Feat/monitor (#1928)

* feat: add monitor

* feat: fix tab

* feat: work

* feat: not reliable monitor

* feat: enhance monitoring page layout with integrated filters and refresh button

* feat: add support for runner recording

* feat: add jump button & alignment

* feat: new

* fix: not show query variables in local agent

* fix: pnpm lint and python ruff check

* fix: ruff fromat

* chore: remove unnecessary migration

* style: optimize monitoring page layout and fix sticky filter issues

- Enhanced metric cards with gradient backgrounds and hover effects
- Increased traffic chart height from 200px to 300px
- Adjusted grid layout and spacing for better visual appeal
- Fixed sticky filter area to properly cover parent padding without transparent gaps
- Used negative margins and positioning to eliminate scrolling artifacts
- Matched padding/margins with other pages (pipelines, bots) for consistency
- Removed duplicate title/subtitle from page content
- Added cursor-pointer styling to tab triggers
- Removed border between tab list and tab content

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

* fix: apply prettier formatting to monitoring components

- Fixed indentation and spacing in MetricCard.tsx
- Fixed formatting in TrafficChart.tsx
- Applied prettier formatting to page.tsx

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

* feat: update HomeSidebar to trigger action on child selection and localize monitoring titles

* refactor: streamline LLM and embedding invocation methods

* feat: add embedding model monitor

* fix: database version

* chore: simplify pnpm-lock.yaml formatting

---------

Co-authored-by: Junyan Qin <rockchinq@gmail.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>

src/langbot/pkg/provider/runners/localagent.py

@@ -130,7 +130,7 @@ class LocalAgentRunner(runner.RequestRunner):
         if not is_stream:
             # 非流式输出，直接请求
 
-            msg = await use_llm_model.provider.requester.invoke_llm(
+            msg = await use_llm_model.provider.invoke_llm(
                 query,
                 use_llm_model,
                 req_messages,
@@ -147,7 +147,7 @@ class LocalAgentRunner(runner.RequestRunner):
             accumulated_content = ''  # 从开始累积的所有内容
             last_role = 'assistant'
             msg_sequence = 1
-            async for msg in use_llm_model.provider.requester.invoke_llm_stream(
+            async for msg in use_llm_model.provider.invoke_llm_stream(
                 query,
                 use_llm_model,
                 req_messages,
@@ -265,7 +265,7 @@ class LocalAgentRunner(runner.RequestRunner):
                 last_role = 'assistant'
                 msg_sequence = first_end_sequence
 
-                async for msg in use_llm_model.provider.requester.invoke_llm_stream(
+                async for msg in use_llm_model.provider.invoke_llm_stream(
                     query,
                     use_llm_model,
                     req_messages,
@@ -321,7 +321,7 @@ class LocalAgentRunner(runner.RequestRunner):
                 )
             else:
                 # 处理完所有调用，再次请求
-                msg = await use_llm_model.provider.requester.invoke_llm(
+                msg = await use_llm_model.provider.invoke_llm(
                     query,
                     use_llm_model,
                     req_messages,