Skip to content

T93 — Give each VM a hostname-proxy port no other VM holds, and fail loudly when it cannot - #1957

Merged
norrietaylor merged 24 commits into
mainfrom
agent/1949-give-each-vm-a-hostname-proxy-port-no-other-vm-h
Oct 4, 2026
Merged

norrietaylor merged 24 commits into
mainfrom
agent/1949-give-each-vm-a-hostname-proxy-port-no-other-vm-h

Conversation

@minimal-foundry

Copy link
Copy Markdown
Contributor

T93 — Give each VM a hostname-proxy port no other VM holds, and fail loudly when it cannot

slice: S15
kind: task
covers: none
size: M
est: 260 code, 300 tests
executor: agent
difficulty: needs care
model: strongest
diagnostics: the VM host daemon log names the proxy port it reserved, every candidate it skipped and why (another VM's reservation, a port the node reserves for itself, or bound on the host), and the publish outcome minvmd checked for that port; a failed start is one error line naming the port and the holder when known
observability: one info line per reserved node port; one info line per skipped candidate; one error line when the publish of the reserved port fails; the min ls NAME SURFACE row and the session-start message carry the named cause
layers:
- vmhost:
- crates/minvmd/src/cmd/run.rs: assign_node_port reserves the drawn port host-wide before the boot uses it, with an OS advisory lock (flock/fcntl) on a per-port file that minvmd holds open for the VM's life, so the kernel releases it on stop, exit or crash; no pid files, no stale-entry cleanup, and minimal never unlinks a lock file; the directory is per user: $XDG_RUNTIME_DIR/minimal/ports/ on Linux (falling back to /tmp/minimal-<uid>/ports/, created 0700 and refused if it exists with another owner or a wider mode) and ~/Library/Application Support/minimal/run/ports/ on macOS, never a cache or temp dir the OS purges; a candidate another VM has reserved, a port the node itself reserves (the answerer's hook port among them, whether or not it is bound at the probe) or a port bound on the published address 127.0.0.1 (with 0.0.0.0 probed as an extra holder check, the proxy never bound to the wildcard) is skipped and logged; another user's VMs are seen only by the bind probe, the residual the single-operator premise leaves
- crates/minvmd/src/control.rs: over the existing control path, minvmd learns the guest's proxy publish outcome and re-probes the port itself, so nothing the guest says changes which port is reserved; for a port minvmd drew, an address-in-use publish redraws under the reservation and asks the guest to publish again, at most 3 tries (a constant), then fails the VM start naming the port and the holder; an operator-configured port never redraws and fails the start naming the port and the holder; a VM never stays up with no hostname proxy
test: cargo nextest run -p minvmd concurrent_boots_never_draw_the_same_proxy_port
test: cargo nextest run -p minvmd reservation_is_released_when_the_vm_stops
test: cargo nextest run -p minvmd publish_in_use_redraws_then_fails_named
test: cargo nextest run -p minvmd configured_proxy_port_in_use_fails_named_without_redraw
test: cargo nextest run -p minvmd draw_skips_the_answerer_hook_port_while_free
- daemon:
- crates/minimald/src/server.rs: an address-in-use failure of the hostname proxy's host publish is reported to the VM host daemon over the existing control path as a terminal publish failure naming the port, not retried with backoff forever; other publish errors keep the existing backoff
test: cargo nextest run -p minimald proxy_publish_in_use_is_reported_not_retried
- cli:
- crates/minimal/src/resolver.rs: the NAME SURFACE row in min ls and the session-start message name the cause when the hostname proxy is not serving (the port and that another process holds it, or the redraws ran out), read from the VM host daemon's side, instead of a bare "not serving"
test: cargo nextest run -p minimal name_surface_names_why_the_proxy_is_not_serving
- e2e:
- scripts/session-e2e.sh: the two-named-VM case also boots both VMs at once and asserts each VM's hostname proxy serves on its own port; a drawn port held by a non-minimal listener on 127.0.0.1 is redrawn (the VM serves on a port other than the held one and the log names the skipped port); a configured port held the same way fails the start naming the port; on macOS a second bind of the same address and port fails loudly
test: ./scripts/session-e2e.sh two_named_vms_on_one_machine
produces: none
consumes:
- crates/minvmd/src/cmd/run.rs
proof: Two VMs booting at the same moment get distinct hostname-proxy ports from a per-user reservation the kernel releases when a VM's daemon stops or dies; a drawn port found taken is redrawn at most three times and then fails the start naming the port, a configured port found taken fails the start naming the port without redraw, and no VM stays up with no hostname proxy; the draw never takes the answerer's hook port; min ls and the session-start message name the cause when the proxy is not serving.

Out of time

The coder ran out of its 7200s before it finished. If it left work uncommitted, its last commit is the runtime's snapshot of that work as it stood — the commit message says so — and not a finished step: it may not build or pass its tests. So this PR is a draft.

Proof

Two VMs booting at the same moment get distinct hostname-proxy ports from a per-user reservation the kernel releases when a VM's daemon stops or dies; a drawn port found taken is redrawn at most three times and then fails the start naming the port, a configured port found taken fails the start naming the port without redraw, and no VM stays up with no hostname proxy; the draw never takes the answerer's hook port; min ls and the session-start message name the cause when the proxy is not serving.

Tests

line exit tail
cargo nextest run -p minvmd concurrent_boots_never_draw_the_same_proxy_port 0 Applying loadouts: default Running task runtime-implement-test-0 in session task-runtime-implement-test-0-a5fb... Compiling args v0.0.1 (/home/runner/.local/state/minimal/sessions/eab53/tree/crates/args) Compiling ot v0.0.1 (/home/runner/.local/state/minimal/sessions/eab53/tree/crates/ot) C
cargo nextest run -p minvmd reservation_is_released_when_the_vm_stops 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-1be8... Compiling version v0.7.0 (/home/runner/.local/state/minimal/sessions/382a3/tree/crates/version) Compiling mlog v0.0.1 (/home/runner/.local/state/minimal/sessions/382a3/tree/crates/
cargo nextest run -p minvmd publish_in_use_redraws_then_fails_named 0 Applying loadouts: default Running task runtime-implement-test-2 in session task-runtime-implement-test-2-abec... Compiling version v0.7.0 (/home/runner/.local/state/minimal/sessions/c00c1/tree/crates/version) Compiling mlog v0.0.1 (/home/runner/.local/state/minimal/sessions/c00c1/tree/crates/
cargo nextest run -p minvmd configured_proxy_port_in_use_fails_named_without_redraw 0 Applying loadouts: default Running task runtime-implement-test-3 in session task-runtime-implement-test-3-07a9... Compiling version v0.7.0 (/home/runner/.local/state/minimal/sessions/3851b/tree/crates/version) Compiling mlog v0.0.1 (/home/runner/.local/state/minimal/sessions/3851b/tree/crates/
cargo nextest run -p minvmd draw_skips_the_answerer_hook_port_while_free 0 Applying loadouts: default Running task runtime-implement-test-4 in session task-runtime-implement-test-4-63c8... Compiling version v0.7.0 (/home/runner/.local/state/minimal/sessions/faffd/tree/crates/version) Compiling mlog v0.0.1 (/home/runner/.local/state/minimal/sessions/faffd/tree/crates/
cargo nextest run -p minimald proxy_publish_in_use_is_reported_not_retried 0 Applying loadouts: default Running task runtime-implement-test-5 in session task-runtime-implement-test-5-c9e8... Compiling args v0.0.1 (/home/runner/.local/state/minimal/sessions/fd8f5/tree/crates/args) Compiling ot v0.0.1 (/home/runner/.local/state/minimal/sessions/fd8f5/tree/crates/ot) C
cargo nextest run -p minimal name_surface_names_why_the_proxy_is_not_serving 0 Applying loadouts: default Running task runtime-implement-test-6 in session task-runtime-implement-test-6-fa54... Compiling ot v0.0.1 (/home/runner/.local/state/minimal/sessions/a3748/tree/crates/ot) Compiling args v0.0.1 (/home/runner/.local/state/minimal/sessions/a3748/tree/crates/args) C
./scripts/session-e2e.sh two_named_vms_on_one_machine 0 two_named_vms_on_one_machine SKIPPED (guest images not available) session e2e OK Applying loadouts: default Running task runtime-implement-test-7 in session task-runtime-implement-test-7-32a2...

Verify

min task run agent-verify exited 101, so this PR is a draft.

Applying loadouts: default
Running task runtime-implement-verify in session task-runtime-implement-verify-3db7...
    Checking args v0.0.1 (/home/runner/.local/state/minimal/sessions/4ab18/tree/crates/args)
    Checking ot v0.0.1 (/home/runner/.local/state/minimal/sessions/4ab18/tree/crates/ot)
    Checking paths v0.0.1 (/home/runner/.local/state/minimal/sessions/4ab18/tree/crates/paths)
   Compiling version v0.7.0 (/home/runner/.local/state/minimal/sessions/4ab18/tree/crates/version)
    Checking switch v0.0.1 (/home/runner/.local/state/minimal/sessions/4ab18/tree/crates/switch)
   Compiling minvmd v0.7.0 (/home/runner/.local/state/minimal/sessions/4ab18/tree/crates/minvmd)
   Compiling stdlib v0.0.21 (/home/runner/.local/state/minimal/sessions/4ab18/tree/crates/stdlib)
    Checking mlog v0.0.1 (/home/runner/.local/state/minimal/sessions/4ab18/tree/crates/mlog)
    Checking diagnostics v0.0.1 (/home/runner/.local/state/minimal/sessions/4ab18/tree/crates/diagnostics)
error: using `chunks_exact` with a constant chunk size
   --> crates/switch/src/refusal.rs:205:10
    |
205 |         .chunks_exact(2)
    |          ^^^^^^^^^^^^^^^ help: consider using `as_chunks` instead: `as_chunks::<2>().0.iter()`
    |
    = help: for further information visit https://rust-lang.github.io/rust-clippy/rust-1.98.0/index.html#chunks_exact_to_as_chunks
    = note: `-D clippy::chunks-exact-to-as-chunks` implied by `-D warnings`
    = help: to override `-D warnings` add `#[allow(clippy::chunks_exact_to_as_chunks)]`

error: using `chunks_exact` with a constant chunk size
   --> crates/switch/src/refusal.rs:209:31
    |
209 |     if let Some(tail) = bytes.chunks_exact(2).remainder().first() {
    |                               ^^^^^^^^^^^^^^^
    |
help: consider using `as_chunks::<2>()` instead
   --> crates/switch/src/refusal.rs:209:31
    |
209 |     if let Some(tail) = bytes.chunks_exact(2).remainder().first() {
    |                               ^^^^^^^^^^^^^^^
    = help: for further information visit https://rust-lang.github.io/rust-clippy/rust-1.98.0/index.html#chunks_exact_to_as_chunks

error: could not compile `switch` (lib) due to 2 previous errors
warning: build failed, waiting for other jobs to finish...

Out of scope

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

  • crates/minimal/src/cmd/session.rs
  • crates/minimald-rpc/src/lib.rs

Closes #1949

The node-port assignment now takes a host-wide reservation on the port it
hands, before the boot uses it: an exclusive flock on a per-port file in
a per-user directory ($XDG_RUNTIME_DIR/minimal/ports on Linux, falling
back to /tmp/minimal-<uid>/ports, and the Application Support runtime dir
on macOS; created 0700 and refused when another user owns it or it is
wider). The supervisor holds the lock's file description for the VM's
life, so the kernel releases it on stop, exit or crash — no pid files, no
stale-entry cleanup, and the lock files themselves are never unlinked.

Every candidate the draw considers is now checked and logged — one info
line per skipped candidate naming the port and the reason (another VM's
reservation, a port the node itself reserves such as the zone answerer's
hook port, a bind refusal, or a listener already answering on loopback),
and one per reserved port. The operator's pin is held to the same checks
and never redraws: a pin some check refuses fails the start naming the
port and the holder.

Over the boot-marker channel — the one existing control path from inside
a microVM to the VM host daemon — the guest's in-VM daemon now reports
its hostname-proxy publish outcome: PROXY_SERVING on success, or a
terminal PROXY_PORT_HELD when the publish is refused for address-in-use.
The supervisor's gate owns the marker listener for its life, watches each
boot's publish, re-probes the port itself, and decides: a drawn port
redraws under the reservation and asks the guest to publish again, at
most three tries, then fails the start naming the port and the holder; a
configured port fails on the first refusal; nothing the guest says
changes which port is reserved. The failure's cause rides the control
socket's read-only status read (ZoneAnswererStatus::ProxyNotServing),
for the CLI's min ls row and session-start message to name.
Inside a microVM, the hostname proxy publishes on the port the VM host
handed down the boot line, and that port has no rung of its own to walk
to: when the host already holds it, the daemon now says so over the
boot-marker channel (vsock CID 2, the same channel the READY and
MOUNT_FAILED beacons travel) as a two-line PROXY_PORT_HELD report naming
the port, records the unavailable note `min ls` warns from, and ends the
publish drive there. The VM host holds the port's reservation, so it
owns the retry — a redraw onto a fresh port, or a start failure naming
this one — and it cannot own what it never hears: a backoff loop here
would leave the VM up with no hostname proxy.

The healthy publication reports PROXY_SERVING the same way, so the host
watch ends without waiting out its bound. Both reports are best-effort
with short dial retries, mirroring guest.rs's emit_marker, because the
host bounds its own watch and falls back to its own probes when nothing
arrives; other publish failures — transient, or a walk that exhausted
its rungs — keep the existing backoff (NET-021), and the native
daemon's pinned-port bind retry keeps its NET-024 behavior untouched.

The old pinned-refusal publish test asserted the retry-forever arm this
removes for the VM path; it is rewritten into the terminal contract as
proxy_publish_in_use_is_reported_not_retried, with a format test for
the two report payloads beside it.
The NAME SURFACE row in `min ls` and the session-start message now say
why the hostname proxy is not serving — the port the failure is about
and the cause the VM host daemon reported: another process on the host
holds the port, or the redraws ran out — instead of a bare "not
serving". The cause rides the existing status reply the verbs already
read: ProxyNotServing settles the surface verdict whole, with no
detection, liveness query, or range probe, because the VM host daemon's
verdict on the proxy's publication is the fact and no host read can
move it.

The session start reads the same status through host_answerer_read,
which now carries the named cause out beside the answerer facts; the
start's third arm prints it before the answerer arms, claiming nothing
the status did not say. The ZONE ANSWERER row keeps its silence for a
status that speaks only about the proxy, as it does for the
pre-acquisition state.

cmd/session.rs changes because the read's call site is there: the
destructure grows the proxy_down fact and the start gains the arm that
prints it. resolver.rs owns everything the fact is decided and spelled
in, so the two verbs keep printing from the one function that cannot
disagree with itself.
@coderabbitai

coderabbitai Bot commented Oct 4, 2026 •

Copy link
Copy Markdown
Contributor

Important

Review skipped

Bot user detected.

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

⚙️ Run configuration
  • Configuration used: Organization UI
  • Review profile: CHILL
  • Plan: Advanced
  • Run ID: 28c88397-5a4c-4aa2-b590-9717341987b4

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
  • Autopilot · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Comment @coderabbitai help to get the list of available commands.

@minimal-foundry minimal-foundry Bot added the needs-human An agent handed off; a human must act, then clear this label. Set by defer and handoffs. label Oct 4, 2026
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

The runtime will not revise this pull request again on its own: round 2 would exceed the cap of 1 (the last trigger was a failed check suite). A person decides now. Remove needs-human from this pull request to let /revise <note> or the automatic rounds resume, or finish #1949 by hand.

The assignment keeps its reservation only to hold the flock for the VM's
life, so the field is `_reservation`; the reservation's own unread port
field goes. The /tmp fallback base is created 0700 and owner-checked like
the ports dir, since /tmp is shared.
The vsock dial to the VM host can take seconds per try, so awaiting it
held the drive past the serving record and past the terminal return.
Record first, then send the report on a spawned task.
Both activates run together and each VM must serve on its own port; a
second bind of either published port must fail with address-in-use. A
plain listener on 7654 then makes a drawn port redraw (the log names the
skipped candidate) and makes a pinned port fail the start naming it.
A start that fails on the hostname proxy's port now fails with one line
naming the port, the holder (pid and exe via procfs or lsof, when the
host shows it) and why: configured ports never redraw, or the publish
tries ran out. `run --detach` lifts that line from run.log, so the
CLI's autospawn error carries it inline.

The reservation directory is now a parameter of the draw, so every unit
test reserves in its own tempdir and none takes a flock in the user's
real directory. The supervisor resolves the directory once, as before.
The detach's stderr, which the CLI's autospawn error carries, must name
the held port, its holder, and that configured ports never redraw.
The run reference names the hostname proxy's default port, the fallback
when it is held, and the env knob that pins it from minvmd run or the
min command that autospawns it.
@norrietaylor
norrietaylor marked this pull request as ready for review October 4, 2026 13:11
@norrietaylor
norrietaylor requested a review from a team as a code owner October 4, 2026 13:11
@minimal-foundry

minimal-foundry Bot commented Oct 4, 2026 •

Copy link
Copy Markdown
Contributor Author

Reviewed: 1 finding, none blocking at 72092e704f3b.

Address the comments on the diff.

Clobber: none: git log on the touched files shows the recent history is this PR's own fixups, and every thread in threads.json — the NoReport→Up mapping, the port-unchecked await_publish_report, the garbled proxy_port_failure grammar, the straggler discrimination, the redraw's own-reservation skip — is addressed at HEAD (716e65c / 85886a4 / f918096 / 72092e7).

@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 — advisory review

Verdict COMMENT — 1 finding, 1 inline.

Comment thread crates/minvmd/src/control.rs Resolved
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

The runtime will not revise this pull request again on its own: round 2 would exceed the cap of 1 (the last trigger was a failed check suite). A person decides now. Remove needs-human from this pull request to let /revise <note> or the automatic rounds resume, or finish #1949 by hand.

@minimal-foundry

Copy link
Copy Markdown
Contributor Author

The runtime will not revise this pull request again on its own: round 2 would exceed the cap of 1 (the last trigger was the runtime's review findings). A person decides now. Remove needs-human from this pull request to let /revise <note> or the automatic rounds resume, or finish #1949 by hand.

@minimal-foundry

Copy link
Copy Markdown
Contributor Author

The runtime will not revise this pull request again on its own: round 2 would exceed the cap of 1 (the last trigger was a failed check suite). A person decides now. Remove needs-human from this pull request to let /revise <note> or the automatic rounds resume, or finish #1949 by hand.

The held-port beats assumed stopping the default VM frees 7654. The named VM
can hold it instead, and its proxy's TIME_WAIT connections refuse a plain bind
for up to a minute on Linux and macOS. Wait until the port binds, and set
SO_REUSEADDR on the probe and the holder; a live listener still refuses them.
… is late

A publish watch that expired without the guest's report no longer maps to
up blindly. The supervisor names the port's holder and matches its pid
against the processes it spawned for the VM (the host switch and the VMM
child): its own forwarder means the report was late and the VM is up;
another process is treated like a refused publish (drawn ports redraw,
pins fail naming the holder); a holder the host will not name gets a
short grace for the report and then comes up unconfirmed, as does a port
nothing answers on. An unconfirmed publish rides the status read as the
new publish_unconfirmed cause, so min ls says so instead of serving,
until the guest's late report clears it.
A refusal the guest reports after an unconfirmed start now records
PortHeldAfterStart with the holder the host names, and `min ls` and the
session start say the VM is up without a hostname proxy, naming the port
and the holder, instead of the start failure's words. ProxyDownCause and
the statuses that carry it lose Copy to hold the holder label.

port_holder takes its procfs root or lsof binary through port_holder_with,
so a missing or failing lookup is proven to name no holder (unknown, never
foreign), and a child-process listener is proven to be named by pid on
both Linux (procfs) and macOS (lsof).
With only the named VM up, `min --vm <vm> ls` prints the discovery row
without a VM column, so the redraw beat read no port. Accept that form for
the scoped listing.

@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.

@minimal-foundry minimal-foundry Bot added the review:approved minimal-review approved the current head label Oct 4, 2026

@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 — advisory review

Verdict COMMENT — 1 finding, 1 inline.

Comment thread crates/minvmd/src/cmd/run.rs Resolved
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

The runtime will not revise this pull request again on its own: round 2 would exceed the cap of 1 (the last trigger was a failed check suite). A person decides now. Remove needs-human from this pull request to let /revise <note> or the automatic rounds resume, or finish #1949 by hand.

@minimal-foundry

Copy link
Copy Markdown
Contributor Author

The runtime will not revise this pull request again on its own: round 2 would exceed the cap of 1 (the last trigger was the runtime's review findings). A person decides now. Remove needs-human from this pull request to let /revise <note> or the automatic rounds resume, or finish #1949 by hand.

@minimal-foundry minimal-foundry Bot removed the review:approved minimal-review approved the current head label Oct 4, 2026
An unscoped listing's lone row belongs to whichever VM is up, so the
stopped-VM beat read the default VM's port as the named VM's. Only the
redraw beat, which lists with --vm, opts in.
The start failure reads "held by {holder}", and the fallback carried its own
verb, so an unnamed holder rendered "held by another process on the host holds
it".

@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 — advisory review

Verdict COMMENT — 1 finding, 1 inline.

Comment thread crates/minvmd/src/cmd/run.rs Resolved
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

The runtime will not revise this pull request again on its own: round 2 would exceed the cap of 1 (the last trigger was the runtime's review findings). A person decides now. Remove needs-human from this pull request to let /revise <note> or the automatic rounds resume, or finish #1949 by hand.

The READY wait dropped every publish report as a killed boot's straggler,
so a refusal this boot sent before READY never reached the publish
decision. The supervisor now draws a publish generation per boot and hands
it beside the proxy port on the boot line; the guest echoes it as a third
line of every publish report. A report with this boot's generation is kept
before or after READY and handed to the watch; any other generation is a
straggler, dropped with a line naming both. A report with no generation
comes from an older guest: dropped before READY, kept after it.
A publish report that lost its generation on the way is still kept after
READY, as an older guest's, so a break in the command line to guest to
report chain left the e2e green. The supervisor now logs the generation it
draws for every boot, and each kept publish report logs the generation it
carried (or absent) beside the boot's. The two-named-VMs proof reads both
lines for each VM's boot and fails when either is missing, the report's
generation is absent, or the two differ.

@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 — advisory review

Verdict COMMENT — 1 finding, 1 inline.

Comment thread crates/minvmd/src/cmd/run.rs Resolved
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

The runtime will not revise this pull request again on its own: round 2 would exceed the cap of 1 (the last trigger was the runtime's review findings). A person decides now. Remove needs-human from this pull request to let /revise <note> or the automatic rounds resume, or finish #1949 by hand.

@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 — advisory review

Verdict COMMENT — 1 finding, 1 inline.

Comment thread crates/minvmd/src/cmd/run.rs Resolved
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

The runtime will not revise this pull request again on its own: round 2 would exceed the cap of 1 (the last trigger was the runtime's review findings). A person decides now. Remove needs-human from this pull request to let /revise <note> or the automatic rounds resume, or finish #1949 by hand.

@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 — advisory review

Verdict COMMENT — 1 finding, 1 inline.

Comment thread crates/minvmd/src/cmd/run.rs Resolved
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

The runtime will not revise this pull request again on its own: round 2 would exceed the cap of 1 (the last trigger was the runtime's review findings). A person decides now. Remove needs-human from this pull request to let /revise <note> or the automatic rounds resume, or finish #1949 by hand.

@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.

Reviewed at 72092e7. Both of the T93 publish-generation gaps are closed: per-boot token, straggler drop, and a log line per decision, asserted in the e2e. The redraw now releases its own flock before redrawing (72092e7). The re-probe-gating finding is declined and ARCH concurs. ARCH PASS. All lanes green on head.

@norrietaylor norrietaylor removed the needs-human An agent handed off; a human must act, then clear this label. Set by defer and handoffs. label Oct 4, 2026
@norrietaylor
norrietaylor added this pull request to the merge queue Oct 4, 2026
Merged via the queue into main with commit 901d29f Oct 4, 2026
34 checks passed
@norrietaylor
norrietaylor deleted the agent/1949-give-each-vm-a-hostname-proxy-port-no-other-vm-h branch October 4, 2026 15:29
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

T93 — Give each VM a hostname-proxy port no other VM holds, and fail loudly when it cannot

1 participant