mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-15 00:21:58 +00:00
助手建图加「关掉分析工具」的开关，给评测的「分析工具开、关」对照用：api/copilot.answer_ops 加关键字参数 analysis_tools（缺省真，和以前一字不差）。为假时给助手的工具清单不列五个分析工具（_tool_catalog），节点手册去掉只讲分析能力的三段（agent 段里分析类问题绑分析工具那一条、分析卡一整条、搭图规则第 7 条；报告段的引用写法和分析说法核对照留，node_reference），问数据的包装不给分析类问题那一条形状（ANALYSIS_SHAPE_PROMPT 抽成常量），问题意图那条自查不提；图里照样绑了分析工具的（Agent、协作成员、调用工具节点）按「绑定的工具不存在」挡（analysis_tools_off，交回模型去掉，改不好就不运行）。chat/drive.TurnDriver 加同名参数和属性 analysis_tools（缺省真），_generate 透传给 answer_ops；问数据页不暴露，eval/answer.Driver 之后按变体设。测试：关着时工具清单、手册、包装都没有分析，绑了被挡、改掉就运行；开着时绑了照常运行；没碰分析工具的一轮开、关交出的操作逐条一样；TurnDriver 透传
This commit is contained in:
ThearchyHelios
+104
-27
@@ -76,7 +76,7 @@ def _scope_note(rows: list[Any], scoped: bool) -> str:
|
||||
"db_schema__ 工具；前几轮用过别的库，这一轮也不要沿用")
|
||||
|
||||
|
||||
def _tool_catalog(rows: list[Any], *, builtins: frozenset[str] | None = None) -> str:
|
||||
def _tool_catalog(rows: list[Any], *, builtins: frozenset[str] | None = None, analysis_tools: bool = True) -> str:
|
||||
"""给助手看的工具清单。
|
||||
|
||||
all_specs() 只有静态注册的内置工具，数据源工具是运行时按库动态生成的
|
||||
@@ -86,11 +86,14 @@ def _tool_catalog(rows: list[Any], *, builtins: frozenset[str] | None = None) ->
|
||||
不列表名（look 文档 D3）：以前每个库列前 12 个表名，和这一轮要做什么无关，闲聊也带着；表数写一句，字段要用时 look。
|
||||
|
||||
builtins 给了的话内置工具只列这几个：使用者的问数据（_CHAT_USER_PROMPT）只能用只读的那几个，列出来用不了的工具，
|
||||
模型照样会绑。
|
||||
模型照样会绑。analysis_tools 为假（评测「关掉分析工具」那一臂，answer_ops）时不列五个分析工具。
|
||||
"""
|
||||
from app.tools.analysis import ANALYSIS_TOOLS
|
||||
|
||||
lines = [
|
||||
f"- {name}（{spec.category}）：{spec.description}"
|
||||
for name, spec in sorted(all_specs().items()) if builtins is None or name in builtins
|
||||
for name, spec in sorted(all_specs().items())
|
||||
if (builtins is None or name in builtins) and (analysis_tools or name not in ANALYSIS_TOOLS)
|
||||
]
|
||||
|
||||
from app.data import introspect as _introspect
|
||||
@@ -391,6 +394,26 @@ skip_if。这些字段按受限的 Python 表达式求值，变量直接写路
|
||||
- 一个节点连出多条普通边 = 并行执行，多条边汇入同一节点 = 等待汇聚
|
||||
"""
|
||||
|
||||
#: 节点手册里只讲分析能力的几段：(从这一行起, 到这一行之前)。评测「关掉分析工具」那一臂（answer_ops 的 analysis_tools 为假）
|
||||
#: 不给这几段——agent 段里「分析类问题绑分析工具」那一条、分析卡一整条、搭图规则第 7 条：助手不知道有分析工具和分析卡，
|
||||
#: 也不会被教着去用。报告段里分析结论的引用写法、分析说法核对照留（报告节点照样会核判断词）
|
||||
_ANALYSIS_PROMPT_SPANS = (
|
||||
(" **问题问的是为什么、怎么变了", " **默认不要写 max_steps"),
|
||||
("- analysis：分析卡。", "- dual_check："),
|
||||
("7. 问题问为什么、怎么变了", "\n模型字段"),
|
||||
)
|
||||
|
||||
|
||||
def node_reference(*, analysis_tools: bool = True) -> str:
|
||||
"""给助手的节点手册。analysis_tools 为假时去掉只讲分析能力的那几段（_ANALYSIS_PROMPT_SPANS）。"""
|
||||
if analysis_tools:
|
||||
return NODE_REFERENCE
|
||||
text = NODE_REFERENCE
|
||||
for start, end in _ANALYSIS_PROMPT_SPANS:
|
||||
i = text.index(start)
|
||||
text = text[:i] + text[text.index(end, i):]
|
||||
return text
|
||||
|
||||
|
||||
class GenerateIn(BaseModel):
|
||||
instruction: str = Field(min_length=1, description="用自然语言描述想要的工作流")
|
||||
@@ -415,8 +438,21 @@ def _question_of(payload: GenerateIn) -> str | None:
|
||||
return (payload.question or "").strip() or payload.instruction
|
||||
|
||||
|
||||
def _user_message(payload: GenerateIn, *, patch: bool) -> str:
|
||||
"""把用户说的话包成给模型的请求。
|
||||
#: 问数据的包装里「分析类问题」那一条形状（00-总方案 §3.7）：问原因、来源、异常、趋势、差异的，判定由平台的分析工具算、系统写
|
||||
#: 判定语，报告引用它。问题意图另由自查按 app/analysis/intent 的词表再核一遍：分析类问题而查库的 agent 没绑分析工具时交回改一轮
|
||||
ANALYSIS_SHAPE_PROMPT = (
|
||||
"- 问的是为什么、怎么变了、哪里拖累、谁贡献最大、是否异常、正常吗、波动、趋势、是不是真的更高这类分析问题时，搭 "
|
||||
"input → agent → report → output：agent 绑 db_query__、db_schema__ 和五个分析工具（analysis_comparable、"
|
||||
"analysis_baseline、analysis_trend、analysis_decompose、analysis_differ），prompt 里写清要回答的问题、比哪两期"
|
||||
"（问题没说就比上一个整期），不用教分析方法（平台会注入）、不写阈值；report 的 instructions 写「回答：{{ input.question }}。"
|
||||
"按分析结论写，判断直接引用判定语；没有分析结论的判断不下，原因没有依据的写成待核实的推测」（可以附上 "
|
||||
"{{ nodes.agent的id.text }} 当分析思路）：数引用 agent 查过的单元格，判定引用它做过的分析结论。analysis_claims "
|
||||
"用默认，不要关\n"
|
||||
)
|
||||
|
||||
|
||||
def _user_message(payload: GenerateIn, *, patch: bool, analysis_tools: bool = True) -> str:
|
||||
"""把用户说的话包成给模型的请求。analysis_tools 为假（评测「关掉分析工具」那一臂）时不给分析类问题那一条形状。
|
||||
|
||||
两个入口的语义完全不同，包法必须跟着变：
|
||||
|
||||
@@ -452,16 +488,9 @@ def _user_message(payload: GenerateIn, *, patch: bool) -> str:
|
||||
"「回答：{{ input.question }}」（可以附上 {{ nodes.agent的id.text }} 当分析思路），数用 [[v:Q1.r0.列名]] "
|
||||
"直接引用 agent 查过的单元格，不必经过口径卡；要比率、增幅再在 agent 和 report 之间加口径卡，agent 配 "
|
||||
"output_schema + cite_fields，口径卡读 vars.<assign_to>.字段。出口字段写 {{ nodes.report的id.text }}\n"
|
||||
# 分析能力一轮（00-总方案 §3.7）：问原因、来源、异常、趋势、差异的，判定由平台的分析工具算、系统写判定语，报告引用它。
|
||||
# 问题意图由自查按 app/analysis/intent 的词表再核一遍：分析类问题而查库的 agent 没绑分析工具时交回改一轮
|
||||
"- 问的是为什么、怎么变了、哪里拖累、谁贡献最大、是否异常、正常吗、波动、趋势、是不是真的更高这类分析问题时，搭 "
|
||||
"input → agent → report → output：agent 绑 db_query__、db_schema__ 和五个分析工具（analysis_comparable、"
|
||||
"analysis_baseline、analysis_trend、analysis_decompose、analysis_differ），prompt 里写清要回答的问题、比哪两期"
|
||||
"（问题没说就比上一个整期），不用教分析方法（平台会注入）、不写阈值；report 的 instructions 写「回答：{{ input.question }}。"
|
||||
"按分析结论写，判断直接引用判定语；没有分析结论的判断不下，原因没有依据的写成待核实的推测」（可以附上 "
|
||||
"{{ nodes.agent的id.text }} 当分析思路）：数引用 agent 查过的单元格，判定引用它做过的分析结论。analysis_claims "
|
||||
"用默认，不要关\n"
|
||||
"- 只问表结构、清单（有哪些表、有哪些字段、列出名单）的，不加 report，agent → output 就行\n"
|
||||
# 分析类问题那一条形状（ANALYSIS_SHAPE_PROMPT）：评测「关掉分析工具」那一臂不给
|
||||
+ (ANALYSIS_SHAPE_PROMPT if analysis_tools else "")
|
||||
+ "- 只问表结构、清单（有哪些表、有哪些字段、列出名单）的，不加 report，agent → output 就行\n"
|
||||
# 三期起报告会核对写出来的表名、字段名：instructions 里让它「列出用到的表」时，编出来的名字会被标出来
|
||||
"- report 提到表名、字段名时写 [[t:表名]] / [[c:表名.字段名]]（英文名也可以放进反引号，中文名不行："
|
||||
"反引号里的中文名不核对），只写 agent 真查过的名字，"
|
||||
@@ -879,16 +908,18 @@ GRAPH_SCHEMA: dict[str, Any] = {
|
||||
|
||||
|
||||
def _graph_system(sources: list[Any], scope: set[str] | None, datasources: str, looks: Any, *,
|
||||
chat_user: bool = False) -> str:
|
||||
chat_user: bool = False, analysis_tools: bool = True) -> str:
|
||||
"""画布、问数据（流式和非流式）共用的 system：节点手册、工具清单、数据源概览、结构要求、输出协议、查看的用法。
|
||||
这一份一直用到自查修正结束（接着写、修正轮都不换），模型前后看到的是同一套说法。
|
||||
|
||||
chat_user：开登录后 user 角色的问数据（D-c）。内置工具只列只读的那几个，结构要求后面再加一段使用者的约束。"""
|
||||
chat_user：开登录后 user 角色的问数据（D-c）。内置工具只列只读的那几个，结构要求后面再加一段使用者的约束。
|
||||
analysis_tools 为假（评测「关掉分析工具」那一臂）：节点手册去掉只讲分析能力的几段，工具清单不列分析工具。"""
|
||||
from app.auth.chat_policy import CHAT_BUILTIN_TOOLS
|
||||
|
||||
catalog = _tool_catalog(sources, builtins=CHAT_BUILTIN_TOOLS if chat_user else None, analysis_tools=analysis_tools)
|
||||
return (
|
||||
"你是一个 agent 工作流编排专家。根据用户需求，以操作流的方式逐步搭出一张可执行的工作流图。\n\n"
|
||||
f"{NODE_REFERENCE}\n\n可用工具：\n{_tool_catalog(sources, builtins=CHAT_BUILTIN_TOOLS if chat_user else None)}"
|
||||
f"{node_reference(analysis_tools=analysis_tools)}\n\n可用工具：\n{catalog}"
|
||||
f"{datasources}{_scope_note(sources, scope is not None)}\n\n"
|
||||
"结构要求：\n"
|
||||
"1. 必须有且只有一个 input 节点和至少一个 output 节点\n"
|
||||
@@ -940,7 +971,41 @@ def _chat_user_issues(nodes: dict[str, dict[str, Any]], edges: list[dict[str, An
|
||||
"去掉不允许的节点、工具和记忆范围 / 知识库配置"}]
|
||||
|
||||
|
||||
def _graph_request(payload: GenerateIn) -> str:
|
||||
#: 关掉分析工具时（answer_ops 的 analysis_tools 为假）图里还绑着分析工具的那条问题的 code
|
||||
ANALYSIS_TOOLS_OFF = "analysis_tools_off"
|
||||
|
||||
|
||||
def _analysis_off_issues(nodes: dict[str, dict[str, Any]]) -> list[dict[str, Any]]:
|
||||
"""评测「关掉分析工具」那一臂：这一轮的工具清单里没有分析工具，图里照样绑了的（Agent、协作成员、调用工具节点）按
|
||||
「绑定的工具不存在」挡（同 engine/launch 发起前那一道的说法），交回模型去掉；改不好就不运行。一个节点一条。"""
|
||||
from app.tools.analysis import ANALYSIS_TOOLS
|
||||
|
||||
out: list[dict[str, Any]] = []
|
||||
for nid, node in nodes.items():
|
||||
cfg = ((node or {}).get("data") or {}).get("config") or {}
|
||||
ntype = (node or {}).get("type")
|
||||
if ntype == NodeType.TOOL:
|
||||
names = [cfg.get("tool")]
|
||||
elif ntype == NodeType.AGENT:
|
||||
names = list(cfg.get("tools") or [])
|
||||
elif ntype == NodeType.SUPERVISOR:
|
||||
names = [t for m in cfg.get("agents") or [] if isinstance(m, dict) for t in m.get("tools") or []]
|
||||
else:
|
||||
continue
|
||||
bound = list(dict.fromkeys(n.strip() for n in names if isinstance(n, str) and n.strip() in ANALYSIS_TOOLS))
|
||||
if not bound:
|
||||
continue
|
||||
title = str(((node or {}).get("data") or {}).get("label") or "").strip() or nid
|
||||
field = "tool" if ntype == NodeType.TOOL else "agents" if ntype == NodeType.SUPERVISOR else "tools"
|
||||
out.append({"level": "error", "node_id": nid, "edge_id": None, "field": field, "code": ANALYSIS_TOOLS_OFF,
|
||||
"message": f"绑定的工具不存在：「{title}」绑定的 {'、'.join(bound)}。这一轮没有分析工具可用，请在节点中去掉它们",
|
||||
"for_model": f"「{nid}」绑定的 {'、'.join(bound)} 不在这一轮的工具清单里，这一轮没有分析工具可用：从它的"
|
||||
"工具里去掉这几个，只用上面列出的工具（db_query__、db_schema__ 照留）；数据要怎么比、怎么拆，"
|
||||
"写进查询"})
|
||||
return out
|
||||
|
||||
|
||||
def _graph_request(payload: GenerateIn, *, analysis_tools: bool = True) -> str:
|
||||
"""这一轮的请求：改现有图时附上原图、只要改动操作；新建时按入口包好（_user_message）。"""
|
||||
if payload.base_graph and payload.base_graph.get("nodes"):
|
||||
return (
|
||||
@@ -948,7 +1013,7 @@ def _graph_request(payload: GenerateIn) -> str:
|
||||
f"{json.dumps(_slim(payload.base_graph), ensure_ascii=False, indent=2)}\n\n"
|
||||
f"请按下面的要求修改它（只输出改动操作）：\n{payload.instruction}"
|
||||
)
|
||||
return _user_message(payload, patch=False)
|
||||
return _user_message(payload, patch=False, analysis_tools=analysis_tools)
|
||||
|
||||
|
||||
def _start_graph(payload: GenerateIn) -> tuple[dict[str, dict[str, Any]], list[dict[str, Any]]]:
|
||||
@@ -1211,12 +1276,14 @@ def _blocking_issues(
|
||||
nodes: dict[str, dict[str, Any]], edges: list[dict[str, Any]], scope: set[str] | None = None,
|
||||
*, sources: list[Any] | None = None, baseline: list[dict[str, Any]] | None = None,
|
||||
level: str | None = None, defaults: dict[str, Any] | None = None,
|
||||
checkers: dict[str, Any] | None = None, chat_user: bool = False,
|
||||
checkers: dict[str, Any] | None = None, chat_user: bool = False, analysis_tools: bool = True,
|
||||
) -> list[dict[str, Any]] | None:
|
||||
"""按运行时同一套校验，挑出会挡住运行的问题。图本身不成形时返回 None。
|
||||
|
||||
chat_user：图要以开登录后 user 角色的身份在问数据里发起（D-c），使用者不能用的节点、工具、配置也挡（_chat_user_issues）。
|
||||
|
||||
analysis_tools 为假（评测「关掉分析工具」那一臂）：图里还绑着分析工具的也挡（_analysis_off_issues）。
|
||||
|
||||
限定了数据源时，用了范围外的库也算：用户点了「只查这个库」，拿别的库的数
|
||||
回答他，比跑不起来更糟——答案看起来是对的。
|
||||
|
||||
@@ -1245,7 +1312,8 @@ def _blocking_issues(
|
||||
out = ([i.model_dump() for i in validate_graph(spec).issues if i.level == "error"]
|
||||
+ _issue_dicts(scope_issues(list(nodes.values()), scope), "datasource_out_of_scope")
|
||||
+ [i for i in authored if i["level"] == "error"]
|
||||
+ (_chat_user_issues(nodes, edges) if chat_user else []))
|
||||
+ (_chat_user_issues(nodes, edges) if chat_user else [])
|
||||
+ ([] if analysis_tools else _analysis_off_issues(nodes)))
|
||||
if level:
|
||||
from app.engine.governance import lint_for_publish
|
||||
|
||||
@@ -1740,7 +1808,7 @@ async def generate_stream(payload: GenerateIn):
|
||||
)
|
||||
|
||||
|
||||
async def answer_ops(payload: GenerateIn, *, catalog_view: Any = None):
|
||||
async def answer_ops(payload: GenerateIn, *, catalog_view: Any = None, analysis_tools: bool = True):
|
||||
"""生成过程：按需求起草、按需查看、自查修正、排版校验，逐条交出操作（op dict）。问数据页（经 SSE）和评测（直接迭代）
|
||||
走的是这同一条路（细案 01 做法 2）。
|
||||
|
||||
@@ -1752,6 +1820,10 @@ async def answer_ops(payload: GenerateIn, *, catalog_view: Any = None):
|
||||
拒绝在这里抛 HTTPException（调用方没迭代到第一条就知道）。catalog_view 是这一轮读哪一份数据目录（data/catalog_view.py：
|
||||
查看的表详情、自查的 SQL 检查器都按它），不给是当前目录。
|
||||
|
||||
analysis_tools 为假是评测「关掉分析工具」那一臂（分析工具开、关对照，chat/drive.TurnDriver 的 analysis_tools 透传过来）：
|
||||
工具清单不列五个分析工具，节点手册、问数据的包装里只讲分析能力的那几段不给，问题意图那条自查不提；图里照样绑了分析工具
|
||||
的按「绑定的工具不存在」挡（_analysis_off_issues）。缺省为真，和以前一字不差。
|
||||
|
||||
final 带 next（chat/turn.next_step：run 运行、ready 只建不跑、fail 判失败），问数据页照它走。最后多交一条 usage
|
||||
（providers/usage.py）：{op: usage, by_model, input_tokens, output_tokens, calls, cost_usd,
|
||||
unpriced_calls}——这一轮助手建图（含挑表、接着写、自查修正）花了多少。前面每一条和抽出来之前逐条一样。运行不在这里，
|
||||
@@ -1783,7 +1855,8 @@ async def answer_ops(payload: GenerateIn, *, catalog_view: Any = None):
|
||||
except ProviderNotConfigured as e:
|
||||
raise HTTPException(400, _unconfigured(e)) from e
|
||||
|
||||
human = _with_history(_graph_request(payload), await _history_section(session, payload.conversation_id))
|
||||
human = _with_history(_graph_request(payload, analysis_tools=analysis_tools),
|
||||
await _history_section(session, payload.conversation_id))
|
||||
# 兜底用：模型只发了改动操作时，把它们重放到这张图上
|
||||
prev_graph = await _previous_graph(session, payload.conversation_id)
|
||||
# 比对工具绑定的基准：画布上是改之前的图；问数据页是上一轮的图（沿用它的节点 id）
|
||||
@@ -1797,12 +1870,14 @@ async def answer_ops(payload: GenerateIn, *, catalog_view: Any = None):
|
||||
looks = await _look_service(session, payload, sources, graph=payload.base_graph if (
|
||||
payload.base_graph or {}).get("nodes") else prev_graph, catalog_view=view, kinds=kinds)
|
||||
# 这一份 system 一直用到最后：接着写、自查修正都沿用，不换
|
||||
system = _graph_system(sources, scope, await copilot_context.section(looks), looks, chat_user=chat_user)
|
||||
system = _graph_system(sources, scope, await copilot_context.section(looks), looks, chat_user=chat_user,
|
||||
analysis_tools=analysis_tools)
|
||||
applier = GraphApplier(nodes, edges, composer=copilot_context.composer(looks))
|
||||
started = time.monotonic()
|
||||
gen = Generation(model, system=system, applier=applier, looks=looks, started=started,
|
||||
checker=GraphChecker(applier, scope=scope, sources=sources, baseline=baseline, checkers=checkers,
|
||||
chat_user=chat_user, question=_question_of(payload)))
|
||||
chat_user=chat_user, question=_question_of(payload),
|
||||
analysis_tools=analysis_tools))
|
||||
|
||||
async def steps():
|
||||
yield {"op": "model", "model": model_id}
|
||||
@@ -1869,7 +1944,7 @@ async def answer_ops(payload: GenerateIn, *, catalog_view: Any = None):
|
||||
async for op in _with_heartbeat(gen.repair(), phase="repairing"):
|
||||
yield op
|
||||
remaining = _blocking_issues(nodes, edges, scope, sources=sources, baseline=baseline, checkers=checkers,
|
||||
chat_user=chat_user)
|
||||
chat_user=chat_user, analysis_tools=analysis_tools)
|
||||
# 工具绑定变化不挡运行，但要在自查这一步就说出来：工具被改没了的图照样
|
||||
# 能跑，只是跑出来的是模型「假设」查过库的答案
|
||||
changes = tool_changes(baseline, list(nodes.values()))
|
||||
@@ -1905,6 +1980,8 @@ async def answer_ops(payload: GenerateIn, *, catalog_view: Any = None):
|
||||
issues += [i for i in authored if i["code"] in CHECK_CODES]
|
||||
# 使用者发起不了的图（D-c）：自查没改好的照实列出，界面据此不运行、说清原因
|
||||
issues += _chat_user_issues(nodes, edges) if chat_user else []
|
||||
# 关掉分析工具的那一臂里还绑着分析工具的（自查没改好）：同上，照实列出，不运行
|
||||
issues += [] if analysis_tools else _analysis_off_issues(nodes)
|
||||
# 跳过的节点要说出来，不能安静地少一步。code 给前端认：这一类要单独
|
||||
# 提示「少了一步」，不能和普通校验警告混在一起
|
||||
issues += [
|
||||
|
||||
@@ -709,13 +709,15 @@ class GraphChecker:
|
||||
known 给了（升级证据）：只把这一轮冒出来的问题交回去（图上原来就有的不归这一轮管），一个修改都没落地时不修。
|
||||
|
||||
question 给了（问数据：用户问的那句话）：问题是分析类（app/analysis/intent）、查库的 Agent 却没绑分析工具时另提一条
|
||||
（analysis_gaps），同 coverage 只交回模型改一轮。
|
||||
（analysis_gaps），同 coverage 只交回模型改一轮。analysis_tools 为假（评测「关掉分析工具」那一臂）时这一条不提，图里
|
||||
还绑着分析工具的按挡路的问题算（copilot._analysis_off_issues）。
|
||||
"""
|
||||
|
||||
def __init__(self, applier: GraphApplier, *, scope: set[str] | None = None, sources: list[Any] | None = None,
|
||||
baseline: list[dict[str, Any]] | None = None, level: str | None = None,
|
||||
defaults: dict[str, Any] | None = None, checkers: dict[str, Any] | None = None,
|
||||
known: set[Any] | None = None, chat_user: bool = False, question: str | None = None) -> None:
|
||||
known: set[Any] | None = None, chat_user: bool = False, question: str | None = None,
|
||||
analysis_tools: bool = True) -> None:
|
||||
from app.analysis.intent import analysis_intent
|
||||
|
||||
self.applier = applier
|
||||
@@ -733,8 +735,10 @@ class GraphChecker:
|
||||
self._coverage_cache: Any = None
|
||||
#: 这类问题已经交回模型改过一轮：之后不再挡（修正后仍在的留在检查结果里当提醒，由模型在说明里照实告诉用户）
|
||||
self._coverage_given = False
|
||||
#: 用户问题的分析意图（问为什么、怎么变了、是否异常、趋势……），不是分析类问题为 None
|
||||
self.intent = analysis_intent(question) if question else None
|
||||
#: 这一轮给不给分析工具（评测「关掉分析工具」那一臂为假）
|
||||
self.analysis_tools = analysis_tools
|
||||
#: 用户问题的分析意图（问为什么、怎么变了、是否异常、趋势……），不是分析类问题、或者这一轮没有分析工具时为 None
|
||||
self.intent = analysis_intent(question) if question and analysis_tools else None
|
||||
#: 「分析类问题、Agent 没绑分析工具」已经交回模型改过一轮：之后不再挡，同 _coverage_given
|
||||
self._analysis_given = False
|
||||
|
||||
@@ -743,7 +747,7 @@ class GraphChecker:
|
||||
|
||||
return _blocking_issues(self.applier.nodes, self.applier.edges, self.scope, sources=self.sources,
|
||||
baseline=self.baseline, level=self.level, defaults=self.defaults,
|
||||
checkers=self.checkers, chat_user=self.chat_user)
|
||||
checkers=self.checkers, chat_user=self.chat_user, analysis_tools=self.analysis_tools)
|
||||
|
||||
async def issues(self) -> list[dict[str, Any]]:
|
||||
errors = self.blocking()
|
||||
|
||||
@@ -123,13 +123,16 @@ class TurnDriver:
|
||||
|
||||
def __init__(self, question: str, *, datasource_ids: list[str],
|
||||
on_phase: Callable[[str], Awaitable[None]] | None = None,
|
||||
provider: str | None = None, model: str | None = None) -> None:
|
||||
provider: str | None = None, model: str | None = None, analysis_tools: bool = True) -> None:
|
||||
self.question = question
|
||||
self.datasource_ids = list(datasource_ids)
|
||||
self.on_phase = on_phase
|
||||
#: 助手模型（生成、复核都用它）：评测按变体覆盖，问数据用设置里的
|
||||
self.provider = provider
|
||||
self.model = model
|
||||
#: 这一轮给不给助手分析工具：透传给 api/copilot.answer_ops 的 analysis_tools。只给评测的「分析工具开、关」对照用
|
||||
#: （eval/answer.Driver 按变体设），问数据页不暴露这个开关，一直是真
|
||||
self.analysis_tools = analysis_tools
|
||||
self.turn = Turn()
|
||||
self.terminal: dict[str, Any] | None = None
|
||||
self.refusal: Exception | None = None
|
||||
@@ -200,7 +203,7 @@ class TurnDriver:
|
||||
payload = self.generate_in(instruction, base_graph)
|
||||
ops: list[dict[str, Any]] = []
|
||||
try:
|
||||
async for op in answer_ops(payload, catalog_view=self.catalog_view()):
|
||||
async for op in answer_ops(payload, catalog_view=self.catalog_view(), analysis_tools=self.analysis_tools):
|
||||
await self.on_op(op)
|
||||
if op.get("op") in ("thinking", "heartbeat"):
|
||||
continue
|
||||
|
||||
@@ -1,6 +1,8 @@
|
||||
"""助手搭图认分析能力（00-总方案 §3.7）：节点手册教分析卡和分析工具、报告的分析结论引用写法；问数据的包装多一种「分析类
|
||||
问题」的形状；自查时问题是分析类（app/analysis/intent）、查库的 Agent 却没绑分析工具，交回模型改一轮（只挡一轮，照 coverage
|
||||
的样板），改过一轮仍在的不挡运行、留作提醒；报告的上游只有分析卡也算有可引用的来源。
|
||||
的样板），改过一轮仍在的不挡运行、留作提醒；报告的上游只有分析卡也算有可引用的来源。评测「分析工具开、关」对照的「关」那一臂
|
||||
（answer_ops 的 analysis_tools、chat/drive.TurnDriver 的同名属性）：工具清单、节点手册、问数据的包装里都没有分析，图里绑了
|
||||
也按「绑定的工具不存在」挡，别的和开着时一样。
|
||||
|
||||
手册里举的引用标记交给真正的解析器，确认写法和系统认的是同一套（同 tests/test_copilot_entity_guide.py）。问法、节点、
|
||||
表都是虚构的零售场景。
|
||||
@@ -14,7 +16,8 @@ import pytest
|
||||
from langchain_core.messages import AIMessageChunk
|
||||
|
||||
from app.analysis import contract
|
||||
from app.api.copilot import _ASSIST_RULES, NODE_REFERENCE, GenerateIn, _evidence_source, _question_of, _user_message
|
||||
from app.api.copilot import (_ASSIST_RULES, ANALYSIS_SHAPE_PROMPT, ANALYSIS_TOOLS_OFF, NODE_REFERENCE, GenerateIn,
|
||||
_evidence_source, _question_of, _tool_catalog, _user_message, node_reference)
|
||||
from app.api.copilot_gen import ANALYSIS_TOOLS_MISSING, GraphApplier, GraphChecker
|
||||
from app.engine.evidence import _CELL_REF, _ROW_REF, SUPPORTED_KINDS, parse_markers
|
||||
from app.engine.schema import ANALYSIS_CLAIMS_VALUES, ANALYSIS_SCOPE_VALUES, GraphNode, NodeType
|
||||
@@ -246,3 +249,112 @@ async def test_a_retry_reads_the_original_question(client, monkeypatch): # noqa
|
||||
assert not [op for op in got if op["op"] == "check" and op["status"] == "repairing"]
|
||||
[final] = [op for op in got if op["op"] == "final"]
|
||||
assert not [i for i in final["issues"] if i["code"] == ANALYSIS_TOOLS_MISSING]
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------
|
||||
# 关掉分析工具（评测「分析工具开、关」对照的「关」那一臂：answer_ops 的 analysis_tools、TurnDriver 的同名属性）
|
||||
# --------------------------------------------------------------------------
|
||||
|
||||
|
||||
def test_the_catalog_and_the_manual_leave_analysis_out_when_switched_off():
|
||||
assert all(f"- {name}（" in _tool_catalog([]) for name in TOOLS)
|
||||
off = _tool_catalog([], analysis_tools=False)
|
||||
assert not [line for line in off.splitlines() if line.startswith("- analysis_")]
|
||||
assert off == "\n".join(line for line in _tool_catalog([]).splitlines() if not line.startswith("- analysis_"))
|
||||
assert node_reference() is NODE_REFERENCE
|
||||
manual = node_reference(analysis_tools=False)
|
||||
assert not any(name in manual for name in TOOLS)
|
||||
# 去掉的是 agent 段里「分析类问题绑分析工具」那一条、分析卡一整条、搭图规则第 7 条；报告段的引用写法、受管规则照留
|
||||
assert "- analysis：" not in manual and "\n7. " not in manual and "**问题问的是为什么" not in manual
|
||||
# 别的段落一字不少：只去掉那三段
|
||||
for kept in (" **默认不要写 max_steps", "- dual_check：", "\n模型字段", "- report：", "[[a:A1]]", "analysis_claims"):
|
||||
assert kept in manual, kept
|
||||
request = GenerateIn(instruction="上周销售额为什么下降", intent="answer")
|
||||
on, off_text = _user_message(request, patch=False), _user_message(request, patch=False, analysis_tools=False)
|
||||
assert ANALYSIS_SHAPE_PROMPT in on and ANALYSIS_SHAPE_PROMPT not in off_text
|
||||
assert on.replace(ANALYSIS_SHAPE_PROMPT, "") == off_text
|
||||
|
||||
|
||||
def _recording(first: list[dict], fix: list[dict], seen: list[list[tuple[str, str]]]):
|
||||
class Recording:
|
||||
async def astream(self, messages):
|
||||
seen.append(list(messages))
|
||||
human = next(text for role, text in messages if role == "human")
|
||||
for op in (fix if "上线前自查" in human else first):
|
||||
yield AIMessageChunk(content=json.dumps(op, ensure_ascii=False) + "\n")
|
||||
|
||||
return Recording()
|
||||
|
||||
|
||||
async def _ops_of(question: str, *, analysis_tools: bool) -> list[dict]:
|
||||
from app.api.copilot import answer_ops
|
||||
|
||||
return [op async for op in answer_ops(GenerateIn(instruction=question, intent="answer"),
|
||||
analysis_tools=analysis_tools)
|
||||
if op.get("op") not in ("heartbeat", "usage")]
|
||||
|
||||
|
||||
async def test_switched_off_the_copilot_sees_no_analysis_and_bound_tools_are_blocked(monkeypatch):
|
||||
seen: list[list[tuple[str, str]]] = []
|
||||
fix = [{"op": "update_node", "id": "bot", "config": {"tools": ["db_query__shop", "db_schema__shop"]}},
|
||||
{"op": "done", "explanation": "去掉了分析工具"}]
|
||||
_use(monkeypatch, _recording(_ops(["db_query__shop", "db_schema__shop", "analysis_decompose"]), fix, seen))
|
||||
got = await _ops_of("上周销售额为什么下降", analysis_tools=False)
|
||||
system = seen[0][0][1]
|
||||
assert seen[0][0][0] == "system" and not any(name in system for name in TOOLS)
|
||||
assert ANALYSIS_TOOLS_MISSING not in json.dumps(got, ensure_ascii=False), "问题意图那条自查不提"
|
||||
[repairing] = [op for op in got if op["op"] == "check" and op["status"] == "repairing"]
|
||||
[issue] = [i for i in repairing["issues"] if i["code"] == ANALYSIS_TOOLS_OFF]
|
||||
assert issue["node_id"] == "bot" and issue["message"].startswith("绑定的工具不存在：「bot」绑定的 analysis_decompose")
|
||||
[final] = [op for op in got if op["op"] == "final"]
|
||||
assert final["next"] == "run" and not [i for i in final["issues"] if i["code"] == ANALYSIS_TOOLS_OFF]
|
||||
|
||||
# 改不好：照实列出、不运行
|
||||
seen.clear()
|
||||
_use(monkeypatch, _recording(_ops(["db_query__shop", "analysis_decompose"]), [{"op": "done", "explanation": "x"}],
|
||||
seen))
|
||||
got = await _ops_of("上周销售额为什么下降", analysis_tools=False)
|
||||
[final] = [op for op in got if op["op"] == "final"]
|
||||
assert final["next"] == "fail" and [i["level"] for i in final["issues"] if i["code"] == ANALYSIS_TOOLS_OFF] == ["error"]
|
||||
|
||||
|
||||
async def test_switched_on_bound_analysis_tools_are_fine(monkeypatch):
|
||||
"""缺省开着：绑了分析工具不挡，和以前一样直接运行。"""
|
||||
seen: list[list[tuple[str, str]]] = []
|
||||
_use(monkeypatch, _recording(_ops(["db_query__shop", "db_schema__shop", *TOOLS]), [], seen))
|
||||
got = await _ops_of("上周销售额为什么下降", analysis_tools=True)
|
||||
assert all(name in seen[0][0][1] for name in TOOLS)
|
||||
assert not [op for op in got if op["op"] == "check" and op["status"] == "repairing"]
|
||||
[final] = [op for op in got if op["op"] == "final"]
|
||||
assert final["next"] == "run"
|
||||
|
||||
|
||||
async def test_other_turns_go_the_same_either_way(monkeypatch):
|
||||
"""没碰分析工具的一轮（不是分析类问题、图里没绑分析工具）：开、关两臂交出的操作逐条一样，差的只是给助手看的那几段。"""
|
||||
runs = {}
|
||||
for flag in (True, False):
|
||||
seen: list[list[tuple[str, str]]] = []
|
||||
_use(monkeypatch, _recording(_ops(["db_query__shop", "db_schema__shop"]), [], seen))
|
||||
runs[flag] = (await _ops_of("上周销售额是多少", analysis_tools=flag), seen[0])
|
||||
assert runs[True][0] == runs[False][0]
|
||||
(_, system_on), (_, human_on) = runs[True][1]
|
||||
(_, system_off), (_, human_off) = runs[False][1]
|
||||
assert human_on.replace(ANALYSIS_SHAPE_PROMPT, "") == human_off and system_on != system_off
|
||||
|
||||
|
||||
async def test_the_turn_driver_passes_the_switch_through(monkeypatch):
|
||||
import app.api.copilot as copilot
|
||||
from app.chat.drive import TurnDriver
|
||||
|
||||
calls: list[dict] = []
|
||||
|
||||
async def fake_ops(payload, **kwargs):
|
||||
calls.append({"question": payload.question, **kwargs})
|
||||
yield {"op": "reply", "text": "上一轮已经查过了。"}
|
||||
|
||||
monkeypatch.setattr(copilot, "answer_ops", fake_ops)
|
||||
assert TurnDriver("上周销售额为什么下降", datasource_ids=[]).analysis_tools is True
|
||||
driver = TurnDriver("上周销售额为什么下降", datasource_ids=[], analysis_tools=False)
|
||||
ops, refused = await driver._generate("上周销售额为什么下降", None)
|
||||
assert refused is None and ops == [{"op": "reply", "text": "上一轮已经查过了。"}]
|
||||
assert calls == [{"question": "上周销售额为什么下降", "catalog_view": None, "analysis_tools": False}]
|
||||
|
||||
Reference in New Issue
Block a user