OSS restructuring for open-core model: - Rename package from agentserver/ to xml_pipeline/ - Update all imports (44 Python files, 31 docs/configs) - Update pyproject.toml for OSS distribution (v0.3.0) - Move prompt_toolkit from core to optional [console] extra - Remove auth/server/lsp from core optional deps (-> Nextra) New console example in examples/console/: - Self-contained demo with handlers and config - Uses prompt_toolkit (optional, falls back to input()) - No password auth, no TUI, no LSP — just the basics - Shows how to use xml-pipeline as a library Import changes: - from agentserver.* -> from xml_pipeline.* - CLI entry points updated: xml_pipeline.cli:main Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
30 lines
718 B
Python
30 lines
718 B
Python
"""
|
|
platform — Trusted orchestration layer for the agent swarm.
|
|
|
|
The platform manages:
|
|
- Prompt registry: immutable system prompts per agent
|
|
- LLM call assembly: platform controls what goes to the LLM
|
|
- Context buffer access: controlled by platform
|
|
|
|
Agents are sandboxed. They receive messages and return responses.
|
|
They cannot see or modify prompts, and cannot directly access the LLM.
|
|
"""
|
|
|
|
from xml_pipeline.platform.prompt_registry import (
|
|
PromptRegistry,
|
|
AgentPrompt,
|
|
get_prompt_registry,
|
|
)
|
|
|
|
from xml_pipeline.platform.llm_api import (
|
|
complete,
|
|
platform_complete,
|
|
)
|
|
|
|
__all__ = [
|
|
"PromptRegistry",
|
|
"AgentPrompt",
|
|
"get_prompt_registry",
|
|
"complete",
|
|
"platform_complete",
|
|
]
|