synth-ai 0.2.6.dev5__tar.gz → 0.4.11__tar.gz

synth_ai-0.4.11/MANIFEST.in

@@ -0,0 +1,44 @@
+include README.md
+include LICENSE
+recursive-include synth_ai *.py
+# Only include lightweight config/data files from core packages
+recursive-include synth_ai *.toml
+# Include examples for task app discovery
+recursive-include examples *.py
+recursive-include examples *.toml
+recursive-include examples *.md
+recursive-include examples *.sh
+
+# Prune heavy example/demo/test/data trees from the sdist (keep code)
+prune tests
+prune private_tests
+prune synth_ai/tracing_v3/tests
+recursive-exclude synth_ai **/test_*.py
+recursive-exclude synth_ai **/tests/*
+
+# Remove large data files from package
+recursive-exclude synth_ai *.json
+# But include TUI package.json and other config files
+include synth_ai/tui/app/package.json
+include synth_ai/tui/app/package.dist.json
+include synth_ai/tui/app/bunfig.toml
+include synth_ai/tui/app/tsconfig.json
+include synth_ai/tui/app/tsconfig.typecheck.json
+# Include TUI TypeScript source files
+recursive-include synth_ai/tui/app/src *.ts
+recursive-include synth_ai/tui/app/src *.tsx
+recursive-exclude synth_ai *.db
+recursive-exclude synth_ai *.duckdb
+recursive-exclude synth_ai *.sqlite
+recursive-exclude synth_ai *.parquet
+recursive-exclude synth_ai *.csv
+recursive-exclude synth_ai *.npz
+recursive-exclude synth_ai *.npy
+recursive-exclude synth_ai *.pt
+recursive-exclude synth_ai *.pth
+recursive-exclude synth_ai *.bin
+recursive-exclude synth_ai *.zip
+recursive-exclude synth_ai *.tar
+global-exclude *.pyc
+global-exclude __pycache__
+global-exclude .DS_Store

synth_ai-0.4.11/PKG-INFO

@@ -0,0 +1,245 @@
+Metadata-Version: 2.4
+Name: synth-ai
+Version: 0.4.11
+Summary: Serverless Posttraining for Agents - Core AI functionality and tracing
+Author-email: Synth AI <josh@usesynth.ai>
+License: MIT
+Project-URL: Homepage, https://github.com/synth-laboratories/synth-ai
+Project-URL: Repository, https://github.com/synth-laboratories/synth-ai
+Project-URL: Issues, https://github.com/synth-laboratories/synth-ai/issues
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: python-dotenv>=1.0.1
+Requires-Dist: requests>=2.32.3
+Requires-Dist: tqdm>=4.66.4
+Requires-Dist: typing_extensions>=4.0.0
+Requires-Dist: rich>=13.9.0
+Requires-Dist: openai>=1.99.0
+Requires-Dist: anthropic>=0.42.0
+Requires-Dist: langfuse<3.0.0,>=2.53.9
+Requires-Dist: opentelemetry-api>=1.26.0
+Requires-Dist: opentelemetry-sdk>=1.26.0
+Requires-Dist: groq>=0.30.0
+Requires-Dist: google-genai>=1.26.0
+Requires-Dist: together>=1.5.21
+Requires-Dist: mistralai>=1.9.2
+Requires-Dist: fastapi>=0.115.12
+Requires-Dist: uvicorn>=0.34.2
+Requires-Dist: numpy>=2.2.3
+Requires-Dist: networkx>=3.4.2
+Requires-Dist: sqlalchemy>=2.0.42
+Requires-Dist: celery>=5.4.0
+Requires-Dist: redis>=6.2.0
+Requires-Dist: aiosqlite>=0.21.0
+Requires-Dist: libsql>=0.1.8
+Requires-Dist: pynacl>=1.5.0
+Requires-Dist: click<8.2,>=8.1.7
+Requires-Dist: aiohttp>=3.8.0
+Requires-Dist: nest_asyncio>=1.6.0
+Requires-Dist: httpx>=0.28.1
+Requires-Dist: modal<2.0.0,>=1.1.4
+Requires-Dist: docker>=7.0.0
+Requires-Dist: mcp>=1.21.0
+Requires-Dist: ruff>=0.12.9
+Requires-Dist: tomli_w>=1.0.0
+Requires-Dist: dspy>=3.0.4
+Requires-Dist: setuptools>=80.9.0
+Requires-Dist: gymnasium>=0.26.2
+Requires-Dist: gepa>=0.0.17
+Requires-Dist: datasets>=4.0.0
+Provides-Extra: dev
+Requires-Dist: build>=1.2.2.post1; extra == "dev"
+Requires-Dist: twine>=4.0.0; extra == "dev"
+Requires-Dist: keyring>=24.0.0; extra == "dev"
+Requires-Dist: pytest>=8.3.3; extra == "dev"
+Requires-Dist: pytest-xdist>=3.6.1; extra == "dev"
+Requires-Dist: pytest-timeout>=2.3.1; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.24.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
+Requires-Dist: pyright>=1.1.350; extra == "dev"
+Requires-Dist: coverage[toml]>=7.3.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Requires-Dist: papermill>=2.6.0; extra == "dev"
+Requires-Dist: nest_asyncio>=1.6.0; extra == "dev"
+Provides-Extra: research
+Requires-Dist: crafter>=1.8.3; extra == "research"
+Requires-Dist: datasets>=4.0.0; extra == "research"
+Provides-Extra: swe
+Requires-Dist: morphcloud>=0.1.3; extra == "swe"
+Requires-Dist: swebench>=2.3.0; extra == "swe"
+Provides-Extra: all
+Requires-Dist: crafter>=1.8.3; extra == "all"
+Requires-Dist: datasets>=4.0.0; extra == "all"
+Requires-Dist: morphcloud>=0.1.3; extra == "all"
+Requires-Dist: swebench>=2.3.0; extra == "all"
+Requires-Dist: pyboy>=2.6.0; extra == "all"
+Requires-Dist: transformers>=4.56.1; extra == "all"
+Requires-Dist: redis>=6.2.0; extra == "all"
+Provides-Extra: analytics
+Requires-Dist: pandas>=2.2.3; extra == "analytics"
+Dynamic: license-file
+
+# Synth
+
+[![Python](https://img.shields.io/badge/python-3.11+-blue)](https://www.python.org/)
+[![PyPI](https://img.shields.io/pypi/v/synth-ai.svg)](https://pypi.org/project/synth-ai/)
+[![PyPI Main](https://img.shields.io/badge/main-0.4.7-blue)](https://pypi.org/project/synth-ai/0.4.7/)
+[![PyPI Nightly](https://img.shields.io/badge/nightly-0.4.7-orange)](https://pypi.org/project/synth-ai/0.4.7/)
+[![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)
+![Coverage](https://img.shields.io/badge/coverage-28.65%25-yellow)
+![Tests](https://img.shields.io/badge/tests-847%20passing-brightgreen)
+
+Serverless Posttraining APIs for Developers
+
+<p align="center">
+  <picture align="center">
+    <source media="(prefers-color-scheme: dark)" srcset="assets/langprobe_v2_dark.png">
+    <source media="(prefers-color-scheme: light)" srcset="assets/langprobe_v2_light.png">
+    <img alt="Shows a bar chart comparing prompt optimization performance across GPT-4.1 Nano, GPT-4o Mini, and GPT-5 Nano with baseline vs GEPA optimized." src="assets/langprobe_v2_light.png">
+  </picture>
+</p>
+
+<p align="center">
+  <i>Average accuracy on <a href="https://arxiv.org/abs/2502.20315">LangProBe</a> prompt optimization benchmarks.</i>
+</p>
+
+## Demo Notebooks (Colab)
+
+- [GEPA Banking77 Prompt Optimization](https://colab.research.google.com/github/synth-laboratories/synth-ai/blob/main/demos/gepa_banking77/gepa_banking77_prompt_optimization.ipynb)
+- [GEPA Crafter VLM Verifier Optimization](https://colab.research.google.com/github/synth-laboratories/synth-ai/blob/main/demos/gepa_crafter_vlm/gepa_crafter_vlm_verifier_optimization.ipynb)
+- [GraphGen Image Style Matching](https://colab.research.google.com/github/synth-laboratories/synth-ai/blob/main/demos/image_style_matching/graphgen_image_style_matching.ipynb)
+
+## Highlights
+
+- 🎯 **GEPA Prompt Optimization** - Automatically improve prompts with evolutionary search. See 70%→95% accuracy gains on Banking77, +62% on critical game achievements
+- 🔍 **Zero-Shot Verifiers** - Fast, accurate rubric-based evaluation with configurable scoring criteria
+- 🧬 **GraphGen** - Train custom verifier graphs optimized for your specific workflows. Train custom pipelines for other tasks
+- 🚀 **No Code Changes** - Wrap existing code in a FastAPI app and optimize via HTTP. Works with any language or framework
+- ⚡️ **Local Development** - Run experiments locally with tunneled task apps. No cloud setup required
+- 🗂️ **Multi-Experiment Management** - Track and compare prompts/models across runs with built-in experiment queues
+
+## Getting Started
+
+```
+uv add
+uv run synth-ai tui
+```
+
+## Testing
+
+Run the TUI integration tests:
+
+```bash
+cd synth_ai/_tui
+bun test
+```
+
+Synth is maintained by devs behind the [MIPROv2](https://scholar.google.com/citations?view_op=view_citation&hl=en&user=jauNVA8AAAAJ&citation_for_view=jauNVA8AAAAJ:u5HHmVD_uO8C) prompt optimizer.
+
+## Documentation
+
+**[docs.usesynth.ai](https://docs.usesynth.ai)**
+
+## GEPA Prompt Optimization (SDK)
+
+Run GEPA prompt optimization programmatically:
+
+```python
+import asyncio
+import os
+from synth_ai.sdk.api.train.prompt_learning import PromptLearningJob
+from synth_ai.sdk.localapi import LocalAPIConfig, create_local_api
+
+# Create a local task app: app = create_local_api(LocalAPIConfig(app_id="my_app", handler=my_handler))
+
+# Create and submit a GEPA job
+pl_job = PromptLearningJob.from_dict({
+    "job_type": "prompt_learning",
+    "config": {
+        "prompt_learning": {
+            "gepa": {
+                "rollout": {"budget": 100},
+                "population_size": 10,
+                "generations": 5,
+            }
+        }
+    },
+    "task_app_id": "my_task_app",
+})
+
+pl_job.submit()
+result = pl_job.stream_until_complete(timeout=3600.0)
+print(f"Best score: {result.best_score}")
+```
+
+See the [Banking77 demo notebook](demos/gepa_banking77/gepa_banking77_prompt_optimization.ipynb) for a complete example with local task apps.
+
+## Zero-Shot Verifiers (SDK)
+
+Run a built-in verifier graph with rubric criteria passed at runtime. See the [Crafter VLM demo](demos/gepa_crafter_vlm/) for verifier optimization:
+
+```python
+import asyncio
+import os
+from synth_ai.sdk.graphs import VerifierClient
+
+async def run_verifier():
+    client = VerifierClient(
+        base_url=os.environ["SYNTH_BACKEND_BASE"],
+        api_key=os.environ["SYNTH_API_KEY"],
+    )
+    result = await client.evaluate(
+        job_id="zero_shot_verifier_single",
+        trace={"session_id": "s", "session_time_steps": []},
+        rubric={
+            "event": [{"id": "accuracy", "weight": 1.0, "description": "Correctness"}],
+            "outcome": [{"id": "task_completion", "weight": 1.0, "description": "Completed task"}],
+        },
+        options={"event": True, "outcome": True, "model": "gpt-5-nano"},
+        policy_name="my_policy",
+        task_app_id="my_task",
+    )
+    return result
+
+asyncio.run(run_verifier())
+```
+
+You can also call arbitrary graphs directly:
+
+```python
+from synth_ai.sdk.graphs import GraphCompletionsClient
+
+client = GraphCompletionsClient(base_url="https://api.usesynth.ai", api_key="...")
+resp = await client.run(
+    graph={"kind": "zero_shot", "verifier_shape": "mapreduce", "verifier_mode": "rubric"},
+    input_data={"trace": {"session_id": "s", "session_time_steps": []}, "rubric": {"event": [], "outcome": []}},
+)
+```
+
+## GraphGen: Train Custom Verifier Graphs
+
+Train custom verifier graphs using GraphGen. See the [Image Style Matching demo](demos/image_style_matching/) for a complete GraphGen example:
+
+```python
+from synth_ai.sdk.api.train.graphgen import GraphGenJob
+
+# Train a verifier graph
+verifier_job = GraphGenJob.from_dataset(
+    dataset="verifier_dataset.json",
+    graph_type="verifier",
+    policy_models=["gpt-4.1"],
+    proposer_effort="medium",  # Use "medium" (gpt-4.1) or "high" (gpt-5.2)
+    rollout_budget=200,
+)
+verifier_job.submit()
+result = verifier_job.stream_until_complete(timeout=3600.0)
+
+# Run inference with trained verifier
+verification = verifier_job.run_verifier(
+    trace=my_trace,
+    context={"rubric": my_rubric},
+)
+print(f"Score: {verification.score}, Reasoning: {verification.reasoning}")
+```

synth_ai-0.4.11/README.md

@@ -0,0 +1,162 @@
+# Synth
+
+[![Python](https://img.shields.io/badge/python-3.11+-blue)](https://www.python.org/)
+[![PyPI](https://img.shields.io/pypi/v/synth-ai.svg)](https://pypi.org/project/synth-ai/)
+[![PyPI Main](https://img.shields.io/badge/main-0.4.7-blue)](https://pypi.org/project/synth-ai/0.4.7/)
+[![PyPI Nightly](https://img.shields.io/badge/nightly-0.4.7-orange)](https://pypi.org/project/synth-ai/0.4.7/)
+[![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)
+![Coverage](https://img.shields.io/badge/coverage-28.65%25-yellow)
+![Tests](https://img.shields.io/badge/tests-847%20passing-brightgreen)
+
+Serverless Posttraining APIs for Developers
+
+<p align="center">
+  <picture align="center">
+    <source media="(prefers-color-scheme: dark)" srcset="assets/langprobe_v2_dark.png">
+    <source media="(prefers-color-scheme: light)" srcset="assets/langprobe_v2_light.png">
+    <img alt="Shows a bar chart comparing prompt optimization performance across GPT-4.1 Nano, GPT-4o Mini, and GPT-5 Nano with baseline vs GEPA optimized." src="assets/langprobe_v2_light.png">
+  </picture>
+</p>
+
+<p align="center">
+  <i>Average accuracy on <a href="https://arxiv.org/abs/2502.20315">LangProBe</a> prompt optimization benchmarks.</i>
+</p>
+
+## Demo Notebooks (Colab)
+
+- [GEPA Banking77 Prompt Optimization](https://colab.research.google.com/github/synth-laboratories/synth-ai/blob/main/demos/gepa_banking77/gepa_banking77_prompt_optimization.ipynb)
+- [GEPA Crafter VLM Verifier Optimization](https://colab.research.google.com/github/synth-laboratories/synth-ai/blob/main/demos/gepa_crafter_vlm/gepa_crafter_vlm_verifier_optimization.ipynb)
+- [GraphGen Image Style Matching](https://colab.research.google.com/github/synth-laboratories/synth-ai/blob/main/demos/image_style_matching/graphgen_image_style_matching.ipynb)
+
+## Highlights
+
+- 🎯 **GEPA Prompt Optimization** - Automatically improve prompts with evolutionary search. See 70%→95% accuracy gains on Banking77, +62% on critical game achievements
+- 🔍 **Zero-Shot Verifiers** - Fast, accurate rubric-based evaluation with configurable scoring criteria
+- 🧬 **GraphGen** - Train custom verifier graphs optimized for your specific workflows. Train custom pipelines for other tasks
+- 🚀 **No Code Changes** - Wrap existing code in a FastAPI app and optimize via HTTP. Works with any language or framework
+- ⚡️ **Local Development** - Run experiments locally with tunneled task apps. No cloud setup required
+- 🗂️ **Multi-Experiment Management** - Track and compare prompts/models across runs with built-in experiment queues
+
+## Getting Started
+
+```
+uv add
+uv run synth-ai tui
+```
+
+## Testing
+
+Run the TUI integration tests:
+
+```bash
+cd synth_ai/_tui
+bun test
+```
+
+Synth is maintained by devs behind the [MIPROv2](https://scholar.google.com/citations?view_op=view_citation&hl=en&user=jauNVA8AAAAJ&citation_for_view=jauNVA8AAAAJ:u5HHmVD_uO8C) prompt optimizer.
+
+## Documentation
+
+**[docs.usesynth.ai](https://docs.usesynth.ai)**
+
+## GEPA Prompt Optimization (SDK)
+
+Run GEPA prompt optimization programmatically:
+
+```python
+import asyncio
+import os
+from synth_ai.sdk.api.train.prompt_learning import PromptLearningJob
+from synth_ai.sdk.localapi import LocalAPIConfig, create_local_api
+
+# Create a local task app: app = create_local_api(LocalAPIConfig(app_id="my_app", handler=my_handler))
+
+# Create and submit a GEPA job
+pl_job = PromptLearningJob.from_dict({
+    "job_type": "prompt_learning",
+    "config": {
+        "prompt_learning": {
+            "gepa": {
+                "rollout": {"budget": 100},
+                "population_size": 10,
+                "generations": 5,
+            }
+        }
+    },
+    "task_app_id": "my_task_app",
+})
+
+pl_job.submit()
+result = pl_job.stream_until_complete(timeout=3600.0)
+print(f"Best score: {result.best_score}")
+```
+
+See the [Banking77 demo notebook](demos/gepa_banking77/gepa_banking77_prompt_optimization.ipynb) for a complete example with local task apps.
+
+## Zero-Shot Verifiers (SDK)
+
+Run a built-in verifier graph with rubric criteria passed at runtime. See the [Crafter VLM demo](demos/gepa_crafter_vlm/) for verifier optimization:
+
+```python
+import asyncio
+import os
+from synth_ai.sdk.graphs import VerifierClient
+
+async def run_verifier():
+    client = VerifierClient(
+        base_url=os.environ["SYNTH_BACKEND_BASE"],
+        api_key=os.environ["SYNTH_API_KEY"],
+    )
+    result = await client.evaluate(
+        job_id="zero_shot_verifier_single",
+        trace={"session_id": "s", "session_time_steps": []},
+        rubric={
+            "event": [{"id": "accuracy", "weight": 1.0, "description": "Correctness"}],
+            "outcome": [{"id": "task_completion", "weight": 1.0, "description": "Completed task"}],
+        },
+        options={"event": True, "outcome": True, "model": "gpt-5-nano"},
+        policy_name="my_policy",
+        task_app_id="my_task",
+    )
+    return result
+
+asyncio.run(run_verifier())
+```
+
+You can also call arbitrary graphs directly:
+
+```python
+from synth_ai.sdk.graphs import GraphCompletionsClient
+
+client = GraphCompletionsClient(base_url="https://api.usesynth.ai", api_key="...")
+resp = await client.run(
+    graph={"kind": "zero_shot", "verifier_shape": "mapreduce", "verifier_mode": "rubric"},
+    input_data={"trace": {"session_id": "s", "session_time_steps": []}, "rubric": {"event": [], "outcome": []}},
+)
+```
+
+## GraphGen: Train Custom Verifier Graphs
+
+Train custom verifier graphs using GraphGen. See the [Image Style Matching demo](demos/image_style_matching/) for a complete GraphGen example:
+
+```python
+from synth_ai.sdk.api.train.graphgen import GraphGenJob
+
+# Train a verifier graph
+verifier_job = GraphGenJob.from_dataset(
+    dataset="verifier_dataset.json",
+    graph_type="verifier",
+    policy_models=["gpt-4.1"],
+    proposer_effort="medium",  # Use "medium" (gpt-4.1) or "high" (gpt-5.2)
+    rollout_budget=200,
+)
+verifier_job.submit()
+result = verifier_job.stream_until_complete(timeout=3600.0)
+
+# Run inference with trained verifier
+verification = verifier_job.run_verifier(
+    trace=my_trace,
+    context={"rubric": my_rubric},
+)
+print(f"Score: {verification.score}, Reasoning: {verification.reasoning}")
+```

synth_ai-0.4.11/pyproject.toml

@@ -0,0 +1,241 @@
+[project]
+name = "synth-ai"
+version = "0.4.11"
+description = "Serverless Posttraining for Agents - Core AI functionality and tracing"
+authors = [{name = "Synth AI", email = "josh@usesynth.ai"}]
+license = { text = "MIT" }
+readme = "README.md"
+requires-python = ">=3.11"
+dependencies = [
+    # Core dependencies
+    "pydantic>=2.0.0",
+    "python-dotenv>=1.0.1",
+    "requests>=2.32.3",
+    "tqdm>=4.66.4",
+    "typing_extensions>=4.0.0",
+    # AI/LLM providers
+    "rich>=13.9.0",
+    "openai>=1.99.0",
+    "anthropic>=0.42.0",
+    # Tracing and observability
+    "langfuse>=2.53.9,<3.0.0",
+    "opentelemetry-api>=1.26.0",
+    "opentelemetry-sdk>=1.26.0",
+    # Storage and caching
+    "groq>=0.30.0",
+    "google-genai>=1.26.0",
+    "together>=1.5.21",
+    "mistralai>=1.9.2",
+    # Environment framework - basic dependencies
+    "fastapi>=0.115.12",
+    "uvicorn>=0.34.2",
+    "numpy>=2.2.3",
+    "networkx>=3.4.2",
+    "sqlalchemy>=2.0.42",
+    "celery>=5.4.0",
+    "redis>=6.2.0",
+    "aiosqlite>=0.21.0",
+    "libsql>=0.1.8",
+    "pynacl>=1.5.0",
+    "click>=8.1.7,<8.2", # For CLI (pin to signature compatible with Typer)
+    "aiohttp>=3.8.0", # For async HTTP requests
+    "nest_asyncio>=1.6.0", # For nested event loops in sync callbacks
+    "httpx>=0.28.1", # CLI preflights and HTTP clients (pulls httpcore)
+    "modal>=1.1.4,<2.0.0",
+    "docker>=7.0.0",
+    "mcp>=1.21.0",
+    "ruff>=0.12.9",
+    "tomli_w>=1.0.0",
+    "dspy>=3.0.4",
+    "setuptools>=80.9.0",
+    "gymnasium>=0.26.2",
+    "gepa>=0.0.17",
+    # Dataset loading - used by many task apps (banking77, math, hotpotqa, etc.)
+    "datasets>=4.0.0",
+]
+
+[project.scripts]
+synth-ai = "synth_ai.cli:cli"
+
+[project.optional-dependencies]
+dev = [
+    "build>=1.2.2.post1",
+    "twine>=4.0.0",
+    "keyring>=24.0.0",
+    "pytest>=8.3.3",
+    "pytest-xdist>=3.6.1",
+    "pytest-timeout>=2.3.1",
+    "pytest-asyncio>=0.24.0",
+    "pytest-cov>=4.1.0",
+    "pyright>=1.1.350",
+    "coverage[toml]>=7.3.0",
+    "ruff>=0.1.0",
+    "papermill>=2.6.0",
+    "nest_asyncio>=1.6.0",
+]
+research = [
+    # Heavy game environment dependencies
+    "crafter>=1.8.3",
+    "datasets>=4.0.0",  # For math environments
+]
+swe = [
+    "morphcloud>=0.1.3",
+    "swebench>=2.3.0",
+]
+all = [
+    # Include research and swe dependencies in all
+    "crafter>=1.8.3",
+    "datasets>=4.0.0",
+    "morphcloud>=0.1.3",
+    "swebench>=2.3.0",
+    "pyboy>=2.6.0",
+    "transformers>=4.56.1",
+    "redis>=6.2.0",
+]
+analytics = [
+    "pandas>=2.2.3",
+]
+
+[project.urls]
+Homepage = "https://github.com/synth-laboratories/synth-ai"
+Repository = "https://github.com/synth-laboratories/synth-ai"
+Issues = "https://github.com/synth-laboratories/synth-ai/issues"
+
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.packages.find]
+include = ["synth_ai*"]
+exclude = [
+    "docs*",
+    "tests*",
+    "scripts*",
+    "private_tests*",
+    # Exclude heavy demo/test subpackages from distribution
+    "synth_ai.*agent_demos*",
+    "synth_ai.*old*",
+    "synth_ai.*tests*",
+    "synth_ai.*units*",
+    "synth_ai.tracing_v3.tests*",
+]
+
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.exclude-package-data]
+"synth_ai" = [
+    # Exclude heavy data inside agent_demos/old/tests
+    "**/agent_demos/**",
+    "**/old/**",
+    "**/tests/**",
+    "**/units/**",
+]
+
+[tool.setuptools.package-data]
+"synth_ai" = [
+    "demos/demo_task_apps/math/config.toml",
+    "demos/demo_task_apps/math/deploy_task_app.sh",
+    "_tui/dist/*",
+    "tui/app/package.json",
+    "tui/app/package.dist.json",
+    "tui/app/bunfig.toml",
+    "tui/app/tsconfig.json",
+    "tui/app/tsconfig.typecheck.json",
+    "tui/app/src/**/*.ts",
+    "tui/app/src/**/*.tsx",
+]
+
+[tool.pytest.ini_options]
+testpaths = ["tests", "private_tests"]
+python_files = "test_*.py"
+python_classes = "Test*"
+python_functions = "test_*"
+asyncio_mode = "auto"
+markers = [
+    "fast: marks tests as fast (≤5 seconds) - these are the default tests to run",
+    "slow: marks tests as slow (>5 seconds) - requires more time/resources",
+    "integration: marks tests as integration tests requiring external services",
+    "unit: marks tests as isolated unit tests",
+    "public: marks tests that can run in any environment",
+    "private: marks tests that may require credentials or special setup",
+]
+# Add timeout for long-running tests
+timeout = 300
+# Show test durations (slowest N tests)
+addopts = "--durations=10"
+
+[tool.coverage.run]
+source = ["synth_ai"]
+omit = ["*/tests/*", "*/test_*"]
+data_file = "coverage/.coverage"
+
+[tool.coverage.report]
+precision = 2
+show_missing = true
+skip_covered = false
+
+[tool.pyright]
+include = ["synth_ai", "tests"]
+exclude = ["**/__pycache__"]
+pythonVersion = "3.11"
+typeCheckingMode = "standard"
+reportMissingImports = true
+reportMissingTypeStubs = false
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+src = ["synth_ai"]
+extend-exclude = [
+    ".venv",
+    ".tmp",
+    "dev",
+    "docs",
+    "scripts",
+    "tests",
+    "private_tests",
+    "old",
+    "tauri",
+    "temp",
+    "traces",
+    "traces_*",
+    "synth_ai.db",
+    "synth_ai/tracing_v3/tests",
+]
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "N", "UP", "YTT", "B", "C4", "T10", "SIM"]
+ignore = [
+    "E501",  # Line too long
+    "B008",  # Do not perform function call in argument defaults
+    "UP035", # Don't require `from __future__ import annotations` (not needed in 3.11+)
+    "UP006", # Allow typing.Tuple
+    "UP045", # Allow Optional[...] annotations
+]
+
+[tool.ruff.lint.per-file-ignores]
+"synth_ai/http.py" = ["F403"]
+"**/__init__.py" = ["N999"]
+"**/__main__.py" = ["N999"]
+
+[tool.ty]
+# Suppress conservative warnings about possibly-missing-attribute
+# These are false positives for dict.get() calls and dynamic attributes
+rules = { "possibly-missing-attribute" = "ignore" }
+
+[dependency-groups]
+dev = [
+    "pytest>=8.3.3",
+    "pytest-xdist>=3.6.1",
+    "pytest-timeout>=2.3.1",
+    "pytest-asyncio>=0.24.0",
+    "pytest-cov>=4.1.0",
+    "ruff>=0.1.0",
+    "pyright>=1.1.350",
+    "responses>=0.25.7",
+    "httpx>=0.28.1",
+    "crafter>=1.8.3",
+    "papermill>=2.6.0",
+    "nest_asyncio>=1.6.0",
+]