# v0.6.0-rc.2 Release Notes ## Version `v0.6.0-rc.2` ## Dist Tag `next` This release candidate is published to npm `next` after QA publish GO, registry gitHead/shasum verification, tag creation, and External registry smoke. `latest` remains `0.5.0`. Verified registry state: - `persona-harness@next`: `0.6.0-rc.2`, gitHead `d3d5fdced355f0ac0fbed5e700d57b2aa1592263`, shasum `0eae3cc232e3f37de9390b0afc662a001aaa0b56`, integrity `sha512-HmJplQNf896/4Sfz/FiTdJoaDU5EkMrDtxCVMU1x0LfLJzJYNDa0NGafUAgiU4zWc/IA9byDUv4+DryubMVZrg==`; - `persona-harness@0.6.0-rc.2`: same version, gitHead, shasum, and integrity; - `persona-harness@latest`: `0.5.0`, gitHead `c0f1085a5182cdd17411bd043173aabc9a76b30e`, shasum `3a7c43e4807e7cc8bd1b6c697746d6334ee56b09`; - `persona-harness@alpha`: `0.3.9-alpha.8`; - dist-tags: `latest=0.5.0`, `next=0.6.0-rc.2`, `alpha=0.3.9-alpha.8`; - local and remote `v0.6.0-rc.2` tags point to `d3d5fdced355f0ac0fbed5e700d57b2aa1592263`; - GitHub release exists as prerelease and not draft: `https://github.com/jyt6640/persona-harness/releases/tag/v0.6.0-rc.2`. ## Summary `0.6.0-rc.2` publishes the post-rc1 correction and roadmap-probe line to the `next` channel. The accepted registry smoke source was npm registry `persona-harness@next` only; no local tarball was used. External registry smoke archive: `/Users/yongtae/Desktop/persona-harness-artifacts/archive/2026-06-24-desktop-persona-runs/rc060-rc2-registry-smoke-20260704T043901Z`. `RESULT.md` classified PASS. 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; - 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, automatic completion/downgrade/removal, or CodeGraph/LSP default/effectiveness. ## Included Since rc1 - Final `0.6.0-rc.1` registry smoke record and docs taxonomy/package-index cleanup. - Ralph-loop n=15 measurement correction: - the `-3.00` style value is blocker resolution/exposure movement, not total blocker reduction; - total visible blockers increased from `3` to `6` after hierarchical gate exposure; - final finish PASS stayed OFF `0/15` and ON `0/15`; - completion-integrity movement and default-change remain unproven; - `cooldownMs=30000` is greater than or near short measured sessions, and attempts staying at `1` is trigger-survival evidence only. - Fake `gradle-shim.js` / Gradle-gate-gaming is elevated as a candidate measured adversarial case after forged-TDD detection. It is a candidate for future measured-behavior reporting after verification, not a broad guarantee. - Ralph-loop blocker-depth wording and finishable-fixture/internal-external loop prep for later completion-integrity measurement. The external loop is archive-local prototype preparation only; there is no product `ph workflow loop` command in this prep. - OpenCode subagent capability probe and Role Checklist Relay wording/UX honesty: - direct OpenCode task-tool subagent invocation was observed in the probe; - PH Role Checklist Relay remains a main-session checklist rail with optional host-dependent subagent invocation; - PH does not prove reliable automatic OpenCode subagent orchestration. - Role-boundary report-only/heuristic wording and wrong-actor attribution caveat remain active. - Prompt regression fixture protects accepted measurement-safe wording. This is test protection only, not a new product capability. ## Accepted Registry Smoke Observations - Packaged LICENSE contains `Copyright 2026 jyt6640` and no placeholder owner text. - Ralph-loop remains default-off. `workflow ralph-loop --json` emits `workflow-ralph-loop.4`; the tool-output trigger marker/depth surfaces are packaged; there is no product `workflow loop` command. - Role Checklist Relay package surfaces accept the compatibility flag, write AGENTS guidance when previewed, expose optional role subagent entries, keep role order/gates, and use checklist-first `promptBlocks`. - The smoke did not accept reliable automatic OpenCode subagent orchestration, production-ready delegation, deterministic role enforcement, or broader product claims. ## Runtime Injection `runtimeInjection` remains a parked opt-in preview. There is no default change or removal claim in this release prep. ## Ralph-loop Ralph-loop remains default-off. Accepted prior measurement supports hybrid tool-output trigger-survival for the calibrated fixture, including marker/state/follow-up survival. It does not prove completion-integrity movement, default-change, autonomous completion, closure success, or broad reliability. The blocker-depth update makes continuation wording name the current blocker in the visible blocker set. That is preparation for better completion-integrity fixtures, not evidence that completion improved. ## Role Checklist Relay The public framing is `Role Checklist Relay`. `--multi-agent-preview` and `multiAgent` remain compatibility flag/config names. The relay may ask a host to invoke a role subagent when a host task surface is available, but PH relay remains checklist-first and does not guarantee automatic OpenCode subagent orchestration or production-ready delegation. ## Role Boundary `workflow role-boundary` remains report-only and heuristic. Runtime write findings are time-window/path/current-role observations. They are not deterministic role enforcement, closure blockers, blocked writes, auto-fix actions, or proof that a specific actor wrote a file. ## Registry Evidence Notes The records included in this `0.6.0-rc.2` package are registry-smoked through gitHead `d3d5fdced355f0ac0fbed5e700d57b2aa1592263`. Later local-current records remain registry NO-GO until a future publish includes them, followed by gitHead/shasum verification and External registry smoke. ## 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; - production-ready delegation or reliable automatic subagent orchestration; - automatic completion, downgrade, removal, or config mutation. Allowed wording: - published release candidate on `next`; - stable remains `latest=0.5.0` until a separate stable publish decision; - `next=0.6.0-rc.2`; - gate-first default; - runtimeInjection parked opt-in preview; - ralph-loop default-off trigger-survival and blocker-depth preparation; - Role Checklist Relay with optional host-dependent subagent use; - role-boundary report-only/heuristic observation; - fake-shim gate-gaming as a candidate adversarial measured case after verification; - prompt regression fixture as test protection only.