release: v2.3.0 — first fully stable release

Bump version to 2.3.0 across package.json, openclaw.plugin.json.
Add comprehensive CHANGELOG documenting all bugs found and fixed
during the v2.x development cycle.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

CHANGELOG.md

@@ -1,75 +1,73 @@
 # Changelog
 
+## v2.3.0 — 2026-03-16
+
+### Summary
+First **fully stable** release. All previous versions had critical bugs causing silent failure on gateway deployments.
+
+### Fixed
+- **Workspace resolution** (`_ctx.workspaceDir`) — Hooks now read workspace path from the hook context parameter instead of `api.runtime.workspaceDir` (which was always `undefined` in gateway mode). This was the root cause of the plugin silently doing nothing on all gateway/Telegram/Discord deployments.
+- **Channel metadata stripping** — User messages from Telegram/Discord are cleaned of `Conversation info (untrusted metadata)` prefixes before saving, preventing garbage in the state file.
+- **Recovery death spiral** — Short conversations (< 2 real user messages) no longer overwrite existing meaningful state. Previously: tell secret → `/new` → model ignores injected context → "I don't remember" → `agent_end` overwrites secret with failure → permanent data loss.
+- **State staleness** — Removed "skip if existing state is meaningful" guard that prevented state from ever updating after the first write.
+
+### Debugging timeline
+1. Hooks not firing → `api.runtime.workspaceDir` was `undefined` → fix: use `_ctx.workspaceDir`
+2. State file full of Telegram metadata → fix: strip `Conversation info` / `Sender` prefixes
+3. State never updating → "Existing state is meaningful, skipping" → fix: always update
+4. Good state overwritten by bad → fix: require ≥ 2 real user messages to overwrite
+
+### Tested on
+- macOS: GPT-5.4 (openai-codex) ✅
+- Oracle Cloud Linux: MiniMax M2.5 ✅
+- Multiple OpenClaw agents via Telegram ✅
+
+### Known limitations
+- State extraction uses last user/assistant message only (not full summary)
+- Models that ignore `prependSystemContext` won't surface recovered state (state file is preserved, not overwritten). Adding recovery instructions to BOOTSTRAP.md helps.
+
+---
+
+## v2.2.0 — 2026-03-16
+
+### Added
+- `package.json` with npm-style metadata and `openclaw.type: "plugin"` provenance
+- `plugins.allow` auto-configuration in `post-install.sh`
+- GitHub release with comparison table vs vector-DB plugins
+
+### Fixed
+- "plugins.allow is empty" gateway warning
+- "loaded without install/load-path provenance" gateway warning
+
+---
+
 ## v2.1.0 — 2026-03-16
 
-### Summary
-Clean install experience: eliminates gateway provenance warnings for fresh installations.
-
 ### Added
-- `package.json` — proper npm-style metadata with `openclaw.type: "plugin"` provenance field
+- `openclaw.plugin.json` manifest with `configSchema`
-- `plugins.allow` auto-configuration in `post-install.sh` — registers plugin in OpenClaw trust list
+- `scripts/post-install.sh` one-command installer
 
 ### Changed
-- `post-install.sh` now copies `package.json` to extensions directory
+- README updated with "Why this plugin?" section
-- `openclaw.plugin.json` now includes `source` field pointing to GitHub repo
-- README updated with `plugins.allow` documentation and install step
-
-### Fixed
-- "plugins.allow is empty; discovered non-bundled plugins may auto-load" warning
-- "loaded without install/load-path provenance; treat as untracked local code" warning
 
 ---
 
 ## v2.0.0 — 2026-03-15
 
 ### Summary
-Major architecture upgrade: from prompt-based skill to **lifecycle plugin**.
+Architecture upgrade: skill (prompt-based) → **plugin** (lifecycle hooks).
-State injection and extraction now happen automatically via OpenClaw hooks,
-making recovery model-agnostic and reliable across all providers.
 
 ### Added
-- `index.js` — plugin entry point with 5 lifecycle hooks
+- `index.js` with 5 lifecycle hooks: `before_agent_start`, `before_compaction`, `before_reset`, `agent_end`, `session_end`
-- `openclaw.plugin.json` — plugin manifest with configSchema
+- Automated state injection via `prependSystemContext`
-- Automated installer (`scripts/post-install.sh`) that handles copy + config + restart
+- Auto-extraction of working state from conversation
-
-### Changed
-- Architecture: skill (prompt-based) → plugin (hook-based)
-- `before_agent_start` hook injects `CURRENT_STATE.md` into system context automatically
-- `agent_end` hook auto-extracts working state from conversation
-- `before_compaction` hook preserves state through context compression
-- `before_reset` hook archives state before `/new`
-- `session_end` hook ensures state file exists
-- README fully rewritten for plugin architecture
-- post-install.sh rewritten for plugin installation flow
 
 ### Removed
 - Dependency on model cooperation for state read/write
-- Reliance on `skillsSnapshot` cache clearing
-
-### Validated
-- Tested with MiniMax M2.5 and GPT-5.4 on OpenClaw 2026.3.12
-- `/new` recovery: agent correctly surfaces recovered state
-- Multi-turn state: conversation context (secrets, scheduled events) persists across resets
 
 ---
 
-## v0.3.0-probe — 2026-03-13
+## v1.0.0 — 2026-03-14
 
 ### Summary
-Transition from skill-only to dual-form package (skill + lifecycle plugin probe).
+Initial release as a skill (SKILL.md only). Required model to voluntarily read/write `CURRENT_STATE.md`. Did not work reliably with weaker models.
-
-### Added
-- `plugin/lifecycle-prototype.ts`
-- `references/phase2-hook-validation.md`
-
-### Changed
-- Repository direction clarified: primary path is lifecycle plugin
-- ContextEngine documented as future option, not v1 default
-
-### Validated
-- Startup continuity injection on resident subagents
-- Hook wiring confirmed without `read` tool dependency
-
-### Known limitation
-- Skill-based approach unreliable: models can ignore recovery instructions
-- This limitation is resolved in v2.0.0 by moving to hooks

index.js

@@ -238,20 +238,48 @@ const plugin = {
       const statePath = resolveStatePath(ws);
       if (!statePath) return;
 
-      // If there's already a meaningful state file, don't overwrite with
+      const messages = event?.messages;
-      // auto-extracted content (agent or user wrote it explicitly)
+      if (!messages || messages.length === 0) {
-      const existing = readFile(statePath);
+        log.info?.("[memory-continuity] No messages in session, skipping");
-      if (existing && buildSnapshot(existing)) {
-        log.info?.("[memory-continuity] Existing state is meaningful, skipping auto-extract");
         return;
       }
 
-      // Extract from conversation messages
+      // Count real user messages (exclude system, metadata-only, short commands)
-      const newState = extractStateFromMessages(event?.messages);
+      const realUserMsgs = messages.filter(m => {
-      if (!newState) return;
+        if (m?.role !== "user") return false;
+        const text = typeof m?.content === "string" ? m.content
+          : Array.isArray(m?.content) ? m.content.filter(b => b?.type === "text").map(b => b.text).join("\n")
+          : "";
+        const cleaned = text
+          .replace(/^Conversation info \(untrusted metadata\):[\s\S]*?\n\n/m, "")
+          .replace(/^Sender \(untrusted metadata\):[\s\S]*?\n\n/m, "")
+          .trim();
+        // Skip very short messages like "/new", "/status", single-word queries
+        return cleaned.length > 10;
+      });
+
+      // Don't overwrite meaningful state with trivial conversations
+      // (e.g., "/new" then "what was my secret?" — only 1 real message)
+      const existing = readFile(statePath);
+      if (existing && buildSnapshot(existing) && realUserMsgs.length < 2) {
+        log.info?.("[memory-continuity] Conversation too short to overwrite existing state (" + realUserMsgs.length + " real msgs)");
+        return;
+      }
+
+      const newState = extractStateFromMessages(messages);
+      if (!newState) {
+        log.info?.("[memory-continuity] No extractable state from conversation");
+        return;
+      }
+
+      // Archive previous state if it exists
+      if (existing) {
+        const archivePath = statePath.replace(/CURRENT_STATE\.md$/, `STATE_ARCHIVE_${Date.now()}.md`);
+        writeFile(archivePath, existing);
+      }
 
       writeFile(statePath, newState);
-      log.info?.("[memory-continuity] Auto-extracted state from conversation");
+      log.info?.("[memory-continuity] Updated state from conversation (" + realUserMsgs.length + " real msgs)");
     }, { priority: 90 }); // low priority, run after other hooks
 
     // ------------------------------------------------------------------

openclaw.plugin.json

@@ -2,7 +2,7 @@
   "id": "memory-continuity",
   "name": "Memory Continuity",
   "description": "Preserves working state across /new, reset, compaction, and gateway restarts via a simple markdown checkpoint file.",
-  "version": "2.2.0",
+  "version": "2.3.0",
   "source": "https://github.com/dtzp555-max/memory-continuity",
   "configSchema": {
     "type": "object",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "memory-continuity",
-  "version": "2.2.0",
+  "version": "2.3.0",
   "description": "Zero-dependency memory continuity for OpenClaw — plain markdown, lifecycle hooks, no vector DB.",
   "main": "index.js",
   "type": "module",