Add null checks in jira connector

backend/Dockerfile

@@ -19,53 +19,54 @@ RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
 # zip for Vespa step futher down
 # ca-certificates for HTTPS
 RUN apt-get update && \
-    apt-get install -y \
-        cmake \
-        curl \
-        zip \
-        ca-certificates \
-        libgnutls30=3.7.9-2+deb12u3 \
-        libblkid1=2.38.1-5+deb12u1 \
-        libmount1=2.38.1-5+deb12u1 \
-        libsmartcols1=2.38.1-5+deb12u1 \
-        libuuid1=2.38.1-5+deb12u1 \
-        libxmlsec1-dev \
-        pkg-config \
-        gcc && \
-    rm -rf /var/lib/apt/lists/* && \
-    apt-get clean
+   apt-get install -y \
+       cmake \
+       curl \
+       zip \
+       ca-certificates \
+       libgnutls30 \
+       libblkid1 \
+       libmount1 \
+       libsmartcols1 \
+       libuuid1 \
+       libxmlsec1-dev \
+       pkg-config \
+       gcc \
+       nano \
+       vim && \
+   rm -rf /var/lib/apt/lists/* && \
+   apt-get clean
 
 # Install Python dependencies
 # Remove py which is pulled in by retry, py is not needed and is a CVE
 COPY ./requirements/default.txt /tmp/requirements.txt
 COPY ./requirements/ee.txt /tmp/ee-requirements.txt
 RUN pip install --no-cache-dir --upgrade \
-        -r /tmp/requirements.txt \
-        -r /tmp/ee-requirements.txt && \
-    pip uninstall -y py && \
-    playwright install chromium && \
-    playwright install-deps chromium && \
-    ln -s /usr/local/bin/supervisord /usr/bin/supervisord
+       -r /tmp/requirements.txt \
+       -r /tmp/ee-requirements.txt && \
+   pip uninstall -y py && \
+   playwright install chromium && \
+   playwright install-deps chromium && \
+   ln -s /usr/local/bin/supervisord /usr/bin/supervisord
 
 # Cleanup for CVEs and size reduction
 # https://github.com/tornadoweb/tornado/issues/3107
 # xserver-common and xvfb included by playwright installation but not needed after
 # perl-base is part of the base Python Debian image but not needed for Danswer functionality
 # perl-base could only be removed with --allow-remove-essential
 RUN apt-get update && \
-    apt-get remove -y --allow-remove-essential \
-        perl-base \
-        xserver-common \
-        xvfb \
-        cmake \
-        libldap-2.5-0 \
-        libxmlsec1-dev \
-        pkg-config \
-        gcc && \
-    apt-get install -y libxmlsec1-openssl && \
-    apt-get autoremove -y && \
-    rm -rf /var/lib/apt/lists/* && \
-    rm -f /usr/local/lib/python3.11/site-packages/tornado/test/test.key
+   apt-get remove -y --allow-remove-essential \
+       perl-base \
+       xserver-common \
+       xvfb \
+       cmake \
+       libldap-2.5-0 \
+       libxmlsec1-dev \
+       pkg-config && \
+   apt-get install -y libxmlsec1-openssl && \
+   apt-get autoremove -y && \
+   rm -rf /var/lib/apt/lists/* && \
+   rm -f /usr/local/lib/python3.11/site-packages/tornado/test/test.key
 
 # Pre-downloading models for setups with limited egress
 RUN python -c "from transformers import AutoTokenizer; AutoTokenizer.from_pretrained('intfloat/e5-base-v2')"
@@ -100,4 +101,4 @@ ENV PYTHONPATH /app
 
 # Default command which does nothing
 # This container is used by api server and background which specify their own CMD
-CMD ["tail", "-f", "/dev/null"]
+CMD ["tail", "-f", "/dev/null"]

backend/danswer/connectors/danswer_jira/connector.py

@@ -38,29 +38,20 @@ def _paginate_jql_search(
     max_results: int,
     fields: str | None = None,
 ) -> Iterable[Issue]:
-    start = 0
-    while True:
-        logger.debug(
-            f"Fetching Jira issues with JQL: {jql}, "
-            f"starting at {start}, max results: {max_results}"
-        )
-        issues = jira_client.search_issues(
-            jql_str=jql,
-            startAt=start,
-            maxResults=max_results,
-            fields=fields,
-        )
-
-        for issue in issues:
-            if isinstance(issue, Issue):
-                yield issue
-            else:
-                raise Exception(f"Found Jira object not of type Issue: {issue}")
-
-        if len(issues) < max_results:
-            break
+    # Use enhanced_search_issues for Jira Cloud (API v3)
+    # It uses search tokens instead of startAt for pagination
+    logger.debug(f"Fetching Jira issues with JQL: {jql}, max results: {max_results}")
+    issues = jira_client.enhanced_search_issues(
+        jql_str=jql,
+        maxResults=max_results,
+        fields=fields or "*all",
+    )
 
-        start += max_results
+    for issue in issues:
+        if isinstance(issue, Issue):
+            yield issue
+        else:
+            raise Exception(f"Found Jira object not of type Issue: {issue}")
 
 
 def fetch_jira_issues_batch(
@@ -84,9 +75,9 @@ def fetch_jira_issues_batch(
                 continue
 
         description = (
-            issue.fields.description
+            issue.fields.description or ""
             if JIRA_API_VERSION == "2"
-            else extract_text_from_content(issue.raw["fields"]["description"])
+            else extract_text_from_content(issue.raw["fields"].get("description"))
         )
         comments = get_comment_strs(
             issue=issue,

backend/danswer/connectors/danswer_jira/utils.py

@@ -45,7 +45,10 @@ def best_effort_get_field_from_issue(jira_issue: Issue, field: str) -> Any:
         return None
 
 
-def extract_text_from_content(content: dict) -> str:
+def extract_text_from_content(content: dict | None) -> str:
+    if content is None:
+        return ""
+
     texts = []
     if "content" in content:
         for block in content["content"]:
@@ -63,9 +66,9 @@ def get_comment_strs(
     for comment in issue.fields.comment.comments:
         try:
             body_text = (
-                comment.body
+                comment.body or ""
                 if JIRA_API_VERSION == "2"
-                else extract_text_from_content(comment.raw["body"])
+                else extract_text_from_content(comment.raw.get("body"))
             )
 
             if (