diff --git a/.changeset/check-stale-outputs.md b/.changeset/check-stale-outputs.md
deleted file mode 100644
index f84d7fe9..00000000
--- a/.changeset/check-stale-outputs.md
+++ /dev/null
@@ -1,5 +0,0 @@
----
-"agentsmesh": minor
----
-
-Detect stale files in managed generated-output locations during `agentsmesh check`, and expose `canonicalDrift`, `outputDrift`, and `outputsStale` across CLI, programmatic, and MCP results.
diff --git a/.changeset/lessons-recurrence-escalation.md b/.changeset/lessons-recurrence-escalation.md
deleted file mode 100644
index fa248fd0..00000000
--- a/.changeset/lessons-recurrence-escalation.md
+++ /dev/null
@@ -1,9 +0,0 @@
----
-"agentsmesh": minor
----
-
-Lessons recall now escalates on repeat failures. When `agentsmesh lessons hook` runs as a `PreToolUse` first-touch guard and the exact action about to run has already failed twice or more (per the opt-in outcome log) with a captured lesson covering it, the covering rule is re-injected above the normal recall bullets as a `RECURRENT FAILURE` escalation — and it cuts through per-session dedup, since a rule the agent saw but did not apply must be shown again. Advisory context only, once per action per session; the covering rule is shown exactly once (the escalation is its delivery), and the default telemetry-off path is unaffected.
-
-Effectiveness telemetry is now attributed per harness session. The hook stamps the harness `session_id` (and a per-batch relevance `rank`) onto the `delivered` / `failure` rows of `.agentsmesh/lessons/outcome-log.jsonl` and onto recall telemetry, so `agentsmesh lessons stats` groups by real sessions and a failure only impeaches deliveries from its own session — no `AGENTSMESH_SESSION_ID` export needed on hook-driven recalls.
-
-Added an opt-in `repairTriggers` flag (default `false`) in `.agentsmesh/lessons/config.json` that repairs degraded triggers at capture time: a broad or wide `file_glob` is narrowed toward the evidence file's directory class, a stopworded or over-long keyword gets a matchable variant added beside it, and a keyword that tokenizes to nothing is dropped — each surfaced as a `NARROWED_GLOB` / `KEYWORD_VARIANT_ADDED` / `DROPPED_KEYWORD` warning on the capture result. It never blocks a capture, never rewrites a glob without covering evidence, and never leaves a lesson with zero triggers.
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 5e4be165..18f965b9 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,16 @@
 # Changelog
 
+## 0.32.0
+
+### Minor Changes
+
+- 9efbab1: Detect stale files in managed generated-output locations during `agentsmesh check`, and expose `canonicalDrift`, `outputDrift`, and `outputsStale` across CLI, programmatic, and MCP results.
+- a722921: Lessons recall now escalates on repeat failures. When `agentsmesh lessons hook` runs as a `PreToolUse` first-touch guard and the exact action about to run has already failed twice or more (per the opt-in outcome log) with a captured lesson covering it, the covering rule is re-injected above the normal recall bullets as a `RECURRENT FAILURE` escalation — and it cuts through per-session dedup, since a rule the agent saw but did not apply must be shown again. Advisory context only, once per action per session; the covering rule is shown exactly once (the escalation is its delivery), and the default telemetry-off path is unaffected.
+
+  Effectiveness telemetry is now attributed per harness session. The hook stamps the harness `session_id` (and a per-batch relevance `rank`) onto the `delivered` / `failure` rows of `.agentsmesh/lessons/outcome-log.jsonl` and onto recall telemetry, so `agentsmesh lessons stats` groups by real sessions and a failure only impeaches deliveries from its own session — no `AGENTSMESH_SESSION_ID` export needed on hook-driven recalls.
+
+  Added an opt-in `repairTriggers` flag (default `false`) in `.agentsmesh/lessons/config.json` that repairs degraded triggers at capture time: a broad or wide `file_glob` is narrowed toward the evidence file's directory class, a stopworded or over-long keyword gets a matchable variant added beside it, and a keyword that tokenizes to nothing is dropped — each surfaced as a `NARROWED_GLOB` / `KEYWORD_VARIANT_ADDED` / `DROPPED_KEYWORD` warning on the capture result. It never blocks a capture, never rewrites a glob without covering evidence, and never leaves a lesson with zero triggers.
+
 ## 0.31.0
 
 ### Minor Changes
diff --git a/package.json b/package.json
index ac226ec8..516fd41c 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "agentsmesh",
-  "version": "0.31.0",
+  "version": "0.32.0",
   "description": "One canonical source for AI coding agent rules, commands, skills, MCP, hooks, and permissions — synced across every major AI coding tool.",
   "type": "module",
   "main": "./dist/index.js",