docs(api-reference): align API docs and openapi schema with v3 spec

- create-memory-export.mdx: replace `session_id` filter with `app_id`
  (spec: /v1/exports/ filters = user_id, agent_id, app_id, run_id)
- get-memory-export.mdx: replace stale filter list (session_id removed)
  with correct fields: user_id, agent_id, app_id, run_id, created_at, updated_at
- search-memories.mdx: fix comparison table — rerank V1/V2 default was
  `true`, spec shows `false`; threshold V1 is absent (not "No default"),
  V2 default is 0.3 (not absent)
- organizations-projects.mdx: rewrite Key Capabilities bullet — org/project
  are NOT init params; they resolve automatically from the API key via /v1/ping/
- openapi.json DELETE /v1/batch/: fix request schema from {memory_ids:[uuid]}
  to {memories:[{memory_id:uuid}]} to match Python client.batch_delete()
- openapi.json PUT /v1/batch/: make `text` optional (remove from required),
  add optional `metadata` property — matches Python client.batch_update() docstring

docs/api-reference/organizations-projects.mdx

@@ -14,7 +14,7 @@ Organizations and projects are **optional** features. You can use Mem0 without t
 
 ## Key Capabilities
 
-- **Multi-org/project Support**: Specify organization and project when initializing the Mem0 client to attribute API usage appropriately
+- **Multi-org/project Support**: Organization and project are resolved automatically from your API key via `/v1/ping/` — no org or project params are accepted by `MemoryClient.__init__`. Use a project-specific API key to target a particular project.
 - **Member Management**: Control access to data through organization and project membership
 - **Access Control**: Only members can access memories and data within their organization/project scope
 - **Team Isolation**: Maintain data separation between different teams and projects for secure collaboration