Skip to content

fix(minvmd): withdraw a renamed own_ip box's row by its box id - #3172

Merged
bryan-minimal merged 3 commits into
mainfrom
fix/841-rename-own-ip-row
Nov 9, 2026
Merged

bryan-minimal merged 3 commits into
mainfrom
fix/841-rename-own-ip-row

Conversation

@bryan-minimal

@bryan-minimal bryan-minimal commented Nov 9, 2026 •

Copy link
Copy Markdown
Member

Part of gominimal/inbox#1116 (teardown); the rename half follows.

The bug

After min session rename, destroying an own_ip box left its row on the VM host for good:

  • the ingress forward stayed up, because it follows the row;
  • the old name kept answering the box's address (127.0.64.3), because the answerer releases an address only on a withdrawal;
  • an activation under the old name was refused, because a live row held it.

The destroy printed the host's refusal, NotTheCreatorsRow ("the row at switch address ... is held by box "", not by the withdrawing """).

Root cause

min session rename is a RenameSession RPC to the in-VM daemon only. Nothing tells the VM host daemon, so minvmd keeps the box's row, its Creation (persisted in box-registry.json) and the answerer's published address under the name the box was registered by.

The destroy then withdrew under the session's current name with box_id: None (destroy_box in crates/minimal/src/cmd/boxes/lifecycle.rs; the same for min box rm, min box prune and the dashboard's settle_destroyed_box). BoxRegistry::withdraw_client_box compares names first, so it refused, and nothing else ever removes a creator-owned row.

The session record already carries the row's id (Record::box_id), and the resume path already finds a renamed box's creation by it (resumable_creation, resume_box_row). Only the withdrawal ignored it.

The change

Host (minvmd):

  • withdraw_client_box (now a wrapper over withdraw_client_box_held): when the request's box id is the row's own id, the id stands in for the name. The loopback check and the id check still run. A request with no id, or with another box's id, is still held to the name.
  • Dormant branch (the drainer already withdrew the row and kept the creation): the creation is looked up by box id first, then by the presented name, as a resume does. The withdrawal generation is bumped under the creation's own name.
  • withdraw_client_box_held returns the name the host held the box under. withdraw_box in control.rs releases the answerer's address under that name, not the request's (wrong after a rename), and labels the guest-audit flush with it. The info line gains asked_as.

Client (minimal):

  • destroy_box (session destroy, destroy-all), min box rm, min box prune and the dashboard destroy present record.box_id. The id goes only together with a pair (box_addresses.and(box_id)), so a host_ip box's destroy does not become a name withdrawal it never sent before.
  • The post-attach release (release_held_name_after_attach, from min session attach, activate --attach and the dashboard's attach) takes the pair and the box id read off the record before the attach. Without it, a renamed session ended through an attach was refused the same way.

Tests

  • box_registry::renamed_creator_withdraws_its_row_by_box_id: under the new name, a withdrawal without the id is refused, and so is one with another box's id. With the row's own id the row goes, the old name is returned, the creation ends and the old name registers a new box.
  • box_registry::renamed_creator_ends_its_dormant_creation_by_box_id: the dormant case, by id and without.
  • control::a_renamed_box_is_withdrawn_by_its_id_and_released_by_its_old_name: over the control socket, the answerer's release goes by the old name.
  • vm_host::a_destroy_withdraws_its_row_by_pair_and_box_id and vm_host::a_destroy_with_a_box_id_but_no_pair_withdraws_nothing drive destroy_box against a stand-in VM host control server.
  • vm_host::an_attach_that_ends_with_the_session_gone_withdraws_its_row and dash::rpc::tui_destroy_withdraws_box_row now assert the id is sent. The new fixture is listed in every_daemon_connection_is_classified.

Scope and review points

  • Teardown only. Between the rename and the destroy the VM host still publishes the box under its old name: the new name is NXDOMAIN, and minvmd's egress-gate and hostname-proxy entries stay under the old name. Moving the row at rename time is the follow-up PR.
  • Presenting the id makes the host enforce NotTheBoxId on destroys that used to go by the pair alone. The record's id is the one the resume and the in-VM row check already rely on; the autospawn re-registration path was not traced end to end.
  • The commit bodies' "(fix: document powershell in completions and add a session policy reference #1116)" means gominimal/inbox#1116.

Verification

  • prepush (CI's exact commands): green at 1cbcf5f
  • Lab: scenario 841 renames an own_ip box with a published port and destroys it, then checks that the port is closed, the old name gets no address from the VM host's answerer and an own_ip activation under the old name succeeds. x2 per distro (FAIL on the release, PASS on this branch), with 727 as the control and 790d and 723 (other own_ip / host_ip gate paths) for no change:

OK: 841-rename-own-ip-1cbcf5f9: 4 expectation(s) on ubuntu-24.04, fedora: 841-rename-destroy-own-ip-row:fail->pass 727-host-ip-egress-fail-open:pass 790d-own-ip-ingress-diagnose-vm:same 723-vm-host-ip-name-502:same

min-regress batch 841-rename-own-ip-1cbcf5f9: base rel-6a01d5ae vs the candidate cand-841-rename-own-ip-1cbcf5f9-b6ec7fdc, per distro:

  • ubuntu-24.04: 841 {'fail': 2} -> {'pass': 2}; 727 {'pass': 1} -> {'pass': 1}; 790d {'fail': 1} -> {'fail': 1}; 723 {'pass': 1} -> {'pass': 1}
  • fedora: 841 {'fail': 2} -> {'pass': 2}; 727 {'pass': 1} -> {'pass': 1}; 790d {'fail': 1} -> {'fail': 1}; 723 {'pass': 1} -> {'pass': 1}

Lab evidence (min-regress batch 841-rename-own-ip-1cbcf5f9 on the lab box, fedora, ubuntu-24.04)

Head: 1cbcf5f925da5a29f2ca43e67979ef8196d3f340 at 1cbcf5f (lab name cand-841-rename-own-ip-1cbcf5f9-b6ec7fdc). Base: rel-6a01d5ae (rel-6a01d5ae).

scenario distro base head
723-vm-host-ip-name-502: 0.7 sweep P1: in the VM, a host_ip session's name through the proxy gave 502 for a dev server on 127.0.0.1; since T138 (NET-071) that is a 403 naming the fix, and a 0.0.0.0 server must answer fedora pass pass
723-vm-host-ip-name-502: 0.7 sweep P1: in the VM, a host_ip session's name through the proxy gave 502 for a dev server on 127.0.0.1; since T138 (NET-071) that is a 403 naming the fix, and a 0.0.0.0 server must answer ubuntu-24.04 pass pass
727-host-ip-egress-fail-open: 0.7 sweep P1: on a host_ip box, declared egress is shown by session policy but never enforced (fail-open) fedora pass pass
727-host-ip-egress-fail-open: 0.7 sweep P1: on a host_ip box, declared egress is shown by session policy but never enforced (fail-open) ubuntu-24.04 pass pass
790d-own-ip-ingress-diagnose-vm: JK 072-bug.md Q11 / W1 (P1) diagnostic: on the Linux VM path every own_ip box's ingress returns empty replies fedora fail fail
790d-own-ip-ingress-diagnose-vm: JK 072-bug.md Q11 / W1 (P1) diagnostic: on the Linux VM path every own_ip box's ingress returns empty replies ubuntu-24.04 fail fail
841-rename-destroy-own-ip-row: gominimal/inbox#1116: renaming an own_ip box and destroying it leaves its VM host row, ingress forward and old name behind fedora fail, fail pass, pass
841-rename-destroy-own-ip-row: gominimal/inbox#1116: renaming an own_ip box and destroying it leaves its VM host row, ingress forward and old name behind ubuntu-24.04 fail, fail pass, pass

Fixed since base: 2. Still reproducing on both: 2. Regressed: 0. Passing on both: 4. A scenario that fails on both sides is the environment or main, not this candidate: read its evidence lines before reading it as the candidate's. A verdict links to the run's trace in Cloud Trace (project access needed); the scenario link is its source with the # issue: it reproduces.

Why each failed run failed: what the scenario measured, then what its trace recorded (error spans and warnings, most frequent first):

  • 841-rename-destroy-own-ip-row on ubuntu-24.04 (base, trace f9d4f708): scenario: destroy_warn=1 port_listening=1 old_name_answer=127.0.64.3 reactivate_rc=2 already_exists=1 destroy_rc=0 registry_names_old=1 answer_before=127.0.64.3 port_before=1; trace: 2x minimal-cli span error cmd; 1x minimal-cli span error activation_step
  • 841-rename-destroy-own-ip-row on ubuntu-24.04 (base, trace af60bd42): scenario: destroy_warn=1 port_listening=1 old_name_answer=127.0.64.3 reactivate_rc=2 already_exists=1 destroy_rc=0 registry_names_old=1 answer_before=127.0.64.3 port_before=1; trace: 2x minimal-cli span error cmd; 1x minimal-cli span error activation_step
  • 790d-own-ip-ingress-diagnose-vm on ubuntu-24.04 (base, trace fb9777c1): scenario: body_bytes=1000 curl_rc=0 cli_addr_bytes=0 cli_name_bytes=0 inbox_bytes=1060 web_ip=100.64.127.255 tcpdump=no syn=0 synack=0 rst=0; trace: 3x minimald WARN exec: ended while its command was starting; the start is ended when it returns; 1x minimald WARN the box's classifier cover fell back to an empty read-only tmpfs: the kernel refused the design's cgroup<n> mount of the box's namespace roo; 1x minimald WARN exec: ssh client disconnected; killing child
  • 790d-own-ip-ingress-diagnose-vm on ubuntu-24.04 (head, trace 84baaf07): scenario: body_bytes=1000 curl_rc=0 cli_addr_bytes=0 cli_name_bytes=0 inbox_bytes=1060 web_ip=100.64.127.255 tcpdump=no syn=0 synack=0 rst=0; trace: 3x minimald WARN exec: ended while its command was starting; the start is ended when it returns; 1x minimald WARN the box's classifier cover fell back to an empty read-only tmpfs: the kernel refused the design's cgroup<n> mount of the box's namespace roo; 1x minimald WARN exec: ssh client disconnected; killing child
  • 841-rename-destroy-own-ip-row on fedora (base, trace f6d87dd2): scenario: destroy_warn=1 port_listening=1 old_name_answer=127.0.64.3 reactivate_rc=2 already_exists=1 destroy_rc=0 registry_names_old=1 answer_before=127.0.64.3 port_before=1; trace: 2x minimal-cli span error cmd; 1x minimal-cli span error activation_step
  • 841-rename-destroy-own-ip-row on fedora (base, trace 4a5d8b43): scenario: destroy_warn=1 port_listening=1 old_name_answer=127.0.64.3 reactivate_rc=2 already_exists=1 destroy_rc=0 registry_names_old=1 answer_before=127.0.64.3 port_before=1; trace: 2x minimal-cli span error cmd; 1x minimal-cli span error activation_step
  • 790d-own-ip-ingress-diagnose-vm on fedora (base, trace 36dbc426): scenario: body_bytes=1000 curl_rc=0 cli_addr_bytes=0 cli_name_bytes=0 inbox_bytes=1060 web_ip=100.64.127.255 tcpdump=no syn=0 synack=0 rst=0; trace: 3x minimald WARN exec: ended while its command was starting; the start is ended when it returns; 1x minimald WARN the box's classifier cover fell back to an empty read-only tmpfs: the kernel refused the design's cgroup<n> mount of the box's namespace roo; 1x minimald WARN exec: ssh client disconnected; killing child
  • 790d-own-ip-ingress-diagnose-vm on fedora (head, trace 6f600f81): scenario: body_bytes=1000 curl_rc=0 cli_addr_bytes=0 cli_name_bytes=0 inbox_bytes=1060 web_ip=100.64.127.255 tcpdump=no syn=0 synack=0 rst=0; trace: 3x minimald WARN exec: ended while its command was starting; the start is ended when it returns; 1x minimald WARN the box's classifier cover fell back to an empty read-only tmpfs: the kernel refused the design's cgroup<n> mount of the box's namespace roo; 1x minimald WARN exec: ssh client disconnected; killing child
Each cited run's verdict and evidence

Each cited run's last VERDICT or ENV line and its EVIDENCE line (the results.jsonl rows of batch 841-rename-own-ip-1cbcf5f9):

  • 841-rename-destroy-own-ip-row ubuntu-24.04 base fail: VERDICT: after rename a841x18687 -> b841x18687 and destroy, left behind: ingress-port-38687 old-name-answers-127.0.64.3 reactivation-refused (destroy warned: 1); EVIDENCE: destroy_warn=1 port_listening=1 old_name_answer=127.0.64.3 reactivate_rc=2 already_exists=1 destroy_rc=0 registry_names_old=1 answer_before=127.0.64.3 port_before=1
  • 841-rename-destroy-own-ip-row ubuntu-24.04 base fail: VERDICT: after rename a841x26269 -> b841x26269 and destroy, left behind: ingress-port-26269 old-name-answers-127.0.64.3 reactivation-refused (destroy warned: 1); EVIDENCE: destroy_warn=1 port_listening=1 old_name_answer=127.0.64.3 reactivate_rc=2 already_exists=1 destroy_rc=0 registry_names_old=1 answer_before=127.0.64.3 port_before=1
  • 841-rename-destroy-own-ip-row ubuntu-24.04 head pass: VERDICT: rename then destroy left nothing behind: port 38251 closed, a841x18251 answers nxdomain, re-activation under a841x18251 succeeded; EVIDENCE: destroy_warn=0 port_listening=0 old_name_answer=nxdomain reactivate_rc=0 already_exists=0 destroy_rc=0 registry_names_old=0 answer_before=127.0.64.3 port_before=1
  • 841-rename-destroy-own-ip-row ubuntu-24.04 head pass: VERDICT: rename then destroy left nothing behind: port 39711 closed, a841x19711 answers nxdomain, re-activation under a841x19711 succeeded; EVIDENCE: destroy_warn=0 port_listening=0 old_name_answer=nxdomain reactivate_rc=0 already_exists=0 destroy_rc=0 registry_names_old=0 answer_before=127.0.64.3 port_before=1
  • 841-rename-destroy-own-ip-row fedora base fail: VERDICT: after rename a841x32228 -> b841x32228 and destroy, left behind: ingress-port-32228 old-name-answers-127.0.64.3 reactivation-refused (destroy warned: 1); EVIDENCE: destroy_warn=1 port_listening=1 old_name_answer=127.0.64.3 reactivate_rc=2 already_exists=1 destroy_rc=0 registry_names_old=1 answer_before=127.0.64.3 port_before=1
  • 841-rename-destroy-own-ip-row fedora base fail: VERDICT: after rename a841x41552 -> b841x41552 and destroy, left behind: ingress-port-21552 old-name-answers-127.0.64.3 reactivation-refused (destroy warned: 1); EVIDENCE: destroy_warn=1 port_listening=1 old_name_answer=127.0.64.3 reactivate_rc=2 already_exists=1 destroy_rc=0 registry_names_old=1 answer_before=127.0.64.3 port_before=1
  • 841-rename-destroy-own-ip-row fedora head pass: VERDICT: rename then destroy left nothing behind: port 30446 closed, a841x10446 answers nxdomain, re-activation under a841x10446 succeeded; EVIDENCE: destroy_warn=0 port_listening=0 old_name_answer=nxdomain reactivate_rc=0 already_exists=0 destroy_rc=0 registry_names_old=0 answer_before=127.0.64.3 port_before=1
  • 841-rename-destroy-own-ip-row fedora head pass: VERDICT: rename then destroy left nothing behind: port 38450 closed, a841x18450 answers nxdomain, re-activation under a841x18450 succeeded; EVIDENCE: destroy_warn=0 port_listening=0 old_name_answer=nxdomain reactivate_rc=0 already_exists=0 destroy_rc=0 registry_names_old=0 answer_before=127.0.64.3 port_before=1
  • 727-host-ip-egress-fail-open ubuntu-24.04 base pass: VERDICT: host_ip: allow-list refused up front; deny-all egress is enforced (1.1.1.1:443 blocked); no EVIDENCE line
  • 727-host-ip-egress-fail-open ubuntu-24.04 head pass: VERDICT: host_ip: allow-list refused up front; deny-all egress is enforced (1.1.1.1:443 blocked); no EVIDENCE line
  • 727-host-ip-egress-fail-open fedora base pass: VERDICT: host_ip: allow-list refused up front; deny-all egress is enforced (1.1.1.1:443 blocked); no EVIDENCE line
  • 727-host-ip-egress-fail-open fedora head pass: VERDICT: host_ip: allow-list refused up front; deny-all egress is enforced (1.1.1.1:443 blocked); no EVIDENCE line
  • 790d-own-ip-ingress-diagnose-vm ubuntu-24.04 base fail: VERDICT: own_ip ingress delivers to the host but a box's half-closing client loses the reply: cli -> web by address 0 B, cli -> web by name 0 B; EVIDENCE: body_bytes=1000 curl_rc=0 cli_addr_bytes=0 cli_name_bytes=0 inbox_bytes=1060 web_ip=100.64.127.255 tcpdump=no syn=0 synack=0 rst=0
  • 790d-own-ip-ingress-diagnose-vm ubuntu-24.04 head fail: VERDICT: own_ip ingress delivers to the host but a box's half-closing client loses the reply: cli -> web by address 0 B, cli -> web by name 0 B; EVIDENCE: body_bytes=1000 curl_rc=0 cli_addr_bytes=0 cli_name_bytes=0 inbox_bytes=1060 web_ip=100.64.127.255 tcpdump=no syn=0 synack=0 rst=0
  • 790d-own-ip-ingress-diagnose-vm fedora base fail: VERDICT: own_ip ingress delivers to the host but a box's half-closing client loses the reply: cli -> web by address 0 B, cli -> web by name 0 B; EVIDENCE: body_bytes=1000 curl_rc=0 cli_addr_bytes=0 cli_name_bytes=0 inbox_bytes=1060 web_ip=100.64.127.255 tcpdump=no syn=0 synack=0 rst=0
  • 790d-own-ip-ingress-diagnose-vm fedora head fail: VERDICT: own_ip ingress delivers to the host but a box's half-closing client loses the reply: cli -> web by address 0 B, cli -> web by name 0 B; EVIDENCE: body_bytes=1000 curl_rc=0 cli_addr_bytes=0 cli_name_bytes=0 inbox_bytes=1060 web_ip=100.64.127.255 tcpdump=no syn=0 synack=0 rst=0
  • 723-vm-host-ip-name-502 ubuntu-24.04 base pass: VERDICT: the session name reaches its 0.0.0.0 dev server through the proxy and a 127.0.0.1-only port is refused naming the fix (ok: local.min.internal min.internal); EVIDENCE: min.internal loopback-only :P -> GET 403 The box listens on this port at 127.0.0.1 only. Bind it to 0.0.0.0 to reach it by name. | 0.0.0.0 :Q -> GET 200 WILD-41637
  • 723-vm-host-ip-name-502 ubuntu-24.04 head pass: VERDICT: the session name reaches its 0.0.0.0 dev server through the proxy and a 127.0.0.1-only port is refused naming the fix (ok: local.min.internal min.internal); EVIDENCE: min.internal loopback-only :P -> GET 403 The box listens on this port at 127.0.0.1 only. Bind it to 0.0.0.0 to reach it by name. | 0.0.0.0 :Q -> GET 200 WILD-32551
  • 723-vm-host-ip-name-502 fedora base pass: VERDICT: the session name reaches its 0.0.0.0 dev server through the proxy and a 127.0.0.1-only port is refused naming the fix (ok: local.min.internal min.internal); EVIDENCE: min.internal loopback-only :P -> GET 403 The box listens on this port at 127.0.0.1 only. Bind it to 0.0.0.0 to reach it by name. | 0.0.0.0 :Q -> GET 200 WILD-19681
  • 723-vm-host-ip-name-502 fedora head pass: VERDICT: the session name reaches its 0.0.0.0 dev server through the proxy and a 127.0.0.1-only port is refused naming the fix (ok: local.min.internal min.internal); EVIDENCE: min.internal loopback-only :P -> GET 403 The box listens on this port at 127.0.0.1 only. Bind it to 0.0.0.0 to reach it by name. | 0.0.0.0 :Q -> GET 200 WILD-38750

🤖 Generated with Claude Code

Summary by CodeRabbit

  • Bug Fixes
    • Box cleanup now identifies the registered box even if its session name has changed, helping prevent a stale cleanup from affecting a newer box that reused the same name and addresses.
    • Attach and destroy flows now pass the box’s registered identity when available, so host resources can be released under the correct name.
    • Cleanup remains best-effort when registration details are missing; destruction and reaping can still proceed.

bryan-minimal and others added 3 commits November 7, 2026 10:28
A session rename changes only the in-VM record: the VM host keeps the box's row, its creation and
its published address under the name the box was registered by. The destroy then withdrew under
the new name with no box id, the host refused it as another box's row, and the ingress forward,
the old name's answer and the name itself stayed held for good (gominimal/inbox#1116).

The destroy, `min box rm`, `min box prune` and the dashboard's destroy now present the record's
box id beside the pair. The host accepts the row's own id in place of its name, finds a dormant
creation by the id first (as a resume does), and releases the published address under the name
the host held the box by. A withdrawal without the id is still held to the name.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
An attach that ends with the session gone (the shell-exit Delete, ends_with_run, or a destroy
from another shell) withdrew the row with the pair alone, under the session's current name. After
a rename that is refused with NotTheCreatorsRow, and the row, its ingress forward and the old name
stay (#1116). The CLI's attach and the dashboard's now read the box id off the record beside the
pair, before the attach, and present it; the id still goes only with a pair.

minvmd's withdrawal hands back the name the host held the box under, and the guest-audit flush
after it is labelled with that name rather than the one the request presented.

New tests pin box_addresses.and(box_id) on destroy_box: a pair and an id send the id; an id with
no pair sends no withdrawal.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…daemon connections

The lab prepush (job 05240) failed only on every_daemon_connection_is_classified: the new vm_host
test fixture connects to the daemon and belongs in the inventory as ungated, like box_record_by.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
@bryan-minimal
bryan-minimal requested a review from a team as a code owner November 9, 2026 15:48
@coderabbitai

coderabbitai Bot commented Nov 9, 2026 •

Copy link
Copy Markdown
Contributor

Explain Change →

No actionable comments were generated in the recent review.

Walkthrough

Box withdrawal now uses the registered BoxId with the address pair to identify a box after its session name changes. The host returns the registered name, and attach, destroy, and dashboard cleanup pass the saved identity when available.

Changes: Rename-safe box withdrawal

Layer / File(s) Summary
Registry withdrawal by BoxId
crates/minvmd/src/box_registry.rs
BoxRegistry can locate standing rows and dormant creations by BoxId after a rename. Without a matching ID, the presented name remains part of the proof.
Host release under the registered name
crates/minvmd/src/control.rs
The withdrawal handler releases the address and flushes the guest-audit window using the name held by the withdrawn row. Tests cover refusal without the matching ID and release under the registered name.
Pass BoxId through attach and destroy cleanup
crates/minimal-client/src/attach.rs, crates/minimal-client/src/box_registration.rs, crates/minimal/src/cmd/boxes/*, crates/minimal/src/cmd/session.rs, crates/minimal/src/dash/*, crates/minimal/src/tests.rs
Attach, destroy, and dashboard cleanup retain and pass BoxId with the registered address pair when available. Tests check withdrawal requests, and client documentation describes the ID’s role.

Estimated code review effort: 4 (Complex) | ~45 minutes

Sequence Diagram(s)

sequenceDiagram
  participant AttachCleanup as release_held_name_after_attach
  participant WithdrawalHelper as withdraw_box_row_with_vm_host
  participant Control as minvmd withdraw_box
  participant Registry as BoxRegistry
  participant Answerer
  AttachCleanup->>WithdrawalHelper: saved address pair and BoxId
  WithdrawalHelper->>Control: withdrawal request with name, addresses, and BoxId
  Control->>Registry: withdraw_client_box_held
  Registry-->>Control: removed row and registered held name
  Control->>Answerer: release address under registered held name
Loading

Possibly related PRs

  • gominimal/minimal#2114: Introduced the shared dashboard attach and destroy cleanup flow and row-withdrawal helper that this change extends with BoxId.
  • gominimal/minimal#2728: Consolidated the VM-host APIs used by attach and dashboard cleanup; this change adds BoxId to the shared withdrawal contract.
  • gominimal/minimal#2225: Manages the pre-attach VM-host name re-hold that complements this change’s post-attach cleanup.

Suggested reviewers: mitodrummer, norrietaylor

Merge Risk: Minimal · up to 1cbcf

This change makes teardown of renamed boxes release the ingress forward, address and row held under the original name. No concrete merge-blocking risk was identified in the supplied changes.

Pre-merge checks: Passed 5

Check name Status Explanation
Title check Passed The title "fix(minvmd): withdraw a renamed own_ip box's row by its box id" matches the main change. The changeset adds box-ID-aware withdrawal on the VM host (minvmd) so a renamed own_ip box's row can…
Docstring Coverage Passed Docstring coverage is 90.91% which is sufficient. The required threshold is 80.00%. Docstring coverage is scoped to functions touched by this diff with cyclomatic complexity of at least 2. Documentati…
Linked Issues check Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check Passed Check skipped because no linked issues were found for this pull request.
Description check Passed The description follows the template's main sections. The Summary section gives a detailed account of the bug, root cause, change, and scope. The Testing section lists the new unit and integration tes…
Full details: Title check

Explanation

The title "fix(minvmd): withdraw a renamed own_ip box's row by its box id" matches the main change. The changeset adds box-ID-aware withdrawal on the VM host (minvmd) so a renamed own_ip box's row can be removed on teardown. It follows the Conventional Commit form the template asks for, and it is specific enough for a teammate scanning history. Minor note: the title is 62 characters, which is within a typical limit.

Full details: Docstring Coverage

Explanation

Docstring coverage is 90.91% which is sufficient. The required threshold is 80.00%. Docstring coverage is scoped to functions touched by this diff with cyclomatic complexity of at least 2. Documentation-only edits and deletions within surviving functions are included; unchanged diff context and fully deleted functions are excluded. Analyzed 22 functions across 10 files. (1 skipped: 1 too large.)

Full details: Description check

Explanation

The description follows the template's main sections. The Summary section gives a detailed account of the bug, root cause, change, and scope. The Testing section lists the new unit and integration tests, prepush results, and lab evidence with run links and verdicts. Minor gaps: the Summary does not use the template's explicit Refs:/Closes: link format for gominimal/inbox#1116 (it names it only as a teardown part and in the commit-body note). The Checklist is absent, so the author did not confirm that docs were updated if behavior changed, or whether a BREAKING CHANGE: footer applies. The title check is outside this description review. The change alters host-side enforcement (NotTheBoxId on destroys that previously matched by pair alone), so the breaking-change status needs an explicit answer.

Finishing Touches

Generate docstrings

  • Commit to this branch
  • Create a new PR
Generate unit tests (beta)

  • Commit to this branch
  • Create a new PR
  • Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

A rabbit checks the row by ID,
The old name stays where it should be.
A box may wear a name anew,
Its saved ID still points it through.
The host releases, neat and spry,
While carrots wait for passersby.

Recent review info

Run configuration

  • Source mode: Auto
  • Repository: Unavailable
  • Branch: Unavailable
  • File: No configuration file from this repository applied
  • Commit: Unavailable
  • Layers: Organization UI
  • Review profile: CHILL
  • Plan: Essentials
  • Run ID: 5dce6119-05da-451c-ba3a-f3cf1e56c0c0
Commits

Reviewing files that changed from the base of the PR and between 620a1ce and 1cbcf5f.

Files selected for processing: 11

  • crates/minimal-client/src/attach.rs
  • crates/minimal-client/src/box_registration.rs
  • crates/minimal/src/cmd/boxes/attach.rs
  • crates/minimal/src/cmd/boxes/lifecycle.rs
  • crates/minimal/src/cmd/boxes/vm_host.rs
  • crates/minimal/src/cmd/session.rs
  • crates/minimal/src/dash/app.rs
  • crates/minimal/src/dash/rpc.rs
  • crates/minimal/src/tests.rs
  • crates/minvmd/src/box_registry.rs
  • crates/minvmd/src/control.rs

Included review availability: This review used your included allowance. 4 included reviews remain after this review. Your included PR review attempts over the past 7 days set your current allowance at 5 reviews per hour.

@minimal-foundry

minimal-foundry Bot commented Nov 9, 2026 •

Copy link
Copy Markdown
Contributor

Approved: no findings at 1cbcf5f925da.

Nothing to do.

Clobber: not checked in depth. If that was not intentional, restore the earlier change.

@minimal-foundry minimal-foundry Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

minimal-review — advisory review

Verdict COMMENT — No findings.

Panel: 1 of 3 personas ran (correctness); did not complete: security, supply-chain.

@minimal-foundry minimal-foundry Bot added the review:approved minimal-review approved the current head label Nov 9, 2026

@agent-137 agent-137 left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Review on Karl's behalf, at 1cbcf5f92. This is a comment, not an approval. Nothing was built for it: every point comes from reading the code, and each finding says how it was checked.

  • CI at head 1cbcf5f92: all green. Every lane aggregator passed.
  • Existing reviews: CodeRabbit APPROVED at head, and a review exists on that commit. minimal-review gave COMMENT with no findings, but only 1 of 3 personas ran (correctness). Security and supply-chain did not complete, so you may want to re-trigger it with /review. No humans have reviewed.

Should-fix: none.

Nit: none worth raising.

Checked and found fine:

  • withdraw_client_box_held: the id stands in for the name only when it equals the row's own id. The loopback check and the NotTheBoxId check still run.
  • In the dormant branch the creation is looked up by id first and by name second. The proves check still requires the pair and a matching id. The withdrawal generation is bumped under the creation's own name.
  • withdraw_box releases the answerer's address by the name the host held the box under, and flush_guest_audit keeps its old condition (held is Some exactly on the Addresses reply).
  • On the client, box_addresses.and(box_id) in destroy_box, cmd_box_rm, prune_host, the post-attach release and the dashboard.
  • Record::box_id is set to the minted row id only for a box with a row (minimald/src/box_manager.rs:3650).
  • Open point (not a finding): the PR body says the autospawn re-registration path was not traced end to end. That is the one way a record's box_id could fall behind its row's, which would turn a destroy that used to pass on the pair alone into a NotTheBoxId refusal. I did not trace it either.

Verdict: ready to approve. Merge it before #3175.

@agent-137 agent-137 left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Approving at 1cbcf5f92. The earlier comment review found nothing that needs fixing, and its nits are optional.

@bryan-minimal
bryan-minimal added this pull request to the merge queue Nov 9, 2026
Merged via the queue into main with commit 9f09a39 Nov 9, 2026
35 checks passed
@bryan-minimal
bryan-minimal deleted the fix/841-rename-own-ip-row branch November 9, 2026 23:32
bryan-minimal added a commit that referenced this pull request Nov 10, 2026
Resolves crates/minvmd/src/box_registry.rs and control.rs: #3172 landed on
main with `Record::name` returning `&str`, so this branch's rename path and
its tests take a name as main does, with no borrow of the returned slice.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

review:approved minimal-review approved the current head

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants