# v0.6.0-rc.3 Release Notes

## Version

`v0.6.0-rc.3`

## Dist Tag

Dist-tag: `next`.

This prerelease is published to npm `next`; `latest` did not move. Current npm
registry state:

- `persona-harness@latest=0.5.0`;
- `persona-harness@next=0.6.0-rc.3`;
- `persona-harness@alpha=0.3.9-alpha.8`.

Registry verification confirmed `persona-harness@next=0.6.0-rc.3` and explicit
`persona-harness@0.6.0-rc.3` both resolve to gitHead
`e1af520cf000e805e7df6a1616906f3f9b0e4976`, shasum
`ef498adfac138d9d0843406cba53acf76b34c6f1`, and integrity
`sha512-nXImwyxON5zoph8Y3LyXqJhW1NIcX+3JvsBSFAdQlersZ8zO1KmRuRJVKB1DF87fbYxDpVyxMqFU1C6sA8HJQQ==`.

The local and remote `v0.6.0-rc.3` tags point to the same gitHead. GitHub
release: `https://github.com/jyt6640/persona-harness/releases/tag/v0.6.0-rc.3`;
draft false, prerelease true.

## Summary

`0.6.0-rc.3` publishes the post-rc2 Stage 15-20 line to npm `next`. It keeps
the product center gate-first: workflow/check/finish/archive
gates, PH-generated evidence, deterministic conformance blockers, read-only
status/report surfaces, and default-off continuation previews.

This prep does not claim token saving, provider-token saving, product efficacy,
navigation benefit, app quality, full-TDD sufficiency, broad reliability,
closure guarantee, autonomous completion, generated-app certification,
deterministic role enforcement, production-ready delegation, reliable automatic
subagent orchestration, automatic completion/downgrade/removal, or CodeGraph/LSP
default/effectiveness.

## Included Since rc2

- Stage 15 docs correction: the ralph-loop n=15 `blockerDelta -3.00` style
  value is blocker resolution/exposure movement, not total blocker reduction.
  Actual visible blockers increased `3 -> 6`, final finish PASS stayed OFF
  `0/15` and ON `0/15`, and the fixture is reclassified as
  finish-unreachable/loop-unrotated. Fake Gradle/Spring gate-gaming via
  `gradle-shim.js` / Node shim behavior was elevated as a candidate
  adversarial measured case after forged-TDD detection.
- Stage 16 maintenance: package-visible rail-entry prompt regression gate,
  package files policy regression, canonical docs index, and external-review
  adoption/rejection/defer matrix.
- Stage 17 product CLI: explicit `ph workflow loop` command, bounded process
  runner, and workflow-loop state. Accepted archive:
  `/Users/yongtae/Desktop/persona-harness-artifacts/archive/2026-06-24-desktop-persona-runs/stage17-workflow-loop-package-smoke-d4d85bc-20260704T092858Z`.
  This is package-runtime/command viability evidence only.
- Stage 18 measurement: pilot-gated PARTIAL archive
  `stage18-completion-integrity-3arm-20260704T093610Z`, repair/calibration
  archive `stage18-repair-calibration-20260704T101436Z`, and accepted main
  rerun archive
  `/Users/yongtae/Desktop/persona-harness-artifacts/archive/2026-06-24-desktop-persona-runs/stage18-completion-integrity-main-rerun-20260704T105124Z`.
- Stage 20 output UX: failed `ph workflow finish` human stderr now prints a
  concise `Summary:` before existing `Required fixes:` details. Accepted
  archive:
  `/Users/yongtae/Desktop/persona-harness-artifacts/archive/2026-06-24-desktop-persona-runs/stage20-finish-summary-package-smoke-2f3625d-20260704T130812Z`.

## Stage 17 Workflow Loop

`ph workflow loop` is an explicit capped fresh-session blocker loop command. It
reads deterministic PH finish/closure blockers, builds a minimal
blocker-depth prompt, runs a fresh `opencode run` session per iteration,
persists `.persona/workflow/workflow-loop-state.json`, and terminates on finish
PASS, no blockers, or iteration cap.

The Stage 17 External local-current smoke accepted command/package viability
only. It did not prove completion-integrity movement, default change, product
efficacy, token saving, app quality, broad reliability, or autonomous
completion.

## Stage 18 Completion-Integrity Measurement

The accepted Stage 18 main rerun is fixture-scoped completion-integrity
evidence for a finish-reachable Java/Spring/Gradle fixture:

| Condition | Final finish PASS | Paired comparison |
| --- | ---: | --- |
| OFF | `0/10` | baseline |
| Internal tool-output trigger | `10/10` | one-sided `p=0.0009765625` |
| External `ph workflow loop` | `7/10` | one-sided `p=0.0078125`; `3/10` cap hits |

Internal met the preregistered positive completion-integrity criterion for this
fixture. External also met the finish PASS comparison criterion, but is
cap-risky because `3/10` external rows hit iteration cap and did not finish.
No default change is made by this measurement.

## Stage 20 Finish Summary

Failed `ph workflow finish` human output now starts with `Summary:` before the
existing `Required fixes:` details. The summary is UX and measurement-support
only. Gate semantics, exit codes, closure blockers, and JSON/machine-readable
details remain unchanged.

## Registry Smoke Notes

External registry smoke PASS archive:
`/Users/yongtae/Desktop/persona-harness-artifacts/archive/2026-06-24-desktop-persona-runs/rc060-rc3-registry-smoke-20260704T133936Z`.
The smoke source was npm registry `persona-harness@next` only; no local tarball
evidence was used.

The smoke observed required package entries for LICENSE, localized READMEs,
`CHANGELOG.md`, this current release note, the rc3 versioned capsule files,
`workflow-loop`, `workflow-loop-state`, `bounded-process`, `workflow-output`,
`workflow-ralph-loop`, `workflow-relay`, and `workflow-relay-ui`. Packaged
LICENSE contained `Copyright 2026 jyt6640` and no template placeholders.

Stage 17 registry package behavior: `ph workflow loop` dry-run emitted schema
`workflow-loop.1`, `defaultOff=true`, a blocker-depth prompt, and no state
write; execute mode with a fake bounded OpenCode operation wrote
workflow-loop-state plus prompt/stdout/stderr artifacts and ended at iteration
cap.

Stage 20 registry package behavior: failed finish stderr includes `Summary:`
before `Required fixes:`, detailed blockers remain, and closure JSON parses.
Ralph-loop reporting remains default-off with `workflow-ralph-loop.4`,
`defaultOff=true`, and `mutates=false`. Role Checklist Relay remains
checklist-first with optional host-dependent subagent/task invocation and no
reliable orchestration or production-ready delegation claim.

## Claim Audit

Do not claim:

- token saving or provider-token saving;
- product efficacy or navigation benefit;
- app/product quality guarantee;
- full TDD framework, coverage, mutation testing, or test sufficiency;
- CodeGraph or LSP default behavior or effectiveness;
- broad reliability, closure guarantee, autonomous completion, or generated-app
  certification;
- deterministic role enforcement or production-ready delegation;
- reliable automatic OpenCode subagent orchestration;
- automatic completion, downgrade, removal, or config mutation.

Allowed wording:

- published prerelease `persona-harness@next=0.6.0-rc.3`;
- stable remains `latest=0.5.0` until a separate stable publish decision;
- `ph workflow loop` as explicit capped fresh-session blocker loop command;
- Stage 18 fixture-scoped completion-integrity evidence with cap-risk caveat;
- Stage 20 human finish summary UX support;
- no `latest` movement in this prerelease publish.