feat(autonomy): first flight - one real iteration against live Docker (P2) - #303
Merged
Conversation
…Docker The acceptance step recorded as outstanding in docs/certification-evidence.md: the loop has never run against a live container engine. This spike is that flight, deliberately OUTSIDE Nexo.sln and every CI gate - its output is a run recorded in the evidence doc, not a shipped artifact. Program.cs composes AddCertificationGate + AddNexoAutonomy exactly the way a host would (ValidateOnBuild/ValidateScopes), hand-authors a Triage objective, projects it to a ProposalIterationContext in the host glue (the one place BackgroundAgents and Infrastructure types may meet), and runs ONE iteration: tier classification, attested sandbox session, the real certification chain, autonomous Tier-0 swap, three post-swap executions clearing the watch window, and the digest render. The SandboxSpec carries no mounts, deliberately: sessions are SIBLING containers on the host daemon (docker.sock pass-through), so container-local paths would be meaningless - and the session's certified role today is provisioning attestation only. Mount handling gets proven when build/test move in-container, not smuggled in here untested. --dry swaps in the TestKit fake runner (same wiring, no daemon) and asserts zero leaked sessions. run-first-flight.ps1 mirrors test-in-container.ps1 (Smart App Control blocks fresh host DLLs) plus the docker.sock mount and a static docker CLI fetch. The spike includes build/GlobalUsings.DomainBrick.cs directly because spikes/ has no Directory.Build.props tree to inject it. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…engine The acceptance step is no longer outstanding. One real iteration flew from commit 1afac86: Triage objective -> Tier0Autonomous -> attested session on the live daemon (alpine:3.20 @ sha256:d9e853e8..., engine 29.7.2, effective caps verified) -> full certification chain ADMIT (signed, escape_rate=0, all five inputs recorded) -> autonomous Tier-0 swap as generation 1 in 4.4s -> 3/3 post-swap invocations clearing the watch window -> digest. Zero nexo-session-* containers left on the host daemon afterwards. The --dry leg (fake runner, same wiring) passed with an explicit zero-leaked-sessions assertion. Known limitation 5 is rewritten to what actually remains: the loop has still never admitted a MODEL-produced candidate - the flight brick was hand-authored to the gate-teeth shape. Limitation 4 (session attests, does not contain) is unchanged by the flight and the section says so. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Contributor
Bugbot is not enabled for your account, so this pull request was not reviewed. Enable Bugbot in the Cursor dashboard to get automatic reviews on future PRs. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Phase 2 of the post-merge plan: the first flight — one real autonomy iteration, end to end, against a live container engine. This is the acceptance step
docs/certification-evidence.mdrecords as outstanding ("the loop has never run against a live container engine or a real proposer's output").Stacked on #291 (P0 honesty docs + P1
AddNexoAutonomy), because the flight is the first consumer ofAddNexoAutonomy.What flies
spikes/autonomy-first-flight/— deliberately outsideNexo.slnand every CI gate. Its deliverable is a recorded run in the evidence doc, not a shipped artifact (same contract as the existingspikes/precedent).One iteration, composed exactly the way a host would (
AddCertificationGate+AddNexoAutonomy,ValidateOnBuild/ValidateScopes):ObjectiveTierClassifier→ Tier 0AutonomousAdmission)ExecuteAsyncinvocations clearing the watch windowAutonomyDigest.Renderover the collected swap provenance--dryswaps in the TestKit fake session runner (same wiring, no daemon) and asserts zero leaked sessions.Design decisions worth reading
/var/run/docker.sockmounted through, so sessions it starts are siblings on the host daemon. Container-local paths would be meaningless to that daemon — which is why the flight'sSandboxSpeccarries no mounts. That is also the honest shape: the session's certified role today is provisioning attestation. Mount-path handling gets proven when build/test move in-container (Phase 3), not smuggled in here untested.run-first-flight.ps1mirrorsscripts/test-in-container.ps1(clone from read-only mirror; Smart App Control blocks fresh host DLLs) plus the socket mount and a static docker CLI fetch.ObjectiveDocument; the host is where they meet, and the spike is the host.Flight record
Recorded in
docs/certification-evidence.md(this PR): dry run and real run, both PASS — outcomeAdmittedAndSwapped, real attestation values from the live daemon, certificate inputs includingsession-attestationandsession-environment, digest output.Testing
alpine:3.20session): PASSmake kernel-coverage-gate— n/a paths (spike + docs only), runs in CI regardless🤖 Generated with Claude Code