trace: Claude Code's `<synthetic>` notices count as requests and can make a Claude session price on the fallback curve

Abierto
  • ¿Algo no está bien?
#189 0 comentarios 0 reacciones 0 asignados Ver en GitHub

Los mantenedores suelen responder en 1 día

@1AbdullahButt ya está trabajando en esto.

Desde el 9/11/2026.

  • #190 de @1AbdullahButt — abierto

Evaluación

Dificultad
2/5
Tiempo estimado
1-3 horas
Aptitud para principiantes
20/100
Tipo de issue
Error
Claridad
Bien especificado
Estado de actividad
Estancado
Stack tecnológico
python
Área
ai, backend

Línea de trabajo

Read tokeneconomizer/trace/claude.py around claude_session_usage and the linked accounting code in tokeneconomizer/plugin/accounting.py. The issue includes a reproduction and expected output; compare how synthetic assistant entries affect request counting and model selection. Done means the reproduction reports one request, the real Claude model, and model pricing. A linked pull request is already open.

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

Descripción

When a request fails, or there is nothing to answer, Claude Code writes its own notice into the session log as an assistant entry. The entry has "model": "<synthetic>", its own message id, and a usage object of zeros. For example:

{"type": "assistant", "isApiErrorMessage": true, "message": {"id": "046e4526-...", "model": "<synthetic>", "role": "assistant", "usage": {"input_tokens": 0, "output_tokens": 0, "cache_creation_input_tokens": 0, "cache_read_input_tokens": 0, ...}, "content": [{"type": "text", "text": "API Error: Can't reach the API server ..."}]}}

I see these in my own logs for "API Error: ..." and "No response requested.".

claude_session_usage (trace/claude.py#L298-L315) counts each of these entries as a request and as a vote for <synthetic> as the session's model. So:

  • requests is too high by one for every notice. This number is in the ledger and in te status.
  • If the notices outnumber the real replies, model becomes <synthetic>. pricing.weights_for has no entry for it, so accounting.effective prices a plain Claude session on the fallback curve and records priced_by: "fallback". The accounting docstring says Claude ids never need the fallback. The fallback weighs output at 6x, where Claude's curve uses 5x.

The token totals are right, because the notices carry zeros.

Repro (on main at 264e7a7): one real reply, then two notices.

import json, os, tempfile
from tokeneconomizer import trace
from tokeneconomizer.plugin import accounting

def asst(mid, model, usage):
    return json.dumps({"type": "assistant", "message": {"id": mid, "model": model,
        "role": "assistant", "content": [{"type": "text", "text": "x"}], "usage": usage}})

zero = dict.fromkeys(("input_tokens", "output_tokens", "cache_creation_input_tokens",
                      "cache_read_input_tokens"), 0)
real = {"input_tokens": 10, "output_tokens": 200, "cache_creation_input_tokens": 1000,
        "cache_read_input_tokens": 5000}
p = os.path.join(tempfile.mkdtemp(), "s.jsonl")
open(p, "w").write("\n".join([asst("msg_1", "claude-sonnet-4-5", real),
                              asst("u-1", "<synthetic>", zero),
                              asst("u-2", "<synthetic>", zero)]) + "\n")
u = trace.claude_session_usage(p)
print(u["requests"], u["model"], accounting.effective(u))

Expected: 1 claude-sonnet-4-5 (2760.0, 'model')
Actual: 3 <synthetic> (2960.0, 'fallback')

I have a fix with a regression test and will open a PR.

Lenguaje dominante
Python
Estrellas
5.6k
Forks
344
Merge medio
14 h 41 min
PR fusionados (30 d)
54

Preparar el entorno

Este proyecto no incluye contenedor de desarrollo, Dockerfile ni guía de contribución, así que la configuración corre por tu cuenta: empieza por su README y consulta nuestra guía para la primera contribución para los pasos generales.

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 microsoft/TokenEconomizer

Todos los issues de microsoft/TokenEconomizer

Issues similares

Más issues de Python

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.