[Bug]: strict json.loads on lax LLM JSON breaks extraction (trailing commas) and 500s /flush

Abierto
  • ¿Algo no está bien?
#564 1 comentario 0 reacciones 0 asignados Ver en GitHub

Los mantenedores suelen responder en 1 día

@1AbdullahButt ya está trabajando en esto.

Desde el 6/11/2026.

  • #580 de @1AbdullahButt — abierto

Evaluación

Dificultad
3/5
Tiempo estimado
1-2 días
Aptitud para principiantes
74/100
Tipo de issue
Error
Claridad
Bien especificado
Estado de actividad
Activo
Stack tecnológico
python
Área
ai, backend

Línea de trabajo

Start with everalgo/user_memory/episode.py and its _extract_json_object() parsing path, then compare the related call sites in profile.py, atomic_fact.py, and foresight.py. Reproduce with the trailing-comma JSON example in the issue and trace how extraction errors reach /api/v2/memory/flush. Done when malformed LLM JSON no longer crashes flush with a 500 and extraction failures are handled as described.

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

Descripción

Title: memorize_extraction_failed with strict json.loads on lax LLM JSON; extraction error crashes /flush with 500

Environment

  • everos 1.5.1 (uv tool install), everalgo vendored
  • [llm] provider: DeepSeek (deepseek-chat, OpenAI-compatible), embeddings: DashScope text-embedding-v4
  • Observed under real multi-session traffic (~170 /add, ~50 /flush per day)

Symptoms

Intermittent (14 occurrences in ~30h) on flush-triggered extraction:

memorize_extraction_failed  error='JSONDecodeError: Expecting property name enclosed in double quotes: line 4 column 1 (char 2954)'
unhandled_exception         exception_type=JSONDecodeError path=/api/v2/memory/flush
  • The parse failure is unhandled at the route level: POST /api/v2/memory/flush returns 500 instead of degrading gracefully; the memcells stay buffered and retry later, delaying memory availability and logging a traceback every time.
  • episode_extract_retry re-prompts, but retries reproduce the same malformed JSON.

Root cause

LLM output (DeepSeek in our case) is occasionally not strict RFC-8259 JSON — e.g. trailing commas before a closing brace ({..., }), which produces exactly Expecting property name enclosed in double quotes: line N column 1. The extraction path does strict parsing with no repair:

  • everalgo/user_memory/episode.py: _extract_json_object() (brace-balanced substring) → bare json.loads(json_str) — no response_format={"type":"json_object"} enforcement, no sanitization.
  • Same pattern in profile.py (×3 sites), atomic_fact.py, foresight.py. (everalgo.llm.parse.parse_llm_json_object already has a multi-strategy parser, but these modules don't use it.)

GLM and some other providers happen to emit strict JSON, which masks the bug; switching providers exposes it.

Suggested fixes (any one suffices; first is smallest)

  1. One repair pass before strict parsing: strip commas directly preceding } / ], e.g. re.sub(r",\s*([}\]])", r"\1", json_str) on JSONDecodeError, retry once.
  2. Route all extractor call sites through everalgo.llm.parse.parse_llm_json_object and add the same repair as a strategy there (single choke point — the four _extract_json_object copies are already duplicated).
  3. Optionally enforce response_format={"type": "json_object"} for OpenAI-compatible providers that support it.
  4. Separately: catch extraction exceptions in the /flush handler and return a structured error envelope instead of an unhandled 500.

Repro

Any OpenAI-compatible model that emits a trailing comma (DeepSeek deepseek-chat does this intermittently) + a flush that triggers episode extraction. Local repro of the parse failure: json.loads('{\n"title": "<1200 chars>",\n"content": "<1500 chars>",\n}') → JSONDecodeError: Expecting property name enclosed in double quotes: line 4 column 1.

Local workaround

Patched the four modules with a _loads_lenient helper (repair-once-on-JSONDecodeError); failures stopped. Happy to send the diff/PR.

Lenguaje dominante
Python
Estrellas
13.3k
Forks
926
Merge medio
19 h 29 min
PR fusionados (30 d)
43

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 EverMind-AI/EverOS

Todos los issues de EverMind-AI/EverOS

Issues similares

Más issues de Python

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.