, or formatting
          - Focus on semantic meaning rather than exact wording
          - Consider both answers correct if they convey the same essential information
          - Be tolerant of different levels of detail if the core answer is preserved
          - Evaluate based on what a person asking this question would need to know
        role: system
      - content: |-
          QUESTION: What innovative form of civic engagement did Bintang introduce for gathering feedback from citizens during Jakarta's election?

          GENERATED ANSWER: Bintang launched an interactive app that allows citizens to give real‑time feedback on their daily commute challenges during the Jakarta election.

          EXPECTED ANSWER: Bintang introduced an interactive app for real-time feedback on daily commute challenges.
        role: user
      model: gpt-oss
      reasoning_effort: low
      stream: false
      tool_choice: auto
      tools:
      - function:
          description: The final response which ends this conversation
          name: final_result
          parameters:
            additionalProperties: false
            properties:
              equivalent:
                type: boolean
            required:
            - equivalent
            type: object
          strict: true
        type: function
    uri: http://localhost:11434/v1/chat/completions
  response:
    headers:
      content-length:
      - '923'
      content-type:
      - application/json
    parsed_body:
      choices:
      - finish_reason: tool_calls
        index: 0
        message:
          content: ''
          reasoning: 'We compare: Generated: "Bintang launched an interactive app that allows citizens to give real‑time feedback
            on their daily commute challenges during the Jakarta election." Expected: "Bintang introduced an interactive app
            for real-time feedback on daily commute challenges." They match core: interactive app for real-time feedback on
            daily commute challenges. Both mention election? Generated mentions during the Jakarta election, but expected
            doesn''t. It''s same. Equivalent.'
          role: assistant
          tool_calls:
          - function:
              arguments: '{"equivalent":true}'
              name: final_result
            id: call_qsyyucid
            index: 0
            type: function
      created: 1766863152
      id: chatcmpl-662
      model: gpt-oss
      object: chat.completion
      system_fingerprint: fp_ollama
      usage:
        completion_tokens: 109
        prompt_tokens: 388
        total_tokens: 497
    status:
      code: 200
      message: OK
version: 1