<< All versions

Skill v1.0.0

currentLLM-judged scan90/100
cheaper-inference/omniroute/omni-settings
──Details
PublishedOctober 22, 2026 at 05:44 PM
Content Hashsha256:19adbab9565f92fa...
Git SHAdaca9902e859
──Files
Files (1 file, 14.7 KB)
SKILL.md14.7 KBactive
SKILL.md · 186 lines · 14.7 KB

version: "1.0.0" name: omni-settings description: "Read and update global application settings: system prompts, thinking budget, IP filters, payload rules, combo defaults, and require-login configuration."

<!-- generated by src/lib/agentSkills/generator.ts; manual edits will be overwritten -->

Overview

Read and update global application settings: system prompts, thinking budget, IP filters, payload rules, combo defaults, and require-login configuration.

Authentication

All requests require a valid Bearer token or session cookie. Obtain a token via POST /api/auth/login or configure REQUIRE_API_KEY=false for local development.

Endpoints

Payloads

See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml for detailed request/response schemas.

<!-- skill:custom-start --> <!-- Thinking budget behavior (preserved curated content — #10169) -->

GET /api/settings/thinking-budget — behavior

Returns proxy-level thinking/reasoning request rewrite settings:

FieldMeaning
modepassthrough (leave client reasoning alone — required for Codex visible thinking), auto (strips all client thinking fields), custom, adaptive
customBudgetFixed budget when mode=custom
effortLevelBase effort when mode=adaptive

Not compression and not "decrypt encrypted reasoning". Full guide: docs/guides/THINKING_BUDGET.md.

Example — keep client-controlled reasoning (Codex/Desktop):

bash
curl -X PUT https://localhost:20128/api/settings/thinking-budget \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"mode":"passthrough","customBudget":10240,"effortLevel":"medium"}'

Warning: mode=auto deletes reasoning / reasoning_effort / Claude thinking from the outbound body before upstream. That can empty thinking panels even when the client requested Ultra + summary. <!-- skill:custom-end -->

All versions