Skip to content

feat(minvmd): start the Box Egress Proxy beside gvproxy so git and gh reach GitHub - #2497

Merged
bryan-minimal merged 15 commits into
mainfrom
agent/2275-run-the-proxy-beside-gvproxy-so-git-and-gh-reach
Oct 24, 2026
Merged

bryan-minimal merged 15 commits into
mainfrom
agent/2275-run-the-proxy-beside-gvproxy-so-git-and-gh-reach

Conversation

@minimal-foundry

@minimal-foundry minimal-foundry Bot commented Oct 23, 2026 •

Copy link
Copy Markdown
Contributor

T18 — Run the proxy beside gvproxy so git and gh reach GitHub from a box

slice: S0
kind: task
covers: BEP-015
size: L
est: 280 code, 220 tests
executor: agent
difficulty: unknown ground
model: strongest
diagnostics: the support bundle carries the proxy's log tail and the audit log segments, collected beside the VM host daemon's log
observability: one info log line when the VM host daemon starts the proxy, naming its socket and pid, and one warn line when it exits
layers:
- host:
- crates/minvmd/src/cmd/run.rs: starts bep serve beside gvproxy with the per-boot token in production, the stub staying test-only
test: cargo nextest run -p minvmd proxy_is_started_with_the_per_boot_token
- ship:
- justfile: builds and signs the bep binary beside minvmd
- crates/minimal/src/diag/collect.rs: collects the proxy log and the audit segments
test: cargo nextest run -p minimal bundle_collects_the_proxy_log_and_audit_segments
- e2e:
- scripts/session-e2e.sh: adds the case; the T14 leg bep_second_box_needs_no_sign_in records NOT RUN on every lane until this task starts bep serve, and must record a pass on the macOS lane against the live proxy (arch C1 on #2490, residual filed here; do not change that leg to pass without a proxy); the T16 grant legs bep_root_ca_present_in_box_trust_store, the grant half of bep_root_ca_absent_from_box_without_credentialed_upstream and bep_trust_env_points_at_bundle_and_root record NOT RUN off macOS the same way and must each record a pass on the macOS lane against the live proxy (arch C2 on #2495, residual filed here)
test: ./scripts/session-e2e.sh bep_git_and_gh_against_private_repo
test: ./scripts/session-e2e.sh bep_second_box_needs_no_sign_in
test: ./scripts/session-e2e.sh bep_box_env_holds_sealed_value_only
produces: none
consumes:
- crates/bep/src/main.rs
- crates/bep/src/forward.rs
proof: From a box holding only a sealed member, git clone, git push and gh api succeed against a private repository.
depends on:
- blocked by #2259
- blocked by #2272
- blocked by #2273
- blocked by #2274
- blocked by #2334
- blocked by #2483
- blocked by #2488

Proof

Not shown on this branch. A macOS boot of minvmd now starts bep serve --listener <provider>/gvproxy-bep.sock. It gives the per-boot token on standard input, appends the proxy output to /bep.log, and binds the boxes' pool shares. min bug collects bep.log and the newest audit segments. The e2e case bep_git_and_gh_against_private_repo runs git clone, git push and gh api from a proxy_env grant box, but only on the macOS lane with a sign-in and E2E_BEP_PRIVATE_REPO set. Nobody ran it, and I expect the git half to fail. See notes.

Notes from the agent: 1) Likely product gap for the proof: git in a box has no way to send the sealed value. The forwarder substitutes only a request that carries a sealed value (Authorization Bearer/token/Basic x-access-token:), and a request without one goes upstream unchanged. gh reads GH_TOKEN, so gh api can work. git reads no GH_TOKEN, and nothing in minimald gives a box a git credential helper at creation (I found no gitconfig or credential.helper writer). The case does not configure git in the box, as BEP-015 says. So I expect git clone of a private repo to fail on the macOS lane until a box carries a credential helper (for example gh auth git-credential) at creation. That change is in minimald, which is outside this task's layers. 2) Judgement call in run.rs: bep_box_source now registers the boxes' pool shares when bep serve started, not only under MINVMD_BEP_STUB. Without that, no box connection reaches the proxy. The credentialed-only gate rule (NET-145, #1665) is still ahead. The proxy admits only deliveries that carry the boot token, and it redeems only for boxes its control socket registered. I updated the doc comments and the production_wiring test doc. 3) minvmd starts bep only on macOS, because bep exits on other hosts. It does not start bep under MINVMD_BEP_STUB, or when gvproxy is absent. The binary is MINVMD_BEP_BIN, else bep beside minvmd. A missing or failed proxy is a warn, and t…[truncated]

Tests

line exit tail
cargo nextest run -p minvmd proxy_is_started_with_the_per_boot_token 0 Applying loadouts: default Running task runtime-implement-test-0 in session task-runtime-implement-test-0-8fdc... 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 version v0.8.0 (/workbenc
cargo nextest run -p minimal bundle_collects_the_proxy_log_and_audit_segments 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-a526... 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
./scripts/session-e2e.sh bep_git_and_gh_against_private_repo 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 bep_second_box_needs_no_sign_in 0 ::group::GitHub grant boxes: the second box needs no sign-in bep_second_box_needs_no_sign_in: NOT RUN (the Box Egress Proxy runs on macOS only) ::endgroup:: session e2e: 1 case(s) NOT RUN: bep_second_box_needs_no_sign_in session e2e OK Applying loadouts: default Running task runtime-implement-test-3
./scripts/session-e2e.sh bep_box_env_holds_sealed_value_only 0 ::group::GitHub grant boxes: the grant's variable holds a sealed value only bep_box_env_holds_sealed_value_only: NOT RUN (the Box Egress Proxy runs on macOS only) ::endgroup:: session e2e: 1 case(s) NOT RUN: bep_box_env_holds_sealed_value_only session e2e OK Applying loadouts: default Running task r

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.

 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-7387...
    Checking opentelemetry v0.33.1
    Checking ot v0.0.1 (/workbench/crates/ot)
    Checking args v0.0.1 (/workbench/crates/args)
    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 opentelemetry_sdk v0.33.1
    Checking tracing-opentelemetry v0.34.0
    Checking opentelemetry-http v0.33.1
    Checking google-cloud-gax-internal v0.7.20
    Checking opentelemetry-proto v0.33.0
    Checking opentelemetry-otlp v0.33.0
    Checking opentelemetry-appender-tracing v0.33.1
    Checking google-cloud-longrunning v1.14.0
    Checking google-cloud-iam-v1 v1.13.0
   Compiling minvmd v0.8.0 (/workbench/crates/minvmd)
    Checking mlog v0.0.1 (/workbench/crates/mlog)
    Checking google-cloud-lro v1.11.0
   Compiling stdlib v0.0.22 (/workbench/crates/stdlib)
   Compiling serial_test_derive v4.0.1
    Checking google-cloud-storage v1.20.0
    Checking diagnostics v0.0.1 (/workbench/crates/diagnostics)
    Checking serial_test v4.0.1
    Checking bep v0.0.1 (/workbench/crates/bep)
    Checking async-dialog v0.0.1 (/workbench/crates/async-dialog)
    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)
    Checking graph v0.0.1 (/workbench/crates/graph)
    Checking lcache v0.0.1 (/workbench/crates/lcache)
    Checking rcache v0.0.1 (/workbench/crates/rcache)
    Checking op v0.0.1 (/workbench/crates/op)
    Checking check v0.0.1 (/workbench/crates/check)
    Checking orchestrator v0.0.1 (/workbench/crates/orchestrator)
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...

Closes #2275

Layer exception

crates/switch/src/bep_host.rs is outside this task's layers:. Round 2 changed two comment lines there (lines 80 and 334) and nothing else: the credentialed-only gate they called "still ahead" landed as egress::proxy_lane_admits in #1885, and arch condition C3 on review 5623734228 (thread 4355956171) asked for the same edit in switch::bep_host that bep_box_source got. Round 3 changed two doc paragraphs in the same file (the module doc around line 80 and the NoBoxes doc around line 336) for arch condition C1 on review 5624123100 (threads 4356289331, 4356289343): they now say a boot with no listening acceptor wires NoBoxes and a boot whose bep serve listens wires CredentialedBoxes. Comment text only. Accepted under the layer-exception rule of 2026-10-19 (arch-required comment changes).

Residuals


Generated by Claude Code

The support bundle now carries providers/<name>/bep.log, beside the VM
host daemon's run.log, and the newest segments of the Box Egress
Proxy's audit log under bep/audit/.
A production macOS boot now starts the Box Egress Proxy on the socket
the switch peer dials. The token goes to its standard input, its output
to bep.log beside the socket, and the pool binds the boxes' shares once
the proxy is started. The stand-in stays behind MINVMD_BEP_STUB.
minvmd starts bep serve from its own directory, so minvmd-build now
builds bep there and signs it before minvmd's own codesign.
Adds bep_git_and_gh_against_private_repo. The T14 and T16 grant legs
now share one gate: off macOS, without gvproxy or without a sign-in
they record NOT RUN. On macOS the proxy that minvmd starts must answer
on its control socket, or the case fails with the proxy's log.
@coderabbitai

coderabbitai Bot commented Oct 23, 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: 6c64086a-5c13-4ecd-a98f-36e2dcb22d19

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-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 · 4 conditions · the full ruling

The proxy now starts beside gvproxy, as §7.1 line 244 says. The host-side gate keeps the box→host default-deny of line 248. But BEP-015 is not met. Every BEP leg records NOT RUN on every lane. Also, git in a box has no credential helper, and no task plans one (Gatehouse line 718). C1 asks for a macOS pass against the live proxy. C2 asks you to plan the helper. C3 limits pool shares to credentialed-lane boxes and corrects the comments that call the T45 gate "still ahead". C4 corrects the installer claim and files the release gap.

Ruled at f99e712 against gominimal/arch@109541a48c31 by claude-opus-5-5.

Comment thread scripts/session-e2e.sh Resolved
Comment thread scripts/session-e2e.sh Resolved
Comment thread crates/minvmd/src/cmd/run.rs Resolved
Comment thread crates/minvmd/src/cmd/run.rs Resolved
Comment thread crates/minvmd/src/cmd/run.rs Resolved

@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 T18 against its plan block, at f99e7126.

Layer host. crates/minvmd/src/cmd/run.rs starts bep serve --listener <provider>/gvproxy-bep.sock on a production macOS boot, hands it this boot's token as 64 hex digits on standard input and never in argv, appends its output to bep.log beside the socket, and a watcher thread stops it with the supervisor and logs one warn line if it exits on its own. The stand-in keeps its flag; the two never contend for the path. A missing or failed proxy is a warn and the boot goes on without a credentialed lane. proxy_is_started_with_the_per_boot_token pins the argv, the stdin token, the log and the stop. One judgement call to flag for the arch review: bep_box_source now registers the boxes' pool shares when either acceptor started, where before only the stand-in did; the doc comment and the production-wiring test's doc say why.

Layer ship. The justfile builds and signs bep beside minvmd on macOS, with BEP_CODESIGN_IDENTITY for a stable identity, since the Keychain admits the keys only to the signed program that made them. crates/minimal/src/diag/collect.rs collects bep.log from each provider dir and the newest audit segments from the proxy's audit directory, with provenance lines; two tests pin it.

Layer e2e. scripts/session-e2e.sh adds bep_git_and_gh_against_private_repo, wired into the full run, the dispatcher and the usage text, and gates it and the residual legs from T14, T42 and T16 through one bep_live_gate: off macOS, without gvproxy or without a sign-in they record NOT RUN; on a lane that qualifies the gate restarts the daemon without the stub and fails, never NOT RUN, if the proxy is not serving within 60 s. The case needs E2E_BEP_PRIVATE_REPO and records NOT RUN without it.

Two things the epic owner must decide, outside this PR's layers.

  1. The proof is not shown, and the agent expects git clone to fail: the forwarder substitutes only a request that already carries the sealed value, gh reads GH_TOKEN, but git reads no such variable and nothing in minimald gives a box a git credential helper at creation. The babysitter checked: no code under crates/minimald, crates/boxes or crates/minimal writes a credential helper or a gitconfig for a box. BEP-015 forbids tool configuration beyond what the box carries at creation, so the helper belongs to the box's launch, which is T42's and T16's ground, not T18's.
  2. CI cannot run the live legs on the macOS lane as it stands. The lane's e2e job builds its testbed with a direct cargo build -p minvmd, so bep is not beside minvmd there and the daemon boots without the proxy; and the runner holds no GitHub sign-in, so the gate records NOT RUN before it looks. The workflow is frozen, so shipping bep into the testbed is a workflow change, and the sign-in and private repository are runner provisioning.

Commits. All four pass commitlint.

No blocking findings of my own on the code. The two decisions above are put to the epic owner.


Generated by Claude Code

@minimal-foundry

minimal-foundry Bot commented Oct 23, 2026 •

Copy link
Copy Markdown
Contributor Author

Reviewed: no findings; approval withheld, 1 thread unresolved at 236f3128f869.

APPROVE withheld: 1 unresolved thread — minimal-arch[bot] crates/minvmd/src/cmd/run.rs:1493. Resolving the last thread releases the approval on this head.

Resolve the open threads. Resolving the last one releases the approval on this head; no new review is required.

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/cmd/run.rs Resolved
The pool now reads a listening flag the watcher keeps: set while bep
runs and its listener socket is new, cleared when it exits. Shares go
only to rows that declare a credentialed upstream, the same rows the
gate's proxy_lane_admits lets reach the proxy address. The comments name
that gate and say the installer does not ship bep yet.
git sends no Authorization header without a credential helper, and no
box ships one yet. The comment names the gap so the clone step's failure
on a live lane is not read as a proxy fault.

@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.

APPROVE withheld: 6 unresolved threads — minimal-arch[bot] scripts/session-e2e.sh:11753, minimal-arch[bot] scripts/session-e2e.sh:11710, minimal-arch[bot] crates/minvmd/src/cmd/run.rs, minimal-arch[bot] crates/minvmd/src/cmd/run.rs, minimal-arch[bot] crates/minvmd/src/cmd/run.rs, ….

minimal-review — advisory review

Verdict COMMENT — No findings.

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

@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 1 of 10 on the runtime's review findings, pushed as a5547ffc9376.

line exit tail
cargo nextest run -p minvmd proxy_is_started_with_the_per_boot_token 0 Applying loadouts: default Running task runtime-implement-test-0 in session task-runtime-implement-test-0-75f5... 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 version v0.8.0 (/workbenc
cargo nextest run -p minimal bundle_collects_the_proxy_log_and_audit_segments 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-a1d1... 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
./scripts/session-e2e.sh bep_git_and_gh_against_private_repo 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 bep_second_box_needs_no_sign_in 0 ::group::GitHub grant boxes: the second box needs no sign-in bep_second_box_needs_no_sign_in: NOT RUN (the Box Egress Proxy runs on macOS only) ::endgroup:: session e2e: 1 case(s) NOT RUN: bep_second_box_needs_no_sign_in session e2e OK Applying loadouts: default Running task runtime-implement-test-3
./scripts/session-e2e.sh bep_box_env_holds_sealed_value_only 0 ::group::GitHub grant boxes: the grant's variable holds a sealed value only bep_box_env_holds_sealed_value_only: NOT RUN (the Box Egress Proxy runs on macOS only) ::endgroup:: session e2e: 1 case(s) NOT RUN: bep_box_env_holds_sealed_value_only session e2e OK Applying loadouts: default Running task r

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.

 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 cobs v0.3.0
    Checking getifaddrs v0.6.2
    Checking boxes v0.0.1 (/workbench/crates/boxes)
   Compiling serial_test_derive v4.0.1
    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 serial_test v4.0.1
    Checking postcard v1.1.3
    Checking route_manager v0.2.13
    Checking caps v0.5.6
    Checking minimald-rpc v0.0.1 (/workbench/crates/minimald-rpc)
    Checking mfile v0.0.1 (/workbench/crates/mfile)
    Checking close_fds v0.3.2
    Checking sendfd v0.4.4
    Checking castaway v0.2.4
    Checking hakoniwa v1.7.2 (https://github.com/souk4711/hakoniwa.git?rev=0810ffa37620ef5c57de263c8eaa1f4d7633c14a#0810ffa3)
    Checking checkouts v0.0.1 (/workbench/crates/checkouts)
    Checking decode v0.0.1 (/workbench/crates/decode)
    Checking strum v0.28.0
    Checking sandbox v0.0.1 (/workbench/crates/sandbox)
    Checking compact_str v0.9.1
    Checking graph v0.0.1 (/workbench/crates/graph)
    Checking signal-hook v0.3.18
    Checking unicode-truncate v2.0.1
    Checking lcache v0.0.1 (/workbench/crates/lcache)
    Checking kasuari v0.4.12
    Checking lru v0.18.2
    Checking compression-core v0.4.33
    Checking rcache v0.0.1 (/workbench/crates/rcache)
    Checking size v0.5.0
    Checking compression-codecs v0.4.45
    Checking ratatui-core v0.1.2
    Checking signal-hook-mio v0.2.5
    Checking op v0.0.1 (/workbench/crates/op)
    Checking derive_more v2.1.1
    Checking tagptr v0.2.0
    Checking async-compression v0.4.50
    Checking crossterm v0.29.0
    Checking moka v0.12.16
    Checking async-tar v0.6.1
    Checking line-clipping v0.3.8
    Checking object v0.40.0
    Checking getrandom v0.2.17
    Checking ratatui-widgets v0.3.2
    Checking ring v0.17.14
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 — scripts/session-e2e.sh:11753: Holds: no box ships a git credential helper, so git sends no Authorization for the proxy to substitute. The comment above the case now records the gap. The spec requirement and its issue are outside this task's files and need a person to add and file them.
  • 👍 valid — scripts/session-e2e.sh:11710: Holds: no lane sets E2E_BEP_PRIVATE_REPO or makes a sign-in, so these cases record NOT RUN everywhere. This round ran on a Linux box with no proxy, so a macOS pass could not be recorded. It needs a run on a signed-in macOS host with a private repository named.
  • 👍 valid — crates/minvmd/src/cmd/run.rs: bep_box_source now returns CredentialedBoxes, which keeps only rows where declares_credentialed_upstream() is true. production_wiring_leaves_pool_len_zero_with_rows_registered adds a box with no lane and asserts that it holds no share.
  • 👍 valid — crates/minvmd/src/cmd/run.rs: The bep_box_source doc and the wiring test doc now name egress::proxy_lane_admits (T45 — Reach the proxy only as a credentialed lane's infrastructure #1885) and no longer say 'still ahead'. switch::bep_host is outside this task's layers and still needs the same edit.
  • 👍 valid — crates/minvmd/src/cmd/run.rs: The BEP_BIN_ENV doc now says only just minvmd-build puts bep beside minvmd. It also says dist-build.sh and the release workflow build only minvmd, and it names the release gap as a BEP-015 residual. The issue for that gap is not filed from here.
  • 👍 valid — crates/minvmd/src/cmd/run.rs:896: Shares now follow a listening flag. The watcher sets it only while bep runs and a new socket is at the listener path, and clears it on exit. The pool polls the source every turn, so shares bind only while bep listens and go away when it exits.

Not delivered on this branch. A macOS boot of minvmd starts bep serve with the per-boot token. Pool shares now bind only while bep listens, and only for boxes that declare a credentialed upstream. The proof (git clone, git push and gh api against a private repository from a box with only a sealed member) is not observed: no lane sets E2E_BEP_PRIVATE_REPO, and no box ships a git credential helper, so git sends no credential for the proxy to substitute.

Notes from the agent: Revise round 1. run.rs: the box source is now gated by a listening flag that the bep watcher sets while the child runs and its listener socket is new (device, inode and change time differ from the socket at the path before the start). The watcher clears the flag on exit. Because the pool polls the source every stack turn, a late listen grows the shares and an exit removes them. The boot does not block on it. Shares are also filtered to rows that declare a credentialed upstream. Comments now name egress::proxy_lane_admits (#1885) and say the installer does not ship bep. Not done, outside this task's layers or this box: (1) crates/switch/src/bep_host.rs still says the T45 gate is 'still ahead' (module doc near line 80 and the NoBoxes doc). It needs a change in that file. (2) The release gap (scripts/dist-build.sh and release.yml build only minvmd) needs a residual issue. I cannot file issues from here. (3) The git credential helper needs a BEP spec requirement and an issue. The spec is outside the layers, so the e2e comment records the gap without an issue number. (4) A macOS pass of the BEP cases against the live proxy needs a signed-in macOS host and a private repository. This Linux box has no KVM and no proxy. just clippy-strict was not run.

@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 · 4 conditions · the full ruling

The host half now conforms. Shares bind only for credentialed-lane rows while the proxy listens, as §7.1 line 248 requires. Four gaps still have no issue, and rule 6 refuses a residual that nobody owns. These are the shipped git-credential-helper (C1, Gatehouse §6.4 line 718), the installer that does not ship bep (C2), the BEP proof legs that no lane runs (C3), and the bep/gvproxy user split (C4, Gatehouse §6.10 line 831). File each issue, name it where the code states the gap, and list it in the PR body. Then the change conforms with those residuals open.

Ruled at a5547ff against gominimal/arch@109541a48c31 by claude-opus-5-5.

Comment thread scripts/session-e2e.sh Resolved
Comment thread scripts/session-e2e.sh Resolved
Comment thread crates/minvmd/src/cmd/run.rs Resolved
Comment thread crates/minvmd/src/cmd/run.rs Resolved

Copy link
Copy Markdown
Member

/revise

Arch review 5623925208 at a5547ff rules CONDITIONS with four residuals to name. The issues now exist; this round names them where the code states each gap and lists them in the PR body. It also finishes the T45 comment edit that round 1 left.

Name the residual issues (threads 4356113702, 4356113708, 4356113718, 4356113724)

  1. scripts/session-e2e.sh, the header comment above proof_bep_git_and_gh_against_private_repo (~line 11707): replace the sentences "the BEP spec has no requirement for it and no issue tracks it. Until both exist," with one that gives the issue: Ship a git credential helper in grant boxes so git sends a header the proxy substitutes #2499 (Ship a git credential helper in grant boxes so git sends a header the proxy substitutes #2499) tracks the helper and the spec requirement.
  2. The same header comment, the lane sentence (~line 11715, "A lane without the proxy, or without a repository named, records NOT RUN"): add that T82 — Run the Box Egress Proxy legs on the macOS lane #2500 (T82 — Run the Box Egress Proxy legs on the macOS lane #2500) owns the macOS lane with bep in its testbed, a sign-in and E2E_BEP_PRIVATE_REPO, and that the T14 (feat(minimal): mint sealed GitHub sign-in references and register the box with the proxy #2490) and T16 (feat(minimald): put the proxy's root certificate in a grant box's trust store #2495) residuals moved there.
  3. crates/minvmd/src/cmd/run.rs ~1402, the BEP_BIN_ENV doc: replace "That release gap is a residual of BEP-015." with "Ship bep in the minvmd release artefacts #2498 (Ship bep in the minvmd release artefacts #2498) owns that release gap."
  4. crates/minvmd/src/cmd/run.rs ~1430, the BepProxy doc: state the interim, that bep starts as minvmd's own user, which is also the user of gvproxy and the VM, while Gatehouse §6.10 requires distinct OS users (BEP-047), and name T38 T38 — Run the egress gate and bep_host in an EGW process apart from the proxy #2285 (T38 — Run the egress gate and bep_host in an EGW process apart from the proxy #2285) as the task that owns that split.
  5. PR body: add a ## Residuals section listing Ship bep in the minvmd release artefacts #2498 (release artefacts ship no bep), Ship a git credential helper in grant boxes so git sends a header the proxy substitutes #2499 (git credential helper), T82 — Run the Box Egress Proxy legs on the macOS lane #2500 (macOS lane for the live proxy legs) and T38 — Run the egress gate and bep_host in an EGW process apart from the proxy #2285 (T38, the bep/gvproxy user split), one line each.

Finish C3 from the previous review (thread 4355956171)

  1. crates/switch/src/bep_host.rs lines 80 and 334 still say the credentialed-only gate rule (NET-145, T45, T45 — Reach the proxy only as a credentialed lane's infrastructure #1665) is still ahead or has yet to decide. T45 landed in T45 — Reach the proxy only as a credentialed lane's infrastructure #1885: boxes::core::egress::proxy_lane_admits refuses a frame to the proxy address from a row that declared no credentialed upstream. Change those two comment lines to name that gate, as the bep_box_source doc in run.rs now does. Two comment lines only, nothing else in that file; the babysitter records the layer exception.
  2. crates/minvmd/src/cmd/run.rs tests: add tests for CredentialedBoxes::box_switch_addresses: a registered row that declares no credentialed upstream gets no share while the proxy listens; a row that declares one gets its share; no row gets a share while listening is false.

Keep every other file unchanged. The Proof section is unchanged by this round.


Generated by Claude Code

A row with no credentialed upstream gets no share while bep listens, a
declaring row gets its share, and no row gets one while bep does not
listen. The BEP_BIN_ENV and BepProxy docs now name #2498 and #2285 (T38).
The private-repo case names #2499 (git credential helper) and #2500
(macOS lane with bep, a sign-in and E2E_BEP_PRIVATE_REPO). switch's
bep_host comments name the T45 gate, egress::proxy_lane_admits (#1885).
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 2 of 10 on a /revise note, pushed as 7092a59c1b86.

line exit tail
cargo nextest run -p minvmd proxy_is_started_with_the_per_boot_token 0 Applying loadouts: default Running task runtime-implement-test-0 in session task-runtime-implement-test-0-2a87... 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 version v0.8.0 (/workbenc
cargo nextest run -p minimal bundle_collects_the_proxy_log_and_audit_segments 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-a3a2... 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
./scripts/session-e2e.sh bep_git_and_gh_against_private_repo 0 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/build-cache/target/debug/min and /work/build-cache/target/debug/minimald ::group::GitHub grant box: git clone,
./scripts/session-e2e.sh bep_second_box_needs_no_sign_in 0 ::group::GitHub grant boxes: the second box needs no sign-in bep_second_box_needs_no_sign_in: NOT RUN (the Box Egress Proxy runs on macOS only) ::endgroup:: session e2e: 1 case(s) NOT RUN: bep_second_box_needs_no_sign_in session e2e OK Applying loadouts: default Running task runtime-implement-test-3
./scripts/session-e2e.sh bep_box_env_holds_sealed_value_only 0 ::group::GitHub grant boxes: the grant's variable holds a sealed value only bep_box_env_holds_sealed_value_only: NOT RUN (the Box Egress Proxy runs on macOS only) ::endgroup:: session e2e: 1 case(s) NOT RUN: bep_box_env_holds_sealed_value_only session e2e OK Applying loadouts: default Running task r

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.

crates/minvmd)
    Checking dashmap v6.2.1
    Checking netlink-packet-core v0.8.1
   Compiling stdlib v0.0.22 (/workbench/crates/stdlib)
    Checking russh-sftp v2.4.0
    Checking konst_macro_rules v0.2.19
    Checking netlink-sys v0.8.8
    Checking konst v0.2.20
    Checking derive_builder v0.20.2
    Checking nix v0.30.1
    Checking nickel-lang-core v0.19.0
    Checking const_format v0.2.36
    Checking netlink-packet-route v0.25.1
    Checking procfs-core v0.18.0
    Checking hash32 v0.2.1
    Checking itertools v0.15.0
    Checking args v0.0.1 (/workbench/crates/args)
    Checking common v0.0.1 (/workbench/crates/common)
    Checking generational-arena v0.2.9
    Checking spin v0.9.9
    Checking strum v0.27.2
    Checking heapless v0.7.17
    Checking boxes v0.0.1 (/workbench/crates/boxes)
    Checking oci-spec v0.10.0
    Checking netconfig-rs v0.1.6
    Checking procfs v0.18.0
    Checking pathrs v0.2.5
    Checking nix v0.29.0
    Checking netlink-packet-route v0.31.0
    Checking minimald-rpc v0.0.1 (/workbench/crates/minimald-rpc)
    Checking mfile v0.0.1 (/workbench/crates/mfile)
    Checking cobs v0.3.0
    Checking getifaddrs v0.6.2
   Compiling serial_test_derive v4.0.1
    Checking checkouts v0.0.1 (/workbench/crates/checkouts)
    Checking decode v0.0.1 (/workbench/crates/decode)
    Checking path-dedot v4.0.1
    Checking fixedbitset v0.5.7
    Checking graph v0.0.1 (/workbench/crates/graph)
    Checking libcgroups v0.7.0
    Checking serial_test v4.0.1
    Checking path-absolutize v4.0.1
    Checking tun-rs v2.8.8
    Checking postcard v1.1.3
    Checking route_manager v0.2.13
    Checking caps v0.5.6
    Checking sendfd v0.4.4
    Checking close_fds v0.3.2
    Checking lcache v0.0.1 (/workbench/crates/lcache)
    Checking castaway v0.2.4
    Checking hakoniwa v1.7.2 (https://github.com/souk4711/hakoniwa.git?rev=0810ffa37620ef5c57de263c8eaa1f4d7633c14a#0810ffa3)
    Checking strum v0.28.0
    Checking rcache v0.0.1 (/workbench/crates/rcache)
    Checking compact_str v0.9.1
    Checking sandbox v0.0.1 (/workbench/crates/sandbox)
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/switch/src/bep_host.rs

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

Review threads the coder judged:

Unchanged by this round. From a box that holds only a sealed member, git clone, git push and gh api succeed against a private repository. This is true only on a lane with bep, a sign-in and E2E_BEP_PRIVATE_REPO, after #2499 ships a git credential helper. #2500 owns that macOS lane. On this branch the code now names each residual issue where it states the gap.

Notes from the agent: Directive item 5 (the ## Residuals section in the PR body) is not mine to do. The runner writes the PR body. Add these four lines: #2498 release artefacts ship no bep. #2499 git credential helper and its spec requirement. #2500 macOS lane for the live proxy legs (the T14 #2490 and T16 #2495 residuals moved there). #2285 T38, the bep/gvproxy/VM OS user split (BEP-047). crates/switch/src/bep_host.rs is outside the layers. The directive asked for it, and only two comment lines changed there. Other sentences around those two lines are still stale: 'not even T69 binds on a production boot yet' and 'the supervisor wires NoBoxes there'. A production boot with a listening bep now wires CredentialedBoxes. The directive limited that file to two lines, so I left those sentences as they were. The three new tests construct CredentialedBoxes directly and run as plain #[test]. The e2e lines (./scripts/session-e2e.sh bep_git_and_gh_against_private_repo, bep_second_box_needs_no_sign_in, bep_box_env_holds_sealed_value_only) did not run: this box has no /dev/kvm and no libkrun. The script changed only in comments, and bash -n passes. cargo clippy -p minvmd -p switch --all-targets showed no warnings in these crates. The one warning (chunks_exact) is in minimald-rpc, which this round does not touch.

@minimal-foundry
minimal-foundry Bot marked this pull request as draft October 23, 2026 04:58

@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: 10 unresolved threads — minimal-arch[bot] scripts/session-e2e.sh:11757, minimal-arch[bot] scripts/session-e2e.sh:11714, minimal-arch[bot] crates/minvmd/src/cmd/run.rs, minimal-arch[bot] crates/minvmd/src/cmd/run.rs, minimal-arch[bot] crates/minvmd/src/cmd/run.rs, …. No findings.

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

@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 · 1 condition · the full ruling

The host and ship layers conform to §7.1 line 244. The proxy runs beside gvproxy, and only credentialed-lane rows get a share while bep serve listens. The residuals now name their issues, and the OS-user interim names #2285. One edit is open. The crates/switch/src/bep_host.rs docs still say that a production boot wires NoBoxes and that only the stand-in registers rows. Make the change in C1. BEP-015 stays open on #2499 and #2500, and its legs are not passes.

Ruled at 7092a59 against gominimal/arch@109541a48c31 by claude-opus-5-5.

Comment thread crates/switch/src/bep_host.rs Resolved
Comment thread crates/switch/src/bep_host.rs Resolved

@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 at 7092a59, after rounds 1 and 2.

Round 1 (a5547ff) fixed the MEDIUM finding and the host half of the arch conditions. BepProxy::spawn records the socket identity at the listener path before the start, and the watcher sets a listening flag only while the child runs and a socket that is not the stale one sits at the path, clearing it on exit, wait error or stop. bep_box_source takes that flag, and CredentialedBoxes returns no share while it is false and, while true, only the rows whose declares_credentialed_upstream() holds, which the gate egress::proxy_lane_admits (#1885) also admits. The stand-in passes an always-true flag, which matches its bind-before-return start. The wiring test registers a second, lane-less row and proves it holds no share.

Round 2 (7092a59) names the four residual issues where the code states each gap (#2498 in the BEP_BIN_ENV doc, #2285 for the BEP-047 interim in the BepProxy doc, #2499 and #2500 in the e2e case header), replaces the two "still ahead" lines in switch::bep_host with the landed gate, and adds three tests that pin which rows get a share and that the shares follow the flag. The PR body now carries a Layer exception for the two bep_host.rs lines and a Residuals section.

Read against spec 24 §7.1 and the arch rulings 5623734228 and 5623925208. Nothing left for the runtime from those; C1 and C3 of the second ruling are filed and named, so the change conforms with those residuals open. A macOS pass against the live proxy stays owned by #2500.


Generated by Claude Code

@norrietaylor
norrietaylor marked this pull request as ready for review October 23, 2026 05:08

@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 at e875443, after round 6.

Round 6 closes the LOW finding on the proxy log. cap_bep_log runs before the log is opened: a log past 8 MiB moves aside to bep.log.old, replacing an older copy, and a log at or under the cap or no log stays as it is. A failure to move it is logged and the start goes on, which is the right side to fail on for a log. The test covers no log, a log at the cap and a log past the cap with an older .old present. The diag bundle's retention note in crates/minimal/src/diag/collect.rs says so and that the bundle does not collect bep.log.old; that file is in the ship layer, so no layer exception.

The diff touches no proxy, share or watcher logic, so the arch pass (5624582210, PASS_WITH_CONDITIONS with every condition held on #2500, #2499, #2498, T38 #2285 and the macOS half of the parent tie on #2501) stands. The native lane is green on this head, so the earlier concurrent_boots_never_draw_the_same_proxy_port failure on c2bc795 was transient and this run was its one re-run.


Generated by Claude Code

@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/minimal/src/diag/collect.rs Resolved
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 7 of 10 on the runtime's review findings, pushed as 714be7b7e5a3.

line exit tail
cargo nextest run -p minvmd proxy_is_started_with_the_per_boot_token 0 0.9.2 Compiling lalrpop v0.23.1 Compiling google-cloud-rpc v1.6.0 Compiling hyper-rustls v0.27.9 Compiling hyper-timeout v0.5.2 Compiling reqwest v0.13.5 Compiling tonic v0.14.6 Compiling google-cloud-gax v1.15.0 Compiling malachite-nz v0.9.2 Compiling tracing-opentelemetr
cargo nextest run -p minimal bundle_collects_the_proxy_log_and_audit_segments 0 Applying loadouts: default Running task runtime-implement-test-1 in session task-runtime-implement-test-1-36c9... 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
./scripts/session-e2e.sh bep_git_and_gh_against_private_repo 0 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/build-cache/target/debug/min and /work/build-cache/target/debug/minimald ::group::GitHub grant box: git clone,
./scripts/session-e2e.sh bep_second_box_needs_no_sign_in 0 ::group::GitHub grant boxes: the second box needs no sign-in bep_second_box_needs_no_sign_in: NOT RUN (the Box Egress Proxy runs on macOS only) ::endgroup:: session e2e: 1 case(s) NOT RUN: bep_second_box_needs_no_sign_in session e2e OK Applying loadouts: default Running task runtime-implement-test-3
./scripts/session-e2e.sh bep_box_env_holds_sealed_value_only 0 ::group::GitHub grant boxes: the grant's variable holds a sealed value only bep_box_env_holds_sealed_value_only: NOT RUN (the Box Egress Proxy runs on macOS only) ::endgroup:: session e2e: 1 case(s) NOT RUN: bep_box_env_holds_sealed_value_only session e2e OK Applying loadouts: default Running task r

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.

 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-a7e3...
    Checking opentelemetry v0.33.1
    Checking ot v0.0.1 (/workbench/crates/ot)
    Checking args v0.0.1 (/workbench/crates/args)
    Checking paths v0.0.1 (/workbench/crates/paths)
   Compiling version v0.8.0 (/workbench/crates/version)
    Checking switch v0.0.1 (/workbench/crates/switch)
   Compiling minvmd v0.8.0 (/workbench/crates/minvmd)
    Checking opentelemetry_sdk v0.33.1
    Checking tracing-opentelemetry v0.34.0
    Checking opentelemetry-http v0.33.1
    Checking opentelemetry-appender-tracing v0.33.1
   Compiling stdlib v0.0.22 (/workbench/crates/stdlib)
   Compiling serial_test_derive v4.0.1
    Checking google-cloud-gax-internal v0.7.20
    Checking opentelemetry-proto v0.33.0
    Checking google-cloud-longrunning v1.14.0
    Checking google-cloud-iam-v1 v1.13.0
    Checking opentelemetry-otlp v0.33.0
    Checking serial_test v4.0.1
    Checking mlog v0.0.1 (/workbench/crates/mlog)
    Checking google-cloud-lro v1.11.0
    Checking diagnostics v0.0.1 (/workbench/crates/diagnostics)
    Checking bep v0.0.1 (/workbench/crates/bep)
    Checking google-cloud-storage v1.20.0
    Checking async-dialog v0.0.1 (/workbench/crates/async-dialog)
    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 decode v0.0.1 (/workbench/crates/decode)
    Checking checkouts v0.0.1 (/workbench/crates/checkouts)
    Checking graph v0.0.1 (/workbench/crates/graph)
    Checking lcache v0.0.1 (/workbench/crates/lcache)
    Checking rcache v0.0.1 (/workbench/crates/rcache)
    Checking op v0.0.1 (/workbench/crates/op)
    Checking orchestrator v0.0.1 (/workbench/crates/orchestrator)
    Checking check v0.0.1 (/workbench/crates/check)
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/switch/src/bep_host.rs

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

Review threads the coder judged:

  • 👍 valid — crates/minimal/src/diag/collect.rs: logs() now delegates to logs_with_audit(), which takes the audit dir. The test injects a temp dir there and no longer calls bep_audit a second time, so the real home audit log stays out of its bundle.

From a box that holds only a sealed member, git clone, git push and gh api succeed against a private repository, through the bep serve proxy that minvmd starts beside gvproxy. This round makes no change to that path. It only makes the bundle test hermetic.

Notes from the agent: Round 7 addresses one review thread. logs() now delegates to a private logs_with_audit() that takes the audit dir. The production call still passes bep::audit::default_dir(). The test passes a temp dir, so a real ~/.minimal/bep/audit on the host never enters its bundle. I did not run the minvmd test line or the three session-e2e.sh lines this round, because the change does not touch their code and the e2e legs need a VM lane. clippy -p minimal --all-targets shows no warnings in minimal. The warnings it prints are in minimald and minimald-rpc, which this round does not touch.

@minimal-foundry
minimal-foundry Bot marked this pull request as draft October 23, 2026 07:36

@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: 1 unresolved thread — minimal-foundry[bot] crates/minimal/src/diag/collect.rs. No findings.

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

@norrietaylor
norrietaylor marked this pull request as ready for review October 23, 2026 07:37

@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 at 714be7b, after round 7.

Round 7 closes the LOW test-hermeticity finding in crates/minimal/src/diag/collect.rs: logs() keeps its signature and delegates to logs_with_audit(), which takes the audit directory, and bundle_collects_the_proxy_log_and_audit_segments passes a temp dir there instead of calling bep_audit a second time, so a real audit log under the host's home never enters the test's bundle. Production behaviour is unchanged: logs() still reads bep::audit::default_dir(). The file is in the ship layer.

Nothing here bears on the arch conditions; the pass (5624582210) stands with every condition held on #2500, #2499, #2498, T38 #2285 and #2501.


Generated by Claude Code

@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 714be7b7e5a3 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 Oct 23, 2026
@norrietaylor norrietaylor reopened this Oct 23, 2026
@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 8 of 10 on a failed check suite: the coder changed nothing. Noop. The cargo-deny job fails on a new RUSTSEC advisory, "Non-constant-time mask generation and u128 comparisons". cargo-deny reaches it through the ssh-key / ssh-cipher / universal-hash tree. ci-success fails only because cargo-deny fails. The branch does not change Cargo.lock or deny.toml: git diff --stat against the merge base 608ab9c lists only collect.rs, run.rs, bep_host.rs, justfile and session-e2e.sh. origin/main has no commit after the merge base that touches deny.toml or Cargo.lock, so main has the same failure. The fix is a dependency bump in Cargo.lock or an ignore entry in deny.toml. Both files are outside this task's layers, and the fix belongs in its own pull request against main. The excerpt also shows a non-fatal 'override toolchain 1.97.0-x86_64-unknown-linux-musl is not installed' line and an advisory-not-detected warning for RUSTSEC-2026-0009. Neither is from this branch. I ran no test lines this round because I changed no code.

@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 9 of 10 on a failed check suite: the coder changed nothing. Round 9 directive lists failed checks only, and no review threads. I found no failure that this branch causes. (1) cargo-deny: the advisories gate fails on a vulnerability in a dependency under ssh-key/ssh-cipher. The deny.toml warning about RUSTSEC-2026-0009 also comes from main. This branch does not change Cargo.lock or deny.toml, and both are outside the task layers. A separate pull request on main must fix it. (2) tests: the log excerpt does not name the failing test. Locally, all of minimal (724) and switch (62) pass. Of the 610 minvmd tests, 609 pass. net::egress_gate::tests::a_query_dropped_at_the_queue_is_not_observed failed once on a 5 s timing window, then passed when it ran alone. This branch does not touch crates/minvmd/src/net. So that test is the probable flake, but the CI log does not prove it. (3) ci-success and ci-linux-native-success are aggregators that fail because of (1) and (2). Local clippy is rustc 1.98.1, not the 1.97.0 pin. It warns only in untouch…[truncated]

Copy link
Copy Markdown
Member

/revise

Base merge only. main now carries the cargo-deny fix: c9114e1 (#2503) moves ctutils to 0.4.5 for RUSTSEC-2026-0385, and cargo-deny is green on main. This branch still carries the old lock, so ci-success is red on 714be7b for that reason alone.

  1. Merge origin/main (c9114e1) into the branch and push. Resolve nothing by hand; the only change main brings is Cargo.lock, which this branch does not touch.
  2. Change no other file. No test lines need to run for a merge commit.

The Proof section is unchanged by this round.


Generated by Claude Code

@minimal-foundry

Copy link
Copy Markdown
Contributor Author

Round 10 of 10 on a /revise note: the coder changed nothing. every commit this round put on the branch above 714be7b is a merge of the base branch, so it carries no work of its own

@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 at 236f312.

This head is the merge of main c5ea7aa into the branch, made with GitHub's update-branch at the owner's word after the runtime's rounds were exhausted. It brings only main's changes: the ctutils 0.4.5 lock bump from #2503, which clears RUSTSEC-2026-0385 for cargo-deny, and the minimal CLI fix from #2226. Nothing of this PR's own changes, so the reviews at 714be7b and the arch pass (5624332061 at a1c15c5, PASS_WITH_CONDITIONS with every condition held on #2500, #2499, #2498, T38 #2285 and #2501) stand on the same diff.


Generated by Claude Code

@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 · 4 conditions · the full ruling

The ruling on c2bc795a stands for this head. The new log cap moves only bep.log, the proxy's stdout and stderr. It does not touch the audit segments, which Gatehouse §6.10 line 836 makes the source of record. The hermetic bundle test now goes through the production path. BEP-015 is still not proved end to end. C1 to C4 stay open, and each one has a filed issue.

Ruled at 236f312 against gominimal/arch@109541a48c31 by claude-opus-5-5.

Comment thread crates/minvmd/src/cmd/run.rs Resolved
@minimal-foundry minimal-foundry Bot removed the review:approved minimal-review approved the current head label Oct 23, 2026
@norrietaylor norrietaylor changed the title T18 — Run the proxy beside gvproxy so git and gh reach GitHub from a box feat(minvmd): start the Box Egress Proxy beside gvproxy so git and gh reach GitHub Oct 23, 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.

Approved for merge at 236f312.

All twelve babysit gates pass on this head: own review, arch PASS_WITH_CONDITIONS with its conditions filed as #2498, #2499, #2500 and #2501, minimal-review concluded, every review thread resolved and re-verified on the head, ci-success, ci-linux-native-success, ci-linux-kvm-success, ci-macos-success and ci-shell-installer-success green, CodeRabbit and license/cla green, ready for review, no needs-human, Closes #2275. The squash title passes commitlint.


Generated by Claude Code

@norrietaylor
norrietaylor added this pull request to the merge queue Oct 23, 2026
@github-merge-queue
github-merge-queue Bot removed this pull request from the merge queue due to no response for status checks Oct 23, 2026
@norrietaylor
norrietaylor added this pull request to the merge queue Oct 23, 2026
@bryan-minimal
bryan-minimal merged commit ccc4f95 into main Oct 24, 2026
37 checks passed
@bryan-minimal
bryan-minimal deleted the agent/2275-run-the-proxy-beside-gvproxy-so-git-and-gh-reach branch October 24, 2026 00:56
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.

T18 — Run the proxy beside gvproxy so git and gh reach GitHub from a box

2 participants