mirror of
https://github.com/wassname/openrouter-python-sdk-retry-errors.git
synced 2026-07-29 11:23:49 +08:00
19 lines
17 KiB
Plaintext
19 lines
17 KiB
Plaintext
---
|
|
title: "FusionServerToolConfig"
|
|
---
|
|
|
|
Configuration for the openrouter:fusion server tool.
|
|
|
|
|
|
## Fields
|
|
|
|
| Field | Type | Required | Description | Example |
|
|
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
| `analysis_models` | List[*str*] | :heavy_minus_sign: | Slugs of models to run in parallel as the analysis panel. Each model receives the user prompt with openrouter:web_search and openrouter:web_fetch enabled, then a judge model summarizes the collective output into structured analysis JSON. Capped at 8 models to bound cost amplification. Defaults to the Quality preset from /labs/fusion. | [<br/>"~anthropic/claude-opus-latest",<br/>"~openai/gpt-latest",<br/>"~google/gemini-pro-latest"<br/>] |
|
|
| `cache_control` | [Optional[components.AnthropicCacheControlDirective]](../components/anthropiccachecontroldirective.mdx) | :heavy_minus_sign: | Enable automatic prompt caching. When set at the top level, the system automatically applies cache breakpoints to the last cacheable block in the request. Currently supported for Anthropic Claude models. | \{<br/>"type": "ephemeral"<br/>} |
|
|
| `max_completion_tokens` | *Optional[int]* | :heavy_minus_sign: | 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. | 16384 |
|
|
| `max_tool_calls` | *Optional[int]* | :heavy_minus_sign: | Maximum number of tool-calling steps each panelist (analysis model) and the judge model may take during their agentic web-research loop. Models with web_search/web_fetch enabled iterate until they produce a text response or hit this ceiling. Defaults to 8. Capped at 16. | 12 |
|
|
| `model` | *Optional[str]* | :heavy_minus_sign: | Slug of the judge model that produces the structured analysis JSON. Defaults to the model used in the outer API request. | ~anthropic/claude-opus-latest |
|
|
| `reasoning` | [Optional[components.FusionServerToolConfigReasoning]](../components/fusionservertoolconfigreasoning.mdx) | :heavy_minus_sign: | Reasoning configuration forwarded to panelist and judge inner calls. Use this to control reasoning effort and token budget for models that support extended thinking. | |
|
|
| `temperature` | *Optional[float]* | :heavy_minus_sign: | Temperature forwarded to panelist inner calls. The judge always runs at temperature 0 regardless of this value. When omitted, the provider's default applies. | 0.7 |
|
|
| `tools` | List[[components.FusionServerToolConfigTool](../components/fusionservertoolconfigtool.mdx)] | :heavy_minus_sign: | Server tools available to panelist and judge inner calls. Each entry uses the same `{ type, parameters? }` shorthand as the outer Chat Completions request. When omitted, defaults to `[{ type: "openrouter:web_search" }, { type: "openrouter:web_fetch" }]`. Pass an empty array to disable tools entirely (panelists answer from parametric knowledge only). | [<br/>\{<br/>"parameters": \{<br/>"excluded_domains": [<br/>"example.com"<br/>]<br/>},<br/>"type": "openrouter:web_search"<br/>},<br/>\{<br/>"type": "openrouter:web_fetch"<br/>}<br/>] | |