@psiclawops/hypermem 0.9.5 → 0.9.7

package/CHANGELOG.md

@@ -2,6 +2,18 @@
 
 All notable changes to hypermem are documented here.
 
+## 0.9.7 - 2026-05-02
+
+- **OpenClaw Plugin SDK imports modernized.** HyperCompositor and HyperMem memory now import plugin entry helpers through the canonical public Plugin SDK surface and refresh OpenClaw/Plugin SDK build provenance to the validated runtime.
+- **SDK drift is now actively challenged.** Release gates enforce public SDK imports and exact build metadata for reproducibility, while a latest-SDK canary and Dependabot tracking keep the pin from quietly aging into another compatibility break.
+- **Memory plugin tool contract declared.** `hypermem` now declares ownership of the optional `history_query` tool in its OpenClaw plugin manifest, satisfying the 2026.5.2 plugin checker contract gate.
+- **Plugin checker gates are now standard release infrastructure.** HyperMem CI runs Plugin Inspector static/runtime checks plus isolated dependency-install cold import proof, production/dev dependency audit, and issue-debt validation; publish readiness has a packed-artifact OpenClaw `plugins doctor`/runtime-inspect gate. The previous context-engine root SDK barrel P2 is fixed by deriving context-engine types from the public `OpenClawPluginApi` core type surface.
+
+## 0.9.6 - 2026-05-01
+
+- **OpenClaw 2026.4.29 plugin startup compatibility.** HyperCompositor and HyperMem memory manifests now declare `activation.onStartup: false`, making slot-triggered loading explicit and removing reliance on deprecated implicit startup sidecar fallback behavior.
+- **Release parity preserved.** Core, context-engine plugin, memory plugin, and lockfiles are aligned at 0.9.6 for the compatibility update.
+
 ## 0.9.5 - 2026-04-29
 
 - **Install-readiness defaults hardened.** Fresh installs now stage `embedding.provider: "none"` by default, making the first-install path FTS5-only and free of Ollama or hosted-provider dependencies.
@@ -22,7 +34,7 @@ All notable changes to hypermem are documented here.
 ## 0.9.3 - OpenClaw 2026.4.26 compatibility hardening
 
 - **Plugin manifests declare runtime config schema.** HyperCompositor and HyperMem memory manifests now expose the supported config surface for OpenClaw 2026.4.26 registry/config validation.
-- **Install and doctor flow aligned with persisted plugin registry.** operator guidance and `hypermem-doctor` now include registry refresh, doctor repair, and plugin-list verification steps.
+- **Install and doctor flow aligned with persisted plugin registry.** Operator guidance and `hypermem-doctor` now include registry refresh, doctor repair, and plugin-list verification steps.
 - **Native compaction collision guard added.** `hypermem-doctor` warns when `agents.defaults.compaction.maxActiveTranscriptBytes` is set; HyperMem deployments should leave it unset so HyperMem remains the single trim/compose pressure owner.
 - **Embedding query/document asymmetry supported.** HyperMem config now supports query/document input types and prefixes, with defaults for `nomic-embed-text`, `qwen3-embedding`, and `mxbai-embed-large`.
 - **Forked subagent warm-start repair.** `prepareSubagentSpawn()` falls back to durable runtime history when the hot cache is empty, so forked children inherit parent working context instead of silently starting cold.
@@ -41,7 +53,7 @@ All notable changes to hypermem are documented here.
 - **Vector store init log shows actual provider/model/dims.** Diagnostic log line at startup now reflects the resolved configuration instead of the static placeholder, so misconfiguration is visible immediately.
 - **Tool artifact API arity + hydration docs aligned.** Doc-only follow-ups; no runtime behavior change.
 
-**operator action:** upgrade from 0.9.0 is recommended. 0.9.0 in production with a configured non-default embedder may have written mismatched vectors; check `hypermem-status` for vector-store init line after upgrade.
+**Operator action:** upgrade from 0.9.0 is recommended. 0.9.0 in production with a configured non-default embedder may have written mismatched vectors; check `hypermem-status` for vector-store init line after upgrade.
 
 ## 0.9.0 - adaptive context lifecycle
 
@@ -74,7 +86,7 @@ All notable changes to hypermem are documented here.
 - **Provider + model identity is now tracked explicitly in HyperCompositor model state.** Mid-session routing changes are detected on the full `provider/model` key, not budget alone, so `github-copilot/claude-sonnet-4-6` and `anthropic/claude-sonnet-4-6` are treated as different operational envelopes.
 - **Downshift detection now keys off provider/model-aware state.** Budget-downshift handling still stays conservative, but verbose logs now surface provider swaps, model swaps, and budget deltas clearly during `context:assemble`.
 - **Install docs now declare the full operator path.** README, INSTALL.md, and TUNING.md now separate staging from activation, document install states explicitly, add merge-safe wiring guidance, and clarify what healthy-but-empty looks like on a first run.
-- **0.8.5 release parity.** Package versions are aligned for the next publish while preserving the npm-first installer and merge-safe config guidance landed from Hank's install review.
+- **0.8.5 release parity.** Package versions are aligned for the next publish while preserving the npm-first installer and merge-safe config guidance landed from Pylon's install review.
 
 ## 0.8.4 — compaction fence fix, install-path fixes, zod runtime packaging
 

package/INSTALL.md

@@ -616,7 +616,7 @@ openclaw status                                     # look for hypermem in plugi
 
 ### Step 5 — Configure your fleet
 
-hypermem works out of the box for both single-agent and multi-agent installs. The source ships with generic placeholder agent names (`alice`, `bob`, `director1`, etc.) in two files that define fleet topology:
+hypermem works out of the box for both single-agent and multi-agent installs. The source ships with generic placeholder agent names (`agent1`, `agent2`, `director1`, etc.) in two files that define fleet topology:
 
 | File | What it defines |
 |---|---|
@@ -643,7 +643,7 @@ Facts, episodes, and topics are all scoped to your agent ID automatically. Cross
 
 #### Multi-agent installs
 
-hypermem ships with generic placeholder agent names (`alice`, `bob`, `director1`, etc.) in the two fleet topology files listed above.
+hypermem ships with generic placeholder agent names (`agent1`, `agent2`, `director1`, etc.) in the two fleet topology files listed above.
 
 Replace the placeholder names with your fleet:
 
@@ -651,7 +651,7 @@ Replace the placeholder names with your fleet:
 
 ```typescript
 // Before (placeholder):
-alice: { agentId: 'alice', tier: 'council' },
+agent1: { agentId: 'agent1', tier: 'council' },
 
 // After (your fleet):
 architect: { agentId: 'architect', tier: 'council' },
@@ -661,7 +661,7 @@ architect: { agentId: 'architect', tier: 'council' },
 
 ```typescript
 // Before (placeholder):
-alice: 'infrastructure',
+agent1: 'infrastructure',
 
 // After (your fleet):
 architect: 'infrastructure',
@@ -820,17 +820,14 @@ Resolution order is: (1) `plugins.entries.hypercompositor.config` in `openclaw.j
 
 These settings live in `~/.openclaw/hypermem/config.json` under the `compositor` key. All fields are optional — omit any knob to get the code-level default. Gateway restart required after changes.
 
-The recommended starting config for a standard single-agent deployment is the same recall-friendly profile shipped in `assets/default-config.json` and written by `hypermem-install` when no config exists. It keeps semantic recall active, protects topic-bearing warm context, boosts recent antecedents, and guards the literal antecedent of the current user turn under non-critical pressure.
+The recommended starting config for a standard single-agent deployment is the same recall-friendly context profile shipped in `assets/default-config.json` and written by `hypermem-install` when no config exists. It keeps embeddings disabled for baseline install safety, protects topic-bearing warm context, boosts recent antecedents, and guards the literal antecedent of the current user turn under non-critical pressure. Enable Ollama, OpenRouter, or Gemini after the baseline FTS5 install is verified.
 
-Key 0.9.4 defaults:
+Key starter defaults:
 
 ```json
 {
   "embedding": {
-    "provider": "ollama",
-    "model": "nomic-embed-text",
-    "dims": 768,
-    "dimensions": 768
+    "provider": "none"
   },
   "compositor": {
     "turnBudget": {

package/README.md

@@ -332,7 +332,7 @@ Diagnostics expose reranker status, candidate count, and provider, so operators
 | Knowledge / wiki | Domain knowledge and synthesized topic pages with full-text search |
 | Episodes | Significant events, decisions, discoveries, participants, and source links |
 | Topics | Cross-session thread tracking and topic lifecycle state |
-| Preferences | operator and agent behavior patterns |
+| Preferences | Operator and agent behavior patterns |
 | Documents | Chunked workspace/governance docs, doc sources, and trigger retrieval metadata |
 | Knowledge graph | Links between facts, knowledge, topics, episodes, agents, and preferences |
 | Fleet registry | Agents, orgs, tiers, capabilities, and fleet topology |
@@ -477,7 +477,7 @@ If you prefer, hand the install to your OpenClaw agent:
 
 > "Install hypermem following INSTALL.md. I'm running a [solo / multi-agent] setup."
 
-### operator guides
+### Operator guides
 
 - **[docs/MEMORY_MD_AUTHORING.md](./docs/MEMORY_MD_AUTHORING.md)**, how to keep `MEMORY.md` compact, durable, and reviewable
 - **[docs/TUNING.md](./docs/TUNING.md)**, context assembly and output shaping profiles
@@ -546,7 +546,7 @@ README keeps the interface surface short. Use the detailed docs for exact exampl
 
 **Runtime API:** import `HyperMem` from `@psiclawops/hypermem` for direct Node.js use, custom tests, and non-OpenClaw integrations. See **[INSTALL.md § Non-OpenClaw usage](./INSTALL.md#non-openclaw-usage)** and package TypeScript declarations for the current interface.
 
-**operator CLIs:**
+**Operator CLIs:**
 
 ```bash
 hypermem-status --health
@@ -613,7 +613,7 @@ The migration guide includes worked examples showing how to bring data from Open
 
 All examples default to dry-run. Nothing is written until you add `--apply`.
 
-operator guide: **[docs/MIGRATION_GUIDE.md](./docs/MIGRATION_GUIDE.md)**
+Operator guide: **[docs/MIGRATION_GUIDE.md](./docs/MIGRATION_GUIDE.md)**
 
 
 ---

package/bench/data-access-bench.mjs

@@ -16,7 +16,7 @@ function argValue(name, fallback = null) {
   return process.argv.find((a, i) => process.argv[i - 1] === name) ?? fallback;
 }
 
-const DATA_DIR = argValue('--data-dir', process.env.HYPERMEM_DATA_DIR ?? path.join(process.env.HOME || os.homedir(), '.openclaw', 'hypermem'));
+const DATA_DIR = argValue('--data-dir', process.env.HYPERMEM_DATA_DIR ?? path.join(process.env.HOME || '/home/user', '.openclaw', 'hypermem'));
 const ITERATIONS = parseInt(argValue('--iterations', '100'), 10);
 const WARMUP = parseInt(argValue('--warmup', '3'), 10);
 const TARGET_AGENT = argValue('--agent', null);

package/dist/background-indexer.js

@@ -37,27 +37,27 @@ import { isSafeForSharedVisibility } from './secret-scanner.js';
 // returns results. New agents default to 'general'.
 //
 // ── EXAMPLE DATA ──────────────────────────────────────────────────
-// The agent names below (alice, director1, etc.) are PLACEHOLDERS.
+// The agent names below (agent1, director1, etc.) are PLACEHOLDERS.
 // Replace them with your own agent IDs and domain labels to match
 // your fleet. Single-agent installs don't need to edit this:
 // unknown agents fall through to 'general' automatically.
 // See INSTALL.md § "Configure your fleet" for details.
 // ─────────────────────────────────────────────────────────────────
 const AGENT_DOMAIN_MAP = {
-    alice: 'infrastructure',
+    agent1: 'infrastructure',
     director2: 'infrastructure',
     director1: 'infrastructure',
     director3: 'infrastructure',
-    bob: 'product',
+    agent2: 'product',
     director4: 'product',
     director5: 'product',
     director6: 'product',
-    dave: 'security',
+    agent3: 'security',
     director7: 'security',
     director8: 'security',
     agent4: 'ux',
-    carol: 'governance',
-    oscar: 'strategy',
+    agent6: 'governance',
+    agent5: 'strategy',
     specialist1: 'development',
     specialist2: 'communications',
     main: 'general',
@@ -94,7 +94,7 @@ function extractFactCandidates(content) {
     // Preference patterns — medium confidence (0.60)
     const preferencePatterns = [
         /(?:prefer|always use|never use|don't use|avoid) (.{10,150})/gi,
-        /(?:operator) (?:wants|prefers|likes|hates|dislikes) (.{10,150})/gi,
+        /(?:operator|operator) (?:wants|prefers|likes|hates|dislikes) (.{10,150})/gi,
     ];
     // Operational patterns: deployments, incidents, fixes — high confidence (0.70)
     const operationalPatterns = [
@@ -148,7 +148,7 @@ const OPERATIONAL_BOILERPLATE = [
     /still\s*waiting/i,
     /will\s*pick\s*(it\s*)?up\s*(on\s*(next|the))?/i,
     /message\s*is\s*in\s*(his|her|their|the)\s*queue/i,
-    /sent\s+to\s+(carol|bob|agent4|dave|oscar|alice)/i,
+    /sent\s+to\s+(agent6|agent2|agent4|agent3|agent5|agent1)/i,
     /dispatched\s+(it\s+)?to/i,
     /timed\s*out\s*after/i,
     /\bNO_REPLY\b/,
@@ -393,7 +393,7 @@ function detectTopic(content) {
     if (!content || content.length < 50)
         return null;
     // Product/project name detection
-    const productMatch = content.match(/\b(HyperMem|ClawText|dashboard|canvas|council|automation|OpenClaw|dispatch)\b/i);
+    const productMatch = content.match(/\b(HyperMem|ClawText|ClawDash|ClawCanvas|ClawCouncil|ClawTomation|OpenClaw|ClawDispatch)\b/i);
     if (productMatch)
         return productMatch[1];
     // Infrastructure topic detection

package/dist/cross-agent.d.ts

@@ -27,7 +27,7 @@ export interface OrgRegistry {
  * Default fleet org structure.
  *
  * ── EXAMPLE DATA ──────────────────────────────────────────────────────────
- * The agent names below (alice, bob, director1, etc.) are PLACEHOLDERS.
+ * The agent names below (agent1, agent2, director1, etc.) are PLACEHOLDERS.
  * Replace them with your own agent IDs to match your fleet configuration.
  *
  * Single-agent installs: you don't need to edit this. Your agent ID is

package/dist/cross-agent.js

@@ -21,7 +21,7 @@ import { FleetStore } from './fleet-store.js';
  * Default fleet org structure.
  *
  * ── EXAMPLE DATA ──────────────────────────────────────────────────────────
- * The agent names below (alice, bob, director1, etc.) are PLACEHOLDERS.
+ * The agent names below (agent1, agent2, director1, etc.) are PLACEHOLDERS.
  * Replace them with your own agent IDs to match your fleet configuration.
  *
  * Single-agent installs: you don't need to edit this. Your agent ID is
@@ -34,27 +34,27 @@ import { FleetStore } from './fleet-store.js';
  */
 export function defaultOrgRegistry() {
     const agents = {
-        alice: { agentId: 'alice', tier: 'council' },
-        bob: { agentId: 'bob', tier: 'council' },
+        agent1: { agentId: 'agent1', tier: 'council' },
+        agent2: { agentId: 'agent2', tier: 'council' },
         agent4: { agentId: 'agent4', tier: 'council' },
-        dave: { agentId: 'dave', tier: 'council' },
-        carol: { agentId: 'carol', tier: 'council' },
-        oscar: { agentId: 'oscar', tier: 'council' },
-        director1: { agentId: 'director1', tier: 'director', org: 'alice-org', councilLead: 'alice' },
-        director2: { agentId: 'director2', tier: 'director', org: 'alice-org', councilLead: 'alice' },
-        director3: { agentId: 'director3', tier: 'director', org: 'alice-org', councilLead: 'alice' },
-        director4: { agentId: 'director4', tier: 'director', org: 'bob-org', councilLead: 'bob' },
-        director5: { agentId: 'director5', tier: 'director', org: 'bob-org', councilLead: 'bob' },
-        director6: { agentId: 'director6', tier: 'director', org: 'bob-org', councilLead: 'bob' },
-        director7: { agentId: 'director7', tier: 'director', org: 'dave-org', councilLead: 'dave' },
-        director8: { agentId: 'director8', tier: 'director', org: 'dave-org', councilLead: 'dave' },
+        agent3: { agentId: 'agent3', tier: 'council' },
+        agent6: { agentId: 'agent6', tier: 'council' },
+        agent5: { agentId: 'agent5', tier: 'council' },
+        director1: { agentId: 'director1', tier: 'director', org: 'agent1-org', councilLead: 'agent1' },
+        director2: { agentId: 'director2', tier: 'director', org: 'agent1-org', councilLead: 'agent1' },
+        director3: { agentId: 'director3', tier: 'director', org: 'agent1-org', councilLead: 'agent1' },
+        director4: { agentId: 'director4', tier: 'director', org: 'agent2-org', councilLead: 'agent2' },
+        director5: { agentId: 'director5', tier: 'director', org: 'agent2-org', councilLead: 'agent2' },
+        director6: { agentId: 'director6', tier: 'director', org: 'agent2-org', councilLead: 'agent2' },
+        director7: { agentId: 'director7', tier: 'director', org: 'agent3-org', councilLead: 'agent3' },
+        director8: { agentId: 'director8', tier: 'director', org: 'agent3-org', councilLead: 'agent3' },
         specialist1: { agentId: 'specialist1', tier: 'specialist' },
         specialist2: { agentId: 'specialist2', tier: 'specialist' },
     };
     const orgs = {
-        'alice-org': ['alice', 'director1', 'director2', 'director3'],
-        'bob-org': ['bob', 'director4', 'director5', 'director6'],
-        'dave-org': ['dave', 'director7', 'director8'],
+        'agent1-org': ['agent1', 'director1', 'director2', 'director3'],
+        'agent2-org': ['agent2', 'director4', 'director5', 'director6'],
+        'agent3-org': ['agent3', 'director7', 'director8'],
     };
     return { orgs, agents };
 }

package/dist/index.d.ts

@@ -135,8 +135,8 @@ export interface StartupFleetSeedResult {
  *
  * Usage:
  *   const hm = await hypermem.create({ dataDir: '~/.openclaw/hypermem' });
- *   await hm.record('alice', 'agent:alice:webchat:main', userMsg);
- *   const result = await hm.compose({ agentId: 'alice', sessionKey: '...', ... });
+ *   await hm.record('agent1', 'agent:agent1:webchat:main', userMsg);
+ *   const result = await hm.compose({ agentId: 'agent1', sessionKey: '...', ... });
  */
 export declare class HyperMem {
     readonly dbManager: DatabaseManager;
@@ -202,7 +202,7 @@ export declare class HyperMem {
     /**
      * List archived or forked contexts for an agent.
      *
-     * operator-safe enumeration path. This is the approved archived-context
+     * Operator-safe enumeration path. This is the approved archived-context
      * listing surface. Active composition remains separate.
      */
     listArchivedContexts(agentId: string, opts?: {

package/dist/index.js

@@ -103,7 +103,7 @@ const DEFAULT_CONFIG = {
     cache: {
         keyPrefix: 'hm:',
         sessionTTL: 14400, // 4 hours — system/identity/meta slots
-        historyTTL: 604800, // 7 days — extended for canvas display
+        historyTTL: 604800, // 7 days — extended for ClawCanvas display
     },
     compositor: {
         // TUNE-010 (2026-04-02): Raised from 65000 → 90000.
@@ -337,8 +337,8 @@ function discoverStartupFleetCandidates(dbManager, opts = {}) {
  *
  * Usage:
  *   const hm = await hypermem.create({ dataDir: '~/.openclaw/hypermem' });
- *   await hm.record('alice', 'agent:alice:webchat:main', userMsg);
- *   const result = await hm.compose({ agentId: 'alice', sessionKey: '...', ... });
+ *   await hm.record('agent1', 'agent:agent1:webchat:main', userMsg);
+ *   const result = await hm.compose({ agentId: 'agent1', sessionKey: '...', ... });
  */
 export class HyperMem {
     dbManager;
@@ -604,7 +604,7 @@ export class HyperMem {
     /**
      * List archived or forked contexts for an agent.
      *
-     * operator-safe enumeration path. This is the approved archived-context
+     * Operator-safe enumeration path. This is the approved archived-context
      * listing surface. Active composition remains separate.
      */
     listArchivedContexts(agentId, opts) {

package/dist/seed.d.ts

@@ -6,7 +6,7 @@
  *
  * Usage:
  *   const seeder = new WorkspaceSeeder(hypermem);
- *   const result = await seeder.seedWorkspace('/path/to/workspace', { agentId: 'alice' });
+ *   const result = await seeder.seedWorkspace('/path/to/workspace', { agentId: 'agent1' });
  *
  * Idempotent: skips files whose source hash hasn't changed since last index.
  * Atomic: each file's chunks are swapped in a single transaction.

package/dist/seed.js

@@ -6,7 +6,7 @@
  *
  * Usage:
  *   const seeder = new WorkspaceSeeder(hypermem);
- *   const result = await seeder.seedWorkspace('/path/to/workspace', { agentId: 'alice' });
+ *   const result = await seeder.seedWorkspace('/path/to/workspace', { agentId: 'agent1' });
  *
  * Idempotent: skips files whose source hash hasn't changed since last index.
  * Atomic: each file's chunks are swapped in a single transaction.

package/dist/session-flusher.d.ts

@@ -33,8 +33,8 @@ export interface FlushSessionResult {
  * from those stores naturally.
  *
  * @param cache   Connected CacheLayer instance
- * @param agentId Agent identifier (e.g. "alice")
- * @param sessionKey  Full session key (e.g. "agent:alice:webchat:scratchpad")
+ * @param agentId Agent identifier (e.g. "agent1")
+ * @param sessionKey  Full session key (e.g. "agent:agent1:webchat:scratchpad")
  * @param opts    Optional flags
  */
 export declare function flushSession(cache: CacheLayer, agentId: string, sessionKey: string, opts?: FlushSessionOptions): Promise<FlushSessionResult>;

package/dist/session-flusher.js

@@ -18,8 +18,8 @@
  * from those stores naturally.
  *
  * @param cache   Connected CacheLayer instance
- * @param agentId Agent identifier (e.g. "alice")
- * @param sessionKey  Full session key (e.g. "agent:alice:webchat:scratchpad")
+ * @param agentId Agent identifier (e.g. "agent1")
+ * @param sessionKey  Full session key (e.g. "agent:agent1:webchat:scratchpad")
  * @param opts    Optional flags
  */
 export async function flushSession(cache, agentId, sessionKey, opts = {}) {

package/dist/spawn-context.d.ts

@@ -6,7 +6,7 @@
  *
  * Usage:
  *   const ctx = await buildSpawnContext(messageStore, docChunkStore, agentId, {
- *     parentSessionKey: 'agent:alice:webchat:main',
+ *     parentSessionKey: 'agent:agent1:webchat:main',
  *     workingSnapshot: 10,
  *     documents: ['/path/to/spec.md'],
  *   });

package/dist/spawn-context.js

@@ -6,7 +6,7 @@
  *
  * Usage:
  *   const ctx = await buildSpawnContext(messageStore, docChunkStore, agentId, {
- *     parentSessionKey: 'agent:alice:webchat:main',
+ *     parentSessionKey: 'agent:agent1:webchat:main',
  *     workingSnapshot: 10,
  *     documents: ['/path/to/spec.md'],
  *   });

package/dist/topic-store.js

@@ -12,12 +12,12 @@
 const KNOWN_NAMES = {
     hypermem: 'HyperMem',
     hyperbuilder: 'HyperBuilder',
-    canvas: 'canvas',
-    dashboard: 'dashboard',
-    dispatch: 'dispatch',
+    clawcanvas: 'ClawCanvas',
+    clawdash: 'ClawDash',
+    clawdispatch: 'ClawDispatch',
     clawtext: 'ClawText',
-    automation: 'automation',
-    council: 'council',
+    clawtomation: 'ClawTomation',
+    clawcouncil: 'ClawCouncil',
     openclaw: 'OpenClaw',
     clawhub: 'ClawHub',
 };

package/dist/topic-synthesizer.js

@@ -35,7 +35,7 @@ function keystoneScore(msg) {
     const backtickMatches = text.match(/`[^`]+`/g) || [];
     score += backtickMatches.length * 0.2;
     // Agent mentions (known patterns)
-    const agentMentions = text.match(/\b(alice|bob|agent4|dave|oscar|carol|director1|director2|director7|specialist2|specialist1)\b/gi) || [];
+    const agentMentions = text.match(/\b(agent1|agent2|agent4|agent3|agent5|agent6|director1|director2|director7|specialist2|specialist1)\b/gi) || [];
     score += agentMentions.length * 0.25;
     // Quoted content
     const quotedMatches = text.match(/"[^"]{10,}"/g) || [];

package/dist/trigger-registry.d.ts

@@ -39,7 +39,7 @@ export interface CollectionTrigger {
 export declare const TRIGGER_REGISTRY_VERSION = "1.0.0";
 /**
  * Default trigger registry for standard ACA collections.
- * Covers the core ACA offload use case from carol's spec.
+ * Covers the core ACA offload use case from agent6's spec.
  */
 export declare const TRIGGER_REGISTRY: CollectionTrigger[];
 /** Backward-compat alias — same reference as TRIGGER_REGISTRY */

package/dist/trigger-registry.js

@@ -13,7 +13,7 @@ import { createHash } from 'node:crypto';
 export const TRIGGER_REGISTRY_VERSION = '1.0.0';
 /**
  * Default trigger registry for standard ACA collections.
- * Covers the core ACA offload use case from carol's spec.
+ * Covers the core ACA offload use case from agent6's spec.
  */
 export const TRIGGER_REGISTRY = [
     {
@@ -69,7 +69,7 @@ export const TRIGGER_REGISTRY = [
         ],
         maxTokens: 800,
         maxChunks: 2,
-        owner: 'alice',
+        owner: 'agent1',
         category: 'operations',
         description: 'Agent operational procedures: boot sequence, heartbeat, work queue, session startup',
     },
@@ -106,7 +106,7 @@ export const TRIGGER_REGISTRY = [
         ],
         maxTokens: 1500,
         maxChunks: 4,
-        owner: 'alice',
+        owner: 'agent1',
         category: 'memory',
         description: 'Decision history: past choices, previously agreed approaches, recalled context',
     },
@@ -132,7 +132,7 @@ export const TRIGGER_REGISTRY = [
         ],
         maxTokens: 1200,
         maxChunks: 3,
-        owner: 'alice',
+        owner: 'agent1',
         category: 'operations',
         description: 'Agent tooling reference: CLI commands, config paths, deployment procedures, quick reference',
     },

package/dist/types.d.ts

@@ -72,7 +72,7 @@ export type FactScope = 'agent' | 'session' | 'user';
 /**
  * Memory visibility levels:
  * - private:  Only the owning agent can read. Identity, SOUL, personal reflections.
- * - org:      Agents in the same org (e.g., alice's directors: Hank, Jack, Irene).
+ * - org:      Agents in the same org (e.g., agent1's directors: Pylon, Vigil, Plane).
  * - council:  All council seats can read.
  * - fleet:    Any agent in the fleet can read.
  */
@@ -654,7 +654,7 @@ export interface ProviderMessage {
  * to identify high-signal unprocessed messages.
  *
  * Stored in Redis (hm:{a}:s:{s}:cursor) with dual-write to SQLite for
- * durability across Redis eviction (bob Gate 2).
+ * durability across Redis eviction (agent2 Gate 2).
  */
 export interface SessionCursor {
     /** StoredMessage.id of the newest message included in the last window */

package/docs/DIAGNOSTICS.md

@@ -7,18 +7,33 @@ HyperMem diagnostics are split into operator CLIs, validation scripts, and runti
 | Surface | Command | Proves |
 |---|---|---|
 | Health summary | `hypermem-status --health` | data dir, SQLite health, basic runtime state |
-| operator dashboard | `hypermem-status --master` | concise fleet-facing status summary |
+| Operator dashboard | `hypermem-status --master` | concise fleet-facing status summary |
 | JSON status | `hypermem-status --json` | machine-readable database and runtime state |
 | Model audit | `hypermem-model-audit --strict` | active models have known context-window behavior or overrides |
 | Memory benchmark | `hypermem-bench --iterations 1000 --warmup 50 --agent <agent>` | local dataset access latency with p50/p95/p99 timings |
 | Compose report | `node scripts/compose-report.mjs` | direct compositor slot selection, budget decisions, diagnostics fields |
 | Trim report | `node scripts/trim-report.mjs` | trim events, cache invalidation, pressure behavior |
 | Version parity | `npm run validate:version-parity` | package versions and plugin dependencies are release-aligned |
+| SDK import policy | `npm run validate:sdk-imports` | plugin packages use public OpenClaw Plugin SDK entrypoints and pinned build metadata |
+| Latest SDK canary | `npm run validate:sdk-latest-canary` | both plugin packages still typecheck and build against the latest published OpenClaw SDK |
+| Plugin compatibility gates | `npm run validate:plugin-checkers` | Plugin Inspector static/runtime reports, isolated dependency-install cold import proof, production/dev dependency audit, and zero unhandled Plugin Inspector issue debt |
+| OpenClaw plugin runtime gate | `npm run validate:plugins:runtime` | packed artifact installs into OpenClaw's plugin runtime, registry refreshes, plugin doctor passes for HyperMem-owned plugins, and runtime inspection is clean |
 | Release path | `npm run validate:release-path` | build plus plugin pipeline gateway path |
 | Docs/config validation | `npm run validate:docs && npm run validate:config` | documented commands and config surfaces match code |
 | History query validation | `npm run validate:history-query` | `MessageStore.queryHistory()`, `history_query` plugin tool, metadata-only telemetry, and health JSON surface are wired |
 | Fresh-install smoke gate | `npm run release:install-smoke` | packed npm artifact installs without source fallback, no-Ollama failure is clear, skip-mode stages, existing config is preserved, and failure artifacts are captured |
 
+## Plugin compatibility gates
+
+Use the smallest gate that matches the decision.
+
+- Sprint completion / PR readiness: `npm run validate:plugin-checkers`. This runs Plugin Inspector static/runtime reports, proves dependency-install cold import in isolated npm workspaces, audits production and plugin dev dependencies, and fails if any Plugin Inspector issue lacks proof-backed coverage.
+- Publish readiness on an OpenClaw host: `npm run validate:plugins:runtime`. This installs the packed 0.9.x-shaped artifact, refreshes the OpenClaw plugin registry, runs `openclaw plugins doctor`, and inspects both HyperMem plugins with `--runtime`.
+
+`openclaw plugins doctor` is not a replacement for Plugin Inspector. Doctor proves the installed artifact satisfies the current host loader. Plugin Inspector proves the package remains compatible as a plugin project and produces durable CI artifacts. The full release gate runs both because either one alone can lie. That's how you buy fewer 3am pages.
+
+As of 0.9.7, Plugin Inspector's raw reports can still surface `package-dependency-install-required` as an inspector-owned P2 because Plugin Inspector 0.3.6 does not reconcile dependency-install proof artifacts. HyperMem does not ignore that row: `validate:plugin-checkers` runs `validate:plugin-isolated-cold-import`, writes proof under `.artifacts/plugin-isolated-cold-import/`, and `validate:plugin-inspector:debt` fails on any Plugin Inspector issue without proof-backed coverage. P0/P1/live issues, deprecations, hard breakages, production or plugin dev audit findings, unproved inspector gaps, and HyperMem-owned `openclaw plugins doctor` diagnostics block publish.
+
 ## `hypermem-status`
 
 Primary uses:

package/docs/INTEGRATION_VALIDATION.md

@@ -143,6 +143,9 @@ Before publishing a release, run:
 
 ```bash
 npm run validate:version-parity
+npm run validate:sdk-imports
+npm run validate:sdk-latest-canary
+npm run validate:plugin-checkers
 npm run validate:docs
 npm run validate:config
 npm run validate:release-path
@@ -154,6 +157,10 @@ npm pack ./plugin --dry-run
 npm pack ./memory-plugin --dry-run
 ```
 
+The SDK gates are split deliberately: `validate:sdk-imports` enforces reproducible pinned OpenClaw Plugin SDK metadata, while `validate:sdk-latest-canary` rebuilds both plugin packages against the latest published OpenClaw SDK in a temp workspace so a stale pin cannot hide a future import break.
+
+The plugin checker gate is deliberately composite: it runs Plugin Inspector static/runtime reports, isolated dependency-install cold import proof, production/dev dependency audit, Plugin Inspector issue-debt validation for the plugin packages. Raw Plugin Inspector P2 rows are not ignored: they must either disappear or have a proof artifact consumed by `validate:plugin-inspector:debt`.
+
 Runtime validation must install the packed artifact, not the repo working tree. The production-shaped local install path is:
 
 ```bash
@@ -163,6 +170,14 @@ openclaw plugins list
 node ~/.openclaw/plugins/hypermem/bin/hypermem-status.mjs --master
 ```
 
+The final OpenClaw host-runtime plugin checker is:
+
+```bash
+npm run validate:plugins:runtime
+```
+
+That gate packs and installs the release artifact into OpenClaw's managed plugin directory, refreshes the plugin registry, runs `openclaw plugins doctor`, and runs runtime inspection for `hypercompositor` and `hypermem`. Treat HyperMem-owned doctor diagnostics as release-blocking. Unrelated local plugin diagnostics are reported but ignored by the HyperMem gate.
+
 For isolated validation, test the packed artifact from a temp directory:
 
 ```bash

package/docs/MIGRATION.md

@@ -2,7 +2,7 @@
 
 Start here.
 
-- **operator guide:** [`MIGRATION_GUIDE.md`](./MIGRATION_GUIDE.md)
+- **Operator guide:** [`MIGRATION_GUIDE.md`](./MIGRATION_GUIDE.md)
 - **Current repo state:** source-specific migration examples live in `MIGRATION_GUIDE.md`. There is no bundled unified migration dispatcher in this repo yet.
 
 All migration examples default to **dry-run** where shown. Add `--apply` only when you are ready to write data.

package/memory-plugin/dist/index.d.ts

@@ -18,7 +18,7 @@ declare const _default: {
     id: string;
     name: string;
     description: string;
-    configSchema: import("openclaw/plugin-sdk").OpenClawPluginConfigSchema;
-    register: NonNullable<import("openclaw/plugin-sdk/plugin-entry").OpenClawPluginDefinition["register"]>;
-} & Pick<import("openclaw/plugin-sdk/plugin-entry").OpenClawPluginDefinition, "kind" | "reload" | "nodeHostCommands" | "securityAuditCollectors">;
+    configSchema: import("openclaw/plugin-sdk/core").OpenClawPluginConfigSchema;
+    register: NonNullable<import("openclaw/plugin-sdk/core").OpenClawPluginDefinition["register"]>;
+} & Pick<import("openclaw/plugin-sdk/core").OpenClawPluginDefinition, "kind" | "reload" | "nodeHostCommands" | "securityAuditCollectors">;
 export default _default;

package/memory-plugin/dist/index.js

@@ -14,7 +14,7 @@
  *
  * Both plugins share the same HyperMem singleton (loaded from repo dist).
  */
-import { definePluginEntry, emptyPluginConfigSchema } from 'openclaw/plugin-sdk/plugin-entry';
+import { definePluginEntry, emptyPluginConfigSchema } from 'openclaw/plugin-sdk/core';
 import { matchTriggers, TRIGGER_REGISTRY } from '@psiclawops/hypermem';
 import path from 'path';
 import fs from 'fs/promises';

package/memory-plugin/openclaw.plugin.json

@@ -5,6 +5,12 @@
   "activation": {
     "onCapabilities": [
       "memory"
+    ],
+    "onStartup": false
+  },
+  "contracts": {
+    "tools": [
+      "history_query"
     ]
   },
   "configSchema": {