# ============================================================================
# Cortiq Gateway — example configuration
# Copy to gateway.toml and edit for your own model pool.
# Do NOT store secrets here — provide them via *_env (environment variables)
# or set them from the admin console (stored in config/secrets.toml).
# ============================================================================

listen = "0.0.0.0:9000"

# --- connection to cortiq-router (decides task type / complexity) -----------
# Hosted allaigate router: url = "https://138.226.222.209", verify_tls = false
# (cert is bound to an IP), taxonomy_id = "data-assistant", a cortiq_… key in
# CORTIQ_ROUTER_KEY.
# NOTE: on hard prompts the router escalates to an oracle LLM (~10 s) — for the
# hosted router set timeout_ms = 12000+, otherwise the gateway degrades to default.
[router]
url         = "http://localhost:8080"
api_key_env = "CORTIQ_ROUTER_KEY"   # name of the env var holding the router key
timeout_ms  = 800                    # timeout for the /v1/route call (12000+ for oracle)
taxonomy_id = "general.task-type"    # for allaigate: "data-assistant"
verify_tls  = true                   # false if the router uses an IP / self-signed cert

# --- how to pick the text to classify from the conversation -----------------
[route]
text_strategy = "last_user"   # last_user | last_user_plus_system | concat_all
max_chars     = 4000
cache_ttl     = "60s"
profile       = "balanced"    # cost-saver | balanced | quality-first

# ============================================================================
# Model pool: mix cheap local models and expensive cloud ones.
# provider = "openai" covers OpenAI, OpenRouter, Together, Groq, and also
# LOCAL servers vLLM / llama.cpp / LM Studio / Ollama (/v1).
# ============================================================================

[[models]]
id        = "local-qwen"
provider  = "openai"
base_url  = "http://localhost:8000/v1"
model     = "qwen2.5-7b-instruct"
cost_tier = "cheap"
price_in  = 0.0
price_out = 0.0
caps      = ["tools"]

[[models]]
id          = "gpt-4o-mini"
provider    = "openai"
base_url    = "https://api.openai.com/v1"
model       = "gpt-4o-mini"
api_key_env = "OPENAI_API_KEY"
cost_tier   = "mid"
price_in    = 0.15
price_out   = 0.60
caps        = ["tools", "vision"]

[[models]]
id          = "claude-opus"
provider    = "anthropic"
base_url    = "https://api.anthropic.com"
model       = "claude-opus-4"
api_key_env = "ANTHROPIC_API_KEY"
cost_tier   = "expensive"
price_in    = 15.0
price_out   = 75.0
caps        = ["tools", "vision"]

# --- embedding model (for /v1/embeddings in provider mode) ------------------
[[models]]
id          = "local-embed"
provider    = "openai"
base_url    = "http://localhost:8000/v1"
model       = "nomic-embed-text"
cost_tier   = "cheap"
kind        = "embedding"

# ============================================================================
# Routing table: complexity tier → ordered pool (priority = fallback chain)
# ============================================================================
[routing]
low     = ["local-qwen"]
medium  = ["gpt-4o-mini", "local-qwen"]
high    = ["claude-opus", "gpt-4o-mini"]
default = "gpt-4o-mini"        # used when the router is unreachable

[routing.policy]
mode = "fixed_table"           # fixed_table | cost_aware
# for cost_aware:
# min_class = { low = "cheap", medium = "mid", high = "expensive" }
# max_cost_usd_per_request = 0.50

# --- resilience -------------------------------------------------------------
[breaker]
threshold = 5
cooldown  = "30s"

# ============================================================================
# Inbound protocols — enable only what you need (toggles apply live in the UI)
# ============================================================================
[protocols]
openai_chat        = true
openai_completions = true
openai_embeddings  = true
openai_models      = true
anthropic_messages = false
mcp                = false
native_passthrough = true

# --- response routing metadata ----------------------------------------------
[cortiq]
echo = true     # add a "cortiq" field to the response body (X-Cortiq-* headers are always sent)

# ============================================================================
# Authentication: virtual gateway keys (agents get these, not provider keys).
# If this section is empty, the gateway runs in open mode (local development).
# ============================================================================
[[api_keys]]
key          = "sk-gw-team-a"
account      = "team-a"
rate_per_min = 600
# allow_models = ["cortiq-auto", "local-qwen"]   # restrict available models (optional)

# --- idempotency and logging ------------------------------------------------
[idempotency]
ttl = "10m"

[log]
bodies = false   # do NOT log message bodies (privacy) — default
level  = "info"

[telemetry]
metrics = true   # GET /metrics (Prometheus)
otlp_endpoint_env = "OTEL_EXPORTER_OTLP_ENDPOINT"   # optional

# ============================================================================
# Admin web console — embedded in the binary, served at /admin
# ============================================================================
[admin]
enabled   = true
# Name of the env var holding the admin token. If unset (or empty), a token is
# generated at startup and printed to the log (see also the --admin-token flag).
token_env = "CORTIQ_ADMIN_TOKEN"
# listen  = "127.0.0.1:9001"   # optional: separate bind for admin (default: main listen)

# ============================================================================
# Request statistics (dashboard + /metrics). Kept in memory + appended to JSONL.
# ============================================================================
[stats]
enabled   = true
file      = "config/stats.jsonl"   # empty = in-memory only
ring_size = 500                     # how many recent requests to keep in the feed
retention = "7d"                    # aggregate/series depth (replayed on startup)