# v0.6.0-rc.1 Release Notes

## Version

`v0.6.0-rc.1`

## Dist Tag

`next`

This is the final registry-smoke record for `0.6.0-rc.1`.

Post-publish registry state:

- `persona-harness@next`: `0.6.0-rc.1`;
- `persona-harness@0.6.0-rc.1` gitHead:
  `b673633533a314e1a64dd6dcb18c4097c5889a2c`;
- dist.shasum: `5c8bcd5c1bd4165dd129e39624408672f88091ce`;
- `persona-harness@latest`: `0.5.0`;
- `persona-harness@alpha`: `0.3.9-alpha.8`;
- local and remote `v0.6.0-rc.1` tags point to
  `b673633533a314e1a64dd6dcb18c4097c5889a2c` after registry verification.

Trusted Publisher run `28653322434` succeeded. Release workflow run
`28653429619` succeeded. The GitHub release exists as a prerelease:
`https://github.com/jyt6640/persona-harness/releases/tag/v0.6.0-rc.1`.

## Summary

`0.6.0-rc.1` prepares the post-0.5 Stage 1-13 line for prerelease testers.

The product center remains gate-first:

- workflow/check/finish/archive gates;
- PH-generated evidence and explicit verification records;
- deterministic conformance blockers;
- read-only evidence and P-minus decision-support reports.

Runtime and multi-agent guidance remain preview/opt-in surfaces. This release
candidate 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, or automatic completion/downgrade/removal.

## External Registry Smoke

QA accepted the External registry smoke narrowly as registry package-runtime
evidence.

- source: registry `persona-harness@next` only;
- installed version: `0.6.0-rc.1`;
- archive:
  `/Users/yongtae/Desktop/persona-harness-artifacts/archive/2026-06-24-desktop-persona-runs/stage14-rc060-rc1-registry-smoke-20260703T100732Z`;
- `RESULT.md`: PASS.

Accepted package-runtime observations:

- package entries included localized READMEs, `CHANGELOG.md`,
  `docs/current/release/v0.6.0-rc.1-release-notes.md`,
  ralph-loop/state runtime, session registry, hooks, role-boundary
  heuristic/policy/evidence, continuation utterance gate,
  `workflow ralph-loop`, `workflow role-boundary`, bootstrap, workflow relay,
  and continuation prompt;
- `ph --help`, `ph version`, `ph bootstrap --help`,
  `workflow ralph-loop --json`, `workflow role-boundary --json`, human
  `workflow role-boundary`, default init/bootstrap, multi-agent preview
  init/bootstrap/rerun, `workflow relay status --json`,
  `workflow relay next --json`, and the smoke driver exited 0;
- `ph version` returned `0.6.0-rc.1`;
- `workflow ralph-loop --json` emitted schema `workflow-ralph-loop.3`, stayed
  default-off, dry-run, and no-write, and reported `maxAttempts=3` plus
  `maxSessionAttempts=9`;
- `workflow role-boundary --json` emitted schema
  `workflow-role-boundary-report.2`, remained report-only/heuristic, reported
  block mode unavailable/no deterministic enforcement, and wrote no files;
- bootstrap relay guidance was absent by default, present and idempotent with
  `--multi-agent-preview`; relay status/next JSON used role order
  `test-writer`, `implementer`, `reviewer`;
- ralph-loop dry-run and role-boundary report commands wrote no files; other
  writes were confined to disposable fixture init/bootstrap/workflow state.

External did not publish, tag, move `latest`/dist-tags, or change version.

## Runtime Injection And Session Boundaries

`runtimeInjection` remains a parked opt-in preview. There is no default change
in this release prep.

Accepted Stage 1-2 work tightened session classification and subagent
boundaries:

- runtime injection and continuation surfaces classify sessions using
  OpenCode session lifecycle data;
- classified main sessions can receive enabled runtime surfaces;
- classified subagent and unknown/unclassified sessions fail closed;
- skip evidence is aggregated rather than emitted per message;
- public multi-agent role names are `test-writer`, `implementer`, and
  `reviewer`.

Legacy role names remain compatibility/readback artifacts only. They are not
active public role keys.

## Rail-entry Measurements

The rail-entry evidence is recorded with correction history:

- Stage 3 is `stack-vs-nothing rail entry` evidence. It must not be cited as
  banner-only or runtimeInjection H1 evidence.
- Stage 9 banner-only H1 evidence was null, so runtimeInjection remains parked
  opt-in preview rather than recommended or default.

These measurements support scoped rail-entry observations only. They do not
support token-saving, product-efficacy, navigation-benefit, app-quality, or
generated-app certification claims.

## Continuation And Ralph-loop

Stage 4 unified continuation prompt/gate behavior across workflow continue,
closure, idle continuation, and ralph-loop preview/runtime paths.

Ralph-loop is still default-off. Stage 5 and Stage 8 introduced a retry-capped
blocker continuation runtime path with persisted state and separate
per-blocker/per-session budgets. The CLI preview reports dry-run state with
`workflow-ralph-loop.3`.

Stage 12 is a negative/partial measurement that must remain visible:

- the ON pilot did not exercise ralph-loop;
- ralph-loop remains parked/default-off preview;
- there is no default-ON evidence, autonomous completion proof, closure-success
  guarantee, or broad reliability evidence.

## Role Boundary And Relay Guidance

`workflow role-boundary` remains report-only.

Stage 6 added the report surface with block mode unavailable because stable
per-session role identity is not available at PH runtime boundaries. Stage 10
added heuristic time-window write observation under
`.persona/evidence/role-boundary/`. Those findings are warning/report-only
observations, not deterministic enforcement, closure blockers, auto-fixes, or
blocked writes.

Stage 11 added static Role Checklist Relay guidance behind the compatibility
flag:

```sh
npx ph bootstrap backend --multi-agent-preview
```

The guidance names the current roles and points agents at relay/closure
commands. It is static checklist guidance only. Stage 13 was a partial `n=1`
proxy trial: the static guidance path was observed, but reliable OpenCode role
subagent invocation or orchestration was not observed. `--multi-agent-preview`
and `multiAgent` remain compatibility names, not a stronger orchestration claim.

## Measurement Scorecard

`docs/current/measurement-scorecard.md` is the canonical `scorecard.1`
definition for experiment archives.

The scorecard is a secondary observation surface. It does not override
predeclared kill criteria, does not expand `.persona/evidence` schemas, and is
not a package-presence claim unless packaging policy changes later.

## Registry NO-GO Notes

Local-current NO-GO notes for post-`0.5.0` commits included in
`b673633533a314e1a64dd6dcb18c4097c5889a2c` are resolved by this accepted
`0.6.0-rc.1` registry smoke. Later local-current records still require a future
publish plus registry smoke before becoming registry evidence.

## Claim Audit

Do not claim:

- token saving or provider-token saving;
- product efficacy or navigation benefit;
- app/product quality guarantee;
- full TDD framework, scaffolding, coverage, mutation testing, or test
  sufficiency;
- CodeGraph or LSP default behavior or effectiveness;
- broad AST/linter product or general architecture correctness;
- broad reliability, closure guarantee, autonomous completion, or generated-app
  certification;
- Codex support or code-nav replacement;
- deterministic role enforcement or fake block mode;
- automatic completion, downgrade, removal, or config mutation.

Allowed wording:

- release-prep target for `next`;
- gate-first default;
- runtimeInjection parked opt-in preview;
- ralph-loop default-off retry-capped blocker continuation preview;
- role-boundary report-only/heuristic observation;
- static relay guidance with Stage 13 partial/no reliable subagent-orchestration
  caveat;
- scorecard.1 as secondary archive observation;
- registry evidence pending future publish and smoke.