feat(operator): surface managed conversation diagnostics

Author: Jacobinwwey

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

@@ -454,13 +454,13 @@ This delivery path already replaced "generic conversation enhancement" and most
 The immediate remaining priority is no longer basic focus/path shell delivery.
 It is conversation-product hardening on top of the shipped shell.
 `M8.22` already closed the minimum correction-flow gap by turning missing managed-memory state into explicit next-step guidance.
+`M8.23` now exposes operator-facing diagnostics counts for managed conversation actions and missing correction state.
 
 Priority order:
 
-1. operator-facing visibility for conversation-memory and correction actions,
-2. stronger focus-mode / learning-path action surfaces tied to the active conversation atom,
-3. only then deeper personalization work,
-4. markdown-reader improvements only when they clearly compound the same study loop.
+1. stronger focus-mode / learning-path action surfaces tied to the active conversation atom,
+2. only then deeper personalization work,
+3. markdown-reader improvements only when they clearly compound the same study loop.
 
 ## Related Pages
 

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-M8.22`,
-- treat `M8.22` as the minimum correction-flow closure baseline and move the remaining near-term budget into operator-facing visibility and stronger focus/path action surfaces,
-- keep remote `main` CI interpretation evidence-based: the latest fully completed `main` workflow set (`3a1926a`) is green, and the newer `e73b5c6` push remains non-red with `Migration Gates` still running at refresh time.
+- keep closing the correction/product/operator gap exposed after `M8.20-M8.23`,
+- treat `M8.23` as the operator-visibility baseline for conversation-memory and correction actions and move the remaining near-term budget into stronger focus/path action surfaces,
+- 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)
 
@@ -120,6 +120,22 @@ Execution anchor:
 - Expanded regression coverage for:
   - runtime managed-memory state messaging with explicit next-step guidance.
 
+## Latest Mainline Increment (2026-04-21 M8.23 Operator Visibility for Managed Conversation Actions)
+
+- Upgraded persisted agent-workspace diagnostics from generic memory-policy counts to operator-usable conversation-memory visibility:
+  - runtime diagnostics now retain managed conversation action identity for `inspect_managed_memory_state`, `write_memory_note`, `record_memory_correction`, and `evict_memory_note`,
+  - targeted managed-state results now retain matched vs missing `note` / `correction` key classes inside the diagnostics report.
+- Kept the slice bounded to the existing diagnostics surface:
+  - no new operator route or backend persistence model was introduced,
+  - `latest` / `index` summaries now expose compact managed-conversation counts by reusing the current diagnostics report pipeline.
+- Operator-facing reports can now answer the previously missing questions:
+  - whether correction actions are actually being executed,
+  - whether targeted managed-state reads are still surfacing missing correction state,
+  - whether note/correction actions are visible separately instead of being collapsed under generic `apply_memory_policy`.
+- Expanded regression coverage for:
+  - runtime managed-conversation diagnostics summary/index export,
+  - server-side diagnostics metadata summary extraction for managed conversation actions.
+
 ## Latest Mainline Increment (2026-04-14 M1 Baseline)
 
 - Added first `AgentConversationAPI` contract surface:

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

@@ -245,8 +245,8 @@ Recommended next product order:
 1. conversation-product hardening:
    - extend explicit conversation memory APIs beyond the current snapshot/read/managed-key inspection and note/correction/eviction surface,
    - the minimum correction / feedback closure is now integrated through explicit next-step guidance on missing managed state,
-   - next add operator-facing visibility for conversation-memory and correction actions,
-   - then harden stronger agent action surfaces around focus mode and learning path.
+   - operator-facing visibility for conversation-memory and correction actions is now integrated through persisted diagnostics summary/index counts,
+   - next harden stronger agent action surfaces around focus mode and learning path.
 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

@@ -442,13 +442,13 @@
 当前第一优先级已经不再是基础 focus/path 壳层交付，
 而是建立在该壳层之上的 conversation-product 加固。
 `M8.22` 已经通过“把缺失托管记忆状态转成显式下一步提示”补上最小 correction-flow 缺口。
+`M8.23` 现在又补上了托管对话动作与缺失 correction state 的 operator-facing diagnostics 计数。
 
 优先顺序：
 
-1. 增加 conversation-memory / correction action 的 operator-facing visibility，
-2. 继续加固绑定当前会话 atom 的 focus-mode / learning-path action surface，
-3. 之后才进入更深的 personalization 工作，
-4. 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。
+1. 继续加固绑定当前会话 atom 的 focus-mode / learning-path action surface，
+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。
 
 ## 关联页面
 

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-M8.22` 之后暴露出的 correction / product / operator 缺口，
-- 将 `M8.22` 视作最小 correction-flow closure 基线，把剩余近端预算转向 operator-facing visibility 与更强的 focus/path action surface，
-- 远端 `main` CI 解释继续基于代码事实：最近一组已完整结束的 `main` 工作流（`3a1926a`）为绿色，而更新的 `e73b5c6` 推送在刷新时也保持非红，仅 `Migration Gates` 仍在执行。
+- 持续收口 `M8.20-M8.23` 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，把剩余近端预算转向更强的 focus/path action surface，
+- 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）
 
@@ -120,6 +120,22 @@
 - 回归覆盖同步扩展到：
   - runtime 托管记忆状态消息对显式下一步提示的断言。
 
+## 主线最新增量（2026-04-21 M8.23 托管对话动作的 Operator Visibility）
+
+- 已把持久化 agent-workspace diagnostics 从泛化 memory-policy 计数升级为 operator 可用的 conversation-memory 可见性：
+  - runtime diagnostics 现在会保留 `inspect_managed_memory_state`、`write_memory_note`、`record_memory_correction`、`evict_memory_note` 的动作身份，
+  - 定向托管状态读取结果也会在 diagnostics report 中保留 `note` / `correction` 的 matched / missing 键类。
+- 范围继续保持收敛，复用现有 diagnostics surface：
+  - 没有新增 operator 路由，也没有新增 backend 持久化模型，
+  - `latest` / `index` 摘要现在只是在既有 diagnostics report pipeline 上补出紧凑的 managed-conversation 计数。
+- 这让 operator report 能回答此前缺失的问题：
+  - correction action 是否真的被执行，
+  - 定向托管状态读取是否仍在暴露缺失 correction state，
+  - note / correction action 是否能从泛化的 `apply_memory_policy` 统计里拆分出来。
+- 回归覆盖同步扩展到：
+  - runtime managed-conversation diagnostics summary / index 导出，
+  - server 侧 diagnostics metadata summary 对 managed conversation action 的提取断言。
+
 ## 主线最新增量（2026-04-14 M1 基线）
 
 - 已新增第一版 `AgentConversationAPI` 合同面：

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

@@ -244,8 +244,8 @@
 1. conversation-product 加固：
    - 在当前 snapshot/read/托管 key 检查与 note/correction/eviction 能力之上继续扩展显式 conversation memory API，
    - 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，
-   - 下一步补 conversation-memory / correction action 的 operator-facing visibility，
-   - 之后再继续加固围绕 focus mode 与 learning path 的 agent action surface。
+   - 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，
+   - 下一步继续加固围绕 focus mode 与 learning path 的 agent action surface。
 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。