tokenwise-sdk 0.1.1__tar.gz

tokenwise_sdk-0.1.1/.gitignore

@@ -0,0 +1,221 @@
+# 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/
+!frontend/lib/
+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
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# 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/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+test_sdk.py

tokenwise_sdk-0.1.1/PKG-INFO

@@ -0,0 +1,149 @@
+Metadata-Version: 2.4
+Name: tokenwise-sdk
+Version: 0.1.1
+Summary: Metadata-only usage tracking for Anthropic and OpenAI — swap one import line.
+Project-URL: Homepage, https://tokenwise.io
+Project-URL: Documentation, https://docs.tokenwise.io
+Author: Tokenwise
+License: MIT
+Keywords: anthropic,cost,llm,observability,openai,tokens,usage
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.9
+Requires-Dist: httpx>=0.23
+Provides-Extra: anthropic
+Requires-Dist: anthropic>=0.40; extra == 'anthropic'
+Provides-Extra: dev
+Requires-Dist: anthropic>=0.40; extra == 'dev'
+Requires-Dist: openai>=1.40; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Provides-Extra: openai
+Requires-Dist: openai>=1.40; extra == 'openai'
+Description-Content-Type: text/markdown
+
+# Tokenwise Python SDK
+
+Metadata-only usage tracking for Anthropic and OpenAI. Swap **one import line**
+and every API call's token counts and latency flow to your Tokenwise dashboard
+— with **zero access to your prompts or responses**.
+
+```diff
+- from anthropic import Anthropic
++ from tokenwise import Anthropic
+```
+
+Your code is otherwise unchanged: the wrapper exposes the identical interface,
+forwards every call to the official SDK, and returns its response untouched.
+
+## Why it's safe
+
+- **Metadata only.** The SDK reads exactly: `model`, `input_tokens`,
+  `output_tokens`, `cache_read_input_tokens`, `cache_creation_input_tokens`,
+  `latency_ms`, `timestamp`, `endpoint`. It never reads or transmits prompt
+  text, response text, system prompts, or tool definitions. (Contrast with
+  proxy-based tools, which see all your traffic.)
+- **Non-blocking.** Events are queued and sent on a background daemon thread.
+  If Tokenwise is slow or down, your AI calls complete normally.
+- **Fail-silent + bounded.** Up to 1,000 events buffer when offline; the oldest
+  drop silently if the buffer fills. Capture never raises, never waits.
+
+## Install
+
+```bash
+pip install tokenwise-sdk[anthropic]   # if you use Anthropic
+pip install tokenwise-sdk[openai]      # if you use OpenAI
+pip install tokenwise-sdk[anthropic,openai]
+```
+
+`anthropic` and `openai` are optional extras — install only what you use.
+
+## Configure
+
+Set your Tokenwise key (from the dashboard, looks like `tw_...`):
+
+```bash
+export TOKENWISE_API_KEY=tw_your_key
+# optional:
+export TOKENWISE_API_URL=https://tokenwise-production-aa59.up.railway.app   # default
+export TOKENWISE_DISABLED=true                       # emergency kill switch
+```
+
+Precedence for every setting: constructor argument > environment variable >
+default. If no key is configured the SDK runs disabled and your AI calls behave
+exactly as the official SDK.
+
+## Usage
+
+```python
+# Pattern 1 — key from environment
+import os
+os.environ["TOKENWISE_API_KEY"] = "tw_abc123"
+from tokenwise import Anthropic
+client = Anthropic(api_key="sk-ant-...")
+msg = client.messages.create(
+    model="claude-sonnet-4-6",
+    max_tokens=256,
+    messages=[{"role": "user", "content": "Hello"}],
+)
+
+# Pattern 2 — key passed explicitly
+from tokenwise import Anthropic
+client = Anthropic(api_key="sk-ant-...", tokenwise_key="tw_abc123")
+
+# Pattern 3 — OpenAI
+from tokenwise import OpenAI
+client = OpenAI(api_key="sk-...", tokenwise_key="tw_abc123")
+client.chat.completions.create(
+    model="gpt-5.4",
+    messages=[{"role": "user", "content": "Hello"}],
+)
+```
+
+Streaming and async work the same way:
+
+```python
+# Streaming (sync) — usage captured on stream completion
+with client.messages.create(..., stream=True) as stream:
+    for event in stream:
+        ...
+
+# Async
+from tokenwise import AsyncAnthropic
+client = AsyncAnthropic(api_key="sk-ant-...", tokenwise_key="tw_abc123")
+msg = await client.messages.create(...)
+```
+
+## What's instrumented (v1)
+
+| Provider | Method | Streaming |
+|----------|--------|-----------|
+| Anthropic | `messages.create` | ✅ usage read from the event stream (request unchanged) |
+| OpenAI | `chat.completions.create` | ✅ see note below |
+
+Other methods pass through and work, but aren't yet recorded. (OpenAI Responses
+API and legacy completions are planned.)
+
+### Note on OpenAI streaming
+
+OpenAI only returns token usage on a streamed response when the request includes
+`stream_options={"include_usage": True}`. When you stream **without** supplying
+your own `stream_options`, Tokenwise injects it for you so usage can be captured.
+This adds one final usage-only chunk (with an empty `choices` list) to the
+stream. If you already pass `stream_options`, Tokenwise respects yours and does
+not modify the request (in that case usage is captured only if you enabled it).
+
+### Latency semantics
+
+For non-streaming calls, `latency_ms` is the wall-clock time of the call. For
+streaming calls it is the **total stream duration** (until the last chunk is
+consumed), which includes time your code spends between chunks — events from
+streaming calls carry `streamed: true` so this is distinguishable.
+
+## License
+
+MIT

tokenwise_sdk-0.1.1/README.md

@@ -0,0 +1,121 @@
+# Tokenwise Python SDK
+
+Metadata-only usage tracking for Anthropic and OpenAI. Swap **one import line**
+and every API call's token counts and latency flow to your Tokenwise dashboard
+— with **zero access to your prompts or responses**.
+
+```diff
+- from anthropic import Anthropic
++ from tokenwise import Anthropic
+```
+
+Your code is otherwise unchanged: the wrapper exposes the identical interface,
+forwards every call to the official SDK, and returns its response untouched.
+
+## Why it's safe
+
+- **Metadata only.** The SDK reads exactly: `model`, `input_tokens`,
+  `output_tokens`, `cache_read_input_tokens`, `cache_creation_input_tokens`,
+  `latency_ms`, `timestamp`, `endpoint`. It never reads or transmits prompt
+  text, response text, system prompts, or tool definitions. (Contrast with
+  proxy-based tools, which see all your traffic.)
+- **Non-blocking.** Events are queued and sent on a background daemon thread.
+  If Tokenwise is slow or down, your AI calls complete normally.
+- **Fail-silent + bounded.** Up to 1,000 events buffer when offline; the oldest
+  drop silently if the buffer fills. Capture never raises, never waits.
+
+## Install
+
+```bash
+pip install tokenwise-sdk[anthropic]   # if you use Anthropic
+pip install tokenwise-sdk[openai]      # if you use OpenAI
+pip install tokenwise-sdk[anthropic,openai]
+```
+
+`anthropic` and `openai` are optional extras — install only what you use.
+
+## Configure
+
+Set your Tokenwise key (from the dashboard, looks like `tw_...`):
+
+```bash
+export TOKENWISE_API_KEY=tw_your_key
+# optional:
+export TOKENWISE_API_URL=https://tokenwise-production-aa59.up.railway.app   # default
+export TOKENWISE_DISABLED=true                       # emergency kill switch
+```
+
+Precedence for every setting: constructor argument > environment variable >
+default. If no key is configured the SDK runs disabled and your AI calls behave
+exactly as the official SDK.
+
+## Usage
+
+```python
+# Pattern 1 — key from environment
+import os
+os.environ["TOKENWISE_API_KEY"] = "tw_abc123"
+from tokenwise import Anthropic
+client = Anthropic(api_key="sk-ant-...")
+msg = client.messages.create(
+    model="claude-sonnet-4-6",
+    max_tokens=256,
+    messages=[{"role": "user", "content": "Hello"}],
+)
+
+# Pattern 2 — key passed explicitly
+from tokenwise import Anthropic
+client = Anthropic(api_key="sk-ant-...", tokenwise_key="tw_abc123")
+
+# Pattern 3 — OpenAI
+from tokenwise import OpenAI
+client = OpenAI(api_key="sk-...", tokenwise_key="tw_abc123")
+client.chat.completions.create(
+    model="gpt-5.4",
+    messages=[{"role": "user", "content": "Hello"}],
+)
+```
+
+Streaming and async work the same way:
+
+```python
+# Streaming (sync) — usage captured on stream completion
+with client.messages.create(..., stream=True) as stream:
+    for event in stream:
+        ...
+
+# Async
+from tokenwise import AsyncAnthropic
+client = AsyncAnthropic(api_key="sk-ant-...", tokenwise_key="tw_abc123")
+msg = await client.messages.create(...)
+```
+
+## What's instrumented (v1)
+
+| Provider | Method | Streaming |
+|----------|--------|-----------|
+| Anthropic | `messages.create` | ✅ usage read from the event stream (request unchanged) |
+| OpenAI | `chat.completions.create` | ✅ see note below |
+
+Other methods pass through and work, but aren't yet recorded. (OpenAI Responses
+API and legacy completions are planned.)
+
+### Note on OpenAI streaming
+
+OpenAI only returns token usage on a streamed response when the request includes
+`stream_options={"include_usage": True}`. When you stream **without** supplying
+your own `stream_options`, Tokenwise injects it for you so usage can be captured.
+This adds one final usage-only chunk (with an empty `choices` list) to the
+stream. If you already pass `stream_options`, Tokenwise respects yours and does
+not modify the request (in that case usage is captured only if you enabled it).
+
+### Latency semantics
+
+For non-streaming calls, `latency_ms` is the wall-clock time of the call. For
+streaming calls it is the **total stream duration** (until the last chunk is
+consumed), which includes time your code spends between chunks — events from
+streaming calls carry `streamed: true` so this is distinguishable.
+
+## License
+
+MIT

tokenwise_sdk-0.1.1/pyproject.toml

@@ -0,0 +1,47 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "tokenwise-sdk"
+dynamic = ["version"]
+description = "Metadata-only usage tracking for Anthropic and OpenAI — swap one import line."
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "MIT" }
+authors = [{ name = "Tokenwise" }]
+keywords = ["anthropic", "openai", "llm", "observability", "cost", "usage", "tokens"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "License :: OSI Approved :: MIT License",
+]
+# Core dependency only. The provider SDKs are optional extras — you install
+# whichever you actually use. httpx is already pulled in by both anyway.
+dependencies = ["httpx>=0.23"]
+
+[project.optional-dependencies]
+anthropic = ["anthropic>=0.40"]
+openai = ["openai>=1.40"]
+dev = [
+    "pytest>=8.0",
+    "anthropic>=0.40",
+    "openai>=1.40",
+]
+
+[project.urls]
+Homepage = "https://tokenwise.io"
+Documentation = "https://docs.tokenwise.io"
+
+[tool.hatch.version]
+path = "tokenwise/_version.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["tokenwise"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]