Skip to content

T123 — A host-address box's name answers its node's address on a VM host - #2831

Merged
norrietaylor merged 13 commits into
mainfrom
agent/2706-a-host-address-box-s-name-answers-its-node-s-add
Nov 3, 2026
Merged

norrietaylor merged 13 commits into
mainfrom
agent/2706-a-host-address-box-s-name-answers-its-node-s-add

Conversation

@minimal-foundry

@minimal-foundry minimal-foundry Bot commented Nov 1, 2026 •

Copy link
Copy Markdown
Contributor

T123 — A host-address box's name answers its node's address on a VM host

slice: S18
kind: task
covers: NET-009, NET-129
size: L
est: 180 code, 380 tests
executor: agent
difficulty: needs care
model: strongest
diagnostics: a person reads min ls, whose address column shows the node's address for every host_ip box on a VM, and the minvmd log line for each zone answer change
observability: the zone answer for a host-address name logged at debug with the address it carried, or NODATA and why
layers:
- answerer:
- crates/minvmd/src/control.rs: hold_box_name stops being the NODATA interim for a running host-address box whose node's binds are mirrored, and records the name against the node row
- crates/minvmd/src/net/answerer.rs: answers every host-address box's name on a VM node with the node's one address; NODATA while the box is not running, read at the host's end of the attachment, and while the node's binds are not mirrored; the name returns to NODATA when the node's last running host-address box ends
test: cargo nextest run -p minvmd host_address_name_answers_node_loopback_on_vm_host
test: cargo nextest run -p minvmd two_host_address_boxes_answer_one_node_address
- guest:
- crates/minimald/src/net/dns.rs: the in-VM daemon reports no address for a host-address name; the host decides the answer
test: cargo nextest run -p minimald host_ip_box_answers_node_loopback_address
- e2e:
- scripts/session-e2e.sh: the VM host answerer case asserts that two host-address boxes on one VM answer the same node address and that a port each binds opens at it
test (deferred: vm): ./scripts/session-e2e.sh native_resolution_from_host_answerer_on_vm_host
test: ./scripts/session-e2e.sh native_resolution_without_proxy_env
produces: none
consumes: none
proof: On a macOS host, http://<name>.min.internal:<port> for a host_ip box opens the port the box binds, with no proxy setting.
depends on:
- blocked by #2699

Proof

On a VM-backed host (macOS), the VM host daemon's answerer now answers .min.internal for a running host_ip box with the node's one reserved-range address, which is where the host mirrors the node's binds. So http://.min.internal: opens the port the box binds, with no proxy setting. Two host_ip boxes on one VM answer the same address. The name answers NODATA while the box is not running or the binds are not mirrored, and again after the node's last host_ip box ends. The unit tests prove the answers. Only the deferred VM e2e case proves the port opening on a real host, and it was not run here.

Notes from the agent: Outside the layers: crates/minvmd/src/box_registry.rs. The answer needs registry state that had no public read. I added BoxRegistry::held_name_owners, NodeMirror::mirrored_address (address open, range probe passing, binder set), and table pings when a host_ip box is admitted or retired and when the node mirror opens. Without the pings, a publish to the installed answer service waits for the 30 s cadence. I also changed one info log line: it said a held name 'answers NODATA', and that is no longer always true. Two items stay open. (1) A change in the range probe verdict does not ping, because NodeMirror holds no ping sender and run.rs is out of scope. The service sees that change within the 30 s PORT_RECHECK cadence. The interim holder sees it at once, because it builds its view for each lookup. (2) The diag zone dump (minvmd diag.rs) still reads BoxRegistry::zone_view, so it shows held host-address names with no address. The answerer and its publish use the new fold. Design: 'running' is read as the host_ip residency that the CLI's attachment admits and retires. A residency that HostIpResidency::keep keeps for a stopped box still answers the address. Issue #2747 owns that gap. A hold with no session id (an older client) always answers NODATA. Wire: RegisteredRow gains an optional node_address flag (serde default, left out when…[truncated]

Tests

line exit tail
cargo nextest run -p minvmd host_address_name_answers_node_loopback_on_vm_host 0 Applying loadouts: default Running task runtime-implement-test-0 in session task-runtime-implement-test-0-9840... Compiling paths v0.0.1 (/workbench/crates/paths) Compiling args v0.0.1 (/workbench/crates/args) Compiling ot v0.0.1 (/workbench/crates/ot) Compiling client-config v0.0.1 (/wo
cargo nextest run -p minvmd two_host_address_boxes_answer_one_node_address 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-ae10... Compiling version v0.8.0 (/workbench/crates/version) Compiling mlog v0.0.1 (/workbench/crates/mlog) Compiling minvmd v0.8.0 (/workbench/crates/minvmd) Finished 'test' profil
cargo nextest run -p minimald host_ip_box_answers_node_loopback_address 0 Applying loadouts: default Running task runtime-implement-test-2 in session task-runtime-implement-test-2-b94d... Compiling args v0.0.1 (/workbench/crates/args) Compiling ot v0.0.1 (/workbench/crates/ot) Compiling stdlib v0.0.22 (/workbench/crates/stdlib) Compiling version v0.8.0 (/workb
./scripts/session-e2e.sh native_resolution_without_proxy_env 0 the 'min' and 'minimald' under /work/build-cache/target/debug report different versions; rebuilding the pair no usable 'min' and 'minimald' pair on PATH or under target/; building the pair this run drives (cargo build --locked -p minimal --bin min -p minimald --bin minimald) built the pair: /work/bu
./scripts/session-e2e.sh native_resolution_from_host_answerer_on_vm_host 0 local macOS run at d3dfa9d, the reserved range on lo0, no name service installed: e2e-answerer-ha1.min.internal answers the node's address 127.0.64.2; e2e-answerer-ha2.min.internal answers the node's address 127.0.64.2; http://e2e-answerer-ha1.min.internal:18091/ and http://e2e-answerer-ha2.min.internal:18092/ open at 127.0.64.2 with no proxy setting; native min.internal resolution from the VM host daemon's answerer OK; session e2e OK

Verify

min task run agent-verify passed ([tasks.verify]).

Base

The base branch moved while the coder worked and was merged in before the tests ran. These files changed on BOTH sides since the branch point — read them first, because a rewrite from a stale reading can undo a merge without a conflict:

  • scripts/session-e2e.sh

Deferred

None. The deferred VM line ran on a local macOS host at d3dfa9d with the reserved range present (Tests above). It took the node-address branch, not NODATA.

Out of scope

These files are outside the task's layers:, so this PR is a draft:

  • crates/minvmd/src/box_registry.rs

Closes #2706

On a VM host, a held host_ip name now answers the node's reserved-range
address while its session is a resident host_ip box and the node's binds
are mirrored. It answers NODATA otherwise, and again when the box ends.

The publish marks such rows as the node's address, so the machine's
answer service holds several names at it and no box's release frees it.
The registry gains read accessors for held names and the mirrored
address, and pings the answerer when residency or the mirror changes.
The VM host decides what a host-address box's name answers there, so
the in-VM daemon's zone table leaves the address to it.
The VM host answerer case now activates two host_ip boxes, checks that
both names answer the node's one reserved-range address, and opens a
port each binds there with no proxy setting.
@coderabbitai

coderabbitai Bot commented Nov 1, 2026 •

Copy link
Copy Markdown
Contributor

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

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: Advanced
  • Run ID: 1c0826f0-280d-4d01-9e65-cfa58c499a6e

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

  • Trigger review
  • Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Tip

🎯 Customize your risk assessments

Guide how CodeRabbit assesses merge risk and security architecture risk. Highlight sensitive changes and explain your security boundaries using Merge Risk Instructions and Security Risk Instructions in your review settings. Security architecture risk assessments require the Advanced plan or above.

✅ Automatic approvals, with your rules

Let CodeRabbit approve pull requests once required threads are resolved, pre-merge checks pass, and your risk limits are met. Enable Automatic approvals in review settings, with overrides for teams or file paths.

CodeRabbit Verify

  • Run CodeRabbit Verify to test the changes in this pull request.

A macOS host carries the reserved range on lo0 only after
min finalize-install. Without it the node's binds are not mirrored, and
a host-address box's name answers NODATA, as the task specifies. The
VM host answerer case now reads the range state first and asserts the
node address and open ports only where the range is present.
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 1 of 10 on a failed check suite, pushed as d58218a0000f.

line exit tail
cargo nextest run -p minvmd host_address_name_answers_node_loopback_on_vm_host 0 Applying loadouts: default Running task runtime-implement-test-0 in session task-runtime-implement-test-0-7cde... Compiling paths v0.0.1 (/workbench/crates/paths) Compiling ot v0.0.1 (/workbench/crates/ot) Compiling args v0.0.1 (/workbench/crates/args) Compiling client-config v0.0.1 (/wo
cargo nextest run -p minvmd two_host_address_boxes_answer_one_node_address 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-90a5... Compiling version v0.8.0 (/workbench/crates/version) Compiling mlog v0.0.1 (/workbench/crates/mlog) Compiling minvmd v0.8.0 (/workbench/crates/minvmd) Finished 'test' profil
cargo nextest run -p minimald host_ip_box_answers_node_loopback_address 0 Applying loadouts: default Running task runtime-implement-test-2 in session task-runtime-implement-test-2-8592... Compiling ot v0.0.1 (/workbench/crates/ot) Compiling args v0.0.1 (/workbench/crates/args) Compiling stdlib v0.0.22 (/workbench/crates/stdlib) Compiling version v0.8.0 (/workb
./scripts/session-e2e.sh native_resolution_without_proxy_env 0 the 'min' and 'minimald' under /work/build-cache/target/debug report different versions; rebuilding the pair no usable 'min' and 'minimald' pair on PATH or under target/; building the pair this run drives (cargo build --locked -p minimal --bin min -p minimald --bin minimald) built the pair: /work/bu

Verify min task run agent-verify passed.

Outside the task's layers::

  • crates/minvmd/src/box_registry.rs

Converted to a draft: something above needs a person before review.

On a macOS host that carries the reserved range (after min finalize-install), http://.min.internal: for a host_ip box opens the port the box binds at the node's one 127.0.64.N address, with no proxy setting. On a macOS host without the range, the name answers NODATA and the e2e case now asserts exactly that.

Notes from the agent: Revise round 1. The macOS e2e failed because the case required an address for e2e-answerer-ha1.min.internal on a runner whose lo0 does not carry 127.0.64.0/24. No min finalize-install ran there. Without the range the node mirror never opens, so mirrored_address() is None, and NODATA is the answer the task specifies ("NODATA ... while the node's binds are not mirrored"). The Linux KVM lane, where all of 127/8 is on lo, did not fail. The fix is in scripts/session-e2e.sh only. The case reads the range from ifconfig lo0, the way the macOS ingress case does. With the range it keeps the address and port checks. Without it, it asserts NOERROR with no A record, which is NODATA and not NXDOMAIN. ci-macos-success is the lane aggregator over that e2e job, so it needs no separate change. I did not observe the CI dig output, because the excerpt cut it. The diagnosis comes from the code path and the lane difference, and the next macOS run confirms it. On the macOS lane the port-opening half of the proof runs only where the runner has the range. Deferred: ./scripts/session-e2e.sh native_resolution_from_host_answerer_on_vm_host (lane: vm), not run here. Outside the layers: an earlier round changed crates/minvmd/src/box_registry.rs (held_name_owners, mirrored_address, and pings on admit, retire and mirror open). The answerer needs them. This round did not touch it.

@norrietaylor

Copy link
Copy Markdown
Member

/revise The macOS lane fails at d58218a in minvmd::vm_escape_integration::vm_escape_bounded_to_resident_union (job 124757386483, crates/minvmd/tests/vm_escape_integration.rs:2048):

a box-marked frame a resident host_ip box admits never reached 192.168.0.147:64456: the listener accepted no new connection (the reply went to the in-VM daemon [no SYN-ACK for spoofed source 100.64.255.253 within 10s; the flow's frames were decided before they left the VM])

The same test passes on #2830 and #2832, whose bases are the same or newer, so this branch most likely causes it. This PR changes the path the test exercises:

  • In crates/minvmd/src/control.rs, AdmitHostIpBox and RetireHostIpBox now run inside order.apply(...).
  • In crates/minvmd/src/box_registry.rs, admit_host_ip_box, retire_host_ip_box and the mirror open now call self.ping().

Find out why a frame from a resident host_ip box no longer reaches its admitted destination after these changes. Check whether the ticket ordering delays or reorders residency relative to the frame, and whether the ping rebuilds a table the gate reads mid-flow. Fix it so the test passes unchanged. Keep NET-129: the name answers the node's address only while the box is resident and the binds are mirrored.

Run cargo nextest run -p minvmd --run-ignored all vm_escape_bounded_to_resident_union (or just test-vm) as well as this task's own test lines.

The answerer reads the name holds and the resident host_ip set together
when it builds its view, so the order of a hold and an admit cannot change
a host-address name's answer (NET-129). The ticket was not needed, and it
moved the admit and the retire off the path the VM escape test exercises.
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 2 of 10 on a /revise note, pushed as 5b3430d8db84.

line exit tail
cargo nextest run -p minvmd host_address_name_answers_node_loopback_on_vm_host 0 Applying loadouts: default Running task runtime-implement-test-0 in session task-runtime-implement-test-0-6355... Compiling paths v0.0.1 (/workbench/crates/paths) Compiling args v0.0.1 (/workbench/crates/args) Compiling ot v0.0.1 (/workbench/crates/ot) Compiling client-config v0.0.1 (/wo
cargo nextest run -p minvmd two_host_address_boxes_answer_one_node_address 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-8b7d... Compiling version v0.8.0 (/workbench/crates/version) Compiling mlog v0.0.1 (/workbench/crates/mlog) Compiling minvmd v0.8.0 (/workbench/crates/minvmd) Finished 'test' profil
cargo nextest run -p minimald host_ip_box_answers_node_loopback_address 0 Applying loadouts: default Running task runtime-implement-test-2 in session task-runtime-implement-test-2-9802... Compiling args v0.0.1 (/workbench/crates/args) Compiling ot v0.0.1 (/workbench/crates/ot) Compiling stdlib v0.0.22 (/workbench/crates/stdlib) Compiling version v0.8.0 (/workb
./scripts/session-e2e.sh native_resolution_without_proxy_env 0 the 'min' and 'minimald' under /work/build-cache/target/debug report different versions; rebuilding the pair no usable 'min' and 'minimald' pair on PATH or under target/; building the pair this run drives (cargo build --locked -p minimal --bin min -p minimald --bin minimald) built the pair: /work/bu

Verify min task run agent-verify passed.

Outside the task's layers::

  • crates/minvmd/src/box_registry.rs

Converted to a draft: something above needs a person before review.

On a macOS host, http://.min.internal: for a host_ip box opens the port the box binds, with no proxy setting. This round makes no change to that behaviour. It only puts AdmitHostIpBox and RetireHostIpBox back on their pre-branch path, without a ticket. This box cannot show the proof, because it has no VM lane.

Notes from the agent: Revise round 2. I looked for the cause of the vm_escape_bounded_to_resident_union failure and did not find one in this branch. (1) Ticket: order.apply runs the admit synchronously before the reply is written. The test waits for that reply before it sends the marked frame, so the ticket cannot delay or reorder residency relative to the frame. A long wait would fail the test at the admit's 30 s read timeout, not at line 2048. (2) Ping: BoxRegistry::ping only sends () on the channels of the two subscribers, the answerer acquire loop (answerer.rs) and the zone dump (diag.rs). Neither rebuilds anything the gate reads. host_ip_verdict reads table.host_ip_boxes() live under the resident lock. The answerer's republish only takes read locks, one at a time. (3) The guest dns.rs change affects only host_net boxes that the guest daemon registers, and the test admits its host_ip boxes on the host socket directly. Change made: AdmitHostIpBox and RetireHostIpBox no longer take a ticket. The answerer builds the answer from the holds and the resident set each time it builds its view, so the order of a hold and an admit cannot change it. NET-129 still holds: the name answers the node address only while the session is resident and mirrored_address() is Some. The pings stay, because the cross-process publish needs them to carry the change before the PORT_RECHECK cadence. I was not able to run the VM test here (no /dev/kvm, the binary is not built on Linux), so it is still unverified whether this round fixes the macOS failure. If the test still fails, the next step is the gate account from the failing job (gate_account output), which …[truncated]

@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Revise round 1 ran against ci-macos-success, e2e and left it red; a coder round cannot clear it, a person should look. No round was started for the failed suite on 5b3430d8db84.

@norrietaylor

Copy link
Copy Markdown
Member

/revise Round 2 (5b3430d) took the ticket off admit and retire, and the macOS lane still fails the same test in the same way (job 124785897525, crates/minvmd/tests/vm_escape_integration.rs:2048):

a box-marked frame a resident host_ip box admits never reached 192.168.0.237:58417: the listener accepted no new connection (the reply went to the in-VM daemon [no SYN-ACK for spoofed source 100.64.255.253 within 10s; the flow's frames were decided before they left the VM])

So the ticket was not the cause. This test runs only on the macOS VM lane: the KVM lane passes, and its log does not run it. That is why your sandbox does not see it. Before you push, reason from the code about what this branch changes on that test's path. These are the remaining changes it could hit:

  • crates/minvmd/src/box_registry.rs: the new self.ping() calls in admit_host_ip_box, retire_host_ip_box and the mirror open. Check what a ping rebuilds, whether it resets or re-derives the resident union or the cohort record the gate decides box-marked frames by, and whether it races the test's admit, then frame sequence.
  • crates/minimald/src/net/dns.rs: the in-VM daemon now reports no address for a host-address name. Check whether the test's spoofed 100.64.255.253 flow, or the resident box's admission, depends on that address.
  • crates/minvmd/src/net/answerer.rs: whether answering a held host-address name with the node's address changes anything the egress gate or the mirror reads.

Read vm_escape_bounded_to_resident_union from line 1669 to see which of these it exercises. Fix the cause so the test passes unchanged. If you cannot find a cause on this branch, say so in the PR body with what you ruled out, and do not push a speculative change.

@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 3 of 10 on a /revise note: the coder changed nothing. Round 3: I found no cause on this branch for the macOS VM lane failure in vm_escape_bounded_to_resident_union (crates/minvmd/tests/vm_escape_integration.rs:2048). The directive says not to push a speculative change, so this round changes nothing. Ruled out, from the code:

  1. box_registry.rs ping() calls. ping() (box_registry.rs:5804) only sends () on the table_pings channels. Two threads subscribe: the zone answerer's publish loop (net/answerer.rs acquire) and the zone-table dump (diag.rs dump_loop). Both only read the registry: zone_view, held_name_owners, table().host_ip_boxes() and node_mirror().mirrored_address(), which is a pure read of bind_target(). None of them rebuilds, resets or writes the resident set or its cohort record. admit_host_ip_box and retire_host_ip_box call ping() after drop(resident), so no ping runs under the resident set's write lock. The answerer takes the resident read lock and the mirror lock one after the other, never nested, so it cannot deadl…[truncated]

@norrietaylor

Copy link
Copy Markdown
Member

/revise Make vm_escape_bounded_to_resident_union say why the admitted frame never arrives, so the next macOS lane run carries the cause. This round adds diagnostics only. Do not change product behaviour.

The test fails only on the macOS VM lane at this branch (jobs 124757386483 and 124785897525, crates/minvmd/tests/vm_escape_integration.rs:2048). It passes on main's macOS run at 6bddc07 (job 124767767473). Neither the coder sandbox nor a local Mac could compare the two.

  1. In the test, move the check for the gate's drop line for the admitted marked frame ahead of the assert at :2048. Today it runs only after the assert. Put every gate line about that flow's destination and source (192.168.x.x:<port>, the box mark, resident_host_ip_boxes=) into the failure message.
  2. In the failure message, also include:
    • the resident set and the cohort record when the frame was sent, read from the gate's debug or diag dump (crates/minvmd/src/diag.rs dump_loop, if the harness can reach it);
    • whether node_mirror().mirrored_address() was Some at that moment;
    • any ingress-backpressure warnings for the flow's addresses. The failing run logged one toward 100.64.255.253 about 40 s before the failure.
  3. If the gate has no log line that says why it decides a box-marked frame, add one at debug level naming the verdict and the rule. The test reads it from the minvmd log the harness already collects.

Keep the test's assertion unchanged. Run this task's test lines. Say in the PR body that this round is diagnostic and that the cause comes from the next macOS lane run.

Diagnostic only, for the macOS VM lane failure in
vm_escape_bounded_to_resident_union. The gate logs at debug, under its
own target, the verdict and rule for each box-marked frame that opens a
flow, with the resident host_ip set and the cohort record it read. The
host_ip admission line carries the mirrored node address. The test
checks the host_ip drop line before the arrival assert, and the arrival
assert's message quotes the flow's gate lines, the marked-frame
decisions, the mirrored address, backpressure drops and the zone dump.
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 4 of 10 on a /revise note, pushed as 0270f75f0b01.

line exit tail
cargo nextest run -p minvmd host_address_name_answers_node_loopback_on_vm_host 0 Applying loadouts: default Running task runtime-implement-test-0 in session task-runtime-implement-test-0-3f78... Compiling paths v0.0.1 (/workbench/crates/paths) Compiling args v0.0.1 (/workbench/crates/args) Compiling ot v0.0.1 (/workbench/crates/ot) Compiling client-config v0.0.1 (/wo
cargo nextest run -p minvmd two_host_address_boxes_answer_one_node_address 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-de95... Compiling version v0.8.0 (/workbench/crates/version) Compiling mlog v0.0.1 (/workbench/crates/mlog) Compiling minvmd v0.8.0 (/workbench/crates/minvmd) Finished 'test' profil
cargo nextest run -p minimald host_ip_box_answers_node_loopback_address 0 Applying loadouts: default Running task runtime-implement-test-2 in session task-runtime-implement-test-2-c09d... Compiling args v0.0.1 (/workbench/crates/args) Compiling ot v0.0.1 (/workbench/crates/ot) Compiling stdlib v0.0.22 (/workbench/crates/stdlib) Compiling version v0.8.0 (/workb
./scripts/session-e2e.sh native_resolution_without_proxy_env 0 the 'min' and 'minimald' under /work/build-cache/target/debug report different versions; rebuilding the pair no usable 'min' and 'minimald' pair on PATH or under target/; building the pair this run drives (cargo build --locked -p minimal --bin min -p minimald --bin minimald) built the pair: /work/bu

Verify min task run agent-verify passed.

Outside the task's layers::

  • crates/minvmd/src/box_registry.rs
  • crates/minvmd/src/net/egress_gate.rs
  • crates/minvmd/tests/vm_escape_integration.rs

Converted to a draft: something above needs a person before review.

This round is diagnostic only and does not change the proof. When vm_escape_bounded_to_resident_union fails again on the macOS VM lane, its failure message will say why the admitted box-marked frame did not arrive. The message quotes the gate's verdict, its rule and the decision arm, the resident host_ip set and cohort record at that frame, the mirrored node address at each host_ip admission, the backpressure drops and the zone-table dump. The cause comes from the next macOS lane run. The task's proof (http://.min.internal: opens a host_ip box's port on macOS with no proxy setting) still waits on that lane.

Notes from the agent: This round is diagnostic. Put that in the PR body: the cause of the vm_escape_bounded_to_resident_union failure comes from the next macOS lane run. Product behaviour does not change. The one new log line is at debug, under its own tracing target (minvmd::egress_gate::marked), so it is off at the default info filter.

Files outside the task's layers, touched because the /revise note asks for them: crates/minvmd/tests/vm_escape_integration.rs (the test), crates/minvmd/src/net/egress_gate.rs (item 3: the gate had no line for an admitted box-marked frame, and none for a marked frame that reaches the source-row arm), and crates/minvmd/src/box_registry.rs (an earlier round on this branch already changed it; this round adds mirrored_address to the host_ip admission info line).

What each item became:

  1. The check for the egress-host-ip-boxes drop line with resident_host_ip_boxes=2 now runs before the arrival assert. The arrival assert keeps its condition. Its message adds every gate line that names source=, destination=, : or resident_host_ip_boxes=.
  2. The gate cannot reach the node mirror (BoxTable does not hold it), so mirrored_address is the value at each host_ip admission, logged by admit_host_ip_box. The admitted flow is sent right after the second admission. The resident set and the cohort rec…[truncated]

@norrietaylor norrietaylor 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.

Babysitter review of 0270f75 against T123. vm_escape_bounded_to_resident_union, which failed on this branch's macOS lane at d58218a and 5b3430d, passes at this head (35 s) after the diagnostic round (6be9b87) and two merges from main. The cause of the earlier failures was not found. The new diagnostics stay: a debug line on its own target (minvmd::egress_gate::marked), written only for a flow's opening frame, plus richer failure messages in the test. A recurrence will now say why. Diagnostics aside, the change matches the T123 plan block: a host-address name answers its node's address only while the box is resident and the binds are mirrored, and NODATA otherwise. All lanes are green.

@norrietaylor
norrietaylor marked this pull request as ready for review November 3, 2026 05:42
@norrietaylor
norrietaylor requested a review from a team as a code owner November 3, 2026 05:42
@minimal-foundry

minimal-foundry Bot commented Nov 3, 2026 •

Copy link
Copy Markdown
Contributor Author

Approved: every review thread resolved at d3dfa9d7c12c.

@norrietaylor resolved the last thread, which releases the approval this review had withheld.

Nothing to do.

@minimal-foundry minimal-foundry Bot left a comment

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

minimal-review — approved

Verdict APPROVE — No findings.

Panel: 3 of 3 personas ran (correctness, security, supply-chain).

@minimal-foundry minimal-foundry Bot added the review:approved minimal-review approved the current head label Nov 3, 2026

@minimal-arch minimal-arch Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

arch-review: PASS_WITH_CONDITIONS · 3 conditions · the full ruling

The answer is in the right owner. minvmd builds it from host-door residency and the node mirror, and minimald reports no address (§7.1 lines 244, 255, 261). Three gaps stay. C1: a range-probe change does not ping, so the answer service keeps a stale address for up to 30 s (line 255). C2: the diag zone dump disagrees with the answer. C3: the deferred VM e2e leg did not run, and it is the only proof that the port opens. The keep residency gap is a residual under #2747.

Ruled at 0270f75 against gominimal/arch@7a86ec7bb3c0 by claude-opus-5-5.

Comment thread crates/minvmd/src/box_registry.rs Resolved
Comment thread crates/minvmd/src/net/answerer.rs Resolved
Comment thread scripts/session-e2e.sh Resolved
@norrietaylor

Copy link
Copy Markdown
Member

/revise Arch C1 and C2 on 0270f75 (arch_rulings 780).

  1. C1 (crates/minvmd/src/box_registry.rs, crates/minvmd/src/cmd/run.rs): add BoxRegistry::set_node_range_probe(passes: bool). It calls self.node_mirror.set_range_probe(passes), then self.ping() when self.node_mirror.mirrored_address() changed. In run.rs, node_mirror_pass() calls it in place of mirror.set_range_probe(probe.present()). A range-probe failure then republishes NODATA at once, instead of the installed answer service keeping the node address for up to PORT_RECHECK (30 s) after the binds are undone. In host_address_name_answers_node_loopback_on_vm_host, assert that a table ping arrives when the probe fails.
  2. C2 (crates/minvmd/src/diag.rs write_table()): build the rows from crate::net::answerer::own_zone_view(registry), made pub(crate), in place of registry.zone_view(). Then the zone-table dump shows the node address for a running host_ip box's held name, the same answer the answerer gives. The module doc says a dump and a lookup never disagree. Remove the "open" note about this from the PR body.

Keep the diagnostic logging from 6be9b87. Leave C3, the VM-lane run with the reserved range on lo0, to the babysitter. Run this task's test lines.

A failing whole-range probe now pings the table at once, so the
installed answer service drops the node's address with no recheck
wait. The zone-table dump reads the answerer's own view, so it shows
the node address a lookup answers.

@minimal-arch minimal-arch Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

arch-review: PASS_WITH_CONDITIONS · 1 condition · the full ruling

The compare closes the two open items from the last head. A failing range probe now republishes NODATA at once, as §7.1 line 255 requires. The zone dump now shows the address that a lookup answers. NET-009 and NET-129 conform. The VM e2e leg is still deferred and did not run. Run it on a VM lane and record the result (C1).

Ruled at d3dfa9d against gominimal/arch@7a86ec7bb3c0 by claude-opus-5-5.

Comment thread scripts/session-e2e.sh Resolved

@minimal-foundry minimal-foundry Bot left a comment

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

minimal-review — approval withheld

Verdict COMMENT — APPROVE withheld: 4 unresolved threads — minimal-arch[bot] crates/minvmd/src/box_registry.rs:6588, minimal-arch[bot] crates/minvmd/src/net/answerer.rs:2606, minimal-arch[bot] scripts/session-e2e.sh:8950, minimal-arch[bot] scripts/session-e2e.sh:8943. No findings.

Panel: 3 of 3 personas ran (correctness, security, supply-chain).

@minimal-foundry minimal-foundry Bot removed the review:approved minimal-review approved the current head label Nov 3, 2026
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 5 of 10 on a /revise note, pushed as d3dfa9d7c12c.

line exit tail
cargo nextest run -p minvmd host_address_name_answers_node_loopback_on_vm_host 0 Applying loadouts: default Running task runtime-implement-test-0 in session task-runtime-implement-test-0-6aa6... Compiling paths v0.0.1 (/workbench/crates/paths) Compiling args v0.0.1 (/workbench/crates/args) Compiling ot v0.0.1 (/workbench/crates/ot) Compiling client-config v0.0.1 (/wo
cargo nextest run -p minvmd two_host_address_boxes_answer_one_node_address 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-5772... Compiling version v0.8.0 (/workbench/crates/version) Compiling mlog v0.0.1 (/workbench/crates/mlog) Compiling minvmd v0.8.0 (/workbench/crates/minvmd) Finished 'test' profil
cargo nextest run -p minimald host_ip_box_answers_node_loopback_address 0 Applying loadouts: default Running task runtime-implement-test-2 in session task-runtime-implement-test-2-175a... Compiling args v0.0.1 (/workbench/crates/args) Compiling ot v0.0.1 (/workbench/crates/ot) Compiling stdlib v0.0.22 (/workbench/crates/stdlib) Compiling version v0.8.0 (/workb
./scripts/session-e2e.sh native_resolution_without_proxy_env 0 the 'min' and 'minimald' under /work/build-cache/target/debug report different versions; rebuilding the pair no usable 'min' and 'minimald' pair on PATH or under target/; building the pair this run drives (cargo build --locked -p minimal --bin min -p minimald --bin minimald) built the pair: /work/bu

Verify min task run agent-verify passed.

Outside the task's layers::

  • crates/minvmd/src/box_registry.rs
  • crates/minvmd/src/cmd/run.rs
  • crates/minvmd/src/diag.rs
  • crates/minvmd/src/net/egress_gate.rs
  • crates/minvmd/tests/vm_escape_integration.rs

Converted to a draft: something above needs a person before review.

Review threads the coder judged:

  • 👍 valid — crates/minvmd/src/box_registry.rs:6588: Added BoxRegistry::set_node_range_probe. It pings the table when mirrored_address() changes, and node_mirror_pass() in run.rs now calls it. The test asserts that a failing probe pings.
  • 👍 valid — crates/minvmd/src/net/answerer.rs:2606: own_zone_view is now pub(crate), and diag.rs write_table() builds the dump from it. The dump now shows the node address that a lookup answers.
  • 👍 valid — scripts/session-e2e.sh:8950: The finding holds: this leg needs the macOS VM lane, and that lane is not on this box. The /revise note gives the VM-lane run to the babysitter, so this round changed nothing for it.

On a macOS host, http://.min.internal: for a host_ip box opens the port the box binds, with no proxy setting. This round makes the name fall back to NODATA at once when the range probe fails, and makes the zone-table dump show the same node address that a lookup answers. Only the VM lane can show the port open at the node address on macOS. That run is deferred and did not happen on this box.

Notes from the agent: Round 5 did C1 and C2 from the /revise note. C1: added BoxRegistry::set_node_range_probe. It pings the table when mirrored_address() changes, and it logs the change at debug. run.rs node_mirror_pass() now calls it. The host_address_name_answers_node_loopback_on_vm_host test now asserts that a failing verdict pings, that a repeated failing verdict does not ping, and that a passing verdict pings. C2: own_zone_view is now pub(crate), and diag.rs write_table() builds its rows from it. The module doc now says that. The test also asserts that own_zone_view carries the node address for the held name. Scope: box_registry.rs, cmd/run.rs and diag.rs are outside the task's layers. The /revise note asked for these changes by name. box_registry.rs and egress_gate.rs were already in the diff from earlier rounds. The diagnostic logging from 6be9b87 is unchanged. C3 is not done, as the note directs: the deferred test ./scripts/session-e2e.sh native_resolution_from_host_answerer_on_vm_host (lane: vm) did not run here. native_resolution_without_proxy_env exited 0 but skipped its proof, because the daemon on this box never owned the zone answerer ports. The PR body's 'open' note about C2 is the runner's to remove. I cannot edit the PR body.

@minimal-foundry
minimal-foundry Bot marked this pull request as draft November 3, 2026 06:30

@norrietaylor norrietaylor 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.

Babysitter review of d3dfa9d. Arch C1 is met: set_node_range_probe pings only when mirrored_address() changes, node_mirror_pass() calls it, and the test asserts both a ping on a failing probe and no ping on a repeated verdict. C2 is met: diag.rs dumps own_zone_view, and the test asserts that the dump and a lookup agree. I am running C3 (the reserved-range VM run) locally and will record it in the PR body.

@norrietaylor
norrietaylor marked this pull request as ready for review November 3, 2026 15:59

@minimal-foundry minimal-foundry Bot left a comment

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

minimal-review — approved

Verdict APPROVE — every review thread is resolved; @norrietaylor closed the last one. The review of d3dfa9d7c12c withheld this approval on the threads open then. Posted as a comment: the App cannot approve its own pull request; the check and the label carry it.

@minimal-foundry minimal-foundry Bot added the review:approved minimal-review approved the current head label Nov 3, 2026
@norrietaylor
norrietaylor added this pull request to the merge queue Nov 3, 2026
@github-merge-queue
github-merge-queue Bot removed this pull request from the merge queue due to failed status checks Nov 3, 2026
@norrietaylor
norrietaylor added this pull request to the merge queue Nov 3, 2026
Merged via the queue into main with commit fab6ba0 Nov 3, 2026
36 checks passed
@norrietaylor
norrietaylor deleted the agent/2706-a-host-address-box-s-name-answers-its-node-s-add branch November 3, 2026 20:52
yermakoffivan pushed a commit to yermakoffivan/minimal that referenced this pull request Nov 4, 2026
The session e2e now takes main's test-kvm to 28.5 of its 30 minutes
(merge-queue run 41673262055 for gominimal#2824). Queue runs for gominimal#2831 and gominimal#2819
were cancelled at the limit while the e2e still made progress, and
the queue dequeued both PRs.
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.

T123 — A host-address box's name answers its node's address on a VM host

1 participant