@lmzhen/dsh-evolution-review 0.8.0 → 0.9.0

package/README.md

@@ -17,7 +17,7 @@ own, and the delivery mode lives on the `evolution-policy` row, not here.
 - Review subagents are spawned with the plain `skill` tool only (`reviewToolAllow` default and the host/preset config both = `[skill]`: the DSH tool catalog has no `skill_search`/`skill_load` discovery pair, so the Hermes-lineage Anchored Standard `skill_search`/`skill_load` allow-list does not exist here).
 - Review subagents run as `spawn` children on the deployment default preset rather than inheriting the parent agent's composition (`fork`): a fork child is always promoted by the Anchored Standard bootstrap and its narrowed resident catalog would drop the plain `skill` tool from the review allow-list.
 - The review request text is redacted for credential-shaped patterns before it reaches the subagent, but redaction is pattern-based and best-effort, not a security boundary.
-- Read-before-write tracks only reads through the `skill` tool. `skill_manage` has no per-skill read action (`list`/`review` are whole-library, not targeted at one name), so a skill that was only listed via `skill_manage` is not marked as read: a background review may still reject a patch to it until it is actually loaded.
+- Read-before-write (the rule is `evolution-core`'s `skill-reads.ts`, shared with the tool path's admission gate) tracks only reads through the `skill` tool. `skill_manage` has no per-skill read action (`list`/`review` are whole-library, not targeted at one name), so a skill that was only listed via `skill_manage` is not marked as read: a background review may still reject a patch to it until it is actually loaded.
 - The completion-channel counters (`cumulativeToolCalls` / `completionInjected`) are in-memory only. A process restart resets them, which is accepted behavior: the completion review is a one-per-session post-task adaptation and a restart is treated as a fresh conversation boundary. The cadence state (`turnsSinceMemory` / `turnsSinceSkill`) is persisted via `ReviewState` and survives restart: bounded by `REVIEW_STATE_SESSION_CAP` (500, seam constant): the least-recently-active sessions are pruned on save, so a very old session restarting resumes from a fresh cadence baseline rather than an unbounded store.
 - `evolution/review-scheduled` and `evolution/review-error` are emitted for platform/user wiring only: this family has no in-repo production `ctx.on` consumer for them. They are declared externally owned (the platform side wires consumption), which matches the `EXEMPT_ORPHANS` set in `scripts/verify-event-pairing.mjs`.
 - When the `evolution-state` service is not mounted, the memory/skill cadence state is not persisted and every turn restarts from a clean `{ turnsSinceMemory: 0, turnsSinceSkill: 0 }` baseline: the review schedule is stateless and re-decided each turn rather than accumulating across the conversation. The loss is surfaced once per process as a logger warning at the first turn/end.

package/lib/index.js

@@ -2,7 +2,7 @@ import { createHash, randomUUID } from "node:crypto";
 import z from "@deepseek-ai/schemastery";
 import { createUserMessage } from "@deepseek-ai/dsh-llm";
 import { SessionId } from "@deepseek-ai/dsh-session";
-import { COMPLETION_SKILL_REVIEW_PROMPT, DEFAULT_MAX_OPS_PER_PLAN, DEFAULT_MEMORY_CHAR_LIMIT, DEFAULT_MEMORY_REVIEW_MODEL, DEFAULT_REVIEW_CONTEXT_MESSAGES, DEFAULT_REVIEW_MEMORY_INTERVAL, DEFAULT_REVIEW_MESSAGE_CHARS, DEFAULT_REVIEW_SKILL_INTERVAL, DEFAULT_REVIEW_TIMEOUT_MS, DEFAULT_SKILL_CONTENT_CHARS, DEFAULT_SKILL_LIMITS, DEFAULT_SKILL_REVIEW_COMPLETION_MIN_TOOL_CALLS, DEFAULT_SKILL_REVIEW_MODEL, DEFAULT_SKILL_REVIEW_TRIGGER, DEFAULT_SUBSTANTIVE_MIN_AGENT_CHARS, DEFAULT_SUBSTANTIVE_MIN_TOOL_CALLS, DEFAULT_SUBSTANTIVE_MIN_USER_CHARS, DEFAULT_USER_CHAR_LIMIT, MAX_TIMER_DELAY_MS, PROMPT_BUNDLE, advanceReview, assertSkillsRootAliasRetired, clampedNumber, clearReviewChannel, contentHash, evolutionIoAdapter, foldToolDispatches, foldTurn, installParamSection, markReviewChannel, newSkillLibrary, paramNamespace, policyStageLimits, readDispatchSignal, readNumberParam, redactSecrets, resolveOrigins, resolveRootConfig, reviewPrompt, sessionAudited, skillReadNameOf, sweepReviewChannelSessions, verifyPromptBundle } from "@lmzhen/dsh-evolution-core";
+import { COMPLETION_SKILL_REVIEW_PROMPT, DEFAULT_MAX_OPS_PER_PLAN, DEFAULT_MEMORY_CHAR_LIMIT, DEFAULT_MEMORY_REVIEW_MODEL, DEFAULT_REVIEW_CONTEXT_MESSAGES, DEFAULT_REVIEW_MEMORY_INTERVAL, DEFAULT_REVIEW_MESSAGE_CHARS, DEFAULT_REVIEW_SKILL_INTERVAL, DEFAULT_REVIEW_TIMEOUT_MS, DEFAULT_SKILL_CONTENT_CHARS, DEFAULT_SKILL_LIMITS, DEFAULT_SKILL_REVIEW_COMPLETION_MIN_TOOL_CALLS, DEFAULT_SKILL_REVIEW_MODEL, DEFAULT_SKILL_REVIEW_TRIGGER, DEFAULT_SUBSTANTIVE_MIN_AGENT_CHARS, DEFAULT_SUBSTANTIVE_MIN_TOOL_CALLS, DEFAULT_SUBSTANTIVE_MIN_USER_CHARS, DEFAULT_USER_CHAR_LIMIT, MAX_TIMER_DELAY_MS, PROMPT_BUNDLE, advanceReview, assertSkillsRootAliasRetired, clampedNumber, clearReviewChannel, collectReadSkillNames, contentHash, evolutionIoAdapter, filterUnreadSkillOps, filterUnreadSkillOps as filterUnreadSkillOps$1, foldTurn, installParamSection, markReviewChannel, newSkillLibrary, paramNamespace, policyStageLimits, readDispatchSignal, readNumberParam, redactSecrets, resolveOrigins, resolveRootConfig, reviewPrompt, sessionAudited, sweepReviewChannelSessions, verifyPromptBundle } from "@lmzhen/dsh-evolution-core";
 import { validateEvolutionPlan } from "@lmzhen/dsh-evolution-plan-validator";
 //#region lib/types/session-state.js
 /**
@@ -661,7 +661,7 @@ function apply(ctx, rawConfig = {}) {
 					ctx.logger.warn(`dsh-evolution-review: review subagent returned no structured plan${stopDetail !== void 0 ? ` (stopReason=${stopDetail}${diagDetail !== void 0 ? `; diagnostic=${diagDetail}` : ""})` : ""}`);
 					return false;
 				}
-				const childReads = run.localAgent ? collectReadSkillNames(run.localAgent.session) : /* @__PURE__ */ new Set();
+				const childReads = run.localAgent ? collectReadSkillNames(run.localAgent.session.snapshotEvents()) : /* @__PURE__ */ new Set();
 				const plan = result.structured;
 				const policyFingerprint = fingerprintPolicy(snapshot);
 				const validation = validateEvolutionPlan(plan, {
@@ -673,7 +673,7 @@ function apply(ctx, rawConfig = {}) {
 					maxSkillContentChars: snapshot?.skillContentChars ?? DEFAULT_SKILL_CONTENT_CHARS
 				});
 				const acceptedSkillOps = validation.accepted.skillOps ?? [];
-				const skippedUnread = filterUnreadSkillOps(acceptedSkillOps, new Set([...collectReadSkillNames(session), ...childReads]));
+				const skippedUnread = filterUnreadSkillOps$1(acceptedSkillOps, new Set([...collectReadSkillNames(session.snapshotEvents()), ...childReads]));
 				const evidenceQuotes = [...validation.accepted.memoryOps ?? [], ...acceptedSkillOps].reduce((total, op) => total + (Array.isArray(op.evidence) ? op.evidence.length : 0), 0);
 				const emitApplied = (report) => {
 					try {
@@ -1054,29 +1054,6 @@ function staleRefusal(result, name, filePath) {
 		message: filePath === void 0 ? `Skill "${name}" changed since this plan was produced — the full-content update was refused as stale. Re-read the skill and produce a fresh plan.` : `Support file "${filePath}" of "${name}" changed since this plan was produced — the staged file operation was refused as stale. Re-read the skill tree and produce a fresh plan.`
 	};
 }
-/**
-* v37 P7a: the read-before-write credit now comes from evolution-core's
-* `tool-dispatch` module — the ONE reader of the platform's dispatch event
-* types, and the ONE authority on which tool reads a skill.
-*
-* v32 REV-06(a) is preserved by the normalizer: a skill counts as READ only
-* when it did not fail, so a failed/timeout read still cannot pass the
-* read-before-write gate and let the review blind-overwrite content the model
-* never saw. What changed is the vocabulary the gate listens to: matching
-* `tool/call` here meant every PTC session (`tool/ptc-dispatch*`) collected an
-* EMPTY set, so `filterUnreadSkillOps` dropped every mutating op the model had
-* legitimately read first — and nothing reported the loss.
-* @param session - the session whose log is folded.
-* @returns the skill names this session read through a non-failed dispatch.
-*/
-function collectReadSkillNames(session) {
-	const names = /* @__PURE__ */ new Set();
-	for (const dispatch of foldToolDispatches(session.snapshotEvents())) {
-		const name = skillReadNameOf(dispatch);
-		if (name !== void 0) names.add(name);
-	}
-	return names;
-}
 /** Map/set size that triggers a dead-session counter sweep (bounded, not a hard cap). */
 const COUNTER_SWEEP_THRESHOLD = 128;
 /**
@@ -1094,35 +1071,6 @@ function sweepDeadSessionEntries(entries, isAlive) {
 	}
 	return removed;
 }
-/**
-* Drop mutating ops whose target was not read this session, in place.
-* Create is exempt (no read required to author a new skill). Covers the same
-* mutating surface Hermes guards (edit/patch/write_file/remove_file), so a
-* background review cannot blind-touch support files or edits of skills it
-* never loaded. Returns the count of dropped ops so the plan event can report
-* them as rejected.
-*/
-function filterUnreadSkillOps(ops, readNames) {
-	const READ_REQUIRED = [
-		"edit",
-		"update",
-		"patch",
-		"delete",
-		"write_file",
-		"remove_file",
-		"restructure"
-	];
-	let dropped = 0;
-	for (let index = ops.length - 1; index >= 0; index -= 1) {
-		const op = ops[index];
-		if (!op) continue;
-		if (op.name && READ_REQUIRED.includes(op.action ?? "patch") && !readNames.has(op.name)) {
-			ops.splice(index, 1);
-			dropped += 1;
-		}
-	}
-	return dropped;
-}
 function fingerprintPolicy(snapshot) {
 	try {
 		return createHash("sha256").update(JSON.stringify(snapshot)).digest("hex").slice(0, 12);

package/lib/types/index.d.ts

@@ -6,6 +6,7 @@ import type { Context } from '@deepseek-ai/cordis';
 import z from '@deepseek-ai/schemastery';
 import type { Session } from '@deepseek-ai/dsh-session';
 import { type ReviewKind } from '@lmzhen/dsh-evolution-core';
+export { filterUnreadSkillOps } from '@lmzhen/dsh-evolution-core';
 export declare const name = "evolution-review";
 export declare const inject: string[];
 export interface Config {
@@ -26,6 +27,8 @@ export interface Config {
     /** Shadowed by the policy snapshot in every shipped composition — configure
      * `reviewMemoryInterval` on the `evolution-policy` row instead (v37 P2-24).
      * Deprecated alias (G0/S0.3): still readable, refused by writes; removed 0.7.0. */
+    /** Review cadence in TOOL CALLS (signals.ts: a turn advances by its tool-call count, minimum 1,
+     * or by 1 when the turn itself carried the memory signal). */
     memoryInterval?: number;
     /** Shadowed by the policy snapshot in every shipped composition — configure
      * `reviewSkillInterval` on the `evolution-policy` row instead. Deprecated
@@ -133,9 +136,11 @@ export declare function clampReviewConfig(rawConfig: Config, ctx: Context): Clam
  * parameter ids from the registry, so the settings document, the params output,
  * the doctor report and the cards all spell one name. */
 export interface ReviewSettings {
-    /** Activity units between skill-review injections. */
+    /** Tool calls between skill-review injections (a turn with no tool call counts as one; a turn
+     * that itself used a skill advances the counter by 1). */
     reviewSkillInterval: number;
-    /** Activity units between memory-review injections. */
+    /** Tool calls between memory-review injections (a turn with no tool call counts as one; a turn
+     * that itself touched memory advances the counter by 1). */
     reviewMemoryInterval: number;
     /** Which channel may inject a skill review. */
     skillReviewTrigger: 'cadence' | 'completion' | 'both';
@@ -164,18 +169,6 @@ export declare function shouldCompletionReview(reason: {
  * number of removed entries.
  */
 export declare function sweepDeadSessionEntries<K>(entries: Map<K, unknown> | Set<K>, isAlive: (id: K) => boolean): number;
-/**
- * Drop mutating ops whose target was not read this session, in place.
- * Create is exempt (no read required to author a new skill). Covers the same
- * mutating surface Hermes guards (edit/patch/write_file/remove_file), so a
- * background review cannot blind-touch support files or edits of skills it
- * never loaded. Returns the count of dropped ops so the plan event can report
- * them as rejected.
- */
-export declare function filterUnreadSkillOps(ops: Array<{
-    action?: string;
-    name?: string;
-}>, readNames: ReadonlySet<string>): number;
 /**
  * V10-10 (P2-11) / A1 (audit P1-1): render one `[result]` evidence line from
  * a tool-result event payload. The former read (`data.output`) targeted a
@@ -204,5 +197,4 @@ export declare function buildReviewRequest(session: Session, kind: ReviewKind, s
     userChars: number;
     assistantChars: number;
 }, maxMessages: number, maxMessageChars: number): string;
-export {};
 //# sourceMappingURL=index.d.ts.map

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@lmzhen/dsh-evolution-review",
   "description": "Background review orchestration (community build)",
-  "version": "0.8.0",
+  "version": "0.9.0",
   "publishConfig": {
     "access": "public"
   },
@@ -27,9 +27,9 @@
   "license": "MIT",
   "dependencies": {
     "@deepseek-ai/schemastery": "^3.18.1",
-    "@lmzhen/dsh-evolution-approval": "^0.8.0",
-    "@lmzhen/dsh-evolution-core": "^0.8.0",
-    "@lmzhen/dsh-evolution-plan-validator": "^0.8.0"
+    "@lmzhen/dsh-evolution-approval": "^0.9.0",
+    "@lmzhen/dsh-evolution-core": "^0.9.0",
+    "@lmzhen/dsh-evolution-plan-validator": "^0.9.0"
   },
   "peerDependencies": {
     "@deepseek-ai/cordis": "^4.0.1",
@@ -37,8 +37,8 @@
     "@deepseek-ai/dsh-llm": "^0.1.5-rc.2",
     "@deepseek-ai/dsh-session": "^0.1.5-rc.2",
     "@deepseek-ai/dsh-tools": "^0.1.5-rc.2",
-    "@lmzhen/dsh-evolution-state": "^0.8.0",
-    "@lmzhen/dsh-evolution-policy": "^0.8.0"
+    "@lmzhen/dsh-evolution-state": "^0.9.0",
+    "@lmzhen/dsh-evolution-policy": "^0.9.0"
   },
   "devDependencies": {
     "@deepseek-ai/dsh-agent": "^0.1.5-rc.2",
@@ -48,10 +48,10 @@
     "@deepseek-ai/dsh-session-persistence": "^0.1.5-rc.2",
     "@deepseek-ai/dsh-session-persistence-jsonl": "^0.1.5-rc.2",
     "@deepseek-ai/dsh-tools": "^0.1.5-rc.2",
-    "@lmzhen/dsh-evolution-approval": "^0.8.0",
-    "@lmzhen/dsh-evolution-core": "^0.8.0",
-    "@lmzhen/dsh-evolution-curator": "^0.8.0",
-    "@lmzhen/dsh-evolution-plan-validator": "^0.8.0",
-    "@lmzhen/dsh-evolution-state": "^0.8.0"
+    "@lmzhen/dsh-evolution-approval": "^0.9.0",
+    "@lmzhen/dsh-evolution-core": "^0.9.0",
+    "@lmzhen/dsh-evolution-curator": "^0.9.0",
+    "@lmzhen/dsh-evolution-plan-validator": "^0.9.0",
+    "@lmzhen/dsh-evolution-state": "^0.9.0"
   }
 }