mirror of
https://github.com/wassname/openrouter-python-sdk-retry-errors.git
synced 2026-07-29 11:23:49 +08:00
chore: update OpenAPI spec from monorepo (#297)
Co-authored-by: OpenRouter SDK Bot <sdk-bot@openrouter.ai>
This commit is contained in:
robert-j-y
co-authored by
OpenRouter SDK Bot
OpenRouter SDK Bot
parent
8df520997d
commit
1725abad89
+66
-114
@@ -119,12 +119,51 @@ components:
|
||||
required:
|
||||
- type
|
||||
type: object
|
||||
AdvisorProfile:
|
||||
AdvisorReasoning:
|
||||
description: >-
|
||||
A named advisor profile. The executor model selects it by `name` and the profile's config (model, instructions,
|
||||
etc.) takes precedence over the request-wide advisor parameters for that call.
|
||||
Reasoning configuration forwarded to the advisor call. Use this to control reasoning effort and token budget for
|
||||
models that support extended thinking.
|
||||
example:
|
||||
effort: high
|
||||
properties:
|
||||
effort:
|
||||
description: Reasoning effort level for the advisor call.
|
||||
enum:
|
||||
- xhigh
|
||||
- high
|
||||
- medium
|
||||
- low
|
||||
- minimal
|
||||
- none
|
||||
type: string
|
||||
max_tokens:
|
||||
description: Maximum number of reasoning tokens the advisor may use.
|
||||
type: integer
|
||||
type: object
|
||||
AdvisorServerTool_OpenRouter:
|
||||
description: >-
|
||||
OpenRouter built-in server tool: consults a higher-intelligence advisor model (any OpenRouter model) for
|
||||
guidance mid-generation and returns its response. The advisor may run as a sub-agent with its own tools. Include
|
||||
multiple entries to offer several named advisors; at most one entry may omit `name` to act as the default
|
||||
advisor.
|
||||
example:
|
||||
parameters:
|
||||
model: ~anthropic/claude-opus-latest
|
||||
name: reviewer
|
||||
type: openrouter:advisor
|
||||
properties:
|
||||
parameters:
|
||||
$ref: '#/components/schemas/AdvisorServerToolConfig'
|
||||
type:
|
||||
enum:
|
||||
- openrouter:advisor
|
||||
type: string
|
||||
required:
|
||||
- type
|
||||
type: object
|
||||
AdvisorServerToolConfig:
|
||||
description: Configuration for one openrouter:advisor server tool entry.
|
||||
example:
|
||||
instructions: You are a critical code reviewer.
|
||||
model: ~anthropic/claude-opus-latest
|
||||
name: reviewer
|
||||
properties:
|
||||
@@ -164,123 +203,24 @@ components:
|
||||
type: string
|
||||
name:
|
||||
description: >-
|
||||
Name of this advisor profile. The executor model passes this `name` to the advisor tool to select the
|
||||
profile. Must be unique within the `advisors` roster. Letters, digits, underscores, and dashes; 1–64 chars.
|
||||
Optional name for this advisor. The model sees one tool per named advisor (and one default for an unnamed
|
||||
entry). Names must be unique across advisor entries. Letters, digits, spaces, underscores, and dashes;
|
||||
trimmed; 1–64 chars.
|
||||
example: reviewer
|
||||
pattern: ^[a-zA-Z0-9_-]{1,64}$
|
||||
maxLength: 64
|
||||
minLength: 1
|
||||
pattern: ^[a-zA-Z0-9 _-]+$
|
||||
type: string
|
||||
reasoning:
|
||||
$ref: '#/components/schemas/AdvisorReasoning'
|
||||
temperature:
|
||||
description: Sampling temperature forwarded to the advisor call. When omitted, the provider's default applies.
|
||||
example: 0.7
|
||||
format: double
|
||||
type: number
|
||||
tools:
|
||||
stream:
|
||||
description: >-
|
||||
Tools the advisor sub-agent may use while forming its advice. The advisor runs as an agentic sub-agent over
|
||||
these tools, then returns its text. Must not include the advisor tool itself.
|
||||
items:
|
||||
$ref: '#/components/schemas/AdvisorNestedTool'
|
||||
type: array
|
||||
required:
|
||||
- name
|
||||
type: object
|
||||
AdvisorReasoning:
|
||||
description: >-
|
||||
Reasoning configuration forwarded to the advisor call. Use this to control reasoning effort and token budget for
|
||||
models that support extended thinking.
|
||||
example:
|
||||
effort: high
|
||||
properties:
|
||||
effort:
|
||||
description: Reasoning effort level for the advisor call.
|
||||
enum:
|
||||
- xhigh
|
||||
- high
|
||||
- medium
|
||||
- low
|
||||
- minimal
|
||||
- none
|
||||
type: string
|
||||
max_tokens:
|
||||
description: Maximum number of reasoning tokens the advisor may use.
|
||||
type: integer
|
||||
type: object
|
||||
AdvisorServerTool_OpenRouter:
|
||||
description: >-
|
||||
OpenRouter built-in server tool: consults a higher-intelligence advisor model (any OpenRouter model) for
|
||||
guidance mid-generation and returns its response. The advisor may run as a sub-agent with its own tools.
|
||||
example:
|
||||
parameters:
|
||||
model: ~anthropic/claude-opus-latest
|
||||
type: openrouter:advisor
|
||||
properties:
|
||||
parameters:
|
||||
$ref: '#/components/schemas/AdvisorServerToolConfig'
|
||||
type:
|
||||
enum:
|
||||
- openrouter:advisor
|
||||
type: string
|
||||
required:
|
||||
- type
|
||||
type: object
|
||||
AdvisorServerToolConfig:
|
||||
description: Configuration for the openrouter:advisor server tool.
|
||||
example:
|
||||
model: ~anthropic/claude-opus-latest
|
||||
properties:
|
||||
advisors:
|
||||
description: >-
|
||||
Roster of named advisor profiles. When set, the executor model selects one by passing its `name` to the
|
||||
advisor tool; the chosen profile's config overrides the request-wide advisor parameters. Profile names must
|
||||
be unique.
|
||||
example:
|
||||
- instructions: You are a critical code reviewer.
|
||||
model: ~anthropic/claude-opus-latest
|
||||
name: reviewer
|
||||
- instructions: You are a systems architect.
|
||||
model: ~openai/gpt-latest
|
||||
name: architect
|
||||
items:
|
||||
$ref: '#/components/schemas/AdvisorProfile'
|
||||
type: array
|
||||
forward_transcript:
|
||||
description: >-
|
||||
When true, the full parent conversation is forwarded to the advisor so it sees the same context the executor
|
||||
does (and the tool-call `prompt`, if given, is appended as a final user turn). When false or omitted, the
|
||||
advisor receives only the `prompt` the executor passes in the tool call.
|
||||
When true, the advisor's advice streams incrementally as it is produced. In the Responses API this emits
|
||||
`response.output_text.delta` events targeting the advisor output item; the final `advice` field is still set
|
||||
on the completed item. Has no effect on the Chat Completions API (where the advice arrives only as the final
|
||||
tool result). When false or omitted, the advice arrives only as the final result.
|
||||
example: false
|
||||
type: boolean
|
||||
instructions:
|
||||
description: >-
|
||||
System instructions for the advisor sub-agent. When omitted, the advisor responds with no system prompt of
|
||||
its own.
|
||||
example: You are a senior staff engineer. Give a focused, decisive plan.
|
||||
type: string
|
||||
max_completion_tokens:
|
||||
description: >-
|
||||
Maximum number of output tokens (including reasoning) the advisor may produce. When omitted, the provider's
|
||||
default applies.
|
||||
example: 2048
|
||||
type: integer
|
||||
max_tool_calls:
|
||||
description: >-
|
||||
Maximum number of tool-calling steps the advisor sub-agent may take during its agentic loop. Capped at 25.
|
||||
Only relevant when the advisor is given tools.
|
||||
example: 5
|
||||
maximum: 25
|
||||
minimum: 1
|
||||
type: integer
|
||||
model:
|
||||
description: >-
|
||||
Slug of the advisor model to consult (any OpenRouter model). When omitted, the executor can choose it via
|
||||
the tool call's `model` argument; if neither is set, the model from the outer API request is used. The
|
||||
advisor tool itself cannot be the advisor model.
|
||||
example: ~anthropic/claude-opus-latest
|
||||
type: string
|
||||
reasoning:
|
||||
$ref: '#/components/schemas/AdvisorReasoning'
|
||||
temperature:
|
||||
description: Sampling temperature forwarded to the advisor call. When omitted, the provider's default applies.
|
||||
example: 0.7
|
||||
@@ -9163,6 +9103,7 @@ components:
|
||||
- $ref: '#/components/schemas/OutputMemoryServerToolItem'
|
||||
- $ref: '#/components/schemas/OutputMcpServerToolItem'
|
||||
- $ref: '#/components/schemas/OutputSearchModelsServerToolItem'
|
||||
- $ref: '#/components/schemas/OutputAdvisorServerToolItem'
|
||||
- $ref: '#/components/schemas/LocalShellCallItem'
|
||||
- $ref: '#/components/schemas/LocalShellCallOutputItem'
|
||||
- $ref: '#/components/schemas/ShellCallItem'
|
||||
@@ -14505,6 +14446,17 @@ components:
|
||||
type: string
|
||||
id:
|
||||
type: string
|
||||
instance_name:
|
||||
description: >-
|
||||
Provider-safe function name of the specific advisor instance that produced this item (e.g.
|
||||
`openrouter_advisor__1`). Present only when more than one advisor tool is configured; omitted for the
|
||||
default single advisor. Echo this field back unchanged so the advisor's cross-request memory stays
|
||||
namespaced to the correct instance. This identity is positional: it is derived from the index of the advisor
|
||||
entry in the request `tools` array, so clients must keep the order of advisor tool entries stable across
|
||||
requests in a conversation. Reordering or inserting advisor entries shifts these names and causes each
|
||||
advisor's cross-request memory to be attributed to the wrong instance.
|
||||
example: openrouter_advisor__1
|
||||
type: string
|
||||
model:
|
||||
description: Slug of the advisor model that was consulted.
|
||||
type: string
|
||||
|
||||
Reference in New Issue
Block a user