proxym 0.1.2__tar.gz

proxym-0.1.2/.env.example

@@ -0,0 +1,66 @@
+# ============================================================
+# AI Proxy — Environment Configuration
+# Copy to .env and fill in your API keys
+# ============================================================
+
+# --- Server ---
+AI_PROXY_HOST=0.0.0.0
+AI_PROXY_PORT=4000
+AI_PROXY_MASTER_KEY=sk-proxy-local-dev
+AI_PROXY_LOG_LEVEL=info
+
+# --- Redis (cache + semantic search) ---
+REDIS_URL=redis://localhost:6379/0
+
+# --- Provider API Keys (fill only those you use) ---
+# Anthropic — Opus 4.6, Sonnet 4.6, Haiku 4.5
+ANTHROPIC_API_KEY=
+
+# OpenAI — GPT-5.4, GPT-4.1, GPT-4o
+OPENAI_API_KEY=
+
+# OpenRouter — 300+ models, single key
+OPENROUTER_API_KEY=
+
+# Google AI Studio — Gemini 2.5 Pro/Flash (free tier)
+GOOGLE_AI_KEY=
+
+# DeepSeek — V3, R1 (cheapest cloud)
+DEEPSEEK_API_KEY=
+
+# Groq — ultra-fast inference (free tier available)
+GROQ_API_KEY=
+
+# Together AI — open-source models
+TOGETHER_API_KEY=
+
+# Mistral — Codestral, Mistral Large
+MISTRAL_API_KEY=
+
+# Fireworks AI — fast open-source inference
+FIREWORKS_API_KEY=
+
+# Cerebras — fastest inference (free tier)
+CEREBRAS_API_KEY=
+
+# --- Local Models (Ollama) ---
+# Where Ollama runs — localhost for same machine, IP for Jetson/RPi
+OLLAMA_BASE_URL=http://localhost:11434
+# Secondary Ollama instance (e.g., Jetson Orin on LAN)
+OLLAMA_SECONDARY_URL=
+
+# --- Delta Context Buffer ---
+# Directory watched for code2llm output
+WATCH_DIR=./project
+# Max context window tokens to send
+MAX_CONTEXT_TOKENS=120000
+# Delta sensitivity (0.0–1.0, lower = more diffs sent)
+DELTA_THRESHOLD=0.15
+
+# --- Budget Limits ---
+# Monthly budget cap in USD (0 = unlimited)
+MONTHLY_BUDGET_USD=60
+# Daily budget cap
+DAILY_BUDGET_USD=5
+# Per-request max cost
+MAX_REQUEST_COST_USD=2.0

proxym-0.1.2/.gitignore

@@ -0,0 +1,220 @@
+.idea
+.llm
+managed_components
+.gui-agent.pid
+.gui-server.pid
+.gui-server.log
+gui-server/app_old.py
+gui-server/app.py.bak
+gui-server/index_old.html
+gui-server/index.html.bak
+gui-server/logs/
+gui-agent/logs/
+logs/
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

proxym-0.1.2/CHANGELOG.md

@@ -0,0 +1,38 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+
+## [0.1.2] - 2026-03-21
+
+## [0.1.1] - 2026-03-21
+
+### Docs
+- Update README.md
+
+### Test
+- Update tests/conftest.py
+- Update tests/test_accounts.py
+- Update tests/test_analyzer.py
+- Update tests/test_dashboard.py
+- Update tests/test_delta_buffer.py
+- Update tests/test_e2e.py
+- Update tests/test_router.py
+
+### Other
+- Update .env.example
+- Update .gitignore
+- Update Dockerfile.jetson
+- Update ai-proxy-dashboard.jsx
+- Update docker-compose.prod.yml
+- Update project.sh
+- Update quadlet/ai-proxy.container
+- Update quadlet/ai-proxy.network
+- Update quadlet/ollama.container
+- Update quadlet/redis.container
+- ... and 4 more files
+

proxym-0.1.2/Dockerfile

@@ -0,0 +1,42 @@
+# ── Stage 1: Build ────────────────────────────────────────────
+FROM python:3.12-slim AS builder
+
+WORKDIR /build
+COPY pyproject.toml .
+COPY src/ src/
+
+RUN pip install --no-cache-dir build && \
+    python -m build --wheel --outdir /dist
+
+# ── Stage 2: Runtime ──────────────────────────────────────────
+FROM python:3.12-slim
+
+LABEL maintainer="wronai" \
+      description="AI Proxy — multi-provider LLM gateway" \
+      version="0.1.0"
+
+WORKDIR /app
+
+# System deps
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends curl && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install wheel + extras
+COPY --from=builder /dist/*.whl /tmp/
+RUN pip install --no-cache-dir /tmp/*.whl && rm -rf /tmp/*.whl
+
+# Copy config
+COPY .env.example .env.example
+
+# Non-root user
+RUN useradd -m -s /bin/bash proxy
+USER proxy
+
+EXPOSE 4000
+
+HEALTHCHECK --interval=15s --timeout=5s --retries=3 \
+    CMD curl -f http://localhost:4000/health || exit 1
+
+ENTRYPOINT ["ai-proxy"]
+CMD ["--host", "0.0.0.0", "--port", "4000"]

proxym-0.1.2/Dockerfile.jetson

@@ -0,0 +1,37 @@
+# Dockerfile.jetson — for NVIDIA Jetson Orin (ARM64 + CUDA)
+# Build on Jetson or with buildx for linux/arm64
+#
+# Usage:
+#   docker build -f Dockerfile.jetson -t ai-proxy:jetson .
+#   docker run --runtime nvidia --gpus all -p 4000:4000 ai-proxy:jetson
+
+FROM dustynv/ollama:r36.4.0 AS ollama-base
+
+# ── Runtime ───────────────────────────────────────────────────
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install system deps
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends curl && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install Python deps
+COPY pyproject.toml .
+COPY src/ src/
+RUN pip install --no-cache-dir ".[gpu]" 2>/dev/null || pip install --no-cache-dir .
+
+# Copy Ollama binary from jetson container
+COPY --from=ollama-base /bin/ollama /usr/local/bin/ollama
+
+# Entrypoint script that starts Ollama + proxy
+COPY scripts/jetson-entrypoint.sh /entrypoint.sh
+RUN chmod +x /entrypoint.sh
+
+EXPOSE 4000 11434
+
+HEALTHCHECK --interval=15s --timeout=5s --retries=3 \
+    CMD curl -f http://localhost:4000/health || exit 1
+
+ENTRYPOINT ["/entrypoint.sh"]