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_graph_rag_integration.py

@@ -12,6 +12,7 @@ import pytest
 from unittest.mock import AsyncMock, MagicMock
 from trustgraph.retrieval.graph_rag.graph_rag import GraphRag
 from trustgraph.schema import EntityMatch, Term, IRI
+from trustgraph.base import PromptResult
 
 
 @pytest.mark.integration
@@ -93,18 +94,21 @@ class TestGraphRagIntegration:
         # 4. kg-synthesis returns the final answer
         async def mock_prompt(prompt_name, variables=None, streaming=False, chunk_callback=None):
             if prompt_name == "extract-concepts":
-                return ""  # Falls back to raw query
+                return PromptResult(response_type="text", text="")
             elif prompt_name == "kg-edge-scoring":
-                return ""  # No edges scored
+                return PromptResult(response_type="text", text="")
             elif prompt_name == "kg-edge-reasoning":
-                return ""  # No reasoning
+                return PromptResult(response_type="text", text="")
             elif prompt_name == "kg-synthesis":
-                return (
-                    "Machine learning is a subset of artificial intelligence that enables computers "
-                    "to learn from data without being explicitly programmed. It uses algorithms "
-                    "and statistical models to find patterns in data."
+                return PromptResult(
+                    response_type="text",
+                    text=(
+                        "Machine learning is a subset of artificial intelligence that enables computers "
+                        "to learn from data without being explicitly programmed. It uses algorithms "
+                        "and statistical models to find patterns in data."
+                    )
                 )
-            return ""
+            return PromptResult(response_type="text", text="")
 
         client.prompt.side_effect = mock_prompt
         return client
@@ -169,6 +173,7 @@ class TestGraphRagIntegration:
         assert mock_prompt_client.prompt.call_count == 4
 
         # Verify final response
+        response, usage = response
         assert response is not None
         assert isinstance(response, str)
         assert "machine learning" in response.lower()