Merge branch 'main' into enhancements/observability

.all-contributorsrc

@@ -408,6 +408,15 @@
       "contributions": [
         "code"
       ]
+    },
+    {
+      "login": "youcefs21",
+      "name": "Youcef Boumar",
+      "avatar_url": "https://avatars.githubusercontent.com/u/34604972?v=4",
+      "profile": "https://github.com/youcefs21",
+      "contributions": [
+        "doc"
+      ]
     }
   ],
   "contributorsPerLine": 7,

README.md

@@ -1,4 +1,9 @@
 <div align="center" style="margin: 30px">
+  <div>
+    <a href="https://agentaai.notion.site/Careers-at-agenta-fb8a76d4d9044e27bd3a32678818dbc8/">
+      <img src="https://github.com/Agenta-AI/agenta/raw/main/.github/images/we-are-hiring.svg" alt="We are hiring! Join our team!" width="350" height="60" alt="We are hiring! Join our team!" width="350" height="60">
+    </a>
+  </div>
   <a href="https://agenta.ai/">
     <div  align="center" >
       <picture >
@@ -148,6 +153,11 @@ To disable anonymized telemetry, follow these steps:
 
 After making this change, restart Agenta Compose.
 
+# ⭐️ Join Our Team
+- [Founding Lead Software Engineer Backend](https://agentaai.notion.site/Founding-Lead-Software-Engineer-Backend-d70bfefed6d543778bc4aa38b543a678)
+- [Founding Product Engineer Frontend](https://agentaai.notion.site/Founding-Product-Engineer-Frontend-b6d26a3e9b254be6b6c2bfffbf0b53c5)
+- [Founding Product Designer](https://agentaai.notion.site/Founding-Product-Designer-96b1e760ff0241fd96632578d533a778)
+
 # Contributing
 
 We warmly welcome contributions to Agenta. Feel free to submit issues, fork the repository, and send pull requests.
@@ -159,7 +169,7 @@ Check out our [Contributing Guide](https://docs.agenta.ai/contributing/getting-s
 ## Contributors ✨
 
 <!-- ALL-CONTRIBUTORS-BADGE:START - Do not remove or modify this section -->
-[![All Contributors](https://img.shields.io/badge/all_contributors-43-orange.svg?style=flat-square)](#contributors-)
+[![All Contributors](https://img.shields.io/badge/all_contributors-44-orange.svg?style=flat-square)](#contributors-)
 <!-- ALL-CONTRIBUTORS-BADGE:END -->
 
 Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/docs/en/emoji-key)):
@@ -225,6 +235,7 @@ Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/d
     </tr>
     <tr>
       <td align="center" valign="top" width="14.28%"><a href="https://github.com/vishalvanpariya"><img src="https://avatars.githubusercontent.com/u/27823328?v=4?s=100" width="100px;" alt="Vishal Vanpariya"/><br /><sub><b>Vishal Vanpariya</b></sub></a><br /><a href="https://github.com/Agenta-AI/agenta/commits?author=vishalvanpariya" title="Code">💻</a></td>
+      <td align="center" valign="top" width="14.28%"><a href="https://github.com/youcefs21"><img src="https://avatars.githubusercontent.com/u/34604972?v=4?s=100" width="100px;" alt="Youcef Boumar"/><br /><sub><b>Youcef Boumar</b></sub></a><br /><a href="https://github.com/Agenta-AI/agenta/commits?author=youcefs21" title="Documentation">📖</a></td>
     </tr>
   </tbody>
 </table>

agenta-backend/agenta_backend/routers/variants_router.py

@@ -1,4 +1,5 @@
 import os
+import inspect
 import logging
 from typing import Any, Optional, Union, List
 
@@ -24,11 +25,13 @@
         Image_ as Image,
         AppVariantResponse_ as AppVariantResponse,
     )
+    from agenta_backend.cloud.services import logs_manager
 else:
     from agenta_backend.models.api.api_models import (
         Image,
         AppVariantResponse,
     )
+    from agenta_backend.services import logs_manager
 
 from agenta_backend.models.api.api_models import (
     URI,
@@ -312,6 +315,18 @@ async def start_variant(
     return url
 
 
+@router.get("/{variant_id}/logs/", operation_id="retrieve_variant_logs")
+async def retrieve_variant_logs(variant_id: str, request: Request):
+    try:
+        app_variant = await db_manager.fetch_app_variant_by_id(variant_id)
+        deployment = await db_manager.get_deployment_by_appid(str(app_variant.app.id))
+        logs_result = await logs_manager.retrieve_logs(deployment.container_id)
+        return logs_result
+    except Exception as exc:
+        logger.exception(f"An error occurred: {str(exc)}")
+        raise HTTPException(500, {"message": str(exc)})
+
+
 @router.get(
     "/{variant_id}/",
     operation_id="get_variant",

agenta-backend/agenta_backend/services/db_manager.py

@@ -994,17 +994,15 @@ async def check_is_last_variant_for_image(db_app_variant: AppVariantDB) -> bool:
         true if it's the last variant, false otherwise
     """
 
-    query_expression = {"base.id": db_app_variant.base.id}
+    query = AppVariantDB.find(AppVariantDB.base.id == ObjectId(db_app_variant.base.id))
 
     if isCloudEE():
-        query_expression.update(
-            {
-                "organization.id": db_app_variant.organization.id,
-                "workspace.id": db_app_variant.workspace.id,
-            }
+        query = query.find(
+            AppVariantDB.organization.id == db_app_variant.organization.id,
+            AppVariantDB.workspace.id == db_app_variant.workspace.id,
         )
 
-    count_variants = await AppVariantDB.find(query_expression).count()
+    count_variants = await query.count()
     return count_variants == 1
 
 
@@ -1017,7 +1015,10 @@ async def remove_deployment(deployment_db: DeploymentDB):
     logger.debug("Removing deployment")
     assert deployment_db is not None, "deployment_db is missing"
 
-    await deployment_db.delete()
+    deployment = await DeploymentDB.find_one(
+        DeploymentDB.id == ObjectId(deployment_db.id)
+    )
+    await deployment.delete()
 
 
 async def remove_app_variant_from_db(app_variant_db: AppVariantDB):
@@ -1041,7 +1042,10 @@ async def remove_app_variant_from_db(app_variant_db: AppVariantDB):
     for app_variant_revision in app_variant_revisions:
         await app_variant_revision.delete()
 
-    await app_variant_db.delete()
+    app_variant = await AppVariantDB.find_one(
+        AppVariantDB.id == ObjectId(app_variant_db.id)
+    )
+    await app_variant.delete()
 
 
 async def deploy_to_environment(
@@ -1376,6 +1380,8 @@ async def remove_image(image: ImageDB):
     """
     if image is None:
         raise ValueError("Image is None")
+
+    image = await ImageDB.find_one(ImageDB.id == ObjectId(image.id))
     await image.delete()
 
 

agenta-backend/agenta_backend/services/llm_apps_service.py

@@ -1,11 +1,13 @@
 import json
 import logging
 import asyncio
+import traceback
 import aiohttp
 from typing import Any, Dict, List
 
 
 from agenta_backend.models.db_models import InvokationResult, Result, Error
+from agenta_backend.utils import common
 
 # Set logger
 logger = logging.getLogger(__name__)
@@ -96,37 +98,40 @@ async def invoke_app(
             )
 
         except aiohttp.ClientResponseError as e:
-            # Parse error details from the API response
-            error_message = "Error in invoking the LLM App:"
-            try:
-                error_message = e.message
-            except ValueError:
-                # Fallback if the error response is not JSON or doesn't have the expected structure
-                logger.error(f"Failed to parse error response: {e}")
-
-            logger.error(f"Error occurred during request: {error_message}")
-            return InvokationResult(
-                result=Result(
-                    type="error",
-                    error=Error(
-                        message=f"{e.code}: {error_message}",
-                        stacktrace=str(e),
-                    ),
-                )
-            )
-
+            error_message = f"HTTP error {e.status}: {e.message}"
+            stacktrace = "".join(traceback.format_exception_only(type(e), e))
+            logger.error(f"HTTP error occurred during request: {error_message}")
+            common.capture_exception_in_sentry(e)
+        except aiohttp.ServerTimeoutError as e:
+            error_message = "Request timed out"
+            stacktrace = "".join(traceback.format_exception_only(type(e), e))
+            logger.error(error_message)
+            common.capture_exception_in_sentry(e)
+        except aiohttp.ClientConnectionError as e:
+            error_message = f"Connection error: {str(e)}"
+            stacktrace = "".join(traceback.format_exception_only(type(e), e))
+            logger.error(error_message)
+            common.capture_exception_in_sentry(e)
+        except json.JSONDecodeError as e:
+            error_message = "Failed to decode JSON from response"
+            stacktrace = "".join(traceback.format_exception_only(type(e), e))
+            logger.error(error_message)
+            common.capture_exception_in_sentry(e)
         except Exception as e:
-            # Catch-all for any other unexpected errors
-            logger.error(f"Unexpected error: {e}")
-            return InvokationResult(
-                result=Result(
-                    type="error",
-                    error=Error(
-                        message="Unexpected error while invoking the LLM App",
-                        stacktrace=str(e),
-                    ),
-                )
+            error_message = f"Unexpected error: {str(e)}"
+            stacktrace = "".join(traceback.format_exception_only(type(e), e))
+            logger.error(error_message)
+            common.capture_exception_in_sentry(e)
+
+        return InvokationResult(
+            result=Result(
+                type="error",
+                error=Error(
+                    message=error_message,
+                    stacktrace=stacktrace,
+                ),
             )
+        )
 
 
 async def run_with_retry(
@@ -165,10 +170,13 @@ async def run_with_retry(
             retries += 1
         except Exception as e:
             last_exception = e
-            logger.info(f"Error processing datapoint: {input_data}")
+            logger.info(f"Error processing datapoint: {input_data}. {str(e)}")
+            logger.info("".join(traceback.format_exception_only(type(e), e)))
+            common.capture_exception_in_sentry(e)
 
     # If max retries is reached or an exception that isn't in the second block,
     # update & return the last exception
+    logging.info("Max retries reached")
     exception_message = (
         "Max retries reached"
         if retries == max_retry_count

agenta-backend/agenta_backend/services/logs_manager.py

@@ -0,0 +1,18 @@
+import aiodocker
+
+
+async def retrieve_logs(container_id: str) -> str:
+    """
+    Retrieves and returns the last 10 lines of logs (both stdout and stderr)
+    for a specified Docker container.
+    Args:
+        container_id (str): The docker container identifier
+    Returns:
+        the last 10 lines of logs
+    """
+
+    async with aiodocker.Docker() as client:
+        container = await client.containers.get(container_id)
+        logs = await container.log(stdout=True, stderr=True)
+        outputs = logs[::-1][:10]
+        return "".join(outputs)

agenta-backend/agenta_backend/utils/common.py

@@ -4,6 +4,7 @@
 
 from fastapi.types import DecoratedCallable
 from fastapi import APIRouter as FastAPIRouter
+from sentry_sdk import capture_exception
 
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.DEBUG)
@@ -76,3 +77,8 @@ def isCloudDev():
 
 def isOss():
     return os.environ["FEATURE_FLAG"] == "oss"
+
+
+def capture_exception_in_sentry(e: Exception):
+    if isCloudProd():
+        capture_exception(e)