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
Live commands emit related but different preflight reports. Their passed
flags and caller-supplied counters are not independently trustworthy. Before a
native collector or execution gate can be shared, Needle needs one bounded
artifact schema and a pure verifier that performs no process launch.
Outcome
Define canonical expectation, observed-evidence, artifact, and
verification-result contracts for provider preflight. Add an offline verifier
that recomputes identity and rejects drift, unsafe bounds, or any observed
provider model turn. Native transport collection is a separate dependent issue.
Scope
Define versioned bounded schemas with unknown-field rejection.
Run focused schema, canonicalization, verifier, event-counter, compatibility,
freshness, path, budget, and adversarial fixture tests. All validation is
process-free and provider-free.
Context
Live commands emit related but different preflight reports. Their
passedflags and caller-supplied counters are not independently trustworthy. Before a
native collector or execution gate can be shared, Needle needs one bounded
artifact schema and a pure verifier that performs no process launch.
Outcome
Define canonical expectation, observed-evidence, artifact, and
verification-result contracts for provider preflight. Add an offline verifier
that recomputes identity and rejects drift, unsafe bounds, or any observed
provider model turn. Native transport collection is a separate dependent issue.
Scope
compatibility fixture, model/reasoning/tier, pricing, execution limits,
output-root identity/containment, estimated budget, cleanup, and observed
transport evidence.
events; never trust summary counters or a
passedfield.current expectation and emits a canonical verification digest.
material, raw secret paths, unbounded diagnostics, and unknown fields.
pricing/limit mismatch, unsafe root, counter mismatch, non-zero provider
events, expiry, and cleanup failure.
Non-goals
recording approval, migrating commands, or authorizing spend.
evidence by itself.
Acceptance criteria
observed events, and current expectation.
bounds, path identity, and cost inputs instead of trusting summaries.
incompatible fixture, or cleanup failure rejects the artifact.
sealed material, or raw secret paths.
changes approval state or launches a process.
Starting points
crates/needle-platform-codex/src/worker.rstransport report shapescrates/needle-platform-codex/src/app_server.rscompatibility validationcrates/needle-app/src/worker_live_diagnostic.rsexisting report shapecrates/needle-app/src/minimal_live_pilot.rsexisting budget/binding shapedocs/SECURITY_AND_APPROVALS.mdValidation
Run focused schema, canonicalization, verifier, event-counter, compatibility,
freshness, path, budget, and adversarial fixture tests. All validation is
process-free and provider-free.