lm-deluge 0.0.90__tar.gz → 0.0.91__tar.gz

{lm_deluge-0.0.90/src/lm_deluge.egg-info → lm_deluge-0.0.91}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lm_deluge
-Version: 0.0.90
+Version: 0.0.91
 Summary: Python utility for using LLM API models.
 Author-email: Benjamin Anderson <ben@trytaylor.ai>
 Requires-Python: >=3.10
@@ -9,7 +9,6 @@ License-File: LICENSE
 Requires-Dist: python-dotenv
 Requires-Dist: json5
 Requires-Dist: PyYAML
-Requires-Dist: pandas
 Requires-Dist: aiohttp
 Requires-Dist: tiktoken
 Requires-Dist: xxhash
@@ -49,9 +48,9 @@ Dynamic: license-file
 - **Spray across models/providers** – Configure a client with multiple models from any provider(s), and sampling weights. The client samples a model for each request.
 - **Tool Use** – Unified API for defining tools for all providers, and creating tools automatically from python functions.
 - **MCP Support** – Instantiate a `Tool` from a local or remote MCP server so that any LLM can use it, whether or not that provider natively supports MCP.
-- **Computer Use** – We support Claude Computer Use via the computer_use argument to process_prompts_sync/async. It works with Anthropic's API; Bedrock's API is broken right now and rejects the tool definitions, but in principle this will work there too when Bedrock gets their sh*t together.
-- **Caching** – Save completions in a local or distributed cache to avoid repeated LLM calls to process the same input.
-- **Convenient message constructor** – No more looking up how to build an Anthropic messages list with images. Our `Conversation` and `Message` classes work great with our client or with the `openai` and `anthropic` packages.
+- **Computer Use** – We support computer use for all major providers, and have pre-fabricated tools to integrate with Kernel, TryCUA, and more.
+- **Local & Remote Caching** – Use Anthropic caching more easily with common patterns (system-only, tools-only, last N messages, etc.) Use client-side caching to save completions to avoid repeated LLM calls to process the same input.
+- **Convenient message constructor** – No more looking up how to build an Anthropic messages list with images. Our `Conversation` and `Message` classes work great with our `LLMClient` or with the `openai` and `anthropic` packages.
 - **Sync and async APIs** – Use the client from sync or async code.
 
 **STREAMING IS NOT IN SCOPE.** There are plenty of packages that let you stream chat completions across providers. The sole purpose of this package is to do very fast batch inference using APIs. Sorry!
@@ -146,7 +145,7 @@ Constructing conversations to pass to models is notoriously annoying. Each provi
 ```python
 from lm_deluge import Message, Conversation
 
-prompt = Conversation.system("You are a helpful assistant.").add(
+prompt = Conversation().system("You are a helpful assistant.").add(
     Message.user("What's in this image?").add_image("tests/image.jpg")
 )
 
@@ -167,7 +166,7 @@ from lm_deluge import LLMClient, Conversation
 
 # Simple file upload
 client = LLMClient("gpt-4.1-mini")
-conversation = Conversation.user(
+conversation = Conversation().user(
     "Please summarize this document",
     file="path/to/document.pdf"
 )
@@ -176,7 +175,7 @@ resps = client.process_prompts_sync([conversation])
 # You can also create File objects for more control
 from lm_deluge import File
 file = File("path/to/report.pdf", filename="Q4_Report.pdf")
-conversation = Conversation.user("Analyze this financial report")
+conversation = Conversation().user("Analyze this financial report")
 conversation.messages[0].parts.append(file)
 ```
 
@@ -246,7 +245,7 @@ for tool_call in resps[0].tool_calls:
 import asyncio
 
 async def main():
-    conv = Conversation.user("List the files in the current directory")
+    conv = Conversation().user("List the files in the current directory")
     conv, resp = await client.run_agent_loop(conv, tools=tools)
     print(resp.content.completion)
 
@@ -262,7 +261,7 @@ from lm_deluge import LLMClient, Conversation, Message
 
 # Create a conversation with system message
 conv = (
-    Conversation.system("You are an expert Python developer with deep knowledge of async programming.")
+    Conversation().system("You are an expert Python developer with deep knowledge of async programming.")
     .add(Message.user("How do I use asyncio.gather?"))
 )
 

{lm_deluge-0.0.90 → lm_deluge-0.0.91}/README.md

@@ -8,9 +8,9 @@
 - **Spray across models/providers** – Configure a client with multiple models from any provider(s), and sampling weights. The client samples a model for each request.
 - **Tool Use** – Unified API for defining tools for all providers, and creating tools automatically from python functions.
 - **MCP Support** – Instantiate a `Tool` from a local or remote MCP server so that any LLM can use it, whether or not that provider natively supports MCP.
-- **Computer Use** – We support Claude Computer Use via the computer_use argument to process_prompts_sync/async. It works with Anthropic's API; Bedrock's API is broken right now and rejects the tool definitions, but in principle this will work there too when Bedrock gets their sh*t together.
-- **Caching** – Save completions in a local or distributed cache to avoid repeated LLM calls to process the same input.
-- **Convenient message constructor** – No more looking up how to build an Anthropic messages list with images. Our `Conversation` and `Message` classes work great with our client or with the `openai` and `anthropic` packages.
+- **Computer Use** – We support computer use for all major providers, and have pre-fabricated tools to integrate with Kernel, TryCUA, and more.
+- **Local & Remote Caching** – Use Anthropic caching more easily with common patterns (system-only, tools-only, last N messages, etc.) Use client-side caching to save completions to avoid repeated LLM calls to process the same input.
+- **Convenient message constructor** – No more looking up how to build an Anthropic messages list with images. Our `Conversation` and `Message` classes work great with our `LLMClient` or with the `openai` and `anthropic` packages.
 - **Sync and async APIs** – Use the client from sync or async code.
 
 **STREAMING IS NOT IN SCOPE.** There are plenty of packages that let you stream chat completions across providers. The sole purpose of this package is to do very fast batch inference using APIs. Sorry!
@@ -105,7 +105,7 @@ Constructing conversations to pass to models is notoriously annoying. Each provi
 ```python
 from lm_deluge import Message, Conversation
 
-prompt = Conversation.system("You are a helpful assistant.").add(
+prompt = Conversation().system("You are a helpful assistant.").add(
     Message.user("What's in this image?").add_image("tests/image.jpg")
 )
 
@@ -126,7 +126,7 @@ from lm_deluge import LLMClient, Conversation
 
 # Simple file upload
 client = LLMClient("gpt-4.1-mini")
-conversation = Conversation.user(
+conversation = Conversation().user(
     "Please summarize this document",
     file="path/to/document.pdf"
 )
@@ -135,7 +135,7 @@ resps = client.process_prompts_sync([conversation])
 # You can also create File objects for more control
 from lm_deluge import File
 file = File("path/to/report.pdf", filename="Q4_Report.pdf")
-conversation = Conversation.user("Analyze this financial report")
+conversation = Conversation().user("Analyze this financial report")
 conversation.messages[0].parts.append(file)
 ```
 
@@ -205,7 +205,7 @@ for tool_call in resps[0].tool_calls:
 import asyncio
 
 async def main():
-    conv = Conversation.user("List the files in the current directory")
+    conv = Conversation().user("List the files in the current directory")
     conv, resp = await client.run_agent_loop(conv, tools=tools)
     print(resp.content.completion)
 
@@ -221,7 +221,7 @@ from lm_deluge import LLMClient, Conversation, Message
 
 # Create a conversation with system message
 conv = (
-    Conversation.system("You are an expert Python developer with deep knowledge of async programming.")
+    Conversation().system("You are an expert Python developer with deep knowledge of async programming.")
     .add(Message.user("How do I use asyncio.gather?"))
 )
 

{lm_deluge-0.0.90 → lm_deluge-0.0.91}/pyproject.toml

@@ -3,7 +3,7 @@ requires = ["setuptools", "wheel"]
 
 [project]
 name = "lm_deluge"
-version = "0.0.90"
+version = "0.0.91"
 authors = [{ name = "Benjamin Anderson", email = "ben@trytaylor.ai" }]
 description = "Python utility for using LLM API models."
 readme = "README.md"
@@ -15,7 +15,6 @@ dependencies = [
     "python-dotenv",
     "json5",
     "PyYAML",
-    "pandas",
     "aiohttp",
     "tiktoken",
     "xxhash",
@@ -28,8 +27,7 @@ dependencies = [
     "pdf2image",
     "pillow",
     "fastmcp>=2.4",
-    "rich",
-    # "textual>=0.58.0"
+    "rich"
 ]
 
 [project.optional-dependencies]
@@ -39,5 +37,6 @@ full_text_search = ["tantivy>=0.21.0", "lenlp>=0.1.0"]
 sandbox = ["modal>=0.64.0", "daytona-sdk>=0.1.4", "docker>=7.0.0"]
 server = ["fastapi>=0.100.0", "uvicorn>=0.20.0"]
 
-# [project.scripts]
-# deluge = "lm_deluge.cli:main"
+[project.scripts]
+deluge = "lm_deluge.cli:main"
+deluge-server = "lm_deluge.server.__main__:main"

{lm_deluge-0.0.90 → lm_deluge-0.0.91}/src/lm_deluge/__init__.py

@@ -1,7 +1,6 @@
 from .client import APIResponse, LLMClient, SamplingParams
-from .file import File
-from .prompt import Conversation, Message
-from .tool import Tool
+from .prompt import Conversation, Message, File
+from .tool import Tool, MCPServer
 
 # dotenv.load_dotenv() - don't do this, fucks with other packages
 
@@ -12,5 +11,6 @@ __all__ = [
     "Conversation",
     "Message",
     "Tool",
+    "MCPServer",
     "File",
 ]

{lm_deluge-0.0.90 → lm_deluge-0.0.91}/src/lm_deluge/api_requests/anthropic.py

@@ -10,7 +10,7 @@ from lm_deluge.prompt import (
     Thinking,
     ToolCall,
 )
-from lm_deluge.request_context import RequestContext
+from lm_deluge.api_requests.context import RequestContext
 from lm_deluge.tool import MCPServer, Tool
 from lm_deluge.usage import Usage
 from lm_deluge.util.schema import (
@@ -103,7 +103,9 @@ def _build_anthropic_request(
             if "top_p" in request_json:
                 request_json["top_p"] = max(request_json["top_p"], 0.95)
             request_json["temperature"] = 1.0
-            request_json["max_tokens"] += budget
+            max_tokens = request_json["max_tokens"]
+            assert isinstance(max_tokens, int)
+            request_json["max_tokens"] = max_tokens + budget
         else:
             request_json["thinking"] = {"type": "disabled"}
             if "kimi" in model.id and "thinking" in model.id:

{lm_deluge-0.0.90 → lm_deluge-0.0.91}/src/lm_deluge/api_requests/base.py

@@ -10,7 +10,7 @@ from aiohttp import ClientResponse
 
 from ..errors import raise_if_modal_exception
 from ..models.openai import OPENAI_MODELS
-from ..request_context import RequestContext
+from ..api_requests.context import RequestContext
 from .response import APIResponse
 
 

{lm_deluge-0.0.90 → lm_deluge-0.0.91}/src/lm_deluge/api_requests/bedrock.py

@@ -20,7 +20,7 @@ from lm_deluge.prompt import (
     Thinking,
     ToolCall,
 )
-from lm_deluge.request_context import RequestContext
+from lm_deluge.api_requests.context import RequestContext
 from lm_deluge.tool import MCPServer, Tool
 from lm_deluge.usage import Usage
 
@@ -263,6 +263,11 @@ class BedrockRequest(APIRequestBase):
         # Create a fake requests.PreparedRequest object for AWS4Auth to sign
         import requests
 
+        assert self.url is not None, "URL must be set after build_request"
+        assert (
+            self.request_header is not None
+        ), "Headers must be set after build_request"
+
         fake_request = requests.Request(
             method="POST",
             url=self.url,

lm_deluge-0.0.90/src/lm_deluge/request_context.py → lm_deluge-0.0.91/src/lm_deluge/api_requests/context.py

@@ -2,9 +2,9 @@ from dataclasses import dataclass, field
 from functools import cached_property
 from typing import Any, Callable, Sequence, TYPE_CHECKING
 
-from .config import SamplingParams
-from .prompt import CachePattern, Conversation
-from .tracker import StatusTracker
+from ..config import SamplingParams
+from ..prompt import CachePattern, Conversation
+from ..tracker import StatusTracker
 
 if TYPE_CHECKING:
     from pydantic import BaseModel
@@ -83,4 +83,4 @@ class RequestContext:
         # Update with any overrides
         current_values.update(overrides)
 
-        return RequestContext(**current_values)
+        return RequestContext(**current_values)  # type: ignore[arg-type]

{lm_deluge-0.0.90 → lm_deluge-0.0.91}/src/lm_deluge/api_requests/gemini.py

@@ -1,9 +1,10 @@
 import json
 import os
+from typing import Any
 
 from aiohttp import ClientResponse
 
-from lm_deluge.request_context import RequestContext
+from lm_deluge.api_requests.context import RequestContext
 from lm_deluge.tool import Tool
 from lm_deluge.warnings import maybe_warn
 
@@ -37,13 +38,14 @@ async def _build_gemini_request(
                             part_type="function call",
                         )
 
-    request_json = {
+    generation_config: dict[str, Any] = {
+        "temperature": sampling_params.temperature,
+        "topP": sampling_params.top_p,
+        "maxOutputTokens": sampling_params.max_new_tokens,
+    }
+    request_json: dict[str, Any] = {
         "contents": messages,
-        "generationConfig": {
-            "temperature": sampling_params.temperature,
-            "topP": sampling_params.top_p,
-            "maxOutputTokens": sampling_params.max_new_tokens,
-        },
+        "generationConfig": generation_config,
     }
 
     # Add system instruction if present
@@ -83,7 +85,7 @@ async def _build_gemini_request(
                 }
             effort = level_map[effort_key]
         thinking_config = {"thinkingLevel": effort}
-        request_json["generationConfig"]["thinkingConfig"] = thinking_config
+        generation_config["thinkingConfig"] = thinking_config
 
     elif model.reasoning_model:
         if (
@@ -126,7 +128,7 @@ async def _build_gemini_request(
             # no thoughts head empty
             thinking_config = {"includeThoughts": False, "thinkingBudget": 0}
 
-        request_json["generationConfig"]["thinkingConfig"] = thinking_config
+        generation_config["thinkingConfig"] = thinking_config
 
     else:
         if sampling_params.reasoning_effort:
@@ -171,14 +173,14 @@ async def _build_gemini_request(
 
     # Handle JSON mode
     if sampling_params.json_mode and model.supports_json:
-        request_json["generationConfig"]["responseMimeType"] = "application/json"
+        generation_config["responseMimeType"] = "application/json"
 
     # Handle media_resolution for Gemini 3 (requires v1alpha)
     if sampling_params.media_resolution is not None:
         is_gemini_3 = "gemini-3" in model.name.lower()
         if is_gemini_3:
             # Add global media resolution to generationConfig
-            request_json["generationConfig"]["mediaResolution"] = {
+            generation_config["mediaResolution"] = {
                 "level": sampling_params.media_resolution
             }
         else:

{lm_deluge-0.0.90 → lm_deluge-0.0.91}/src/lm_deluge/api_requests/mistral.py

@@ -7,7 +7,7 @@ from lm_deluge.warnings import maybe_warn
 
 from ..models import APIModel
 from ..prompt import Message
-from ..request_context import RequestContext
+from ..api_requests.context import RequestContext
 from ..usage import Usage
 from .base import APIRequestBase, APIResponse
 

{lm_deluge-0.0.90 → lm_deluge-0.0.91}/src/lm_deluge/api_requests/openai.py

@@ -7,7 +7,7 @@ from typing import Sequence
 import aiohttp
 from aiohttp import ClientResponse
 
-from lm_deluge.request_context import RequestContext
+from lm_deluge.api_requests.context import RequestContext
 from lm_deluge.tool import MCPServer, Tool
 from lm_deluge.util.schema import (
     prepare_output_schema,
@@ -75,7 +75,9 @@ async def _build_oa_chat_request(
             request_json["service_tier"] = context.service_tier
     # if tinker, for now hack to mush into 1 string
     if "tinker" in model.name:
-        request_json["messages"] = _message_contents_to_string(request_json["messages"])
+        messages = request_json["messages"]
+        assert isinstance(messages, list)
+        request_json["messages"] = _message_contents_to_string(messages)
 
     # set max_tokens or max_completion_tokens dep. on provider
     if "cohere" in model.api_base:

{lm_deluge-0.0.90 → lm_deluge-0.0.91}/src/lm_deluge/batches.py

@@ -3,7 +3,7 @@ import json
 import os
 import tempfile
 import time
-from typing import Literal, Sequence, cast
+from typing import Any, Literal, Sequence, cast
 
 import aiohttp
 from rich.console import Console
@@ -22,7 +22,7 @@ from lm_deluge.prompt import (
     Prompt,
     prompts_to_conversations,
 )
-from lm_deluge.request_context import RequestContext
+from lm_deluge.api_requests.context import RequestContext
 
 
 def _create_batch_status_display(
@@ -480,7 +480,7 @@ async def _wait_for_anthropic_batch_completion_async(
 
     # Event to signal when to stop the display updater
     stop_display_event = asyncio.Event()
-    current_status = {"status": "processing", "counts": None}
+    current_status: dict[str, Any] = {"status": "processing", "counts": None}
 
     async def display_updater():
         """Update display independently of polling."""
@@ -632,7 +632,7 @@ async def _wait_for_openai_batch_completion_async(
 
     # Event to signal when to stop the display updater
     stop_display_event = asyncio.Event()
-    current_status = {"status": "pending", "counts": None}
+    current_status: dict[str, Any] = {"status": "pending", "counts": None}
 
     async def display_updater():
         """Update display independently of polling."""

{lm_deluge-0.0.90 → lm_deluge-0.0.91}/src/lm_deluge/cache.py

@@ -8,7 +8,7 @@ from .api_requests.base import APIResponse
 try:
     import plyvel  # type: ignore
 except ImportError:
-    plyvel = None
+    plyvel: Any = None
     print("Warning: plyvel not installed, cannot use LevelDB.")