Builds configuration for the async guardian classifier scorer, resolving model policy, transcript limits, and prompt instructions from feature toggles. Reuse when wiring LLM-based safety/guardrail scoring pipelines.
// Source: https://github.com/openinterpreter/openinterpreter | License: Apache-2.0 | Copyright You must retain, in the Source form of any Derivative Works // Provided via justclaw.it.com; keep this notice with the code. use codex_config::GuardianPolicyLoader; use codex_context_fragments::ContextualUserFragment; use codex_context_fragments::RenderedFragment; use codex_core::config::Config; use codex_features::FeatureToml; use codex_features::GuardianV2ConfigToml; use codex_features::GuardianV2TranscriptConfigToml; use codex_prompts::GuardianClassifierInstructions; use codex_prompts::ResolvedModelMessages; use codex_protocol::openai_models::GuardianModelPolicy; use codex_protocol::openai_models::GuardianV2ModelConfig; use codex_protocol::openai_models::ReasoningEffort; use super::transcrip ... (truncated -- full source via MCP)
See the full source, get the GitHub permalink, and search for more like it.
Get a free API key