Epic: Leverage Paperclip features into AI Dark Factory

Overview

Phased plan to bring key Paperclip (paperclipai/paperclip) control-plane features into ADF (terraphim_orchestrator), adapted for Rust and file-based state (no database).

Research document: cto-executive-system/plans/research-paperclip-leverage-into-adf.md

Phases

• Phase 1: Cost Tracking + Output Parsing #638
• Phase 2: Session Persistence #639
• Phase 3: Config Revisions with Rollback #640
• Phase 4: Structured Activity Log #641
• Phase 5: Approval Gates #642

Context

ADF is a Rust-based agent orchestrator running on bigbox that spawns CLI agents (Claude Code, Codex) using a reconciliation loop with Safety/Core/Growth layer hierarchy. Paperclip is a Node.js/React control plane for AI agent companies with cost tracking, session persistence, config versioning, approval gates, and audit logging.

Architecture Decision

All features implemented in Rust with file-based JSON/JSONL state. No PostgreSQL dependency. Each phase is independently shippable and testable.

ADF Strengths to Preserve

• Rust performance (single binary orchestrator)
• NightwatchMonitor drift detection
• CompoundReview cross-agent synthesis
• RoutingEngine keyword-based model selection
• Safety/Core/Growth layer hierarchy

Key Design Decisions

• No database: File-based JSON/JSONL state (atomic writes with .tmp+rename)
• Backward-compatible: All new config fields use #[serde(default)]
• Incremental: Each phase ships independently with its own tests
• Claude-first: Cost tracking and session persistence leverage Claude Code's --output-format stream-json and --resume flags; Codex agents gracefully degrade

Start with cto-executive-system/plans/research-paperclip-leverage-into-adf.md and review phase issues #638–#642. Confirm how each Paperclip feature maps to Rust and file-based JSON/JSONL state without PostgreSQL. Done means the five phases are independently shippable, backward-compatible, and covered by their own tests.