datarobot-genai 0.2.20__py3-none-any.whl → 0.2.21__py3-none-any.whl

datarobot_genai/drmcp/tools/clients/confluence.py

@@ -30,6 +30,9 @@ from .atlassian import get_atlassian_cloud_id
 
 logger = logging.getLogger(__name__)
 
+# Search expand fields for CQL search - content.space gives us space.key directly
+SEARCH_EXPAND_FIELDS = "content.space"
+
 
 class ConfluenceError(Exception):
     """Exception for Confluence API errors."""
@@ -75,6 +78,32 @@ class ConfluenceComment(BaseModel):
         }
 
 
+class ContentSearchResult(BaseModel):
+    """Pydantic model for Confluence search result item."""
+
+    id: str
+    title: str
+    type: str
+    space_key: str = ""
+    space_name: str = ""
+    excerpt: str = ""
+    last_modified: str | None = None
+    url: str = ""
+
+    def as_flat_dict(self) -> dict[str, Any]:
+        """Return a flat dictionary representation of the search result."""
+        return {
+            "id": self.id,
+            "title": self.title,
+            "type": self.type,
+            "spaceKey": self.space_key,
+            "spaceName": self.space_name,
+            "excerpt": self.excerpt,
+            "lastModified": self.last_modified,
+            "url": self.url,
+        }
+
+
 class ConfluenceClient:
     """
     Client for interacting with Confluence API using OAuth access token.
@@ -382,6 +411,76 @@ class ConfluenceClient:
 
         return self._parse_comment_response(response.json(), page_id)
 
+    async def search_confluence_content(
+        self, cql_query: str, max_results: int
+    ) -> list[ContentSearchResult]:
+        """
+        Search Confluence content using CQL (Confluence Query Language).
+
+        Args:
+            cql_query: CQL Query
+            max_results: Maximum number of results to return
+
+        Returns
+        -------
+            List of Confluence content search results
+
+        Raises
+        ------
+            ConfluenceError: If the API request fails (400, 403, 429)
+        """
+        cloud_id = await self._get_cloud_id()
+        url = f"{ATLASSIAN_API_BASE}/ex/confluence/{cloud_id}/wiki/rest/api/search"
+
+        response = await self._client.get(
+            url,
+            params={
+                "cql": cql_query,
+                "limit": max_results,
+                "expand": SEARCH_EXPAND_FIELDS,
+            },
+        )
+
+        if response.status_code == HTTPStatus.BAD_REQUEST:
+            error_msg = self._extract_error_message(response)
+            raise ConfluenceError(f"Invalid CQL query: {error_msg}", status_code=400)
+
+        if response.status_code == HTTPStatus.FORBIDDEN:
+            raise ConfluenceError(
+                "Permission denied: you don't have access to search this content",
+                status_code=403,
+            )
+
+        if response.status_code == HTTPStatus.TOO_MANY_REQUESTS:
+            raise ConfluenceError("Rate limit exceeded. Please try again later.", status_code=429)
+
+        response.raise_for_status()
+        raw_results = response.json().get("results", [])
+        results = [ContentSearchResult(**self._parse_search_item(item)) for item in raw_results]
+        return results
+
+    def _parse_search_item(self, item: dict) -> dict:
+        """Parse raw search API response item into model-compatible dict."""
+        content = item.get("content", item)
+        links = content.get("_links", {})
+        base_url = links.get("base", "")
+        webui = links.get("webui", "")
+        url = f"{base_url}{webui}" if base_url and webui else webui
+
+        # Get space from content.space (requires expand=content.space)
+        content_space = content.get("space", {})
+
+        return {
+            "id": str(content.get("id", "")),
+            "title": content.get("title", ""),
+            "type": content.get("type", "page"),
+            "space_key": content_space.get("key", ""),
+            "space_name": content_space.get("name", ""),
+            "excerpt": item.get("excerpt", ""),
+            "last_modified": item.get("lastModified"),
+            "url": url,
+        }
+
     async def __aenter__(self) -> "ConfluenceClient":
         """Async context manager entry."""
         return self

datarobot_genai/drmcp/tools/confluence/tools.py

@@ -186,3 +186,69 @@ async def confluence_add_comment(
             "page_id": page_id,
         },
     )
+
+
+@dr_mcp_tool(tags={"confluence", "search", "content"})
+async def confluence_search(
+    *,
+    cql_query: Annotated[
+        str,
+        "The CQL (Confluence Query Language) string used to filter content, "
+        "e.g., 'type=page and space=DOC'.",
+    ],
+    max_results: Annotated[int, "Maximum number of content items to return. Default is 10."] = 10,
+    include_body: Annotated[
+        bool,
+        "If True, fetch full page body content for each result (slower, "
+        "makes additional API calls). Default is False, which returns only excerpts.",
+    ] = False,
+) -> ToolResult:
+    """
+    Search Confluence pages and content efficiently using a CQL query string.
+    This pushes the search logic to the Confluence API (Push-Down).
+
+    Refer to Confluence documentation for advanced searching using CQL:
+    https://developer.atlassian.com/cloud/confluence/advanced-searching-using-cql/
+    """
+    if not cql_query:
+        raise ToolError("Argument validation error: 'cql_query' cannot be empty.")
+
+    if max_results < 1 or max_results > 100:
+        raise ToolError("Argument validation error: 'max_results' must be between 1 and 100.")
+
+    access_token = await get_atlassian_access_token()
+    if isinstance(access_token, ToolError):
+        raise access_token
+
+    try:
+        async with ConfluenceClient(access_token) as client:
+            results = await client.search_confluence_content(
+                cql_query=cql_query, max_results=max_results
+            )
+
+            # If include_body is True, fetch full content for each page
+            if include_body and results:
+                data = []
+                for result in results:
+                    flat = result.as_flat_dict()
+                    try:
+                        page = await client.get_page_by_id(result.id)
+                        flat["body"] = page.body
+                    except ConfluenceError:
+                        flat["body"] = None  # Keep excerpt if page fetch fails
+                    data.append(flat)
+            else:
+                data = [result.as_flat_dict() for result in results]
+
+    except ConfluenceError as e:
+        logger.error(f"Confluence error searching content: {e}")
+        raise ToolError(str(e))
+    except Exception as e:
+        logger.error(f"Unexpected error searching Confluence content: {e}")
+        raise ToolError(f"An unexpected error occurred while searching Confluence: {str(e)}")
+
+    n = len(results)
+    return ToolResult(
+        content=f"Successfully executed CQL query and retrieved {n} result(s).",
+        structured_content={"data": data, "count": n},
+    )

{datarobot_genai-0.2.20.dist-info → datarobot_genai-0.2.21.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datarobot-genai
-Version: 0.2.20
+Version: 0.2.21
 Summary: Generic helpers for GenAI
 Project-URL: Homepage, https://github.com/datarobot-oss/datarobot-genai
 Author: DataRobot, Inc.

{datarobot_genai-0.2.20.dist-info → datarobot_genai-0.2.21.dist-info}/RECORD

@@ -78,12 +78,12 @@ datarobot_genai/drmcp/test_utils/utils.py,sha256=esGKFv8aO31-Qg3owayeWp32BYe1CdY
 datarobot_genai/drmcp/tools/__init__.py,sha256=0kq9vMkF7EBsS6lkEdiLibmUrghTQqosHbZ5k-V9a5g,578
 datarobot_genai/drmcp/tools/clients/__init__.py,sha256=0kq9vMkF7EBsS6lkEdiLibmUrghTQqosHbZ5k-V9a5g,578
 datarobot_genai/drmcp/tools/clients/atlassian.py,sha256=__M_uz7FrcbKCYRzeMn24DCEYD6OmFx_LuywHCxgXsA,6472
-datarobot_genai/drmcp/tools/clients/confluence.py,sha256=gDzy8t5t3b1mwEr-CuZ5BwXXQ52AXke8J_Ra7i_8T1g,13692
+datarobot_genai/drmcp/tools/clients/confluence.py,sha256=YS5XsKd-jK5Yg0rgwOcC76v9e8fDJgUZIW5B9kcq5B0,17101
 datarobot_genai/drmcp/tools/clients/gdrive.py,sha256=QmNTmJdSqYO5Y5Vnp3roNZiNNJeocBVjF9UcSzcjgRY,8635
 datarobot_genai/drmcp/tools/clients/jira.py,sha256=Rm91JAyrNIqxu66-9rU1YqoRXVnWbEy-Ahvy6f6HlVg,9823
 datarobot_genai/drmcp/tools/clients/s3.py,sha256=GmwzvurFdNfvxOooA8g5S4osRysHYU0S9ypg_177Glg,953
 datarobot_genai/drmcp/tools/confluence/__init__.py,sha256=0kq9vMkF7EBsS6lkEdiLibmUrghTQqosHbZ5k-V9a5g,578
-datarobot_genai/drmcp/tools/confluence/tools.py,sha256=jSF7yXGFqqlMcavkRIY4HbMxb7tCeunA2ST41wa2vGI,7219
+datarobot_genai/drmcp/tools/confluence/tools.py,sha256=ySwABe8osAzky3BO3lRaF6UHnXQgaurkmvM0iHFfL30,9849
 datarobot_genai/drmcp/tools/gdrive/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datarobot_genai/drmcp/tools/gdrive/tools.py,sha256=wmCUSaCWqepdlOIApA8tZ-grPYSV7wZKoer6uRy26Qg,3459
 datarobot_genai/drmcp/tools/jira/__init__.py,sha256=0kq9vMkF7EBsS6lkEdiLibmUrghTQqosHbZ5k-V9a5g,578
@@ -111,9 +111,9 @@ datarobot_genai/nat/datarobot_llm_clients.py,sha256=Yu208Ed_p_4P3HdpuM7fYnKcXtim
 datarobot_genai/nat/datarobot_llm_providers.py,sha256=aDoQcTeGI-odqydPXEX9OGGNFbzAtpqzTvHHEkmJuEQ,4963
 datarobot_genai/nat/datarobot_mcp_client.py,sha256=35FzilxNp4VqwBYI0NsOc91-xZm1C-AzWqrOdDy962A,9612
 datarobot_genai/nat/helpers.py,sha256=Q7E3ADZdtFfS8E6OQPyw2wgA6laQ58N3bhLj5CBWwJs,3265
-datarobot_genai-0.2.20.dist-info/METADATA,sha256=iWXFNkplo7YmQoa5bCbVPhhv-KzDIHsotkbKf-bEbEk,6301
-datarobot_genai-0.2.20.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-datarobot_genai-0.2.20.dist-info/entry_points.txt,sha256=jEW3WxDZ8XIK9-ISmTyt5DbmBb047rFlzQuhY09rGrM,284
-datarobot_genai-0.2.20.dist-info/licenses/AUTHORS,sha256=isJGUXdjq1U7XZ_B_9AH8Qf0u4eX0XyQifJZ_Sxm4sA,80
-datarobot_genai-0.2.20.dist-info/licenses/LICENSE,sha256=U2_VkLIktQoa60Nf6Tbt7E4RMlfhFSjWjcJJfVC-YCE,11341
-datarobot_genai-0.2.20.dist-info/RECORD,,
+datarobot_genai-0.2.21.dist-info/METADATA,sha256=wdbafq2Z77RRyxy7nG-kYCUU5pfCbsDbBTH7QdENnRU,6301
+datarobot_genai-0.2.21.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+datarobot_genai-0.2.21.dist-info/entry_points.txt,sha256=jEW3WxDZ8XIK9-ISmTyt5DbmBb047rFlzQuhY09rGrM,284
+datarobot_genai-0.2.21.dist-info/licenses/AUTHORS,sha256=isJGUXdjq1U7XZ_B_9AH8Qf0u4eX0XyQifJZ_Sxm4sA,80
+datarobot_genai-0.2.21.dist-info/licenses/LICENSE,sha256=U2_VkLIktQoa60Nf6Tbt7E4RMlfhFSjWjcJJfVC-YCE,11341
+datarobot_genai-0.2.21.dist-info/RECORD,,