@fitlab-ai/agent-infra 0.11.3 → 0.11.5

package/templates/.agents/skills/code-task/SKILL.zh-CN.md

@@ -1,8 +1,8 @@
 ---
 name: code-task
 description: >
-  根据技术方案编码任务并输出报告。
-  当技术方案已批准需要落地实现，或代码审查发现问题需要修复时使用。
+  根据生命周期输入编码任务并输出报告。
+  当分析或技术方案已按所选路径准备完成，或代码审查发现问题需要修复时使用。
   仅当对话包含可解析的任务引用时才可自动调用本技能。
 ---
 
@@ -11,16 +11,20 @@ description: >
 
 若入口业务操作数包含 `--orchestrated`，绑定 `{execution-flag}` = `--orchestrated` 并原样转发给 completed 事件；否则绑定为空。不得从 `orchestration.json`、环境变量或历史产物推断该标记。生命周期事件还必须携带显式触发信息：编排调用使用 `{trigger-initiator}=orchestrator`，否则使用 `model`；`{request-id}` 是本任务与本轮产物的稳定单行标识，`{reason-code}` 初次实现使用 `user-request`，修复或裁决使用 `review-finding`；started 与 completed 使用同一组值。
 
-根据已批准的技术方案编码任务，并产出 `code.md` 或 `code-r{N}.md`。本技能支持初次实现、基于 `review-code` 反馈的修复，以及人工裁决驱动实现三种模式。
+根据所选生命周期路径的实现输入编码任务，并产出 `code.md` 或 `code-r{N}.md`。本技能支持初次实现、基于 `review-code` 反馈的修复，以及人工裁决驱动实现三种模式。
 
 ## 行为边界 / 关键规则
 
+### 路径与返工
+
+本阶段只消费核心从最新有效分析产物解析出的规范路径事实；未被所选路径包含的阶段不得创建产物。同阶段完成一次修订—复审后再次收到 Changes Requested 时，必须在下一执行产物前提交绑定 finding、来源 SHA 和稳定任务事实摘要的返工分类；轮次或文件名变化不是新证据。
+
 ### 持久化报告证据
 
 生成实现报告时，先读取 `.agents/rules/evidence-reporting.md`。成功测试记录命令、目标范围、状态/结构化结果、实际结果和未覆盖部分；失败、阻塞或争议保留复现入口、准确位置和决定性摘录，不默认粘贴完整成功 stdout。
 
 - 涉及候选资格或 `HD-N` 判断时，先读取 `.agents/rules/decision-qualification.md`，基于 task.md 规范化约束/候选完成资格审计，并在实现报告记录五张资格审计表；不得把来源不明或未确认约束自动升级为排除条件
-- 严格遵循最新方案产物：`plan.md` 或 `plan-r{N}.md`
+- 严格遵循核心选择的最新生命周期输入：精简路径为 `analysis.md` / `analysis-r{N}.md`，标准或完整路径为 `plan.md` / `plan-r{N}.md`
 - 生成会同步到 Issue 的任务或生命周期 Markdown 前，先读取 `.agents/rules/sync-content-generation.md` 并遵循其中的生成端约束；同步端不解析或改写正文
 - 实现前读取 `.agents/rules/compatibility-policy.md`；只实现方案明确批准的兼容预算，不以“稳妥”为由保留旧分支、旧结果契约或迁移 shim
 - 修复模式逐条核实最新 `review-code` 的发现：成立则修复，判定为不成立/幻觉则在报告中反驳并记入 unresolved；不擅自扩大到审查未列出的问题；manual-validation 项不在修复范围
@@ -40,7 +44,7 @@ description: >
 |------|------|
 | 「代码太简单，不需要测试」 | 简单代码也会回归；没有"失败→通过"的用例就没有完成标志，先写验证业务行为的测试。 |
 | 「先写代码再补测试更高效」 | 后补测试常沦为对实现的镜像；目标驱动应先定义可验证用例再让它通过。 |
-| 「方案这里不合理，顺手改更好」 | 偏离 `{plan-artifact}` 必须在报告中记录原因；有异议先停下确认，不擅自改方向。 |
+| 「输入这里不合理，顺手改更好」 | 偏离 `{lifecycle-input-artifact}` 必须在报告中记录原因；有异议按任务规则处理，不擅自改方向。 |
 | 「测试过了，顺便推送一下」 | 本技能只创建本地 checkpoint；远端推送是 `create-pr` 的唯一边界。 |
 | 「审查既然写了，照着改就行」 | 审查可能基于错误 `file:line` 或幻觉；动手前先 Read/Grep 核实，成立才修，不成立就反驳并记入 unresolved，不盲从。 |
 | 「保留旧入口更稳妥，反正只多一个分支」 | 未获批准的兼容是范围扩张和长期债务；没有对象、必要性、期限和退出条件就只实现当前契约。 |
@@ -72,9 +76,8 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 先检查：
 - `.agents/workspace/active/{task-id}/task.md`
-- 至少一个技术方案产物：`plan.md` 或 `plan-r{N}.md`
 
-如果缺少任一文件，立即停止并提示用户先完成前置步骤。
+如果缺少任务文件，立即停止。生命周期输入由步骤 4 的核心查询按已选路径验证；技能不得预先固定要求方案产物。
 
 ### 2. 确保任务分支
 
@@ -105,6 +108,8 @@ status=$?
 echo "$result"
 ```
 
+若 `selection.disposition` 为 `reuse`，复用 `selection.artifact`，不得执行 started、init、代码修改或写入新产物，并直接进入完成校验与下一步提示。其他状态继续按下表处理。
+
 按 `$status` 与 `result.mode` 分流；二者不一致时按 `$status` 为准并报告异常：
 
 | `$status` | `result.mode` | 行动 |
@@ -118,13 +123,13 @@ echo "$result"
 
 > 双模式判定规则见 `reference/dual-mode.md`。执行此步骤前先读取 `reference/dual-mode.md`。
 
-### 5. 确定输入方案
+### 5. 确定生命周期输入
 
-只使用步骤 4 的结构化结果：从 `inputs` 取得 `{plan-artifact}`，从 `next_round` / `next_artifact` 取得 `{code-round}` / `{code-artifact}`；修复模式从 `review_artifact` 取得 `{review-artifact}`；裁决模式从 `implementation_input`、`decision_id`、`decision_evidence` 取得统一输入身份。不得自行扫描轮次或拼装文件名。
+只使用步骤 4 的结构化结果：从 `inputs` 取得核心选择的 `{lifecycle-input-artifact}`（精简路径为 analysis，其他路径为 plan），从 `next_round` / `next_artifact` 取得 `{code-round}` / `{code-artifact}`；修复模式从 `review_artifact` 取得 `{review-artifact}`；裁决模式从 `implementation_input`、`decision_id`、`decision_evidence` 取得统一输入身份。不得自行扫描轮次或拼装文件名。
 
-### 6. 阅读技术方案
+### 6. 阅读生命周期输入
 
-仔细阅读 `{plan-artifact}`，提取：
+仔细阅读 `{lifecycle-input-artifact}`，提取：
 - 实施步骤
 - 需要创建或修改的文件
 - 测试策略
@@ -237,11 +242,11 @@ agent-infra-internal task-verify {task-id} code.completed --artifact {code-artif
 ## 注意事项
 
 - 首轮实现使用 `code.md`，后续轮次使用 `code-r{N}.md`
-- 如偏离 `{plan-artifact}`，必须在报告中记录原因
+- 如偏离 `{lifecycle-input-artifact}`，必须在报告中记录原因
 - 新测试必须验证有意义的业务行为，而不是机械透传
 
 ## 错误处理
 
 - 任务未找到：`Task {task-id} not found`
-- 缺少方案：`Technical plan not found, please run the plan-task skill first`
+- 缺少生命周期输入：透传步骤 4 返回的 `ARTIFACT_INPUT_MISSING`，按所选路径补充 analysis 或 plan
 - 本地修复后仍无法通过测试：说明外部阻塞并停止，且不要创建实现产物

package/templates/.agents/skills/code-task/reference/code-rules.en.md

@@ -14,7 +14,7 @@ Follow the `code` step in `.agents/workflows/feature-development.yaml`.
 - [ ] follow project coding standards
 
 **Implementation principles**:
-1. **Follow the plan strictly**: do not deviate from the technical plan
+1. **Follow the input strictly**: do not deviate from the analysis or plan lifecycle input selected by core
 2. **Work step by step**: execute the planned sequence
 3. **Keep testing continuously**: run the **fast smoke subset** continuously as work progresses (see the `test` skill)
 4. **Keep it simple**: do not add unplanned features
@@ -46,7 +46,7 @@ Two-way failure handling:
 
 ## Notes
 
-1. **Prerequisite**: the approved technical plan must exist (`plan.md` or `plan-r{N}.md`)
+1. **Prerequisite**: the analysis or plan lifecycle input selected by core must exist
 2. **No auto-commit**: do not run `git commit` or `git add`
 3. **Test quality**: new tests must validate meaningful business logic
 4. **Code quality**: follow project coding conventions

package/templates/.agents/skills/code-task/reference/code-rules.zh-CN.md

@@ -14,7 +14,7 @@
 - [ ] 遵守项目编码规范
 
 **实现原则**：
-1. **严格遵循方案**：不要偏离技术方案
+1. **严格遵循输入**：不要偏离核心选择的 analysis 或 plan 生命周期输入
 2. **按步骤推进**：按计划顺序执行
 3. **持续测试**：实现过程中持续运行 **fast smoke 子集**（参见 `test` skill）
 4. **保持简单**：不要加入未计划的功能
@@ -46,7 +46,7 @@
 
 ## 注意事项
 
-1. **前置条件**：必须存在已批准的技术方案（`plan.md` 或 `plan-r{N}.md`）
+1. **前置条件**：必须存在核心按所选路径返回的 analysis 或 plan 生命周期输入
 2. **禁止自动提交**：不要执行 `git commit` 或 `git add`
 3. **测试质量**：新增测试必须验证有意义的业务逻辑
 4. **代码质量**：遵循项目编码规范

package/templates/.agents/skills/code-task/reference/dual-mode.en.md

@@ -8,9 +8,9 @@ This file documents the core artifact lifecycle's code-mode decision. The `task-
 agent-infra-internal task-artifact {task-id} inspect --family code
 ```
 
-The core scans `plan.md` / `plan-r{N}.md`, `review-plan.md` / `review-plan-r{N}.md`, `code.md` / `code-r{N}.md`, and `review-code.md` / `review-code-r{N}.md` in the task directory.
+The core reads the path decision from the latest analysis and selects the lifecycle input: analysis for streamlined, plan for standard or full. The full path also validates review-plan before scanning code and review-code artifacts.
 
-`code.started` persists the plan identity and SHA-256 for the round in task.md frontmatter. `code.completed` uses that start context and verifies the current latest plan; changed input fails closed. The implementation report's `Plan Input` field is reader-facing traceability, not lifecycle identity validation.
+`code.started` persists the lifecycle input identity and SHA-256 for the round in task.md frontmatter. `code.completed` verifies the current latest input against that context; changed input fails closed. The implementation report field is reader-facing traceability only.
 
 ## Eight Branches
 
@@ -18,8 +18,8 @@ The core scans `plan.md` / `plan-r{N}.md`, `review-plan.md` / `review-plan-r{N}.
 
 | Condition | mode | exit | Behavior |
 |---|---|---:|---|
-| no code artifact, and the latest review-plan is exactly `Approved` and references the latest plan | `init` | 0 | initial implementation, output `code.md`; a missing matching approval or `Approved-with-issues` returns an error |
-| latest review-plan is exactly `Approved`, references the latest plan, and the latest code completion receipt does not bind the same plan digest | `init` | 0 | enter a new implementation round. `Approved-with-issues` remains parse-compatible for history but is not cross-stage approval; missing or invalid receipts fail closed |
+| no code artifact and the selected lifecycle input is valid; full also requires an exactly `Approved` review-plan bound to the latest plan | `init` | 0 | initial implementation, output `code.md` |
+| the latest analysis or plan lifecycle input is not bound by the latest code completion receipt | `init` | 0 | enter a new implementation round; missing or invalid receipts fail closed |
 | the latest review-code completion receipt does not bind the latest code identity/SHA | `error` | 2 | latest code is unreviewed; run `review-code`; code and review-code family rounds may advance independently |
 | latest review-code is Approved and a pending implementation input was decided after that review completed | `decision` | 0 | select the earliest `II-N` and enter decision-driven implementation; false/not-required and consumed inputs do not trigger |
 | latest review-code is Approved with 0/0/0 | `refused` | 1 | already approved; do not run `code-task` again |

package/templates/.agents/skills/code-task/reference/dual-mode.zh-CN.md

@@ -8,9 +8,9 @@
 agent-infra-internal task-artifact {task-id} inspect --family code
 ```
 
-核心扫描任务目录中的 `plan.md` / `plan-r{N}.md`、`review-plan.md` / `review-plan-r{N}.md`、`code.md` / `code-r{N}.md` 和 `review-code.md` / `review-code-r{N}.md`。
+核心读取最新 analysis 的路径裁定，并选择生命周期输入：精简路径使用 analysis，标准或完整路径使用 plan；完整路径还校验对应 review-plan。随后扫描 code 与 review-code 产物。
 
-`code.started` 会在 task.md frontmatter 中绑定本轮方案文件及其 SHA-256。`code.completed` 使用该开始上下文并校验当前最新 plan；内容变化失败关闭。实现报告的“方案输入”/“Plan Input”仅供读者追溯，不参与生命周期身份校验。
+`code.started` 会在 task.md frontmatter 中绑定本轮生命周期输入及其 SHA-256。`code.completed` 使用该开始上下文并校验当前最新输入；内容变化失败关闭。实现报告的“生命周期输入”仅供读者追溯，不参与生命周期身份校验。
 
 ## 8 个分支
 
@@ -18,8 +18,8 @@ agent-infra-internal task-artifact {task-id} inspect --family code
 
 | 条件 | mode | exit | 行为 |
 |---|---|---:|---|
-| 无 code 产物，且最新 review-plan 精确为 `Approved` 并引用最新 plan | `init` | 0 | 初次实现，产物为 `code.md`；缺少匹配审批或为 `Approved-with-issues` 时返回 error |
-| 最新 review-plan 精确为 `Approved`，且其「审查输入」/「Review Input」字段引用最新 plan，而最新 code 的完成 receipt 未绑定相同 plan 摘要 | `init` | 0 | plan 内容在 code 输入之后获批；进入新一轮实现。`Approved-with-issues` 仅保留历史解析兼容，不构成跨阶段批准；缺失或无效 receipt 失败关闭 |
+| 无 code 产物，且所选生命周期输入有效；完整路径的最新 review-plan 还必须精确为 `Approved` 并引用最新 plan | `init` | 0 | 初次实现，产物为 `code.md` |
+| 最新 analysis 或 plan 生命周期输入未被最新 code 完成 receipt 绑定 | `init` | 0 | 输入在上轮 code 后发生有效变化，进入新一轮实现；缺失或无效 receipt 失败关闭 |
 | 最新 review-code 的完成收据未绑定最新 code identity/SHA | `error` | 2 | 最新代码未审查，先运行 `review-code`；code 与 review-code 的 family 轮次可独立增长 |
 | 最新 review-code 为 Approved 且存在审查完成后产生的 pending 实现输入 | `decision` | 0 | 选择最早 `II-N`，进入裁决驱动实现；false/not-required 与 consumed 输入不触发 |
 | 最新 review-code 为 Approved 且 0/0/0 | `refused` | 1 | 已通过，无需再次运行 `code-task` |

package/templates/.agents/skills/code-task/reference/report-template.en.md

@@ -17,7 +17,7 @@ Use this structure when creating `code.md` or `code-r{N}.md`.
 ## Implementation Input
 
 - **Mode**: {init / fix / decision}
-- **Plan Input**: `{plan-artifact}`
+- **Lifecycle Input**: `{lifecycle-input-artifact}`
 - **Review Input**: `{review-artifact or N/A}`
 - **Decision Input**: `{implementation-input or N/A}`
 - **Ledger ID**: `{decision-id or N/A}`
@@ -102,25 +102,25 @@ Use this structure when creating `code.md` or `code-r{N}.md`.
 
 ## State Check
 
-> Record the state-check command, task/artifact scope, key result, and uncovered parts; each command starts with `$ `.
+> Record the state-check command, task/artifact scope, key result, and uncovered parts.
 > Follow `.agents/rules/evidence-reporting.md`: record task/artifact scope, key result, and uncovered parts; do not paste complete successful stdout.
 
-Record at least one actually executed `$ ` command and its result summary; prose-only status is insufficient. An implementation-stage report normally includes:
+Record at least one actually executed command and its result summary; prose-only status is insufficient. An implementation-stage report normally includes:
 
 ```text
-$ agent-infra-internal task-snapshot {task-id} --format text
+agent-infra-internal task-snapshot {task-id} --format text
 {task state, implementation-artifact scope, and uncovered-area summary}
-$ agent-infra-internal task-artifact {task-id} inspect --family code
+agent-infra-internal task-artifact {task-id} inspect --family code
 {code artifact, upstream input, and next-step summary}
 ```
 
 ## Raw Evidence
 
-> Follow `.agents/rules/evidence-reporting.md`: pair each claim with a `$ ` command and proportionate result summary; include a decisive raw excerpt only for failures, blocking conditions, or disputes.
+> Follow `.agents/rules/evidence-reporting.md`: pair each claim with an executable command and proportionate result summary; include a decisive raw excerpt only for failures, blocking conditions, or disputes.
 
 - Claim: {verified claim}
 ```text
-$ {command}
+{command}
 {result summary or decisive excerpt}
 ```
 

package/templates/.agents/skills/code-task/reference/report-template.zh-CN.md

@@ -17,7 +17,7 @@
 ## 实现输入
 
 - **模式**：{init / fix / decision}
-- **方案输入**：`{plan-artifact}`
+- **生命周期输入**：`{lifecycle-input-artifact}`
 - **审查输入**：`{review-artifact 或 N/A}`
 - **裁决输入**：`{implementation-input 或 N/A}`
 - **账本 ID**：`{decision-id 或 N/A}`
@@ -102,25 +102,25 @@
 
 ## 状态核对
 
-> 记录状态核对命令、任务/产物范围、关键结果和未覆盖部分；每条命令以 `$ ` 开头。
+> 记录状态核对命令、任务/产物范围、关键结果和未覆盖部分。
 > 按 `.agents/rules/evidence-reporting.md` 同时记录任务/产物范围、关键结果和未覆盖部分；正常成功不粘贴完整 stdout。
 
-必须记录至少一条实际执行的 `$ ` 命令及其结果摘要，不能只写自然语言状态。实现阶段通常包括：
+必须记录至少一条实际执行的命令及其结果摘要，不能只写自然语言状态。实现阶段通常包括：
 
 ```text
-$ agent-infra-internal task-snapshot {task-id} --format text
+agent-infra-internal task-snapshot {task-id} --format text
 {任务状态、实现产物范围和未覆盖项摘要}
-$ agent-infra-internal task-artifact {task-id} inspect --family code
+agent-infra-internal task-artifact {task-id} inspect --family code
 {code artifact、上游输入和下一步摘要}
 ```
 
 ## 证据原文
 
-> 遵循 `.agents/rules/evidence-reporting.md`：每条断言配对 `$ ` 命令和相称结果摘要；仅为失败、阻塞或争议附决定性原文摘录。
+> 遵循 `.agents/rules/evidence-reporting.md`：每条断言配对可执行命令和相称结果摘要；仅为失败、阻塞或争议附决定性原文摘录。
 
 - 断言：{verified claim}
 ```text
-$ {command}
+{command}
 {result summary or decisive excerpt}
 ```
 

package/templates/.agents/skills/complete-manual-validation/config/verify.en.json

@@ -23,8 +23,8 @@
         "Validation Details",
         "PR Summary Sync"
       ],
-      "required_patterns": [
-        "^\\$ "
+      "state_check_patterns": [
+        "agent-infra-internal[ \\t]+task-snapshot\\b"
       ]
     },
     "activity-log": {

package/templates/.agents/skills/complete-manual-validation/config/verify.zh-CN.json

@@ -23,8 +23,8 @@
         "验证详情",
         "PR 摘要同步"
       ],
-      "required_patterns": [
-        "^\\$ "
+      "state_check_patterns": [
+        "agent-infra-internal[ \\t]+task-snapshot\\b"
       ]
     },
     "activity-log": {

package/templates/.agents/skills/complete-manual-validation/reference/report-template.en.md

@@ -12,9 +12,7 @@ Read this file before creating `manual-validation.md` / `manual-validation-r{N}.
 ## State Check
 
 ```text
-$ git status -s
-$ ls -la .agents/workspace/active/{task-id}/
-$ tail .agents/workspace/active/{task-id}/task.md
+agent-infra-internal task-snapshot {task-id} --format text
 ```
 > Follow `.agents/rules/evidence-reporting.md`: record task scope, key result, and uncovered parts; do not paste the complete directory listing or task tail for normal success.
 

package/templates/.agents/skills/complete-manual-validation/reference/report-template.zh-CN.md

@@ -12,9 +12,7 @@
 ## 状态核对
 
 ```text
-$ git status -s
-$ ls -la .agents/workspace/active/{task-id}/
-$ tail .agents/workspace/active/{task-id}/task.md
+agent-infra-internal task-snapshot {task-id} --format text
 ```
 > 按 `.agents/rules/evidence-reporting.md` 记录任务范围、关键结果和未覆盖部分；正常成功不粘贴完整目录清单或 task tail。
 

package/templates/.agents/skills/complete-task/SKILL.en.md

@@ -9,7 +9,7 @@ description: >
 # Complete Task
 > `--agent` values are defined in `.agents/rules/task-management.md` under “Collaborator Token Specification”.
 
-Host finalization uses receipt v3 with an immutable `receiptId`, monotonic `revision`, staged summary input, and canonical warnings. Lifecycle/identity/required-PR hard failures return `result: failed|blocked`; after lifecycle succeeds, comment, peripheral verification, and other sync failures return `result: completed_with_warnings` and six-field warnings, retrying only receipt-pending steps.
+Host finalization uses receipt v4 with an immutable `receiptId`, monotonic `revision`, staged summary input, and canonical warnings. Lifecycle/identity/required-PR hard failures return `result: failed|blocked`; after lifecycle succeeds, it retries only receipt-pending peripheral steps or open backfill warnings. Per-check verification warnings transition by observed target: a later observation resolves the prior code while retaining its history, and unobserved targets remain unchanged.
 
 
 ## Boundary / Critical Rules
@@ -176,7 +176,7 @@ If a summary must mirror a human-decided `post-review-commit` exemption, make a
 agent-infra-internal task-finalization {task-id} complete --agent {standard-agent-token}
 ```
 
-Finalization runs allowed artifact backfill -> lifecycle -> terminal task comment -> core verification -> warning task-comment update -> summary seal in a fixed order. Every backfill must reach a successful terminal result before lifecycle starts. Summary seal always reads the durable staging record retained in the task directory; the platform entry point validates marker, owner, and digest, performs any required delete/recreate, and reads back final remote order. Re-entry repeats this idempotent operation instead of recovering local input from a remote comment. `result=completed` means the host safely completed the task from structured results and the receipt; if peripheral warnings or pending steps remain, return `result=completed_with_warnings`, warnings, and pending steps. Use `result=failed` or `result=blocked` only for hard or receipt/capability failures, then fix the cause and retry through the same entry point; do not claim completion or hand-repair partial state. A sandbox must not run `ls completed` or a local terminal verification against its historical mount to re-decide this result.
+Finalization runs allowed artifact backfill -> lifecycle -> terminal task comment -> core verification -> warning task-comment update -> summary seal in a fixed order. Every backfill that actually runs must reach a successful terminal result before lifecycle starts; an ordinary replay with a complete receipt and no recovery fact does not rerun backfill, comments, verification, or summary. A completed recovery that may write a managed comment first persists a done summary as pending, then seals it only at the end. Summary seal always reads the durable staging record retained in the task directory; the platform entry point validates marker, owner, and digest, performs any required delete/recreate, and reads back final remote order. `result=completed` means the host safely completed the task from structured results and the receipt; if peripheral warnings or pending steps remain, return `result=completed_with_warnings`, warnings, and pending steps. Use `result=failed` or `result=blocked` only for hard or receipt/capability failures, then fix the cause and retry through the same entry point; do not claim completion or hand-repair partial state. A sandbox must not run `ls completed` or a local terminal verification against its historical mount to re-decide this result.
 
 ### 7. Handle Finalization Retries and Results
 

package/templates/.agents/skills/complete-task/SKILL.zh-CN.md

@@ -9,7 +9,7 @@ description: >
 # 完成任务
 > `--agent` 取值见 `.agents/rules/task-management.md`「合作者 token 规范」。
 
-宿主 finalization 使用 receipt v3（不可变 `receiptId`、单调 `revision`、摘要暂存和 canonical warnings）。生命周期/身份/required PR 等硬失败返回 `result: failed|blocked`；生命周期完成后，评论、外围验证和其他同步失败返回 `result: completed_with_warnings` 及六字段 warning，并仅重试 receipt 中的 pending step。
+宿主 finalization 使用 receipt v4（不可变 `receiptId`、单调 `revision`、摘要暂存和 canonical warnings）。生命周期/身份/required PR 等硬失败返回 `result: failed|blocked`；生命周期完成后，只重试 receipt 指出的 pending 外围步骤或 open backfill warning。逐检查 verification warning 以 observed target 为单位转换：新观察替代旧 code 时保留旧行 resolved 历史，未观察的 target 不变。
 
 
 ## 行为边界 / 关键规则
@@ -175,7 +175,7 @@ agent-infra-internal task-verify {task-id} complete-task.preflight --format text
 agent-infra-internal task-finalization {task-id} complete --agent {standard-agent-token}
 ```
 
-finalization 按允许的 artifact backfill → lifecycle → task 评论 → core verification → warning task 评论更新 → summary seal 的固定顺序执行。每项 backfill 必须取得成功终态，否则不得进入 lifecycle。summary seal 始终读取任务目录中保留的 durable staging record；平台入口负责校验 marker、owner 和 digest，必要时删除并重建摘要，再复读最终远端顺序。重入直接重复该幂等操作，不从远端评论反向恢复本地正文。`result=completed` 即表示宿主已依据结构化结果和 receipt 安全完成；若还有外围 warning 或 pending step，返回 `result=completed_with_warnings`、warnings 和 pending steps。`result=failed` 或 `result=blocked` 仅用于硬失败或 receipt/capability 失败，修复原因后以同一入口重试，不得宣称完成或手工补写局部状态。沙箱不得从旧挂载执行 `ls completed` 或本地终态校验来重新裁决该结果。
+finalization 按允许的 artifact backfill → lifecycle → task 评论 → core verification → warning task 评论更新 → summary seal 的固定顺序执行。每项实际运行的 backfill 必须取得成功终态，否则不得进入 lifecycle；完整 receipt 且无恢复事实的普通重入不执行 backfill、评论、验证或 summary。任何可能写入 managed comment 的 completed 恢复会先把 done summary 持久化为 pending，恢复末尾才重新 seal。summary seal 始终读取任务目录中保留的 durable staging record；平台入口负责校验 marker、owner 和 digest，必要时删除并重建摘要，再复读最终远端顺序。`result=completed` 即表示宿主已依据结构化结果和 receipt 安全完成；若还有外围 warning 或 pending step，返回 `result=completed_with_warnings`、warnings 和 pending steps。`result=failed` 或 `result=blocked` 仅用于硬失败或 receipt/capability 失败，修复原因后以同一入口重试，不得宣称完成或手工补写局部状态。沙箱不得从旧挂载执行 `ls completed` 或本地终态校验来重新裁决该结果。
 
 ### 7. 处理 finalization 重试与结果
 

package/templates/.agents/skills/complete-task/config/verify.en.json

@@ -38,8 +38,8 @@
       "required_sections": [
         "State Check"
       ],
-      "required_patterns": [
-        "^\\$ "
+      "state_check_patterns": [
+        "agent-infra-internal[ \\t]+task-snapshot\\b"
       ]
     }
   }

package/templates/.agents/skills/complete-task/config/verify.zh-CN.json

@@ -38,8 +38,8 @@
       "required_sections": [
         "状态核对"
       ],
-      "required_patterns": [
-        "^\\$ "
+      "state_check_patterns": [
+        "agent-infra-internal[ \\t]+task-snapshot\\b"
       ]
     }
   }

package/templates/.agents/skills/plan-task/SKILL.en.md

@@ -13,13 +13,17 @@ If the entry operands contain `--orchestrated`, bind `{execution-flag}` to `--or
 
 ## Boundary / Critical Rules
 
+### Path and rework
+
+This stage consumes only the canonical path fact parsed by core from the latest valid analysis artifact; a stage omitted by that path must not create an artifact. When another Changes Requested verdict follows one completed revision-review cycle in the same stage, classify the rework before the next executor artifact and bind it to the finding, source SHA, and stable task-fact digest. A round or filename change is not new evidence.
+
 ### Persisted Report Evidence
 
 Before generating the plan report, read `.agents/rules/evidence-reporting.md`. Record the command, target scope, status or structured result, actual result, and uncovered parts for state checks and verification; include decisive raw excerpts only for failures, blocking conditions, or disputes.
 
 - When evaluating candidate qualification or `HD-N`, read `.agents/rules/decision-qualification.md`, audit normalized task constraints/candidates, and record the five qualification-audit tables in the plan artifact; unknown or unconfirmed constraints must not automatically exclude a candidate
 - This skill only outputs a technical plan document (`plan.md` or `plan-r{N}.md`) and does not modify any business code
-- This is a **mandatory human review checkpoint**; do not automatically proceed to implementation
+- The full path proceeds to plan review; the standard path may proceed directly to implementation
 - Before generating task or lifecycle Markdown that will be synchronized to an Issue, read `.agents/rules/sync-content-generation.md` and apply its producer-side constraints; the sync path does not parse or rewrite the body
 - When the plan touches compatibility, migration, old formats, or old entry points, read `.agents/rules/compatibility-policy.md` first. Do not design adapters, shims, dual writes, or parallel state machines without passing its admission gate
 - After executing this skill, you **must** immediately update task status in task.md
@@ -62,7 +66,7 @@ If any required file is missing, prompt the user to complete the prerequisite st
 
 ### 2. Resolve the Artifact Context
 
-Run `agent-infra-internal task-artifact {task-id} inspect --family plan`. Continue only for `ready`; take the latest `{analysis-artifact}` from `inputs` and `{plan-round}` / `{plan-artifact}` from `next.round` / `next.name`. Do not scan rounds or construct names in the skill. Then run the started event and verify the returned identity.
+Run `agent-infra-internal task-artifact {task-id} inspect --family plan`. Continue only for `ready`. When `selection.disposition` is `reuse`, reuse `selection.artifact`, do not run started/init or write a new artifact, and continue directly to completion verification and next-step guidance. Otherwise take the latest `{analysis-artifact}` from `inputs` and `{plan-round}` / `{plan-artifact}` from `next.round` / `next.name`. Do not scan rounds or construct names in the skill. Then run the started event and verify the returned identity.
 
 ### 3. Read Requirements Analysis
 
@@ -169,7 +173,9 @@ Keep the gate output in your reply as fresh evidence. Do not claim completion wi
 > Before rendering next steps, read `.agents/rules/next-step-output.md`, invoke the shared helper only for the selected scenario, and insert its stdout at `{next-step-commands}`.
 
 Output format:
-Populate `{next-step-commands}` for this scenario by running `agent-infra-internal agent-client next-steps --skill review-plan --task-ref {task-ref}`.
+Select one command from the canonical path to populate `{next-step-commands}`:
+- Standard: `agent-infra-internal agent-client next-steps --skill code-task --task-ref {task-ref}`
+- Full: `agent-infra-internal agent-client next-steps --skill review-plan --task-ref {task-ref}`
 
 ```
 Technical plan complete for task {task-id}.
@@ -184,10 +190,7 @@ Plan summary:
 Output file:
 - Technical plan: .agents/workspace/active/{task-id}/{plan-artifact}
 
-Important: human review checkpoint.
-Please review the technical plan before continuing to implementation.
-
-Next step - review the technical plan:
+Next step - continue on the selected path:
 {next-step-commands}
 ```
 
@@ -201,18 +204,18 @@ Next step - review the technical plan:
 - [ ] Recorded `{plan-artifact}` as a completed artifact in task.md
 - [ ] Marked technical-design as complete in workflow progress
 - [ ] Appended an Activity Log entry to task.md
-- [ ] Informed the user that this is a human review checkpoint
+- [ ] Selected code implementation or plan review from the canonical path
 - [ ] Rendered the selected next-step commands through the shared helper
 
 ## STOP
 
 After completing the checklist, **stop immediately**.
-This is a **mandatory human review checkpoint**; the user must review and approve the plan before implementation can continue.
+The full path proceeds to plan review here; the standard path proceeds directly to code implementation.
 
 ## Notes
 
 1. **Prerequisite**: at least one round of requirements analysis must already be complete (`analysis.md` or `analysis-r{N}.md` exists)
-2. **Human review**: this is a mandatory checkpoint; do not automatically proceed to implementation
+2. **Next stage**: standard proceeds to code implementation; full proceeds to plan review
 3. **Plan quality**: the plan should be detailed enough that another AI agent can implement it without extra context
 4. **Versioning rule**: the first plan uses `plan.md`; later revisions use `plan-r{N}.md`
 

package/templates/.agents/skills/plan-task/SKILL.zh-CN.md

@@ -13,6 +13,10 @@ description: >
 
 ## 行为边界 / 关键规则
 
+### 路径与返工
+
+本阶段只消费核心从最新有效分析产物解析出的规范路径事实；未被所选路径包含的阶段不得创建产物。同阶段完成一次修订—复审后再次收到 Changes Requested 时，必须在下一执行产物前提交绑定 finding、来源 SHA 和稳定任务事实摘要的返工分类；轮次或文件名变化不是新证据。
+
 ### 持久化报告证据
 
 生成方案报告时，先读取 `.agents/rules/evidence-reporting.md`。状态核对和验证记录命令、目标范围、状态/结构化结果、实际结果和未覆盖部分；失败、阻塞或争议才附决定性原文摘录。
@@ -20,7 +24,7 @@ description: >
 - 涉及候选资格或 `HD-N` 判断时，先读取 `.agents/rules/decision-qualification.md`，基于 task.md 规范化约束/候选完成资格审计，并在方案产物记录五张资格审计表；不得把来源不明或未确认约束自动升级为排除条件
 - 本技能仅产出技术方案文档（`plan.md` 或 `plan-r{N}.md`）—— 不修改任何业务代码
 - 生成会同步到 Issue 的任务或生命周期 Markdown 前，先读取 `.agents/rules/sync-content-generation.md` 并遵循其中的生成端约束；同步端不解析或改写正文
-- 这是一个**强制性的人工审查检查点** —— 不要自动进入实现阶段
+- 完整路径进入方案审查；标准路径完成方案后可直接进入实现阶段
 - 方案涉及兼容、迁移、旧格式或旧入口时，先读取 `.agents/rules/compatibility-policy.md`；未通过准入门槛时不得设计 adapter、shim、双写或并行状态机
 - 执行本技能后，你**必须**立即更新 task.md 中的任务状态
 
@@ -65,7 +69,7 @@ agent-infra-internal task-event {task-id} plan.started --agent {standard-agent-t
 
 ### 2. 解析方案上下文
 
-运行 `agent-infra-internal task-artifact {task-id} inspect --family plan`。仅当结果为 `ready` 时继续；从 `inputs` 取得最新 `{analysis-artifact}`，从 `next.round` / `next.name` 取得 `{plan-round}` / `{plan-artifact}`。不得自行扫描轮次或拼装文件名。随后执行 started 事件并复核返回身份。
+运行 `agent-infra-internal task-artifact {task-id} inspect --family plan`。仅当结果为 `ready` 时继续。若 `selection.disposition` 为 `reuse`，复用 `selection.artifact`，不得执行 started、init 或写入新产物，并直接进入完成校验与下一步提示。其他状态从 `inputs` 取得最新 `{analysis-artifact}`，从 `next.round` / `next.name` 取得 `{plan-round}` / `{plan-artifact}`；不得自行扫描轮次或拼装文件名。随后执行 started 事件并复核返回身份。
 
 ### 3. 阅读需求分析
 
@@ -165,7 +169,9 @@ agent-infra-internal task-verify {task-id} plan.completed --artifact {plan-artif
 > 渲染下一步前先读取 `.agents/rules/next-step-output.md`，仅为已选场景调用统一 helper，并将 stdout 填入 `{next-step-commands}`。
 
 输出格式：
-使用 `agent-infra-internal agent-client next-steps --skill review-plan --task-ref {task-ref}` 生成本场景的 `{next-step-commands}`。
+按分析中的规范路径选择一条命令生成 `{next-step-commands}`：
+- 标准路径：`agent-infra-internal agent-client next-steps --skill code-task --task-ref {task-ref}`
+- 完整路径：`agent-infra-internal agent-client next-steps --skill review-plan --task-ref {task-ref}`
 
 ```
 任务 {task-id} 技术方案完成。
@@ -180,10 +186,7 @@ agent-infra-internal task-verify {task-id} plan.completed --artifact {plan-artif
 产出文件：
 - 技术方案：.agents/workspace/active/{task-id}/{plan-artifact}
 
-重要：人工审查检查点。
-请在继续实现之前审查技术方案。
-
-下一步 - 审查技术方案：
+下一步 - 按所选路径继续：
 {next-step-commands}
 ```
 
@@ -197,18 +200,18 @@ agent-infra-internal task-verify {task-id} plan.completed --artifact {plan-artif
 - [ ] 在 task.md 中记录了 `{plan-artifact}` 为已完成产物
 - [ ] 在工作流进度中标记了 technical-design 为已完成
 - [ ] 追加了 Activity Log 条目到 task.md
-- [ ] 告知了用户这是人工审查检查点
+- [ ] 已按所选路径选择代码实现或方案审查
 - [ ] 已通过统一 helper 渲染已选场景的下一步命令
 
 ## 停止
 
 完成检查清单后，**立即停止**。
-这是一个**强制性的人工审查检查点** —— 用户必须审查并批准计划后才能继续实现。
+完整路径在此进入方案审查；标准路径直接进入代码实现。
 
 ## 注意事项
 
 1. **前置条件**：必须已完成至少一轮需求分析（`analysis.md` 或 `analysis-r{N}.md` 存在）
-2. **人工审查**：这是强制性检查点 —— 不要自动进入实现阶段
+2. **后续阶段**：标准路径进入代码实现，完整路径进入方案审查
 3. **计划质量**：计划应足够具体，使另一个 AI 代理无需额外上下文即可实现
 4. **版本化规则**：首轮方案使用 `plan.md`；后续修订使用 `plan-r{N}.md`
 

package/templates/.agents/skills/review-analysis/SKILL.en.md

@@ -15,6 +15,10 @@ Review the latest analysis artifact and produce `review-analysis.md` or `review-
 
 ## Boundary / Critical Rules
 
+### Path and rework
+
+This stage consumes only the canonical path fact parsed by core from the latest valid analysis artifact; a stage omitted by that path must not create an artifact. When another Changes Requested verdict follows one completed revision-review cycle in the same stage, classify the rework before the next executor artifact and bind it to the finding, source SHA, and stable task-fact digest. A round or filename change is not new evidence.
+
 ### Persisted Report Evidence
 
 Before generating the review report, read `.agents/rules/evidence-reporting.md`. Normal inspection records the command, scope, structured result, actual conclusion, and uncovered parts; findings, blocking conditions, or disputes retain reproducible locations and decisive excerpts, while identity fields remain exact.
@@ -54,7 +58,7 @@ Require `task.md` and at least one analysis artifact: `analysis.md` or `analysis
 
 ### 2. Resolve Review Context
 
-Run `agent-infra-internal task-artifact {task-id} inspect --family review-analysis`. Continue only for `ready`; take `{analysis-artifact}` from `inputs` and `{review-round}` / `{review-artifact}` from `next.round` / `next.name`. Do not scan rounds or construct names in the skill.
+Run `agent-infra-internal task-artifact {task-id} inspect --family review-analysis`. Continue only for `ready`. When `selection.disposition` is `reuse`, reuse `selection.artifact`, do not run started/init or write a new artifact, and continue directly to completion verification and next-step guidance. Otherwise take `{analysis-artifact}` from `inputs` and `{review-round}` / `{review-artifact}` from `next.round` / `next.name`. Do not scan rounds or construct names in the skill.
 
 ### 3. Read Analysis Context
 

package/templates/.agents/skills/review-analysis/SKILL.zh-CN.md

@@ -15,6 +15,10 @@ description: >
 
 ## 行为边界 / 关键规则
 
+### 路径与返工
+
+本阶段只消费核心从最新有效分析产物解析出的规范路径事实；未被所选路径包含的阶段不得创建产物。同阶段完成一次修订—复审后再次收到 Changes Requested 时，必须在下一执行产物前提交绑定 finding、来源 SHA 和稳定任务事实摘要的返工分类；轮次或文件名变化不是新证据。
+
 ### 持久化报告证据
 
 生成审查报告时，先读取 `.agents/rules/evidence-reporting.md`。正常检视记录命令、范围、结构化结果、实际结论和未覆盖部分；finding、阻塞或争议保留可复现位置与决定性摘录，身份字段必须精确保留。
@@ -57,7 +61,7 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ### 2. 解析审查上下文
 
-运行 `agent-infra-internal task-artifact {task-id} inspect --family review-analysis`。仅当结果为 `ready` 时继续；从 `inputs` 取得 `{analysis-artifact}`，从 `next.round` / `next.name` 取得 `{review-round}` / `{review-artifact}`。不得自行扫描轮次或拼装文件名。随后执行 started 事件并复核返回身份。
+运行 `agent-infra-internal task-artifact {task-id} inspect --family review-analysis`。仅当结果为 `ready` 时继续。若 `selection.disposition` 为 `reuse`，复用 `selection.artifact`，不得执行 started、init 或写入新产物，并直接进入完成校验与下一步提示。其他状态从 `inputs` 取得 `{analysis-artifact}`，从 `next.round` / `next.name` 取得 `{review-round}` / `{review-artifact}`；不得自行扫描轮次或拼装文件名。随后执行 started 事件并复核返回身份。
 
 ### 3. 阅读分析上下文
 

package/templates/.agents/skills/review-analysis/reference/report-template.en.md

@@ -147,16 +147,16 @@ Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`
 
 ## State Check
 
-> Record the state-check command, review scope, key result, and uncovered parts; each command starts with `$ `.
+> Record the state-check command, review scope, key result, and uncovered parts.
 > Follow `.agents/rules/evidence-reporting.md`: record review scope, key result, and uncovered parts; do not paste complete successful stdout.
 
 ## Raw Evidence
 
-> Follow `.agents/rules/evidence-reporting.md`: pair each claim with a `$ ` command and proportionate result summary; Blockers, failures, blocking conditions, or disputes require a reproducible command, exact location, and decisive excerpt; a judgment that cannot be reproduced must be downgraded or moved to Self-Doubt.
+> Follow `.agents/rules/evidence-reporting.md`: pair each claim with an executable command and proportionate result summary; Blockers, failures, blocking conditions, or disputes require a reproducible command, exact location, and decisive excerpt; a judgment that cannot be reproduced must be downgraded or moved to Self-Doubt.
 
 - Claim: {verified claim}
 ```text
-$ {command}
+{command}
 {result summary or decisive excerpt}
 ```