Merge pull request #7 from pzqpzq/codex/mdia-rebuild

Rebuild repository around the MDia pipeline

Author: pzqpzq

.env.example

@@ -0,0 +1,11 @@
+# The deterministic toy pipeline does not require any environment variables.
+# For a provider-backed adapter, export the variables consumed by that
+# adapter through your shell or secret manager. The package does not parse
+# `.env` files; `.env` is ignored only as a safety backstop.
+
+MDIA_API_KEY=
+MDIA_API_BASE=
+
+# The model name and optional api_key_env override belong in the validated
+# run config. If api_key_env names a different variable, define it only in
+# your local environment; do not add a resolved key here.

.github/workflows/ci.yml

@@ -0,0 +1,40 @@
+name: CI
+
+on:
+  push:
+  pull_request:
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+      - run: python -m pip install --upgrade pip
+      - run: python -m pip install -e ".[dev]"
+      - run: ruff check src tests scripts
+      - run: ruff format --check src tests scripts
+      - run: mypy src/mdia
+      - run: pytest
+      - run: python scripts/check_markdown_links.py
+      - run: python scripts/check_release_hygiene.py
+
+  secrets:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - uses: gitleaks/gitleaks-action@v2
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -0,0 +1,35 @@
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.coverage
+htmlcov/
+
+# Environments and local configuration
+.venv/
+venv/
+.env
+.env.*
+!.env.example
+
+# Generated runs and caches
+runs/
+tmp/
+.cache/
+dist/
+build/
+
+# Editors and operating systems
+.DS_Store
+Thumbs.db
+.idea/
+.vscode/
+
+# Private/restricted experiment material
+private_data/
+secrets/
+api_usage*.jsonl
+*usage_ledger*

.gitleaksignore

@@ -0,0 +1,3 @@
+# Deterministic SHA-256 for execution/token_accounting.json in the toy example.
+# Gitleaks associates the artifact path's "token" substring with the checksum.
+693d3aa30e065ae3d8d047f884e271f6eb4739ba:artifacts/example/manifest.json:generic-api-key:10

CITATION.cff

@@ -0,0 +1,28 @@
+cff-version: 1.2.0
+message: "If you use this software, cite the software and the relevant MDia or CLSR paper."
+title: "Machine Dialectology (MDia)"
+type: software
+authors:
+  - family-names: Pei
+    given-names: Zhengqi
+  - family-names: Huang
+    given-names: Qingming
+  - family-names: Wang
+    given-names: Shuhui
+version: 1.0.0
+date-released: 2026-07-30
+repository-code: "https://github.com/pzqpzq/LSF_MDia"
+url: "https://github.com/pzqpzq/LSF_MDia"
+license: MIT
+references:
+  - type: article
+    title: "When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning"
+    authors:
+      - family-names: Pei
+        given-names: Zhengqi
+      - family-names: Huang
+        given-names: Qingming
+      - family-names: Wang
+        given-names: Shuhui
+    year: 2026
+    url: "https://arxiv.org/abs/2606.29354"