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

trustgraph-flow/trustgraph/extract/kg/definitions/extract.py

@@ -117,10 +117,11 @@ class Processor(FlowProcessor):
 
             try:
 
-                defs = await flow("prompt-request").extract_definitions(
+                result = await flow("prompt-request").extract_definitions(
                     text = chunk
                 )
 
+                defs = result.objects
                 logger.debug(f"Definitions response: {defs}")
 
                 if type(defs) != list:

trustgraph-flow/trustgraph/extract/kg/ontology/extract.py

@@ -376,10 +376,11 @@ class Processor(FlowProcessor):
         """
         try:
             # Call prompt service with simplified format prompt
-            extraction_response = await flow("prompt-request").prompt(
+            result = await flow("prompt-request").prompt(
                 id="extract-with-ontologies",
                 variables=prompt_variables
             )
+            extraction_response = result.object
             logger.debug(f"Simplified extraction response: {extraction_response}")
 
             # Parse response into structured format

trustgraph-flow/trustgraph/extract/kg/relationships/extract.py

@@ -100,10 +100,11 @@ class Processor(FlowProcessor):
 
             try:
 
-                rels = await flow("prompt-request").extract_relationships(
+                result = await flow("prompt-request").extract_relationships(
                     text = chunk
                 )
 
+                rels = result.objects
                 logger.debug(f"Prompt response: {rels}")
 
                 if type(rels) != list:

trustgraph-flow/trustgraph/extract/kg/rows/processor.py

@@ -148,11 +148,12 @@ class Processor(FlowProcessor):
             schema_dict = row_schema_translator.encode(schema)
             
             # Use prompt client to extract rows based on schema
-            objects = await flow("prompt-request").extract_objects(
+            result = await flow("prompt-request").extract_objects(
                 schema=schema_dict,
                 text=text
             )
-            
+
+            objects = result.objects
             if not isinstance(objects, list):
                 return []