cleanup: убрать мёртвые env-переменные, консолидировать чтение в agent/_config.py

Удалены из кода: - JWT_SECRET — мёртвая (decode_token использует AUTH_SECRET_KEY) - SESSION_SECRET_KEY — заменён на прямой AUTH_SECRET_KEY - POSTGRES_URL — deprecated fallback, удалён из database.py и reencrypt.py Консолидировано чтение env-переменных agent-модуля: - Создан agent/_config.py — единый модуль для FASTAPI_URL, SERVICE_JWT, GRADIO_*, STORAGE_ROOT, AGENT_* (9 констант) - Все agent/*.py импортируют из _config вместо разрозненных os.getenv Удалены or-дефолты (безопасность): - agent/langgraph_setup.py — удалён hardcoded DB URL postgres:postgres - agent/langgraph_setup.py — удалены fallback API URL и model name - scripts/reencrypt.py — удалён hardcoded DB URL postgres:postgres - plugins/llm_analysis/service.py — удалены or-дефолты URL/app name .env.example — минимализация: - backend/.env.example: только 4 обязательные переменные - root/.env.example: обязательные + docker + SSO/админ Обновлены тесты (139 passed)
2026-07-04 14:58:43 +03:00
parent a99c1d6d01
commit ec9bc76a37
16 changed files with 163 additions and 179 deletions
--- a/backend/src/agent/_config.py
+++ b/backend/src/agent/_config.py
@@ -0,0 +1,30 @@
+# backend/src/agent/_config.py
+# #region AgentChat.Config [C:2] [TYPE Module] [SEMANTICS agent-chat,config,env]
+# @ingroup AgentChat
+# @BRIEF Centralized env-var reads for agent services. Read once, import everywhere.
+# @RATIONALE FASTAPI_URL, SERVICE_JWT, GRADIO_* were read from os.getenv in 4+
+#            separate files. Consolidating here eliminates redundant env-reads and
+#            ensures consistent defaults across the agent module.
+import os
+
+# ── FastAPI backend URL ──────────────────────────────────────────
+FASTAPI_URL: str = os.getenv("FASTAPI_URL", "http://localhost:8000")
+
+# ── Service-to-service JWT (agent → FastAPI auth) ────────────────
+SERVICE_JWT: str = os.getenv("SERVICE_JWT", "")
+
+# ── Gradio server ────────────────────────────────────────────────
+GRADIO_SERVER_NAME: str = os.getenv("GRADIO_SERVER_NAME", "0.0.0.0")
+GRADIO_SERVER_PORT: int = int(os.getenv("GRADIO_SERVER_PORT", "7860"))
+GRADIO_ALLOW_PORT_FALLBACK: bool = os.getenv("GRADIO_ALLOW_PORT_FALLBACK", "").strip().lower() in {"1", "true", "yes"}
+
+# ── File storage ─────────────────────────────────────────────────
+STORAGE_ROOT: str = os.getenv("STORAGE_ROOT", "/app/storage")
+
+# ── Prefetch ─────────────────────────────────────────────────────
+AGENT_PREFETCH_DASHBOARD_LIMIT: int = int(os.getenv("AGENT_PREFETCH_DASHBOARD_LIMIT", "25"))
+
+# ── HITL (Human-in-the-Loop) ────────────────────────────────────
+AGENT_CONFIRM_TOOLS: bool = os.getenv("AGENT_CONFIRM_TOOLS", "").strip().lower() in ("true", "1", "yes")
+AGENT_INTERRUPT_BEFORE: str = os.getenv("AGENT_INTERRUPT_BEFORE", "")
+# #endregion AgentChat.Config
--- a/backend/src/agent/_persistence.py
+++ b/backend/src/agent/_persistence.py
@@ -15,9 +15,10 @@ from typing import Any

 import httpx

+from src.agent._config import FASTAPI_URL, SERVICE_JWT as _SERVICE_JWT, AGENT_PREFETCH_DASHBOARD_LIMIT as _PREFETCH_LIMIT
 from src.core.logger import logger

-SAVE_API_URL = os.getenv("FASTAPI_URL", "http://localhost:8000") + "/api/agent/conversations/save"
+SAVE_API_URL = FASTAPI_URL + "/api/agent/conversations/save"
 TITLE_MAX_LENGTH = 80

 # ── Rule-based title cleaning ────────────────────────────────────
@@ -254,10 +255,9 @@ async def generate_llm_title(conv_id: str, user_text: str) -> None:

        # Patch the title via the same save endpoint
        try:
-            service_token = os.getenv("SERVICE_JWT", "")
            headers = {"Content-Type": "application/json"}
-            if service_token:
-                headers["Authorization"] = f"Bearer {service_token}"
+            if _SERVICE_JWT:
+                headers["Authorization"] = f"Bearer {_SERVICE_JWT}"
            payload = {
                "conversation_id": conv_id,
                "title": title,
@@ -308,7 +308,7 @@ async def prefetch_dashboards(env_id: str) -> str:
            dashboards = data.get("dashboards", [])
            if not dashboards:
                return "No dashboards found."
-            limit = int(os.getenv("AGENT_PREFETCH_DASHBOARD_LIMIT", "25"))
+            limit = _PREFETCH_LIMIT
            total = len(dashboards)
            lines = []
            for db in dashboards[:limit]:
@@ -345,10 +345,9 @@ async def prefetch_dashboards(env_id: str) -> str:
 # @REJECTED Requiring explicit authentication for Gradio was rejected — the agent is designed for internal-network use where the auth proxy handles auth; adding a separate auth layer would create unnecessary friction and duplicate the proxy's responsibility.
 async def save_conversation(conv_id: str, user_text: str, user_id: str = "admin", assistant_text: str = "") -> None:
    try:
-        service_token = os.getenv("SERVICE_JWT", "")
        headers = {"Content-Type": "application/json"}
-        if service_token:
-            headers["Authorization"] = f"Bearer {service_token}"
+        if _SERVICE_JWT:
+            headers["Authorization"] = f"Bearer {_SERVICE_JWT}"

        # Normalize user_id: anonymous Gradio sessions use "anon_" prefix
        if not user_id or user_id.startswith("anon_"):
--- a/backend/src/agent/app.py
+++ b/backend/src/agent/app.py
@@ -1,7 +1,7 @@
 # backend/src/agent/app.py
 # #region AgentChat.GradioApp [C:4] [TYPE Module] [SEMANTICS agent-chat,gradio,app]
 # @defgroup AgentChat Gradio ChatInterface wrapping LangGraph agent. Streaming via submit(), HITL via interrupt().
-# @PRE JWT_SECRET env var set. Shared with FastAPI for stateless validation.
+# @PRE AUTH_SECRET_KEY env var set. Shared with FastAPI for stateless validation.
 # @POST Agent streams tokens via Gradio yield; audit logged via LoggingMiddleware.
 # @SIDE_EFFECT Calls LLM, invokes tools via FastAPI REST, writes checkpoints to PostgreSQL.
 # @RELATION DEPENDS_ON -> [AgentChat.Document.Parser]
@@ -23,6 +23,8 @@ import time
 from typing import Any
 import uuid

+from src.agent._config import GRADIO_SERVER_NAME, GRADIO_SERVER_PORT, STORAGE_ROOT as _STORAGE_ROOT
+
 import gradio as gr
 import httpx
 from jose import JWTError
@@ -52,7 +54,6 @@ from src.core.auth.jwt import decode_token
 from src.core.cot_logger import seed_trace_id
 from src.core.logger import logger

-JWT_SECRET = os.environ["JWT_SECRET"]  # @INVARIANT JWT_SECRET must be set in environment — crash-early, no default fallback
 MAX_FILE_SIZE_BYTES = 10 * 1024 * 1024  # 10 MB


@@ -106,7 +107,7 @@ _LLM_LAST_ERROR_TS_KEY = "last_llm_error_ts"
 # @SIDE_EFFECT Writes file to local storage directory.
 def _persist_chat_file(file_path: str, conv_id: str) -> str | None:
    """Copy uploaded file to chat_uploads storage, return relative path for download."""
-    storage_root = os.getenv("STORAGE_ROOT", "/app/storage")
+    storage_root = _STORAGE_ROOT

    if not os.path.isabs(storage_root):
        storage_root = os.path.join(os.getcwd(), storage_root)
@@ -571,7 +572,7 @@ async def health():
 if __name__ == "__main__":
    demo = create_chat_interface()
    demo.launch(
-        server_name=os.getenv("GRADIO_SERVER_NAME", "0.0.0.0"),
-        server_port=int(os.getenv("GRADIO_SERVER_PORT", "7860")),
+        server_name=GRADIO_SERVER_NAME,
+        server_port=GRADIO_SERVER_PORT,
    )
 # #endregion AgentChat.GradioApp
--- a/backend/src/agent/langgraph_setup.py
+++ b/backend/src/agent/langgraph_setup.py
@@ -1,7 +1,7 @@
 # backend/src/agent/langgraph_setup.py
 # #region AgentChat.LangGraph.Setup [C:4] [TYPE Module] [SEMANTICS agent-chat,langgraph,agent]
 # @defgroup AgentChat LangGraph agent setup: create_react_agent with PostgresSaver.
-# @PRE LLM provider configured. Priority: 1) llm_config param 2) env vars LLM_API_KEY/LLM_BASE_URL/LLM_MODEL.
+# @PRE LLM provider configured via backend API /api/agent/llm-config.
 # @POST Compiled StateGraph ready for astream_events().
 # @SIDE_EFFECT Initializes checkpointer and message history tables on first call.
 # @RELATION DEPENDS_ON -> [AgentChat.Tools]
@@ -20,6 +20,7 @@ from langgraph.checkpoint.postgres.aio import AsyncPostgresSaver
 from langgraph.prebuilt import create_react_agent
 from psycopg.rows import dict_row

+from src.agent._config import FASTAPI_URL, AGENT_CONFIRM_TOOLS, AGENT_INTERRUPT_BEFORE as _INTERRUPT_BEFORE
 from src.core.logger import logger

 # ── Monkey-patch: OpenAI SDK for Pydantic BaseModel classes ──
@@ -79,7 +80,7 @@ async def init_checkpointer() -> None:
    global _CHECKPOINTER, _CHECKPOINTER_INIT, _CHECKPOINTER_CONN
    if _CHECKPOINTER_INIT:
        return
-    db_url = os.getenv("DATABASE_URL", "postgresql+psycopg2://postgres:postgres@localhost:5432/ss_tools")
+    db_url = os.getenv("DATABASE_URL")
    # Convert SQLAlchemy-style URL to psycopg format
    pg_url = db_url.replace("postgresql+psycopg2://", "postgres://").replace("postgresql://", "postgres://")
    _CHECKPOINTER_CONN = await psycopg.AsyncConnection.connect(pg_url, autocommit=True, row_factory=dict_row)
@@ -101,11 +102,11 @@ async def _fetch_llm_config() -> dict | None:
    """Fetch LLM config from FastAPI.

    Called on every create_agent() to pick up Admin UI changes immediately.
-    Falls back to cached config or env vars on failure.
+    Falls back to cached config if fetch fails.
    """
    global _llm_config
    try:
-        fastapi_url = os.getenv("FASTAPI_URL", "http://localhost:8000")
+        fastapi_url = FASTAPI_URL
        async with httpx.AsyncClient(timeout=5) as client:
            resp = await client.get(f"{fastapi_url}/api/agent/llm-config")
            if resp.status_code == 200:
@@ -121,9 +122,9 @@ async def _fetch_llm_config() -> dict | None:

 def _interrupt_before_from_env() -> list[str]:
    """Return LangGraph node names that must pause for HITL confirmation."""
-    if (os.getenv("AGENT_CONFIRM_TOOLS", "") or "").strip().lower() in ("true", "1", "yes"):
+    if AGENT_CONFIRM_TOOLS:
        return ["tools"]
-    raw = os.getenv("AGENT_INTERRUPT_BEFORE", "") or ""
+    raw = _INTERRUPT_BEFORE
    if not raw:
        return []
    return [name.strip() for name in raw.split(",") if name.strip()]
@@ -136,10 +137,9 @@ async def create_agent(
 ):
    """Create the LangGraph agent with PostgreSQL checkpointer and message history.

-    LLM configuration priority:
-        1. llm_config from FastAPI /api/agent/llm-config (fetched on every call)
-        2. Environment vars: LLM_API_KEY, LLM_BASE_URL, LLM_MODEL
-        3. Defaults: gpt-4o, https://api.openai.com/v1
+    LLM configuration source:
+        llm_config from FastAPI /api/agent/llm-config (fetched on every call).
+        If backend has no configured provider, agent raises an error.

    Returns a compiled StateGraph ready for astream_events().
    interrupt_before is set from AGENT_CONFIRM_TOOLS (or AGENT_INTERRUPT_BEFORE env var)
@@ -152,19 +152,13 @@ async def create_agent(

    if config and config.get("configured"):
        api_key = config["api_key"]
-        base_url = config.get("base_url") or "https://api.openai.com/v1"
-        model = config.get("default_model") or "gpt-4o-mini"
+        base_url = config.get("base_url")
+        model = config.get("default_model")
        config_source = "FastAPI"
    else:
-        api_key = os.getenv("LLM_API_KEY")
-        base_url = os.getenv("LLM_BASE_URL", "https://api.openai.com/v1")
-        model = os.getenv("LLM_MODEL", "gpt-4o")
-        config_source = "env vars"
-        logger.explore(
-            "LLM config not found in FastAPI, falling back to env vars",
-            payload={"model": model, "provider_type": config.get("provider_type") if config else None},
-            error="No configured LLM provider in FastAPI",
-            extra={"src": "AgentChat.LangGraph.Setup"},
+        raise RuntimeError(
+            "No LLM provider configured in backend. "
+            "Configure one via Settings → AI Providers in the web UI."
        )

    logger.reason(
--- a/backend/src/agent/run.py
+++ b/backend/src/agent/run.py
@@ -8,15 +8,13 @@
 # @RATIONALE Gradio port must match the frontend proxy target. Optional fallback is available only
 #            when GRADIO_ALLOW_PORT_FALLBACK=true and an external proxy is updated separately.
 # @REJECTED Hardcoding the port was rejected — it must be configurable for different deployment environments.
-import os
 import socket
 import httpx

+from src.agent._config import FASTAPI_URL, SERVICE_JWT, GRADIO_SERVER_NAME, GRADIO_SERVER_PORT, GRADIO_ALLOW_PORT_FALLBACK
 from src.core.cot_logger import seed_trace_id
 from src.core.logger import logger

-FASTAPI_URL = os.getenv("FASTAPI_URL", "http://localhost:8000")
-

 def _find_free_port(start_port: int, max_attempts: int = 100) -> int:
    """Find a free TCP port starting from start_port, scanning up to max_attempts ports."""
@@ -37,7 +35,7 @@ def _fetch_llm_config() -> dict | None:
    Falls back to env vars if FastAPI is unreachable or returns no active provider.
    """
    import time
-    service_token = os.getenv("SERVICE_JWT", "")
+    service_token = SERVICE_JWT
    headers = {"Authorization": f"Bearer {service_token}"} if service_token else {}

    for attempt in range(6):
@@ -89,9 +87,8 @@ if __name__ == "__main__":
    seed_trace_id()  # Seed trace for agent startup lifecycle

    # Propagate SERVICE_JWT to ContextVar for tool calls
-    service_token = os.getenv("SERVICE_JWT", "")
-    if service_token:
-        set_service_jwt(service_token)
+    if SERVICE_JWT:
+        set_service_jwt(SERVICE_JWT)

    # Fetch LLM config from FastAPI at startup
    llm_config = _fetch_llm_config()
@@ -102,8 +99,8 @@ if __name__ == "__main__":
    asyncio.run(init_checkpointer())

    # Bind the configured port. Falling back silently breaks the Vite/nginx proxy target.
-    configured_port = int(os.getenv("GRADIO_SERVER_PORT", "7860"))
-    allow_port_fallback = os.getenv("GRADIO_ALLOW_PORT_FALLBACK", "").strip().lower() in {"1", "true", "yes"}
+    configured_port = GRADIO_SERVER_PORT
+    allow_port_fallback = GRADIO_ALLOW_PORT_FALLBACK
    if allow_port_fallback:
        try:
            port = _find_free_port(configured_port)
@@ -127,7 +124,7 @@ if __name__ == "__main__":
    demo = create_chat_interface()

    demo.launch(
-        server_name=os.getenv("GRADIO_SERVER_NAME", "0.0.0.0"),
+        server_name=GRADIO_SERVER_NAME,
        server_port=port,
    )
 # #endregion AgentChat.Run
--- a/backend/src/agent/tools.py
+++ b/backend/src/agent/tools.py
@@ -13,10 +13,10 @@ import httpx
 from langchain_core.tools import tool
 from pydantic import BaseModel, Field

+from src.agent._config import FASTAPI_URL, SERVICE_JWT as _SERVICE_JWT
 from src.agent.context import get_service_jwt, get_user_jwt
 from src.core.logger import logger

-FASTAPI_URL = os.getenv("FASTAPI_URL", "http://localhost:8000")
 TOOL_RESPONSE_LIMIT = 4000

 # ── Internal helpers ─────────────────────────────────────────────
@@ -26,7 +26,7 @@ TOOL_RESPONSE_LIMIT = 4000
 # @BRIEF Build dual-identity auth headers for tool→FastAPI calls per FR-007/FR-019.
 def _dual_auth_headers() -> dict[str, str]:
    user_jwt = get_user_jwt() or ""
-    svc_jwt = get_service_jwt() or os.getenv("SERVICE_JWT", "")
+    svc_jwt = get_service_jwt() or _SERVICE_JWT
    headers = {}
    if svc_jwt:
        headers["Authorization"] = f"Bearer {svc_jwt}"
--- a/backend/src/app.py
+++ b/backend/src/app.py
@@ -244,16 +244,10 @@ def run_alembic_migrations() -> None:
 # @REJECTED SessionMiddleware sharing JWT SECRET_KEY rejected in [SEC:H-4] — key reuse expands blast radius.

 # Configure Session Middleware (required by Authlib for OAuth2 flow)
+# Uses AUTH_SECRET_KEY directly — separate SESSION_SECRET_KEY eliminated.
 from .core.auth.config import auth_config

-_session_secret = os.getenv("SESSION_SECRET_KEY", "").strip()
-if not _session_secret:
-    _session_secret = auth_config.SECRET_KEY
-    logger.explore(
-        "SESSION_SECRET_KEY not set — falling back to AUTH_SECRET_KEY",
-        error="Missing SESSION_SECRET_KEY",
-    )
-app.add_middleware(SessionMiddleware, secret_key=_session_secret)
+app.add_middleware(SessionMiddleware, secret_key=auth_config.SECRET_KEY)

 # Configure CORS
 _allowed_origins_raw = os.getenv("ALLOWED_ORIGINS", "").strip()
--- a/backend/src/core/database.py
+++ b/backend/src/core/database.py
@@ -38,15 +38,15 @@ BASE_DIR = Path(__file__).resolve().parent.parent.parent

 # #region DATABASE_URL [C:1] [TYPE Constant]
 # @BRIEF URL for the main application database. Read from env; crashes if unset.
-# @RATIONALE DATABASE_URL reads from env (DATABASE_URL or POSTGRES_URL).
-#            Crashes at import if unset. DEV_MODE fallback removed in [SEC:C-4].
+# @RATIONALE DATABASE_URL is required. POSTGRES_URL removed — use only DATABASE_URL.
+#            Crashes at import if unset.
 # @REJECTED Hardcoded postgres:postgres@localhost in source code rejected — exposes
 #           database credentials in version control (Class 1 security violation).
 #           DEV_MODE fallback removed — same violation via env toggle.
-DATABASE_URL = os.getenv("DATABASE_URL") or os.getenv("POSTGRES_URL")
+DATABASE_URL = os.getenv("DATABASE_URL")
 if not DATABASE_URL:
    raise RuntimeError(
-        "DATABASE_URL (or POSTGRES_URL) environment variable is required. "
+        "DATABASE_URL environment variable is required. "
        "Set it before starting the server. "
        "For local development, create a .env file or use docker-compose.yml."
    )
--- a/backend/src/plugins/llm_analysis/service.py
+++ b/backend/src/plugins/llm_analysis/service.py
@@ -889,9 +889,8 @@ class LLMClient:
            default_headers["HTTP-Referer"] = (
                os.getenv("OPENROUTER_SITE_URL", "").strip()
                or os.getenv("APP_BASE_URL", "").strip()
-                or "http://localhost:8000"
            )
-            default_headers["X-Title"] = os.getenv("OPENROUTER_APP_NAME", "").strip() or "superset-tools"
+            default_headers["X-Title"] = os.getenv("OPENROUTER_APP_NAME", "").strip() or ""
        if self.provider_type == LLMProviderType.KILO:
            default_headers["Authentication"] = f"Bearer {self.api_key}"
            default_headers["X-API-Key"] = self.api_key
--- a/backend/src/scripts/reencrypt.py
+++ b/backend/src/scripts/reencrypt.py
@@ -131,11 +131,7 @@ def main() -> None:
    _r("")

    # ── Load database URL ──────────────────────────────────────────
-    db_url = (
-        os.getenv("DATABASE_URL", "")
-        or os.getenv("POSTGRES_URL", "")
-        or "postgresql+psycopg2://postgres:postgres@localhost:5432/ss_tools"
-    )
+    db_url = os.getenv("DATABASE_URL", "")
    # Use psycopg2 for sync access in script
    engine = create_engine(db_url)