Hacktoberfest 2026: los issues que los mantenedores marcaron para octubre, abiertos y aptos para principiantes. Explorar issues de Hacktoberfest

fix(backtests): the pipeline LLM preflight is 5x optimistic and lets uncompletable runs through

Abierto
  • ¿Algo no está bien?
#522 0 comentarios 0 reacciones 0 asignados Ver en GitHub

Los mantenedores suelen responder en 1 día

Nadie ha tomado este issue todavía.

Evaluación

Dificultad
4/5
Tiempo estimado
3-5 días
Aptitud para principiantes
48/100
Tipo de issue
Error
Claridad
Bastante claro
Estado de actividad
Activo
Stack tecnológico
python
Área
backend

Línea de trabajo

Start by reading _enforce_pipeline_llm_window and the credit_llm_reservations timestamps mentioned in the issue to understand how the current estimate compares with measured per-model wall time. Then inspect portfolio_manager.py for retries and _backtest_subprocess_timeout for the hosted-runtime budget approach. Done means the preflight accounts for measured latency and provider attempts, and does not approve runs that cannot fit the budget.

Escrito por el modelo de indexación a partir del texto del issue.

Descripción

Prod run agent_20260922_202119_fc7bd724 (DJIA 30, 2026-09-07→09-18, deepseek/deepseek-v4-pro, pipeline + platform_credits) was killed at the 3600s limit having completed 47 of the 70 decision bars it needed. No results; the user was billed 81,130 micro-credits for 38 model calls.

_enforce_pipeline_llm_window approved it with what looked like a 2.9x margin:
estimated calls 70 (10 trading days x 7 bars x 1 pipeline step)
allowed 200 — (3600 - 600) // PIPELINE_SECONDS_PER_LLM_CALL
implied wall clock @ 15s/call 1050s
measured wall clock 76.7 s/call (decision-bar cycle: median 63.0s, mean 75.6s, n=46)
calls that fit in 3600s at the measured rate 47

The estimate is 5.1x optimistic, so the headroom is fictional — a run needing ~5370s passed a 3600s budget check.

Two separate errors in the model:

  1. The 15s constant was never fitted. It is documented as a calibrated estimate where under-estimating is the safe direction, which is correct for a refusal — but nothing has ever measured it, and it is plainly wrong for a reasoning model.
  2. It counts calls, not attempts. Every call on this run made 2 provider attempts (see the OpenRouter issue filed alongside this), and portfolio_manager.py retries an empty reply up to 4x on top of that.

credit_llm_reservations timestamps give per-model wall clock directly, so this is measurable from data already in prod rather than by guessing a bigger constant.

  • Re-fit the default from prod data, or make it per-model.
  • Account for attempts, not just calls.
  • Reconsider sizing the pipeline budget from the window, as _backtest_subprocess_timeout already does for the hosted runtime. #474 item 1 chose fixed-budget + preflight; the preflight is the half that turned out mis-calibrated.

Related: #474 (closed).

Filed from one diagnosis of the same prod run: #522 (why it timed out) · #523 (the dead primary provider) · #524 (why nothing is visible afterwards) · #525 (the refund log flood).

Lenguaje dominante
Python
Estrellas
767
Forks
156
Merge medio
22 h 57 min
PR fusionados (30 d)
84

Preparar el entorno

  • Incluye un Dockerfile o un archivo de Docker Compose
  • Sin plantilla de pull request
  • Sin guía de contribución

Primeros pasos

  1. Lee el issue completo y luego la guía de contribución del proyecto.
  2. Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
  3. Haz un fork del repositorio y trabaja en una rama.
  4. Abre un pull request que haga referencia al número del issue.

Más de Open-Finance-Lab/AgenticTrading

Todos los issues de Open-Finance-Lab/AgenticTrading

Issues similares

Más issues de Python

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.