Merge branch 'gzy' into 'master'

Gzy

See merge request knowledge-base-bj/deerflow-server!149

offline-backend-20260512/backend/app/gateway/routers/browser_context.py

@@ -27,7 +27,7 @@ from app.gateway.routers.thread_runs import RunCreateRequest
 from app.gateway.routers.threads import ThreadCreateRequest, create_thread
 from app.gateway.routers.uploads import _make_file_sandbox_writable
 from app.gateway.services import start_run
-from deerflow.browser_context.tasks import claim_next_browser_task, complete_browser_task, prune_browser_tasks
+from deerflow.browser_context.tasks import claim_next_browser_task, complete_browser_task, prune_browser_tasks, tasks_dir
 from deerflow.config.app_config import AppConfig
 from deerflow.config.browser_context_config import BrowserContextConfig
 from deerflow.runtime import serialize_channel_values
@@ -307,10 +307,19 @@ async def claim_browser_context_task(
     config: AppConfig = Depends(get_config),
 ) -> BrowserContextTaskNextResponse:
     settings = _require_enabled(config)
+    effective_user_id = get_effective_user_id()
+    effective_worker_id = worker_id or "chrome-extension"
+    logger.info(
+        "Browser task next poll user_id=%s worker_id=%s tasks_dir=%s client=%s",
+        effective_user_id,
+        effective_worker_id,
+        tasks_dir(),
+        getattr(request.client, "host", None),
+    )
     prune_browser_tasks()
     task = claim_next_browser_task(
-        user_id=get_effective_user_id(),
+        user_id=effective_user_id,
-        worker_id=worker_id or "chrome-extension",
+        worker_id=effective_worker_id,
         lease_seconds=settings.task_lease_seconds,
     )
     if task is None:

offline-backend-20260512/backend/config.yaml

@@ -171,6 +171,11 @@ vision:
   # prompt: 请详细描述这张图片的内容。
   # max_tokens: 2048
 
+# browser_act 相关配置
+browser_context:
+  enabled: true
+  actions_enabled: true
+
 # 上传文件识别配置。
 # - auto_convert_documents: true 时,上传的 PDF / Word / Excel / PPT 会在服务端自动转换为
 #   Markdown(.md),agent 通过 read_file / grep 读取其内容 —— 即“识别”文档内容。
@@ -268,6 +273,16 @@ tools:
     group: bash
     use: deerflow.sandbox.tools:bash_tool
 
+  # browser_act 相关配置
+  - name: browser_fetch_page
+    group: web
+    use: deerflow.tools.builtins.browser_context_tool:browser_fetch_page_tool
+
+  # browser_act 相关配置
+  - name: browser_act
+    group: web
+    use: deerflow.tools.builtins.browser_act_tool:browser_act_tool
+
 sandbox:
   use: deerflow.sandbox.local:LocalSandboxProvider
   allow_host_bash: true

offline-backend-20260512/backend/extensions_config.json

@@ -1,14 +1,35 @@
 {
   "mcpServers": {},
   "skills": {
-    "web-research": { "enabled": true },
+    "web-research": {
-    "deep-search": { "enabled": true },
+      "enabled": true
-    "code-retrieval": { "enabled": true },
+    },
-    "news-briefing": { "enabled": true },
+    "deep-search": {
-    "workspace-search": { "enabled": true },
+      "enabled": true
-    "policy-knowledge": { "enabled": false },
+    },
-    "html-page-builder": { "enabled": true },
+    "code-retrieval": {
-    "html-charts": { "enabled": true },
+      "enabled": true
-    "html-multipage": { "enabled": true }
+    },
+    "news-briefing": {
+      "enabled": true
+    },
+    "workspace-search": {
+      "enabled": true
+    },
+    "policy-knowledge": {
+      "enabled": false
+    },
+    "html-page-builder": {
+      "enabled": true
+    },
+    "html-charts": {
+      "enabled": true
+    },
+    "html-multipage": {
+      "enabled": true
+    },
+    "browser_act": {
+      "enabled": true
+    }
   }
 }

offline-backend-20260512/backend/packages/harness/deerflow/browser_context/tasks.py

@@ -193,16 +193,22 @@ def claim_next_browser_task(
     user_id = str(user_id or "default")
     worker_id = (worker_id or "chrome-extension").strip()[:128] or "chrome-extension"
     lease_seconds = max(10, int(lease_seconds))
+    queue_dir = tasks_dir()
 
     with _LOCK:
-        paths = sorted(tasks_dir().glob("*.json"), key=lambda p: p.stat().st_mtime)
+        paths = sorted(queue_dir.glob("*.json"), key=lambda p: p.stat().st_mtime)
+        matching_user = 0
+        matching_status_counts: dict[str, int] = {}
         for path in paths:
             data = _read_task(path)
             if not data or str(data.get("user_id") or "") != user_id:
                 continue
+            matching_user += 1
 
             data = _expire_if_needed(path, data, now)
             status = data.get("status")
+            status_key = str(status or "unknown")
+            matching_status_counts[status_key] = matching_status_counts.get(status_key, 0) + 1
             if status == "running":
                 updated_at = _parse_iso(data.get("updated_at")) or now
                 if (now - updated_at).total_seconds() <= lease_seconds:
@@ -220,8 +226,32 @@ def claim_next_browser_task(
             data["claimed_at"] = _iso(now)
             data["updated_at"] = _iso(now)
             _write_task(path, data)
+            logger.info(
+                "Browser task claim scan user_id=%s worker_id=%s tasks_dir=%s total_files=%d matching_user=%d "
+                "matching_statuses=%s claimed_task_id=%s claimed_kind=%s",
+                user_id,
+                worker_id,
+                queue_dir,
+                len(paths),
+                matching_user,
+                matching_status_counts,
+                data.get("id"),
+                data.get("kind") or "fetch",
+            )
             return _public_task(data)
 
+    logger.info(
+        "Browser task claim scan user_id=%s worker_id=%s tasks_dir=%s total_files=%d matching_user=%d "
+        "matching_statuses=%s claimed_task_id=%s claimed_kind=%s",
+        user_id,
+        worker_id,
+        queue_dir,
+        len(paths),
+        matching_user,
+        matching_status_counts,
+        None,
+        None,
+    )
     return None
 
 
@@ -300,4 +330,3 @@ async def wait_for_browser_task_result(
         if time.monotonic() >= deadline:
             return task
         await asyncio.sleep(interval)
-

offline-backend-20260512/backend/tests/test_browser_act.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import asyncio
+import logging
 
 import pytest
 
@@ -76,6 +77,22 @@ def test_fetch_task_default_kind_is_fetch():
     assert claimed["action"] is None
 
 
+def test_claim_next_browser_task_logs_claim_diagnostics(caplog):
+    task_queue.create_browser_task(user_id="u1", url="https://example.com/1")
+    task_queue.create_browser_task(user_id="u2", url="https://example.com/2")
+
+    with caplog.at_level(logging.INFO, logger=task_queue.__name__):
+        claimed = task_queue.claim_next_browser_task(user_id="u1", worker_id="worker-1")
+
+    assert claimed is not None
+    assert "Browser task claim scan" in caplog.text
+    assert "user_id=u1" in caplog.text
+    assert "worker_id=worker-1" in caplog.text
+    assert "total_files=2" in caplog.text
+    assert "matching_user=1" in caplog.text
+    assert "claimed_task_id=" in caplog.text
+
+
 # --- tool validation --------------------------------------------------------