Setup basic github actions and cleaning up pyproject.toml

.github/workflows/quality.yml

@@ -0,0 +1,39 @@
+name: Verify Code Quality
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+concurrency:
+    group: ${{ github.workflow }}-${{ github.event_name == 'pull_request' && github.event.pull_request.number || github.ref_name }}
+    cancel-in-progress: true
+
+jobs:
+  quality:
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    strategy:
+      matrix:
+        python-version: ['3.10', '3.11', '3.12'] # Need to add 3.13 once we resolve outlines issues.
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install uv and set the python version
+        uses: astral-sh/setup-uv@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          enable-cache: true
+      - name: pre-commit cache key
+        run: echo "PY=$(python -VV | sha256sum | cut -d' ' -f1)" >> "$GITHUB_ENV"
+      - uses: actions/cache@v4
+        with:
+          path: ~/.cache/pre-commit
+          key: pre-commit|${{ env.PY }}|${{ hashFiles('.pre-commit-config.yaml') }}
+      - name: Install dependencies
+        run: uv sync --frozen --all-extras
+      - name: Check style and run tests
+        run: pre-commit run --all-files
+      - name: Send failure message
+        if: failure()  # This step will only run if a previous step failed
+        run: echo "The quality verification failed. Please run precommit "

docs/dev/constrained_decoding.md

@@ -10,7 +10,7 @@ The `m` framework currently uses the `format` argument to pydantic schemas, **ou
 
 > If a keyword had meaning across multiple types of backends, and if it means the same thing in all of those backends but has different names, then we use the `@@@`-style args so that the user can pass these args across all backends in the same way. Otherwise, the arguments in model_args are passed along verbatim.
 
-This argues for `@@@format@@@` as opposed to a dedicated `format` option in the method signature. Or, in the alternative, for an entir re-think of ModelArgs.
+This argues for `@@@format@@@` as opposed to a dedicated `format` option in the method signature. Or, in the alternative, for an entire re-think of ModelArgs.
 
 ## Integration with grammar-targeted LLMs
 

docs/examples/notebooks/compositionality_with_generative_slots.ipynb

@@ -33,8 +33,13 @@
     "!nohup ollama serve >/dev/null 2>&1 &\n",
     "\n",
     "from IPython.display import HTML, display\n",
-    "def set_css(): display(HTML('\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n'))\n",
-    "get_ipython().events.register('pre_run_cell',set_css)"
+    "\n",
+    "\n",
+    "def set_css():\n",
+    "    display(HTML(\"\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n\"))\n",
+    "\n",
+    "\n",
+    "get_ipython().events.register(\"pre_run_cell\", set_css)"
    ]
   },
   {
@@ -76,15 +81,18 @@
    "source": [
     "from mellea import generative\n",
     "\n",
+    "\n",
     "# The Summarizer Library\n",
     "@generative\n",
     "def summarize_meeting(transcript: str) -> str:\n",
     "    \"\"\"Summarize the meeting transcript into a concise paragraph of main points.\"\"\"\n",
     "\n",
+    "\n",
     "@generative\n",
     "def summarize_contract(contract_text: str) -> str:\n",
     "    \"\"\"Produce a natural language summary of contract obligations and risks.\"\"\"\n",
     "\n",
+    "\n",
     "@generative\n",
     "def summarize_short_story(story: str) -> str:\n",
     "    \"\"\"Summarize a short story, with one paragraph on plot and one paragraph on braod themes.\"\"\""
@@ -109,10 +117,12 @@
     "def propose_business_decision(summary: str) -> str:\n",
     "    \"\"\"Given a structured summary with clear recommendations, propose a business decision.\"\"\"\n",
     "\n",
+    "\n",
     "@generative\n",
     "def generate_risk_mitigation(summary: str) -> str:\n",
     "    \"\"\"If the summary contains risk elements, propose mitigation strategies.\"\"\"\n",
     "\n",
+    "\n",
     "@generative\n",
     "def generate_novel_recommendations(summary: str) -> str:\n",
     "    \"\"\"Provide a list of novel recommendations that are similar in plot or theme to the short story summary.\"\"\""
@@ -135,16 +145,19 @@
    "outputs": [],
    "source": [
     "# Compose the libraries.\n",
-    "from typing import Literal  # noqa: E402\n",
+    "from typing import Literal\n",
+    "\n",
     "\n",
     "@generative\n",
     "def has_structured_conclusion(summary: str) -> Literal[\"yes\", \"no\"]:\n",
     "    \"\"\"Determine whether the summary contains a clearly marked conclusion or recommendation.\"\"\"\n",
     "\n",
+    "\n",
     "@generative\n",
     "def contains_actionable_risks(summary: str) -> Literal[\"yes\", \"no\"]:\n",
     "    \"\"\"Check whether the summary contains references to business risks or exposure.\"\"\"\n",
     "\n",
+    "\n",
     "@generative\n",
     "def has_theme_and_plot(summary: str) -> Literal[\"yes\", \"no\"]:\n",
     "    \"\"\"Check whether the summary contains both a plot and thematic elements.\"\"\""
@@ -166,7 +179,7 @@
    },
    "outputs": [],
    "source": [
-    "from mellea import start_session  # noqa: E402\n",
+    "from mellea import start_session\n",
     "\n",
     "m = start_session()"
    ]

docs/examples/notebooks/context_example.ipynb

@@ -33,8 +33,13 @@
     "!nohup ollama serve >/dev/null 2>&1 &\n",
     "\n",
     "from IPython.display import HTML, display\n",
-    "def set_css(): display(HTML('\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n'))\n",
-    "get_ipython().events.register('pre_run_cell',set_css)"
+    "\n",
+    "\n",
+    "def set_css():\n",
+    "    display(HTML(\"\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n\"))\n",
+    "\n",
+    "\n",
+    "get_ipython().events.register(\"pre_run_cell\", set_css)"
    ]
   },
   {
@@ -80,6 +85,7 @@
    "outputs": [],
    "source": [
     "from mellea import LinearContext, start_session\n",
+    "\n",
     "m = start_session(ctx=LinearContext())\n",
     "m.chat(\"Make up a math problem.\")\n",
     "m.chat(\"Solve your math problem.\")\n",

docs/examples/notebooks/document_mobject.ipynb

@@ -33,8 +33,13 @@
     "!nohup ollama serve >/dev/null 2>&1 &\n",
     "\n",
     "from IPython.display import HTML, display\n",
-    "def set_css(): display(HTML('\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n'))\n",
-    "get_ipython().events.register('pre_run_cell',set_css)"
+    "\n",
+    "\n",
+    "def set_css():\n",
+    "    display(HTML(\"\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n\"))\n",
+    "\n",
+    "\n",
+    "get_ipython().events.register(\"pre_run_cell\", set_css)"
    ]
   },
   {
@@ -77,6 +82,7 @@
    "outputs": [],
    "source": [
     "from mellea.stdlib.docs.richdocument import RichDocument\n",
+    "\n",
     "rd = RichDocument.from_document_file(\"https://arxiv.org/pdf/1906.04043\")"
    ]
   },
@@ -96,7 +102,8 @@
    },
    "outputs": [],
    "source": [
-    "from mellea.stdlib.docs.richdocument import Table  # noqa: E402\n",
+    "from mellea.stdlib.docs.richdocument import Table\n",
+    "\n",
     "table1: Table = rd.get_tables()[0]\n",
     "print(table1.to_markdown())"
    ]
@@ -119,8 +126,9 @@
    },
    "outputs": [],
    "source": [
-    "from mellea import start_session  # noqa: E402\n",
-    "from mellea.backends.types import ModelOption  # noqa: E402\n",
+    "from mellea import start_session\n",
+    "from mellea.backends.types import ModelOption\n",
+    "\n",
     "m = start_session()\n",
     "for seed in [x * 12 for x in range(5)]:\n",
     "    table2 = m.transform(\n",

docs/examples/notebooks/example.ipynb

@@ -33,8 +33,13 @@
     "!nohup ollama serve >/dev/null 2>&1 &\n",
     "\n",
     "from IPython.display import HTML, display\n",
-    "def set_css(): display(HTML('\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n'))\n",
-    "get_ipython().events.register('pre_run_cell',set_css)"
+    "\n",
+    "\n",
+    "def set_css():\n",
+    "    display(HTML(\"\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n\"))\n",
+    "\n",
+    "\n",
+    "get_ipython().events.register(\"pre_run_cell\", set_css)"
    ]
   },
   {
@@ -77,6 +82,7 @@
    "outputs": [],
    "source": [
     "import mellea\n",
+    "\n",
     "m = mellea.start_session()"
    ]
   },

docs/examples/notebooks/instruct_validate_repair.ipynb

@@ -33,8 +33,13 @@
     "!nohup ollama serve >/dev/null 2>&1 &\n",
     "\n",
     "from IPython.display import HTML, display\n",
-    "def set_css(): display(HTML('\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n'))\n",
-    "get_ipython().events.register('pre_run_cell',set_css)"
+    "\n",
+    "\n",
+    "def set_css():\n",
+    "    display(HTML(\"\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n\"))\n",
+    "\n",
+    "\n",
+    "get_ipython().events.register(\"pre_run_cell\", set_css)"
    ]
   },
   {
@@ -66,9 +71,9 @@
    "source": [
     "## Import Mellea and Specify Requirements\n",
     "We create 3 requirements:\n",
-    "- 1st requirement (r1) will be validated by LLM-as-a-judge on the output of the instruction. This is the default behavior.\n",
-    "- 2nd requirement (r2) uses a function that takes the output of a sampling step and returns a boolean value indicating successful or unsuccessful validation. While the validation_fn parameter requires to run validation on the full session context, Mellea provides a wrapper for simpler validation functions (simple_validate(fn: Callable[[str], bool])) that take the output string and return a boolean as seen in this case.\n",
-    "- 3rd requirement is a check(). Checks are only used for validation, not for generation. Checks aim to avoid the \"do not think about B\" effect that often primes models (and humans) to do the opposite and \"think\" about B."
+    "- First requirement (r1) will be validated by LLM-as-a-judge on the output of the instruction. This is the default behavior.\n",
+    "- Second requirement (r2) uses a function that takes the output of a sampling step and returns a boolean value indicating successful or unsuccessful validation. While the validation_fn parameter requires to run validation on the full session context, Mellea provides a wrapper for simpler validation functions (simple_validate(fn: Callable[[str], bool])) that take the output string and return a boolean as seen in this case.\n",
+    "- Third requirement is a check(). Checks are only used for validation, not for generation. Checks aim to avoid the \"do not think about B\" effect that often primes models (and humans) to do the opposite and \"think\" about B."
    ]
   },
   {
@@ -79,9 +84,10 @@
    },
    "outputs": [],
    "source": [
+    "import mellea\n",
     "from mellea.stdlib.requirement import check, req, simple_validate\n",
-    "import mellea  # noqa: E402\n",
-    "from mellea.stdlib.sampling import RejectionSamplingStrategy  # noqa: E402\n",
+    "from mellea.stdlib.sampling import RejectionSamplingStrategy\n",
+    "\n",
     "requirements = [\n",
     "    req(\"The email should have a salutation\"),  # == r1\n",
     "    req(\n",

docs/examples/notebooks/m_serve_example.ipynb

@@ -33,8 +33,13 @@
     "!nohup ollama serve >/dev/null 2>&1 &\n",
     "\n",
     "from IPython.display import HTML, display\n",
-    "def set_css(): display(HTML('\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n'))\n",
-    "get_ipython().events.register('pre_run_cell',set_css)"
+    "\n",
+    "\n",
+    "def set_css():\n",
+    "    display(HTML(\"\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n\"))\n",
+    "\n",
+    "\n",
+    "get_ipython().events.register(\"pre_run_cell\", set_css)"
    ]
   },
   {

docs/examples/notebooks/mcp_example.ipynb

@@ -35,8 +35,13 @@
     "!uv pip install mcp -q\n",
     "\n",
     "from IPython.display import HTML, display\n",
-    "def set_css(): display(HTML('\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n'))\n",
-    "get_ipython().events.register('pre_run_cell',set_css)"
+    "\n",
+    "\n",
+    "def set_css():\n",
+    "    display(HTML(\"\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n\"))\n",
+    "\n",
+    "\n",
+    "get_ipython().events.register(\"pre_run_cell\", set_css)"
    ]
   },
   {
@@ -76,6 +81,7 @@
    "outputs": [],
    "source": [
     "from mcp.server.fastmcp import FastMCP\n",
+    "\n",
     "from mellea import MelleaSession\n",
     "from mellea.backends import model_ids\n",
     "from mellea.backends.ollama import OllamaModelBackend\n",
@@ -100,6 +106,7 @@
    "source": [
     "mcp = FastMCP(\"Demo\")\n",
     "\n",
+    "\n",
     "@mcp.tool()\n",
     "def write_a_poem(word_limit: int) -> str:\n",
     "    \"\"\"Write a poem with a word limit.\"\"\"\n",
@@ -116,10 +123,11 @@
     "    assert isinstance(res, ModelOutputThunk)\n",
     "    return str(res.value)\n",
     "\n",
+    "\n",
     "@mcp.resource(\"greeting://{name}\")\n",
     "def get_greeting(name: str) -> str:\n",
     "    \"\"\"Get a personalized greeting\"\"\"\n",
-    "    return f\"Hello, {name}!\"    "
+    "    return f\"Hello, {name}!\""
    ]
   }
  ],

docs/examples/notebooks/model_options_example.ipynb

@@ -7,7 +7,7 @@
    },
    "source": [
     "# Model Options Example\n",
-    "This Jupyter notebook runs on Colab and demostrates specifying model options"
+    "This Jupyter notebook runs on Colab and demonstrates specifying model options"
    ]
   },
   {
@@ -33,8 +33,13 @@
     "!nohup ollama serve >/dev/null 2>&1 &\n",
     "\n",
     "from IPython.display import HTML, display\n",
-    "def set_css(): display(HTML('\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n'))\n",
-    "get_ipython().events.register('pre_run_cell',set_css)"
+    "\n",
+    "\n",
+    "def set_css():\n",
+    "    display(HTML(\"\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n\"))\n",
+    "\n",
+    "\n",
+    "get_ipython().events.register(\"pre_run_cell\", set_css)"
    ]
   },
   {

docs/examples/notebooks/sentiment_classifier.ipynb

@@ -33,8 +33,13 @@
     "!nohup ollama serve >/dev/null 2>&1 &\n",
     "\n",
     "from IPython.display import HTML, display\n",
-    "def set_css(): display(HTML('\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n'))\n",
-    "get_ipython().events.register('pre_run_cell',set_css)"
+    "\n",
+    "\n",
+    "def set_css():\n",
+    "    display(HTML(\"\\n<style>\\n pre{\\n white-space: pre-wrap;\\n}\\n</style>\\n\"))\n",
+    "\n",
+    "\n",
+    "get_ipython().events.register(\"pre_run_cell\", set_css)"
    ]
   },
   {
@@ -77,7 +82,10 @@
    "outputs": [],
    "source": [
     "from typing import Literal\n",
+    "\n",
     "from mellea import generative, start_session\n",
+    "\n",
+    "\n",
     "@generative\n",
     "def classify_sentiment(text: str) -> Literal[\"positive\", \"negative\"]:\n",
     "    \"\"\"Classify the sentiment of the input text as 'positive' or 'negative'.\"\"\""