picoclaw/pkg/swarm/core/interfaces.go
Danieldd28 52e3470e06 feat: implement swarm agents with hierarchical collaboration and vector memory
This commit introduces a multi-agent Swarm Engine to PicoClaw,
enabling complex task orchestration through autonomous collaboration and long-term
semantic memory.

Key Features:
- Actor Model Architecture: Every agent (node) runs in an isolated goroutine,
  communicating via a lightweight internal Event Bus.
- Hierarchical Delegation: Manager nodes can dynamically spawn specialized
  worker nodes (Researchers, Analysts, etc.) to perform sub-tasks in parallel.
- Hybrid Memory System: Combined SQLite for state persistence and Chromem-go
  for a persistent, cross-swarm Vector Knowledge Base.
- Progressive Summarization: Implemented an intelligent memory pruning mechanism
  that summarizes older context before truncation to preserve findings without
  exceeding token limits.
- Role-Based Access Control (RBAC): Configurable tool policies per role
  (e.g., Researchers can browse but not execute shell commands).

Performance & Scaling:
- Low Footprint: Idle memory usage is ~7-8 MB RSS.
- Efficient Scaling: During a stress test with 10 concurrent agents performing
  intensive research, memory usage peaked at only 27 MB.
- Per-Node Cost: Each active agent consumes approximately 0.6 MB to 2 MB of
  physical RAM depending on conversation length and summarization state.
- Stability: Successfully handled 10 parallel LLM requests with zero race
  conditions, showcasing the robustness of the Go-based Actor model.

Integration:
- Native CLI Support: Added /swarm spawn, /swarm list, and /swarm status commands.
- Mermaid Visualization: Support for /swarm viz <id> to generate organizational
  charts of active agent hierarchies.
- Configurable: Roles, models, and security policies are fully customizable
  via config.json.
2026-02-10 21:53:43 +07:00

37 lines
No EOL
1.1 KiB
Go

package core
import (
"context"
)
type SwarmStore interface {
CreateSwarm(ctx context.Context, swarm *Swarm) error
GetSwarm(ctx context.Context, id SwarmID) (*Swarm, error)
UpdateSwarm(ctx context.Context, swarm *Swarm) error
ListSwarms(ctx context.Context, status SwarmStatus) ([]*Swarm, error)
CreateNode(ctx context.Context, node *Node) error
GetNode(ctx context.Context, id NodeID) (*Node, error)
UpdateNode(ctx context.Context, node *Node) error
GetSwarmNodes(ctx context.Context, swarmID SwarmID) ([]*Node, error)
}
type SharedMemory interface {
SaveFact(ctx context.Context, fact Fact) error
SearchFacts(ctx context.Context, swarmID SwarmID, query string, limit int, global bool) ([]FactResult, error)
ClearMemory(ctx context.Context, swarmID SwarmID) error
}
type EventBus interface {
Publish(topic string, event Event) error
Subscribe(topic string, handler func(Event)) (Subscription, error)
}
type Subscription interface {
Unsubscribe() error
}
type LLMClient interface {
Chat(ctx context.Context, messages []Message, tools []ToolDef, model string) (*LLMResponse, error)
Embed(ctx context.Context, text string) ([]float32, error)
}