refactor(agent-runner): remove protocol_version from various components and update related documentation

src/langbot/pkg/agent/runner/context_builder.py

@@ -124,7 +124,6 @@ class AgentRuntimeContext(typing.TypedDict):
     """Agent runtime context."""
 
     langbot_version: str | None
-    protocol_version: str
     trace_id: str | None
     deadline_at: float | None
     metadata: dict[str, typing.Any]
@@ -272,7 +271,6 @@ class AgentRunContextBuilder:
         # Build runtime context
         runtime: AgentRuntimeContext = {
             'langbot_version': self.ap.ver_mgr.get_current_version(),
-            'protocol_version': descriptor.protocol_version,
             'trace_id': run_id,
             'deadline_at': self._build_deadline_from_binding(binding),
             'metadata': {
@@ -424,6 +422,5 @@ class AgentRunContextBuilder:
                 'artifact_read': artifact_read_enabled,
                 'state': state_enabled,
                 'storage': True,
-                'prompt_get': False,
             },
         }

src/langbot/pkg/agent/runner/descriptor.py

@@ -36,9 +36,6 @@ class AgentRunnerDescriptor(pydantic.BaseModel):
     plugin_version: str | None = None
     """Optional plugin version"""
 
-    protocol_version: str = '1'
-    """SDK protocol version, default '1'"""
-
     config_schema: list[dict[str, typing.Any]] = []
     """Configuration schema using DynamicForm format"""
 
@@ -69,4 +66,4 @@ class AgentRunnerDescriptor(pydantic.BaseModel):
 
     def supports_knowledge_retrieval(self) -> bool:
         """Check if runner supports knowledge retrieval."""
-        return self.capabilities.get('knowledge_retrieval', False)
+        return self.capabilities.get('knowledge_retrieval', False)

src/langbot/pkg/agent/runner/orchestrator.py

@@ -97,8 +97,6 @@ class AgentRunOrchestrator:
             session_query_id = adapter_context.get('query_id')
             if 'params' in adapter_context:
                 context['adapter']['extra']['params'] = adapter_context['params']
-            if adapter_context.get('prompt_get'):
-                context['context']['available_apis']['prompt_get'] = True
 
         state_context = build_state_context(event, binding, descriptor)
         run_id = context['run_id']

src/langbot/pkg/agent/runner/query_entry_adapter.py

@@ -149,7 +149,6 @@ class QueryEntryAdapter:
         return {
             'params': cls.build_params(query),
             'query_id': getattr(query, 'query_id', None),
-            'prompt_get': cls._has_effective_prompt(query),
         }
 
     @classmethod
@@ -187,12 +186,6 @@ class QueryEntryAdapter:
             )
         return False
 
-    @classmethod
-    def _has_effective_prompt(cls, query: pipeline_query.Query) -> bool:
-        prompt = getattr(query, 'prompt', None)
-        messages = getattr(prompt, 'messages', None) if prompt is not None else None
-        return isinstance(messages, list)
-
     # Private helper methods
 
     @classmethod

src/langbot/pkg/agent/runner/registry.py

@@ -80,7 +80,7 @@ class AgentRunnerRegistry:
             runner_data: Raw runner data from plugin runtime with fields:
                 - plugin_author, plugin_name, runner_name
                 - manifest (full component manifest dict)
-                - protocol_version, capabilities, permissions, config (extracted from spec)
+                - capabilities, permissions, config (extracted from spec)
 
         Returns:
             AgentRunnerDescriptor if valid, None if invalid
@@ -114,7 +114,6 @@ class AgentRunnerRegistry:
 
         # SDK now provides these directly extracted from spec. Fall back to
         # manifest.spec for older runtimes/tests that return the raw manifest.
-        protocol_version = runner_data.get('protocol_version') or spec.get('protocol_version', '1')
         config_schema = runner_data.get('config') or spec.get('config', [])
         capabilities = runner_data.get('capabilities') or spec.get('capabilities', {})
         permissions = runner_data.get('permissions') or spec.get('permissions', {})
@@ -136,7 +135,6 @@ class AgentRunnerRegistry:
             plugin_name=plugin_name,
             runner_name=runner_name,
             plugin_version=runner_data.get('plugin_version'),
-            protocol_version=protocol_version,
             config_schema=config_schema,
             capabilities=capabilities,
             permissions=permissions,

src/langbot/pkg/plugin/handler.py

@@ -378,25 +378,6 @@ def _resolve_remove_think(data: dict[str, Any], query: Any | None) -> bool:
     return False
 
 
-def _dump_prompt_messages(query: Any) -> list[dict[str, Any]]:
-    """Serialize the current effective prompt from a cached Query."""
-    prompt = getattr(query, 'prompt', None)
-    messages = getattr(prompt, 'messages', None) if prompt is not None else None
-    if not isinstance(messages, list):
-        return []
-
-    dumped: list[dict[str, Any]] = []
-    for message in messages:
-        if hasattr(message, 'model_dump'):
-            try:
-                dumped.append(message.model_dump(mode='json'))
-            except TypeError:
-                dumped.append(message.model_dump())
-        elif isinstance(message, dict):
-            dumped.append(message)
-    return dumped
-
-
 def _merge_model_extra_args(model: Any, call_extra_args: Any) -> dict[str, Any]:
     """Merge persisted model extra_args with action-level overrides."""
     merged: dict[str, Any] = {}
@@ -1250,7 +1231,7 @@ class RuntimeConnectionHandler(handler.Handler):
             except Exception as e:
                 return _make_rag_error_response(e, 'VectorStoreError', collection_id=collection_id)
 
-        @self.action(PluginToRuntimeAction.GET_KNOWLEDGE_FILE_STREAM)
+        @self.action(PluginToRuntimeAction.GET_KNOWLEDEGE_FILE_STREAM)
         async def get_knowledge_file_stream(data: dict[str, Any]) -> handler.ActionResponse:
             storage_path = data['storage_path']
             try:
@@ -1458,32 +1439,6 @@ class RuntimeConnectionHandler(handler.Handler):
 
         # ================= Agent History/Event APIs =================
 
-        @self.action(PluginToRuntimeAction.PROMPT_GET)
-        async def prompt_get(data: dict[str, Any]) -> handler.ActionResponse:
-            """Return the post-preprocessing effective prompt for a query-backed run."""
-            run_id = data.get('run_id')
-            caller_plugin_identity = data.get('caller_plugin_identity')
-
-            if not run_id:
-                return handler.ActionResponse.error(message='run_id is required')
-
-            session, error = await _validate_agent_run_session(
-                run_id,
-                caller_plugin_identity,
-                self.ap,
-                'Prompt get',
-            )
-            if error:
-                return error
-
-            query = _resolve_action_query(data, session, self.ap)
-            if query is None:
-                return handler.ActionResponse.error(
-                    message='Prompt get is only available for query-backed agent runs',
-                )
-
-            return handler.ActionResponse.success(data={'prompt': _dump_prompt_messages(query)})
-
         @self.action(PluginToRuntimeAction.HISTORY_PAGE)
         async def history_page(data: dict[str, Any]) -> handler.ActionResponse:
             """Page through transcript history for a conversation.
@@ -2236,7 +2191,6 @@ class RuntimeConnectionHandler(handler.Handler):
         - runner_name
         - runner_description
         - manifest
-        - protocol_version
         - capabilities
         - permissions
         - config

src/langbot/pkg/rag/service/runtime.py

@@ -107,7 +107,7 @@ class RAGRuntimeService:
         )
 
     async def get_file_stream(self, storage_path: str) -> bytes:
-        """Handle GET_KNOWLEDGE_FILE_STREAM action.
+        """Handle GET_KNOWLEDEGE_FILE_STREAM action.
 
         Uses the storage manager abstraction to load file content,
         regardless of the underlying storage provider.