Proposal: Codex-native evidence-driven semantic escalation for dynamic multi-agent graphs

Evidence-driven decisions in native agent graphs

Update, 2026-09-05: this experiment produced the Slopdex source and Windows CLI preview. The release update summarizes what shipped. A separate semantic-escalation mechanism remains unvalidated; in field runs, the current owner made these decisions.

The original question: when execution reveals that an agent's task is failing or incorrectly scoped, who should resolve it next?

Depending on the evidence, the useful action may be to retry locally, change model, return the problem to its parent, split or replan the subtree, or abort. Choosing a stronger model does not repair a wrong task boundary.

Codex already supplied much of the substrate at the audited upstream snapshot: recursive spawn and lineage, bounded child contexts, model/effort selection, parent-directed completion, and resource limits.

The proposed experiment was a compact handoff containing the task contract, ownership chain, attempts, relevant failure evidence and remaining budget. The owner or a temporary child would choose the next action using existing graph primitives. Compare that policy with local retries and automatic tier-ups, measuring recovery, rework and cost where observable. That comparison has not been completed.

Models interpret evidence and revise the workflow. Runtime enforces identity, permissions, budgets, cancellation and delivery. A permanent escalation agent or fixed pipeline is unnecessary unless experiments demonstrate a need.

Questions for maintainers:

1. Is the current owner the intended place for evidence-driven replanning?
2. Which native attempt/receipt surface should carry a compact failure handoff?
3. Which planned lifecycle or backend capabilities would make local work redundant?

Related: #34278 and #32705 for model routing; #15723 for completion delivery and owner wake.

Read codex-rs/core/src/tools/handlers/multi_agents_v2/spawn.rs and codex-rs/core/src/tools/handlers/multi_agents_common.rs at the audited snapshot first, tracing the existing spawn, lineage, model/effort, completion, and resource-limit paths. Evaluate the proposed handoff against local retries and automatic tier-ups, measuring recovery, rework, and cost; done means producing validated results that answer the three maintainer questions. No test command is named.