rote

docs/05 · roadmap

The phase arc

One phase at a time, each behind an exit gate with a number on it. We are late to tier 1 and early to tier 0 — where the field ships eviction alone and no major harness sends a diff.

now · P1 working memoryG1 pass · 37.2%G2 pendingtarget 2026 Q3
P0

Foundations

tier — · shipped · done

“Nothing above this is worth building on sand.”

  • Core schemas and the closed Expect DSL — Zod first, types derived
  • Lossless crash-safe recorder: append-only, fsync per event, blobs over 64KB content-addressed
  • Verified replay executor — deterministic steps at zero LLM tokens, every expect re-checked
  • The sacred invariant suite touching every executor exit path
P1

Working memory — tier 0

tier 0 · launched 2026-08-08 · done

“The first browser agent with a managed context window.”

  • A11 observation eviction — kills the dominant quadratic term
  • A4 diff observations — 849 diffs in G1, median 24 chars, −99.6% vs re-send
  • B3 cache-layout discipline — immutable prefix routed through prompt_cache_key, 20.5% cost cut at WP-N25
  • Launch package: the npx quickstart, the README number, the demo
G1 · exit gate · the curvePASS — 37.2% [35.6–38.8], 75/75 verified

Cumulative logical input must grow materially slower with task length — a public ≥30% floor, CI-bounded, at success parity.

G2 · exit gate · the levelPASS — corrected B2 18/18 per harness; 83.1% [82.1–83.9] vs Browser Use 0.13.7

A tokens-per-task win at success parity — at least 15 runs, seeded-bootstrap lower bound above the floor.

P2

The harness that learns — tiers 1 & 2

tier 1 · 2 · 2026 Q4 · ← we are here

“Your 50th task on a site costs a fraction of your 1st.”

  • Playbook distiller — trajectories become verified playbooks
  • Matcher: semantic match + bind behind the fingerprint gate
  • B4, identity v2, and synthetic nested frame/open-shadow contexts are built; authoritative evidence is next
P3

Speculation

tier 2 · 2027 Q1

“Warm flows bounded by think-time only.”

  • Transition models learned from recorded runs
  • Speculative pre-execution with assertion-gated commits
P4

Fleet & enterprise

tier — · 2027 Q2–Q3

“10K tasks a day, audited, lowest $ per task.”

  • Fleet-scale memory administration and audit surfaces
  • Every replay attributable: who, when, from which verified run
P5

Platform

tier — · 2027 Q4+

“The efficiency substrate other agents build on.”

  • The memory manager as a surface other harnesses consume

Built and working end-to-end

  • ✓Core schemas + the closed Expect DSL (10 primitives)
  • ✓Lossless, crash-safe recorder
  • ✓Verified replay executor — zero-LLM deterministic steps
  • ✓CDP browser backend + fake-world fixture backends
  • ✓Perception: distill → stable IDs → budget → diffs
  • ✓A11 observation eviction
  • ✓A4 diff observations, measured on real pages
  • ✓B3 cache-layout discipline, economically qualified (T11)
  • ✓B4 deterministic action-history compaction (long-run qualification pending)
  • ✓Agent loop with tagged LLM accounting on every call
  • ✓Benchmark matrix, curve reports, head-to-head launch gate
  • ✓Action plane: settledness, self-healing resolution, scoped repair

Not built — on purpose, on the record

The roadmap rule is executor before distiller — never build ahead of the phase. The gaps are part of the ledger:

B4 long-run qualification

the mechanism is built; 50+ step provider cache economics and SPA parity remain E7.6

Playbook distiller

V1 replays hand-written playbooks; trajectory → playbook distillation is unbuilt

Matcher (semantic match + bind)

only the exact-fingerprint hard gate exists today

Site memory, model routing, speculation

designed in docs/02, scheduled for P2/P3

P1 launch closure

G1 and corrected G2 pass. Public @rotehq/cli@0.1.0 matches its audited registry artifact, and T28 verifies the provider-backed quickstart from an empty directory. P1 launched without expanding its one-provider, pinned-cell claims. E7.1's corpus, identity v2, and T31 synthetic composed contexts are built; authoritative evidence is next, with structural action-contract drift still the cross-cutting P2 priority.