Skip to content

Roadmap

coo1white edited this page Jun 9, 2026 · 6 revisions

Roadmap

Reconciled with the current v0.1.53 code surface on 2026-06-10.

Completed Foundation

  • StateNode and pipeline contract
  • Pipeline runner foundations
  • Error feedback loop
  • Worker isolation
  • Candidate scoring
  • Verifier-gated commits
  • Sandbox Profiles
  • Workflow App SDK

End-to-End Runtime Layer

  • End-to-End Golden Path
  • Canonical Workflow Apps
  • Operator UX
  • MCP / App Surface completion
  • Release and migration discipline
  • Security / Trust Hardening
  • Dogfood One Real Repo release proof

First-Class Multi-Agent Runtime

  • Multi-Agent Runtime Core (v0.1.17)
  • Coordinator / Blackboard (v0.1.18)
  • Multi-Agent Topologies (v0.1.19)
  • Multi-Agent CLI + MCP Surface (v0.1.20)
  • Multi-Agent Operator UX (v0.1.21)
  • Multi-Agent Trust / Policy / Audit (v0.1.22)
  • Multi-Agent Eval & Replay Harness (v0.1.23)

Hardening, Scale & Explainability

  • Robustness Hardening (v0.1.24)
  • State Explosion Management — derived summaries, compact graph views (v0.1.25)
  • Evidence Adoption Reasoning Chain — why adopted, fail-closed (v0.1.26)

Platform & Control Plane

  • CLI ↔ MCP Parity — one capability registry, both surfaces, fail-closed (v0.1.27)
  • Run Registry / Control Plane — cross-repo search, resume, queue, archive, history, failed-run rerun (v0.1.28)
  • Execution Backends — pluggable node/bun/shell/container/remote/ci driver layer, identical evidence envelopes, fail-closed attestation (v0.1.29)
  • Cross-vendor distribution: single source-of-truth manifest generator with a fail-closed drift gate (Claude/Codex/…)

Agent-Driven Self-Evolution (v0.1.53) 🆕

  • Capability Registry: registerCapabilityHandler({ descriptor, run }) — new tools auto-register across CLI + MCP + Workbench. 182 built-in + dynamic dispatch fallback in all 27 CLI switch defaults and the MCP callTool.
  • Topology Registry: registerTopology(definition) — custom topologies with open string ids and data-driven role.count expansion. materializedRoles() no longer hardcodes mapper/judge switch logic.
  • BSD discipline: mechanism (Map / pipe) separate from policy (entries). Fail-closed on unknown ids.

Open Follow-Ups

  • Real container/remote/ci backend integrations beyond the contract-conformant delegating drivers
  • Richer graph inspection; node snapshot, diff, and replay
  • Contract migration tooling
  • Deeper persisted failure-node payloads
  • Control-plane scheduling/queue policies on top of the Run Registry

Known Boundary

Sandbox policy enforcement remains split by design, now made explicit per execution backend:

  • CW validates, records, and reports policy; each backend declares per-dimension enforce / attest / unsupported and fails closed when a required dimension cannot be honored.
  • The agent host (or the delegated container/remote/ci runner) enforces OS/process/network/environment controls.

This boundary should stay explicit in docs, manifests, worker prompts, operator summaries, and backend attestations.

Clone this wiki locally