dsh-continual-evolve 0.7.1 → 0.7.2

package/README.md

@@ -7,7 +7,7 @@
 [![CI](https://github.com/ZK-Andy/dsh-continual-evolve/actions/workflows/ci.yml/badge.svg)](https://github.com/ZK-Andy/dsh-continual-evolve/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
 [![Node](https://img.shields.io/badge/node-%5E22.19%20%7C%7C%20%3E%3D24-339933)](package.json)
-[![Tests](https://img.shields.io/badge/tests-665%20passing-brightgreen)]()
+[![Tests](https://img.shields.io/badge/tests-675%20passing-brightgreen)]()
 
 Continual self-evolution for [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness): a versioned, auditable, rollback-safe harness state layer — prompt notes, memories, skills, subagent specs — refined from session trajectories.
 
@@ -25,7 +25,7 @@ Agents accumulate reusable experience (repeated failures, durable facts, reusabl
 
 ## How it works
 
-1. **Sediment** — the model creates entries via `evolve_add`, or the automatic review gate proposes them from the session trajectory (turn-interval + compaction checkpoints).
+1. **Sediment** — the model creates entries via `evolve_add`, or the automatic review gate proposes them from incremental snapshots captured after successful turns (plus compaction checkpoints).
 2. **Guard** — code-enforced validation: edit schema, blast-radius/scope coherence, and the promotion policy (project-scoped markers, thin content, near-duplicate detection, credential screening keep the global store clean — secrets are rejected at every write sink, including mount materialization). Global creates that near-duplicate an existing entry are rejected at write time (≥0.8 similarity); moderate overlaps carry a `conflictHint` for later consolidation.
 3. **Approve** — global and project writes require explicit human approval; local-fate proposals are consulted before they land.
 4. **Apply & inject** — atomic apply with snapshot + audit event. Prompt notes and delegation specs inject into the system prompt (capped, relevance-ranked, contradicted entries demoted, zero tokens when empty); memories/skills appear as a relevance-ordered capped directory index (`- [memory:type:id] title` hooks, full text one `evolve_list` away).
@@ -77,8 +77,8 @@ Injection shape: prompt notes and delegation specs inject with content (≤6/kin
 | Key | Default | Meaning |
 |---|---|---|
 | `baseDir` | resolved DSH home | root for the `evolve/` stores |
-| `autoReview` | `false` | enable the automatic review gate |
-| `reviewIntervalTurns` | `6` | gate cadence on the turn-interval path |
+| `autoReview` | `false` | initial automatic-review default when no runtime switch exists; the listener is always registered |
+| `reviewIntervalTurns` | `6` | legacy local-fate cadence fallback; successful-turn review no longer waits for this interval |
 | `maxReviewInputChars` | `40000` | trajectory slice handed to the gate |
 | `reviewBudgetTokens` | `4096` | output budget for the gate call |
 | `notifyOnAutoReview` | `true` | visible follow-up notice after an applied gate run |
@@ -109,11 +109,18 @@ Example profile patch:
     reviewIntervalTurns: 6
 ```
 
+The listener is registered even when `autoReview` is `false`. Use `/evolve resume`
+to enable successful-turn snapshots immediately, `/evolve pause` to suppress new
+snapshots and fate/model work, and `/evolve status` to inspect the configured
+default plus the current runtime state. The runtime switch is stored in
+`evolve/runtime.json`; manual `evolve_*` tools and `/evolve` commands are not
+paused.
+
 ## Development
 
 ```bash
 pnpm install && pnpm build   # deps + tsc -> lib/
-pnpm test                    # vitest (665 tests)
+pnpm test                    # vitest (675 tests)
 pnpm test:coverage           # v8 coverage, thresholds enforced in CI
 pnpm lint                    # oxlint src test
 ```
@@ -122,7 +129,7 @@ Project layout:
 
 ```
 ├── src/                   # engine, tools, commands, gate, fate, benchmark, injection + token usage…
-├── test/                  # vitest suites (41 files)
+├── test/                  # vitest suites (43 files)
 ├── lib/                   # build output (tsc)
 ├── docs/
 │   ├── design.md          # full design doc (hardening matrix)

package/README.zh.md

@@ -7,7 +7,7 @@
 [![CI](https://github.com/ZK-Andy/dsh-continual-evolve/actions/workflows/ci.yml/badge.svg)](https://github.com/ZK-Andy/dsh-continual-evolve/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
 [![Node](https://img.shields.io/badge/node-%5E22.19%20%7C%7C%20%3E%3D24-339933)](package.json)
-[![Tests](https://img.shields.io/badge/tests-665%20passing-brightgreen)]()
+[![Tests](https://img.shields.io/badge/tests-675%20passing-brightgreen)]()
 
 [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness)（`dsh`）的持续自进化插件：一套**版本化、可审计、可回滚**的 harness 状态层——提示词补充、记忆、技能、子代理规格——从会话轨迹中沉淀而来。
 
@@ -25,7 +25,7 @@ Agent 在每个会话里积累可复用经验（重复失败、持久事实、
 
 ## 工作原理
 
-1. **沉淀**——模型经 `evolve_add` 创建条目，或自动 review 门禁从会话轨迹提议（回合间隔 + 压缩检查点）。
+1. **沉淀**——模型经 `evolve_add` 创建条目，或自动 review 门禁从成功回合后的增量 snapshot（以及压缩检查点）提议。
 2. **守卫**——代码强制校验：编辑 schema、blast-radius 与作用域一致性、晋升政策（项目专属标记 / 过薄内容 / 近似重复检测 / 凭据筛查保持全局库干净——密钥类内容在所有写入出口被拒，含 mount 物化）。全局 create 与既有条目高度相似（≥0.8）时写入即拒；中等重叠带 `conflictHint` 供后续合并。
 3. **审批**——全局与项目写入需明确人工批准；local 归宿提议先征询后落地。
 4. **应用与注入**——原子应用带快照与审计事件。prompt 补充与委派规格注入系统提示词（封顶、按相关性排序、被证伪条目降权、空 store 零 token）；memory/skill 以按相关性排序的目录索引出现（`[memory:type:id] 标题`钩子）。
@@ -77,8 +77,8 @@ dsh plugin add ZK-Andy/dsh-continual-evolve
 | 键 | 默认 | 含义 |
 |---|---|---|
 | `baseDir` | 解析后的 DSH home | `evolve/` 存储根目录 |
-| `autoReview` | `false` | 启用自动 review 门禁 |
-| `reviewIntervalTurns` | `6` | 回合间隔路径的门禁节奏 |
+| `autoReview` | `false` | 没有 runtime 开关时的自动 review 初始默认；监听器始终注册 |
+| `reviewIntervalTurns` | `6` | local-fate 的兼容节奏；成功回合 review 不再等待这个间隔 |
 | `maxReviewInputChars` | `40000` | 交给门禁的轨迹切片 |
 | `reviewBudgetTokens` | `4096` | 门禁调用输出预算 |
 | `notifyOnAutoReview` | `true` | 门禁应用后发可见跟进通知 |
@@ -109,11 +109,13 @@ profile patch 示例：
     reviewIntervalTurns: 6
 ```
 
+即使 `autoReview` 为 `false`，监听器也会注册。使用 `/evolve resume` 立即开启成功回合 snapshot，使用 `/evolve pause` 抑制新 snapshot、fate 和模型调用，使用 `/evolve status` 查看配置默认值与运行时状态。开关保存在 `evolve/runtime.json`；手动 `evolve_*` 工具和 `/evolve` 命令不受暂停影响。
+
 ## 开发
 
 ```bash
 pnpm install && pnpm build   # 依赖 + tsc -> lib/
-pnpm test                    # vitest（665 例）
+pnpm test                    # vitest（675 例）
 pnpm test:coverage           # v8 覆盖率，CI 强制阈值
 pnpm lint                    # oxlint src test
 ```
@@ -122,7 +124,7 @@ pnpm lint                    # oxlint src test
 
 ```
 ├── src/                   # 引擎、工具、命令、门禁、fate、benchmark、注入 + token 用量…
-├── test/                  # vitest 测试套件（41 个文件）
+├── test/                  # vitest 测试套件（43 个文件）
 ├── lib/                   # 构建产物（tsc）
 ├── docs/
 │   ├── design.md          # 完整设计文档（硬化矩阵）

package/lib/auto.d.ts

@@ -6,7 +6,10 @@ import { type AutoRefineReason } from "./review.js";
 import type { PromotionPolicy } from "./promotion.js";
 import type { PlannerPrefixCacheMode } from "./prefix-cache.js";
 export interface AutoReviewConfig {
+    /** Legacy fate cadence; successful turns are no longer gated by this value. */
     intervalTurns: number;
+    /** Initial runtime state when no runtime.json exists. */
+    enabledByDefault?: boolean;
     maxInputChars: number;
     budgetTokens: number;
     /** Queue a visible follow-up notice after an approved, applied gate run. */
@@ -18,10 +21,9 @@ export interface AutoReviewConfig {
      */
     localFate: boolean;
     /**
-     * Minimum turns between local-fate assessments on the turn-interval path
-     * (compaction is unconditional). Independent of the review cadence so
-     * goal-driven sessions (gate every round) do not pay an assessment per
-     * round.
+     * Minimum turns between local-fate assessments on the successful-turn path
+     * (compaction is unconditional). Independent of snapshot review cadence so
+     * eligible turns do not pay an assessment every round.
      */
     fateIntervalTurns: number;
     /**
@@ -68,6 +70,10 @@ export interface AutoReviewConfig {
 }
 export interface GateState {
     turns: number;
+    /** Latest successful turn boundary seen by the listener. */
+    completedTurn: number;
+    /** Latest turn whose snapshot acquisition was reserved. */
+    lastSnapshotTurn: number;
     lastReviewAt: number;
     running: boolean;
     /**
@@ -98,7 +104,7 @@ export interface ReviewRecord {
     sessionId: string;
     reason: AutoRefineReason;
     turnsSinceLastReview: number;
-    outcome: "approved" | "declined" | "failed" | "assessed" | "deferred";
+    outcome: "approved" | "declined" | "failed" | "assessed" | "deferred" | "skipped" | "armed";
     rationale?: string;
     refinementId?: string;
 }

package/lib/auto.js

@@ -5,38 +5,42 @@
  * fire-and-forget with error containment: an auto-review failure never
  * disturbs the agent loop.
  *
- * Every gate decision (approved / declined / failed) is appended to
+ * Every gate decision (approved / declined / failed / skipped) is appended to
  * `<dshHome>/evolve/reviews.jsonl` so auto-review activity is durably
  * auditable — the server console is not a reliable place to look.
  *
  * Hook wiring:
- * - `agent/turn-stopping` increments a per-session turn counter (sync, cheap).
- * - `agent/status` (idle) checks the interval and may start the gate.
- * - `session/event` (compaction/start) starts an unconditional gate run so
- *   experiences about to be summarized away are persisted first.
+ * - `agent/turn-stopping` records the successful turn boundary.
+ * - `agent/status` (idle) captures an incremental snapshot and feeds the
+ *   per-session latest-pending serial scheduler.
+ * - `session/event` (compaction/start) forces a snapshot flush before data is
+ *   summarized away.
  */
 import { appendFileSync, mkdirSync } from "node:fs";
 import { join } from "node:path";
 import { slug } from "./types.js";
 import { planWithLlm } from "./planner.js";
-import { reviewAutoRefine, serializeSurface } from "./review.js";
-import { goalDrivesRounds, goalServiceOf } from "./goal.js";
+import { reviewAutoRefine } from "./review.js";
+import { goalServiceOf } from "./goal.js";
 import { notifyAutoReview } from "./notify.js";
 import { runLocalFatePhase } from "./fate.js";
-import { entrySourceOf } from "./source.js";
 import { mergeHarnessStates } from "./state.js";
 import { projectKeyOf } from "./project.js";
 import { questionServiceOf } from "./approval.js";
 import { buildEvolveCompleteEvent, emitEvolveComplete } from "./evolve-event.js";
 import { DEFAULT_REVIEWS_RETAIN, pruneJsonlFile } from "./store.js";
-import { isGatePaused } from "./runtime.js";
+import { isGateEnabled } from "./runtime.js";
+import { createReviewScheduler } from "./review-scheduler.js";
+import { captureTurnSnapshot } from "./turn-snapshot.js";
 import { captureAutoCase } from "./autocase.js";
 /** Turns a rejected skill candidate stays silent before being offered again. */
 export const SKILL_CONSULT_COOLDOWN_TURNS = 10;
 export function registerAutoReview(ctx, engine, config) {
     const perSession = new Map();
+    const schedulers = new Map();
     const logger = ctx.logger("continual-evolve");
     const reviewsPath = join(engine.baseDir, "evolve", "reviews.jsonl");
+    const defaultEnabled = config.enabledByDefault ?? true;
     const record = (entry) => {
         try {
             mkdirSync(join(engine.baseDir, "evolve"), { recursive: true });
@@ -54,9 +58,77 @@ export function registerAutoReview(ctx, engine, config) {
             // ignored — the next record retries
         }
     };
-    // Turn counting uses `agent/turn-stopping` — empirically the only event
-    // whose payload carries the agent subject in every dispatch (verified: the
-    // gate fired under it at 20:56). `agent/status` serves as the idle trigger.
+    const schedulerFor = (agent, state) => {
+        const existing = schedulers.get(agent.id);
+        if (existing)
+            return existing;
+        const scheduler = createReviewScheduler(async ({ snapshot, signal }) => {
+            if (!isGateEnabled(engine.baseDir, defaultEnabled))
+                return "aborted";
+            if (!snapshot.eligible) {
+                record({
+                    sessionId: snapshot.sessionId,
+                    reason: snapshot.reason,
+                    turnsSinceLastReview: state.turns - state.lastReviewAt,
+                    outcome: "skipped",
+                    rationale: `snapshot ${snapshot.cursor} skipped: ${snapshot.skipReason ?? "not eligible"}`,
+                });
+                return "no-op";
+            }
+            try {
+                await runGate(ctx, engine, agent, config, state, snapshot, record, signal);
+                return "success";
+            }
+            catch (cause) {
+                const message = cause instanceof Error ? cause.message : String(cause);
+                logger.warn(`auto-review failed for ${agent.id}: ${message}`);
+                record({
+                    sessionId: agent.id,
+                    reason: snapshot.reason,
+                    turnsSinceLastReview: state.turns - state.lastReviewAt,
+                    outcome: "failed",
+                    rationale: `gate error: ${message}`,
+                });
+                return "error";
+            }
+        }, (snapshot) => snapshot.cursor);
+        schedulers.set(agent.id, scheduler);
+        return scheduler;
+    };
+    const captureAndSchedule = (agent, state, reason) => {
+        if (!isGateEnabled(engine.baseDir, defaultEnabled))
+            return;
+        const turn = state.completedTurn;
+        const previousSnapshotTurn = state.lastSnapshotTurn;
+        if (reason === "turn_snapshot" && turn <= previousSnapshotTurn)
+            return;
+        if (reason === "turn_snapshot")
+            state.lastSnapshotTurn = turn;
+        const cursor = schedulerFor(agent, state).getCursor();
+        void captureTurnSnapshot(ctx, agent, {
+            turn,
+            reason,
+            ...(cursor !== undefined ? { cursor } : {}),
+            maxChars: config.maxInputChars,
+        })
+            .then((snapshot) => schedulerFor(agent, state).schedule(snapshot))
+            .catch((cause) => {
+            const message = cause instanceof Error ? cause.message : String(cause);
+            logger.warn(`auto-review snapshot failed for ${agent.id}: ${message}`);
+            record({
+                sessionId: agent.id,
+                reason,
+                turnsSinceLastReview: state.turns - state.lastReviewAt,
+                outcome: "failed",
+                rationale: `snapshot error: ${message}`,
+            });
+            if (reason === "turn_snapshot" && state.lastSnapshotTurn === turn) {
+                state.lastSnapshotTurn = previousSnapshotTurn;
+            }
+        });
+    };
+    // DSH emits this awaited boundary when a turn is about to close. The idle
+    // transition is the safe point at which to read the durable surface.
     ctx.on("agent/turn-stopping", (payload) => {
         const agent = payload.agent;
         if (!agent) {
@@ -65,42 +137,20 @@ export function registerAutoReview(ctx, engine, config) {
         }
         const state = stateFor(perSession, agent.id);
         state.turns += 1;
+        if (typeof payload.turn === "number")
+            state.completedTurn = Math.max(state.completedTurn, payload.turn);
     });
     ctx.on("agent/status", (payload) => {
         const agent = payload.agent;
         if (!agent || payload.status !== "idle")
             return;
         const state = stateFor(perSession, agent.id);
-        // v3 optional: an active evolution goal drives the gate EVERY round
-        // (the goal's round machine keeps the session continuing); without a
-        // goal the plain turn interval applies.
-        const goalDriven = goalDrivesRounds(goalServiceOf(ctx)?.get(agent));
-        if (!goalDriven && state.turns - state.lastReviewAt < config.intervalTurns)
-            return;
-        // #21 P2 runtime switch: a paused gate stays fully dormant — no LLM
-        // calls, no fate assessments, no audit records. Checked after the
-        // cheap in-memory interval check so the paused path costs one file
-        // read at most. Manual tools/commands are unaffected (separate path).
-        if (isGatePaused(engine.baseDir))
+        if (state.completedTurn <= state.lastSnapshotTurn)
             return;
-        // Run the gate outside the listener turn: agent is idle, work is auxiliary.
-        // Every failure is durably recorded — nothing fails silently.
-        void runGate(ctx, engine, agent, config, state, "turn_interval", record).catch((cause) => {
-            const message = cause instanceof Error ? cause.message : String(cause);
-            logger.warn(`auto-review failed for ${agent.id}: ${message}`);
-            record({
-                sessionId: agent.id,
-                reason: "turn_interval",
-                turnsSinceLastReview: state.turns - state.lastReviewAt,
-                outcome: "failed",
-                rationale: `gate error: ${message}`,
-            });
-            state.lastReviewAt = state.turns; // back off until the interval elapses again
-        });
+        captureAndSchedule(agent, state, "turn_snapshot");
     });
-    // Diagnostic: the armed marker proves registerAutoReview ran with the
-    // configured interval; a restart that writes it but nothing after means the
-    // trigger events are not reaching this listener.
+    // Diagnostic: the armed marker proves the listener was registered even when
+    // its runtime default is off, distinguishing "not registered" from "off".
     try {
         mkdirSync(join(engine.baseDir, "evolve"), { recursive: true });
         appendFileSync(reviewsPath, `${JSON.stringify({
@@ -109,7 +159,7 @@ export function registerAutoReview(ctx, engine, config) {
             reason: "boot",
             turnsSinceLastReview: 0,
             outcome: "armed",
-            rationale: `auto-review gate registered (interval=${config.intervalTurns})`,
+            rationale: `auto-review gate registered (default=${defaultEnabled ? "on" : "off"}; per-success-turn snapshots; local-fate every ${config.fateIntervalTurns} turns)`,
         })}\n`, "utf8");
     }
     catch (cause) {
@@ -121,6 +171,14 @@ export function registerAutoReview(ctx, engine, config) {
     catch {
         // ignored — the next record retries
     }
+    ctx.on("agent/disposed", (payload) => {
+        const agent = payload.agent;
+        if (!agent)
+            return;
+        schedulers.get(agent.id)?.shutdown();
+        schedulers.delete(agent.id);
+        perSession.delete(agent.id);
+    });
     ctx.on("session/event", (session, event) => {
         if (event.type !== "compaction/start")
             return;
@@ -129,21 +187,7 @@ export function registerAutoReview(ctx, engine, config) {
         if (!agent)
             return; // no live agent for that session (e.g. cold read)
         const state = stateFor(perSession, agent.id);
-        // Compaction is unconditional — unless the human paused the gate
-        // (#21): a paused gate skips even the compaction run, so "pause"
-        // is a true zero-LLM-call state.
-        if (isGatePaused(engine.baseDir))
-            return;
-        void runGate(ctx, engine, agent, config, state, "compact", record).catch((cause) => {
-            logger.warn(`auto-review failed at compaction for ${agent.id}: ${cause instanceof Error ? cause.message : String(cause)}`);
-            record({
-                sessionId: agent.id,
-                reason: "compact",
-                turnsSinceLastReview: state.turns - state.lastReviewAt,
-                outcome: "failed",
-                rationale: `gate error at compaction: ${cause instanceof Error ? cause.message : String(cause)}`,
-            });
-        });
+        captureAndSchedule(agent, state, "compact");
     });
 }
 /**
@@ -167,6 +211,8 @@ function stateFor(map, sessionId) {
     if (!state) {
         state = {
             turns: 0,
+            completedTurn: 0,
+            lastSnapshotTurn: 0,
             lastReviewAt: 0,
             running: false,
             skillRejects: new Map(),
@@ -199,23 +245,22 @@ export function loadGateHarnessView(engine, sessionId, opts) {
  * review's baseline fresh — fate re-loads the store and never races the
  * review's optimistic-concurrency checks.
  */
-async function runGate(ctx, engine, agent, config, state, reason, record) {
+async function runGate(ctx, engine, agent, config, state, snapshot, record, signal) {
     // Reentry guard (review audit 2026-08-28 S3): a gate run holds LLM calls
     // and possibly a user question for a long time; an idle/compaction
     // trigger overlapping the run would start a second concurrent pipeline
     // whose stale whole-file saves clobber the first run's writes.
     if (state.running) {
-        ctx.logger("continual-evolve").info(`auto-review skipped [${agent.id}]: previous gate run still in flight`);
-        return;
+        throw new Error(`previous gate run still in flight for ${agent.id}`);
     }
     state.running = true;
     try {
-        await runReviewPhase(ctx, engine, agent, config, state, reason, record);
+        await runReviewPhase(ctx, engine, agent, config, state, snapshot, record, signal);
         // D3: a goal stuck in "blocked" for consecutive gate runs gets one
         // local-fate assessment (the pipeline below), so whatever led the
         // goal astray is distilled before the session moves on.
-        await runGoalBlockedFate(ctx, engine, agent, config, state, reason, record);
-        await runLocalFatePhase(ctx, engine, agent, config, state, reason, record);
+        await runGoalBlockedFate(ctx, engine, agent, config, state, snapshot.reason, record);
+        await runLocalFatePhase(ctx, engine, agent, config, state, snapshot.reason, record);
     }
     finally {
         state.running = false;
@@ -250,8 +295,9 @@ export async function runGoalBlockedFate(ctx, engine, agent, config, state, _rea
     logger.info(`auto-review goal-blocked trigger [${agent.id}]: ${config.goalBlockedWrapupTurns} consecutive blocked gate runs → local-fate assessment`);
     await runLocalFatePhase(ctx, engine, agent, config, state, "goal_blocked", record);
 }
-async function runReviewPhase(ctx, engine, agent, config, state, reason, record) {
+async function runReviewPhase(ctx, engine, agent, config, state, snapshot, record, signal) {
     const sessionId = agent.id;
+    const reason = snapshot.reason;
     const turnsSinceLastReview = state.turns - state.lastReviewAt;
     const logger = ctx.logger("continual-evolve");
     const tokenUsage = {
@@ -260,14 +306,9 @@ async function runReviewPhase(ctx, engine, agent, config, state, reason, record)
         retain: engine.retention.tokenUsage,
         onError: (cause) => logger.warn(`token-usage ledger failed for ${sessionId}: ${cause instanceof Error ? cause.message : String(cause)}`),
     };
-    const trajectory = await readTrajectory(ctx, agent, config.maxInputChars).catch((cause) => {
-        logger.warn(`auto-review skipped for ${sessionId}: trajectory unavailable: ${cause instanceof Error ? cause.message : String(cause)}`);
-        record({ sessionId, reason, turnsSinceLastReview, outcome: "failed", rationale: `trajectory unavailable: ${cause instanceof Error ? cause.message : String(cause)}` });
-        return undefined;
-    });
+    const trajectory = snapshot.trajectory;
     if (!trajectory) {
-        state.lastReviewAt = state.turns;
-        return;
+        throw new Error("eligible snapshot has no trajectory");
     }
     // The gate judges the merged view (global + local, scopes labeled) so it
     // can recognize topics already covered globally and decline duplicates;
@@ -283,6 +324,8 @@ async function runReviewPhase(ctx, engine, agent, config, state, reason, record)
         state: harnessState,
         history,
         trajectory,
+        trajectoryEvents: snapshot.events,
+        ...(signal ? { signal } : {}),
         context: { reason, turnsSinceLastReview },
         budgetTokens: config.budgetTokens,
         tokenUsage,
@@ -306,6 +349,9 @@ async function runReviewPhase(ctx, engine, agent, config, state, reason, record)
         agent,
         state: harnessState,
         history,
+        trajectory: snapshot.trajectory,
+        trajectoryEvents: snapshot.events,
+        ...(signal ? { signal } : {}),
         ...(review.instructions ? { instructions: review.instructions } : {}),
         global: false,
         // Read the skill-creator template facts (fallback: builtin distilled
@@ -358,7 +404,7 @@ async function runReviewPhase(ctx, engine, agent, config, state, reason, record)
         record({ sessionId, reason, turnsSinceLastReview, outcome: "declined", rationale: `${review.rationale}${withheld}` });
         return;
     }
-    const source = entrySourceOf(agent, sessionId);
+    const source = { sessionId, ...(snapshot.sourceSeqs.length > 0 ? { seqs: [...snapshot.sourceSeqs] } : {}) };
     const result = engine.apply("local", sessionId, finalProposal, {
         scope: "local",
         baselineState: localState,
@@ -369,21 +415,13 @@ async function runReviewPhase(ctx, engine, agent, config, state, reason, record)
     // Gap C4: emit structured evolve_complete event for third-party consumers.
     emitEvolveComplete(engine.baseDir, buildEvolveCompleteEvent(result, `auto_review:${reason}`, sessionId), config.reviewsRetain ?? DEFAULT_REVIEWS_RETAIN);
     // Visibility: tell the user what the gate just persisted. Only the
-    // turn-interval path notifies — a compaction-triggered gate must not wake
+    // turn snapshot path notifies — a compaction-triggered gate must not wake
     // the agent mid-compaction — and only when something was actually applied
     // (a notice for zero edits is noise). Failure is contained in notifyAutoReview.
-    if (config.notifyOnAutoReview && reason === "turn_interval" && result.appliedEdits.some((e) => e.applied)) {
+    if (config.notifyOnAutoReview && reason === "turn_snapshot" && result.appliedEdits.some((e) => e.applied)) {
         notifyAutoReview(ctx, agent, result, turnsSinceLastReview);
     }
 }
-async function readTrajectory(ctx, agent, maxChars) {
-    const sessionQuery = ctx.sessionQuery;
-    if (!sessionQuery) {
-        throw new Error("sessionQuery unavailable");
-    }
-    const snapshot = await sessionQuery.readSurface(agent.id);
-    return serializeSurface(snapshot.events, maxChars);
-}
 /**
  * Split a proposal into skill edits and everything else. Skill edits are the
  * governed part: they need explicit user consent before the gate applies

package/lib/command.d.ts

@@ -18,9 +18,8 @@ export interface CommandRuntimeOptions {
     /** Mechanical promotion guards for wrapup/fate (2026-08-22 policy). */
     promotionPolicy: PromotionPolicy;
     /**
-     * Static patch flag for the auto-review gate (#21 status display).
-     * Absent (older wiring/tests) renders as unknown — the runtime pause
-     * switch still works.
+     * Initial auto-review default from plugin config. The listener is always
+     * registered; this is not a registration gate.
      */
     autoReview?: boolean;
 }

package/lib/command.js

@@ -376,18 +376,22 @@ async function executeEvolveCommand(ctx, engine, invocation, opts, runtime) {
             }
             case "pause":
             case "resume": {
-                // #21 P2 runtime switch: pause the AUTOMATIC gate only. Manual
-                // evolve_* tools and /evolve commands keep working — the human
-                // is acting explicitly there, so no gate is being bypassed.
+                // The switch is independent of the static registration flag. A
+                // resume explicitly enables automatic snapshots; a pause leaves
+                // the enable bit intact so status explains the paused state.
                 const pausing = sub === "pause";
-                const current = loadGateRuntime(engine.baseDir);
-                if (current.paused === pausing) {
-                    return success(`auto-review gate is already ${pausing ? "paused" : "running"} (no change).`);
+                const defaultEnabled = runtime.autoReview ?? false;
+                const current = loadGateRuntime(engine.baseDir, defaultEnabled);
+                if (pausing && current.paused) {
+                    return success("auto-review gate is already paused (no change).");
                 }
-                saveGateRuntime(engine.baseDir, pausing);
+                if (!pausing && current.enabled && !current.paused) {
+                    return success("auto-review gate is already running (no change).");
+                }
+                saveGateRuntime(engine.baseDir, pausing, pausing ? current.enabled : true);
                 return success(pausing
-                    ? "auto-review gate paused: no automatic reviews, fate assessments, or gate LLM calls until /evolve resume. Manual evolve_* tools and /evolve commands keep working."
-                    : "auto-review gate resumed: automatic reviews run again on their configured cadence.");
+                    ? "auto-review gate paused: no automatic snapshots, fate assessments, or gate LLM calls until /evolve resume. Manual evolve_* tools and /evolve commands keep working."
+                    : "auto-review gate resumed: successful turns will produce incremental snapshots immediately.");
             }
             case "status": {
                 return success(renderGateStatus(engine, sessionId, projectKeyOf(invocation.agent), runtime));
@@ -454,16 +458,14 @@ function demoteEntry(engine, id, sessionId, projectKey) {
     return error(`entry ${id} not found in the global, project, or local store`);
 }
 /**
- * #21 status: one screen answering "is the gate on, and what is in the
- * stores". The patch flag says whether the gate was registered at boot;
- * the runtime switch says whether the human paused it since.
+ * Status answers whether the always-registered listener is enabled at runtime
+ * and what stores/retention it currently sees.
  */
 function renderGateStatus(engine, sessionId, projectKey, runtime) {
-    const paused = loadGateRuntime(engine.baseDir).paused;
-    const patch = runtime.autoReview === undefined ? "unknown" : runtime.autoReview ? "on" : "off";
-    const gateLine = patch === "off"
-        ? "gate: disabled in patch config (autoReview off — /evolve pause has nothing to pause)"
-        : `gate: ${patch === "unknown" ? "patch flag unknown" : "enabled in patch config"} · ${paused ? "PAUSED by /evolve pause (resume with /evolve resume)" : "running"}`;
+    const configuredDefault = runtime.autoReview === undefined ? "unknown" : runtime.autoReview ? "on" : "off";
+    const current = loadGateRuntime(engine.baseDir, runtime.autoReview ?? false);
+    const effective = current.paused ? "PAUSED (resume with /evolve resume)" : current.enabled ? "running" : "off (enable with /evolve resume)";
+    const gateLine = `gate: listener registered · config default ${configuredDefault} · runtime ${effective}`;
     const countEntries = (state) => Object.values(state.entries).reduce((n, byKind) => n + Object.keys(byKind).length, 0);
     const lines = [gateLine];
     lines.push(`stores: global ${countEntries(engine.load("global", undefined))} entries · local(${sessionId}) ${countEntries(engine.load("local", sessionId))} entries`);

package/lib/fate.d.ts

@@ -119,7 +119,7 @@ export interface FateApplyResult {
 export declare function applyLocalFates(engine: EvolutionEngine, sessionId: string, plan: FatePlan, localState: HarnessState, mode: FateApplyMode): FateApplyResult;
 /**
  * The gate's local-fate phase. Runs after the review phase on every gate
- * trigger (turn_interval / compact), subject to cadence and cooldown. All
+ * trigger (turn_snapshot / compact), subject to cadence and cooldown. All
  * failures are contained and recorded — a broken fate dimension never
  * disturbs the agent loop.
  */

package/lib/fate.js

@@ -192,7 +192,7 @@ export function applyLocalFates(engine, sessionId, plan, localState, mode) {
 }
 /**
  * The gate's local-fate phase. Runs after the review phase on every gate
- * trigger (turn_interval / compact), subject to cadence and cooldown. All
+ * trigger (turn_snapshot / compact), subject to cadence and cooldown. All
  * failures are contained and recorded — a broken fate dimension never
  * disturbs the agent loop.
  */
@@ -255,7 +255,7 @@ export async function runLocalFatePhase(ctx, engine, agent, config, state, reaso
             rationale: `fate: ${assessment.rationale} (${applied.join("; ")})`,
             refinementId: results.map((result) => result.id).join(","),
         });
-        if (config.notifyOnAutoReview && reason === "turn_interval" && applied.length > 0) {
+        if (config.notifyOnAutoReview && (reason === "turn_snapshot" || reason === "turn_interval") && applied.length > 0) {
             notifyFateApplied(ctx, agent, applied);
         }
         return;
@@ -309,7 +309,7 @@ export async function runLocalFatePhase(ctx, engine, agent, config, state, reaso
             rationale: `fate: ${assessment.rationale} (${applied.join("; ")})`,
             refinementId: results.map((result) => result.id).join(","),
         });
-        if (config.notifyOnAutoReview && reason === "turn_interval") {
+        if (config.notifyOnAutoReview && (reason === "turn_snapshot" || reason === "turn_interval")) {
             notifyFateApplied(ctx, agent, applied);
         }
         return;
@@ -333,7 +333,7 @@ export function buildFateNotice(applied) {
         "请用一句话简短确认即可，不要调用任何工具。",
     ].join("\n");
 }
-/** Queue the follow-up notice turn (turn_interval only, like the review notice). */
+/** Queue the follow-up notice turn (successful-turn path only). */
 function notifyFateApplied(ctx, agent, applied) {
     try {
         agent.followup(createUserMessage({

package/lib/index.d.ts

@@ -10,9 +10,9 @@ export declare const Config: z<Schemastery.ObjectS<NoInfer<{
     baseDir: z<string, string, "plain">;
     /** System-prompt section order for the evolution guidance. */
     sectionOrder: z<number, number, "defined">;
-    /** Enable the automatic review gate (off by default: it costs model calls). */
+    /** Initial automatic-review default when no runtime switch exists (off by default: it costs model calls). */
     autoReview: z<boolean, boolean, "defined">;
-    /** Gate runs when this many turns have passed since the last review. */
+    /** Legacy/local-fate cadence fallback; successful-turn review is snapshot-driven. */
     reviewIntervalTurns: z<number, number, "defined">;
     /** Trajectory slice handed to the gate, in characters. */
     maxReviewInputChars: z<number, number, "defined">;
@@ -107,9 +107,9 @@ export declare const Config: z<Schemastery.ObjectS<NoInfer<{
     baseDir: z<string, string, "plain">;
     /** System-prompt section order for the evolution guidance. */
     sectionOrder: z<number, number, "defined">;
-    /** Enable the automatic review gate (off by default: it costs model calls). */
+    /** Initial automatic-review default when no runtime switch exists (off by default: it costs model calls). */
     autoReview: z<boolean, boolean, "defined">;
-    /** Gate runs when this many turns have passed since the last review. */
+    /** Legacy/local-fate cadence fallback; successful-turn review is snapshot-driven. */
     reviewIntervalTurns: z<number, number, "defined">;
     /** Trajectory slice handed to the gate, in characters. */
     maxReviewInputChars: z<number, number, "defined">;