Skip to content

refactor(boxes): make the box id the one key for every record - #2485

Merged
norrietaylor merged 12 commits into
mainfrom
agent/2385-make-the-box-id-the-one-key-for-every-record
Oct 24, 2026
Merged

norrietaylor merged 12 commits into
mainfrom
agent/2385-make-the-box-id-the-one-key-for-every-record

Conversation

@minimal-foundry

@minimal-foundry minimal-foundry Bot commented Oct 21, 2026 •

Copy link
Copy Markdown
Contributor

T45 — Make the box id the one key for every record

slice: S0
kind: enablement
covers: none
size: L
est: 420 code, 300 tests
executor: agent
difficulty: needs care
model: strongest
diagnostics: daemon log names boxes by one id
observability: spans and log lines carry box id
layers:
- record:
- crates/boxes/src/lib.rs: box id is the key; alias kept
- crates/boxes/src/store.rs: keyed by box id; reads old records
test: cargo nextest run -p boxes record_json_written_before_the_merge_round_trips
- wire:
- crates/minimald-rpc/src/lib.rs: reply ids convert, bytes unchanged
- crates/minimald-rpc/src/tests.rs: reply id round-trips
test: cargo nextest run -p minimald-rpc every_reply_id_round_trips_byte_for_byte
- daemon:
- crates/minimald/src/box_manager.rs: holder keeps id time order
- crates/minimald/src/box_manager/tests.rs: tests
test: cargo nextest run -p minimald creation_order_holder_follows_box_id_time_order
- vm-host:
- crates/minvmd/src/bep_attach.rs: mints the one id type
test: cargo nextest run -p minvmd minted_box_id_is_the_record_key_type
produces: none
consumes: none
proof: Old records and replies round-trip; one id everywhere.
depends on:
- blocked by #2375
- blocked by #2380
- blocked by #2383
- blocked by #2381
- blocked by #2376
- blocked by #2377
- blocked by #2378
- blocked by #2379
- blocked by #2384

Proof

The tree has one box id type. boxes::BoxId wraps a UUIDv7. SessionId is now an alias of it, and minimald-rpc and minvmd mint and carry that same type. A record.json written before the merge loads from disk under the same id and saves back with both id spellings unchanged. That is the hyphenated record id and the 32-hex box_id. Each session reply and each VM host box control reply decodes and re-encodes byte for byte. The daemon's map of live boxes holds them in box id time order, which is creation order. A minimald log line and a minvmd log line spell a box id in the same hyphenated form.

Notes from the agent: Design: BoxId is now a Uuid newtype with mint, nil, is_nil, parse_str, simple, From and AsRef. pub type SessionId = BoxId keeps the 600-odd SessionId uses outside the layers compiling unchanged. The default serde form and Display are the hyphenated UUID, so record files, session replies and printed ids stay the same. The fields that carried the 32-hex spelling (Record.box_id and the minimald-rpc box control fields) use the new boxes::box_id_hex adapter, so their bytes stay the same. A reader accepts either spelling.

One visible change: Display of a value that was a BoxId now prints the hyphenated form, not 32 hex digits. This changes the minimal-client registration log line and the minvmd log lines through BoxIdText, including the box_id string on a minvmd ask record. The bep and switch crates keep their own [u8; 16] and hex text, outside the layers.

Reverted inside this branch: the first commit also filed a VM box's record under the id the VM host handed it, and refused a duplicate id. The full minimald run then failed 10 box_actor tests, because they hand the one fixture id [0x42; 16] to every box. Also, the AlreadyExists refusal reached the client as "A session with that name already exists", which is wrong. That is BOX-002 and BOX-001's collision refusal, which this task does not cover. It needs crates/minimald/src/box_actor/te…[truncated]

Residuals

Tests

line exit tail
cargo nextest run -p boxes record_json_written_before_the_merge_round_trips 0 Applying loadouts: default Running task runtime-implement-test-0 in session task-runtime-implement-test-0-289c... Compiling args v0.0.1 (/workbench/crates/args) Compiling ot v0.0.1 (/workbench/crates/ot) Compiling paths v0.0.1 (/workbench/crates/paths) Compiling common v0.0.1 (/workbench
cargo nextest run -p minimald-rpc every_reply_id_round_trips_byte_for_byte 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-576f... Compiling common v0.0.1 (/workbench/crates/common) Compiling boxes v0.0.1 (/workbench/crates/boxes) Compiling minimald-rpc v0.0.1 (/workbench/crates/minimald-rpc) Finished '
cargo nextest run -p minimald creation_order_holder_follows_box_id_time_order 0 Applying loadouts: default Running task runtime-implement-test-2 in session task-runtime-implement-test-2-7e4f... Compiling ot v0.0.1 (/workbench/crates/ot) Compiling args v0.0.1 (/workbench/crates/args) Compiling paths v0.0.1 (/workbench/crates/paths) Compiling stdlib v0.0.22 (/workbenc
cargo nextest run -p minvmd minted_box_id_is_the_record_key_type 0 Applying loadouts: default Running task runtime-implement-test-3 in session task-runtime-implement-test-3-9e87... Compiling ot v0.0.1 (/workbench/crates/ot) Compiling args v0.0.1 (/workbench/crates/args) Compiling version v0.8.0 (/workbench/crates/version) Compiling minvmd v0.8.0 (/workb

Verify

min task run agent-verify exited 101 under rustc 1.98.1, which the repository does not pin (1.97.0 in rust-toolchain.toml); the PR is not a draft on that alone — CI, which honours the pin, is the gate.

the sandbox ran rustc (1.98.1), the repository pins 1.97.0 in rust-toolchain.toml; a failure here may be the newer toolchain's, not this change's
Applying loadouts: default
Running task runtime-implement-verify in session task-runtime-implement-verify-e253...
    Checking args v0.0.1 (/workbench/crates/args)
    Checking ot v0.0.1 (/workbench/crates/ot)
    Checking paths v0.0.1 (/workbench/crates/paths)
   Compiling version v0.8.0 (/workbench/crates/version)
    Checking switch v0.0.1 (/workbench/crates/switch)
    Checking common v0.0.1 (/workbench/crates/common)
   Compiling minvmd v0.8.0 (/workbench/crates/minvmd)
   Compiling stdlib v0.0.22 (/workbench/crates/stdlib)
    Checking boxes v0.0.1 (/workbench/crates/boxes)
    Checking sandbox v0.0.1 (/workbench/crates/sandbox)
    Checking mlog v0.0.1 (/workbench/crates/mlog)
    Checking diagnostics v0.0.1 (/workbench/crates/diagnostics)
    Checking async-dialog v0.0.1 (/workbench/crates/async-dialog)
    Checking minimald-rpc v0.0.1 (/workbench/crates/minimald-rpc)
    Checking mfile v0.0.1 (/workbench/crates/mfile)
    Checking decode v0.0.1 (/workbench/crates/decode)
    Checking checkouts v0.0.1 (/workbench/crates/checkouts)
error: using `chunks_exact` with a constant chunk size
   --> crates/minimald-rpc/src/trace.rs:199:46
    |
199 |     for (byte, pair) in out.iter_mut().zip(s.chunks_exact(2)) {
    |                                              ^^^^^^^^^^^^^^^
    |
help: consider using `as_chunks::<2>()` instead
   --> crates/minimald-rpc/src/trace.rs:199:46
    |
199 |     for (byte, pair) in out.iter_mut().zip(s.chunks_exact(2)) {
    |                                              ^^^^^^^^^^^^^^^
    = 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: could not compile `minimald-rpc` (lib) due to 1 previous error
warning: build failed, waiting for other jobs to finish...
error: could not compile `minimald-rpc` (lib test) due to 1 previous error

Closes #2385


Undrafted 2026-10-24. The one edit outside the layers, crates/minvmd/src/control.rs (AskAudit::with_facts writes the ask audit box_id as 32 hex, with a pin test), is the one the arch review's C2 named. A maintainer accepted it.

SessionId is now an alias of BoxId, a UUIDv7 newtype. A record
keeps writing its id in the hyphenated form and its handed box_id
as 32 hex digits, and reads either spelling, so records written
before the merge round-trip unchanged. The store files a record
under the id the VM host handed it when there is one, and refuses
an id a retained record already holds.
The box control fields spell the box id as 32 hex digits through
boxes::box_id_hex, so every reply carries the bytes it carried before
the id types merged. A test pins each pre-merge reply byte for byte.
The manager's running map is keyed by the one box id, a UUIDv7, so
it holds boxes in creation order. A create logs the id the record is
filed under, and a test pins the holder's order and the handed key.
The VM host mints a boxes::BoxId, the record key type, and hands the
switch its bytes. Log lines spell the id the way the in-VM daemon's
record and log do.
Filing a VM box's record under the id its host handed back refused
the box_actor tests that hand one fixture id to every box, and the
refusal surfaced as a name collision. That is the BOX-002 change and
needs its own task, so the store mints the key as before, now in the
one box id type.
@coderabbitai

coderabbitai Bot commented Oct 21, 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: 607a0e4d-b6da-40da-9343-4f37e15b8c0d

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

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

@minimal-foundry

minimal-foundry Bot commented Oct 21, 2026 •

Copy link
Copy Markdown
Contributor Author

Approved: no findings at 21c8592af131.

Nothing to do.

Clobber: none seen.

@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.

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

Comment thread crates/minvmd/src/bep_attach.rs Resolved

@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: CONDITIONS · 3 conditions · the full ruling

The type merge conforms, and the box-control wire bytes do not change. On a VM guest, the in-VM store still mints Record::id, because the last commit reverted the BOX-002 work. The PR documents that id as the box's one key and logs it as box_id. Architecture line 495 says minvmd mints the box_id outside the VM, and Record::box_id holds that id. Make the log field exact (C1) and the docs true (C2). File the reverted work as an issue and link it from the PR (C3).

Ruled at 8c8e7d4 against gominimal/arch@109541a48c31 by claude-opus-5-5.

Comment thread crates/minimald/src/box_manager.rs Resolved
Comment thread crates/boxes/src/lib.rs Resolved
Comment thread crates/boxes/src/lib.rs Resolved
Comment thread crates/minvmd/src/bep_attach.rs Resolved
Comment thread crates/boxes/src/store.rs Resolved
The audit subject and the box control wire spell a box id as 32 hex
digits. Log lines from the VM host now use the same form, so a tail
can match one box across them.

@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.

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

Comment thread crates/minvmd/src/bep_attach.rs Resolved

@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: CONDITIONS · 2 conditions · the full ruling

The record key is still not the box id. DiskLoader::create mints record.id in minimald, which runs inside the VM on a LocalVM host. Line 495 of architecture.md says a party outside the host VM mints the box_id, and ids key every record. The PR names the revert but links no issue. Make C1: file the record under the handed id and refuse a duplicate. Make C2: give each box_actor test box its own minted id, and add that test file to the task layers. The minvmd log spelling change in this push conforms.

Outside the diff

  • crates/minimald/src/box_actor/tests.rs:3365: C2 · Every test box shares this one id. Mint a fresh BoxId for each box, so the C1 refusal does not fire. Do not relax the refusal.

Ruled at bdeaeb7 against gominimal/arch@109541a48c31 by claude-opus-5-5.

Comment thread crates/boxes/src/store.rs Resolved
Comment thread crates/boxes/src/lib.rs Resolved
Comment thread crates/minimald/src/box_manager.rs Resolved
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 1 of 10 on the runtime's review findings, pushed as bdeaeb72d537.

line exit tail
cargo nextest run -p boxes record_json_written_before_the_merge_round_trips 0 Applying loadouts: default Running task runtime-implement-test-0 in session task-runtime-implement-test-0-a31d... Compiling args v0.0.1 (/workbench/crates/args) Compiling ot v0.0.1 (/workbench/crates/ot) Compiling paths v0.0.1 (/workbench/crates/paths) Compiling common v0.0.1 (/workbench
cargo nextest run -p minimald-rpc every_reply_id_round_trips_byte_for_byte 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-cff6... Compiling common v0.0.1 (/workbench/crates/common) Compiling boxes v0.0.1 (/workbench/crates/boxes) Compiling minimald-rpc v0.0.1 (/workbench/crates/minimald-rpc) Finished '
cargo nextest run -p minimald creation_order_holder_follows_box_id_time_order 0 Applying loadouts: default Running task runtime-implement-test-2 in session task-runtime-implement-test-2-b1f7... Compiling ot v0.0.1 (/workbench/crates/ot) Compiling args v0.0.1 (/workbench/crates/args) Compiling paths v0.0.1 (/workbench/crates/paths) Compiling stdlib v0.0.22 (/workbenc
cargo nextest run -p minvmd minted_box_id_is_the_record_key_type 0 Applying loadouts: default Running task runtime-implement-test-3 in session task-runtime-implement-test-3-2a02... Compiling ot v0.0.1 (/workbench/crates/ot) Compiling args v0.0.1 (/workbench/crates/args) Compiling version v0.8.0 (/workbench/crates/version) Compiling minvmd v0.8.0 (/workb

Verify min task run agent-verify exited 101 under rustc 1.98.1, which the repository does not pin (1.97.0 in rust-toolchain.toml); the PR is not a draft on that alone — CI, which honours the pin, is the gate.

nst_format v0.2.36
    Checking derive_builder v0.20.2
    Checking nix v0.30.1
    Checking netlink-packet-route v0.25.1
    Checking procfs-core v0.18.0
    Checking hash32 v0.2.1
    Checking itertools v0.15.0
    Checking spin v0.9.9
    Checking generational-arena v0.2.9
    Checking strum v0.27.2
    Checking pathrs v0.2.5
    Checking nickel-lang-core v0.19.0
    Checking heapless v0.7.17
    Checking oci-spec v0.10.0
    Checking netconfig-rs v0.1.6
    Checking procfs v0.18.0
    Checking nix v0.29.0
    Checking netlink-packet-route v0.31.0
    Checking args v0.0.1 (/workbench/crates/args)
    Checking common v0.0.1 (/workbench/crates/common)
    Checking boxes v0.0.1 (/workbench/crates/boxes)
    Checking cobs v0.3.0
    Checking getifaddrs v0.6.2
    Checking path-dedot v4.0.1
    Checking fixedbitset v0.5.7
    Checking tun-rs v2.8.8
    Checking libcgroups v0.7.0
    Checking path-absolutize v4.0.1
    Checking postcard v1.1.3
    Checking route_manager v0.2.13
    Checking sendfd v0.4.4
    Checking minimald-rpc v0.0.1 (/workbench/crates/minimald-rpc)
    Checking mfile v0.0.1 (/workbench/crates/mfile)
    Checking caps v0.5.6
    Checking close_fds v0.3.2
    Checking size v0.5.0
    Checking hakoniwa v1.7.2 (https://github.com/souk4711/hakoniwa.git?rev=0810ffa37620ef5c57de263c8eaa1f4d7633c14a#0810ffa3)
    Checking wait-timeout v0.2.1
    Checking decode v0.0.1 (/workbench/crates/decode)
    Checking checkouts v0.0.1 (/workbench/crates/checkouts)
    Checking sandbox v0.0.1 (/workbench/crates/sandbox)
    Checking tagptr v0.2.0
    Checking bit-vec v0.8.0
    Checking graph v0.0.1 (/workbench/crates/graph)
    Checking compression-core v0.4.33
    Checking quick-error v1.2.3
    Checking compression-codecs v0.4.45
    Checking rusty-fork v0.3.1
    Checking moka v0.12.16
    Checking bit-set v0.8.0
    Checking rand_xorshift v0.4.0
    Checking object v0.40.0
    Checking unarray v0.1.4
    Checking proptest v1.11.0
    Checking async-compression v0.4.50
    Checking vsock v0.5.4
    Checking vte v0.15.0
    Checking async-tar v0.6.1
error: using `chunks_exact` with a constant chunk size
   --> crates/minimald-rpc/src/trace.rs:199:46
    |
199 |     for (byte, pair) in out.iter_mut().zip(s.chunks_exact(2)) {
    |                                              ^^^^^^^^^^^^^^^
    |
help: consider using `as_chunks::<2>()` instead
   --> crates/minimald-rpc/src/trace.rs:199:46
    |
199 |     for (byte, pair) in out.iter_mut().zip(s.chunks_exact(2)) {
    |                                              ^^^^^^^^^^^^^^^
    = 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: could not compile `minimald-rpc` (lib) due to 1 previous error
warning: build failed, waiting for other jobs to finish...

Review threads the coder judged:

  • 👍 valid — crates/minvmd/src/bep_attach.rs: BoxIdText prints 32 lowercase hex digits again (BoxId::simple), the same form as bep's box_id_text and the audit subject. minted_box_id_is_the_record_key_type pins it.

Records and replies written before the merge read back and write the same bytes. The record, the wire, the daemon and the VM host all use the one boxes::BoxId type. The VM host log now spells a box id as 32 hex digits, the same form as the audit subject and the box control wire.

Notes from the agent: Revise round 1: BoxIdText in minvmd goes back to 32 lowercase hex digits through BoxId::simple(). The test now pins that form. The minvmd crate does not depend on bep, so the test compares against a hex rendering of the raw bytes, not bep::listener::box_id_text. The record on disk and the in-VM daemon log still use the hyphenated form, as boxes::BoxId documents. Clippy on minvmd shows one warning in crates/minimald-rpc/src/trace.rs (chunks_exact_to_as_chunks). That file is outside this branch's diff.

The merged box id type prints hyphenated, and minvmd's control tests
compare its log and audit lines against that spelling. minimald now
logs the id the VM host handed in, and the id docs say that the in-VM
store still mints the record key until BOX-002.

@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.

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

Comment thread crates/minvmd/src/bep_attach.rs Resolved

@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: CONDITIONS · 2 conditions · the full ruling

The box id type merge conforms off a VM guest, and the code is in the right crates. On a VM guest the in-VM store still mints the record key, but architecture.md line 495 says a party outside the VM mints the box_id. The head documents this as "until BOX-002", but it links no issue. C1 adds the issue URL, the flip condition and a residual in the PR body. The ask audit record's box_id changes to the hyphenated form, but the BEP audit subject stays 32 hex. Line 495 says ids key every audit entry, so C2 keeps audit records in 32 hex.

Ruled at 731c8cf against gominimal/arch@109541a48c31 by claude-opus-5-5.

Comment thread crates/boxes/src/lib.rs Resolved
Comment thread crates/boxes/src/lib.rs Resolved
Comment thread crates/minimald/src/box_manager.rs Resolved
Comment thread crates/minvmd/src/bep_attach.rs Resolved
Comment thread crates/boxes/src/lib.rs Resolved
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 2 of 10 on a failed check suite, pushed as 731c8cf256f6.

line exit tail
cargo nextest run -p boxes record_json_written_before_the_merge_round_trips 0 Applying loadouts: default Running task runtime-implement-test-0 in session task-runtime-implement-test-0-60d2... Compiling args v0.0.1 (/workbench/crates/args) Compiling ot v0.0.1 (/workbench/crates/ot) Compiling paths v0.0.1 (/workbench/crates/paths) Compiling common v0.0.1 (/workbench
cargo nextest run -p minimald-rpc every_reply_id_round_trips_byte_for_byte 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-e961... Compiling common v0.0.1 (/workbench/crates/common) Compiling boxes v0.0.1 (/workbench/crates/boxes) Compiling minimald-rpc v0.0.1 (/workbench/crates/minimald-rpc) Finished '
cargo nextest run -p minimald creation_order_holder_follows_box_id_time_order 0 Applying loadouts: default Running task runtime-implement-test-2 in session task-runtime-implement-test-2-65cf... Compiling ot v0.0.1 (/workbench/crates/ot) Compiling args v0.0.1 (/workbench/crates/args) Compiling paths v0.0.1 (/workbench/crates/paths) Compiling stdlib v0.0.22 (/workbenc
cargo nextest run -p minvmd minted_box_id_is_the_record_key_type 0 Applying loadouts: default Running task runtime-implement-test-3 in session task-runtime-implement-test-3-4b0a... Compiling ot v0.0.1 (/workbench/crates/ot) Compiling args v0.0.1 (/workbench/crates/args) Compiling version v0.8.0 (/workbench/crates/version) Compiling minvmd v0.8.0 (/workb

Verify min task run agent-verify exited 101 under rustc 1.98.1, which the repository does not pin (1.97.0 in rust-toolchain.toml); the PR is not a draft on that alone — CI, which honours the pin, is the gate.

the sandbox ran rustc (1.98.1), the repository pins 1.97.0 in rust-toolchain.toml; a failure here may be the newer toolchain's, not this change's
Applying loadouts: default
Running task runtime-implement-verify in session task-runtime-implement-verify-650f...
    Checking args v0.0.1 (/workbench/crates/args)
    Checking ot v0.0.1 (/workbench/crates/ot)
    Checking paths v0.0.1 (/workbench/crates/paths)
   Compiling version v0.8.0 (/workbench/crates/version)
    Checking switch v0.0.1 (/workbench/crates/switch)
    Checking common v0.0.1 (/workbench/crates/common)
   Compiling minvmd v0.8.0 (/workbench/crates/minvmd)
   Compiling stdlib v0.0.22 (/workbench/crates/stdlib)
    Checking diagnostics v0.0.1 (/workbench/crates/diagnostics)
    Checking boxes v0.0.1 (/workbench/crates/boxes)
    Checking sandbox v0.0.1 (/workbench/crates/sandbox)
    Checking async-dialog v0.0.1 (/workbench/crates/async-dialog)
    Checking mlog v0.0.1 (/workbench/crates/mlog)
    Checking minimald-rpc v0.0.1 (/workbench/crates/minimald-rpc)
    Checking mfile v0.0.1 (/workbench/crates/mfile)
    Checking checkouts v0.0.1 (/workbench/crates/checkouts)
    Checking decode v0.0.1 (/workbench/crates/decode)
error: using `chunks_exact` with a constant chunk size
   --> crates/minimald-rpc/src/trace.rs:199:46
    |
199 |     for (byte, pair) in out.iter_mut().zip(s.chunks_exact(2)) {
    |                                              ^^^^^^^^^^^^^^^
    |
help: consider using `as_chunks::<2>()` instead
   --> crates/minimald-rpc/src/trace.rs:199:46
    |
199 |     for (byte, pair) in out.iter_mut().zip(s.chunks_exact(2)) {
    |                                              ^^^^^^^^^^^^^^^
    = 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: could not compile `minimald-rpc` (lib) due to 1 previous error
warning: build failed, waiting for other jobs to finish...
error: could not compile `minimald-rpc` (lib test) due to 1 previous error

Review threads the coder judged:

  • 👍 valid — crates/minimald/src/box_manager.rs: create now copies config.box_id before build_record and logs it as box_id when it is Some. It logs the record key only when it is None.
  • 👍 valid — crates/boxes/src/lib.rs: The BoxId doc now says that on a VM guest the in-VM store mints Record::id inside the VM, and that Record::box_id is the box's id there until BOX-002.
  • 👍 valid — crates/boxes/src/lib.rs: Record::id doc now says that on a VM guest it is the in-VM store's key, not the VM host's id, and points to Record::box_id.
  • 👍 valid — crates/minvmd/src/bep_attach.rs: The docs on mint_box_id and mint_record_box_id now say that the in-VM daemon stores the id in the record's box_id field, not as the key.
  • 👎 invalid — crates/boxes/src/store.rs:878: The deferral is real, but filing an issue is not a code change and this round has no credential to file one. The deferral is named in the BoxId and Record::id docs and in the round notes, so a person can file and link it.
  • 👍 valid — crates/minvmd/src/bep_attach.rs: BoxIdText now prints the hyphenated Display of minimald_rpc::BoxId, the same as minimald's log line. Its doc no longer claims a hex form. This also fixes the two failing minvmd control tests.
  • 👎 invalid — crates/boxes/src/store.rs:878: This needs a change outside the task's layers. crates/minimald/src/box_actor/tests.rs hands the one HANDED_BOX_ID constant to every box, so a store that files under the handed id refuses the second creation. Round 1 tried it and reverted it for this reason. It needs a task that includes that test fi
  • 👎 invalid — crates/boxes/src/lib.rs: This depends on C1, which is not in this round (see the store.rs thread). The doc now says what is true at this head: the VM host mints the box id, and the in-VM store still mints the record key.
  • 👎 invalid — crates/minimald/src/box_manager.rs: C1 is not in this round, so without a change the label stays false. Per the companion thread on this line, box_id now logs the handed config.box_id when it is Some.

A box record or a reply written before the merge still reads back and writes the same bytes. Every crate names a box with the one boxes::BoxId type. A minimald log line and a minvmd log or audit line print a box id in the same hyphenated form.

Notes from the agent: CI failure: minvmd control::tests::ask_outcomes_written_to_host_audit and box_addresses_allocated_on_host_and_handed_to_daemon compare log and audit lines with the Display of the merged BoxId, which is hyphenated. BoxIdText printed 32 hex digits. BoxIdText now prints the hyphenated form, and both tests pass. Follow-up outside the layers: bep::listener::box_id_text (crates/bep/src/listener.rs:64) still prints 32 hex digits in the proxy's log lines. C1 (the in-VM store files the record under the handed box id) is not done: crates/minimald/src/box_actor/tests.rs gives one HANDED_BOX_ID to every box, so the store refuses the second creation. That test file is outside this task's layers. The BOX-002 work needs a task that includes it. I cannot file an issue, so a person must file it and link it from the pull request. Pre-existing clippy warnings in minimald-rpc/src/trace.rs, minimald/src/box_runtime/handle.rs and minimald/src/net/switch.rs are in files this branch does not touch.

@mitodrummer

Copy link
Copy Markdown
Member

/revise Apply the two conditions from the arch-review check on 731c8cf.

C1. Give the VM-guest interim its owner, #2397. That is T13 in this epic, "Mint every box's id in the VM host and take it only from there" (covers BOX-002). Its box_manager.rs layer is "id only from VM host".

  • Replace the bare BOX-002 with https://github.com/gominimal/minimal/issues/2397 in three places: the BoxId doc in crates/boxes/src/lib.rs (~line 971, "until BOX-002 files the record under it"), the Record::id doc (~line 1217), and the comment in BoxManager create in crates/minimald/src/box_manager.rs (~line 1304).
  • In the BoxId doc, state the flip condition: the interim ends when DiskLoader::create keys a record by a handed config.box_id instead of minting one.
  • Add a ## Residuals section to the PR body. It names T13 — Mint every box's id in the VM host and take it only from there #2397, and it says that on a VM guest Record::id is still minted inside the VM, so the title's "one key" holds only off a VM guest until T13 — Mint every box's id in the VM host and take it only from there #2397 lands.

C2. Keep one spelling of the box id in audit records.

  • In crates/minvmd/src/control.rs AskAudit::with_facts, write box_id as 32 lowercase hex: minimald_rpc::BoxId::from_bytes(facts.box_id).simple(). That is what bep::listener::box_id_text gives every BEP audit subject, and what the box-admissions.log lines written before this PR carry. Log lines can keep the hyphenated BoxIdText.
  • Change the BoxIdText doc in crates/minvmd/src/bep_attach.rs (~line 143) to say it is the log-line spelling only.
  • Change the paragraph "One id has one printed spelling" in crates/boxes/src/lib.rs (~line 982) to name 32 hex as the audit-record spelling.
  • Add a minvmd test that pins the ask audit line's box_id as facts.box_id in 32 hex.

Run the plan's test lines and cargo nextest run -p minvmd for the new audit test.

Audit records keep the 32-hex spelling that every BEP audit subject and
older box-admissions.log lines carry. Log lines keep the hyphenated form.
The VM-guest interim docs now link #2397.

@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 · the full ruling

This head resolves the two open points of the ruling on 731c8cf. The ask audit record writes the box id as 32 hex again, which is the same form as on base and in each BEP audit subject. The VM-guest record-key interim now links issue 2397 and states the condition that ends it. The change agrees with architecture.md line 495 and Gatehouse §5.2 line 244. Issue 2397 is a residual.

Ruled at 1e04eb7 against gominimal/arch@109541a48c31 by claude-opus-5-5.

@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: 16 unresolved threads — minimal-foundry[bot] crates/minvmd/src/bep_attach.rs, minimal-arch[bot] crates/minimald/src/box_manager.rs, minimal-arch[bot] crates/boxes/src/lib.rs, minimal-arch[bot] crates/boxes/src/lib.rs, minimal-arch[bot] crates/minvmd/src/bep_attach.rs, …. No findings.

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

@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 3 of 10 on a /revise note, pushed as 1e04eb7f43c4.

line exit tail
cargo nextest run -p boxes record_json_written_before_the_merge_round_trips 0 Applying loadouts: default Running task runtime-implement-test-0 in session task-runtime-implement-test-0-43df... Compiling args v0.0.1 (/workbench/crates/args) Compiling ot v0.0.1 (/workbench/crates/ot) Compiling paths v0.0.1 (/workbench/crates/paths) Compiling common v0.0.1 (/workbench
cargo nextest run -p minimald-rpc every_reply_id_round_trips_byte_for_byte 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-bcd2... Compiling common v0.0.1 (/workbench/crates/common) Compiling boxes v0.0.1 (/workbench/crates/boxes) Compiling minimald-rpc v0.0.1 (/workbench/crates/minimald-rpc) Finished '
cargo nextest run -p minimald creation_order_holder_follows_box_id_time_order 0 Applying loadouts: default Running task runtime-implement-test-2 in session task-runtime-implement-test-2-e46a... Compiling args v0.0.1 (/workbench/crates/args) Compiling ot v0.0.1 (/workbench/crates/ot) Compiling paths v0.0.1 (/workbench/crates/paths) Compiling stdlib v0.0.22 (/workbenc
cargo nextest run -p minvmd minted_box_id_is_the_record_key_type 0 Applying loadouts: default Running task runtime-implement-test-3 in session task-runtime-implement-test-3-4cdb... Compiling ot v0.0.1 (/workbench/crates/ot) Compiling args v0.0.1 (/workbench/crates/args) Compiling version v0.8.0 (/workbench/crates/version) Compiling minvmd v0.8.0 (/workb

Verify min task run agent-verify exited 101 under rustc 1.98.1, which the repository does not pin (1.97.0 in rust-toolchain.toml); the PR is not a draft on that alone — CI, which honours the pin, is the gate.

crypt-pbkdf v0.11.0
    Checking argon2 v0.6.0-rc.8
    Checking ssh-cipher v0.3.0
    Checking mlog v0.0.1 (/workbench/crates/mlog)
    Checking ed25519-dalek v3.0.0
    Checking generic-array v0.14.7
    Checking sha3 v0.11.0
    Checking p256 v0.14.0
    Checking p384 v0.14.0
    Checking p521 v0.14.0
    Checking module-lattice v0.2.3
    Checking kem v0.3.0
    Checking sponge-cursor v0.1.0
    Checking data-encoding v2.11.1
    Checking constcat v0.6.1
    Checking managed v0.8.0
    Checking bitflags v1.3.2
    Checking tinyvec_macros v0.1.1
    Checking sha3 v0.12.0
    Checking tinyvec v1.12.0
    Checking smoltcp v0.14.0
    Checking ml-kem v0.3.2
    Checking ssh-key v0.7.0-rc.11
    Checking generic-array v1.4.4
    Checking russh-cryptovec v0.62.0
    Checking num-bigint v0.5.1
    Checking russh-util v0.52.0
    Checking hex-literal v1.1.0
    Checking switch v0.0.1 (/workbench/crates/switch)
    Checking hickory-proto v0.26.3
    Checking russh v0.63.3
    Checking clap_complete v4.6.11
    Checking sysinfo v0.39.6
    Checking hashbrown v0.14.5
    Checking serde_bytes v0.11.19
    Checking serial_test v4.0.1
    Checking dashmap v6.2.1
   Compiling minvmd v0.8.0 (/workbench/crates/minvmd)
    Checking netlink-packet-core v0.8.1
    Checking russh-sftp v2.4.0
   Compiling stdlib v0.0.22 (/workbench/crates/stdlib)
    Checking konst_macro_rules v0.2.19
    Checking minimald-rpc v0.0.1 (/workbench/crates/minimald-rpc)
    Checking konst v0.2.20
    Checking mfile v0.0.1 (/workbench/crates/mfile)
    Checking netlink-sys v0.8.8
    Checking const_format v0.2.36
    Checking derive_builder v0.20.2
    Checking nix v0.30.1
    Checking netlink-packet-route v0.25.1
    Checking procfs-core v0.18.0
    Checking hash32 v0.2.1
    Checking itertools v0.15.0
    Checking spin v0.9.9
    Checking generational-arena v0.2.9
    Checking strum v0.27.2
    Checking pathrs v0.2.5
    Checking heapless v0.7.17
    Checking oci-spec v0.10.0
    Checking decode v0.0.1 (/workbench/crates/decode)
    Checking checkouts v0.0.1 (/workbench/crates/checkouts)
error: using `chunks_exact` with a constant chunk size
   --> crates/minimald-rpc/src/trace.rs:199:46
    |
199 |     for (byte, pair) in out.iter_mut().zip(s.chunks_exact(2)) {
    |                                              ^^^^^^^^^^^^^^^
    |
help: consider using `as_chunks::<2>()` instead
   --> crates/minimald-rpc/src/trace.rs:199:46
    |
199 |     for (byte, pair) in out.iter_mut().zip(s.chunks_exact(2)) {
    |                                              ^^^^^^^^^^^^^^^
    = 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: could not compile `minimald-rpc` (lib) due to 1 previous error
warning: build failed, waiting for other jobs to finish...

Outside the task's layers::

  • crates/minvmd/src/control.rs

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

Review threads the coder judged:

  • 👍 valid — crates/minvmd/src/bep_attach.rs:155: AskAudit::with_facts now writes box_id as 32 hex (BoxId::simple), the same spelling as bep::box_id_text, so audit lines match the proxy's audit subjects. Log lines stay hyphenated.
  • 👍 valid — crates/boxes/src/lib.rs: BoxId doc now links T13 — Mint every box's id in the VM host and take it only from there #2397 and states that the interim ends when DiskLoader::create keys a record by a handed config.box_id instead of minting one.
  • 👍 valid — crates/boxes/src/lib.rs:1222: Record::id doc now links T13 — Mint every box's id in the VM host and take it only from there #2397 next to the note that a VM guest mints this key inside the VM.
  • 👍 valid — crates/minimald/src/box_manager.rs: Replaced the bare BOX-002 in the BoxManager create comment with the T13 — Mint every box's id in the VM host and take it only from there #2397 issue URL.
  • 👍 valid — crates/minvmd/src/bep_attach.rs: BoxIdText doc now says it is the log-line spelling only. The ask audit box_id uses .simple(), and a new test pins it as 32 hex.
  • 👍 valid — crates/boxes/src/lib.rs: The spelling paragraph in the BoxId doc now names 32 lowercase hex as the audit-record spelling (BEP audit subject, ask audit box_id, box-admissions.log).

Records and replies written before the merge still read back as the same id. Log lines spell a box id in the hyphenated form. Every audit record, including the ask audit line's box_id, spells it as 32 lowercase hex. The VM-guest interim, where Record::id is still minted inside the VM, now links #2397 and states its flip condition.

Notes from the agent: Out of layers: crates/minvmd/src/control.rs. The /revise note C2 named it explicitly. AskAudit::with_facts now writes minimald_rpc::BoxId::from_bytes(facts.box_id).simple(). The new test ask_audit_line_spells_box_id_as_32_hex is in control.rs tests. The existing test ask_outcomes_written_to_host_audit pinned the hyphenated form, so it now matches web.box_id.simple(). The first full minvmd run had one failure in cmd::run::tests::concurrent_boots_never_draw_the_same_proxy_port (a port race). It passed on the two runs after that, and this change does not touch that code. C1 PR body: the runner writes the body, so I did not add a Residuals section. Add this text to the body: '## Residuals — #2397 (T13). On a VM guest, Record::id is still minted inside the VM, so the title's "one key" holds only off a VM guest until #2397 lands.'

@minimal-foundry

Copy link
Copy Markdown
Contributor Author

A merge of main before round 4, not counted against the cap (1 of 3), pushed as ae9fe701cfdb.

Resolved conflicts in: crates/minimald/src/box_manager/tests.rs

line exit tail
cargo nextest run -p boxes record_json_written_before_the_merge_round_trips 0 ment-test-0 in session task-runtime-implement-test-0-c263... Updating crates.io index Downloading crates ... Downloaded core_detect v1.0.0 Downloaded bit-vec v0.10.1 Downloaded borsh-derive v1.8.1 Downloaded bit-set v0.11.1 Downloaded borsh v1.8.1 Downloaded arbitrary v1.5.0 Downl
cargo nextest run -p minimald-rpc every_reply_id_round_trips_byte_for_byte 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-d713... Compiling jaq-fmts v0.1.1 Compiling jaq-all v0.3.0 Compiling common v0.0.1 (/workbench/crates/common) Compiling boxes v0.0.1 (/workbench/crates/boxes) Compiling minimald-r
cargo nextest run -p minimald creation_order_holder_follows_box_id_time_order 0 om/tweag/topiary.git?rev=838c74ab4058f82bc3c6a12380f22c10f22ac814#838c74ab) Compiling rayon v1.12.0 Compiling nickel-lang-core v0.19.0 Compiling tree-sitter-nickel v0.5.0 Compiling google-cloud-type v1.6.0 Compiling toml-span v0.7.1 Compiling jaq-fmts v0.1.1 Compiling paths v0.0
cargo nextest run -p minvmd minted_box_id_is_the_record_key_type 0 Applying loadouts: default Running task runtime-implement-test-3 in session task-runtime-implement-test-3-7f9e... Compiling parking_lot_core v0.9.12 Compiling tracing-subscriber v0.3.23 Compiling nickel-lang-parser v0.4.0 Compiling jaq-fmts v0.1.1 Compiling parking_lot v0.12.5 Comp

Verify min task run agent-verify exited 101 under rustc 1.98.1, which the repository does not pin (1.97.0 in rust-toolchain.toml); the PR is not a draft on that alone — CI, which honours the pin, is the gate.

apless v0.7.17
    Checking oci-spec v0.10.0
    Checking procfs v0.18.0
    Checking netconfig-rs v0.1.6
    Checking nix v0.29.0
    Checking netlink-packet-route v0.31.0
    Checking cobs v0.3.0
    Checking getifaddrs v0.6.2
    Checking path-dedot v4.0.1
    Checking fixedbitset v0.5.7
    Checking path-absolutize v4.0.1
    Checking libcgroups v0.7.0
    Checking tun-rs v2.8.8
    Checking route_manager v0.2.13
    Checking postcard v1.1.3
    Checking close_fds v0.3.2
    Checking caps v0.5.6
    Checking sendfd v0.4.4
    Checking size v0.5.0
    Checking wait-timeout v0.2.1
    Checking quick-error v1.2.3
    Checking compression-core v0.4.33
    Checking tagptr v0.2.0
    Checking bit-vec v0.10.1
    Checking compression-codecs v0.4.45
    Checking moka v0.12.16
    Checking bit-set v0.11.1
    Checking rusty-fork v0.3.1
    Checking hakoniwa v1.7.2 (https://github.com/souk4711/hakoniwa.git?rev=0810ffa37620ef5c57de263c8eaa1f4d7633c14a#0810ffa3)
    Checking rand_xorshift v0.5.0
    Checking object v0.40.0
    Checking core_detect v1.0.0
    Checking unarray v0.1.4
    Checking async-compression v0.4.50
    Checking proptest v1.12.0
    Checking vsock v0.5.4
    Checking vte v0.15.0
    Checking async-tar v0.6.1
    Checking vt100 v0.16.2 (https://github.com/gominimal/vt100-rust.git?rev=9b8cce5a6798daf061948259ebcb073bb1ea54a6#9b8cce5a)
    Checking tokio-vsock v0.7.2
    Checking async-dialog v0.0.1 (/workbench/crates/async-dialog)
    Checking diagnostics v0.0.1 (/workbench/crates/diagnostics)
    Checking nickel-lang-core v0.19.0
    Checking args v0.0.1 (/workbench/crates/args)
    Checking common v0.0.1 (/workbench/crates/common)
    Checking boxes v0.0.1 (/workbench/crates/boxes)
    Checking sandbox v0.0.1 (/workbench/crates/sandbox)
    Checking minimald-rpc v0.0.1 (/workbench/crates/minimald-rpc)
    Checking mfile v0.0.1 (/workbench/crates/mfile)
    Checking checkouts v0.0.1 (/workbench/crates/checkouts)
    Checking decode v0.0.1 (/workbench/crates/decode)
error: using `chunks_exact` with a constant chunk size
   --> crates/minimald-rpc/src/trace.rs:199:46
    |
199 |     for (byte, pair) in out.iter_mut().zip(s.chunks_exact(2)) {
    |                                              ^^^^^^^^^^^^^^^
    |
help: consider using `as_chunks::<2>()` instead
   --> crates/minimald-rpc/src/trace.rs:199:46
    |
199 |     for (byte, pair) in out.iter_mut().zip(s.chunks_exact(2)) {
    |                                              ^^^^^^^^^^^^^^^
    = 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: could not compile `minimald-rpc` (lib) due to 1 previous error
warning: build failed, waiting for other jobs to finish...
error: could not compile `minimald-rpc` (lib test) due to 1 previous error

Outside the task's layers::

  • crates/minvmd/src/control.rs

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

The branch merges main without conflicts. Record JSON written before the merge and every RPC reply id still round-trip. The box id is the one id type that the store, the wire, the daemon and minvmd use.

Notes from the agent: This round resolved the merge conflict in crates/minimald/src/box_manager/tests.rs. The resolution keeps both tests: this branch's creation_order_holder_follows_box_id_time_order and main's sealed_deliveries_ride_the_record_to_the_host_params. The merge commit is c013190. The other files in the merge commit come from main, not from this task. sealed_deliveries_ride_the_record_to_the_host_params also passes on the merged tree. No thread verdict changed this round.

@mitodrummer
mitodrummer marked this pull request as ready for review October 24, 2026 19:32

@mitodrummer mitodrummer 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.

Babysit review on ae9fe70 against T45's plan block.

  • Type: SessionId is now pub type SessionId = BoxId, and BoxId wraps a UUIDv7 Uuid. Its derived Ord follows creation time, which the creation-order holder relies on.
  • Spellings: the default serde form and Display are the hyphenated UUID, as SessionId had. Every field that carried 32 hex (record box_id, BoxConfig, the box-control requests and replies) keeps it through box_id_hex. The deserializer accepts both spellings. Only JSON and TOML carry these ids, so moving from Uuid's derived serde to text parsing loses nothing. No binary serde format is in the workspace.
  • Proofs: record_json_written_before_the_merge_round_trips checks that an old record reads back and rewrites unchanged. every_reply_id_round_trips_byte_for_byte does the same for replies, and minted_box_id_is_the_record_key_type ties minvmd's mint to the record key type.
  • Arch conditions: "filed the box record" logs the VM-handed id when there is one (C1). Audit records keep 32 hex (C2, control.rs, accepted outside the layers). The VM-guest interim is owned by #2397 (Residuals).
  • CI: green on this head, and arch-review is PASS on the change before the merge of main.

@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 · the full ruling

This head merges main twice into the branch. The PR's own change lines did not change since the PASS on 1e04eb7, so that ruling stands. I checked the new BEP-007 code from main. It accepts the hyphenated box id that Display now prints, and the proxy still gets 32 hex digits. The VM-guest interim stays the filed residual #2397. CI is the compile gate for the merged tree.

Ruled at ae9fe70 against gominimal/arch@109541a48c31 by claude-opus-5-5.

@minimal-foundry minimal-foundry Bot added the review:approved minimal-review approved the current head label Oct 24, 2026
@mitodrummer

Copy link
Copy Markdown
Member

/revise Merge the current origin/main (20e25e4 or later) into this branch and make no other change. The merge queue on main is gone, so this PR merges directly. Its CI has to run against today's main, not 10-22's, which is when the branch last took main. Resolve any conflicts in favour of the branch's changes, and run the plan's four test lines after the merge.

@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 4 of 10 on a /revise note: the coder changed nothing. every commit this round put on the branch above ae9fe70 is a merge of the base branch, so it carries no work of its own

@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 · the full ruling

This head merges main into the branch. The lines that the PR adds and removes are the same as on ae9fe701, which passed. The new proxy grant code from main sends the box id through mint::box_id_hex, so the hyphenated Display does not change the id that the proxy sees. The PASS stands. The VM-guest record key stays the filed interim in #2397.

Ruled at 21c8592 against gominimal/arch@109541a48c31 by claude-opus-5-5.

@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Revise round 2 ran against ci-linux-native-success, tests and left it red; a coder round cannot clear it, a person should look. No round was started for the failed suite on 21c8592af131.

@norrietaylor norrietaylor changed the title T45 — Make the box id the one key for every record refactor(boxes): make the box id the one key for every record Oct 24, 2026

@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 verification at 21c8592. This head is GitHub's merge of main fa31776 onto the reviewed head; arch ruled PASS and minimal-review concluded. I read the full diff at this head: every BoxId field on the minimald-rpc wire (BoxConfig, RegisteredBox, WithdrawBoxRequest, ResumeBoxRequest, RowStandingRequest, BoxRow, SubscribeAsksRequest, PendingAskOffer, BoxControlReply::AsksSubscribed) carries the box_id_hex adapter, so the 32-hex bytes stay as they were while Record::id and the session replies keep the hyphenated form; every_reply_id_round_trips_byte_for_byte and record_json_written_before_the_merge_round_trips pin both. The minvmd ids stay the switch's raw 16 bytes, so no other wire changes. One visible change, as the body says: BoxIdText log lines and the two NotTheBoxId refusals now print the hyphenated id, while the ask audit record keeps 32 hex (pinned by ask_audit_line_spells_box_id_as_32_hex). Zero open threads; ci-success, native, kvm, shell-installer, cargo-deny and commitlint green; ci-macos-success queued behind the single runner. Squash title refactor(boxes): make the box id the one key for every record passes commitlint. The hex dependency of the boxes crate is now unused in its sources; a nit for a later cleanup, not this PR. Residual #2397 (VM guest record key) is filed and linked from the body.


Generated by Claude Code

@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 approval at 21c8592: every merge gate passes at this head (arch PASS, zero open threads, every lane aggregator green including ci-macos-success, bot resolutions re-verified). Squash title refactor(boxes): make the box id the one key for every record and the squashed message pass commitlint. Queued for squash merge.


Generated by Claude Code

@norrietaylor
norrietaylor added this pull request to the merge queue Oct 24, 2026
Merged via the queue into main with commit b197a79 Oct 24, 2026
40 of 42 checks passed
@norrietaylor
norrietaylor deleted the agent/2385-make-the-box-id-the-one-key-for-every-record branch October 24, 2026 23:06
norrietaylor pushed a commit that referenced this pull request Nov 4, 2026
Policy and destroy resolve a box's VM from its name, as attach, exec, run and net forward do.
A box no running VM holds names --vm, a box on a stopped VM names the command that starts it,
and a name any two VMs hold, running or stopped, is refused with every VM listed. A relay
failure writes the unwind before the attach error prints, so the error stays on screen.

Backport of #2811. Adapted to the line: cmd/boxes/attach.rs and policy.rs hunks land in
cmd/session.rs. Dropped, because the line has no stopped session status (#2676) and keeps box
ids apart from session ids (#2485): min ls rows for a stopped VM's boxes, vm_running in its
JSON, and id-prefix matching against a stopped VM's records, which match by name only here.

(cherry picked from commit 2e3962f)
norrietaylor pushed a commit that referenced this pull request Nov 5, 2026
Policy and destroy resolve a box's VM from its name, as attach, exec, run and net forward do.
A box no running VM holds names --vm, a box on a stopped VM names the command that starts it,
and a name any two VMs hold, running or stopped, is refused with every VM listed. A relay
failure writes the unwind before the attach error prints, so the error stays on screen.

Backport of #2811. Adapted to the line: cmd/boxes/attach.rs and policy.rs hunks land in
cmd/session.rs. Dropped, because the line has no stopped session status (#2676) and keeps box
ids apart from session ids (#2485): min ls rows for a stopped VM's boxes, vm_running in its
JSON, and id-prefix matching against a stopped VM's records, which match by name only here.

(cherry picked from commit 2e3962f)
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.

T45 — Make the box id the one key for every record

2 participants