docs: refresh references stale since the v3 pipeline landed

Commit a488e1904 deleted mem0/graphs/ and mem0-ts/src/oss/src/graphs/ when the
v3 pipeline landed, and 3f717e545 reframed the docs as Platform-only, but the
agent-facing context files were never updated. Agents reading them still
believe OSS graph memory exists and propose graph_store config that cannot work.

- AGENTS.md: drop graphs/ from the directory map and dependency tree, correct
  the provider table (4 categories, not 5; LLMs 24->18, vector stores 30->25,
  embeddings 15->12), and rewrite the Graph Memory section as Platform-only
- skills: replace the OSS graph-memory prompt example and stop indexing
  /open-source/features/graph-memory, which 404s; also fix four other
  SECTION_MAP paths that no longer resolve
- mem0/exceptions.py: DependencyError example referenced kuzu/graph_store
- tests/test_telemetry.py: drop four mock_memory.config.graph_store lines;
  graph_store is not a MemoryConfig field and telemetry never reads it
- CONTRIBUTING.md: add the three missing release tag prefixes (opencode-v*,
  pi-agent-v*, n8n-nodes-mem0-v*) and note Zapier deploys off-registry

AGENTS.md

@@ -18,7 +18,7 @@ This is a **polyglot monorepo** containing Python and TypeScript packages, CLIs,
 
 | Directory | Description |
 |-----------|-------------|
-| `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) — 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` |
@@ -46,8 +46,7 @@ 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, for OSS mode)
 cli/node/   ──▶ mem0ai (npm, for API calls)
@@ -304,7 +303,7 @@ python -m benchmarks.beam.run --project-name my-test --backend cloud --mem0-api-
 
 ### Python Conventions
 
-- **Provider pattern:** All providers (LLMs, embeddings, vector stores, graphs, rerankers) inherit from a `base.py` abstract class in their directory. Config classes live in `configs.py`.
+- **Provider pattern:** All providers (LLMs, embeddings, vector stores, rerankers) inherit from a `base.py` abstract class in their directory. Config classes live in `configs.py`.
 - **Pydantic v2** for all data models and configuration.
 - **Ruff** is the single linting and formatting tool — no black, no flake8.
   - Root SDK: line length **120**
@@ -337,23 +336,24 @@ cd <package> && pnpm run typecheck    # or: tsc --noEmit
 
 ### Provider Pattern
 
-The SDK uses a consistent plugin architecture across 5 categories. Each category has a `base.py` abstract class and concrete provider implementations:
+The SDK uses a consistent plugin architecture across 4 categories. Each category has a `base.py` abstract class and concrete provider implementations:
 
 | 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** | 12 | OpenAI, Azure OpenAI, Gemini, HuggingFace, FastEmbed, Together, AWS Bedrock, Ollama, Vertex AI |
 | **Rerankers** | 5 | Cohere, HuggingFace, LLM-based, Sentence Transformer, Zero Entropy |
 
 ### Two Usage Modes
 
 Self-hosted `Memory` / `AsyncMemory` classes and hosted-platform `MemoryClient` — both in Python and TypeScript.
 
-### Graph Memory
+### Graph Memory (Platform only)
 
-Optional layer on top of vector memory for relationship-aware retrieval. Configured via the `graph` section of `MemoryConfig`.
+**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 v3 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.
 
 ### MCP Integration