@zq-silk/yui 2.16.0 → 2.17.0

package/docs/testing/verification-levels.md

@@ -53,12 +53,12 @@ is required.
 Both include `test/core` and `test/platform`. For an already built checkout,
 `npm run test:business` runs only `test/core` and `npm run test:platform` runs
 only `test/platform`; neither rebuilds. CI owns one explicit build per job.
-The stable suite owns current storage 1.21 and its declared 1.0 through 1.20 minor
+The stable suite owns current storage 1.22 and its declared 1.0 through 1.21 minor
 transition. It contains no undeclared historical format compatibility path.
 
 Current coverage includes:
 
-1. Fresh storage 1.21, exact schema/record validation, no initialization over
+1. Fresh storage 1.22, exact schema/record validation, no initialization over
    unknown data, and rejection of old integer formats without mutation.
 2. Exact-version staging, mismatched-target refusal, same-major contiguous
    minor preflight, explicit maintenance-owner identity across handover, and

package/docs/testing/verification-levels.zh-CN.md

@@ -39,12 +39,12 @@ Yui 是一个单用户本地产品。永久验证保护关键的 happy path 和
 两者均包含 `test/core` 和 `test/platform`。已构建的 checkout 可分别运行
 `npm run test:business` 与 `npm run test:platform`，它们不会再次构建。
 CI 每个作业只显式构建一次。
-稳定套件维护当前存储 1.21 和明确声明的 1.0 至 1.20 连续小版本迁移，
+稳定套件维护当前存储 1.22 和明确声明的 1.0 至 1.21 连续小版本迁移，
 不包含未声明的历史格式兼容路径。
 
 当前覆盖包括：
 
-1. 新建存储 1.21、精确结构与记录校验、禁止覆盖未知数据库、无修改拒绝旧整数格式。
+1. 新建存储 1.22、精确结构与记录校验、禁止覆盖未知数据库、无修改拒绝旧整数格式。
 2. 精确版本暂存、目标不匹配拒绝、同主版本连续小版本预检、交接锁显式所有者，
    以及恢复时核对捕获的协议和存储身份，不接受缺失字段。
 3. 持久 Task／Message／Decision 上下文、Draft 激活权威、mailbox 认领、

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@zq-silk/yui",
-  "version": "2.16.0",
+  "version": "2.17.0",
   "description": "Local control plane for long-running native agent CLI sessions backed by tmux.",
   "license": "MIT",
   "private": false,

package/skills/yui-leader/VERSION

@@ -1 +1 @@
-6
+7

package/skills/yui-leader/references/execution.md

@@ -303,12 +303,20 @@ authority. Never invent authorization, impersonate Operator, or modify the core
 
 ## Validate and make the review judgment
 
-Prepare useful evidence, not a documentation gate. Supply or reference the
-effective goals/non-goals and decisions, independently grounded expected
-behavior, key user paths/constraints, contract entry points and relevant callers.
-Keep three things distinct: a behavioral scenario and its expectation, an
-executable test reference, and an actual result with candidate/environment/
-command. Disclose real gaps rather than deriving acceptance from current code.
+Prepare useful evidence, not a documentation gate. From effective requirements,
+non-goals and decisions, distill the few observable behavioral constraints that
+matter to this change, with independently grounded expectations. Do not infer
+correctness from the candidate or its mocks.
+
+For material cross-layer or asynchronous risks, trace a short real path in the
+exact candidate: entry -> actual consumers -> relevant waits/atomic commit
+boundaries -> observable result and failure/recovery consequences. Point to
+candidate code or existing documents, not just module names or a coverage claim.
+Use it to expose where the same constraint must hold across boundaries; do not
+enumerate every entry or generate a combination matrix. Keep three things
+distinct: constraints/scenarios and expectations, executable test references,
+and actual results with candidate/environment/command. Name material unverified
+boundaries; a test reference alone is not a passing result.
 
 Small tasks can reference existing materials directly. For complex tasks, put a
 short review index in Task artifacts and its commit-pinned reference in Brief.
@@ -380,8 +388,11 @@ main synthesis through its exact AgentRun, preserving its selected source snapsh
 A Worker or Reviewer AgentRun result is evidence, not acceptance. Inspect the
 result, diff, checks, and current Candidate before deciding.
 
-Group confirmed findings by root cause and repair other reachable instances
-within scope together. For ordinary full re-review, preserve the current complete
+Group confirmed findings by root cause. Use the traced paths to check other
+reachable consumers/boundaries within scope and repair affected instances
+together, not just the reported checkpoint. Refresh the short material index
+and repair evidence where they changed, without accumulating round-by-round
+history. For ordinary full re-review, preserve the current complete
 candidate and requirements; add repair delta, prior finding dispositions and
 still-valid evidence. Delta is an attention aid, not the full-review boundary.
 Do not conflate this with an explicitly authorized equivalence Delta Recheck.

package/skills/yui-reviewer/SKILL.md

@@ -111,9 +111,20 @@ contracts, state/data invariants, failure and partial recovery, authorization,
 and whether verification tests the actual contract. Multiple perspectives do
 not require multiple Agents or every perspective on every task.
 
+Use the Leader's real-path material as navigation and risk hints, not a scope
+ceiling or proof of completeness. Check its links against the frozen candidate
+and independently derive scenarios. For relevant cross-layer/asynchronous paths,
+follow actual consumers and compare the same constraint before/after key waits
+and atomic commits, through downstream error classification and recovery.
+Inspect other reachable consumers when a shared assumption may fail elsewhere;
+neither a module list nor a passing mock establishes end-to-end behavior.
+
 Turn applicable perspectives into concrete scenarios, expected behavior and
-evidence. Challenge important assumptions with the smallest reachable
-counterexample; check normal controls and non-goals too. A shared assumption
+evidence. Distinguish independently grounded expectations, executable test
+references, and actual results for the stated candidate/environment; retain
+material unverified boundaries as gaps. Challenge important assumptions with
+the smallest reachable counterexample; check normal controls and non-goals too.
+A shared assumption
 between a mock and implementation is not independent confirmation. Reuse valid
 checks; do not run external-resource validation without its exact authorization.
 Stop neither at the changed lines nor after finding a few defects.

package/skills/yui-reviewer/VERSION

@@ -1 +1 @@
-4
+5