omni-settings

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).

curl https://localhost:20128/api/settings/memory \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

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.

curl -X PUT https://localhost:20128/api/settings/memory \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

GET /api/settings/qdrant

Get Qdrant settings

Returns current Qdrant configuration. The apiKey field is never returned raw — use hasApiKey / apiKeyMasked instead.

curl https://localhost:20128/api/settings/qdrant \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

PUT /api/settings/qdrant

Update Qdrant settings

Update Qdrant configuration. Pass apiKey: "" to remove the stored key. Schema: QdrantSettingsUpdateSchema.

curl -X PUT https://localhost:20128/api/settings/qdrant \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

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).

curl https://localhost:20128/api/settings/qdrant/health \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

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.

curl -X POST https://localhost:20128/api/settings/qdrant/search \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

POST /api/settings/qdrant/cleanup

Clean up expired Qdrant points

Removes Qdrant points for memories that have expired or exceeded the configured retention window.

curl -X POST https://localhost:20128/api/settings/qdrant/cleanup \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

GET /api/settings/qdrant/embedding-models

List Qdrant embedding models

Returns the list of embedding models available for use with Qdrant.

curl https://localhost:20128/api/settings/qdrant/embedding-models \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

GET /api/settings

Get application settings

curl https://localhost:20128/api/settings \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

PATCH /api/settings

Update settings

curl -X PATCH https://localhost:20128/api/settings \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

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.

curl -X POST https://localhost:20128/api/settings/purge-request-history \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

GET /api/settings/compression

Get global compression settings

curl https://localhost:20128/api/settings/compression \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

PUT /api/settings/compression

Update global compression settings

curl -X PUT https://localhost:20128/api/settings/compression \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

GET /api/settings/compression/mcp-accessibility

Get the MCP tool-output accessibility (trimming) config

curl https://localhost:20128/api/settings/compression/mcp-accessibility \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

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.

curl -X PUT https://localhost:20128/api/settings/compression/mcp-accessibility \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

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.

curl https://localhost:20128/api/settings/payload-rules \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

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.

curl -X PUT https://localhost:20128/api/settings/payload-rules \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

GET /api/settings/combo-defaults

Get combo default settings

curl https://localhost:20128/api/settings/combo-defaults \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

GET /api/settings/proxy

Get proxy settings

curl https://localhost:20128/api/settings/proxy \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

PATCH /api/settings/proxy

Update proxy settings

curl -X PATCH https://localhost:20128/api/settings/proxy \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

POST /api/settings/proxy/test

Test proxy connection

curl -X POST https://localhost:20128/api/settings/proxy/test \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

POST /api/settings/require-login

Toggle login requirement

curl -X POST https://localhost:20128/api/settings/require-login \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

GET /api/settings/ip-filter

Get IP filter configuration

Returns the current IP filter settings including blacklist, whitelist, and temp bans.

curl https://localhost:20128/api/settings/ip-filter \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

PUT /api/settings/ip-filter

Update IP filter configuration

Configure IP filtering with blacklist/whitelist modes, add/remove individual IPs, and manage temp bans.

curl -X PUT https://localhost:20128/api/settings/ip-filter \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

GET /api/settings/system-prompt

Get system prompt configuration

Returns the current system prompt injection settings.

curl https://localhost:20128/api/settings/system-prompt \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

PUT /api/settings/system-prompt

Update system prompt configuration

curl -X PUT https://localhost:20128/api/settings/system-prompt \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

GET /api/settings/thinking-budget

Get thinking budget configuration

Returns the current thinking/reasoning budget settings for AI models.

curl https://localhost:20128/api/settings/thinking-budget \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

PUT /api/settings/thinking-budget

Update thinking budget configuration

curl -X PUT https://localhost:20128/api/settings/thinking-budget \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

GET /api/tags

List Ollama-compatible model tags

Returns models in Ollama /api/tags format for Ollama client compatibility

curl https://localhost:20128/api/tags \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

GET /api/settings/quota-store

Get current quota store driver settings

Redis URL is masked in the response (shows only scheme+host).

curl https://localhost:20128/api/settings/quota-store \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"

PUT /api/settings/quota-store

Update quota store driver settings

curl -X PUT https://localhost:20128/api/settings/quota-store \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

POST /api/settings/purge-usage-history

Purge usage history

Dashboard-only. Purges stored usage-history records.

curl -X POST https://localhost:20128/api/settings/purge-usage-history \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN"
  -H "Content-Type: application/json" \
  -d '{}'

Payloads

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

GET /api/settings/thinking-budget — behavior

Returns proxy-level thinking/reasoning request rewrite settings:

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

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

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.