Limits & defaults
Every default and cap in one table: manifest field defaults, operator env-var defaults, hardcoded model defaults, and behavioural constants.
Last updated
Was this helpful?
Every default and cap in one table: manifest field defaults, operator env-var defaults, hardcoded model defaults, and behavioural constants.
Context — Every default value and cap in one place, introspected from runtime version
0.8.14(manifest schema 6.1.5). Field semantics live on the concept pages; this is the lookup table.
agent_config.runtime.log_level
"INFO"
agent_config.runtime.max_engine_iterations
5
agent_config.runtime.policy_batch_size
5
agent_config.llms.default
"interactive/agent"
agent_config.llms.fallback
[]
agent_config.database.port
5432
agent_config.database.user
"postgres"
agent_config.database.dbname
"postgres"
agent_config.database.sslmode
"require"
agent_config.search (pgvector).type
"pgvector"
agent_config.search (pgvector).user
"postgres"
agent_config.search (pgvector).dbname
"postgres"
agent_config.search (pgvector).sslmode
"require"
agent_config.search (pgvector).content_key
"content"
agent_config.search (pgvector).metadata_filter
{}
agent_config.search (pgvector).top_k
5
agent_config.search (external).type
"external"
agent_config.search (external).top_k
5
agent_config.search (external).max_messages
20
agent_config.search (external).timeout_seconds
5.0
agent_config.traces.deployment_environment
"production"
agent_config.traces.backend.api_key_scheme
"bearer"
agent_config.webhooks[].algorithm
"sha256"
agent_config.webhooks[].prefix
""
ROUTER_MAX_TOKENS
100000
STREAMING
False
AUTONOMOUS_DEFAULT_TIMEOUT_SECONDS
120
AUTONOMOUS_MAX_TIMEOUT_SECONDS
600
AUTONOMOUS_CALLBACK_MAX_RETRIES
5
SHUTDOWN_DRAIN_TIMEOUT_SECONDS
120
STORE_GC_DELAY_SECONDS
120
EVAL_NODE_PARALLELISM
50
LLM_PROVIDER_ORDER
unset
Chat (llms.default absent)
interactive/agent
Evaluation (llms.evaluation absent)
interactive/google/gemini-3-flash-preview
Evaluation fallback (llms.evaluation_fallback absent)
interactive/google/gemini-3.1-pro-preview
HTTP port
8080
Container listen port.
Evaluation retry attempts
3 + 3
Per internal decision call: 3 on the primary evaluation model, then 3 on the fallback. See Models.
Autonomous timeout default / cap
120s / 600s
Routine timeout_seconds falls back to the default and is clamped to the cap.
Callback delivery attempts
5
Autonomous callbacks / event webhooks, with backoff.
Knowledge-base query timeout
30s
Internal cap on pgvector searches (retrieval soft-fails past it).
Startup failure exit window
10s
Boot errors exit the process non-zero within this window.
Last updated
Was this helpful?
Was this helpful?

