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/unit/test_extract/test_streaming_triples/test_definitions_batching.py

@@ -12,6 +12,7 @@ from unittest.mock import AsyncMock, MagicMock
 from trustgraph.extract.kg.definitions.extract import (
     Processor, default_triples_batch_size, default_entity_batch_size,
 )
+from trustgraph.base import PromptResult
 from trustgraph.schema import (
     Chunk, Triples, EntityContexts, Triple, Metadata, Term, IRI, LITERAL,
 )
@@ -51,8 +52,12 @@ def _make_flow(prompt_result, llm_model="test-llm", ontology_uri="test-onto"):
     mock_triples_pub = AsyncMock()
     mock_ecs_pub = AsyncMock()
     mock_prompt_client = AsyncMock()
+    if isinstance(prompt_result, list):
+        wrapped = PromptResult(response_type="jsonl", objects=prompt_result)
+    else:
+        wrapped = PromptResult(response_type="text", text=prompt_result)
     mock_prompt_client.extract_definitions = AsyncMock(
-        return_value=prompt_result
+        return_value=wrapped
     )
 
     def flow(name):

tests/unit/test_extract/test_streaming_triples/test_relationships_batching.py

@@ -14,6 +14,7 @@ from trustgraph.extract.kg.relationships.extract import (
 from trustgraph.schema import (
     Chunk, Triples, Triple, Metadata, Term, IRI, LITERAL,
 )
+from trustgraph.base import PromptResult
 
 
 # ---------------------------------------------------------------------------
@@ -58,7 +59,10 @@ def _make_flow(prompt_result, llm_model="test-llm", ontology_uri="test-onto"):
     mock_triples_pub = AsyncMock()
     mock_prompt_client = AsyncMock()
     mock_prompt_client.extract_relationships = AsyncMock(
-        return_value=prompt_result
+        return_value=PromptResult(
+            response_type="jsonl",
+            objects=prompt_result,
+        )
     )
 
     def flow(name):