AI infrastructure

Token-budgeted context packs

Tested in CILabPersonal labboundedcode-bounded-context

Claim

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.

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

Codeinternal/contextplan/plan.go (GitHub, pinned to commit)

Evidence

Testinternal/contextplan/plan_test.go (GitHub, pinned to commit)
Asserted by TestBudgetEnforced
CI runci.yml run 37773301609 (GitHub, pinned to commit)
success

Environment

ci runner: GitHub-hosted ubuntu
default budget tokens: 24000
go: 1.27.1

Limitations

Token counts are a byte-based estimate, not the model tokenizer's count.
The budget bounds the initial pack; the agent can read more code through tools.

Appears in

BoundedCode

Related claims

Tested in CILab

Deterministic, budgeted model-escalation policy

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.

AI infrastructureboundedcode v0.1.0-alpha.32 test files, 6 artifactsEvidence