feat: improve ai writing imitation flow

This commit is contained in:
董宏凯 committed 2026-07-01 17:16:12 +08:00
1 parent 0547fb1715
commit 025e43f4c5
14 files changed
+927 -117

No files matched your search

@@ -5,10 +5,19 @@ import json
import logging
import re
from langchain_core.messages import HumanMessage, SystemMessage
from langchain_core.runnables import RunnableConfig
from ..state import AIWritingState, SampleStyleProfile
from ._utils import count_words, llm_json
from ._utils import (
ThinkTagParser,
_content_to_text,
count_words,
get_model,
parse_json,
reasoning_delta,
safe_get_stream_writer,
)
logger = logging.getLogger(__name__)
@@ -146,6 +155,72 @@ def render_sample_style_section(state: AIWritingState) -> str:
)
async def _stream_sample_analysis(
*,
filename: str,
sample_text: str,
clipped: str,
fallback: dict,
config: RunnableConfig,
model_name: str | None,
) -> dict:
writer = safe_get_stream_writer()
writer({
"type": "sample_chunk",
"agent_name": "样文分析师",
"text": (
f"读取样文《{filename}》,约 {count_words(sample_text)} 字;"
f"本轮提取前 {len(clipped)} 字用于文风画像。\n"
"正在识别文章类型、结构骨架、语气、句式节奏、仿写建议和避抄边界...\n\n"
),
"is_thinking": False,
})
messages = [
SystemMessage(content=SAMPLE_ANALYZE_SYSTEM),
HumanMessage(content=SAMPLE_ANALYZE_USER.format(
filename=filename,
word_count=count_words(sample_text),
sample_text=clipped,
)),
]
full_text = ""
try:
model = get_model(config, model_name=model_name, disable_thinking=True)
parser = ThinkTagParser()
async for chunk in model.astream(messages):
reasoning = reasoning_delta(chunk)
if reasoning:
writer({
"type": "sample_chunk",
"agent_name": "样文分析师",
"text": reasoning,
"is_thinking": True,
})
delta = _content_to_text(chunk.content)
if not delta:
continue
for is_thinking, text in parser.feed(delta):
if not is_thinking:
full_text += text
writer({
"type": "sample_chunk",
"agent_name": "样文分析师",
"text": text,
"is_thinking": is_thinking,
})
return parse_json(full_text, fallback) if full_text.strip() else fallback
except Exception as exc:
logger.error("sample_analyzer streaming failed: %s", exc, exc_info=True)
writer({
"type": "sample_chunk",
"agent_name": "样文分析师",
"text": "\n样文分析模型异常,已改用基础画像兜底。\n",
"is_thinking": False,
})
return {**fallback, "_llm_error": str(exc)}
async def sample_analyzer_node(state: AIWritingState, config: RunnableConfig) -> dict:
if not _is_imitate_mode(state):
return {}
@@ -168,17 +243,13 @@ async def sample_analyzer_node(state: AIWritingState, config: RunnableConfig) ->
fallback = _fallback_profile(clipped)
configurable = (config or {}).get("configurable", {}) or {}
model_name = (state.get("model_name") or configurable.get("model_name") or "").strip() or None
raw = await llm_json(
SAMPLE_ANALYZE_SYSTEM,
SAMPLE_ANALYZE_USER.format(
filename=filename,
word_count=count_words(sample_text),
sample_text=clipped,
),
fallback,
config,
raw = await _stream_sample_analysis(
filename=filename,
sample_text=sample_text,
clipped=clipped,
fallback=fallback,
config=config,
model_name=model_name,
disable_thinking=True,
)
profile = _normalize_profile(raw, clipped)
events = [