Skip to content

v1.10.0 — goal loop (loop engineering / /goal)

Choose a tag to compare

View all tags
@erain erain released this 09 Jun 17:06
· 21 commits to main since this release
v1.10.0
b3286c7

Loop engineering comes to glue. Agent.PursueGoal turns one persistent objective into an autonomous loop — the /goal pattern (Codex, pi-goal), as a reusable library primitive.

How it works

  1. Plan — a planner decomposes the objective into a verifiable checklist.
  2. Maker — a fresh session (Ralph-style, seeded from the durable checklist so memory lives in state, not a growing transcript) works the open items.
  3. Checker — a separate session with its own model + verifier prompt audits each item against real evidence via structured output, and decides completion. The writer never grades its own homework.
  4. Decide — stop on achieved, blocked (no progress), budget_limited, or max_iterations.

Guardrails are first-class (MaxIterations, NoProgressLimit, TokenBudget); GoalSpec.Emit streams progress.

Built entirely on existing primitives (Session.Prompt, Session.PromptJSON, loop.Run/MaxTurns, Agent.Session) — no new dependencies.

This is Phase 1: the headless primitive. The TUI /goal command (Phase 2) and durable resume + branch isolation (Phase 3) follow. Designed in ADR-0016.

(#320, PR #321)

Verified

go build/vet/test ./... green; 7 tests cover every terminal status, the maker/checker call sequence, and event emission.

Full Changelog: v1.9.0...v1.10.0

Assets 2
Loading