# ol.llx.ai _platforms: clj, cljs_ ## default-env ### clj _platforms: clj_ ```clojure (default-env) ``` Returns the default environment for your platform. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L12-L17) ### cljs _platforms: cljs_ ```clojure (default-env) ``` Returns the default environment for your platform. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L12-L17) --- ## complete* ### clj _platforms: clj_ ```clojure (complete* env model context opts) ``` Runs one non-streaming assistant turn using provider-style options. Use `complete*` when you need provider-level control and adapter-specific options. This is the provider path. `opts` is validated against `:ol.llx/provider-request-options` in `src/ol/llx/ai/impl/schema/options.cljc`. Adapter `build-request` boundaries also validate adapter-specific schemas: `:ol.llx/openai-completions-provider-options`, `:ol.llx/openai-responses-provider-options`, `:ol.llx/anthropic-provider-options`, and `:ol.llx/google-provider-options`. Common provider option keys: | | | | --- | --- | | key | description | | `:max-output-tokens` | Requested output token cap. | | `:temperature` | Sampling temperature. | | `:top-p` | Nucleus sampling probability. | | `:reasoning` | Provider reasoning map (shape depends on adapter). | | `:session-id` | Optional session identifier for provider-side caching/routing. | | `:api-key` | Provider API key override for this call. | | `:headers` | Additional provider request headers. | | `:signal` | Abort/cancel signal forwarded to runtime/provider layer. | | `:max-retry-delay-ms` | Optional cap for server-requested retry delays. | | `:metadata` | Request metadata map forwarded to adapter payload builders. | | `:registry` | Per-call adapter registry override. | | `:max-retries` | Retry count for transient failures (default `2`). | Returns a promise that resolves to one canonical assistant message map. Errors reject the promise with structured LLX exception data. Use [`complete`](#complete) for the unified API. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L19-L56) ### cljs _platforms: cljs_ ```clojure (complete* env model context opts) ``` Runs one non-streaming assistant turn using provider-style options. Use `complete*` when you need provider-level control and adapter-specific options. This is the provider path. `opts` is validated against `:ol.llx/provider-request-options` in `src/ol/llx/ai/impl/schema/options.cljc`. Adapter `build-request` boundaries also validate adapter-specific schemas: `:ol.llx/openai-completions-provider-options`, `:ol.llx/openai-responses-provider-options`, `:ol.llx/anthropic-provider-options`, and `:ol.llx/google-provider-options`. Common provider option keys: | | | | --- | --- | | key | description | | `:max-output-tokens` | Requested output token cap. | | `:temperature` | Sampling temperature. | | `:top-p` | Nucleus sampling probability. | | `:reasoning` | Provider reasoning map (shape depends on adapter). | | `:session-id` | Optional session identifier for provider-side caching/routing. | | `:api-key` | Provider API key override for this call. | | `:headers` | Additional provider request headers. | | `:signal` | Abort/cancel signal forwarded to runtime/provider layer. | | `:max-retry-delay-ms` | Optional cap for server-requested retry delays. | | `:metadata` | Request metadata map forwarded to adapter payload builders. | | `:registry` | Per-call adapter registry override. | | `:max-retries` | Retry count for transient failures (default `2`). | Returns a promise that resolves to one canonical assistant message map. Errors reject the promise with structured LLX exception data. Use [`complete`](#complete) for the unified API. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L19-L56) --- ## stream* ### clj _platforms: clj_ ```clojure (stream* env model context opts) ``` Runs one streaming assistant turn using provider-style options. Use `stream*` when you need provider-level control and adapter-specific options. This is the provider path. `opts` is validated against `:ol.llx/provider-request-options` in `src/ol/llx/ai/impl/schema/options.cljc`, and adapter-specific schemas are enforced at each adapter `build-request` boundary. Common provider option keys: | | | | --- | --- | | key | description | | `:max-output-tokens` | Requested output token cap. | | `:temperature` | Sampling temperature. | | `:top-p` | Nucleus sampling probability. | | `:reasoning` | Provider reasoning map (shape depends on adapter). | | `:session-id` | Optional session identifier for provider-side caching/routing. | | `:api-key` | Provider API key override for this call. | | `:headers` | Additional provider request headers. | | `:signal` | Abort/cancel signal forwarded to runtime/provider layer. | | `:max-retry-delay-ms` | Optional cap for server-requested retry delays. | | `:metadata` | Request metadata map forwarded to adapter payload builders. | | `:registry` | Per-call adapter registry override. | | `:max-retries` | Retry count for transient failures (default `2`). | Returns a Promesa CSP channel emitting canonical LLX event maps. Stream completion emits terminal `:done` or `:error` and closes the channel. Consumer cancellation is channel closure. Use [`stream`](#stream) for the unified API. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L58-L91) ### cljs _platforms: cljs_ ```clojure (stream* env model context opts) ``` Runs one streaming assistant turn using provider-style options. Use `stream*` when you need provider-level control and adapter-specific options. This is the provider path. `opts` is validated against `:ol.llx/provider-request-options` in `src/ol/llx/ai/impl/schema/options.cljc`, and adapter-specific schemas are enforced at each adapter `build-request` boundary. Common provider option keys: | | | | --- | --- | | key | description | | `:max-output-tokens` | Requested output token cap. | | `:temperature` | Sampling temperature. | | `:top-p` | Nucleus sampling probability. | | `:reasoning` | Provider reasoning map (shape depends on adapter). | | `:session-id` | Optional session identifier for provider-side caching/routing. | | `:api-key` | Provider API key override for this call. | | `:headers` | Additional provider request headers. | | `:signal` | Abort/cancel signal forwarded to runtime/provider layer. | | `:max-retry-delay-ms` | Optional cap for server-requested retry delays. | | `:metadata` | Request metadata map forwarded to adapter payload builders. | | `:registry` | Per-call adapter registry override. | | `:max-retries` | Retry count for transient failures (default `2`). | Returns a Promesa CSP channel emitting canonical LLX event maps. Stream completion emits terminal `:done` or `:error` and closes the channel. Consumer cancellation is channel closure. Use [`stream`](#stream) for the unified API. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L58-L91) --- ## complete ### clj _platforms: clj_ ```clojure (complete env model context unified-opts) ``` Runs one non-streaming assistant turn using the unified options API. This is the unified path and is recommended for most callers. `opts` is validated against `:ol.llx/unified-request-options` in `src/ol/llx/ai/impl/schema/options.cljc`. Unified options are normalized and forwarded to provider adapters. For example: - `:max-tokens` -> provider `:max-output-tokens` - `:reasoning` / `:reasoning-effort` -> provider reasoning shape Unified option keys: | | | | --- | --- | | key | description | | `:max-tokens` | Requested output cap. Defaults to `min(model.max-tokens, 32000)`. | | `:temperature` | Sampling temperature. | | `:top-p` | Nucleus sampling probability. | | `:reasoning` | Reasoning level keyword (`:minimal` `:low` `:medium` `:high` `:xhigh`). | | `:reasoning-effort` | Alias for `:reasoning`. | | `:session-id` | Optional session identifier for provider-side caching/routing. | | `:thinking-budgets` | Optional token budgets per reasoning level (provider-dependent). | | `:api-key` | Provider API key override for this call. | | `:headers` | Additional provider request headers. | | `:signal` | Abort/cancel signal forwarded to runtime/provider layer. | | `:max-retry-delay-ms` | Optional cap for server-requested retry delays. | | `:metadata` | Request metadata map forwarded to adapter payload builders. | | `:registry` | Per-call adapter registry override. | Returns a promise that resolves to one canonical assistant message map. Errors reject the promise with structured LLX exception data. Use [`complete*`](#complete*) if you need provider-specific options that are outside the unified schema. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L93-L129) ### cljs _platforms: cljs_ ```clojure (complete env model context unified-opts) ``` Runs one non-streaming assistant turn using the unified options API. This is the unified path and is recommended for most callers. `opts` is validated against `:ol.llx/unified-request-options` in `src/ol/llx/ai/impl/schema/options.cljc`. Unified options are normalized and forwarded to provider adapters. For example: - `:max-tokens` -> provider `:max-output-tokens` - `:reasoning` / `:reasoning-effort` -> provider reasoning shape Unified option keys: | | | | --- | --- | | key | description | | `:max-tokens` | Requested output cap. Defaults to `min(model.max-tokens, 32000)`. | | `:temperature` | Sampling temperature. | | `:top-p` | Nucleus sampling probability. | | `:reasoning` | Reasoning level keyword (`:minimal` `:low` `:medium` `:high` `:xhigh`). | | `:reasoning-effort` | Alias for `:reasoning`. | | `:session-id` | Optional session identifier for provider-side caching/routing. | | `:thinking-budgets` | Optional token budgets per reasoning level (provider-dependent). | | `:api-key` | Provider API key override for this call. | | `:headers` | Additional provider request headers. | | `:signal` | Abort/cancel signal forwarded to runtime/provider layer. | | `:max-retry-delay-ms` | Optional cap for server-requested retry delays. | | `:metadata` | Request metadata map forwarded to adapter payload builders. | | `:registry` | Per-call adapter registry override. | Returns a promise that resolves to one canonical assistant message map. Errors reject the promise with structured LLX exception data. Use [`complete*`](#complete*) if you need provider-specific options that are outside the unified schema. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L93-L129) --- ## stream ### clj _platforms: clj_ ```clojure (stream env model context unified-opts) ``` Runs one streaming assistant turn using the unified options API. This is the unified path and is recommended for most callers. `opts` is validated against `:ol.llx/unified-request-options` in `src/ol/llx/ai/impl/schema/options.cljc`. Unified option keys: | | | | --- | --- | | key | description | | `:max-tokens` | Requested output cap. Defaults to `min(model.max-tokens, 32000)`. | | `:temperature` | Sampling temperature. | | `:top-p` | Nucleus sampling probability. | | `:reasoning` | Reasoning level keyword (`:minimal` `:low` `:medium` `:high` `:xhigh`). | | `:reasoning-effort` | Alias for `:reasoning`. | | `:session-id` | Optional session identifier for provider-side caching/routing. | | `:thinking-budgets` | Optional token budgets per reasoning level (provider-dependent). | | `:api-key` | Provider API key override for this call. | | `:headers` | Additional provider request headers. | | `:signal` | Abort/cancel signal forwarded to runtime/provider layer. | | `:max-retry-delay-ms` | Optional cap for server-requested retry delays. | | `:metadata` | Request metadata map forwarded to adapter payload builders. | | `:registry` | Per-call adapter registry override. | Returns a Promesa CSP channel emitting canonical LLX event maps. Stream completion emits terminal `:done` or `:error` and closes the channel. Consumer cancellation is channel closure. Use [`stream*`](#stream*) for provider-specific option control. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L131-L162) ### cljs _platforms: cljs_ ```clojure (stream env model context unified-opts) ``` Runs one streaming assistant turn using the unified options API. This is the unified path and is recommended for most callers. `opts` is validated against `:ol.llx/unified-request-options` in `src/ol/llx/ai/impl/schema/options.cljc`. Unified option keys: | | | | --- | --- | | key | description | | `:max-tokens` | Requested output cap. Defaults to `min(model.max-tokens, 32000)`. | | `:temperature` | Sampling temperature. | | `:top-p` | Nucleus sampling probability. | | `:reasoning` | Reasoning level keyword (`:minimal` `:low` `:medium` `:high` `:xhigh`). | | `:reasoning-effort` | Alias for `:reasoning`. | | `:session-id` | Optional session identifier for provider-side caching/routing. | | `:thinking-budgets` | Optional token budgets per reasoning level (provider-dependent). | | `:api-key` | Provider API key override for this call. | | `:headers` | Additional provider request headers. | | `:signal` | Abort/cancel signal forwarded to runtime/provider layer. | | `:max-retry-delay-ms` | Optional cap for server-requested retry delays. | | `:metadata` | Request metadata map forwarded to adapter payload builders. | | `:registry` | Per-call adapter registry override. | Returns a Promesa CSP channel emitting canonical LLX event maps. Stream completion emits terminal `:done` or `:error` and closes the channel. Consumer cancellation is channel closure. Use [`stream*`](#stream*) for provider-specific option control. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L131-L162) --- ## get-model ### clj _platforms: clj_ ```clojure (get-model provider model-id) ``` Returns the model definition for `provider` and `model-id`, or `nil` when absent. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L164-L167) ### cljs _platforms: cljs_ ```clojure (get-model provider model-id) ``` Returns the model definition for `provider` and `model-id`, or `nil` when absent. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L164-L167) --- ## get-models ### clj _platforms: clj_ ```clojure (get-models provider) ``` Returns all models for `provider` as a deterministic vector sorted by `:id`. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L169-L172) ### cljs _platforms: cljs_ ```clojure (get-models provider) ``` Returns all models for `provider` as a deterministic vector sorted by `:id`. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L169-L172) --- ## get-providers ### clj _platforms: clj_ ```clojure (get-providers) ``` Returns supported providers as a deterministic sorted vector. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L174-L177) ### cljs _platforms: cljs_ ```clojure (get-providers) ``` Returns supported providers as a deterministic sorted vector. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L174-L177) --- ## calculate-cost ### clj _platforms: clj_ ```clojure (calculate-cost model usage) ``` Calculates usage cost totals from `model` pricing and `usage` token counts. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L179-L182) ### cljs _platforms: cljs_ ```clojure (calculate-cost model usage) ``` Calculates usage cost totals from `model` pricing and `usage` token counts. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L179-L182) --- ## supports-xhigh? ### clj _platforms: clj_ ```clojure (supports-xhigh? model) ``` Returns true when `model` supports `:xhigh` reasoning effort. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L184-L187) ### cljs _platforms: cljs_ ```clojure (supports-xhigh? model) ``` Returns true when `model` supports `:xhigh` reasoning effort. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L184-L187) --- ## models-equal? ### clj _platforms: clj_ ```clojure (models-equal? a b) ``` Returns true when two model maps refer to the same `:provider` and `:id`. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L189-L192) ### cljs _platforms: cljs_ ```clojure (models-equal? a b) ``` Returns true when two model maps refer to the same `:provider` and `:id`. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L189-L192) --- ## validate-tool-call ### clj _platforms: clj_ ```clojure (validate-tool-call tools tool-call) ``` Validates a `tool-call` entry against matching tool definitions in `tools`. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L194-L197) ### cljs _platforms: cljs_ ```clojure (validate-tool-call tools tool-call) ``` Validates a `tool-call` entry against matching tool definitions in `tools`. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L194-L197) --- ## context-overflow? ### clj _platforms: clj_ ```clojure (context-overflow? assistant-message) (context-overflow? assistant-message context-window) ``` Returns true when the input matches known context-window overflow patterns. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L199-L204) ### cljs _platforms: cljs_ ```clojure (context-overflow? assistant-message) (context-overflow? assistant-message context-window) ``` Returns true when the input matches known context-window overflow patterns. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L199-L204) --- ## sanitize-surrogates ### clj _platforms: clj_ ```clojure (sanitize-surrogates text) ``` Removes unpaired surrogate code units while preserving valid Unicode pairs. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L206-L209) ### cljs _platforms: cljs_ ```clojure (sanitize-surrogates text) ``` Removes unpaired surrogate code units while preserving valid Unicode pairs. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L206-L209) --- ## schema-regsitry ### clj _platforms: clj_ ```clojure (schema-regsitry) ``` Returns the full LLX schema registry map. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L211-L214) ### cljs _platforms: cljs_ ```clojure (schema-regsitry) ``` Returns the full LLX schema registry map. [source,window=_blank](https://github.com/outskirtslabs/llx/blob/main/src/ol/llx/ai.cljc#L211-L214)