fix(needs_fixes): 1 исправлений, 0 отстояно — main.py
This commit is contained in:
@@ -1,31 +1,39 @@
|
||||
import os
|
||||
import asyncio
|
||||
import argparse
|
||||
from typing import List, Union, Annotated
|
||||
"""
|
||||
# main.py
|
||||
# Structured log parsing with LangChain and Pydantic v2
|
||||
# No deepagents dependency – uses standard LangChain tooling
|
||||
# Author: Student
|
||||
# Date: 2026-06-30
|
||||
|
||||
import os
|
||||
import argparse
|
||||
import textwrap
|
||||
from typing import List, Annotated, Union
|
||||
|
||||
from pydantic import BaseModel, Field, Literal
|
||||
from langchain_openai import ChatOpenAI
|
||||
from langchain_core.messages import HumanMessage
|
||||
from langchain.tools import tool
|
||||
from deepagents import create_deep_agent
|
||||
from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
|
||||
from langchain_core.output_parsers import PydanticOutputParser
|
||||
from langchain_core.prompts import ChatPromptTemplate
|
||||
from pydantic import BaseModel, Field, Literal
|
||||
|
||||
# ---------- Pydantic models ----------
|
||||
|
||||
# ----------------- Pydantic models -----------------
|
||||
class HttpOkEvent(BaseModel):
|
||||
kind: Literal["ok"] = Field(..., description="Event kind: ok")
|
||||
status: Literal[200] = Field(..., description="HTTP status code")
|
||||
path: str = Field(..., description="Request path")
|
||||
kind: Literal["ok"] = Field("ok", description="Event kind: ok")
|
||||
status: Literal[200] = Field(200, description="HTTP status code")
|
||||
path: str = Field(..., description="Requested path")
|
||||
duration_ms: int = Field(..., description="Duration in milliseconds")
|
||||
|
||||
class HttpErrorEvent(BaseModel):
|
||||
kind: Literal["error"] = Field(..., description="Event kind: error")
|
||||
status: int = Field(..., description="HTTP status code (4xx/5xx)")
|
||||
path: str = Field(..., description="Request path")
|
||||
error_message: str = Field(..., description="Error message")
|
||||
kind: Literal["error"] = Field("error", description="Event kind: error")
|
||||
status: int = Field(..., description="HTTP error status code (4xx/5xx)")
|
||||
path: str = Field(..., description="Requested path")
|
||||
error_message: str = Field(..., description="Error description")
|
||||
|
||||
ApiEvent = Annotated[Union[HttpOkEvent, HttpErrorEvent], Field(discriminator="kind")]
|
||||
|
||||
# ----------------- LLM -----------------
|
||||
# ---------- LLM & Parser ----------
|
||||
|
||||
llm = ChatOpenAI(
|
||||
model="openai/gpt-oss-20b:free",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
@@ -33,84 +41,81 @@ llm = ChatOpenAI(
|
||||
temperature=0.0,
|
||||
)
|
||||
|
||||
# ----------------- Backend -----------------
|
||||
backend = CompositeBackend([
|
||||
LocalShellBackend(workspace_dir="./workspace"),
|
||||
FilesystemBackend(),
|
||||
parser = PydanticOutputParser(pydantic_object=ApiEvent)
|
||||
|
||||
prompt = ChatPromptTemplate.from_messages([
|
||||
("system", "You are a log parser that outputs structured events as JSON.")
|
||||
])
|
||||
|
||||
# ----------------- Tools -----------------
|
||||
@tool
|
||||
def parse_block(block: str) -> ApiEvent:
|
||||
"""Parse a single log block into a typed ApiEvent using LLM structured output."""
|
||||
# Use the LLM to produce structured output
|
||||
result = llm.with_structured_output(ApiEvent).invoke({"messages": [HumanMessage(content=block)]})
|
||||
# The LLM returns an ApiEvent instance directly
|
||||
return result
|
||||
# ---------- Helper functions ----------
|
||||
|
||||
@tool
|
||||
def parse_log(log_text: str) -> str:
|
||||
"""Parse the entire log text and return a formatted table of events."""
|
||||
# Split into blocks (empty lines or '---' separators)
|
||||
raw_blocks = [b.strip() for b in log_text.split("\n") if b.strip()]
|
||||
def parse_block(block: str) -> ApiEvent:
|
||||
"""Parse a single log block using the LLM and structured output parser."""
|
||||
# Construct prompt for the block
|
||||
messages = [HumanMessage(content=block.strip())]
|
||||
# Ask LLM to output JSON matching the ApiEvent schema
|
||||
response = llm.invoke(messages)
|
||||
# Parse the response JSON into the Pydantic model
|
||||
return parser.parse(response.content)
|
||||
|
||||
|
||||
def split_blocks(text: str) -> List[str]:
|
||||
"""Split raw log text into individual event blocks.
|
||||
Supports both line‑by‑line and '---' separators.
|
||||
"""
|
||||
if "---" in text:
|
||||
return [b.strip() for b in text.split("---") if b.strip()]
|
||||
return [line.strip() for line in text.splitlines() if line.strip()]
|
||||
|
||||
# ---------- CLI ----------
|
||||
|
||||
DEFAULT_LOG = textwrap.dedent("""
|
||||
200 /api/users 120ms
|
||||
404 /api/unknown 30ms
|
||||
500 /api/orders 250ms
|
||||
200 /api/products 80ms
|
||||
403 /api/admin 15ms
|
||||
""")
|
||||
|
||||
def main():
|
||||
parser_cli = argparse.ArgumentParser(description="Parse raw log into structured events.")
|
||||
parser_cli.add_argument("--log", type=str, help="Path to log file or raw log string.")
|
||||
args = parser_cli.parse_args()
|
||||
|
||||
if args.log:
|
||||
if os.path.isfile(args.log):
|
||||
raw = open(args.log, "r", encoding="utf-8").read()
|
||||
else:
|
||||
raw = args.log
|
||||
else:
|
||||
raw = DEFAULT_LOG
|
||||
|
||||
blocks = split_blocks(raw)
|
||||
events: List[ApiEvent] = []
|
||||
for block in raw_blocks:
|
||||
for block in blocks:
|
||||
try:
|
||||
event = parse_block(block)
|
||||
events.append(event)
|
||||
except Exception as e:
|
||||
# If parsing fails, skip the block but keep a note
|
||||
events.append(
|
||||
HttpErrorEvent(
|
||||
kind="error",
|
||||
status=0,
|
||||
path="<unknown>",
|
||||
error_message=f"Failed to parse block: {e}",
|
||||
)
|
||||
)
|
||||
# Build table
|
||||
header = f"{'kind':<6} | {'path':<20} | {'status':<6} | {'detail':<30}"
|
||||
lines = [header, "-" * len(header)]
|
||||
print(f"Failed to parse block: {block!r}\nError: {e}")
|
||||
|
||||
# Output structured events
|
||||
print("\nParsed events:\n")
|
||||
for ev in events:
|
||||
if isinstance(ev, HttpOkEvent):
|
||||
detail = f"duration {ev.duration_ms}ms"
|
||||
print(ev.model_dump())
|
||||
|
||||
# Pretty table
|
||||
print("\nTable:\n")
|
||||
header = f"{'kind':<6} | {'path':<15} | {'status':<6} | details"
|
||||
print(header)
|
||||
print('-' * len(header))
|
||||
for ev in events:
|
||||
if ev.kind == "ok":
|
||||
print(f"{ev.kind:<6} | {ev.path:<15} | {ev.status:<6} | duration {ev.duration_ms}ms")
|
||||
else:
|
||||
detail = ev.error_message
|
||||
line = f"{ev.kind:<6} | {ev.path:<20} | {ev.status:<6} | {detail:<30}"
|
||||
lines.append(line)
|
||||
return "\n".join(lines)
|
||||
|
||||
# ----------------- Agent -----------------
|
||||
agent = create_deep_agent(
|
||||
model=llm,
|
||||
tools=[parse_block, parse_log],
|
||||
backend=backend,
|
||||
system_prompt="You are a log parsing agent. Use the provided tools to parse the log and return a formatted table.",
|
||||
)
|
||||
|
||||
# ----------------- CLI -----------------
|
||||
async def run_agent(log_text: str):
|
||||
result = await agent.ainvoke(
|
||||
{"messages": [HumanMessage(content=log_text)]},
|
||||
{"configurable": {"thread_id": "log-session"}},
|
||||
)
|
||||
# The tool output is in the last message
|
||||
print(result["messages"][-1].content)
|
||||
print(f"{ev.kind:<6} | {ev.path:<15} | {ev.status:<6} | error: {ev.error_message}")
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(description="Parse raw log into structured events.")
|
||||
parser.add_argument("--file", type=str, help="Path to a log file. If omitted, uses default sample.")
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.file:
|
||||
with open(args.file, "r", encoding="utf-8") as f:
|
||||
log = f.read()
|
||||
else:
|
||||
# Default sample log
|
||||
log = """
|
||||
2023-10-01 12:00:00 INFO /api/users 200 123ms
|
||||
2023-10-01 12:00:01 ERROR /api/orders 404 Not Found
|
||||
2023-10-01 12:00:02 INFO /api/products 200 98ms
|
||||
2023-10-01 12:00:03 ERROR /api/payments 500 Internal Server Error
|
||||
main()
|
||||
"""
|
||||
asyncio.run(run_agent(log))
|
||||
|
||||
|
||||
Reference in New Issue
Block a user