6a03fdf284
- LiteLLMAdapter (subclasses OpenAIAdapter via _acreate hook): routes DeepSeek through LiteLLM. Opt-in AGENTIC_DEFAULT_MODEL_PROVIDER=litellm. A/B beat the hand-rolled adapter (0 DSML, 0 parse-fails). Defensive chunk.usage getattr, token-estimate usage fallback for billing, quiet litellm logs. - DSML parser: tolerate single/multi fullwidth pipes, honor string="true/false" typed args (openai_adapter fallback when DeepSeek leaks tool calls as text). - Thinking mode: capture and round-trip reasoning_content across turns. - Embeddings: dedicated AGENTIC_EMBEDDINGS_API_KEY (DeepSeek has no embeddings); disable cleanly when unset to avoid per-turn 401. - claude_format: friendly generic error messages to the chat, raw only in logs. - acai agent max_tokens 4096->16384 (whole-file writes no longer truncate); system.md size-based edit policy; strict tools opt-in (off). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
25 lines
859 B
YAML
25 lines
859 B
YAML
name: acai
|
|
display_name: "Acai Developer"
|
|
description: "Agente genérico de Acai CMS: crea módulos, edita contenido, gestiona datos, hooks y todo lo relacionado con el desarrollo de tu web."
|
|
icon: "code"
|
|
category: "development"
|
|
temperature: 0.2
|
|
# 16K de salida: cubre escribir un fichero entero (acai_write) + el razonamiento
|
|
# (thinking) en un solo turno. Con 4096 el JSON del tool_use se truncaba a mitad
|
|
# en ficheros medianos y el agente caia en micro-ediciones lentas. v4-pro soporta
|
|
# hasta 384K de salida, asi que 16K es conservador.
|
|
max_tokens: 16384
|
|
context_sections:
|
|
- immutable_rules
|
|
- project_profile
|
|
- knowledge_base
|
|
- task_state
|
|
allowed_tools: []
|
|
model_id: null
|
|
# planner_model_id: null # null → usa AGENTIC_PLANNER_MODEL_ID del .env
|
|
stream_deltas: true
|
|
kb_load_strategy: top_n
|
|
kb_max_tokens: 4000
|
|
kb_top_n: 2
|
|
has_planner_tool: true
|