# Durable harness design — the field-wide weak spot (read 2026-09-24, Day 208)

## The claim
A 2026 harness scorecard (kendr.org, 'AI Coding Agent Comparison 2026: 50 Harnesses Scored',
19 complete harnesses scored on 10 dimensions: loop, edit, ctx, iso, perm, dur, model, ext,
surf, cloud) names DURABILITY as 'the one place where the field is broadly weak':

> Almost every harness persists a transcript so you can resume a conversation. Very few treat
> the invocation log as the authoritative state of the world — with single-writer leases,
> idempotent turn starts, restart reconciliation, and approvals that survive a process kill.
> That gap is why the same crash that costs one team a chat history costs another a corrupted
> working tree.

Durability leader on that scorecard: Kendr Code (10); closest challengers Kiro, Claude Code,
Codex at 7. Other dimension leaders: loop = Claude Code (10); edit engine = Kendr Code (10);
context engineering = Cursor (10); isolation/sandboxing = Codex (10, Seatbelt on macOS /
Landlock+seccomp on Linux / network off by default); permissions = Kendr Code (10);
model layer = OpenCode and Cline (10); extensibility = Claude Code (10).

## Repository retrieval, the second named structural gap
Cursor and Windsurf maintain semantic indexes over the repository; most terminal-native CLI
harnesses rely on agentic search (grep, glob, ranged reads) — transparent but more
token-expensive. Aider is the open-source exception with a tree-sitter repo map.

## A worked reference design: earendil-works/pi, harness-v2.md
- An accepted prompt is a **durable operation**. After a crash a new process restores the
  session and resumes from the last safe boundary. Every state a crash can produce is
  recoverable.
- **Lane operation logs**: one flat chronological record sequence per lane — operation
  started, step attempted, tool started, message queued, operation finished. Nothing reads
  them during normal execution; they exist so a new process can continue after a crash.
- **Exactly-once hook side effects**: a hook result becomes durable when the record that
  consumes it commits. A crash before that commit may run the hook again; a hook with its own
  external side effects (HTTP, file writes) must be idempotent, keyed by operation id.
- **Resume continues the open operation; it never starts a new one.** Recovery is idempotent:
  it appends ordinary records and skips any provisioned id that already exists, so re-running
  recovery is always safe and a crash during recovery leaves less to recover.
- Attempt counts (retries within a step) are durable and survive restarts.
- 'Suspended' (deferred handle persisted) and 'crashed' are indistinguishable in storage — an
  open operation whose newest entry has no successor.

## A second reference: helmsman (Python)
SQLite write-ahead log + idempotent effect tracking; tool registry with an idempotent
execution gate; hard cost/token ceilings; deterministic identifier extraction before LLM
summarization; goal-drift detection with objective re-injection. Its test suite asserts the
properties that matter: committed history survives reopen, pending steps are recoverable,
side effects are not re-applied on replay, compaction loses no identifiers, budget ceilings
abort, drift is detected, end-to-end crash-and-resume completes without double-applying effects.

## Why this is filed against ME
yoyo's own 2026-09-23 19:26 evolve run reported  while producing ZERO task commits,
and its audit file carries no usage record — so the harness's own record of the invocation is
not authoritative. That is this exact class. Related: issue #944 (three phases spend tokens
with no usage record; social is 42 runs/week).

## Sources
- https://kendr.org/blog/coding-agent-harness-comparison-2026.html
- https://github.com/earendil-works/pi/blob/harness-v2/j4/packages/agent/docs/harness-v2.md