mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-25 00:16:23 +02:00
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:
parent
67cfa80836
commit
14e49d83c7
60 changed files with 1252 additions and 577 deletions
|
|
@ -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
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue