51 lines
1.7 KiB
TOML
51 lines
1.7 KiB
TOML
# Copy to an untracked config/llm.local.toml. Array order is failover order.
|
|
[llm]
|
|
# Raw model-answer capture in the case package (never operational logs).
|
|
# Additional ceiling: 64 KiB and max_response_bytes; larger answers retain hashes/size only.
|
|
response_capture_bytes = 65536
|
|
# 0 disables targeted model patches; version 1 permits at most one per original answer.
|
|
max_field_repairs = 1
|
|
max_attempts = 10 # Full rounds, not individual HTTP calls
|
|
retry_delay_seconds = 60
|
|
blocked_retry_seconds = 3600 # Earliest explicit restart after exhaustion
|
|
max_request_bytes = 1048576
|
|
max_response_bytes = 1048576
|
|
privacy_profile = "local_only" # local_only / self_hosted / cloud_allowed
|
|
|
|
[[llm.providers]]
|
|
id = "local"
|
|
adapter = "openai_compatible"
|
|
privacy = "local"
|
|
base_url = "http://127.0.0.1:8000/v1"
|
|
model = "your-local-model"
|
|
timeout_seconds = 30
|
|
response_format = "json_object"
|
|
token_parameter = "max_tokens"
|
|
max_output_tokens = 4096
|
|
# Optional; omit for provider defaults. Supported values depend on the model.
|
|
# reasoning_effort = "medium"
|
|
# Optional override for entity resolution planning and assessment only:
|
|
# entity_resolution_reasoning_effort = "low"
|
|
# Optional override only for settling pending work before early diagnosis:
|
|
# investigation_review_reasoning_effort = "low"
|
|
|
|
[[llm.providers]]
|
|
id = "own-server"
|
|
adapter = "openai_compatible"
|
|
privacy = "self_hosted"
|
|
base_url = "https://your-server.example/v1"
|
|
model = "your-server-model"
|
|
api_key_env = "VBA_OWN_SERVER_KEY"
|
|
enabled = false
|
|
response_format = "json_object"
|
|
|
|
[[llm.providers]]
|
|
id = "cloud"
|
|
adapter = "openai_compatible"
|
|
privacy = "cloud"
|
|
base_url = "https://api.openai.com/v1"
|
|
model = "your-cloud-model"
|
|
api_key_env = "OPENAI_API_KEY"
|
|
enabled = false
|
|
response_format = "json_schema"
|