Skip to main content

coreason-human-layer

Project description

coreason-human-layer

License: Prosperity 3.0 Build Status Code Style: Ruff Documentation

Domain: HITL, Durable Execution, & RLHF Data Capture Role: The "Switchboard" & "Labeling Factory"

coreason-human-layer is the dedicated bridge between autonomous execution and human oversight, operationalizing Online Alignment through a Multiverse Branching Strategy. Instead of a simple "Stop/Go" model, it allows humans to fork agent reality, capturing decisions as DPO Triplets to fuel the model improvement loop.

Features

1. The Stasis Engine (Durable Execution)

Implements an event-sourcing pattern for durable execution.

  • Snapshot: Stores a pointer to the last event ID rather than a massive state blob.
  • Rehydration: Replays events to rebuild context.
  • Storage: Hot storage in Redis Streams, cold archival in S3.

2. The Branch Manager (Cognitive Forking)

Manages the tree topology of execution branches.

  • Forking: create_fork API allows instantiating new execution paths with human overrides.
  • Prefix Caching: Optimizes costs and latency by reusing the KV Cache of the shared prefix (cached_prefix_id) on the LLM backend.
  • Topology: Exposes the conversation tree structure for visualization.

3. The Super-Prompt Injector (System Injection)

Ensures the model obeys human overrides.

  • Frame Injection: Injects a high-priority [SYSTEM PRIORITY INTERRUPT] block.
  • Variable Patching: Parses and hard-updates variables from human overrides (e.g., "Dose = 50mg").

4. The Learning Bridge (Auto-DPO)

Converts operational actions into training assets.

  • Trigger: Merging a fork (approving it) while abandoning another.
  • Auto-DPO: Automatically constructs a DPO object ({ prompt, chosen, rejected }) and pushes it to coreason-synthesis.

Server Mode (The Switchboard)

The library now includes a standalone microservice mode, exposing a REST API for managing branches and forks.

Deployment (Docker)

docker build -t coreason-human-layer .
docker run -p 8000:8000 \
  -e REDIS_URL=redis://host.docker.internal:6379 \
  -e SYNTHESIS_BASE_URL=http://host.docker.internal:8001 \
  coreason-human-layer

Endpoints

  • POST /fork: Create a new execution branch.
  • POST /merge: Merge two branches (triggers DPO signal).
  • GET /topology/{root_id}: Get the branch tree structure.
  • GET /health: Check service health.

Installation

pip install coreason-human-layer

Usage (Library)

See docs/usage.md for detailed usage examples including the REST API.

from uuid import uuid4
from coreason_human_layer.branch_manager import BranchManager
from coreason_human_layer.stasis import InMemoryStasisEngine

# Initialize engines
stasis = InMemoryStasisEngine()
manager = BranchManager(stasis_engine=stasis)

# Create a root branch
root_id = uuid4()
branch_id = manager.create_fork(
    parent_branch_id=None,
    parent_event_id=None,
    root_id=root_id,
    human_override_text="Initial Start",
    user_context=... # UserContext object
)

License

Copyright (c) 2025 CoReason, Inc. Licensed under the Prosperity Public License 3.0.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

coreason_human_layer-0.4.0.tar.gz (17.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

coreason_human_layer-0.4.0-py3-none-any.whl (23.4 kB view details)

Uploaded Python 3

File details

Details for the file coreason_human_layer-0.4.0.tar.gz.

File metadata

  • Download URL: coreason_human_layer-0.4.0.tar.gz
  • Upload date:
  • Size: 17.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for coreason_human_layer-0.4.0.tar.gz
Algorithm Hash digest
SHA256 9ff969410e2d9000d3d18fc9c2d9838bd5d67dba2b7c7fe0b040067b17abacad
MD5 1a690f98d7e881a632e8c58ae1012e77
BLAKE2b-256 97af7ecd6cdc4d466a206b63d5fc48be682d4d8dc9214957b855759ef9f46205

See more details on using hashes here.

Provenance

The following attestation bundles were made for coreason_human_layer-0.4.0.tar.gz:

Publisher: publish.yml on CoReason-AI/coreason-human-layer

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file coreason_human_layer-0.4.0-py3-none-any.whl.

File metadata

File hashes

Hashes for coreason_human_layer-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0d12b85bce803f7d5f34e61c8de2f87f275ac2cc8376c8a2af6943732bf2cba5
MD5 488b1140ba1388eb409ca291babd9c65
BLAKE2b-256 cbc718bb334be4c9f6ecf5ddeb9cada180680f4f2b34a30a44d609aa10c8ba1c

See more details on using hashes here.

Provenance

The following attestation bundles were made for coreason_human_layer-0.4.0-py3-none-any.whl:

Publisher: publish.yml on CoReason-AI/coreason-human-layer

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page