bugfix: max_tokens hardcoded

This commit is contained in:
2026-09-19 00:30:53 -03:00
parent 2ad9afd974
commit e7b0ce4912
45 changed files with 464 additions and 284 deletions

View File

@@ -1,250 +0,0 @@
###############################################################################
# AI AGENT PLATFORM - CONFIGURAÇÃO ÚNICA
# Este arquivo é lido por Pydantic Settings no framework e no backend template.
###############################################################################
APP_NAME=ai-agent-template
APP_ENV=local
LOG_LEVEL=INFO
API_HOST=0.0.0.0
API_PORT=8000
CORS_ORIGINS=http://localhost:5173,http://127.0.0.1:5173
###############################################################################
# LLM - OCI Generative AI como provider principal
###############################################################################
# Opções: mock, oci_openai, oci_sdk, openai_compatible
LLM_PROVIDER=oci_sdk
LLM_TEMPERATURE=0.2
LLM_MAX_TOKENS=2048
LLM_TIMEOUT_SECONDS=120
# OCI OpenAI-compatible endpoint
OCI_GENAI_BASE_URL=https://inference.generativeai.us-chicago-1.oci.oraclecloud.com
OCI_GENAI_MODEL=openai.gpt-4.1
OCI_GENAI_API_KEY=sk-ph3FgX6iP3fxAQCXb9IpPIDTadkeeYAWntUWhzcWysIM6zsS
OCI_GENAI_PROJECT_OCID=
#OCI_GENAI_BASE_URL=https://inference.generativeai.eu-frankfurt-1.oci.oraclecloud.com/openai/v1
#OCI_GENAI_MODEL=ocid1.generativeaiendpoint.oc1.eu-frankfurt-1.amaaaaaad6nji3aa5fmicyft7qci6snu5idhwoomviehnsv4lrostzbmenkq
#OCI_GENAI_API_KEY=sk-TB0OzfrhPLXbQTqZ4aKlrLpcgjHAcn11O1o8C4I4aPvWF0Vx
#OCI_GENAI_PROJECT_OCID=
# OCI_AUTH_MODE=config_file|instance_principal|resource_principal
OCI_AUTH_MODE=config_file
# OCI SDK / signer / profiles
OCI_CONFIG_FILE=~/.oci/config
OCI_PROFILE=LATINOAMERICA-Chicago
OCI_COMPARTMENT_ID=ocid1.compartment.oc1..aaaaaaaaexpiw4a7dio64mkfv2t273s2hgdl6mgfvvyv7tycalnjlvpvfl3q
OCI_REGION=us-chicago-1
###############################################################################
# Persistência
###############################################################################
# Opções: memory, autonomous, mongodb
SESSION_REPOSITORY_PROVIDER=autonomous
MEMORY_REPOSITORY_PROVIDER=autonomous
CHECKPOINT_REPOSITORY_PROVIDER=autonomous
# Autonomous Database
ADB_USER=admin
ADB_PASSWORD=Moniquinha19721972
ADB_DSN=oradb23ai_high
ADB_WALLET_LOCATION=/mnt/d/Dropbox/ORACLE/LatinoAmerica/Wallet_ORADB23ai
ADB_WALLET_PASSWORD=Moniquinha1972
ADB_TABLE_PREFIX=AGENTFW
# MongoDB - também pode representar Autonomous usando API compatível com Mongo, se habilitada no ambiente
MONGODB_URI=mongodb://mongo:mongopassword@localhost:27017
MONGODB_DATABASE=agent_platform
# Redis
REDIS_URL=redis://localhost:6379/0
ENABLE_REDIS_CACHE=false
###############################################################################
# RAG / Vector / Graph
###############################################################################
VECTOR_STORE_PROVIDER=autonomous
GRAPH_STORE_PROVIDER=autonomous
RAG_TOP_K=5
EMBEDDING_PROVIDER=oci
OCI_EMBEDDING_MODEL=cohere.embed-multilingual-v3.0
RAG_FILE_GLOBS=*.md,*.txt,*.yaml,*.yml,*.json
###############################################################################
# Observabilidade
###############################################################################
ENABLE_LANGFUSE=true
# Opcional: verbose, compact
LANGFUSE_TRACE_MODE=compact
# Nome customizado do trace pai, ex.: backoffice.checklist.workflow ou backoffice.emulador.workflow
LANGFUSE_COMPACT_VISIBLE_EVENT_PREFIXES=AGA.,NOC., IC.
LANGFUSE_COMPACT_SUPPRESSED_PREFIXES=llm.chat_completion
LANGFUSE_IGNORE_HEALTHCHECKS=true
LANGFUSE_IGNORED_PATHS=/health,/ready,/metrics
LANGFUSE_PUBLIC_KEY=pk-lf-4a1e3921-5158-4fd3-a16d-7a77549fb312
LANGFUSE_SECRET_KEY=sk-lf-efc6fd59-c5ec-4858-b6ec-4aa129734915
LANGFUSE_HOST=http://localhost:3005
ENABLE_OTEL=false
OTEL_EXPORTER_OTLP_ENDPOINT=
OTEL_SERVICE_NAME=ai-agent-template
ENABLE_LANGFUSE_OPENAI_AUTO_INSTRUMENTATION=true
ENABLE_LANGFUSE_ANALYTICS_PUBLISHER=false
###############################################################################
# Analytics / Observer corporativo
###############################################################################
# Quando true, AgentObserver publica eventos IC.*, NOC.* e GRL.* nos providers abaixo.
ENABLE_ANALYTICS=true
# Providers aceitos: oci_streaming,pubsub,noop
ANALYTICS_PROVIDERS=pubsub
# Compatibilidade FIRST/TIM: pode informar AGENT_PUBSUB_TOPIC diretamente.
AGENT_PUBSUB_TOPIC=teste_pubsub
PUBSUB_TOPIC_PATH=projects/project-7f829b68-bf43-442c-ad3/topics/teste_pubsub
PROJECT_ID=project-7f829b68-bf43-442c-ad3
GCP_PUBSUB_TOPIC_PATH=projects/project-7f829b68-bf43-442c-ad3/topics/teste_pubsub
GCP_PROJECT_ID=project-7f829b68-bf43-442c-ad3
GCP_PUBSUB_TOPIC=teste_pubsub
GCP_PUBSUB_TIMEOUT_SECONDS=30
# Credencial GCP segue padrão Google:
GOOGLE_APPLICATION_CREDENTIALS=/mnt/d/Dropbox/ORACLE/TIM/FY27/Testes/sa-hoshikawa.json
PUBSUB_SEQUENCE_ENABLED=true
PUBSUB_SEQUENCE_PROVIDER=mongodb
#PUBSUB_SEQUENCE_MONGODB_URI=mongodb://mongo:mongopassword@localhost:27017
#PUBSUB_SEQUENCE_MONGODB_DATABASE=agent_platform
PUBSUB_SEQUENCE_MONGODB_URI=mongodb://ADMIN:Moniquinha1972@srlrz1eg.adb.sa-saopaulo-1.oraclecloudapps.com:37017/ADMIN?authMechanism=PLAIN&authSource=$external&ssl=true&retryWrites=false&loadBalanced=true
PUBSUB_SEQUENCE_MONGODB_DATABASE=ADMIN
PUBSUB_SEQUENCE_MONGODB_COLLECTION=observer_event_counters
PUBSUB_SEQUENCE_TTL_SECONDS=86400
PUBSUB_SEQUENCE_KEY_PREFIX=observer:sequence
PUBSUB_SEQUENCE_MEMORY_FALLBACK=false
SIMULATE_AGA_MISSING_TRANSACTION_ID=true
###############################################################################
# OCI Streaming
###############################################################################
ENABLE_OCI_STREAMING=false
OCI_STREAM_ENDPOINT=
OCI_STREAM_OCID=
OCI_STREAM_PARTITION_KEY=agent-events
###############################################################################
# Guardrails, Judges, Supervisor
###############################################################################
ENABLE_INPUT_GUARDRAILS=true
ENABLE_OUTPUT_GUARDRAILS=true
ENABLE_JUDGES=true
ENABLE_SUPERVISOR=true
ENABLE_OUTPUT_SUPERVISOR=true
ENABLE_PARALLEL_GUARDRAILS=true
GUARDRAILS_FAIL_FAST=true
OUTPUT_SUPERVISOR_MAX_RETRIES=3
GUARDRAILS_CONFIG_PATH=./config/guardrails.yaml
JUDGES_CONFIG_PATH=./config/judges.yaml
PROMPT_POLICY_PATH=./config/prompt_policy.yaml
###############################################################################
# Gateway de canais
###############################################################################
DEFAULT_CHANNEL=web
# embedded = backend may parse simple/native channel payloads.
# external = backend only accepts GatewayRequest normalized by an external Channel Gateway.
FRAMEWORK_CHANNEL_INPUT_MODE=embedded
ENABLE_VOICE_ADAPTER=true
ENABLE_WHATSAPP_ADAPTER=true
ENABLE_TEXT_ADAPTER=true
#################################################
# ENTERPRISE ROUTING
#################################################
# Arquivo YAML com intents, keywords, políticas de estado e fallback.
ROUTING_CONFIG_PATH=./config/routing.yaml
# true = usa LLM para classificar quando keywords/estado não resolverem.
# Em produção, costuma ser útil; em desenvolvimento, false evita custo e latência.
ENABLE_LLM_ROUTER=true
# Semantic route stickiness (optional).
# Uses a lightweight LLM profile to decide only CONTINUE vs ROUTE.
# There are no regexes or deterministic language rules.
ENABLE_ROUTE_STICKINESS=true
ROUTE_STICKINESS_LLM_PROFILE=route_continuity
ROUTE_STICKINESS_CONFIDENCE_THRESHOLD=0.90
ROUTE_STICKINESS_HISTORY_TURNS=2
ROUTE_STICKINESS_MAX_TOKENS=80
HUMAN_HANDOFF_MESSAGE=Vou encaminhar seu atendimento para uma pessoa.
END_SESSION_MESSAGE=Atendimento encerrado. Obrigado pelo contato.
###############################################################################
# MCP / Tools
###############################################################################
ENABLE_MCP_TOOLS=true
MCP_SERVERS_CONFIG_PATH=./config/mcp_servers.yaml
TOOLS_CONFIG_PATH=./config/tools.yaml
MCP_TOOL_TIMEOUT_SECONDS=30
# router = EnterpriseRouter seleciona um agente; supervisor = pode acionar múltiplos agentes
ROUTING_MODE=router
# Usage/cost accounting
USAGE_REPOSITORY_PROVIDER=autonomous
IDENTITY_CONFIG_PATH=./config/identity.yaml
MCP_PARAMETER_MAPPING_PATH=./config/mcp_parameter_mapping.yaml
# -----------------------------------------------------------------------------
# ConversationSummaryMemory / compressão de contexto conversacional
# -----------------------------------------------------------------------------
ENABLE_CONVERSATION_SUMMARY_MEMORY=true
MEMORY_CONTEXT_STRATEGY=summary
MEMORY_HISTORY_LIMIT=80
MEMORY_RECENT_MESSAGES_LIMIT=8
MEMORY_SUMMARY_TRIGGER_MESSAGES=20
MEMORY_MAX_SUMMARY_CHARS=6000
MEMORY_SUMMARY_USE_LLM=true
MEMORY_INJECT_RECENT_MESSAGES=true
MEMORY_INJECT_SUMMARY=true
###############################################################################
# LONG-TERM MEMORY
###############################################################################
ENABLE_LONG_TERM_MEMORY=true
LONG_TERM_MEMORY_PROVIDER=sqlite
LONG_TERM_MEMORY_SQLITE_PATH=./data/agent_framework.db
LONG_TERM_MEMORY_TABLE=agentfw_long_term_memory
# For Autonomous/Oracle, defaults to ${ADB_TABLE_PREFIX}_LONG_TERM_MEMORY
# LONG_TERM_MEMORY_ORACLE_TABLE=AGENTFW_LONG_TERM_MEMORY
LONG_TERM_MEMORY_MAX_CONTEXT_ITEMS=20
LONG_TERM_MEMORY_MIN_CONFIDENCE=0.70
LONG_TERM_MEMORY_AUTO_EXTRACT=true
LONG_TERM_MEMORY_INJECT_CONTEXT=true
###############################################################################
# RAG provider selection (mutually exclusive at runtime)
###############################################################################
# standard = RAG original do agent_framework_oci (default, backward compatible)
# kbdb = KBDB enterprise via PKG_KB_SERVING.SEARCH_KNOWLEDGE_BASE
RAG_PROVIDER=kbdb
# Somente usados quando RAG_PROVIDER=kbdb. Se vazios, credenciais caem para ADB_*.
KBDB_DB_USER=KB_USER
KBDB_DB_PASSWORD=SuperStr0ngPa##w0rd
KBDB_DB_DSN=kbdb_public_high
KBDB_DB_WALLET_LOCATION=/mnt/d/Dropbox/ORACLE/TIM/FY27/kb/Wallet_kbdb
KBDB_DB_WALLET_PASSWORD=SuperStr0ngPa##w0rd
KBDB_SEARCH_TYPE=hybrid
KBDB_NODE_EXPANSION=true
KBDB_NODE_MAX_RELATED=8
KBDB_GRAPH_CROSS_REF=false
KBDB_MAX_CROSS_REF_HOPS=1
KBDB_DOCUMENT_TYPE=customer_safe
KBDB_METADATA_JSON=
KBDB_MIN_SCORE=0.5
KBDB_IDENTIFY_DOCUMENT=true
KBDB_STORE_QUERY=true
KBDB_IDENTIFY_TOP_N=3

View File

@@ -15,11 +15,17 @@ profiles:
temperature: 0
max_tokens: 80
timeout_seconds: 5
processing_interruption_classifier:
provider: oci_openai
model: openai.gpt-4.1-mini
temperature: 0
max_tokens: 8
timeout_seconds: 5
router:
provider: oci_openai
model: openai.gpt-4.1
temperature: 0
max_tokens: 500
max_tokens: 768
guardrail:
provider: oci_openai
model: openai.gpt-4.1

View File

@@ -15,11 +15,17 @@ profiles:
temperature: 0
max_tokens: 80
timeout_seconds: 5
processing_interruption_classifier:
provider: oci_openai
model: openai.gpt-4.1-mini
temperature: 0
max_tokens: 8
timeout_seconds: 5
router:
provider: oci_openai
model: openai.gpt-4.1
temperature: 0
max_tokens: 500
max_tokens: 768
guardrail:
provider: oci_openai
model: openai.gpt-4.1