@lmzhen/dsh-evolution-review 0.9.0 → 0.11.1

package/README.md

@@ -23,6 +23,7 @@ own, and the delivery mode lives on the `evolution-policy` row, not here.
 - 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.
 - Read-before-write can see the review subagent's own `skill` reads only when the subagent backend exposes `localAgent` (the in-process driver does; out-of-process backends such as ACP and the CLI providers set `localAgent: undefined`). With a remote backend the subagent's reads are invisible, so a plan item patching a skill the subagent itself loaded is dropped as "unread": the review then falls back to the parent session's reads only.
 - **The default `reviewMode: 'inject'` produces no plan ledger.** The review runs in the parent session and emits no `evolution/plan-applied` event, so `evolution-activity`'s `activity.json` and the `evolution-replay` leaderboard never grow in this mode: the only production emit point sits inside the subagent path. Set `reviewMode: 'subagent'` on the `evolution-policy` row when the plan audit trail is required; the plugin states this once at load instead of leaving an empty ledger to be read as "no reviews happened" (v37 S2.2, plan decision (c)).
+- **Evidence that cites only bookkeeping frames is REPORTED, never refused (phase 1).** `EVIDENCE_CLASS` (`evolution-plan-validator`) counts the ops whose entire `evidence` list points at turn/step boundary frames — a seq the range rule accepts but that carries no content — and this plugin logs one `dsh-evolution-review:` warning per plan; the count rides `evolution/plan-applied` as `evidenceClassReports` and appears in no model-visible text. Nothing is dropped: `EVIDENCE_RANGE` remains the only evidence gate, and a session log whose frames carry no `seq` leaves the report silent (`undefined` is not an empty index) instead of reporting every op.
 - **`.pinned` protection in the `'inject'` channel rides a family-internal session mark.** The review prompt marks the parent session, `tool-skill-manage` reads that mark and resolves both origin surfaces (approval + library) to `background_review`, and the next REAL user message (`source.kind === 'user'`) clears it (plugin notices, including the review prompt itself, do not). Two bounds follow from the platform's inject contract (no driver wake; a prompt is dropped on cancel/dispose and may be missed with an already-claimed batch): with `reviewWakeInject: false`, or on a host without `followup`, (a) a pending prompt may never execute while the session stays idle, and (b) when the user's next message wakes the session, the mark is cleared before that pending prompt reaches the model (its writes are then attributed `foreground` and the pinned guard does not cover them). A prompt delivered while a HUMAN message is already queued is not marked at all: the platform claims that human turn first, so a session-level window would attribute the user's own writes to `background_review` (S2-8, FLOW1-3): the plugin reads the pre-claim queue (`agent.inbox`) because the platform exposes no claim identity, and warns once per mount when it withholds the mark.
 
 ## Configuration

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, 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 { 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, evidenceKindIndex, 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
 /**
@@ -634,6 +634,7 @@ function apply(ctx, rawConfig = {}) {
 			}
 			const preRunHashes = await treeSkillHashes();
 			const sessionSeqAtPlanTime = session.seq - 1;
+			const substantiveEvidenceSeqs = evidenceKindIndex(session.snapshotEvents());
 			const run = await subagents.start("spawn", {
 				label: "dsh-evolution-review",
 				prompt: [{
@@ -666,12 +667,14 @@ function apply(ctx, rawConfig = {}) {
 				const policyFingerprint = fingerprintPolicy(snapshot);
 				const validation = validateEvolutionPlan(plan, {
 					sessionSeq: sessionSeqAtPlanTime,
+					substantiveEvidenceSeqs,
 					maxOpsPerPlan: snapshot?.maxOpsPerPlan ?? DEFAULT_MAX_OPS_PER_PLAN,
 					protectedSkillNames: new Set(snapshot?.protectedSkillNames ?? []),
 					maxMemoryChars: snapshot?.memoryChars ?? DEFAULT_MEMORY_CHAR_LIMIT,
 					maxUserChars: snapshot?.userChars ?? DEFAULT_USER_CHAR_LIMIT,
 					maxSkillContentChars: snapshot?.skillContentChars ?? DEFAULT_SKILL_CONTENT_CHARS
 				});
+				if (validation.reports.length > 0) ctx.logger.warn(`dsh-evolution-review: ${validation.reports.length} op(s) cite only bookkeeping frames as evidence: ${validation.reports.map((report) => report.reason).join("; ")}`);
 				const acceptedSkillOps = validation.accepted.skillOps ?? [];
 				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);
@@ -685,6 +688,7 @@ function apply(ctx, rawConfig = {}) {
 							skillApplied: report.actions.filter((action) => action.startsWith("Skill ")).length,
 							rejectedOps: validation.rejected.length,
 							...skippedUnread > 0 ? { skippedUnread } : {},
+							...validation.reports.length > 0 ? { evidenceClassReports: validation.reports.length } : {},
 							executionFailures: report.failedOps?.length ?? 0,
 							...report.executionError !== void 0 ? { executionError: report.executionError } : {},
 							evidenceQuotes,

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@lmzhen/dsh-evolution-review",
   "description": "Background review orchestration (community build)",
-  "version": "0.9.0",
+  "version": "0.11.1",
   "publishConfig": {
     "access": "public"
   },
@@ -27,9 +27,9 @@
   "license": "MIT",
   "dependencies": {
     "@deepseek-ai/schemastery": "^3.18.1",
-    "@lmzhen/dsh-evolution-approval": "^0.9.0",
-    "@lmzhen/dsh-evolution-core": "^0.9.0",
-    "@lmzhen/dsh-evolution-plan-validator": "^0.9.0"
+    "@lmzhen/dsh-evolution-approval": "^0.11.1",
+    "@lmzhen/dsh-evolution-core": "^0.11.1",
+    "@lmzhen/dsh-evolution-plan-validator": "^0.11.1"
   },
   "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": "^0.9.0",
-    "@lmzhen/dsh-evolution-policy": "^0.9.0"
+    "@lmzhen/dsh-evolution-state": "^0.11.1",
+    "@lmzhen/dsh-evolution-policy": "^0.11.1"
   },
   "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": "^0.9.0",
-    "@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"
+    "@lmzhen/dsh-evolution-approval": "^0.11.1",
+    "@lmzhen/dsh-evolution-core": "^0.11.1",
+    "@lmzhen/dsh-evolution-curator": "^0.11.1",
+    "@lmzhen/dsh-evolution-plan-validator": "^0.11.1",
+    "@lmzhen/dsh-evolution-state": "^0.11.1"
   }
 }