mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-21 16:18:55 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

Merge pull request #67788 from NousResearch/perf/backend-ttft-request-estimate

Browse source 
perf(agent): drop per-call base64 re-serialization from request-size estimate
This commit is contained in:
brooklyn! 2026-07-19 21:09:51 -05:00 • committed by GitHub
commit b61c033c0b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 9 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

18
agent/conversation_loop.py
View file

@ -52,6 +52,7 @@ from agent.message_sanitization import (
)
from agent.model_metadata import (
MINIMUM_CONTEXT_LENGTH,
_estimate_tools_tokens_rough,
estimate_messages_tokens_rough,
estimate_request_tokens_rough,
get_context_length_from_provider_error,
@ -1072,17 +1073,16 @@ def run_conversation(
# the OpenAI SDK. Sanitizing here prevents the 3-retry cycle.
_sanitize_messages_surrogates(api_messages)
# Calculate approximate request size for logging and pressure checks.
# estimate_messages_tokens_rough(api_messages) includes the system
# prompt copy but not the tool schema payload, which is sent as a
# separate field. Add tools back for compression decisions so long
# tool-heavy turns do not creep up to the context ceiling and leave
# no room for the model's final answer.
total_chars = sum(len(str(msg)) for msg in api_messages)
# One image-stripped message estimate feeds both figures. Was: a
# str(msg) char walk (re-serialized base64 every call) + a second
# messages walk inside estimate_request_tokens_rough. Tools added
# separately (compression needs them: 50+ tools = 20-30K tokens).
# total_chars is a rough (~) proxy — verbose log + hook metric only.
approx_tokens = estimate_messages_tokens_rough(api_messages)
request_pressure_tokens = estimate_request_tokens_rough(
api_messages, tools=agent.tools or None
request_pressure_tokens = approx_tokens + (
_estimate_tools_tokens_rough(agent.tools) if agent.tools else 0
)
total_chars = approx_tokens * 4
_runtime_context_error = _ollama_context_limit_error(
agent, request_pressure_tokens