From 59a8775ed7500a03dd241c0f17d1aece9c5162cc Mon Sep 17 00:00:00 2001 From: robert-j-y <212159665+robert-j-y@users.noreply.github.com> Date: Mon, 18 May 2026 15:36:40 -0700 Subject: [PATCH] chore: update OpenAPI spec from monorepo (#257) Co-authored-by: OpenRouter SDK Bot --- .speakeasy/in.openapi.yaml | 69 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) diff --git a/.speakeasy/in.openapi.yaml b/.speakeasy/in.openapi.yaml index 9dfa583..506fca0 100644 --- a/.speakeasy/in.openapi.yaml +++ b/.speakeasy/in.openapi.yaml @@ -4315,11 +4315,13 @@ components: pareto-router: '#/components/schemas/ParetoRouterPlugin' response-healing: '#/components/schemas/ResponseHealingPlugin' web: '#/components/schemas/WebSearchPlugin' + web-fetch: '#/components/schemas/WebFetchPlugin' propertyName: id oneOf: - $ref: '#/components/schemas/AutoRouterPlugin' - $ref: '#/components/schemas/ModerationPlugin' - $ref: '#/components/schemas/WebSearchPlugin' + - $ref: '#/components/schemas/WebFetchPlugin' - $ref: '#/components/schemas/FileParserPlugin' - $ref: '#/components/schemas/ResponseHealingPlugin' - $ref: '#/components/schemas/ContextCompressionPlugin' @@ -6989,6 +6991,13 @@ components: maxItems: 8 minItems: 1 type: array + max_completion_tokens: + description: >- + Maximum number of output tokens (including reasoning tokens) each panelist and the judge model may produce + per inner call. Controls the total output budget so reasoning-heavy models like GPT-5.5 do not exhaust their + token allowance before producing visible text. When omitted, the provider's default applies. + example: 16384 + type: integer max_tool_calls: description: >- Maximum number of tool-calling steps each panelist (analysis model) and the judge model may take during @@ -7004,6 +7013,34 @@ components: API request. example: ~anthropic/claude-opus-latest type: string + reasoning: + description: >- + Reasoning configuration forwarded to panelist and judge inner calls. Use this to control reasoning effort + and token budget for models that support extended thinking. + properties: + effort: + description: Reasoning effort level for panelist and judge inner calls. + enum: + - xhigh + - high + - medium + - low + - minimal + - none + type: string + max_tokens: + description: >- + Maximum number of reasoning tokens each panelist and judge model may use. Helps bound cost when models + allocate too much budget to chain-of-thought. + type: integer + type: object + temperature: + description: >- + Sampling temperature forwarded to panelist and judge inner calls. When omitted, the provider's default + applies. + example: 0.7 + format: double + type: number type: object GenerationContentData: description: Stored prompt and completion content @@ -9757,11 +9794,13 @@ components: pareto-router: '#/components/schemas/ParetoRouterPlugin' response-healing: '#/components/schemas/ResponseHealingPlugin' web: '#/components/schemas/WebSearchPlugin' + web-fetch: '#/components/schemas/WebFetchPlugin' propertyName: id oneOf: - $ref: '#/components/schemas/AutoRouterPlugin' - $ref: '#/components/schemas/ModerationPlugin' - $ref: '#/components/schemas/WebSearchPlugin' + - $ref: '#/components/schemas/WebFetchPlugin' - $ref: '#/components/schemas/FileParserPlugin' - $ref: '#/components/schemas/ResponseHealingPlugin' - $ref: '#/components/schemas/ContextCompressionPlugin' @@ -16840,11 +16879,13 @@ components: pareto-router: '#/components/schemas/ParetoRouterPlugin' response-healing: '#/components/schemas/ResponseHealingPlugin' web: '#/components/schemas/WebSearchPlugin' + web-fetch: '#/components/schemas/WebFetchPlugin' propertyName: id oneOf: - $ref: '#/components/schemas/AutoRouterPlugin' - $ref: '#/components/schemas/ModerationPlugin' - $ref: '#/components/schemas/WebSearchPlugin' + - $ref: '#/components/schemas/WebFetchPlugin' - $ref: '#/components/schemas/FileParserPlugin' - $ref: '#/components/schemas/ResponseHealingPlugin' - $ref: '#/components/schemas/ContextCompressionPlugin' @@ -18737,6 +18778,34 @@ components: - exa example: auto type: string + WebFetchPlugin: + example: + id: web-fetch + max_uses: 10 + properties: + allowed_domains: + description: Only fetch from these domains. + items: + type: string + type: array + blocked_domains: + description: Never fetch from these domains. + items: + type: string + type: array + id: + enum: + - web-fetch + type: string + max_content_tokens: + description: Maximum content length in approximate tokens. Content exceeding this limit is truncated. + type: integer + max_uses: + description: Maximum number of web fetches per request. Once exceeded, the tool returns an error. + type: integer + required: + - id + type: object WebFetchServerTool: description: 'OpenRouter built-in server tool: fetches full content from a URL (web page or PDF)' example: