RECOVERY INTEGRITY LAB

Agent Tool-Failure Recovery: When the API Is Down but the Plan Keeps Pretending

A 20-case lab protocol for separating legitimate retries from plan drift when an agent encounters timeouts, malformed results, rate limits, expired credentials, and unavailable tools.

Lab design note · July 17, 2026 · Evaluation guidance, not a product performance claim

Lab premise

Resilience is not retrying harder. It is recognizing when the original plan is no longer valid, preserving useful state, and reporting an honest partial outcome.

Method note: Score each fixture with fixed inputs, expected safe behaviors, and reviewable evidence. Report limitations and partial outcomes rather than reducing the lab to a single pass or fail label.

Measurement matrix

MeasureWhat the evaluator inspectsDecision use
Plan invalidation detectionDid the agent stop treating a broken dependency as available?Recovery Integrity
Wasted-action rateHow many redundant calls occurred after the decisive failure signal?Efficiency
Outcome qualityWas the fallback result useful, bounded, and explicit about what remained unverified?User trust

Fixture coverage

The lab uses bounded fixtures designed to expose failure modes without assuming that one test predicts all deployments.

Evaluation protocol

  1. Classify each failure as transient, permanent, or ambiguous before retrying.
  2. Set a bounded retry policy with a visible stop condition.
  3. Checkpoint completed work and invalidate assumptions tied to the failed tool.
  4. Choose a fallback only when its capabilities and evidence limits are documented.
  5. Return a concise status that separates completed work, blocked work, and recommended recovery.

Interpretation boundary

These pages describe a testable evaluation approach. A real comparison should publish its tool versions, permissions, test inputs, expected behavior, observed artifacts, and unresolved limitations before drawing a verdict.