deepseek-v4.1-flash tool-calling regression: missing tool_calls, DSML markers leaking into content (since Sep 22)
Nadie ha tomado este issue todavía.
Evaluación
- Dificultad
- 4/5
- Tiempo estimado
- 3-5 días
- Aptitud para principiantes
- 25/100
Línea de trabajo
No repository file or test is identified. Start by reproducing the request against the deepseek-v4.1-flash OpenAI-compatible endpoint and compare its response with the expected standard tool_calls shape. Check whether the leaked DSML markers occur only for deepseek-family models; done would require a confirmed repository-side path to restore parsing or a clear upstream attribution.
Escrito por el modelo de indexación a partir del texto del issue.
Descripción
Summary
Since the morning of 2026-09-22 (starting 02:21 UTC), tool calling on deepseek-v4.1-flash has regressed: the model no longer returns the standard tool_calls field. Instead, DeepSeek's internal DSML tool-call markup is emitted as plain text inside content, making it unparseable for any agent client that relies on standard tool_calls.
Environment
Client: pi-coding-agent (0.86.1 / 0.87.0 — behavior identical on both, ruling out a client regression)
Model: deepseek-v4.1-flash
API: OpenAI-compatible endpoint, with tools defined in the request body
Affected window: 2026-09-22 10:21 – 10:56 (UTC+8), for server-side log lookup
Expected Behavior
{
"choices": [{
"message": {
"content": null,
"tool_calls": [{
"id": "...",
"type": "function",
"function": { "name": "read", "arguments": "{"path": "..."}" }
}]
}
}]
}
Actual Behavior
I'll run a grilling session. First, let me read the skill and gather the facts.
<｜｜DSML｜｜ calls>
<｜｜DSML｜｜ invoke name="read">
<｜｜DSML｜｜ parameter name="path" string="true">/Users/xiaodi/.agents/skills/grill-me/SKILL.md</｜｜DSML｜｜ parameter>
</｜｜DSML｜｜ invoke>
</｜｜DSML｜｜ calls>
Steps to reproduce the issue
Time | Status -- | -- Sep 16 – 21 | Tool calling fully normal — ~420 responses with parsed tool_calls, zero anomalies Sep 22, 10:21 onward | Identical requests start returning the leaked format; 100% reproducible across retries Sep 22, 10:49 | Client upgraded to 0.87.0 — no change, ruling out a client regression Sep 22, 11:00 | Switching to glm-5.3-flash restores normal tool calling — issue specific to deepseek-family modelsCommand Code Version
go sub
Operating System
macOS
Terminal/IDE
No response
Shell
No response
Session file (optional)
No response
Fix prompt (optional)
No response
Additional context
No response
- Lenguaje dominante
- Sin datos de lenguaje
- Estrellas
- 4k
- Forks
- 350
- Métricas de merge de PR
- Sin PR fusionados en 30 d
Guía de contribución
No hay ninguna guía de contribución indexada para este repositorio
Primeros pasos
- Lee el issue completo y luego la guía de contribución del proyecto.
- Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
- Haz un fork del repositorio y trabaja en una rama.
- Abre un pull request que haga referencia al número del issue.
Más de CommandCodeAI/command-code
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 68/100
CommandCodeAI/command-code#903 · 2 comentarios ·
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 68/100
CommandCodeAI/command-code#855 ·
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 78/100
CommandCodeAI/command-code#841 · 1 comentario ·
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 68/100
CommandCodeAI/command-code#655 · 1 comentario ·
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 68/100
CommandCodeAI/command-code#608 ·
Todos los issues de CommandCodeAI/command-code
Issues similares
-
ai-observability bug team/ai-observability
Dificultad 2/5 1-3 horas Aptitud para principiantes 78/100
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 74/100
dair-ai/Prompt-Engineering-Guide#810 · 1 comentario ·
-
[addtool] DeepZero Abierto
Dificultad 2/5 1-3 horas Aptitud para principiantes 72/100
gwen001/offsectools_www#2055 ·
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 68/100
UKGovernmentBEIS/inspect_evals#2503 ·
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 88/100
google-gemma/gemma-skills#13 ·