ReMe/reme4/application.py
jinliyl 83831ec90c
feat(core): enhance reme4 (#281)
### 1. Agent Wrapper(统一 Agent 后端抽象)
- **`base_agent_wrapper.py`**:`reply()` 返回值从 `tuple[str, Any]` 改为 `dict`(含 `session_id` / `last_message` / `result` / 可选 `structured_output`);`reply_stream()` 改为产出统一的 `StreamChunk`。废弃 `add_tools()`,改为 `add_job_tools(names: list[str])`(按名解析 BaseJob)与 `add_skills()`;新增 `_resolve_job_tools()`、`_merged_kwargs()`、`_chunk()` 辅助方法及 `project_path` / `project_skills_root` 属性。
- **`as_agent_wrapper.py`(AgentScope 后端)**:
  - 会话持久化重写:`session_path` 落地到 `<vault>/<session_dir>/agentscope/`,`_load_state` 支持 `resume` / `session_id` / `fork_session`,并做 UUID 校验(`_validate_session_id`);`_cleanup_expired_sessions` 按天数清理过期会话。
  - 新增内置工具集(`BypassAnalysisBash` + Edit/Glob/Grep/Read/Write),`BypassAnalysisBash` 绕过 AgentScope 自带 Bash 静态分析以让 permission_mode 生效;`_resolve_skills()` 把配置的 skill 暴露给后端,`_load_tool_env()` 注入项目 `.env`。
  - `_event_to_chunk()` 把 20+ 种 AgentScope 事件(Reply/Text/Thinking/Data/ToolCall/ToolResult/ModelCall/ExceedMaxIters)归一化为 `StreamChunk`。
- **`cc_agent_wrapper.py`(Claude Code SDK 后端,+551 行)**:
  - 新增 `_CcFileSessionStore`:基于 vault 的文件型会话存储,实现 append(按 uuid 去重)/ load / list / delete / list_subkeys,并对路径做 `_safe_parts` + `resolve()` 防越界校验。
  - `_build_options()`:统一构建 `ClaudeAgentOptions`,处理 skills、disallowed_tools(默认禁 `WebSearch`)、`.env` 注入、Claude Code 的 API 凭据解析(`_claude_code_api_env`,多级 base_url/api_key 回退)、`CLAUDE_CONFIG_DIR` 设置、skill 目录软链接(`_ensure_claude_skill_dir`)。
  - `_raw_event_to_chunk()` / `_message_content_to_chunks()`:把 Anthropic 流式事件(message_start/delta/stop、content_block_*)与 SDK 消息块(AssistantMessage/UserMessage/ResultMessage/RateLimitEvent)转换为统一 `StreamChunk`;跟踪 block_id/block_type/tool_call_name 做关联;处理尾部 `"success"` 误报异常的吞掉逻辑。

### 2. 统一流式协议(StreamChunk / ChunkEnum)
- **`stream_chunk.py`**:`StreamChunk` 扩展为承载 AS + CC 双后端完整信息的统一结构,新增 `session_id` / `block_id` / `tool_call_id` / `tool_call_name` / `media_type` / `input_tokens` / `output_tokens` 等字段,纯文本流仍保持轻量。
- **`chunk_enum.py`**:补全生命周期标记 `REPLY_START` / `REPLY_END`,并文档化两套后端事件 → ChunkEnum 的映射。

### 3. Index 模块重构(变化批次化 + dispatch)
- 新增 `_change_batch.py`:`coalesce_changes()` 把同路径多次事件折叠为最终状态(结合 path 存在性判定),`bucket_changes()` 按 watchfiles.Change 分桶。
- 新增 `init_changes.py`(`InitChangesStep`):一次性扫描,对比 file_store / file_catalog 已索引节点计算 added/modified/deleted,写入 `context["changes"]` 后 dispatch。
- 新增 `update_changes.py`:抽象基类 `ChangeApplyStep` 统一 added/modified/deleted 处理与错误收集;`UpdateCatalogStep`(写 file_catalog)、`UpdateIndexStep`(写 file_store,含按后缀解析 chunker)。
- **`watch_changes.py`**:改用 `dispatch_step_specs`(基类提供的 `dispatch_steps()`),每批先 `coalesce_changes` 再 dispatch;默认参数调整(debounce 5000ms / step 1000ms / poll 5000ms)并暴露常量。
- 删除旧步骤:`clear_and_scan` / `foreach_dispatch` / `scan_changes` / `update_catalog`(旧) / `update_index`(旧);`clear_store.py` 取代 clear_and_scan。

### 4. Evolve / Dream 模块(拆分为多步 pipeline)
- 删除旧的单体 `auto_dream.py` / `dream.py` / `dream.yaml`,新增 `dream/` 子包,按 5 个步骤组织:
  - **`extract.py`**:扫描当日 day-index + daily 笔记,对比 file_catalog 找出 changed/deleted,调用 LLM 全局抽取 `units`(procedure/personal/wiki 三桶)与 `topics`,路径与桶做清洗/路由。
  - **`integrate.py`**:逐个 unit 调用 LLM 写入 digest,结构化输出 `IntegrateOutcome`(CREATE/CORROBORATE/REFINE/CORRECT),失败 unit/路径收集回写。
  - **`topics.py`**:写 `daily/<date>/interests.yaml`,结合当天已有 + 近 N 天做去重(`normalize_topic`),可走 LLM 或纯规则去重两条路径。
  - **`proactive.py`**:读取当日 `interests.yaml`,作为主动推荐话题的入口。
  - **`finish.py`**:把变更路径落盘到 dream file_catalog(checkpoint),渲染最终汇总摘要。
- 新增 `schema.py`(`DreamState` 等跨步骤共享状态与结构化输出模型)与 `utils.py`(状态存取、扫描打包、YAML 读写、结构化回复解析等公共函数)。
- `evolve/__init__.py` 导出全部新 step。

### 5. auto_memory / auto_resource(适配新 Agent API)
- **`auto_memory.py`**:会话路径迁移到 `<session_dir>/dialog/<session_id>.jsonl`;改用 `job_tools`;新增 `source_conversation` frontmatter 反向链接(`_session_link`);执行后刷新 day 索引(`refresh_day_index`),并对 session_id 做合法性校验。
- **`auto_resource.py`**:资源改用「同名 daily note」方案(`_compute_note_stem` 取文件 stem);批量处理 `changes: list[dict]`(`_handle_change` 逐项处理,返回逐项结果摘要);agent 会话 id 用稳定的 `uuid5`;同样刷新 day 索引。

### 6. BaseStep 基类增强
- 新增 `dispatch_steps` / `dispatch_step_specs` 机制:`_resolve_dispatch_step()` 支持字符串或 dict 形式的 step spec,`dispatch_steps()` 复用当前 context 调用下游 step。
- 新增 `config_value()`:按 key 取 app config,缺失时回退 `ApplicationConfig` 默认值。
- 小幅清理:`language` 初始化、`copy()`、`Ref.__init__` 签名精简。

### 7. Components 改动
- **`file_store/local_file_store.py`**:持久化改用 zstd 压缩(`.jsonl.zst`,通过新 `utils/jsonl_zst.py`);upsert 时先删除旧 chunk 的 keyword 文档;embedding 复用改为 `(text, embedding)` 键控,要求文本一致才复用;新增 `_matches_search_filter()` 对 vector/keyword 搜索做 path/path_prefix/metadata 的统一后过滤。
- **`keyword_index/bm25_index.py`**:索引文件名加入组件名 + tokenizer 指纹(sha256 前 12 位),快照/恢复时校验指纹防配置漂移;空索引 dump 时删除文件,加载失败抛错而非静默。
- **`file_chunker/markdown_file_chunker.py`**:弃用 `python-frontmatter`,改用内置 YAML 解析(非法 YAML 不阻断正文索引),并修正因 frontmatter 占用行号导致的 AST 行号偏移(`line_offset`)。
- **`cron_job.py`**:大幅简化(-187 行),由原来「dispatch 外部 job/step + 多种调度模式」改为「在自身 steps 上跑 cron 表达式」;`Application` 启动顺序随之调整为 base > stream > background > cron。
- 其余小调整:service(base/http/mcp)、file_graph、file_catalog、as_llm、as_embedding、tokenizer、prompt_handler、base_component 的签名/接口微调。

### 8. Application 生命周期
- `_start()` 启动顺序明确为 components → base → stream → background → cron,启动失败会触发 `_close()` 回滚并 re-raise(不再吞异常)。
- 启动时创建 `session_dir` 目录;新增 `update_component()`(按类型/名就地更新已存在组件,不存在则报错)。

### 9. File IO / 路径安全
- **`_path.py`**:`resolve_path` 增加 vault 越界防护(`is_relative_to` 校验),禁止 `.` / `..` 路径分量,支持 `allow_empty`。
- **`read.py`**:大文件(超过 `MAX_FILE_READ_BYTES`)走按行读取 `read_file_lines_safe`,避免一次性载入内存。
- **`_file_io.py` / `_daily_index.py` / `_path.py`** 等支持函数补齐(如 `refresh_day_index`、`read_file_lines_safe`)。
- **`env_utils.py`**:新增 `parse_env_file()`,`load_env()` 返回加载到的键值、支持 `override`、对无路径调用做幂等缓存。

### 10. Config
- `ApplicationConfig` 新增 `session_dir`(默认 `reme_session`)。
- `config_parser.py`:环境变量展开后做类型转换(`_convert_value`)、dot-notation 与 key=value 参数校验更严格、配置文件路径支持相对 `_CONFIG_DIR` 查找、根非 dict 报错。
- `default.yaml`:作业编排改用 `init_changes_step` + `dispatch_steps`(index/resource/digest 三个 watch loop 与 reindex);新增 `auto_dream`(4 步)、`proactive` 作业,移除旧 `dream`;file_catalog 增配 `resource` / `digest` / `dream` 实例;LLM 默认值与 Claude Code 凭据配置调整(tool_result_limit 50000、thinking_enable=false 等)。

### 11. 其它
- 新增 `steps/common/add.py`(`AddStep` 算术 demo)、`channel/__init__.py` 与 common `__init__` 导出整理。
- 新增 4 篇文档:`docs4/auto_dream_logic_and_step_refactor.md`、`docs4/watch_loop_step_refactor_plan.md`、`docs4/todo.md`,以及 `reme_design.md` 更新。
**
2026-06-19 01:35:31 +08:00

252 lines
11 KiB
Python

"""Main application entry point."""
import asyncio
import heapq
from concurrent.futures import ThreadPoolExecutor
from pathlib import Path
from typing import AsyncGenerator, TypeVar
from .components import BaseComponent, ApplicationContext
from .components.job import BackgroundJob, BaseJob, CronJob, StreamJob
from .components.service import BaseService
from .enumeration import ComponentEnum
from .schema import ComponentConfig, Response, StreamChunk
from .utils import execute_stream_task, print_logo, get_logger
T = TypeVar("T", bound=BaseComponent)
_NodeKey = tuple[ComponentEnum, str]
class Application(BaseComponent):
"""Wires components from config and runs jobs against them."""
def __init__(self, **kwargs) -> None:
self.context = ApplicationContext(**kwargs)
self._started_components: list[BaseComponent] = []
self._setup_vault_directories()
if self.config.enable_logo:
print_logo(self.config)
logger = get_logger(log_to_console=self.config.log_to_console, log_to_file=self.config.log_to_file)
logger.info(f"Initializing {self.config.app_name} Application")
super().__init__()
self._init_service()
self._init_components()
self._init_jobs()
@property
def config(self):
"""Typed view onto the application config held by the context."""
return self.context.app_config
# ----- Wiring (called once during __init__) --------------------------
def _setup_vault_directories(self) -> None:
"""Ensure the vault root and configured subdirectories exist on disk."""
cfg = self.config
vault_path = Path(cfg.vault_dir).absolute()
vault_path.mkdir(parents=True, exist_ok=True)
for subdir in [cfg.metadata_dir, cfg.session_dir, cfg.resource_dir, cfg.daily_dir, cfg.digest_dir]:
if subdir:
(vault_path / subdir).mkdir(parents=True, exist_ok=True)
def _init_service(self) -> None:
"""Instantiate the single service backend declared in config.service."""
self.context.service = self._instantiate(
ComponentEnum.SERVICE,
self.config.service,
label="Service",
expected_type=BaseService,
)
def _init_components(self) -> None:
"""Instantiate every component declared under config.components."""
for ctype, group in self.config.components.items():
self.context.components[ctype] = {}
for name, cfg in group.items():
self.context.components[ctype][name] = self._instantiate(
ctype,
cfg,
label=f"Component '{name}'",
expected_type=BaseComponent,
name=name,
)
def _init_jobs(self) -> None:
"""Instantiate every job declared under config.jobs."""
for name, cfg in self.config.jobs.items():
self.context.jobs[name] = self._instantiate(
ComponentEnum.JOB,
cfg,
label=f"Job '{name}'",
expected_type=BaseJob,
name=name,
)
def _instantiate(
self,
ctype: ComponentEnum,
cfg: ComponentConfig,
*,
label: str,
expected_type: type[T],
name: str | None = None,
) -> T:
"""Resolve cfg.backend through the registry and construct the instance.
`label` is the human-readable identifier used only in error messages.
`expected_type` narrows the return type and guards against a backend
registered under the wrong ComponentEnum.
`name` is forwarded to the constructor for named components/jobs;
leave it None for the service, which is keyed solely by type.
"""
# Lazy import: the registry self-populates as component modules load.
from .components import R
if not cfg.backend:
raise ValueError(f"{label} is missing the required 'backend' field")
backend_cls = R.get(ctype, cfg.backend)
if backend_cls is None:
raise ValueError(f"Unregistered backend '{cfg.backend}' for {label}")
params = cfg.model_dump()
params["app_context"] = self.context
if name is not None:
params.setdefault("name", name)
instance = backend_cls(**params)
if not isinstance(instance, expected_type):
got, want = type(instance).__name__, expected_type.__name__
raise TypeError(f"{label} backend '{cfg.backend}' produced {got}, expected {want} subclass")
return instance
# ----- Dependency ordering ------------------------------------------
def _topological_order(self) -> list[BaseComponent]:
"""Return components in dependency order via Kahn's algorithm; raise on missing dep or cycle."""
nodes: dict[_NodeKey, BaseComponent] = {
(ctype, name): comp for ctype, group in self.context.components.items() for name, comp in group.items()
}
in_degree, dependents = self._build_dependency_graph(nodes)
ready = [k for k, d in in_degree.items() if d == 0]
heapq.heapify(ready)
ordered: list[BaseComponent] = []
while ready:
key = heapq.heappop(ready)
ordered.append(nodes[key])
for downstream in dependents[key]:
in_degree[downstream] -= 1
if in_degree[downstream] == 0:
heapq.heappush(ready, downstream)
if len(ordered) != len(nodes):
unresolved = [f"{k[0].value}:{k[1]}" for k, d in in_degree.items() if d > 0]
raise ValueError(f"Circular dependency detected among: {unresolved}")
return ordered
@staticmethod
def _build_dependency_graph(
nodes: dict[_NodeKey, BaseComponent],
) -> tuple[dict[_NodeKey, int], dict[_NodeKey, list[_NodeKey]]]:
"""Compute in-degree and adjacency lists; raise if a required dep is missing."""
in_degree: dict[_NodeKey, int] = dict.fromkeys(nodes, 0)
dependents: dict[_NodeKey, list[_NodeKey]] = {k: [] for k in nodes}
for key, comp in nodes.items():
for dep in comp.dependencies:
dep_key = (dep.ctype, dep.name)
if dep_key in nodes:
dependents[dep_key].append(key)
in_degree[key] += 1
elif not dep.optional:
raise ValueError(
f"Component {key[0].value}:{key[1]} depends on unregistered {dep.ctype.value}:{dep.name}",
)
return in_degree, dependents
# ----- Lifecycle -----------------------------------------------------
async def _start(self) -> None:
"""Start components, then jobs as base > stream > background > cron."""
pool_size = self.config.thread_pool_max_workers
if pool_size > 0:
self.context.thread_pool = ThreadPoolExecutor(max_workers=pool_size)
self.logger.info(f"Thread pool created with max_workers={pool_size}")
try:
components = self._topological_order()
jobs = list(self.context.jobs.values())
base_jobs = [j for j in jobs if not isinstance(j, (StreamJob, BackgroundJob))]
stream_jobs = [j for j in jobs if isinstance(j, StreamJob)]
background_jobs = [j for j in jobs if isinstance(j, BackgroundJob) and not isinstance(j, CronJob)]
cron_jobs = [j for j in jobs if isinstance(j, CronJob)]
for c in components + base_jobs + stream_jobs + background_jobs + cron_jobs:
await self._start_one(c)
except Exception:
await self._close()
raise
async def _start_one(self, c: BaseComponent) -> None:
"""Start one component and record it for ordered shutdown."""
try:
if isinstance(c, BackgroundJob):
self.logger.info(f"Starting background job: {c.name}")
await c.start()
self._started_components.append(c)
except Exception as e:
self.logger.exception(f"Failed to start {c.component_type.value}:{c.name}: {e}")
raise
async def _close(self) -> None:
"""Close in reverse start order so every peer outlives its dependents."""
for c in reversed(self._started_components):
try:
await c.close()
except Exception as e:
self.logger.exception(f"Failed to close {c.component_type.value}:{c.name}: {e}")
self._started_components.clear()
if self.context.thread_pool is not None:
self.context.thread_pool.shutdown(wait=True)
self.context.thread_pool = None
# ----- Job execution -------------------------------------------------
async def run_job(self, name: str, /, **kwargs) -> Response:
"""Execute a registered job by name and return its final Response."""
if name not in self.context.jobs:
raise KeyError(f"Job '{name}' not found")
return await self.context.jobs[name](**kwargs)
async def update_component(self, component_enum: ComponentEnum | str, name: str, /, **kwargs) -> BaseComponent:
"""Update an existing component by type/name; never creates missing components."""
component_enum = ComponentEnum(component_enum)
group = self.context.components.get(component_enum)
if not group or name not in group:
raise KeyError(f"Component '{name}' not found in {component_enum.value}")
component = group[name]
for key, value in kwargs.items():
if not hasattr(component, key):
raise AttributeError(f"Component {component_enum.value}:{name} has no attribute '{key}'")
setattr(component, key, value)
return component
async def run_stream_job(self, name: str, /, **kwargs) -> AsyncGenerator[StreamChunk, None]:
"""Execute a streaming job, yielding chunks as they are produced."""
if name not in self.context.jobs:
raise KeyError(f"Job '{name}' not found")
stream_queue: asyncio.Queue = asyncio.Queue()
task = asyncio.create_task(self.context.jobs[name](stream_queue=stream_queue, **kwargs))
async for chunk in execute_stream_task(
stream_queue=stream_queue,
task=task,
task_name=name,
output_format="chunk",
):
assert isinstance(chunk, StreamChunk)
yield chunk
def run_app(self):
"""Serve the application through the configured service backend."""
assert isinstance(self.context.service, BaseService)
self.context.service.run_app(app=self)