fix(agent-plugins): match memo prompts and tool descriptions, release 0.3.3 (#7420)

Co-authored-by: Claude <noreply@anthropic.com>

integrations/pi-agent-plugin/README.md

@@ -71,7 +71,7 @@ The plugin includes 6 skills that guide the agent on how to use each capability:
 
 | Skill | Purpose |
 |-------|---------|
-| `context-loader` | Pre-fetch relevant memories at session start |
+| `context-loader` | Search memories when earlier work may already explain the task |
 | `remember` | Store facts with category classification |
 | `search` | Quick semantic search with compact results |
 | `forget` | Delete memories with confirmation |

integrations/pi-agent-plugin/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mem0/pi-agent-plugin",
-  "version": "0.3.1",
+  "version": "0.3.2",
   "type": "module",
   "description": "Mem0 memory extension for Pi Agent persistent, scoped, semantic memory across sessions and projects",
   "license": "Apache-2.0",

integrations/pi-agent-plugin/skills/context-loader/SKILL.md

@@ -1,34 +1,19 @@
 ---
 name: context-loader
-description: Searches and injects relevant memories into context before starting work on a task or topic. Use when beginning a new task, switching context, or when past decisions, preferences, or knowledge need to be loaded.
+description: Search memories from earlier Pi sessions in this repository. Use it when earlier work may already explain the code, error, decision, or command you need, so you can avoid repeating file reads, searches, or experiments.
 ---
 
 # Context Loader
 
 Pre-fetches relevant memories to prime context before working on a task or topic.
 
-## When to use
-
-- Session start (auto-triggered by the extension's `before_agent_start` event)
-- User starts work on a specific topic or area
-- User says "what do we know about X" or "context for X"
-
 ## Steps
 
 1. **Extract topics** from current message/task. Identify: subject areas, people mentioned, project names, goal references.
 
-2. **Run 2-4 parallel searches** using `mem0_memory` tool with `action="search"` and different query angles:
+2. **Call `mem0_memory` once** with `action="search"` and a focused question about the task.
 
-   | Query angle | Purpose |
-   |---|---|
-   | Topic/subject name | Relevant decisions and preferences |
-   | People mentioned | Relationship context |
-   | Project/goal references | Progress and background |
-   | Broad context | Catch-all for anything relevant |
-
-3. **Deduplicate** results by memory ID across all search responses.
-
-4. **Output compact context block** (max 10 memories):
+3. **Output compact context block** (max 10 memories):
 
 ```
 context-loader: loaded <N> memories for "<task summary>"
@@ -37,7 +22,7 @@ context-loader: loaded <N> memories for "<task summary>"
   - [lessons] <content> [mem0:<short_id>]
 ```
 
-5. If **zero results**: output nothing. Don't announce empty context.
+4. If **zero results**: output nothing. Don't announce empty context.
 
 ## Constraints
 

integrations/pi-agent-plugin/src/memory/tools.ts

@@ -1,4 +1,5 @@
 import { resolveToolScope } from "../../../agent-plugin-core/typescript/src/scoping.ts";
+import { SEARCH_QUERY_DESCRIPTION, SEARCH_WHEN } from "../../../agent-plugin-core/typescript/src/prompts.ts";
 import type { ExtensionAPI } from "@earendil-works/pi-coding-agent";
 import { Type } from "typebox";
 import { StringEnum } from "@earendil-works/pi-ai";
@@ -144,11 +145,10 @@ export function registerMemoryTool(
     name: "mem0_memory",
     label: "Mem0 Memory",
     description:
-      "Search, add, update, and manage persistent semantic memories powered by Mem0. Memories persist across sessions and devices. Use action \"search\" proactively -- before answering anything that may depend on what the user told you earlier -- and run multiple searches with different phrasings for multi-part questions. Output is truncated to 200 lines / 50KB.",
+      `Search, add, update, and manage persistent semantic memories powered by Mem0. Memories persist across sessions and devices. Use action "search" ${SEARCH_WHEN}. Output is truncated to 200 lines / 50KB.`,
     promptSnippet: "Semantic memory search and storage via Mem0",
     promptGuidelines: [
-      'Use mem0_memory with action "search" proactively whenever the request may depend on the user\'s past work, preferences, decisions, or environment -- not only when they explicitly mention the past',
-      'For multi-part or comparative questions, run several searches with different phrasings and combine the results before answering -- one search is rarely enough',
+      `Use mem0_memory with action "search" ${SEARCH_WHEN}`,
       'Use mem0_memory with action "add" to save important facts, preferences, goals, decisions, or lessons the user shares',
       'Use mem0_memory with action "update" to modify an existing memory — requires memory_id and content. Preserves the memory ID',
       "Always use the default project scope unless the user EXPLICITLY asks to search across all projects — only after the user selects /mem0-scope global use scope \"global\"",
@@ -166,13 +166,13 @@ export function registerMemoryTool(
         ] as const,
         {
           description:
-            "Memory operation to run: \"search\" (semantic recall -- use proactively before answering; run several with different phrasings for multi-part questions), \"add\" (save a new fact/preference/decision), \"get_all\" (list everything in scope, no query needed), \"update\" (replace an existing memory's text by id), \"delete\" (remove one memory by id), \"delete_all\" (wipe every memory in the scope -- destructive, only on explicit request).",
+            "Memory operation to run: \"search\" (semantic recall of earlier work in this repository), \"add\" (save a new fact/preference/decision), \"get_all\" (list everything in scope, no query needed), \"update\" (replace an existing memory's text by id), \"delete\" (remove one memory by id), \"delete_all\" (wipe every memory in the scope -- destructive, only on explicit request).",
         },
       ),
       query: Type.Optional(
         Type.String({
           description:
-            "Search text -- required for action \"search\". Use a focused noun-phrase; for multi-part questions run several searches with different phrasings.",
+            `Search text -- required for action "search". ${SEARCH_QUERY_DESCRIPTION}`,
         }),
       ),
       content: Type.Optional(

integrations/pi-agent-plugin/src/prompt.ts

@@ -1,10 +1,9 @@
-export const MEMORY_POLICY = `<mem0-memory-policy>
-You have persistent semantic memory via the mem0_memory tool, powered by Mem0. Relevant memories may be auto-injected under <mem0-relevant-memories>, but that retrieval is shallow — treat it as a starting point, not the full picture.
+import { SEARCH_WHEN } from "../../agent-plugin-core/typescript/src/prompts.ts";
 
-Be proactive about retrieval:
-- Search memory BEFORE answering whenever the request could depend on the user's past work, preferences, decisions, environment, or anything they told you earlier — don't wait to be asked.
-- Check memory before asking the user something they may have already told you.
-- For multi-part, comparative, or "how did we…" questions, run SEVERAL searches with different phrasings and combine the results. One search is rarely enough — keep going until you have what you need (multi-hop).
+export const MEMORY_POLICY = `<mem0-memory-policy>
+You have persistent semantic memory via the mem0_memory tool, powered by Mem0. Relevant memories may be auto-injected under <mem0-relevant-memories>.
+
+Use mem0_memory with action "search" ${SEARCH_WHEN}.
 
 Be proactive about saving:
 - Save important facts, preferences, goals, decisions, lessons learned, identity, relationships, and routines the user shares.