# metsuke agent configuration. Copy to /etc/metsuke/config.toml and set the
# three required values; every commented line shows a default (pinned to the
# code by a test in crates/metsuke/tests/config.rs).

# Required: your pool id, bech32.
pool_id = "pool1CHANGEME"

# Required: the node's loopback PrometheusSimple endpoint.
metrics_url = "http://127.0.0.1:12798/metrics"

# Required: the metsuke-server submission endpoint.
upload_url = "https://metsuke-leios.play.dev.cardano.org/v1/submit"

# What to call this Agent on every line it ships, so a pool reporting from more
# than one Agent can tell them apart. Defaults to this Agent's hostname, folded
# to lowercase a-z0-9 in dash-separated runs; a value set here is folded the
# same way.
# agent_id = "edge-1"

# Path to the signing key, a cardano-cli TextEnvelope: the cold key pool_id
# above hashes from, or the pool's Leios key. A cold key that does not hash to
# pool_id refuses to start; a Leios key hashes to nothing, so nothing is
# checked here and the server's roster settles which pool it speaks for. The
# --signing-key flag overrides this: with systemd, leave this unset and pass
# the key as a credential. See https://metsuke-leios.play.dev.cardano.org/files/metsuke.service.
# signing_key = "/etc/metsuke/bls.skey"

# Cadences: scraping and uploading are independent.
# scrape_interval_secs = 300
# upload_interval_secs = 3600

# SNTP clock-offset probe: servers tried in order, per-server timeout.
# sntp_servers = ["time.cloudflare.com:123"]
# sntp_timeout_secs = 5

# SQLite spool: scrapes wait here until the server acks them. Oldest bytes
# beyond spool_max_bytes are dropped. spool_busy_timeout_secs is how long one
# write waits for the other connection, which exists only with [log] below.
# spool_path = "/var/lib/metsuke/spool.sqlite"
# spool_max_bytes = 33554432
# spool_busy_timeout_secs = 5

# Scrape limits.
# scrape_timeout_secs = 5
# scrape_max_body_bytes = 4194304

# Upload limits: request deadline, the spread that places this agent within
# the upload interval, and the clamp on the rejection backoff. The first
# accepted submission picks a point in upload_jitter_max_secs and every upload
# after it keeps that point, so agents installed together do not all upload in
# the same second while yours still lands on a cadence you can watch for.
# It is a ceiling: a spread wider than the interval places nobody better than
# one exactly as wide, so a shorter upload_interval_secs bounds it instead.
#
# upload_batch_max_bytes counts the header frame and the payload before
# compression; the server's own ceiling is [ingest].max_body_bytes on the
# compressed bytes (contrib/server.example.toml), and nothing checks the two
# against each other. Raising this past what your server allows earns a 413 on
# every attempt, and the same rows reseal to the same size, so they stay
# spooled until the cap drops them. Why the two count a line the same way:
# docs/adr/0010.
#
# upload_max_submissions is how many submissions one upload tick may send. A
# node emits more trace lines between ticks than one submission carries, so at
# one per tick the remainder is spooled until the cap drops it. Raise it if
# your node still gains spool between uploads; the ceiling on it is whatever
# the server allows per pool per window.
# upload_timeout_secs = 60
# upload_jitter_max_secs = 300
# upload_backoff_max_secs = 86400
# upload_batch_max_bytes = 4194304
# upload_max_submissions = 16

# zstd level for the upload body (0 = zstd's default).
# compression_level = 0

# Trace-line collection, off unless this whole section is present. It reads the
# node's journal, which the unit has to be allowed to do. The instructions
# page says which two directives change, and the NixOS module makes both when
# this section is set (docs/adr/0010). The node also has to be configured to
# write these traces at all: that is on the server's details page too.
#
# source picks the stream and is never guessed. With "journald", journal_unit
# and journalctl_path have no default: name your node's unit, and give
# journalctl's absolute path, because this unit's PATH is not one to resolve a
# program on.
#
# With source = "pipe" the node runs as `cardano-node run | metsuke`: metsuke
# reads the node's stdout, writes every line through to its own stdout
# unchanged, and never makes the node wait. A line it has no room to queue is
# dropped and counted, and pipe_queue_capacity is how many it may hold. It
# reads no journal, so none of the journal keys may be set, and the NixOS module
# does not render this source: the unit it writes has no node upstream of it.
#
# namespaces are prefixes and are the selection rule, less whatever
# exclude_namespaces names; namespace_roots is this host's ceiling on them, and
# a namespaces entry outside it is refused at startup. All three match on
# segment boundaries, so an entry names a namespace the node emits or an
# ancestor of one, never a fragment of a name. Why severity is not a further
# rule: docs/adr/0010.
#
# An exclusion is for a namespace the node puts under a prefix you otherwise
# want whole. Narrowing namespaces instead would give up every namespace added
# under that prefix later. Exclusions are not checked against namespace_roots,
# because they only ever ship less.
#
# start_grace_secs is how long a just-started journalctl has to stay running
# before the agent accepts it as following, so a unit that may not read the
# journal fails the start rather than collecting nothing (docs/adr/0010).
# [log]
#
# Which stream the lines come from, "journald" or "pipe". Never guessed.
# source = "journald"
#
# Your node's unit. No default: which service the node runs as is not
# something this agent can guess.
# journal_unit = "cardano-node"
#
# journalctl's absolute path. No default either, because a hardened unit's
# PATH is not one to resolve a program on.
# journalctl_path = "/usr/bin/journalctl"
#
# The ceiling on what may be selected, and the selection itself. Both are
# prefixes matched on segment boundaries.
# namespace_roots = ["Consensus", "ChainDB", "Forge"]
# namespaces = ["Consensus.LeiosKernel", "Consensus.LeiosPeer", "ChainDB.AddBlockEvent.AddedToCurrentChain", "Forge.Loop.AdoptedBlock"]
#
# Namespaces to drop back out of that selection. Empty by default.
# exclude_namespaces = []
#
# The trace-line spool's cap, and how long a journalctl that died waits before
# it is started again.
# log_max_bytes = 268435456
# respawn_backoff_secs = 30
#
# The most of one line the agent keeps. A longer one is read whole, so the
# stream stays in sync, written through unchanged in pipe mode, and then
# dropped and counted. The default is 64 KiB, more than ten times the longest
# line a node has been seen to write, and it is here so that what the node
# writes cannot decide how much the agent allocates. In pipe mode the product
# with pipe_queue_capacity is what a queue full of lines at this length costs.
# max_line_bytes = 65536
#
# How long a just-started journalctl has to stay running before the agent
# accepts it as following.
# start_grace_secs = 1