feat: judge and send runner category (local or cloud) for telemetry

* feat(chat): add runner_url to payload for telemetry tracking

* feat(telemetry): add runner_url to sanitized fields in telemetry payload

* feat(telemetry): replace runner_url with runner_category in telemetry payload and add runner utility functions

* fix:ruff

src/langbot/pkg/pipeline/process/handlers/chat.py

@@ -12,7 +12,7 @@ from ... import entities
 from ....provider import runner as runner_module
 
 import langbot_plugin.api.entities.events as events
-from ....utils import importutil, constants
+from ....utils import importutil, constants, runner as runner_utils
 from ....provider import runners
 import langbot_plugin.api.entities.builtin.provider.session as provider_session
 import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
@@ -185,10 +185,15 @@ class ChatMessageHandler(handler.MessageHandler):
 
                     pipeline_plugins = query.variables.get('_pipeline_bound_plugins', None)
 
+                    runner_category = runner_utils.get_runner_category_from_runner(
+                        runner_name, runner, query.pipeline_config
+                    )
+
                     payload = {
                         'query_id': query.query_id,
                         'adapter': adapter_name,
                         'runner': runner_name,
+                        'runner_category': runner_category,
                         'duration_ms': duration_ms,
                         'model_name': model_name,
                         'version': constants.semantic_version,

src/langbot/pkg/telemetry/telemetry.py

@@ -60,7 +60,7 @@ class TelemetryManager:
                     except Exception:
                         sanitized['query_id'] = str(sanitized.get('query_id', ''))
 
-                for sfield in ('adapter', 'runner', 'model_name', 'version', 'error', 'timestamp'):
+                for sfield in ('adapter', 'runner', 'runner_category', 'model_name', 'version', 'error', 'timestamp'):
                     v = sanitized.get(sfield)
                     sanitized[sfield] = '' if v is None else str(v)
 

src/langbot/pkg/utils/runner.py

@@ -0,0 +1,105 @@
+from __future__ import annotations
+
+from urllib.parse import urlparse
+
+
+class RunnerCategory:
+    LOCAL = 'local'
+    CLOUD = 'cloud'
+    UNKNOWN = 'unknown'
+
+
+CLOUD_DOMAINS = [
+    '.n8n.cloud',
+    '.n8n.io',
+    'api.dify.ai',
+    'cloud.dify.ai',
+    '.coze.com',
+    '.coze.cn',
+    'cloud.langflow.ai',
+    '.langflow.org',
+]
+
+LOCAL_PATTERNS = [
+    'localhost',
+    '127.0.0.1',
+    '0.0.0.0',
+    '192.168.',
+    '10.',
+    '172.16.',
+    '172.17.',
+    '172.18.',
+    '172.19.',
+    '172.20.',
+    '172.21.',
+    '172.22.',
+    '172.23.',
+    '172.24.',
+    '172.25.',
+    '172.26.',
+    '172.27.',
+    '172.28.',
+    '172.29.',
+    '172.30.',
+    '172.31.',
+]
+
+
+def get_runner_category(runner_name: str, runner_url: str) -> str:
+    if not runner_url:
+        return RunnerCategory.UNKNOWN
+
+    try:
+        parsed_url = urlparse(runner_url)
+        host = parsed_url.hostname.lower() if parsed_url.hostname else ''
+    except Exception:
+        return RunnerCategory.UNKNOWN
+
+    for pattern in LOCAL_PATTERNS:
+        if host.startswith(pattern):
+            return RunnerCategory.LOCAL
+
+    for domain in CLOUD_DOMAINS:
+        if host.endswith(domain):
+            return RunnerCategory.CLOUD
+
+    return RunnerCategory.CLOUD
+
+
+def get_runner_info(runner_name: str, runner_url: str) -> dict:
+    return {
+        'name': runner_name,
+        'url': runner_url,
+        'category': get_runner_category(runner_name, runner_url),
+    }
+
+
+def is_cloud_runner(runner_name: str, runner_url: str) -> bool:
+    return get_runner_category(runner_name, runner_url) == RunnerCategory.CLOUD
+
+
+def is_local_runner(runner_name: str, runner_url: str) -> bool:
+    return get_runner_category(runner_name, runner_url) == RunnerCategory.LOCAL
+
+
+def extract_runner_url(runner_name: str, runner, pipeline_config: dict | None) -> str | None:
+    if not runner or not hasattr(runner, 'pipeline_config'):
+        return None
+
+    ai_config = pipeline_config.get('ai', {}) if pipeline_config else {}
+
+    if runner_name == 'dify-service-api':
+        return ai_config.get('dify-service-api', {}).get('base-url')
+    elif runner_name == 'n8n-service-api':
+        return ai_config.get('n8n-service-api', {}).get('webhook-url')
+    elif runner_name == 'coze-api':
+        return ai_config.get('coze-api', {}).get('api-base')
+    elif runner_name == 'langflow-api':
+        return ai_config.get('langflow-api', {}).get('base-url')
+
+    return None
+
+
+def get_runner_category_from_runner(runner_name: str, runner, pipeline_config: dict | None) -> str:
+    runner_url = extract_runner_url(runner_name, runner, pipeline_config)
+    return get_runner_category(runner_name, runner_url)