# Lakehouse-Go config — G0 dev defaults. Overrides via env are a
# G1+ concern; for G0 edit this file and restart the affected service.

# G0 dev ports — shifted to 3110+ so the Go services run alongside
# the live Rust lakehouse on 3100/3201-3204 without colliding. G5
# (demo cutover) flips gateway back to 3100 when Rust retires.
[gateway]
bind = "127.0.0.1:3110"
storaged_url = "http://127.0.0.1:3211"
catalogd_url = "http://127.0.0.1:3212"
ingestd_url  = "http://127.0.0.1:3213"
queryd_url   = "http://127.0.0.1:3214"
vectord_url  = "http://127.0.0.1:3215"
embedd_url   = "http://127.0.0.1:3216"
pathwayd_url = "http://127.0.0.1:3217"
matrixd_url  = "http://127.0.0.1:3218"
observerd_url = "http://127.0.0.1:3219"

[storaged]
bind = "127.0.0.1:3211"

[catalogd]
bind = "127.0.0.1:3212"
storaged_url = "http://127.0.0.1:3211"

[ingestd]
bind = "127.0.0.1:3213"
storaged_url = "http://127.0.0.1:3211"
catalogd_url = "http://127.0.0.1:3212"
# CSV uploads are ~4-6× the resulting Parquet. 256 MiB cap keeps the in-memory
# parse + Arrow + Parquet output footprint bounded. Bump for known large
# datasets (e.g. workers_500k → 344 MiB CSV needs 512 MiB).
max_ingest_bytes = 268435456

[vectord]
bind = "127.0.0.1:3215"
# Optional — set to empty string to disable persistence (dev/test).
storaged_url = "http://127.0.0.1:3211"

[embedd]
bind = "127.0.0.1:3216"
# G2: Ollama local. G3+ may swap in OpenAI/Voyage by changing
# this URL + the wire format inside the provider.
provider_url  = "http://localhost:11434"
default_model = "nomic-embed-text"

[queryd]
bind = "127.0.0.1:3214"
catalogd_url = "http://127.0.0.1:3212"
secrets_path = "/etc/lakehouse/secrets-go.toml"
refresh_every = "30s"

[pathwayd]
bind = "127.0.0.1:3217"
# Empty = in-memory only (dev/test). Production sets a path under
# /var/lib/lakehouse/pathway/state.jsonl so traces survive restart.
persist_path = ""

[matrixd]
bind = "127.0.0.1:3218"
# matrixd calls embedd (query-text → vector) and vectord (per-corpus
# search) directly. Localhost defaults; in distributed deployments
# these point at the gateway's upstream addresses.
embedd_url  = "http://127.0.0.1:3216"
vectord_url = "http://127.0.0.1:3215"

[observerd]
bind = "127.0.0.1:3219"
# Empty = in-memory only (dev/test). Production sets a path under
# /var/lib/lakehouse/observer/ops.jsonl so ops survive restart.
persist_path = ""

[s3]
endpoint        = "http://localhost:9000"
region          = "us-east-1"
bucket          = "lakehouse-go-primary"   # G0 dedicated bucket so Rust + Go coexist
access_key_id   = ""                       # populated by SecretsProvider from /etc/lakehouse/secrets-go.toml
secret_access_key = ""                     # ditto
use_path_style  = true

[log]
level = "info"