The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
fix(mem0-plugin): store assistant-authored summaries with role="assistant" (#6316)
Kartikd6d2588ef516
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.jsonindex 51668aff8..6954d4af7 100644--- a/.claude-plugin/marketplace.json+++ b/.claude-plugin/marketplace.json@@ -12,7 +12,7 @@"name": "mem0","source": "./integrations/mem0-plugin","description": "Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search to Claude workflows.",- "version": "0.2.12"+ "version": "0.2.13"}]}diff --git a/.cursor-plugin/marketplace.json b/.cursor-plugin/marketplace.jsonindex 40527fb93..2dae82c22 100644--- a/.cursor-plugin/marketplace.json+++ b/.cursor-plugin/marketplace.json@@ -12,7 +12,7 @@"name": "mem0","source": "./integrations/mem0-plugin","description": "Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search.",- "version": "0.2.12"+ "version": "0.2.13"}]}diff --git a/docs/changelog/sdk.mdx b/docs/changelog/sdk.mdxindex d2b480e9d..7543c8b98 100644--- a/docs/changelog/sdk.mdx+++ b/docs/changelog/sdk.mdx@@ -1825,6 +1825,15 @@ A full-featured command-line interface for Mem0, available in both Python and No<Tabs><Tab title="Mem0 Plugin">+<Update label="2026-07-14" description="mem0-plugin v0.2.13">++**Fixes:**+- **Assistant messages no longer stored as your own:** The session-summary hook (fires at the end of every assistant turn) and the post-compaction hook were sending the assistant's own message to Mem0 tagged `role: "user"`. Because Mem0 extracts *facts about the user* from each message and uses `role` to decide who spoke, the assistant's first-person prose was being saved as the human's stated preferences — "I recommend we drop Redis" became `User prefers dropping Redis entirely`. Both hooks now send `role: "assistant"`, so the same session is stored as `Assistant recommended...`. Affects Claude Code, Cursor, Codex, and Antigravity, which share these hooks.++Existing memories written by the previous versions are not rewritten. If your memories contain preferences you never expressed, delete them — the plugin will not recreate them.++</Update>+<Update label="2026-06-30" description="mem0-plugin v0.2.12">**New Features:**@@ -2148,6 +2157,15 @@ Initial release of the Mem0 plugin for Claude Code and Cursor, followed by Codex<Tab title="Antigravity">+<Update label="2026-07-14" description="Antigravity plugin v0.1.5">++**Fixes:**+- **Assistant messages no longer stored as your own:** The session-summary hook (fires at the end of every assistant turn) and the post-compaction hook were sending the assistant's own message to Mem0 tagged `role: "user"`. Because Mem0 extracts *facts about the user* from each message and uses `role` to decide who spoke, the assistant's first-person prose was being saved as the human's stated preferences — "I recommend we drop Redis" became `User prefers dropping Redis entirely`. Both hooks now send `role: "assistant"`, so the same session is stored as `Assistant recommended...`.++Existing memories written by the previous versions are not rewritten. If your memories contain preferences you never expressed, delete them — the plugin will not recreate them.++</Update>+<Update label="2026-06-30" description="Antigravity plugin v0.1.4">**New Features:**diff --git a/docs/integrations/antigravity.mdx b/docs/integrations/antigravity.mdxindex c76ecd7f6..f759e7ec9 100644--- a/docs/integrations/antigravity.mdx+++ b/docs/integrations/antigravity.mdx@@ -65,7 +65,9 @@ The plugin uses the same shell scripts as Claude Code, Cursor, and Codex: hooks| **User prompt** | `UserPromptSubmit` | Searches relevant memories before each message || **Pre-tool** | `PreToolUse` | Blocks MEMORY.md writes, enforces `user_id`/`app_id` on mem0 tools || **Post-tool** | `PostToolUse` | Tracks stats, scans bash errors for related memories |-| **Stop** | `Stop` | Stores a session summary when the session ends |+| **Stop** | `Stop` | Stores a session summary at the end of every assistant turn (not just at session end) |++What you type is stored as yours. What the agent produces — session summaries and compaction summaries — is stored as the assistant's, so its suggestions never become your stated preferences.## Troubleshootingdiff --git a/docs/integrations/claude-code.mdx b/docs/integrations/claude-code.mdxindex a571f813d..7e6df670e 100644--- a/docs/integrations/claude-code.mdx+++ b/docs/integrations/claude-code.mdx@@ -143,9 +143,11 @@ When installed via the plugin marketplace, Mem0 hooks into Claude Code's lifecyc| **User prompt** | `UserPromptSubmit` | Searches relevant memories before each message; skips short prompts || **Pre-tool (3 handlers)** | `PreToolUse` | Blocks MEMORY.md writes; enforces `user_id`/`app_id` on mem0 tool calls; scans files being read for relevant memory context || **Post-tool** | `PostToolUse` | Tracks stats, scans bash errors for related memories |-| **Stop** | `Stop` | Stores a session summary when the session ends |+| **Stop** | `Stop` | Stores a session summary at the end of every assistant turn (not just at session end) || **Pre-compact** | `PreCompact` | Stores a summary before the context is compacted |+What you type is stored as yours. What Claude produces — session summaries and compaction summaries — is stored as the assistant's, so its suggestions never become your stated preferences.+## Example Workflow```text@@ -153,16 +155,17 @@ When installed via the plugin marketplace, Mem0 hooks into Claude Code's lifecycYou: Let's refactor the auth module to use JWT tokens instead of sessions.# Claude searches memories, finds nothing relevant, proceeds with the work.-# After completing the task, Mem0 stores:+# Mem0 stores what you said as yours:+# - Your preference: "Prefers TypeScript, uses ESLint"+# ...and what Claude did as the assistant's, in the session summary:# - Decision: "Migrated auth from sessions to JWT tokens"# - Files modified: auth/middleware.ts, auth/token.ts-# - User preference: "Prefers TypeScript, uses ESLint"# Session 2 (days later): Related workYou: Add refresh token rotation to the auth system.# Claude searches memories, retrieves the JWT migration context.-# Knows the file structure, decisions made, and user preferences.+# Knows the file structure, decisions made, and your stated preferences.# Continues seamlessly without re-explaining the codebase.```diff --git a/docs/integrations/codex.mdx b/docs/integrations/codex.mdxindex 5737a579e..d06d228dd 100644--- a/docs/integrations/codex.mdx+++ b/docs/integrations/codex.mdx@@ -125,20 +125,23 @@ When installed via the plugin marketplace, Mem0 hooks into Codex's lifecycle to| **User prompt** | `UserPromptSubmit` | Searches relevant memories before each message || **Pre-tool (3 handlers)** | `PreToolUse` | Blocks MEMORY.md writes; enforces `user_id`/`app_id` on mem0 tool calls; scans files being read for relevant memory context || **Post-tool** | `PostToolUse` | Tracks stats, scans bash errors for related memories |-| **Stop** | `Stop` | Stores a session summary when the session ends |+| **Stop** | `Stop` | Stores a session summary at the end of every assistant turn (not just at session end) || **Pre-compact** | `PreCompact` | Stores a summary before the context is compacted |+What you type is stored as yours. What Codex produces — session summaries and compaction summaries — is stored as the assistant's, so its suggestions never become your stated preferences.+## Example Workflow```text# Task 1: Setting up a new serviceYou: Create a REST API for the notifications service using Express and TypeScript.-# Codex searches memories, finds user preferences from prior tasks.-# After completing the task, Mem0 stores:+# Codex searches memories, finds your preferences from prior tasks.+# Mem0 stores what you said as yours:+# - Your preference: "Prefers explicit error types over generic catch-all"+# ...and what Codex did as the assistant's, in the session summary:# - Decision: "Notifications service uses Express + TypeScript + Zod validation"# - Convention: "All API routes follow /api/v1/{resource} pattern"-# - Preference: "User prefers explicit error types over generic catch-all"# Task 2 (days later): Extending the serviceYou: Add WebSocket support for real-time notification delivery.diff --git a/docs/integrations/cursor.mdx b/docs/integrations/cursor.mdxindex cfaa5e208..e02c593b4 100644--- a/docs/integrations/cursor.mdx+++ b/docs/integrations/cursor.mdx@@ -96,10 +96,11 @@ Once installed, the following tools are available in every Cursor session:You: The API endpoint /users is taking 3 seconds. Help me optimize it.# Cursor agent searches memories, proceeds with investigation.-# After completing the task, Mem0 stores:+# Mem0 stores what you said as yours:+# - Your preference: "Prefers query-level fixes over caching"+# ...and what the agent did as the assistant's:# - Learning: "N+1 query in UserService.getAll(): fixed with eager loading"# - Decision: "Added database index on users.email column"-# - Preference: "User prefers query-level fixes over caching"# Session 2 (next week): Similar issueYou: The /orders endpoint is also slow, same pattern as before.diff --git a/integrations/mem0-plugin/.claude-plugin/plugin.json b/integrations/mem0-plugin/.claude-plugin/plugin.jsonindex a2be0f0ee..de77fc2ea 100644--- a/integrations/mem0-plugin/.claude-plugin/plugin.json+++ b/integrations/mem0-plugin/.claude-plugin/plugin.json@@ -1,6 +1,6 @@{"name": "mem0",- "version": "0.2.12",+ "version": "0.2.13","description": "Persistent memory for Claude Code. Remembers decisions, patterns, and preferences across sessions.","author": {"name": "Mem0",diff --git a/integrations/mem0-plugin/.codex-plugin/plugin.json b/integrations/mem0-plugin/.codex-plugin/plugin.jsonindex 382808b46..a705b3f72 100644--- a/integrations/mem0-plugin/.codex-plugin/plugin.json+++ b/integrations/mem0-plugin/.codex-plugin/plugin.json@@ -1,6 +1,6 @@{"name": "mem0",- "version": "0.2.12",+ "version": "0.2.13","description": "Persistent memory for Codex. Remembers decisions, patterns, and preferences across sessions.","author": {"name": "Mem0",diff --git a/integrations/mem0-plugin/.cursor-plugin/plugin.json b/integrations/mem0-plugin/.cursor-plugin/plugin.jsonindex 5ca6205ce..cdceabb02 100644--- a/integrations/mem0-plugin/.cursor-plugin/plugin.json+++ b/integrations/mem0-plugin/.cursor-plugin/plugin.json@@ -1,6 +1,6 @@{"name": "mem0",- "version": "0.2.12",+ "version": "0.2.13","description": "Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search using the Mem0 Platform MCP server.","author": {"name": "Mem0",diff --git a/integrations/mem0-plugin/plugin.json b/integrations/mem0-plugin/plugin.jsonindex 4636c32ef..0bed60d4a 100644--- a/integrations/mem0-plugin/plugin.json+++ b/integrations/mem0-plugin/plugin.json@@ -1,7 +1,7 @@{"id": "mem0","name": "mem0",- "version": "0.1.4",+ "version": "0.1.5","description": "Persistent semantic memory for Antigravity agents. Cross-session, user-level recall via the Mem0 Platform MCP server. 16 slash commands, lifecycle hooks for auto-capture and metadata enforcement.","author": { "name": "Mem0", "email": "[email protected]" },"publisher": "mem0ai",diff --git a/integrations/mem0-plugin/scripts/capture_compact_summary.py b/integrations/mem0-plugin/scripts/capture_compact_summary.pyindex d6e70b356..244913e49 100644--- a/integrations/mem0-plugin/scripts/capture_compact_summary.py+++ b/integrations/mem0-plugin/scripts/capture_compact_summary.py@@ -104,8 +104,11 @@ def store_summary(api_key: str, summary: str, user_id: str, session_id: str, pro}if branch:metadata["branch"] = branch+ # The compact summary is model-authored prose, in the first person and with no+ # framing to mark it as such. Under role="user" mem0 reads "I recommend X" as+ # the human saying it and stores "User recommends X".body = {- "messages": [{"role": "user", "content": summary}],+ "messages": [{"role": "assistant", "content": summary}],"user_id": user_id,"app_id": project_id,"metadata": metadata,diff --git a/integrations/mem0-plugin/scripts/capture_session_summary.py b/integrations/mem0-plugin/scripts/capture_session_summary.pyindex 441ed9a6e..2f0279179 100644--- a/integrations/mem0-plugin/scripts/capture_session_summary.py+++ b/integrations/mem0-plugin/scripts/capture_session_summary.py@@ -175,8 +175,12 @@ def store_summary(if files:metadata["files_touched"] = files[:20]+ # summary_prompt wraps the assistant's own last message. Mem0 extracts "facts+ # about the user" from each message and role is the only signal telling it who+ # spoke, so role="user" here turns Claude's opinions into the human's stated+ # preferences ("User prefers dropping Redis...").body = {- "messages": [{"role": "user", "content": summary_prompt}],+ "messages": [{"role": "assistant", "content": summary_prompt}],"user_id": user_id,"app_id": project_id,"run_id": session_id,diff --git a/integrations/mem0-plugin/tests/test_message_roles.py b/integrations/mem0-plugin/tests/test_message_roles.pynew file mode 100644index 000000000..0a36ca66e--- /dev/null+++ b/integrations/mem0-plugin/tests/test_message_roles.py@@ -0,0 +1,144 @@+"""Regression tests: assistant-authored text must never be posted as role="user".++The Stop hook (capture_session_summary) and the post-compact hook+(capture_compact_summary) both ship *model-authored* prose to+POST /v3/memories/add/. Mem0's fact extractor renders each message as+"{role}: {content}" and is instructed to extract "facts and preferences about+the user" — so role is the only signal separating what the human said from what+Claude said.++Posting Claude's own words under role="user" made the extractor read Claude's+first-person prose ("I recommend pgvector", "I found the bug in auth.py") as the+*human's* statements and store them under their user_id. The Stop hook fires on+every assistant turn, so this corrupted memory on nearly every message.+"""++from __future__ import annotations++import json+++class _FakeResp:+ status = 200++ def __enter__(self):+ return self++ def __exit__(self, *_):+ return False+++def _capture(monkeypatch, module):+ """Patch urlopen so store_summary posts nowhere; capture the request body."""+ captured: dict = {}++ def fake_urlopen(req, timeout=0):+ captured["body"] = json.loads(req.data.decode("utf-8"))+ return _FakeResp()++ monkeypatch.setattr(module.urllib.request, "urlopen", fake_urlopen)+ return captured+++# Claude's own voice — first-person prose that must never be attributed to the human.+ASSISTANT_PROSE = (+ "I traced the root cause to auth.py and I recommend we switch to pgvector "+ "for the vector store. I'll refactor the session handler next."+)+++def test_session_summary_posts_assistant_prose_as_assistant(monkeypatch):+ """Stop hook: the last assistant message must be tagged role="assistant"."""+ import capture_session_summary as css++ captured = _capture(monkeypatch, css)++ css.store_summary(+ api_key="test-key",+ summary_prompt=css.build_summary_prompt(ASSISTANT_PROSE, []),+ user_id="u1",+ session_id="s1",+ project_id="p1",+ branch="main",+ files=[],+ )++ messages = captured["body"]["messages"]+ for msg in messages:+ if ASSISTANT_PROSE in msg["content"]:+ assert msg["role"] == "assistant", (+ "Claude's own words were posted as role='user' — mem0 will extract "+ "them as facts about the human. Got role=%r" % msg["role"]+ )+ break+ else:+ raise AssertionError("assistant prose never made it into the payload")+++def test_compact_summary_posts_assistant_prose_as_assistant(monkeypatch):+ """Post-compact hook: the compact summary is model-authored, not user-authored."""+ import capture_compact_summary as ccs++ captured = _capture(monkeypatch, ccs)++ ccs.store_summary(+ api_key="test-key",+ summary=ASSISTANT_PROSE,+ user_id="u1",+ session_id="s1",+ project_id="p1",+ branch="main",+ )++ messages = captured["body"]["messages"]+ for msg in messages:+ if ASSISTANT_PROSE in msg["content"]:+ assert msg["role"] == "assistant", (+ "Compact summary (written by Claude) was posted as role='user'. Got role=%r" % msg["role"]+ )+ break+ else:+ raise AssertionError("assistant prose never made it into the payload")+++def test_no_user_role_message_carries_assistant_prose(monkeypatch):+ """Belt and braces: no user-role message may contain the assistant's words."""+ import capture_session_summary as css++ captured = _capture(monkeypatch, css)++ css.store_summary(+ api_key="test-key",+ summary_prompt=css.build_summary_prompt(ASSISTANT_PROSE, ["auth.py"]),+ user_id="u1",+ session_id="s1",+ project_id="p1",+ branch="main",+ files=["auth.py"],+ )++ for msg in captured["body"]["messages"]:+ if msg["role"] == "user":+ assert ASSISTANT_PROSE not in msg["content"], (+ "A user-role message carries Claude's prose — this is the misattribution bug."+ )+++def test_auto_capture_preserves_real_roles():+ """auto_capture is the reference: it must pass roles through untouched."""+ import auto_capture++ lines = [+ json.dumps({"type": "user", "message": {"role": "user", "content": "why is the build failing on main?"}}),+ json.dumps(+ {+ "type": "assistant",+ "message": {"role": "assistant", "content": [{"type": "text", "text": ASSISTANT_PROSE}]},+ }+ ),+ ]++ messages = auto_capture.extract_recent_exchanges(lines)++ assert [m["role"] for m in messages] == ["user", "assistant"]+ assert ASSISTANT_PROSE in messages[1]["content"]