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 GET /api/settings/memory Get memory settings Returns the extended memory settings including 7 new fields added in plan 21 (embeddingSource, embeddingProviderModel, transformersEnabled, staticEnabled, rerankEnabled, rerankProviderModel, vectorStore). PUT /api/settings/memory Update memory settings Update any subset of the extended memory settings. All fields are optional; only provided fields are updated. Schema: MemorySettingsExtendedSchema . GET /api/settings/qdrant Get Qdrant settings Returns current Qdrant configuration. The apiKey field is never returned raw — use hasApiKey / apiKeyMasked instead. PUT /api/settings/qdrant Update Qdrant settings Update Qdrant configuration. Pass apiKey: "" to remove the stored key. Schema: QdrantSettingsUpdateSchema . GET /api/settings/qdrant/health Qdrant health probe Performs a liveness check against the configured Qdrant instance. Returns latency and any connection error (sanitized — no stack traces). POST /api/settings/qdrant/search Qdrant semantic search test Performs a test semantic search against the Qdrant collection. Useful for validating that the integration works end to end. Schema: QdrantSearchSchema . POST /api/settings/qdrant/cleanup Clean up expired Qdrant points Removes Qdrant points for memories that have expired or exceeded the configured retention window. GET /api/settings/qdrant/embedding models List Qdrant embedding models Returns the list of embedding models available for use with Qdrant. GET /api/settings Get application settings PATCH /api/settings Update settings POST /api/settings/purge request history Clear request log history Deletes call logs , legacy request detail logs , and local request artifact files under DATA DIR/call logs . GET /api/settings/compression Get global compression settings PUT /api/settings/compression Update global compression settings GET /api/settings/compression/mcp accessibility Get the MCP tool output accessibility (trimming) config PUT /api/settings/compression/mcp accessibility Update the MCP tool output accessibility (trimming) config Partial merge update. Numeric floors (e.g. a maxTextChars below the truncation tail reserve) are folded back to the safe defaults server side, so the response reflects the effective config. GET /api/settings/payload rules Get payload rules configuration Returns the current payload rules used to mutate outgoing request payloads before they are sent upstream. Requires a dashboard management session cookie when management auth is enabled. PUT /api/settings/payload rules Update payload rules configuration Persists and hot reloads payload rules. The legacy input field default raw is accepted on writes and normalized to defaultRaw in responses/runtime state. Requires a dashboard management session cookie when management auth is enabled. GET /api/settings/combo defaults Get combo default settings GET /api/settings/proxy Get proxy settings PATCH /api/settings/proxy Update proxy settings POST /api/settings/proxy/test Test proxy connection POST /api/settings/require login Toggle login requirement GET /api/settings/ip filter Get IP filter configuration Returns the current IP filter settings including blacklist, whitelist, and temp bans. PUT /api/settings/ip filter Update IP filter configuration Configure IP filtering with blacklist/whitelist modes, add/remove individual IPs, and manage temp bans. GET /api/settings/system prompt Get system prompt configuration Returns the current system prompt injection settings. PUT /api/settings/system prompt Update system prompt configuration GET /api/settings/thinking budget Get thinking budget configuration Returns the current thinking/reasoning budget settings for AI models. PUT /api/settings/thinking budget Update thinking budget configuration GET /api/tags List Ollama compatible model tags Returns models in Ollama /api/tags format for Ollama client compatibility GET /api/settings/quota store Get current quota store driver settings Redis URL is masked in the response (shows only scheme+host). PUT /api/settings/quota store Update quota store driver settings POST /api/settings/purge usage history Purge usage history Dashboard only. Purges stored usage history records. 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: Field Meaning mode passthrough (leave client reasoning alone — required for Codex visible thinking ), auto ( strips all client thinking fields), custom , adaptive customBudget Fixed budget when mode=custom effortLevel Base 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): 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

omni-settings