Merge current dev and refresh PR #6738 from the 7011 integration

routes/session_routes.py

@@ -6,17 +6,24 @@ import uuid
 import time
 from pathlib import Path
 from datetime import datetime
-from fastapi import APIRouter, Form, HTTPException, Response, Request, Query
+from fastapi import APIRouter, Form, HTTPException, Response, Request, Depends, Query
 import logging
 
 from core.session_manager import SessionManager
 from core.models import ChatMessage
 from src.request_models import SessionResponse
 from core.database import Session as DbSession, SessionLocal, Document, GalleryImage, utcnow_naive
-from src.auth_helpers import effective_user, _auth_disabled, owner_filter
+from src.auth_helpers import (
+    effective_user,
+    _auth_disabled,
+    owner_filter,
+    is_delegated_credential,
+    require_chat_api_token_scope,
+)
 from src.session_image_cleanup import _generated_image_path_for_cleanup, session_image_refs
 from src.session_actions import is_session_recently_active
 from src.upload_handler import reserve_message_upload_references
+from src.tool_approval_scopes import sanitize_client_message_metadata
 
 
 def _sanitize_export_filename(name: str) -> str:
@@ -234,9 +241,15 @@ def _verify_session_owner(request: Request, session_id: str, session_manager=Non
 
 logger = logging.getLogger(__name__)
 
-router = APIRouter(prefix="/api", tags=["sessions"])
+router = APIRouter(
+    prefix="/api",
+    tags=["sessions"],
+    dependencies=[Depends(require_chat_api_token_scope)],
+)
 
 def _current_user_is_admin(request: Request, user: str | None) -> bool:
+    if is_delegated_credential(request):
+        return False
     if not user:
         return False
     auth_mgr = getattr(request.app.state, "auth_manager", None)
@@ -267,6 +280,22 @@ def _reject_raw_endpoint_url_for_non_admin(
         raise HTTPException(403, "Choose a registered model endpoint")
 
 
+def _reject_delegated_session_options(
+    request: Request,
+    *,
+    skip_validation: bool = False,
+    api_key: str | None = None,
+) -> None:
+    """Keep bearer credentials from exercising interactive-admin options."""
+    if is_delegated_credential(request) and (
+        skip_validation or bool((api_key or "").strip())
+    ):
+        raise HTTPException(
+            403,
+            "API tokens cannot supply endpoint credentials or skip endpoint validation",
+        )
+
+
 def _persist_session_headers(session_id: str, headers: dict | None) -> bool:
     """Persist endpoint auth headers for DB-backed session metadata."""
     delays = (0.05, 0.15, 0.35)
@@ -480,6 +509,7 @@ def setup_session_routes(
                     "has_documents": s.id in doc_session_ids,
                     "has_images": s.id in img_session_ids,
                     "mode": s.mode,
+                    "thinking_mode": s.thinking_mode or "off",
                     "message_count": s.message_count or 0,
                 })
         finally:
@@ -501,6 +531,11 @@ def setup_session_routes(
     ):
         skip_val = str(skip_validation).lower() == "true"
         user = effective_user(request)
+        _reject_delegated_session_options(
+            request,
+            skip_validation=skip_val,
+            api_key=api_key,
+        )
         endpoint_api_key = ""
         endpoint_base_url = ""
         _reject_raw_endpoint_url_for_non_admin(request, user, endpoint_id, endpoint_url)
@@ -757,7 +792,11 @@ def setup_session_routes(
         except (AttributeError, TypeError, ValueError) as exc:
             raise HTTPException(400, "Invalid message attachment metadata") from exc
         for m in messages:
-            sess.add_message(ChatMessage(m["role"], m["content"], metadata=m.get("metadata")))
+            sess.add_message(ChatMessage(
+                m["role"],
+                m["content"],
+                metadata=sanitize_client_message_metadata(m.get("metadata")),
+            ))
         session_manager.save_sessions()
         return {"ok": True, "count": len(messages)}
 
@@ -1004,6 +1043,7 @@ def setup_session_routes(
                     "id": s.id,
                     "name": s.name,
                     "model": s.model,
+                    "thinking_mode": s.thinking_mode or "off",
                     "message_count": s.message_count or 0,
                     "created_at": s.created_at.isoformat() if s.created_at else None,
                     "updated_at": s.updated_at.isoformat() if s.updated_at else None,
@@ -1118,6 +1158,8 @@ def setup_session_routes(
         model: str = Form("gpt-4o"),
         rag: str = Form(None)
     ):
+        if is_delegated_credential(request):
+            raise HTTPException(403, "This session type requires an interactive session")
         if not OPENAI_API_KEY:
             raise HTTPException(400, "Server missing OPENAI_API_KEY")
         sid = str(uuid.uuid4())
@@ -1198,9 +1240,16 @@ def setup_session_routes(
         from src.context_compactor import SELF_SUMMARY_SYSTEM_PROMPT
         from src.endpoint_resolver import resolve_endpoint
         from src.llm_core import llm_call_async
+        from src.utility_effort import effort_for_call
 
         owner = getattr(session, "owner", None) or effective_user(request)
-        url, model, headers = resolve_endpoint("utility", owner=owner)
+        url, model, headers = resolve_endpoint(
+            "utility",
+            fallback_url=getattr(session, "endpoint_url", None),
+            fallback_model=getattr(session, "model", None),
+            fallback_headers=getattr(session, "headers", None),
+            owner=owner,
+        )
         if not url or not model:
             url, model, headers = session.endpoint_url, session.model, session.headers
         if not url or not model:
@@ -1228,6 +1277,7 @@ def setup_session_routes(
                 max_tokens=1024,
                 headers=headers,
                 timeout=60,
+                reasoning_effort=effort_for_call(url, model, owner, session),
             )
         except Exception as e:
             logger.error("Manual compaction failed: %s", e)
@@ -1270,7 +1320,8 @@ def setup_session_routes(
         after Phase 1 — used by the "Tidy (no AI)" UI affordance so
         users can clean junk without spending tokens.
         """
-        from src.llm_core import llm_call
+        from src.llm_core import llm_call, llm_call_with_fallback
+        from src.utility_effort import effort_for_call
         user = effective_user(request)
         single_user_mode = not user and _auth_disabled()
         user_sessions = session_manager.get_sessions_for_user(user)
@@ -1416,7 +1467,7 @@ def setup_session_routes(
             return {"status": "skipped", "reason": "No unfiled sessions to sort"}
 
         # Pick an endpoint — prefer admin-configured task endpoint
-        from src.task_endpoint import resolve_task_endpoint
+        from src.task_endpoint import resolve_task_endpoint, resolve_task_candidates
         url, model, headers = resolve_task_endpoint(owner=user)
         if not url:
             url, model, headers = _pick_endpoint_for_sort(owner=user)
@@ -1442,8 +1493,12 @@ def setup_session_routes(
             # 16384 (was 4096): with many chats the folder JSON is large, and a
             # reasoning model spends tokens thinking first — 4096 truncated the
             # JSON mid-output, so it never parsed ("invalid JSON for auto-sort").
-            raw = llm_call(url, model, [{"role": "user", "content": prompt}],
-                           temperature=0.3, max_tokens=16384, headers=headers, timeout=120)
+            raw = llm_call_with_fallback(
+                resolve_task_candidates(fallback_url=url, fallback_model=model,
+                                        fallback_headers=headers, owner=user),
+                [{"role": "user", "content": prompt}],
+                temperature=0.3, max_tokens=16384, timeout=120,
+                reasoning_effort=effort_for_call(url, model, user))
             logger.info(f"Auto-sort raw response ({len(raw)} chars): {raw[:300]}")
             # Extract JSON from response — handle markdown fences, leading text,
             # reasoning-model <think> blocks, and trailing commas.
@@ -1561,7 +1616,13 @@ def setup_session_routes(
             raise HTTPException(404, "Session not found")
         skills = _context_info_skill_inventory(skills_manager, owner=owner)
         tools = _context_info_tool_inventory()
-        agents_md = _context_info_agents_md_inventory(cwd)
+        # `cwd` is caller-chosen. Walking it for AGENTS.md and reporting whether
+        # it exists confirms paths on the host, which /api/workspace/browse and
+        # /vet reserve for admins (or single-user mode); keep that boundary here.
+        from src.tool_security import owner_is_admin_or_single_user
+
+        _host_paths_visible = owner_is_admin_or_single_user(owner)
+        agents_md = _context_info_agents_md_inventory(cwd) if _host_paths_visible else []
         # Workspace visibility: lets the TUI answer "can the backend actually
         # see this directory?" (mounted vs bridge-only) without probing.
         from src.workspace_paths import backend_workspace_path, workspace_mount_pairs
@@ -1571,19 +1632,22 @@ def setup_session_routes(
         # Server-side tool policy: non-admin owners silently lose the computer
         # tools (src/tool_security); surface that so the TUI can show it.
         try:
-            from src.tool_security import blocked_tools_for_owner
+            from src.tool_security import blocked_tools_for_owner, delegated_credential_blocked_tools
 
             _blocked = blocked_tools_for_owner(owner)
+            if is_delegated_credential(request):
+                _blocked.update(delegated_credential_blocked_tools())
         except Exception:
             _blocked = set()
         _computer = {"bash", "python", "read_file", "write_file", "host_shell"}
         _policy = {
             "computer_tools": "restricted" if _computer & _blocked else "full",
-            "reason": "non-admin owner" if _blocked else "single-user or admin",
+            "reason": "API-token caller" if is_delegated_credential(request) else
+                      "non-admin owner" if _blocked else "single-user or admin",
         }
         _workspace = {
             "backend_path": _backend_cwd,
-            "exists_in_backend": bool(_backend_cwd) and Path(_backend_cwd).is_dir(),
+            "exists_in_backend": _host_paths_visible and bool(_backend_cwd) and Path(_backend_cwd).is_dir(),
             "mount_configured": bool(workspace_mount_pairs()),
             "via_mount": bool(_raw_cwd) and backend_workspace_path(_raw_cwd) != _raw_cwd,
         }