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>
27 lines
649 B
Python
27 lines
649 B
Python
"""
|
|
memory — Virtual memory management for AI agents.
|
|
|
|
Provides thread-scoped, append-only context buffers with:
|
|
- Immutable slots (handlers can't modify messages)
|
|
- Thread isolation (handlers only see their context)
|
|
- Complete audit trail (all messages preserved)
|
|
- GC and limits (prevent runaway memory usage)
|
|
"""
|
|
|
|
from xml_pipeline.memory.context_buffer import (
|
|
ContextBuffer,
|
|
ThreadContext,
|
|
BufferSlot,
|
|
SlotMetadata,
|
|
get_context_buffer,
|
|
slot_to_handler_metadata,
|
|
)
|
|
|
|
__all__ = [
|
|
"ContextBuffer",
|
|
"ThreadContext",
|
|
"BufferSlot",
|
|
"SlotMetadata",
|
|
"get_context_buffer",
|
|
"slot_to_handler_metadata",
|
|
]
|