AI infrastructure

Deterministic, budgeted model-escalation policy

Tested in CILabPersonal labboundedcode-escalation-policy

Claim

Whether a task escalates from the local model to a frontier model is decided by deterministic rules: routine tasks stay local, repeated failures and high-risk changes escalate, a call budget caps escalation, and an explicit user request overrides the budget.

Status

tested: An automated test in CI asserts the claimed behaviour, including a failure case where relevant, and passes at the verified commit.
lab: Local machine, local clusters or CI runners.
personal lab: My own public repositories.

Verified commit

repository: akynte/boundedcode
release: v0.1.0-alpha.3
commit: be1aa9f87ec5ea92567d29c48bf1982ce018c227
committed: 8 October 2026
CI: ci.yml #37773301609 success at be1aa9f

Curated source: paths, test names and the CI conclusion were checked against this commit by the evidence sync.

Implementation

Evidence

Testinternal/frontier/frontier_test.go (GitHub, pinned to commit)
Asserted by TestEvaluate, TestPacketRewritesHostPaths
Testinternal/orchestrator/runner_test.go (GitHub, pinned to commit)
Asserted by TestRunFailEscalateCrashResumeAndComplete
ADRADR-0009: Frontier escalation through the Codex CLI subscription (GitHub, pinned to commit)
CI runci.yml run 37773301609 (GitHub, pinned to commit)
success

Environment

ci runner: GitHub-hosted ubuntu
go: 1.27.1

Limitations

The frontier model is faked in CI; the policy is tested, its usefulness is not.
In the held-out validation, escalation was enabled but never triggered.

That frontier escalation improves task outcomes: NOT VERIFIED.

Appears in

BoundedCode

Related claims

Tested in CILab

Token-budgeted context packs

The context-pack builder keeps its estimated token count within the configured budget, truncating sections when inputs exceed it, and renders the same pack for the same inputs.

AI infrastructureboundedcode v0.1.0-alpha.31 test file, 3 artifactsEvidence