Skip to content

Instantly share code, notes, and snippets.

@simonw

simonw/plugin.md Secret

Created May 4, 2025 20:54
Show Gist options
  • Select an option

  • Save simonw/4f545ecb347884d1d923dbc49550b8b0 to your computer and use it in GitHub Desktop.

Select an option

Save simonw/4f545ecb347884d1d923dbc49550b8b0 to your computer and use it in GitHub Desktop.

2025-05-04T19:11:56 conversation: 01jtebdce63p76q37m0pnwvt60 id: 01jtebdce8cwefh24t2c3ck0qk

Model: openai/o4-mini

Prompt

-- none --

Prompt fragments

c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4
Apache License
                           Version 2.0, January 2004
                        http://www.apache.org/licenses/

   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

   1. Definitions.

      "License" shall mean the terms and conditions for use, reproduction,
      and distribution as defined by Sections 1 through 9 of this document.

      "Licensor" shall mean the copyright owner or entity authorized by
      the copyright owner that is granting the License.

      "Legal Entity" shall mean the union of the acting entity and all
      other entities that control, are controlled by, or are under common
      control with that entity. For the purposes of this definition,
      "control" means (i) the power, direct or indirect, to cause the
      direction or management of such entity, whether by contract or
      otherwise, or (ii) ownership of fifty percent (50%) or more of the
      outstanding shares, or (iii) beneficial ownership of such entity.

      "You" (or "Your") shall mean an individual or Legal Entity
      exercising permissions granted by this License.

      "Source" form shall mean the preferred form for making modifications,
      including but not limited to software source code, documentation
      source, and configuration files.

      "Object" form shall mean any form resulting from mechanical
      transformation or translation of a Source form, including but
      not limited to compiled object code, generated documentation,
      and conversions to other media types.

      "Work" shall mean the work of authorship, whether in Source or
      Object form, made available under the License, as indicated by a
      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the
      editorial revisions, annotations, elaborations, or other modifications
      represent, as a whole, an original work of authorship. For the purposes
      of this License, Derivative Works shall not include works that remain
      separable from, or merely link (or bind by name) to the interfaces of,
      the Work and Derivative Works thereof.

      "Contribution" shall mean any work of authorship, including
      the original version of the Work and any modifications or additions
      to that Work or Derivative Works thereof, that is intentionally
      submitted to Licensor for inclusion in the Work by the copyright owner
      or by an individual or Legal Entity authorized to submit on behalf of
      the copyright owner. For the purposes of this definition, "submitted"
      means any form of electronic, verbal, or written communication sent
      to the Licensor or its representatives, including but not limited to
      communication on electronic mailing lists, source code control systems,
      and issue tracking systems that are managed by, or on behalf of, the
      Licensor for the purpose of discussing and improving the Work, but
      excluding communication that is conspicuously marked or otherwise
      designated in writing by the copyright owner as "Not a Contribution."

      "Contributor" shall mean Licensor and any individual or Legal Entity
      on behalf of whom a Contribution has been received by Licensor and
      subsequently incorporated within the Work.

   2. Grant of Copyright License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      copyright license to reproduce, prepare Derivative Works of,
      publicly display, publicly perform, sublicense, and distribute the
      Work and such Derivative Works in Source or Object form.

   3. Grant of Patent License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      (except as stated in this section) patent license to make, have made,
      use, offer to sell, sell, import, and otherwise transfer the Work,
      where such license applies only to those patent claims licensable
      by such Contributor that are necessarily infringed by their
      Contribution(s) alone or by combination of their Contribution(s)
      with the Work to which such Contribution(s) was submitted. If You
      institute patent litigation against any entity (including a
      cross-claim or counterclaim in a lawsuit) alleging that the Work
      or a Contribution incorporated within the Work constitutes direct
      or contributory patent infringement, then any patent licenses
      granted to You under this License for that Work shall terminate
      as of the date such litigation is filed.

   4. Redistribution. You may reproduce and distribute copies of the
      Work or Derivative Works thereof in any medium, with or without
      modifications, and in Source or Object form, provided that You
      meet the following conditions:

      (a) You must give any other recipients of the Work or
          Derivative Works a copy of this License; and

      (b) You must cause any modified files to carry prominent notices
          stating that You changed the files; and

      (c) You must retain, in the Source form of any Derivative Works
          that You distribute, all copyright, patent, trademark, and
          attribution notices from the Source form of the Work,
          excluding those notices that do not pertain to any part of
          the Derivative Works; and

      (d) If the Work includes a "NOTICE" text file as part of its
          distribution, then any Derivative Works that You distribute must
          include a readable copy of the attribution notices contained
          within such NOTICE file, excluding those notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed
          as part of the Derivative Works; within the Source form or
          documentation, if provided along with the Derivative Works; or,
          within a display generated by the Derivative Works, if and
          wherever such third-party notices normally appear. The contents
          of the NOTICE file are for informational purposes only and
          do not modify the License. You may add Your own attribution
          notices within Derivative Works that You distribute, alongside
          or as an addendum to the NOTICE text from the Work, provided
          that such additional attribution notices cannot be construed
          as modifying the License.

      You may add Your own copyright statement to Your modifications and
      may provide additional or different license terms and conditions
      for use, reproduction, or distribution of Your modifications, or
      for any such Derivative Works as a whole, provided Your use,
      reproduction, and distribution of the Work otherwise complies with
      the conditions stated in this License.

   5. Submission of Contributions. Unless You explicitly state otherwise,
      any Contribution intentionally submitted for inclusion in the Work
      by You to the Licensor shall be under the terms and conditions of
      this License, without any additional terms or conditions.
      Notwithstanding the above, nothing herein shall supersede or modify
      the terms of any separate license agreement you may have executed
      with Licensor regarding such Contributions.

   6. Trademarks. This License does not grant permission to use the trade
      names, trademarks, service marks, or product names of the Licensor,
      except as required for reasonable and customary use in describing the
      origin of the Work and reproducing the content of the NOTICE file.

   7. Disclaimer of Warranty. Unless required by applicable law or
      agreed to in writing, Licensor provides the Work (and each
      Contributor provides its Contributions) on an "AS IS" BASIS,
      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
      implied, including, without limitation, any warranties or conditions
      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
      PARTICULAR PURPOSE. You are solely responsible for determining the
      appropriateness of using or redistributing the Work and assume any
      risks associated with Your exercise of permissions under this License.

   8. Limitation of Liability. In no event and under no legal theory,
      whether in tort (including negligence), contract, or otherwise,
      unless required by applicable law (such as deliberate and grossly
      negligent acts) or agreed to in writing, shall any Contributor be
      liable to You for damages, including any direct, indirect, special,
      incidental, or consequential damages of any character arising as a
      result of this License or out of the use or inability to use the
      Work (including but not limited to damages for loss of goodwill,
      work stoppage, computer failure or malfunction, or any and all
      other commercial damages or losses), even if such Contributor
      has been advised of the possibility of such damages.

   9. Accepting Warranty or Additional Liability. While redistributing
      the Work or Derivative Works thereof, You may choose to offer,
      and charge a fee for, acceptance of support, warranty, indemnity,
      or other liability obligations and/or rights consistent with this
      License. However, in accepting such obligations, You may act only
      on Your own behalf and on Your sole responsibility, not on behalf
      of any other Contributor, and only if You agree to indemnify,
      defend, and hold each Contributor harmless for any liability
      incurred by, or claims asserted against, such Contributor by reason
      of your accepting any such warranty or additional liability.

   END OF TERMS AND CONDITIONS

   APPENDIX: How to apply the Apache License to your work.

      To apply the Apache License to your work, attach the following
      boilerplate notice, with the fields enclosed by brackets "[]"
      replaced with your own identifying information. (Don't include
      the brackets!)  The text should be enclosed in the appropriate
      comment syntax for the file format. We also recommend that a
      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

   Copyright [yyyy] [name of copyright owner]

   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.
   You may obtain a copy of the License at

       http://www.apache.org/licenses/LICENSE-2.0

   Unless required by applicable law or agreed to in writing, software
   distributed under the License is distributed on an "AS IS" BASIS,
   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   See the License for the specific language governing permissions and
   limitations under the License.
76b5b21267fdc0d6ee512ab67bc99b323574c71bcd3a1eb55a3fed9d16d48c54
import llm
import html
import httpx
import json
import re
from typing import Dict, List, Any


@llm.hookimpl
def register_fragment_loaders(register):
    register("hn", hacker_news_loader)


def hacker_news_loader(argument: str) -> llm.Fragment:
    try:
        response = httpx.get(f"https://hn.algolia.com/api/v1/items/{argument}")
        response.raise_for_status()
        data = response.json()
    except Exception as ex:
        raise ValueError(f"Could not load Hacker News {argument}: {str(ex)}")
    return llm.Fragment(
        process_hn_comments(data),
        source=f"https://news.ycombinator.com/item?id={argument}",
    )


def convert_hn_to_thread_path(
    json_data: Dict[str, Any], path: str = "", result: List[str] = None
) -> List[str]:
    """
    Convert Hacker News JSON hierarchy to thread path notation.

    Args:
        json_data: The JSON data from HN API
        path: Current thread path (used in recursion)
        result: Accumulator for formatted comments

    Returns:
        List of formatted comments in thread path notation
    """
    if result is None:
        result = []

    # Handle root node
    if not path:
        # Root node needs special handling as it might not be in the standard format
        if "text" in json_data:  # It's a comment
            comment_text = clean_html_content(json_data.get("text", ""))
            result.append(f"[1] {json_data.get('author', 'Anonymous')}: {comment_text}")
            current_path = "1"
        else:  # It's a story or top-level item
            title = json_data.get("title", "")
            result.append(f"[1] {json_data.get('author', 'Anonymous')}: {title}")
            current_path = "1"
    else:
        current_path = path

    # Process children recursively
    if "children" in json_data and json_data["children"]:
        for i, child in enumerate(json_data["children"], 1):
            child_path = f"{current_path}.{i}" if current_path else f"{i}"

            # Handle the comment text, unescape HTML entities and clean HTML
            comment_text = clean_html_content(child.get("text", ""))

            result.append(
                f"[{child_path}] {child.get('author', 'Anonymous')}: {comment_text}"
            )

            # Process this child's children
            convert_hn_to_thread_path(child, child_path, result)

    return result


def clean_html_content(text: str) -> str:
    """
    Clean HTML content by unescaping entities and removing HTML tags.

    Args:
        text: HTML text to clean

    Returns:
        Cleaned text
    """
    if not text:
        return ""

    # First unescape HTML entities
    text = html.unescape(text)

    # Replace paragraph tags with newlines
    text = text.replace("<p>", "\n").replace("</p>", "")

    # Remove link tags but keep the link text
    text = re.sub(r"<a\s+href=[^>]*>(.*?)</a>", r"\1", text)

    # Remove all other HTML tags
    text = re.sub(r"<[^>]*>", "", text)

    return text


def process_hn_comments(json_str: str) -> str:
    """
    Process the JSON string from HN API and return thread path notation.

    Args:
        json_str: JSON string from HN API

    Returns:
        Formatted string with thread path notation
    """
    try:
        json_data = json.loads(json_str) if isinstance(json_str, str) else json_str
        formatted_comments = convert_hn_to_thread_path(json_data)
        return "\n\n".join(formatted_comments)
    except Exception as e:
        return f"Error processing JSON: {str(e)}"
cb0b0b1aae76cbe7f7ba5644f3f54f62bd4322b233cab628c95adf4c01481fbe
[project]
name = "llm-hacker-news"
version = "0.1"
description = "LLM plugin for pulling content from Hacker News"
readme = "README.md"
authors = [{name = "Simon Willison"}]
license = "Apache-2.0"
classifiers = []
requires-python = ">=3.9"
dependencies = [
    "llm>=0.24"
]

[build-system]
requires = ["setuptools"]
build-backend = "setuptools.build_meta"

[project.urls]
Homepage = "https://github.com/simonw/llm-hacker-news"
Changelog = "https://github.com/simonw/llm-hacker-news/releases"
Issues = "https://github.com/simonw/llm-hacker-news/issues"
CI = "https://github.com/simonw/llm-hacker-news/actions"

[project.entry-points.llm]
hacker_news = "llm_hacker_news"

[project.optional-dependencies]
test = ["pytest", "pytest-httpx"]
49255a891b377ccaba61a01026c98680de5f83d38795593d3658ffa91bc1280f # llm-hacker-news

PyPI Changelog Tests License

LLM plugin for pulling content from Hacker News

For background on how this works:

Installation

Install this plugin in the same environment as LLM.

llm install llm-hacker-news

Usage

You can feed a full conversation thread from Hacker News into LLM using the hn: fragment with the ID of the conversation. For example:

llm -f hn:43615912 'summary with illustrative direct quotes'

Item IDs can be found in the URL of the conversation thread.

Development

To set up this plugin locally, first checkout the code. Then create a new virtual environment:

cd llm-hacker-news
python -m venv venv
source venv/bin/activate

Now install the dependencies and test dependencies:

pip install -e '.[test]'

To run the tests:

python -m pytest
98769434d2c6001edd8f9cd236d0a137c37732d0796873c1c759927addfdf7fd
.venv
__pycache__/
*.py[cod]
*$py.class
venv
.eggs
.pytest_cache
*.egg-info
.DS_Store
.vscode
dist
build
fd9ae3faccb5bb2227ef436c186a560df2b04809bfa1273ed1278920560a130b
import llm
from llm_hacker_news import hacker_news_loader


def test_hacker_news_loader(httpx_mock):
    httpx_mock.add_response(json=EXAMPLE)
    fragment = hacker_news_loader("123456")
    assert isinstance(fragment, llm.Fragment)
    assert fragment.source == "https://news.ycombinator.com/item?id=123456"
    assert str(fragment) == (
        '[1] BeakMaster: Fish Spotting Techniques\n\n'
        '[1.1] CoastalFlyer: The dive technique works best when hunting in shallow waters.\n\n'
        '[1.1.1] PouchBill: Agreed. Have you tried the hover method near the pier?\n\n'
        '[1.1.2] WingSpan22: My bill gets too wet with that approach.\n\n'
        '[1.1.2.1] CoastalFlyer: Try tilting at a 40° angle like our Australian cousins.\n\n'
        '[1.2] BrownFeathers: Anyone spotted those "silver fish" near the rocks?\n\n'
        '[1.2.1] GulfGlider: Yes! They\'re best caught at dawn.\nJust remember: swoop > grab > lift'
    )


EXAMPLE = {
    "author": "BeakMaster",
    "title": "Fish Spotting Techniques",
    "children": [
        {
            "author": "CoastalFlyer",
            "text": "The dive technique works best when hunting in shallow waters.",
            "children": [
                {
                    "author": "PouchBill",
                    "text": "Agreed. Have you tried the hover method near the pier?",
                    "children": [],
                },
                {
                    "author": "WingSpan22",
                    "text": "My bill gets too wet with that approach.",
                    "children": [
                        {
                            "author": "CoastalFlyer",
                            "text": "Try tilting at a 40° angle like our Australian cousins.",
                            "children": [],
                        }
                    ],
                },
            ],
        },
        {
            "author": "BrownFeathers",
            "text": "Anyone spotted those &quot;silver fish&quot; near the rocks?",
            "children": [
                {
                    "author": "GulfGlider",
                    "text": "Yes! They're best caught at dawn.<p>Just remember: <code>swoop &gt; grab &gt; lift</code>",
                    "children": [],
                }
            ],
        },
    ],
}
fd7da2a5c82824ad71ed3e70e6f72082e37c860bdafec56be8a95c39142c108f
name: Publish Python Package

on:
  release:
    types: [created]

permissions:
  contents: read

jobs:
  test:
    runs-on: ubuntu-latest
    strategy:
      matrix:
        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
    steps:
    - uses: actions/checkout@v4
    - name: Set up Python ${{ matrix.python-version }}
      uses: actions/setup-python@v5
      with:
        python-version: ${{ matrix.python-version }}
        cache: pip
        cache-dependency-path: pyproject.toml
    - name: Install dependencies
      run: |
        pip install -e '.[test]'
    - name: Run tests
      run: |
        python -m pytest
  deploy:
    runs-on: ubuntu-latest
    needs: [test]
    environment: release
    permissions:
      id-token: write
    steps:
    - uses: actions/checkout@v4
    - name: Set up Python
      uses: actions/setup-python@v5
      with:
        python-version: "3.13"
        cache: pip
        cache-dependency-path: pyproject.toml
    - name: Install dependencies
      run: |
        pip install setuptools wheel build
    - name: Build
      run: |
        python -m build
    - name: Publish
      uses: pypa/gh-action-pypi-publish@release/v1
1a564a200569424b8ef1276a16daa3d1697dc5d615adc85a9f51a18cd453020c
name: Test

on: [push, pull_request]

permissions:
  contents: read

jobs:
  test:
    runs-on: ubuntu-latest
    strategy:
      matrix:
        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
    steps:
    - uses: actions/checkout@v4
    - name: Set up Python ${{ matrix.python-version }}
      uses: actions/setup-python@v5
      with:
        python-version: ${{ matrix.python-version }}
        cache: pip
        cache-dependency-path: pyproject.toml
    - name: Install dependencies
      run: |
        pip install -e '.[test]'
    - name: Run tests
      run: |
        python -m pytest

System

write a new plugin called llm_video_frames.py which takes video:path-to-video.mp4 and creates a temporary directory which it then populates with one frame per second of that video using ffmpeg - then it returns a list of [llm.Attachment(path="path-to-frame1.jpg"), ...] - it should also support passing video:video.mp4?fps=2 to increase to two frames per second, and if you pass ?timestamps=1 or &timestamps=1 then it should add a text timestamp to the bottom right conner of each image with the mm:ss timestamp of that frame (or hh:mm:ss if more than one hour in) and the filename of the video without the path as well.

Response

# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

import os
import tempfile
import subprocess
import glob
from urllib.parse import urlparse, parse_qs
import llm

@llm.hookimpl
def register_fragment_loaders(register):
    register("video", video_frame_loader)

def video_frame_loader(argument: str):
    """
    Fragment loader "video:<path>?fps=N&timestamps=1"
    - extracts frames at `fps` per second (default 1)
    - if `timestamps=1`, overlays "filename hh:mm:ss" at bottom-right
    """
    # parse out path and query params
    parts = urlparse(argument)
    video_path = parts.path
    params = parse_qs(parts.query)
    fps = int(params.get("fps", ["1"])[0])
    timestamps = params.get("timestamps", ["0"])[0] in ("1", "true", "True")
    if not os.path.exists(video_path):
        raise ValueError(f"Video file not found: {video_path}")

    # prepare temp dir
    out_dir = tempfile.mkdtemp(prefix="llm_video_frames_")
    # base filename for overlay
    base_name = os.path.basename(video_path)

    # build ffmpeg filter
    vf_parts = [f"fps={fps}"]
    if timestamps:
        # overlay filename and timestamp (hh:mm:ss) at bottom-right
        # %% escapes to a single % in ffmpeg expression
        text = f"{base_name} %%{{pts\\:hms}}"
        draw = (
            "drawtext=fontcolor=white:fontsize=24:box=1:boxcolor=black@0.5"
            f":text='{text}':x=w-tw-10:y=h-th-10"
        )
        vf_parts.append(draw)
    vf = ",".join(vf_parts)

    # output pattern
    pattern = os.path.join(out_dir, "frame_%05d.jpg")

    # run ffmpeg
    cmd = [
        "ffmpeg", "-v", "error",
        "-i", video_path,
        "-vf", vf,
        "-q:v", "2",
        pattern
    ]
    try:
        subprocess.run(cmd, check=True)
    except subprocess.CalledProcessError as e:
        raise RuntimeError(f"ffmpeg failed: {e}")

    # collect frames
    files = sorted(glob.glob(os.path.join(out_dir, "frame_*.jpg")))
    attachments = [ llm.Attachment(path=f) for f in files ]
    return attachments

Explanation:

• We register a fragment loader under the prefix “video”.
• The loader parses the argument as a URL to extract the path, fps (default 1), and a boolean timestamps flag.
• We create a temporary output directory with tempfile.mkdtemp().
• We build an ffmpeg “-vf” filter string: first fps=N, then, if requested, a DrawText filter that overlays filename hh:mm:ss in the bottom-right corner.
• We invoke ffmpeg to output JPEG frames (-q:v 2 for good quality) named frame_00001.jpg, etc.
• Finally we glob the output directory, wrap each frame in llm.Attachment, and return the list.

Token usage:

5,018 input, 2,208 output, {"output_tokens_details": {"reasoning_tokens": 1408}}

@simonw

simonw commented May 4, 2025

Copy link
Copy Markdown
Author

llm -m openai/o4-mini -f github:simonw/llm-hacker-news -s 'write a new plugin called llm_video_frames.py which takes video:path-to-video.mp4 and creates a temporary directory which it then populates with one frame per second of that video using ffmpeg - then it returns a list of [llm.Attachment(path="path-to-frame1.jpg"), ...] - it should also support passing video:video.mp4?fps=2 to increase to two frames per second, and if you pass ?timestamps=1 or &timestamps=1 then it should add a text timestamp to the bottom right conner of each image with the mm:ss timestamp of that frame (or hh:mm:ss if more than one hour in) and the filename of the video without the path as well.' -o reasoning_effort high

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment