mirror of
https://github.com/katanemo/plano.git
synced 2026-04-25 00:36:34 +02:00
897fda2deb
* fix(routing): auto-migrate v0.3.0 inline routing_preferences to v0.4.0 top-level Lift inline routing_preferences under each model_provider into the top-level routing_preferences list with merged models[] and bump version to v0.4.0, with a deprecation warning. Existing v0.3.0 demo configs (Claude Code, Codex, preference_based_routing, etc.) keep working unchanged. Schema flags the inline shape as deprecated but still accepts it. Docs and skills updated to canonical top-level multi-model form. * test(common): bump reference config assertion to v0.4.0 The rendered reference config was bumped to v0.4.0 when its inline routing_preferences were lifted to the top level; align the configuration deserialization test with that change. * fix(config_generator): bump version to v0.4.0 up front in migration Move the v0.3.0 -> v0.4.0 version bump to the top of migrate_inline_routing_preferences so it runs unconditionally, including for configs that already declare top-level routing_preferences at v0.3.0. Previously the bump only fired when inline migration produced entries, leaving top-level v0.3.0 configs rejected by brightstaff's v0.4.0 gate. Tests updated to cover the new behavior and to confirm we never downgrade newer versions. * fix(config_generator): gate routing_preferences migration on version < v0.4.0 Short-circuit the migration when the config already declares v0.4.0 or newer. Anything at v0.4.0+ is assumed to be on the canonical top-level shape and is passed through untouched, including stray inline preferences (which are the author's bug to fix). Only v0.3.0 and older configs are rewritten and bumped.
623 lines
16 KiB
YAML
623 lines
16 KiB
YAML
$schema: 'http://json-schema.org/draft-07/schema#'
|
|
type: object
|
|
properties:
|
|
version:
|
|
type: string
|
|
enum:
|
|
- v0.1
|
|
- v0.1.0
|
|
- 0.1-beta
|
|
- 0.2.0
|
|
- v0.3.0
|
|
- v0.4.0
|
|
|
|
agents:
|
|
type: array
|
|
items:
|
|
type: object
|
|
properties:
|
|
id:
|
|
type: string
|
|
url:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
- id
|
|
- url
|
|
filters:
|
|
type: array
|
|
items:
|
|
type: object
|
|
properties:
|
|
id:
|
|
type: string
|
|
url:
|
|
type: string
|
|
type:
|
|
type: string
|
|
enum:
|
|
- mcp
|
|
- http
|
|
transport:
|
|
type: string
|
|
enum:
|
|
- streamable-http
|
|
tool:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
- id
|
|
- url
|
|
listeners:
|
|
oneOf:
|
|
- type: array
|
|
additionalProperties: false
|
|
items:
|
|
type: object
|
|
properties:
|
|
name:
|
|
type: string
|
|
port:
|
|
type: integer
|
|
address:
|
|
type: string
|
|
timeout:
|
|
type: string
|
|
router:
|
|
type: string
|
|
enum:
|
|
- plano_orchestrator_v1
|
|
max_retries:
|
|
type: integer
|
|
type:
|
|
type: string
|
|
enum:
|
|
- model
|
|
- prompt
|
|
- agent
|
|
agents:
|
|
type: array
|
|
items:
|
|
type: object
|
|
properties:
|
|
id:
|
|
type: string
|
|
description:
|
|
type: string
|
|
default:
|
|
type: boolean
|
|
input_filters:
|
|
type: array
|
|
items:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
- id
|
|
- description
|
|
input_filters:
|
|
type: array
|
|
items:
|
|
type: string
|
|
output_filters:
|
|
type: array
|
|
items:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
- type
|
|
- name
|
|
- type: object # deprecated legacy format, use list format instead
|
|
additionalProperties: false
|
|
properties:
|
|
ingress_traffic:
|
|
type: object
|
|
properties:
|
|
address:
|
|
type: string
|
|
port:
|
|
type: integer
|
|
message_format:
|
|
type: string
|
|
enum:
|
|
- openai
|
|
timeout:
|
|
type: string
|
|
additionalProperties: false
|
|
egress_traffic:
|
|
type: object
|
|
properties:
|
|
address:
|
|
type: string
|
|
port:
|
|
type: integer
|
|
message_format:
|
|
type: string
|
|
enum:
|
|
- openai
|
|
timeout:
|
|
type: string
|
|
additionalProperties: false
|
|
endpoints:
|
|
type: object
|
|
patternProperties:
|
|
'^[a-zA-Z][a-zA-Z0-9_]*$':
|
|
type: object
|
|
properties:
|
|
endpoint:
|
|
type: string
|
|
pattern: '^.*$'
|
|
connect_timeout:
|
|
type: string
|
|
protocol:
|
|
type: string
|
|
enum:
|
|
- http
|
|
- https
|
|
http_host:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
- endpoint
|
|
|
|
model_providers:
|
|
type: array
|
|
items:
|
|
type: object
|
|
properties:
|
|
name:
|
|
type: string
|
|
access_key:
|
|
type: string
|
|
model:
|
|
type: string
|
|
default:
|
|
type: boolean
|
|
base_url:
|
|
type: string
|
|
passthrough_auth:
|
|
type: boolean
|
|
description: "When true, forwards the client's Authorization header to upstream instead of using the configured access_key. Useful for routing to services like LiteLLM that validate their own virtual keys."
|
|
http_host:
|
|
type: string
|
|
provider_interface:
|
|
type: string
|
|
enum:
|
|
- plano
|
|
- claude
|
|
- deepseek
|
|
- groq
|
|
- mistral
|
|
- openai
|
|
- xiaomi
|
|
- gemini
|
|
- chatgpt
|
|
- digitalocean
|
|
- vercel
|
|
- openrouter
|
|
headers:
|
|
type: object
|
|
additionalProperties:
|
|
type: string
|
|
description: "Additional headers to send with upstream requests (e.g., ChatGPT-Account-Id, originator)."
|
|
routing_preferences:
|
|
type: array
|
|
description: "[DEPRECATED] Inline routing_preferences under a model_provider are auto-migrated to the top-level routing_preferences list by the config generator. New configs should declare routing_preferences at the top level with an explicit models: [...] list. See docs/routing-api.md."
|
|
items:
|
|
type: object
|
|
properties:
|
|
name:
|
|
type: string
|
|
description:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
- name
|
|
- description
|
|
additionalProperties: false
|
|
required:
|
|
- model
|
|
|
|
llm_providers: # deprecated for legacy support, use model_providers instead
|
|
type: array
|
|
items:
|
|
type: object
|
|
properties:
|
|
name:
|
|
type: string
|
|
access_key:
|
|
type: string
|
|
model:
|
|
type: string
|
|
default:
|
|
type: boolean
|
|
base_url:
|
|
type: string
|
|
passthrough_auth:
|
|
type: boolean
|
|
description: "When true, forwards the client's Authorization header to upstream instead of using the configured access_key. Useful for routing to services like LiteLLM that validate their own virtual keys."
|
|
http_host:
|
|
type: string
|
|
provider_interface:
|
|
type: string
|
|
enum:
|
|
- plano
|
|
- claude
|
|
- deepseek
|
|
- groq
|
|
- mistral
|
|
- openai
|
|
- xiaomi
|
|
- gemini
|
|
- chatgpt
|
|
- digitalocean
|
|
- vercel
|
|
- openrouter
|
|
headers:
|
|
type: object
|
|
additionalProperties:
|
|
type: string
|
|
description: "Additional headers to send with upstream requests (e.g., ChatGPT-Account-Id, originator)."
|
|
routing_preferences:
|
|
type: array
|
|
description: "[DEPRECATED] Inline routing_preferences under an llm_provider are auto-migrated to the top-level routing_preferences list by the config generator. New configs should declare routing_preferences at the top level with an explicit models: [...] list. See docs/routing-api.md."
|
|
items:
|
|
type: object
|
|
properties:
|
|
name:
|
|
type: string
|
|
description:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
- name
|
|
- description
|
|
additionalProperties: false
|
|
required:
|
|
- model
|
|
|
|
model_aliases:
|
|
type: object
|
|
patternProperties:
|
|
'^.*$':
|
|
type: object
|
|
properties:
|
|
target:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
- target
|
|
|
|
overrides:
|
|
type: object
|
|
properties:
|
|
prompt_target_intent_matching_threshold:
|
|
type: number
|
|
optimize_context_window:
|
|
type: boolean
|
|
use_agent_orchestrator:
|
|
type: boolean
|
|
disable_signals:
|
|
type: boolean
|
|
description: "Disable agentic signal analysis (frustration, repetition, escalation, etc.) on LLM responses to save CPU. Default false."
|
|
upstream_connect_timeout:
|
|
type: string
|
|
description: "Connect timeout for upstream provider clusters (e.g., '5s', '10s'). Default is '5s'."
|
|
upstream_tls_ca_path:
|
|
type: string
|
|
description: "Path to the trusted CA bundle for upstream TLS verification. Default is '/etc/ssl/certs/ca-certificates.crt'."
|
|
llm_routing_model:
|
|
type: string
|
|
description: "Model name for the LLM router (e.g., 'Plano-Orchestrator'). Must match a model in model_providers."
|
|
agent_orchestration_model:
|
|
type: string
|
|
description: "Model name for the agent orchestrator (e.g., 'Plano-Orchestrator'). Must match a model in model_providers."
|
|
orchestrator_model_context_length:
|
|
type: integer
|
|
description: "Maximum token length for the orchestrator/routing model context window. Default is 8192."
|
|
system_prompt:
|
|
type: string
|
|
prompt_targets:
|
|
type: array
|
|
items:
|
|
type: object
|
|
properties:
|
|
name:
|
|
type: string
|
|
default:
|
|
type: boolean
|
|
description:
|
|
type: string
|
|
auto_llm_dispatch_on_response:
|
|
type: boolean
|
|
parameters:
|
|
type: array
|
|
items:
|
|
type: object
|
|
properties:
|
|
name:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
type: boolean
|
|
default:
|
|
anyOf:
|
|
- type: string
|
|
- type: integer
|
|
- type: boolean
|
|
description:
|
|
type: string
|
|
type:
|
|
type: string
|
|
enum:
|
|
type: array
|
|
items:
|
|
anyOf:
|
|
- type: string
|
|
- type: integer
|
|
- type: boolean
|
|
in_path:
|
|
type: boolean
|
|
format:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
- name
|
|
- description
|
|
- type
|
|
endpoint:
|
|
type: object
|
|
properties:
|
|
name:
|
|
type: string
|
|
path:
|
|
type: string
|
|
http_method:
|
|
type: string
|
|
enum:
|
|
- GET
|
|
- POST
|
|
http_headers:
|
|
type: object
|
|
additionalProperties:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
- name
|
|
- path
|
|
system_prompt:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
- name
|
|
- description
|
|
ratelimits:
|
|
type: array
|
|
items:
|
|
type: object
|
|
properties:
|
|
model:
|
|
type: string
|
|
selector:
|
|
type: object
|
|
properties:
|
|
key:
|
|
type: string
|
|
value:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
- key
|
|
- value
|
|
limit:
|
|
type: object
|
|
properties:
|
|
tokens:
|
|
type: integer
|
|
unit:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
- tokens
|
|
- unit
|
|
additionalProperties: false
|
|
required:
|
|
- model
|
|
- selector
|
|
- limit
|
|
tracing:
|
|
type: object
|
|
properties:
|
|
random_sampling:
|
|
type: integer
|
|
trace_arch_internal:
|
|
type: boolean
|
|
opentracing_grpc_endpoint:
|
|
type: string
|
|
span_attributes:
|
|
type: object
|
|
properties:
|
|
header_prefixes:
|
|
type: array
|
|
items:
|
|
type: string
|
|
static:
|
|
type: object
|
|
additionalProperties:
|
|
type: string
|
|
additionalProperties: false
|
|
additionalProperties: false
|
|
mode:
|
|
type: string
|
|
enum:
|
|
- llm
|
|
- prompt
|
|
routing:
|
|
type: object
|
|
properties:
|
|
llm_provider:
|
|
type: string
|
|
model:
|
|
type: string
|
|
session_ttl_seconds:
|
|
type: integer
|
|
minimum: 1
|
|
description: TTL in seconds for session-pinned routing cache entries. Default 600 (10 minutes).
|
|
session_max_entries:
|
|
type: integer
|
|
minimum: 1
|
|
maximum: 10000
|
|
description: Maximum number of session-pinned routing cache entries. Default 10000.
|
|
session_cache:
|
|
type: object
|
|
properties:
|
|
type:
|
|
type: string
|
|
enum:
|
|
- memory
|
|
- redis
|
|
default: memory
|
|
description: Session cache backend. "memory" (default) is in-process; "redis" is shared across replicas.
|
|
url:
|
|
type: string
|
|
description: Redis URL, e.g. redis://localhost:6379. Required when type is redis.
|
|
tenant_header:
|
|
type: string
|
|
description: >
|
|
Optional HTTP header name whose value is used as a tenant prefix in the cache key.
|
|
When set, keys are scoped as plano:affinity:{tenant_id}:{session_id}.
|
|
additionalProperties: false
|
|
additionalProperties: false
|
|
state_storage:
|
|
type: object
|
|
properties:
|
|
type:
|
|
type: string
|
|
enum:
|
|
- memory
|
|
- postgres
|
|
connection_string:
|
|
type: string
|
|
description: Required when type is postgres. Supports environment variable substitution using $VAR or ${VAR} syntax.
|
|
additionalProperties: false
|
|
required:
|
|
- type
|
|
# Note: connection_string is conditionally required based on type
|
|
# If type is 'postgres', connection_string must be provided
|
|
# If type is 'memory', connection_string is not needed
|
|
allOf:
|
|
- if:
|
|
properties:
|
|
type:
|
|
const: postgres
|
|
then:
|
|
required:
|
|
- connection_string
|
|
prompt_guards:
|
|
type: object
|
|
properties:
|
|
input_guards:
|
|
type: object
|
|
properties:
|
|
jailbreak:
|
|
type: object
|
|
properties:
|
|
on_exception:
|
|
type: object
|
|
properties:
|
|
message:
|
|
type: string
|
|
additionalProperties: false
|
|
required:
|
|
- message
|
|
additionalProperties: false
|
|
required:
|
|
- on_exception
|
|
additionalProperties: false
|
|
required:
|
|
- jailbreak
|
|
routing_preferences:
|
|
type: array
|
|
items:
|
|
type: object
|
|
properties:
|
|
name:
|
|
type: string
|
|
description:
|
|
type: string
|
|
models:
|
|
type: array
|
|
items:
|
|
type: string
|
|
minItems: 1
|
|
selection_policy:
|
|
type: object
|
|
properties:
|
|
prefer:
|
|
type: string
|
|
enum:
|
|
- cheapest
|
|
- fastest
|
|
- none
|
|
additionalProperties: false
|
|
required:
|
|
- prefer
|
|
additionalProperties: false
|
|
required:
|
|
- name
|
|
- description
|
|
- models
|
|
|
|
model_metrics_sources:
|
|
type: array
|
|
items:
|
|
oneOf:
|
|
- type: object
|
|
properties:
|
|
type:
|
|
type: string
|
|
const: cost
|
|
provider:
|
|
type: string
|
|
enum:
|
|
- digitalocean
|
|
refresh_interval:
|
|
type: integer
|
|
minimum: 1
|
|
description: "Refresh interval in seconds"
|
|
model_aliases:
|
|
type: object
|
|
description: "Map DO catalog keys (lowercase(creator)/model_id) to Plano model names used in routing_preferences. Example: 'openai/openai-gpt-oss-120b: openai/gpt-4o'"
|
|
additionalProperties:
|
|
type: string
|
|
required:
|
|
- type
|
|
- provider
|
|
additionalProperties: false
|
|
- type: object
|
|
properties:
|
|
type:
|
|
type: string
|
|
const: latency
|
|
provider:
|
|
type: string
|
|
enum:
|
|
- prometheus
|
|
url:
|
|
type: string
|
|
query:
|
|
type: string
|
|
refresh_interval:
|
|
type: integer
|
|
minimum: 1
|
|
description: "Refresh interval in seconds"
|
|
required:
|
|
- type
|
|
- provider
|
|
- url
|
|
- query
|
|
additionalProperties: false
|
|
|
|
additionalProperties: false
|
|
required:
|
|
- version
|
|
- listeners
|