wassname/openrouter-python-sdk-retry-errors
1
0
Fork 0
mirror of https://github.com/wassname/openrouter-python-sdk-retry-errors.git synced 2026-07-30 12:20:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

chore: 🐝 Update SDK - Generate (spec change merged) 0.11.6 (#400)

Browse Source 
Co-authored-by: speakeasybot <bot@speakeasyapi.dev>
Co-authored-by: speakeasy-github[bot] <128539517+speakeasy-github[bot]@users.noreply.github.com>
This commit is contained in:
github-actions[bot]
2026-07-07 19:13:32 +00:00
committed by GitHub
co-authored by speakeasybot speakeasy-github[bot] <128539517+speakeasy-github[bot]@users.noreply.github.com>
parent 9ac997d8b8
commit d18d840c52
10 changed files with 39 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/openrouter/components/fusionservertoolconfig.py
+2 -2
View File
@@ -100,7 +100,7 @@ class FusionServerToolConfigTypedDict(TypedDict):
cache_control: NotRequired[AnthropicCacheControlDirectiveTypedDict]
r"""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."""
max_completion_tokens: NotRequired[int]
r"""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."""
r"""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, panelists default to 32000 and the judge to 50000."""
max_tool_calls: NotRequired[int]
r"""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."""
model: NotRequired[str]
@@ -123,7 +123,7 @@ class FusionServerToolConfig(BaseModel):
r"""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."""
max_completion_tokens: Optional[int] = None
r"""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."""
r"""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, panelists default to 32000 and the judge to 50000."""
max_tool_calls: Optional[int] = None
r"""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."""