fix(memoir): 改善 story 合并决策，少生碎片篇
以前模型只看到很短预览，还容易被引导成新建 story。现在优先用已有摘要、 按需带正文片段，并区分「像续写同一主题」和「像换了一件事」； beliefs/summary 更鼓励接着写， career/童年等仍可按新事件新开。
This commit is contained in:
Kevin
128
.cursor/plans/story_route_append_context.plan.md
Normal file
128
.cursor/plans/story_route_append_context.plan.md
Normal file
@@ -0,0 +1,128 @@
|
||||
---
|
||||
name: Story route append context
|
||||
overview: 候选载荷增胖（summary 优先 + 可配置预算）+ category-aware prompt 纠偏 + 最小测试集；不扩大路由体系、不改 schema、不接离线合并。
|
||||
todos:
|
||||
- id: config-budget
|
||||
content: Add Settings — story_route_candidate_body_max_chars, total_max, head/tail, summary_min_len (optional)
|
||||
status: completed
|
||||
- id: payload-builder
|
||||
content: build_route_candidate_rows — fixed sort, summary-first body rules, total budget downgrade to index rows
|
||||
status: completed
|
||||
- id: prompts-merge-bias
|
||||
content: get_story_route_prompt + get_story_batch_plan — two-layer criteria, category blocks, remove default-to-new_story
|
||||
status: completed
|
||||
- id: wire-agent
|
||||
content: StoryRouteAgent decide/plan_batch use new builder + prompts; validate_story_batch_plan unchanged; no pipeline signature change
|
||||
status: completed
|
||||
- id: tests
|
||||
content: Builder tests + prompt contains + beliefs append smoke + career new_story smoke + test_story_route_oral_invariant
|
||||
status: completed
|
||||
isProject: false
|
||||
---
|
||||
|
||||
# Story Route：候选上下文增胖 + category-aware append 纠偏
|
||||
|
||||
## Ticket / PR 一句话
|
||||
|
||||
用更富的候选 JSON（**summary 优先**、再按需补正文）与 **按类目纠偏** 的提示词，修复 `StoryRouteAgent` 在强主题类目下过度 `new_story`；预算 **Settings 化**，默认值 **保守**；**不改** memoir 流水线签名与 DB schema。
|
||||
|
||||
## 根因（代码事实）
|
||||
|
||||
- `[api/app/agents/memoir/story_route_agent.py](api/app/agents/memoir/story_route_agent.py)`：`preview_chars=220`，同类目下多条短感悟几乎不可区分。
|
||||
- `[api/app/agents/memoir/prompts.py](api/app/agents/memoir/prompts.py)`：**「若无法自信匹配某一候选，选 new_story」** → 与「主题容器逐步加厚」产品预期相反。
|
||||
- `Story.summary` 列存在，**路由未用**；仅截 `canonical_markdown`。
|
||||
|
||||
## 本轮 scope（做）
|
||||
|
||||
|
||||
| 交付物 | 说明 |
|
||||
| -------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `[story_route_agent.py](api/app/agents/memoir/story_route_agent.py)` | 新增 candidate **payload builder**，`_build_candidate_json` 改为走 builder |
|
||||
| `[prompts.py](api/app/agents/memoir/prompts.py)` | `get_story_route_prompt`、`get_story_batch_plan_prompt` 纠偏 + **两层决策标准** + **三类 category 规则** |
|
||||
| `[config.py](api/app/core/config.py)` | **3–4 个**预算相关字段（见下） |
|
||||
| 测试 | builder 单测、prompt 片段断言、**2 条类目行为样例**、`[test_story_route_oral_invariant.py](api/tests/test_story_route_oral_invariant.py)` 回归 |
|
||||
|
||||
|
||||
## 本轮 scope（不做）
|
||||
|
||||
- 离线 / admin 合并历史垃圾 story
|
||||
- schema 变更、二次 merge worker、family 细分子策略扩写、时间跨度阈值
|
||||
- 扩大路由体系（多模型级联、新端口签名等）
|
||||
|
||||
## 1. 候选行结构（summary 主角）
|
||||
|
||||
每条候选字典 **必带**：`id`、`title`、`char_count`、`version_count`、`updated_at`（ISO）、`linked_chapters`（保持现有拼接逻辑）。
|
||||
|
||||
**内容优先级，严格顺序：**
|
||||
|
||||
1. 若 `Story.summary` **非空且达到 `summary` 最小长度阈值**（可配置，如 ≥30 字或复用现有惯例），则带 `summary`，**本轮不带** `body_for_route`（避免长正文冲淡摘要）。
|
||||
2. 若 summary **缺失或过短**，再构造 `body_for_route`：**短正文**尽量全文；超长用 **head + tail**（中间省略说明），长度受 `story_route_long_body_head_chars` / `tail` 与单篇 cap 约束。
|
||||
3. 超 **总预算** 时，将该条 **降级为索引行**（仅 `id`、`title`、`char_count`、极短 `preview`，提示中说明索引项优先匹配带 `summary`/`body` 的条目）。
|
||||
|
||||
**初版默认值（保守，可线上调大）：**
|
||||
|
||||
- `story_route_candidate_body_max_chars`：**1200–2000**（落地取单值如 **1600**）
|
||||
- `story_route_candidate_total_max_chars`：**12000–18000**（如 **16000**）
|
||||
- head/tail：按现有「长文才切」思路配一对合理默认（如各 **600–800**）
|
||||
|
||||
## 2. 排序规则（写死，tie-break）
|
||||
|
||||
在进入 builder **之前**对 `candidate_stories` 排序（同 stage 列表）：
|
||||
|
||||
`has_summary(desc) → updated_at(desc) → version_count(desc) → char_count(desc) → id(asc)`
|
||||
|
||||
其中 `has_summary`：summary strip 后长度 ≥ 配置的 `summary` 最小长度。
|
||||
|
||||
## 3. 提示词
|
||||
|
||||
### 3.1 去掉保守偏置
|
||||
|
||||
删除「拿不准就 `new_story`」；改为：**先看是否与某候选在主题/事件层级上可合并，再决定**。
|
||||
|
||||
### 3.2 两层决策标准（显式写在 prompt 里）
|
||||
|
||||
- **主题连续性信号**：价值观、关系模式、长期总结、同一反思维度。
|
||||
- **事件切换信号**：新人物组合、新地点、新时间段、新事件因果链。
|
||||
|
||||
指引：`beliefs` / `summary` **更看主题连续性**；`career_*` / `childhood` / `education` **更看事件链**。
|
||||
|
||||
### 3.3 类目规则（第一版只三件）
|
||||
|
||||
- `**beliefs`、`summary`**：**强容器** → 多条短感悟、同一句式起笔、同价值维度 → **强烈倾向 `append_story`**（指向最匹配的一条候选 id）。
|
||||
- `**career_*`、`childhood`、`education**`：**强 episode** → 明确不同事件链可 `new_story`；同一经历续问可 append。
|
||||
- `**family`**：**中性** → 一句话：原则/关系反思倾向 append；**明确的新事件链**可 new；**不**展开长列表例外。
|
||||
|
||||
`get_story_batch_plan_prompt` 与 `get_story_route_prompt` **对齐**上述规则。
|
||||
|
||||
## 4. 接线
|
||||
|
||||
- `[story_pipeline_sync.py](api/app/features/memoir/story_pipeline_sync.py)` **不改** `StoryRouteAgent` 调用签名。
|
||||
- `validate_story_batch_plan`、Pydantic 模型 **不变**。
|
||||
|
||||
## 5. 测试（最小集 + 2 条行为）
|
||||
|
||||
|
||||
| 测试 | 目的 |
|
||||
| -------- | ----------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Builder | summary 优先不带 body；summary 短则带 body；总预算降级；**排序**稳定 |
|
||||
| Prompt | 类目块、两层标准、`beliefs`/`family` 中性句等 **包含断言** |
|
||||
| **行为 A** | mock LLM：`beliefs` + 两则短感悟口述 + 已有 1 条 story → 期望 **append**（或断言传给 mock 的 payload 含足够 summary/body 且 prompt 强调强容器；实现时二选一并写死断言） |
|
||||
| **行为 B** | mock LLM：`career_achievement`（或 `childhood`）+ 两起明确不同事件 → 允许/期望 **new_story** |
|
||||
| 回归 | `[test_story_route_oral_invariant.py](api/tests/test_story_route_oral_invariant.py)`：路由输入仍 **不含 evidence** |
|
||||
|
||||
|
||||
行为测试若不便绑定真实 LLM，采用 **mock `invoke_json_object` / StoryRouteAgent** 固定返回或 **断言 prompt + candidate JSON 形状**，与现有 `[test_story_route_oral_invariant.py](api/tests/test_story_route_oral_invariant.py)` 风格一致。
|
||||
|
||||
## 6. 风险与验收
|
||||
|
||||
- **Token**：默认保守；观察 staging 日志 `route_decision` / `is_append` 再调 `Settings`。
|
||||
- **过度合并**：靠 episode 类与「事件切换信号」段落缓解。
|
||||
|
||||
## 实施顺序
|
||||
|
||||
1. `config.py` 字段
|
||||
2. Builder + builder 单测 + 排序单测
|
||||
3. Prompt 改造 + prompt 断言
|
||||
4. `StoryRouteAgent` 接线
|
||||
5. 行为 A/B + oral invariant + 相关 memoir 测试
|
||||
|
||||
@@ -436,6 +436,40 @@ def get_narrative_merge_json_prompt(
|
||||
"""
|
||||
|
||||
|
||||
def story_route_merge_hint_for_category(chapter_category: str) -> str:
|
||||
"""按章节类目的 append/new 倾向（与 StoryRouteAgent 路由提示共用）。"""
|
||||
cc = (chapter_category or "").strip()
|
||||
if cc in ("beliefs", "summary"):
|
||||
return (
|
||||
"### 本章类别路由倾向（强主题容器）\n"
|
||||
"- 多条短感悟、同一价值维度、同一总结脉络的补充 → **优先 append_story**，"
|
||||
"选最匹配的一条候选 id。\n"
|
||||
"- 仅在用户明确讲述**与所有候选主题明显不相关**、且可独立成篇的长经历时，才用 new_story。"
|
||||
)
|
||||
if cc == "family":
|
||||
return (
|
||||
"### 本章类别路由倾向（家庭）\n"
|
||||
"- 原则性反思、关系模式、相处之道的补充 → **倾向 append_story**。\n"
|
||||
"- **明确的新事件链**（新场景、新时间线、不同人物组合的新经历）→ 可 new_story。"
|
||||
)
|
||||
if cc in (
|
||||
"childhood",
|
||||
"education",
|
||||
"career_early",
|
||||
"career_achievement",
|
||||
"career_challenge",
|
||||
):
|
||||
return (
|
||||
"### 本章类别路由倾向（经历叙事）\n"
|
||||
"- 以具体事件链为主：**不同事件 / 时期 / 地点** → 可 new_story。\n"
|
||||
"- 明显是**同一段经历的续叙、补充细节** → append_story。"
|
||||
)
|
||||
return (
|
||||
"### 本章类别路由倾向（一般）\n"
|
||||
"- 同时参考「主题连续性」与「事件切换」两类信号做判断。"
|
||||
)
|
||||
|
||||
|
||||
def get_story_route_prompt(
|
||||
*,
|
||||
chapter_category: str,
|
||||
@@ -448,15 +482,24 @@ def get_story_route_prompt(
|
||||
「故事」= 可独立讲述的一段人生经历；进入本步的批次已归入具体 chapter category
|
||||
（含模型返回 none 或零散档案启发式时映射的 summary）。
|
||||
"""
|
||||
return f"""你是回忆录编辑助手。根据本批用户口述与候选故事列表，决定：
|
||||
- append_story：内容明显延续、补充某一已有故事的主题与时间线，且能对应到具体 candidate id
|
||||
- new_story：新话题、新人生阶段片段，或与所有候选故事都不够贴合
|
||||
merge_hint = story_route_merge_hint_for_category(chapter_category)
|
||||
return f"""你是回忆录编辑助手。根据本批用户口述与【候选故事】决定 append_story 或 new_story。
|
||||
|
||||
**JSON 输出**：接口已启用 `response_format=json_object`，只输出下面 schema 的一个合法 JSON 对象，不要 markdown。
|
||||
|
||||
「故事」在此指：**可独立讲述的一段人生经历**——单一主题或同一事件链；不要假设本批里包含多个互不相关的故事（多段由系统其它步骤处理）。
|
||||
## 两层决策标准（必须先在心里过一遍）
|
||||
1. **主题连续性信号**：价值观、关系模式、长期总结、同一反思维度；口述是否像在**同一主题容器**里加厚？
|
||||
2. **事件切换信号**：是否出现**新人物组合、新地点、新时间段、新事件因果链**，与候选正文明显是**另一段经历**？
|
||||
|
||||
**路由边界（必须遵守）**：仅根据下方「本批口述合并文本」判断 new_story 与 append_story；不得将系统检索摘要、记忆摘录、图谱事实或其它非用户口述材料当作本批口述内容来匹配候选故事。
|
||||
- 类别 **beliefs / summary**：更重主题连续性；除非事件切换信号极强，否则倾向 append。
|
||||
- 类别 **career_* / childhood / education**：更重事件链；不同事件可 new，同一经历续聊则 append。
|
||||
- 类别 **family**：两类信号兼顾——原则/关系反思倾向 append；明确新事件链可 new。
|
||||
|
||||
{merge_hint}
|
||||
|
||||
**路由边界（必须遵守）**：仅根据下方「本批口述合并文本」判断；不得将系统检索摘要、记忆摘录等当作本批口述内容来匹配候选。
|
||||
|
||||
**候选故事说明**：列表项可能含 `summary` 或 `body_for_route`（正文摘要）；仅含 `preview` 者为索引项，信息不全。**append 时优先匹配带 summary 或 body 的条目**；索引项仅作候选 id 备忘。
|
||||
|
||||
当前章节（写作容器）：
|
||||
- category: {chapter_category}
|
||||
@@ -465,7 +508,7 @@ def get_story_route_prompt(
|
||||
【本批口述合并文本】
|
||||
{batch_transcript}
|
||||
|
||||
【候选故事】（仅允许在 append 时选择其中的 id；id 必须原样复制）
|
||||
【候选故事】（append 时 target_story_id 必须来自下列 id，且原样复制）
|
||||
{candidate_stories_json}
|
||||
|
||||
## 输出 JSON（仅此一个对象，不要 markdown）
|
||||
@@ -476,7 +519,8 @@ def get_story_route_prompt(
|
||||
}}
|
||||
|
||||
规则：
|
||||
- 若无法自信匹配某一候选，选 new_story
|
||||
- **不要**只因「不太确定」就选 new_story；在主题可并入某一候选时应 append_story。
|
||||
- 仅当口述与**所有**候选在两层标准下都明显不兼容时，才选 new_story。
|
||||
"""
|
||||
|
||||
|
||||
@@ -488,17 +532,28 @@ def get_story_batch_plan_prompt(
|
||||
candidate_stories_json: str,
|
||||
) -> str:
|
||||
"""同一章节类别下多 segment：划分为若干写入单元（每单元 new 或 append）。输出严格 JSON。"""
|
||||
merge_hint = story_route_merge_hint_for_category(chapter_category)
|
||||
return f"""你是回忆录编辑助手。下面同一章节类别下有一批**按时间顺序**的用户口述片段（每段有 id 与文本）。
|
||||
|
||||
**JSON 输出**：接口已启用 `response_format=json_object`，只输出下面 schema 的一个合法 JSON 对象，不要 markdown。
|
||||
|
||||
## 两层决策标准（每一块都要应用）
|
||||
1. **主题连续性信号**：价值观、关系模式、长期总结、同一反思维度。
|
||||
2. **事件切换信号**：新人物组合、新地点、新时间段、新事件因果链。
|
||||
|
||||
各类别倾向与单段路由一致：beliefs/summary 重主题连续性；career/childhood/education 重事件链；family 兼顾。
|
||||
|
||||
{merge_hint}
|
||||
|
||||
## 「故事」定义（必须遵守）
|
||||
一段「故事」= **可独立讲述的一段人生经历**：单一主题或同一事件链，能单独成篇。若话题切换、时间线跳到另一件事、人物/主线明显变化，应作为**新的故事**（new_story），而不是塞进同一段 append。
|
||||
一段「故事」= **可独立讲述的一段人生经历**。**同一主题容器内的连续口述**应并入同一块 append，而不是切碎成多个 new_story。
|
||||
|
||||
## 任务
|
||||
将本批 segment **划分为连续若干块**（每块包含至少一个 segment，顺序不能打乱；每个 segment 必须恰好属于一块）。对每一块决定：
|
||||
- **append_story**：内容明显延续、补充**某一已有候选故事**的主题与时间线，且能对应到具体 candidate id
|
||||
- **new_story**：新话题、与所有候选故事都不够贴合、或应独立成篇的片段
|
||||
将本批 segment **划分为连续若干块**（每块至少一个 segment，顺序不能打乱；每个 segment 必须恰好属于一块）。对每一块决定：
|
||||
- **append_story**：与某一候选在两层标准下可合并，且能对应到具体 candidate id
|
||||
- **new_story**：该块与**所有**候选都明显不兼容，或确认为独立新经历
|
||||
|
||||
**候选故事说明**：条目可能含 `summary`/`body_for_route`；仅 `preview` 者为索引项。**优先用带摘要/正文的条目做 append 目标**。
|
||||
|
||||
当前章节（写作容器）：
|
||||
- category: {chapter_category}
|
||||
@@ -507,7 +562,7 @@ def get_story_batch_plan_prompt(
|
||||
【本批口述片段】（JSON 数组，顺序即口述顺序）
|
||||
{segments_json}
|
||||
|
||||
【候选故事】（仅允许在 append 时选择其中的 id；id 必须原样复制）
|
||||
【候选故事】（append 时 target_story_id 必须来自下列 id，且原样复制）
|
||||
{candidate_stories_json}
|
||||
|
||||
## 输出 JSON（仅此一个对象，不要 markdown）
|
||||
@@ -524,7 +579,7 @@ def get_story_batch_plan_prompt(
|
||||
|
||||
规则：
|
||||
- `units` 中所有 `segment_ids` 拼接后，必须**不重不漏**地覆盖本批全部 id，且顺序与【本批口述片段】数组一致
|
||||
- 若无法自信匹配某一候选，对该块选 new_story
|
||||
- **不要**仅因不确定就对整块选 new_story；能并入候选时应 append_story
|
||||
"""
|
||||
|
||||
|
||||
|
||||
@@ -13,6 +13,8 @@ from app.agents.memoir.prompts import (
|
||||
get_story_batch_plan_prompt,
|
||||
get_story_route_prompt,
|
||||
)
|
||||
from app.agents.memoir.story_route_payload import build_route_candidate_json
|
||||
from app.core.config import settings
|
||||
from app.core.langchain_llm import invoke_json_object
|
||||
from app.core.logging import get_logger
|
||||
from app.features.story.models import Story
|
||||
@@ -63,40 +65,6 @@ class StoryRouteDecision(BaseModel):
|
||||
return str(v)
|
||||
|
||||
|
||||
def _build_candidate_json(
|
||||
stories: list[Story],
|
||||
*,
|
||||
preview_chars: int = 220,
|
||||
story_meta: dict[str, dict[str, int]] | None = None,
|
||||
) -> str:
|
||||
"""story_meta: story_id -> { char_count, version_count }，供路由感知篇幅与版本数。"""
|
||||
rows: list[dict[str, Any]] = []
|
||||
meta = story_meta or {}
|
||||
for s in stories:
|
||||
md = (s.canonical_markdown or "").strip().replace("\n", " ")
|
||||
preview = md[:preview_chars] + ("…" if len(md) > preview_chars else "")
|
||||
links: list[str] = []
|
||||
for cl in getattr(s, "chapter_links", None) or []:
|
||||
ch = getattr(cl, "chapter", None)
|
||||
if ch is None:
|
||||
continue
|
||||
cat = getattr(ch, "category", None) or ""
|
||||
tit = getattr(ch, "title", None) or ""
|
||||
links.append(f"{tit}({cat})")
|
||||
row: dict[str, Any] = {
|
||||
"id": s.id,
|
||||
"title": s.title,
|
||||
"preview": preview,
|
||||
"linked_chapters": links,
|
||||
}
|
||||
m = meta.get(str(s.id))
|
||||
if m:
|
||||
row["char_count"] = int(m.get("char_count", 0))
|
||||
row["version_count"] = int(m.get("version_count", 0))
|
||||
rows.append(row)
|
||||
return json.dumps(rows, ensure_ascii=False, indent=2)
|
||||
|
||||
|
||||
def _build_segments_json_for_plan(
|
||||
segments: list[tuple[str, str]], *, text_preview_chars: int = 4000
|
||||
) -> str:
|
||||
@@ -157,7 +125,7 @@ class StoryRouteAgent:
|
||||
new_story_title=None,
|
||||
reason="no_llm",
|
||||
)
|
||||
payload = _build_candidate_json(candidate_stories, story_meta=story_meta)
|
||||
payload = build_route_candidate_json(candidate_stories, story_meta, settings)
|
||||
prompt = get_story_route_prompt(
|
||||
chapter_category=chapter_category,
|
||||
chapter_title=chapter_title,
|
||||
@@ -211,7 +179,7 @@ class StoryRouteAgent:
|
||||
"""
|
||||
if not llm or len(segments) < 2:
|
||||
return None
|
||||
payload = _build_candidate_json(candidate_stories, story_meta=story_meta)
|
||||
payload = build_route_candidate_json(candidate_stories, story_meta, settings)
|
||||
segments_json = _build_segments_json_for_plan(segments)
|
||||
prompt = get_story_batch_plan_prompt(
|
||||
chapter_category=chapter_category,
|
||||
|
||||
230
api/app/agents/memoir/story_route_payload.py
Normal file
230
api/app/agents/memoir/story_route_payload.py
Normal file
@@ -0,0 +1,230 @@
|
||||
"""
|
||||
Story 路由：候选故事 JSON 载荷（summary 优先、预算裁剪、固定排序）。
|
||||
|
||||
供 StoryRouteAgent 与单测复用。
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from datetime import timezone
|
||||
from typing import Any, TYPE_CHECKING
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from app.core.config import Settings
|
||||
|
||||
from app.features.story.models import Story
|
||||
|
||||
|
||||
def _linked_chapters(s: Story) -> list[str]:
|
||||
links: list[str] = []
|
||||
for cl in getattr(s, "chapter_links", None) or []:
|
||||
ch = getattr(cl, "chapter", None)
|
||||
if ch is None:
|
||||
continue
|
||||
cat = getattr(ch, "category", None) or ""
|
||||
tit = getattr(ch, "title", None) or ""
|
||||
links.append(f"{tit}({cat})")
|
||||
return links
|
||||
|
||||
|
||||
def _updated_at_iso(s: Story) -> str:
|
||||
ua = getattr(s, "updated_at", None)
|
||||
if ua is None:
|
||||
return ""
|
||||
if ua.tzinfo is None:
|
||||
ua = ua.replace(tzinfo=timezone.utc)
|
||||
return ua.isoformat()
|
||||
|
||||
|
||||
def _has_usable_summary(s: Story, summary_min_len: int) -> bool:
|
||||
t = (getattr(s, "summary", None) or "").strip()
|
||||
return len(t) >= summary_min_len
|
||||
|
||||
|
||||
def _truncate_body_for_route(
|
||||
md: str,
|
||||
*,
|
||||
body_max_chars: int,
|
||||
head_chars: int,
|
||||
tail_chars: int,
|
||||
) -> str:
|
||||
"""单篇正文进入路由 prompt 的裁剪：尽量全文，否则 head+tail。"""
|
||||
m = (md or "").strip()
|
||||
if not m:
|
||||
return ""
|
||||
if len(m) <= body_max_chars:
|
||||
return m
|
||||
hc = max(1, min(head_chars, body_max_chars // 2))
|
||||
tc = max(1, min(tail_chars, body_max_chars // 2))
|
||||
mid_omit = len(m) - hc - tc
|
||||
if mid_omit <= 0:
|
||||
return m[:body_max_chars]
|
||||
return f"{m[:hc]}\n…（中间省略 {mid_omit} 字）…\n{m[-tc:]}"
|
||||
|
||||
|
||||
def sort_stories_for_route(
|
||||
stories: list[Story],
|
||||
story_meta: dict[str, dict[str, int]],
|
||||
*,
|
||||
summary_min_chars: int,
|
||||
) -> list[Story]:
|
||||
"""has_summary(desc) → updated_at(desc) → version_count(desc) → char_count(desc) → id(asc)"""
|
||||
|
||||
def key(s: Story) -> tuple:
|
||||
sid = str(s.id)
|
||||
m = story_meta.get(sid) or {}
|
||||
vc = int(m.get("version_count", 0))
|
||||
cc = int(m.get("char_count", 0))
|
||||
ua = getattr(s, "updated_at", None)
|
||||
ts = 0.0
|
||||
if ua is not None:
|
||||
if ua.tzinfo is None:
|
||||
ua = ua.replace(tzinfo=timezone.utc)
|
||||
ts = ua.timestamp()
|
||||
return (
|
||||
not _has_usable_summary(s, summary_min_chars),
|
||||
-ts,
|
||||
-vc,
|
||||
-cc,
|
||||
sid,
|
||||
)
|
||||
|
||||
return sorted(stories, key=key)
|
||||
|
||||
|
||||
def _build_full_row(
|
||||
s: Story,
|
||||
story_meta: dict[str, dict[str, int]],
|
||||
*,
|
||||
summary_min_chars: int,
|
||||
body_max_chars: int,
|
||||
head_chars: int,
|
||||
tail_chars: int,
|
||||
) -> dict[str, Any]:
|
||||
sid = str(s.id)
|
||||
meta = story_meta.get(sid) or {}
|
||||
canon = (s.canonical_markdown or "").strip()
|
||||
char_count = int(meta.get("char_count", len(canon)))
|
||||
version_count = int(meta.get("version_count", 0))
|
||||
row: dict[str, Any] = {
|
||||
"id": s.id,
|
||||
"title": s.title,
|
||||
"char_count": char_count,
|
||||
"version_count": version_count,
|
||||
"updated_at": _updated_at_iso(s),
|
||||
"linked_chapters": _linked_chapters(s),
|
||||
}
|
||||
if _has_usable_summary(s, summary_min_chars):
|
||||
row["summary"] = (getattr(s, "summary", None) or "").strip()
|
||||
return row
|
||||
body = _truncate_body_for_route(
|
||||
canon,
|
||||
body_max_chars=body_max_chars,
|
||||
head_chars=head_chars,
|
||||
tail_chars=tail_chars,
|
||||
)
|
||||
if body:
|
||||
row["body_for_route"] = body
|
||||
return row
|
||||
|
||||
|
||||
def _build_index_row(
|
||||
s: Story,
|
||||
story_meta: dict[str, dict[str, int]],
|
||||
*,
|
||||
preview_chars: int,
|
||||
) -> dict[str, Any]:
|
||||
sid = str(s.id)
|
||||
meta = story_meta.get(sid) or {}
|
||||
canon = (s.canonical_markdown or "").strip().replace("\n", " ")
|
||||
preview = canon[:preview_chars] + ("…" if len(canon) > preview_chars else "")
|
||||
char_count = int(meta.get("char_count", len((s.canonical_markdown or "").strip())))
|
||||
return {
|
||||
"id": s.id,
|
||||
"title": s.title,
|
||||
"char_count": char_count,
|
||||
"preview": preview,
|
||||
}
|
||||
|
||||
|
||||
def _rows_json_len(rows: list[dict[str, Any]]) -> int:
|
||||
return len(json.dumps(rows, ensure_ascii=False))
|
||||
|
||||
|
||||
def apply_total_budget_downgrade(
|
||||
rows: list[dict[str, Any]],
|
||||
*,
|
||||
stories_by_id: dict[str, Story],
|
||||
story_meta: dict[str, dict[str, int]],
|
||||
total_max_chars: int,
|
||||
index_preview_chars: int,
|
||||
) -> list[dict[str, Any]]:
|
||||
"""从列表尾部（低优先级）起将整行降级为索引行，直到 JSON 总长不超过预算。"""
|
||||
out = [dict(r) for r in rows]
|
||||
|
||||
def _is_index_row(r: dict[str, Any]) -> bool:
|
||||
return "preview" in r and "summary" not in r and "body_for_route" not in r
|
||||
|
||||
while _rows_json_len(out) > total_max_chars:
|
||||
replaced = False
|
||||
for i in range(len(out) - 1, -1, -1):
|
||||
sid = str(out[i].get("id", ""))
|
||||
st = stories_by_id.get(sid)
|
||||
if st is None or _is_index_row(out[i]):
|
||||
continue
|
||||
out[i] = _build_index_row(
|
||||
st,
|
||||
story_meta,
|
||||
preview_chars=index_preview_chars,
|
||||
)
|
||||
replaced = True
|
||||
break
|
||||
if not replaced:
|
||||
break
|
||||
return out
|
||||
|
||||
|
||||
def build_route_candidate_rows(
|
||||
stories: list[Story],
|
||||
story_meta: dict[str, dict[str, int]] | None,
|
||||
settings: "Settings",
|
||||
) -> list[dict[str, Any]]:
|
||||
"""排序 + 完整候选行（尚未做总预算降级）。"""
|
||||
meta = story_meta or {}
|
||||
summary_min = int(settings.story_route_summary_min_chars)
|
||||
ordered = sort_stories_for_route(stories, meta, summary_min_chars=summary_min)
|
||||
body_max = int(settings.story_route_candidate_body_max_chars)
|
||||
head_c = int(settings.story_route_long_body_head_chars)
|
||||
tail_c = int(settings.story_route_long_body_tail_chars)
|
||||
rows: list[dict[str, Any]] = []
|
||||
for s in ordered:
|
||||
rows.append(
|
||||
_build_full_row(
|
||||
s,
|
||||
meta,
|
||||
summary_min_chars=summary_min,
|
||||
body_max_chars=body_max,
|
||||
head_chars=head_c,
|
||||
tail_chars=tail_c,
|
||||
)
|
||||
)
|
||||
by_id = {str(s.id): s for s in ordered}
|
||||
total_max = int(settings.story_route_candidate_total_max_chars)
|
||||
index_prev = int(settings.story_route_index_preview_chars)
|
||||
return apply_total_budget_downgrade(
|
||||
rows,
|
||||
stories_by_id=by_id,
|
||||
story_meta=meta,
|
||||
total_max_chars=total_max,
|
||||
index_preview_chars=index_prev,
|
||||
)
|
||||
|
||||
|
||||
def build_route_candidate_json(
|
||||
stories: list[Story],
|
||||
story_meta: dict[str, dict[str, int]] | None,
|
||||
settings: "Settings",
|
||||
) -> str:
|
||||
rows = build_route_candidate_rows(stories, story_meta, settings)
|
||||
return json.dumps(rows, ensure_ascii=False, indent=2)
|
||||
@@ -217,6 +217,15 @@ class Settings(BaseSettings):
|
||||
# Append 硬上限：canonical 字符数、版本数（超限强制 new_story）
|
||||
story_append_max_canonical_chars: int = Field(default=12000, ge=1000, le=500_000)
|
||||
story_append_max_versions: int = Field(default=20, ge=1, le=500)
|
||||
# StoryRouteAgent：候选 JSON 预算（保守默认，可调大）
|
||||
story_route_candidate_body_max_chars: int = Field(default=1600, ge=200, le=8000)
|
||||
story_route_candidate_total_max_chars: int = Field(
|
||||
default=16_000, ge=2000, le=100_000
|
||||
)
|
||||
story_route_long_body_head_chars: int = Field(default=700, ge=100, le=4000)
|
||||
story_route_long_body_tail_chars: int = Field(default=700, ge=100, le=4000)
|
||||
story_route_summary_min_chars: int = Field(default=30, ge=0, le=500)
|
||||
story_route_index_preview_chars: int = Field(default=80, ge=20, le=500)
|
||||
# Evidence 检索 top_k：大批次 unit 时降低检索量
|
||||
evidence_top_k_default: int = Field(default=10, ge=1, le=50)
|
||||
evidence_top_k_large_batch: int = Field(default=5, ge=1, le=50)
|
||||
|
||||
146
api/tests/test_story_route_payload.py
Normal file
146
api/tests/test_story_route_payload.py
Normal file
@@ -0,0 +1,146 @@
|
||||
"""Story 路由候选 JSON：排序、summary 优先、预算降级。"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from datetime import datetime, timezone
|
||||
from types import SimpleNamespace
|
||||
|
||||
from app.agents.memoir.story_route_payload import (
|
||||
build_route_candidate_json,
|
||||
build_route_candidate_rows,
|
||||
sort_stories_for_route,
|
||||
_truncate_body_for_route,
|
||||
)
|
||||
from app.core.config import Settings
|
||||
|
||||
|
||||
def _story(**kwargs):
|
||||
defaults = dict(
|
||||
id="s-default",
|
||||
title="T",
|
||||
summary=None,
|
||||
canonical_markdown="",
|
||||
updated_at=None,
|
||||
chapter_links=[],
|
||||
)
|
||||
defaults.update(kwargs)
|
||||
return SimpleNamespace(**defaults)
|
||||
|
||||
|
||||
def test_sort_has_summary_first_then_recency():
|
||||
older = _story(
|
||||
id="old",
|
||||
summary="x" * 40,
|
||||
updated_at=datetime(2020, 1, 1, tzinfo=timezone.utc),
|
||||
)
|
||||
newer = _story(
|
||||
id="new",
|
||||
summary="",
|
||||
canonical_markdown="body",
|
||||
updated_at=datetime(2025, 1, 1, tzinfo=timezone.utc),
|
||||
)
|
||||
meta = {
|
||||
"old": {"char_count": 10, "version_count": 1},
|
||||
"new": {"char_count": 20, "version_count": 2},
|
||||
}
|
||||
out = sort_stories_for_route([newer, older], meta, summary_min_chars=30)
|
||||
assert [s.id for s in out] == ["old", "new"]
|
||||
|
||||
|
||||
def test_sort_tiebreak_version_then_char_then_id():
|
||||
t = datetime(2024, 6, 1, tzinfo=timezone.utc)
|
||||
a = _story(id="a", summary="", canonical_markdown="a", updated_at=t)
|
||||
b = _story(id="b", summary="", canonical_markdown="bb", updated_at=t)
|
||||
meta = {
|
||||
"a": {"char_count": 100, "version_count": 1},
|
||||
"b": {"char_count": 50, "version_count": 3},
|
||||
}
|
||||
out = sort_stories_for_route([a, b], meta, summary_min_chars=30)
|
||||
assert [s.id for s in out] == ["b", "a"]
|
||||
|
||||
|
||||
def test_summary_sufficient_omits_body():
|
||||
s = _story(
|
||||
id="1",
|
||||
summary="信" * 40,
|
||||
canonical_markdown="正文" * 500,
|
||||
)
|
||||
settings = Settings()
|
||||
rows = build_route_candidate_rows(
|
||||
[s], {"1": {"char_count": 10, "version_count": 1}}, settings
|
||||
)
|
||||
assert "summary" in rows[0]
|
||||
assert "body_for_route" not in rows[0]
|
||||
|
||||
|
||||
def test_short_summary_falls_back_to_body():
|
||||
s = _story(
|
||||
id="1",
|
||||
summary="短",
|
||||
canonical_markdown="唯一的正文用于路由",
|
||||
)
|
||||
settings = Settings()
|
||||
rows = build_route_candidate_rows(
|
||||
[s], {"1": {"char_count": 20, "version_count": 1}}, settings
|
||||
)
|
||||
assert "summary" not in rows[0]
|
||||
assert rows[0].get("body_for_route")
|
||||
|
||||
|
||||
def test_long_body_uses_head_tail():
|
||||
md = "块" * 3000
|
||||
out = _truncate_body_for_route(
|
||||
md,
|
||||
body_max_chars=1600,
|
||||
head_chars=100,
|
||||
tail_chars=100,
|
||||
)
|
||||
assert "中间省略" in out
|
||||
assert len(out) < len(md)
|
||||
|
||||
|
||||
def test_total_budget_downgrades_tail_rows(monkeypatch):
|
||||
settings = Settings()
|
||||
monkeypatch.setattr(settings, "story_route_candidate_total_max_chars", 800)
|
||||
monkeypatch.setattr(settings, "story_route_index_preview_chars", 40)
|
||||
stories = [
|
||||
_story(
|
||||
id="1",
|
||||
summary="",
|
||||
canonical_markdown="A" * 400,
|
||||
updated_at=datetime(2025, 1, 2, tzinfo=timezone.utc),
|
||||
),
|
||||
_story(
|
||||
id="2",
|
||||
summary="",
|
||||
canonical_markdown="B" * 400,
|
||||
updated_at=datetime(2025, 1, 1, tzinfo=timezone.utc),
|
||||
),
|
||||
]
|
||||
meta = {
|
||||
"1": {"char_count": 400, "version_count": 1},
|
||||
"2": {"char_count": 400, "version_count": 1},
|
||||
}
|
||||
payload = build_route_candidate_json(stories, meta, settings)
|
||||
data = json.loads(payload)
|
||||
assert any("preview" in row and "body_for_route" not in row for row in data)
|
||||
|
||||
|
||||
def test_json_includes_core_fields():
|
||||
s = _story(
|
||||
id="x1",
|
||||
title="标题",
|
||||
summary="y" * 40,
|
||||
updated_at=datetime(2024, 1, 1, tzinfo=timezone.utc),
|
||||
)
|
||||
settings = Settings()
|
||||
js = build_route_candidate_json(
|
||||
[s], {"x1": {"char_count": 5, "version_count": 2}}, settings
|
||||
)
|
||||
row = json.loads(js)[0]
|
||||
assert row["id"] == "x1"
|
||||
assert row["title"] == "标题"
|
||||
assert row["version_count"] == 2
|
||||
assert row["char_count"] == 5
|
||||
assert "updated_at" in row
|
||||
130
api/tests/test_story_route_prompts_and_behavior.py
Normal file
130
api/tests/test_story_route_prompts_and_behavior.py
Normal file
@@ -0,0 +1,130 @@
|
||||
"""Story 路由：提示词片段与 mock LLM 行为回归。"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from datetime import datetime, timezone
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
from app.agents.memoir.prompts import (
|
||||
get_story_batch_plan_prompt,
|
||||
get_story_route_prompt,
|
||||
story_route_merge_hint_for_category,
|
||||
)
|
||||
from app.agents.memoir.story_route_agent import StoryRouteAgent
|
||||
|
||||
|
||||
def test_route_prompt_beliefs_has_strong_container_and_no_uncertain_new():
|
||||
p = get_story_route_prompt(
|
||||
chapter_category="beliefs",
|
||||
chapter_title="信念与价值观",
|
||||
batch_transcript="口述测试内容用于路由协议长度达标",
|
||||
candidate_stories_json="[]",
|
||||
)
|
||||
assert "强主题容器" in p
|
||||
assert "不太确定" in p and "new_story" in p
|
||||
assert "两层决策标准" in p
|
||||
|
||||
|
||||
def test_batch_plan_prompt_aligns_with_route():
|
||||
p = get_story_batch_plan_prompt(
|
||||
chapter_category="beliefs",
|
||||
chapter_title="t",
|
||||
segments_json="[]",
|
||||
candidate_stories_json="[]",
|
||||
)
|
||||
assert "强主题容器" in p
|
||||
assert "仅因不确定" in p
|
||||
|
||||
|
||||
def test_merge_hint_family_neutral_line():
|
||||
h = story_route_merge_hint_for_category("family")
|
||||
assert "家庭" in h
|
||||
assert "新事件链" in h
|
||||
|
||||
|
||||
def test_merge_hint_career_episodic():
|
||||
h = story_route_merge_hint_for_category("career_achievement")
|
||||
assert "经历叙事" in h
|
||||
|
||||
|
||||
def test_decide_beliefs_mock_llm_append_and_prompt_has_payload():
|
||||
captured: dict[str, str] = {}
|
||||
|
||||
def fake_invoke(_llm, prompt: str, **_kwargs):
|
||||
captured["prompt"] = prompt
|
||||
return json.dumps(
|
||||
{
|
||||
"decision": "append_story",
|
||||
"target_story_id": "story-a",
|
||||
"reason": "同一价值观补充",
|
||||
},
|
||||
ensure_ascii=False,
|
||||
)
|
||||
|
||||
cand = SimpleNamespace(
|
||||
id="story-a",
|
||||
title="信念",
|
||||
summary="y" * 40,
|
||||
canonical_markdown="x" * 200,
|
||||
updated_at=datetime(2025, 1, 1, tzinfo=timezone.utc),
|
||||
chapter_links=[],
|
||||
)
|
||||
with patch(
|
||||
"app.agents.memoir.story_route_agent.invoke_json_object",
|
||||
side_effect=fake_invoke,
|
||||
):
|
||||
agent = StoryRouteAgent()
|
||||
d = agent.decide(
|
||||
chapter_category="beliefs",
|
||||
chapter_title="信念与价值观",
|
||||
batch_transcript="我始终相信要谨慎行事。",
|
||||
candidate_stories=[cand],
|
||||
llm=MagicMock(),
|
||||
valid_story_ids={"story-a"},
|
||||
story_meta={"story-a": {"char_count": 200, "version_count": 1}},
|
||||
)
|
||||
assert d.decision == "append_story"
|
||||
assert d.target_story_id == "story-a"
|
||||
assert "强主题容器" in captured["prompt"]
|
||||
assert "story-a" in captured["prompt"]
|
||||
|
||||
|
||||
def test_decide_career_mock_llm_new_story_and_prompt_episodic():
|
||||
captured: dict[str, str] = {}
|
||||
|
||||
def fake_invoke(_llm, prompt: str, **_kwargs):
|
||||
captured["prompt"] = prompt
|
||||
return json.dumps(
|
||||
{
|
||||
"decision": "new_story",
|
||||
"target_story_id": None,
|
||||
"reason": "另一段完全不同的任职经历",
|
||||
},
|
||||
ensure_ascii=False,
|
||||
)
|
||||
|
||||
cand = SimpleNamespace(
|
||||
id="s1",
|
||||
title="早期",
|
||||
summary="",
|
||||
canonical_markdown="南京军区经历若干字",
|
||||
updated_at=datetime(2024, 1, 1, tzinfo=timezone.utc),
|
||||
chapter_links=[],
|
||||
)
|
||||
with patch(
|
||||
"app.agents.memoir.story_route_agent.invoke_json_object",
|
||||
side_effect=fake_invoke,
|
||||
):
|
||||
d = StoryRouteAgent().decide(
|
||||
chapter_category="career_achievement",
|
||||
chapter_title="主要成就",
|
||||
batch_transcript="后来调动到北京机关，岗位与南京完全不同。",
|
||||
candidate_stories=[cand],
|
||||
llm=MagicMock(),
|
||||
valid_story_ids={"s1"},
|
||||
story_meta={"s1": {"char_count": 20, "version_count": 1}},
|
||||
)
|
||||
assert d.decision == "new_story"
|
||||
assert "经历叙事" in captured["prompt"]
|
||||
Reference in New Issue
Block a user