google-cloud-db-context-engineering 0.7.0__tar.gz → 0.7.2__tar.gz

{google_cloud_db_context_engineering-0.7.0/src/google_cloud_db_context_engineering.egg-info → google_cloud_db_context_engineering-0.7.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: google-cloud-db-context-engineering
-Version: 0.7.0
+Version: 0.7.2
 Summary: A FastMCP server for generating natural language to SQL templates from database schemas.
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
@@ -20,25 +20,25 @@ This is not an officially supported Google product. This project is not eligible
 
 # Context Engineering Agent
 
-The **Context Engineering Agent** is an AI coding agent plugin designed to run in developer agent harnesses (such as Claude Code, Antigravity, or Gemini CLI). It generates, evaluates, and iteratively tunes tailored context artifacts (`ContextSets` comprising `Templates`, `Facets`, and `Value Searches`) to enrich database schemas for **Gemini Data Analytics's data agent developer platform tools**, such as QueryData ([AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/data-agent-overview) | Cloud SQL: [PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/data-agent-overview) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/data-agent-overview) | [Spanner (GoogleSQL)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/data-agent-overview)).
+The **Context Engineering Agent** is an AI coding agent plugin designed to run in developer agent harnesses (such as Claude Code, Antigravity, or Gemini CLI). It generates, evaluates, and iteratively tunes tailored context artifacts (`ContextSets` comprising `Templates`, `Facets`, and `Value Searches`) to enrich database schemas for **Gemini Data Analytics's data agent developer platform tools**, supporting both **relational SQL** and **Graph Query Language (GQL)** across [AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/data-agent-overview), Cloud SQL ([PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/data-agent-overview) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/data-agent-overview)), and [Cloud Spanner (GoogleSQL & Spanner Graph)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/data-agent-overview).
 
 ---
 
 ## Why Context Engineering?
 
-When building data agents and natural language analytics interfaces, accurately translating user intent into database queries is critical. 
+When building data agents and natural language analytics interfaces, accurately translating user intent into database queries—whether relational SQL, pure GQL, or hybrid graph queries—is critical. 
 
-As outlined in **Build Context with Context Engineering Agent** ([AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/build-context-gemini-cli) | Cloud SQL: [PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/build-context-gemini-cli) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/build-context-gemini-cli) | [Spanner (GoogleSQL)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/build-context-gemini-cli)), by optimizing a `ContextSet` to match your application's expected query stream, the **QueryData API** acts as a data agent tool capable of achieving **~100% NL-to-SQL translation accuracy with low latency**.
+As outlined in **Build Context with Context Engineering Agent** ([AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/build-context-gemini-cli) | Cloud SQL: [PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/build-context-gemini-cli) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/build-context-gemini-cli) | [Spanner (GoogleSQL)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/build-context-gemini-cli)), by optimizing a `ContextSet` to match your application's expected query stream, the **QueryData API** acts as a data agent tool capable of achieving **~100% NL-to-SQL/GQL translation accuracy with low latency**.
 
 ---
 
 ## Core Concepts
 
-A `ContextSet` is the central artifact generated and managed by the agent, containing structured knowledge in three primary forms:
+A `ContextSet` is the central artifact generated and managed by the agent, containing structured knowledge across SQL and GQL query domains in three primary forms:
 
-* **Templates**: Link natural language query patterns to complete query statements.
-* **Facets**: Reusable, modular query fragments (e.g., parameterized `WHERE` clauses or specialized join filters) linked to domain vocabulary.
-* **Value Searches**: Specialized mapping queries that dynamically resolve user-supplied values (e.g., *"Lndn"*) to database records (*"London"*) via the capabilities of the underlying database, such as embedding search, AI operators, or simple trigram search.
+* **Templates**: Link natural language query patterns to complete query statements (supporting relational SQL, pure GQL with `GRAPH ... MATCH`, and hybrid `GRAPH_TABLE` queries for Spanner Graph).
+* **Facets**: Reusable, modular query fragments (e.g., parameterized `WHERE` clauses, specialized join filters, or graph `MATCH` traversal patterns) linked to domain vocabulary.
+* **Value Searches**: Specialized mapping queries that dynamically resolve user-supplied values (e.g., *"Lndn"*) to database records (*"London"*) via the capabilities of the underlying database, such as embedding search, AI operators, or trigram search on relational and graph property tables.
 
 For full schema details, structure specifications, and dialect-specific JSON representations of `ContextSets`, see the official **Context Sets Overview** ([AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/context-sets-overview) | Cloud SQL: [PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/context-sets-overview) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/context-sets-overview) | [Spanner (GoogleSQL)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/context-sets-overview)).
 
@@ -95,6 +95,18 @@ You can provide business artifacts directly to the agent from local filesystems
 
 ---
 
+## Installing via a compatible Agent Plugins client
+
+This repository ships a valid [Agent Plugins](https://github.com/agentplugins/agent-plugins-spec) (v1) plugin under [`plugin/`](plugin/), bundling both agent skills and its MCP servers. Any [Agent Plugins–compatible client](https://agent-plugins.org/compatible-clients) (VS Code, Cursor, GitHub Copilot, Kiro, and others) can install it directly using its own built-in plugin command — no extra tooling required — by pointing at this repository:
+
+```
+https://github.com/GoogleCloudPlatform/db-context-enrichment
+```
+
+See your agent's documentation for its exact install command.
+
+---
+
 ## How to Use
 
 Launch your agent harness (Gemini CLI, Claude Code, or Antigravity) in your workspace directory and interact in natural language:

{google_cloud_db_context_engineering-0.7.0 → google_cloud_db_context_engineering-0.7.2}/README.md

@@ -2,25 +2,25 @@ This is not an officially supported Google product. This project is not eligible
 
 # Context Engineering Agent
 
-The **Context Engineering Agent** is an AI coding agent plugin designed to run in developer agent harnesses (such as Claude Code, Antigravity, or Gemini CLI). It generates, evaluates, and iteratively tunes tailored context artifacts (`ContextSets` comprising `Templates`, `Facets`, and `Value Searches`) to enrich database schemas for **Gemini Data Analytics's data agent developer platform tools**, such as QueryData ([AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/data-agent-overview) | Cloud SQL: [PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/data-agent-overview) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/data-agent-overview) | [Spanner (GoogleSQL)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/data-agent-overview)).
+The **Context Engineering Agent** is an AI coding agent plugin designed to run in developer agent harnesses (such as Claude Code, Antigravity, or Gemini CLI). It generates, evaluates, and iteratively tunes tailored context artifacts (`ContextSets` comprising `Templates`, `Facets`, and `Value Searches`) to enrich database schemas for **Gemini Data Analytics's data agent developer platform tools**, supporting both **relational SQL** and **Graph Query Language (GQL)** across [AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/data-agent-overview), Cloud SQL ([PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/data-agent-overview) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/data-agent-overview)), and [Cloud Spanner (GoogleSQL & Spanner Graph)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/data-agent-overview).
 
 ---
 
 ## Why Context Engineering?
 
-When building data agents and natural language analytics interfaces, accurately translating user intent into database queries is critical. 
+When building data agents and natural language analytics interfaces, accurately translating user intent into database queries—whether relational SQL, pure GQL, or hybrid graph queries—is critical. 
 
-As outlined in **Build Context with Context Engineering Agent** ([AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/build-context-gemini-cli) | Cloud SQL: [PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/build-context-gemini-cli) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/build-context-gemini-cli) | [Spanner (GoogleSQL)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/build-context-gemini-cli)), by optimizing a `ContextSet` to match your application's expected query stream, the **QueryData API** acts as a data agent tool capable of achieving **~100% NL-to-SQL translation accuracy with low latency**.
+As outlined in **Build Context with Context Engineering Agent** ([AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/build-context-gemini-cli) | Cloud SQL: [PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/build-context-gemini-cli) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/build-context-gemini-cli) | [Spanner (GoogleSQL)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/build-context-gemini-cli)), by optimizing a `ContextSet` to match your application's expected query stream, the **QueryData API** acts as a data agent tool capable of achieving **~100% NL-to-SQL/GQL translation accuracy with low latency**.
 
 ---
 
 ## Core Concepts
 
-A `ContextSet` is the central artifact generated and managed by the agent, containing structured knowledge in three primary forms:
+A `ContextSet` is the central artifact generated and managed by the agent, containing structured knowledge across SQL and GQL query domains in three primary forms:
 
-* **Templates**: Link natural language query patterns to complete query statements.
-* **Facets**: Reusable, modular query fragments (e.g., parameterized `WHERE` clauses or specialized join filters) linked to domain vocabulary.
-* **Value Searches**: Specialized mapping queries that dynamically resolve user-supplied values (e.g., *"Lndn"*) to database records (*"London"*) via the capabilities of the underlying database, such as embedding search, AI operators, or simple trigram search.
+* **Templates**: Link natural language query patterns to complete query statements (supporting relational SQL, pure GQL with `GRAPH ... MATCH`, and hybrid `GRAPH_TABLE` queries for Spanner Graph).
+* **Facets**: Reusable, modular query fragments (e.g., parameterized `WHERE` clauses, specialized join filters, or graph `MATCH` traversal patterns) linked to domain vocabulary.
+* **Value Searches**: Specialized mapping queries that dynamically resolve user-supplied values (e.g., *"Lndn"*) to database records (*"London"*) via the capabilities of the underlying database, such as embedding search, AI operators, or trigram search on relational and graph property tables.
 
 For full schema details, structure specifications, and dialect-specific JSON representations of `ContextSets`, see the official **Context Sets Overview** ([AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/context-sets-overview) | Cloud SQL: [PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/context-sets-overview) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/context-sets-overview) | [Spanner (GoogleSQL)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/context-sets-overview)).
 
@@ -77,6 +77,18 @@ You can provide business artifacts directly to the agent from local filesystems
 
 ---
 
+## Installing via a compatible Agent Plugins client
+
+This repository ships a valid [Agent Plugins](https://github.com/agentplugins/agent-plugins-spec) (v1) plugin under [`plugin/`](plugin/), bundling both agent skills and its MCP servers. Any [Agent Plugins–compatible client](https://agent-plugins.org/compatible-clients) (VS Code, Cursor, GitHub Copilot, Kiro, and others) can install it directly using its own built-in plugin command — no extra tooling required — by pointing at this repository:
+
+```
+https://github.com/GoogleCloudPlatform/db-context-enrichment
+```
+
+See your agent's documentation for its exact install command.
+
+---
+
 ## How to Use
 
 Launch your agent harness (Gemini CLI, Claude Code, or Antigravity) in your workspace directory and interact in natural language:

{google_cloud_db_context_engineering-0.7.0 → google_cloud_db_context_engineering-0.7.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "google-cloud-db-context-engineering"
-version = "0.7.0"
+version = "0.7.2"
 description = "A FastMCP server for generating natural language to SQL templates from database schemas."
 readme = "README.md"
 requires-python = ">=3.12"
@@ -46,7 +46,7 @@ dev = [
 
 [tool.db-context-engineering]
 toolbox_version = "1.4.0"
-evalbench_version = "1.9.0"
+evalbench_version = "1.12.0"
 
 [tool.ruff]
 line-length = 88

{google_cloud_db_context_engineering-0.7.0 → google_cloud_db_context_engineering-0.7.2}/src/google/cloud/db_context_enrichment/evaluate/db_generators/alloydb.py

@@ -1,6 +1,5 @@
 from typing import Any
 
-import google.cloud.geminidataanalytics_v1beta as gda
 import yaml
 
 from .base import BaseDBConfigGenerator
@@ -52,21 +51,20 @@ class AlloyDBConfigGenerator(BaseDBConfigGenerator):
             db_config, sort_keys=False, default_flow_style=False
         ).strip()
 
-    def build_datasource_reference(
-        self, context_set_id: str
-    ) -> gda.DatasourceReferences:
-        datasource_ref = gda.DatasourceReferences()
-
-        datasource_ref.alloydb = gda.AlloyDbReference(
-            database_reference=gda.AlloyDbDatabaseReference(
-                project_id=self.project,
-                region=self.region,
-                cluster_id=self.cluster,
-                instance_id=self.instance,
-                database_id=self.database,
-            ),
-            agent_context_reference=gda.AgentContextReference(
-                context_set_id=context_set_id
-            ),
-        )
-        return datasource_ref
+    def build_datasource_reference(self, context_set_id: str) -> dict[str, Any]:
+        ref: dict[str, Any] = {
+            "alloydb": {
+                "database_reference": {
+                    "project_id": self.project,
+                    "region": self.region,
+                    "cluster_id": self.cluster,
+                    "instance_id": self.instance,
+                    "database_id": self.database,
+                }
+            }
+        }
+        if context_set_id:
+            ref["alloydb"]["agent_context_reference"] = {
+                "context_set_id": context_set_id
+            }
+        return ref

{google_cloud_db_context_engineering-0.7.0 → google_cloud_db_context_engineering-0.7.2}/src/google/cloud/db_context_enrichment/evaluate/db_generators/base.py

@@ -1,16 +1,14 @@
 from abc import ABC, abstractmethod
 from typing import Any
 
-import google.cloud.geminidataanalytics_v1beta as gda
 import yaml
-from google.protobuf.json_format import MessageToDict
 
 
 class BaseDBConfigGenerator(ABC):
     """
     Abstract Base Class enforcing the construction contract for Evalbench database topologies.
     Each distinct DB type (Spanner, Postgres, AlloyDB, MySQL) must inherit and implement
-    the mappings required by both the standard EvalBench framework and the GDA SDK model.
+    the mappings required by both the standard EvalBench framework and the GDA REST API.
     """
 
     SOURCE_TYPE = "unknown"
@@ -29,11 +27,9 @@ class BaseDBConfigGenerator(ABC):
         raise NotImplementedError("Subclasses must implement generate_db_config")
 
     @abstractmethod
-    def build_datasource_reference(
-        self, context_set_id: str
-    ) -> gda.DatasourceReferences:
+    def build_datasource_reference(self, context_set_id: str) -> dict[str, Any]:
         """
-        Constructs the strict Protocol Buffer DatasourceReference required by the QueryDataAPI
+        Constructs the REST datasource_references dictionary required by the QueryDataAPI
         context generation flow.
         """
         raise NotImplementedError(
@@ -54,23 +50,21 @@ class BaseDBConfigGenerator(ABC):
 
     def generate_model_config(self, context_set_id: str) -> str:
         """
-        Standardized Model Builder converting the strictly typed GDA object into an EvalBench model dict.
+        Standardized Model Builder converting the datasource reference dict into an EvalBench model dict.
         """
         datasource_ref = self.build_datasource_reference(context_set_id)
 
-        query_context = gda.QueryDataContext(datasource_references=datasource_ref)
-
-        query_context_dict = MessageToDict(
-            query_context._pb, preserving_proto_field_name=True
-        )
-
         model_config = {
             "generator": "query_data_api",
             "project_id": self.params.get("project"),
             "location": self.params.get("region") or "global",
-            "context": query_context_dict,
+            "use_rest_api": True,
+            "context": {"datasource_references": datasource_ref},
         }
 
+        if self.params.get("api_endpoint"):
+            model_config["api_endpoint"] = self.params.get("api_endpoint")
+
         return yaml.safe_dump(
             model_config, sort_keys=False, default_flow_style=False
         ).strip()

{google_cloud_db_context_engineering-0.7.0 → google_cloud_db_context_engineering-0.7.2}/src/google/cloud/db_context_enrichment/evaluate/db_generators/mysql.py

@@ -1,6 +1,5 @@
 from typing import Any
 
-import google.cloud.geminidataanalytics_v1beta as gda
 import yaml
 
 from .base import BaseDBConfigGenerator
@@ -49,21 +48,20 @@ class MySQLConfigGenerator(BaseDBConfigGenerator):
             db_config, sort_keys=False, default_flow_style=False
         ).strip()
 
-    def build_datasource_reference(
-        self, context_set_id: str
-    ) -> gda.DatasourceReferences:
-        datasource_ref = gda.DatasourceReferences()
-
-        datasource_ref.cloud_sql_reference = gda.CloudSqlReference(
-            database_reference=gda.CloudSqlDatabaseReference(
-                engine=gda.CloudSqlDatabaseReference.Engine.MYSQL,
-                project_id=self.project,
-                region=self.region,
-                instance_id=self.instance,
-                database_id=self.database,
-            ),
-            agent_context_reference=gda.AgentContextReference(
-                context_set_id=context_set_id
-            ),
-        )
-        return datasource_ref
+    def build_datasource_reference(self, context_set_id: str) -> dict[str, Any]:
+        ref: dict[str, Any] = {
+            "cloud_sql_reference": {
+                "database_reference": {
+                    "engine": "MYSQL",
+                    "project_id": self.project,
+                    "region": self.region,
+                    "instance_id": self.instance,
+                    "database_id": self.database,
+                }
+            }
+        }
+        if context_set_id:
+            ref["cloud_sql_reference"]["agent_context_reference"] = {
+                "context_set_id": context_set_id
+            }
+        return ref

{google_cloud_db_context_engineering-0.7.0 → google_cloud_db_context_engineering-0.7.2}/src/google/cloud/db_context_enrichment/evaluate/db_generators/postgres.py

@@ -1,6 +1,5 @@
 from typing import Any
 
-import google.cloud.geminidataanalytics_v1beta as gda
 import yaml
 
 from .base import BaseDBConfigGenerator
@@ -49,21 +48,20 @@ class PostgresConfigGenerator(BaseDBConfigGenerator):
             db_config, sort_keys=False, default_flow_style=False
         ).strip()
 
-    def build_datasource_reference(
-        self, context_set_id: str
-    ) -> gda.DatasourceReferences:
-        datasource_ref = gda.DatasourceReferences()
-
-        datasource_ref.cloud_sql_reference = gda.CloudSqlReference(
-            database_reference=gda.CloudSqlDatabaseReference(
-                engine=gda.CloudSqlDatabaseReference.Engine.POSTGRESQL,
-                project_id=self.project,
-                region=self.region,
-                instance_id=self.instance,
-                database_id=self.database,
-            ),
-            agent_context_reference=gda.AgentContextReference(
-                context_set_id=context_set_id
-            ),
-        )
-        return datasource_ref
+    def build_datasource_reference(self, context_set_id: str) -> dict[str, Any]:
+        ref: dict[str, Any] = {
+            "cloud_sql_reference": {
+                "database_reference": {
+                    "engine": "POSTGRESQL",
+                    "project_id": self.project,
+                    "region": self.region,
+                    "instance_id": self.instance,
+                    "database_id": self.database,
+                }
+            }
+        }
+        if context_set_id:
+            ref["cloud_sql_reference"]["agent_context_reference"] = {
+                "context_set_id": context_set_id
+            }
+        return ref

{google_cloud_db_context_engineering-0.7.0 → google_cloud_db_context_engineering-0.7.2}/src/google/cloud/db_context_enrichment/evaluate/db_generators/spanner.py

@@ -1,6 +1,5 @@
 from typing import Any
 
-import google.cloud.geminidataanalytics_v1beta as gda
 import yaml
 
 from .base import BaseDBConfigGenerator
@@ -43,20 +42,21 @@ class SpannerConfigGenerator(BaseDBConfigGenerator):
             db_config, sort_keys=False, default_flow_style=False
         ).strip()
 
-    def build_datasource_reference(
-        self, context_set_id: str
-    ) -> gda.DatasourceReferences:
-        datasource_ref = gda.DatasourceReferences()
-
-        datasource_ref.spanner_reference = gda.SpannerReference(
-            database_reference=gda.SpannerDatabaseReference(
-                engine=gda.SpannerDatabaseReference.Engine.GOOGLE_SQL,
-                project_id=self.project,
-                instance_id=self.instance,
-                database_id=self.database,
-            ),
-            agent_context_reference=gda.AgentContextReference(
-                context_set_id=context_set_id
-            ),
-        )
-        return datasource_ref
+    def build_datasource_reference(self, context_set_id: str) -> dict[str, Any]:
+        database_ref: dict[str, Any] = {
+            "engine": "GOOGLE_SQL",
+            "project_id": self.project,
+            "instance_id": self.instance,
+            "database_id": self.database,
+        }
+        if graph_ids := self.params.get("graph_ids"):
+            if not isinstance(graph_ids, list) or not all(
+                isinstance(g, str) for g in graph_ids
+            ):
+                raise ValueError("graph_ids must be a list of strings")
+            database_ref["graph_ids"] = graph_ids
+
+        spanner_ref: dict[str, Any] = {"database_reference": database_ref}
+        if context_set_id:
+            spanner_ref["agent_context_reference"] = {"context_set_id": context_set_id}
+        return {"spanner_reference": spanner_ref}

{google_cloud_db_context_engineering-0.7.0 → google_cloud_db_context_engineering-0.7.2/src/google_cloud_db_context_engineering.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: google-cloud-db-context-engineering
-Version: 0.7.0
+Version: 0.7.2
 Summary: A FastMCP server for generating natural language to SQL templates from database schemas.
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
@@ -20,25 +20,25 @@ This is not an officially supported Google product. This project is not eligible
 
 # Context Engineering Agent
 
-The **Context Engineering Agent** is an AI coding agent plugin designed to run in developer agent harnesses (such as Claude Code, Antigravity, or Gemini CLI). It generates, evaluates, and iteratively tunes tailored context artifacts (`ContextSets` comprising `Templates`, `Facets`, and `Value Searches`) to enrich database schemas for **Gemini Data Analytics's data agent developer platform tools**, such as QueryData ([AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/data-agent-overview) | Cloud SQL: [PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/data-agent-overview) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/data-agent-overview) | [Spanner (GoogleSQL)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/data-agent-overview)).
+The **Context Engineering Agent** is an AI coding agent plugin designed to run in developer agent harnesses (such as Claude Code, Antigravity, or Gemini CLI). It generates, evaluates, and iteratively tunes tailored context artifacts (`ContextSets` comprising `Templates`, `Facets`, and `Value Searches`) to enrich database schemas for **Gemini Data Analytics's data agent developer platform tools**, supporting both **relational SQL** and **Graph Query Language (GQL)** across [AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/data-agent-overview), Cloud SQL ([PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/data-agent-overview) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/data-agent-overview)), and [Cloud Spanner (GoogleSQL & Spanner Graph)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/data-agent-overview).
 
 ---
 
 ## Why Context Engineering?
 
-When building data agents and natural language analytics interfaces, accurately translating user intent into database queries is critical. 
+When building data agents and natural language analytics interfaces, accurately translating user intent into database queries—whether relational SQL, pure GQL, or hybrid graph queries—is critical. 
 
-As outlined in **Build Context with Context Engineering Agent** ([AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/build-context-gemini-cli) | Cloud SQL: [PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/build-context-gemini-cli) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/build-context-gemini-cli) | [Spanner (GoogleSQL)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/build-context-gemini-cli)), by optimizing a `ContextSet` to match your application's expected query stream, the **QueryData API** acts as a data agent tool capable of achieving **~100% NL-to-SQL translation accuracy with low latency**.
+As outlined in **Build Context with Context Engineering Agent** ([AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/build-context-gemini-cli) | Cloud SQL: [PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/build-context-gemini-cli) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/build-context-gemini-cli) | [Spanner (GoogleSQL)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/build-context-gemini-cli)), by optimizing a `ContextSet` to match your application's expected query stream, the **QueryData API** acts as a data agent tool capable of achieving **~100% NL-to-SQL/GQL translation accuracy with low latency**.
 
 ---
 
 ## Core Concepts
 
-A `ContextSet` is the central artifact generated and managed by the agent, containing structured knowledge in three primary forms:
+A `ContextSet` is the central artifact generated and managed by the agent, containing structured knowledge across SQL and GQL query domains in three primary forms:
 
-* **Templates**: Link natural language query patterns to complete query statements.
-* **Facets**: Reusable, modular query fragments (e.g., parameterized `WHERE` clauses or specialized join filters) linked to domain vocabulary.
-* **Value Searches**: Specialized mapping queries that dynamically resolve user-supplied values (e.g., *"Lndn"*) to database records (*"London"*) via the capabilities of the underlying database, such as embedding search, AI operators, or simple trigram search.
+* **Templates**: Link natural language query patterns to complete query statements (supporting relational SQL, pure GQL with `GRAPH ... MATCH`, and hybrid `GRAPH_TABLE` queries for Spanner Graph).
+* **Facets**: Reusable, modular query fragments (e.g., parameterized `WHERE` clauses, specialized join filters, or graph `MATCH` traversal patterns) linked to domain vocabulary.
+* **Value Searches**: Specialized mapping queries that dynamically resolve user-supplied values (e.g., *"Lndn"*) to database records (*"London"*) via the capabilities of the underlying database, such as embedding search, AI operators, or trigram search on relational and graph property tables.
 
 For full schema details, structure specifications, and dialect-specific JSON representations of `ContextSets`, see the official **Context Sets Overview** ([AlloyDB](https://docs.cloud.google.com/gemini/data-agents/querydata/alloydb/context-sets-overview) | Cloud SQL: [PostgreSQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-postgres/context-sets-overview) / [MySQL](https://docs.cloud.google.com/gemini/data-agents/querydata/sql-mysql/context-sets-overview) | [Spanner (GoogleSQL)](https://docs.cloud.google.com/gemini/data-agents/querydata/spanner/context-sets-overview)).
 
@@ -95,6 +95,18 @@ You can provide business artifacts directly to the agent from local filesystems
 
 ---
 
+## Installing via a compatible Agent Plugins client
+
+This repository ships a valid [Agent Plugins](https://github.com/agentplugins/agent-plugins-spec) (v1) plugin under [`plugin/`](plugin/), bundling both agent skills and its MCP servers. Any [Agent Plugins–compatible client](https://agent-plugins.org/compatible-clients) (VS Code, Cursor, GitHub Copilot, Kiro, and others) can install it directly using its own built-in plugin command — no extra tooling required — by pointing at this repository:
+
+```
+https://github.com/GoogleCloudPlatform/db-context-enrichment
+```
+
+See your agent's documentation for its exact install command.
+
+---
+
 ## How to Use
 
 Launch your agent harness (Gemini CLI, Claude Code, or Antigravity) in your workspace directory and interact in natural language: