tokenstretcher 1.3.0__tar.gz

tokenstretcher-1.3.0/LICENSE

@@ -0,0 +1,76 @@
+Business Source License 1.1 (BSL 1.1)
+
+Copyright (c) 2026 TokenStretcher Contributors
+
+Parameters:
+- Licensor: TokenStretcher Contributors
+- Licensed Work: TokenStretcher (all files in this repository)
+- Additional Use Grant: You may use the Licensed Work for non-commercial purposes,
+  including personal use and use inside internal tools at companies.
+- Change Date: Four years from the date this file was first published.
+- Change License: MIT License
+
+On the fourth anniversary of the date this file was first published, this license
+will automatically convert to the MIT License.
+
+Until the Change Date, the following restrictions apply:
+
+**Commercial Use Restriction:**
+You may NOT use this software, in whole or in substantial part, to provide a
+commercial service, hosted product, or resold offering (including as part of an
+AI coding agent, devtool, or proxy service) without a separate commercial license
+from the Licensor.
+
+This includes, but is not limited to:
+- Offering TokenStretcher (or a derivative) as a paid or freemium service
+- Embedding it into a commercial AI coding product and charging for usage
+- Reselling access to the decomposition, routing, or proxy capabilities
+
+The intent is to keep the local client and core ideas open for individuals and
+builders, while protecting the commercial rights around the prepaid proxy model
+and high-quality orchestration intelligence.
+
+For commercial licensing inquiries, contact the maintainers.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+
+ADDITIONAL DISCLAIMER FOR PAID / PROXY USAGE:
+
+This software includes functionality that can be used to operate a paid proxy
+service that resells or intermediates access to third-party large language model
+APIs (such as those provided by xAI, OpenAI, Anthropic, etc.).
+
+THE AUTHORS AND COPYRIGHT HOLDERS PROVIDE NO WARRANTY that:
+- Use of this software (including the proxy, virtual key, and prepaid billing
+  components) complies with the terms of service of any third-party LLM provider.
+- The prepaid balance tracking, virtual key system, or billing logic is accurate,
+  secure, or free from errors.
+- Any funds collected through the use of this software will be honored, refunded,
+  or result in continued service.
+- The software will be available, error-free, or suitable for any particular
+  commercial purpose.
+
+USERS WHO OPERATE PAID INSTANCES OF THIS SOFTWARE (including via Lemon Squeezy,
+Stripe, or any other payment processor) ASSUME ALL RISK AND LIABILITY for
+compliance with applicable laws, third-party terms of service, data protection
+regulations, and consumer protection obligations.
+
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY INDIRECT,
+INCIDENTAL, SPECIAL, CONSEQUENTIAL, OR PUNITIVE DAMAGES, INCLUDING BUT NOT
+LIMITED TO LOSS OF PROFITS, DATA, USE, GOODWILL, OR OTHER INTANGIBLE LOSSES,
+RESULTING FROM (A) THE USE OR INABILITY TO USE THE SOFTWARE; (B) ANY CONDUCT OR
+CONTENT OF ANY THIRD PARTY; (C) ANY CONTENT OBTAINED FROM THE SOFTWARE; OR (D)
+UNAUTHORIZED ACCESS, USE, OR ALTERATION OF YOUR TRANSMISSIONS OR CONTENT,
+WHETHER BASED ON WARRANTY, CONTRACT, STATUTE, TORT (INCLUDING NEGLIGENCE), OR
+ANY OTHER LEGAL THEORY, WHETHER OR NOT WE HAVE BEEN INFORMED OF THE POSSIBILITY
+OF SUCH DAMAGE.
+
+YOU ARE SOLELY RESPONSIBLE FOR ENSURING THAT YOUR USE OF THIS SOFTWARE, INCLUDING
+ANY PAID PROXY OR BILLING FUNCTIONALITY, COMPLIES WITH ALL APPLICABLE LAWS AND
+THE TERMS OF SERVICE OF ANY LLM PROVIDERS WHOSE MODELS ARE ACCESSED THROUGH IT.

tokenstretcher-1.3.0/MANIFEST.in

@@ -0,0 +1,18 @@
+include README.md
+include LICENSE
+include pyproject.toml
+include requirements.txt
+
+# Explicitly exclude sensitive / user-specific files
+exclude .env
+exclude .env.*
+exclude .tokensaver/config.toml
+prune .tokensaver
+prune tests
+prune examples
+prune .venv
+prune __pycache__
+global-exclude *.pyc
+global-exclude *.pyo
+global-exclude *.egg-info
+global-exclude .DS_Store

tokenstretcher-1.3.0/PKG-INFO

@@ -0,0 +1,181 @@
+Metadata-Version: 2.4
+Name: tokenstretcher
+Version: 1.3.0
+Summary: Get better results for far less cost. TokenStretcher decomposes complex work, routes tasks intelligently, and enforces hard prepaid budgets so you never blow past limits.
+Author: TokenStretcher Contributors
+License: Business Source License 1.1
+Project-URL: Homepage, https://github.com/ResponsiveDesignLLC/TokenStretcher
+Project-URL: Documentation, https://github.com/ResponsiveDesignLLC/TokenStretcher#readme
+Project-URL: Repository, https://github.com/ResponsiveDesignLLC/TokenStretcher
+Project-URL: Issues, https://github.com/ResponsiveDesignLLC/TokenStretcher/issues
+Keywords: ai,llm,agents,token-optimization,cost-saving,orchestration,grok,litellm
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Internet :: Proxy Servers
+Classifier: Topic :: Office/Business :: Financial :: Point-Of-Sale
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: litellm>=1.40.0
+Requires-Dist: pydantic>=2.7.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: rich>=13.7.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: aiofiles>=23.0.0
+Requires-Dist: tomli>=2.0.0; python_version < "3.11"
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.0.0; extra == "mcp"
+Provides-Extra: proxy
+Requires-Dist: fastapi>=0.110.0; extra == "proxy"
+Requires-Dist: uvicorn[standard]>=0.29.0; extra == "proxy"
+Requires-Dist: python-multipart>=0.0.9; extra == "proxy"
+Requires-Dist: resend>=0.8.0; extra == "proxy"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-asyncio; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: mypy; extra == "dev"
+Requires-Dist: black; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Requires-Dist: twine; extra == "dev"
+Dynamic: license-file
+
+# TokenStretcher
+
+**Higher quality results for far less cost.**
+
+Most people throw entire complex tasks at a powerful model in one giant prompt. This wastes massive context on irrelevant details, produces unfocused output, and makes it easy to blow past budgets.
+
+**TokenStretcher works differently.**
+
+It breaks complex work into focused subtasks, routes each piece to the right model, executes in parallel where it makes sense, and synthesizes a superior final result — while using dramatically fewer tokens overall.
+
+Typical real-world outcome on hard tasks: **30–60% lower cost** with **better, more reliable results** than a single massive prompt.
+
+---
+
+## Why Giant Prompts Are Wasteful
+
+- 70%+ of the tokens often go to context that doesn't matter for the current part of the work.
+- One model is forced to be a jack-of-all-trades.
+- Output quality suffers from lack of focus.
+- Costs are unpredictable and easy to overrun.
+
+## With TokenStretcher
+
+- **Prepaid only, hard caps** — You preload funds. The system enforces your budget in real time. No surprise bills, ever.
+- **Focused work** — Each part of the task gets only the context and expertise it needs.
+- **Better results** — Specialists handle what they're good at. You get sharper, more production-grade output.
+- **Full visibility** — Every run gives you a clear report so you can see exactly what you got for the cost.
+
+You stay in control. The system stays efficient.
+
+---
+
+## Real Results on Complex Tasks
+
+Here are outcomes from recent production-grade tasks (measured against strong single-prompt baselines using the same underlying models):
+
+**EvalForge** — Complete LLM Evaluation & Prompt Optimization Platform  
+- Requirements: evaluation engine with multiple dimensions + caching/routing, prompt optimizer with Pareto analysis, analytics (kappa, cost curves, exports), background jobs, auth/billing integration, FastAPI + HTMX UI, SDK + CLI, Docker, full tests, demo.  
+- Result: **52% token reduction**, "excellent" quality rating, clean modular production code delivered across specialized components.
+
+**Personal Finance Dashboard** — Full end-to-end system  
+- Requirements: CoinGecko price data, 30/90-day metrics (volatility, Sharpe, correlations, trends), FastAPI + JWT auth, Redis-backed background jobs, interactive HTMX frontend, CSV/PDF export, pytest suite with golden data, Docker Compose, comprehensive README.  
+- Result: **9%+ token savings** (significant improvement vs earlier versions), fully working runnable system with real calculations, auth, jobs, and frontend.
+
+On the right tasks (new features, large refactors, multi-domain systems with research + code + tests + infra), teams routinely see **30–60%+ effective cost reduction** while getting more focused, higher-quality deliverables.
+
+---
+
+## Quick Start
+
+### CLI
+
+```bash
+pip install tokenstretcher
+
+# Run a task
+tokenstretcher "Build a production FastAPI service with JWT auth, user CRUD, and rate limiting"
+
+# See the plan only (no cost)
+tokenstretcher --plan-only "Refactor the entire payment module"
+
+# JSON output (ideal when called by other AI agents)
+tokenstretcher --json "Design a multi-tenant permissions system"
+```
+
+### Python API
+
+```python
+from tokenstretcher import run
+
+result = await run(
+    "Create a complete, secure FastAPI authentication system with refresh tokens and roles"
+)
+
+print(result.final_output)
+print(result.savings.summary())
+```
+
+---
+
+## Built for Agentic Tools
+
+TokenStretcher is designed to be called as a tool by other AI coding environments (Grok Build, OpenCode, Cursor, Aider, Continue.dev, etc.).
+
+Every run returns structured results and clear savings data so the calling agent can decide intelligently when decomposition is worth it.
+
+---
+
+## Prepay Model — Zero Surprise Bills
+
+1. Add funds to your wallet.
+2. Run tasks.
+3. Every call is tracked against your prepaid balance in real time.
+4. If balance is too low, it simply stops — no overages.
+
+This is the safest possible way to use powerful models at scale, whether you're a human or an autonomous agent.
+
+---
+
+## Installation
+
+```bash
+pip install tokenstretcher
+```
+
+Optional proxy features (for running your own prepaid key service):
+
+```bash
+pip install "tokenstretcher[proxy]"
+```
+
+---
+
+## Why It Matters
+
+Most AI usage today is extremely wasteful.
+
+TokenStretcher gives you a practical way to get **better work** while using **far fewer tokens** and staying within hard budget limits.
+
+Prepaid. Hard-capped. Focused. Effective.
+
+That’s the entire point.
+
+---
+
+## License
+
+TokenStretcher is released under the Business Source License (BSL 1.1).
+
+Free for individuals and internal use. Commercial resale or hosting as a paid service requires a separate license after the change date.
+
+See the LICENSE file for details.

tokenstretcher-1.3.0/PYPI_README.md

@@ -0,0 +1,132 @@
+# TokenStretcher
+
+**Higher quality results for far less cost.**
+
+Most people throw entire complex tasks at a powerful model in one giant prompt. This wastes massive context on irrelevant details, produces unfocused output, and makes it easy to blow past budgets.
+
+**TokenStretcher works differently.**
+
+It breaks complex work into focused subtasks, routes each piece to the right model, executes in parallel where it makes sense, and synthesizes a superior final result — while using dramatically fewer tokens overall.
+
+Typical real-world outcome on hard tasks: **30–60% lower cost** with **better, more reliable results** than a single massive prompt.
+
+---
+
+## Why Giant Prompts Are Wasteful
+
+- 70%+ of the tokens often go to context that doesn't matter for the current part of the work.
+- One model is forced to be a jack-of-all-trades.
+- Output quality suffers from lack of focus.
+- Costs are unpredictable and easy to overrun.
+
+## With TokenStretcher
+
+- **Prepaid only, hard caps** — You preload funds. The system enforces your budget in real time. No surprise bills, ever.
+- **Focused work** — Each part of the task gets only the context and expertise it needs.
+- **Better results** — Specialists handle what they're good at. You get sharper, more production-grade output.
+- **Full visibility** — Every run gives you a clear report so you can see exactly what you got for the cost.
+
+You stay in control. The system stays efficient.
+
+---
+
+## Real Results on Complex Tasks
+
+Here are outcomes from recent production-grade tasks (measured against strong single-prompt baselines using the same underlying models):
+
+**EvalForge** — Complete LLM Evaluation & Prompt Optimization Platform  
+- Requirements: evaluation engine with multiple dimensions + caching/routing, prompt optimizer with Pareto analysis, analytics (kappa, cost curves, exports), background jobs, auth/billing integration, FastAPI + HTMX UI, SDK + CLI, Docker, full tests, demo.  
+- Result: **52% token reduction**, "excellent" quality rating, clean modular production code delivered across specialized components.
+
+**Personal Finance Dashboard** — Full end-to-end system  
+- Requirements: CoinGecko price data, 30/90-day metrics (volatility, Sharpe, correlations, trends), FastAPI + JWT auth, Redis-backed background jobs, interactive HTMX frontend, CSV/PDF export, pytest suite with golden data, Docker Compose, comprehensive README.  
+- Result: **9%+ token savings** (significant improvement vs earlier versions), fully working runnable system with real calculations, auth, jobs, and frontend.
+
+On the right tasks (new features, large refactors, multi-domain systems with research + code + tests + infra), teams routinely see **30–60%+ effective cost reduction** while getting more focused, higher-quality deliverables.
+
+---
+
+## Quick Start
+
+### CLI
+
+```bash
+pip install tokenstretcher
+
+# Run a task
+tokenstretcher "Build a production FastAPI service with JWT auth, user CRUD, and rate limiting"
+
+# See the plan only (no cost)
+tokenstretcher --plan-only "Refactor the entire payment module"
+
+# JSON output (ideal when called by other AI agents)
+tokenstretcher --json "Design a multi-tenant permissions system"
+```
+
+### Python API
+
+```python
+from tokenstretcher import run
+
+result = await run(
+    "Create a complete, secure FastAPI authentication system with refresh tokens and roles"
+)
+
+print(result.final_output)
+print(result.savings.summary())
+```
+
+---
+
+## Built for Agentic Tools
+
+TokenStretcher is designed to be called as a tool by other AI coding environments (Grok Build, OpenCode, Cursor, Aider, Continue.dev, etc.).
+
+Every run returns structured results and clear savings data so the calling agent can decide intelligently when decomposition is worth it.
+
+---
+
+## Prepay Model — Zero Surprise Bills
+
+1. Add funds to your wallet.
+2. Run tasks.
+3. Every call is tracked against your prepaid balance in real time.
+4. If balance is too low, it simply stops — no overages.
+
+This is the safest possible way to use powerful models at scale, whether you're a human or an autonomous agent.
+
+---
+
+## Installation
+
+```bash
+pip install tokenstretcher
+```
+
+Optional proxy features (for running your own prepaid key service):
+
+```bash
+pip install "tokenstretcher[proxy]"
+```
+
+---
+
+## Why It Matters
+
+Most AI usage today is extremely wasteful.
+
+TokenStretcher gives you a practical way to get **better work** while using **far fewer tokens** and staying within hard budget limits.
+
+Prepaid. Hard-capped. Focused. Effective.
+
+That’s the entire point.
+
+---
+
+## License
+
+TokenStretcher is released under the Business Source License (BSL 1.1).
+
+Free for individuals and internal use. Commercial resale or hosting as a paid service requires a separate license after the change date.
+
+See the LICENSE file for details.