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_streaming_integration.py

@@ -10,6 +10,7 @@ from unittest.mock import AsyncMock, MagicMock
 from trustgraph.agent.react.agent_manager import AgentManager
 from trustgraph.agent.react.tools import KnowledgeQueryImpl
 from trustgraph.agent.react.types import Tool, Argument
+from trustgraph.base import PromptResult
 from tests.utils.streaming_assertions import (
     assert_agent_streaming_chunks,
     assert_streaming_chunks_valid,
@@ -51,10 +52,10 @@ Args: {
                     is_final = (i == len(chunks) - 1)
                     await chunk_callback(chunk, is_final)
 
-                return full_text
+                return PromptResult(response_type="text", text=full_text)
             else:
                 # Non-streaming response - same text
-                return full_text
+                return PromptResult(response_type="text", text=full_text)
 
         client.agent_react.side_effect = agent_react_streaming
         return client
@@ -317,8 +318,8 @@ Final Answer: AI is the simulation of human intelligence in machines."""
                 for i, chunk in enumerate(chunks):
                     is_final = (i == len(chunks) - 1)
                     await chunk_callback(chunk + " ", is_final)
-                return response
-            return response
+                return PromptResult(response_type="text", text=response)
+            return PromptResult(response_type="text", text=response)
 
         mock_prompt_client_streaming.agent_react.side_effect = multi_step_agent_react