opengradient 0.5.2__tar.gz → 0.5.7__tar.gz

{opengradient-0.5.2/src/opengradient.egg-info → opengradient-0.5.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opengradient
-Version: 0.5.2
+Version: 0.5.7
 Summary: Python SDK for OpenGradient decentralized model management & inference services
 Author-email: OpenGradient <kyle@vannalabs.ai>
 License-Expression: MIT
@@ -24,6 +24,7 @@ Requires-Dist: langchain>=0.3.7
 Requires-Dist: openai>=1.58.1
 Requires-Dist: pydantic>=2.9.2
 Requires-Dist: og-test-x402==0.0.1
+Requires-Dist: x402==0.2.1
 Dynamic: license-file
 
 # OpenGradient Python SDK

{opengradient-0.5.2 → opengradient-0.5.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "opengradient"
-version = "0.5.2"
+version = "0.5.7"
 description = "Python SDK for OpenGradient decentralized model management & inference services"
 authors = [{name = "OpenGradient", email = "kyle@vannalabs.ai"}]
 readme = "README.md"
@@ -30,6 +30,7 @@ dependencies = [
     "openai>=1.58.1",
     "pydantic>=2.9.2",
     "og-test-x402==0.0.1",
+    "x402==0.2.1"
 ]
 
 [project.scripts]

{opengradient-0.5.2 → opengradient-0.5.7}/src/opengradient/cli.py

@@ -20,7 +20,7 @@ from .defaults import (
     DEFAULT_API_URL,
     DEFAULT_LLM_SERVER_URL,
 )
-from .types import InferenceMode, LlmInferenceMode, LLM, TEE_LLM
+from .types import InferenceMode, LlmInferenceMode, LLM, TEE_LLM, x402SettlementMode
 
 OG_CONFIG_FILE = Path.home() / ".opengradient_config.json"
 
@@ -74,6 +74,12 @@ LlmInferenceModes = {
 }
 
 
+x402SettlementModes = {
+    "settle-batch": x402SettlementMode.SETTLE_BATCH,
+    "settle": x402SettlementMode.SETTLE,
+    "settle-metadata": x402SettlementMode.SETTLE_METADATA,
+}
+
 def initialize_config(ctx):
     """Interactively initialize OpenGradient config"""
     if ctx.obj:  # Check if config data already exists
@@ -422,8 +428,9 @@ def infer(ctx, model_cid: str, inference_mode: str, input_data, input_file: Path
 @click.option("--stop-sequence", multiple=True, help="Stop sequences for LLM")
 @click.option("--temperature", type=float, default=0.0, help="Temperature for LLM inference (0.0 to 1.0)")
 @click.option("--local", is_flag=True, help="Force use of local model even if not in LLM enum")
+@click.option("--x402-settlement-mode", "x402_settlement_mode", type=click.Choice(x402SettlementModes.keys()), default="settle-batch", help="Settlement mode for x402 payload")
 @click.pass_context
-def completion(ctx, model_cid: str, inference_mode: str, prompt: str, max_tokens: int, stop_sequence: List[str], temperature: float, local: bool):
+def completion(ctx, model_cid: str, inference_mode: str, x402_settlement_mode: str, prompt: str, max_tokens: int, stop_sequence: List[str], temperature: float, local: bool):
     """
     Run completion inference on an LLM model (local or external).
 
@@ -464,6 +471,7 @@ def completion(ctx, model_cid: str, inference_mode: str, prompt: str, max_tokens
             stop_sequence=list(stop_sequence),
             temperature=temperature,
             local_model=local,
+            x402_settlement_mode=x402_settlement_mode,
         )
 
         print_llm_completion_result(model_cid, completion_output.transaction_hash, completion_output.completion_output, is_local)
@@ -529,6 +537,7 @@ def print_llm_completion_result(model_cid, tx_hash, llm_output, is_local=True):
 )
 @click.option("--tool-choice", type=str, default="", help="Specific tool choice for the LLM")
 @click.option("--local", is_flag=True, help="Force use of local model even if not in LLM enum")
+@click.option("--x402-settlement-mode", type=click.Choice(x402SettlementModes.keys()), default="settle-batch", help="Settlement mode for x402 payload")
 @click.pass_context
 def chat(
     ctx,
@@ -542,6 +551,7 @@ def chat(
     tools: Optional[str],
     tools_file: Optional[Path],
     tool_choice: Optional[str],
+    x402_settlement_mode: Optional[str],
     local: bool,
 ):
     """
@@ -637,6 +647,7 @@ def chat(
             tools=parsed_tools,
             tool_choice=tool_choice,
             local_model=local,
+            x402_settlement_mode=x402_settlement_mode,
         )
 
         print_llm_chat_result(

{opengradient-0.5.2 → opengradient-0.5.7}/src/opengradient/client.py

@@ -23,6 +23,7 @@ from .proto import infer_pb2, infer_pb2_grpc
 from .types import (
     LLM,
     TEE_LLM,
+    x402SettlementMode,
     HistoricalInputQuery,
     InferenceMode,
     LlmInferenceMode,
@@ -436,6 +437,7 @@ class Client:
         inference_mode: LlmInferenceMode = LlmInferenceMode.VANILLA,
         max_retries: Optional[int] = None,
         local_model: Optional[bool] = False,
+        x402_settlement_mode: Optional[x402SettlementMode] = x402SettlementMode.SETTLE_BATCH,
     ) -> TextGenerationOutput:
         """
         Perform inference on an LLM model using completions.
@@ -470,6 +472,7 @@ class Client:
                 max_tokens=max_tokens,
                 stop_sequence=stop_sequence,
                 temperature=temperature,
+                x402_settlement_mode=x402_settlement_mode,
             )
         
         # Original local model logic
@@ -516,6 +519,7 @@ class Client:
         max_tokens: int = 100,
         stop_sequence: Optional[List[str]] = None,
         temperature: float = 0.0,
+        x402_settlement_mode: Optional[x402SettlementMode] = x402SettlementMode.SETTLE_BATCH,
     ) -> TextGenerationOutput:
         """
         Route completion request to external LLM server with x402 payments.
@@ -584,7 +588,8 @@ class Client:
             ) as client:
                 headers = {
                     "Content-Type": "application/json",
-                    "Authorization": f"Bearer {X402_PLACEHOLDER_API_KEY}"
+                    "Authorization": f"Bearer {X402_PLACEHOLDER_API_KEY}",
+                    "X-SETTLEMENT-TYPE": x402_settlement_mode,
                 }
                 
                 payload = {
@@ -645,6 +650,7 @@ class Client:
         tool_choice: Optional[str] = None,
         max_retries: Optional[int] = None,
         local_model: Optional[bool] = False,
+        x402_settlement_mode: Optional[x402SettlementMode] = x402SettlementMode.SETTLE_BATCH,
     ) -> TextGenerationOutput:
         """
         Perform inference on an LLM model using chat.
@@ -681,6 +687,7 @@ class Client:
                 temperature=temperature,
                 tools=tools,
                 tool_choice=tool_choice,
+                x402_settlement_mode=x402_settlement_mode,
             )
         
         # Original local model logic
@@ -760,6 +767,7 @@ class Client:
         temperature: float = 0.0,
         tools: Optional[List[Dict]] = None,
         tool_choice: Optional[str] = None,
+        x402_settlement_mode: x402SettlementMode = x402SettlementMode.SETTLE_BATCH,
     ) -> TextGenerationOutput:
         """
         Route chat request to external LLM server with x402 payments.
@@ -835,7 +843,8 @@ class Client:
             ) as client:
                 headers = {
                     "Content-Type": "application/json",
-                    "Authorization": f"Bearer {X402_PLACEHOLDER_API_KEY}"
+                    "Authorization": f"Bearer {X402_PLACEHOLDER_API_KEY}",
+                    "X-SETTLEMENT-TYPE": x402_settlement_mode
                 }
                 
                 payload = {
@@ -858,6 +867,8 @@ class Client:
                     # Read the response content
                     content = await response.aread()
                     result = json.loads(content.decode())
+                    # print(f"Response: {response}")
+                    # print(f"Response Headers: {response.headers}")
 
                     payment_hash = ""
                     if X402_PROCESSING_HASH_HEADER in response.headers:

{opengradient-0.5.2 → opengradient-0.5.7}/src/opengradient/types.py

@@ -1,10 +1,15 @@
 import time
 from dataclasses import dataclass
-from enum import Enum, IntEnum
+from enum import Enum, IntEnum, StrEnum
 from typing import Dict, List, Optional, Tuple, Union, DefaultDict
 import numpy as np
 
 
+class x402SettlementMode(StrEnum):
+    SETTLE = "settle"
+    SETTLE_METADATA = "settle-metadata"
+    SETTLE_BATCH = "settle-batch"
+
 class CandleOrder(IntEnum):
     ASCENDING = 0
     DESCENDING = 1
@@ -193,36 +198,37 @@ class Abi:
 class LLM(str, Enum):
     """Enum for available LLM models"""
 
-    # Existing open-source OG hosted models
-    META_LLAMA_3_8B_INSTRUCT = "meta-llama/Meta-Llama-3-8B-Instruct"
-    LLAMA_3_2_3B_INSTRUCT = "meta-llama/Llama-3.2-3B-Instruct"
-    QWEN_2_5_72B_INSTRUCT = "Qwen/Qwen2.5-72B-Instruct"
-    META_LLAMA_3_1_70B_INSTRUCT = "meta-llama/Llama-3.1-70B-Instruct"
-    DOBBY_UNHINGED_3_1_8B = "SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B"
-    DOBBY_LEASHED_3_1_8B = "SentientAGI/Dobby-Mini-Leashed-Llama-3.1-8B"
+    # # Existing open-source OG hosted models
+    # META_LLAMA_3_8B_INSTRUCT = "meta-llama/Meta-Llama-3-8B-Instruct"
+    # LLAMA_3_2_3B_INSTRUCT = "meta-llama/Llama-3.2-3B-Instruct"
+    # QWEN_2_5_72B_INSTRUCT = "Qwen/Qwen2.5-72B-Instruct"
+    # META_LLAMA_3_1_70B_INSTRUCT = "meta-llama/Llama-3.1-70B-Instruct"
+    # DOBBY_UNHINGED_3_1_8B = "SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B"
+    # DOBBY_LEASHED_3_1_8B = "SentientAGI/Dobby-Mini-Leashed-Llama-3.1-8B"
     
     # OpenAI models via TEE
-    GPT_4_1_2025_04_14 = "OpenAI/gpt-4.1-2025-04-14"
-    GPT_4O = "OpenAI/gpt-4o"
-    O4_MINI = "OpenAI/o4-mini"
+    GPT_4_1_2025_04_14 = "openai/gpt-4.1-2025-04-14"
+    GPT_4O = "openai/gpt-4o"
+    O4_MINI = "openai/o4-mini"
     
     # Anthropic models via TEE
-    CLAUDE_3_7_SONNET = "Anthropic/claude-3.7-sonnet"
-    CLAUDE_3_5_HAIKU = "Anthropic/claude-3.5-haiku"
-    CLAUDE_4_0_SONNET = "Anthropic/claude-4.0-sonnet"
+    CLAUDE_3_7_SONNET = "anthropic/claude-3.7-sonnet"
+    CLAUDE_3_5_HAIKU = "anthropic/claude-3.5-haiku"
+    CLAUDE_4_0_SONNET = "anthropic/claude-4.0-sonnet"
     
     # Google models via TEE
-    GEMINI_2_5_FLASH = "Google/gemini-2.5-flash"
-    GEMINI_2_5_PRO = "Google/gemini-2.5-pro"
-    GEMINI_2_0_FLASH = "Google/gemini-2.0-flash"
+    GEMINI_2_5_FLASH = "google/gemini-2.5-flash"
+    GEMINI_2_5_PRO = "google/gemini-2.5-pro"
+    GEMINI_2_0_FLASH = "google/gemini-2.0-flash"
+    GEMINI_2_5_FLASH_LITE = "google/gemini-2.5-flash-lite"
     
     # xAI Grok models via TEE
-    GROK_3_MINI_BETA = "xAI/grok-3-mini-beta"
-    GROK_3_BETA = "xAI/grok-3-beta"
-    GROK_2_1212 = "grok-2-1212"
-    GROK_2_VISION_LATEST = "xAI/grok-2-vision-latest"
-    GROK_4_1_FAST = "xAI/grok-4.1-fast"
-    GROK_4_1_FAST_NON_REASONING = "xAI/grok-4-1-fast-non-reasoning"
+    GROK_3_MINI_BETA = "x-ai/grok-3-mini-beta"
+    GROK_3_BETA = "x-ai/grok-3-beta"
+    GROK_2_1212 = "x-ai/grok-2-1212"
+    GROK_2_VISION_LATEST = "x-ai/grok-2-vision-latest"
+    GROK_4_1_FAST = "x-ai/grok-4.1-fast"
+    GROK_4_1_FAST_NON_REASONING = "x-ai/grok-4-1-fast-non-reasoning"
 
 class TEE_LLM(str, Enum):
     """Enum for LLM models available for TEE execution"""
@@ -231,27 +237,28 @@ class TEE_LLM(str, Enum):
     # META_LLAMA_3_1_70B_INSTRUCT = "meta-llama/Llama-3.1-70B-Instruct"
     
     # OpenAI models via TEE
-    GPT_4_1_2025_04_14 = "OpenAI/gpt-4.1-2025-04-14"
-    GPT_4O = "OpenAI/gpt-4o"
-    O4_MINI = "OpenAI/o4-mini"
+    GPT_4_1_2025_04_14 = "openai/gpt-4.1-2025-04-14"
+    GPT_4O = "openai/gpt-4o"
+    O4_MINI = "openai/o4-mini"
     
     # Anthropic models via TEE
-    CLAUDE_3_7_SONNET = "Anthropic/claude-3.7-sonnet"
-    CLAUDE_3_5_HAIKU = "Anthropic/claude-3.5-haiku"
-    CLAUDE_4_0_SONNET = "Anthropic/claude-4.0-sonnet"
+    CLAUDE_3_7_SONNET = "anthropic/claude-3.7-sonnet"
+    CLAUDE_3_5_HAIKU = "anthropic/claude-3.5-haiku"
+    CLAUDE_4_0_SONNET = "anthropic/claude-4.0-sonnet"
     
     # Google models via TEE
-    GEMINI_2_5_FLASH = "Google/gemini-2.5-flash"
-    GEMINI_2_5_PRO = "Google/gemini-2.5-pro"
-    GEMINI_2_0_FLASH = "Google/gemini-2.0-flash"
+    GEMINI_2_5_FLASH = "google/gemini-2.5-flash"
+    GEMINI_2_5_PRO = "google/gemini-2.5-pro"
+    GEMINI_2_0_FLASH = "google/gemini-2.0-flash"
+    GEMINI_2_5_FLASH_LITE = "google/gemini-2.5-flash-lite"
     
     # xAI Grok models via TEE
-    GROK_3_MINI_BETA = "xAI/grok-3-mini-beta"
-    GROK_3_BETA = "xAI/grok-3-beta"
-    GROK_2_1212 = "xAI/grok-2-1212"
-    GROK_2_VISION_LATEST = "xAI/grok-2-vision-latest"
-    GROK_4_1_FAST = "xAI/grok-4.1-fast"
-    GROK_4_1_FAST_NON_REASONING = "xAI/grok-4-1-fast-non-reasoning"
+    GROK_3_MINI_BETA = "x-ai/grok-3-mini-beta"
+    GROK_3_BETA = "x-ai/grok-3-beta"
+    GROK_2_1212 = "x-ai/grok-2-1212"
+    GROK_2_VISION_LATEST = "x-ai/grok-2-vision-latest"
+    GROK_4_1_FAST = "x-ai/grok-4.1-fast"
+    GROK_4_1_FAST_NON_REASONING = "x-ai/grok-4-1-fast-non-reasoning"
 
 
 @dataclass

{opengradient-0.5.2 → opengradient-0.5.7/src/opengradient.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opengradient
-Version: 0.5.2
+Version: 0.5.7
 Summary: Python SDK for OpenGradient decentralized model management & inference services
 Author-email: OpenGradient <kyle@vannalabs.ai>
 License-Expression: MIT
@@ -24,6 +24,7 @@ Requires-Dist: langchain>=0.3.7
 Requires-Dist: openai>=1.58.1
 Requires-Dist: pydantic>=2.9.2
 Requires-Dist: og-test-x402==0.0.1
+Requires-Dist: x402==0.2.1
 Dynamic: license-file
 
 # OpenGradient Python SDK

{opengradient-0.5.2 → opengradient-0.5.7}/src/opengradient.egg-info/requires.txt

@@ -9,3 +9,4 @@ langchain>=0.3.7
 openai>=1.58.1
 pydantic>=2.9.2
 og-test-x402==0.0.1
+x402==0.2.1