Bring in changes from main

.github/workflows/publish.yml

@@ -12,7 +12,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
     steps:
     - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
@@ -38,7 +38,7 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
-        python-version: '3.12'
+        python-version: '3.13'
         cache: pip
         cache-dependency-path: setup.py
     - name: Install dependencies

.github/workflows/test.yml

@@ -11,7 +11,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, macos-latest, windows-latest]
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
         pydantic: ["==1.10.2", ">=2.0.0"]
     steps:
     - uses: actions/checkout@v4

docs/plugins/directory.md

@@ -7,7 +7,8 @@ The following plugins are available for LLM. Here's {ref}`how to install them <i
 
 These plugins all help you run LLMs directly on your own computer:
 
-- **[llm-llama-cpp](https://github.com/simonw/llm-llama-cpp)** uses [llama.cpp](https://github.com/ggerganov/llama.cpp) to run models published in the GGUF format.
+
+- **[llm-gguf](https://github.com/simonw/llm-gguf)** uses [llama.cpp](https://github.com/ggerganov/llama.cpp) to run models published in the GGUF format.
 - **[llm-mlc](https://github.com/simonw/llm-mlc)** can run local models released by the [MLC project](https://mlc.ai/mlc-llm/), including models that can take advantage of the GPU on Apple Silicon M1/M2 devices.
 - **[llm-gpt4all](https://github.com/simonw/llm-gpt4all)** adds support for various models released by the [GPT4All](https://gpt4all.io/) project that are optimized to run locally on your own machine. These models include versions of Vicuna, Orca, Falcon and MPT - here's [a full list of models](https://observablehq.com/@simonw/gpt4all-models).
 - **[llm-mpt30b](https://github.com/simonw/llm-mpt30b)** adds support for the [MPT-30B](https://huggingface.co/mosaicml/mpt-30b) local model.
@@ -52,6 +53,7 @@ If an API model host provides an OpenAI-compatible API you can also [configure L
 - **[llm-cmd](https://github.com/simonw/llm-cmd)** accepts a prompt for a shell command, runs that prompt and populates the result in your shell so you can review it, edit it and then hit `<enter>` to execute or `ctrl+c` to cancel.
 - **[llm-python](https://github.com/simonw/llm-python)** adds a `llm python` command for running a Python interpreter in the same virtual environment as LLM. This is useful for debugging, and also provides a convenient way to interact with the LLM {ref}`python-api` if you installed LLM using Homebrew or `pipx`.
 - **[llm-cluster](https://github.com/simonw/llm-cluster)** adds a `llm cluster` command for calculating clusters for a collection of embeddings. Calculated clusters can then be passed to a Large Language Model to generate a summary description.
+- **[llm-jq](https://github.com/simonw/llm-jq)** lets you pipe in JSON data and a prompt describing a `jq` program, then executes the generated program against the JSON.
 
 ## Just for fun
 

setup.py

@@ -64,5 +64,5 @@ def get_long_description():
             "types-setuptools",
         ]
     },
-    python_requires=">=3.8",
+    python_requires=">=3.9",
 )

tests/test_keys.py

@@ -52,6 +52,9 @@ def test_keys_list(monkeypatch, tmpdir, args):
     assert result2.output.strip() == "openai"
 
 
+@pytest.mark.httpx_mock(
+    assert_all_requests_were_expected=False, can_send_already_matched_responses=True
+)
 def test_uses_correct_key(mocked_openai_chat, monkeypatch, tmpdir):
     user_dir = tmpdir / "user-dir"
     pathlib.Path(user_dir).mkdir()

tests/test_templates.py

@@ -133,19 +133,21 @@ def test_templates_prompt_save(templates_path, args, expected_prompt, expected_e
             "Summarize this: Input text",
             None,
         ),
-        (
+        pytest.param(
             "boo",
             ["-s", "s"],
             None,
             None,
             "Error: Cannot use -t/--template and --system together",
+            marks=pytest.mark.httpx_mock(assert_all_responses_were_requested=False),
         ),
-        (
+        pytest.param(
             "prompt: 'Say $hello'",
             [],
             None,
             None,
             "Error: Missing variables: hello",
+            marks=pytest.mark.httpx_mock(assert_all_responses_were_requested=False),
         ),
         (
             "prompt: 'Say $hello'",
@@ -183,4 +185,4 @@ def test_template_basic(
     else:
         assert result.exit_code == 1
         assert result.output.strip() == expected_error
-        mocked_openai_chat.reset(assert_all_responses_were_requested=False)
+        mocked_openai_chat.reset()