chore(agent-runner): merge split tool runtime base

# Conflicts:
#	src/langbot/pkg/box/workspace.py
#	src/langbot/pkg/provider/tools/loaders/mcp_stdio.py
#	src/langbot/pkg/provider/tools/loaders/native.py
#	src/langbot/pkg/provider/tools/loaders/skill.py
#	tests/unit_tests/box/test_workspace.py
#	tests/unit_tests/provider/test_mcp_box_integration.py

src/langbot/pkg/api/http/controller/groups/plugins.py

@@ -271,6 +271,20 @@ class PluginsRouterGroup(group.RouterGroup):
             readme = await self.ap.plugin_connector.get_plugin_readme(author, plugin_name, language=language)
             return self.success(data={'readme': readme})
 
+        @self.route(
+            '/<author>/<plugin_name>/logs',
+            methods=['GET'],
+            auth_type=group.AuthType.USER_TOKEN_OR_API_KEY,
+        )
+        async def _(author: str, plugin_name: str) -> quart.Response:
+            try:
+                limit = int(quart.request.args.get('limit', 200))
+            except (TypeError, ValueError):
+                limit = 200
+            level = quart.request.args.get('level') or None
+            logs = await self.ap.plugin_connector.get_plugin_logs(author, plugin_name, limit=limit, level=level)
+            return self.success(data={'logs': logs})
+
         @self.route(
             '/<author>/<plugin_name>/icon',
             methods=['GET'],

src/langbot/pkg/core/stages/load_config.py

@@ -202,6 +202,16 @@ class LoadConfigStage(stage.BootingStage):
                 constants.instance_id = new_id
         constants.edition = ap.instance_config.data.get('system', {}).get('edition', 'community')
 
+        # Instance creation timestamp: sourced from data/labels/instance_id.json.
+        # Instances created before this field existed (or supplied via
+        # system.instance_id) won't have it, so backfill with the current time
+        # and persist it via the dump below — from then on it stays stable.
+        instance_create_ts = ap.instance_id.data.get('instance_create_ts', 0)
+        if not isinstance(instance_create_ts, int) or instance_create_ts <= 0:
+            instance_create_ts = int(time.time())
+            ap.instance_id.data['instance_create_ts'] = instance_create_ts
+        constants.instance_create_ts = instance_create_ts
+
         print(f'LangBot instance id: {constants.instance_id}')
         print(f'LangBot edition: {constants.edition}')
 

src/langbot/pkg/platform/sources/web_page_bot_adapter.py

@@ -84,6 +84,18 @@ class WebPageBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter
     ):
         self.listeners.pop(event_type, None)
 
+    async def is_stream_output_supported(self) -> bool:
+        """Delegate stream output check to ws_adapter."""
+        if self._ws_adapter is not None:
+            return await self._ws_adapter.is_stream_output_supported()
+        return False
+
+    async def create_message_card(self, message_id: str | int, event: platform_events.MessageEvent) -> bool:
+        """Delegate create_message_card to ws_adapter."""
+        if self._ws_adapter is not None:
+            return await self._ws_adapter.create_message_card(message_id, event)
+        return False
+
     async def is_muted(self, group_id: int) -> bool:
         return False
 

src/langbot/pkg/plugin/connector.py

@@ -708,6 +708,16 @@ class PluginRuntimeConnector(ManagedRuntimeConnector):
     async def get_plugin_readme(self, plugin_author: str, plugin_name: str, language: str = 'en') -> str:
         return await self.handler.get_plugin_readme(plugin_author, plugin_name, language)
 
+    async def get_plugin_logs(
+        self,
+        plugin_author: str,
+        plugin_name: str,
+        limit: int = 200,
+        level: str | None = None,
+    ) -> list[dict[str, Any]]:
+        # Not cached: logs are live and change constantly.
+        return await self.handler.get_plugin_logs(plugin_author, plugin_name, limit, level)
+
     @alru_cache(ttl=5 * 60)
     async def get_plugin_assets(self, plugin_author: str, plugin_name: str, filepath: str) -> dict[str, Any]:
         return await self.handler.get_plugin_assets(plugin_author, plugin_name, filepath)

src/langbot/pkg/plugin/handler.py

@@ -2515,6 +2515,31 @@ class RuntimeConnectionHandler(handler.Handler):
 
         return readme_bytes.decode('utf-8')
 
+    async def get_plugin_logs(
+        self,
+        plugin_author: str,
+        plugin_name: str,
+        limit: int = 200,
+        level: str | None = None,
+    ) -> list[dict[str, Any]]:
+        """Get recent log lines captured from the plugin's stderr."""
+        try:
+            result = await self.call_action(
+                LangBotToRuntimeAction.GET_PLUGIN_LOGS,
+                {
+                    'plugin_author': plugin_author,
+                    'plugin_name': plugin_name,
+                    'limit': limit,
+                    'level': level,
+                },
+                timeout=20,
+            )
+        except Exception:
+            traceback.print_exc()
+            return []
+
+        return result.get('logs', [])
+
     async def get_plugin_assets(self, plugin_author: str, plugin_name: str, filepath: str) -> dict[str, Any]:
         """Get plugin assets"""
         result = await self.call_action(

src/langbot/pkg/provider/modelmgr/requester.py

@@ -12,6 +12,19 @@ import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 import langbot_plugin.api.entities.builtin.provider.message as provider_message
 
 
+LLM_USAGE_QUERY_VARIABLE = '_llm_usage'
+STREAM_USAGE_QUERY_VARIABLE = '_stream_usage'
+
+
+def _store_llm_usage(query: pipeline_query.Query | None, usage_info: dict | None) -> None:
+    """Store the latest provider usage on the query for upstream action handlers."""
+    if query is None or not usage_info:
+        return
+    if query.variables is None:
+        query.variables = {}
+    query.variables[LLM_USAGE_QUERY_VARIABLE] = dict(usage_info)
+
+
 class RuntimeProvider:
     """运行时模型提供商"""
 
@@ -67,6 +80,7 @@ class RuntimeProvider:
             if isinstance(result, tuple):
                 msg, usage_info = result
                 if usage_info:
+                    _store_llm_usage(query, usage_info)
                     input_tokens = usage_info.get('prompt_tokens', 0)
                     output_tokens = usage_info.get('completion_tokens', 0)
                 return msg
@@ -146,11 +160,12 @@ class RuntimeProvider:
             if query:
                 if query.variables is None:
                     query.variables = {}
-                if '_stream_usage' in query.variables:
-                    usage_info = query.variables['_stream_usage']
+                if STREAM_USAGE_QUERY_VARIABLE in query.variables:
+                    usage_info = query.variables[STREAM_USAGE_QUERY_VARIABLE]
+                    _store_llm_usage(query, usage_info)
                     input_tokens = usage_info.get('prompt_tokens', 0)
                     output_tokens = usage_info.get('completion_tokens', 0)
-                    del query.variables['_stream_usage']
+                    del query.variables[STREAM_USAGE_QUERY_VARIABLE]
         except Exception as e:
             status = 'error'
             error_message = str(e)

src/langbot/pkg/provider/modelmgr/requesters/litellmchat.py

@@ -75,22 +75,33 @@ class LiteLLMRequester(requester.ProviderAPIRequester):
                 continue
         return False
 
+    @staticmethod
+    def _positive_int(value: typing.Any) -> int | None:
+        if isinstance(value, bool):
+            return None
+        if isinstance(value, int) and value > 0:
+            return value
+        if isinstance(value, str) and value.isdigit():
+            parsed_value = int(value)
+            if parsed_value > 0:
+                return parsed_value
+        return None
+
     def _context_length_from_scan_payload(self, model_payload: dict[str, typing.Any] | None) -> int | None:
         if not model_payload:
             return None
 
         for field_name in ('context_length', 'context_window', 'max_context_length'):
-            value = model_payload.get(field_name)
-            if isinstance(value, bool):
-                continue
-            if isinstance(value, int) and value > 0:
-                return value
-            if isinstance(value, str) and value.isdigit():
-                parsed_value = int(value)
-                if parsed_value > 0:
-                    return parsed_value
+            context_length = self._positive_int(model_payload.get(field_name))
+            if context_length is not None:
+                return context_length
         return None
 
+    def _context_length_from_litellm_model_info(self, model_info: typing.Any) -> int | None:
+        if isinstance(model_info, dict):
+            return self._positive_int(model_info.get('max_input_tokens'))
+        return self._positive_int(getattr(model_info, 'max_input_tokens', None))
+
     def _metadata_provider_candidates(self, model_name: str) -> list[str]:
         normalized_model_name = (model_name or '').lower()
         candidates = []
@@ -126,7 +137,7 @@ class LiteLLMRequester(requester.ProviderAPIRequester):
         return None
 
     def _safe_context_length(self, model_name: str) -> int | None:
-        helper = getattr(litellm, 'get_max_tokens', None)
+        helper = getattr(litellm, 'get_model_info', None)
         if not callable(helper):
             return self._known_context_length_fallback(model_name)
 
@@ -143,11 +154,12 @@ class LiteLLMRequester(requester.ProviderAPIRequester):
                 continue
             tried_candidates.append(candidate)
             try:
-                max_tokens = helper(candidate)
+                model_info = helper(candidate)
             except Exception:
                 continue
-            if isinstance(max_tokens, int) and max_tokens > 0:
-                return max_tokens
+            context_length = self._context_length_from_litellm_model_info(model_info)
+            if context_length is not None:
+                return context_length
         return self._known_context_length_fallback(model_name)
 
     def _supports_function_calling(self, model_name: str) -> bool:
@@ -250,32 +262,82 @@ class LiteLLMRequester(requester.ProviderAPIRequester):
         - dict with the same keys
         - missing ``total_tokens`` (derived from prompt + completion)
         - ``None`` / partially-populated usage (defaults to 0)
+        - provider-specific token details, including cache token counters
         """
-        if usage is None:
-            return {'prompt_tokens': 0, 'completion_tokens': 0, 'total_tokens': 0}
 
-        def _get(key: str) -> typing.Any:
-            if isinstance(usage, dict):
-                return usage.get(key)
-            return getattr(usage, key, None)
+        def _plain_value(value: typing.Any) -> typing.Any:
+            if value is None:
+                return None
+            if isinstance(value, dict):
+                return {k: _plain_value(v) for k, v in value.items() if v is not None}
+            if isinstance(value, (list, tuple)):
+                return [_plain_value(v) for v in value]
 
-        prompt_tokens = _get('prompt_tokens') or 0
-        completion_tokens = _get('completion_tokens') or 0
-        total_tokens = _get('total_tokens') or 0
+            model_dump = getattr(value, 'model_dump', None)
+            if callable(model_dump):
+                try:
+                    dumped = model_dump()
+                    if isinstance(dumped, dict):
+                        return _plain_value(dumped)
+                except Exception:
+                    pass
+
+            return value
+
+        def _usage_dict(value: typing.Any) -> dict[str, typing.Any]:
+            if value is None:
+                return {}
+            plain = _plain_value(value)
+            if isinstance(plain, dict):
+                return plain
+
+            def _is_mock_attr(attr: typing.Any) -> bool:
+                return type(attr).__module__.startswith('unittest.mock')
+
+            data: dict[str, typing.Any] = {}
+            for key in (
+                'prompt_tokens',
+                'completion_tokens',
+                'total_tokens',
+                'prompt_tokens_details',
+                'completion_tokens_details',
+                'cache_creation_input_tokens',
+                'cache_read_input_tokens',
+                'input_token_details',
+                'output_token_details',
+            ):
+                attr_value = getattr(value, key, None)
+                if attr_value is not None and not _is_mock_attr(attr_value):
+                    data[key] = _plain_value(attr_value)
+            return data
+
+        def _to_int(value: typing.Any) -> int:
+            try:
+                return int(value or 0)
+            except (TypeError, ValueError):
+                return 0
+
+        normalized = _usage_dict(usage)
+
+        prompt_tokens = _to_int(normalized.get('prompt_tokens'))
+        completion_tokens = _to_int(normalized.get('completion_tokens'))
+        total_tokens = _to_int(normalized.get('total_tokens'))
 
         # Some providers omit total_tokens in streaming usage; derive it.
         if not total_tokens:
             total_tokens = prompt_tokens + completion_tokens
 
-        return {
-            'prompt_tokens': int(prompt_tokens),
-            'completion_tokens': int(completion_tokens),
-            'total_tokens': int(total_tokens),
-        }
+        normalized['prompt_tokens'] = prompt_tokens
+        normalized['completion_tokens'] = completion_tokens
+        normalized['total_tokens'] = total_tokens
+        return normalized
 
-    def _extract_usage(self, response) -> dict:
+    def _extract_usage(self, response) -> dict | None:
         """Extract usage info from a non-streaming LiteLLM response."""
-        return self._normalize_usage(getattr(response, 'usage', None))
+        usage = getattr(response, 'usage', None)
+        if usage is None:
+            return None
+        return self._normalize_usage(usage)
 
     @staticmethod
     def _as_dict(value: typing.Any) -> dict:
@@ -474,7 +536,7 @@ class LiteLLMRequester(requester.ProviderAPIRequester):
                     if query is not None:
                         if query.variables is None:
                             query.variables = {}
-                        query.variables['_stream_usage'] = usage_info
+                        query.variables[requester.STREAM_USAGE_QUERY_VARIABLE] = usage_info
 
                 if not hasattr(chunk, 'choices') or not chunk.choices:
                     continue

src/langbot/pkg/provider/tools/loaders/skill_authoring.py

@@ -117,6 +117,7 @@ class SkillToolLoader(loader.ToolLoader):
             'activated': True,
             'skill_name': skill_name,
             'mount_path': mount_path,
+            'activated_skill_names': skill_loader.get_activated_skill_names(query),
             'content': result_content,
         }
 

src/langbot/pkg/telemetry/heartbeat.py

@@ -109,6 +109,7 @@ async def build_heartbeat_payload(ap: core_app.Application) -> dict:
         'query_id': '',
         'version': constants.semantic_version,
         'instance_id': constants.instance_id,
+        'instance_create_ts': constants.instance_create_ts,
         'edition': constants.edition,
         'features': features,
         'timestamp': datetime.now(timezone.utc).isoformat(),

src/langbot/pkg/utils/constants.py

@@ -16,3 +16,11 @@ debug_mode = False
 edition = 'community'
 
 instance_id = ''
+
+instance_create_ts = 0
+"""Unix timestamp (seconds) of when this instance was first created.
+
+Sourced from ``data/labels/instance_id.json``. Backfilled to the current
+time for instances created before this field existed, so it is always a
+positive value once load_config has run.
+"""