Expose LLM token usage across all service layers (#782)

Expose LLM token usage (in_token, out_token, model) across all
service layers

Propagate token counts from LLM services through the prompt,
text-completion, graph-RAG, document-RAG, and agent orchestrator
pipelines to the API gateway and Python SDK. All fields are Optional
— None means "not available", distinguishing from a real zero count.

Key changes:

- Schema: Add in_token/out_token/model to TextCompletionResponse,
  PromptResponse, GraphRagResponse, DocumentRagResponse,
  AgentResponse

- TextCompletionClient: New TextCompletionResult return type. Split
  into text_completion() (non-streaming) and
  text_completion_stream() (streaming with per-chunk handler
  callback)

- PromptClient: New PromptResult with response_type
  (text/json/jsonl), typed fields (text/object/objects), and token
  usage. All callers updated.

- RAG services: Accumulate token usage across all prompt calls
  (extract-concepts, edge-scoring, edge-reasoning,
  synthesis). Non-streaming path sends single combined response
  instead of chunk + end_of_session.

- Agent orchestrator: UsageTracker accumulates tokens across
  meta-router, pattern prompt calls, and react reasoning. Attached
  to end_of_dialog.

- Translators: Encode token fields when not None (is not None, not truthy)

- Python SDK: RAG and text-completion methods return
  TextCompletionResult (non-streaming) or RAGChunk/AgentAnswer with
  token fields (streaming)

- CLI: --show-usage flag on tg-invoke-llm, tg-invoke-prompt,
  tg-invoke-graph-rag, tg-invoke-document-rag, tg-invoke-agent

tests/integration/test_agent_structured_query_integration.py

@@ -16,6 +16,7 @@ from trustgraph.schema import (
     Error
 )
 from trustgraph.agent.react.service import Processor
+from trustgraph.base import PromptResult
 
 
 @pytest.mark.integration  
@@ -95,11 +96,14 @@ class TestAgentStructuredQueryIntegration:
         
         # Mock the prompt client that agent calls for reasoning
         mock_prompt_client = AsyncMock()
-        mock_prompt_client.agent_react.return_value = """Thought: I need to find customers from New York using structured query
+        mock_prompt_client.agent_react.return_value = PromptResult(
+            response_type="text",
+            text="""Thought: I need to find customers from New York using structured query
 Action: structured-query
 Args: {
     "question": "Find all customers from New York"
 }"""
+        )
         
         # Set up flow context routing
         def flow_context(service_name):
@@ -173,11 +177,14 @@ Args: {
         
         # Mock the prompt client that agent calls for reasoning
         mock_prompt_client = AsyncMock()
-        mock_prompt_client.agent_react.return_value = """Thought: I need to query for a table that might not exist
+        mock_prompt_client.agent_react.return_value = PromptResult(
+            response_type="text",
+            text="""Thought: I need to query for a table that might not exist
 Action: structured-query
 Args: {
     "question": "Find data from a table that doesn't exist"
 }"""
+        )
         
         # Set up flow context routing
         def flow_context(service_name):
@@ -250,11 +257,14 @@ Args: {
         
         # Mock the prompt client that agent calls for reasoning
         mock_prompt_client = AsyncMock()
-        mock_prompt_client.agent_react.return_value = """Thought: I need to find customers from California first
+        mock_prompt_client.agent_react.return_value = PromptResult(
+            response_type="text",
+            text="""Thought: I need to find customers from California first
 Action: structured-query
 Args: {
     "question": "Find all customers from California"
 }"""
+        )
         
         # Set up flow context routing
         def flow_context(service_name):
@@ -339,11 +349,14 @@ Args: {
         
         # Mock the prompt client that agent calls for reasoning
         mock_prompt_client = AsyncMock()
-        mock_prompt_client.agent_react.return_value = """Thought: I need to query the sales data
+        mock_prompt_client.agent_react.return_value = PromptResult(
+            response_type="text",
+            text="""Thought: I need to query the sales data
 Action: structured-query
 Args: {
     "question": "Query the sales data for recent transactions"
 }"""
+        )
         
         # Set up flow context routing
         def flow_context(service_name):
@@ -447,11 +460,14 @@ Args: {
         
         # Mock the prompt client that agent calls for reasoning
         mock_prompt_client = AsyncMock()
-        mock_prompt_client.agent_react.return_value = """Thought: I need to get customer information
+        mock_prompt_client.agent_react.return_value = PromptResult(
+            response_type="text",
+            text="""Thought: I need to get customer information
 Action: structured-query
 Args: {
     "question": "Get customer information and format it nicely"
 }"""
+        )
         
         # Set up flow context routing
         def flow_context(service_name):