idun-agent-engine 0.1.0__tar.gz → 0.2.1__tar.gz

idun_agent_engine-0.2.1/.gitignore

@@ -0,0 +1,206 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+.DS_Store
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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
+.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/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Database files
+*.db
+*.db-shm
+*.db-wai
+*.db-journal*
+*.sqlite
+*.sqlite3
+agents.db
+checkpoint_async.db
+
+# Python virtual environment
+.venv/
+venv/
+ENV/
+
+# Python cache
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+
+# Poetry
+poetry.lock
+
+# Environment variables
+.env
+
+# Custom Gitignore for Idun
+*.db-wal
+.DS_Store
+*.DS_Store

idun_agent_engine-0.2.1/PKG-INFO

@@ -0,0 +1,278 @@
+Metadata-Version: 2.4
+Name: idun-agent-engine
+Version: 0.2.1
+Summary: Python SDK and runtime to serve AI agents with FastAPI, LangGraph, and observability.
+Project-URL: Homepage, https://github.com/geoffreyharrazi/idun-agent-platform
+Project-URL: Repository, https://github.com/geoffreyharrazi/idun-agent-platform
+Project-URL: Documentation, https://github.com/geoffreyharrazi/idun-agent-platform/tree/main/libs/idun_agent_engine
+Project-URL: Issues, https://github.com/geoffreyharrazi/idun-agent-platform/issues
+Author-email: Geoffrey HARRAZI <geoffreyharrazi@gmail.com>
+License-Expression: MIT
+Keywords: agents,fastapi,langgraph,llm,observability,sdk
+Classifier: Framework :: FastAPI
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Typing :: Typed
+Requires-Python: <3.14,>=3.13
+Requires-Dist: ag-ui-protocol<0.2.0,>=0.1.8
+Requires-Dist: aiosqlite<0.22.0,>=0.21.0
+Requires-Dist: arize-phoenix-otel<1.0.0,>=0.2.0
+Requires-Dist: arize-phoenix<12,>=11.22.0
+Requires-Dist: fastapi<0.117.0,>=0.116.1
+Requires-Dist: google-adk<2.0.0,>=1.9.0
+Requires-Dist: httpx<0.29.0,>=0.28.1
+Requires-Dist: idun-agent-schema<0.3.0,>=0.2.0
+Requires-Dist: langchain-core<0.4.0,>=0.3.72
+Requires-Dist: langchain-google-vertexai<3.0.0,>=2.0.27
+Requires-Dist: langchain<0.4,>=0.3.27
+Requires-Dist: langfuse-haystack>=2.3.0
+Requires-Dist: langfuse==2.60.8
+Requires-Dist: langgraph-checkpoint-sqlite<3.0.0,>=2.0.11
+Requires-Dist: langgraph<0.7.0,>=0.6.3
+Requires-Dist: openinference-instrumentation-langchain<1.0.0,>=0.1.13
+Requires-Dist: pydantic<3.0.0,>=2.11.7
+Requires-Dist: python-dotenv>=1.1.1
+Requires-Dist: streamlit<2.0.0,>=1.47.1
+Requires-Dist: uvicorn<0.36.0,>=0.35.0
+Description-Content-Type: text/markdown
+
+# Idun Agent Engine
+
+Turn any LangGraph-based agent into a production-grade API in minutes.
+
+Idun Agent Engine is a lightweight runtime and SDK that wraps your agent with a FastAPI server, adds streaming, structured responses, config validation, and optional observability — with zero boilerplate. Use a YAML file or a fluent builder to configure and run.
+
+## Installation
+
+```bash
+pip install idun-agent-engine
+```
+
+- Requires Python 3.13
+- Ships with FastAPI, Uvicorn, LangGraph, SQLite checkpointing, and optional observability hooks
+
+## Quickstart
+
+### 1) Minimal one-liner (from a YAML config)
+
+```python
+from idun_agent_engine.core.server_runner import run_server_from_config
+
+run_server_from_config("config.yaml")
+```
+
+Example `config.yaml`:
+
+```yaml
+server:
+  api:
+    port: 8000
+
+agent:
+  type: "langgraph"
+  config:
+    name: "My Example LangGraph Agent"
+    graph_definition: "./examples/01_basic_config_file/example_agent.py:app"
+    # Optional: conversation persistence
+    checkpointer:
+      type: "sqlite"
+      db_url: "sqlite:///example_checkpoint.db"
+    # Optional: provider-agnostic observability
+    observability:
+      provider: langfuse   # or phoenix
+      enabled: true
+      options:
+        host: ${LANGFUSE_HOST}
+        public_key: ${LANGFUSE_PUBLIC_KEY}
+        secret_key: ${LANGFUSE_SECRET_KEY}
+        run_name: "idun-langgraph-run"
+```
+
+Run and open docs at `http://localhost:8000/docs`.
+
+### 2) Programmatic setup with the fluent builder
+
+```python
+from pathlib import Path
+from idun_agent_engine import ConfigBuilder, create_app, run_server
+
+config = (
+    ConfigBuilder()
+    .with_api_port(8000)
+    .with_langgraph_agent(
+        name="Programmatic Example Agent",
+        graph_definition=str(Path("./examples/02_programmatic_config/smart_agent.py:app")),
+        sqlite_checkpointer="programmatic_example.db",
+    )
+    .build()
+)
+
+app = create_app(engine_config=config)
+run_server(app, reload=True)
+```
+
+## Endpoints
+
+All servers expose these by default:
+
+- POST `/agent/invoke`: single request/response
+- POST `/agent/stream`: server-sent events stream of `ag-ui` protocol events
+- GET `/health`: service health with engine version
+- GET `/`: root landing with links
+
+Invoke example:
+
+```bash
+curl -X POST "http://localhost:8000/agent/invoke" \
+  -H "Content-Type: application/json" \
+  -d '{"query": "Hello!", "session_id": "user-123"}'
+```
+
+Stream example:
+
+```bash
+curl -N -X POST "http://localhost:8000/agent/stream" \
+  -H "Content-Type: application/json" \
+  -d '{"query": "Tell me a story", "session_id": "user-123"}'
+```
+
+## LangGraph integration
+
+Point the engine to a `StateGraph` variable in your file using `graph_definition`:
+
+```python
+# examples/01_basic_config_file/example_agent.py
+import operator
+from typing import Annotated, TypedDict
+from langgraph.graph import END, StateGraph
+
+class AgentState(TypedDict):
+    messages: Annotated[list, operator.add]
+
+def greeting_node(state):
+    user_message = state["messages"][-1] if state["messages"] else ""
+    return {"messages": [("ai", f"Hello! You said: '{user_message}'")]}
+
+graph = StateGraph(AgentState)
+graph.add_node("greet", greeting_node)
+graph.set_entry_point("greet")
+graph.add_edge("greet", END)
+
+# This variable name is referenced by graph_definition
+app = graph
+```
+
+Then reference it in config:
+
+```yaml
+agent:
+  type: "langgraph"
+  config:
+    graph_definition: "./examples/01_basic_config_file/example_agent.py:app"
+```
+
+Behind the scenes, the engine:
+
+- Validates config with Pydantic models
+- Loads your `StateGraph` from disk
+- Optionally wires a SQLite checkpointer via `langgraph.checkpoint.sqlite`
+- Exposes `invoke` and `stream` endpoints
+- Bridges LangGraph events to `ag-ui` stream events
+
+## Observability (optional)
+
+Enable provider-agnostic observability via the `observability` block in your agent config. Today supports Langfuse and Arize Phoenix (OpenInference) patterns; more coming soon.
+
+```yaml
+agent:
+  type: "langgraph"
+  config:
+    observability:
+      provider: langfuse   # or phoenix
+      enabled: true
+      options:
+        host: ${LANGFUSE_HOST}
+        public_key: ${LANGFUSE_PUBLIC_KEY}
+        secret_key: ${LANGFUSE_SECRET_KEY}
+        run_name: "idun-langgraph-run"
+```
+
+## Configuration reference
+
+- `server.api.port` (int): HTTP port (default 8000)
+- `agent.type` (enum): currently `langgraph` (CrewAI placeholder exists but not implemented)
+- `agent.config.name` (str): human-readable name
+- `agent.config.graph_definition` (str): absolute or relative `path/to/file.py:variable`
+- `agent.config.checkpointer` (sqlite): `{ type: "sqlite", db_url: "sqlite:///file.db" }`
+- `agent.config.observability` (optional): provider options as shown above
+
+Config can be sourced by:
+
+- `engine_config` (preferred): pass a validated `EngineConfig` to `create_app`
+- `config_dict`: dict validated at runtime
+- `config_path`: path to YAML; defaults to `config.yaml`
+
+## Examples
+
+The `examples/` folder contains complete projects:
+
+- `01_basic_config_file`: YAML config + simple agent
+- `02_programmatic_config`: `ConfigBuilder` usage and advanced flows
+- `03_minimal_setup`: one-line server from config
+
+Run any example with Python 3.13 installed.
+
+## CLI and runtime helpers
+
+Top-level imports for convenience:
+
+```python
+from idun_agent_engine import (
+  create_app,
+  run_server,
+  run_server_from_config,
+  run_server_from_builder,
+  ConfigBuilder,
+)
+```
+
+- `create_app(...)` builds the FastAPI app and registers routes
+- `run_server(app, ...)` runs with Uvicorn
+- `run_server_from_config(path, ...)` loads config, builds app, and runs
+- `run_server_from_builder(builder, ...)` builds from a builder and runs
+
+## Production notes
+
+- Use a process manager (e.g., multiple Uvicorn workers behind a gateway). Note: `reload=True` is for development and incompatible with multi-worker mode.
+- Mount behind a reverse proxy and enable TLS where appropriate.
+- Persist conversations using the SQLite checkpointer in production or replace with a custom checkpointer when available.
+
+## Roadmap
+
+- CrewAI adapter (placeholder exists, not yet implemented)
+- Additional stores and checkpointers
+- First-class CLI for `idun` commands
+
+## Contributing
+
+Issues and PRs are welcome. See the repository:
+
+- Repo: `https://github.com/geoffreyharrazi/idun-agent-platform`
+- Package path: `libs/idun_agent_engine`
+- Open an issue: `https://github.com/geoffreyharrazi/idun-agent-platform/issues`
+
+Run locally:
+
+```bash
+cd libs/idun_agent_engine
+poetry install
+poetry run pytest -q
+```
+
+## License
+
+MIT — see `LICENSE` in the repo root.

idun_agent_engine-0.2.1/README.md

@@ -0,0 +1,236 @@
+# Idun Agent Engine
+
+Turn any LangGraph-based agent into a production-grade API in minutes.
+
+Idun Agent Engine is a lightweight runtime and SDK that wraps your agent with a FastAPI server, adds streaming, structured responses, config validation, and optional observability — with zero boilerplate. Use a YAML file or a fluent builder to configure and run.
+
+## Installation
+
+```bash
+pip install idun-agent-engine
+```
+
+- Requires Python 3.13
+- Ships with FastAPI, Uvicorn, LangGraph, SQLite checkpointing, and optional observability hooks
+
+## Quickstart
+
+### 1) Minimal one-liner (from a YAML config)
+
+```python
+from idun_agent_engine.core.server_runner import run_server_from_config
+
+run_server_from_config("config.yaml")
+```
+
+Example `config.yaml`:
+
+```yaml
+server:
+  api:
+    port: 8000
+
+agent:
+  type: "langgraph"
+  config:
+    name: "My Example LangGraph Agent"
+    graph_definition: "./examples/01_basic_config_file/example_agent.py:app"
+    # Optional: conversation persistence
+    checkpointer:
+      type: "sqlite"
+      db_url: "sqlite:///example_checkpoint.db"
+    # Optional: provider-agnostic observability
+    observability:
+      provider: langfuse   # or phoenix
+      enabled: true
+      options:
+        host: ${LANGFUSE_HOST}
+        public_key: ${LANGFUSE_PUBLIC_KEY}
+        secret_key: ${LANGFUSE_SECRET_KEY}
+        run_name: "idun-langgraph-run"
+```
+
+Run and open docs at `http://localhost:8000/docs`.
+
+### 2) Programmatic setup with the fluent builder
+
+```python
+from pathlib import Path
+from idun_agent_engine import ConfigBuilder, create_app, run_server
+
+config = (
+    ConfigBuilder()
+    .with_api_port(8000)
+    .with_langgraph_agent(
+        name="Programmatic Example Agent",
+        graph_definition=str(Path("./examples/02_programmatic_config/smart_agent.py:app")),
+        sqlite_checkpointer="programmatic_example.db",
+    )
+    .build()
+)
+
+app = create_app(engine_config=config)
+run_server(app, reload=True)
+```
+
+## Endpoints
+
+All servers expose these by default:
+
+- POST `/agent/invoke`: single request/response
+- POST `/agent/stream`: server-sent events stream of `ag-ui` protocol events
+- GET `/health`: service health with engine version
+- GET `/`: root landing with links
+
+Invoke example:
+
+```bash
+curl -X POST "http://localhost:8000/agent/invoke" \
+  -H "Content-Type: application/json" \
+  -d '{"query": "Hello!", "session_id": "user-123"}'
+```
+
+Stream example:
+
+```bash
+curl -N -X POST "http://localhost:8000/agent/stream" \
+  -H "Content-Type: application/json" \
+  -d '{"query": "Tell me a story", "session_id": "user-123"}'
+```
+
+## LangGraph integration
+
+Point the engine to a `StateGraph` variable in your file using `graph_definition`:
+
+```python
+# examples/01_basic_config_file/example_agent.py
+import operator
+from typing import Annotated, TypedDict
+from langgraph.graph import END, StateGraph
+
+class AgentState(TypedDict):
+    messages: Annotated[list, operator.add]
+
+def greeting_node(state):
+    user_message = state["messages"][-1] if state["messages"] else ""
+    return {"messages": [("ai", f"Hello! You said: '{user_message}'")]}
+
+graph = StateGraph(AgentState)
+graph.add_node("greet", greeting_node)
+graph.set_entry_point("greet")
+graph.add_edge("greet", END)
+
+# This variable name is referenced by graph_definition
+app = graph
+```
+
+Then reference it in config:
+
+```yaml
+agent:
+  type: "langgraph"
+  config:
+    graph_definition: "./examples/01_basic_config_file/example_agent.py:app"
+```
+
+Behind the scenes, the engine:
+
+- Validates config with Pydantic models
+- Loads your `StateGraph` from disk
+- Optionally wires a SQLite checkpointer via `langgraph.checkpoint.sqlite`
+- Exposes `invoke` and `stream` endpoints
+- Bridges LangGraph events to `ag-ui` stream events
+
+## Observability (optional)
+
+Enable provider-agnostic observability via the `observability` block in your agent config. Today supports Langfuse and Arize Phoenix (OpenInference) patterns; more coming soon.
+
+```yaml
+agent:
+  type: "langgraph"
+  config:
+    observability:
+      provider: langfuse   # or phoenix
+      enabled: true
+      options:
+        host: ${LANGFUSE_HOST}
+        public_key: ${LANGFUSE_PUBLIC_KEY}
+        secret_key: ${LANGFUSE_SECRET_KEY}
+        run_name: "idun-langgraph-run"
+```
+
+## Configuration reference
+
+- `server.api.port` (int): HTTP port (default 8000)
+- `agent.type` (enum): currently `langgraph` (CrewAI placeholder exists but not implemented)
+- `agent.config.name` (str): human-readable name
+- `agent.config.graph_definition` (str): absolute or relative `path/to/file.py:variable`
+- `agent.config.checkpointer` (sqlite): `{ type: "sqlite", db_url: "sqlite:///file.db" }`
+- `agent.config.observability` (optional): provider options as shown above
+
+Config can be sourced by:
+
+- `engine_config` (preferred): pass a validated `EngineConfig` to `create_app`
+- `config_dict`: dict validated at runtime
+- `config_path`: path to YAML; defaults to `config.yaml`
+
+## Examples
+
+The `examples/` folder contains complete projects:
+
+- `01_basic_config_file`: YAML config + simple agent
+- `02_programmatic_config`: `ConfigBuilder` usage and advanced flows
+- `03_minimal_setup`: one-line server from config
+
+Run any example with Python 3.13 installed.
+
+## CLI and runtime helpers
+
+Top-level imports for convenience:
+
+```python
+from idun_agent_engine import (
+  create_app,
+  run_server,
+  run_server_from_config,
+  run_server_from_builder,
+  ConfigBuilder,
+)
+```
+
+- `create_app(...)` builds the FastAPI app and registers routes
+- `run_server(app, ...)` runs with Uvicorn
+- `run_server_from_config(path, ...)` loads config, builds app, and runs
+- `run_server_from_builder(builder, ...)` builds from a builder and runs
+
+## Production notes
+
+- Use a process manager (e.g., multiple Uvicorn workers behind a gateway). Note: `reload=True` is for development and incompatible with multi-worker mode.
+- Mount behind a reverse proxy and enable TLS where appropriate.
+- Persist conversations using the SQLite checkpointer in production or replace with a custom checkpointer when available.
+
+## Roadmap
+
+- CrewAI adapter (placeholder exists, not yet implemented)
+- Additional stores and checkpointers
+- First-class CLI for `idun` commands
+
+## Contributing
+
+Issues and PRs are welcome. See the repository:
+
+- Repo: `https://github.com/geoffreyharrazi/idun-agent-platform`
+- Package path: `libs/idun_agent_engine`
+- Open an issue: `https://github.com/geoffreyharrazi/idun-agent-platform/issues`
+
+Run locally:
+
+```bash
+cd libs/idun_agent_engine
+poetry install
+poetry run pytest -q
+```
+
+## License
+
+MIT — see `LICENSE` in the repo root.