171 lines
11 KiB
YAML
171 lines
11 KiB
YAML
server:
|
|
host: 127.0.0.1
|
|
port: 9000
|
|
|
|
# ── Global timezone ─────────────────────────────────────────────────────────────
|
|
# IANA timezone name applied globally to:
|
|
# - cron expression evaluation (next_run_at computation)
|
|
# - the date/time string injected into the LLM context each turn
|
|
# When omitted, the server's local system timezone is used.
|
|
# Examples: Europe/Rome, Europe/London, America/New_York, Asia/Tokyo
|
|
#
|
|
# timezone: Europe/Rome
|
|
# ────────────────────────────────────────────────────────────────────────────────
|
|
|
|
web:
|
|
static_dir: ./web
|
|
|
|
# ── Connector marketplace ──────────────────────────────────────────────────────
|
|
# The feed of vetted connectors the admin browses under Connectors → Marketplace.
|
|
# It is *consultative*: the feed proposes, the admin installs into the local
|
|
# catalog, and only then can a connector be enabled globally or activated by a
|
|
# user. The trust anchor stays on this box.
|
|
#
|
|
# Point it at a self-hosted mirror or a local copy to run fully offline — the feed
|
|
# is plain static files (`connectors.json` + `<folder>/connector.json`).
|
|
marketplace:
|
|
url: https://connectors.skaldagent.net
|
|
|
|
# The database lives at ./database/system.db — fixed, not configurable.
|
|
|
|
# ── LLM clients ────────────────────────────────────────────────────────────────
|
|
# LLM clients (providers, models, API keys, strength) are configured
|
|
# via the web app and stored in the database — not in this file.
|
|
# ───────────────────────────────────────────────────────────────────────────────
|
|
llm:
|
|
# ── History window (DISABLED by default) ────────────────────────────────────
|
|
# Hard cap on the number of history messages sent to the LLM, applied as a
|
|
# sliding tail window: past the cap, the oldest messages are dropped.
|
|
#
|
|
# Off by default, for two reasons:
|
|
# 1. Cache. Once history exceeds the cap, every turn shifts the window's
|
|
# start, so the prompt prefix changes on every single request and the
|
|
# provider's prompt cache (Anthropic breakpoints, OpenAI automatic prefix
|
|
# caching) misses every time. Append-only history keeps the prefix stable
|
|
# for the whole conversation.
|
|
# 2. Memory. The window drops messages with no summary standing in for them,
|
|
# so the assistant silently forgets. `/compact` replaces them with a
|
|
# summary instead.
|
|
#
|
|
# With this off and automatic compaction off (the shipped default), the context
|
|
# grows until the model's own limit — use `/compact` to summarise it.
|
|
# Ignored when automatic compaction is enabled (see `compaction` below).
|
|
#
|
|
# max_history_messages: 30
|
|
# ───────────────────────────────────────────────────────────────────────────
|
|
max_tool_rounds: 100
|
|
# Max synchronous sub-agents dispatched concurrently when the LLM emits a
|
|
# homogeneous batch (≥2) of sub-agent calls (execute_task mode=sync /
|
|
# execute_subtask) in a single response. Bounds fan-out to avoid provider
|
|
# rate-limit storms. Omit for the default (4); set to 1 to force sequential.
|
|
max_parallel_subagents: 4
|
|
# Injects "Current date and time: Sunday 2026-08-02 17:00 +02:00 (Europe/Rome)"
|
|
# as the last system message of each request. The time is always truncated to
|
|
# the hour and the block tells the model so, pointing it at `date` when it
|
|
# needs the exact minute — there is no rounding setting.
|
|
datetime:
|
|
enabled: true
|
|
|
|
# ── Tool result size limit ──────────────────────────────────────────────────
|
|
# When set, tool results from *previous* turns that exceed this character
|
|
# count are replaced (at context-build time) with a short placeholder:
|
|
# "[Tool response hidden: N chars. Call the tool again if you need it.]"
|
|
# The original result is always preserved in the database and shown in the
|
|
# frontend; only what the LLM receives in subsequent turns is affected.
|
|
# The current turn always sees full results regardless of this limit.
|
|
# Omit or comment out to disable (no limit).
|
|
max_tool_result_chars: 10000
|
|
# ───────────────────────────────────────────────────────────────────────────
|
|
|
|
# ── Context compaction (AUTOMATIC pass disabled by default) ─────────────────
|
|
# Compaction summarises old history into a single block, persisted to the DB
|
|
# and injected at the start of subsequent turns in place of the messages it
|
|
# covers, keeping the last `keep_recent` raw messages for immediate context.
|
|
#
|
|
# The `/compact` command works ALWAYS and needs nothing here — this whole
|
|
# section is optional and only tunes it.
|
|
#
|
|
# `threshold_tokens` is what arms the AUTOMATIC pass: set it, and history is
|
|
# compacted on its own once the previous turn exceeded that many input tokens.
|
|
# It is COMMENTED OUT by default: every compaction rewrites the prompt prefix
|
|
# and so costs a prompt-cache miss, and doing it unprompted trades away context
|
|
# the user may still need. Compact manually with `/compact` for now.
|
|
# (Future: an automatic pass triggered by the model's own context window rather
|
|
# than by a hand-tuned token count.)
|
|
#
|
|
# `strength` controls which LLM is picked for summary generation via the AUTO
|
|
# selector (same strength levels used for agent assignment). Compaction is a
|
|
# simple writing task — `low` or `average` is usually sufficient.
|
|
# Omit `strength` to use whatever AUTO picks.
|
|
# NOTE: the Settings page has an instance-wide "Compaction model" picker
|
|
# (registry config key `compaction_model`) — when set, it wins over this
|
|
# `strength` fallback and needs no restart.
|
|
#
|
|
# When the LLM provider does not report token usage (e.g. some LM Studio
|
|
# setups), a rough estimate (total chars / 4) is used as a fallback.
|
|
#
|
|
# compaction:
|
|
# threshold_tokens: 30000 # arms the automatic pass, above this many input tokens
|
|
# keep_recent: 6 # raw messages kept outside the summary
|
|
# strength: low # LLM strength for summary generation
|
|
# ───────────────────────────────────────────────────────────────────────────
|
|
|
|
# ── Date/time injection ─────────────────────────────────────────────────────
|
|
# Configured above as `datetime`. The only setting is `enabled`.
|
|
# The injected time is always truncated to the hour: not for the prompt cache
|
|
# (the block is the LAST system message, so the cached prefix never changes
|
|
# whatever the timestamp says) but because a second-precision stamp reads as
|
|
# exact to the model long after it stopped being true. The block states the
|
|
# granularity and tells the agent to run `date` when it needs the minute.
|
|
# enabled: true # set to false to disable injection entirely
|
|
# ───────────────────────────────────────────────────────────────────────────
|
|
|
|
# ── LLM request/response log ────────────────────────────────────────────────
|
|
# Logs every chat_with_tools call to the `llm_requests` table.
|
|
# Captures the full HTTP request body, response body, headers (api-key redacted),
|
|
# token counts, and round-trip duration.
|
|
#
|
|
# WARNING: disabling `enabled` also disables the home-page LLM statistics.
|
|
#
|
|
# What to save (all default to true):
|
|
# request_payload_save — full request JSON (can be hundreds of KB per call)
|
|
# response_payload_save — full response JSON
|
|
# request_header_save — HTTP request headers (api-key always redacted)
|
|
# response_header_save — HTTP response headers
|
|
#
|
|
# Cleanup policy (all optional — omit to keep data forever):
|
|
# cleanup_request_payload_after — set request_json = '' after N days
|
|
# cleanup_response_payload_after — set response_json = NULL after N days
|
|
# cleanup_headers_after — null out both header columns after N days
|
|
# cleanup_rows_after — physically delete rows after N days
|
|
#
|
|
# The cleaner runs 1 minute after startup, then every 12 hours.
|
|
#
|
|
requests_log:
|
|
enabled: true
|
|
request_payload_save: false
|
|
response_payload_save: true
|
|
request_header_save: true
|
|
response_header_save: true
|
|
cleanup_request_payload_after: 7
|
|
cleanup_response_payload_after: 14
|
|
cleanup_headers_after: 30
|
|
cleanup_rows_after: 90
|
|
# ───────────────────────────────────────────────────────────────────────────
|
|
|
|
# ── Event triage (background event processor) ──────────────────────────────────
|
|
# Runs periodically to process pending MCP events (email, calendar, WhatsApp) and
|
|
# decide whether to surface a notification to the user.
|
|
#
|
|
# NOTE: top-level, NOT under `llm:` — nesting it there parses fine and is then
|
|
# silently ignored.
|
|
#
|
|
# interval_secs — how often it runs (default: 900 = 15 minutes)
|
|
# batch_size — max events processed per pass (default: 50)
|
|
#
|
|
# event_triage:
|
|
# interval_secs: 900
|
|
# batch_size: 50
|
|
# ───────────────────────────────────────────────────────────────────────────────
|
|
|