API Updates (#73)

* API Keys passed from Client instead of distro configuration

* delete distribution registry

* Rename the "package" word away

* Introduce a "Router" layer for providers

Some providers need to be factorized and considered as thin routing
layers on top of other providers. Consider two examples:

- The inference API should be a routing layer over inference providers,
  routed using the "model" key
- The memory banks API is another instance where various memory bank
  types will be provided by independent providers (e.g., a vector store
  is served by Chroma while a keyvalue memory can be served by Redis or
  PGVector)

This commit introduces a generalized routing layer for this purpose.

* update `apis_to_serve`

* llama_toolchain -> llama_stack

* Codemod from llama_toolchain -> llama_stack

- added providers/registry
- cleaned up api/ subdirectories and moved impls away
- restructured api/api.py
- from llama_stack.apis.<api> import foo should work now
- update imports to do llama_stack.apis.<api>
- update many other imports
- added __init__, fixed some registry imports
- updated registry imports
- create_agentic_system -> create_agent
- AgenticSystem -> Agent

* Moved some stuff out of common/; re-generated OpenAPI spec

* llama-toolchain -> llama-stack (hyphens)

* add control plane API

* add redis adapter + sqlite provider

* move core -> distribution

* Some more toolchain -> stack changes

* small naming shenanigans

* Removing custom tool and agent utilities and moving them client side

* Move control plane to distribution server for now

* Remove control plane from API list

* no codeshield dependency randomly plzzzzz

* Add "fire" as a dependency

* add back event loggers

* stack configure fixes

* use brave instead of bing in the example client

* add init file so it gets packaged

* add init files so it gets packaged

* Update MANIFEST

* bug fix

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
Co-authored-by: Xi Yan <xiyan@meta.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>

llama_stack/providers/impls/meta_reference/agents/tests/__init__.py

@@ -0,0 +1,5 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.

llama_stack/providers/impls/meta_reference/agents/tests/code_execution.py

@@ -0,0 +1,93 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+import unittest
+
+from llama_models.llama3.api.datatypes import (
+    Attachment,
+    BuiltinTool,
+    CompletionMessage,
+    StopReason,
+    ToolCall,
+)
+
+from ..tools.builtin import CodeInterpreterTool
+
+
+class TestCodeInterpreter(unittest.IsolatedAsyncioTestCase):
+    async def test_matplotlib(self):
+        tool = CodeInterpreterTool()
+        code = """
+import matplotlib.pyplot as plt
+import numpy as np
+
+x = np.array([1, 1])
+y = np.array([0, 10])
+
+plt.plot(x, y)
+plt.title('x = 1')
+plt.xlabel('x')
+plt.ylabel('y')
+plt.grid(True)
+plt.axvline(x=1, color='r')
+plt.show()
+        """
+        message = CompletionMessage(
+            role="assistant",
+            content="",
+            tool_calls=[
+                ToolCall(
+                    call_id="call_id",
+                    tool_name=BuiltinTool.code_interpreter,
+                    arguments={"code": code},
+                )
+            ],
+            stop_reason=StopReason.end_of_message,
+        )
+        ret = await tool.run([message])
+
+        self.assertEqual(len(ret), 1)
+
+        output = ret[0].content
+        self.assertIsInstance(output, Attachment)
+        self.assertEqual(output.mime_type, "image/png")
+
+    async def test_path_unlink(self):
+        tool = CodeInterpreterTool()
+        code = """
+import os
+from pathlib import Path
+import tempfile
+
+dpath = Path(os.environ["MPLCONFIGDIR"])
+with open(dpath / "test", "w") as f:
+    f.write("hello")
+
+Path(dpath / "test").unlink()
+print("_OK_")
+        """
+        message = CompletionMessage(
+            role="assistant",
+            content="",
+            tool_calls=[
+                ToolCall(
+                    call_id="call_id",
+                    tool_name=BuiltinTool.code_interpreter,
+                    arguments={"code": code},
+                )
+            ],
+            stop_reason=StopReason.end_of_message,
+        )
+        ret = await tool.run([message])
+
+        self.assertEqual(len(ret), 1)
+
+        output = ret[0].content
+        self.assertTrue("_OK_" in output)
+
+
+if __name__ == "__main__":
+    unittest.main()