You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Issues #6 and #7 already provide the answer-free v4 corpus, PowerPlan, exact
schedule, bounded ArmLaunch, and final-gate identity. The missing broker
contract can be implemented and tested without a native provider. Keeping the
native Codex adapter separate makes this slice assignable without credentials,
budget authority, or sealed material.
Outcome
Add an offline broker that validates one ArmLaunch, verifies a caller-provided
pinned source checkout, invokes an injected arm executor, and records one
immutable bounded ArmExecutionResult. Provide a deterministic simulator for
every arm and failure class.
Scope
Define canonical broker request/result identity from manifest, schedule,
PowerPlan, task, route, split, arm, repetition, pair seed, source, execution
policy, model policy, and pricing commitments.
Accept only ArmLaunch plus bounded public execution policy; forbidden
evaluator fields must be unrepresentable.
Verify the caller-provided checkout SHA and copy/materialize only a disposable
local snapshot; perform no network clone.
Invoke an injected executor with bounded turns, workers, retries, time, output,
and accounting.
Persist one immutable result or explicit failure per launch identity,
including bounded response bytes/digest, usage, worker/discovery metrics,
process status, cancellation, and cleanup.
Run focused schedule, broker identity, immutable result, source, accounting,
cancellation, restart, and all-arm simulator tests using synthetic v4 fixtures.
No Codex installation, provider credential, or sealed bundle is required.
Context
Issues #6 and #7 already provide the answer-free v4 corpus, PowerPlan, exact
schedule, bounded
ArmLaunch, and final-gate identity. The missing brokercontract can be implemented and tested without a native provider. Keeping the
native Codex adapter separate makes this slice assignable without credentials,
budget authority, or sealed material.
Outcome
Add an offline broker that validates one
ArmLaunch, verifies a caller-providedpinned source checkout, invokes an injected arm executor, and records one
immutable bounded
ArmExecutionResult. Provide a deterministic simulator forevery arm and failure class.
Scope
PowerPlan, task, route, split, arm, repetition, pair seed, source, execution
policy, model policy, and pricing commitments.
ArmLaunchplus bounded public execution policy; forbiddenevaluator fields must be unrepresentable.
local snapshot; perform no network clone.
and accounting.
including bounded response bytes/digest, usage, worker/discovery metrics,
process status, cancellation, and cleanup.
source mismatch, over-budget request, and adaptive retry.
FinalArm::ALLarms and terminalresults.
Non-goals
execution, sealed bundle access, oracle evaluation, or focused evaluator argv.
FinalObservation, PowerPlan, schedule, BCa report, or a claim.Acceptance criteria
location, focused argv, evaluator result, or credential.
invocation.
the same identity; duplicates and rewrites fail closed.
drift, budget violation, and restart without a provider.
Starting points
crates/needle-bench/src/schedule.rscrates/needle-bench/src/final_gate.rscrates/needle-platform-codex/src/bin/needle-sim-codex.rsdocs/BENCHMARKING.mdValidation
Run focused schedule, broker identity, immutable result, source, accounting,
cancellation, restart, and all-arm simulator tests using synthetic v4 fixtures.
No Codex installation, provider credential, or sealed bundle is required.