[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-78609":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":10,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":21,"hasPages":23,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":25,"readmeContent":26,"aiSummary":27,"trendingCount":15,"starSnapshotCount":15,"syncStatus":28,"lastSyncTime":29,"discoverSource":30},78609,"Math-To-Manim","HarleyCoops\u002FMath-To-Manim","HarleyCoops","Create Epic Math and Physics Animations & Study Notes From Text and Images.","",null,"Python",2356,249,18,0,59,88,274,177,29.19,false,"main",true,[],"2026-06-12 02:03:47","\u003Cdiv align=\"center\">\n\n\u003Ca href=\"https:\u002F\u002Fwww.star-history.com\u002F#HarleyCoops\u002FMath-To-Manim&Date\">\n  \u003Cpicture>\n    \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=HarleyCoops\u002FMath-To-Manim&type=Date&theme=dark\" \u002F>\n    \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=HarleyCoops\u002FMath-To-Manim&type=Date\" \u002F>\n    \u003Cimg alt=\"Star History Chart\" src=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=HarleyCoops\u002FMath-To-Manim&type=Date\" width=\"100%\" \u002F>\n  \u003C\u002Fpicture>\n\u003C\u002Fa>\n\n# Math to Manim\n\n### Ask a question -> reverse reasoning -> Manim movie\n\n[![Python 3.10+](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPython-3.10%2B-3b82f6)](https:\u002F\u002Fwww.python.org\u002F)\n[![Manim CE](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FManim-CE-f59e0b)](https:\u002F\u002Fwww.manim.community\u002F)\n[![OpenAI Agents SDK](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FOpenAI-Agents%20SDK-111827)](https:\u002F\u002Fopenai.github.io\u002Fopenai-agents-python\u002F)\n[![Hermes assisted](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FHermes-agent%20assisted-8b5cf6)](#hermes-agent)\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-22c55e)](LICENSE)\n\n[Motion showcase](docs\u002Fshowcase\u002FREADME.md) · [Architecture](docs\u002FARCHITECTURE.md) · [Prime RL](docs\u002FPRIME_INTELLECT_RL.md) · [Roadmap](docs\u002FROADMAP.md) · [Agent guide](AGENTS.md)\n\n\u003Cbr \u002F>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Fcontinuous-geometric-picture.gif\" alt=\"GRPO semantic manifold: sibling completions become a geometric policy update across the full scene\" width=\"48%\" \u002F>\n  \u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Fqed-minkowski-epic-3d.gif\" alt=\"QED and Minkowski spacetime: light cones, electromagnetic waves, gauge symmetry, and renormalization flow on an off-white 3D stage\" width=\"48%\" \u002F>\n\u003C\u002Fp>\n\n\u003Cbr \u002F>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Frhombicosidodecahedron.gif\" alt=\"Rhombicosidodecahedron animation\" width=\"24%\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Fcosmic-gravity-3d.gif\" alt=\"Cosmic gravity 3D animation\" width=\"24%\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Fcontinuous-geometric-picture.gif\" alt=\"Full GRPO semantic manifold animation\" width=\"24%\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Fderivative-visualization.gif\" alt=\"Derivative visualization animation\" width=\"24%\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Fprolip-scene.gif\" alt=\"ProLIP animation\" width=\"24%\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Florenz-attractor.gif\" alt=\"Lorenz attractor animation\" width=\"24%\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Fhopf-fibration.gif\" alt=\"Hopf fibration animation\" width=\"24%\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Ffourier-epicycles.gif\" alt=\"Fourier epicycles animation\" width=\"24%\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Fteaching-hopf.gif\" alt=\"Teaching Hopf animation\" width=\"24%\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Fbrownian-finance.gif\" alt=\"Brownian finance animation\" width=\"24%\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Fradius-of-convergence.gif\" alt=\"Radius of convergence animation\" width=\"24%\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Fwhiskering-exchange.gif\" alt=\"Whiskering exchange animation\" width=\"24%\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n**Math-To-Manim turns short prompts into reverse-reasoned lesson plans, typed pipeline artifacts, generated Manim code, and reusable visual explanations.**\n\n[**Browse the local GIF gallery →**](docs\u002Fshowcase\u002FREADME.md)\n\n\u003Cbr \u002F>\n\n\u003Cimg src=\"docs\u002Fassets\u002Freverse-reasoning-pipeline.svg\" alt=\"Reverse reasoning pipeline diagram showing the actual Math-To-Manim stage agents, artifacts, validation gate, render path, review, package, and manifest\" width=\"100%\" \u002F>\n\n\u003Cbr \u002F>\n\n\u003Cem>Code-grounded workflow: every run stays inspectable from prompt to artifacts to render.\u003C\u002Fem>\n\n\u003C\u002Fdiv>\n\n---\n\n## What this is\n\n**Math to Manim** is for the moment when a learner asks, “Can you show me why?” A teacher, tutor, parent, or guardian can type a question and get back a visual explanation plan: the concept, the missing prerequisites, the order of ideas, the screen beats, the generated Manim code, and optionally the rendered video.\n\nThe input can be short, but the product is the explanation: what the learner needs to understand, what should appear first, where the aha moment lives, and which visual metaphor makes the idea feel inevitable.\n\nMath-To-Manim proves that calculus, topology, chaos, spacetime, stochastic finance, and ML concepts can become useful mathematical motion when agents plan the explanation before they write code.\n\nThis repo turns that idea into a durable agent pipeline:\n\n- a prerequisite-story pipeline inspired by the original reverse knowledge tree;\n- typed Pydantic artifacts between every stage;\n- OpenAI Agents SDK-compatible adapters for planning and generation;\n- optional Codex CLI-backed codegen for subscription-authenticated iteration;\n- a reproducible `runs\u002F\u003Crun_id>\u002F` bundle for every generation;\n- static validation, render metadata, review artifacts, and manifests that are easy to inspect in CI or by another agent.\n\nThe design principle is simple: **story before symbols, geometry before algebra, artifacts before side effects.**\n\n---\n\n## Reverse reasoning pipeline\n\nA normal text-to-code demo jumps from request to Python. Math-To-Manim takes the long way on purpose: it reasons backward from the final concept to the prerequisites, then walks forward through a teachable visual sequence.\n\nThe code path is explicit in [`math_to_manim\u002Fpipeline\u002Frunner.py`](math_to_manim\u002Fpipeline\u002Frunner.py). `AnimationPipeline.generate()` runs a fixed stage chain: `IntentAgent`, `PrerequisiteGraphAgent`, `CurriculumAgent`, `MathAgent`, `StoryboardAgent`, `SceneSpecAgent`, `ManimCodeAgent`, `StaticReviewAgent`, `RenderAgent`, `VideoReviewAgent`, and `PublisherAgent`.\n\n| Stage | Why it exists | Artifact |\n| --- | --- | --- |\n| Intent | Clarify what the learner is really asking. | `intent.json` |\n| Reverse prerequisites | Build the knowledge graph needed before the target idea. | `knowledge_graph.json` |\n| Curriculum | Turn the graph into a teachable order. | `curriculum.json` |\n| Math packet | Select definitions, equations, assumptions, and examples. | `math_packet.json` |\n| Storyboard | Decide the screen beats before code exists. | `storyboard.json` |\n| Scene spec | Compile the visual plan into Manim objects, animations, timing, and camera notes. | `scene_spec.json` |\n| Code, validation, render, review | Generate runnable Manim, gate it with static checks, render when allowed, and package the evidence. | `generated_scene.py`, reports, manifest |\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fassets\u002Frender-repair-loop.svg\" alt=\"Render validation and bounded repair loop diagram showing static review, render skip, Manim subprocess, repair from frozen scene spec, video review, and publisher package\" width=\"100%\" \u002F>\n\u003C\u002Fp>\n\nThat gives every run a memory: JSON contracts, generated code, render results, review notes, and a manifest. The output is not just a video; it is an inspectable path from **question** to **understanding** to **animation**.\n\nFor current editable-video status and the planned prompt\u002Fspec\u002Fcode edit loop, see the [roadmap](docs\u002FROADMAP.md).\n\n---\n\n## Prime Intellect RL repair loop\n\nMath-To-Manim is also becoming a Prime Intellect reinforcement-learning environment. The first RL target is not \"make the whole video in one shot.\" It is the repair move that matters most when generated animation code fails: take the typed scene plan, the broken `generated_scene.py`, and validation\u002Frender evidence, then return corrected Manim Python that is safe, sparse, and more likely to render.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fassets\u002Fprime-intellect\u002Fprimeintellect-logo.svg\" alt=\"Prime Intellect logo\" width=\"220\" \u002F>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fassets\u002Fprime-intellect\u002Fm2m2-prime-rl-loop.svg\" alt=\"Diagram of the Math-To-Manim Prime Intellect RL repair loop from generated Manim code through static reward checks back to corrected renderable Manim Python\" width=\"100%\" \u002F>\n\u003C\u002Fp>\n\n\u003Ctable>\n\u003Ctr>\n\u003Ctd width=\"33%\">\u003Cimg src=\"docs\u002Fassets\u002Fprime-intellect\u002Fprimeintellect-lab.png\" alt=\"Prime Intellect lab field visual, used here to represent the environment task space\" \u002F>\u003C\u002Ftd>\n\u003Ctd width=\"33%\">\u003Cimg src=\"docs\u002Fassets\u002Fprime-intellect\u002Fprimeintellect-reward-hacking-cover.png\" alt=\"Prime Intellect reward hacking visual, used here to represent reward design pressure\" \u002F>\u003C\u002Ftd>\n\u003Ctd width=\"33%\">\u003Cimg src=\"docs\u002Fassets\u002Fprime-intellect\u002Fprimeintellect-compute-bg.png\" alt=\"Prime Intellect compute corridor visual, used here to represent hosted training and inference\" \u002F>\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cb>Run bundle as environment\u003C\u002Fb>\u003C\u002Ftd>\n\u003Ctd>\u003Cb>Reward function as critic\u003C\u002Fb>\u003C\u002Ftd>\n\u003Ctd>\u003Cb>Policy update as repair engine\u003C\u002Fb>\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftable>\n\nThe current hub environment is `harleycooper\u002Fmath-to-manim`. A repair task carries the original prompt, typed `scene_spec`, generated Manim Python, static-validation report, and render\u002Frecovery evidence when available. The model must return one strict `GeneratedCode` JSON block. The Verifiers reward checks whether the proposed code parses, defines the expected Manim scene, avoids unsafe imports and calls, preserves expected math terms, and reduces obvious text\u002Flayout crowding hazards.\n\n```text\ngenerated_scene.py + scene_spec + validation\u002Frender evidence\n  -> Prime Intellect Verifiers environment\n  -> model proposes corrected GeneratedCode JSON\n  -> static reward checks parseability, scene shape, safety, terms, layout\n  -> hosted RL updates the repair policy\n  -> corrected, renderable Manim Python flows back into M2M2 recovery\n```\n\nThat keeps the fast RL loop text-and-AST based while the slower Manim renderer remains the audit gate. The intended result is a model that learns the house style of this repo: cinematic but readable scenes, sparse formulas, staged captions, safe Manim code, and scripts that are much more likely to render on the first recovery attempt.\n\nCurrent hosted-training status: the environment action passes on Prime, the hub package is published as `harleycooper\u002Fmath-to-manim@0.1.1`, a 1-step smoke completed, and a 25-step W&B-enabled pilot has been launched on `Qwen\u002FQwen3.5-35B-A3B`.\n\nSee the full integration notes in [`docs\u002FPRIME_INTELLECT_RL.md`](docs\u002FPRIME_INTELLECT_RL.md).\n\n---\n\n## Clone and run\n\n### 1. Clone\n\nWindows PowerShell:\n\n```powershell\ngit clone https:\u002F\u002Fgithub.com\u002FHarleyCoops\u002FMath-To-Manim.git\ncd Math-To-Manim\npython -m venv .venv\n.\\.venv\\Scripts\\Activate.ps1\npython -m pip install -U pip\npython -m pip install -e \".[dev]\"\npython -m pytest\n```\n\nmacOS \u002F Linux \u002F WSL:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FHarleyCoops\u002FMath-To-Manim.git\ncd Math-To-Manim\npython3 -m venv .venv\nsource .venv\u002Fbin\u002Factivate\npython -m pip install -U pip\npython -m pip install -e \".[dev]\"\npython -m pytest\n```\n\n### 2. Run a no-API smoke test\n\nThis proves the CLI, artifact contracts, and validators are wired before you spend model or render time:\n\n```bash\nmath-to-manim generate \"Explain why derivatives are slopes\" --deterministic --no-render\n```\n\nEquivalent module form:\n\n```bash\npython -m math_to_manim.cli generate \"Explain why derivatives are slopes\" --deterministic --no-render\n```\n\n### 3. Generate with model calls\n\nSet an OpenAI key and choose a model if desired:\n\n```bash\nexport OPENAI_API_KEY=\"sk-...\"\nexport OPENAI_MODEL=\"gpt-4.1\"\nmath-to-manim generate \"Explain Fourier epicycles as rotating vectors\" --no-render\n```\n\nPowerShell:\n\n```powershell\n$env:OPENAI_API_KEY = \"sk-...\"\n$env:OPENAI_MODEL = \"gpt-4.1\"\nmath-to-manim generate \"Explain Fourier epicycles as rotating vectors\" --no-render\n```\n\n### 4. Install render extras when you want MP4 output\n\nPython render dependency:\n\n```bash\npython -m pip install -e \".[dev,render]\"\n```\n\nSystem render dependencies are also needed for real Manim output, especially FFmpeg and LaTeX for `MathTex`. On Debian\u002FUbuntu\u002FWSL:\n\n```bash\n.\u002Fscripts\u002Fbootstrap-render.sh\n```\n\nThe package list lives in [`requirements-system.txt`](requirements-system.txt).\n\n---\n\n## Codex CLI codegen path\n\nMath-To-Manim can keep the typed planning pipeline while sending the Manim codegen and repair loop through a locally authenticated Codex CLI session.\n\nCheck Codex first:\n\n```bash\ncodex --version\ncodex exec \"Say ready from inside this repo\"\n```\n\nThen route codegen through Codex:\n\n```bash\nmath-to-manim generate \"Explain derivatives as slopes with a cinematic tangent-line reveal\" \\\n  --codegen-provider codex-cli \\\n  --codex-full-auto \\\n  --style cinematic \\\n  --quality l\n```\n\nEarlier planning stages remain on the typed adapters; only the generated-code and repair stages move first. That makes the migration incremental instead of all-or-nothing.\n\n---\n\n## What lands on disk\n\nA generation writes a self-contained run bundle:\n\n```text\nruns\u002F\u003Crun_id>\u002F\n  request.json\n  intent.json\n  knowledge_graph.json\n  curriculum.json\n  math_packet.json\n  storyboard.json\n  scene_spec.json\n  generated_code.json\n  generated_scene.py\n  validation_report.json\n  render_result.json\n  review_report.json\n  recovery_manifest.json  # after recover-render\n  draft_review\u002F\n    draft_review.md\n    contact_sheet.png\n    frames\u002F\n  animation_package.json\n  manifest.json\n```\n\nAfter editing `generated_scene.py` inside a run bundle, rerun the recovery path:\n\n```bash\nmath-to-manim recover-render runs\u002F\u003Crun_id> --quality l\n```\n\nThat command refreshes validation, render, review, draft-review assets, and\n`recovery_manifest.json` without regenerating upstream planning artifacts.\n\nPackage layout:\n\n```text\nmath_to_manim\u002F\n  agents\u002F      # stage adapters\n  schemas\u002F     # versioned artifact contracts\n  tools\u002F       # graph, validation, rendering, video, artifact helpers\n  pipeline\u002F    # orchestration, tracing, repair loop\n  rendering\u002F   # Manim and FFmpeg wrappers\n  review\u002F      # static and visual review scoring\n```\n\n---\n\n## Hermes Agent\n\nHermes is the contributor\u002Foperator agent around this repository. It is not imported by Math-To-Manim and is not a runtime dependency; it uses the repo the way a developer would: read files, search code, patch docs and code, run terminal checks, inspect generated artifacts, review frames or GIFs, track todos, delegate larger work, and preserve stable context through skills.\n\nThat makes Hermes useful for maintaining the reverse-reasoning pipeline without becoming part of it. A Hermes session can inspect `AGENTS.md`, `pyproject.toml`, schemas, tests, and `runs\u002F\u003Crun_id>\u002F` bundles; run `pytest`, CLI smoke commands, Manim, FFmpeg, and git checks; then verify that docs, code, and showcase media still match the artifact contracts.\n\nRepo-local Hermes skills live under [`hermes\u002Fskills\u002F`](hermes\u002Fskills\u002F). The old Claude `.\u002Fskill` path is historical; current contributor guidance is in [`AGENTS.md`](AGENTS.md), with launch notes in [`docs\u002FHERMES_LEARNS_MANIM.md`](docs\u002FHERMES_LEARNS_MANIM.md).\n\n---\n\n## Motion showcase\n\nSixteen curated GIFs are tracked under [`docs\u002Fshowcase\u002Fassets\u002F`](docs\u002Fshowcase\u002Fassets\u002F) as the **art direction target** for Math-To-Manim's visual explanations.\n\n\u003Ctable>\n\u003Ctr>\n\u003Ctd width=\"33%\">\u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Frhombicosidodecahedron.gif\" alt=\"Rhombicosidodecahedron\" \u002F>\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd width=\"33%\">\u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Fhopf-fibration.gif\" alt=\"Hopf fibration\" \u002F>\u003C\u002Fa>\u003C\u002Ftd>\n\u003Ctd width=\"33%\">\u003Ca href=\"docs\u002Fshowcase\u002FREADME.md\">\u003Cimg src=\"docs\u002Fshowcase\u002Fassets\u002Florenz-attractor.gif\" alt=\"Lorenz attractor\" \u002F>\u003C\u002Fa>\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd>\u003Cb>Geometry as spectacle\u003C\u002Fb>\u003C\u002Ftd>\n\u003Ctd>\u003Cb>Topology as choreography\u003C\u002Fb>\u003C\u002Ftd>\n\u003Ctd>\u003Cb>Chaos as intuition\u003C\u002Fb>\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftable>\n\nSee the full gallery with descriptions: **[`docs\u002Fshowcase\u002FREADME.md`](docs\u002Fshowcase\u002FREADME.md)**.\n\n### Make a README-sized GIF from a render\n\n```bash\nMP4=\"media\u002Fvideos\u002Fyour_scene\u002F480p15\u002FYourScene.mp4\"\n\nffmpeg -y -ss 95 -t 24 -i \"$MP4\" \\\n  -vf \"fps=12,scale=720:-1:flags=lanczos,split[s0][s1];[s0]palettegen=max_colors=96[p];[s1][p]paletteuse=dither=bayer:bayer_scale=5\" \\\n  docs\u002Fshowcase\u002Fassets\u002Fyour-clip.gif\n```\n\nAdjust `-ss` and `-t` to capture the teaching beat you want.\n\n---\n\n## License\n\nMIT.\n","Math-To-Manim 是一个用于从文本和图像生成数学和物理动画及学习笔记的工具。该项目利用 Python 语言，结合 Manim 社区版进行动画制作，并通过 OpenAI Agents SDK 和 Hermes 代理辅助实现从问题到反向推理再到动画生成的过程。其核心功能包括将复杂的数学概念和物理现象可视化，支持用户自定义输入以生成个性化的教学材料。适合教育工作者、学生以及对数学物理感兴趣的个人使用，在教学演示、在线课程开发和个人学习中都能发挥重要作用。",2,"2026-06-11 03:56:58","high_star"]