dsh-decision-layer 0.4.0 → 0.5.1

package/README.en.md

@@ -1,10 +1,10 @@
 # dsh-decision-layer
 
-> 中文：[README.md](<README.md>)
+> English | [简体中文](README.md)
 
 `dsh-decision-layer` adds structured, explicitly scoped decisions to the DeepSeek Harness (DSH) agent loop, backed by a pluggable adjudication backend. Dangerous-call gating, output self-check, tool narrowing, and loop prevention hook into the agent loop as automatic interventions.
 
-> **0.4.0 is a preview release.** The plugin works, but how much real value the adjudication interventions add is still being explored — every threshold is an unvalidated heuristic default. Treat it as something to observe, not a proven guarantee of impact. See [ROADMAP.md](<ROADMAP.md>) for scope and progress.
+> **0.5.1 is a preview release.** The plugin works, but how much real value the adjudication interventions add is still being explored — every threshold is an unvalidated heuristic default. Treat it as something to observe, not a proven guarantee of impact. See [ROADMAP.md](<ROADMAP.md>) for scope and progress.
 
 ## Installation
 
@@ -36,14 +36,17 @@ Restart `dsh web` and refresh after installing or updating: the host and client
 
 - **Manual verdicts** — `decision_evaluate` and the `decision-layer` skill submit `noul`, `score`, or `choice` questions; `decision_check_connection` tests connectivity. Neither counts as an automatic decision or changes agent behavior.
 - **Configurable backend** — defaults to `https://api.typesafe.ai` and `jev-latest`, with per-field URL/key/model overrides under the same protocol. No request without a key. Custom HTTP endpoints require address-bound plaintext-risk confirmation.
-- **Dangerous-call gate** — before a destructive tool call, a redacted summary asks the backend for allow/ask/deny. A model allow only downgrades to native host approval; a deny is enforced monotonically; backend failure, low confidence, or invalid results defer to host approval. Rules are configurable.
+- **Dangerous-call gate** — before a destructive tool call, a redacted summary asks the backend for a verdict, using a **two-tier model**: only a high-confidence deny is enforced monotonically through the guard to block that call; every other case (a high-confidence allow/ask, low confidence, backend failure, or an invalid result) does not intervene and runs the host's original path. The gate is a safety net that only blocks when the model is confident of danger — it never authorizes on the host's behalf or downgrades approval. Rules are configurable.
 - **Output self-check** — scores the final output at turn end against a rubric (0–2, a probability-weighted mean across levels, so it can be fractional). Observe-only by default; an opt-in low-score re-prompt appends one prompt on your behalf when the score is low and the model is confident, at most once per turn.
+- **Task-completion review** — when the user spells out multiple delivery conditions (numbered / bulleted / multi-command), each is judged satisfied / unsatisfied / insufficient-evidence via a choice before turn end, with tool evidence primary and self-reported replies not counting as evidence; extraction is deterministic and never infers implicit expectations. Observe-only by default, steer configurable, coexisting with self-check and tracked as separate metrics.
+- **Output-quality trend alert** — a read-only reminder built on self-check data. After several consecutive high-confidence low scores, the trigger button's icon shifts from grey to amber to red, with a hover hint that the task may have grown harder or the model may be fluctuating and suggesting a prompt tweak or model swap. Purely a hint, never driving automatic intervention; the three thresholds (high-confidence bar / consecutive rounds / severe tier) are configurable (defaults 0.6 / 3 / 5), conservative, and pending real-data calibration.
 - **Tool narrowing** — at turn start, a noul judges each optional tool's relevance to the task and drops the ones not needed (relevance probability below the drop threshold, default 0.3, configurable), intersecting the host-allowed set and never expanding it. Enforced by default; switch to observe-only to log without changing the tool set. Three safeguards: core tools (read/write/edit/shell/search/todos, plus agent meta-abilities such as asking the user, goals, skills, delivery, background jobs, and teamwork) are always kept and never judged; more optional tools than the candidate cap (default 20, configurable) falls back to observe only; fewer than 5 tools remaining is treated as untrustworthy and skipped. Tools matching a **keep-prefix** allowlist (defaults to `mcp__openviking` and `team_task_`) are also always kept and never judged — good for resident, on-demand tools like memory, retrieval, and teamwork.
 - **Loop guard** — deterministic and backend-free; denies the same call repeated consecutively past a threshold. Always on and outside the per-feature switches.
 - **Session panel** — a dock trigger below the composer opens the panel with automatic-decision metrics (attempts, fallbacks, model suggestions vs actual outcomes), the master switch, and the decision log, with an empty state before any automatic decision. The master switch pauses only automatic intervention.
+- **Decision-analysis view** — an in-session "Decision analysis" tab (`conversation.view`, alongside chat and trajectory, naturally scoped per session) that reads the persisted log read-only and shows a process profile (per-point attempts and outcome distribution, mean self-check score), a quality-trend threshold backtest, and a decision-accuracy summary, and lets you rate each decision correct / wrong / unsure. Ratings share one source with the intervention panel: a rating on either surface writes to the same log, keyed by decision id, latest wins. Read-only over logs, append-only for annotations; it changes no decision behavior.
 - **Per-feature switches** — the config page has an independent switch for the danger gate, output self-check, and tool narrowing, all on by default; turning one off drops that intervention. The loop guard is not covered by these switches.
 - **Persisted decision log** — beyond the in-memory panel, decisions are written in full per session to `~/.config/dsh-decision-layer/logs` for research. Files roll by running-instance port and date (`decisions-<port>-YYYY-MM-DD.jsonl`), are batched, and retained for 30 days. Writing is best-effort: a failed flush drops that batch and never breaks the decision path.
 
 ## Safety boundary and development
 
-Automatic intervention only subtracts: the gate only denies, narrowing only removes tools, and neither grants new permissions. The gate defers to native DSH approval on backend failure rather than allowing; self-check, narrowing, and loop-guard errors skip intervention. The redacted summary sent to the backend carries only tool name and command/path with secret redaction — never file content. Node.js `>=20.11`; `npm test` and `npm run build:client` run local checks. Rebuild and commit `lib/client.js` with any client change. 0.4.0 is a preview: the interventions work, but their real value and thresholds are still being explored — feedback on misjudgments and feel observed in the decision log is welcome.
+Automatic intervention only subtracts: the gate only denies, narrowing only removes tools, and neither grants new permissions. The gate defers to native DSH approval on backend failure rather than allowing; self-check, narrowing, and loop-guard errors skip intervention. The redacted summary sent to the backend carries only tool name and command/path with secret redaction — never file content. Node.js `>=20.11`; `npm test` and `npm run build:client` run local checks. Rebuild and commit `lib/client.js` with any client change. 0.5.1 is a preview: the interventions work, but their real value and thresholds are still being explored — feedback on misjudgments and feel observed in the decision log is welcome.

package/README.md

@@ -1,10 +1,10 @@
 # dsh-decision-layer
 
-> English: [README.en.md](<README.en.md>)
+> [English](README.en.md) | 简体中文
 
 DeepSeek Harness（DSH）的结构化裁决插件。它把有明确判断标准的问题交给同协议的裁决后端，供 agent 在需要时使用，并在 agent loop 上接入危险门控、产出自检、工具收窄和防循环等自动介入。
 
-> **0.4.0 是体验版。** 插件功能已可用，但裁决介入能带来多少实际价值仍在探索中——各决策点的阈值都是未经验证的启发式默认值，建议先以观察心态体验，别当成经过验证的效果保证。功能与后续进度以 [ROADMAP.md](<ROADMAP.md>) 为准。
+> **0.5.1 是体验版。** 插件功能已可用，但裁决介入能带来多少实际价值仍在探索中——各决策点的阈值都是未经验证的启发式默认值，建议先以观察心态体验，别当成经过验证的效果保证。功能与后续进度以 [ROADMAP.md](<ROADMAP.md>) 为准。
 
 ## 安装
 
@@ -36,18 +36,21 @@ dsh plugin --profile web add file:/绝对路径/dsh-decision-layer
 
 - **手动裁决**：`decision_evaluate` 工具与 `decision-layer` skill 支持显式提交 `noul`、`score`、`choice` 问题，`decision_check_connection` 做连通测试。手动调用和连通测试不计入自动裁决指标，也不改变 agent 行为。
 - **可配置后端**：默认 `https://api.typesafe.ai`、`jev-latest`，URL、Key、model 可逐字段覆盖；仅支持相同的结构化裁决协议。未配置 Key 时不发送请求。自定义 HTTP 地址需针对实际目标确认明文传输风险，地址变更须重新确认。
-- **危险门控**：破坏性工具调用执行前用脱敏摘要请后端给放行 / 询问 / 拒绝建议。模型建议不能授予宿主未允许的权限——放行只降级为宿主原生审批，拒绝经监控守卫单调生效；后端失败、低置信或响应不合法时交回宿主审批。危险规则可增删配置。
+- **危险门控**：破坏性工具调用执行前用脱敏摘要请后端裁决，采用**两档模型**——只有模型高置信判定「拒绝」时才经监控守卫单调拦截该调用；其余情况（高置信放行 / 询问、低置信、后端失败或响应不合法）一律不介入，按宿主原路径执行。门控只做「确信危险才拦」的安全网，不替宿主授权、不降级审批。危险规则可增删配置。
 - **产出自检**：回合结束用评分量表给最终产出打分（0–2，按各档位概率加权，可能是小数）。默认只提示、不打断；可开启「低分补完」，得分偏低且模型有把握时以你的名义追加一次补完提示，同一回合最多补一次。
+- **任务完成核对**：当用户明确列出多个交付条件（编号 / 项目符号 / 多命令）时，回合结束前用单选逐项判定「已满足 / 未满足 / 证据不足」，工具证据优先、回复自述不算证据；确定性提取、不推断隐含期望。默认只观察、可配 steer，与产出自检并存、指标分列。
+- **产出质量趋势告警**：建在自检数据上的只读提醒。连续多次高置信低分时，把输入框旁触发按钮的图标从灰变橙、变红，hover 提示可能是任务变难或模型波动、建议调整 prompt 或更换模型。纯提示、不驱动自动干预；高置信门槛 / 连续轮数 / 严重档三个阈值可配（默认 0.6 / 3 / 5），偏保守、待实测校准。
 - **工具收窄**：回合开始时用 noul 逐个判断可选工具与本轮任务的相关性，摘掉用不上的（相关性概率低于摘除阈值，默认 0.3、可配），只在宿主已允许的集合内取交集、不扩权。默认真正生效，可切到「仅观察」只记录不改工具集。三重保护：核心工具（读写、编辑、Shell、检索、待办，以及问用户、目标、技能、交付、后台作业、协作等 agent 元能力）始终保留、不参与判定；可选工具超过候选上限（默认 20，可配）时自动降为仅观察；保留下来不足 5 个时视为判定不可信、跳过。**保留工具前缀**白名单里的工具（默认含 `mcp__openviking`、`team_task_`）也始终保留、不参与判定，适合记忆 / 检索、协作这类常驻、按需触发的工具。
 - **防循环**：确定性判断，不走后端；同一调用连续重复超过阈值即拒绝，打断死循环。始终生效，不在决策点开关范围内。
 - **会话面板**：输入框下方的 dock 触发器弹出面板，展示自动裁决指标（评估数、失败回退、模型建议与实际结果分列）、会话总开关和决策日志；无自动裁决时显示空态。总开关关闭只暂停自动介入，不影响手动裁决。
+- **决策分析页**：会话内「决策分析」tab（`conversation.view`，与对话/轨迹平级、天然按会话隔离），基于已落盘日志做只读聚合，展示过程画像（各决策点触发数与结果分布、自检平均分）、质量趋势阈值回测、判断准确度汇总，并可对每条决策标注「判对 / 判错 / 说不准」。标注与介入面板同源：任一处标注都写入同一份日志、按决策 id 关联、取最新。只读日志、只追加标注，不改任何决策行为。
 - **决策点开关**：详情页配置里，危险门控、产出自检、工具收窄各有独立开关，默认全开；关掉某个决策点就不再对应地介入。防循环不在此范围。
 - **决策日志落盘**：决策记录在内存面板之外，还按会话全量落盘到 `~/.config/dsh-decision-layer/logs`，供研究回看。文件按运行实例端口和日期滚动切分（`decisions-<端口>-YYYY-MM-DD.jsonl`），批量写入，保留 30 天。写盘为尽力而为，失败只丢当批、不影响决策路径。
 
 ## 安全边界
 
-自动介入只减不增：门控只拒绝、收窄只删工具，都不给 agent 新权限。危险门控在后端失败或无法可靠交接时交回 DSH 原生审批，不因裁决故障直接放行；自检、收窄与防循环异常则跳过介入。发送到后端的危险摘要只含工具名与命令 / 路径并对疑似密钥脱敏，不含文件内容。
+自动介入只减不增：门控只拒绝、收窄只删工具，都不给 agent 新权限。危险门控采用两档模型，只在模型高置信判定拒绝时拦截；后端失败、低置信或响应不合法时一律不介入、按原路径执行，不因裁决故障阻断，也不替宿主放行。自检、收窄与防循环异常则跳过介入。发送到后端的危险摘要只含工具名与命令 / 路径并对疑似密钥脱敏，不含文件内容。
 
 ## 开发
 
-服务端使用 Node.js `>=20.11`（`.mjs`，无需构建）；客户端用 TypeScript + esbuild 构建。`npm test` 跑本地测试，`npm run build:client` 生成 `lib/client.js`。改动客户端后需重建并连同 `lib/client.js` 一起提交，否则 GitHub 安装拿到的是旧 bundle。0.4.0 为体验版：介入能力已可用，但实际价值与阈值仍在探索，欢迎反馈决策日志观察到的误判与体感。
+服务端使用 Node.js `>=20.11`（`.mjs`，无需构建）；客户端用 TypeScript + esbuild 构建。`npm test` 跑本地测试，`npm run build:client` 生成 `lib/client.js`。改动客户端后需重建并连同 `lib/client.js` 一起提交，否则 GitHub 安装拿到的是旧 bundle。0.5.1 为体验版：介入能力已可用，但实际价值与阈值仍在探索，欢迎反馈决策日志观察到的误判与体感。