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
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

View file

@ -9,6 +9,7 @@ from unittest.mock import AsyncMock, MagicMock
from trustgraph.agent.orchestrator.meta_router import (
MetaRouter, DEFAULT_PATTERN, DEFAULT_TASK_TYPE,
)
from trustgraph.base import PromptResult
def _make_config(patterns=None, task_types=None):
@ -28,7 +29,9 @@ def _make_config(patterns=None, task_types=None):
def _make_context(prompt_response):
"""Build a mock context that returns a mock prompt client."""
client = AsyncMock()
client.prompt = AsyncMock(return_value=prompt_response)
client.prompt = AsyncMock(
return_value=PromptResult(response_type="text", text=prompt_response)
)
def context(service_name):
return client
@ -274,8 +277,8 @@ class TestRoute:
nonlocal call_count
call_count += 1
if call_count == 1:
return "research" # task type
return "plan-then-execute" # pattern
return PromptResult(response_type="text", text="research")
return PromptResult(response_type="text", text="plan-then-execute")
client.prompt = mock_prompt
context = lambda name: client