okstra 0.34.1 → 0.36.0

package/runtime/templates/reports/final-report.template.md

@@ -17,6 +17,7 @@ task-group: {{ frontmatter.taskGroup | yaml_scalar }}
 project-id: {{ frontmatter.projectId | yaml_scalar }}
 taskType: {{ frontmatter.taskType | yaml_scalar }}
 workerId: {{ frontmatter.workerId | yaml_scalar }}
+approved: {{ frontmatter.approved | yaml_scalar }}
 ---
 
 # {{ header.taskKey }} - Multi-Agent Cross Verification Final Report
@@ -31,43 +32,28 @@ workerId: {{ frontmatter.workerId | yaml_scalar }}
 
 ## Verdict Card
 
-한눈에 보는 결과 카드. 본 표의 모든 값은 `## 2. Final Verdict` 및 `## 6. Recommended Next Steps` 의 권위 있는 값과 정확히 일치해야 합니다.
+{{ t("sectionIntro.verdictCard") }}
 
-| 항목 | 값 |
+| {{ t("verdictCard.tableHeaderLabel") }} | {{ t("verdictCard.tableHeaderValue") }} |
 |------|----|
 | Final Conclusion | {{ verdictCard.finalConclusion }} |
 | Verdict Token | `{{ verdictCard.verdictToken }}` |
 | Direction | `{{ verdictCard.direction }}` |
-| Approval Required? | `{% if verdictCard.approvalRequired %}yes — User Approval Request 블록 참조{% else %}no{% endif %}` |
+| Approval Required? | `{% if verdictCard.approvalRequired %}yes — {{ t("verdictCard.approvalRequiredSuffix") }}{% else %}no{% endif %}` |
 | Next Step | {{ verdictCard.nextStep }} |
 
-{% if header.taskType == 'implementation-planning' %}
-## User Approval Request (사용자 승인 게이트)
-
-다음 `implementation` run 은 아래 체크박스가 `[x]` 일 때에만 진입할 수 있습니다 (`okstra_ctl.run._validate_approved_plan` 가 line-anchored 정규식으로 검사). `## 5. Clarification Items` 표에서 `Blocks=approval` 인 모든 행이 `resolved` / `obsolete` 가 된 뒤 승인해 주세요.
-
-- 승인 체크박스 (사용자가 직접 편집): `- [{% if approvalBlock.approved %}x{% else %} {% endif %}] Approved`
-- 승인 후 다음 단계 명령 (수동 편집 방식):
-  - Claude Code: `/okstra-run task-key={{ header.taskKey }} task-type=implementation approved-plan=<이 보고서 경로>`
-  - 별도 터미널: `scripts/okstra.sh --task-key {{ header.taskKey }} --task-type implementation --approved-plan <이 보고서 경로>`
-- 승인 + 실행 한 번에 (진입 명령 자체를 승인 의사로):
-  - Claude Code: `/okstra-run task-key={{ header.taskKey }} task-type=implementation approved-plan=<이 보고서 경로> approve`
-  - 별도 터미널: `scripts/okstra.sh --task-key {{ header.taskKey }} --task-type implementation --approved-plan <이 보고서 경로> --approve`
-- 보류·거부: 체크박스를 `[ ]` 로 두고 `--approve` 를 사용하지 마세요. 필요 변경은 `## 5.` 표에 `Blocks=approval` 행으로 등록한 뒤 같은 phase 를 재실행합니다.
-
-{% endif %}
 {% if clarificationCarryIn and clarificationCarryIn.sourceFile %}
 ## 0. Clarification Response Carried In From Previous Run
 
 - Source file: `{{ clarificationCarryIn.sourceFile }}`
-- 이전 보고서의 `## 5. Clarification Items` 표 매 행(`C-001`, `C-002`, …) 을 새 증거에 비추어 검토하고, 각 행의 `Status` 를 `resolved` 또는 `obsolete` 로 갱신한 뒤 본 run 의 `## 5.` 표에 carry-in 합니다. 해소 근거(파일:라인 / 로그 / 워커 결과) 를 함께 인용합니다.
+- {{ t("sectionIntro.clarificationCarryIn") }}
 
 {% endif %}
 ## Summary of the Problem or Verification Target
 
-3~5 개 row 로 핵심 문제·요구사항·검증 대상을 표로 정리합니다. brief, 소스 자료, worker 결과를 근거로 작성합니다.
+{{ t("sectionIntro.ticketCoverage") }}
 
-| ID | Ticket ID | 한 줄 요약 | 출처 (brief/source/worker) |
+| ID | Ticket ID | {{ t("columns.summary") }} | {{ t("columns.source") }} |
 |----|-----------|------------|----------------------------|
 {% for row in summary -%}
 | {{ row.id }} | `{{ row.ticketId }}` | {{ row.summary }} | {{ row.source }} |
@@ -78,43 +64,43 @@ workerId: {{ frontmatter.workerId | yaml_scalar }}
 {%- else %}
 ## Ticket Coverage
 
-본 run 이 다룬 ticket 의 역방향 인덱스. 본문 항목들은 모두 `Ticket ID` 컬럼 또는 `[TICKETID: <id>]` 태그로 ticket 과 묶여 있습니다.
+{{ t("ticketCoverage.intro") }}
 
 {% if ticketCoverage.singleTicket -%}
 - Single ticket run: {{ ticketCoverage.singleTicket }}
 {%- else %}
-| Ticket ID | 등장 섹션 | 관련 항목 IDs |
+| Ticket ID | {{ t("ticketCoverage.columnSections") }} | {{ t("ticketCoverage.columnRelatedIds") }} |
 |-----------|-----------|---------------|
 {% for row in ticketCoverage.rows -%}
 | `{{ row.ticketId }}` | `{{ row.sections }}` | `{{ row.relatedIds }}` |
 {% endfor %}
 {%- endif %}
 
-규칙: `Ticket ID` 는 본문에서 등장한 ticket 키와 정확히 동일 문자열. `Issue / Ticket` 이 비어 폴백된 경우 `Task ID` 값을 prefix 없이 그대로 (예: `8852`). 식별 불가는 `unknown`.
+{{ t("ticketCoverage.ruleNote") }}
 
 {% endif %}
 ## Execution Status by Agent
 
-각 worker 의 status, 배정 모델, key finding 을 한 표에 모읍니다. worker 산출물을 근거 없는 주장으로 대체하지 않습니다.
+{{ t("sectionIntro.executionStatus") }}
 
-| Agent | Role | Model | Status | 처리 토큰 | 환산 토큰 | 비용 (USD) | Duration | Summary of Key Findings |
+| Agent | Role | Model | Status | {{ t("columns.rawTokens") }} | {{ t("columns.billableTokens") }} | {{ t("columns.cost") }} | Duration | Summary of Key Findings |
 |-------|------|-------|--------|-----------|-----------|------------|----------|-------------------------|
 {% for row in executionStatus -%}
 | {{ row.agent }} | {{ row.role }} | {{ row.model }} | {{ row.status }} | {{ row.totalTokens | format_int }}{% if row.cliTotalTokens %} (CLI: {{ row.cliTotalTokens | format_int }}){% endif %} | {{ row.billableTokens | format_int }} | {{ row.costUsd | format_usd }}{% if row.cliCostUsd %} (+ CLI {{ row.cliCostUsd | format_usd }}){% endif %} | {{ row.durationMs | format_duration_ms }} | {{ row.summary }} |
 {% endfor %}
 
-## Token Usage Summary
+## {{ t("tokenSummary.heading") }}
 
-| 항목 | 처리 토큰 | 환산 토큰 (input 기준) | 비용 (USD) |
+| {{ t("tokenSummary.tableHeaderItem") }} | {{ t("columns.rawTokens") }} | {{ t("columns.billableTokensInputEquiv") }} | {{ t("columns.cost") }} |
 |------|-----------|------------------------|------------|
-| Lead | `{{ tokenUsage.lead.totalTokens | format_int }}` | `{{ tokenUsage.lead.billableTokens | format_int }}` | `{{ tokenUsage.lead.costUsd | format_usd }}` |
-| Worker 합계 | `{{ tokenUsage.worker.totalTokens | format_int }}` | `{{ tokenUsage.worker.billableTokens | format_int }}` | `{{ tokenUsage.worker.costUsd | format_usd }}` |
-| **전체 합계** | **`{{ tokenUsage.grand.totalTokens | format_int }}`** | **`{{ tokenUsage.grand.billableTokens | format_int }}`** | **`{{ tokenUsage.grand.costUsd | format_usd }}`** |
-| Codex/Gemini CLI 추가 비용 |  |  | `{{ tokenUsage.cli.costUsd | format_usd }}` |
+| {{ t("tokenSummary.rowLead") }} | `{{ tokenUsage.lead.totalTokens | format_int }}` | `{{ tokenUsage.lead.billableTokens | format_int }}` | `{{ tokenUsage.lead.costUsd | format_usd }}` |
+| {{ t("tokenSummary.rowWorkerTotal") }} | `{{ tokenUsage.worker.totalTokens | format_int }}` | `{{ tokenUsage.worker.billableTokens | format_int }}` | `{{ tokenUsage.worker.costUsd | format_usd }}` |
+| {{ t("tokenSummary.rowGrandTotal") }} | **`{{ tokenUsage.grand.totalTokens | format_int }}`** | **`{{ tokenUsage.grand.billableTokens | format_int }}`** | **`{{ tokenUsage.grand.costUsd | format_usd }}`** |
+| {{ t("tokenSummary.rowCliExtra") }} |  |  | `{{ tokenUsage.cli.costUsd | format_usd }}` |
 
-{# Phase 6 시점에는 numeric cells 가 null → 모두 `--` 로 렌더링.
-   Phase 7 의 okstra-token-usage.py 가 data.json 의 tokenUsage 를 채우고
-   이 renderer 를 재호출하여 최종 markdown 을 다시 생성합니다. #}
+{# At Phase 6 numeric cells are null and render as `--`.
+   Phase 7's okstra-token-usage.py populates tokenUsage in data.json then
+   re-invokes this renderer to produce the final markdown. #}
 
 ## 1. Cross Verification Results
 
@@ -127,13 +113,13 @@ workerId: {{ frontmatter.workerId | yaml_scalar }}
 | {{ row.round }} | {{ row.inputQueueSize }} | {{ row.resolvedCount }} | {{ row.carriedForwardCount }} | {{ row.dispatches }} | {{ row.skippedWorkers }} |
 {% endfor %}
 
-- `round2SkippedReason`: `{{ crossVerification.roundHistory.round2SkippedReason }}`  ← 값은 `queue-empty | max-rounds-1 | all-reverify-non-result | not-skipped | convergence-disabled | single-analyser-only` 중 하나.
+- `round2SkippedReason`: `{{ crossVerification.roundHistory.round2SkippedReason }}`  ← {{ t("roundHistory.round2SkippedReasonNote") }}
 
 {% endif %}
 ### 1.1 Consensus
 
 {% if crossVerification.consensus | length == 0 -%}
-- 합의 항목 없음.
+{{ t("emptyState.consensusItems") }}
 {%- else %}
 | ID | Ticket ID | Statement | Source items (worker:item) | Evidence (path:line / log / worker report) |
 |----|-----------|-----------|----------------------------|---------------------------------------------|
@@ -142,12 +128,12 @@ workerId: {{ frontmatter.workerId | yaml_scalar }}
 {% endfor %}
 {%- endif %}
 
-`Source items` 규칙: 본 합의 row 가 어느 워커의 어느 항목들에서 합성됐는지를 `<worker>:<item-id>` 페어 콤마-리스트로 적습니다. 자세한 정책은 `prompts/profiles/_common-contract.md` "Cross-worker traceability" SSOT.
+{{ t("sectionIntro.sourceItemsRule") }}
 
 ### 1.2 Differences
 
 {% if crossVerification.differences | length == 0 -%}
-- 유의미한 차이 없음. 1.1 Consensus 가 그대로 유효합니다.
+{{ t("emptyState.differences") }}
 {%- else %}
 | ID | Ticket ID | Disagreement | Workers (position + item) | Evidence |
 |----|-----------|--------------|---------------------------|----------|
@@ -158,22 +144,22 @@ workerId: {{ frontmatter.workerId | yaml_scalar }}
 
 ## 2. Final Verdict
 
-최종 결론과 권장 방향을 한 표로 명시합니다. `Direction` ∈ `continue-investigation / begin-implementation / approve / reject / hold`. `task-type` 이 `final-verification` 이면 `Verdict Token` 은 `accepted / conditional-accept / blocked` 중 하나여야 하며, `release-handoff` 는 이 값을 진입 게이트로 사용합니다. 다른 task-type 에서는 `not-applicable`.
+{{ t("finalVerdict.intro") }}
 
-| 항목 | 값 |
+| {{ t("verdictCard.tableHeaderLabel") }} | {{ t("verdictCard.tableHeaderValue") }} |
 |------|----|
 | Final Conclusion | {{ finalVerdict.finalConclusion }} |
 | Verdict Token | `{{ finalVerdict.verdictToken }}` |
 | Direction | `{{ finalVerdict.direction }}` |
-| 근거 요약 | {{ finalVerdict.rationaleRowIds | join(', ') }} |
-| 다음 단계 | {{ finalVerdict.nextStep }} |
+| {{ t("verdictCard.rationaleLabel") }} | {{ finalVerdict.rationaleRowIds | join(', ') }} |
+| {{ t("verdictCard.nextStepLabel") }} | {{ finalVerdict.nextStep }} |
 
 ## 3. Evidence and Detailed Analysis
 
 ### 3.1 Primary Evidence
 
 {% if evidence.primary | length == 0 -%}
-- 주 증거 없음.
+{{ t("emptyState.primaryEvidence") }}
 {%- else %}
 | ID | Ticket ID | Evidence | Source items (worker:item) | Source (path:line / log) |
 |----|-----------|----------|----------------------------|---------------------------|
@@ -182,12 +168,12 @@ workerId: {{ frontmatter.workerId | yaml_scalar }}
 {% endfor %}
 {%- endif %}
 
-`Source items` 컬럼 규칙은 §1.1 과 동일.
+{{ t("evidence.sourceItemsColumnNote") }}
 
 ### 3.2 Secondary Evidence or Alternate Interpretations
 
 {% if not evidence.secondary or evidence.secondary | length == 0 -%}
-- 보조 증거 또는 대안 해석 없음.
+{{ t("emptyState.secondaryEvidence") }}
 {%- else %}
 | ID | Ticket ID | Hypothesis or supporting evidence | Source / confidence |
 |----|-----------|-----------------------------------|---------------------|
@@ -199,7 +185,7 @@ workerId: {{ frontmatter.workerId | yaml_scalar }}
 ## 4. Missing Information and Risks
 
 {% if missingInformation | length == 0 -%}
-- 누락된 정보·위험 없음.
+{{ t("emptyState.risks") }}
 {%- else %}
 | ID | Ticket ID | Item | Risk if ignored | Mitigation Owner |
 |----|-----------|------|-----------------|------------------|
@@ -211,7 +197,7 @@ workerId: {{ frontmatter.workerId | yaml_scalar }}
 {% if header.taskType == 'implementation-planning' %}
 ## 4.5 Implementation Plan Deliverables
 
-### 4.5.1 Option Candidates (옵션 후보)
+### 4.5.1 Option Candidates{% if t("sectionAside.optionCandidates") != "Option Candidates" %} ({{ t("sectionAside.optionCandidates") }}){% endif %}
 
 {% for opt in implementationPlanning.optionCandidates %}
 **{{ opt.name }}**
@@ -224,12 +210,12 @@ workerId: {{ frontmatter.workerId | yaml_scalar }}
   | {{ fs.id }} | `{{ fs.ticketId }}` | {{ fs.action }} | `{{ fs.path }}` | {{ fs.summary }} |
 {% endfor %}
 
-- 영향 인터페이스 / 공개 계약 / 다운스트림 소비자: {{ opt.interfaces }}
-- 폭발 반경 추정: {{ opt.blastRadius }}
+- {{ t("implementationPlanning.optionInterfacesLabel") }}: {{ opt.interfaces }}
+- {{ t("implementationPlanning.optionBlastRadiusLabel") }}: {{ opt.blastRadius }}
 
 {% endfor %}
 
-### 4.5.2 Trade-off Matrix (트레이드오프 매트릭스)
+### 4.5.2 Trade-off Matrix{% if t("sectionAside.tradeOffMatrix") != "Trade-off Matrix" %} ({{ t("sectionAside.tradeOffMatrix") }}){% endif %}
 
 | Option | Complexity | Risk | Reversibility | Test Coverage Cost | Rollout Cost |
 |--------|-----------|------|---------------|--------------------|--------------|
@@ -237,16 +223,16 @@ workerId: {{ frontmatter.workerId | yaml_scalar }}
 | {{ row.option }} | {{ row.complexity }} | {{ row.risk }} | {{ row.reversibility }} | {{ row.testCoverageCost }} | {{ row.rolloutCost }} |
 {% endfor %}
 
-### 4.5.3 Recommended Option (권장 옵션)
+### 4.5.3 Recommended Option{% if t("sectionAside.recommendedOption") != "Recommended Option" %} ({{ t("sectionAside.recommendedOption") }}){% endif %}
 
-| 항목 | 값 |
+| {{ t("implementationPlanning.recommendedTableHeaderLabel") }} | {{ t("implementationPlanning.recommendedTableHeaderValue") }} |
 |------|----|
 | Recommended Option | {{ implementationPlanning.recommendedOption.name }} |
-| 핵심 이유 | {{ implementationPlanning.recommendedOption.coreReason }} |
-| 근거 (Trade-off 행 / 원칙) | {{ implementationPlanning.recommendedOption.rationale }} |
-| 채택되지 않은 옵션 요약 | {{ implementationPlanning.recommendedOption.rejectedSummary }} |
+| {{ t("implementationPlanning.coreReasonLabel") }} | {{ implementationPlanning.recommendedOption.coreReason }} |
+| {{ t("implementationPlanning.rationaleLabel") }} | {{ implementationPlanning.recommendedOption.rationale }} |
+| {{ t("implementationPlanning.rejectedSummaryLabel") }} | {{ implementationPlanning.recommendedOption.rejectedSummary }} |
 
-### 4.5.4 Stepwise Execution Order (단계별 실행 순서)
+### 4.5.4 Stepwise Execution Order{% if t("sectionAside.stepwiseExecutionOrder") != "Stepwise Execution Order" %} ({{ t("sectionAside.stepwiseExecutionOrder") }}){% endif %}
 
 | Step | Ticket ID | Action (≤ 5min) | Files | Command / Test | Expected outcome |
 |------|-----------|------------------|-------|----------------|-------------------|
@@ -254,21 +240,21 @@ workerId: {{ frontmatter.workerId | yaml_scalar }}
 | {{ row.step }} | `{{ row.ticketId }}` | {{ row.action }} | `{{ row.files }}` | `{{ row.commandOrTest }}` | {{ row.expectedOutcome }} |
 {% endfor %}
 
-규칙: 한 step 은 약 2~5 분. 모든 step 은 정확한 파일 경로와 명령어 포함.
+{{ t("sectionIntro.stepRule") }}
 
-### 4.5.5 Dependency / Migration Risk (의존성·마이그레이션 위험)
+### 4.5.5 Dependency / Migration Risk{% if t("sectionAside.dependencyRisk") != "Dependency / Migration Risk" %} ({{ t("sectionAside.dependencyRisk") }}){% endif %}
 
 {% if implementationPlanning.dependencyMigrationRisk | length == 0 -%}
-- 의존성·마이그레이션 위험 없음.
+{{ t("emptyState.dependencyRisk") }}
 {%- else %}
-| ID | Kind | Item | 영향 | 완화 / 선행 작업 |
+| ID | Kind | Item | {{ t("implementationPlanning.columnImpact") }} | {{ t("implementationPlanning.columnMitigation") }} |
 |----|------|------|------|------------------|
 {% for row in implementationPlanning.dependencyMigrationRisk -%}
 | {{ row.id }} | {{ row.kind }} | {{ row.item }} | {{ row.impact }} | {{ row.mitigation }} |
 {% endfor %}
 {%- endif %}
 
-### 4.5.6 Validation Checklist (검증 체크리스트)
+### 4.5.6 Validation Checklist{% if t("sectionAside.validationChecklist") != "Validation Checklist" %} ({{ t("sectionAside.validationChecklist") }}){% endif %}
 
 | Phase | Ticket ID | Check | Command / Observation | Expected outcome |
 |-------|-----------|-------|------------------------|-------------------|
@@ -276,17 +262,17 @@ workerId: {{ frontmatter.workerId | yaml_scalar }}
 | {{ row.phase }} | `{{ row.ticketId }}` | {{ row.check }} | `{{ row.commandOrObservation }}` | {{ row.expectedOutcome }} |
 {% endfor %}
 
-### 4.5.7 Rollback Strategy (롤백 전략)
+### 4.5.7 Rollback Strategy{% if t("sectionAside.rollbackStrategy") != "Rollback Strategy" %} ({{ t("sectionAside.rollbackStrategy") }}){% endif %}
 
-| ID | Step | Action | Trigger signal | 확인 방법 |
+| ID | Step | Action | Trigger signal | {{ t("columns.checkMethod") }} |
 |----|------|--------|----------------|-----------|
 {% for row in implementationPlanning.rollbackStrategy -%}
 | {{ row.id }} | {{ row.step }} | `{{ row.action }}` | {{ row.triggerSignal }} | `{{ row.verificationMethod }}` |
 {% endfor %}
 
-### 4.5.9 Plan Body Verification (계획 본문 검증)
+### 4.5.9 Plan Body Verification{% if t("sectionAside.planBodyVerification") != "Plan Body Verification" %} ({{ t("sectionAside.planBodyVerification") }}){% endif %}
 
-Phase 6 에서 report-writer 가 합성한 4.5 본문을 lead 가 plan-item 단위로 워커들에게 다시 던지고 평결을 수집한 결과.
+{{ t("sectionIntro.planBodyVerification") }}
 
 - **Round count**: `{{ implementationPlanning.planBodyVerification.roundCount }}`
 - **Gate result**: `{{ implementationPlanning.planBodyVerification.gateResult }}`
@@ -310,7 +296,7 @@ Phase 6 에서 report-writer 가 합성한 4.5 본문을 lead 가 plan-item 단
 #### Dissent log
 
 {% if implementationPlanning.planBodyVerification.dissentLog | length == 0 -%}
-- 반대 의견 없음.
+{{ t("emptyState.dissent") }}
 {%- else %}
 {% for row in implementationPlanning.planBodyVerification.dissentLog -%}
 - **{{ row.planItem }}**: `{{ row.workerRole }}` — {{ row.body }}
@@ -321,7 +307,7 @@ Phase 6 에서 report-writer 가 합성한 4.5 본문을 lead 가 plan-item 단
 {% if header.taskType == 'release-handoff' %}
 ## 4.6 Release Handoff Deliverables
 
-git/gh mutating 명령이 실행된 phase 의 감사 기록.
+{{ t("releaseHandoff.auditNote") }}
 
 ### 4.6.1 Source Verification Report
 
@@ -329,29 +315,29 @@ git/gh mutating 명령이 실행된 phase 의 감사 기록.
 - Quoted `Verdict Token` row from that report's `## 2.` table:
   > {{ releaseHandoff.sourceVerificationReport.verdictTokenQuote }}
 
-### 4.6.2 Feature Branch & Working-Tree State (run 시작 시점)
+### 4.6.2 Feature Branch & Working-Tree State{% if t("releaseHandoff.branchStateAside") != "captured at run start" %} ({{ t("releaseHandoff.branchStateAside") }}){% endif %}
 
 - Feature branch: `{{ releaseHandoff.featureBranchState.branchName }}`
-- `git status --short` 출력:
+- {{ t("releaseHandoff.gitStatusShortLabel") }}:
   ```
   {{ releaseHandoff.featureBranchState.gitStatusShort }}
   ```
-- 기존 PR 존재 여부: `{{ releaseHandoff.featureBranchState.existingPrUrl or '(none)' }}`
+- {{ t("releaseHandoff.existingPrLabel") }}: `{{ releaseHandoff.featureBranchState.existingPrUrl or '(none)' }}`
 
-### 4.6.3 User Selections (메뉴 응답 기록)
+### 4.6.3 User Selections{% if t("releaseHandoff.userSelectionsAside") != "menu response log" %} ({{ t("releaseHandoff.userSelectionsAside") }}){% endif %}
 
-| 질문 ID | 질문 본문 | 사용자 응답 (원문) | 응답이 가능한 보기 |
+| {{ t("releaseHandoff.questionsTableHeader.questionId") }} | {{ t("releaseHandoff.questionsTableHeader.questionBody") }} | {{ t("releaseHandoff.questionsTableHeader.userResponse") }} | {{ t("releaseHandoff.questionsTableHeader.allowedOptions") }} |
 |---------|-----------|--------------------|--------------------|
-| H1 | 어떤 작업을 실행할까요? | `{{ releaseHandoff.userSelections.h1 }}` | `local only` / `push + PR` / `skip` |
-| H2 | PR base 브랜치 (H1=`push + PR` 인 경우) | `{{ releaseHandoff.userSelections.h2 or '(n/a)' }}` | staging / preprod / prod / main / dev / 사용자 입력 |
-| H3 | PR title/body 초안 처리 | `{{ releaseHandoff.userSelections.h3 }}` | `use as-is` / `edit then proceed` / `cancel` |
+| H1 | {{ t("releaseHandoff.h1Body") }} | `{{ releaseHandoff.userSelections.h1 }}` | `local only` / `push + PR` / `skip` |
+| H2 | {{ t("releaseHandoff.h2Body") }} | `{{ releaseHandoff.userSelections.h2 or t("releaseHandoff.h2DefaultLabel") }}` | {{ t("releaseHandoff.h2OptionsLabel") }} |
+| H3 | {{ t("releaseHandoff.h3Body") }} | `{{ releaseHandoff.userSelections.h3 }}` | `use as-is` / `edit then proceed` / `cancel` |
 
 ### 4.6.4 Executed Commands
 
 {% if releaseHandoff.executedCommands | length == 0 -%}
-- (mutating 명령 미실행 — H1=`skip` 또는 H3=`cancel`)
+- {{ t("releaseHandoff.noMutationNote") }}
 {%- else %}
-| # | command (verbatim) | exit code | stdout/stderr 요약 |
+| # | command (verbatim) | exit code | {{ t("releaseHandoff.commandsTableHeader.outputSummary") }} |
 |---|---------------------|-----------|--------------------|
 {% for row in releaseHandoff.executedCommands -%}
 | {{ row.number }} | `{{ row.command }}` | `{{ row.exitCode }}` | {{ row.outputSummary }} |
@@ -405,8 +391,8 @@ git/gh mutating 명령이 실행된 phase 의 감사 기록.
 - Plan file (project-relative): `{{ implementation.approvedPlanReference.planFile }}`
 - Approval evidence:
   > {{ implementation.approvedPlanReference.approvalEvidence }}
-- 본 run 의 `EXECUTOR_WORKTREE_PATH`: `{{ implementation.approvedPlanReference.executorWorktreePath }}`
-- 본 run 의 base ref: `{{ implementation.approvedPlanReference.baseRefSha }}`
+- {{ t("executionMeta.runExecutorWorktreePath") }}: `{{ implementation.approvedPlanReference.executorWorktreePath }}`
+- {{ t("executionMeta.runBaseRef") }}: `{{ implementation.approvedPlanReference.baseRefSha }}`
 
 ### 4.7.2 Commit List
 
@@ -435,7 +421,7 @@ git/gh mutating 명령이 실행된 phase 의 감사 기록.
 ### 4.7.4 Out-of-plan Edits
 
 {% if implementation.outOfPlanEdits | length == 0 -%}
-- 계획 외 편집 없음.
+{{ t("emptyState.outOfPlanEdits") }}
 {%- else %}
 | ID | File | Rationale | Trigger |
 |----|------|-----------|---------|
@@ -459,8 +445,8 @@ git/gh mutating 명령이 실행된 phase 의 감사 기록.
   - Read-only command log: {{ block.readOnlyCommandLog }}
   - Independent validation re-run: {{ block.independentValidationRerun }}
   - Style / lint / type-check: {{ block.styleLintTypecheck or '--' }}
-  - Declined fix recommendations: {{ block.declinedFixRecommendations or '- 없음.' }}
-  - Discrepancy: {{ block.discrepancy or '- 없음.' }}
+  - Declined fix recommendations: {{ block.declinedFixRecommendations or t("emptyState.declinedFixRecommendations") }}
+  - Discrepancy: {{ block.discrepancy or t("emptyState.discrepancy") }}
 {% endfor %}
 
 ### 4.7.7 Rollback Verification
@@ -482,11 +468,11 @@ git/gh mutating 명령이 실행된 phase 의 감사 기록.
 ### 4.8.1 Source Implementation Report
 
 - Path (project-relative): `{{ finalVerification.sourceImplementationReport.path }}`
-- 인용된 commit list / diff summary 요약:
+- {{ t("evidenceMeta.commitListSummary") }}:
   > {{ finalVerification.sourceImplementationReport.commitListQuote }}
-- 검증 대상 worktree path: `{{ finalVerification.sourceImplementationReport.worktreePath }}`
-- run 시작 시 capture 한 head/base SHA: `{{ finalVerification.sourceImplementationReport.baseHeadSha }}`
-- `git status --short` (run 시작 시점):
+- {{ t("evidenceMeta.targetWorktreePath") }}: `{{ finalVerification.sourceImplementationReport.worktreePath }}`
+- {{ t("evidenceMeta.capturedHeadBaseSha") }}: `{{ finalVerification.sourceImplementationReport.baseHeadSha }}`
+- {{ t("evidenceMeta.gitStatusAtRunStart") }}:
   ```
   {{ finalVerification.sourceImplementationReport.gitStatusShort }}
   ```
@@ -506,7 +492,7 @@ git/gh mutating 명령이 실행된 phase 의 감사 기록.
 ### 4.8.3 Residual Risk
 
 {% if finalVerification.residualRisk | length == 0 -%}
-- 추적 대상 잔존 위험 없음.
+{{ t("emptyState.lingeringRisks") }}
 {%- else %}
 | ID | Item | Mitigation owner | Escalation trigger |
 |----|------|------------------|---------------------|
@@ -515,9 +501,9 @@ git/gh mutating 명령이 실행된 phase 의 감사 기록.
 {% endfor %}
 {%- endif %}
 
-### 4.8.4 Validation Evidence (요구사항 커버리지)
+### 4.8.4 Validation Evidence{% if t("finalVerification.validationEvidenceAside") != "requirements coverage" %} ({{ t("finalVerification.validationEvidenceAside") }}){% endif %}
 
-| ID | Requirement (plan/brief 인용) | Artifact | Status |
+| ID | {{ t("finalVerification.columnRequirement") }} | Artifact | Status |
 |----|--------------------------------|----------|--------|
 {% for row in finalVerification.validationEvidence -%}
 | {{ row.id }} | {{ row.requirement }} | `{{ row.artifact }}` | {{ row.status }} |
@@ -535,18 +521,27 @@ git/gh mutating 명령이 실행된 phase 의 감사 기록.
 
 {{ finalVerification.routingRecommendation }}
 
+{% endif %}
+{% if header.taskType == 'improvement-discovery' %}
+## 4.9 Improvement Candidates
+
+> Lens whitelist and column schema enforced by `validators/validate-improvement-report.py`. Row count is bounded by the brief's `candidate-cap` (default 8, absolute max 12).
+
+| Cand ID | Lens | Title | Scope | Severity | Effort | Consensus | Source workers | Recommended next-phase | Evidence |
+|---------|------|-------|-------|----------|--------|-----------|----------------|------------------------|----------|
+
 {% endif %}
 ## 5. Clarification Items
 
-다음 run 으로 넘어가기 전에 사용자가 답하거나 자료를 첨부해야 하는 항목을 **한 표 안에서** 추적합니다.
+{{ t("sectionIntro.clarificationItems") }}
 
 {% if clarificationItems | length == 0 -%}
-- 추가 정보 요청 없음. Section 2 의 최종 판단이 그대로 유효합니다.
+{{ t("emptyState.noClarification") }}
 {%- else %}
-답을 채우신 뒤 같은 phase 를 다시 실행:
+{{ t("clarification.fillAndRerun") }}
 
 - Claude Code: `/okstra-run resume-clarification task-key={{ header.taskKey }}`
-- 별도 터미널: `scripts/okstra.sh --resume-clarification --task-key {{ header.taskKey }}`
+- {{ t("clarification.separateTerminalLabel") }}: `scripts/okstra.sh --resume-clarification --task-key {{ header.taskKey }}`
 
 | ID | Ticket ID | Kind | Statement | Expected form | Blocks | Status | User input |
 |----|-----------|------|-----------|---------------|--------|--------|-----------|
@@ -554,7 +549,7 @@ git/gh mutating 명령이 실행된 phase 의 감사 기록.
 | {{ row.id }} | `{{ row.ticketId }}` | `{{ row.kind }}` | {{ row.statement }} | {{ row.expectedForm }} | `{{ row.blocks }}` | {{ row.status }} | {{ row.userInput or '' }} |
 {% endfor %}
 
-컬럼 가이드 (전체 정의는 `prompts/profiles/_common-contract.md §Clarification request policy` SSOT 참조):
+{{ t("clarification.columnGuide") }}
 
 - **`Kind`** ∈ `{material, decision, data-point}`.
 - **`Blocks`** ∈ `{approval, next-phase, none}`.
@@ -572,16 +567,16 @@ git/gh mutating 명령이 실행된 phase 의 감사 기록.
 {% for cmd in step.commands %}
    - {{ cmd.label }}:
      - Claude Code: `{{ cmd.claudeCode }}`
-     - 별도 터미널: `{{ cmd.terminal }}`
+     - {{ t("clarification.separateTerminalLabel") }}: `{{ cmd.terminal }}`
 {% endfor -%}
 {%- endif %}
 {% endfor %}
 {%- endif %}
 
-## 7. Follow-up Tasks (후속 작업)
+## 7. Follow-up Tasks{% if t("followUpTasks.headingAside") != "Follow-up Tasks" %} ({{ t("followUpTasks.headingAside") }}){% endif %}
 
 {% if followUpTasks | length == 0 -%}
-- 후속 작업 없음. 본 run 의 다음 phase 는 §6 (Recommended Next Steps) 참고.
+{{ t("emptyState.noFollowUp") }}
 {%- else %}
 | ID | Ticket ID | Origin | New Task ID | Title | Suggested task-type | Scope (files/areas) | Reason / Why deferred | Priority (P0/P1/P2) | Auto-spawn? |
 |----|-----------|--------|-------------|-------|---------------------|---------------------|------------------------|---------------------|-------------|

package/runtime/templates/reports/i18n/en.json

@@ -0,0 +1,135 @@
+{
+  "_meta": {
+    "lang": "en",
+    "note": "okstra final-report fixed strings (English). Keys must mirror ko.json exactly. Add a key here AND in ko.json in the same commit."
+  },
+  "emptyState": {
+    "consensusItems": "- No consensus items.",
+    "differences": "- No significant differences. 1.1 Consensus stands as-is.",
+    "primaryEvidence": "- No primary evidence.",
+    "secondaryEvidence": "- No secondary evidence or alternate interpretations.",
+    "risks": "- No missing information or risks.",
+    "dependencyRisk": "- No dependency / migration risks.",
+    "dissent": "- No dissenting opinions.",
+    "outOfPlanEdits": "- No out-of-plan edits.",
+    "declinedFixRecommendations": "- None.",
+    "discrepancy": "- None.",
+    "lingeringRisks": "- No tracked lingering risks.",
+    "noClarification": "- No additional information requested. The Section 2 verdict stands as-is.",
+    "noFollowUp": "- No follow-up tasks. The next phase for this run is in §6 (Recommended Next Steps)."
+  },
+  "columns": {
+    "summary": "Summary",
+    "source": "Source (brief/source/worker)",
+    "rawTokens": "Raw tokens",
+    "billableTokens": "Billable tokens",
+    "billableTokensInputEquiv": "Billable tokens (input-equiv.)",
+    "cost": "Cost (USD)",
+    "checkMethod": "How to check"
+  },
+  "sectionAside": {
+    "dependencyRisk": "Dependency / Migration Risk",
+    "validationChecklist": "Validation Checklist",
+    "rollbackStrategy": "Rollback Strategy",
+    "planBodyVerification": "Plan Body Verification",
+    "recommendedOption": "Recommended Option",
+    "optionCandidates": "Option Candidates",
+    "tradeOffMatrix": "Trade-off Matrix",
+    "stepwiseExecutionOrder": "Stepwise Execution Order"
+  },
+  "sectionIntro": {
+    "verdictCard": "At-a-glance verdict card. Every value in this table MUST exactly match the authoritative values in `## 2. Final Verdict` and `## 6. Recommended Next Steps`.",
+    "clarificationCarryIn": "Walk every C-* row of the prior report's `## 5. Clarification Items` table against new evidence. Update each row's `Status` to `resolved` or `obsolete` and carry it into this run's `## 5.` table. Cite the resolution evidence (file:line / log / worker result) inline.",
+    "ticketCoverage": "Summarize 3-5 core problems / requirements / verification targets as a table. Base this on the brief, source material, and worker results.",
+    "executionStatus": "Aggregate each worker's status, assigned model, and key findings into one table. Do NOT replace worker artifacts with ungrounded claims.",
+    "sourceItemsRule": "`Source items` rule: list which worker items this consensus row was synthesised from, as a comma-list of `<worker>:<item-id>` pairs. Full policy: `prompts/profiles/_common-contract.md` \"Cross-worker traceability\" SSOT.",
+    "stepRule": "Rule: each step is roughly 2-5 minutes. Every step MUST include exact file paths and commands.",
+    "planBodyVerification": "Result of Phase 6 — report-writer's synthesised 4.5 body re-cast to workers by the lead on a plan-item basis, with verdicts collected.",
+    "clarificationItems": "Track items that must be answered by the user or backed by attached material before the next run advances, **all inside one table**."
+  },
+  "tokenSummary": {
+    "heading": "Token Usage Summary",
+    "tableHeaderItem": "Item",
+    "rowLead": "Lead",
+    "rowWorkerTotal": "Worker subtotal",
+    "rowGrandTotal": "**Grand total**",
+    "rowCliExtra": "Codex/Gemini CLI add-on"
+  },
+  "verdictCard": {
+    "tableHeaderLabel": "Item",
+    "tableHeaderValue": "Value",
+    "approvalRequiredSuffix": "frontmatter `approved` must be `true` to enter `implementation`",
+    "rationaleLabel": "Rationale summary",
+    "nextStepLabel": "Next step"
+  },
+  "ticketCoverage": {
+    "intro": "Reverse index of tickets covered in this run. All body items are linked to a ticket via the `Ticket ID` column or `[TICKETID: <id>]` tag.",
+    "columnSections": "Sections",
+    "columnRelatedIds": "Related item IDs",
+    "ruleNote": "Rule: `Ticket ID` must match the ticket key exactly as it appears in the body. When `Issue / Ticket` is empty and falls back, use the `Task ID` value as-is without prefix (e.g. `8852`). Use `unknown` when not identifiable."
+  },
+  "finalVerdict": {
+    "intro": "State the final conclusion and recommended direction in one table. `Direction` ∈ `continue-investigation / begin-implementation / approve / reject / hold`. When `task-type` is `final-verification`, `Verdict Token` must be one of `accepted / conditional-accept / blocked`; `release-handoff` uses this value as an entry gate. For all other task-types use `not-applicable`."
+  },
+  "evidence": {
+    "sourceItemsColumnNote": "`Source items` column rule is the same as §1.1."
+  },
+  "roundHistory": {
+    "round2SkippedReasonNote": "value is one of `queue-empty | max-rounds-1 | all-reverify-non-result | not-skipped | convergence-disabled | single-analyser-only`"
+  },
+  "implementationPlanning": {
+    "optionInterfacesLabel": "Affected interfaces / public contracts / downstream consumers",
+    "optionBlastRadiusLabel": "Blast radius estimate",
+    "recommendedTableHeaderLabel": "Item",
+    "recommendedTableHeaderValue": "Value",
+    "coreReasonLabel": "Core reason",
+    "rationaleLabel": "Rationale (trade-off row / principle)",
+    "rejectedSummaryLabel": "Summary of rejected options",
+    "columnImpact": "Impact",
+    "columnMitigation": "Mitigation / prerequisite"
+  },
+  "releaseHandoff": {
+    "auditNote": "Audit trail for the phase that ran git/gh mutating commands.",
+    "branchStateAside": "captured at run start",
+    "gitStatusShortLabel": "`git status --short` output",
+    "existingPrLabel": "Existing PR",
+    "userSelectionsAside": "menu response log",
+    "questionsTableHeader": {
+      "questionId": "Question ID",
+      "questionBody": "Question",
+      "userResponse": "User response (raw)",
+      "allowedOptions": "Allowed options"
+    },
+    "h1Body": "Which action should run?",
+    "h2Body": "PR base branch (when H1 = `push + PR`)",
+    "h3Body": "How should the PR title/body draft be handled?",
+    "h2DefaultLabel": "(n/a)",
+    "h2OptionsLabel": "staging / preprod / prod / main / dev / user input",
+    "noMutationNote": "(no mutating command — H1=`skip` or H3=`cancel`)",
+    "commandsTableHeader": {
+      "outputSummary": "stdout/stderr summary"
+    }
+  },
+  "executionMeta": {
+    "runExecutorWorktreePath": "This run's `EXECUTOR_WORKTREE_PATH`",
+    "runBaseRef": "This run's base ref"
+  },
+  "evidenceMeta": {
+    "commitListSummary": "Cited commit list / diff summary",
+    "targetWorktreePath": "Target worktree path for verification",
+    "capturedHeadBaseSha": "head/base SHA captured at run start",
+    "gitStatusAtRunStart": "`git status --short` (at run start)"
+  },
+  "clarification": {
+    "fillAndRerun": "Fill in your answers then re-run the same phase:",
+    "separateTerminalLabel": "Separate terminal",
+    "columnGuide": "Column guide (full definitions: `prompts/profiles/_common-contract.md §Clarification request policy` SSOT):"
+  },
+  "followUpTasks": {
+    "headingAside": "Follow-up Tasks"
+  },
+  "finalVerification": {
+    "validationEvidenceAside": "requirements coverage",
+    "columnRequirement": "Requirement (plan/brief citation)"
+  }
+}