apunkt/trustgraph
1
0
Fork 0
mirror of https://github.com/trustgraph-ai/trustgraph.git synced 2026-04-25 08:26:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

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

Browse source 
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
This commit is contained in:
cybermaggedon 2026-04-13 14:38:34 +01:00 • committed by GitHub
parent 67cfa80836
commit 14e49d83c7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
60 changed files with 1252 additions and 577 deletions
Download patch file Download diff file Expand all files Collapse all files

87
tests/integration/test_object_extraction_integration.py
View file

@ -16,6 +16,7 @@ from trustgraph.schema import (
Chunk, ExtractedObject, Metadata, RowSchema, Field,
PromptRequest, PromptResponse
)
from trustgraph.base import PromptResult
@pytest.mark.integration
@ -114,49 +115,61 @@ class TestObjectExtractionServiceIntegration:
schema_name = schema.get("name") if isinstance(schema, dict) else schema.name
if schema_name == "customer_records":
if "john" in text.lower():
return [
{
"customer_id": "CUST001",
"name": "John Smith",
"email": "john.smith@email.com",
"phone": "555-0123"
}
]
return PromptResult(
response_type="jsonl",
objects=[
{
"customer_id": "CUST001",
"name": "John Smith",
"email": "john.smith@email.com",
"phone": "555-0123"
}
]
)
elif "jane" in text.lower():
return [
{
"customer_id": "CUST002",
"name": "Jane Doe",
"email": "jane.doe@email.com",
"phone": ""
}
]
return PromptResult(
response_type="jsonl",
objects=[
{
"customer_id": "CUST002",
"name": "Jane Doe",
"email": "jane.doe@email.com",
"phone": ""
}
]
)
else:
return []
return PromptResult(response_type="jsonl", objects=[])
elif schema_name == "product_catalog":
if "laptop" in text.lower():
return [
{
"product_id": "PROD001",
"name": "Gaming Laptop",
"price": "1299.99",
"category": "electronics"
}
]
return PromptResult(
response_type="jsonl",
objects=[
{
"product_id": "PROD001",
"name": "Gaming Laptop",
"price": "1299.99",
"category": "electronics"
}
]
)
elif "book" in text.lower():
return [
{
"product_id": "PROD002",
"name": "Python Programming Guide",
"price": "49.99",
"category": "books"
}
]
return PromptResult(
response_type="jsonl",
objects=[
{
"product_id": "PROD002",
"name": "Python Programming Guide",
"price": "49.99",
"category": "books"
}
]
)
else:
return []
return []
return PromptResult(response_type="jsonl", objects=[])
return PromptResult(response_type="jsonl", objects=[])
prompt_client.extract_objects.side_effect = mock_extract_objects