openai_web_search_dispatch
Web search filter for model-driven web_search_call dispatch.
Versions marked “overview” do not contain this page. Selecting one opens that version’s documentation overview.
On this page
Web search filter for model-driven web_search_call dispatch.
Configuration Notes
Detects pending web search calls in the response phase and executes them on re-entry via the iterative_request_router agentic loop.
Each provider request is executed through the shared filtered-subrequest executor, which enforces destination authority, DNS/SSRF, TLS/SNI, and Host centrally. An optional outbound_chain runs operator-managed cross-cutting filters (headers, credentials, logging) on the callout; when omitted it defaults to an empty inline chain (pure passthrough), so the central protections still apply.
Configuration
| Field | Type | Required | Description |
|---|---|---|---|
provider | brave | tavily | you | yes | Search backend provider. |
user_credential | string | no | Optional callout-credential slot id (see [WebSearchFilterConfig::user_credential]). |
api_key | CredentialSource | yes | API key credential source for the search provider: exactly one of value, env_var, or file; see [CredentialSource]. |
default_context_size | string | no | Default search context size when the client omits it. |
timeout_ms | integer | no | Callout timeout in milliseconds. Inside an iterative request router, the effective timeout is capped by the router’s remaining deadline. |
max_calls_per_round | integer | no | Hard cap on web-search calls processed from one model response (1..=1024; default: 32). |
base_url | string | no | Override the provider’s default API base URL. |
outbound_chain | string | object | no | Outbound filter chain the provider callout executes through. See [WebSearchFilterConfig::outbound_chain]; the two configs stay in sync. Optional — when omitted it defaults to an empty inline passthrough chain via [default_outbound_chain]. |
Examples
Example 1
filter: openai_web_search_dispatch
provider: brave
api_key:
env_var: WEB_SEARCH_API_KEY
Example 2
filter: openai_web_search_dispatch
provider: brave
api_key:
env_var: WEB_SEARCH_API_KEY
outbound_chain: web_search_outbound
default_context_size: medium
timeout_ms: 10000
max_calls_per_round: 32