Merge branch 'main' into rajat/DEV-1069

README.md

@@ -8,7 +8,7 @@
 
 ---
 
-![Static Badge](https://img.shields.io/badge/Version-2.3.0-blue)
+![Static Badge](https://img.shields.io/badge/Version-2.3.1-blue)
 [![PyPI version](https://img.shields.io/pypi/v/honcho-ai.svg)](https://pypi.org/project/honcho-ai/)
 [![NPM version](https://img.shields.io/npm/v/@honcho-ai/sdk.svg)](https://npmjs.org/package/@honcho-ai/sdk)
 [![Discord](https://img.shields.io/discord/1016845111637839922?style=flat&logo=discord&logoColor=23ffffff&label=Plastic%20Labs&labelColor=235865F2)](https://discord.gg/plasticlabs)

docs/v2/documentation/introduction/quickstart.mdx

@@ -87,7 +87,7 @@ client = Honcho(
     api_key=os.environ["HONCHO_API_KEY"],
     environment="production",
     # Create a workspace, otherwise set to "default"
-    # workspace="your-workspace-id"
+    # workspaceId="your-workspace-id"
 )
 ```
 

docs/v2/openapi.documented.yml

@@ -2932,7 +2932,7 @@ components:
       properties:
         content:
           type: string
-          maxLength: 50000
+          maxLength: 25000
           minLength: 0
           title: Content
         peer_id:

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "honcho"
-version = "2.3.0"
+version = "2.3.1"
 description = "Honcho Server"
 authors = [
   {name = "Plastic Labs", email = "hello@plasticlabs.ai"},

src/config.py

@@ -280,6 +280,7 @@ class AppSettings(HonchoSettings):
         100_000
     )
 
+    MAX_MESSAGE_SIZE: Annotated[int, Field(default=25_000, gt=0)] = 25_000
     EMBED_MESSAGES: bool = True
     MAX_EMBEDDING_TOKENS: Annotated[int, Field(default=8192, gt=0)] = 8192
     MAX_EMBEDDING_TOKENS_PER_REQUEST: Annotated[int, Field(default=300_000, gt=0)] = (

src/deriver/queue_manager.py

@@ -15,7 +15,7 @@ from sqlalchemy.sql import func
 from src.config import settings
 from src.models import QueueItem
 
-from .. import exceptions, models
+from .. import models
 from ..dependencies import tracked_db
 from .consumer import process_items
 
@@ -278,13 +278,6 @@ class QueueManager:
                     try:
                         raw_payloads = [msg.payload for msg in messages_to_process]
                         await process_items(task_type, raw_payloads)
-                    except exceptions.LLMError as e:
-                        logger.error(
-                            f"LLM returned bad JSON for messages in work unit {work_unit_key}, re-queueing",
-                        )
-                        if settings.SENTRY.ENABLED:
-                            sentry_sdk.capture_exception(e)
-                        continue  # Don't mark as processed, allow re-queue
                     except Exception as e:
                         logger.error(
                             f"Error processing tasks for work unit {work_unit_key}: {e}",

src/main.py

@@ -117,7 +117,7 @@ app = FastAPI(
     title="Honcho API",
     summary="The Identity Layer for the Agentic World",
     description="""Honcho is a platform for giving agents user-centric memory and social cognition""",
-    version="2.3.0",
+    version="2.3.1",
     contact={
         "name": "Plastic Labs",
         "url": "https://honcho.dev",

src/schemas.py

@@ -14,6 +14,8 @@ from pydantic import (
     model_validator,
 )
 
+from src.config import settings
+
 RESOURCE_NAME_PATTERN = r"^[a-zA-Z0-9_-]+$"
 
 
@@ -114,7 +116,7 @@ class MessageBase(BaseModel):
 
 
 class MessageCreate(MessageBase):
-    content: Annotated[str, Field(min_length=0, max_length=50000)]
+    content: Annotated[str, Field(min_length=0, max_length=settings.MAX_MESSAGE_SIZE)]
     peer_name: str = Field(alias="peer_id")
     metadata: dict[str, Any] | None = None
     created_at: datetime.datetime | None = None

src/utils/files.py

@@ -9,6 +9,7 @@ from sqlalchemy import Integer, select
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from src import schemas
+from src.config import settings
 from src.exceptions import FileProcessingError, UnsupportedFileTypeError
 from src.schemas import Message
 
@@ -157,7 +158,7 @@ async def get_file_messages(
 async def process_file_uploads_for_messages(
     file: UploadFile,
     peer_id: str,
-    max_chars: int = 49500,
+    max_chars: int = settings.MAX_MESSAGE_SIZE,
 ) -> list[dict[str, Any]]:
     """
     Process an uploaded file and prepare message creation data.

tests/routes/test_validation_api.py

@@ -1,6 +1,7 @@
 from fastapi.testclient import TestClient
 from nanoid import generate as generate_nanoid
 
+from src.config import settings
 from src.models import Peer, Workspace
 
 
@@ -73,14 +74,21 @@ def test_message_validations_api(
         f"/v2/workspaces/{test_workspace.name}/sessions/{session_id}/messages",
         json={
             "messages": [
-                {"content": "a" * 50001, "peer_id": test_peer.name, "metadata": {}}
+                {
+                    "content": "a" * (settings.MAX_MESSAGE_SIZE + 1),
+                    "peer_id": test_peer.name,
+                    "metadata": {},
+                }
             ]
         },
     )
     assert response.status_code == 422
     error = response.json()["detail"][0]
     assert "content" in str(error["loc"])
-    assert error["msg"] == "String should have at most 50000 characters"
+    assert (
+        error["msg"]
+        == f"String should have at most {settings.MAX_MESSAGE_SIZE} characters"
+    )
     assert error["type"] == "string_too_long"
 
 

uv.lock

@@ -828,7 +828,7 @@ wheels = [
 
 [[package]]
 name = "honcho"
-version = "2.3.0"
+version = "2.3.1"
 source = { virtual = "." }
 dependencies = [
     { name = "alembic" },