test(release): guard the CONTRIBUTING.md tag-prefix table against release.yml drift

# Conflicts:
#	AGENTS.md

AGENTS.md

@@ -39,7 +39,7 @@ This is a polyglot monorepo and **every package sets its own rules**. Read the `
 
 | Directory | What it is |
 |-----------|------------|
-| `mem0/` | Core Python SDK (`mem0ai` on PyPI): memory, LLMs, embeddings, vector stores, graphs, rerankers |
+| `mem0/` | Core Python SDK (`mem0ai` on PyPI): memory, LLMs, embeddings, vector stores, rerankers |
 | `mem0-ts/` | TypeScript SDK (`mem0ai` on npm): hosted client + OSS memory |
 | `cli/python/` | Python CLI (`mem0-cli` on PyPI), Typer-based, entry point `mem0` |
 | `cli/node/` | Node CLI (`@mem0/cli` on npm), Commander-based, entry point `mem0` |
@@ -59,8 +59,7 @@ mem0 (Python SDK)          mem0-ts (TypeScript SDK)
 ├── mem0/llms/             └── src/oss/       Memory (self-hosted)
 ├── mem0/embeddings/           ├── src/llms/
 ├── mem0/vector_stores/        ├── src/embeddings/
-├── mem0/graphs/               ├── src/vector_stores/
-└── mem0/reranker/             └── src/graphs/
+└── mem0/reranker/             └── src/vector_stores/
 
 cli/python/                 ──▶ mem0ai (optional, OSS mode)
 cli/node/                   ──▶ mem0ai (npm)

CONTRIBUTING.md

@@ -211,6 +211,13 @@ is created with the correct tag prefix.
 | `@mem0/cli` (Node CLI) | npm | `cli-node-v*` | `cli-node-v0.1.2` |
 | `@mem0/vercel-ai-provider` | npm | `vercel-ai-v*` | `vercel-ai-v2.0.6` |
 | `@mem0/openclaw-mem0` | npm | `openclaw-v*` | `openclaw-v1.0.1` |
+| `@mem0/opencode-plugin` | npm | `opencode-v*` | `opencode-v1.0.1` |
+| `@mem0/pi-agent-plugin` | npm | `pi-agent-v*` | `pi-agent-v1.0.1` |
+| `@mem0/n8n-nodes-mem0` | npm | `n8n-nodes-mem0-v*` | `n8n-nodes-mem0-v1.0.1` |
+
+The Zapier app (`integrations/zapier-mem0`) deploys to Zapier's own platform rather
+than a package registry, so it has no release tag. Deploy it manually with
+`gh workflow run zapier-mem0-cd.yml --ref main`.
 
 ### How to Release
 

integrations/mem0-plugin/skills/mem0/README.md

@@ -40,7 +40,7 @@ After installing, just ask Claude:
 - "Add memory to my chatbot"
 - "Help me search user memories with filters"
 - "Integrate mem0 with my LangChain app"
-- "Add graph memory to track entity relationships"
+- "Migrate my app from mem0 v2 to v3"
 
 ## What's Inside
 
@@ -56,7 +56,7 @@ skills/mem0/
     ├── sdk-guide.md            # All SDK methods (Python + TypeScript)
     ├── api-reference.md        # REST endpoints, filters, memory object
     ├── architecture.md         # Processing pipeline, lifecycle, scoping, performance
-    ├── features.md             # Retrieval, graph, categories, MCP, webhooks, multimodal
+    ├── features.md             # Retrieval, entity linking, categories, MCP, webhooks, multimodal
     ├── integration-patterns.md # LangChain, CrewAI, Vercel AI, LangGraph, LlamaIndex, etc.
     └── use-cases.md            # 7 real-world patterns with Python + TypeScript code
 ```

integrations/mem0-plugin/skills/mem0/scripts/mem0_doc_search.py

@@ -36,9 +36,8 @@ SECTION_MAP = {
     "platform": [
         "/platform/overview",
         "/platform/quickstart",
-        "/platform/features",
         "/platform/features/graph-memory",
-        "/platform/features/selective-memory",
+        "/platform/features/advanced-retrieval",
         "/platform/features/custom-categories",
         "/platform/features/v2-memory-filters",
         "/platform/features/async-client",
@@ -57,10 +56,10 @@ SECTION_MAP = {
         "/open-source/overview",
         "/open-source/python-quickstart",
         "/open-source/node-quickstart",
-        "/open-source/features",
-        "/open-source/features/graph-memory",
+        "/open-source/features/overview",
         "/open-source/features/rest-api",
-        "/open-source/configure-components",
+        "/open-source/features/metadata-filtering",
+        "/open-source/configuration",
     ],
     "sdks": [
         "/sdks/python",

mem0/AGENTS.md

@@ -1,6 +1,6 @@
 # Python SDK (`mem0/`)
 
-The `mem0ai` package on PyPI. Memory core plus five pluggable provider categories.
+The `mem0ai` package on PyPI. Memory core plus four pluggable provider categories.
 
 ## Commands
 
@@ -35,10 +35,9 @@ mem0/
 ├── memory/          Memory, AsyncMemory
 ├── client/          MemoryClient, AsyncMemoryClient
 ├── configs/         MemoryConfig and per-category config models
-├── llms/            24 providers
-├── embeddings/      15 providers
-├── vector_stores/   30 providers
-├── graphs/          4 providers
+├── llms/            18 providers
+├── embeddings/      11 providers
+├── vector_stores/   25 providers
 └── reranker/        5 providers
 ```
 
@@ -48,10 +47,9 @@ Every category follows the same shape: a `base.py` with the abstract class, one
 
 | Category | Count | Examples |
 |----------|-------|---------|
-| LLMs | 24 | OpenAI, Anthropic, AWS Bedrock, Azure OpenAI, Gemini, Groq, Ollama, Together, DeepSeek, vLLM, LiteLLM, LM Studio, xAI |
-| Vector stores | 30 | Qdrant, Pinecone, Chroma, Weaviate, Milvus, MongoDB, Redis, Elasticsearch, pgvector, Supabase, Faiss, S3 Vectors |
-| Embeddings | 15 | OpenAI, Azure OpenAI, Gemini, HuggingFace, FastEmbed, Together, AWS Bedrock, Ollama, Vertex AI |
-| Graph stores | 4 | Neo4j, Memgraph, Kuzu, Apache AGE |
+| LLMs | 18 | OpenAI, Anthropic, AWS Bedrock, Azure OpenAI, Gemini, Groq, Ollama, Together, DeepSeek, vLLM, LiteLLM, LM Studio, xAI |
+| Vector stores | 25 | Qdrant, Pinecone, Chroma, Weaviate, Milvus, MongoDB, Redis, Elasticsearch, pgvector, Supabase, Faiss, S3 Vectors |
+| Embeddings | 11 | OpenAI, Azure OpenAI, Gemini, HuggingFace, FastEmbed, Together, AWS Bedrock, Ollama, Vertex AI |
 | Rerankers | 5 | Cohere, HuggingFace, LLM-based, Sentence Transformer, Zero Entropy |
 
 ### Adding a provider
@@ -100,6 +98,8 @@ Changing any of these signatures means updating `docs/` in the same PR.
 | Embedding provider | `from mem0.embeddings.<provider> import <ProviderEmbedding>` |
 | Vector store provider | `from mem0.vector_stores.<provider> import <ProviderVectorStore>` |
 
-## Graph memory
+## Graph memory (Platform only)
 
-An optional layer on top of vector memory for relationship-aware retrieval, configured through the `graph` section of `MemoryConfig`. It supplements vector search rather than replacing it.
+Removed from the OSS SDKs. `mem0/graphs/` and `mem0-ts/src/oss/src/graphs/` were deleted in `a488e1904` when the v3 pipeline landed; relationship-aware retrieval in OSS is now handled by entity extraction inside the pipeline itself. There is no `graph_store` key in `MemoryConfig` and no `enable_graph` flag in the OSS SDKs.
+
+Graph memory remains a hosted Platform feature. Do not add `graph_store` config, Neo4j/Memgraph/Kuzu/Apache AGE providers, or graph examples to OSS code, docs, or skills. See `3f717e545` for the docs framing.

mem0/exceptions.py

@@ -393,8 +393,8 @@ class DependencyError(MemoryError):
         raise DependencyError(
             message="Required dependency missing",
             error_code="DEPS_001",
-            details={"package": "kuzu", "feature": "graph_store"},
-            suggestion="Please install the required dependencies: pip install kuzu"
+            details={"package": "chromadb", "feature": "vector_store"},
+            suggestion="Please install the required dependencies: pip install chromadb"
         )
     """
     def __init__(self, message: str, error_code: str = "DEPS_001", details: dict = None, 

skills/mem0/README.md

@@ -54,7 +54,7 @@ After installing, just ask Claude:
 - "Add memory to my chatbot"
 - "Help me search user memories with filters"
 - "Integrate mem0 with my LangChain app"
-- "Add graph memory to track entity relationships"
+- "Migrate my app from mem0 v2 to v3"
 
 ## What's Inside
 
@@ -74,7 +74,7 @@ skills/mem0/
     ├── sdk-guide.md            # All SDK methods (Python + TypeScript)
     ├── api-reference.md        # REST endpoints, filters, memory object
     ├── architecture.md         # Processing pipeline, lifecycle, scoping, performance
-    ├── features.md             # Retrieval, graph, categories, MCP, webhooks, multimodal
+    ├── features.md             # Retrieval, entity linking, categories, MCP, webhooks, multimodal
     ├── integration-patterns.md # LangChain, CrewAI, OpenAI Agents, LangGraph, LlamaIndex, etc.
     └── use-cases.md            # 7 real-world patterns with Python + TypeScript code
 ```

skills/mem0/scripts/mem0_doc_search.py

@@ -36,9 +36,8 @@ SECTION_MAP = {
     "platform": [
         "/platform/overview",
         "/platform/quickstart",
-        "/platform/features",
         "/platform/features/graph-memory",
-        "/platform/features/selective-memory",
+        "/platform/features/advanced-retrieval",
         "/platform/features/custom-categories",
         "/platform/features/v2-memory-filters",
         "/platform/features/async-client",
@@ -57,10 +56,10 @@ SECTION_MAP = {
         "/open-source/overview",
         "/open-source/python-quickstart",
         "/open-source/node-quickstart",
-        "/open-source/features",
-        "/open-source/features/graph-memory",
+        "/open-source/features/overview",
         "/open-source/features/rest-api",
-        "/open-source/configure-components",
+        "/open-source/features/metadata-filtering",
+        "/open-source/configuration",
     ],
     "sdks": [
         "/sdks/python",

tests/test_agents_md_provider_counts.py

@@ -0,0 +1,37 @@
+"""Drift test: the provider counts in mem0/AGENTS.md must match the factory registries."""
+
+import re
+from pathlib import Path
+
+import pytest
+
+from mem0.utils.factory import (
+    EmbedderFactory,
+    LlmFactory,
+    RerankerFactory,
+    VectorStoreFactory,
+)
+
+AGENTS_MD = Path(__file__).resolve().parents[1] / "mem0" / "AGENTS.md"
+
+ROW_TO_FACTORY = {
+    "LLMs": LlmFactory,
+    "Vector stores": VectorStoreFactory,
+    "Embeddings": EmbedderFactory,
+    "Rerankers": RerankerFactory,
+}
+
+
+def _documented_count(row_name: str) -> int:
+    match = re.search(rf"^\|\s*{re.escape(row_name)}\s*\|\s*(\d+)\s*\|", AGENTS_MD.read_text(), re.M)
+    return int(match.group(1)) if match else None
+
+
+@pytest.mark.parametrize("row_name,factory", ROW_TO_FACTORY.items())
+def test_documented_count_matches_registry(row_name, factory):
+    documented = _documented_count(row_name)
+    assert documented is not None, f"mem0/AGENTS.md provider table has no {row_name!r} row"
+    assert documented == len(factory.provider_to_class), (
+        f"mem0/AGENTS.md says {documented} {row_name} but "
+        f"{factory.__name__}.provider_to_class has {len(factory.provider_to_class)}"
+    )

tests/test_release_tag_prefixes.py

@@ -0,0 +1,27 @@
+"""Drift test: the tag prefixes in CONTRIBUTING.md must match the router in release.yml."""
+
+import re
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parents[1]
+CONTRIBUTING_MD = REPO_ROOT / "CONTRIBUTING.md"
+RELEASE_YML = REPO_ROOT / ".github" / "workflows" / "release.yml"
+
+
+def _documented_prefixes():
+    section = CONTRIBUTING_MD.read_text().split("### Tag Prefixes")[1].split("###")[0]
+    return set(re.findall(r"^\|[^|\n]+\|[^|\n]+\|\s*`([^`\n]+\*)`\s*\|", section, re.M))
+
+
+def _routed_prefixes():
+    case_block = re.search(r'case "\$TAG" in\n(.*?)\n\s*esac', RELEASE_YML.read_text(), re.S).group(1)
+    return set(re.findall(r"^\s*([\w.-]+\*)\)", case_block, re.M))
+
+
+def test_documented_prefixes_match_release_router():
+    documented, routed = _documented_prefixes(), _routed_prefixes()
+    assert documented, "CONTRIBUTING.md '### Tag Prefixes' table has no tag prefixes"
+    assert documented == routed, (
+        f"CONTRIBUTING.md documents {sorted(documented - routed)} with no arm in release.yml, "
+        f"and release.yml routes {sorted(routed - documented)} with no row in CONTRIBUTING.md"
+    )

tests/test_telemetry.py

@@ -83,7 +83,6 @@ class TestTelemetryEnabled:
             mock_at = MagicMock()
             with patch.object(telemetry_module, "_oss_telemetry_instance", mock_at):
                 mock_memory = MagicMock()
-                mock_memory.config.graph_store.config = None
                 mock_memory.api_version = "v1"
                 telemetry_module.capture_event("test.event", mock_memory)
                 mock_at.capture_event.assert_called_once()
@@ -223,7 +222,6 @@ class TestTelemetrySingleton:
                 with patch("mem0.memory.telemetry.get_or_create_user_id", return_value="u"):
                     with patch("atexit.register"):
                         mock_memory = MagicMock()
-                        mock_memory.config.graph_store.config = None
                         mock_memory.api_version = "v1"
 
                         telemetry_module.capture_event("e1", mock_memory)
@@ -242,7 +240,6 @@ class TestTelemetrySingleton:
                 with patch("mem0.memory.telemetry.get_or_create_user_id", return_value="u"):
                     with patch("atexit.register"):
                         mock_memory = MagicMock()
-                        mock_memory.config.graph_store.config = None
                         mock_memory.api_version = "v1"
 
                         for i in range(50):
@@ -421,7 +418,6 @@ class TestTelemetryNullUserIdHandling:
 
             with patch.object(telemetry_module, "_oss_telemetry_instance", mock_at):
                 mock_memory = MagicMock()
-                mock_memory.config.graph_store.config = None
                 mock_memory.api_version = "v1"
 
                 # This should not raise, even when telemetry fails