mirror of
https://github.com/katanemo/plano.git
synced 2026-06-08 14:55:14 +02:00
config: add retry_policy to plano_config_schema.yaml
Add JSON schema definitions for retry policy configuration including RetryPolicy, BackoffConfig, RetryAfterConfig, HighLatencyConfig, LatencyTriggerConfig, RetryStrategy, StatusCodeEntry, and all associated enums. Signed-off-by: Troy Mitchell <i@troy-y.org>
This commit is contained in:
Troy Mitchell
parent
388fbff8e6
commit
18dbbd25f7
1 changed files with 354 additions and 0 deletions
|
|
@ -213,6 +213,183 @@ properties:
|
|||
required:
|
||||
- name
|
||||
- description
|
||||
retry_policy:
|
||||
type: object
|
||||
description: "Retry policy configuration. When not specified, no retry logic is enabled."
|
||||
properties:
|
||||
fallback_models:
|
||||
type: array
|
||||
description: "Ordered list of model identifiers to fallback to before using Provider_List."
|
||||
items:
|
||||
type: string
|
||||
default_strategy:
|
||||
type: string
|
||||
description: "Default retry strategy for unconfigured status codes. Default: different_provider."
|
||||
enum:
|
||||
- same_model
|
||||
- same_provider
|
||||
- different_provider
|
||||
default_max_attempts:
|
||||
type: integer
|
||||
description: "Default max retry attempts for unconfigured status codes. Default: 2."
|
||||
minimum: 0
|
||||
on_status_codes:
|
||||
type: array
|
||||
description: "Per-status-code retry configuration."
|
||||
items:
|
||||
type: object
|
||||
properties:
|
||||
codes:
|
||||
type: array
|
||||
description: "List of status codes as integers or range strings (e.g. '502-504')."
|
||||
items:
|
||||
anyOf:
|
||||
- type: integer
|
||||
minimum: 100
|
||||
maximum: 599
|
||||
- type: string
|
||||
description: "Range string in 'start-end' format (e.g. '502-504')."
|
||||
strategy:
|
||||
type: string
|
||||
description: "Retry strategy for these status codes."
|
||||
enum:
|
||||
- same_model
|
||||
- same_provider
|
||||
- different_provider
|
||||
max_attempts:
|
||||
type: integer
|
||||
description: "Max retry attempts for these status codes."
|
||||
minimum: 0
|
||||
additionalProperties: false
|
||||
required:
|
||||
- codes
|
||||
- strategy
|
||||
- max_attempts
|
||||
on_timeout:
|
||||
type: object
|
||||
description: "Timeout-specific retry configuration. When omitted, timeouts use default_strategy and default_max_attempts."
|
||||
properties:
|
||||
strategy:
|
||||
type: string
|
||||
description: "Retry strategy for timeout errors."
|
||||
enum:
|
||||
- same_model
|
||||
- same_provider
|
||||
- different_provider
|
||||
max_attempts:
|
||||
type: integer
|
||||
description: "Max retry attempts for timeout errors."
|
||||
minimum: 1
|
||||
additionalProperties: false
|
||||
required:
|
||||
- strategy
|
||||
- max_attempts
|
||||
on_high_latency:
|
||||
type: object
|
||||
description: "High latency proactive failover configuration. When omitted, no latency-based failover is performed."
|
||||
properties:
|
||||
threshold_ms:
|
||||
type: integer
|
||||
description: "Latency threshold in milliseconds. When response time exceeds this value, a High_Latency_Event is triggered."
|
||||
minimum: 1
|
||||
measure:
|
||||
type: string
|
||||
description: "What latency metric to measure. Default: ttfb."
|
||||
enum:
|
||||
- ttfb
|
||||
- total
|
||||
strategy:
|
||||
type: string
|
||||
description: "Retry strategy when latency threshold is exceeded."
|
||||
enum:
|
||||
- same_model
|
||||
- same_provider
|
||||
- different_provider
|
||||
max_attempts:
|
||||
type: integer
|
||||
description: "Max retry attempts when latency threshold is exceeded."
|
||||
minimum: 1
|
||||
block_duration_seconds:
|
||||
type: integer
|
||||
description: "How long to block the model/provider after detecting high latency, in seconds. Default: 300."
|
||||
minimum: 1
|
||||
scope:
|
||||
type: string
|
||||
description: "What to block: model-level or provider-level. Default: model."
|
||||
enum:
|
||||
- model
|
||||
- provider
|
||||
apply_to:
|
||||
type: string
|
||||
description: "Blocking scope: global or request-scoped. Default: global."
|
||||
enum:
|
||||
- global
|
||||
- request
|
||||
min_triggers:
|
||||
type: integer
|
||||
description: "Number of High_Latency_Events required before creating a block. Default: 1."
|
||||
minimum: 1
|
||||
trigger_window_seconds:
|
||||
type: integer
|
||||
description: "Sliding time window in seconds for counting triggers. Required when min_triggers > 1."
|
||||
minimum: 1
|
||||
additionalProperties: false
|
||||
required:
|
||||
- threshold_ms
|
||||
- strategy
|
||||
- max_attempts
|
||||
- block_duration_seconds
|
||||
backoff:
|
||||
type: object
|
||||
description: "Exponential backoff configuration. When omitted, no backoff delays are applied."
|
||||
properties:
|
||||
apply_to:
|
||||
type: string
|
||||
description: "REQUIRED. Determines when backoff delays are applied."
|
||||
enum:
|
||||
- same_model
|
||||
- same_provider
|
||||
- global
|
||||
base_ms:
|
||||
type: integer
|
||||
description: "Base delay in milliseconds for exponential backoff. Default: 100."
|
||||
minimum: 1
|
||||
max_ms:
|
||||
type: integer
|
||||
description: "Maximum delay in milliseconds for exponential backoff. Default: 5000."
|
||||
minimum: 1
|
||||
jitter:
|
||||
type: boolean
|
||||
description: "Add random jitter to prevent thundering herd. Default: true."
|
||||
additionalProperties: false
|
||||
required:
|
||||
- apply_to
|
||||
retry_after_handling:
|
||||
type: object
|
||||
description: "Retry-After header handling customization. When omitted, Retry-After is honored with defaults (scope: model, apply_to: global, max_retry_after_seconds: 300)."
|
||||
properties:
|
||||
scope:
|
||||
type: string
|
||||
description: "What to block: model-level or provider-level. Default: model."
|
||||
enum:
|
||||
- model
|
||||
- provider
|
||||
apply_to:
|
||||
type: string
|
||||
description: "Blocking scope: request-scoped or global. Default: global."
|
||||
enum:
|
||||
- request
|
||||
- global
|
||||
max_retry_after_seconds:
|
||||
type: integer
|
||||
description: "Maximum Retry-After value honored in seconds. Default: 300."
|
||||
minimum: 1
|
||||
additionalProperties: false
|
||||
max_retry_duration_ms:
|
||||
type: integer
|
||||
description: "Maximum total time in milliseconds for all retry attempts combined. Timer starts on first retry."
|
||||
minimum: 0
|
||||
additionalProperties: false
|
||||
additionalProperties: false
|
||||
required:
|
||||
- model
|
||||
|
|
@ -271,6 +448,183 @@ properties:
|
|||
required:
|
||||
- name
|
||||
- description
|
||||
retry_policy:
|
||||
type: object
|
||||
description: "Retry policy configuration. When not specified, no retry logic is enabled."
|
||||
properties:
|
||||
fallback_models:
|
||||
type: array
|
||||
description: "Ordered list of model identifiers to fallback to before using Provider_List."
|
||||
items:
|
||||
type: string
|
||||
default_strategy:
|
||||
type: string
|
||||
description: "Default retry strategy for unconfigured status codes. Default: different_provider."
|
||||
enum:
|
||||
- same_model
|
||||
- same_provider
|
||||
- different_provider
|
||||
default_max_attempts:
|
||||
type: integer
|
||||
description: "Default max retry attempts for unconfigured status codes. Default: 2."
|
||||
minimum: 0
|
||||
on_status_codes:
|
||||
type: array
|
||||
description: "Per-status-code retry configuration."
|
||||
items:
|
||||
type: object
|
||||
properties:
|
||||
codes:
|
||||
type: array
|
||||
description: "List of status codes as integers or range strings (e.g. '502-504')."
|
||||
items:
|
||||
anyOf:
|
||||
- type: integer
|
||||
minimum: 100
|
||||
maximum: 599
|
||||
- type: string
|
||||
description: "Range string in 'start-end' format (e.g. '502-504')."
|
||||
strategy:
|
||||
type: string
|
||||
description: "Retry strategy for these status codes."
|
||||
enum:
|
||||
- same_model
|
||||
- same_provider
|
||||
- different_provider
|
||||
max_attempts:
|
||||
type: integer
|
||||
description: "Max retry attempts for these status codes."
|
||||
minimum: 0
|
||||
additionalProperties: false
|
||||
required:
|
||||
- codes
|
||||
- strategy
|
||||
- max_attempts
|
||||
on_timeout:
|
||||
type: object
|
||||
description: "Timeout-specific retry configuration. When omitted, timeouts use default_strategy and default_max_attempts."
|
||||
properties:
|
||||
strategy:
|
||||
type: string
|
||||
description: "Retry strategy for timeout errors."
|
||||
enum:
|
||||
- same_model
|
||||
- same_provider
|
||||
- different_provider
|
||||
max_attempts:
|
||||
type: integer
|
||||
description: "Max retry attempts for timeout errors."
|
||||
minimum: 1
|
||||
additionalProperties: false
|
||||
required:
|
||||
- strategy
|
||||
- max_attempts
|
||||
on_high_latency:
|
||||
type: object
|
||||
description: "High latency proactive failover configuration. When omitted, no latency-based failover is performed."
|
||||
properties:
|
||||
threshold_ms:
|
||||
type: integer
|
||||
description: "Latency threshold in milliseconds. When response time exceeds this value, a High_Latency_Event is triggered."
|
||||
minimum: 1
|
||||
measure:
|
||||
type: string
|
||||
description: "What latency metric to measure. Default: ttfb."
|
||||
enum:
|
||||
- ttfb
|
||||
- total
|
||||
strategy:
|
||||
type: string
|
||||
description: "Retry strategy when latency threshold is exceeded."
|
||||
enum:
|
||||
- same_model
|
||||
- same_provider
|
||||
- different_provider
|
||||
max_attempts:
|
||||
type: integer
|
||||
description: "Max retry attempts when latency threshold is exceeded."
|
||||
minimum: 1
|
||||
block_duration_seconds:
|
||||
type: integer
|
||||
description: "How long to block the model/provider after detecting high latency, in seconds. Default: 300."
|
||||
minimum: 1
|
||||
scope:
|
||||
type: string
|
||||
description: "What to block: model-level or provider-level. Default: model."
|
||||
enum:
|
||||
- model
|
||||
- provider
|
||||
apply_to:
|
||||
type: string
|
||||
description: "Blocking scope: global or request-scoped. Default: global."
|
||||
enum:
|
||||
- global
|
||||
- request
|
||||
min_triggers:
|
||||
type: integer
|
||||
description: "Number of High_Latency_Events required before creating a block. Default: 1."
|
||||
minimum: 1
|
||||
trigger_window_seconds:
|
||||
type: integer
|
||||
description: "Sliding time window in seconds for counting triggers. Required when min_triggers > 1."
|
||||
minimum: 1
|
||||
additionalProperties: false
|
||||
required:
|
||||
- threshold_ms
|
||||
- strategy
|
||||
- max_attempts
|
||||
- block_duration_seconds
|
||||
backoff:
|
||||
type: object
|
||||
description: "Exponential backoff configuration. When omitted, no backoff delays are applied."
|
||||
properties:
|
||||
apply_to:
|
||||
type: string
|
||||
description: "REQUIRED. Determines when backoff delays are applied."
|
||||
enum:
|
||||
- same_model
|
||||
- same_provider
|
||||
- global
|
||||
base_ms:
|
||||
type: integer
|
||||
description: "Base delay in milliseconds for exponential backoff. Default: 100."
|
||||
minimum: 1
|
||||
max_ms:
|
||||
type: integer
|
||||
description: "Maximum delay in milliseconds for exponential backoff. Default: 5000."
|
||||
minimum: 1
|
||||
jitter:
|
||||
type: boolean
|
||||
description: "Add random jitter to prevent thundering herd. Default: true."
|
||||
additionalProperties: false
|
||||
required:
|
||||
- apply_to
|
||||
retry_after_handling:
|
||||
type: object
|
||||
description: "Retry-After header handling customization. When omitted, Retry-After is honored with defaults (scope: model, apply_to: global, max_retry_after_seconds: 300)."
|
||||
properties:
|
||||
scope:
|
||||
type: string
|
||||
description: "What to block: model-level or provider-level. Default: model."
|
||||
enum:
|
||||
- model
|
||||
- provider
|
||||
apply_to:
|
||||
type: string
|
||||
description: "Blocking scope: request-scoped or global. Default: global."
|
||||
enum:
|
||||
- request
|
||||
- global
|
||||
max_retry_after_seconds:
|
||||
type: integer
|
||||
description: "Maximum Retry-After value honored in seconds. Default: 300."
|
||||
minimum: 1
|
||||
additionalProperties: false
|
||||
max_retry_duration_ms:
|
||||
type: integer
|
||||
description: "Maximum total time in milliseconds for all retry attempts combined. Timer starts on first retry."
|
||||
minimum: 0
|
||||
additionalProperties: false
|
||||
additionalProperties: false
|
||||
required:
|
||||
- model
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue