diff --git a/.readthedocs.yaml b/.readthedocs.yaml
new file mode 100644
index 0000000..c18da2e
--- /dev/null
+++ b/.readthedocs.yaml
@@ -0,0 +1,27 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the OS, Python version, and other tools you might need
+build:
+  os: ubuntu-24.04
+  tools:
+    python: "3.13"
+
+# Build documentation in the "docs/" directory with Sphinx
+sphinx:
+   configuration: docs/source/conf.py
+
+
+format:
+   - html
+   - pdf
+# Optionally, but recommended,
+# declare the Python requirements required to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+python:
+   install:
+   - requirements: docs/source/requirements.txt
+        
diff --git a/docs/ARCHITECTURE.md b/docs/ARCHITECTURE.md
deleted file mode 100644
index a85ea59..0000000
--- a/docs/ARCHITECTURE.md
+++ /dev/null
@@ -1,138 +0,0 @@
-# Architecture
-
-*multiplex* is a modular framework for prototyping LLM-based mutation testing.
-One run mutates **one method/function** in a target project and evaluates the
-generated mutants against that project's test suite. The source language is set
-by `project.language` (`java` — the default — or `python`); see the language
-registry below.
-
-## Pipeline
-
-Orchestrated top-to-bottom by `multiplex/__main__.py`:
-
-```
-config.yml
-   │
-   ▼
-1. Load YAML config; resolve the approach's system_prompts and the language
-   (languages.get_language(project.language), default "java")
-   │
-   ▼
-2. Back up target source file to <filename>.orig
-   Delete and recreate <projectroot>/output/          ← destroys previous results
-   │
-   ▼
-3. util/extract_method.py (tree-sitter, grammar from the LanguageSpec)
-   Find method/function by name + start line
-   → writes output/original_method.<ext>   (.java / .py)
-   → returns (start_byte, end_byte) offsets into the source file
-   │
-   ▼
-4. approach/<name>/controller.main(model, output_path, prompts, language)
-   One or more LLM calls (via model.Model / LiteLLM)
-   → writes mutant files to output/<approach>-mutants/mutant_N.<ext>
-   │
-   ▼
-5. execute/{maven,defects4j,pytest_runner}.run_mutants(...)
-   For each mutant file:
-     a. restore source file from .orig backup
-     b. util/rewrite_method.py splices mutant text into the file
-        at the saved byte offsets
-     c. checks/compilable.py        — tree-sitter parse-error scan
-        checks/syntactic_equivalence.py — AST equality vs original (ignores comments)
-     d. run the project's tests (Defects4J backend only; see Status below)
-   → writes output/<approach>-mutants/mutant_summary.csv (Defects4J)
-   │
-   ▼
-6. (optional, --marv flag) util/marv.py output_marv(output_path, approach)
-   Reads original_method.java + mutant files + mutant_summary.csv
-   → writes output/marv.json (Marv mutations schema; pure Python, no marv binary)
-   │
-   ▼
-7. Restore original source file from .orig backup
-```
-
-Key mechanism: the method's **byte offsets** captured in step 3 are reused in
-step 5b to splice each mutant into a pristine copy of the file. Anything that
-changes the file between those steps invalidates the offsets.
-
-## Mutant-generation approaches (`multiplex/approach/`)
-
-Each approach is a package with a `controller.py` exposing
-`main(model, output_dir, prompts, language)`. Dispatch is an if/elif chain in
-`__main__.py` keyed on `mutation.approach`.
-
-| Approach | Strategy | LLM calls |
-|----------|----------|-----------|
-| `basic` | Single system prompt, ask for a mutant 10 times | 10 |
-| `hazop` | Chain: describe method line-by-line → mutate descriptions using HAZOP guidewords (NO/MORE/LESS/...) → implement each deviation | 2 + 1 per deviation |
-| `stpa` | Chain: describe control flow as GraphViz DOT → identify Unsafe Control Actions (UCAs) → implement each UCA | 2 + 1 per UCA |
-| `mutahunter` | Single call with AST + line-numbered source; LLM returns YAML of line-level mutations spliced in locally (prompts not bundled — licensing) | 1 |
-| `llmorpheus` | tree-sitter query finds mutation sites (conditions, loop headers, call args), each replaced by `<PLACEHOLDER>`; LLM proposes 3 replacements per site | 1 per placeholder |
-
-All five approaches are language-aware via the `language` argument (file
-extension, code fence, prompt noun). llmorpheus additionally selects its
-mutation-site query per language from `MUTATION_QUERIES` in
-`approach/llmorpheus/placeholders.py`.
-
-Intermediate artifacts are files in `output/` — approaches communicate between
-their own steps via files, not in-memory state (see artifact table below).
-
-## Execution backends (`multiplex/execute/`)
-
-Selected by `project.runtool`:
-
-- `d4j` → `defects4j.py` — the complete backend. Baselines the unmutated
-  project first (aborts if its tests fail), times the baseline run, then runs
-  each compilable mutant's tests with a timeout of 5× baseline. A surviving
-  mutant is one whose test run reports `Failing tests: 0`. Requires the
-  `defects4j` CLI and a `JDK_11` env var (see DEVELOPMENT.md).
-- `mvn` → `maven.py` — self-contained backend for plain Maven projects. Runs
-  `mvn -f <project_root> clean test`; a mutant survives if the build passes
-  (`BUILD SUCCESS`). Baselines the original first (aborts if its tests fail),
-  then per mutant does the same equivalence → rewrite → compilable → test →
-  summary flow as the Defects4J backend. Used by the runnable Java example under
-  `examples/` (see DEVELOPMENT.md § Example).
-- `pytest` → `pytest_runner.py` — self-contained backend for Python projects.
-  Runs `sys.executable -m pytest -q <project_root>` (pytest under multiplex's own
-  interpreter); a mutant survives if pytest exits 0 (all tests pass). Same
-  baseline → per-mutant flow as the Maven backend. Drives the runnable Python
-  example (`examples/config-python.yml`). Named `pytest_runner` so it does not
-  shadow the installed `pytest` package.
-
-## Language registry (`multiplex/languages/`)
-
-`get_language(project.language)` returns a `LanguageSpec` (grammar, definition
-node types, comment node types, extension, code-fence tag, prompt noun,
-mutahunter label). It is resolved once in `__main__.py` and threaded into
-`extract_method`, every approach's `main`, the checks, and the execution
-backend — so the pipeline is language-agnostic and adding a language is a
-registry entry plus prompts and an example (see docs/EXTENDING.md § Add a
-language). `project.language` defaults to `java`.
-
-## Output artifacts
-
-Everything lands under `<projectroot>/output/` (wiped at the start of each run):
-
-| Artifact | Written by |
-|----------|-----------|
-| `original_method.<ext>` | extract_method (step 3); read by every approach (`.java`/`.py`) |
-| `hazop-descriptions.txt`, `hazop-mutated-descriptions.txt` | hazop chain steps |
-| `control_diagram.txt`, `ucas.csv` | stpa chain steps |
-| `placeholders/{N_placeholder.<ext>, N_orig.<ext>, placeholders.json}` | llmorpheus site finder |
-| `<approach>-mutants/mutant_N.<ext>` | every approach's final step |
-| `<approach>-mutants/mutant_summary.csv` | maven/defects4j/pytest backends; columns `MUTANT, EQUIVALENCE, COMPILABLE, SURVIVES` |
-| `<approach>-test/<mutant>_test.txt` | defects4j backend; per-mutant test output |
-| `marv.json` | util/marv.py (`--marv` flag only); Marv-schema view of every mutant |
-
-## LLM access (`multiplex/model.py`)
-
-All LLM traffic goes through `Model.make_request(messages)`, a thin wrapper
-over LiteLLM `completion()`. Model/endpoint come from config; the API key is
-read from the environment variable *named* by `llm.token_env_var` (never stored
-in config). Azure endpoints get `AZURE_AI_API_BASE`/`AZURE_AI_API_KEY` set
-specially. To support another provider, replace or extend `model.py`.
-
-LLM responses are treated as fenced code: approaches strip a leading
-```` ```<lang> ```` fence (the tag is `language.fence`, e.g. `java`/`python`) and
-keep everything before the next ```` ``` ```` fence.
diff --git a/docs/CONFIG.md b/docs/CONFIG.md
deleted file mode 100644
index a15633e..0000000
--- a/docs/CONFIG.md
+++ /dev/null
@@ -1,61 +0,0 @@
-# Configuration Reference
-
-*multiplex* takes a single YAML config file:
-`uv run ./multiplex ./path/to/config.yml`.
-Templates: [`examples/config-java.yml`](../examples/config-java.yml),
-[`examples/config-python.yml`](../examples/config-python.yml).
-
-Only the keys the selected `mutation.approach` needs are required. `project`,
-`mutation`, and `llm` keys are always required; `system_prompts` keys are
-required per-approach (see that section). Missing required keys fail fast at
-startup with an actionable `SystemExit`, before any output is wiped.
-
-## `project`
-
-| Key | Type | Meaning |
-|-----|------|---------|
-| `language` | `java` \| `python` | Source language of the file under test. **Optional; defaults to `java`** (existing configs need no change). Selects the tree-sitter grammar, the definition node types extracted, the artifact/mutant file extension, and the code-fence/prompt wording. An unknown value fails fast at startup with a `SystemExit`. |
-| `projectroot` | path | Root of the project under test. `output/` is created (and **wiped every run**) inside it. |
-| `filename` | path | The source file containing the method/function under test (`.java` or `.py`). Backed up to `<filename>.orig` during the run. |
-| `method` | string | Name of the method/constructor (Java) or function (Python) to mutate. |
-| `line` | int | 1-based line number of the method/function **name identifier** in `filename` (not annotations/decorators above it). Both `method` and `line` must match for extraction to succeed; disambiguates overloads. |
-| `runtool` | `mvn` \| `d4j` \| `pytest` | Execution backend. `mvn` runs a plain Maven project (`mvn clean test`); `d4j` targets a Defects4J checkout (needs the `defects4j` CLI + `JDK_11`); `pytest` runs pytest under multiplex's own interpreter (`sys.executable -m pytest <projectroot>`) — a mutant survives if pytest exits 0. `mvn` drives the Java `examples/` setup and `pytest` the Python one. |
-
-## `mutation`
-
-| Key | Type | Meaning |
-|-----|------|---------|
-| `approach` | `basic` \| `hazop` \| `stpa` \| `mutahunter` \| `llmorpheus` | Mutant-generation approach. An unknown value fails fast at startup with a `SystemExit` listing the valid approaches. |
-
-## `llm`
-
-| Key | Type | Meaning |
-|-----|------|---------|
-| `model` | string | LiteLLM model string, e.g. `ollama/gpt-oss:20b`. |
-| `endpoint` | URL | LLM API endpoint, e.g. `http://127.0.0.1:11434`. If the string contains `azure`, Azure env vars are set automatically. |
-| `token_env_var` | string or empty | **Name** of the environment variable holding the API key — never the key itself. Leave empty for keyless local endpoints (e.g. Ollama). The named var must exist or startup fails with KeyError. |
-
-## `system_prompts`
-
-Multi-line YAML strings (typically `|` blocks). Only the keys used by the
-selected `mutation.approach` are required — prompts for other approaches may be
-omitted. The approach→required-keys mapping is `APPROACH_PROMPT_KEYS` in
-`multiplex/prompts.py`; a missing or empty required key raises a `SystemExit`
-naming it. User prompts are constructed in code; only system prompts live in
-config.
-
-| Key | Used by |
-|-----|---------|
-| `basic_generate_mutants` | basic |
-| `hazop_describe_process` | hazop step 1 (line-by-line description) |
-| `hazop_identify_deviations` | hazop step 2 (guideword mutation; must instruct CSV output `number, original_rule, GUIDEWORD, changed_rule`) |
-| `hazop_implement_deviations` | hazop step 3 (code generation) |
-| `stpa_describe_control_flow` | stpa step 1 (GraphViz DOT control diagram) |
-| `stpa_identify_ucas` | stpa step 2 (numbered UCA list) |
-| `stpa_implement_ucas` | stpa step 3 (code generation) |
-| `mutahunter_generate_mutants` | mutahunter — **not bundled**; users must paste Mutahunter's own prompt text (licensing restriction). Response must be YAML with `mutants: [{mutated_code, line_number}]`. |
-| `llmorpheus_system` | llmorpheus (per-placeholder replacement generation) |
-
-Output-format expectations matter: downstream parsing is brittle string/CSV/
-YAML/regex handling (see MODULE_REFERENCE.md), so prompts must pin the exact
-output format the next step expects.
diff --git a/docs/DEVELOPMENT.md b/docs/DEVELOPMENT.md
deleted file mode 100644
index 3c0623e..0000000
--- a/docs/DEVELOPMENT.md
+++ /dev/null
@@ -1,116 +0,0 @@
-# Development Guide
-
-## Setup and commands
-
-Dependency management is [uv](https://github.com/astral-sh/uv); Python >= 3.13.
-
-```bash
-uv sync -p 3.13                  # install deps incl. dev group (pytest, ruff, pylint)
-uv run pytest tests              # all tests — run from the REPO ROOT
-uv run pytest tests/checks/test_compiles.py                # one file
-uv run pytest tests/checks/test_compiles.py::test_name     # one test
-uv run ruff check .              # lint (CI uses --output-format=github)
-uv run ./multiplex ./path/to/config.yml                    # run the tool
-```
-
-- **Pin Python 3.13** (as CI does): `requires-python` allows >= 3.13, but
-  litellm's `tiktoken` dependency fails to build on 3.14.
-- Tests must run from the repo root: they reference `tests/resources/...`
-  relatively.
-- Running the tool needs a reachable LLM endpoint and a target project (Java or
-  Python, per `project.language`). `mvn` runs need Maven + a JDK; `pytest` runs
-  need pytest for the active interpreter; `d4j` runs additionally need the
-  `defects4j` CLI (expected under `./defects4j/framework/bin`) and a `JDK_11` env
-  var pointing at a JDK 11 home.
-
-CI (GitHub Actions, on push/PR to `main`): `test.yml` runs
-`uv run pytest tests` on Python 3.13; `ruff.yml` runs `uv run ruff check`.
-
-## Example
-
-Self-contained end-to-end examples live under `examples/`:
-
-```bash
-uv run ./multiplex ./examples/config-java.yml     # Java   (from the repo root)
-uv run ./multiplex ./examples/config-python.yml   # Python
-```
-
-- Target: `examples/project/java-example/` — a tiny Maven project with one method
-  (`com.example.Classifier.classify`) and JUnit tests pinning its behavior.
-- `examples/config-java.yml` uses the `basic` approach and the `mvn` runtool.
-- Prerequisites: `mvn` + a JDK 11+ on PATH (the project targets Java 11; if
-  `mvn` picks up an older JDK via `JAVA_HOME` the compile fails with "release
-  version 11 not supported"), and a running Ollama serving the model
-  named in `llm.model` (default `gpt-oss:20b`; point it at any model you have,
-  e.g. `ollama pull gpt-oss:20b`). Any LiteLLM-supported endpoint works if you
-  edit `llm`.
-- Output lands in `examples/project/java-example/output/basic-mutants/`
-  (`mutant_N.java` plus `mutant_summary.csv`). Run artifacts (`output/`,
-  `*.orig`, Maven `target/`) are git-ignored.
-- The `basic` approach makes 10 LLM calls and the `mvn` backend runs the test
-  suite once per compilable mutant, so a full run takes a few minutes (longer
-  on a slow/local model).
-- Python counterpart: `examples/config-python.yml` (`project.language: python`,
-  `pytest` runtool) mutates `classify` in
-  `examples/project/python-example/classifier.py` and evaluates each mutant with
-  pytest (run under multiplex's own interpreter). Same output layout
-  (`output/basic-mutants/mutant_N.py` +
-  `mutant_summary.csv`). Needs pytest (already provided by `uv run`) and the same
-  Ollama/LLM endpoint.
-
-## Import convention (critical)
-
-The tool is executed as a directory (`uv run ./multiplex`), which puts
-`multiplex/` itself on `sys.path`:
-
-- **Inside `multiplex/`**: flat imports, no package prefix —
-  `from model import Model`, `from util.io import write_to_file`,
-  `import approach.basic.controller as basic`.
-- **Inside `tests/`**: package-prefixed imports —
-  `from multiplex.checks.syntactic_equivalence import check_mutant_equivalent`.
-
-Using the wrong style in either place breaks at import time. This also means
-`multiplex/` modules are not importable as `multiplex.x` **and** `x` in the
-same process; keep the two worlds separate.
-
-## Conventions
-
-- tree-sitter is the universal source-analysis tool (extraction, compilability,
-  equivalence, placeholder finding); the grammar comes from the run's
-  `languages.LanguageSpec`. Versions are pinned (`tree-sitter==0.23.2`,
-  `tree-sitter-java==0.23.5`, `tree-sitter-python` 0.23.x); the code depends on
-  that API — do not bump casually.
-- Approaches communicate between their own steps via files in `output/`, not
-  in-memory state; artifact names are prefixed with the approach name.
-- LLM code responses are unfenced by stripping a leading ```` ```<lang> ````
-  fence (the tag is `language.fence`, e.g. `java`/`python`) and truncating at the
-  next ```` ``` ```` fence (`removeprefix` + `split`, see EXTENDING.md for the
-  exact two lines).
-- Mutant files are named `mutant_<N>.java` in `output/<approach>-mutants/`.
-- Status/progress reporting is `print()`-based throughout (no logging config,
-  one `logging.warning` in extract_method).
-
-## Known issues and gotchas (verified 2026-07)
-
-Bugs — fix or work around, don't replicate:
-
-_No open bugs currently tracked._
-
-Behavioral gotchas — by design (or at least current design), be aware:
-
-- `<projectroot>/output/` is **deleted without prompting** at every run start
-  (the confirmation prompt in `__main__.py` is commented out, answer
-  hard-coded to `"y"`).
-- The target source file is mutated **in place** during execution; it is
-  backed up to `<filename>.orig` and restored at run end, but a crash mid-run
-  can leave a mutant in the working tree (the `.orig` file remains for manual
-  restore).
-- "Compilable" means *parses without tree-sitter ERROR nodes* — no compiler
-  runs; type errors and unresolved symbols count as compilable.
-- An invalid `mutation.approach` value, or a missing/empty required
-  `system_prompts` key for the chosen approach, raises `SystemExit` at startup
-  (before the output wipe). Only the selected approach's prompt keys are
-  required — see `multiplex/prompts.py`.
-- Mutahunter prompts are not bundled (licensing); the user pastes them into
-  the config. Running the `mutahunter` approach without them fails fast with a
-  clear message.
diff --git a/docs/EXTENDING.md b/docs/EXTENDING.md
deleted file mode 100644
index 87755bd..0000000
--- a/docs/EXTENDING.md
+++ /dev/null
@@ -1,139 +0,0 @@
-# Extending multiplex
-
-Checklists for adding modules. Follow the import convention: inside
-`multiplex/`, import siblings **without** the `multiplex.` prefix
-(DEVELOPMENT.md § Import convention).
-
-## Add a mutant-generation approach
-
-Use `approach/basic/` as the single-prompt template or `approach/hazop/` as
-the multi-prompt-chain template.
-
-1. **Create the package** `multiplex/approach/<name>/` with `__init__.py` and
-   `controller.py` exposing:
-   ```python
-   def main(model, output_dir, prompts, language):
-       ...
-   ```
-   - `model` is a `model.Model`; call `model.make_request(messages)` with
-     OpenAI-style message dicts.
-   - `language` is a `languages.LanguageSpec` (resolved in `__main__.py`); use it
-     for anything language-specific — `language.extension`, `language.fence`,
-     `language.noun` — so your approach works for every registered language.
-   - Read the method under test via
-     `from approach.util import get_method_under_test` — call it as
-     `get_method_under_test(output_dir, language)`.
-   - Pass intermediate results between steps as files in `output_dir`
-     (convention: prefix them with your approach name).
-   - **Required output**: write final mutants to
-     `Path(output_dir, "<name>-mutants/") / f"mutant_{count}{language.extension}"`.
-     Each file must contain the complete replacement method body (it is spliced
-     verbatim over the original method's byte range). Strip LLM code fences:
-     ```python
-     mutant = mutant.removeprefix("```" + language.fence)
-     mutant = mutant.split("```", 1)[0]
-     ```
-2. **Register the prompt key(s)**: add a `"<name>": [...]` entry to
-   `APPROACH_PROMPT_KEYS` in `multiplex/prompts.py` listing the
-   `system_prompts` keys your approach reads. Only the selected approach's keys
-   are required at runtime, so users running other approaches need not define
-   yours (and vice versa). Document the keys in `docs/CONFIG.md`; adding them to
-   `examples/config-java.yml` (a commented stub is fine) is optional but helpful.
-3. **Register the dispatch branch**: add an `elif config['mutation']['approach']
-   == "<name>":` branch in `multiplex/__main__.py` calling
-   `<name>.main(model, output_path, prompts, language)`, plus the corresponding
-   `import approach.<name>.controller as <name>`.
-4. The `-mutants` directory name must equal the `mutation.approach` config
-   value — the execution backends reconstruct the path as
-   `output/<approach>-mutants/`.
-
-## Add an execution/evaluation backend
-
-Model on `multiplex/execute/defects4j.py` or `multiplex/execute/maven.py`
-(both follow the same flow; `maven.py` is the simpler, self-contained one).
-
-1. Create `multiplex/execute/<name>.py` exposing:
-   ```python
-   def run_mutants(project_root, original_file, output_path,
-                   method_start_byte, method_end_byte, duplicate, approach,
-                   language):
-   ```
-   `language` is a `languages.LanguageSpec` — use it for the artifact path and
-   the checks below.
-2. The expected loop, per mutant file in `output/<approach>-mutants/`:
-   - restore the pristine source: `shutil.copy2(duplicate, original_file)`
-     (guard on `duplicate.exists()`);
-   - `rewrite_method(original_file, method_start_byte, method_end_byte,
-     mutant_path)` — note: **4 arguments**;
-   - `check_mutant_equivalent(mutant_path,
-     language.original_method_path(output_path), language)` and
-     `check_mutant_compilable(original_file, language)` from `checks/`;
-   - if compilable, run the project's tests with your build tool and decide
-     survived/killed;
-   - collect rows and finish with `write_mutant_summary(mutants_dir, rows)`
-     (header row: `["MUTANT", "EQUIVALENCE", "COMPILABLE", "SURVIVES"]`).
-3. Register it in `multiplex/__main__.py` under a new `project.runtool` value
-   (pass `language` through to `run_mutants`).
-4. Useful pattern from defects4j: run the unmutated project first as a
-   baseline (abort if it fails), and use a multiple of its wall-clock time as
-   the per-mutant test timeout to catch infinite-loop mutants.
-
-## Add a language
-
-The pipeline is language-agnostic: the parser, checks, approaches and execution
-backends all take a `languages.LanguageSpec` resolved once in `__main__.py` from
-the `project.language` config value. Java and Python ship in
-`multiplex/languages/__init__.py`.
-
-To add a language:
-
-1. **Add the tree-sitter grammar** dependency (e.g. `tree-sitter-<lang>`) to
-   `pyproject.toml` and add a `LanguageSpec` entry to `_REGISTRY` in
-   `multiplex/languages/__init__.py`:
-   ```python
-   "<lang>": LanguageSpec(
-       name="<lang>",
-       extension=".<ext>",
-       ts_language=Language(ts_<lang>.language()),
-       def_node_types=frozenset({...}),      # nodes that denote a definition
-       comment_node_types=frozenset({...}),  # ignored by the equivalence check
-       fence="<lang>",                       # ```<lang> fence tag
-       noun="<Lang> function",               # prompt wording
-       label="<Lang>",                       # mutahunter language string
-   ),
-   ```
-   `def_node_types` are the node types `extract_method` matches (their child
-   `identifier` is compared to `project.method`); `comment_node_types` are
-   dropped when comparing ASTs for syntactic equivalence. Inspect a grammar with
-   a few lines of tree-sitter to find the right node types.
-2. **Provide a prompt set** for the language in the config's `system_prompts`
-   (see `examples/config-python.yml`). Prompt *keys* are shared across languages;
-   only the wording differs. mutahunter prompts remain user-supplied.
-3. **Add a mutation-site query for llmorpheus** if you want that approach:
-   add a `"<lang>": <QUERY>` entry to `MUTATION_QUERIES` in
-   `multiplex/approach/llmorpheus/placeholders.py` (keyed by `language.name`).
-   The other four approaches work with no per-approach changes.
-4. **Pick an execution backend**: reuse an existing `project.runtool`
-   (`mvn`/`d4j`/`pytest`) or add one (see the section above). `pytest_runner.py`
-   is the template for a script/test-command backend.
-5. **Add an end-to-end example** under `examples/` (a small project + a config
-   with `project.language: <lang>`), mirroring `examples/project/python-example/`.
-
-Existing configs are unaffected: `project.language` defaults to `java`.
-
-## Add / change the LLM provider
-
-`multiplex/model.py` wraps LiteLLM, so most providers work by editing only the
-config (`llm.model`, `llm.endpoint`, `llm.token_env_var`). If a provider needs
-extra setup (custom env vars, headers), extend `Model.__init__` — see the
-existing Azure special-case. Keep the `make_request(messages) -> str` interface
-unchanged; every approach depends on it.
-
-## Testing your module
-
-Put tests under `tests/<area>/test_<module>.py` with fixture files in
-`tests/resources/`. Import production code **with** the package prefix
-(`from multiplex.checks.compilable import ...`). Run from the repo root:
-`uv run pytest tests`. LLM calls are not mocked anywhere yet — keep pure logic
-(parsing, splicing, checks) in functions separate from `model.make_request`
-call sites so it is testable without an LLM.
diff --git a/docs/MODULE_REFERENCE.md b/docs/MODULE_REFERENCE.md
deleted file mode 100644
index ad2868e..0000000
--- a/docs/MODULE_REFERENCE.md
+++ /dev/null
@@ -1,269 +0,0 @@
-# Module Reference
-
-Function-level reference for every module. Paths are relative to `multiplex/`.
-Signatures are exact; use this instead of opening source files.
-
-Note on imports: inside `multiplex/` modules import each other without the
-package prefix (e.g. `from util.io import write_to_file`). See DEVELOPMENT.md.
-
-Most pipeline functions take a `language` argument — a `languages.LanguageSpec`
-resolved once in `__main__.py` from `project.language` (default `java`).
-
-## languages/__init__.py
-
-```python
-@dataclass(frozen=True)
-class LanguageSpec:
-    name: str; extension: str; ts_language: Language
-    def_node_types: frozenset; comment_node_types: frozenset
-    fence: str; noun: str; label: str
-    def original_method_path(self, output_dir) -> Path   # output_dir/original_method<extension>
-
-get_language(name=None) -> LanguageSpec   # default "java"; SystemExit on unknown
-DEFAULT_LANGUAGE = "java"
-```
-
-- `_REGISTRY` holds the `java` and `python` specs. `name` matching is
-  case-insensitive. Raises `SystemExit` (actionable, lists valid languages) for
-  an unknown name — same fail-fast contract as `prompts.resolve_prompts`.
-
-## model.py
-
-```python
-class Model:
-    def __init__(self, model=None, endpoint=None, api_key_var=None)
-    def current_model(self) -> str
-    def make_request(self, messages) -> str   # returns response.choices[0].message.content
-```
-
-- `api_key_var` is the **name** of an env var; its value is read from
-  `os.environ` (KeyError if the named var is unset).
-- If `"azure" in endpoint`, sets `AZURE_AI_API_BASE` and `AZURE_AI_API_KEY`.
-- `messages` is a LiteLLM/OpenAI-style list of `{"role": ..., "content": ...}`.
-
-## prompts.py
-
-```python
-APPROACH_PROMPT_KEYS: dict[str, list[str]]     # approach name -> required system_prompts keys
-resolve_prompts(config, approach) -> dict      # {key: prompt} for the approach's keys
-```
-
-- `resolve_prompts` reads only the selected approach's keys from
-  `config["system_prompts"]`. Raises `SystemExit` (actionable message) if
-  `approach` is unknown or any required key is missing/empty. Pure function, no
-  I/O — called by `__main__.py` before any destructive step. Importable in tests
-  as `from multiplex.prompts import ...` (no sibling imports, so it works under
-  both the flat runtime import and the package-prefixed test import).
-
-## util/io.py
-
-```python
-write_to_file(output_file_path, output)            # plain text write (mode "w")
-write_ucas(ucas_output_path, ucas_output)          # writes str line-by-line
-write_mutant_summary(mutants_dir, mutants)         # writes mutants_dir/mutant_summary.csv from list-of-rows
-read_input_to_str(input_file_path) -> str
-read_ucas(input_file_path) -> (list[str], int)     # (lines, line count)
-read_hazop_mutations(input_file_path) -> (list[str], int)  # 4th CSV column of each line
-reset_source_code(duplicate_file_path, filename)
-```
-
-- `reset_source_code`: if `<filename>.orig` exists, moves it over `filename`
-  (restore); then always re-copies `filename` → `.orig`. Called at run start
-  and end by `__main__.py`.
-
-## util/extract_method.py
-
-```python
-extract_method_from_file(file_path, method_name, output_dir, start_line, language)
-    -> (start_byte, end_byte) | None
-```
-
-- tree-sitter walk (grammar from `language`) for a node in
-  `language.def_node_types` whose identifier text == `method_name` **and** whose
-  identifier is on line `start_line` (1-based). Both must match — `start_line` is
-  the line of the method/function *name*, not of annotations/decorators above it.
-- Writes the method source to `language.original_method_path(output_dir)`
-  (`output_dir/original_method.<ext>`).
-- Returns `None` if not found (logs a warning). The caller in `__main__.py`
-  checks for `None` and exits with a clear `SystemExit` naming
-  `project.method`/`project.line`.
-
-## util/rewrite_method.py
-
-```python
-rewrite_method(orig_path, start_byte, end_byte, mutant_file_path)
-```
-
-- Reads the pristine file from `orig_path + ".orig"` (the backup), splices the
-  mutant file's stripped text over bytes `[start_byte:end_byte)`, writes the
-  result to `orig_path`. Byte offsets come from `extract_method_from_file`.
-
-## util/parser.py
-
-```python
-parse_output(input) -> dict | None      # strips ```yaml fences, yaml.safe_load; None on parse error
-add_mutant_to_method(numbered_src, mutant, line_number) -> str
-```
-
-- `add_mutant_to_method` takes source whose lines are prefixed `"N: "`,
-  replaces line `line_number` with `mutant` (preserving indentation), and
-  returns un-numbered source. Used by the mutahunter approach.
-
-## util/marv.py
-
-```python
-output_marv(output_dir, approach)   # writes output_dir/marv.json (Marv schema); no-op unless --marv
-```
-
-- Called from `__main__.py` only when the `--marv` flag is set, after execution.
-  Reads `output_dir/original_method.java` and every
-  `<approach>-mutants/mutant_N.java`; raises `FileNotFoundError` if the original
-  method file or the mutants dir is missing. Pure Python — does **not** invoke
-  the `marv` binary.
-- Per-mutant `Status` comes from `<approach>-mutants/mutant_summary.csv`:
-  `equivalent` → `IGNORED`, non-compilable → `CRASHED`, `survives` → `SURVIVED`,
-  otherwise `KILLED`; `PENDING` when no summary row exists.
-- `Operation` is `REPLACE_METHOD`, except under the `hazop` approach where it is
-  the guideword from `hazop-mutated-descriptions.txt` (zipped to mutants in
-  sorted order).
-- Each mutation's `Start`/`End` are the line/char bounds of the code that
-  **differs** between the original method and that mutant, located with `difflib`
-  (`_file_span`). The enclosing `MutantRegion` spans the whole
-  `original_method.java`.
-- Emits JSON mapping `"original_method.java"` → one region → its mutations,
-  matching Marv's mutations schema.
-
-## util/marv_model.py
-
-Dataclasses mirroring [Marv's mutations schema](https://github.com/SecretSheppy/marv/blob/main/api/marv-mutations-schema.json),
-serialized to JSON by `util/marv.py`:
-
-- `Status` — enum: `KILLED`, `SURVIVED`, `CRASHED`, `TIMEOUT`, `NO_COVERAGE`,
-  `PENDING`, `IGNORED`.
-- `Pos(Line, Char)` — a source position; both fields 0-indexed.
-- `Mutation(ID, Description, Operation, Start, End, Status, Replacement, FrameworkMutantID=None)`.
-- `MutantRegion(ID, StartLine, EndLine, Mutations=[])` — a conflict region
-  (`StartLine` inclusive, `EndLine` non-inclusive, both 0-indexed).
-- `MarvOutput(files={})` — map of source path → list of `MutantRegion`.
-
-## checks/compilable.py
-
-```python
-check_mutant_compilable(filename, language) -> bool
-```
-
-- **Not a real compile.** tree-sitter (grammar from `language`) parses the file
-  and returns False if any `ERROR` or missing node exists. Catches syntax errors
-  only — type errors, missing symbols, etc. pass.
-
-## checks/syntactic_equivalence.py
-
-```python
-check_mutant_equivalent(mutant_filename, original_filename, language) -> bool
-```
-
-- Serializes both files' tree-sitter ASTs to strings, dropping
-  `language.comment_node_types`; True iff the strings are identical. Detects
-  mutants that only change comments/formatting. Prints a `SequenceMatcher`
-  similarity ratio as a side effect (not used in the decision).
-
-## approach/util.py
-
-```python
-get_method_under_test(output_dir, language) -> str   # reads language.original_method_path(output_dir); FileNotFoundError if absent
-```
-
-## approach/*/controller.py (all five)
-
-```python
-main(model, output_dir, prompts, language)   # prompts: the full dict built in __main__.py
-```
-
-Each approach's `generate_code` uses `language` for the mutant file extension,
-the ```` ``` ````-fence tag it strips, and the prompt noun
-(`Java method`/`Python function`).
-
-Each controller just calls its package's step functions in order with the
-relevant `prompts[...]` key(s):
-
-- `basic`: `code_generator.generate_code` — 10 requests, each response saved as
-  `basic-mutants/mutant_N.java`.
-- `hazop`: `method_explainer.describe_method` → `hazop-descriptions.txt`;
-  `description_mutator.mutate_descriptions` → `hazop-mutated-descriptions.txt`
-  (CSV rows `number, original_rule, GUIDEWORD, changed_rule`);
-  `code_generator.generate_code` → one mutant per changed rule.
-- `stpa`: `control_diagram.create_control_diagram` → `control_diagram.txt` (DOT);
-  `uca_generator.generate_ucas` → `ucas.csv`;
-  `code_generator.generate_code` → one mutant per UCA
-  (loop is `range(0, ucas_count)` — one mutant for every UCA).
-- `mutahunter`: `code_generator.generate_code` — one request containing the
-  method's AST plus line-numbered source; expects YAML back with
-  `mutants: [{mutated_code, line_number}, ...]`, spliced locally via
-  `util.parser.add_mutant_to_method`. The user-prompt template is intentionally
-  gutted (licensing) — users must fill in Mutahunter's own prompt text.
-- `llmorpheus`: `placeholders.create_placeholders` — the tree-sitter query for
-  `language.name` (from `MUTATION_QUERIES`) captures mutation sites (Java:
-  if/while/do/switch conditions, for-loop parts, loop headers, call
-  names/receivers/args; Python: if/while conditions, for target/iterable,
-  comparison/boolean/binary operators, call function/args); each capture produces
-  `placeholders/N_placeholder.<ext>` (method with `<PLACEHOLDER>` substituted),
-  `placeholders/N_orig.<ext>` (original fragment), and an entry in
-  `placeholders/placeholders.json` (`{tag, start_byte, end_byte, text}`).
-  `code_generator.generate_code` — one request per placeholder asking for 3
-  replacements ("Option 1/2/3" fenced blocks, extracted with the regex
-  ```` \n```\n(.*?)\n``` ```` under `re.DOTALL`); each replacement spliced into
-  the method at the placeholder's byte offsets →
-  `llmorpheus-mutants/mutant_N.<ext>`.
-
-## execute/defects4j.py
-
-```python
-run_mutants(project_root, original_file, output_path,
-            method_start_byte, method_end_byte, duplicate, approach, language)
-```
-
-- `_execute(project_root, file=None, approach=None, timer=None) -> bool`:
-  deletes `.classes_instrumented`/`target`, runs `defects4j test -w
-  <project_root>` with `PATH += ./defects4j/framework/bin` and
-  `JAVA_HOME = $JDK_11`; True iff output contains `Failing tests: 0`.
-  With `timer` set it enforces a subprocess timeout and writes test output to
-  `output/<approach>-test/<mutant>_test.txt`. Kills stray Java processes after.
-- `run_mutants` baselines the original project (raises IOError if its tests
-  fail), sets per-mutant timeout = 5× baseline duration, then per mutant:
-  restore from backup → equivalence check → rewrite → compilable check →
-  (if compilable) run tests. Appends `[name, equivalent, compilable, survives]`
-  rows and writes `mutant_summary.csv`.
-
-## execute/maven.py
-
-```python
-run_mutants(project_root, filename, output_path,
-            method_start_byte, method_end_byte, duplicate, approach, language)
-```
-
-- `_execute(project_root) -> bool`: runs `mvn -f <project_root> clean test`;
-  True if the output contains `BUILD SUCCESS` (all tests green → mutant
-  survived), False otherwise (mutant killed, incl. compile failures Maven
-  catches that tree-sitter does not).
-- `run_mutants`: same flow as the Defects4J backend — baseline the original
-  project (raises `IOError` if its tests fail), then per mutant: restore from
-  backup → equivalence check → rewrite → compilable check → (if compilable) run
-  tests → append `[name, equivalent, compilable, survives]` → write
-  `mutant_summary.csv`. Drives the runnable Java example under `examples/`.
-
-## execute/pytest_runner.py
-
-```python
-run_mutants(project_root, original_file, output_path,
-            method_start_byte, method_end_byte, duplicate, approach, language)
-```
-
-- `_execute(project_root) -> bool`: runs `sys.executable -m pytest -q
-  <project_root>` (argv list, no shell) — pytest runs under multiplex's own
-  interpreter, not a `python` resolved from PATH. True iff pytest exits 0 (all
-  tests pass → mutant survived), False otherwise (mutant killed, incl.
-  collection/syntax errors). If pytest is not installed for that interpreter,
-  raises a `SystemExit`.
-- `run_mutants`: identical baseline → per-mutant flow as the Maven backend.
-  Drives the runnable Python example (`examples/config-python.yml`). Module named
-  `pytest_runner` so importing it does not shadow the installed `pytest` package.
diff --git a/docs/Makefile b/docs/Makefile
new file mode 100644
index 0000000..faf5089
--- /dev/null
+++ b/docs/Makefile
@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= uv run sphinx-build
+SOURCEDIR     = source
+BUILDDIR      = build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
diff --git a/docs/README.md b/docs/README.md
deleted file mode 100644
index 39c218a..0000000
--- a/docs/README.md
+++ /dev/null
@@ -1,26 +0,0 @@
-# docs/ — Agent Documentation Index
-
-Documentation for humans and AI agents working on *multiplex*. Each file is
-self-contained: **load only the file(s) relevant to your task** rather than
-reading source code or every doc.
-
-| File | Read it when you need to... |
-|------|-----------------------------|
-| [ARCHITECTURE.md](ARCHITECTURE.md) | Understand the pipeline end-to-end: data flow, output artifacts, how mutants are injected and evaluated. |
-| [MODULE_REFERENCE.md](MODULE_REFERENCE.md) | Call or modify an existing function — every public function's signature, inputs, outputs, and side effects, without opening source files. |
-| [CONFIG.md](CONFIG.md) | Read, write, or validate a `config.yml` — full schema, every key. |
-| [EXTENDING.md](EXTENDING.md) | Add a new mutant-generation approach, execution backend, language, or LLM provider — exact checklists of files to touch. |
-| [DEVELOPMENT.md](DEVELOPMENT.md) | Set up, run commands, run tests, follow conventions, or avoid known gotchas and open bugs. |
-
-Quick orientation (enough for trivial tasks, no further reading needed):
-
-- *multiplex* mutates **one method/function** per run (Java or Python, set by
-  `project.language`): extract it with tree-sitter, ask an LLM to generate
-  mutants, splice each mutant back into the source file, run the project's tests,
-  and record which mutants survive.
-- Entry point: `multiplex/__main__.py`, run as `uv run ./multiplex ./config.yml`.
-- Python >= 3.13 (pin 3.13 — see DEVELOPMENT.md), deps via `uv`, lint via `ruff`,
-  tests via `pytest` from the repo root.
-- Code inside `multiplex/` imports siblings **without** the `multiplex.` prefix
-  (`from model import Model`); tests import **with** it
-  (`from multiplex.checks... import ...`). See DEVELOPMENT.md before editing imports.
diff --git a/docs/make.bat b/docs/make.bat
new file mode 100644
index 0000000..dc1312a
--- /dev/null
+++ b/docs/make.bat
@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd
diff --git a/docs/source/_static/custom.css b/docs/source/_static/custom.css
new file mode 100644
index 0000000..0d031f8
--- /dev/null
+++ b/docs/source/_static/custom.css
@@ -0,0 +1,84 @@
+/* ==========================================================================
+   Read the Docs (sphinx_rtd_theme) Custom Theme Overrides
+   ========================================================================== */
+
+:root {
+    --accent-green: #3FD55C;
+    --accent-green-hover: #35b84f;
+    --bg-dark: #1E242B;
+    --bg-hover: #252B31;
+    --text-light: #F0F4F8;
+}
+
+/* --------------------------------------------------------------------------
+   Navigation Sidebar & Top Bar Backgrounds
+   -------------------------------------------------------------------------- */
+
+.wy-nav-side,
+.wy-nav-top {
+    background: var(--bg-dark);
+}
+
+/* Search Box Focus Ring */
+.wy-side-nav-search input[type="text"]:focus {
+    border-color: var(--accent-green);
+}
+
+/* --------------------------------------------------------------------------
+   Sidebar Menu Styles
+   -------------------------------------------------------------------------- */
+
+/* Default Sidebar Item Hover */
+.wy-menu-vertical a:hover {
+    background-color: var(--bg-hover);
+    color: #ffffff;
+}
+
+/* Active / Expanded Section Container & Header ("Included Modules") */
+.wy-menu-vertical li.current > a,
+.wy-menu-vertical li.on > a {
+    background: var(--bg-hover);
+    color: #ffffff !important;
+    border-right: 4px solid var(--accent-green);
+
+    border-top: none !important;
+    border-bottom: none !important;
+    box-shadow: none !important;
+}
+
+.wy-menu-vertical li.current > a:hover,
+.wy-menu-vertical li.on > a:hover {
+    background: var(--bg-hover);
+    color: #ffffff !important;
+}
+
+/* Expand / Collapse Icon for Active Section */
+.wy-menu-vertical li.current > a span.toctree-expand,
+.wy-menu-vertical li.on > a span.toctree-expand {
+    color: var(--accent-green) !important;
+}
+
+/* --------------------------------------------------------------------------
+   Main Content Area Links & Buttons
+   -------------------------------------------------------------------------- */
+
+/* Inline Links */
+.rst-content a,
+.rst-content a:visited {
+    color: var(--accent-green);
+}
+
+.rst-content a:hover {
+    color: var(--accent-green-hover);
+}
+
+/* Navigation Buttons */
+.btn-neutral {
+    background-color: var(--bg-hover) !important;
+    color: #ffffff !important;
+}
+
+.btn-neutral:hover {
+    background-color: var(--accent-green) !important;
+    color: var(--bg-dark) !important;
+}
diff --git a/docs/source/_static/images/favicon.png b/docs/source/_static/images/favicon.png
new file mode 100644
index 0000000..66b3546
Binary files /dev/null and b/docs/source/_static/images/favicon.png differ
diff --git a/docs/source/_static/images/logo.png b/docs/source/_static/images/logo.png
new file mode 100644
index 0000000..7aa57ab
Binary files /dev/null and b/docs/source/_static/images/logo.png differ
diff --git a/docs/source/adding-execution-and-evaluation.rst b/docs/source/adding-execution-and-evaluation.rst
new file mode 100644
index 0000000..6869b31
--- /dev/null
+++ b/docs/source/adding-execution-and-evaluation.rst
@@ -0,0 +1,2 @@
+Adding an Execution and Evaluation Module
+=========================================
diff --git a/docs/source/adding-language.rst b/docs/source/adding-language.rst
new file mode 100644
index 0000000..05f6200
--- /dev/null
+++ b/docs/source/adding-language.rst
@@ -0,0 +1,2 @@
+Adding a Programming Language
+=============================
diff --git a/docs/source/adding-mutant-generation.rst b/docs/source/adding-mutant-generation.rst
new file mode 100644
index 0000000..3cd557e
--- /dev/null
+++ b/docs/source/adding-mutant-generation.rst
@@ -0,0 +1,2 @@
+Adding a Mutant Generation Approach
+===================================
diff --git a/docs/source/architecture.rst b/docs/source/architecture.rst
new file mode 100644
index 0000000..3837742
--- /dev/null
+++ b/docs/source/architecture.rst
@@ -0,0 +1,2 @@
+Architecture
+============
diff --git a/docs/source/conf.py b/docs/source/conf.py
new file mode 100644
index 0000000..876991e
--- /dev/null
+++ b/docs/source/conf.py
@@ -0,0 +1,35 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+
+project = "multiplex"
+copyright = "2026, Megan Maton"
+author = "Megan Maton"
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
+
+extensions = []
+
+templates_path = ["_templates"]
+exclude_patterns = []
+
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+html_theme = "sphinx_rtd_theme"
+html_static_path = ["_static"]
+html_logo = "_static/images/logo.png"
+html_favicon = "_static/images/favicon.png"
+
+html_theme_options = {
+    "style_nav_header_background": "#1E242B",
+}
+html_css_files = [
+    "custom.css",
+]
diff --git a/docs/source/configuration.rst b/docs/source/configuration.rst
new file mode 100644
index 0000000..6e79ebd
--- /dev/null
+++ b/docs/source/configuration.rst
@@ -0,0 +1,2 @@
+Configuration
+=============
diff --git a/docs/source/existing-modules.rst b/docs/source/existing-modules.rst
new file mode 100644
index 0000000..f93521e
--- /dev/null
+++ b/docs/source/existing-modules.rst
@@ -0,0 +1,45 @@
+Included Modules
+================
+
+Languages
+---------
+*multiplex* currently includes Java and Python compatibility.
+These are selected per run through the configuration file through ``project.language``.
+Instructions for adding additional language compatibility can be found in :doc:`adding-language`.
+
+Mutant Generation
+-----------------
+*multiplex* currently includes the following five mutant generation modules:
+
++-------------+--------------------+--------------------------------------------+
+| Approach    | *multiplex* config | Description                                |
++=============+====================+============================================+
+| STPA        | stpa               | Implements Systems Theoretic Process       | 
+|             |                    | Analysis mutant generation approach        |
++-------------+--------------------+--------------------------------------------+
+| HAZOP       | hazop              | Implements HAZard and OPerability study    |
+|             |                    | mutant generation approach                 |
++-------------+--------------------+--------------------------------------------+
+| Unguided    | basic              | Implements an unguided mutant generation   |
+|             |                    | approach                                   |
++-------------+--------------------+--------------------------------------------+
+| LLMorpheus  | llmorpheus         | Implements the LLMorpheus approach         |
++-------------+--------------------+--------------------------------------------+
+| Mutahunter  | mutahunter         | Implements the mutahunter approach         |
++-------------+--------------------+--------------------------------------------+
+
+Execution and Evaluation
+------------------------
+*multiplex* currently offers the following for mutant execution and evaluation.
+
++-------------+--------------------+--------------------------------------------+
+| Framework   | *multiplex* config | Description                                |
++=============+====================+============================================+
+| Maven       | mvn                | Execute mutants using a Maven runner       |
++-------------+--------------------+--------------------------------------------+
+| Defects4J   | d4j                | Framework to execute test suites from      |
++-------------+--------------------+--------------------------------------------+
+| PyTest      | pytest             | Execute mutants using PyTest runner        |
++-------------+--------------------+--------------------------------------------+
+
+
diff --git a/docs/source/getting-started.rst b/docs/source/getting-started.rst
new file mode 100644
index 0000000..5ef60cc
--- /dev/null
+++ b/docs/source/getting-started.rst
@@ -0,0 +1,148 @@
+Getting Started
+===============
+
+Requirements
+------------
+Using the *multiplex* tool requires the following:
+
+- UV Dependency Management: Follow installation instructions at `uv`_.
+- ``yq`` for parsing yaml config files with bash
+
+.. _uv: https://github.com/astral-sh/uv
+
+
+Installation
+------------
+
+1. Clone the repository:
+   
+    .. code-block:: bash
+    
+        git clone https://github.com/LLM-Mutation/multiplex.git
+   
+2. Install the dependencies and activate environment:
+    
+    .. code-block:: bash
+
+        cd multiplex
+        uv sync 
+        source .venv/bin/activate
+        cd ..
+   
+
+Configuration
+-------------
+
+*multiplex* is configured using a ``yaml`` file.
+Users can use the example configuration file in the ``examples/`` to set up their project. 
+This section overviews the content required in the configuration file.
+
+ 
+Project
+^^^^^^^
+
+This section includes the details about the project and method under test, including reference to the module for running and parsing the tests.
+
+LLM
+^^^
+
+To configure the LLM, update the config.yml file. 
+Below is an example for ``gpt-oss:20b``, run locally using Ollama.
+To use `gpt-oss:20b`, download Ollama, and run `ollama pull gpt-oss:20b`. 
+Ensure Ollama is running (``ollama serve``) when using *multiplex* for this example.
+
+.. code-block:: yaml
+    
+    llm:
+        model: ollama/gpt-oss:20b
+        endpoint: http://127.0.0.1:11434
+        token_env_var: # env var name storing token (NOT TOKEN)
+
+.. important::
+    Security Note: Never hardcode API keys in your config file. Set an environment variable and reference its name in the token_env_var field.
+
+System Prompts
+^^^^^^^^^^^^^^
+
+.. note::
+    Mutahunter Module prompts must be added by user due to licensing restrictions. - `User Prompt Link`_ / `System Prompt Link`_.
+
+.. _User Prompt Link:: https://github.com/codeintegrity-ai/mutahunter/blob/main/src/mutahunter/core/templates/mutant_generation/mutator_user.txt
+
+.. _System Prompt Link:: https://github.com/codeintegrity-ai/mutahunter/blob/main/src/mutahunter/core/templates/mutant_generation/mutator_system.txt
+
+The System Prompts are included in the configuration file for easy updating. 
+The user prompts are constructed within *multiplex* so users should modify or create modules to alter these.
+
+Running *multiplex*
+-------------------
+Once configured and modules are set up, users can run *multiplex* using the following command:
+
+
+.. code-block:: bash
+
+    uv run /path/to/multiplex ./path/to/config.yml
+
+
+Included examples
+^^^^^^^^^^^^^^^^^
+
+Self-contained examples are included for both supported languages, each mutating
+a small project with the ``basic`` approach. With a running Ollama instance
+(``ollama pull gpt-oss:20b``, ``ollama serve`` and edit ``llm.model`` in the config), run from the repo
+root:
+
+.. code-block:: bash
+
+    uv run ./multiplex ./examples/config-java.yml     # Java  (needs mvn + a JDK on PATH)
+    uv run ./multiplex ./examples/config-python.yml   # Python (uses pytest via uv run)
+
+
+Results are written to the project's ``output/<approach>-mutants/mutant_summary.csv``. See `examples/README.md`_ for
+details.
+
+.. examples/README.md:: https://github.com/LLM-Mutation/multiplex/blob/main/examples/README.md
+
+Optional: Marv output
+^^^^^^^^^^^^^^^^^^^^^
+If you want Marv-compatible output, install Marv and make sure its binary is
+on your ``PATH`` before running ``multiplex``:
+
+.. code-block:: bash
+
+    go install github.com/SecretSheppy/marv@latest
+    export PATH="$HOME/go/bin:$PATH"
+    marv --version
+
+Inside the project, run 
+
+.. code-block:: bash
+
+    marv init -f generic
+
+
+and update the .marv.yml file to the following:
+
+.. code-block:: yaml
+    marv:
+        port: 8080
+        output:
+            path: .marv
+            merge: false
+        review-dir: .marv/reviews
+    generic:
+        framework: "multiplex"
+        marv-json: "output/marv.json"
+        src-dir: "output"
+
+
+Then run *multiplex* with the ``--marv`` flag to generate ``output/marv.json``
+alongside the usual mutant files and summary:
+
+.. code-block:: bash
+
+    uv run multiplex --marv ./examples/config.yml
+
+
+Marv can then read the generated ``marv.json`` from the project output folder by running the ``marv`` command.
+
diff --git a/docs/source/index.rst b/docs/source/index.rst
new file mode 100644
index 0000000..67acf64
--- /dev/null
+++ b/docs/source/index.rst
@@ -0,0 +1,59 @@
+.. multiplex documentation main file, created by
+   sphinx-quickstart on Fri Aug  7 10:42:38 2026.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Welcome to *multiplex*
+=======================
+
+A tool for prototyping and comparing LLM-based mutation testing techniques.
+
+*multiplex* has a modular design to enable researchers to build, design and test LLM-based Mutation testing approaches in an easy to use framework.
+
+Multiplex is currently designed to enable mutation at the method level, but
+prompting and further modularisation could support other context levels. 
+Fork this project and add your own modules.
+
+Questions and Community
+-----------------------
+Have a question or found a bug? We’d love to hear from you. Please open an issue in the **Issue Tracker** and we'll get back to you!
+
+Citing this tool
+----------------------
+If you use this tool in your work or research, please cite as follows:
+
+.. code-block:: latex
+
+    @inproceedings{Maton2026a,
+      author    = {Maton, Megan and Kapfhammer, Gregory M. and McMinn, Phil},
+      title     = {multiplex: A Modular LLM-based Mutation Framework},
+      booktitle = {Proceedings of the International Conference on Automated Software Engineering (ASE) - Tools and Datasets Track},
+      year      = {2026},
+    }
+
+If you are specifically interested in Hazard Analysis approaches for guiding LLM-based mutant generation, please consider reading (and if relevant, citing):
+
+.. code-block:: latex
+
+    @inproceedings{Maton2026,
+      author    = "Maton, Megan and Kapfhammer, Gregory M. and McMinn, Phil",
+      title     = "Empirically Comparing Hazard-Guided LLM Mutation Techniques with Existing LLM- and
+                   Rule-Based Approaches",
+      booktitle = "International Conference on Evaluation and Assessment in Software Engineering (EASE)",
+      year      = "2026"
+    }
+
+.. toctree::
+   :hidden:
+   :caption: Home
+
+.. toctree::
+   :hidden:
+   :maxdepth: 3
+   :caption: Introduction
+
+   getting-started
+   existing-modules
+   configuration
+
+
diff --git a/docs/source/requirements.txt b/docs/source/requirements.txt
new file mode 100644
index 0000000..8d129a6
--- /dev/null
+++ b/docs/source/requirements.txt
@@ -0,0 +1 @@
+sphinx_rtd_theme=1.3.0
diff --git a/multiplex/execute/pytest_runner.py b/multiplex/execute/pytest_runner.py
index 518ed31..1dcd319 100644
--- a/multiplex/execute/pytest_runner.py
+++ b/multiplex/execute/pytest_runner.py
@@ -1,9 +1,5 @@
 """Pytest execution backend.
 
-Mirrors ``execute/maven.py``: baseline the original (unmutated) project, then per
-mutant restore the source, run the equivalence/compilable checks, splice the
-mutant into the source, and run the project's tests to decide survived/killed.
-
 Named ``pytest_runner`` (not ``pytest``) so it does not shadow the installed
 ``pytest`` package on import.
 """
@@ -31,8 +27,11 @@ def _execute(project_root, output_path=None, approach=None, label=None):
     command = [sys.executable, "-m", "pytest", "-q", str(project_root)]
     try:
         result = subprocess.run(
-            command, stdout=subprocess.PIPE, stderr=subprocess.STDOUT,
-            text=True, check=False
+            command,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.STDOUT,
+            text=True,
+            check=False,
         )
     except FileNotFoundError as exc:
         raise SystemExit(
@@ -70,7 +69,7 @@ def run_mutants(
     mutants = [["MUTANT", "EQUIVALENCE", "COMPILABLE", "SURVIVES"]]
 
     if not _execute(project_root, output_path, approach, "ORIGINAL"):
-        raise IOError(
+        raise OSError(
             "The original (unmutated) project did not pass pytest, so mutants "
             "cannot be evaluated against it. Run it manually to see why: "
             f"{sys.executable} -m pytest {project_root}"
@@ -83,7 +82,9 @@ def run_mutants(
             shutil.copy2(duplicate, original_file)
 
         path = Path(mutants_dir, mutant_file)
-        mutant_equivalent = check_mutant_equivalent(path, original_method_path, language)
+        mutant_equivalent = check_mutant_equivalent(
+            path, original_method_path, language
+        )
         mutant_output.append(mutant_equivalent)
 
         rewrite_method(original_file, method_start_byte, method_end_byte, path)
diff --git a/multiplex/model.py b/multiplex/model.py
index f1c648a..154b59c 100644
--- a/multiplex/model.py
+++ b/multiplex/model.py
@@ -3,23 +3,21 @@
 from litellm import completion
 
 
-
 class Model:
-
     def __init__(self, model=None, endpoint=None, api_key_var=None):
         self.model = model
         self.endpoint = endpoint
-        if api_key_var is not None and api_key_var != '':
+        if api_key_var is not None and api_key_var != "":
             self.api_key = os.environ[api_key_var]
 
-            if "azure" in endpoint:
+            if "azure" in str(endpoint):
                 os.environ["AZURE_AI_API_BASE"] = endpoint
                 os.environ["AZURE_AI_API_KEY"] = os.environ[api_key_var]
-
+        if "ollama" in self.model:
+            os.environ["OLLAMA_API_BASE"] = self.endpoint
 
         print("Model:", self.model)
 
-
     def current_model(self):
         """Return current model"""
         return self.model
diff --git a/pyproject.toml b/pyproject.toml
index 52dc08a..a870248 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -18,4 +18,6 @@ dev = [
     "pylint>=3.3.7",
     "pytest>=8.4.1",
     "ruff>=0.11.12",
+    "sphinx>=9.1.0",
+    "sphinx-rtd-theme>=3.1.0",
 ]
diff --git a/uv.lock b/uv.lock
index 466268a..db2221c 100644
--- a/uv.lock
+++ b/uv.lock
@@ -57,6 +57,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/fb/76/641ae371508676492379f16e2fa48f4e2c11741bd63c48be4b12a6b09cba/aiosignal-1.4.0-py3-none-any.whl", hash = "sha256:053243f8b92b990551949e63930a839ff0cf0b0ebbe0597b0f3fb19e1a0fe82e", size = 7490, upload-time = "2025-07-03T22:54:42.156Z" },
 ]
 
+[[package]]
+name = "alabaster"
+version = "1.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a6/f8/d9c74d0daf3f742840fd818d69cfae176fa332022fd44e3469487d5a9420/alabaster-1.0.0.tar.gz", hash = "sha256:c00dca57bca26fa62a6d7d0a9fcce65f3e026e9bfe33e9c538fd3fbb2144fd9e", size = 24210, upload-time = "2024-07-26T18:15:03.762Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/7e/b3/6b4067be973ae96ba0d615946e314c5ae35f9f993eca561b356540bb0c2b/alabaster-1.0.0-py3-none-any.whl", hash = "sha256:fc6786402dc3fcb2de3cabd5fe455a2db534b371124f1f21de8731783dec828b", size = 13929, upload-time = "2024-07-26T18:15:02.05Z" },
+]
+
 [[package]]
 name = "annotated-types"
 version = "0.7.0"
@@ -97,6 +106,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/77/06/bb80f5f86020c4551da315d78b3ab75e8228f89f0162f2c3a819e407941a/attrs-25.3.0-py3-none-any.whl", hash = "sha256:427318ce031701fea540783410126f03899a97ffc6f61596ad581ac2e40e3bc3", size = 63815, upload-time = "2025-03-13T11:10:21.14Z" },
 ]
 
+[[package]]
+name = "babel"
+version = "2.18.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/7d/b2/51899539b6ceeeb420d40ed3cd4b7a40519404f9baf3d4ac99dc413a834b/babel-2.18.0.tar.gz", hash = "sha256:b80b99a14bd085fcacfa15c9165f651fbb3406e66cc603abf11c5750937c992d", size = 9959554, upload-time = "2026-02-01T12:30:56.078Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/77/f5/21d2de20e8b8b0408f0681956ca2c69f1320a3848ac50e6e7f39c6159675/babel-2.18.0-py3-none-any.whl", hash = "sha256:e2b422b277c2b9a9630c1d7903c2a00d0830c409c59ac8cae9081c92f1aeba35", size = 10196845, upload-time = "2026-02-01T12:30:53.445Z" },
+]
+
 [[package]]
 name = "certifi"
 version = "2025.8.3"
@@ -176,6 +194,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/12/b3/231ffd4ab1fc9d679809f356cebee130ac7daa00d6d6f3206dd4fd137e9e/distro-1.9.0-py3-none-any.whl", hash = "sha256:7bffd925d65168f85027d8da9af6bddab658135b840670a223589bc0c8ef02b2", size = 20277, upload-time = "2023-12-24T09:54:30.421Z" },
 ]
 
+[[package]]
+name = "docutils"
+version = "0.22.4"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/ae/b6/03bb70946330e88ffec97aefd3ea75ba575cb2e762061e0e62a213befee8/docutils-0.22.4.tar.gz", hash = "sha256:4db53b1fde9abecbb74d91230d32ab626d94f6badfc575d6db9194a49df29968", size = 2291750, upload-time = "2025-12-18T19:00:26.443Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/02/10/5da547df7a391dcde17f59520a231527b8571e6f46fc8efb02ccb370ab12/docutils-0.22.4-py3-none-any.whl", hash = "sha256:d0013f540772d1420576855455d050a2180186c91c15779301ac2ccb3eeb68de", size = 633196, upload-time = "2025-12-18T19:00:18.077Z" },
+]
+
 [[package]]
 name = "fastuuid"
 version = "0.14.0"
@@ -347,6 +374,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/76/c6/c88e154df9c4e1a2a66ccf0005a88dfb2650c1dffb6f5ce603dfbd452ce3/idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3", size = 70442, upload-time = "2024-09-15T18:07:37.964Z" },
 ]
 
+[[package]]
+name = "imagesize"
+version = "2.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/6c/e6/7bf14eeb8f8b7251141944835abd42eb20a658d89084b7e1f3e5fe394090/imagesize-2.0.0.tar.gz", hash = "sha256:8e8358c4a05c304f1fccf7ff96f036e7243a189e9e42e90851993c558cfe9ee3", size = 1773045, upload-time = "2026-03-03T14:18:29.941Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/5f/53/fb7122b71361a0d121b669dcf3d31244ef75badbbb724af388948de543e2/imagesize-2.0.0-py2.py3-none-any.whl", hash = "sha256:5667c5bbb57ab3f1fa4bc366f4fbc971db3d5ed011fd2715fd8001f782718d96", size = 9441, upload-time = "2026-03-03T14:18:27.892Z" },
+]
+
 [[package]]
 name = "importlib-metadata"
 version = "8.7.0"
@@ -578,6 +614,8 @@ dev = [
     { name = "pylint" },
     { name = "pytest" },
     { name = "ruff" },
+    { name = "sphinx" },
+    { name = "sphinx-rtd-theme" },
 ]
 
 [package.metadata]
@@ -595,6 +633,8 @@ dev = [
     { name = "pylint", specifier = ">=3.3.7" },
     { name = "pytest", specifier = ">=8.4.1" },
     { name = "ruff", specifier = ">=0.11.12" },
+    { name = "sphinx", specifier = ">=9.1.0" },
+    { name = "sphinx-rtd-theme", specifier = ">=3.1.0" },
 ]
 
 [[package]]
@@ -860,6 +900,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/7c/e4/56027c4a6b4ae70ca9de302488c5ca95ad4a39e190093d6c1a8ace08341b/requests-2.32.4-py3-none-any.whl", hash = "sha256:27babd3cda2a6d50b30443204ee89830707d396671944c998b5975b031ac2b2c", size = 64847, upload-time = "2025-06-09T16:43:05.728Z" },
 ]
 
+[[package]]
+name = "roman-numerals"
+version = "4.1.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/ae/f9/41dc953bbeb056c17d5f7a519f50fdf010bd0553be2d630bc69d1e022703/roman_numerals-4.1.0.tar.gz", hash = "sha256:1af8b147eb1405d5839e78aeb93131690495fe9da5c91856cb33ad55a7f1e5b2", size = 9077, upload-time = "2025-12-17T18:25:34.381Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/04/54/6f679c435d28e0a568d8e8a7c0a93a09010818634c3c3907fc98d8983770/roman_numerals-4.1.0-py3-none-any.whl", hash = "sha256:647ba99caddc2cc1e55a51e4360689115551bf4476d90e8162cf8c345fe233c7", size = 7676, upload-time = "2025-12-17T18:25:33.098Z" },
+]
+
 [[package]]
 name = "rpds-py"
 version = "0.27.1"
@@ -960,6 +1009,123 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2", size = 10235, upload-time = "2024-02-25T23:20:01.196Z" },
 ]
 
+[[package]]
+name = "snowballstemmer"
+version = "3.1.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/43/f8/0a71edf031f03c40db17503cb8ca78a69a171254e568e7db241b0ab57ea1/snowballstemmer-3.1.1.tar.gz", hash = "sha256:e07bbc54a0d798fe6010a12398422e62a8bfbba95c394fd0956ef58cb4d3e260", size = 123314, upload-time = "2026-06-03T00:56:40.194Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/4c/07/2ebca9b11fb9be7340a818d8d6f63feaebb146be2c4afbd6061701d6df6e/snowballstemmer-3.1.1-py3-none-any.whl", hash = "sha256:7e207fa178741da09cdee59d3ecec3827ad5f92b1fc5c9ff3755b639f71f5752", size = 104164, upload-time = "2026-06-03T00:56:38.614Z" },
+]
+
+[[package]]
+name = "sphinx"
+version = "9.1.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "alabaster" },
+    { name = "babel" },
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "docutils" },
+    { name = "imagesize" },
+    { name = "jinja2" },
+    { name = "packaging" },
+    { name = "pygments" },
+    { name = "requests" },
+    { name = "roman-numerals" },
+    { name = "snowballstemmer" },
+    { name = "sphinxcontrib-applehelp" },
+    { name = "sphinxcontrib-devhelp" },
+    { name = "sphinxcontrib-htmlhelp" },
+    { name = "sphinxcontrib-jsmath" },
+    { name = "sphinxcontrib-qthelp" },
+    { name = "sphinxcontrib-serializinghtml" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/cd/bd/f08eb0f4eed5c83f1ba2a3bd18f7745a2b1525fad70660a1c00224ec468a/sphinx-9.1.0.tar.gz", hash = "sha256:7741722357dd75f8190766926071fed3bdc211c74dd2d7d4df5404da95930ddb", size = 8718324, upload-time = "2025-12-31T15:09:27.646Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/73/f7/b1884cb3188ab181fc81fa00c266699dab600f927a964df02ec3d5d1916a/sphinx-9.1.0-py3-none-any.whl", hash = "sha256:c84fdd4e782504495fe4f2c0b3413d6c2bf388589bb352d439b2a3bb99991978", size = 3921742, upload-time = "2025-12-31T15:09:25.561Z" },
+]
+
+[[package]]
+name = "sphinx-rtd-theme"
+version = "3.1.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "docutils" },
+    { name = "sphinx" },
+    { name = "sphinxcontrib-jquery" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/84/68/a1bfbf38c0f7bccc9b10bbf76b94606f64acb1552ae394f0b8285bfaea25/sphinx_rtd_theme-3.1.0.tar.gz", hash = "sha256:b44276f2c276e909239a4f6c955aa667aaafeb78597923b1c60babc76db78e4c", size = 7620915, upload-time = "2026-01-12T16:03:31.17Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/87/c7/b5c8015d823bfda1a346adb2c634a2101d50bb75d421eb6dcb31acd25ebc/sphinx_rtd_theme-3.1.0-py2.py3-none-any.whl", hash = "sha256:1785824ae8e6632060490f67cf3a72d404a85d2d9fc26bce3619944de5682b89", size = 7655617, upload-time = "2026-01-12T16:03:28.101Z" },
+]
+
+[[package]]
+name = "sphinxcontrib-applehelp"
+version = "2.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/ba/6e/b837e84a1a704953c62ef8776d45c3e8d759876b4a84fe14eba2859106fe/sphinxcontrib_applehelp-2.0.0.tar.gz", hash = "sha256:2f29ef331735ce958efa4734873f084941970894c6090408b079c61b2e1c06d1", size = 20053, upload-time = "2024-07-29T01:09:00.465Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/5d/85/9ebeae2f76e9e77b952f4b274c27238156eae7979c5421fba91a28f4970d/sphinxcontrib_applehelp-2.0.0-py3-none-any.whl", hash = "sha256:4cd3f0ec4ac5dd9c17ec65e9ab272c9b867ea77425228e68ecf08d6b28ddbdb5", size = 119300, upload-time = "2024-07-29T01:08:58.99Z" },
+]
+
+[[package]]
+name = "sphinxcontrib-devhelp"
+version = "2.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f6/d2/5beee64d3e4e747f316bae86b55943f51e82bb86ecd325883ef65741e7da/sphinxcontrib_devhelp-2.0.0.tar.gz", hash = "sha256:411f5d96d445d1d73bb5d52133377b4248ec79db5c793ce7dbe59e074b4dd1ad", size = 12967, upload-time = "2024-07-29T01:09:23.417Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/35/7a/987e583882f985fe4d7323774889ec58049171828b58c2217e7f79cdf44e/sphinxcontrib_devhelp-2.0.0-py3-none-any.whl", hash = "sha256:aefb8b83854e4b0998877524d1029fd3e6879210422ee3780459e28a1f03a8a2", size = 82530, upload-time = "2024-07-29T01:09:21.945Z" },
+]
+
+[[package]]
+name = "sphinxcontrib-htmlhelp"
+version = "2.1.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/43/93/983afd9aa001e5201eab16b5a444ed5b9b0a7a010541e0ddfbbfd0b2470c/sphinxcontrib_htmlhelp-2.1.0.tar.gz", hash = "sha256:c9e2916ace8aad64cc13a0d233ee22317f2b9025b9cf3295249fa985cc7082e9", size = 22617, upload-time = "2024-07-29T01:09:37.889Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0a/7b/18a8c0bcec9182c05a0b3ec2a776bba4ead82750a55ff798e8d406dae604/sphinxcontrib_htmlhelp-2.1.0-py3-none-any.whl", hash = "sha256:166759820b47002d22914d64a075ce08f4c46818e17cfc9470a9786b759b19f8", size = 98705, upload-time = "2024-07-29T01:09:36.407Z" },
+]
+
+[[package]]
+name = "sphinxcontrib-jquery"
+version = "4.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "sphinx" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/de/f3/aa67467e051df70a6330fe7770894b3e4f09436dea6881ae0b4f3d87cad8/sphinxcontrib-jquery-4.1.tar.gz", hash = "sha256:1620739f04e36a2c779f1a131a2dfd49b2fd07351bf1968ced074365933abc7a", size = 122331, upload-time = "2023-03-14T15:01:01.944Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/76/85/749bd22d1a68db7291c89e2ebca53f4306c3f205853cf31e9de279034c3c/sphinxcontrib_jquery-4.1-py2.py3-none-any.whl", hash = "sha256:f936030d7d0147dd026a4f2b5a57343d233f1fc7b363f68b3d4f1cb0993878ae", size = 121104, upload-time = "2023-03-14T15:01:00.356Z" },
+]
+
+[[package]]
+name = "sphinxcontrib-jsmath"
+version = "1.0.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/b2/e8/9ed3830aeed71f17c026a07a5097edcf44b692850ef215b161b8ad875729/sphinxcontrib-jsmath-1.0.1.tar.gz", hash = "sha256:a9925e4a4587247ed2191a22df5f6970656cb8ca2bd6284309578f2153e0c4b8", size = 5787, upload-time = "2019-01-21T16:10:16.347Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c2/42/4c8646762ee83602e3fb3fbe774c2fac12f317deb0b5dbeeedd2d3ba4b77/sphinxcontrib_jsmath-1.0.1-py2.py3-none-any.whl", hash = "sha256:2ec2eaebfb78f3f2078e73666b1415417a116cc848b72e5172e596c871103178", size = 5071, upload-time = "2019-01-21T16:10:14.333Z" },
+]
+
+[[package]]
+name = "sphinxcontrib-qthelp"
+version = "2.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/68/bc/9104308fc285eb3e0b31b67688235db556cd5b0ef31d96f30e45f2e51cae/sphinxcontrib_qthelp-2.0.0.tar.gz", hash = "sha256:4fe7d0ac8fc171045be623aba3e2a8f613f8682731f9153bb2e40ece16b9bbab", size = 17165, upload-time = "2024-07-29T01:09:56.435Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/27/83/859ecdd180cacc13b1f7e857abf8582a64552ea7a061057a6c716e790fce/sphinxcontrib_qthelp-2.0.0-py3-none-any.whl", hash = "sha256:b18a828cdba941ccd6ee8445dbe72ffa3ef8cbe7505d8cd1fa0d42d3f2d5f3eb", size = 88743, upload-time = "2024-07-29T01:09:54.885Z" },
+]
+
+[[package]]
+name = "sphinxcontrib-serializinghtml"
+version = "2.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/3b/44/6716b257b0aa6bfd51a1b31665d1c205fb12cb5ad56de752dfa15657de2f/sphinxcontrib_serializinghtml-2.0.0.tar.gz", hash = "sha256:e9d912827f872c029017a53f0ef2180b327c3f7fd23c87229f7a8e8b70031d4d", size = 16080, upload-time = "2024-07-29T01:10:09.332Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/52/a7/d2782e4e3f77c8450f727ba74a8f12756d5ba823d81b941f1b04da9d033a/sphinxcontrib_serializinghtml-2.0.0-py3-none-any.whl", hash = "sha256:6e2cb0eef194e10c27ec0023bfeb25badbbb5868244cf5bc5bdc04e4464bf331", size = 92072, upload-time = "2024-07-29T01:10:08.203Z" },
+]
+
 [[package]]
 name = "tiktoken"
 version = "0.11.0"