Merge branch 'main' into incremental_development

# Conflicts: # metagpt/schema.py
2026-05-12 01:02:37 +02:00 · 2024-01-19 19:53:17 +08:00 · 2024-01-19 19:53:17 +08:00 · e1b783ca14
commit e1b783ca14
parent bed3040ff3 5389c52556
127 changed files with 2346 additions and 648 deletions
--- a/metagpt/actions/invoice_ocr.py
+++ b/metagpt/actions/invoice_ocr.py
@ -88,6 +88,8 @@ class InvoiceOCR(Action):
    async def _ocr(invoice_file_path: Path):
        ocr = PaddleOCR(use_angle_cls=True, lang="ch", page_num=1)
        ocr_result = ocr.ocr(str(invoice_file_path), cls=True)
+        for result in ocr_result[0]:
+            result[1] = (result[1][0], round(result[1][1], 2))  # round long confidence scores to reduce token costs
        return ocr_result

    async def run(self, file_path: Path, *args, **kwargs) -> list:
--- a/metagpt/actions/prepare_documents.py
+++ b/metagpt/actions/prepare_documents.py
@ -35,7 +35,6 @@ class PrepareDocuments(Action):
        if path.exists() and not CONFIG.inc:
            shutil.rmtree(path)
        CONFIG.project_path = path
-        CONFIG.project_name = path.name
        CONFIG.git_repo = GitRepository(local_path=path, auto_init=True)

    async def run(self, with_messages, **kwargs):
--- a/metagpt/actions/rebuild_class_view.py
+++ b/metagpt/actions/rebuild_class_view.py
@ -9,60 +9,209 @@
 import re
 from pathlib import Path

+import aiofiles
+
 from metagpt.actions import Action
 from metagpt.config import CONFIG
-from metagpt.const import CLASS_VIEW_FILE_REPO, GRAPH_REPO_FILE_REPO
+from metagpt.const import (
+    AGGREGATION,
+    COMPOSITION,
+    DATA_API_DESIGN_FILE_REPO,
+    GENERALIZATION,
+    GRAPH_REPO_FILE_REPO,
+)
+from metagpt.logs import logger
 from metagpt.repo_parser import RepoParser
+from metagpt.schema import ClassAttribute, ClassMethod, ClassView
+from metagpt.utils.common import split_namespace
 from metagpt.utils.di_graph_repository import DiGraphRepository
 from metagpt.utils.graph_repository import GraphKeyword, GraphRepository


 class RebuildClassView(Action):
-    def __init__(self, name="", context=None, llm=None):
-        super().__init__(name=name, context=context, llm=llm)
-
    async def run(self, with_messages=None, format=CONFIG.prompt_schema):
        graph_repo_pathname = CONFIG.git_repo.workdir / GRAPH_REPO_FILE_REPO / CONFIG.git_repo.workdir.name
        graph_db = await DiGraphRepository.load_from(str(graph_repo_pathname.with_suffix(".json")))
-        repo_parser = RepoParser(base_directory=self.context)
-        class_views = await repo_parser.rebuild_class_views(path=Path(self.context))  # use pylint
+        repo_parser = RepoParser(base_directory=Path(self.context))
+        # use pylint
+        class_views, relationship_views, package_root = await repo_parser.rebuild_class_views(path=Path(self.context))
        await GraphRepository.update_graph_db_with_class_views(graph_db, class_views)
-        symbols = repo_parser.generate_symbols()  # use ast
+        await GraphRepository.update_graph_db_with_class_relationship_views(graph_db, relationship_views)
+        # use ast
+        direction, diff_path = self._diff_path(path_root=Path(self.context).resolve(), package_root=package_root)
+        symbols = repo_parser.generate_symbols()
        for file_info in symbols:
+            # Align to the same root directory in accordance with `class_views`.
+            file_info.file = self._align_root(file_info.file, direction, diff_path)
            await GraphRepository.update_graph_db_with_file_info(graph_db, file_info)
-        await self._create_mermaid_class_view(graph_db=graph_db)
-        await self._save(graph_db=graph_db)
+        await self._create_mermaid_class_views(graph_db=graph_db)
+        await graph_db.save()

-    async def _create_mermaid_class_view(self, graph_db):
-        pass
-        # dataset = await graph_db.select(subject=concat_namespace(filename, class_name), predicate=GraphKeyword.HAS_PAGE_INFO)
-        # if not dataset:
-        #     logger.warning(f"No page info for {concat_namespace(filename, class_name)}")
-        #     return
-        # code_block_info = CodeBlockInfo.parse_raw(dataset[0].object_)
-        # src_code = await read_file_block(filename=Path(self.context) / filename, lineno=code_block_info.lineno, end_lineno=code_block_info.end_lineno)
-        # code_type = ""
-        # dataset = await graph_db.select(subject=filename, predicate=GraphKeyword.IS)
-        # for spo in dataset:
-        #     if spo.object_ in ["javascript", "python"]:
-        #         code_type = spo.object_
-        #         break
+    async def _create_mermaid_class_views(self, graph_db):
+        path = Path(CONFIG.git_repo.workdir) / DATA_API_DESIGN_FILE_REPO
+        path.mkdir(parents=True, exist_ok=True)
+        pathname = path / CONFIG.git_repo.workdir.name
+        async with aiofiles.open(str(pathname.with_suffix(".mmd")), mode="w", encoding="utf-8") as writer:
+            content = "classDiagram\n"
+            logger.debug(content)
+            await writer.write(content)
+            # class names
+            rows = await graph_db.select(predicate=GraphKeyword.IS, object_=GraphKeyword.CLASS)
+            class_distinct = set()
+            relationship_distinct = set()
+            for r in rows:
+                await RebuildClassView._create_mermaid_class(r.subject, graph_db, writer, class_distinct)
+            for r in rows:
+                await RebuildClassView._create_mermaid_relationship(r.subject, graph_db, writer, relationship_distinct)

-        # try:
-        #     node = await REBUILD_CLASS_VIEW_NODE.fill(context=f"```{code_type}\n{src_code}\n```", llm=self.llm, to=format)
-        #     class_view = node.instruct_content.model_dump()["Class View"]
-        # except Exception as e:
-        #     class_view = RepoParser.rebuild_class_view(src_code, code_type)
-        # await graph_db.insert(subject=concat_namespace(filename, class_name), predicate=GraphKeyword.HAS_CLASS_VIEW, object_=class_view)
-        # logger.info(f"{concat_namespace(filename, class_name)} {GraphKeyword.HAS_CLASS_VIEW} {class_view}")
+    @staticmethod
+    async def _create_mermaid_class(ns_class_name, graph_db, file_writer, distinct):
+        fields = split_namespace(ns_class_name)
+        if len(fields) > 2:
+            # Ignore sub-class
+            return

-    async def _save(self, graph_db):
-        class_view_file_repo = CONFIG.git_repo.new_file_repository(relative_path=CLASS_VIEW_FILE_REPO)
-        dataset = await graph_db.select(predicate=GraphKeyword.HAS_CLASS_VIEW)
-        all_class_view = []
-        for spo in dataset:
-            title = f"---\ntitle: {spo.subject}\n---\n"
-            filename = re.sub(r"[/:]", "_", spo.subject) + ".mmd"
-            await class_view_file_repo.save(filename=filename, content=title + spo.object_)
-            all_class_view.append(spo.object_)
-        await class_view_file_repo.save(filename="all.mmd", content="\n".join(all_class_view))
+        class_view = ClassView(name=fields[1])
+        rows = await graph_db.select(subject=ns_class_name)
+        for r in rows:
+            name = split_namespace(r.object_)[-1]
+            name, visibility, abstraction = RebuildClassView._parse_name(name=name, language="python")
+            if r.predicate == GraphKeyword.HAS_CLASS_PROPERTY:
+                var_type = await RebuildClassView._parse_variable_type(r.object_, graph_db)
+                attribute = ClassAttribute(
+                    name=name, visibility=visibility, abstraction=bool(abstraction), value_type=var_type
+                )
+                class_view.attributes.append(attribute)
+            elif r.predicate == GraphKeyword.HAS_CLASS_FUNCTION:
+                method = ClassMethod(name=name, visibility=visibility, abstraction=bool(abstraction))
+                await RebuildClassView._parse_function_args(method, r.object_, graph_db)
+                class_view.methods.append(method)
+
+        # update graph db
+        await graph_db.insert(ns_class_name, GraphKeyword.HAS_CLASS_VIEW, class_view.model_dump_json())
+
+        content = class_view.get_mermaid(align=1)
+        logger.debug(content)
+        await file_writer.write(content)
+        distinct.add(ns_class_name)
+
+    @staticmethod
+    async def _create_mermaid_relationship(ns_class_name, graph_db, file_writer, distinct):
+        s_fields = split_namespace(ns_class_name)
+        if len(s_fields) > 2:
+            # Ignore sub-class
+            return
+
+        predicates = {GraphKeyword.IS + v + GraphKeyword.OF: v for v in [GENERALIZATION, COMPOSITION, AGGREGATION]}
+        mappings = {
+            GENERALIZATION: " <|-- ",
+            COMPOSITION: " *-- ",
+            AGGREGATION: " o-- ",
+        }
+        content = ""
+        for p, v in predicates.items():
+            rows = await graph_db.select(subject=ns_class_name, predicate=p)
+            for r in rows:
+                o_fields = split_namespace(r.object_)
+                if len(o_fields) > 2:
+                    # Ignore sub-class
+                    continue
+                relationship = mappings.get(v, " .. ")
+                link = f"{o_fields[1]}{relationship}{s_fields[1]}"
+                distinct.add(link)
+                content += f"\t{link}\n"
+
+        if content:
+            logger.debug(content)
+            await file_writer.write(content)
+
+    @staticmethod
+    def _parse_name(name: str, language="python"):
+        pattern = re.compile(r"<I>(.*?)<\/I>")
+        result = re.search(pattern, name)
+
+        abstraction = ""
+        if result:
+            name = result.group(1)
+            abstraction = "*"
+        if name.startswith("__"):
+            visibility = "-"
+        elif name.startswith("_"):
+            visibility = "#"
+        else:
+            visibility = "+"
+        return name, visibility, abstraction
+
+    @staticmethod
+    async def _parse_variable_type(ns_name, graph_db) -> str:
+        rows = await graph_db.select(subject=ns_name, predicate=GraphKeyword.HAS_TYPE_DESC)
+        if not rows:
+            return ""
+        vals = rows[0].object_.replace("'", "").split(":")
+        if len(vals) == 1:
+            return ""
+        val = vals[-1].strip()
+        return "" if val == "NoneType" else val + " "
+
+    @staticmethod
+    async def _parse_function_args(method: ClassMethod, ns_name: str, graph_db: GraphRepository):
+        rows = await graph_db.select(subject=ns_name, predicate=GraphKeyword.HAS_ARGS_DESC)
+        if not rows:
+            return
+        info = rows[0].object_.replace("'", "")
+
+        fs_tag = "("
+        ix = info.find(fs_tag)
+        fe_tag = "):"
+        eix = info.rfind(fe_tag)
+        if eix < 0:
+            fe_tag = ")"
+            eix = info.rfind(fe_tag)
+        args_info = info[ix + len(fs_tag) : eix].strip()
+        method.return_type = info[eix + len(fe_tag) :].strip()
+        if method.return_type == "None":
+            method.return_type = ""
+        if "(" in method.return_type:
+            method.return_type = method.return_type.replace("(", "Tuple[").replace(")", "]")
+
+        # parse args
+        if not args_info:
+            return
+        splitter_ixs = []
+        cost = 0
+        for i in range(len(args_info)):
+            if args_info[i] == "[":
+                cost += 1
+            elif args_info[i] == "]":
+                cost -= 1
+            if args_info[i] == "," and cost == 0:
+                splitter_ixs.append(i)
+        splitter_ixs.append(len(args_info))
+        args = []
+        ix = 0
+        for eix in splitter_ixs:
+            args.append(args_info[ix:eix])
+            ix = eix + 1
+        for arg in args:
+            parts = arg.strip().split(":")
+            if len(parts) == 1:
+                method.args.append(ClassAttribute(name=parts[0].strip()))
+                continue
+            method.args.append(ClassAttribute(name=parts[0].strip(), value_type=parts[-1].strip()))
+
+    @staticmethod
+    def _diff_path(path_root: Path, package_root: Path) -> (str, str):
+        if len(str(path_root)) > len(str(package_root)):
+            return "+", str(path_root.relative_to(package_root))
+        if len(str(path_root)) < len(str(package_root)):
+            return "-", str(package_root.relative_to(path_root))
+        return "=", "."
+
+    @staticmethod
+    def _align_root(path: str, direction: str, diff_path: str):
+        if direction == "=":
+            return path
+        if direction == "+":
+            return diff_path + "/" + path
+        else:
+            return path[len(diff_path) + 1 :]
--- a/metagpt/actions/rebuild_class_view_an.py
+++ b/metagpt/actions/rebuild_class_view_an.py
@ -1,33 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-"""
-@Time    : 2023/12/19
-@Author  : mashenquan
-@File    : rebuild_class_view_an.py
-@Desc    : Defines `ActionNode` objects used by rebuild_class_view.py
-"""
-from metagpt.actions.action_node import ActionNode
-
-CLASS_SOURCE_CODE_BLOCK = ActionNode(
-    key="Class View",
-    expected_type=str,
-    instruction='Generate the mermaid class diagram corresponding to source code in "context."',
-    example="""
-    classDiagram
-        class A {
-        -int x
-        +int y
-        -int speed
-        -int direction
-        +__init__(x: int, y: int, speed: int, direction: int)
-        +change_direction(new_direction: int) None
-        +move() None
-    }
-    """,
-)
-
-REBUILD_CLASS_VIEW_NODES = [
-    CLASS_SOURCE_CODE_BLOCK,
-]
-
-REBUILD_CLASS_VIEW_NODE = ActionNode.from_children("RebuildClassView", REBUILD_CLASS_VIEW_NODES)
--- a/metagpt/actions/rebuild_sequence_view.py
+++ b/metagpt/actions/rebuild_sequence_view.py
@ -0,0 +1,60 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+@Time    : 2024/1/4
+@Author  : mashenquan
+@File    : rebuild_sequence_view.py
+@Desc    : Rebuild sequence view info
+"""
+from __future__ import annotations
+
+from pathlib import Path
+from typing import List
+
+from metagpt.actions import Action
+from metagpt.config import CONFIG
+from metagpt.const import GRAPH_REPO_FILE_REPO
+from metagpt.logs import logger
+from metagpt.utils.common import aread, list_files
+from metagpt.utils.di_graph_repository import DiGraphRepository
+from metagpt.utils.graph_repository import GraphKeyword
+
+
+class RebuildSequenceView(Action):
+    async def run(self, with_messages=None, format=CONFIG.prompt_schema):
+        graph_repo_pathname = CONFIG.git_repo.workdir / GRAPH_REPO_FILE_REPO / CONFIG.git_repo.workdir.name
+        graph_db = await DiGraphRepository.load_from(str(graph_repo_pathname.with_suffix(".json")))
+        entries = await RebuildSequenceView._search_main_entry(graph_db)
+        for entry in entries:
+            await self._rebuild_sequence_view(entry, graph_db)
+        await graph_db.save()
+
+    @staticmethod
+    async def _search_main_entry(graph_db) -> List:
+        rows = await graph_db.select(predicate=GraphKeyword.HAS_PAGE_INFO)
+        tag = "__name__:__main__"
+        entries = []
+        for r in rows:
+            if tag in r.subject or tag in r.object_:
+                entries.append(r)
+        return entries
+
+    async def _rebuild_sequence_view(self, entry, graph_db):
+        filename = entry.subject.split(":", 1)[0]
+        src_filename = RebuildSequenceView._get_full_filename(root=self.context, pathname=filename)
+        content = await aread(filename=src_filename, encoding="utf-8")
+        content = f"```python\n{content}\n```\n\n---\nTranslate the code above into Mermaid Sequence Diagram."
+        data = await self.llm.aask(
+            msg=content, system_msgs=["You are a python code to Mermaid Sequence Diagram translator in function detail"]
+        )
+        await graph_db.insert(subject=filename, predicate=GraphKeyword.HAS_SEQUENCE_VIEW, object_=data)
+        logger.info(data)
+
+    @staticmethod
+    def _get_full_filename(root: str | Path, pathname: str | Path) -> Path | None:
+        files = list_files(root=root)
+        postfix = "/" + str(pathname)
+        for i in files:
+            if str(i).endswith(postfix):
+                return i
+        return None
--- a/metagpt/actions/rebuild_sequence_view_an.py
+++ b/metagpt/actions/rebuild_sequence_view_an.py
@ -0,0 +1,16 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+@Time    : 2024/1/4
+@Author  : mashenquan
+@File    : rebuild_sequence_view_an.py
+"""
+from metagpt.actions.action_node import ActionNode
+from metagpt.utils.mermaid import MMC2
+
+CODE_2_MERMAID_SEQUENCE_DIAGRAM = ActionNode(
+    key="Program call flow",
+    expected_type=str,
+    instruction='Translate the "context" content into "format example" format.',
+    example=MMC2,
+)
--- a/metagpt/actions/write_code.py
+++ b/metagpt/actions/write_code.py
@ -158,7 +158,7 @@ class WriteCode(Action):
        if not coding_context.code_doc:
            # avoid root_path pydantic ValidationError if use WriteCode alone
            root_path = CONFIG.src_workspace if CONFIG.src_workspace else ""
-            coding_context.code_doc = Document(filename=coding_context.filename, root_path=root_path)
+            coding_context.code_doc = Document(filename=coding_context.filename, root_path=str(root_path))
        coding_context.code_doc.content = code
        return coding_context

--- a/metagpt/actions/write_code_review.py
+++ b/metagpt/actions/write_code_review.py
@ -188,9 +188,11 @@ class WriteCodeReview(Action):
            cr_prompt = EXAMPLE_AND_INSTRUCTION.format(
                format_example=format_example,
            )
+            len1 = len(iterative_code) if iterative_code else 0
+            len2 = len(self.context.code_doc.content) if self.context.code_doc.content else 0
            logger.info(
-                f"Code review and rewrite {self.context.code_doc.filename}: {i + 1}/{k} | {len(iterative_code)=}, "
-                f"{len(self.context.code_doc.content)=}"
+                f"Code review and rewrite {self.context.code_doc.filename}: {i + 1}/{k} | len(iterative_code)={len1}, "
+                f"len(self.context.code_doc.content)={len2}"
            )
            result, rewrited_code = await self.write_code_review_and_rewrite(
                context_prompt, cr_prompt, self.context.code_doc.filename
--- a/metagpt/actions/write_prd.py
+++ b/metagpt/actions/write_prd.py
@ -14,6 +14,7 @@
 from __future__ import annotations

 import json
+import uuid
 from pathlib import Path
 from typing import Optional

@ -120,7 +121,7 @@ class WritePRD(Action):
        # if sas.result:
        #     logger.info(sas.result)
        #     logger.info(rsp)
-        project_name = CONFIG.project_name if CONFIG.project_name else ""
+        project_name = CONFIG.project_name or ""
        context = CONTEXT_TEMPLATE.format(requirements=requirements, project_name=project_name)
        exclude = [PROJECT_NAME.key] if project_name else []
        node = await WRITE_PRD_NODE.fill(context=context, llm=self.llm, exclude=exclude)  # schema=schema
@ -190,6 +191,8 @@ class WritePRD(Action):
                ws_name = CodeParser.parse_str(block="Project Name", text=prd)
            if ws_name:
                CONFIG.project_name = ws_name
+        if not CONFIG.project_name:  # The LLM failed to provide a project name, and the user didn't provide one either.
+            CONFIG.project_name = "app" + uuid.uuid4().hex[:16]
        CONFIG.git_repo.rename_root(CONFIG.project_name)

    async def _is_bugfix(self, context) -> bool:
--- a/metagpt/actions/write_test.py
+++ b/metagpt/actions/write_test.py
@ -11,7 +11,6 @@
 from typing import Optional

 from metagpt.actions.action import Action
-from metagpt.config import CONFIG
 from metagpt.const import TEST_CODES_FILE_REPO
 from metagpt.logs import logger
 from metagpt.schema import Document, TestingContext
@ -60,11 +59,12 @@ class WriteTest(Action):
            self.context.test_doc = Document(
                filename="test_" + self.context.code_doc.filename, root_path=TEST_CODES_FILE_REPO
            )
+        fake_root = "/data"
        prompt = PROMPT_TEMPLATE.format(
            code_to_test=self.context.code_doc.content,
            test_file_name=self.context.test_doc.filename,
-            source_file_path=self.context.code_doc.root_relative_path,
-            workspace=CONFIG.git_repo.workdir,
+            source_file_path=fake_root + "/" + self.context.code_doc.root_relative_path,
+            workspace=fake_root,
        )
        self.context.test_doc.content = await self.write_code(prompt)
        return self.context