Structs§
- Agent
Checkpointing Config - Agent
Codex AppServer Config - Agent
Config - Agent-wide configuration
- Agent
Harness Config - Agent
Onboarding Config - Agent
Prompt Suggestions Config - Inline prompt suggestion configuration for the chat composer.
- Agent
Small Model Config - Small/lightweight model configuration for efficient operations
- Agent
Vibe Coding Config - Vibe coding configuration for lazy/vague request support
- Async
Approval Config - Configuration for async (out-of-band) approval of tool execution requests.
- Circuit
Breaker Config - Confidence
Escalation Config - Implements the escalation decision rule from “The Hitchhiker’s Guide to Agentic AI” (Eq. 18.12): Escalate iff p_success < tau_conf OR action in A_irreversible OR cost > B_auto
- Memories
Config - Codex-compatible memories configuration.
- Open
Responses Config - Open Responses specification compliance configuration
- Persistent
Memory Config - Skeptic
Panel Config - Configuration for the adversarial multi-model evaluator panel.
- Tool
Result Clearing Config - Tracker
Continuation Config - Tracker-aware auto-continuation policy.
- Verification
Auto Recovery Config - Autonomous recovery policy for the anti-blind-editing verification gate.
Enums§
- Context
Reset Mode - When to trigger a context reset — starting a clean session from external artifacts only, discarding conversation history to clear noise and bad assumptions. This is distinct from compaction, which preserves conversational continuity within the same task/agent loop.
- Continuation
Policy - Harness
Orchestration Mode