feat(agent-workspace): add history follow-up confidence signals

Author: Jacobinwwey

docs/diataxis/en/explanation/agent-conversation-focus-mode-plan.md

@@ -468,10 +468,11 @@ It is conversation-product hardening on top of the shipped shell.
 `M8.30` now adds deterministic follow-up affordances inside expanded history items so the rail can suggest the next bounded action without leaving that same active-atom surface.
 `M8.31` now makes those follow-up suggestions continuity-aware, so older history entries skip already-completed recent steps when a fresher deterministic action exists.
 `M8.32` now explains those freshness-aware suggestions and exposes one secondary alternative, so expanded history items read like bounded decision surfaces instead of opaque action picks.
+`M8.33` now layers confidence signals onto that rationale surface, so each expanded history item exposes rank/freshness/alternative-availability evidence instead of leaving suggestion certainty implicit.
 
 Priority order:
 
-1. deeper continuity explanation quality and confidence signals on top of the shipped rationale-enabled current-atom recent-activity card,
+1. deeper continuity explanation quality around alternative tradeoffs and confidence drift on top of the shipped signal-enabled current-atom recent-activity card,
 2. only then deeper personalization work,
 3. markdown-reader improvements only when they clearly compound the same study loop.
 

docs/diataxis/en/explanation/development-progress-dashboard.md

@@ -18,9 +18,9 @@ Current top priority is not feature-count expansion.
 Current top priority is **conversation-product hardening on top of the already-green backend baseline**:
 
 - keep backend sufficiency as a standing decision gate rather than an active execution lane,
-- keep closing the correction/product/operator gap exposed after `M8.20-M8.32`,
-- treat `M8.23` as the operator-visibility baseline for conversation-memory/correction actions, `M8.24` as the active-atom action-surface baseline, `M8.25` as the active-atom pane-state continuity baseline, `M8.26` as the active-atom study-loop summary baseline, `M8.27` as the active-atom recent-result continuity baseline, `M8.28` as the active-atom result-preview baseline, `M8.29` as the active-atom history-drill-down baseline, `M8.30` as the active-atom history follow-up baseline, `M8.31` as the active-atom history freshness-ranking baseline, and `M8.32` as the active-atom history rationale/alternative baseline,
-- keep the remaining near-term budget on deeper continuity explanation quality instead of reopening backend scope,
+- keep closing the correction/product/operator gap exposed after `M8.20-M8.33`,
+- treat `M8.23` as the operator-visibility baseline for conversation-memory/correction actions, `M8.24` as the active-atom action-surface baseline, `M8.25` as the active-atom pane-state continuity baseline, `M8.26` as the active-atom study-loop summary baseline, `M8.27` as the active-atom recent-result continuity baseline, `M8.28` as the active-atom result-preview baseline, `M8.29` as the active-atom history-drill-down baseline, `M8.30` as the active-atom history follow-up baseline, `M8.31` as the active-atom history freshness-ranking baseline, `M8.32` as the active-atom history rationale/alternative baseline, and `M8.33` as the active-atom history confidence-signal baseline,
+- keep the remaining near-term budget on deeper continuity explanation quality around alternative tradeoffs and confidence drift instead of reopening backend scope,
 - keep remote `main` CI interpretation evidence-based: the latest fully completed `main` workflow set is green, and new pushes should be treated as pending until their workflow set finishes.
 
 ## Current Mainline Snapshot (2026-04-21 M8.18)
@@ -223,6 +223,22 @@ Execution anchor:
   - diagnostics snapshot coverage for stored preview payloads,
   - EN/ZH re-render coverage for localized preview text.
 
+## Latest Mainline Increment (2026-04-21 M8.33 Active-Atom History Confidence Signals)
+
+- Extended the expanded history follow-up surface with explicit confidence evidence:
+  - each suggested next step now exposes deterministic rank/freshness badges instead of treating certainty as implicit,
+  - the rail also shows whether a bounded secondary alternative is still available from the same history context,
+  - confidence copy now distinguishes between clean fresh picks and suggestions that had to skip more recent repeats.
+- Kept the slice frontend-bounded:
+  - no backend route, API contract, persistence model, or capability schema changed,
+  - signal derivation still reuses the local recent-history list plus existing point capabilities and fallback actions.
+- Closed the next post-`M8.32` explanation gap:
+  - operators can now see why a suggestion is trustworthy without mentally reconstructing candidate order,
+  - the card exposes lightweight confidence evidence before deeper personalization or backend work.
+- Expanded regression coverage for:
+  - top-ranked suggestions rendering rank/freshness/alternative badges plus fresh-candidate copy,
+  - stale-step skips rendering adjusted confidence signals and rerendering those signals correctly in EN/ZH.
+
 ## Latest Mainline Increment (2026-04-21 M8.32 Active-Atom History Rationale And Alternatives)
 
 - Upgraded freshness-aware history follow-up suggestions into a more legible continuity surface:
@@ -1342,8 +1358,8 @@ Note: foundation-lane gates now exist on `main`; keep them in the normal verific
 
 1. Treat backend sufficiency as closed-by-default while the gate remains green; do not reopen heavier backend work without new measured pressure.
 2. Treat remote `main` CI as evidence-bound to the latest fully completed workflow set; only reopen CI-triage narrative when a fresh failing run exists.
-3. Make the next planning round about post-`M8.32` bounded conversation-product hardening:
-   - deeper continuity explanation quality and confidence signals on top of the shipped rationale-enabled current-atom recent-activity card before deeper personalization work,
+3. Make the next planning round about post-`M8.33` bounded conversation-product hardening:
+   - deeper continuity explanation quality around alternative tradeoffs and confidence drift on top of the shipped signal-enabled current-atom recent-activity card before deeper personalization work,
    - only then deeper personalization work,
    - markdown-reader improvements only when they compound the same study loop.
 4. Treat notification-threshold governance as closed after `M7.29`; do not plan `M7.30+` unless a materially new operator requirement appears.

docs/diataxis/en/explanation/local-backend-sufficiency-and-escalation-plan.md

@@ -248,7 +248,7 @@ Recommended next product order:
    - the minimum correction / feedback closure is now integrated through explicit next-step guidance on missing managed state,
    - operator-facing visibility for conversation-memory and correction actions is now integrated through persisted diagnostics summary/index counts,
    - stronger agent action surfaces around focus mode and learning path are now integrated through the active-atom quick-action rail, toolbar routing, continuity notes/path-target diagnostics, capability-taxonomy summary cards, the recent-activity history card, localized result-detail previews on that history surface, expandable history drill-down, deterministic history follow-up affordances, continuity-aware freshness ranking for those affordances, and bounded rationale/secondary-alternative rendering,
-   - next prioritize deeper continuity explanation quality and confidence signals on top of the shipped rationale-enabled current-atom recent-activity card before deeper personalization work.
+   - next prioritize deeper continuity explanation quality around alternative tradeoffs and confidence drift on top of the shipped signal-enabled current-atom recent-activity card before deeper personalization work.
 2. markdown-reader improvement:
    - only when it clearly compounds knowledge review or focus-mode study loops.
 

docs/diataxis/zh/explanation/agent-conversation-focus-mode-plan.md

@@ -456,10 +456,11 @@
 `M8.30` 现在又在展开的 history item 内补上确定性的 follow-up affordance，让 rail 在同一块 active-atom surface 内就能建议下一个有界动作。
 `M8.31` 现在又让这条 follow-up suggestion 具备 continuity-aware freshness：只要存在更新鲜的确定性动作，较旧 history item 就会跳过已经完成过的近期步骤。
 `M8.32` 现在又给这条 freshness-aware suggestion 补上原因解释与一个 secondary alternative，让展开后的 history item 更像有界决策面，而不是黑盒动作推荐。
+`M8.33` 现在又在这层 rationale surface 之上补上置信信号，让每条展开的 history item 直接暴露排序 / 新鲜度 / 备选可用性，而不是把建议可信度继续留给操作者自己猜。
 
 优先顺序：
 
-1. 围绕已落地且已带 rationale 的 current-atom recent-activity card 继续补更深的 continuity explanation quality 与 confidence signal，
+1. 围绕已经带 signal 的 current-atom recent-activity card 继续补更深的 alternative tradeoff / confidence drift explanation，
 2. 之后才进入更深的 personalization 工作，
 3. Markdown 阅读器提升只有在能明确复利同一学习闭环时才进入前列。
 

docs/diataxis/zh/explanation/development-progress-dashboard.md

@@ -18,9 +18,9 @@
 当前重心是 **建立在已转绿 backend 基线之上的 conversation-product 加固**：
 
 - 让 backend sufficiency 继续作为常驻 decision gate，而不是继续占用主动执行预算，
-- 持续收口 `M8.20-M8.32` 之后暴露出的 correction / product / operator 缺口，
-- 将 `M8.23` 视作 conversation-memory / correction action 的 operator-visibility 基线，将 `M8.24` 视作当前 atom action-surface 基线，将 `M8.25` 视作当前 atom pane-state continuity 基线，将 `M8.26` 视作当前 atom study-loop summary 基线，将 `M8.27` 视作当前 atom recent-result continuity 基线，将 `M8.28` 视作当前 atom result-preview 基线，将 `M8.29` 视作当前 atom history-drill-down 基线，将 `M8.30` 视作当前 atom history follow-up 基线，将 `M8.31` 视作当前 atom history freshness-ranking 基线，并将 `M8.32` 视作当前 atom history rationale/alternative 基线，
-- 把剩余近端预算继续压在更深的 continuity explanation quality 上，而不是重开 backend 范围，
+- 持续收口 `M8.20-M8.33` 之后暴露出的 correction / product / operator 缺口，
+- 将 `M8.23` 视作 conversation-memory / correction action 的 operator-visibility 基线，将 `M8.24` 视作当前 atom action-surface 基线，将 `M8.25` 视作当前 atom pane-state continuity 基线，将 `M8.26` 视作当前 atom study-loop summary 基线，将 `M8.27` 视作当前 atom recent-result continuity 基线，将 `M8.28` 视作当前 atom result-preview 基线，将 `M8.29` 视作当前 atom history-drill-down 基线，将 `M8.30` 视作当前 atom history follow-up 基线，将 `M8.31` 视作当前 atom history freshness-ranking 基线，将 `M8.32` 视作当前 atom history rationale/alternative 基线，并将 `M8.33` 视作当前 atom history confidence-signal 基线，
+- 把剩余近端预算继续压在围绕 alternative tradeoff / confidence drift 的更深 continuity explanation 上，而不是重开 backend 范围，
 - 远端 `main` CI 解释继续基于代码事实：最近一组已完整结束的主线工作流为绿色，新推送在整组工作流结束前只应视为 pending。
 
 ## 当前主线快照（2026-04-21 M8.18）
@@ -223,6 +223,22 @@
   - diagnostics snapshot 中 preview payload 的可见性，
   - EN/ZH 对 preview 文本的重渲覆盖。
 
+## 主线最新增量（2026-04-21 M8.33 当前 Atom History Confidence Signals）
+
+- 已把展开的 history follow-up surface 再补一层显式置信证据：
+  - 每条建议下一步现在都会暴露确定性的排序 / 新鲜度 badge，而不是把可信度留在黑盒里，
+  - rail 还会明确标出同一段 history 上是否还保留一个有界 secondary alternative，
+  - confidence copy 现在能区分“干净的新鲜选择”和“跳过较新重复动作后的调整选择”。
+- 继续保持 frontend-bounded：
+  - 没有新增 backend route、API contract、持久化模型或 capability schema，
+  - 所有 signal 仍然只复用本地 recent-history 列表、point capability 与 fallback action 推导。
+- 关闭了 post-`M8.32` 的下一处 explanation 缺口：
+  - 操作者现在不用自己脑补 candidate order 才能判断这条建议靠不靠谱，
+  - 在进入更深 personalization 或 backend 工作前，这张卡已经先暴露出轻量但可读的 confidence evidence。
+- 回归覆盖继续扩到：
+  - top-ranked suggestion 的排序 / 新鲜度 / 备选可用 badge 与 fresh-candidate copy，
+  - stale-step skip 的调整后 confidence signal，以及这些 signal 在 EN/ZH 下的稳定 rerender。
+
 ## 主线最新增量（2026-04-21 M8.32 当前 Atom History Rationale And Alternatives）
 
 - 已把 freshness-aware history follow-up suggestion 继续升级为更可读的 continuity surface：
@@ -1345,8 +1361,8 @@ npm test -- src/learning/KnowledgeLearningPlatform.persistence.test.ts --runInBa
 
 1. backend sufficiency 在 gate 继续为绿时默认视为已收口；没有新的 measured pressure 前，不重开更重 backend 工作。
 2. 远端 `main` CI 继续以最近一组已完整结束的工作流为事实依据；只有出现新的失败 run，才重开 CI-triage 叙事。
-3. 下一轮 planning 应只讨论 post-`M8.32` 的有界 conversation-product 加固：
-   - 围绕已落地且已带 rationale 的 current-atom recent-activity card 继续补更深的 continuity explanation quality 与 confidence signal，再进入更深 personalization，
+3. 下一轮 planning 应只讨论 post-`M8.33` 的有界 conversation-product 加固：
+   - 围绕已经带 signal 的 current-atom recent-activity card 继续补更深的 alternative tradeoff / confidence drift explanation，再进入更深 personalization，
    - 之后才进入更深的 personalization 工作，
    - Markdown 阅读器提升只有在能复利同一学习闭环时才进入前列。
 4. notification-threshold 治理链路继续视为在 `M7.29` 后已收口；没有新的强运维需求前，不再规划 `M7.30+`。

docs/diataxis/zh/explanation/local-backend-sufficiency-and-escalation-plan.md

@@ -247,7 +247,7 @@
    - 最小 correction / feedback 收口已经通过“缺失托管状态 -> 显式下一步提示”集成到主线，
    - conversation-memory / correction action 的 operator-facing visibility 已经通过持久化 diagnostics summary / index 计数集成到主线，
    - 围绕 focus mode 与 learning path 的更强 agent action surface 已经通过当前 atom quick-action rail、toolbar routing、continuity note / path-target diagnostics、capability-taxonomy summary card、recent-activity history card、这张卡上的本地化 result-detail preview、可展开的 history drill-down、确定性的 history follow-up affordance、这条 affordance 的 continuity-aware freshness ranking，以及有界的 rationale / secondary-alternative 渲染集成到主线，
-   - 下一步是在更深 personalization 之前，优先围绕已落地且已带 rationale 的 current-atom recent-activity card 继续补更深的 continuity explanation quality 与 confidence signal。
+   - 下一步是在更深 personalization 之前，优先围绕已经带 signal 的 current-atom recent-activity card 继续补更深的 alternative tradeoff / confidence drift explanation。
 2. markdown reader 提升：
    - 只有在它能明确加强知识 review 或 focus-mode 学习闭环时，再提升优先级。