mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-10-20 05:42:20 +02:00
Merge branch 'dev' into fix/add-directory-event-loop
This commit is contained in:
+53
-1
@@ -345,9 +345,61 @@ def setup_auth_routes(auth_manager: AuthManager) -> APIRouter:
|
||||
# docs, email accounts, tasks, etc.
|
||||
try:
|
||||
from sqlalchemy import func
|
||||
from core.database import Base, SessionLocal
|
||||
from core.database import (
|
||||
Base,
|
||||
EmailAccount,
|
||||
SessionLocal,
|
||||
lock_email_account_owner_mutations,
|
||||
)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
# Email-account defaults are protected by per-owner mutex rows.
|
||||
# A rename crosses two owner partitions, so lock both in the
|
||||
# shared helper's canonical order before inspecting either.
|
||||
lock_email_account_owner_mutations(
|
||||
db, old_username, new_username
|
||||
)
|
||||
|
||||
source_default_ids = [
|
||||
row[0]
|
||||
for row in (
|
||||
db.query(EmailAccount.id)
|
||||
.filter(
|
||||
func.lower(EmailAccount.owner) == old_username,
|
||||
EmailAccount.is_default == True, # noqa: E712
|
||||
)
|
||||
.order_by(EmailAccount.created_at.asc(), EmailAccount.id.asc())
|
||||
.all()
|
||||
)
|
||||
]
|
||||
destination_default_ids = [
|
||||
row[0]
|
||||
for row in (
|
||||
db.query(EmailAccount.id)
|
||||
.filter(
|
||||
func.lower(EmailAccount.owner) == new_username,
|
||||
EmailAccount.is_default == True, # noqa: E712
|
||||
)
|
||||
.order_by(EmailAccount.created_at.asc(), EmailAccount.id.asc())
|
||||
.all()
|
||||
)
|
||||
]
|
||||
if destination_default_ids:
|
||||
clear_default_ids = (
|
||||
destination_default_ids[1:] + source_default_ids
|
||||
)
|
||||
else:
|
||||
clear_default_ids = source_default_ids[1:]
|
||||
if clear_default_ids:
|
||||
(
|
||||
db.query(EmailAccount)
|
||||
.filter(EmailAccount.id.in_(clear_default_ids))
|
||||
.update(
|
||||
{EmailAccount.is_default: False},
|
||||
synchronize_session=False,
|
||||
)
|
||||
)
|
||||
|
||||
for mapper in Base.registry.mappers:
|
||||
model = mapper.class_
|
||||
if not hasattr(model, "owner"):
|
||||
|
||||
+10
-1
@@ -6,6 +6,7 @@ from datetime import datetime
|
||||
|
||||
from fastapi import APIRouter, HTTPException, Request, Response
|
||||
from core.middleware import require_admin
|
||||
from services.memory import MemoryStoreUnreadable
|
||||
from src.auth_helpers import get_current_user
|
||||
from src.settings import load_settings, save_settings, load_features, save_features
|
||||
|
||||
@@ -76,7 +77,15 @@ def setup_backup_routes(memory_manager, preset_manager, skills_manager) -> APIRo
|
||||
|
||||
# ── Memories ──
|
||||
if "memories" in body and isinstance(body["memories"], list):
|
||||
existing = memory_manager.load_all()
|
||||
# Strict load: importing on top of an unreadable store would write
|
||||
# only the incoming rows back and drop everything already saved.
|
||||
try:
|
||||
existing = memory_manager.load_all_for_update()
|
||||
except MemoryStoreUnreadable as e:
|
||||
logger.error("Refusing to import memories: %s", e)
|
||||
raise HTTPException(
|
||||
503, "Memory store is temporarily unreadable — nothing was imported."
|
||||
)
|
||||
# Dedup against THIS user's own memories only. Using every tenant's
|
||||
# rows (load_all) meant a memory whose text matched any other
|
||||
# user's was silently skipped, so the importing user lost their own
|
||||
|
||||
+115
-7
@@ -10,6 +10,7 @@ from typing import Optional, List
|
||||
from fastapi import APIRouter, HTTPException, Request, UploadFile, File
|
||||
from pydantic import BaseModel
|
||||
from sqlalchemy import or_, and_
|
||||
from sqlalchemy.exc import IntegrityError
|
||||
from dateutil.rrule import rrulestr
|
||||
|
||||
from core.database import SessionLocal, CalendarCal, CalendarDeletedEvent, CalendarEvent
|
||||
@@ -221,22 +222,125 @@ class EventUpdate(BaseModel):
|
||||
|
||||
# ── Helpers ──
|
||||
|
||||
_DEFAULT_CALENDAR_NAMESPACE = uuid.UUID("4840613a-9847-4a3b-bd75-19e6bc5fc3ce")
|
||||
|
||||
|
||||
def _default_calendar_id(owner: str, collision_index: int = 0) -> str:
|
||||
"""Return one stable primary-key candidate for an owner's lazy default.
|
||||
|
||||
Slot zero preserves the original owner-derived identifier. Later slots
|
||||
let a username be reused after its prior calendar was migrated to another
|
||||
owner during a rename, without making concurrent first use choose random
|
||||
and therefore divergent identifiers.
|
||||
"""
|
||||
if collision_index == 0:
|
||||
candidate_name = owner
|
||||
else:
|
||||
candidate_name = json.dumps(
|
||||
[owner, collision_index],
|
||||
ensure_ascii=False,
|
||||
separators=(",", ":"),
|
||||
)
|
||||
return str(uuid.uuid5(_DEFAULT_CALENDAR_NAMESPACE, candidate_name))
|
||||
|
||||
|
||||
def _begin_sqlite_default_write(db) -> None:
|
||||
"""Serialize an absent-default check with other SQLite writers.
|
||||
|
||||
SQLite's default deferred transactions allow two workers to both read an
|
||||
empty calendar set before either writes. ``BEGIN IMMEDIATE`` acquires the
|
||||
writer reservation before the second, authoritative lookup. We issue it
|
||||
only when the driver has not already opened a write transaction; a caller
|
||||
with a pending write already owns the required reservation.
|
||||
"""
|
||||
connection = db.connection()
|
||||
dbapi_connection = connection.connection
|
||||
driver_connection = getattr(
|
||||
dbapi_connection,
|
||||
"driver_connection",
|
||||
dbapi_connection,
|
||||
)
|
||||
if not getattr(driver_connection, "in_transaction", False):
|
||||
connection.exec_driver_sql("BEGIN IMMEDIATE")
|
||||
|
||||
|
||||
def _ensure_default_calendar(db, owner: str = None) -> CalendarCal:
|
||||
"""Create default calendar if none exist for this owner."""
|
||||
"""Return the owner's calendar, staging a default in the caller's transaction.
|
||||
|
||||
A stable owner-derived primary key makes concurrent first-use inserts
|
||||
converge on one row on every SQL backend. SQLite additionally serializes
|
||||
the absent-row check because its deferred transactions otherwise permit
|
||||
both workers to read the gap before either writes. Other backends recover
|
||||
a lost insert race inside a savepoint so the caller's event transaction
|
||||
remains usable and atomic.
|
||||
"""
|
||||
owner = owner or FALLBACK_OWNER
|
||||
cal = db.query(CalendarCal).filter(CalendarCal.owner == owner).first()
|
||||
if not cal:
|
||||
if cal:
|
||||
return cal
|
||||
|
||||
dialect = db.get_bind().dialect.name
|
||||
if dialect == "sqlite":
|
||||
_begin_sqlite_default_write(db)
|
||||
# Another worker may have committed while BEGIN IMMEDIATE waited.
|
||||
cal = db.query(CalendarCal).filter(CalendarCal.owner == owner).first()
|
||||
if cal:
|
||||
return cal
|
||||
|
||||
collision_index = 0
|
||||
while True:
|
||||
default_id = _default_calendar_id(owner, collision_index)
|
||||
|
||||
if dialect == "sqlite":
|
||||
# BEGIN IMMEDIATE above makes this occupancy check authoritative:
|
||||
# another SQLite writer cannot rename, delete, or claim this slot
|
||||
# until the caller commits or rolls back.
|
||||
occupant = db.query(CalendarCal).filter(
|
||||
CalendarCal.id == default_id,
|
||||
).first()
|
||||
if occupant is not None:
|
||||
if occupant.owner == owner:
|
||||
return occupant
|
||||
collision_index += 1
|
||||
continue
|
||||
|
||||
cal = CalendarCal(
|
||||
id=str(uuid.uuid4()),
|
||||
id=default_id,
|
||||
owner=owner,
|
||||
name="Personal",
|
||||
color="#5b8abf",
|
||||
source="local",
|
||||
)
|
||||
db.add(cal)
|
||||
db.commit()
|
||||
db.refresh(cal)
|
||||
return cal
|
||||
|
||||
if dialect == "sqlite":
|
||||
db.add(cal)
|
||||
db.flush()
|
||||
return cal
|
||||
|
||||
try:
|
||||
# A uniqueness failure rolls back only this savepoint, not an event
|
||||
# or reminder already staged by the caller's outer transaction.
|
||||
with db.begin_nested():
|
||||
db.add(cal)
|
||||
db.flush()
|
||||
return cal
|
||||
except IntegrityError:
|
||||
# Use a locking/current read so repeatable-read backends can observe
|
||||
# the row that won after our transaction's original empty snapshot.
|
||||
occupant = db.query(CalendarCal).filter(
|
||||
CalendarCal.id == default_id,
|
||||
).with_for_update().first()
|
||||
if occupant is None:
|
||||
# Do not misclassify an unrelated integrity failure as an ID
|
||||
# collision and loop forever. A concurrently deleted winner is
|
||||
# safe for the caller to retry as a fresh transaction.
|
||||
raise
|
||||
if occupant.owner == owner:
|
||||
return occupant
|
||||
# A renamed calendar owns this deterministic slot. Advance to the
|
||||
# next stable slot; concurrent callers for this owner will still
|
||||
# converge there.
|
||||
collision_index += 1
|
||||
|
||||
|
||||
# Per-request user time context. chat_routes sets this from browser timezone
|
||||
@@ -1015,6 +1119,9 @@ def setup_calendar_routes(upload_handler=None) -> APIRouter:
|
||||
db = SessionLocal()
|
||||
try:
|
||||
_ensure_default_calendar(db, owner)
|
||||
# Listing calendars intentionally lazily creates a durable default.
|
||||
# Other callers commit it with the event they are creating.
|
||||
db.commit()
|
||||
cals = db.query(CalendarCal).filter(CalendarCal.owner == owner).all()
|
||||
return {"calendars": [
|
||||
{"name": c.name, "href": c.id, "color": c.color, "source": c.source}
|
||||
@@ -1023,6 +1130,7 @@ def setup_calendar_routes(upload_handler=None) -> APIRouter:
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
db.rollback()
|
||||
logger.error("Failed to list calendars: %s", e)
|
||||
raise HTTPException(500, "Failed to list calendars")
|
||||
finally:
|
||||
|
||||
+11
-11
@@ -21,6 +21,7 @@ from src import agent_runs
|
||||
from src.model_context import estimate_tokens
|
||||
from src.chat_helpers import coerce_message_and_session
|
||||
from src.endpoint_resolver import normalize_base as _normalize_base, build_chat_url
|
||||
from src.foreground_model_routing import build_foreground_model_candidates
|
||||
from src.session_search import search_session_messages
|
||||
from src.prompt_security import untrusted_context_message
|
||||
from core.exceptions import SessionNotFoundError
|
||||
@@ -1399,14 +1400,14 @@ def setup_chat_routes(
|
||||
thinking_response = ""
|
||||
last_metrics = None
|
||||
|
||||
# Configured fallback chain for the default chat model. Tried in
|
||||
# order if the session's primary model fails before producing
|
||||
# output. Resolved once per request.
|
||||
try:
|
||||
from src.endpoint_resolver import resolve_chat_fallback_candidates
|
||||
_fallback_candidates = resolve_chat_fallback_candidates(owner=_user)
|
||||
except Exception:
|
||||
_fallback_candidates = []
|
||||
# Foreground Chat and Agent requests use one owner-aware policy
|
||||
# boundary. Legacy `default_model_fallbacks` data is not eligible.
|
||||
_foreground_candidates = build_foreground_model_candidates(
|
||||
sess.endpoint_url,
|
||||
sess.model,
|
||||
sess.headers,
|
||||
owner=_user,
|
||||
)
|
||||
|
||||
# Send model name early so the frontend can show it during streaming
|
||||
_model_suffix = "Research" if effective_do_research else None
|
||||
@@ -1522,9 +1523,8 @@ def setup_chat_routes(
|
||||
_actual_model = None
|
||||
# ── Chat mode: call stream_llm directly, NO tools, NO document access ──
|
||||
try:
|
||||
_chat_candidates = [(sess.endpoint_url, sess.model, sess.headers)] + _fallback_candidates
|
||||
async for chunk in stream_llm_with_fallback(
|
||||
_chat_candidates,
|
||||
_foreground_candidates,
|
||||
messages,
|
||||
temperature=ctx.preset.temperature,
|
||||
# Respect the preset; 0/unset = let the server decide (no
|
||||
@@ -1710,7 +1710,7 @@ def setup_chat_routes(
|
||||
disabled_tools=disabled_tools if disabled_tools else None,
|
||||
tool_policy=tool_policy,
|
||||
owner=_user,
|
||||
fallbacks=_fallback_candidates,
|
||||
fallbacks=_foreground_candidates[1:],
|
||||
plan_mode=plan_mode,
|
||||
approved_plan=approved_plan or None,
|
||||
workspace=workspace or None,
|
||||
|
||||
@@ -73,6 +73,30 @@ _HF_TOKEN_STATUS_SNIPPET = (
|
||||
)
|
||||
|
||||
|
||||
def _windows_local_pid_record_line(pid_path: Path, ready_path: Path) -> str:
|
||||
"""Build the Git Bash prelude that records a Win32-stoppable PID.
|
||||
|
||||
Python publishes the detached outer process's Win32 PID first, then touches
|
||||
``ready_path``. The inner Git Bash runner waits for that publication before
|
||||
replacing the fallback with its own Win32 PID from /proc/<msys-pid>/winpid.
|
||||
|
||||
Missing, malformed, or late mappings leave the valid outer PID untouched.
|
||||
"""
|
||||
pp = shlex.quote(pid_path.as_posix())
|
||||
rp = shlex.quote(ready_path.as_posix())
|
||||
return (
|
||||
"i=0; "
|
||||
f"while [ ! -e {rp} ] && [ \"$i\" -lt 500 ]; do "
|
||||
"i=$((i+1)); sleep 0.01; done; "
|
||||
f"if [ -e {rp} ]; then "
|
||||
"winpid=\"$(cat /proc/$$/winpid 2>/dev/null || true)\"; "
|
||||
"case \"$winpid\" in ''|*[!0-9]*) ;; "
|
||||
f"*) printf '%s\\n' \"$winpid\" > {pp} ;; esac; "
|
||||
"fi; "
|
||||
f"rm -f {rp}"
|
||||
)
|
||||
|
||||
|
||||
def _append_mlx_image_server_script(runner_lines: list[str]) -> None:
|
||||
"""Write the MLX image API helper next to the tmux runner on remote hosts."""
|
||||
script_path = Path(__file__).resolve().parents[1] / "scripts" / "mlx_image_server.py"
|
||||
@@ -978,15 +1002,18 @@ def setup_cookbook_routes() -> APIRouter:
|
||||
directly (simple commands only). Returns the launched job record."""
|
||||
log_path = TMUX_LOG_DIR / f"{session_id}.log"
|
||||
pid_path = TMUX_LOG_DIR / f"{session_id}.pid"
|
||||
pid_ready_path: Path | None = None
|
||||
bash = find_bash()
|
||||
if bash:
|
||||
# Run the existing bash wrapper verbatim through Git Bash, redirecting
|
||||
# all output to the log the poller reads. Paths handed to bash use
|
||||
# POSIX form + shell-quoting so drive paths / spaces survive.
|
||||
inner = TMUX_LOG_DIR / f"{session_id}_run.sh"
|
||||
pp = shlex.quote(pid_path.as_posix())
|
||||
pid_ready_path = TMUX_LOG_DIR / f"{session_id}.pid.ready"
|
||||
pid_ready_path.unlink(missing_ok=True)
|
||||
inner.write_text(
|
||||
f"printf '%s\\n' \"$$\" > {pp}\n" + "\n".join(bash_lines) + "\n",
|
||||
_windows_local_pid_record_line(pid_path, pid_ready_path) + "\n"
|
||||
+ "\n".join(bash_lines) + "\n",
|
||||
encoding="utf-8",
|
||||
)
|
||||
lp = shlex.quote(log_path.as_posix())
|
||||
@@ -1020,7 +1047,18 @@ def setup_cookbook_routes() -> APIRouter:
|
||||
env=env,
|
||||
**detached_popen_kwargs(),
|
||||
)
|
||||
# Publish a valid Win32 ancestor first. The Git Bash runner may then
|
||||
# replace it with its own Win32 pid, but never before this fallback exists.
|
||||
pid_path.write_text(str(proc.pid), encoding="utf-8")
|
||||
if pid_ready_path is not None:
|
||||
try:
|
||||
pid_ready_path.touch()
|
||||
except OSError as e:
|
||||
logger.warning(
|
||||
"Could not publish Windows local PID handoff for %s: %s",
|
||||
session_id,
|
||||
e,
|
||||
)
|
||||
return {"pid": proc.pid, "log_path": str(log_path)}
|
||||
|
||||
@router.post("/api/model/download")
|
||||
|
||||
@@ -0,0 +1,6 @@
|
||||
"""Document route domain package (slice 2m, #4082/#4071).
|
||||
|
||||
Contains document_routes.py and document_helpers.py, migrated from the flat
|
||||
routes/ directory. Backward-compat shims at routes/document_routes.py and
|
||||
routes/document_helpers.py re-export from here.
|
||||
"""
|
||||
@@ -0,0 +1,243 @@
|
||||
"""document_helpers.py — Pydantic models, doc serializers, owner gating, file-locator helpers shared with document_routes.py."""
|
||||
|
||||
"""Document routes — CRUD for living documents with version history."""
|
||||
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
from fastapi import HTTPException, Request
|
||||
from pydantic import BaseModel
|
||||
|
||||
from core.database import Document, DocumentVersion
|
||||
from core.database import Session as DbSession
|
||||
from src.auth_helpers import _auth_disabled
|
||||
from src.upload_handler import UploadHandler
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
# ---- Request schemas ----
|
||||
|
||||
class DocumentCreate(BaseModel):
|
||||
session_id: Optional[str] = None
|
||||
title: str = "Untitled"
|
||||
language: Optional[str] = None
|
||||
content: str = ""
|
||||
|
||||
class DocumentUpdate(BaseModel):
|
||||
content: str
|
||||
summary: Optional[str] = None
|
||||
force_version: bool = False
|
||||
|
||||
class DocumentPatch(BaseModel):
|
||||
title: Optional[str] = None
|
||||
language: Optional[str] = None
|
||||
session_id: Optional[str] = None # link/unlink document to a session
|
||||
|
||||
|
||||
# ---- Helpers ----
|
||||
|
||||
def _doc_to_dict(doc: Document) -> Dict[str, Any]:
|
||||
return {
|
||||
"id": doc.id,
|
||||
"session_id": doc.session_id,
|
||||
"title": doc.title,
|
||||
"language": doc.language,
|
||||
"current_content": doc.current_content,
|
||||
"version_count": doc.version_count,
|
||||
"is_active": doc.is_active,
|
||||
"archived": bool(getattr(doc, "archived", False)),
|
||||
"created_at": (doc.created_at.isoformat() + "Z") if doc.created_at else None,
|
||||
"updated_at": (doc.updated_at.isoformat() + "Z") if doc.updated_at else None,
|
||||
# Source-email provenance (set when doc was created from an email
|
||||
# attachment) — drives the "Send signed reply" menu item.
|
||||
"source_email_uid": getattr(doc, "source_email_uid", None),
|
||||
"source_email_folder": getattr(doc, "source_email_folder", None),
|
||||
"source_email_account_id": getattr(doc, "source_email_account_id", None),
|
||||
"source_email_message_id": getattr(doc, "source_email_message_id", None),
|
||||
}
|
||||
|
||||
def _version_to_dict(v: DocumentVersion) -> Dict[str, Any]:
|
||||
return {
|
||||
"id": v.id,
|
||||
"document_id": v.document_id,
|
||||
"version_number": v.version_number,
|
||||
"content": v.content,
|
||||
"summary": v.summary,
|
||||
"source": v.source,
|
||||
"created_at": v.created_at.isoformat() if v.created_at else None,
|
||||
}
|
||||
|
||||
|
||||
def _verify_doc_owner(db, doc: Document, user: str):
|
||||
"""Verify `user` owns this document. Raise 404 if not.
|
||||
|
||||
Documents now carry their own `owner` column, so a doc whose session
|
||||
was deleted (session_id → NULL) can still prove ownership and stay
|
||||
openable / cloneable. We trust that column first and only fall back to
|
||||
the session join for any not-yet-backfilled legacy row.
|
||||
"""
|
||||
if user is None:
|
||||
if _auth_disabled():
|
||||
return # Single-user / no-auth mode: allow access
|
||||
raise HTTPException(403, "Authentication required")
|
||||
if doc.owner is not None:
|
||||
if doc.owner != user:
|
||||
raise HTTPException(404, "Document not found")
|
||||
return
|
||||
# Legacy fallback: derive ownership from the linked session.
|
||||
if not doc.session_id:
|
||||
raise HTTPException(404, "Document not found")
|
||||
session = db.query(DbSession).filter(DbSession.id == doc.session_id).first()
|
||||
if not session or session.owner != user:
|
||||
raise HTTPException(404, "Document not found")
|
||||
|
||||
|
||||
def _owner_session_filter(q, user):
|
||||
"""Restrict a documents query to those owned by `user`.
|
||||
|
||||
Documents now carry their own `owner` column (backfilled at boot from
|
||||
the linked session, or assigned to the admin user for legacy/orphaned
|
||||
docs). We filter on that directly rather than on a session join, so a
|
||||
document whose session was deleted (session_id → NULL) still shows up
|
||||
for its owner instead of silently vanishing from the Library + search.
|
||||
|
||||
The owner backfill runs in init_db before the app serves requests, so
|
||||
by the time this filter is live there are no NULL-owner rows to leak;
|
||||
we therefore match the owner strictly for authenticated callers."""
|
||||
if not user:
|
||||
if user == "" or _auth_disabled():
|
||||
return q
|
||||
return q.filter(False)
|
||||
return q.filter(Document.owner == user)
|
||||
|
||||
|
||||
|
||||
def _slug(name: str) -> str:
|
||||
"""Filesystem-friendly version of a document title.
|
||||
|
||||
Whitespace becomes underscores; other unsafe punctuation is dropped.
|
||||
Preserves letters, digits, dot, hyphen, underscore. Idempotent.
|
||||
"""
|
||||
import re as _re
|
||||
s = (name or "").strip()
|
||||
# Drop the trailing extension if the title happens to include one
|
||||
s = _re.sub(r'\.pdf$', '', s, flags=_re.IGNORECASE)
|
||||
s = _re.sub(r'\s+', '_', s)
|
||||
s = _re.sub(r'[^A-Za-z0-9._-]', '', s)
|
||||
s = _re.sub(r'_+', '_', s).strip('_')
|
||||
return s or "form"
|
||||
|
||||
|
||||
# DPI scale for the interactive PDF view. ~150 DPI (2x of 72 PDF user-units).
|
||||
_PDF_RENDER_SCALE = 2.0
|
||||
|
||||
|
||||
def _upload_path_inside(upload_dir: str, path: str) -> bool:
|
||||
base = os.path.realpath(upload_dir)
|
||||
p = os.path.realpath(path)
|
||||
try:
|
||||
return os.path.commonpath([base, p]) == base
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
def _resolve_user_upload_path(
|
||||
upload_handler: Any,
|
||||
upload_id: str,
|
||||
owner: Optional[str],
|
||||
auth_manager=None,
|
||||
) -> Optional[str]:
|
||||
"""Resolve an upload id to a filesystem path the caller may read."""
|
||||
if upload_handler is None:
|
||||
return None
|
||||
resolved = upload_handler.resolve_upload(
|
||||
upload_id,
|
||||
owner=owner,
|
||||
auth_manager=auth_manager,
|
||||
)
|
||||
if not isinstance(resolved, dict) or not resolved:
|
||||
return None
|
||||
path = resolved.get("path")
|
||||
upload_dir = getattr(upload_handler, "upload_dir", None)
|
||||
if path and upload_dir and not _upload_path_inside(upload_dir, path):
|
||||
logger.warning("Upload path outside upload directory: %s", path)
|
||||
return None
|
||||
return path
|
||||
|
||||
|
||||
def _locate_upload(
|
||||
upload_dir: str,
|
||||
file_id: str,
|
||||
owner: Optional[str] = None,
|
||||
auth_manager=None,
|
||||
upload_handler: Any = None,
|
||||
):
|
||||
"""Find an upload by its filename ID via UploadHandler.resolve_upload."""
|
||||
if upload_handler is None:
|
||||
from src.upload_handler import UploadHandler
|
||||
|
||||
base_dir = os.path.dirname(os.path.abspath(upload_dir))
|
||||
upload_handler = UploadHandler(base_dir, upload_dir)
|
||||
return _resolve_user_upload_path(upload_handler, file_id, owner, auth_manager)
|
||||
|
||||
|
||||
def _assert_pdf_marker_upload_owned(
|
||||
request: Request,
|
||||
content: str,
|
||||
user: Optional[str],
|
||||
upload_handler: Any,
|
||||
) -> None:
|
||||
"""Reject document content whose pdf_source marker points at another user's upload."""
|
||||
if upload_handler is None:
|
||||
return
|
||||
from src.pdf_form_doc import find_source_upload_id
|
||||
|
||||
upload_id = find_source_upload_id(content or "")
|
||||
if not upload_id:
|
||||
return
|
||||
auth_manager = getattr(getattr(request.app, "state", None), "auth_manager", None)
|
||||
if not _resolve_user_upload_path(upload_handler, upload_id, user, auth_manager):
|
||||
raise HTTPException(
|
||||
400,
|
||||
"Document PDF marker references an upload you do not own",
|
||||
)
|
||||
|
||||
|
||||
def _derive_title(content: str) -> str:
|
||||
"""Derive a title from document content."""
|
||||
import re
|
||||
if not isinstance(content, str):
|
||||
return "Untitled"
|
||||
text = content.strip()
|
||||
if not text:
|
||||
return "Untitled"
|
||||
|
||||
# Markdown header
|
||||
md = re.match(r'^#{1,3}\s+(.+)', text, re.MULTILINE)
|
||||
if md:
|
||||
title = md.group(1).strip()
|
||||
if len(title) > 50:
|
||||
title = title[:48] + "…"
|
||||
return title
|
||||
|
||||
# HTML heading
|
||||
html = re.search(r'<h[1-3][^>]*>([^<]+)</h[1-3]>', text, re.IGNORECASE)
|
||||
if html:
|
||||
title = html.group(1).strip()
|
||||
if len(title) > 50:
|
||||
title = title[:48] + "…"
|
||||
return title
|
||||
|
||||
# First non-empty line (if short enough)
|
||||
for line in text.split('\n'):
|
||||
line = line.strip()
|
||||
if line and 2 <= len(line) <= 60:
|
||||
title = re.sub(r'[:#*`]+$', '', line).strip()
|
||||
if title and len(title) > 50:
|
||||
title = title[:48] + "…"
|
||||
return title or "Untitled"
|
||||
|
||||
return "Untitled"
|
||||
File diff suppressed because it is too large
Load Diff
+10
-239
@@ -1,243 +1,14 @@
|
||||
"""document_helpers.py — Pydantic models, doc serializers, owner gating, file-locator helpers shared with document_routes.py."""
|
||||
"""Backward-compat shim — canonical location is routes/document/document_helpers.py.
|
||||
|
||||
"""Document routes — CRUD for living documents with version history."""
|
||||
This module is replaced in ``sys.modules`` by the canonical module object so
|
||||
that ``import routes.document_helpers``, ``from routes.document_helpers import
|
||||
X``, and the ``sys.modules.pop("routes.document_helpers")`` + re-import
|
||||
pattern used by test_security_regressions.py all operate on the *same* object.
|
||||
Keeps existing import paths working after slice 2m (#4082/#4071).
|
||||
"""
|
||||
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
from typing import Any, Dict, Optional
|
||||
import sys as _sys
|
||||
|
||||
from fastapi import HTTPException, Request
|
||||
from pydantic import BaseModel
|
||||
from routes.document import document_helpers as _canonical # noqa: F401
|
||||
|
||||
from core.database import Document, DocumentVersion
|
||||
from core.database import Session as DbSession
|
||||
from src.auth_helpers import _auth_disabled
|
||||
from src.upload_handler import UploadHandler
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
# ---- Request schemas ----
|
||||
|
||||
class DocumentCreate(BaseModel):
|
||||
session_id: Optional[str] = None
|
||||
title: str = "Untitled"
|
||||
language: Optional[str] = None
|
||||
content: str = ""
|
||||
|
||||
class DocumentUpdate(BaseModel):
|
||||
content: str
|
||||
summary: Optional[str] = None
|
||||
force_version: bool = False
|
||||
|
||||
class DocumentPatch(BaseModel):
|
||||
title: Optional[str] = None
|
||||
language: Optional[str] = None
|
||||
session_id: Optional[str] = None # link/unlink document to a session
|
||||
|
||||
|
||||
# ---- Helpers ----
|
||||
|
||||
def _doc_to_dict(doc: Document) -> Dict[str, Any]:
|
||||
return {
|
||||
"id": doc.id,
|
||||
"session_id": doc.session_id,
|
||||
"title": doc.title,
|
||||
"language": doc.language,
|
||||
"current_content": doc.current_content,
|
||||
"version_count": doc.version_count,
|
||||
"is_active": doc.is_active,
|
||||
"archived": bool(getattr(doc, "archived", False)),
|
||||
"created_at": (doc.created_at.isoformat() + "Z") if doc.created_at else None,
|
||||
"updated_at": (doc.updated_at.isoformat() + "Z") if doc.updated_at else None,
|
||||
# Source-email provenance (set when doc was created from an email
|
||||
# attachment) — drives the "Send signed reply" menu item.
|
||||
"source_email_uid": getattr(doc, "source_email_uid", None),
|
||||
"source_email_folder": getattr(doc, "source_email_folder", None),
|
||||
"source_email_account_id": getattr(doc, "source_email_account_id", None),
|
||||
"source_email_message_id": getattr(doc, "source_email_message_id", None),
|
||||
}
|
||||
|
||||
def _version_to_dict(v: DocumentVersion) -> Dict[str, Any]:
|
||||
return {
|
||||
"id": v.id,
|
||||
"document_id": v.document_id,
|
||||
"version_number": v.version_number,
|
||||
"content": v.content,
|
||||
"summary": v.summary,
|
||||
"source": v.source,
|
||||
"created_at": v.created_at.isoformat() if v.created_at else None,
|
||||
}
|
||||
|
||||
|
||||
def _verify_doc_owner(db, doc: Document, user: str):
|
||||
"""Verify `user` owns this document. Raise 404 if not.
|
||||
|
||||
Documents now carry their own `owner` column, so a doc whose session
|
||||
was deleted (session_id → NULL) can still prove ownership and stay
|
||||
openable / cloneable. We trust that column first and only fall back to
|
||||
the session join for any not-yet-backfilled legacy row.
|
||||
"""
|
||||
if user is None:
|
||||
if _auth_disabled():
|
||||
return # Single-user / no-auth mode: allow access
|
||||
raise HTTPException(403, "Authentication required")
|
||||
if doc.owner is not None:
|
||||
if doc.owner != user:
|
||||
raise HTTPException(404, "Document not found")
|
||||
return
|
||||
# Legacy fallback: derive ownership from the linked session.
|
||||
if not doc.session_id:
|
||||
raise HTTPException(404, "Document not found")
|
||||
session = db.query(DbSession).filter(DbSession.id == doc.session_id).first()
|
||||
if not session or session.owner != user:
|
||||
raise HTTPException(404, "Document not found")
|
||||
|
||||
|
||||
def _owner_session_filter(q, user):
|
||||
"""Restrict a documents query to those owned by `user`.
|
||||
|
||||
Documents now carry their own `owner` column (backfilled at boot from
|
||||
the linked session, or assigned to the admin user for legacy/orphaned
|
||||
docs). We filter on that directly rather than on a session join, so a
|
||||
document whose session was deleted (session_id → NULL) still shows up
|
||||
for its owner instead of silently vanishing from the Library + search.
|
||||
|
||||
The owner backfill runs in init_db before the app serves requests, so
|
||||
by the time this filter is live there are no NULL-owner rows to leak;
|
||||
we therefore match the owner strictly for authenticated callers."""
|
||||
if not user:
|
||||
if user == "" or _auth_disabled():
|
||||
return q
|
||||
return q.filter(False)
|
||||
return q.filter(Document.owner == user)
|
||||
|
||||
|
||||
|
||||
def _slug(name: str) -> str:
|
||||
"""Filesystem-friendly version of a document title.
|
||||
|
||||
Whitespace becomes underscores; other unsafe punctuation is dropped.
|
||||
Preserves letters, digits, dot, hyphen, underscore. Idempotent.
|
||||
"""
|
||||
import re as _re
|
||||
s = (name or "").strip()
|
||||
# Drop the trailing extension if the title happens to include one
|
||||
s = _re.sub(r'\.pdf$', '', s, flags=_re.IGNORECASE)
|
||||
s = _re.sub(r'\s+', '_', s)
|
||||
s = _re.sub(r'[^A-Za-z0-9._-]', '', s)
|
||||
s = _re.sub(r'_+', '_', s).strip('_')
|
||||
return s or "form"
|
||||
|
||||
|
||||
# DPI scale for the interactive PDF view. ~150 DPI (2x of 72 PDF user-units).
|
||||
_PDF_RENDER_SCALE = 2.0
|
||||
|
||||
|
||||
def _upload_path_inside(upload_dir: str, path: str) -> bool:
|
||||
base = os.path.realpath(upload_dir)
|
||||
p = os.path.realpath(path)
|
||||
try:
|
||||
return os.path.commonpath([base, p]) == base
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
def _resolve_user_upload_path(
|
||||
upload_handler: Any,
|
||||
upload_id: str,
|
||||
owner: Optional[str],
|
||||
auth_manager=None,
|
||||
) -> Optional[str]:
|
||||
"""Resolve an upload id to a filesystem path the caller may read."""
|
||||
if upload_handler is None:
|
||||
return None
|
||||
resolved = upload_handler.resolve_upload(
|
||||
upload_id,
|
||||
owner=owner,
|
||||
auth_manager=auth_manager,
|
||||
)
|
||||
if not isinstance(resolved, dict) or not resolved:
|
||||
return None
|
||||
path = resolved.get("path")
|
||||
upload_dir = getattr(upload_handler, "upload_dir", None)
|
||||
if path and upload_dir and not _upload_path_inside(upload_dir, path):
|
||||
logger.warning("Upload path outside upload directory: %s", path)
|
||||
return None
|
||||
return path
|
||||
|
||||
|
||||
def _locate_upload(
|
||||
upload_dir: str,
|
||||
file_id: str,
|
||||
owner: Optional[str] = None,
|
||||
auth_manager=None,
|
||||
upload_handler: Any = None,
|
||||
):
|
||||
"""Find an upload by its filename ID via UploadHandler.resolve_upload."""
|
||||
if upload_handler is None:
|
||||
from src.upload_handler import UploadHandler
|
||||
|
||||
base_dir = os.path.dirname(os.path.abspath(upload_dir))
|
||||
upload_handler = UploadHandler(base_dir, upload_dir)
|
||||
return _resolve_user_upload_path(upload_handler, file_id, owner, auth_manager)
|
||||
|
||||
|
||||
def _assert_pdf_marker_upload_owned(
|
||||
request: Request,
|
||||
content: str,
|
||||
user: Optional[str],
|
||||
upload_handler: Any,
|
||||
) -> None:
|
||||
"""Reject document content whose pdf_source marker points at another user's upload."""
|
||||
if upload_handler is None:
|
||||
return
|
||||
from src.pdf_form_doc import find_source_upload_id
|
||||
|
||||
upload_id = find_source_upload_id(content or "")
|
||||
if not upload_id:
|
||||
return
|
||||
auth_manager = getattr(getattr(request.app, "state", None), "auth_manager", None)
|
||||
if not _resolve_user_upload_path(upload_handler, upload_id, user, auth_manager):
|
||||
raise HTTPException(
|
||||
400,
|
||||
"Document PDF marker references an upload you do not own",
|
||||
)
|
||||
|
||||
|
||||
def _derive_title(content: str) -> str:
|
||||
"""Derive a title from document content."""
|
||||
import re
|
||||
if not isinstance(content, str):
|
||||
return "Untitled"
|
||||
text = content.strip()
|
||||
if not text:
|
||||
return "Untitled"
|
||||
|
||||
# Markdown header
|
||||
md = re.match(r'^#{1,3}\s+(.+)', text, re.MULTILINE)
|
||||
if md:
|
||||
title = md.group(1).strip()
|
||||
if len(title) > 50:
|
||||
title = title[:48] + "…"
|
||||
return title
|
||||
|
||||
# HTML heading
|
||||
html = re.search(r'<h[1-3][^>]*>([^<]+)</h[1-3]>', text, re.IGNORECASE)
|
||||
if html:
|
||||
title = html.group(1).strip()
|
||||
if len(title) > 50:
|
||||
title = title[:48] + "…"
|
||||
return title
|
||||
|
||||
# First non-empty line (if short enough)
|
||||
for line in text.split('\n'):
|
||||
line = line.strip()
|
||||
if line and 2 <= len(line) <= 60:
|
||||
title = re.sub(r'[:#*`]+$', '', line).strip()
|
||||
if title and len(title) > 50:
|
||||
title = title[:48] + "…"
|
||||
return title or "Untitled"
|
||||
|
||||
return "Untitled"
|
||||
_sys.modules[__name__] = _canonical
|
||||
|
||||
+13
-1806
File diff suppressed because it is too large
Load Diff
@@ -247,6 +247,7 @@ import re as _re_reply
|
||||
_REPLY_OPEN_RE = _re_reply.compile(r"<<<\s*(?:REPLY|SUMMARY|OUTPUT)\s*>>+", _re_reply.I)
|
||||
_REPLY_CLOSE_RE = _re_reply.compile(r"<<<\s*END\s*>>+", _re_reply.I)
|
||||
_REPLY_ROLE_MARKER_RE = _re_reply.compile(r"</?\|(?:assistant|assistan|user|system|tool)\|>?|</\|end\|>?", _re_reply.I)
|
||||
_SUMMARY_BULLET_RE = _re_reply.compile(r"^(?:[-*\u2022]\s+|\d+[.)]\s+)")
|
||||
|
||||
|
||||
def _extract_reply(text: str) -> str:
|
||||
@@ -277,6 +278,125 @@ def _extract_reply(text: str) -> str:
|
||||
return _strip_think(t).strip()
|
||||
|
||||
|
||||
def _build_email_summary_messages(sender: str, subject: str, body_for_llm: str) -> list[dict[str, str]]:
|
||||
return [
|
||||
{
|
||||
"role": "system",
|
||||
"content": (
|
||||
"You are an email summarizer. Format: 1-3 short bullet points "
|
||||
"(use '- '). Cover: main point, action items, deadlines. If the "
|
||||
"email has attachments (marked '--- ATTACHMENTS ---'), USE THEIR "
|
||||
"CONTENTS - pull invoice totals, deadlines, key clauses, concrete "
|
||||
"numbers/dates from PDFs/docs into the bullets. Be terse.\n\n"
|
||||
"OUTPUT FORMAT: Put ONLY the bullet points between these exact "
|
||||
"markers, each on its own line:\n"
|
||||
"<<<SUMMARY>>>\n"
|
||||
"- ...\n"
|
||||
"<<<END>>>\n"
|
||||
"Any reasoning must come BEFORE <<<SUMMARY>>> (ideally inside "
|
||||
"<think>...</think>). Only the text between the markers is kept."
|
||||
),
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": (
|
||||
f"From: {sender}\nSubject: {subject}\n\n{body_for_llm[:12000]}"
|
||||
"\n\n---\n\nSummarize the email. Output the bullets between "
|
||||
"<<<SUMMARY>>> and <<<END>>>."
|
||||
),
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
async def _generate_email_summary(
|
||||
url: str,
|
||||
model: str,
|
||||
sender: str,
|
||||
subject: str,
|
||||
body_for_llm: str,
|
||||
*,
|
||||
headers: dict | None = None,
|
||||
max_tokens: int = 8192,
|
||||
timeout: int = 180,
|
||||
) -> str:
|
||||
"""Generate an interactive email summary through the shared LLM adapter."""
|
||||
from src.llm_core import llm_call_async
|
||||
|
||||
raw = await llm_call_async(
|
||||
url=url,
|
||||
model=model,
|
||||
messages=_build_email_summary_messages(sender, subject, body_for_llm),
|
||||
temperature=0.3,
|
||||
max_tokens=max_tokens,
|
||||
headers=headers,
|
||||
timeout=timeout,
|
||||
workload="foreground",
|
||||
)
|
||||
return _normalize_email_summary(raw)
|
||||
|
||||
|
||||
async def _generate_scheduled_email_summary(
|
||||
url: str,
|
||||
model: str,
|
||||
sender: str,
|
||||
subject: str,
|
||||
body_for_llm: str,
|
||||
*,
|
||||
headers: dict | None = None,
|
||||
owner: str | None = None,
|
||||
max_tokens: int = 8192,
|
||||
timeout: int = 180,
|
||||
) -> str:
|
||||
"""Generate a scheduled summary through the background task candidate chain."""
|
||||
from src.task_endpoint import task_llm_call_async
|
||||
|
||||
raw = await task_llm_call_async(
|
||||
messages=_build_email_summary_messages(sender, subject, body_for_llm),
|
||||
fallback_url=url,
|
||||
fallback_model=model,
|
||||
fallback_headers=headers,
|
||||
owner=owner,
|
||||
temperature=0.3,
|
||||
max_tokens=max_tokens,
|
||||
timeout=timeout,
|
||||
)
|
||||
return _normalize_email_summary(raw)
|
||||
|
||||
|
||||
def _normalize_email_summary(raw) -> str:
|
||||
"""Extract a stable cache/UI summary from provider output."""
|
||||
raw_text = raw or ""
|
||||
if _REPLY_OPEN_RE.search(raw_text):
|
||||
summary = _extract_reply(raw_text)
|
||||
if summary:
|
||||
return summary
|
||||
|
||||
cleaned = _strip_think(raw_text).strip()
|
||||
bullets = [
|
||||
line.strip()
|
||||
for line in cleaned.splitlines()
|
||||
if _SUMMARY_BULLET_RE.match(line.strip())
|
||||
]
|
||||
if bullets:
|
||||
return "\n".join(bullets)
|
||||
return cleaned.strip()
|
||||
|
||||
|
||||
EMAIL_SUMMARY_ERROR_CODE = "email_summary_unavailable"
|
||||
EMAIL_SUMMARY_ERROR_MESSAGE = "Failed to summarize"
|
||||
|
||||
|
||||
def _email_summary_failure_log_detail(exc: BaseException) -> str:
|
||||
"""Return useful provider-failure metadata without echoing exception text."""
|
||||
detail = f"type={type(exc).__name__}"
|
||||
status = getattr(exc, "status_code", None)
|
||||
if status is None:
|
||||
status = getattr(getattr(exc, "response", None), "status_code", None)
|
||||
if isinstance(status, int):
|
||||
detail += f" status={status}"
|
||||
return detail
|
||||
|
||||
|
||||
def _apply_email_style_mechanics(text: str) -> str:
|
||||
"""Enforce deterministic writing-style mechanics that models often miss."""
|
||||
if not text:
|
||||
|
||||
+23
-9
@@ -40,6 +40,7 @@ from routes.email_helpers import (
|
||||
_pre_retrieve_context,
|
||||
_attach_compose_uploads, _cleanup_compose_uploads, _q,
|
||||
SCHEDULED_DB, _EMAIL_REPLY_SYS_PROMPT_BASE, _email_cache_owner_clause,
|
||||
_generate_scheduled_email_summary, _email_summary_failure_log_detail,
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -653,6 +654,7 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
|
||||
no_msgid = 0
|
||||
examined = 0
|
||||
_summaries_created = 0
|
||||
_summary_failed = 0
|
||||
_events_created = 0
|
||||
_replies_drafted = 0
|
||||
_reply_failed = 0
|
||||
@@ -785,16 +787,17 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
|
||||
|
||||
if need_sum:
|
||||
try:
|
||||
summary = await task_llm_call_async(
|
||||
messages=[
|
||||
{"role": "system", "content": "You are an email summarizer. Format: 1-3 short bullet points (use '- '). Cover: main point, action items, deadlines. If the email has attachments (marked '--- ATTACHMENTS ---'), USE THEIR CONTENTS — pull out invoice totals, deadlines, key clauses, any concrete numbers/dates in PDFs/docs, and reflect them in the bullets. Be terse.\n\nOUTPUT FORMAT: Put ONLY the bullet points between these exact markers, each on its own line:\n<<<SUMMARY>>>\n- ...\n<<<END>>>\nAny reasoning or planning must come BEFORE <<<SUMMARY>>> (ideally inside <think>...</think>). Only the text between the markers is kept."},
|
||||
{"role": "user", "content": f"From: {sender}\nSubject: {subject}\n\n{body_for_llm[:12000]}\n\n---\n\nSummarize the email. Output the bullets between <<<SUMMARY>>> and <<<END>>>."},
|
||||
],
|
||||
fallback_url=url, fallback_model=model, fallback_headers=headers,
|
||||
summary = await _generate_scheduled_email_summary(
|
||||
url=url,
|
||||
model=model,
|
||||
sender=sender,
|
||||
subject=subject,
|
||||
body_for_llm=body_for_llm,
|
||||
headers=req_headers,
|
||||
owner=account_owner or None,
|
||||
temperature=0.3, max_tokens=16384, timeout=240,
|
||||
max_tokens=16384,
|
||||
timeout=240,
|
||||
)
|
||||
summary = _extract_reply((summary or "").strip())
|
||||
if summary:
|
||||
_c = _sql3.connect(SCHEDULED_DB)
|
||||
_c.execute("""
|
||||
@@ -808,10 +811,19 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
|
||||
_summaries_created += 1
|
||||
_uid_text = uid.decode() if isinstance(uid, bytes) else str(uid)
|
||||
_detail_lines.append(f"summary · {_folder}#{_uid_text} · {subject or '(no subject)'} — {sender or '(unknown sender)'}")
|
||||
else:
|
||||
_summary_failed += 1
|
||||
_uid_text = uid.decode() if isinstance(uid, bytes) else str(uid)
|
||||
_detail_lines.append(f"summary empty · {_folder}#{_uid_text} · {subject or '(no subject)'} — {sender or '(unknown sender)'}")
|
||||
except Exception as e:
|
||||
_summary_failed += 1
|
||||
_uid_text = uid.decode() if isinstance(uid, bytes) else str(uid)
|
||||
_detail_lines.append(f"summary failed · {_folder}#{_uid_text} · {subject or '(no subject)'} — {sender or '(unknown sender)'}")
|
||||
logger.warning(f"Auto-summary {uid} failed: {e}")
|
||||
logger.warning(
|
||||
"Auto-summary uid=%s failed %s",
|
||||
_uid_text,
|
||||
_email_summary_failure_log_detail(e),
|
||||
)
|
||||
|
||||
if need_reply:
|
||||
await _emit_progress(progress_cb, f"Drafting reply {processed + 1}/{_max_process} · checked {examined}/{len(uid_list)}")
|
||||
@@ -1320,6 +1332,8 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
|
||||
parts.append(f"processed {processed} new")
|
||||
if auto_sum:
|
||||
parts.append(f"summarized {_summaries_created}")
|
||||
if _summary_failed:
|
||||
parts.append(f"{_summary_failed} summary failed")
|
||||
if auto_reply_draft:
|
||||
parts.append(f"drafted {_replies_drafted} repl" + ("y" if _replies_drafted == 1 else "ies"))
|
||||
if _reply_failed:
|
||||
|
||||
+242
-115
@@ -45,6 +45,7 @@ from src.upload_limits import read_upload_limited, EMAIL_COMPOSE_UPLOAD_MAX_BYTE
|
||||
|
||||
from routes.email_helpers import (
|
||||
_strip_think, _extract_reply, _apply_email_style_mechanics, require_owner, require_user, _assert_owns_account,
|
||||
_account_visible_to_owner,
|
||||
_q, _attach_compose_uploads, _cleanup_compose_uploads,
|
||||
_load_settings, _save_settings, _get_email_config,
|
||||
_send_smtp_message, _smtp_security_mode,
|
||||
@@ -57,7 +58,8 @@ from routes.email_helpers import (
|
||||
_extract_attachment_to_disk, _extract_html, _extract_text,
|
||||
_fetch_sender_thread_context, _pre_retrieve_context,
|
||||
_EMAIL_REPLY_SYS_PROMPT_BASE, _POOL_HOOKS,
|
||||
_friendly_email_auth_error,
|
||||
_friendly_email_auth_error, _email_summary_failure_log_detail,
|
||||
_generate_email_summary, EMAIL_SUMMARY_ERROR_CODE, EMAIL_SUMMARY_ERROR_MESSAGE,
|
||||
SendEmailRequest, ExtractStyleRequest,
|
||||
ATTACHMENTS_DIR, COMPOSE_UPLOADS_DIR, SCHEDULED_DB,
|
||||
attachment_extract_dir, _email_cache_owner_clause, email_translation_body_hash,
|
||||
@@ -194,6 +196,64 @@ def _coerce_port(value, default):
|
||||
return None, f"Invalid port {value!r}; must be a whole number"
|
||||
|
||||
|
||||
def _lock_email_account_owner_mutation(db, *owners: str) -> None:
|
||||
"""Delegate account/default serialization to the shared DB primitive."""
|
||||
from core.database import lock_email_account_owner_mutations
|
||||
|
||||
lock_email_account_owner_mutations(db, *owners)
|
||||
|
||||
|
||||
def _email_account_owner_scope(query, owner: str):
|
||||
"""Restrict a query to one normalized EmailAccount owner partition."""
|
||||
from core.database import EmailAccount
|
||||
from sqlalchemy import or_
|
||||
|
||||
if owner:
|
||||
return query.filter(EmailAccount.owner == owner)
|
||||
return query.filter(or_(EmailAccount.owner == None, EmailAccount.owner == "")) # noqa: E711
|
||||
|
||||
|
||||
def _discover_email_account_mutation_scope(account_id: str, owner: str) -> str:
|
||||
"""Read the initial lock key and fail closed before a mutation session."""
|
||||
from core.database import EmailAccount, SessionLocal
|
||||
|
||||
db = SessionLocal()
|
||||
try:
|
||||
row = db.get(EmailAccount, account_id)
|
||||
if row is None or (owner and not _account_visible_to_owner(row, owner)):
|
||||
raise HTTPException(404, "Account not found")
|
||||
return row.owner or ""
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as exc:
|
||||
logger.error("Account-owner mutation check failed: %s", exc)
|
||||
raise HTTPException(503, "Account check failed")
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
|
||||
def _lock_and_reload_email_account(db, account_id: str, owner: str, scope: str):
|
||||
"""Lock, reload, and revalidate an account, retrying if its owner moved."""
|
||||
from core.database import EmailAccount
|
||||
|
||||
owner_scopes = {scope or ""}
|
||||
while True:
|
||||
_lock_email_account_owner_mutation(db, *owner_scopes)
|
||||
row = db.get(EmailAccount, account_id, populate_existing=True)
|
||||
if row is None or (owner and not _account_visible_to_owner(row, owner)):
|
||||
raise HTTPException(404, "Account not found")
|
||||
|
||||
current_scope = row.owner or ""
|
||||
if current_scope in owner_scopes or db.get_bind().dialect.name == "sqlite":
|
||||
return row
|
||||
|
||||
# The account changed owner after discovery but before lock acquisition.
|
||||
# Release the partial lock set and reacquire all observed scopes in the
|
||||
# shared helper's canonical order, then validate from the database again.
|
||||
db.rollback()
|
||||
owner_scopes.add(current_scope)
|
||||
|
||||
|
||||
def _email_tag_owner_aliases(account_id: str | None, owner: str = "") -> list[str]:
|
||||
aliases = [owner or ""]
|
||||
try:
|
||||
@@ -2860,13 +2920,22 @@ def setup_email_routes():
|
||||
return indexed_response
|
||||
return {"emails": [], "total": 0, "error": "Mail operation failed"}
|
||||
|
||||
def _read_email_sync(uid, folder, account_id, owner, mark_seen=True, full=False):
|
||||
def _read_email_sync(uid, folder, account_id, owner, mark_seen=False, full=False):
|
||||
"""Sync IMAP read — wrapped in to_thread by the async handler.
|
||||
|
||||
The normal reader path fetches the headers plus a bounded body prefix.
|
||||
That avoids downloading multi-megabyte attachments just to open a
|
||||
message. Full-message fetch remains available for flows that need
|
||||
attachment metadata immediately, such as forwarding.
|
||||
|
||||
`mark_seen` defaults to False because it mutates provider state: it
|
||||
selects the mailbox read-write and issues a STORE. Only a foreground
|
||||
open should ask for it, and it has to ask explicitly.
|
||||
|
||||
A failed \\Seen transition is reported as `mark_seen_failed` on an
|
||||
otherwise normal response, never as an error. The body has already been
|
||||
fetched at that point, so refusing to return it would turn a cosmetic
|
||||
flag failure into an unreadable message.
|
||||
"""
|
||||
import time as _t
|
||||
_t0 = _t.monotonic()
|
||||
@@ -2874,9 +2943,28 @@ def setup_email_routes():
|
||||
preview_bytes = 384 * 1024
|
||||
_t_select = 0.0
|
||||
_t_fetch = 0.0
|
||||
mark_seen_failed = False
|
||||
try:
|
||||
with _imap(account_id, owner=owner) as conn:
|
||||
conn.select(_q(folder), readonly=True)
|
||||
# A foreground open owns both the body fetch and the \Seen
|
||||
# transition. Keep them on one read-write IMAP selection so the
|
||||
# route never schedules a second connection that can race the
|
||||
# response. Prefetch/read-only callers retain BODY.PEEK and a
|
||||
# read-only mailbox selection.
|
||||
try:
|
||||
conn.select(_q(folder), readonly=not mark_seen)
|
||||
except Exception as select_exc:
|
||||
if not mark_seen:
|
||||
raise
|
||||
# Read-only mailboxes (shared archives, some provider
|
||||
# folders) reject a read-write SELECT. Serve the message
|
||||
# read-only and report the flag failure.
|
||||
logger.warning(
|
||||
f"read-write SELECT rejected for {folder!r}; "
|
||||
f"serving read-only without \\Seen: {select_exc}"
|
||||
)
|
||||
conn.select(_q(folder), readonly=True)
|
||||
mark_seen_failed = True
|
||||
_t_select = _t.monotonic() - _t0
|
||||
fetch_query = "(BODY.PEEK[])" if full else f"(BODY.PEEK[HEADER] BODY.PEEK[TEXT]<0.{preview_bytes}>)"
|
||||
status, msg_data = _imap_uid_fetch(conn, uid, fetch_query)
|
||||
@@ -2902,22 +2990,44 @@ def setup_email_routes():
|
||||
header_part = msg_data[0][1] or b""
|
||||
raw = header_part + b"\r\n" + text_part
|
||||
|
||||
msg = email_mod.message_from_bytes(raw)
|
||||
# Parse the fetched payload before mutating provider state. If
|
||||
# the message is malformed enough that the reader cannot build
|
||||
# a response, the caller gets an error while the message stays
|
||||
# unread instead of receiving a false optimistic rollback.
|
||||
msg = email_mod.message_from_bytes(raw)
|
||||
|
||||
subject = _decode_header(msg.get("Subject", "(no subject)"))
|
||||
sender = _decode_header(msg.get("From", "unknown"))
|
||||
to = _decode_header(msg.get("To", ""))
|
||||
cc = _decode_header(msg.get("Cc", ""))
|
||||
date_str = msg.get("Date", "")
|
||||
message_id = msg.get("Message-ID", "")
|
||||
in_reply_to = msg.get("In-Reply-To", "")
|
||||
references = msg.get("References", "")
|
||||
body = _extract_text(msg)
|
||||
body_html = _extract_html(msg)
|
||||
subject = _decode_header(msg.get("Subject", "(no subject)"))
|
||||
sender = _decode_header(msg.get("From", "unknown"))
|
||||
to = _decode_header(msg.get("To", ""))
|
||||
cc = _decode_header(msg.get("Cc", ""))
|
||||
date_str = msg.get("Date", "")
|
||||
message_id = msg.get("Message-ID", "")
|
||||
in_reply_to = msg.get("In-Reply-To", "")
|
||||
references = msg.get("References", "")
|
||||
body = _extract_text(msg)
|
||||
body_html = _extract_html(msg)
|
||||
|
||||
sender_name, sender_addr = email.utils.parseaddr(sender)
|
||||
parsed_date = email.utils.parsedate_to_datetime(date_str) if date_str else None
|
||||
attachments = _list_attachments_from_msg(msg) if full else (_email_attachment_meta_cache_get(owner, account_id, folder, uid) or [])
|
||||
|
||||
if mark_seen and not mark_seen_failed:
|
||||
seen_status, _ = conn.uid("STORE", _uid_bytes(uid), "+FLAGS", "(\\Seen)")
|
||||
if seen_status != "OK":
|
||||
# Report, don't raise. The parsed body below is still a
|
||||
# valid response; only the flag claim is untrue.
|
||||
logger.warning(
|
||||
f"IMAP STORE \\Seen failed for UID {uid} in {folder!r}: {seen_status}"
|
||||
)
|
||||
mark_seen_failed = True
|
||||
|
||||
# Only record the local flag transition when the provider actually
|
||||
# accepted it, so the index and list cache cannot drift ahead of
|
||||
# the mailbox.
|
||||
if mark_seen and not mark_seen_failed:
|
||||
_email_index_update_flags(owner, account_id, folder, uid, "\\Seen", True)
|
||||
_update_list_cache_seen(account_id, folder, uid, True)
|
||||
|
||||
sender_name, sender_addr = email.utils.parseaddr(sender)
|
||||
parsed_date = email.utils.parsedate_to_datetime(date_str) if date_str else None
|
||||
attachments = _list_attachments_from_msg(msg) if full else (_email_attachment_meta_cache_get(owner, account_id, folder, uid) or [])
|
||||
related_attachments = []
|
||||
if full and not _has_visible_attachments(msg):
|
||||
related_attachments = _related_thread_attachments_sync(
|
||||
@@ -3038,20 +3148,29 @@ def setup_email_routes():
|
||||
"boundaries": cached_boundaries,
|
||||
"thread_turns": cached_turns,
|
||||
"sender_signature": cached_sender_sig,
|
||||
# Per-request, not part of the message: the route strips this
|
||||
# before caching so a one-off flag failure is never replayed to
|
||||
# later readers.
|
||||
"mark_seen_failed": mark_seen_failed,
|
||||
}
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to read email {uid}: {e}")
|
||||
return {"error": "Mail operation failed"}
|
||||
|
||||
def _mark_email_seen_sync(uid, folder, account_id, owner):
|
||||
"""Synchronously mark a cached email seen and report success."""
|
||||
try:
|
||||
with _imap(account_id, owner=owner) as conn:
|
||||
conn.select(_q(folder))
|
||||
conn.uid("STORE", _uid_bytes(uid), "+FLAGS", "\\Seen")
|
||||
conn.select(_q(folder), readonly=False)
|
||||
status, _ = conn.uid("STORE", _uid_bytes(uid), "+FLAGS", "(\\Seen)")
|
||||
if status != "OK":
|
||||
return False
|
||||
_email_index_update_flags(owner, account_id, folder, uid, "\\Seen", True)
|
||||
_update_list_cache_seen(account_id, folder, uid, True)
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.debug(f"mark-seen after cached read failed uid={uid}: {e}")
|
||||
logger.warning(f"mark-seen after cached read failed uid={uid}: {e}")
|
||||
return False
|
||||
|
||||
@router.get("/read/{uid}")
|
||||
async def read_email_by_uid(
|
||||
@@ -3077,32 +3196,32 @@ def setup_email_routes():
|
||||
if cached.get("attachment_version") != EMAIL_READ_ATTACHMENT_VERSION:
|
||||
cached = None
|
||||
if cached is not None:
|
||||
if mark_seen:
|
||||
try:
|
||||
_asyncio.create_task(_asyncio.to_thread(_mark_email_seen_sync, uid, folder, account_id, owner))
|
||||
except RuntimeError:
|
||||
pass
|
||||
# A cache hit already holds a complete, valid message. Await the
|
||||
# STORE so the response reports the real flag state, but never let
|
||||
# a failed STORE withhold a body we are holding in memory.
|
||||
if mark_seen and not await _asyncio.to_thread(
|
||||
_mark_email_seen_sync, uid, folder, account_id, owner
|
||||
):
|
||||
return {**cached, "mark_seen_failed": True}
|
||||
return cached
|
||||
if not full:
|
||||
persisted = _email_preview_cache_get(owner, account_id, folder, uid)
|
||||
if persisted and persisted.get("attachment_version") == EMAIL_READ_ATTACHMENT_VERSION:
|
||||
_read_cache_put(ck, persisted)
|
||||
if mark_seen:
|
||||
try:
|
||||
_asyncio.create_task(_asyncio.to_thread(_mark_email_seen_sync, uid, folder, account_id, owner))
|
||||
except RuntimeError:
|
||||
pass
|
||||
if mark_seen and not await _asyncio.to_thread(
|
||||
_mark_email_seen_sync, uid, folder, account_id, owner
|
||||
):
|
||||
return {**persisted, "mark_seen_failed": True}
|
||||
return persisted
|
||||
result = await _asyncio.to_thread(_read_email_sync, uid, folder, account_id, owner, mark_seen, full)
|
||||
if result and not result.get("error"):
|
||||
_read_cache_put(ck, result)
|
||||
# `mark_seen_failed` describes this request, not the message, so it
|
||||
# must not enter either cache — a later reader would otherwise be
|
||||
# told a STORE failed that it never issued.
|
||||
cacheable = {k: v for k, v in result.items() if k != "mark_seen_failed"}
|
||||
_read_cache_put(ck, cacheable)
|
||||
if not full:
|
||||
_email_preview_cache_put(owner, account_id, folder, uid, result)
|
||||
if mark_seen:
|
||||
try:
|
||||
_asyncio.create_task(_asyncio.to_thread(_mark_email_seen_sync, uid, folder, account_id, owner))
|
||||
except RuntimeError:
|
||||
pass
|
||||
_email_preview_cache_put(owner, account_id, folder, uid, cacheable)
|
||||
return result
|
||||
|
||||
def _schedule_recent_email_warm(emails: list, folder: str, account_id: str | None, owner: str):
|
||||
@@ -4766,8 +4885,6 @@ def setup_email_routes():
|
||||
"""Generate a quick AI summary of an email body."""
|
||||
try:
|
||||
from src.endpoint_resolver import resolve_endpoint
|
||||
from src.llm_core import _uses_max_completion_tokens, _restricts_temperature
|
||||
import requests as _req
|
||||
|
||||
body = data.get("body", "")
|
||||
subject = data.get("subject", "")
|
||||
@@ -4778,7 +4895,11 @@ def setup_email_routes():
|
||||
if account_id:
|
||||
_assert_owns_account(account_id, owner)
|
||||
if not body:
|
||||
return {"success": False, "error": "No body provided"}
|
||||
return {
|
||||
"success": False,
|
||||
"error": "No body provided",
|
||||
"error_code": "email_summary_missing_body",
|
||||
}
|
||||
|
||||
# If we know which UID this is, fetch the raw message and pull
|
||||
# attachment text so the summary can reference invoice totals,
|
||||
@@ -4807,53 +4928,43 @@ def setup_email_routes():
|
||||
if not url:
|
||||
url, model, headers = resolve_endpoint("default", owner=owner)
|
||||
if not url or not model:
|
||||
return {"success": False, "error": "No LLM endpoint configured"}
|
||||
return {
|
||||
"success": False,
|
||||
"error": "No model configured for email summaries",
|
||||
"error_code": "email_summary_not_configured",
|
||||
}
|
||||
|
||||
req_headers = {"Content-Type": "application/json"}
|
||||
if headers:
|
||||
req_headers.update(headers)
|
||||
tok_key = "max_completion_tokens" if _uses_max_completion_tokens(model) else "max_tokens"
|
||||
payload = {
|
||||
"model": model,
|
||||
"messages": [
|
||||
{"role": "system", "content": "You are an email summarizer. Format: 1-3 short bullet points (use '- '). Cover: main point, action items, deadlines. If the email has attachments (marked '--- ATTACHMENTS ---'), USE THEIR CONTENTS — pull invoice totals, deadlines, key clauses, concrete numbers/dates from PDFs/docs into the bullets. Be terse.\n\nOUTPUT FORMAT: Put ONLY the bullet points between these exact markers, each on its own line:\n<<<SUMMARY>>>\n- ...\n<<<END>>>\nAny reasoning must come BEFORE <<<SUMMARY>>> (ideally inside <think>...</think>). Only the text between the markers is kept."},
|
||||
{"role": "user", "content": f"From: {sender}\nSubject: {subject}\n\n{body_for_llm[:12000]}\n\n---\n\nSummarize the email. Output the bullets between <<<SUMMARY>>> and <<<END>>>."},
|
||||
],
|
||||
tok_key: 8192,
|
||||
"temperature": 0.3,
|
||||
"stream": False,
|
||||
}
|
||||
# Reasoning models (o1/o3/o4/gpt-5) reject an explicit temperature.
|
||||
if _restricts_temperature(model):
|
||||
payload.pop("temperature", None)
|
||||
resp = await asyncio.to_thread(
|
||||
_req.post, url, json=payload, headers=req_headers, timeout=180
|
||||
)
|
||||
if not resp.ok:
|
||||
return {"success": False, "error": f"LLM HTTP {resp.status_code}"}
|
||||
rdata = resp.json()
|
||||
msg = (rdata.get("choices") or [{}])[0].get("message", {})
|
||||
content = (msg.get("content") or "").strip()
|
||||
content = _extract_reply(content)
|
||||
try:
|
||||
content = await _generate_email_summary(
|
||||
url=url,
|
||||
model=model,
|
||||
sender=sender,
|
||||
subject=subject,
|
||||
body_for_llm=body_for_llm,
|
||||
headers=req_headers,
|
||||
max_tokens=8192,
|
||||
timeout=180,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
"Email summary LLM call failed %s",
|
||||
_email_summary_failure_log_detail(e),
|
||||
)
|
||||
return {
|
||||
"success": False,
|
||||
"error": EMAIL_SUMMARY_ERROR_MESSAGE,
|
||||
"error_code": EMAIL_SUMMARY_ERROR_CODE,
|
||||
}
|
||||
|
||||
if not content:
|
||||
# Model put everything in reasoning_content — extract bullet points
|
||||
rc = (msg.get("reasoning_content") or "").strip()
|
||||
# Find bullet-point style output (lines starting with -, •, *, or numbered)
|
||||
bullet_lines = []
|
||||
for line in rc.split("\n"):
|
||||
stripped = line.strip()
|
||||
if re.match(r"^[-•*]\s+|^\d+[.)]\s+", stripped):
|
||||
bullet_lines.append(stripped)
|
||||
if bullet_lines:
|
||||
content = "\n".join(bullet_lines)
|
||||
else:
|
||||
# Last resort: take the last paragraph
|
||||
paragraphs = [p.strip() for p in rc.split("\n\n") if p.strip()]
|
||||
content = paragraphs[-1] if paragraphs else rc[:500]
|
||||
|
||||
if not content:
|
||||
return {"success": False, "error": "Empty response from model"}
|
||||
return {
|
||||
"success": False,
|
||||
"error": "The model returned an empty summary",
|
||||
"error_code": "email_summary_empty",
|
||||
}
|
||||
|
||||
# Cache the summary if we have a message_id
|
||||
mid = data.get("message_id", "")
|
||||
@@ -4876,8 +4987,15 @@ def setup_email_routes():
|
||||
|
||||
return {"success": True, "summary": content, "model_used": model}
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to summarize: {e}")
|
||||
return {"success": False, "error": "Mail operation failed"}
|
||||
logger.error(
|
||||
"Email summary route failed %s",
|
||||
_email_summary_failure_log_detail(e),
|
||||
)
|
||||
return {
|
||||
"success": False,
|
||||
"error": EMAIL_SUMMARY_ERROR_MESSAGE,
|
||||
"error_code": EMAIL_SUMMARY_ERROR_CODE,
|
||||
}
|
||||
|
||||
@router.post("/translate")
|
||||
async def translate_email(data: dict, owner: str = Depends(require_owner)):
|
||||
@@ -5209,9 +5327,9 @@ def setup_email_routes():
|
||||
# Build a candidate chain so a stale session-stored API key
|
||||
# (the most common cause of "authentication failed" here)
|
||||
# doesn't kill AI Reply outright — fall through to the
|
||||
# user's Utility / Default endpoints AND their configured
|
||||
# fallback chains. Dedupe by url+model so we don't retry
|
||||
# the same broken endpoint.
|
||||
# user's Utility / Default endpoints and the active Utility
|
||||
# fallback chain. The retired default-fallback hook stays empty.
|
||||
# Dedupe by url+model so we don't retry the same broken endpoint.
|
||||
from src.llm_core import llm_call_async_with_fallback
|
||||
from src.endpoint_resolver import (
|
||||
resolve_utility_fallback_candidates,
|
||||
@@ -5240,7 +5358,7 @@ def setup_email_routes():
|
||||
_add(_d_url, _d_model, _d_headers)
|
||||
except Exception:
|
||||
pass
|
||||
# Configured fallback chains last.
|
||||
# Active Utility fallbacks, then the retired default hook.
|
||||
for cand in resolve_utility_fallback_candidates(owner=owner) or []:
|
||||
_add(*cand)
|
||||
for cand in resolve_chat_fallback_candidates(owner=owner) or []:
|
||||
@@ -5428,9 +5546,9 @@ def setup_email_routes():
|
||||
import uuid as _uuid
|
||||
db = SessionLocal()
|
||||
try:
|
||||
_lock_email_account_owner_mutation(db, owner)
|
||||
q = db.query(EmailAccount).filter(EmailAccount.is_default == True) # noqa: E712
|
||||
if owner:
|
||||
q = q.filter(EmailAccount.owner == owner)
|
||||
q = _email_account_owner_scope(q, owner)
|
||||
row = q.first()
|
||||
if row is None:
|
||||
row = EmailAccount(id=_uuid.uuid4().hex, owner=owner, name="Default", is_default=True, enabled=True)
|
||||
@@ -5456,8 +5574,7 @@ def setup_email_routes():
|
||||
if data.get("smtp_password"):
|
||||
row.smtp_password = _enc(data["smtp_password"])
|
||||
clear_q = db.query(EmailAccount).filter(EmailAccount.id != row.id)
|
||||
if owner:
|
||||
clear_q = clear_q.filter(EmailAccount.owner == owner)
|
||||
clear_q = _email_account_owner_scope(clear_q, owner)
|
||||
clear_q.update({EmailAccount.is_default: False})
|
||||
db.commit()
|
||||
finally:
|
||||
@@ -5552,6 +5669,7 @@ def setup_email_routes():
|
||||
return {"ok": False, "error": port_err}
|
||||
db = SessionLocal()
|
||||
try:
|
||||
_lock_email_account_owner_mutation(db, owner)
|
||||
row = EmailAccount(
|
||||
id=_uuid.uuid4().hex,
|
||||
name=name,
|
||||
@@ -5578,9 +5696,7 @@ def setup_email_routes():
|
||||
# the one-default invariant — but scope it to THIS user's accounts,
|
||||
# otherwise creating a default would clear every other user's
|
||||
# default flag too.
|
||||
scope_q = db.query(EmailAccount)
|
||||
if owner:
|
||||
scope_q = scope_q.filter(EmailAccount.owner == owner)
|
||||
scope_q = _email_account_owner_scope(db.query(EmailAccount), owner)
|
||||
existing_count = scope_q.count()
|
||||
if row.is_default or existing_count == 0:
|
||||
scope_q.update({EmailAccount.is_default: False})
|
||||
@@ -5631,28 +5747,39 @@ def setup_email_routes():
|
||||
|
||||
@router.delete("/accounts/{account_id}")
|
||||
async def delete_email_account(account_id: str, owner: str = Depends(require_user)):
|
||||
_assert_owns_account(account_id, owner)
|
||||
initial_scope = _discover_email_account_mutation_scope(account_id, owner)
|
||||
from core.database import SessionLocal, EmailAccount
|
||||
db = SessionLocal()
|
||||
try:
|
||||
row = db.get(EmailAccount, account_id)
|
||||
if not row:
|
||||
return {"ok": False, "error": "Account not found"}
|
||||
row = _lock_and_reload_email_account(
|
||||
db, account_id, owner, initial_scope
|
||||
)
|
||||
row_scope = row.owner or ""
|
||||
was_default = bool(row.is_default)
|
||||
db.delete(row)
|
||||
db.commit()
|
||||
# Flush the removal before staging a replacement default. The
|
||||
# partial unique index is checked statement-by-statement, and the
|
||||
# ORM is otherwise free to UPDATE the promoted row before DELETE.
|
||||
db.flush()
|
||||
# If the deleted row was default, promote the next-oldest enabled
|
||||
# row owned by THIS user. Without the owner filter we'd promote
|
||||
# another user's account and the deleter would silently inherit
|
||||
# it as their default.
|
||||
if was_default:
|
||||
promote_q = db.query(EmailAccount).filter(EmailAccount.enabled == True) # noqa: E712
|
||||
if owner:
|
||||
promote_q = promote_q.filter(EmailAccount.owner == owner)
|
||||
promote = promote_q.order_by(EmailAccount.created_at.asc()).first()
|
||||
promote_q = db.query(EmailAccount).filter(
|
||||
EmailAccount.id != account_id,
|
||||
EmailAccount.enabled == True, # noqa: E712
|
||||
)
|
||||
promote_q = _email_account_owner_scope(promote_q, row_scope)
|
||||
promote = promote_q.order_by(
|
||||
EmailAccount.created_at.asc(), EmailAccount.id.asc()
|
||||
).first()
|
||||
if promote:
|
||||
promote.is_default = True
|
||||
db.commit()
|
||||
# Deletion and any replacement promotion are one durable state
|
||||
# transition, so another worker can never observe or race the old
|
||||
# split-commit gap.
|
||||
db.commit()
|
||||
return {"ok": True}
|
||||
finally:
|
||||
db.close()
|
||||
@@ -5865,18 +5992,18 @@ def setup_email_routes():
|
||||
|
||||
@router.post("/accounts/{account_id}/set-default")
|
||||
async def set_default_account(account_id: str, owner: str = Depends(require_user)):
|
||||
_assert_owns_account(account_id, owner)
|
||||
initial_scope = _discover_email_account_mutation_scope(account_id, owner)
|
||||
from core.database import SessionLocal, EmailAccount
|
||||
db = SessionLocal()
|
||||
try:
|
||||
row = db.get(EmailAccount, account_id)
|
||||
if not row:
|
||||
return {"ok": False, "error": "Account not found"}
|
||||
# SECURITY: scope the "clear other defaults" sweep to this user's
|
||||
# accounts so we don't unset another user's default flag.
|
||||
clear_q = db.query(EmailAccount)
|
||||
if owner:
|
||||
clear_q = clear_q.filter(EmailAccount.owner == owner)
|
||||
row = _lock_and_reload_email_account(
|
||||
db, account_id, owner, initial_scope
|
||||
)
|
||||
# Scope the sweep to the target row's normalized owner partition;
|
||||
# this also handles visible legacy NULL/empty-owner accounts.
|
||||
clear_q = _email_account_owner_scope(
|
||||
db.query(EmailAccount), row.owner or ""
|
||||
)
|
||||
clear_q.update({EmailAccount.is_default: False})
|
||||
row.is_default = True
|
||||
db.commit()
|
||||
@@ -5895,7 +6022,7 @@ def setup_email_routes():
|
||||
raise HTTPException(400, "GOOGLE_OAUTH_CLIENT_ID not set — add it to .env")
|
||||
redirect_uri = (
|
||||
os.environ.get("GOOGLE_OAUTH_REDIRECT_URI")
|
||||
or f"http://{request.headers.get('host', 'localhost:7000')}/api/email/oauth/google/callback"
|
||||
or f"{request.url.scheme}://{request.headers.get('host', 'localhost:7000')}/api/email/oauth/google/callback"
|
||||
)
|
||||
state = make_oauth_state(account_id, owner)
|
||||
params = urllib.parse.urlencode({
|
||||
@@ -5932,7 +6059,7 @@ def setup_email_routes():
|
||||
client_secret = os.environ.get("GOOGLE_OAUTH_CLIENT_SECRET", "")
|
||||
redirect_uri = (
|
||||
os.environ.get("GOOGLE_OAUTH_REDIRECT_URI")
|
||||
or f"http://{request.headers.get('host', 'localhost:7000')}/api/email/oauth/google/callback"
|
||||
or f"{request.url.scheme}://{request.headers.get('host', 'localhost:7000')}/api/email/oauth/google/callback"
|
||||
)
|
||||
import httpx as _httpx
|
||||
try:
|
||||
|
||||
@@ -127,6 +127,25 @@ def _load_grounding_backend():
|
||||
return cached
|
||||
|
||||
|
||||
def _model_input_to_device(value, device: str, torch):
|
||||
if not hasattr(value, "to"):
|
||||
return value
|
||||
if (
|
||||
device == "mps"
|
||||
and hasattr(torch, "float64")
|
||||
and getattr(value, "dtype", None) == torch.float64
|
||||
):
|
||||
return value.to(device=device, dtype=torch.float32)
|
||||
return value.to(device)
|
||||
|
||||
|
||||
def _model_inputs_to_device(inputs, device: str, torch) -> Dict[str, Any]:
|
||||
return {
|
||||
key: _model_input_to_device(value, device, torch)
|
||||
for key, value in inputs.items()
|
||||
}
|
||||
|
||||
|
||||
def _ground_text_to_box(image, text: str, *, threshold: float = 0.05):
|
||||
query = (text or "").strip()
|
||||
if not query:
|
||||
@@ -142,10 +161,7 @@ def _ground_text_to_box(image, text: str, *, threshold: float = 0.05):
|
||||
labels.append(f"a photo of {query}")
|
||||
try:
|
||||
inputs = processor(text=[labels], images=image, return_tensors="pt")
|
||||
model_inputs = {
|
||||
k: (v.to(device) if hasattr(v, "to") else v)
|
||||
for k, v in inputs.items()
|
||||
}
|
||||
model_inputs = _model_inputs_to_device(inputs, device, torch)
|
||||
with torch.no_grad():
|
||||
outputs = model(**model_inputs)
|
||||
target_sizes = torch.tensor([[image.height, image.width]])
|
||||
@@ -1869,10 +1885,7 @@ def setup_gallery_routes() -> APIRouter:
|
||||
|
||||
try:
|
||||
inputs = processor(image, **kwargs)
|
||||
model_inputs = {
|
||||
k: (v.to(device) if hasattr(v, "to") else v)
|
||||
for k, v in inputs.items()
|
||||
}
|
||||
model_inputs = _model_inputs_to_device(inputs, device, torch)
|
||||
with torch.no_grad():
|
||||
outputs = model(**model_inputs)
|
||||
masks = processor.image_processor.post_process_masks(
|
||||
|
||||
@@ -137,44 +137,6 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
|
||||
entry["metadata"] = meta
|
||||
return entry
|
||||
|
||||
def _db_message_metadata(m: DbChatMessage) -> Dict[str, Any]:
|
||||
meta = {}
|
||||
if m.meta_data:
|
||||
try:
|
||||
meta = json.loads(m.meta_data) or {}
|
||||
except (json.JSONDecodeError, ValueError):
|
||||
meta = {}
|
||||
if m.timestamp and "timestamp" not in meta:
|
||||
meta["timestamp"] = m.timestamp.isoformat() + "Z"
|
||||
return meta
|
||||
|
||||
def _hydrate_session_history_from_db(session_id: str, rows: list[DbChatMessage]) -> None:
|
||||
"""Rebuild in-memory context from raw DB rows after a history load.
|
||||
|
||||
The browser history endpoint can return paged/display-trimmed messages,
|
||||
but the next model call reads ``session.history``. After a restart or a
|
||||
stale in-memory session, selecting an old chat through the paged endpoint
|
||||
used to show the transcript while the model only saw fresh context.
|
||||
"""
|
||||
if not rows:
|
||||
return
|
||||
try:
|
||||
session = session_manager.get_session(session_id)
|
||||
except KeyError:
|
||||
return
|
||||
session.history = [
|
||||
ChatMessage(role=m.role, content=m.content, metadata=_db_message_metadata(m) or None)
|
||||
for m in rows
|
||||
]
|
||||
session.message_count = len(session.history)
|
||||
|
||||
def _session_needs_db_history_hydration(session_id: str, total: int) -> bool:
|
||||
try:
|
||||
session = session_manager.get_session(session_id)
|
||||
except KeyError:
|
||||
return False
|
||||
return len(session.history or []) < int(total or 0)
|
||||
|
||||
@router.get("/api/history/{session_id}")
|
||||
async def get_session_history(
|
||||
request: Request,
|
||||
@@ -198,6 +160,8 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
|
||||
)
|
||||
page_offset = int(offset) if offset is not None else max(total - page_limit, 0)
|
||||
page_offset = max(0, min(page_offset, total))
|
||||
# Keep display pagination page-scoped. ``get_session`` is the
|
||||
# full model-context hydration seam and must not be entered here.
|
||||
rows = (
|
||||
db.query(DbChatMessage)
|
||||
.filter(DbChatMessage.session_id == session_id)
|
||||
@@ -206,14 +170,6 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
|
||||
.limit(page_limit)
|
||||
.all()
|
||||
)
|
||||
if _session_needs_db_history_hydration(session_id, total):
|
||||
full_rows = (
|
||||
db.query(DbChatMessage)
|
||||
.filter(DbChatMessage.session_id == session_id)
|
||||
.order_by(DbChatMessage.timestamp)
|
||||
.all()
|
||||
)
|
||||
_hydrate_session_history_from_db(session_id, full_rows)
|
||||
history_dict = [
|
||||
entry for entry in (_db_history_entry(m) for m in rows)
|
||||
if not (entry.get("metadata") or {}).get("hidden")
|
||||
@@ -258,7 +214,10 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
|
||||
entry["metadata"] = msg["metadata"]
|
||||
history_dict.append(entry)
|
||||
|
||||
# Fallback: load from DB if in-memory is empty
|
||||
# Fallback: load from DB if in-memory renders empty. Display only —
|
||||
# get_session above is the hydration seam, so nothing here writes back
|
||||
# into session.history — rebuilding it from raw rows would overwrite
|
||||
# parsed multimodal content and the _db_id edit/delete keys it just set.
|
||||
if not history_dict:
|
||||
db = SessionLocal()
|
||||
try:
|
||||
@@ -268,17 +227,10 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
|
||||
.order_by(DbChatMessage.timestamp)
|
||||
.all()
|
||||
)
|
||||
db_history = []
|
||||
for m in db_messages:
|
||||
db_history.append(_db_history_entry(m))
|
||||
if db_history:
|
||||
# Rebuild in-memory history from the full set so hidden
|
||||
# messages (e.g. compaction summaries) are kept for AI context.
|
||||
_hydrate_session_history_from_db(session_id, db_messages)
|
||||
# Response excludes hidden messages, matching the in-memory path.
|
||||
history_dict = [
|
||||
m for m in db_history
|
||||
if not (m.get("metadata") or {}).get("hidden")
|
||||
entry for entry in (_db_history_entry(m) for m in db_messages)
|
||||
if not (entry.get("metadata") or {}).get("hidden")
|
||||
]
|
||||
except Exception as e:
|
||||
logger.error(f"DB fallback failed for {session_id}: {e}")
|
||||
@@ -645,8 +597,14 @@ def setup_history_routes(session_manager, upload_handler=None) -> APIRouter:
|
||||
body = await request.json()
|
||||
keep_count = body.get("keep_count", 0)
|
||||
|
||||
# Get the source session
|
||||
source = session_manager.sessions.get(session_id)
|
||||
# Get the source session. keep_count indexes into source.history,
|
||||
# so this must go through get_session — reading the cache directly
|
||||
# forks an empty transcript out of a metadata-only session after a
|
||||
# restart (display pagination no longer hydrates it).
|
||||
try:
|
||||
source = session_manager.get_session(session_id)
|
||||
except KeyError:
|
||||
raise HTTPException(404, "Session not found")
|
||||
if not source:
|
||||
raise HTTPException(404, "Session not found")
|
||||
|
||||
|
||||
@@ -0,0 +1,5 @@
|
||||
"""MCP route domain package (slice 2o, #4082/#4071).
|
||||
|
||||
Contains mcp_routes.py, migrated from the flat routes/ directory.
|
||||
Backward-compat shim at routes/mcp_routes.py re-exports from here.
|
||||
"""
|
||||
@@ -0,0 +1,697 @@
|
||||
# routes/mcp_routes.py
|
||||
"""MCP (Model Context Protocol) server management routes."""
|
||||
import json
|
||||
import os
|
||||
import uuid
|
||||
import urllib.parse
|
||||
import html
|
||||
from pathlib import Path
|
||||
from fastapi import APIRouter, Form, HTTPException, Request
|
||||
from fastapi.responses import RedirectResponse, HTMLResponse
|
||||
import logging
|
||||
import httpx
|
||||
|
||||
from core.database import McpServer, SessionLocal
|
||||
from core.middleware import require_admin
|
||||
from src.constants import DATA_DIR, MCP_OAUTH_DIR
|
||||
from src.mcp_manager import McpManager
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter(prefix="/api/mcp", tags=["mcp"])
|
||||
|
||||
|
||||
def _mcp_oauth_base_dir() -> Path:
|
||||
"""Directory that may contain OAuth files managed by Odysseus."""
|
||||
return Path(MCP_OAUTH_DIR).resolve(strict=False)
|
||||
|
||||
|
||||
def _resolve_mcp_oauth_path(raw_path, field_name: str) -> str:
|
||||
"""Resolve an MCP OAuth path and keep it under DATA_DIR/mcp_oauth."""
|
||||
raw = str(raw_path or "").strip()
|
||||
if not raw:
|
||||
return ""
|
||||
|
||||
base = _mcp_oauth_base_dir()
|
||||
path = Path(os.path.expanduser(raw))
|
||||
if not path.is_absolute():
|
||||
path = base / path
|
||||
resolved = path.resolve(strict=False)
|
||||
|
||||
try:
|
||||
resolved.relative_to(base)
|
||||
except ValueError as exc:
|
||||
raise HTTPException(
|
||||
400,
|
||||
f"Invalid OAuth {field_name}: path must stay under {base}",
|
||||
) from exc
|
||||
return str(resolved)
|
||||
|
||||
|
||||
def _sanitize_mcp_oauth_config(oauth_cfg):
|
||||
"""Return an OAuth config copy with file paths confined to mcp_oauth."""
|
||||
if not oauth_cfg:
|
||||
return oauth_cfg
|
||||
if not isinstance(oauth_cfg, dict):
|
||||
return {}
|
||||
sanitized = dict(oauth_cfg)
|
||||
for field_name in ("keys_file", "token_file"):
|
||||
if sanitized.get(field_name):
|
||||
sanitized[field_name] = _resolve_mcp_oauth_path(
|
||||
sanitized[field_name],
|
||||
field_name,
|
||||
)
|
||||
return sanitized
|
||||
|
||||
|
||||
def _mcp_oauth_token_missing(oauth_cfg, *, strict: bool = True) -> bool:
|
||||
"""Check token existence without letting legacy bad paths break listing."""
|
||||
if not isinstance(oauth_cfg, dict):
|
||||
return False
|
||||
try:
|
||||
token_file = _resolve_mcp_oauth_path(oauth_cfg.get("token_file", ""), "token_file")
|
||||
except HTTPException:
|
||||
if strict:
|
||||
raise
|
||||
logger.warning("Ignoring MCP OAuth config with unsafe token_file")
|
||||
return True
|
||||
return bool(token_file and not os.path.exists(token_file))
|
||||
|
||||
|
||||
def _apply_mcp_oauth_env(env: dict, oauth_cfg) -> None:
|
||||
"""Pass sanitized Gmail package paths to MCP servers that honor them."""
|
||||
if not oauth_cfg or not isinstance(env, dict):
|
||||
return
|
||||
keys_file = oauth_cfg.get("keys_file")
|
||||
token_file = oauth_cfg.get("token_file")
|
||||
if keys_file:
|
||||
env["GMAIL_OAUTH_PATH"] = keys_file
|
||||
if token_file:
|
||||
env["GMAIL_CREDENTIALS_PATH"] = token_file
|
||||
|
||||
|
||||
def _load_disabled_map():
|
||||
"""Load per-server disabled tool sets from DB."""
|
||||
db = SessionLocal()
|
||||
try:
|
||||
disabled_map = {}
|
||||
for srv in db.query(McpServer).all():
|
||||
if srv.disabled_tools:
|
||||
try:
|
||||
names = json.loads(srv.disabled_tools)
|
||||
if names:
|
||||
disabled_map[srv.id] = set(names)
|
||||
except (json.JSONDecodeError, TypeError):
|
||||
pass
|
||||
return disabled_map
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
|
||||
def _mcp_oauth_redirect_uri() -> str:
|
||||
"""Shared callback URL for legacy Google and generic MCP OAuth flows."""
|
||||
from src.mcp_oauth import REDIRECT_URI
|
||||
return REDIRECT_URI
|
||||
|
||||
|
||||
def setup_mcp_routes(mcp_manager: McpManager):
|
||||
"""Setup MCP routes with the provided manager."""
|
||||
|
||||
@router.get("/servers")
|
||||
def list_servers(request: Request):
|
||||
"""List all configured MCP servers with connection status."""
|
||||
require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
servers = db.query(McpServer).all()
|
||||
result = []
|
||||
for srv in servers:
|
||||
status = mcp_manager.get_server_status(srv.id)
|
||||
oauth_cfg = json.loads(srv.oauth_config) if srv.oauth_config else None
|
||||
needs_oauth = False
|
||||
if oauth_cfg:
|
||||
needs_oauth = _mcp_oauth_token_missing(oauth_cfg, strict=False)
|
||||
disabled_list = json.loads(srv.disabled_tools) if srv.disabled_tools else []
|
||||
total_tools = status.get("tool_count", 0)
|
||||
result.append({
|
||||
"id": srv.id,
|
||||
"name": srv.name,
|
||||
"transport": srv.transport,
|
||||
"command": srv.command,
|
||||
"args": json.loads(srv.args) if srv.args else [],
|
||||
"env": json.loads(srv.env) if srv.env else {},
|
||||
"url": srv.url,
|
||||
"is_enabled": srv.is_enabled,
|
||||
"status": status.get("status", "disconnected"),
|
||||
"tool_count": total_tools,
|
||||
"disabled_tool_count": len(disabled_list),
|
||||
"enabled_tool_count": max(0, total_tools - len(disabled_list)),
|
||||
"error": status.get("error"),
|
||||
"auth_url": status.get("auth_url"),
|
||||
"has_oauth": oauth_cfg is not None,
|
||||
"needs_oauth": needs_oauth,
|
||||
})
|
||||
return result
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.post("/servers")
|
||||
async def add_server(
|
||||
request: Request,
|
||||
name: str = Form(...),
|
||||
transport: str = Form("stdio"),
|
||||
command: str = Form(None),
|
||||
args: str = Form("[]"),
|
||||
env: str = Form("{}"),
|
||||
url: str = Form(None),
|
||||
oauth_file: str = Form(None),
|
||||
oauth_config: str = Form(None),
|
||||
):
|
||||
"""Add a new MCP server config and attempt connection. Admin-only:
|
||||
registering a stdio server is equivalent to executing arbitrary
|
||||
binaries on the host."""
|
||||
require_admin(request)
|
||||
server_id = str(uuid.uuid4())[:8]
|
||||
|
||||
# Validate
|
||||
if transport == "stdio" and not command:
|
||||
raise HTTPException(400, "command is required for stdio transport")
|
||||
if transport == "sse" and not url:
|
||||
raise HTTPException(400, "url is required for SSE transport")
|
||||
if transport == "http" and not url:
|
||||
raise HTTPException(400, "url is required for HTTP transport")
|
||||
|
||||
# Parse JSON fields
|
||||
try:
|
||||
parsed_args = json.loads(args) if args else []
|
||||
except json.JSONDecodeError:
|
||||
parsed_args = []
|
||||
try:
|
||||
parsed_env = json.loads(env) if env else {}
|
||||
except json.JSONDecodeError:
|
||||
parsed_env = {}
|
||||
if not isinstance(parsed_env, dict):
|
||||
parsed_env = {}
|
||||
|
||||
# Parse OAuth config
|
||||
parsed_oauth_config = None
|
||||
if oauth_config:
|
||||
try:
|
||||
parsed_oauth_config = _sanitize_mcp_oauth_config(json.loads(oauth_config))
|
||||
except json.JSONDecodeError:
|
||||
pass
|
||||
_apply_mcp_oauth_env(parsed_env, parsed_oauth_config)
|
||||
|
||||
# Write OAuth credentials file if provided (for Google MCP servers)
|
||||
logger.info(f"MCP add_server: oauth_file={oauth_file!r}")
|
||||
if oauth_file:
|
||||
try:
|
||||
oauth_data = json.loads(oauth_file)
|
||||
oauth_dir = _resolve_mcp_oauth_path(oauth_data.get("dir", ""), "dir")
|
||||
oauth_filename = oauth_data.get("filename", "")
|
||||
client_id = oauth_data.get("client_id", "")
|
||||
client_secret = oauth_data.get("client_secret", "")
|
||||
if oauth_dir and oauth_filename and client_id and client_secret:
|
||||
filepath = _resolve_mcp_oauth_path(
|
||||
Path(oauth_dir) / str(oauth_filename),
|
||||
"filename",
|
||||
)
|
||||
os.makedirs(os.path.dirname(filepath), exist_ok=True)
|
||||
creds = {
|
||||
"installed": {
|
||||
"client_id": client_id,
|
||||
"client_secret": client_secret,
|
||||
"redirect_uris": ["http://localhost"],
|
||||
"auth_uri": "https://accounts.google.com/o/oauth2/auth",
|
||||
"token_uri": "https://accounts.google.com/o/oauth2/token",
|
||||
}
|
||||
}
|
||||
with open(filepath, "w", encoding="utf-8") as f:
|
||||
json.dump(creds, f, indent=2)
|
||||
logger.info(f"Wrote OAuth credentials to {filepath}")
|
||||
parsed_env.pop("GOOGLE_CLIENT_ID", None)
|
||||
parsed_env.pop("GOOGLE_CLIENT_SECRET", None)
|
||||
except (json.JSONDecodeError, OSError) as e:
|
||||
logger.warning(f"Failed to write OAuth file: {e}")
|
||||
|
||||
# Save to DB
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = McpServer(
|
||||
id=server_id,
|
||||
name=name,
|
||||
transport=transport,
|
||||
command=command,
|
||||
args=json.dumps(parsed_args),
|
||||
env=json.dumps(parsed_env),
|
||||
url=url,
|
||||
is_enabled=True,
|
||||
oauth_config=json.dumps(parsed_oauth_config) if parsed_oauth_config else None,
|
||||
)
|
||||
db.add(srv)
|
||||
db.commit()
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
# Check if OAuth token already exists — skip connection attempt if not
|
||||
needs_oauth = False
|
||||
if parsed_oauth_config:
|
||||
needs_oauth = _mcp_oauth_token_missing(parsed_oauth_config)
|
||||
|
||||
connected = False
|
||||
if not needs_oauth:
|
||||
connected = await mcp_manager.connect_server(
|
||||
server_id=server_id,
|
||||
name=name,
|
||||
transport=transport,
|
||||
command=command,
|
||||
args=parsed_args,
|
||||
env=parsed_env,
|
||||
url=url,
|
||||
)
|
||||
|
||||
status = mcp_manager.get_server_status(server_id)
|
||||
needs_auth = status.get("status") == "needs_auth"
|
||||
return {
|
||||
"id": server_id,
|
||||
"name": name,
|
||||
"connected": connected,
|
||||
"status": "needs_oauth" if needs_oauth else status.get("status", "disconnected"),
|
||||
"tool_count": status.get("tool_count", 0),
|
||||
"error": "OAuth authorization required" if needs_oauth else status.get("error"),
|
||||
"needs_oauth": needs_oauth,
|
||||
"needs_auth": needs_auth,
|
||||
"auth_url": status.get("auth_url"),
|
||||
}
|
||||
|
||||
@router.post("/servers/{server_id}/reconnect")
|
||||
async def reconnect_server(server_id: str, request: Request):
|
||||
"""Reconnect to an MCP server."""
|
||||
require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = db.query(McpServer).filter(McpServer.id == server_id).first()
|
||||
if not srv:
|
||||
raise HTTPException(404, "Server not found")
|
||||
|
||||
await mcp_manager.disconnect_server(server_id)
|
||||
|
||||
args = json.loads(srv.args) if srv.args else []
|
||||
env = json.loads(srv.env) if srv.env else {}
|
||||
connected = await mcp_manager.connect_server(
|
||||
server_id=server_id,
|
||||
name=srv.name,
|
||||
transport=srv.transport,
|
||||
command=srv.command,
|
||||
args=args,
|
||||
env=env,
|
||||
url=srv.url,
|
||||
)
|
||||
|
||||
status = mcp_manager.get_server_status(server_id)
|
||||
return {
|
||||
"connected": connected,
|
||||
"status": status.get("status", "disconnected"),
|
||||
"tool_count": status.get("tool_count", 0),
|
||||
"error": status.get("error"),
|
||||
"auth_url": status.get("auth_url"),
|
||||
"needs_auth": status.get("status") == "needs_auth",
|
||||
}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.patch("/servers/{server_id}")
|
||||
async def toggle_server(server_id: str, request: Request, is_enabled: str = Form(...)):
|
||||
"""Enable or disable an MCP server."""
|
||||
require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = db.query(McpServer).filter(McpServer.id == server_id).first()
|
||||
if not srv:
|
||||
raise HTTPException(404, "Server not found")
|
||||
|
||||
enabled = str(is_enabled).lower() == "true"
|
||||
srv.is_enabled = enabled
|
||||
db.commit()
|
||||
|
||||
if enabled:
|
||||
args = json.loads(srv.args) if srv.args else []
|
||||
env = json.loads(srv.env) if srv.env else {}
|
||||
await mcp_manager.connect_server(
|
||||
server_id=server_id,
|
||||
name=srv.name,
|
||||
transport=srv.transport,
|
||||
command=srv.command,
|
||||
args=args,
|
||||
env=env,
|
||||
url=srv.url,
|
||||
)
|
||||
else:
|
||||
await mcp_manager.disconnect_server(server_id)
|
||||
|
||||
return {"id": server_id, "is_enabled": enabled}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.delete("/servers/{server_id}")
|
||||
async def delete_server(server_id: str, request: Request):
|
||||
"""Remove an MCP server."""
|
||||
require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = db.query(McpServer).filter(McpServer.id == server_id).first()
|
||||
if not srv:
|
||||
raise HTTPException(404, "Server not found")
|
||||
|
||||
await mcp_manager.disconnect_server(server_id)
|
||||
|
||||
db.delete(srv)
|
||||
db.commit()
|
||||
return {"status": "deleted"}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.get("/tools")
|
||||
def list_tools(request: Request):
|
||||
"""List all discovered MCP tools across all connected servers."""
|
||||
require_admin(request)
|
||||
disabled_map = _load_disabled_map()
|
||||
return mcp_manager.get_all_tools(disabled_map)
|
||||
|
||||
@router.get("/servers/{server_id}/tools")
|
||||
def list_server_tools(server_id: str, request: Request):
|
||||
"""List all tools for a specific MCP server with enabled/disabled state."""
|
||||
require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = db.query(McpServer).filter(McpServer.id == server_id).first()
|
||||
if not srv:
|
||||
raise HTTPException(404, "Server not found")
|
||||
disabled_list = json.loads(srv.disabled_tools) if srv.disabled_tools else []
|
||||
disabled_set = set(disabled_list)
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
all_tools = mcp_manager.get_all_tools()
|
||||
server_tools = [t for t in all_tools if t["server_id"] == server_id]
|
||||
for t in server_tools:
|
||||
t["is_disabled"] = t["name"] in disabled_set
|
||||
return server_tools
|
||||
|
||||
@router.patch("/servers/{server_id}/tools")
|
||||
async def update_disabled_tools(server_id: str, request: Request):
|
||||
"""Bulk update disabled tools list for a server.
|
||||
|
||||
Expects JSON body: {"disabled": ["tool_name_1", "tool_name_2"]}
|
||||
"""
|
||||
require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = db.query(McpServer).filter(McpServer.id == server_id).first()
|
||||
if not srv:
|
||||
raise HTTPException(404, "Server not found")
|
||||
|
||||
body = await request.json()
|
||||
disabled = body.get("disabled", [])
|
||||
if not isinstance(disabled, list):
|
||||
raise HTTPException(400, "disabled must be a list of tool names")
|
||||
|
||||
srv.disabled_tools = json.dumps(disabled) if disabled else None
|
||||
db.commit()
|
||||
|
||||
return {"id": server_id, "disabled_count": len(disabled)}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
# ── OAuth flow for Google MCP servers ──────────────────────────
|
||||
|
||||
@router.get("/oauth/authorize/{server_id}")
|
||||
def oauth_authorize(server_id: str, request: Request):
|
||||
"""Show OAuth authorization page with Google sign-in link."""
|
||||
require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = db.query(McpServer).filter(McpServer.id == server_id).first()
|
||||
if not srv:
|
||||
raise HTTPException(404, "Server not found")
|
||||
if not srv.oauth_config:
|
||||
raise HTTPException(400, "Server has no OAuth config")
|
||||
|
||||
oauth_cfg = _sanitize_mcp_oauth_config(json.loads(srv.oauth_config))
|
||||
keys_file = oauth_cfg.get("keys_file", "")
|
||||
if not keys_file or not os.path.exists(keys_file):
|
||||
raise HTTPException(400, "OAuth keys file not found")
|
||||
|
||||
with open(keys_file, encoding="utf-8") as f:
|
||||
keys_data = json.load(f)
|
||||
keys = keys_data.get("installed") or keys_data.get("web")
|
||||
if not keys:
|
||||
raise HTTPException(400, "Invalid OAuth keys file format")
|
||||
|
||||
client_id = keys["client_id"]
|
||||
scopes = oauth_cfg.get("scopes", [])
|
||||
|
||||
# For Desktop App creds, default to localhost — the user will
|
||||
# paste the resulting URL back if they're on a different device.
|
||||
redirect_uri = _mcp_oauth_redirect_uri()
|
||||
|
||||
params = {
|
||||
"client_id": client_id,
|
||||
"redirect_uri": redirect_uri,
|
||||
"response_type": "code",
|
||||
"scope": " ".join(scopes),
|
||||
"access_type": "offline",
|
||||
"prompt": "consent",
|
||||
"state": server_id,
|
||||
}
|
||||
auth_url = "https://accounts.google.com/o/oauth2/v2/auth?" + urllib.parse.urlencode(params)
|
||||
|
||||
# Determine if user is accessing from the same machine
|
||||
host = request.headers.get("host", "")
|
||||
is_local = host.startswith("localhost") or host.startswith("127.0.0.1")
|
||||
|
||||
if is_local:
|
||||
# Same machine — just redirect, callback will work directly
|
||||
return RedirectResponse(auth_url)
|
||||
else:
|
||||
# Remote device — show paste-back page
|
||||
return HTMLResponse(_oauth_authorize_page(auth_url, server_id, host, redirect_uri))
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.get("/oauth/callback")
|
||||
async def oauth_callback(code: str, state: str, request: Request):
|
||||
"""Handle OAuth callback. Generic MCP OAuth flows resolve via the
|
||||
pending-state registry; Google flows fall through to the legacy path."""
|
||||
require_admin(request)
|
||||
from src.mcp_oauth import resolve_pending
|
||||
if resolve_pending(state, code):
|
||||
return HTMLResponse(_oauth_result_page(
|
||||
"Authorization Successful",
|
||||
"The MCP server is connecting. You can close this window and return to Odysseus.",
|
||||
success=True,
|
||||
))
|
||||
# Legacy Google path: state is the server_id
|
||||
return await _exchange_and_connect(state, code, request)
|
||||
|
||||
@router.post("/oauth/exchange/{server_id}")
|
||||
async def oauth_exchange(server_id: str, request: Request, callback_url: str = Form(...)):
|
||||
"""Manual code exchange — user pastes the callback URL from their browser."""
|
||||
require_admin(request)
|
||||
try:
|
||||
parsed = urllib.parse.urlparse(callback_url)
|
||||
params = urllib.parse.parse_qs(parsed.query)
|
||||
code = params.get("code", [None])[0]
|
||||
if not code:
|
||||
return HTMLResponse(_oauth_result_page("Error", "No authorization code found in the URL. Make sure you copied the full URL from your browser."), status_code=400)
|
||||
except Exception:
|
||||
return HTMLResponse(_oauth_result_page("Error", "Invalid URL format."), status_code=400)
|
||||
|
||||
# Generic MCP OAuth: if the pasted URL carries a state we are waiting on,
|
||||
# resolve it directly (the background connect finishes the handshake).
|
||||
state = params.get("state", [None])[0]
|
||||
from src.mcp_oauth import resolve_pending
|
||||
if state and resolve_pending(state, code):
|
||||
return HTMLResponse(_oauth_result_page(
|
||||
"Authorization Successful",
|
||||
"The MCP server is connecting. You can close this window and return to Odysseus.",
|
||||
success=True,
|
||||
))
|
||||
|
||||
return await _exchange_and_connect(server_id, code, request)
|
||||
|
||||
async def _exchange_and_connect(server_id: str, code: str, request: Request):
|
||||
"""Exchange auth code for tokens and connect the MCP server."""
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = db.query(McpServer).filter(McpServer.id == server_id).first()
|
||||
if not srv:
|
||||
return HTMLResponse(_oauth_result_page("Error", "Server not found."), status_code=404)
|
||||
if not srv.oauth_config:
|
||||
return HTMLResponse(_oauth_result_page("Error", "No OAuth config."), status_code=400)
|
||||
|
||||
oauth_cfg = _sanitize_mcp_oauth_config(json.loads(srv.oauth_config))
|
||||
keys_file = oauth_cfg.get("keys_file", "")
|
||||
token_file = oauth_cfg.get("token_file", "")
|
||||
if not keys_file or not token_file:
|
||||
raise HTTPException(400, "OAuth keys/token file not configured")
|
||||
|
||||
with open(keys_file, encoding="utf-8") as f:
|
||||
keys_data = json.load(f)
|
||||
keys = keys_data.get("installed") or keys_data.get("web")
|
||||
client_id = keys["client_id"]
|
||||
client_secret = keys["client_secret"]
|
||||
|
||||
redirect_uri = _mcp_oauth_redirect_uri()
|
||||
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.post(
|
||||
"https://oauth2.googleapis.com/token",
|
||||
data={
|
||||
"code": code,
|
||||
"client_id": client_id,
|
||||
"client_secret": client_secret,
|
||||
"redirect_uri": redirect_uri,
|
||||
"grant_type": "authorization_code",
|
||||
},
|
||||
)
|
||||
|
||||
if resp.status_code != 200:
|
||||
err = resp.text
|
||||
logger.error(f"OAuth token exchange failed: {err}")
|
||||
return HTMLResponse(_oauth_result_page("Authorization Failed", f"Google returned an error: {err}"), status_code=400)
|
||||
|
||||
tokens = resp.json()
|
||||
logger.info(f"OAuth tokens received for server {server_id}")
|
||||
|
||||
# Save tokens to the file the MCP package expects
|
||||
os.makedirs(os.path.dirname(token_file), exist_ok=True)
|
||||
with open(token_file, "w", encoding="utf-8") as f:
|
||||
json.dump(tokens, f, indent=2)
|
||||
logger.info(f"Saved OAuth tokens to {token_file}")
|
||||
|
||||
# Attempt to connect the MCP server now
|
||||
args = json.loads(srv.args) if srv.args else []
|
||||
env = json.loads(srv.env) if srv.env else {}
|
||||
connected = await mcp_manager.connect_server(
|
||||
server_id=server_id,
|
||||
name=srv.name,
|
||||
transport=srv.transport,
|
||||
command=srv.command,
|
||||
args=args,
|
||||
env=env,
|
||||
url=srv.url,
|
||||
)
|
||||
|
||||
if connected:
|
||||
status = mcp_manager.get_server_status(server_id)
|
||||
tool_count = status.get("tool_count", 0)
|
||||
return HTMLResponse(_oauth_result_page(
|
||||
"Authorization Successful",
|
||||
f"{srv.name} connected with {tool_count} tools. You can close this window.",
|
||||
success=True,
|
||||
))
|
||||
else:
|
||||
status = mcp_manager.get_server_status(server_id)
|
||||
return HTMLResponse(_oauth_result_page(
|
||||
"Authorized but Connection Failed",
|
||||
f"Tokens saved, but the server failed to connect: {status.get('error', 'unknown error')}. Try reconnecting from Settings.",
|
||||
))
|
||||
except HTTPException as e:
|
||||
logger.warning(f"OAuth callback rejected: {e.detail}")
|
||||
return HTMLResponse(_oauth_result_page("Error", str(e.detail)), status_code=e.status_code)
|
||||
except Exception as e:
|
||||
logger.exception(f"OAuth callback error: {e}")
|
||||
return HTMLResponse(_oauth_result_page("Error", str(e)), status_code=500)
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
return router
|
||||
|
||||
|
||||
def _oauth_authorize_page(
|
||||
auth_url: str,
|
||||
server_id: str,
|
||||
host: str,
|
||||
redirect_uri: str = "http://localhost:7000/api/mcp/oauth/callback",
|
||||
) -> str:
|
||||
"""Page with Google sign-in link and URL paste-back form for remote access."""
|
||||
# Escape values interpolated into the page: `host` comes from the request
|
||||
# Host header and `server_id` from the OAuth state — neither is trusted.
|
||||
auth_url = html.escape(auth_url, quote=True)
|
||||
server_id = html.escape(server_id, quote=True)
|
||||
host = html.escape(host, quote=True)
|
||||
redirect_uri = html.escape(redirect_uri, quote=True)
|
||||
return f"""<!DOCTYPE html>
|
||||
<html><head>
|
||||
<meta charset="UTF-8"><title>Authorize — Odysseus</title>
|
||||
<style>
|
||||
body {{ font-family: 'Fira Code', monospace; background: #0f0f0f; color: #e0e0e0;
|
||||
display: flex; justify-content: center; align-items: center; min-height: 100vh; }}
|
||||
.card {{ background: #1a1a1a; border: 1px solid #333; border-radius: 12px;
|
||||
padding: 2rem; max-width: 480px; text-align: center; }}
|
||||
h2 {{ color: #e06c75; margin-bottom: 0.5rem; font-size: 1.1rem; }}
|
||||
p {{ color: #aaa; font-size: 0.82rem; line-height: 1.6; margin: 0.8rem 0; }}
|
||||
.step {{ text-align: left; color: #ccc; font-size: 0.82rem; line-height: 1.7; margin: 1rem 0; }}
|
||||
.step b {{ color: #e06c75; }}
|
||||
a.auth-link {{
|
||||
display: inline-block; margin: 1rem 0; padding: 0.6rem 1.5rem;
|
||||
background: #e06c75; color: #fff; text-decoration: none; border-radius: 6px;
|
||||
font-weight: 600; font-size: 0.9rem;
|
||||
}}
|
||||
a.auth-link:hover {{ background: #c55; }}
|
||||
input[type=text] {{
|
||||
width: 100%; padding: 0.5rem; margin: 0.5rem 0;
|
||||
background: #0f0f0f; border: 1px solid #333; border-radius: 6px;
|
||||
color: #e0e0e0; font-family: 'Fira Code', monospace; font-size: 0.8rem;
|
||||
}}
|
||||
input:focus {{ outline: none; border-color: #e06c75; }}
|
||||
button {{
|
||||
padding: 0.5rem 1.5rem; border: none; border-radius: 6px;
|
||||
background: #e06c75; color: #fff; font-weight: 600; cursor: pointer;
|
||||
font-family: 'Fira Code', monospace; font-size: 0.85rem; margin-top: 0.3rem;
|
||||
}}
|
||||
button:hover {{ background: #c55; }}
|
||||
.divider {{ border-top: 1px solid #333; margin: 1.2rem 0; }}
|
||||
</style></head>
|
||||
<body><div class="card">
|
||||
<h2>Authorize Google Account</h2>
|
||||
<div class="step">
|
||||
<b>1.</b> Click the button below to sign in with Google<br>
|
||||
<b>2.</b> After approving, your browser will show an error page — that's normal<br>
|
||||
<b>3.</b> Copy the full URL from your browser's address bar<br>
|
||||
<b>4.</b> Paste it below and click Connect
|
||||
</div>
|
||||
<a class="auth-link" href="{auth_url}" target="_blank" rel="noopener">Sign in with Google</a>
|
||||
<div class="divider"></div>
|
||||
<form method="POST" action="http://{host}/api/mcp/oauth/exchange/{server_id}">
|
||||
<p>Paste the URL from your browser after signing in:</p>
|
||||
<input type="text" name="callback_url" placeholder="{redirect_uri}?code=..." required>
|
||||
<br><button type="submit">Connect</button>
|
||||
</form>
|
||||
</div></body></html>"""
|
||||
|
||||
|
||||
def _oauth_result_page(title: str, message: str, success: bool = False) -> str:
|
||||
"""Generate a simple HTML page for the OAuth result."""
|
||||
safe_title = html.escape(title)
|
||||
safe_message = html.escape(message)
|
||||
color = "#00661a" if success else "#e06c75"
|
||||
icon = "✓" if success else "✗"
|
||||
return f"""<!DOCTYPE html>
|
||||
<html><head>
|
||||
<meta charset="UTF-8"><title>{safe_title}</title>
|
||||
<style>
|
||||
body {{ font-family: 'Fira Code', monospace; background: #0f0f0f; color: #e0e0e0;
|
||||
display: flex; justify-content: center; align-items: center; min-height: 100vh; }}
|
||||
.card {{ background: #1a1a1a; border: 1px solid #333; border-radius: 12px;
|
||||
padding: 2rem; max-width: 420px; text-align: center; }}
|
||||
.icon {{ font-size: 3rem; color: {color}; margin-bottom: 1rem; }}
|
||||
h2 {{ color: {color}; margin-bottom: 0.5rem; font-size: 1.1rem; }}
|
||||
p {{ color: #aaa; font-size: 0.85rem; line-height: 1.5; }}
|
||||
</style></head>
|
||||
<body><div class="card">
|
||||
<div class="icon">{icon}</div>
|
||||
<h2>{safe_title}</h2>
|
||||
<p>{safe_message}</p>
|
||||
</div></body></html>"""
|
||||
+14
-693
@@ -1,697 +1,18 @@
|
||||
# routes/mcp_routes.py
|
||||
"""MCP (Model Context Protocol) server management routes."""
|
||||
import json
|
||||
import os
|
||||
import uuid
|
||||
import urllib.parse
|
||||
import html
|
||||
from pathlib import Path
|
||||
from fastapi import APIRouter, Form, HTTPException, Request
|
||||
from fastapi.responses import RedirectResponse, HTMLResponse
|
||||
import logging
|
||||
import httpx
|
||||
"""Backward-compat shim — canonical location is routes/mcp/mcp_routes.py.
|
||||
|
||||
from core.database import McpServer, SessionLocal
|
||||
from core.middleware import require_admin
|
||||
from src.constants import DATA_DIR, MCP_OAUTH_DIR
|
||||
from src.mcp_manager import McpManager
|
||||
This module is replaced in ``sys.modules`` by the canonical module object so
|
||||
that ``import routes.mcp_routes``, ``from routes.mcp_routes import X``,
|
||||
``importlib.import_module("routes.mcp_routes")``, the
|
||||
``sys.modules.pop("routes.mcp_routes")`` + re-import pattern in
|
||||
test_security_regressions.py, and the ``monkeypatch.setattr(mcp_routes,
|
||||
"MCP_OAUTH_DIR", ...)`` pattern all operate on the *same* object. This also
|
||||
makes ``mcp_routes.__file__`` resolve to the canonical file (which the
|
||||
source-introspection at line 839 reads). Keeps existing import paths working
|
||||
after slice 2o (#4082/#4071).
|
||||
"""
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
import sys as _sys
|
||||
|
||||
router = APIRouter(prefix="/api/mcp", tags=["mcp"])
|
||||
from routes.mcp import mcp_routes as _canonical # noqa: F401
|
||||
|
||||
|
||||
def _mcp_oauth_base_dir() -> Path:
|
||||
"""Directory that may contain OAuth files managed by Odysseus."""
|
||||
return Path(MCP_OAUTH_DIR).resolve(strict=False)
|
||||
|
||||
|
||||
def _resolve_mcp_oauth_path(raw_path, field_name: str) -> str:
|
||||
"""Resolve an MCP OAuth path and keep it under DATA_DIR/mcp_oauth."""
|
||||
raw = str(raw_path or "").strip()
|
||||
if not raw:
|
||||
return ""
|
||||
|
||||
base = _mcp_oauth_base_dir()
|
||||
path = Path(os.path.expanduser(raw))
|
||||
if not path.is_absolute():
|
||||
path = base / path
|
||||
resolved = path.resolve(strict=False)
|
||||
|
||||
try:
|
||||
resolved.relative_to(base)
|
||||
except ValueError as exc:
|
||||
raise HTTPException(
|
||||
400,
|
||||
f"Invalid OAuth {field_name}: path must stay under {base}",
|
||||
) from exc
|
||||
return str(resolved)
|
||||
|
||||
|
||||
def _sanitize_mcp_oauth_config(oauth_cfg):
|
||||
"""Return an OAuth config copy with file paths confined to mcp_oauth."""
|
||||
if not oauth_cfg:
|
||||
return oauth_cfg
|
||||
if not isinstance(oauth_cfg, dict):
|
||||
return {}
|
||||
sanitized = dict(oauth_cfg)
|
||||
for field_name in ("keys_file", "token_file"):
|
||||
if sanitized.get(field_name):
|
||||
sanitized[field_name] = _resolve_mcp_oauth_path(
|
||||
sanitized[field_name],
|
||||
field_name,
|
||||
)
|
||||
return sanitized
|
||||
|
||||
|
||||
def _mcp_oauth_token_missing(oauth_cfg, *, strict: bool = True) -> bool:
|
||||
"""Check token existence without letting legacy bad paths break listing."""
|
||||
if not isinstance(oauth_cfg, dict):
|
||||
return False
|
||||
try:
|
||||
token_file = _resolve_mcp_oauth_path(oauth_cfg.get("token_file", ""), "token_file")
|
||||
except HTTPException:
|
||||
if strict:
|
||||
raise
|
||||
logger.warning("Ignoring MCP OAuth config with unsafe token_file")
|
||||
return True
|
||||
return bool(token_file and not os.path.exists(token_file))
|
||||
|
||||
|
||||
def _apply_mcp_oauth_env(env: dict, oauth_cfg) -> None:
|
||||
"""Pass sanitized Gmail package paths to MCP servers that honor them."""
|
||||
if not oauth_cfg or not isinstance(env, dict):
|
||||
return
|
||||
keys_file = oauth_cfg.get("keys_file")
|
||||
token_file = oauth_cfg.get("token_file")
|
||||
if keys_file:
|
||||
env["GMAIL_OAUTH_PATH"] = keys_file
|
||||
if token_file:
|
||||
env["GMAIL_CREDENTIALS_PATH"] = token_file
|
||||
|
||||
|
||||
def _load_disabled_map():
|
||||
"""Load per-server disabled tool sets from DB."""
|
||||
db = SessionLocal()
|
||||
try:
|
||||
disabled_map = {}
|
||||
for srv in db.query(McpServer).all():
|
||||
if srv.disabled_tools:
|
||||
try:
|
||||
names = json.loads(srv.disabled_tools)
|
||||
if names:
|
||||
disabled_map[srv.id] = set(names)
|
||||
except (json.JSONDecodeError, TypeError):
|
||||
pass
|
||||
return disabled_map
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
|
||||
def _mcp_oauth_redirect_uri() -> str:
|
||||
"""Shared callback URL for legacy Google and generic MCP OAuth flows."""
|
||||
from src.mcp_oauth import REDIRECT_URI
|
||||
return REDIRECT_URI
|
||||
|
||||
|
||||
def setup_mcp_routes(mcp_manager: McpManager):
|
||||
"""Setup MCP routes with the provided manager."""
|
||||
|
||||
@router.get("/servers")
|
||||
def list_servers(request: Request):
|
||||
"""List all configured MCP servers with connection status."""
|
||||
require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
servers = db.query(McpServer).all()
|
||||
result = []
|
||||
for srv in servers:
|
||||
status = mcp_manager.get_server_status(srv.id)
|
||||
oauth_cfg = json.loads(srv.oauth_config) if srv.oauth_config else None
|
||||
needs_oauth = False
|
||||
if oauth_cfg:
|
||||
needs_oauth = _mcp_oauth_token_missing(oauth_cfg, strict=False)
|
||||
disabled_list = json.loads(srv.disabled_tools) if srv.disabled_tools else []
|
||||
total_tools = status.get("tool_count", 0)
|
||||
result.append({
|
||||
"id": srv.id,
|
||||
"name": srv.name,
|
||||
"transport": srv.transport,
|
||||
"command": srv.command,
|
||||
"args": json.loads(srv.args) if srv.args else [],
|
||||
"env": json.loads(srv.env) if srv.env else {},
|
||||
"url": srv.url,
|
||||
"is_enabled": srv.is_enabled,
|
||||
"status": status.get("status", "disconnected"),
|
||||
"tool_count": total_tools,
|
||||
"disabled_tool_count": len(disabled_list),
|
||||
"enabled_tool_count": max(0, total_tools - len(disabled_list)),
|
||||
"error": status.get("error"),
|
||||
"auth_url": status.get("auth_url"),
|
||||
"has_oauth": oauth_cfg is not None,
|
||||
"needs_oauth": needs_oauth,
|
||||
})
|
||||
return result
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.post("/servers")
|
||||
async def add_server(
|
||||
request: Request,
|
||||
name: str = Form(...),
|
||||
transport: str = Form("stdio"),
|
||||
command: str = Form(None),
|
||||
args: str = Form("[]"),
|
||||
env: str = Form("{}"),
|
||||
url: str = Form(None),
|
||||
oauth_file: str = Form(None),
|
||||
oauth_config: str = Form(None),
|
||||
):
|
||||
"""Add a new MCP server config and attempt connection. Admin-only:
|
||||
registering a stdio server is equivalent to executing arbitrary
|
||||
binaries on the host."""
|
||||
require_admin(request)
|
||||
server_id = str(uuid.uuid4())[:8]
|
||||
|
||||
# Validate
|
||||
if transport == "stdio" and not command:
|
||||
raise HTTPException(400, "command is required for stdio transport")
|
||||
if transport == "sse" and not url:
|
||||
raise HTTPException(400, "url is required for SSE transport")
|
||||
if transport == "http" and not url:
|
||||
raise HTTPException(400, "url is required for HTTP transport")
|
||||
|
||||
# Parse JSON fields
|
||||
try:
|
||||
parsed_args = json.loads(args) if args else []
|
||||
except json.JSONDecodeError:
|
||||
parsed_args = []
|
||||
try:
|
||||
parsed_env = json.loads(env) if env else {}
|
||||
except json.JSONDecodeError:
|
||||
parsed_env = {}
|
||||
if not isinstance(parsed_env, dict):
|
||||
parsed_env = {}
|
||||
|
||||
# Parse OAuth config
|
||||
parsed_oauth_config = None
|
||||
if oauth_config:
|
||||
try:
|
||||
parsed_oauth_config = _sanitize_mcp_oauth_config(json.loads(oauth_config))
|
||||
except json.JSONDecodeError:
|
||||
pass
|
||||
_apply_mcp_oauth_env(parsed_env, parsed_oauth_config)
|
||||
|
||||
# Write OAuth credentials file if provided (for Google MCP servers)
|
||||
logger.info(f"MCP add_server: oauth_file={oauth_file!r}")
|
||||
if oauth_file:
|
||||
try:
|
||||
oauth_data = json.loads(oauth_file)
|
||||
oauth_dir = _resolve_mcp_oauth_path(oauth_data.get("dir", ""), "dir")
|
||||
oauth_filename = oauth_data.get("filename", "")
|
||||
client_id = oauth_data.get("client_id", "")
|
||||
client_secret = oauth_data.get("client_secret", "")
|
||||
if oauth_dir and oauth_filename and client_id and client_secret:
|
||||
filepath = _resolve_mcp_oauth_path(
|
||||
Path(oauth_dir) / str(oauth_filename),
|
||||
"filename",
|
||||
)
|
||||
os.makedirs(os.path.dirname(filepath), exist_ok=True)
|
||||
creds = {
|
||||
"installed": {
|
||||
"client_id": client_id,
|
||||
"client_secret": client_secret,
|
||||
"redirect_uris": ["http://localhost"],
|
||||
"auth_uri": "https://accounts.google.com/o/oauth2/auth",
|
||||
"token_uri": "https://accounts.google.com/o/oauth2/token",
|
||||
}
|
||||
}
|
||||
with open(filepath, "w", encoding="utf-8") as f:
|
||||
json.dump(creds, f, indent=2)
|
||||
logger.info(f"Wrote OAuth credentials to {filepath}")
|
||||
parsed_env.pop("GOOGLE_CLIENT_ID", None)
|
||||
parsed_env.pop("GOOGLE_CLIENT_SECRET", None)
|
||||
except (json.JSONDecodeError, OSError) as e:
|
||||
logger.warning(f"Failed to write OAuth file: {e}")
|
||||
|
||||
# Save to DB
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = McpServer(
|
||||
id=server_id,
|
||||
name=name,
|
||||
transport=transport,
|
||||
command=command,
|
||||
args=json.dumps(parsed_args),
|
||||
env=json.dumps(parsed_env),
|
||||
url=url,
|
||||
is_enabled=True,
|
||||
oauth_config=json.dumps(parsed_oauth_config) if parsed_oauth_config else None,
|
||||
)
|
||||
db.add(srv)
|
||||
db.commit()
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
# Check if OAuth token already exists — skip connection attempt if not
|
||||
needs_oauth = False
|
||||
if parsed_oauth_config:
|
||||
needs_oauth = _mcp_oauth_token_missing(parsed_oauth_config)
|
||||
|
||||
connected = False
|
||||
if not needs_oauth:
|
||||
connected = await mcp_manager.connect_server(
|
||||
server_id=server_id,
|
||||
name=name,
|
||||
transport=transport,
|
||||
command=command,
|
||||
args=parsed_args,
|
||||
env=parsed_env,
|
||||
url=url,
|
||||
)
|
||||
|
||||
status = mcp_manager.get_server_status(server_id)
|
||||
needs_auth = status.get("status") == "needs_auth"
|
||||
return {
|
||||
"id": server_id,
|
||||
"name": name,
|
||||
"connected": connected,
|
||||
"status": "needs_oauth" if needs_oauth else status.get("status", "disconnected"),
|
||||
"tool_count": status.get("tool_count", 0),
|
||||
"error": "OAuth authorization required" if needs_oauth else status.get("error"),
|
||||
"needs_oauth": needs_oauth,
|
||||
"needs_auth": needs_auth,
|
||||
"auth_url": status.get("auth_url"),
|
||||
}
|
||||
|
||||
@router.post("/servers/{server_id}/reconnect")
|
||||
async def reconnect_server(server_id: str, request: Request):
|
||||
"""Reconnect to an MCP server."""
|
||||
require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = db.query(McpServer).filter(McpServer.id == server_id).first()
|
||||
if not srv:
|
||||
raise HTTPException(404, "Server not found")
|
||||
|
||||
await mcp_manager.disconnect_server(server_id)
|
||||
|
||||
args = json.loads(srv.args) if srv.args else []
|
||||
env = json.loads(srv.env) if srv.env else {}
|
||||
connected = await mcp_manager.connect_server(
|
||||
server_id=server_id,
|
||||
name=srv.name,
|
||||
transport=srv.transport,
|
||||
command=srv.command,
|
||||
args=args,
|
||||
env=env,
|
||||
url=srv.url,
|
||||
)
|
||||
|
||||
status = mcp_manager.get_server_status(server_id)
|
||||
return {
|
||||
"connected": connected,
|
||||
"status": status.get("status", "disconnected"),
|
||||
"tool_count": status.get("tool_count", 0),
|
||||
"error": status.get("error"),
|
||||
"auth_url": status.get("auth_url"),
|
||||
"needs_auth": status.get("status") == "needs_auth",
|
||||
}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.patch("/servers/{server_id}")
|
||||
async def toggle_server(server_id: str, request: Request, is_enabled: str = Form(...)):
|
||||
"""Enable or disable an MCP server."""
|
||||
require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = db.query(McpServer).filter(McpServer.id == server_id).first()
|
||||
if not srv:
|
||||
raise HTTPException(404, "Server not found")
|
||||
|
||||
enabled = str(is_enabled).lower() == "true"
|
||||
srv.is_enabled = enabled
|
||||
db.commit()
|
||||
|
||||
if enabled:
|
||||
args = json.loads(srv.args) if srv.args else []
|
||||
env = json.loads(srv.env) if srv.env else {}
|
||||
await mcp_manager.connect_server(
|
||||
server_id=server_id,
|
||||
name=srv.name,
|
||||
transport=srv.transport,
|
||||
command=srv.command,
|
||||
args=args,
|
||||
env=env,
|
||||
url=srv.url,
|
||||
)
|
||||
else:
|
||||
await mcp_manager.disconnect_server(server_id)
|
||||
|
||||
return {"id": server_id, "is_enabled": enabled}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.delete("/servers/{server_id}")
|
||||
async def delete_server(server_id: str, request: Request):
|
||||
"""Remove an MCP server."""
|
||||
require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = db.query(McpServer).filter(McpServer.id == server_id).first()
|
||||
if not srv:
|
||||
raise HTTPException(404, "Server not found")
|
||||
|
||||
await mcp_manager.disconnect_server(server_id)
|
||||
|
||||
db.delete(srv)
|
||||
db.commit()
|
||||
return {"status": "deleted"}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.get("/tools")
|
||||
def list_tools(request: Request):
|
||||
"""List all discovered MCP tools across all connected servers."""
|
||||
require_admin(request)
|
||||
disabled_map = _load_disabled_map()
|
||||
return mcp_manager.get_all_tools(disabled_map)
|
||||
|
||||
@router.get("/servers/{server_id}/tools")
|
||||
def list_server_tools(server_id: str, request: Request):
|
||||
"""List all tools for a specific MCP server with enabled/disabled state."""
|
||||
require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = db.query(McpServer).filter(McpServer.id == server_id).first()
|
||||
if not srv:
|
||||
raise HTTPException(404, "Server not found")
|
||||
disabled_list = json.loads(srv.disabled_tools) if srv.disabled_tools else []
|
||||
disabled_set = set(disabled_list)
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
all_tools = mcp_manager.get_all_tools()
|
||||
server_tools = [t for t in all_tools if t["server_id"] == server_id]
|
||||
for t in server_tools:
|
||||
t["is_disabled"] = t["name"] in disabled_set
|
||||
return server_tools
|
||||
|
||||
@router.patch("/servers/{server_id}/tools")
|
||||
async def update_disabled_tools(server_id: str, request: Request):
|
||||
"""Bulk update disabled tools list for a server.
|
||||
|
||||
Expects JSON body: {"disabled": ["tool_name_1", "tool_name_2"]}
|
||||
"""
|
||||
require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = db.query(McpServer).filter(McpServer.id == server_id).first()
|
||||
if not srv:
|
||||
raise HTTPException(404, "Server not found")
|
||||
|
||||
body = await request.json()
|
||||
disabled = body.get("disabled", [])
|
||||
if not isinstance(disabled, list):
|
||||
raise HTTPException(400, "disabled must be a list of tool names")
|
||||
|
||||
srv.disabled_tools = json.dumps(disabled) if disabled else None
|
||||
db.commit()
|
||||
|
||||
return {"id": server_id, "disabled_count": len(disabled)}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
# ── OAuth flow for Google MCP servers ──────────────────────────
|
||||
|
||||
@router.get("/oauth/authorize/{server_id}")
|
||||
def oauth_authorize(server_id: str, request: Request):
|
||||
"""Show OAuth authorization page with Google sign-in link."""
|
||||
require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = db.query(McpServer).filter(McpServer.id == server_id).first()
|
||||
if not srv:
|
||||
raise HTTPException(404, "Server not found")
|
||||
if not srv.oauth_config:
|
||||
raise HTTPException(400, "Server has no OAuth config")
|
||||
|
||||
oauth_cfg = _sanitize_mcp_oauth_config(json.loads(srv.oauth_config))
|
||||
keys_file = oauth_cfg.get("keys_file", "")
|
||||
if not keys_file or not os.path.exists(keys_file):
|
||||
raise HTTPException(400, "OAuth keys file not found")
|
||||
|
||||
with open(keys_file, encoding="utf-8") as f:
|
||||
keys_data = json.load(f)
|
||||
keys = keys_data.get("installed") or keys_data.get("web")
|
||||
if not keys:
|
||||
raise HTTPException(400, "Invalid OAuth keys file format")
|
||||
|
||||
client_id = keys["client_id"]
|
||||
scopes = oauth_cfg.get("scopes", [])
|
||||
|
||||
# For Desktop App creds, default to localhost — the user will
|
||||
# paste the resulting URL back if they're on a different device.
|
||||
redirect_uri = _mcp_oauth_redirect_uri()
|
||||
|
||||
params = {
|
||||
"client_id": client_id,
|
||||
"redirect_uri": redirect_uri,
|
||||
"response_type": "code",
|
||||
"scope": " ".join(scopes),
|
||||
"access_type": "offline",
|
||||
"prompt": "consent",
|
||||
"state": server_id,
|
||||
}
|
||||
auth_url = "https://accounts.google.com/o/oauth2/v2/auth?" + urllib.parse.urlencode(params)
|
||||
|
||||
# Determine if user is accessing from the same machine
|
||||
host = request.headers.get("host", "")
|
||||
is_local = host.startswith("localhost") or host.startswith("127.0.0.1")
|
||||
|
||||
if is_local:
|
||||
# Same machine — just redirect, callback will work directly
|
||||
return RedirectResponse(auth_url)
|
||||
else:
|
||||
# Remote device — show paste-back page
|
||||
return HTMLResponse(_oauth_authorize_page(auth_url, server_id, host, redirect_uri))
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.get("/oauth/callback")
|
||||
async def oauth_callback(code: str, state: str, request: Request):
|
||||
"""Handle OAuth callback. Generic MCP OAuth flows resolve via the
|
||||
pending-state registry; Google flows fall through to the legacy path."""
|
||||
require_admin(request)
|
||||
from src.mcp_oauth import resolve_pending
|
||||
if resolve_pending(state, code):
|
||||
return HTMLResponse(_oauth_result_page(
|
||||
"Authorization Successful",
|
||||
"The MCP server is connecting. You can close this window and return to Odysseus.",
|
||||
success=True,
|
||||
))
|
||||
# Legacy Google path: state is the server_id
|
||||
return await _exchange_and_connect(state, code, request)
|
||||
|
||||
@router.post("/oauth/exchange/{server_id}")
|
||||
async def oauth_exchange(server_id: str, request: Request, callback_url: str = Form(...)):
|
||||
"""Manual code exchange — user pastes the callback URL from their browser."""
|
||||
require_admin(request)
|
||||
try:
|
||||
parsed = urllib.parse.urlparse(callback_url)
|
||||
params = urllib.parse.parse_qs(parsed.query)
|
||||
code = params.get("code", [None])[0]
|
||||
if not code:
|
||||
return HTMLResponse(_oauth_result_page("Error", "No authorization code found in the URL. Make sure you copied the full URL from your browser."), status_code=400)
|
||||
except Exception:
|
||||
return HTMLResponse(_oauth_result_page("Error", "Invalid URL format."), status_code=400)
|
||||
|
||||
# Generic MCP OAuth: if the pasted URL carries a state we are waiting on,
|
||||
# resolve it directly (the background connect finishes the handshake).
|
||||
state = params.get("state", [None])[0]
|
||||
from src.mcp_oauth import resolve_pending
|
||||
if state and resolve_pending(state, code):
|
||||
return HTMLResponse(_oauth_result_page(
|
||||
"Authorization Successful",
|
||||
"The MCP server is connecting. You can close this window and return to Odysseus.",
|
||||
success=True,
|
||||
))
|
||||
|
||||
return await _exchange_and_connect(server_id, code, request)
|
||||
|
||||
async def _exchange_and_connect(server_id: str, code: str, request: Request):
|
||||
"""Exchange auth code for tokens and connect the MCP server."""
|
||||
db = SessionLocal()
|
||||
try:
|
||||
srv = db.query(McpServer).filter(McpServer.id == server_id).first()
|
||||
if not srv:
|
||||
return HTMLResponse(_oauth_result_page("Error", "Server not found."), status_code=404)
|
||||
if not srv.oauth_config:
|
||||
return HTMLResponse(_oauth_result_page("Error", "No OAuth config."), status_code=400)
|
||||
|
||||
oauth_cfg = _sanitize_mcp_oauth_config(json.loads(srv.oauth_config))
|
||||
keys_file = oauth_cfg.get("keys_file", "")
|
||||
token_file = oauth_cfg.get("token_file", "")
|
||||
if not keys_file or not token_file:
|
||||
raise HTTPException(400, "OAuth keys/token file not configured")
|
||||
|
||||
with open(keys_file, encoding="utf-8") as f:
|
||||
keys_data = json.load(f)
|
||||
keys = keys_data.get("installed") or keys_data.get("web")
|
||||
client_id = keys["client_id"]
|
||||
client_secret = keys["client_secret"]
|
||||
|
||||
redirect_uri = _mcp_oauth_redirect_uri()
|
||||
|
||||
async with httpx.AsyncClient() as client:
|
||||
resp = await client.post(
|
||||
"https://oauth2.googleapis.com/token",
|
||||
data={
|
||||
"code": code,
|
||||
"client_id": client_id,
|
||||
"client_secret": client_secret,
|
||||
"redirect_uri": redirect_uri,
|
||||
"grant_type": "authorization_code",
|
||||
},
|
||||
)
|
||||
|
||||
if resp.status_code != 200:
|
||||
err = resp.text
|
||||
logger.error(f"OAuth token exchange failed: {err}")
|
||||
return HTMLResponse(_oauth_result_page("Authorization Failed", f"Google returned an error: {err}"), status_code=400)
|
||||
|
||||
tokens = resp.json()
|
||||
logger.info(f"OAuth tokens received for server {server_id}")
|
||||
|
||||
# Save tokens to the file the MCP package expects
|
||||
os.makedirs(os.path.dirname(token_file), exist_ok=True)
|
||||
with open(token_file, "w", encoding="utf-8") as f:
|
||||
json.dump(tokens, f, indent=2)
|
||||
logger.info(f"Saved OAuth tokens to {token_file}")
|
||||
|
||||
# Attempt to connect the MCP server now
|
||||
args = json.loads(srv.args) if srv.args else []
|
||||
env = json.loads(srv.env) if srv.env else {}
|
||||
connected = await mcp_manager.connect_server(
|
||||
server_id=server_id,
|
||||
name=srv.name,
|
||||
transport=srv.transport,
|
||||
command=srv.command,
|
||||
args=args,
|
||||
env=env,
|
||||
url=srv.url,
|
||||
)
|
||||
|
||||
if connected:
|
||||
status = mcp_manager.get_server_status(server_id)
|
||||
tool_count = status.get("tool_count", 0)
|
||||
return HTMLResponse(_oauth_result_page(
|
||||
"Authorization Successful",
|
||||
f"{srv.name} connected with {tool_count} tools. You can close this window.",
|
||||
success=True,
|
||||
))
|
||||
else:
|
||||
status = mcp_manager.get_server_status(server_id)
|
||||
return HTMLResponse(_oauth_result_page(
|
||||
"Authorized but Connection Failed",
|
||||
f"Tokens saved, but the server failed to connect: {status.get('error', 'unknown error')}. Try reconnecting from Settings.",
|
||||
))
|
||||
except HTTPException as e:
|
||||
logger.warning(f"OAuth callback rejected: {e.detail}")
|
||||
return HTMLResponse(_oauth_result_page("Error", str(e.detail)), status_code=e.status_code)
|
||||
except Exception as e:
|
||||
logger.exception(f"OAuth callback error: {e}")
|
||||
return HTMLResponse(_oauth_result_page("Error", str(e)), status_code=500)
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
return router
|
||||
|
||||
|
||||
def _oauth_authorize_page(
|
||||
auth_url: str,
|
||||
server_id: str,
|
||||
host: str,
|
||||
redirect_uri: str = "http://localhost:7000/api/mcp/oauth/callback",
|
||||
) -> str:
|
||||
"""Page with Google sign-in link and URL paste-back form for remote access."""
|
||||
# Escape values interpolated into the page: `host` comes from the request
|
||||
# Host header and `server_id` from the OAuth state — neither is trusted.
|
||||
auth_url = html.escape(auth_url, quote=True)
|
||||
server_id = html.escape(server_id, quote=True)
|
||||
host = html.escape(host, quote=True)
|
||||
redirect_uri = html.escape(redirect_uri, quote=True)
|
||||
return f"""<!DOCTYPE html>
|
||||
<html><head>
|
||||
<meta charset="UTF-8"><title>Authorize — Odysseus</title>
|
||||
<style>
|
||||
body {{ font-family: 'Fira Code', monospace; background: #0f0f0f; color: #e0e0e0;
|
||||
display: flex; justify-content: center; align-items: center; min-height: 100vh; }}
|
||||
.card {{ background: #1a1a1a; border: 1px solid #333; border-radius: 12px;
|
||||
padding: 2rem; max-width: 480px; text-align: center; }}
|
||||
h2 {{ color: #e06c75; margin-bottom: 0.5rem; font-size: 1.1rem; }}
|
||||
p {{ color: #aaa; font-size: 0.82rem; line-height: 1.6; margin: 0.8rem 0; }}
|
||||
.step {{ text-align: left; color: #ccc; font-size: 0.82rem; line-height: 1.7; margin: 1rem 0; }}
|
||||
.step b {{ color: #e06c75; }}
|
||||
a.auth-link {{
|
||||
display: inline-block; margin: 1rem 0; padding: 0.6rem 1.5rem;
|
||||
background: #e06c75; color: #fff; text-decoration: none; border-radius: 6px;
|
||||
font-weight: 600; font-size: 0.9rem;
|
||||
}}
|
||||
a.auth-link:hover {{ background: #c55; }}
|
||||
input[type=text] {{
|
||||
width: 100%; padding: 0.5rem; margin: 0.5rem 0;
|
||||
background: #0f0f0f; border: 1px solid #333; border-radius: 6px;
|
||||
color: #e0e0e0; font-family: 'Fira Code', monospace; font-size: 0.8rem;
|
||||
}}
|
||||
input:focus {{ outline: none; border-color: #e06c75; }}
|
||||
button {{
|
||||
padding: 0.5rem 1.5rem; border: none; border-radius: 6px;
|
||||
background: #e06c75; color: #fff; font-weight: 600; cursor: pointer;
|
||||
font-family: 'Fira Code', monospace; font-size: 0.85rem; margin-top: 0.3rem;
|
||||
}}
|
||||
button:hover {{ background: #c55; }}
|
||||
.divider {{ border-top: 1px solid #333; margin: 1.2rem 0; }}
|
||||
</style></head>
|
||||
<body><div class="card">
|
||||
<h2>Authorize Google Account</h2>
|
||||
<div class="step">
|
||||
<b>1.</b> Click the button below to sign in with Google<br>
|
||||
<b>2.</b> After approving, your browser will show an error page — that's normal<br>
|
||||
<b>3.</b> Copy the full URL from your browser's address bar<br>
|
||||
<b>4.</b> Paste it below and click Connect
|
||||
</div>
|
||||
<a class="auth-link" href="{auth_url}" target="_blank" rel="noopener">Sign in with Google</a>
|
||||
<div class="divider"></div>
|
||||
<form method="POST" action="http://{host}/api/mcp/oauth/exchange/{server_id}">
|
||||
<p>Paste the URL from your browser after signing in:</p>
|
||||
<input type="text" name="callback_url" placeholder="{redirect_uri}?code=..." required>
|
||||
<br><button type="submit">Connect</button>
|
||||
</form>
|
||||
</div></body></html>"""
|
||||
|
||||
|
||||
def _oauth_result_page(title: str, message: str, success: bool = False) -> str:
|
||||
"""Generate a simple HTML page for the OAuth result."""
|
||||
safe_title = html.escape(title)
|
||||
safe_message = html.escape(message)
|
||||
color = "#00661a" if success else "#e06c75"
|
||||
icon = "✓" if success else "✗"
|
||||
return f"""<!DOCTYPE html>
|
||||
<html><head>
|
||||
<meta charset="UTF-8"><title>{safe_title}</title>
|
||||
<style>
|
||||
body {{ font-family: 'Fira Code', monospace; background: #0f0f0f; color: #e0e0e0;
|
||||
display: flex; justify-content: center; align-items: center; min-height: 100vh; }}
|
||||
.card {{ background: #1a1a1a; border: 1px solid #333; border-radius: 12px;
|
||||
padding: 2rem; max-width: 420px; text-align: center; }}
|
||||
.icon {{ font-size: 3rem; color: {color}; margin-bottom: 1rem; }}
|
||||
h2 {{ color: {color}; margin-bottom: 0.5rem; font-size: 1.1rem; }}
|
||||
p {{ color: #aaa; font-size: 0.85rem; line-height: 1.5; }}
|
||||
</style></head>
|
||||
<body><div class="card">
|
||||
<div class="icon">{icon}</div>
|
||||
<h2>{safe_title}</h2>
|
||||
<p>{safe_message}</p>
|
||||
</div></body></html>"""
|
||||
_sys.modules[__name__] = _canonical
|
||||
|
||||
@@ -21,7 +21,7 @@ def _strip_list_prefix(text: str) -> str:
|
||||
return text
|
||||
return _LIST_PREFIX_RE.sub("", text, count=1).strip()
|
||||
|
||||
from services.memory import MemoryManager
|
||||
from services.memory import MemoryManager, MemoryStoreUnreadable
|
||||
from core.session_manager import SessionManager
|
||||
from src.request_models import MemoryAddRequest
|
||||
from core.database import SessionLocal
|
||||
@@ -35,6 +35,22 @@ from src.upload_limits import read_upload_limited, MEMORY_IMPORT_MAX_BYTES
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _load_for_update(memory_manager) -> List[Dict[str, Any]]:
|
||||
"""Load the whole store for a read-modify-write cycle.
|
||||
|
||||
A transient read failure must not look like an empty store: the caller
|
||||
would append to ``[]`` and save that back, atomically destroying every
|
||||
existing memory (issue #5673). Surface it as a 503 and change nothing.
|
||||
"""
|
||||
try:
|
||||
return memory_manager.load_all_for_update()
|
||||
except MemoryStoreUnreadable as e:
|
||||
logger.error("Refusing to rewrite the memory store: %s", e)
|
||||
raise HTTPException(
|
||||
503, "Memory store is temporarily unreadable — no changes were made."
|
||||
)
|
||||
|
||||
|
||||
def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionManager, memory_vector=None):
|
||||
"""Set up memory-related routes."""
|
||||
router = APIRouter(prefix="/api/memory", tags=["memory"])
|
||||
@@ -116,7 +132,7 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
|
||||
new_entry = memory_manager.add_entry(text, memory_data.source, memory_data.category, owner=user)
|
||||
if memory_data.session_id:
|
||||
new_entry["session_id"] = memory_data.session_id
|
||||
all_mem = memory_manager.load_all()
|
||||
all_mem = _load_for_update(memory_manager)
|
||||
all_mem.append(new_entry)
|
||||
memory_manager.save(all_mem)
|
||||
# Sync vector index
|
||||
@@ -487,7 +503,7 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
|
||||
def pin_memory(request: Request, memory_id: str, pinned: bool = Form(True)):
|
||||
"""Pin or unpin a memory. Pinned memories are always included in context."""
|
||||
user = _owner(request)
|
||||
all_mem = memory_manager.load_all()
|
||||
all_mem = _load_for_update(memory_manager)
|
||||
for i, memory in enumerate(all_mem):
|
||||
if memory["id"] == memory_id:
|
||||
_verify_memory_owner(memory, user)
|
||||
@@ -512,7 +528,7 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
|
||||
def update_memory(request: Request, memory_id: str, text: str = Form(...), category: str = Form(None)):
|
||||
"""Update an existing memory item with new text and optional category."""
|
||||
user = _owner(request)
|
||||
all_mem = memory_manager.load_all()
|
||||
all_mem = _load_for_update(memory_manager)
|
||||
for i, memory in enumerate(all_mem):
|
||||
if memory["id"] == memory_id:
|
||||
_verify_memory_owner(memory, user)
|
||||
@@ -534,7 +550,7 @@ def setup_memory_routes(memory_manager: MemoryManager, session_manager: SessionM
|
||||
def delete_memory(request: Request, memory_id: str):
|
||||
"""Delete a memory item by its ID."""
|
||||
user = _owner(request)
|
||||
all_mem = memory_manager.load_all()
|
||||
all_mem = _load_for_update(memory_manager)
|
||||
|
||||
# Find and verify ownership before deleting
|
||||
target = next((m for m in all_mem if m["id"] == memory_id), None)
|
||||
|
||||
+2
-32
@@ -46,10 +46,11 @@ _ENDPOINT_SETTING_FIELDS = {
|
||||
}
|
||||
|
||||
_ENDPOINT_FALLBACK_FIELDS = {
|
||||
"default_model_fallbacks": "Default Model Fallbacks",
|
||||
"utility_model_fallbacks": "Utility Model Fallbacks",
|
||||
"vision_model_fallbacks": "Vision Model Fallbacks",
|
||||
}
|
||||
# `default_model_fallbacks` is intentionally absent. The legacy data remains
|
||||
# stored as-is even when an endpoint is removed, but no longer affects routing.
|
||||
|
||||
|
||||
def _speech_settings_using_endpoint(settings: dict, ep_id: str) -> list:
|
||||
@@ -2437,7 +2438,6 @@ def setup_model_routes(model_discovery):
|
||||
_user_prefs = _load_for_user(_user) or {}
|
||||
ep_id = (_user_prefs.get("default_endpoint_id") or "").strip()
|
||||
model = (_user_prefs.get("default_model") or "").strip()
|
||||
_fallbacks = _user_prefs.get("default_model_fallbacks") or []
|
||||
# If user has no personal default, fall back to global default
|
||||
# But only based on the "share_defaults_with_users" flag
|
||||
# (only if share_defaults_with_users is enabled)
|
||||
@@ -2446,12 +2446,9 @@ def setup_model_routes(model_discovery):
|
||||
ep_id = settings.get("default_endpoint_id", "")
|
||||
if not model:
|
||||
model = settings.get("default_model", "")
|
||||
if not _fallbacks:
|
||||
_fallbacks = settings.get("default_model_fallbacks") or []
|
||||
else:
|
||||
ep_id = settings.get("default_endpoint_id", "")
|
||||
model = settings.get("default_model", "")
|
||||
_fallbacks = settings.get("default_model_fallbacks") or []
|
||||
db = SessionLocal()
|
||||
try:
|
||||
ep = None
|
||||
@@ -2466,33 +2463,6 @@ def setup_model_routes(model_discovery):
|
||||
if _user and not _is_admin:
|
||||
ep_q = owner_filter(ep_q, ModelEndpoint, _user)
|
||||
ep = ep_q.first()
|
||||
# Configured fallback chain — when the chosen default endpoint is
|
||||
# gone/disabled, honor the user's configured `default_model_fallbacks`
|
||||
# in order BEFORE arbitrarily grabbing the first enabled endpoint.
|
||||
# (Previously this jumped straight to "first enabled", which is why
|
||||
# deleting/changing the main endpoint silently reassigned the default
|
||||
# chat to some unrelated endpoint instead of the fallback.)
|
||||
if not ep:
|
||||
for entry in _fallbacks:
|
||||
if not isinstance(entry, dict):
|
||||
continue
|
||||
fid = (entry.get("endpoint_id") or "").strip()
|
||||
if not fid:
|
||||
continue
|
||||
cand_q = db.query(ModelEndpoint).filter(
|
||||
ModelEndpoint.id == fid, ModelEndpoint.is_enabled == True
|
||||
)
|
||||
if _user and not _is_admin:
|
||||
cand_q = owner_filter(cand_q, ModelEndpoint, _user)
|
||||
cand = cand_q.first()
|
||||
if cand:
|
||||
ep = cand
|
||||
# Use the fallback entry's model. Reset even when empty
|
||||
# so we don't carry the prior endpoint's stale model onto
|
||||
# this fallback — the cached-models lookup below then
|
||||
# fills it from the fallback endpoint.
|
||||
model = (entry.get("model") or "").strip()
|
||||
break
|
||||
# Last resort: first enabled endpoint owned by THIS user. Do not
|
||||
# include null-owner/shared endpoints here: a brand-new user with
|
||||
# no explicit default should not auto-open a pending chat using an
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
"""User preferences API — per-user key/value store backed by a JSON file."""
|
||||
import json
|
||||
import os
|
||||
from typing import Optional
|
||||
from fastapi import APIRouter, Request
|
||||
from core.atomic_io import atomic_write_json
|
||||
from src.auth_helpers import get_current_user
|
||||
from src.constants import USER_PREFS_FILE
|
||||
|
||||
@@ -20,13 +20,7 @@ def _load():
|
||||
|
||||
|
||||
def _save(prefs):
|
||||
os.makedirs(os.path.dirname(PREFS_FILE) or ".", exist_ok=True)
|
||||
tmp = f"{PREFS_FILE}.tmp.{os.getpid()}"
|
||||
with open(tmp, "w", encoding="utf-8") as f:
|
||||
json.dump(prefs, f, indent=2)
|
||||
f.flush()
|
||||
os.fsync(f.fileno())
|
||||
os.replace(tmp, PREFS_FILE)
|
||||
atomic_write_json(PREFS_FILE, prefs, indent=2)
|
||||
|
||||
|
||||
def _load_for_user(user: Optional[str] = None) -> dict:
|
||||
|
||||
@@ -0,0 +1,5 @@
|
||||
"""Search route domain package (slice 2j, #4082/#4071).
|
||||
|
||||
Contains search_routes.py, migrated from the flat routes/ directory.
|
||||
Backward-compat shim at routes/search_routes.py re-exports from here.
|
||||
"""
|
||||
@@ -0,0 +1,111 @@
|
||||
"""Search routes — /api/search/config GET, /api/search POST."""
|
||||
|
||||
import logging
|
||||
from typing import Dict, Any
|
||||
|
||||
from fastapi import APIRouter, Request
|
||||
|
||||
import time
|
||||
|
||||
from services.search import get_search_config, comprehensive_web_search, PROVIDER_INFO
|
||||
from services.search.core import _call_provider
|
||||
from services.search.providers import _get_provider_key, _get_search_instance
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
async def _request_values(request: Request) -> Dict[str, Any]:
|
||||
"""Accept JSON, form data, or query params for search endpoints.
|
||||
|
||||
The browser UI posts FormData, while the agent's generic app_api tool
|
||||
posts JSON. FastAPI Form(...) rejects JSON with a 422 before our handler
|
||||
runs, which made the model think SearXNG was broken.
|
||||
"""
|
||||
values: Dict[str, Any] = dict(request.query_params)
|
||||
content_type = (request.headers.get("content-type") or "").lower()
|
||||
try:
|
||||
if "application/json" in content_type:
|
||||
body = await request.json()
|
||||
if isinstance(body, dict):
|
||||
values.update(body)
|
||||
else:
|
||||
form = await request.form()
|
||||
values.update(dict(form))
|
||||
except Exception:
|
||||
pass
|
||||
return values
|
||||
|
||||
|
||||
def setup_search_routes(config) -> APIRouter:
|
||||
router = APIRouter(tags=["search"])
|
||||
|
||||
@router.get("/api/search/config")
|
||||
async def get_search_settings() -> Dict[str, Any]:
|
||||
return get_search_config()
|
||||
|
||||
@router.post("/api/search")
|
||||
async def do_web_search(request: Request) -> Dict[str, Any]:
|
||||
"""Standalone web search — returns context string + source list.
|
||||
|
||||
Used by Compare mode to pre-search once and share results across panes.
|
||||
"""
|
||||
values = await _request_values(request)
|
||||
query = str(values.get("query") or values.get("q") or "").strip()
|
||||
if not query:
|
||||
return {"context": "", "sources": [], "error": "query is required"}
|
||||
time_filter = values.get("time_filter") or values.get("freshness")
|
||||
if time_filter is not None:
|
||||
time_filter = str(time_filter).strip() or None
|
||||
try:
|
||||
context, sources = comprehensive_web_search(
|
||||
query, return_sources=True, time_filter=time_filter,
|
||||
)
|
||||
return {"context": context, "sources": sources}
|
||||
except Exception as e:
|
||||
logger.error(f"Standalone web search failed: {e}")
|
||||
return {"context": "", "sources": [], "error": str(e)}
|
||||
|
||||
@router.get("/api/search/providers")
|
||||
async def list_search_providers():
|
||||
"""Return available search providers with config status."""
|
||||
providers = []
|
||||
for pid, (label, needs_key, needs_url) in PROVIDER_INFO.items():
|
||||
if pid == "disabled":
|
||||
continue
|
||||
available = True
|
||||
if needs_key and not _get_provider_key(pid):
|
||||
available = False
|
||||
if needs_url and pid == "searxng" and not _get_search_instance():
|
||||
available = False
|
||||
providers.append({
|
||||
"id": pid,
|
||||
"label": label,
|
||||
"available": available,
|
||||
})
|
||||
return providers
|
||||
|
||||
@router.post("/api/search/query")
|
||||
async def search_with_provider(request: Request) -> Dict[str, Any]:
|
||||
"""Search using a specific provider. Used by compare search mode."""
|
||||
values = await _request_values(request)
|
||||
query = str(values.get("query") or values.get("q") or "").strip()
|
||||
provider = str(values.get("provider") or "").strip()
|
||||
try:
|
||||
count = int(values.get("count") or values.get("limit") or 10)
|
||||
except Exception:
|
||||
count = 10
|
||||
if not query:
|
||||
return {"results": [], "provider": provider, "error": "query is required"}
|
||||
if provider not in PROVIDER_INFO or provider == "disabled":
|
||||
return {"results": [], "provider": provider, "error": "Unknown provider"}
|
||||
t0 = time.time()
|
||||
try:
|
||||
results = _call_provider(provider, query, min(count, 20))
|
||||
elapsed = round(time.time() - t0, 2)
|
||||
return {"results": results, "provider": provider, "time": elapsed}
|
||||
except Exception as e:
|
||||
elapsed = round(time.time() - t0, 2)
|
||||
logger.error(f"Search provider {provider} failed: {e}")
|
||||
return {"results": [], "provider": provider, "time": elapsed, "error": str(e)}
|
||||
|
||||
return router
|
||||
+9
-107
@@ -1,111 +1,13 @@
|
||||
"""Search routes — /api/search/config GET, /api/search POST."""
|
||||
"""Backward-compat shim — canonical location is routes/search/search_routes.py.
|
||||
|
||||
import logging
|
||||
from typing import Dict, Any
|
||||
This module is replaced in ``sys.modules`` by the canonical module object so
|
||||
that ``import routes.search_routes`` and ``from routes.search_routes import X``
|
||||
keep resolving to the canonical module. Keeps existing import paths working
|
||||
after slice 2j (#4082/#4071).
|
||||
"""
|
||||
|
||||
from fastapi import APIRouter, Request
|
||||
import sys as _sys
|
||||
|
||||
import time
|
||||
from routes.search import search_routes as _canonical # noqa: F401
|
||||
|
||||
from services.search import get_search_config, comprehensive_web_search, PROVIDER_INFO
|
||||
from services.search.core import _call_provider
|
||||
from services.search.providers import _get_provider_key, _get_search_instance
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
async def _request_values(request: Request) -> Dict[str, Any]:
|
||||
"""Accept JSON, form data, or query params for search endpoints.
|
||||
|
||||
The browser UI posts FormData, while the agent's generic app_api tool
|
||||
posts JSON. FastAPI Form(...) rejects JSON with a 422 before our handler
|
||||
runs, which made the model think SearXNG was broken.
|
||||
"""
|
||||
values: Dict[str, Any] = dict(request.query_params)
|
||||
content_type = (request.headers.get("content-type") or "").lower()
|
||||
try:
|
||||
if "application/json" in content_type:
|
||||
body = await request.json()
|
||||
if isinstance(body, dict):
|
||||
values.update(body)
|
||||
else:
|
||||
form = await request.form()
|
||||
values.update(dict(form))
|
||||
except Exception:
|
||||
pass
|
||||
return values
|
||||
|
||||
|
||||
def setup_search_routes(config) -> APIRouter:
|
||||
router = APIRouter(tags=["search"])
|
||||
|
||||
@router.get("/api/search/config")
|
||||
async def get_search_settings() -> Dict[str, Any]:
|
||||
return get_search_config()
|
||||
|
||||
@router.post("/api/search")
|
||||
async def do_web_search(request: Request) -> Dict[str, Any]:
|
||||
"""Standalone web search — returns context string + source list.
|
||||
|
||||
Used by Compare mode to pre-search once and share results across panes.
|
||||
"""
|
||||
values = await _request_values(request)
|
||||
query = str(values.get("query") or values.get("q") or "").strip()
|
||||
if not query:
|
||||
return {"context": "", "sources": [], "error": "query is required"}
|
||||
time_filter = values.get("time_filter") or values.get("freshness")
|
||||
if time_filter is not None:
|
||||
time_filter = str(time_filter).strip() or None
|
||||
try:
|
||||
context, sources = comprehensive_web_search(
|
||||
query, return_sources=True, time_filter=time_filter,
|
||||
)
|
||||
return {"context": context, "sources": sources}
|
||||
except Exception as e:
|
||||
logger.error(f"Standalone web search failed: {e}")
|
||||
return {"context": "", "sources": [], "error": str(e)}
|
||||
|
||||
@router.get("/api/search/providers")
|
||||
async def list_search_providers():
|
||||
"""Return available search providers with config status."""
|
||||
providers = []
|
||||
for pid, (label, needs_key, needs_url) in PROVIDER_INFO.items():
|
||||
if pid == "disabled":
|
||||
continue
|
||||
available = True
|
||||
if needs_key and not _get_provider_key(pid):
|
||||
available = False
|
||||
if needs_url and pid == "searxng" and not _get_search_instance():
|
||||
available = False
|
||||
providers.append({
|
||||
"id": pid,
|
||||
"label": label,
|
||||
"available": available,
|
||||
})
|
||||
return providers
|
||||
|
||||
@router.post("/api/search/query")
|
||||
async def search_with_provider(request: Request) -> Dict[str, Any]:
|
||||
"""Search using a specific provider. Used by compare search mode."""
|
||||
values = await _request_values(request)
|
||||
query = str(values.get("query") or values.get("q") or "").strip()
|
||||
provider = str(values.get("provider") or "").strip()
|
||||
try:
|
||||
count = int(values.get("count") or values.get("limit") or 10)
|
||||
except Exception:
|
||||
count = 10
|
||||
if not query:
|
||||
return {"results": [], "provider": provider, "error": "query is required"}
|
||||
if provider not in PROVIDER_INFO or provider == "disabled":
|
||||
return {"results": [], "provider": provider, "error": "Unknown provider"}
|
||||
t0 = time.time()
|
||||
try:
|
||||
results = _call_provider(provider, query, min(count, 20))
|
||||
elapsed = round(time.time() - t0, 2)
|
||||
return {"results": results, "provider": provider, "time": elapsed}
|
||||
except Exception as e:
|
||||
elapsed = round(time.time() - t0, 2)
|
||||
logger.error(f"Search provider {provider} failed: {e}")
|
||||
return {"results": [], "provider": provider, "time": elapsed, "error": str(e)}
|
||||
|
||||
return router
|
||||
_sys.modules[__name__] = _canonical
|
||||
|
||||
@@ -801,15 +801,6 @@ def setup_session_routes(
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.get("/history/{sid}")
|
||||
def get_history(request: Request, sid: str):
|
||||
_verify_session_owner(request, sid)
|
||||
try:
|
||||
session = session_manager.get_session(sid)
|
||||
except KeyError:
|
||||
raise HTTPException(404, f"Session {sid} not found")
|
||||
return {"history": [msg.to_dict() for msg in session.history]}
|
||||
|
||||
@router.get("/session/{sid}/export")
|
||||
def export_session(request: Request, sid: str, fmt: str = "md", filename: str = ""):
|
||||
"""Export conversation history as a downloadable file.
|
||||
|
||||
@@ -1409,7 +1409,7 @@ def setup_skills_routes(skills_manager: SkillsManager) -> APIRouter:
|
||||
|
||||
# Prefer the configured DEFAULT (→ Utility) model — not the current chat
|
||||
# session's model. Fall back to the caller's session model only if unset.
|
||||
url, model, headers = resolve_endpoint("default", owner=user)
|
||||
url, model, headers = resolve_endpoint("utility", owner=user)
|
||||
if not url or not model:
|
||||
url = url or ((body.get("endpoint_url") or "").strip() or None)
|
||||
model = model or ((body.get("model") or "").strip() or None)
|
||||
|
||||
@@ -0,0 +1,5 @@
|
||||
"""Vault route domain package (slice 2k, #4082/#4071).
|
||||
|
||||
Contains vault_routes.py, migrated from the flat routes/ directory.
|
||||
Backward-compat shim at routes/vault_routes.py re-exports from here.
|
||||
"""
|
||||
@@ -0,0 +1,242 @@
|
||||
"""
|
||||
vault_routes.py
|
||||
|
||||
Vaultwarden / Bitwarden CLI integration — config and unlock endpoints.
|
||||
Stores the BW_SESSION key in data/vault.json with restrictive permissions.
|
||||
"""
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import shutil
|
||||
import asyncio
|
||||
from pathlib import Path
|
||||
from datetime import datetime
|
||||
from fastapi import APIRouter, Request
|
||||
from pydantic import BaseModel
|
||||
|
||||
from core.middleware import require_admin
|
||||
from core.platform_compat import IS_WINDOWS, safe_chmod, which_tool
|
||||
from src.constants import VAULT_FILE as _VAULT_FILE
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
VAULT_FILE = Path(_VAULT_FILE)
|
||||
|
||||
|
||||
def _find_bw() -> str:
|
||||
"""Locate the bw binary, checking PATH and common npm-global locations.
|
||||
|
||||
On Windows the Bitwarden CLI shim is `bw.cmd`/`bw.exe`, resolved by
|
||||
which_tool via PATHEXT.
|
||||
"""
|
||||
p = which_tool("bw")
|
||||
if p:
|
||||
return p
|
||||
if IS_WINDOWS:
|
||||
appdata = os.environ.get("APPDATA", os.path.expanduser("~"))
|
||||
for candidate in (
|
||||
os.path.join(appdata, "npm", "bw.cmd"),
|
||||
os.path.join(appdata, "npm", "bw.exe"),
|
||||
):
|
||||
if os.path.isfile(candidate):
|
||||
return candidate
|
||||
return "bw"
|
||||
home = os.path.expanduser("~")
|
||||
for candidate in (
|
||||
f"{home}/.npm-global/bin/bw",
|
||||
f"{home}/.nvm/versions/node/*/bin/bw",
|
||||
"/usr/local/bin/bw",
|
||||
"/opt/homebrew/bin/bw",
|
||||
):
|
||||
if "*" in candidate:
|
||||
import glob
|
||||
for m in glob.glob(candidate):
|
||||
if os.path.isfile(m) and os.access(m, os.X_OK):
|
||||
return m
|
||||
elif os.path.isfile(candidate) and os.access(candidate, os.X_OK):
|
||||
return candidate
|
||||
return "bw" # fall back to PATH lookup (will FileNotFoundError, handled below)
|
||||
|
||||
|
||||
def _load_config() -> dict:
|
||||
if VAULT_FILE.exists():
|
||||
try:
|
||||
data = json.loads(VAULT_FILE.read_text(encoding="utf-8"))
|
||||
return data if isinstance(data, dict) else {}
|
||||
except Exception:
|
||||
pass
|
||||
return {}
|
||||
|
||||
|
||||
def _save_config(cfg: dict):
|
||||
VAULT_FILE.parent.mkdir(parents=True, exist_ok=True)
|
||||
VAULT_FILE.write_text(json.dumps(cfg, indent=2), encoding="utf-8")
|
||||
# POSIX: restrict the BW_SESSION store to 0o600. Windows: no-op (profile dir
|
||||
# is ACL-restricted already).
|
||||
safe_chmod(str(VAULT_FILE), 0o600)
|
||||
|
||||
|
||||
async def _run_bw(args: list, session: str = None, input_text: str = None,
|
||||
bw_password: str = None) -> tuple:
|
||||
env = {}
|
||||
env.update(os.environ)
|
||||
if session:
|
||||
env["BW_SESSION"] = session
|
||||
# Secrets must never be passed as argv — process arguments are world-readable
|
||||
# via `ps` / `/proc/<pid>/cmdline` to any local user. Keep --passwordenv
|
||||
# support for bw commands that need it; unlock/login callers should prefer
|
||||
# stdin so the master password is not left in the child environment either.
|
||||
if bw_password is not None:
|
||||
env["BW_PASSWORD"] = bw_password
|
||||
bw_path = _find_bw()
|
||||
try:
|
||||
proc = await asyncio.create_subprocess_exec(
|
||||
bw_path, *args,
|
||||
stdin=asyncio.subprocess.PIPE if input_text else None,
|
||||
stdout=asyncio.subprocess.PIPE,
|
||||
stderr=asyncio.subprocess.PIPE,
|
||||
env=env,
|
||||
)
|
||||
except FileNotFoundError:
|
||||
return "", "bw CLI not installed (install `nodejs-bitwarden-cli` or `bitwarden-cli`)", 127
|
||||
except Exception as e:
|
||||
return "", f"Failed to launch bw: {e}", 1
|
||||
try:
|
||||
stdout, stderr = await proc.communicate(input=input_text.encode() if input_text else None)
|
||||
except Exception as e:
|
||||
return "", f"bw subprocess error: {e}", 1
|
||||
return stdout.decode(errors="replace").strip(), stderr.decode(errors="replace").strip(), proc.returncode
|
||||
|
||||
|
||||
class VaultConfig(BaseModel):
|
||||
server_url: str = ""
|
||||
email: str = ""
|
||||
|
||||
|
||||
class VaultUnlockRequest(BaseModel):
|
||||
master_password: str
|
||||
|
||||
|
||||
class VaultLoginRequest(BaseModel):
|
||||
email: str
|
||||
master_password: str
|
||||
|
||||
|
||||
def setup_vault_routes():
|
||||
router = APIRouter(prefix="/api/vault", tags=["vault"])
|
||||
|
||||
@router.get("/config")
|
||||
async def get_config(request: Request):
|
||||
"""Return vault config (no sensitive fields)."""
|
||||
require_admin(request)
|
||||
cfg = _load_config()
|
||||
return {
|
||||
"server_url": cfg.get("server_url", ""),
|
||||
"email": cfg.get("email", ""),
|
||||
"unlocked": bool(cfg.get("session")),
|
||||
"unlocked_at": cfg.get("unlocked_at", ""),
|
||||
"bw_installed": await _check_bw_installed(),
|
||||
}
|
||||
|
||||
@router.post("/config")
|
||||
async def save_config(req: VaultConfig, request: Request):
|
||||
"""Save vault URL + email. Runs 'bw config server' to point at Vaultwarden."""
|
||||
require_admin(request)
|
||||
cfg = _load_config()
|
||||
cfg["server_url"] = req.server_url.strip().rstrip("/")
|
||||
cfg["email"] = req.email.strip()
|
||||
|
||||
if cfg["server_url"]:
|
||||
_, stderr, rc = await _run_bw(["config", "server", cfg["server_url"]])
|
||||
if rc != 0:
|
||||
return {"ok": False, "error": f"bw config failed: {stderr[:300]}"}
|
||||
|
||||
_save_config(cfg)
|
||||
return {"ok": True}
|
||||
|
||||
@router.post("/login")
|
||||
async def login(req: VaultLoginRequest, request: Request):
|
||||
"""Log in to Vaultwarden (required once per account)."""
|
||||
require_admin(request)
|
||||
cfg = _load_config()
|
||||
# Update email
|
||||
cfg["email"] = req.email
|
||||
_save_config(cfg)
|
||||
|
||||
stdout, stderr, rc = await _run_bw(
|
||||
["login", req.email, "--raw"],
|
||||
input_text=req.master_password + "\n",
|
||||
)
|
||||
if rc != 0:
|
||||
# Already logged in is OK
|
||||
if "already logged in" in stderr.lower():
|
||||
return {"ok": True, "already": True}
|
||||
return {"ok": False, "error": f"Login failed: {stderr[:300]}"}
|
||||
# bw login --raw prints session key on success (when 2FA disabled)
|
||||
if stdout:
|
||||
cfg["session"] = stdout
|
||||
cfg["unlocked_at"] = datetime.utcnow().isoformat()
|
||||
_save_config(cfg)
|
||||
return {"ok": True}
|
||||
|
||||
@router.post("/unlock")
|
||||
async def unlock(req: VaultUnlockRequest, request: Request):
|
||||
"""Unlock the vault and save the session key."""
|
||||
require_admin(request)
|
||||
# Pass the master password on stdin, not argv. argv is visible through
|
||||
# `ps` / /proc/<pid>/cmdline; stdin also avoids leaving the secret in
|
||||
# the child process environment.
|
||||
stdout, stderr, rc = await _run_bw(
|
||||
["unlock", "--raw"],
|
||||
input_text=req.master_password + "\n",
|
||||
)
|
||||
if rc != 0:
|
||||
return {"ok": False, "error": f"Unlock failed: {stderr[:300]}"}
|
||||
session = stdout.strip()
|
||||
if not session:
|
||||
return {"ok": False, "error": "bw returned empty session"}
|
||||
cfg = _load_config()
|
||||
cfg["session"] = session
|
||||
cfg["unlocked_at"] = datetime.utcnow().isoformat()
|
||||
_save_config(cfg)
|
||||
return {"ok": True, "message": "Vault unlocked"}
|
||||
|
||||
@router.post("/lock")
|
||||
async def lock(request: Request):
|
||||
"""Lock the vault (clear session from config)."""
|
||||
require_admin(request)
|
||||
cfg = _load_config()
|
||||
cfg.pop("session", None)
|
||||
cfg.pop("unlocked_at", None)
|
||||
_save_config(cfg)
|
||||
# Also tell bw to lock
|
||||
await _run_bw(["lock"])
|
||||
return {"ok": True, "message": "Vault locked"}
|
||||
|
||||
@router.post("/logout")
|
||||
async def logout(request: Request):
|
||||
"""Log out of the Bitwarden CLI completely."""
|
||||
require_admin(request)
|
||||
await _run_bw(["logout"])
|
||||
cfg = _load_config()
|
||||
cfg.pop("session", None)
|
||||
cfg.pop("email", None)
|
||||
cfg.pop("unlocked_at", None)
|
||||
_save_config(cfg)
|
||||
return {"ok": True}
|
||||
|
||||
return router
|
||||
|
||||
|
||||
async def _check_bw_installed() -> bool:
|
||||
try:
|
||||
proc = await asyncio.create_subprocess_exec(
|
||||
_find_bw(), "--version",
|
||||
stdout=asyncio.subprocess.PIPE,
|
||||
stderr=asyncio.subprocess.PIPE,
|
||||
)
|
||||
await proc.communicate()
|
||||
return proc.returncode == 0
|
||||
except Exception:
|
||||
return False
|
||||
+9
-237
@@ -1,242 +1,14 @@
|
||||
"""
|
||||
vault_routes.py
|
||||
"""Backward-compat shim — canonical location is routes/vault/vault_routes.py.
|
||||
|
||||
Vaultwarden / Bitwarden CLI integration — config and unlock endpoints.
|
||||
Stores the BW_SESSION key in data/vault.json with restrictive permissions.
|
||||
This module is replaced in ``sys.modules`` by the canonical module object so
|
||||
that ``import routes.vault_routes``, ``from routes.vault_routes import X``,
|
||||
and the ``import ... as vr`` + ``monkeypatch.setattr(vr, ...)`` pattern used
|
||||
by test_vault_password_not_in_argv.py all operate on the *same* object.
|
||||
Keeps existing import paths working after slice 2k (#4082/#4071).
|
||||
"""
|
||||
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import shutil
|
||||
import asyncio
|
||||
from pathlib import Path
|
||||
from datetime import datetime
|
||||
from fastapi import APIRouter, Request
|
||||
from pydantic import BaseModel
|
||||
import sys as _sys
|
||||
|
||||
from core.middleware import require_admin
|
||||
from core.platform_compat import IS_WINDOWS, safe_chmod, which_tool
|
||||
from src.constants import VAULT_FILE as _VAULT_FILE
|
||||
from routes.vault import vault_routes as _canonical # noqa: F401
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
VAULT_FILE = Path(_VAULT_FILE)
|
||||
|
||||
|
||||
def _find_bw() -> str:
|
||||
"""Locate the bw binary, checking PATH and common npm-global locations.
|
||||
|
||||
On Windows the Bitwarden CLI shim is `bw.cmd`/`bw.exe`, resolved by
|
||||
which_tool via PATHEXT.
|
||||
"""
|
||||
p = which_tool("bw")
|
||||
if p:
|
||||
return p
|
||||
if IS_WINDOWS:
|
||||
appdata = os.environ.get("APPDATA", os.path.expanduser("~"))
|
||||
for candidate in (
|
||||
os.path.join(appdata, "npm", "bw.cmd"),
|
||||
os.path.join(appdata, "npm", "bw.exe"),
|
||||
):
|
||||
if os.path.isfile(candidate):
|
||||
return candidate
|
||||
return "bw"
|
||||
home = os.path.expanduser("~")
|
||||
for candidate in (
|
||||
f"{home}/.npm-global/bin/bw",
|
||||
f"{home}/.nvm/versions/node/*/bin/bw",
|
||||
"/usr/local/bin/bw",
|
||||
"/opt/homebrew/bin/bw",
|
||||
):
|
||||
if "*" in candidate:
|
||||
import glob
|
||||
for m in glob.glob(candidate):
|
||||
if os.path.isfile(m) and os.access(m, os.X_OK):
|
||||
return m
|
||||
elif os.path.isfile(candidate) and os.access(candidate, os.X_OK):
|
||||
return candidate
|
||||
return "bw" # fall back to PATH lookup (will FileNotFoundError, handled below)
|
||||
|
||||
|
||||
def _load_config() -> dict:
|
||||
if VAULT_FILE.exists():
|
||||
try:
|
||||
data = json.loads(VAULT_FILE.read_text(encoding="utf-8"))
|
||||
return data if isinstance(data, dict) else {}
|
||||
except Exception:
|
||||
pass
|
||||
return {}
|
||||
|
||||
|
||||
def _save_config(cfg: dict):
|
||||
VAULT_FILE.parent.mkdir(parents=True, exist_ok=True)
|
||||
VAULT_FILE.write_text(json.dumps(cfg, indent=2), encoding="utf-8")
|
||||
# POSIX: restrict the BW_SESSION store to 0o600. Windows: no-op (profile dir
|
||||
# is ACL-restricted already).
|
||||
safe_chmod(str(VAULT_FILE), 0o600)
|
||||
|
||||
|
||||
async def _run_bw(args: list, session: str = None, input_text: str = None,
|
||||
bw_password: str = None) -> tuple:
|
||||
env = {}
|
||||
env.update(os.environ)
|
||||
if session:
|
||||
env["BW_SESSION"] = session
|
||||
# Secrets must never be passed as argv — process arguments are world-readable
|
||||
# via `ps` / `/proc/<pid>/cmdline` to any local user. Keep --passwordenv
|
||||
# support for bw commands that need it; unlock/login callers should prefer
|
||||
# stdin so the master password is not left in the child environment either.
|
||||
if bw_password is not None:
|
||||
env["BW_PASSWORD"] = bw_password
|
||||
bw_path = _find_bw()
|
||||
try:
|
||||
proc = await asyncio.create_subprocess_exec(
|
||||
bw_path, *args,
|
||||
stdin=asyncio.subprocess.PIPE if input_text else None,
|
||||
stdout=asyncio.subprocess.PIPE,
|
||||
stderr=asyncio.subprocess.PIPE,
|
||||
env=env,
|
||||
)
|
||||
except FileNotFoundError:
|
||||
return "", "bw CLI not installed (install `nodejs-bitwarden-cli` or `bitwarden-cli`)", 127
|
||||
except Exception as e:
|
||||
return "", f"Failed to launch bw: {e}", 1
|
||||
try:
|
||||
stdout, stderr = await proc.communicate(input=input_text.encode() if input_text else None)
|
||||
except Exception as e:
|
||||
return "", f"bw subprocess error: {e}", 1
|
||||
return stdout.decode(errors="replace").strip(), stderr.decode(errors="replace").strip(), proc.returncode
|
||||
|
||||
|
||||
class VaultConfig(BaseModel):
|
||||
server_url: str = ""
|
||||
email: str = ""
|
||||
|
||||
|
||||
class VaultUnlockRequest(BaseModel):
|
||||
master_password: str
|
||||
|
||||
|
||||
class VaultLoginRequest(BaseModel):
|
||||
email: str
|
||||
master_password: str
|
||||
|
||||
|
||||
def setup_vault_routes():
|
||||
router = APIRouter(prefix="/api/vault", tags=["vault"])
|
||||
|
||||
@router.get("/config")
|
||||
async def get_config(request: Request):
|
||||
"""Return vault config (no sensitive fields)."""
|
||||
require_admin(request)
|
||||
cfg = _load_config()
|
||||
return {
|
||||
"server_url": cfg.get("server_url", ""),
|
||||
"email": cfg.get("email", ""),
|
||||
"unlocked": bool(cfg.get("session")),
|
||||
"unlocked_at": cfg.get("unlocked_at", ""),
|
||||
"bw_installed": await _check_bw_installed(),
|
||||
}
|
||||
|
||||
@router.post("/config")
|
||||
async def save_config(req: VaultConfig, request: Request):
|
||||
"""Save vault URL + email. Runs 'bw config server' to point at Vaultwarden."""
|
||||
require_admin(request)
|
||||
cfg = _load_config()
|
||||
cfg["server_url"] = req.server_url.strip().rstrip("/")
|
||||
cfg["email"] = req.email.strip()
|
||||
|
||||
if cfg["server_url"]:
|
||||
_, stderr, rc = await _run_bw(["config", "server", cfg["server_url"]])
|
||||
if rc != 0:
|
||||
return {"ok": False, "error": f"bw config failed: {stderr[:300]}"}
|
||||
|
||||
_save_config(cfg)
|
||||
return {"ok": True}
|
||||
|
||||
@router.post("/login")
|
||||
async def login(req: VaultLoginRequest, request: Request):
|
||||
"""Log in to Vaultwarden (required once per account)."""
|
||||
require_admin(request)
|
||||
cfg = _load_config()
|
||||
# Update email
|
||||
cfg["email"] = req.email
|
||||
_save_config(cfg)
|
||||
|
||||
stdout, stderr, rc = await _run_bw(
|
||||
["login", req.email, "--raw"],
|
||||
input_text=req.master_password + "\n",
|
||||
)
|
||||
if rc != 0:
|
||||
# Already logged in is OK
|
||||
if "already logged in" in stderr.lower():
|
||||
return {"ok": True, "already": True}
|
||||
return {"ok": False, "error": f"Login failed: {stderr[:300]}"}
|
||||
# bw login --raw prints session key on success (when 2FA disabled)
|
||||
if stdout:
|
||||
cfg["session"] = stdout
|
||||
cfg["unlocked_at"] = datetime.utcnow().isoformat()
|
||||
_save_config(cfg)
|
||||
return {"ok": True}
|
||||
|
||||
@router.post("/unlock")
|
||||
async def unlock(req: VaultUnlockRequest, request: Request):
|
||||
"""Unlock the vault and save the session key."""
|
||||
require_admin(request)
|
||||
# Pass the master password on stdin, not argv. argv is visible through
|
||||
# `ps` / /proc/<pid>/cmdline; stdin also avoids leaving the secret in
|
||||
# the child process environment.
|
||||
stdout, stderr, rc = await _run_bw(
|
||||
["unlock", "--raw"],
|
||||
input_text=req.master_password + "\n",
|
||||
)
|
||||
if rc != 0:
|
||||
return {"ok": False, "error": f"Unlock failed: {stderr[:300]}"}
|
||||
session = stdout.strip()
|
||||
if not session:
|
||||
return {"ok": False, "error": "bw returned empty session"}
|
||||
cfg = _load_config()
|
||||
cfg["session"] = session
|
||||
cfg["unlocked_at"] = datetime.utcnow().isoformat()
|
||||
_save_config(cfg)
|
||||
return {"ok": True, "message": "Vault unlocked"}
|
||||
|
||||
@router.post("/lock")
|
||||
async def lock(request: Request):
|
||||
"""Lock the vault (clear session from config)."""
|
||||
require_admin(request)
|
||||
cfg = _load_config()
|
||||
cfg.pop("session", None)
|
||||
cfg.pop("unlocked_at", None)
|
||||
_save_config(cfg)
|
||||
# Also tell bw to lock
|
||||
await _run_bw(["lock"])
|
||||
return {"ok": True, "message": "Vault locked"}
|
||||
|
||||
@router.post("/logout")
|
||||
async def logout(request: Request):
|
||||
"""Log out of the Bitwarden CLI completely."""
|
||||
require_admin(request)
|
||||
await _run_bw(["logout"])
|
||||
cfg = _load_config()
|
||||
cfg.pop("session", None)
|
||||
cfg.pop("email", None)
|
||||
cfg.pop("unlocked_at", None)
|
||||
_save_config(cfg)
|
||||
return {"ok": True}
|
||||
|
||||
return router
|
||||
|
||||
|
||||
async def _check_bw_installed() -> bool:
|
||||
try:
|
||||
proc = await asyncio.create_subprocess_exec(
|
||||
_find_bw(), "--version",
|
||||
stdout=asyncio.subprocess.PIPE,
|
||||
stderr=asyncio.subprocess.PIPE,
|
||||
)
|
||||
await proc.communicate()
|
||||
return proc.returncode == 0
|
||||
except Exception:
|
||||
return False
|
||||
_sys.modules[__name__] = _canonical
|
||||
|
||||
@@ -0,0 +1,5 @@
|
||||
"""Webhook route domain package (slice 2l, #4082/#4071).
|
||||
|
||||
Contains webhook_routes.py, migrated from the flat routes/ directory.
|
||||
Backward-compat shim at routes/webhook_routes.py re-exports from here.
|
||||
"""
|
||||
@@ -0,0 +1,395 @@
|
||||
"""Webhook, API Token, and sync chat routes."""
|
||||
|
||||
import uuid
|
||||
import logging
|
||||
from typing import Optional
|
||||
|
||||
import httpx
|
||||
from fastapi import APIRouter, HTTPException, Request, Form
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from core.database import SessionLocal, Webhook, ModelEndpoint
|
||||
from src.auth_helpers import owner_filter
|
||||
from src.url_security import validate_public_http_url
|
||||
from src.webhook_manager import WebhookManager, validate_webhook_url, validate_events
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter(prefix="/api", tags=["webhooks"])
|
||||
|
||||
# Input limits
|
||||
MAX_NAME_LEN = 100
|
||||
MAX_URL_LEN = 2048
|
||||
MAX_SECRET_LEN = 256
|
||||
MAX_MESSAGE_LEN = 32_000
|
||||
|
||||
|
||||
from core.middleware import require_admin as _require_admin
|
||||
|
||||
|
||||
def _select_api_chat_fallback_endpoint(db, token_owner: Optional[str]):
|
||||
"""First enabled ModelEndpoint visible to token_owner — their own rows plus
|
||||
legacy null-owner ("shared") rows. Owner-scoped: an unscoped .first() would
|
||||
let a chat-scoped token fall back onto another user's private endpoint and
|
||||
silently spend that owner's API key/quota. Prefer owner rows before shared
|
||||
rows. Fails closed to null-owner rows only when token_owner is absent.
|
||||
Does not validate base_url — admin-configured local/LAN endpoints remain allowed.
|
||||
"""
|
||||
query = db.query(ModelEndpoint).filter(ModelEndpoint.is_enabled == True) # noqa: E712
|
||||
if token_owner:
|
||||
query = owner_filter(query, ModelEndpoint, token_owner)
|
||||
return query.order_by(ModelEndpoint.owner.desc(), ModelEndpoint.created_at).first()
|
||||
return query.filter(ModelEndpoint.owner == None).order_by(ModelEndpoint.created_at).first() # noqa: E711
|
||||
|
||||
|
||||
def _caller_owns_session(sess_owner, caller) -> bool:
|
||||
"""Strict session-ownership gate for the token-authenticated sync-chat
|
||||
endpoint (`POST /api/v1/chat`).
|
||||
|
||||
Mirrors ``_verify_session_owner`` in session_routes.py and the null-owner
|
||||
gates in notes/calendar/gallery: a caller may resume a session ONLY when
|
||||
its owner matches them exactly. A null/empty session owner (legacy or
|
||||
migrated rows) is deliberately NOT resumable by an arbitrary token — the
|
||||
old ``sess_owner and sess_owner != caller`` form skipped the check whenever
|
||||
``sess_owner`` was falsy, so any chat-scoped token (e.g. a paired mobile
|
||||
device) could resume such a session, inject a message, and read back its
|
||||
history and reuse the owner's endpoint credentials. Fail closed: an
|
||||
unresolvable caller also returns False.
|
||||
"""
|
||||
if not caller:
|
||||
return False
|
||||
return sess_owner == caller
|
||||
|
||||
|
||||
def setup_webhook_routes(
|
||||
webhook_manager: WebhookManager,
|
||||
auth_manager,
|
||||
session_manager=None,
|
||||
api_key_manager=None,
|
||||
) -> APIRouter:
|
||||
|
||||
@router.get("/webhooks")
|
||||
def list_webhooks(request: Request):
|
||||
_require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
hooks = db.query(Webhook).all()
|
||||
return [
|
||||
{
|
||||
"id": w.id,
|
||||
"name": w.name,
|
||||
"url": w.url,
|
||||
"has_secret": bool(w.secret),
|
||||
"events": w.events.split(",") if w.events else [],
|
||||
"is_active": w.is_active,
|
||||
"last_triggered_at": w.last_triggered_at.isoformat() if w.last_triggered_at else None,
|
||||
"last_status_code": w.last_status_code,
|
||||
"last_error": w.last_error,
|
||||
"created_at": w.created_at.isoformat() if w.created_at else None,
|
||||
}
|
||||
for w in hooks
|
||||
]
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.post("/webhooks")
|
||||
def create_webhook(
|
||||
request: Request,
|
||||
name: str = Form(""),
|
||||
url: str = Form(""),
|
||||
secret: str = Form(""),
|
||||
events: str = Form(""),
|
||||
):
|
||||
_require_admin(request)
|
||||
name = name.strip()[:MAX_NAME_LEN]
|
||||
if not name:
|
||||
raise HTTPException(400, "Webhook name is required")
|
||||
try:
|
||||
url = validate_webhook_url(url)
|
||||
except ValueError as e:
|
||||
raise HTTPException(400, str(e))
|
||||
try:
|
||||
events = validate_events(events)
|
||||
except ValueError as e:
|
||||
raise HTTPException(400, str(e))
|
||||
|
||||
secret_val = secret.strip()[:MAX_SECRET_LEN] or None
|
||||
# Encrypt the secret at rest using the same Fernet key as API keys
|
||||
encrypted_secret = None
|
||||
if secret_val and api_key_manager:
|
||||
encrypted_secret = api_key_manager.encrypt_api_key(secret_val)
|
||||
elif secret_val:
|
||||
encrypted_secret = secret_val # Fallback if no encryption available
|
||||
|
||||
webhook_id = str(uuid.uuid4())[:8]
|
||||
db = SessionLocal()
|
||||
try:
|
||||
db.add(Webhook(
|
||||
id=webhook_id,
|
||||
name=name,
|
||||
url=url,
|
||||
secret=encrypted_secret,
|
||||
events=events,
|
||||
is_active=True,
|
||||
))
|
||||
db.commit()
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
return {"id": webhook_id, "name": name}
|
||||
|
||||
@router.post("/webhooks/{webhook_id}/test")
|
||||
async def test_webhook(request: Request, webhook_id: str):
|
||||
_require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
wh = db.query(Webhook).filter(Webhook.id == webhook_id).first()
|
||||
if not wh:
|
||||
raise HTTPException(404, "Webhook not found")
|
||||
url, secret = wh.url, wh.secret
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
await webhook_manager.deliver_test(webhook_id, url, secret)
|
||||
return {"status": "sent"}
|
||||
|
||||
@router.patch("/webhooks/{webhook_id}")
|
||||
def toggle_webhook(request: Request, webhook_id: str):
|
||||
_require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
wh = db.query(Webhook).filter(Webhook.id == webhook_id).first()
|
||||
if not wh:
|
||||
raise HTTPException(404, "Webhook not found")
|
||||
wh.is_active = not wh.is_active
|
||||
db.commit()
|
||||
return {"id": webhook_id, "is_active": wh.is_active}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.delete("/webhooks/{webhook_id}")
|
||||
def delete_webhook(request: Request, webhook_id: str):
|
||||
_require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
deleted = db.query(Webhook).filter(Webhook.id == webhook_id).delete()
|
||||
db.commit()
|
||||
if not deleted:
|
||||
raise HTTPException(404, "Webhook not found")
|
||||
finally:
|
||||
db.close()
|
||||
return {"status": "deleted"}
|
||||
|
||||
# ================================================================
|
||||
# Sync Chat Endpoint (for n8n / Make / Activepieces)
|
||||
# ================================================================
|
||||
|
||||
# Known provider base URLs — auto-resolved from api_key prefix or model name
|
||||
KNOWN_PROVIDERS = {
|
||||
"deepseek": "https://api.deepseek.com/v1",
|
||||
"openai": "https://api.openai.com/v1",
|
||||
"mistral": "https://api.mistral.ai/v1",
|
||||
"groq": "https://api.groq.com/openai/v1",
|
||||
"together": "https://api.together.xyz/v1",
|
||||
"openrouter": "https://openrouter.ai/api/v1",
|
||||
"ollama": "https://ollama.com/api",
|
||||
"opencode-zen": "https://opencode.ai/zen/v1",
|
||||
"opencode-go": "https://opencode.ai/zen/go/v1",
|
||||
"fireworks": "https://api.fireworks.ai/inference/v1",
|
||||
"venice": "https://api.venice.ai/api/v1",
|
||||
"kimi-code": "https://api.kimi.com/coding/v1",
|
||||
"kimicode": "https://api.kimi.com/coding/v1",
|
||||
}
|
||||
|
||||
# Model prefix → provider mapping for auto-detection
|
||||
MODEL_PROVIDER_MAP = {
|
||||
"deepseek": "deepseek",
|
||||
"gpt-": "openai",
|
||||
"o1": "openai",
|
||||
"o3": "openai",
|
||||
"o4": "openai",
|
||||
"mistral": "mistral",
|
||||
"llama": "groq",
|
||||
"mixtral": "groq",
|
||||
"kimi-for-coding": "kimi-code",
|
||||
"kimi": "kimi-code",
|
||||
}
|
||||
|
||||
def _resolve_base_url(model: Optional[str], provider: Optional[str]) -> Optional[str]:
|
||||
"""Try to auto-resolve a base URL from provider name or model prefix."""
|
||||
if provider and provider.lower() in KNOWN_PROVIDERS:
|
||||
return KNOWN_PROVIDERS[provider.lower()]
|
||||
if model:
|
||||
model_lower = model.lower()
|
||||
for prefix, prov in MODEL_PROVIDER_MAP.items():
|
||||
if model_lower.startswith(prefix):
|
||||
return KNOWN_PROVIDERS[prov]
|
||||
return None
|
||||
|
||||
class SyncChatRequest(BaseModel):
|
||||
message: str = Field(..., max_length=MAX_MESSAGE_LEN)
|
||||
model: Optional[str] = Field(None, max_length=200)
|
||||
session: Optional[str] = Field(None, max_length=100)
|
||||
api_key: Optional[str] = Field(None, max_length=256)
|
||||
base_url: Optional[str] = Field(None, max_length=MAX_URL_LEN)
|
||||
provider: Optional[str] = Field(None, max_length=50)
|
||||
|
||||
@router.post("/v1/chat")
|
||||
async def sync_chat(request: Request, body: SyncChatRequest):
|
||||
if not getattr(request.state, "api_token", False):
|
||||
raise HTTPException(403, "This endpoint requires an API token")
|
||||
scopes = set(getattr(request.state, "api_token_scopes", []) or [])
|
||||
if "chat" not in scopes:
|
||||
raise HTTPException(403, "API token is not scoped for chat")
|
||||
token_owner = getattr(request.state, "api_token_owner", None)
|
||||
|
||||
from core.models import ChatMessage
|
||||
from src.llm_core import llm_call_async
|
||||
from src.endpoint_resolver import build_chat_url, build_headers, build_models_url, normalize_base
|
||||
|
||||
message = body.message.strip()
|
||||
if not message:
|
||||
raise HTTPException(400, "Message is required")
|
||||
|
||||
session_id = body.session
|
||||
sess = None
|
||||
|
||||
# --- Case 1: Resume an existing session ---
|
||||
if session_id and session_manager:
|
||||
try:
|
||||
sess = session_manager.get_session(session_id)
|
||||
except (KeyError, Exception):
|
||||
raise HTTPException(404, "Session not found")
|
||||
# SECURITY: verify the API-token's user owns this session — without
|
||||
# this any token holder could resume any user's chat by passing its
|
||||
# ID. The token's user is on request.state.user (set by API-token
|
||||
# middleware); fall back to require_user if not present.
|
||||
try:
|
||||
from src.auth_helpers import get_current_user as _gcu
|
||||
_tok_user = token_owner or getattr(request.state, "user", None) or _gcu(request)
|
||||
except Exception:
|
||||
_tok_user = None
|
||||
# Strict ownership (see _caller_owns_session): fail closed so a
|
||||
# null-owner / cross-owner session can't be resumed by an arbitrary
|
||||
# chat-scoped token.
|
||||
_sess_owner = getattr(sess, "owner", None)
|
||||
if not _caller_owns_session(_sess_owner, _tok_user):
|
||||
raise HTTPException(404, "Session not found")
|
||||
|
||||
# --- Case 2: Direct API key + model (no pre-configured endpoint needed) ---
|
||||
if not sess and body.api_key:
|
||||
api_key = body.api_key.strip()
|
||||
model = body.model or "deepseek-chat"
|
||||
|
||||
# Validate only token-supplied direct base_url; auto-resolved known-provider
|
||||
# URLs are not subject to extra local/LAN blocking beyond existing provider logic.
|
||||
direct_base_url = body.base_url.strip().rstrip("/") if body.base_url else None
|
||||
if direct_base_url:
|
||||
try:
|
||||
base_url = validate_public_http_url(direct_base_url)
|
||||
except ValueError as e:
|
||||
detail = str(e).replace("URL", "base_url", 1)
|
||||
raise HTTPException(400, detail)
|
||||
else:
|
||||
base_url = _resolve_base_url(model, body.provider)
|
||||
if not base_url:
|
||||
raise HTTPException(400,
|
||||
"Could not auto-detect provider. Pass base_url (e.g. 'https://api.deepseek.com/v1') "
|
||||
"or provider ('deepseek', 'openai', 'groq', etc.)")
|
||||
base_url = normalize_base(base_url)
|
||||
endpoint_url = build_chat_url(base_url)
|
||||
|
||||
if not session_manager:
|
||||
raise HTTPException(500, "Session manager not available")
|
||||
|
||||
sid = str(uuid.uuid4())
|
||||
sess = session_manager.create_session(
|
||||
session_id=sid, name="API Chat", endpoint_url=endpoint_url,
|
||||
model=model, owner=token_owner,
|
||||
)
|
||||
sess.headers = build_headers(api_key, base_url)
|
||||
session_manager.save_sessions()
|
||||
session_id = sid
|
||||
|
||||
# --- Case 3: Fall back to first configured ModelEndpoint ---
|
||||
if not sess:
|
||||
db = SessionLocal()
|
||||
try:
|
||||
ep = _select_api_chat_fallback_endpoint(db, token_owner)
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
if not ep:
|
||||
raise HTTPException(400,
|
||||
"No session, api_key, or configured endpoints. "
|
||||
"Pass api_key + model, or configure an endpoint in Admin.")
|
||||
|
||||
base_url = normalize_base(ep.base_url)
|
||||
endpoint_url = build_chat_url(base_url)
|
||||
model = body.model or "auto"
|
||||
api_key = ep.api_key
|
||||
if getattr(ep, "provider_auth_id", None):
|
||||
try:
|
||||
from src.endpoint_resolver import resolve_endpoint_runtime
|
||||
base_url, api_key = resolve_endpoint_runtime(ep, owner=token_owner)
|
||||
endpoint_url = build_chat_url(base_url)
|
||||
except Exception:
|
||||
raise HTTPException(500, "Could not resolve endpoint credentials")
|
||||
|
||||
if model == "auto":
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=5) as client:
|
||||
models_url = build_models_url(base_url)
|
||||
hdrs = build_headers(api_key, base_url)
|
||||
if models_url:
|
||||
resp = await client.get(models_url, headers=hdrs)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
items = data if isinstance(data, list) else (data.get("data") or [])
|
||||
ids = [m.get("id") for m in items if isinstance(m, dict) and m.get("id")]
|
||||
if not ids and isinstance(data, dict):
|
||||
ids = [
|
||||
m.get("name") or m.get("model")
|
||||
for m in (data.get("models") or [])
|
||||
if m.get("name") or m.get("model")
|
||||
]
|
||||
else:
|
||||
import json as _json
|
||||
ids = _json.loads(ep.cached_models or "[]")
|
||||
model = ids[0] if ids else "auto"
|
||||
except Exception:
|
||||
raise HTTPException(500, "Could not discover models from endpoint")
|
||||
|
||||
if not session_manager:
|
||||
raise HTTPException(500, "Session manager not available")
|
||||
|
||||
sid = str(uuid.uuid4())
|
||||
sess = session_manager.create_session(
|
||||
session_id=sid, name="API Chat", endpoint_url=endpoint_url,
|
||||
model=model, owner=token_owner,
|
||||
)
|
||||
if api_key:
|
||||
sess.headers = build_headers(api_key, base_url)
|
||||
session_manager.save_sessions()
|
||||
session_id = sid
|
||||
|
||||
# --- Send message and get response ---
|
||||
sess.add_message(ChatMessage("user", message))
|
||||
|
||||
messages = [{"role": m.role, "content": m.content} for m in sess.history]
|
||||
|
||||
reply = await llm_call_async(
|
||||
sess.endpoint_url, sess.model, messages,
|
||||
headers=sess.headers, timeout=120,
|
||||
)
|
||||
sess.add_message(ChatMessage("assistant", reply))
|
||||
session_manager.save_sessions()
|
||||
|
||||
webhook_manager.fire_and_forget("chat.completed", {
|
||||
"session_id": session_id, "model": sess.model,
|
||||
"user_message": message[:2000], "response": reply[:2000],
|
||||
})
|
||||
|
||||
return {"response": reply, "session_id": session_id, "model": sess.model}
|
||||
|
||||
return router
|
||||
+12
-391
@@ -1,395 +1,16 @@
|
||||
"""Webhook, API Token, and sync chat routes."""
|
||||
"""Backward-compat shim — canonical location is routes/webhook/webhook_routes.py.
|
||||
|
||||
import uuid
|
||||
import logging
|
||||
from typing import Optional
|
||||
This module is replaced in ``sys.modules`` by the canonical module object so
|
||||
that ``import routes.webhook_routes``, ``from routes.webhook_routes import X``,
|
||||
``importlib.import_module("routes.webhook_routes")``, and the
|
||||
``__import__("routes.webhook_routes", fromlist=[...])`` + ``setattr(wh_mod,
|
||||
...)`` pattern used by test_null_owner_gates.py all operate on the *same*
|
||||
object. Keeps existing import paths working after slice 2l (#4082/#4071).
|
||||
Source-introspection tests read the canonical file by path.
|
||||
"""
|
||||
|
||||
import httpx
|
||||
from fastapi import APIRouter, HTTPException, Request, Form
|
||||
from pydantic import BaseModel, Field
|
||||
import sys as _sys
|
||||
|
||||
from core.database import SessionLocal, Webhook, ModelEndpoint
|
||||
from src.auth_helpers import owner_filter
|
||||
from src.url_security import validate_public_http_url
|
||||
from src.webhook_manager import WebhookManager, validate_webhook_url, validate_events
|
||||
from routes.webhook import webhook_routes as _canonical # noqa: F401
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter(prefix="/api", tags=["webhooks"])
|
||||
|
||||
# Input limits
|
||||
MAX_NAME_LEN = 100
|
||||
MAX_URL_LEN = 2048
|
||||
MAX_SECRET_LEN = 256
|
||||
MAX_MESSAGE_LEN = 32_000
|
||||
|
||||
|
||||
from core.middleware import require_admin as _require_admin
|
||||
|
||||
|
||||
def _select_api_chat_fallback_endpoint(db, token_owner: Optional[str]):
|
||||
"""First enabled ModelEndpoint visible to token_owner — their own rows plus
|
||||
legacy null-owner ("shared") rows. Owner-scoped: an unscoped .first() would
|
||||
let a chat-scoped token fall back onto another user's private endpoint and
|
||||
silently spend that owner's API key/quota. Prefer owner rows before shared
|
||||
rows. Fails closed to null-owner rows only when token_owner is absent.
|
||||
Does not validate base_url — admin-configured local/LAN endpoints remain allowed.
|
||||
"""
|
||||
query = db.query(ModelEndpoint).filter(ModelEndpoint.is_enabled == True) # noqa: E712
|
||||
if token_owner:
|
||||
query = owner_filter(query, ModelEndpoint, token_owner)
|
||||
return query.order_by(ModelEndpoint.owner.desc(), ModelEndpoint.created_at).first()
|
||||
return query.filter(ModelEndpoint.owner == None).order_by(ModelEndpoint.created_at).first() # noqa: E711
|
||||
|
||||
|
||||
def _caller_owns_session(sess_owner, caller) -> bool:
|
||||
"""Strict session-ownership gate for the token-authenticated sync-chat
|
||||
endpoint (`POST /api/v1/chat`).
|
||||
|
||||
Mirrors ``_verify_session_owner`` in session_routes.py and the null-owner
|
||||
gates in notes/calendar/gallery: a caller may resume a session ONLY when
|
||||
its owner matches them exactly. A null/empty session owner (legacy or
|
||||
migrated rows) is deliberately NOT resumable by an arbitrary token — the
|
||||
old ``sess_owner and sess_owner != caller`` form skipped the check whenever
|
||||
``sess_owner`` was falsy, so any chat-scoped token (e.g. a paired mobile
|
||||
device) could resume such a session, inject a message, and read back its
|
||||
history and reuse the owner's endpoint credentials. Fail closed: an
|
||||
unresolvable caller also returns False.
|
||||
"""
|
||||
if not caller:
|
||||
return False
|
||||
return sess_owner == caller
|
||||
|
||||
|
||||
def setup_webhook_routes(
|
||||
webhook_manager: WebhookManager,
|
||||
auth_manager,
|
||||
session_manager=None,
|
||||
api_key_manager=None,
|
||||
) -> APIRouter:
|
||||
|
||||
@router.get("/webhooks")
|
||||
def list_webhooks(request: Request):
|
||||
_require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
hooks = db.query(Webhook).all()
|
||||
return [
|
||||
{
|
||||
"id": w.id,
|
||||
"name": w.name,
|
||||
"url": w.url,
|
||||
"has_secret": bool(w.secret),
|
||||
"events": w.events.split(",") if w.events else [],
|
||||
"is_active": w.is_active,
|
||||
"last_triggered_at": w.last_triggered_at.isoformat() if w.last_triggered_at else None,
|
||||
"last_status_code": w.last_status_code,
|
||||
"last_error": w.last_error,
|
||||
"created_at": w.created_at.isoformat() if w.created_at else None,
|
||||
}
|
||||
for w in hooks
|
||||
]
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.post("/webhooks")
|
||||
def create_webhook(
|
||||
request: Request,
|
||||
name: str = Form(""),
|
||||
url: str = Form(""),
|
||||
secret: str = Form(""),
|
||||
events: str = Form(""),
|
||||
):
|
||||
_require_admin(request)
|
||||
name = name.strip()[:MAX_NAME_LEN]
|
||||
if not name:
|
||||
raise HTTPException(400, "Webhook name is required")
|
||||
try:
|
||||
url = validate_webhook_url(url)
|
||||
except ValueError as e:
|
||||
raise HTTPException(400, str(e))
|
||||
try:
|
||||
events = validate_events(events)
|
||||
except ValueError as e:
|
||||
raise HTTPException(400, str(e))
|
||||
|
||||
secret_val = secret.strip()[:MAX_SECRET_LEN] or None
|
||||
# Encrypt the secret at rest using the same Fernet key as API keys
|
||||
encrypted_secret = None
|
||||
if secret_val and api_key_manager:
|
||||
encrypted_secret = api_key_manager.encrypt_api_key(secret_val)
|
||||
elif secret_val:
|
||||
encrypted_secret = secret_val # Fallback if no encryption available
|
||||
|
||||
webhook_id = str(uuid.uuid4())[:8]
|
||||
db = SessionLocal()
|
||||
try:
|
||||
db.add(Webhook(
|
||||
id=webhook_id,
|
||||
name=name,
|
||||
url=url,
|
||||
secret=encrypted_secret,
|
||||
events=events,
|
||||
is_active=True,
|
||||
))
|
||||
db.commit()
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
return {"id": webhook_id, "name": name}
|
||||
|
||||
@router.post("/webhooks/{webhook_id}/test")
|
||||
async def test_webhook(request: Request, webhook_id: str):
|
||||
_require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
wh = db.query(Webhook).filter(Webhook.id == webhook_id).first()
|
||||
if not wh:
|
||||
raise HTTPException(404, "Webhook not found")
|
||||
url, secret = wh.url, wh.secret
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
await webhook_manager.deliver_test(webhook_id, url, secret)
|
||||
return {"status": "sent"}
|
||||
|
||||
@router.patch("/webhooks/{webhook_id}")
|
||||
def toggle_webhook(request: Request, webhook_id: str):
|
||||
_require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
wh = db.query(Webhook).filter(Webhook.id == webhook_id).first()
|
||||
if not wh:
|
||||
raise HTTPException(404, "Webhook not found")
|
||||
wh.is_active = not wh.is_active
|
||||
db.commit()
|
||||
return {"id": webhook_id, "is_active": wh.is_active}
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
@router.delete("/webhooks/{webhook_id}")
|
||||
def delete_webhook(request: Request, webhook_id: str):
|
||||
_require_admin(request)
|
||||
db = SessionLocal()
|
||||
try:
|
||||
deleted = db.query(Webhook).filter(Webhook.id == webhook_id).delete()
|
||||
db.commit()
|
||||
if not deleted:
|
||||
raise HTTPException(404, "Webhook not found")
|
||||
finally:
|
||||
db.close()
|
||||
return {"status": "deleted"}
|
||||
|
||||
# ================================================================
|
||||
# Sync Chat Endpoint (for n8n / Make / Activepieces)
|
||||
# ================================================================
|
||||
|
||||
# Known provider base URLs — auto-resolved from api_key prefix or model name
|
||||
KNOWN_PROVIDERS = {
|
||||
"deepseek": "https://api.deepseek.com/v1",
|
||||
"openai": "https://api.openai.com/v1",
|
||||
"mistral": "https://api.mistral.ai/v1",
|
||||
"groq": "https://api.groq.com/openai/v1",
|
||||
"together": "https://api.together.xyz/v1",
|
||||
"openrouter": "https://openrouter.ai/api/v1",
|
||||
"ollama": "https://ollama.com/api",
|
||||
"opencode-zen": "https://opencode.ai/zen/v1",
|
||||
"opencode-go": "https://opencode.ai/zen/go/v1",
|
||||
"fireworks": "https://api.fireworks.ai/inference/v1",
|
||||
"venice": "https://api.venice.ai/api/v1",
|
||||
"kimi-code": "https://api.kimi.com/coding/v1",
|
||||
"kimicode": "https://api.kimi.com/coding/v1",
|
||||
}
|
||||
|
||||
# Model prefix → provider mapping for auto-detection
|
||||
MODEL_PROVIDER_MAP = {
|
||||
"deepseek": "deepseek",
|
||||
"gpt-": "openai",
|
||||
"o1": "openai",
|
||||
"o3": "openai",
|
||||
"o4": "openai",
|
||||
"mistral": "mistral",
|
||||
"llama": "groq",
|
||||
"mixtral": "groq",
|
||||
"kimi-for-coding": "kimi-code",
|
||||
"kimi": "kimi-code",
|
||||
}
|
||||
|
||||
def _resolve_base_url(model: Optional[str], provider: Optional[str]) -> Optional[str]:
|
||||
"""Try to auto-resolve a base URL from provider name or model prefix."""
|
||||
if provider and provider.lower() in KNOWN_PROVIDERS:
|
||||
return KNOWN_PROVIDERS[provider.lower()]
|
||||
if model:
|
||||
model_lower = model.lower()
|
||||
for prefix, prov in MODEL_PROVIDER_MAP.items():
|
||||
if model_lower.startswith(prefix):
|
||||
return KNOWN_PROVIDERS[prov]
|
||||
return None
|
||||
|
||||
class SyncChatRequest(BaseModel):
|
||||
message: str = Field(..., max_length=MAX_MESSAGE_LEN)
|
||||
model: Optional[str] = Field(None, max_length=200)
|
||||
session: Optional[str] = Field(None, max_length=100)
|
||||
api_key: Optional[str] = Field(None, max_length=256)
|
||||
base_url: Optional[str] = Field(None, max_length=MAX_URL_LEN)
|
||||
provider: Optional[str] = Field(None, max_length=50)
|
||||
|
||||
@router.post("/v1/chat")
|
||||
async def sync_chat(request: Request, body: SyncChatRequest):
|
||||
if not getattr(request.state, "api_token", False):
|
||||
raise HTTPException(403, "This endpoint requires an API token")
|
||||
scopes = set(getattr(request.state, "api_token_scopes", []) or [])
|
||||
if "chat" not in scopes:
|
||||
raise HTTPException(403, "API token is not scoped for chat")
|
||||
token_owner = getattr(request.state, "api_token_owner", None)
|
||||
|
||||
from core.models import ChatMessage
|
||||
from src.llm_core import llm_call_async
|
||||
from src.endpoint_resolver import build_chat_url, build_headers, build_models_url, normalize_base
|
||||
|
||||
message = body.message.strip()
|
||||
if not message:
|
||||
raise HTTPException(400, "Message is required")
|
||||
|
||||
session_id = body.session
|
||||
sess = None
|
||||
|
||||
# --- Case 1: Resume an existing session ---
|
||||
if session_id and session_manager:
|
||||
try:
|
||||
sess = session_manager.get_session(session_id)
|
||||
except (KeyError, Exception):
|
||||
raise HTTPException(404, "Session not found")
|
||||
# SECURITY: verify the API-token's user owns this session — without
|
||||
# this any token holder could resume any user's chat by passing its
|
||||
# ID. The token's user is on request.state.user (set by API-token
|
||||
# middleware); fall back to require_user if not present.
|
||||
try:
|
||||
from src.auth_helpers import get_current_user as _gcu
|
||||
_tok_user = token_owner or getattr(request.state, "user", None) or _gcu(request)
|
||||
except Exception:
|
||||
_tok_user = None
|
||||
# Strict ownership (see _caller_owns_session): fail closed so a
|
||||
# null-owner / cross-owner session can't be resumed by an arbitrary
|
||||
# chat-scoped token.
|
||||
_sess_owner = getattr(sess, "owner", None)
|
||||
if not _caller_owns_session(_sess_owner, _tok_user):
|
||||
raise HTTPException(404, "Session not found")
|
||||
|
||||
# --- Case 2: Direct API key + model (no pre-configured endpoint needed) ---
|
||||
if not sess and body.api_key:
|
||||
api_key = body.api_key.strip()
|
||||
model = body.model or "deepseek-chat"
|
||||
|
||||
# Validate only token-supplied direct base_url; auto-resolved known-provider
|
||||
# URLs are not subject to extra local/LAN blocking beyond existing provider logic.
|
||||
direct_base_url = body.base_url.strip().rstrip("/") if body.base_url else None
|
||||
if direct_base_url:
|
||||
try:
|
||||
base_url = validate_public_http_url(direct_base_url)
|
||||
except ValueError as e:
|
||||
detail = str(e).replace("URL", "base_url", 1)
|
||||
raise HTTPException(400, detail)
|
||||
else:
|
||||
base_url = _resolve_base_url(model, body.provider)
|
||||
if not base_url:
|
||||
raise HTTPException(400,
|
||||
"Could not auto-detect provider. Pass base_url (e.g. 'https://api.deepseek.com/v1') "
|
||||
"or provider ('deepseek', 'openai', 'groq', etc.)")
|
||||
base_url = normalize_base(base_url)
|
||||
endpoint_url = build_chat_url(base_url)
|
||||
|
||||
if not session_manager:
|
||||
raise HTTPException(500, "Session manager not available")
|
||||
|
||||
sid = str(uuid.uuid4())
|
||||
sess = session_manager.create_session(
|
||||
session_id=sid, name="API Chat", endpoint_url=endpoint_url,
|
||||
model=model, owner=token_owner,
|
||||
)
|
||||
sess.headers = build_headers(api_key, base_url)
|
||||
session_manager.save_sessions()
|
||||
session_id = sid
|
||||
|
||||
# --- Case 3: Fall back to first configured ModelEndpoint ---
|
||||
if not sess:
|
||||
db = SessionLocal()
|
||||
try:
|
||||
ep = _select_api_chat_fallback_endpoint(db, token_owner)
|
||||
finally:
|
||||
db.close()
|
||||
|
||||
if not ep:
|
||||
raise HTTPException(400,
|
||||
"No session, api_key, or configured endpoints. "
|
||||
"Pass api_key + model, or configure an endpoint in Admin.")
|
||||
|
||||
base_url = normalize_base(ep.base_url)
|
||||
endpoint_url = build_chat_url(base_url)
|
||||
model = body.model or "auto"
|
||||
api_key = ep.api_key
|
||||
if getattr(ep, "provider_auth_id", None):
|
||||
try:
|
||||
from src.endpoint_resolver import resolve_endpoint_runtime
|
||||
base_url, api_key = resolve_endpoint_runtime(ep, owner=token_owner)
|
||||
endpoint_url = build_chat_url(base_url)
|
||||
except Exception:
|
||||
raise HTTPException(500, "Could not resolve endpoint credentials")
|
||||
|
||||
if model == "auto":
|
||||
try:
|
||||
async with httpx.AsyncClient(timeout=5) as client:
|
||||
models_url = build_models_url(base_url)
|
||||
hdrs = build_headers(api_key, base_url)
|
||||
if models_url:
|
||||
resp = await client.get(models_url, headers=hdrs)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
items = data if isinstance(data, list) else (data.get("data") or [])
|
||||
ids = [m.get("id") for m in items if isinstance(m, dict) and m.get("id")]
|
||||
if not ids and isinstance(data, dict):
|
||||
ids = [
|
||||
m.get("name") or m.get("model")
|
||||
for m in (data.get("models") or [])
|
||||
if m.get("name") or m.get("model")
|
||||
]
|
||||
else:
|
||||
import json as _json
|
||||
ids = _json.loads(ep.cached_models or "[]")
|
||||
model = ids[0] if ids else "auto"
|
||||
except Exception:
|
||||
raise HTTPException(500, "Could not discover models from endpoint")
|
||||
|
||||
if not session_manager:
|
||||
raise HTTPException(500, "Session manager not available")
|
||||
|
||||
sid = str(uuid.uuid4())
|
||||
sess = session_manager.create_session(
|
||||
session_id=sid, name="API Chat", endpoint_url=endpoint_url,
|
||||
model=model, owner=token_owner,
|
||||
)
|
||||
if api_key:
|
||||
sess.headers = build_headers(api_key, base_url)
|
||||
session_manager.save_sessions()
|
||||
session_id = sid
|
||||
|
||||
# --- Send message and get response ---
|
||||
sess.add_message(ChatMessage("user", message))
|
||||
|
||||
messages = [{"role": m.role, "content": m.content} for m in sess.history]
|
||||
|
||||
reply = await llm_call_async(
|
||||
sess.endpoint_url, sess.model, messages,
|
||||
headers=sess.headers, timeout=120,
|
||||
)
|
||||
sess.add_message(ChatMessage("assistant", reply))
|
||||
session_manager.save_sessions()
|
||||
|
||||
webhook_manager.fire_and_forget("chat.completed", {
|
||||
"session_id": session_id, "model": sess.model,
|
||||
"user_message": message[:2000], "response": reply[:2000],
|
||||
})
|
||||
|
||||
return {"response": reply, "session_id": session_id, "model": sess.model}
|
||||
|
||||
return router
|
||||
_sys.modules[__name__] = _canonical
|
||||
|
||||
Reference in New Issue
Block a user