mirror of
https://github.com/Twigpine/node.git
synced 2026-11-09 05:20:05 -10:00
Compare commits
104
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
fdf716dd25 | ||
|
|
c926e1ede5 | ||
|
|
5f445152a8 | ||
|
|
cd810b3375 | ||
|
|
acb47145be | ||
|
|
b4016dce9d | ||
|
|
ee9bc93198 | ||
|
|
9836c3a21b | ||
|
|
13b565bcac | ||
|
|
0e42eb3343 | ||
|
|
c83cbc56e0 | ||
|
|
1964f88378 | ||
|
|
99b2b9a166 | ||
|
|
9418e315bf | ||
|
|
c70b1df42d | ||
|
|
811ad504bc | ||
|
|
e2560ee46c | ||
|
|
75e3e03c09 | ||
|
|
fbc5868bd1 | ||
|
|
457be11d72 | ||
|
|
6e64d0d0a7 | ||
|
|
2e664b7885 | ||
|
|
9aa4c17aef | ||
|
|
27b0495a6f | ||
|
|
6456bfb0ba | ||
|
|
3ca94739ed | ||
|
|
c587a40a50 | ||
|
|
9f00e24aec | ||
|
|
51d82ded57 | ||
|
|
a49e04ddcd | ||
|
|
ebfe89d1c9 | ||
|
|
5091f2dba0 | ||
|
|
f2f99c6684 | ||
|
|
b605b2269a | ||
|
|
52a8f010b7 | ||
|
|
b8eff30fc2 | ||
|
|
111cff7e20 | ||
|
|
e9da517fde | ||
|
|
9ca94c4d47 | ||
|
|
c0ad500b55 | ||
|
|
e9d6aadd58 | ||
|
|
b484a24955 | ||
|
|
32006b26a2 | ||
|
|
b75aa2f1da | ||
|
|
c681af70db | ||
|
|
1ba9ee505a | ||
|
|
3fa38dce4e | ||
|
|
c71bba5cd1 | ||
|
|
e1e6e1cf83 | ||
|
|
e3df51d76c | ||
|
|
0765c42fef | ||
|
|
94c61f7942 | ||
|
|
b0a2ed8308 | ||
|
|
cb42a4830d | ||
|
|
2d88937fba | ||
|
|
e14c2d3f3f | ||
|
|
4465beb0c2 | ||
|
|
82efd60229 | ||
|
|
e8f193a5df | ||
|
|
07d76ba556 | ||
|
|
05e434d906 | ||
|
|
7593540f62 | ||
|
|
ccc2cf46f2 | ||
|
|
1fddc81b7c | ||
|
|
62d73c4165 | ||
|
|
2f622ae5fa | ||
|
|
f9506b466e | ||
|
|
d5ec4695f4 | ||
|
|
98d728c325 | ||
|
|
b6877a6598 | ||
|
|
b07d41ea97 | ||
|
|
c7427e943d | ||
|
|
69a62e51c2 | ||
|
|
ee8d7c03b2 | ||
|
|
82fec97a97 | ||
|
|
9be5eac3a2 | ||
|
|
6b2ec93de1 | ||
|
|
ad7c2b2b83 | ||
|
|
c98b503f90 | ||
|
|
3ec8cbf1e1 | ||
|
|
6b5e5bc7ae | ||
|
|
dfcaa22b23 | ||
|
|
2109d08e2c | ||
|
|
c5e5099def | ||
|
|
cd67718f49 | ||
|
|
6bafaa6dc5 | ||
|
|
26bc3f6987 | ||
|
|
d00d89ae5b | ||
|
|
67ad2b876c | ||
|
|
6cff5286b4 | ||
|
|
5f63f28215 | ||
|
|
06388ec26a | ||
|
|
2df6ff9d30 | ||
|
|
2620e973e3 | ||
|
|
e3a20317d5 | ||
|
|
c296e23678 | ||
|
|
20d6848846 | ||
|
|
4891db3889 | ||
|
|
6f36fc07b8 | ||
|
|
563c456803 | ||
|
|
6c95592d18 | ||
|
|
466a550915 | ||
|
|
09a0cb23b9 | ||
|
|
cd4680ebeb |
No files matched your search
@@ -21,6 +21,23 @@ GITLAWB_REPOS_DIR=/data/repos
|
||||
# When using the bundled docker-compose, this is wired automatically.
|
||||
DATABASE_URL=postgresql://gitlawb:changeme@localhost:5432/gitlawb
|
||||
|
||||
# ── Database pool & startup resilience ────────────────────────────────────
|
||||
# Maximum connections in the PostgreSQL pool. A cap, not a floor —
|
||||
# connections open lazily. Size against the DB server's max_connections,
|
||||
# remembering admin tooling opens its own pool.
|
||||
GITLAWB_DB_MAX_CONNECTIONS=20
|
||||
# Seconds a request waits for a pool connection before failing with 503.
|
||||
GITLAWB_DB_ACQUIRE_TIMEOUT_SECS=5
|
||||
# Upper bound on each startup connect+migrate attempt, in seconds. Keep it
|
||||
# generous enough for a peer instance to finish migrating (the migration
|
||||
# advisory lock is held across a deploy); on expiry the attempt is retried.
|
||||
GITLAWB_DB_CONNECT_TIMEOUT_SECS=60
|
||||
# Startup retry backoff while the database is unavailable: first delay and
|
||||
# ceiling, in seconds. The node stays up serving 503s (with a truthful
|
||||
# /ready) instead of crash-looping.
|
||||
GITLAWB_DB_RETRY_INITIAL_SECS=5
|
||||
GITLAWB_DB_RETRY_MAX_SECS=60
|
||||
|
||||
# ── IPFS pinning (Pinata) ─────────────────────────────────────────────────
|
||||
# Get a JWT at https://app.pinata.cloud/developers/api-keys
|
||||
GITLAWB_PINATA_JWT=
|
||||
@@ -90,6 +107,46 @@ GITLAWB_PUBLIC_READ=true
|
||||
# Maximum git smart-HTTP pack request size, in bytes.
|
||||
GITLAWB_MAX_PACK_BYTES=2147483648
|
||||
|
||||
# Max seconds a served git upload-pack / receive-pack (clone / push) may run
|
||||
# before it is aborted with a 504. Bounds a hung git that would otherwise pin a
|
||||
# worker and, on push, the repo write lock. Does NOT cover the info/refs
|
||||
# advertisement or the withheld-blob path, which remain unbounded. Default 600.
|
||||
GITLAWB_GIT_SERVICE_TIMEOUT_SECS=600
|
||||
|
||||
# ── Push rate limiting (git-receive-pack flood brake) ─────────────────────
|
||||
# Max receive-pack requests (info/refs advertisement + push POST) per client
|
||||
# IP per hour. 0 disables. Default 600.
|
||||
GITLAWB_PUSH_RATE_LIMIT=600
|
||||
|
||||
# ── Creation rate limiting (repo/agent/issue/PR flood brake) ──────────────
|
||||
# Max creation requests (POST /api/v1/repos, /api/register, fork, issues,
|
||||
# pulls) per client IP per hour, in addition to the per-DID limit. The per-DID
|
||||
# limit alone is bypassed by a did:key farm (one throwaway identity per repo),
|
||||
# which is how spam-repo floods slip past it and the iCaptcha gate; the per-IP
|
||||
# brake caps a single-source flood. Uses GITLAWB_TRUSTED_PROXY below to resolve
|
||||
# the client IP. 0 disables. Default 120.
|
||||
GITLAWB_CREATE_RATE_LIMIT=120
|
||||
|
||||
# ── Peer-sync rate limiting (per client IP, uses GITLAWB_TRUSTED_PROXY below) ─
|
||||
# /api/v1/peers/announce and /api/v1/sync/notify accept unsigned requests from
|
||||
# known peers and run at higher frequency, so a generous bucket. Separate from
|
||||
# the trigger bucket so an unsigned notify flood can't drain trigger's quota.
|
||||
# 0 disables. Default 600.
|
||||
GITLAWB_PEER_WRITE_RATE_LIMIT=600
|
||||
# /api/v1/sync/trigger requires a signature and fans out to every peer per call,
|
||||
# so it gets a tight bucket. 0 disables. Default 60.
|
||||
GITLAWB_SYNC_TRIGGER_RATE_LIMIT=60
|
||||
|
||||
# Which forwarded header the edge is trusted to set, used to resolve the real
|
||||
# client IP for the push limiter. One of:
|
||||
# (unset) — no trusted proxy: key on the socket peer address, ignore headers.
|
||||
# fly — behind Fly's edge (trust Fly-Client-IP).
|
||||
# x-forwarded-for — behind a single reverse proxy like Caddy/NGINX (trust the
|
||||
# rightmost X-Forwarded-For hop).
|
||||
# Only set this when a proxy you control actually fronts the node; trusting a
|
||||
# forwarded header on a directly-exposed node lets clients spoof the key.
|
||||
GITLAWB_TRUSTED_PROXY=
|
||||
|
||||
# ── Sync ─────────────────────────────────────────────────────────────────
|
||||
# Enable automatic background sync from known peers
|
||||
GITLAWB_AUTO_SYNC=false
|
||||
|
||||
@@ -37,7 +37,18 @@ jobs:
|
||||
with:
|
||||
key: audit-schedule
|
||||
|
||||
- name: Install cargo-audit
|
||||
- name: Install cargo-audit (floating; drift canary)
|
||||
# Deliberately UNPINNED, unlike the blocking gate in pr-checks.yml. This
|
||||
# job is cron-only (weekly); it is never pull_request- or push-triggered,
|
||||
# so it NEVER gates a merge no matter what it does. Floating the scanner
|
||||
# here is the drift canary: if a newer cargo-audit regresses, at worst
|
||||
# this weekly run reds (the install step below is unguarded) or its
|
||||
# visibility report changes, and that is exactly the signal that latest
|
||||
# has moved and the pinned gate should not be bumped yet. The scan result
|
||||
# itself never fails the run (the "Full audit report" step is `|| true`
|
||||
# and the only other hard-fail is a Cargo.lock grep). The point is that
|
||||
# drift surfaces here without ever blocking a PR. Do NOT pin to match
|
||||
# pr-checks.yml.
|
||||
run: cargo install --locked cargo-audit
|
||||
|
||||
# Full advisory report with NO suppressions. Run from a scratch dir that
|
||||
|
||||
@@ -0,0 +1,121 @@
|
||||
# Tracks main's CI state as a labeled issue: opens (or updates) a ci-main-red
|
||||
# issue when a push-to-main run of PR Checks ends red, and closes it when a
|
||||
# subsequent run on main's tip goes green.
|
||||
#
|
||||
# Why: two individually-green PRs can break main in combination when the
|
||||
# second merges on checks that ran against a stale base (semantic merge
|
||||
# race — #113 + #145 broke test compilation, found only via #229). A red main
|
||||
# is otherwise silent, and release-please PRs inherit the breakage.
|
||||
#
|
||||
# The alert reflects main's CURRENT STATE, not raw CI events: runs whose
|
||||
# commit is no longer main's tip are ignored (a re-run of an old red run
|
||||
# after a fix has landed must not cry wolf), and a green run on the tip
|
||||
# closes any open alert.
|
||||
name: Main red alert
|
||||
|
||||
on:
|
||||
workflow_run:
|
||||
workflows: ["PR Checks"]
|
||||
types: [completed]
|
||||
branches: [main]
|
||||
|
||||
permissions:
|
||||
issues: write
|
||||
contents: read # getBranch tip check
|
||||
|
||||
# Serialize runs: concurrent completions would race the label/issue lookups
|
||||
# into duplicates (or 422 on createLabel). queue: max keeps every pending
|
||||
# completion instead of letting a later (possibly green-skipped) arrival
|
||||
# displace a pending red alert under burst merges; it is only incompatible
|
||||
# with cancel-in-progress: true, which we don't use.
|
||||
concurrency:
|
||||
group: main-red-alert
|
||||
cancel-in-progress: false
|
||||
queue: max
|
||||
|
||||
jobs:
|
||||
track:
|
||||
name: Track main CI state
|
||||
# timed_out (the test job runs 45 min against Postgres) and
|
||||
# startup_failure (malformed workflow) are red too — only cancelled is
|
||||
# excluded as a deliberate human abort. success runs are needed to close
|
||||
# the alert once main recovers.
|
||||
if: >-
|
||||
github.event.workflow_run.event == 'push' &&
|
||||
contains(fromJSON('["failure", "timed_out", "startup_failure", "success"]'), github.event.workflow_run.conclusion)
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 5
|
||||
steps:
|
||||
- name: Reconcile the broken-main issue with main's current state
|
||||
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
|
||||
with:
|
||||
script: |
|
||||
const run = context.payload.workflow_run;
|
||||
const label = 'ci-main-red';
|
||||
|
||||
// Freshness gate: only the run for main's current tip may open or
|
||||
// close anything. Re-runs of superseded commits are events about
|
||||
// the past, not statements about main's state.
|
||||
const { data: branch } = await github.rest.repos.getBranch({
|
||||
...context.repo, branch: 'main',
|
||||
});
|
||||
if (branch.commit.sha !== run.head_sha) {
|
||||
core.info(`run ${run.id} is for ${run.head_sha}, main is at ${branch.commit.sha} — ignoring stale run`);
|
||||
return;
|
||||
}
|
||||
|
||||
// listForRepo returns PRs carrying the label too — those must
|
||||
// never be mistaken for the tracking issue.
|
||||
const open = (await github.rest.issues.listForRepo({
|
||||
...context.repo, state: 'open', labels: label, per_page: 100,
|
||||
})).data.filter(item => !item.pull_request);
|
||||
|
||||
if (run.conclusion === 'success') {
|
||||
const body = `Recovered: [PR Checks](${run.html_url}) is green on main at \`${run.head_sha}\`.`;
|
||||
for (const issue of open) {
|
||||
await github.rest.issues.createComment({
|
||||
...context.repo, issue_number: issue.number, body,
|
||||
});
|
||||
await github.rest.issues.update({
|
||||
...context.repo, issue_number: issue.number, state: 'closed', state_reason: 'completed',
|
||||
});
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
const headline = run.head_commit?.message?.split('\n')[0] ?? '';
|
||||
const body = [
|
||||
`[PR Checks run](${run.html_url}) concluded \`${run.conclusion}\` on main at \`${run.head_sha}\`.`,
|
||||
'',
|
||||
`> ${headline}`,
|
||||
'',
|
||||
'Likely a semantic merge race: each merged PR was green on a stale base.',
|
||||
'Fix main before merging anything else — release-please PRs inherit this breakage.',
|
||||
'',
|
||||
"This issue closes automatically when a run on main's tip goes green.",
|
||||
].join('\n');
|
||||
|
||||
try {
|
||||
await github.rest.issues.getLabel({ ...context.repo, name: label });
|
||||
} catch (e) {
|
||||
if (e.status !== 404) throw e;
|
||||
await github.rest.issues.createLabel({
|
||||
...context.repo,
|
||||
name: label,
|
||||
color: 'b60205',
|
||||
description: 'CI is failing on main',
|
||||
});
|
||||
}
|
||||
|
||||
if (open.length > 0) {
|
||||
await github.rest.issues.createComment({
|
||||
...context.repo, issue_number: open[0].number, body,
|
||||
});
|
||||
} else {
|
||||
await github.rest.issues.create({
|
||||
...context.repo,
|
||||
title: 'CI is red on main',
|
||||
body,
|
||||
labels: [label],
|
||||
});
|
||||
}
|
||||
@@ -2,6 +2,17 @@ name: PR Checks
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
# Run in the merge queue so a PR is re-validated against the true merged
|
||||
# result before it lands. Guards against semantic merge races where two
|
||||
# individually-green PRs break main in combination (#113 + #145 → #229).
|
||||
merge_group:
|
||||
# Release-branch heads are created and pushed by GITHUB_TOKEN (release-please
|
||||
# and the lock-sync job), and GitHub's recursion guard means those pushes
|
||||
# trigger no workflow runs. workflow_dispatch is the documented carve-out that
|
||||
# GITHUB_TOKEN CAN trigger, so the release flow dispatches this workflow at
|
||||
# the release branch to attach check runs to its head. Read-only workflow
|
||||
# (contents: read), so the dispatch surface adds no privilege.
|
||||
workflow_dispatch:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
@@ -42,7 +53,7 @@ jobs:
|
||||
run: cargo fmt --all -- --check
|
||||
|
||||
- name: cargo clippy
|
||||
run: cargo clippy --workspace --all-targets -- -D warnings
|
||||
run: cargo clippy --locked --workspace --all-targets -- -D warnings
|
||||
|
||||
test:
|
||||
name: test (${{ matrix.toolchain }})
|
||||
@@ -90,7 +101,7 @@ jobs:
|
||||
- name: cargo test
|
||||
env:
|
||||
DATABASE_URL: postgres://postgres:postgres@localhost:5432/gitlawb_test
|
||||
run: cargo test --workspace
|
||||
run: cargo test --locked --workspace
|
||||
|
||||
build-release:
|
||||
name: build --release
|
||||
@@ -113,7 +124,7 @@ jobs:
|
||||
key: release
|
||||
|
||||
- name: cargo build --release
|
||||
run: cargo build --release --workspace
|
||||
run: cargo build --locked --release --workspace
|
||||
|
||||
audit:
|
||||
name: cargo audit
|
||||
@@ -133,10 +144,30 @@ jobs:
|
||||
- name: Cache cargo
|
||||
uses: Swatinem/rust-cache@98c8021b550208e191a6a3145459bfc9fb29c4c0 # v2.8.0
|
||||
with:
|
||||
key: audit
|
||||
key: audit-0.22.2
|
||||
|
||||
- name: Install cargo-audit
|
||||
run: cargo install --locked cargo-audit
|
||||
- name: Install cargo-audit (pinned)
|
||||
# Pin the scanner on this BLOCKING gate: an unpinned `cargo install`
|
||||
# floats to the latest release, so a regressed cargo-audit could red CI
|
||||
# repo-wide with no code change. Advisory-DB freshness is fetched at scan
|
||||
# time, independent of the binary, so this does not weaken what the gate
|
||||
# catches. The weekly Scheduled Audit (audit-schedule.yml) deliberately
|
||||
# floats to latest as the drift canary; when it shows a newer cargo-audit
|
||||
# behaving differently, bump this version (and the cache key above) as a
|
||||
# deliberate maintainer action. If 0.22.2 is ever yanked from crates.io
|
||||
# this step fails loud until the pin is bumped.
|
||||
run: |
|
||||
set -euo pipefail
|
||||
cargo install --locked --version 0.22.2 cargo-audit
|
||||
# Assert the pin took effect so an accidental future unpin (or a drift
|
||||
# off 0.22.2) fails loudly here instead of silently running a different
|
||||
# scanner. `cargo audit --version` prints "cargo-audit-audit 0.22.2".
|
||||
installed="$(cargo audit --version)"
|
||||
echo "cargo-audit installed: $installed"
|
||||
echo "$installed" | grep -qE '(^| )0\.22\.2($| )' || {
|
||||
echo "::error::cargo-audit is not the pinned 0.22.2 (got: $installed)"
|
||||
exit 1
|
||||
}
|
||||
|
||||
# Hard-fail gate. Suppressions live in .cargo/audit.toml (read automatically
|
||||
# from the repo root), each with no available upstream fix. A green check
|
||||
@@ -175,7 +206,7 @@ jobs:
|
||||
key: msrv
|
||||
|
||||
- name: cargo check on MSRV
|
||||
run: cargo check --workspace --all-targets
|
||||
run: cargo check --locked --workspace --all-targets
|
||||
|
||||
docker-build:
|
||||
name: Docker build smoke test
|
||||
@@ -192,3 +223,63 @@ jobs:
|
||||
|
||||
- name: Smoke test --version
|
||||
run: docker run --rm gitlawb-node:ci-test --version
|
||||
|
||||
test-windows:
|
||||
name: test (windows, non-blocking)
|
||||
runs-on: windows-latest
|
||||
timeout-minutes: 45
|
||||
# Non-blocking, mirroring the informational `beta` lane above. We ship `gl`
|
||||
# and `git-remote-gitlawb` to Windows users (release.yml) with zero Windows
|
||||
# test coverage, so run their suites here to make Windows-only regressions
|
||||
# VISIBLE on the PR without gating merge (#228). These two are the client
|
||||
# CLIs and depend on no database, so no Postgres service is needed (service
|
||||
# containers do not run on windows-latest regardless). `git` is preinstalled
|
||||
# on windows-latest, which the real_git_fetch harness relies on.
|
||||
continue-on-error: true
|
||||
steps:
|
||||
- name: Check out repository
|
||||
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Set up Rust toolchain
|
||||
uses: dtolnay/rust-toolchain@b3b07ba8b418998c39fb20f53e8b695cdcc8de1b # stable
|
||||
with:
|
||||
toolchain: stable
|
||||
|
||||
- name: Cache cargo
|
||||
uses: Swatinem/rust-cache@98c8021b550208e191a6a3145459bfc9fb29c4c0 # v2.8.0
|
||||
with:
|
||||
key: windows
|
||||
|
||||
- name: cargo test (shipped Windows crates)
|
||||
run: cargo test --locked -p gl -p git-remote-gitlawb
|
||||
|
||||
# gitlawb-core is embedded by every consumer (gl, git-remote-gitlawb, the node
|
||||
# daemon), so it must stay lean. This gate fails if gitlawb-core's normal
|
||||
# (non-dev, non-build) dependency tree gains any crate not on the allowlist in
|
||||
# ci/gitlawb-core-allowed-deps.txt. Exhaustive-by-construction: a new heavy
|
||||
# dependency reds CI whether or not anyone thought to ban it, which a denylist
|
||||
# cannot do. Regen instructions live in the allowlist header.
|
||||
core-deps-purity:
|
||||
name: gitlawb-core dependency purity
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 15
|
||||
steps:
|
||||
- name: Check out repository
|
||||
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Set up Rust toolchain
|
||||
uses: dtolnay/rust-toolchain@b3b07ba8b418998c39fb20f53e8b695cdcc8de1b # stable
|
||||
with:
|
||||
toolchain: stable
|
||||
|
||||
- name: Cache cargo
|
||||
uses: Swatinem/rust-cache@98c8021b550208e191a6a3145459bfc9fb29c4c0 # v2.8.0
|
||||
with:
|
||||
key: core-deps-purity
|
||||
|
||||
- name: Check gitlawb-core dependency allowlist
|
||||
run: bash scripts/check-gitlawb-core-deps.sh
|
||||
@@ -24,7 +24,7 @@ jobs:
|
||||
timeout-minutes: 10
|
||||
steps:
|
||||
- name: Label and guide
|
||||
uses: actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b # v7
|
||||
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
|
||||
with:
|
||||
script: |
|
||||
const pr = context.payload.pull_request;
|
||||
|
||||
+372
-63
@@ -4,6 +4,20 @@ on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
# Manual backfill: republish an already-cut release to a channel that
|
||||
# missed it. Fill in only the channel(s) you want — an empty input leaves
|
||||
# that channel's jobs skipped. npm reuses the existing release's binary
|
||||
# assets; docker rebuilds the image from the tag and re-tags the manifest.
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
npm_backfill_tag:
|
||||
description: "Existing release tag to publish to npm (e.g. v0.6.0)"
|
||||
required: false
|
||||
type: string
|
||||
docker_backfill_tag:
|
||||
description: "Existing release tag to publish to ghcr (e.g. v0.6.0)"
|
||||
required: false
|
||||
type: string
|
||||
|
||||
concurrency:
|
||||
group: release-${{ github.ref }}
|
||||
@@ -14,7 +28,10 @@ permissions: {}
|
||||
|
||||
jobs:
|
||||
release-please:
|
||||
if: ${{ github.repository == 'Gitlawb/node' }}
|
||||
# Skipped on manual dispatch: a backfill must never create or advance a
|
||||
# release PR as a side effect (npm-publish tolerates the skipped need via
|
||||
# !cancelled(), and every other job gates on release_created == 'true').
|
||||
if: ${{ github.repository == 'Gitlawb/node' && github.event_name != 'workflow_dispatch' }}
|
||||
name: Release Please
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
@@ -24,6 +41,7 @@ jobs:
|
||||
release_created: ${{ steps.release.outputs.release_created }}
|
||||
tag_name: ${{ steps.release.outputs.tag_name }}
|
||||
version: ${{ steps.release.outputs.version }}
|
||||
pr: ${{ steps.release.outputs.pr }}
|
||||
steps:
|
||||
- name: Run release-please
|
||||
id: release
|
||||
@@ -31,24 +49,198 @@ jobs:
|
||||
with:
|
||||
token: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
docker:
|
||||
name: Build & Push Docker Image
|
||||
# The release PR bumps the workspace crate versions in the Cargo.tomls but
|
||||
# release-please cannot update Cargo.lock, so without this job every release
|
||||
# merge ships a tag whose lockfile disagrees with its manifests (a --locked
|
||||
# build from the tag fails, and pr-checks builds --locked). Sync the lock on
|
||||
# the release branch so the tagged tree is internally consistent.
|
||||
#
|
||||
# Runs on every push-triggered release run, not only when release-please
|
||||
# reports the PR: the `pr` output is set only on runs that CREATE or UPDATE
|
||||
# the release PR, so gating on it would leave an already-open release PR
|
||||
# (opened before this job existed, or untouched by a non-releasable push)
|
||||
# permanently without the sync and without check runs. The resolve step
|
||||
# discovers any open release-please PR itself and no-ops when there is none.
|
||||
sync-release-lock:
|
||||
name: Sync Cargo.lock on the release PR
|
||||
needs: release-please
|
||||
if: ${{ needs.release-please.outputs.release_created == 'true' }}
|
||||
if: ${{ !cancelled() && github.repository == 'Gitlawb/node' && github.event_name != 'workflow_dispatch' }}
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: write
|
||||
pull-requests: read
|
||||
# actions: write lets the final step dispatch pr-checks on the release
|
||||
# branch. Note this grant is repo-wide dispatch rights (GitHub cannot
|
||||
# scope it to one workflow); acceptable here because reaching this job's
|
||||
# steps already requires write to main. Needed because every push to the
|
||||
# release branch (release-please's and the lock sync below) is made with
|
||||
# GITHUB_TOKEN, which triggers no workflow runs, so without an explicit
|
||||
# dispatch the release PR's head carries no check runs and the --locked
|
||||
# gate never validates it.
|
||||
actions: write
|
||||
steps:
|
||||
# Prefer the fresh `pr` output when this run just created/updated the
|
||||
# release PR; otherwise fall back to querying for an open release-please
|
||||
# branch (prefix match: the branch carries `--components--` suffixes).
|
||||
- name: Resolve the open release PR branch
|
||||
id: resolve
|
||||
env:
|
||||
GH_TOKEN: ${{ github.token }}
|
||||
OWNER: ${{ github.repository_owner }}
|
||||
BRANCH_FROM_OUTPUT: ${{ needs.release-please.outputs.pr && fromJSON(needs.release-please.outputs.pr).headBranchName || '' }}
|
||||
run: |
|
||||
branch="$BRANCH_FROM_OUTPUT"
|
||||
if [ -z "$branch" ]; then
|
||||
# The branch name alone is not a trust signal. `gh pr list` includes
|
||||
# fork PRs, and a fork's headRefName is bare (no owner prefix), so a
|
||||
# prefix match by itself lets any fork nominate the branch this job
|
||||
# checks out, commits to, and dispatches checks on. Require the head
|
||||
# repo to be THIS repository and the author to be the release-please
|
||||
# app, so neither a fork nor a same-repo human branch named
|
||||
# `release-please--*` can be selected. Then take the highest PR
|
||||
# number: `[0]` depended on gh's default ordering, which is not a
|
||||
# documented guarantee, and picking a stable one keeps a second
|
||||
# (component) release PR from making the choice flap between runs.
|
||||
branch=$(gh pr list --repo "$GITHUB_REPOSITORY" --state open \
|
||||
--json headRefName,headRepositoryOwner,number,author \
|
||||
--jq '[ .[]
|
||||
| select(.headRepositoryOwner.login == env.OWNER)
|
||||
| select(.author.login == "app/github-actions")
|
||||
| select(.headRefName | startswith("release-please--"))
|
||||
] | max_by(.number).headRefName // empty')
|
||||
fi
|
||||
if [ -z "$branch" ]; then
|
||||
echo "no open release PR; nothing to sync"
|
||||
fi
|
||||
echo "branch=$branch" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Checkout release branch
|
||||
if: ${{ steps.resolve.outputs.branch != '' }}
|
||||
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
|
||||
with:
|
||||
ref: ${{ steps.resolve.outputs.branch }}
|
||||
|
||||
# Resolve on a declared toolchain instead of whatever Rust the runner
|
||||
# image happens to ship, so the lock this job writes comes off the same
|
||||
# stable channel the other cargo jobs use. Not a claim of identical
|
||||
# resolution: `stable` still moves between runs, and the MSRV gate
|
||||
# checks this same lock on 1.91 (pr-checks.yml). It only removes the
|
||||
# runner image as an undeclared input.
|
||||
- name: Install Rust toolchain
|
||||
if: ${{ steps.resolve.outputs.branch != '' }}
|
||||
uses: dtolnay/rust-toolchain@b3b07ba8b418998c39fb20f53e8b695cdcc8de1b # stable
|
||||
with:
|
||||
toolchain: stable
|
||||
|
||||
- name: Sync workspace crate versions into Cargo.lock
|
||||
if: ${{ steps.resolve.outputs.branch != '' }}
|
||||
run: cargo update --workspace
|
||||
|
||||
- name: Commit and push when the lock changed
|
||||
if: ${{ steps.resolve.outputs.branch != '' }}
|
||||
run: |
|
||||
if git diff --quiet Cargo.lock; then
|
||||
echo "Cargo.lock already in sync"
|
||||
exit 0
|
||||
fi
|
||||
git config user.name "github-actions[bot]"
|
||||
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
|
||||
git add Cargo.lock
|
||||
git commit -m "chore: sync Cargo.lock with the release version bump"
|
||||
git push
|
||||
|
||||
# Every push to the release branch is made with GITHUB_TOKEN (release-
|
||||
# please's own pushes and the lock sync above), and events created by
|
||||
# GITHUB_TOKEN start no workflow runs. workflow_dispatch is the documented
|
||||
# exception GITHUB_TOKEN may trigger, so dispatch pr-checks at the release
|
||||
# branch to attach check runs to its current head. Unconditional (also on
|
||||
# the already-in-sync path) because the branch's ORIGINAL head has the
|
||||
# same no-runs problem. Loud on failure by design: a silent fallback
|
||||
# would recreate the checkless-head problem, and a job rerun is safe
|
||||
# (sync no-ops, dispatch retries). Loop-safe: pr-checks is read-only and
|
||||
# dispatches nothing. Runs after the push ack, so the dispatched ref tip
|
||||
# is the sync commit. Merge-queue note: this validates the branch tip;
|
||||
# the enforced merge queue's merge_group run still re-validates the true
|
||||
# merged result before landing.
|
||||
- name: Dispatch PR checks on the release branch
|
||||
if: ${{ steps.resolve.outputs.branch != '' }}
|
||||
env:
|
||||
GH_TOKEN: ${{ github.token }}
|
||||
BRANCH: ${{ steps.resolve.outputs.branch }}
|
||||
run: |
|
||||
# Every dispatch failure fails the job, including the 422 a release
|
||||
# branch cut before pr-checks gained its workflow_dispatch trigger
|
||||
# returns ("does not have a workflow_dispatch trigger", reported
|
||||
# against the dispatched ref's copy of the file). An earlier revision
|
||||
# tolerated exactly that 422 on the theory that release-please would
|
||||
# rewrite the branch and heal it, but a rewrite only happens when a
|
||||
# later releasable commit lands: an open release PR nobody touches is
|
||||
# never rewritten. Tolerating it therefore left the lock-sync commit
|
||||
# this job had just pushed sitting on the release head with no
|
||||
# --locked validation, which is the precise state this workflow exists
|
||||
# to prevent. The tolerance is also no longer needed: once this lands,
|
||||
# every release branch is cut from a main that already carries the
|
||||
# trigger, so the only branch that could 422 is one open at merge time
|
||||
# (there is none), and a job rerun after a manual rebase is safe (the
|
||||
# sync no-ops, the dispatch retries).
|
||||
gh api "repos/${GITHUB_REPOSITORY}/actions/workflows/pr-checks.yml/dispatches" \
|
||||
-f "ref=$BRANCH"
|
||||
|
||||
# Each architecture builds NATIVELY (amd64 on ubuntu-latest, arm64 on
|
||||
# ubuntu-24.04-arm) and pushes by digest; docker-manifest below stitches the
|
||||
# digests into the tagged multi-arch image. No QEMU: emulating the arm64
|
||||
# Rust release build wedged the v0.6.0 run for 3+ hours and, via the
|
||||
# workflow concurrency group, blocked every queued release run behind it.
|
||||
docker:
|
||||
name: Build & Push Docker Image (${{ matrix.arch }})
|
||||
needs: release-please
|
||||
# Runs on a fresh release, or on manual dispatch for an existing tag
|
||||
# (release-please is skipped on dispatch, hence !cancelled()).
|
||||
if: >-
|
||||
${{ !cancelled() && (
|
||||
needs.release-please.outputs.release_created == 'true' ||
|
||||
(github.event_name == 'workflow_dispatch' && inputs.docker_backfill_tag != '')
|
||||
) }}
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
include:
|
||||
- arch: amd64
|
||||
os: ubuntu-latest
|
||||
platform: linux/amd64
|
||||
- arch: arm64
|
||||
os: ubuntu-24.04-arm
|
||||
platform: linux/arm64
|
||||
runs-on: ${{ matrix.os }}
|
||||
permissions:
|
||||
contents: read
|
||||
packages: write
|
||||
steps:
|
||||
- name: Resolve release tag
|
||||
id: rel
|
||||
env:
|
||||
DISPATCH_TAG: ${{ inputs.docker_backfill_tag }}
|
||||
RELEASE_TAG: ${{ needs.release-please.outputs.tag_name }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
TAG="${DISPATCH_TAG:-$RELEASE_TAG}"
|
||||
case "$TAG" in
|
||||
v[0-9]*) ;;
|
||||
*) echo "::error::'$TAG' does not look like a release tag (vX.Y.Z)"; exit 1 ;;
|
||||
esac
|
||||
echo "tag=$TAG" >> "$GITHUB_OUTPUT"
|
||||
echo "version=${TAG#v}" >> "$GITHUB_OUTPUT"
|
||||
# ghcr requires a lowercase repository path, and unlike metadata-action,
|
||||
# buildx's `--output name=` does no lowercasing — a mixed-case owner
|
||||
# makes the digest push fail with "invalid reference format".
|
||||
echo "image=ghcr.io/${GITHUB_REPOSITORY,,}" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Checkout release tag
|
||||
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
|
||||
with:
|
||||
ref: ${{ needs.release-please.outputs.tag_name }}
|
||||
ref: ${{ steps.rel.outputs.tag }}
|
||||
persist-credentials: false
|
||||
|
||||
- name: Set up QEMU
|
||||
uses: docker/setup-qemu-action@29109295f81e9208d7d86ff1c6c12d2833863392 # v3.6.0
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
|
||||
|
||||
@@ -59,45 +251,130 @@ jobs:
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Extract metadata
|
||||
id: meta
|
||||
uses: docker/metadata-action@902fa8ec7d6ecbf8d84d538b9b233a880e428804 # v5.7.0
|
||||
with:
|
||||
images: ghcr.io/${{ github.repository }}
|
||||
tags: |
|
||||
type=semver,pattern={{version}},value=${{ needs.release-please.outputs.version }}
|
||||
type=semver,pattern={{major}}.{{minor}},value=${{ needs.release-please.outputs.version }}
|
||||
type=raw,value=latest
|
||||
|
||||
- name: Build and load locally (smoke)
|
||||
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
|
||||
with:
|
||||
context: .
|
||||
platforms: ${{ matrix.platform }}
|
||||
load: true
|
||||
tags: gitlawb-node:smoke
|
||||
cache-from: type=gha
|
||||
cache-from: type=gha,scope=docker-${{ matrix.arch }}
|
||||
|
||||
# Native runner on both arches, so the built image can always execute.
|
||||
# Assert the released version so a stale artifact fails here, not in prod.
|
||||
- name: Smoke test
|
||||
run: docker run --rm gitlawb-node:smoke --version
|
||||
env:
|
||||
VERSION: ${{ steps.rel.outputs.version }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
out="$(docker run --rm gitlawb-node:smoke --version)"
|
||||
echo "$out"
|
||||
grep -qF "$VERSION" <<<"$out" || {
|
||||
echo "::error::image --version did not report expected version $VERSION (got: $out)"
|
||||
exit 1
|
||||
}
|
||||
|
||||
- name: Build and push (multi-arch)
|
||||
# Push by digest only — tags are applied once by docker-manifest so a
|
||||
# half-finished matrix can never publish a partially-tagged image.
|
||||
# provenance:false keeps each push a plain single-arch manifest, which is
|
||||
# what imagetools create expects to merge.
|
||||
- name: Build and push by digest
|
||||
id: push
|
||||
uses: docker/build-push-action@14487ce63c7a62a4a324b0bfb37086795e31c6c1 # v6.16.0
|
||||
with:
|
||||
context: .
|
||||
platforms: linux/amd64,linux/arm64
|
||||
push: true
|
||||
tags: ${{ steps.meta.outputs.tags }}
|
||||
labels: ${{ steps.meta.outputs.labels }}
|
||||
cache-from: type=gha
|
||||
cache-to: type=gha,mode=max
|
||||
platforms: ${{ matrix.platform }}
|
||||
provenance: false
|
||||
outputs: type=image,name=${{ steps.rel.outputs.image }},push-by-digest=true,name-canonical=true,push=true
|
||||
cache-from: type=gha,scope=docker-${{ matrix.arch }}
|
||||
cache-to: type=gha,mode=max,scope=docker-${{ matrix.arch }}
|
||||
|
||||
- name: Export digest
|
||||
env:
|
||||
DIGEST: ${{ steps.push.outputs.digest }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
mkdir -p /tmp/digests
|
||||
touch "/tmp/digests/${DIGEST#sha256:}"
|
||||
|
||||
- name: Upload digest
|
||||
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
|
||||
with:
|
||||
name: docker-digest-${{ matrix.arch }}
|
||||
path: /tmp/digests/*
|
||||
if-no-files-found: error
|
||||
retention-days: 1
|
||||
|
||||
docker-manifest:
|
||||
name: Publish Docker manifest
|
||||
needs: [release-please, docker]
|
||||
if: ${{ !cancelled() && needs.docker.result == 'success' }}
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
packages: write
|
||||
steps:
|
||||
- name: Resolve release tag
|
||||
id: rel
|
||||
env:
|
||||
DISPATCH_TAG: ${{ inputs.docker_backfill_tag }}
|
||||
RELEASE_TAG: ${{ needs.release-please.outputs.tag_name }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
TAG="${DISPATCH_TAG:-$RELEASE_TAG}"
|
||||
case "$TAG" in
|
||||
v[0-9]*) ;;
|
||||
*) echo "::error::'$TAG' does not look like a release tag (vX.Y.Z)"; exit 1 ;;
|
||||
esac
|
||||
echo "tag=$TAG" >> "$GITHUB_OUTPUT"
|
||||
echo "version=${TAG#v}" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Download digests
|
||||
uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
|
||||
with:
|
||||
pattern: docker-digest-*
|
||||
path: /tmp/digests
|
||||
merge-multiple: true
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
|
||||
|
||||
- name: Log in to GitHub Container Registry
|
||||
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
|
||||
with:
|
||||
registry: ghcr.io
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Create and push multi-arch manifest
|
||||
env:
|
||||
VERSION: ${{ steps.rel.outputs.version }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
# ghcr requires a lowercase repository path.
|
||||
IMAGE="ghcr.io/${GITHUB_REPOSITORY,,}"
|
||||
MAJOR_MINOR="${VERSION%.*}"
|
||||
digests=""
|
||||
for f in /tmp/digests/*; do
|
||||
digests="$digests $IMAGE@sha256:$(basename "$f")"
|
||||
done
|
||||
# shellcheck disable=SC2086
|
||||
docker buildx imagetools create \
|
||||
-t "$IMAGE:$VERSION" \
|
||||
-t "$IMAGE:$MAJOR_MINOR" \
|
||||
-t "$IMAGE:latest" \
|
||||
$digests
|
||||
docker buildx imagetools inspect "$IMAGE:$VERSION"
|
||||
|
||||
- name: Release summary
|
||||
env:
|
||||
VERSION: ${{ steps.rel.outputs.version }}
|
||||
TAG: ${{ steps.rel.outputs.tag }}
|
||||
run: |
|
||||
{
|
||||
echo "## Released ${{ needs.release-please.outputs.tag_name }}"
|
||||
echo "## Released $TAG"
|
||||
echo
|
||||
echo "- Image: \`ghcr.io/${{ github.repository }}:${{ needs.release-please.outputs.version }}\`"
|
||||
echo "- GitHub: https://github.com/${{ github.repository }}/releases/tag/${{ needs.release-please.outputs.tag_name }}"
|
||||
echo "- Image: \`ghcr.io/${GITHUB_REPOSITORY,,}:$VERSION\` (linux/amd64 + linux/arm64)"
|
||||
echo "- GitHub: https://github.com/$GITHUB_REPOSITORY/releases/tag/$TAG"
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
|
||||
release-binaries:
|
||||
@@ -116,10 +393,14 @@ jobs:
|
||||
include:
|
||||
- target: x86_64-unknown-linux-musl
|
||||
os: ubuntu-latest
|
||||
# Native arm64 runner: cross-compiling this target with the glibc
|
||||
# toolchain broke aws-lc-sys, and native lets the smoke test run.
|
||||
- target: aarch64-unknown-linux-musl
|
||||
os: ubuntu-latest
|
||||
os: ubuntu-24.04-arm
|
||||
# macos-13 (the last plain Intel image) is retired and queues forever;
|
||||
# macos-15-intel is GitHub's supported Intel label.
|
||||
- target: x86_64-apple-darwin
|
||||
os: macos-13
|
||||
os: macos-15-intel
|
||||
- target: aarch64-apple-darwin
|
||||
os: macos-14
|
||||
- target: x86_64-pc-windows-msvc
|
||||
@@ -137,16 +418,13 @@ jobs:
|
||||
toolchain: stable
|
||||
targets: ${{ matrix.target }}
|
||||
|
||||
# Both musl targets build natively on a matching-arch runner, so the stock
|
||||
# musl-gcc wrapper is all that's needed (no cross toolchain).
|
||||
- name: Install musl tools (linux)
|
||||
if: contains(matrix.target, 'linux-musl')
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y musl-tools
|
||||
if [ "${{ matrix.target }}" = "aarch64-unknown-linux-musl" ]; then
|
||||
sudo apt-get install -y gcc-aarch64-linux-gnu
|
||||
echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_MUSL_LINKER=aarch64-linux-gnu-gcc" >> "$GITHUB_ENV"
|
||||
echo "CC_aarch64_unknown_linux_musl=aarch64-linux-gnu-gcc" >> "$GITHUB_ENV"
|
||||
fi
|
||||
|
||||
- name: Cache cargo
|
||||
uses: Swatinem/rust-cache@98c8021b550208e191a6a3145459bfc9fb29c4c0 # v2.8.0
|
||||
@@ -168,13 +446,12 @@ jobs:
|
||||
set -euo pipefail
|
||||
args=""
|
||||
for b in $BINS; do args="$args -p $b"; done
|
||||
cargo build --release --target ${{ matrix.target }} $args
|
||||
cargo build --release --locked --target ${{ matrix.target }} $args
|
||||
|
||||
# Run each packaged binary's --version so a broken release artifact fails the
|
||||
# build instead of shipping. Skipped for cross-compiled targets that can't run
|
||||
# on the host runner (aarch64 linux on an x86_64 runner).
|
||||
# build instead of shipping. Every target builds on a matching-arch runner,
|
||||
# so all of them can execute here.
|
||||
- name: Smoke test binaries
|
||||
if: ${{ matrix.target != 'aarch64-unknown-linux-musl' }}
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
@@ -248,37 +525,62 @@ jobs:
|
||||
npm-publish:
|
||||
name: Publish to npm
|
||||
needs: [release-please, release-binaries]
|
||||
if: ${{ needs.release-please.outputs.release_created == 'true' }}
|
||||
# Runs on a fresh release, or on manual dispatch for an existing tag
|
||||
# (release-binaries is skipped on dispatch, hence !cancelled()). Publishing
|
||||
# auth is npm Trusted Publishing (GitHub OIDC) — no NPM_TOKEN. Each
|
||||
# @gitlawb package must have this repo + workflow (release.yml) configured
|
||||
# as its trusted publisher on npmjs.com, or publish fails loudly here —
|
||||
# deliberately loud: the silent secret-guard skip is how 0.4.x–0.6.0
|
||||
# never reached npm.
|
||||
if: >-
|
||||
${{ !cancelled() && (
|
||||
(needs.release-please.outputs.release_created == 'true' && needs.release-binaries.result == 'success') ||
|
||||
(github.event_name == 'workflow_dispatch' && inputs.npm_backfill_tag != '')
|
||||
) }}
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
id-token: write # npm provenance
|
||||
id-token: write # npm trusted publishing (OIDC) + provenance
|
||||
steps:
|
||||
- name: Guard on secret
|
||||
id: guard
|
||||
- name: Resolve release tag
|
||||
id: rel
|
||||
env:
|
||||
NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
|
||||
DISPATCH_TAG: ${{ inputs.npm_backfill_tag }}
|
||||
RELEASE_TAG: ${{ needs.release-please.outputs.tag_name }}
|
||||
run: |
|
||||
if [ -z "${NPM_TOKEN:-}" ]; then
|
||||
echo "::warning::NPM_TOKEN is not set — skipping npm publish."
|
||||
echo "enabled=false" >> "$GITHUB_OUTPUT"
|
||||
else
|
||||
echo "enabled=true" >> "$GITHUB_OUTPUT"
|
||||
fi
|
||||
set -euo pipefail
|
||||
TAG="${DISPATCH_TAG:-$RELEASE_TAG}"
|
||||
case "$TAG" in
|
||||
v[0-9]*) ;;
|
||||
*) echo "::error::'$TAG' does not look like a release tag (vX.Y.Z)"; exit 1 ;;
|
||||
esac
|
||||
echo "tag=$TAG" >> "$GITHUB_OUTPUT"
|
||||
echo "version=${TAG#v}" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Checkout release tag
|
||||
if: ${{ steps.guard.outputs.enabled == 'true' }}
|
||||
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
|
||||
with:
|
||||
ref: ${{ needs.release-please.outputs.tag_name }}
|
||||
ref: ${{ steps.rel.outputs.tag }}
|
||||
persist-credentials: false
|
||||
|
||||
# npm >= 11.5.1 performs the OIDC token exchange automatically when the
|
||||
# package has a trusted publisher configured; older npm silently falls
|
||||
# back to (absent) token auth and fails confusingly.
|
||||
- name: Set up Node 24 + OIDC-capable npm
|
||||
uses: actions/setup-node@a0853c24544627f65ddf259abe73b1d18a591444 # v5.0.0
|
||||
with:
|
||||
node-version: "24"
|
||||
- name: Ensure npm supports trusted publishing
|
||||
run: |
|
||||
set -euo pipefail
|
||||
npm install -g npm@^11.5.1
|
||||
npm --version
|
||||
|
||||
- name: Lay in release binaries
|
||||
if: ${{ steps.guard.outputs.enabled == 'true' }}
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
VERSION: ${{ needs.release-please.outputs.version }}
|
||||
TAG: ${{ needs.release-please.outputs.tag_name }}
|
||||
VERSION: ${{ steps.rel.outputs.version }}
|
||||
TAG: ${{ steps.rel.outputs.tag }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
# npm platform package -> Rust target triple (unix only; Windows is not
|
||||
@@ -305,9 +607,8 @@ jobs:
|
||||
done
|
||||
|
||||
- name: Set versions
|
||||
if: ${{ steps.guard.outputs.enabled == 'true' }}
|
||||
env:
|
||||
VERSION: ${{ needs.release-please.outputs.version }}
|
||||
VERSION: ${{ steps.rel.outputs.version }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
node -e '
|
||||
@@ -327,13 +628,12 @@ jobs:
|
||||
'
|
||||
|
||||
- name: Publish
|
||||
if: ${{ steps.guard.outputs.enabled == 'true' }}
|
||||
env:
|
||||
NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
|
||||
VERSION: ${{ needs.release-please.outputs.version }}
|
||||
VERSION: ${{ steps.rel.outputs.version }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
echo "//registry.npmjs.org/:_authToken=${NPM_TOKEN}" > ~/.npmrc
|
||||
# No token: npm exchanges this job's GitHub OIDC identity with the
|
||||
# registry (trusted publishing); provenance is attested automatically.
|
||||
# Platform packages first, then the wrapper (so its optionalDependencies resolve).
|
||||
# Skip versions already on the registry so a rerun after a partial publish
|
||||
# is idempotent instead of erroring on the first existing package.
|
||||
@@ -429,6 +729,15 @@ jobs:
|
||||
bin.install "git-remote-gitlawb"
|
||||
end
|
||||
|
||||
def caveats
|
||||
<<~CAVEATS
|
||||
oh-my-zsh's git plugin aliases gl='git pull', which shadows this
|
||||
binary in interactive shells. If \`gl\` prints "fatal: not a git
|
||||
repository", run:
|
||||
echo 'unalias gl 2>/dev/null' >> ~/.zshrc && source ~/.zshrc
|
||||
CAVEATS
|
||||
end
|
||||
|
||||
test do
|
||||
assert_match version.to_s, shell_output("#{bin}/gl --version")
|
||||
end
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
{
|
||||
".": "0.4.0"
|
||||
".": "0.7.1"
|
||||
}
|
||||
@@ -1,5 +1,99 @@
|
||||
# Changelog
|
||||
|
||||
## [0.7.1](https://github.com/Gitlawb/node/compare/v0.7.0...v0.7.1) (2026-08-03)
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* **ci:** make the docker dependency cache work and unbreak Dockerfile.bins ([99b2b9a](https://github.com/Gitlawb/node/commit/99b2b9a16662761a3959a2941798e6823621bda5))
|
||||
* **ci:** make the docker dependency cache work and unbreak Dockerfile.bins ([a49e04d](https://github.com/Gitlawb/node/commit/a49e04ddcd23f3b666421486ae60c3c4329e2242)), closes [#265](https://github.com/Gitlawb/node/issues/265) [#266](https://github.com/Gitlawb/node/issues/266)
|
||||
* **db:** pin profile DID matching with lone non-key fixture and boundary matrix ([b4016dc](https://github.com/Gitlawb/node/commit/b4016dce9d1fe450603173f9d92bd880127620fa)), closes [#298](https://github.com/Gitlawb/node/issues/298)
|
||||
* **node:** add a shared owner/name slug validator ([#272](https://github.com/Gitlawb/node/issues/272)) ([51d82de](https://github.com/Gitlawb/node/commit/51d82ded57a776d9c7e2fe65895efdbf9e227dc8))
|
||||
* **node:** bound the slug owner by NAME_MAX, not the DID limit ([#272](https://github.com/Gitlawb/node/issues/272)) ([27b0495](https://github.com/Gitlawb/node/commit/27b0495a6f7edeecddbe62b0f075a7e3b1ef5053))
|
||||
* **node:** fail a sync row terminally when a non-directory holds the owner path ([2e664b7](https://github.com/Gitlawb/node/commit/2e664b7885036ee72ce175af95bb567b18222583))
|
||||
* **node:** make a stalled sync queue visible, and fix two test claims ([9aa4c17](https://github.com/Gitlawb/node/commit/9aa4c17aefd1885d134b1334b54551366cdd8ef0))
|
||||
* **node:** move the attempted_at migration to v17, clear of two open branches ([fbc5868](https://github.com/Gitlawb/node/commit/fbc5868bd16946ea184dad26abcdb0e89d68e99a))
|
||||
* **node:** prove the mirror path is inside repos_dir before running git ([#272](https://github.com/Gitlawb/node/issues/272)) ([3ca9473](https://github.com/Gitlawb/node/commit/3ca94739ed7b90e4c265a0947025dc3b50e7583b))
|
||||
* **node:** reject a malformed slug at the notify boundary ([#272](https://github.com/Gitlawb/node/issues/272)) ([c587a40](https://github.com/Gitlawb/node/commit/c587a40a508acea9f74c3468d42ff037397c75d0))
|
||||
* **node:** reset a peer's reachability gate when an announce changes its http_url ([#270](https://github.com/Gitlawb/node/issues/270)) ([1964f88](https://github.com/Gitlawb/node/commit/1964f88378fe6942ffca5836de3a092b5b8f67b4))
|
||||
* **node:** reset a peer's reachability gate when an announce changes its http_url ([#270](https://github.com/Gitlawb/node/issues/270)) ([e2560ee](https://github.com/Gitlawb/node/commit/e2560ee46c28e4e966d87867a86dc4bad4ca7a3a))
|
||||
* **node:** stamp every dequeued sync row so a stuck one yields the batch ([6e64d0d](https://github.com/Gitlawb/node/commit/6e64d0d0a7fdd38ef3a56820c1808dd7c9bbd658))
|
||||
* **node:** stop a peer-supplied repo slug from escaping repos_dir ([#272](https://github.com/Gitlawb/node/issues/272)) ([c70b1df](https://github.com/Gitlawb/node/commit/c70b1df42d5c3f70ec4c272886c85fcc16ed92d1))
|
||||
* **node:** validate the queued slug before the worker derives a path ([#272](https://github.com/Gitlawb/node/issues/272)) ([9f00e24](https://github.com/Gitlawb/node/commit/9f00e24aec217e4b8256dd437cff4741b1478b96))
|
||||
* **review:** correct two comment claims and guard two more wrong shapes ([#270](https://github.com/Gitlawb/node/issues/270)) ([811ad50](https://github.com/Gitlawb/node/commit/811ad504bc268c8e9cddac93822adcd00bfe9ff8))
|
||||
* **review:** stop the dequeue overclaiming, and pin the starvation premise ([457be11](https://github.com/Gitlawb/node/commit/457be11d728a2a34775cf96be2bc5af9a58cb250))
|
||||
* strict DID matching in get_profile ([acb4714](https://github.com/Gitlawb/node/commit/acb47145beec8ce7b20b7a2479f7a55ed68e2a89))
|
||||
* strict DID matching in get_profile ([13b565b](https://github.com/Gitlawb/node/commit/13b565bcac09f075a7fd555a6e9acdd27de6c7bb))
|
||||
* target stored did on profile update aliases ([9836c3a](https://github.com/Gitlawb/node/commit/9836c3a21bc96a2ce95cb1fd12bd84b22142787d))
|
||||
|
||||
## [0.7.0](https://github.com/Gitlawb/node/compare/v0.6.0...v0.7.0) (2026-07-22)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* **gl:** actually verify certificate signatures in gl cert show ([b0a2ed8](https://github.com/Gitlawb/node/commit/b0a2ed830821b5a77b0dafdcf5ce4b1ad904ec25))
|
||||
* **gl:** doctor warns when a shell alias shadows the gl binary ([0765c42](https://github.com/Gitlawb/node/commit/0765c42feff47b29054b9a277881a7cd5bfd9135))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* **gl:** address review findings — non-fatal DID check, exact-host loopback, detached HEAD, multi-URL remotes, command-aware unalias ([3fa38dc](https://github.com/Gitlawb/node/commit/3fa38dce4e435ef017f607d355266c2892161f8d))
|
||||
* **gl:** anchor cert --verify to a trusted issuer; pin canonical payload form ([c681af7](https://github.com/Gitlawb/node/commit/c681af70dba3a76b11795d324f2ca0fecf7e42fd))
|
||||
* **gl:** detect gitlawb remotes beyond origin in gl status ([2d88937](https://github.com/Gitlawb/node/commit/2d88937fbabf21013f28debb4d4f93270a4bb8cd))
|
||||
* **gl:** doctor treats a reachable local node as configuration, not failure ([94c61f7](https://github.com/Gitlawb/node/commit/94c61f79421fa26ecc1bdf7c255e0c48e66a2048))
|
||||
* **gl:** make gl init's push guidance match the repo's actual state ([cb42a48](https://github.com/Gitlawb/node/commit/cb42a4830d0d070165e2212f316d009ec716dbee))
|
||||
* warn about the oh-my-zsh gl alias at install time ([e3df51d](https://github.com/Gitlawb/node/commit/e3df51d76c0275fde33954ff0af0aab95fd0cb7d))
|
||||
|
||||
## [0.6.0](https://github.com/Gitlawb/node/compare/v0.5.1...v0.6.0) (2026-07-22)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* **icaptcha-client:** solve the iCaptcha proof-of-work on answer ([#181](https://github.com/Gitlawb/node/issues/181)) ([c98b503](https://github.com/Gitlawb/node/commit/c98b503f90cade54ce9c588bd2373a4e3486f2fc))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* **core:** honor wildcard capabilities in Ucan::can, matching is_attenuated_by ([#200](https://github.com/Gitlawb/node/issues/200)) ([b6877a6](https://github.com/Gitlawb/node/commit/b6877a65981dbf41c4a7838971eb5c826c7fcaf2))
|
||||
* **gl:** point doctor's version check at Gitlawb/node, not the frozen Gitlawb/releases repo ([#198](https://github.com/Gitlawb/node/issues/198)) ([98d728c](https://github.com/Gitlawb/node/commit/98d728c325f68f0ee4a62e473dc484b7dd627504))
|
||||
* **node:** carry full owner DID on ref-update wire event ([#144](https://github.com/Gitlawb/node/issues/144)) ([#145](https://github.com/Gitlawb/node/issues/145)) ([69a62e5](https://github.com/Gitlawb/node/commit/69a62e51c2d2f090f9cae88f4d8ce3b9017b7149))
|
||||
* **node:** gate /hooks and sibling read surfaces leaking private repo metadata ([#94](https://github.com/Gitlawb/node/issues/94)) ([#113](https://github.com/Gitlawb/node/issues/113)) ([ee8d7c0](https://github.com/Gitlawb/node/commit/ee8d7c03b26a0b678cc90b8801aa340fe81da700))
|
||||
* strip Cf bidi/format controls in terminal-bound error sanitizers ([#183](https://github.com/Gitlawb/node/issues/183)) ([#188](https://github.com/Gitlawb/node/issues/188)) ([b07d41e](https://github.com/Gitlawb/node/commit/b07d41ea97569d79d3f545ae5d43c373cd6f0f33))
|
||||
|
||||
## [0.5.1](https://github.com/Gitlawb/node/compare/v0.5.0...v0.5.1) (2026-07-10)
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* **bounties:** add tests for claim_bounty repo-read gate ([#160](https://github.com/Gitlawb/node/issues/160)) ([#169](https://github.com/Gitlawb/node/issues/169)) ([6bafaa6](https://github.com/Gitlawb/node/commit/6bafaa6dc5f05c0dcd61c708397afddbcf8c2e3f))
|
||||
* **deps:** bump crossbeam-epoch to 0.9.20 for RUSTSEC-2026-0204 ([#162](https://github.com/Gitlawb/node/issues/162)) ([#163](https://github.com/Gitlawb/node/issues/163)) ([67ad2b8](https://github.com/Gitlawb/node/commit/67ad2b876c8d9a336219d1016968de7a88fc4e75))
|
||||
* **node,git:** bound a hung served git with a total-duration timeout ([#62](https://github.com/Gitlawb/node/issues/62)) ([#165](https://github.com/Gitlawb/node/issues/165)) ([cd67718](https://github.com/Gitlawb/node/commit/cd67718f49ec38726a40f6bcf36f539ccdb42969))
|
||||
* **node:** bound list_ref_certificates with LIMIT and add upsert to prevent unbounded growth ([#147](https://github.com/Gitlawb/node/issues/147)) ([#149](https://github.com/Gitlawb/node/issues/149)) ([6b5e5bc](https://github.com/Gitlawb/node/commit/6b5e5bc7aee00a2d03295d3620df1ee4d8c024a2))
|
||||
* **node:** gate POST /api/v1/sync/trigger and rate-limit the peer-sync routes ([#82](https://github.com/Gitlawb/node/issues/82)) ([#161](https://github.com/Gitlawb/node/issues/161)) ([d00d89a](https://github.com/Gitlawb/node/commit/d00d89ae5be992d1f63e95b714ae1bd3735e8457))
|
||||
* **node:** rate-limit repo/agent creation per client IP to stop DID-farm spam floods ([#180](https://github.com/Gitlawb/node/issues/180)) ([dfcaa22](https://github.com/Gitlawb/node/commit/dfcaa22b23ec91be4c75926956aa994ca89de8d5))
|
||||
* **release:** build aarch64-musl natively on arm64 runners, replace retired macos-13 ([#155](https://github.com/Gitlawb/node/issues/155)) ([6cff528](https://github.com/Gitlawb/node/commit/6cff5286b436fdee44ad881999e2a5f4bdba18f9))
|
||||
* **visibility:** gate repo-scoped read surfaces on visibility ([#120](https://github.com/Gitlawb/node/issues/120)) ([#157](https://github.com/Gitlawb/node/issues/157)) ([26bc3f6](https://github.com/Gitlawb/node/commit/26bc3f69870aa77e43c0d92115a5aa59555b7d88))
|
||||
|
||||
## [0.5.0](https://github.com/Gitlawb/node/compare/v0.4.0...v0.5.0) (2026-07-05)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* **gl:** sanctioned iCaptcha client flow + secure git lifecycle ([#138](https://github.com/Gitlawb/node/issues/138)) ([06388ec](https://github.com/Gitlawb/node/commit/06388ec26aa29d356ae311276fdb91be054e9ecc))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* **gl:** sign the CLI's /ipfs/pins reads under the [#134](https://github.com/Gitlawb/node/issues/134) auth gate ([#146](https://github.com/Gitlawb/node/issues/146)) ([20d6848](https://github.com/Gitlawb/node/commit/20d6848846b3a988d604208833167a528b7d8820))
|
||||
* **node,git-remote:** gate receive-pack advertisement, sign client fetch/push ([#119](https://github.com/Gitlawb/node/issues/119)) ([6f36fc0](https://github.com/Gitlawb/node/commit/6f36fc07b8e10a650c5948b269feac1cb25cae2a))
|
||||
* **node,gossip:** route gossip HTTP through the no-redirect client ([#93](https://github.com/Gitlawb/node/issues/93)) ([#140](https://github.com/Gitlawb/node/issues/140)) ([563c456](https://github.com/Gitlawb/node/commit/563c456803bf3e958d63869db424b3940472bc3d))
|
||||
* **node:** close two spam-vector root causes (trust upsert + ungated push) ([#152](https://github.com/Gitlawb/node/issues/152)) ([2df6ff9](https://github.com/Gitlawb/node/commit/2df6ff9d30de62f754fa41473e85db316021718e))
|
||||
* **node:** gate GET /ipfs/{cid} on reachable allowed-set, not deny-set ([#126](https://github.com/Gitlawb/node/issues/126)) ([#133](https://github.com/Gitlawb/node/issues/133)) ([466a550](https://github.com/Gitlawb/node/commit/466a550915edd711856ef32035f9f474e2577c4f))
|
||||
* **node:** gate the ref-updates feeds on read visibility ([#112](https://github.com/Gitlawb/node/issues/112), [#114](https://github.com/Gitlawb/node/issues/114)) ([#143](https://github.com/Gitlawb/node/issues/143)) ([4891db3](https://github.com/Gitlawb/node/commit/4891db38892663326ee0c1417a2db931988be4b5))
|
||||
* **node:** prefer canonical repo row over mirror row in get_repo ([#124](https://github.com/Gitlawb/node/issues/124)) ([#141](https://github.com/Gitlawb/node/issues/141)) ([6c95592](https://github.com/Gitlawb/node/commit/6c95592d188222ac3446dc23ef8d9befbf82ad6f))
|
||||
* **remote:** include HTTP error response body ([#137](https://github.com/Gitlawb/node/issues/137)) ([09a0cb2](https://github.com/Gitlawb/node/commit/09a0cb23b9f284ccbd69aca6958b70671f3bfb46))
|
||||
* **repos:** log the cause when repo create fails ([#103](https://github.com/Gitlawb/node/issues/103)) ([2620e97](https://github.com/Gitlawb/node/commit/2620e973e3cd4835ed42ddd4adcd8183b5b3080e))
|
||||
|
||||
## [0.4.0](https://github.com/Gitlawb/node/compare/v0.3.9...v0.4.0) (2026-06-30)
|
||||
|
||||
|
||||
|
||||
Generated
+106
-13
@@ -770,6 +770,23 @@ dependencies = [
|
||||
"zeroize",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ark-ff"
|
||||
version = "0.6.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f7a806ac6c8307b929df4645776290a50ee2aac754ad09d8bdf73391309e43af"
|
||||
dependencies = [
|
||||
"ark-ff-asm 0.6.0",
|
||||
"ark-ff-macros 0.6.0",
|
||||
"ark-serialize 0.6.0",
|
||||
"ark-std 0.6.0",
|
||||
"digest 0.10.7",
|
||||
"educe",
|
||||
"num-bigint",
|
||||
"num-traits",
|
||||
"zeroize",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ark-ff-asm"
|
||||
version = "0.3.0"
|
||||
@@ -800,6 +817,16 @@ dependencies = [
|
||||
"syn 2.0.117",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ark-ff-asm"
|
||||
version = "0.6.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "1479009684adc073dff49a1025d3a7065b317a9ead25aaaca38cdc70058ba8a2"
|
||||
dependencies = [
|
||||
"quote",
|
||||
"syn 2.0.117",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ark-ff-macros"
|
||||
version = "0.3.0"
|
||||
@@ -838,6 +865,19 @@ dependencies = [
|
||||
"syn 2.0.117",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ark-ff-macros"
|
||||
version = "0.6.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "4a0691ed21ef00ef89c1e9bda832eba493dda3ec2f8d892fb25b705f73f06bb8"
|
||||
dependencies = [
|
||||
"num-bigint",
|
||||
"num-traits",
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn 2.0.117",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ark-serialize"
|
||||
version = "0.3.0"
|
||||
@@ -871,6 +911,30 @@ dependencies = [
|
||||
"num-bigint",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ark-serialize"
|
||||
version = "0.6.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "a74dd304fd536fb95d0a328e72be759209cc496a9da094c5bc56e5fea4f9e86b"
|
||||
dependencies = [
|
||||
"ark-serialize-derive",
|
||||
"ark-std 0.6.0",
|
||||
"digest 0.10.7",
|
||||
"num-bigint",
|
||||
"serde_with",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ark-serialize-derive"
|
||||
version = "0.6.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "4f153690697a2b91e5e1251ff98411ee5371500a111a0fd317a70e588eb300f9"
|
||||
dependencies = [
|
||||
"proc-macro2",
|
||||
"quote",
|
||||
"syn 2.0.117",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ark-std"
|
||||
version = "0.3.0"
|
||||
@@ -901,6 +965,16 @@ dependencies = [
|
||||
"rand 0.8.6",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ark-std"
|
||||
version = "0.6.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "367c9c827ed431bff6868b7aa926e05b16eb46603cc8b6e768e4a5553fa1d155"
|
||||
dependencies = [
|
||||
"num-traits",
|
||||
"rand 0.8.6",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "arrayref"
|
||||
version = "0.3.9"
|
||||
@@ -2293,9 +2367,9 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "crossbeam-epoch"
|
||||
version = "0.9.18"
|
||||
version = "0.9.20"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
|
||||
checksum = "2d6914041f254d6e9176c01941b21115dcfb7089e55135a35411081bd106ef3f"
|
||||
dependencies = [
|
||||
"crossbeam-utils",
|
||||
]
|
||||
@@ -2556,7 +2630,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "7ab67060fc6b8ef687992d439ca0fa36e7ed17e9a0b16b25b601e8757df720de"
|
||||
dependencies = [
|
||||
"data-encoding",
|
||||
"syn 1.0.109",
|
||||
"syn 2.0.117",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -2928,7 +3002,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
|
||||
dependencies = [
|
||||
"libc",
|
||||
"windows-sys 0.52.0",
|
||||
"windows-sys 0.61.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -3300,10 +3374,11 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "git-remote-gitlawb"
|
||||
version = "0.3.9"
|
||||
version = "0.7.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"gitlawb-core",
|
||||
"mockito",
|
||||
"reqwest",
|
||||
"tracing",
|
||||
"tracing-subscriber",
|
||||
@@ -3311,7 +3386,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "gitlawb-attest"
|
||||
version = "0.3.9"
|
||||
version = "0.7.1"
|
||||
dependencies = [
|
||||
"base64",
|
||||
"ed25519-dalek",
|
||||
@@ -3328,7 +3403,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "gitlawb-core"
|
||||
version = "0.3.9"
|
||||
version = "0.7.1"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"base64",
|
||||
@@ -3355,7 +3430,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "gitlawb-node"
|
||||
version = "0.3.9"
|
||||
version = "0.7.1"
|
||||
dependencies = [
|
||||
"alloy",
|
||||
"anyhow",
|
||||
@@ -3411,14 +3486,16 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "gl"
|
||||
version = "0.3.9"
|
||||
version = "0.7.1"
|
||||
dependencies = [
|
||||
"alloy",
|
||||
"anyhow",
|
||||
"base64",
|
||||
"chrono",
|
||||
"clap",
|
||||
"dirs",
|
||||
"gitlawb-core",
|
||||
"icaptcha-client",
|
||||
"mockito",
|
||||
"reqwest",
|
||||
"serde",
|
||||
@@ -3813,6 +3890,21 @@ dependencies = [
|
||||
"cc",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "icaptcha-client"
|
||||
version = "0.4.0"
|
||||
dependencies = [
|
||||
"anyhow",
|
||||
"gitlawb-core",
|
||||
"mockito",
|
||||
"reqwest",
|
||||
"serde",
|
||||
"serde_json",
|
||||
"sha2",
|
||||
"thiserror 2.0.18",
|
||||
"tracing",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "icu_collections"
|
||||
version = "2.1.1"
|
||||
@@ -5723,14 +5815,15 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "ruint"
|
||||
version = "1.17.2"
|
||||
version = "1.20.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c141e807189ad38a07276942c6623032d3753c8859c146104ac2e4d68865945a"
|
||||
checksum = "f5e99bff0393163bb25029a6af25d3d8d202ba5b5438a74d1bd8789f5c822970"
|
||||
dependencies = [
|
||||
"alloy-rlp",
|
||||
"ark-ff 0.3.0",
|
||||
"ark-ff 0.4.2",
|
||||
"ark-ff 0.5.0",
|
||||
"ark-ff 0.6.0",
|
||||
"bytes",
|
||||
"fastrlp 0.3.1",
|
||||
"fastrlp 0.4.0",
|
||||
@@ -5804,7 +5897,7 @@ dependencies = [
|
||||
"errno",
|
||||
"libc",
|
||||
"linux-raw-sys",
|
||||
"windows-sys 0.52.0",
|
||||
"windows-sys 0.61.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
@@ -6698,7 +6791,7 @@ dependencies = [
|
||||
"getrandom 0.4.2",
|
||||
"once_cell",
|
||||
"rustix",
|
||||
"windows-sys 0.52.0",
|
||||
"windows-sys 0.61.2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
||||
@@ -6,6 +6,7 @@ members = [
|
||||
"crates/gl",
|
||||
"crates/git-remote-gitlawb",
|
||||
"crates/gitlawb-attest",
|
||||
"crates/icaptcha-client",
|
||||
]
|
||||
|
||||
[workspace.package]
|
||||
|
||||
+18
-5
@@ -8,20 +8,33 @@ FROM rust:1.91-bookworm AS builder
|
||||
|
||||
WORKDIR /build
|
||||
|
||||
# Cache dependencies first for faster rebuilds
|
||||
# Cache dependencies first for faster rebuilds.
|
||||
# EVERY workspace member's manifest must be copied here, not just the ones this
|
||||
# image ships: cargo loads the whole workspace before it resolves anything, so a
|
||||
# missing member's Cargo.toml (or a path dependency pointing at one) aborts the
|
||||
# layer before a single crate is fetched.
|
||||
COPY Cargo.toml Cargo.lock ./
|
||||
COPY crates/gitlawb-core/Cargo.toml crates/gitlawb-core/
|
||||
COPY crates/gitlawb-node/Cargo.toml crates/gitlawb-node/
|
||||
COPY crates/gl/Cargo.toml crates/gl/
|
||||
COPY crates/git-remote-gitlawb/Cargo.toml crates/git-remote-gitlawb/
|
||||
COPY crates/gitlawb-attest/Cargo.toml crates/gitlawb-attest/
|
||||
COPY crates/icaptcha-client/Cargo.toml crates/icaptcha-client/
|
||||
|
||||
# Fetch deps (this layer caches until Cargo.{toml,lock} change)
|
||||
RUN mkdir -p crates/gitlawb-core/src crates/gitlawb-node/src crates/gl/src crates/git-remote-gitlawb/src && \
|
||||
# Fetch deps (this layer caches until Cargo.{toml,lock} change).
|
||||
# No `|| true`: this layer is expected to succeed, and swallowing its exit code
|
||||
# is what let it sit dead from the moment gl gained a path dependency on
|
||||
# icaptcha-client. A failure here should stop the build, not silently turn every
|
||||
# image build into a cold one.
|
||||
RUN mkdir -p crates/gitlawb-core/src crates/gitlawb-node/src crates/gl/src \
|
||||
crates/git-remote-gitlawb/src crates/gitlawb-attest/src crates/icaptcha-client/src && \
|
||||
echo 'fn main() {}' > crates/gitlawb-node/src/main.rs && \
|
||||
echo 'fn main() {}' > crates/gl/src/main.rs && \
|
||||
echo 'fn main() {}' > crates/git-remote-gitlawb/src/main.rs && \
|
||||
echo '' > crates/gitlawb-core/src/lib.rs && \
|
||||
cargo build --release -p gitlawb-node -p gl -p git-remote-gitlawb || true
|
||||
echo '' > crates/gitlawb-attest/src/lib.rs && \
|
||||
echo '' > crates/icaptcha-client/src/lib.rs && \
|
||||
cargo build --release --locked -p gitlawb-node -p gl -p git-remote-gitlawb
|
||||
|
||||
# Now copy real sources and build for real.
|
||||
# Force-bump mtimes so cargo's fingerprint check rebuilds — without this,
|
||||
@@ -34,7 +47,7 @@ RUN find crates -name "*.rs" -exec touch {} + && \
|
||||
rm -rf target/release/.fingerprint/gitlawb-node-* \
|
||||
target/release/.fingerprint/gl-* \
|
||||
target/release/.fingerprint/git-remote-gitlawb-* && \
|
||||
cargo build --release -p gitlawb-node -p gl -p git-remote-gitlawb && \
|
||||
cargo build --release --locked -p gitlawb-node -p gl -p git-remote-gitlawb && \
|
||||
strip target/release/gitlawb-node target/release/gl target/release/git-remote-gitlawb
|
||||
|
||||
# ── Runtime stage ───────────────────────────────────────────────────────────
|
||||
|
||||
+5
-2
@@ -3,7 +3,10 @@
|
||||
# Used by scripts/build-bins.sh — not used for node deployment.
|
||||
ARG TARGET=x86_64-unknown-linux-musl
|
||||
|
||||
FROM rust:1.85-bookworm AS builder
|
||||
# Must stay at or above the workspace `rust-version` in Cargo.toml. An unmet
|
||||
# MSRV is a hard cargo error, and nothing in CI builds this file, so a stale
|
||||
# base image here fails only when someone runs scripts/build-bins.sh.
|
||||
FROM rust:1.91-bookworm AS builder
|
||||
ARG TARGET
|
||||
|
||||
WORKDIR /build
|
||||
@@ -23,7 +26,7 @@ COPY crates/ crates/
|
||||
# Configure cross-linker for aarch64
|
||||
ENV CARGO_TARGET_AARCH64_UNKNOWN_LINUX_MUSL_LINKER=aarch64-linux-gnu-gcc
|
||||
|
||||
RUN cargo build --release --target "$TARGET" -p gl -p git-remote-gitlawb
|
||||
RUN cargo build --release --locked --target "$TARGET" -p gl -p git-remote-gitlawb
|
||||
|
||||
FROM debian:bookworm-slim
|
||||
ARG TARGET
|
||||
|
||||
@@ -185,6 +185,45 @@ git clone gitlawb://did:key:z6Mk.../my-repo
|
||||
|
||||
For public-network use, make sure `GITLAWB_NODE` points to the node you want. The helper defaults to localhost for local development.
|
||||
|
||||
### Full lifecycle against an iCaptcha-enforcing node
|
||||
|
||||
Public nodes (e.g. `node.gitlawb.com`) require two things on writes:
|
||||
|
||||
1. **RFC 9421 HTTP Signatures** — every write is signed by your identity key. `gl`
|
||||
and the `git-remote-gitlawb` helper do this automatically. An old/unsigned CLI
|
||||
fails with `401 not_an_agent`; `gl` will tell you to upgrade and register.
|
||||
2. **An iCaptcha proof** on the spam-gated writes (**repo create, fork, register**).
|
||||
`gl` solves this for you: on the node's `403 icaptcha_proof_required` it reads the
|
||||
`x-icaptcha-url` / `x-icaptcha-level` hints, requests a challenge, solves it
|
||||
locally (arithmetic / algebra / sequence), and **retries the same signed request**
|
||||
with the `x-icaptcha-proof` header — no manual steps, no env vars.
|
||||
|
||||
```bash
|
||||
gl identity new # create did:key identity
|
||||
gl register --node https://node.gitlawb.com # signed + auto-solves iCaptcha
|
||||
gl repo create memlawb --node https://node.gitlawb.com # signed + auto-solves iCaptcha
|
||||
git push origin2 main # origin2 = gitlawb://<your-did>/memlawb (signed)
|
||||
git clone gitlawb://<your-did>/memlawb # public read, no proof needed
|
||||
gl doctor # preflight: identity, node, version, iCaptcha
|
||||
```
|
||||
|
||||
Notes:
|
||||
|
||||
- **`requesterId` is always your DID.** The proof's `sub` claim must equal the
|
||||
authenticated signer; `gl`/helper set this automatically and the node enforces
|
||||
`sub == authenticated DID` (so a proof minted for another identity is rejected).
|
||||
- **Proofs are short-lived (~5 min TTL) and single-use.** If one expires between
|
||||
solving and use, the client transparently solves a fresh one and retries.
|
||||
- **What needs what:** create / fork / register are signed **and** iCaptcha-gated;
|
||||
`git push` is **signed-only** (owner signature is the gate — no per-push challenge);
|
||||
reads (clone / fetch / `repo info`) need no proof. A non-existent repo returns a
|
||||
clear `404`, never a placeholder.
|
||||
- **API-key iCaptcha deployments:** set `GITLAWB_ICAPTCHA_URL` to your iCaptcha
|
||||
origin and `GITLAWB_ICAPTCHA_API_KEY` to its key. The client only talks to an
|
||||
`https` origin whose host is allowlisted (that URL or the public default), and
|
||||
sends the bearer token **only** to your configured origin — never to a URL a
|
||||
node advertises — so a hostile node can't capture the key or redirect the solve.
|
||||
|
||||
---
|
||||
|
||||
## Architecture
|
||||
@@ -263,20 +302,21 @@ POST /api/v1/bounties/{id}/...
|
||||
POST /{owner}/{repo}/git-receive-pack
|
||||
```
|
||||
|
||||
Peer write routes support staged rollout:
|
||||
These peer write routes support staged rollout:
|
||||
|
||||
```txt
|
||||
POST /api/v1/peers/announce
|
||||
POST /api/v1/sync/notify
|
||||
POST /api/v1/sync/trigger
|
||||
```
|
||||
|
||||
When `GITLAWB_REQUIRE_SIGNED_PEER_WRITES=false`, unsigned legacy peers are accepted, but signed requests are verified when signature headers are present. Once all live peers upgrade, operators can set:
|
||||
When `GITLAWB_REQUIRE_SIGNED_PEER_WRITES=false`, unsigned legacy peers are accepted on those two routes, but signed requests are verified when signature headers are present. Once all live peers upgrade, operators can set:
|
||||
|
||||
```bash
|
||||
GITLAWB_REQUIRE_SIGNED_PEER_WRITES=true
|
||||
```
|
||||
|
||||
`POST /api/v1/sync/trigger` is not part of the staged rollout: it always requires a signature in both config modes and returns 401 without one, because each call drives an O(peers) outbound fan-out.
|
||||
|
||||
---
|
||||
|
||||
## Configuration
|
||||
@@ -303,6 +343,7 @@ Important node settings:
|
||||
| `GITLAWB_REQUIRE_SIGNED_PEER_WRITES` | Require signed peer announce/sync writes. |
|
||||
| `GITLAWB_AUTO_SYNC` | Enable automatic sync from known peers. |
|
||||
| `GITLAWB_MAX_PACK_BYTES` | Max git pack body size for smart-HTTP routes. |
|
||||
| `GITLAWB_GIT_SERVICE_TIMEOUT_SECS` | Max seconds a served git upload-pack/receive-pack may run before it is aborted (504). Default 600. Does not bound `info/refs` or the withheld-blob path. |
|
||||
| `GITLAWB_TIGRIS_BUCKET` | Optional S3/Tigris shared repo storage bucket. |
|
||||
| `GITLAWB_PINATA_JWT` | Optional Pinata/IPFS warm-storage pinning. |
|
||||
| `GITLAWB_IRYS_URL` | Optional Irys/Arweave permanent anchoring. |
|
||||
|
||||
@@ -0,0 +1,112 @@
|
||||
# Dependency allowlist for the `gitlawb-core` crate.
|
||||
#
|
||||
# gitlawb-core is the shared-primitives crate every consumer embeds (the `gl`
|
||||
# CLI, git-remote-gitlawb, the node daemon). It must stay lean so those
|
||||
# consumers do not inherit daemon-weight dependencies. This file is the source
|
||||
# of truth for the crates gitlawb-core's NORMAL (non-dev, non-build) transitive
|
||||
# dependency closure is allowed to contain. CI (`scripts/check-gitlawb-core-deps.sh`,
|
||||
# wired into the `core-deps-purity` job in .github/workflows/pr-checks.yml)
|
||||
# fails if gitlawb-core's tree contains any crate not listed here.
|
||||
#
|
||||
# The allowlist is exhaustive-by-construction: a NEW dependency reds CI whether
|
||||
# or not anyone thought to ban it, which a denylist cannot do.
|
||||
#
|
||||
# Measured in-workspace, so feature unification across the workspace can, in
|
||||
# rare cases, surface a crate here that gitlawb-core would not pull standalone.
|
||||
# An unexpected new entry is a prompt to check what pulled it in, not noise to
|
||||
# rubber-stamp.
|
||||
#
|
||||
# Regenerate (from repo root, after an INTENTIONAL dependency change):
|
||||
# cargo tree -p gitlawb-core --edges normal --prefix none \
|
||||
# | sed -E 's/ v[0-9].*$//' \
|
||||
# | grep -v '^gitlawb-core$' \
|
||||
# | sort -u
|
||||
# then paste the result below this header block. (The checker snapshots and
|
||||
# restores Cargo.lock; a manual regen may refresh it — `git checkout Cargo.lock`
|
||||
# afterward if you did not intend that.)
|
||||
#
|
||||
# Lines starting with `#` and blank lines are ignored by the checker.
|
||||
aead
|
||||
anyhow
|
||||
base-x
|
||||
base256emoji
|
||||
base64
|
||||
base64ct
|
||||
block-buffer
|
||||
cfg-if
|
||||
chacha20
|
||||
chacha20poly1305
|
||||
chrono
|
||||
cid
|
||||
cipher
|
||||
const-oid
|
||||
const-str
|
||||
core2
|
||||
cpufeatures
|
||||
crypto-common
|
||||
crypto_box
|
||||
crypto_secretbox
|
||||
curve25519-dalek
|
||||
curve25519-dalek-derive
|
||||
data-encoding
|
||||
data-encoding-macro
|
||||
data-encoding-macro-internal
|
||||
der
|
||||
digest
|
||||
ed25519
|
||||
ed25519-dalek
|
||||
equivalent
|
||||
generic-array
|
||||
getrandom
|
||||
hashbrown
|
||||
hex
|
||||
iana-time-zone
|
||||
indexmap
|
||||
inout
|
||||
itoa
|
||||
libc
|
||||
match-lookup
|
||||
memchr
|
||||
multibase
|
||||
multihash
|
||||
multihash-codetable
|
||||
multihash-derive
|
||||
multihash-derive-impl
|
||||
num-traits
|
||||
opaque-debug
|
||||
pem-rfc7468
|
||||
pkcs8
|
||||
poly1305
|
||||
ppv-lite86
|
||||
proc-macro-crate
|
||||
proc-macro2
|
||||
quote
|
||||
rand
|
||||
rand_chacha
|
||||
rand_core
|
||||
salsa20
|
||||
serde
|
||||
serde_core
|
||||
serde_derive
|
||||
serde_json
|
||||
sha2
|
||||
signature
|
||||
spki
|
||||
subtle
|
||||
syn
|
||||
synstructure
|
||||
thiserror
|
||||
thiserror-impl
|
||||
toml_datetime
|
||||
toml_edit
|
||||
toml_parser
|
||||
typenum
|
||||
unicode-ident
|
||||
universal-hash
|
||||
unsigned-varint
|
||||
uuid
|
||||
winnow
|
||||
zerocopy
|
||||
zeroize
|
||||
zeroize_derive
|
||||
zmij
|
||||
@@ -1,7 +1,7 @@
|
||||
[package]
|
||||
name = "git-remote-gitlawb"
|
||||
description = "Git remote helper — enables 'git clone gitlawb://did:gitlawb:...'"
|
||||
version = "0.4.0" # x-release-please-version
|
||||
version = "0.7.1" # x-release-please-version
|
||||
edition.workspace = true
|
||||
rust-version.workspace = true
|
||||
license.workspace = true
|
||||
@@ -16,3 +16,6 @@ anyhow = { workspace = true }
|
||||
reqwest = { workspace = true }
|
||||
tracing = { workspace = true }
|
||||
tracing-subscriber = { workspace = true }
|
||||
|
||||
[dev-dependencies]
|
||||
mockito = "1"
|
||||
@@ -14,7 +14,13 @@
|
||||
//! # Protocol flow (connect capability)
|
||||
//! capabilities → "connect\n\n"
|
||||
//! connect git-upload-pack → GET /info/refs | POST /git-upload-pack
|
||||
//! connect git-receive-pack → GET /info/refs | POST /git-receive-pack (+ auth header)
|
||||
//! connect git-receive-pack → GET /info/refs | POST /git-receive-pack
|
||||
//! Push (git-receive-pack) is RFC-9421 signed from the first request when an
|
||||
//! identity keypair is present, since a push can never be anonymous. Fetch
|
||||
//! (git-upload-pack) stays anonymous and is signed only on a single retry, after
|
||||
//! the node denies the anonymous advertisement with 404 — so a public clone never
|
||||
//! discloses the caller's DID, while a private repo's owner (or an authorized
|
||||
//! reader) still authenticates when the node demands it.
|
||||
|
||||
use anyhow::{bail, Context, Result};
|
||||
use gitlawb_core::http_sig::sign_request;
|
||||
@@ -63,7 +69,10 @@ fn main() -> Result<()> {
|
||||
let repo_base = format!("{}/{}/{}", node_base, short_owner, repo_name);
|
||||
tracing::debug!("repo_base: {repo_base}");
|
||||
|
||||
// Load keypair for signing push requests (optional — push still works unsigned in v0.1)
|
||||
// Load keypair for signing requests (optional). Push always signs when a key is
|
||||
// present; fetch signs only if the node 404s the anonymous advertisement, so
|
||||
// public fetches stay anonymous. Absent a key, public fetch still works and push
|
||||
// falls back to unsigned (v0.1 local alpha only).
|
||||
let keypair = load_keypair();
|
||||
|
||||
run_helper(&repo_base, keypair.as_ref())
|
||||
@@ -115,7 +124,7 @@ fn help_text() -> String {
|
||||
\n\
|
||||
ENVIRONMENT:\n\
|
||||
\x20 GITLAWB_NODE Node base URL (default: http://127.0.0.1:7545)\n\
|
||||
\x20 GITLAWB_KEY Identity PEM path for signed pushes (default: ~/.gitlawb/identity.pem)\n\
|
||||
\x20 GITLAWB_KEY Identity PEM path for signed fetch/push (default: ~/.gitlawb/identity.pem)\n\
|
||||
\x20 GITLAWB_LOG Log filter (default: warn)\n\
|
||||
\n\
|
||||
FLAGS:\n\
|
||||
@@ -179,11 +188,11 @@ fn run_helper(repo_base: &str, keypair: Option<&Keypair>) -> Result<()> {
|
||||
|
||||
// ── HTTP proxy for git smart protocol ────────────────────────────────────────
|
||||
|
||||
fn handle_connect(
|
||||
fn handle_connect<R: Read>(
|
||||
repo_base: &str,
|
||||
service: &str,
|
||||
keypair: Option<&Keypair>,
|
||||
stdin: &mut io::BufReader<io::Stdin>,
|
||||
stdin: &mut R,
|
||||
) -> Result<()> {
|
||||
match service {
|
||||
"git-upload-pack" | "git-receive-pack" => {}
|
||||
@@ -198,19 +207,52 @@ fn handle_connect(
|
||||
//
|
||||
// The server advertises its refs. git reads this to decide what to fetch/push.
|
||||
|
||||
// Signing policy for this exchange, carried through to the Phase-2 POST:
|
||||
// - git-receive-pack (push): sign from the first request; a push is
|
||||
// signature-gated and can never be anonymous.
|
||||
// - git-upload-pack (fetch): start anonymous so a public clone never discloses
|
||||
// the caller's DID, then escalate to a single signed retry only if the node
|
||||
// denies the anonymous advertisement with 404 (how it withholds a private
|
||||
// repo from an unauthenticated reader).
|
||||
let mut signing_key = if service == "git-receive-pack" {
|
||||
keypair
|
||||
} else {
|
||||
None
|
||||
};
|
||||
|
||||
let refs_url = format!("{}/info/refs?service={}", repo_base, service);
|
||||
tracing::debug!("GET {refs_url}");
|
||||
|
||||
let refs_resp = client
|
||||
.get(&refs_url)
|
||||
.header("User-Agent", "git/2.0 git-remote-gitlawb/0.1.0")
|
||||
let mut refs_resp = build_advertisement_request(&client, &refs_url, signing_key)
|
||||
.send()
|
||||
.with_context(|| format!("GET {refs_url}"))?;
|
||||
|
||||
// Fetch escalation: retry the advertisement signed once when the anonymous try
|
||||
// is denied and we hold an identity. A public repo answers 200 on the first
|
||||
// (anonymous) request and never reaches here, so it stays DID-private.
|
||||
if service == "git-upload-pack"
|
||||
&& refs_resp.status() == reqwest::StatusCode::NOT_FOUND
|
||||
&& keypair.is_some()
|
||||
{
|
||||
tracing::debug!("anonymous info/refs returned 404; retrying signed");
|
||||
signing_key = keypair;
|
||||
refs_resp = build_advertisement_request(&client, &refs_url, signing_key)
|
||||
.send()
|
||||
.with_context(|| format!("GET {refs_url} (signed retry)"))?;
|
||||
}
|
||||
|
||||
if !refs_resp.status().is_success() {
|
||||
let status = refs_resp.status();
|
||||
let body = read_error_body(refs_resp);
|
||||
bail!(
|
||||
"GET /info/refs returned {} — is the repo registered on this node?",
|
||||
refs_resp.status()
|
||||
"{}",
|
||||
http_error_message(
|
||||
"GET",
|
||||
"/info/refs",
|
||||
status,
|
||||
&body,
|
||||
Some("— is the repo registered on this node?")
|
||||
)
|
||||
);
|
||||
}
|
||||
|
||||
@@ -266,29 +308,7 @@ fn handle_connect(
|
||||
let post_url = format!("{}/{}", repo_base, service);
|
||||
tracing::debug!("POST {post_url} ({} bytes)", request_body.len());
|
||||
|
||||
// Extract the URL path for signing (e.g., "/z6Mk.../my-repo/git-receive-pack")
|
||||
let path_for_sig = url_path(&post_url);
|
||||
|
||||
let mut req = client
|
||||
.post(&post_url)
|
||||
.header("Content-Type", format!("application/x-{}-request", service))
|
||||
.header("User-Agent", "git/2.0 git-remote-gitlawb/0.1.0");
|
||||
|
||||
// Add RFC 9421 HTTP Signature auth on push operations
|
||||
if service == "git-receive-pack" {
|
||||
if let Some(kp) = keypair {
|
||||
let signed = sign_request(kp, "POST", &path_for_sig, &request_body);
|
||||
req = req
|
||||
.header("Content-Digest", signed.content_digest)
|
||||
.header("Signature-Input", signed.signature_input)
|
||||
.header("Signature", signed.signature);
|
||||
tracing::debug!("attached RFC 9421 HTTP Signature (DID: {})", kp.did());
|
||||
} else {
|
||||
tracing::warn!(
|
||||
"no identity keypair found — push will be unsigned (v0.1 local alpha only)"
|
||||
);
|
||||
}
|
||||
}
|
||||
let req = build_pack_post_request(&client, &post_url, service, &request_body, signing_key);
|
||||
|
||||
// Attach the body after signing so the pack bytes are moved, not cloned —
|
||||
// packs can be large and the clone doubled peak memory on push.
|
||||
@@ -298,7 +318,10 @@ fn handle_connect(
|
||||
.with_context(|| format!("POST {post_url}"))?;
|
||||
|
||||
if !pack_resp.status().is_success() {
|
||||
bail!("POST /{} returned {}", service, pack_resp.status());
|
||||
let status = pack_resp.status();
|
||||
let body = read_error_body(pack_resp);
|
||||
let path = format!("/{service}");
|
||||
bail!("{}", http_error_message("POST", &path, status, &body, None));
|
||||
}
|
||||
|
||||
let pack_bytes = pack_resp.bytes().context("reading pack response")?;
|
||||
@@ -310,6 +333,68 @@ fn handle_connect(
|
||||
Ok(())
|
||||
}
|
||||
|
||||
// ── Smart-protocol request builders ───────────────────────────────────────────
|
||||
|
||||
const USER_AGENT: &str = "git/2.0 git-remote-gitlawb/0.1.0";
|
||||
|
||||
/// Build the Phase-1 ref-advertisement GET, signing it when an identity is
|
||||
/// present. The node gates the ref advertisement on read visibility for BOTH
|
||||
/// services, so a private repo's advertisement is denied (404) to an
|
||||
/// unauthenticated caller; without this signature the repo's own owner can
|
||||
/// neither fetch (upload-pack) nor push (receive-pack) it. Public repos still
|
||||
/// work anonymously (no keypair present, or the gate admits anonymous). Sign over
|
||||
/// the path *and* query (?service=...) because the node verifies the signature
|
||||
/// over its path_and_query.
|
||||
fn build_advertisement_request(
|
||||
client: &reqwest::blocking::Client,
|
||||
refs_url: &str,
|
||||
keypair: Option<&Keypair>,
|
||||
) -> reqwest::blocking::RequestBuilder {
|
||||
let mut req = client.get(refs_url).header("User-Agent", USER_AGENT);
|
||||
if let Some(kp) = keypair {
|
||||
let signed = sign_request(kp, "GET", &url_path(refs_url), b"");
|
||||
req = req
|
||||
.header("Content-Digest", signed.content_digest)
|
||||
.header("Signature-Input", signed.signature_input)
|
||||
.header("Signature", signed.signature);
|
||||
tracing::debug!("signed info/refs advertisement (DID: {})", kp.did());
|
||||
}
|
||||
req
|
||||
}
|
||||
|
||||
/// Build the Phase-2 pack POST, signing it when an identity is present, for BOTH
|
||||
/// services. The node read-gates the git-upload-pack POST with visibility_check
|
||||
/// at "/", and separately owner-gates the git-receive-pack POST (signature
|
||||
/// required, enforced by middleware). The Phase-1 advertisement signature does
|
||||
/// not carry to this separate request, so a private repo's owner must
|
||||
/// authenticate here too or their fetch/push is denied.
|
||||
/// Public-repo fetch still works anonymously when no keypair is present. The body
|
||||
/// is signed (content-digest) but NOT attached here, so the caller can move the
|
||||
/// (possibly large) pack bytes into `.body()` rather than clone them.
|
||||
fn build_pack_post_request(
|
||||
client: &reqwest::blocking::Client,
|
||||
post_url: &str,
|
||||
service: &str,
|
||||
body: &[u8],
|
||||
keypair: Option<&Keypair>,
|
||||
) -> reqwest::blocking::RequestBuilder {
|
||||
let mut req = client
|
||||
.post(post_url)
|
||||
.header("Content-Type", format!("application/x-{}-request", service))
|
||||
.header("User-Agent", USER_AGENT);
|
||||
if let Some(kp) = keypair {
|
||||
let signed = sign_request(kp, "POST", &url_path(post_url), body);
|
||||
req = req
|
||||
.header("Content-Digest", signed.content_digest)
|
||||
.header("Signature-Input", signed.signature_input)
|
||||
.header("Signature", signed.signature);
|
||||
tracing::debug!("signed {service} POST (DID: {})", kp.did());
|
||||
} else if service == "git-receive-pack" {
|
||||
tracing::warn!("no identity keypair found, push will be unsigned (v0.1 local alpha only)");
|
||||
}
|
||||
req
|
||||
}
|
||||
|
||||
// ── URL helpers ───────────────────────────────────────────────────────────────
|
||||
|
||||
/// Parse a `gitlawb://did:key:z6Mk.../repo-name` URL.
|
||||
@@ -347,7 +432,7 @@ fn parse_gitlawb_url(url: &str) -> Result<(String, String, String)> {
|
||||
///
|
||||
/// We also handle the flush-only case (`"0000"`) that git sends when it already
|
||||
/// has everything it needs (up-to-date clone).
|
||||
fn read_upload_pack_request(stdin: &mut io::BufReader<io::Stdin>) -> Result<Vec<u8>> {
|
||||
fn read_upload_pack_request<R: Read>(stdin: &mut R) -> Result<Vec<u8>> {
|
||||
let mut buf = Vec::new();
|
||||
|
||||
loop {
|
||||
@@ -433,6 +518,85 @@ fn url_path(url: &str) -> String {
|
||||
.unwrap_or_else(|| "/".to_string())
|
||||
}
|
||||
|
||||
const MAX_ERROR_BODY_BYTES: u64 = 4096;
|
||||
const MAX_ERROR_BODY_CHARS: usize = 2000;
|
||||
|
||||
fn read_error_body(mut response: reqwest::blocking::Response) -> String {
|
||||
let mut body = Vec::new();
|
||||
let mut limited = (&mut response).take(MAX_ERROR_BODY_BYTES);
|
||||
|
||||
if limited.read_to_end(&mut body).is_err() {
|
||||
return String::new();
|
||||
}
|
||||
|
||||
String::from_utf8_lossy(&body).into_owned()
|
||||
}
|
||||
|
||||
fn http_error_message(
|
||||
method: &str,
|
||||
path: &str,
|
||||
status: reqwest::StatusCode,
|
||||
body: &str,
|
||||
empty_body_hint: Option<&str>,
|
||||
) -> String {
|
||||
let mut message = format!("{method} {path} returned {status}");
|
||||
let body = safe_error_body_excerpt(body);
|
||||
|
||||
if !body.is_empty() {
|
||||
message.push_str(": ");
|
||||
message.push_str(&body);
|
||||
} else if let Some(hint) = empty_body_hint {
|
||||
message.push(' ');
|
||||
message.push_str(hint);
|
||||
}
|
||||
|
||||
message
|
||||
}
|
||||
|
||||
fn safe_error_body_excerpt(body: &str) -> String {
|
||||
let mut excerpt = String::new();
|
||||
let mut pending_space = false;
|
||||
let mut kept_chars = 0;
|
||||
|
||||
for ch in body.trim().chars() {
|
||||
if kept_chars >= MAX_ERROR_BODY_CHARS {
|
||||
break;
|
||||
}
|
||||
|
||||
if ch.is_control() {
|
||||
if matches!(ch, '\n' | '\r' | '\t') {
|
||||
pending_space = true;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
|
||||
if gitlawb_core::sanitize::is_bidi_format(ch) {
|
||||
// Drop Cf bidi/format controls (INV-6, #183) without marking
|
||||
// pending_space: unlike a newline/tab they are not whitespace, so
|
||||
// "a\u{202e}c" collapses to "ac" with no phantom gap.
|
||||
continue;
|
||||
}
|
||||
|
||||
if ch.is_whitespace() {
|
||||
pending_space = true;
|
||||
continue;
|
||||
}
|
||||
|
||||
if pending_space && !excerpt.is_empty() {
|
||||
excerpt.push(' ');
|
||||
kept_chars += 1;
|
||||
if kept_chars >= MAX_ERROR_BODY_CHARS {
|
||||
break;
|
||||
}
|
||||
}
|
||||
excerpt.push(ch);
|
||||
kept_chars += 1;
|
||||
pending_space = false;
|
||||
}
|
||||
|
||||
excerpt
|
||||
}
|
||||
|
||||
// ── Keypair loading ───────────────────────────────────────────────────────────
|
||||
|
||||
fn load_keypair() -> Option<Keypair> {
|
||||
@@ -476,6 +640,467 @@ fn resolve_key_path() -> std::path::PathBuf {
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use std::net::{TcpListener, TcpStream};
|
||||
use std::thread::JoinHandle;
|
||||
|
||||
struct TestResponse {
|
||||
request_line: &'static str,
|
||||
status: &'static str,
|
||||
body: &'static str,
|
||||
}
|
||||
|
||||
fn serve_http(responses: Vec<TestResponse>) -> (String, JoinHandle<Vec<String>>) {
|
||||
let listener = TcpListener::bind("127.0.0.1:0").unwrap();
|
||||
let base_url = format!("http://{}", listener.local_addr().unwrap());
|
||||
let handle = std::thread::spawn(move || {
|
||||
let mut requests = Vec::new();
|
||||
|
||||
for response in responses {
|
||||
let (mut stream, _) = listener.accept().unwrap();
|
||||
let request = read_http_request(&mut stream);
|
||||
assert!(
|
||||
request.starts_with(response.request_line),
|
||||
"unexpected request:\n{request}"
|
||||
);
|
||||
|
||||
let response_text = format!(
|
||||
"HTTP/1.1 {}\r\ncontent-type: application/json\r\ncontent-length: {}\r\nconnection: close\r\n\r\n{}",
|
||||
response.status,
|
||||
response.body.len(),
|
||||
response.body
|
||||
);
|
||||
stream.write_all(response_text.as_bytes()).unwrap();
|
||||
requests.push(request);
|
||||
}
|
||||
|
||||
requests
|
||||
});
|
||||
|
||||
(base_url, handle)
|
||||
}
|
||||
|
||||
fn read_http_request(stream: &mut TcpStream) -> String {
|
||||
let mut buf = Vec::new();
|
||||
let mut chunk = [0u8; 512];
|
||||
let mut header_len = None;
|
||||
|
||||
loop {
|
||||
let n = stream.read(&mut chunk).unwrap();
|
||||
if n == 0 {
|
||||
break;
|
||||
}
|
||||
buf.extend_from_slice(&chunk[..n]);
|
||||
|
||||
if header_len.is_none() {
|
||||
header_len = buf.windows(4).position(|w| w == b"\r\n\r\n").map(|p| p + 4);
|
||||
}
|
||||
|
||||
if let Some(header_len) = header_len {
|
||||
let header = String::from_utf8_lossy(&buf[..header_len]);
|
||||
let content_len = header
|
||||
.lines()
|
||||
.find_map(|line| {
|
||||
let (name, value) = line.split_once(':')?;
|
||||
name.eq_ignore_ascii_case("content-length")
|
||||
.then(|| value.trim().parse::<usize>().ok())
|
||||
.flatten()
|
||||
})
|
||||
.unwrap_or(0);
|
||||
|
||||
if buf.len() >= header_len + content_len {
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
String::from_utf8_lossy(&buf).into_owned()
|
||||
}
|
||||
|
||||
/// The regression that round-1 missed: the Phase-2 `git-upload-pack` POST was
|
||||
/// left unsigned, so an owner's fetch of a private repo cleared the (now signed)
|
||||
/// advertisement and then 404'd on the pack POST. Drive BOTH request builders
|
||||
/// against a mock node and assert the RFC-9421 headers actually go out on the
|
||||
/// wire for BOTH services when a keypair is present (the mock only matches when
|
||||
/// the headers exist, so `.assert()` fails if any are dropped).
|
||||
#[test]
|
||||
fn advertisement_and_pack_post_are_signed_for_both_services_with_keypair() {
|
||||
let kp = Keypair::generate();
|
||||
let client = reqwest::blocking::Client::new();
|
||||
let body = b"0009done\n".to_vec();
|
||||
|
||||
for service in ["git-upload-pack", "git-receive-pack"] {
|
||||
let mut server = mockito::Server::new();
|
||||
let repo_base = format!("{}/zOwner/myrepo", server.url());
|
||||
|
||||
let get_mock = server
|
||||
.mock("GET", mockito::Matcher::Regex(r"/info/refs".to_string()))
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.match_header("content-digest", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.create();
|
||||
let refs_url = format!("{repo_base}/info/refs?service={service}");
|
||||
let resp = build_advertisement_request(&client, &refs_url, Some(&kp))
|
||||
.send()
|
||||
.unwrap();
|
||||
assert!(resp.status().is_success());
|
||||
get_mock.assert();
|
||||
|
||||
let post_mock = server
|
||||
.mock("POST", mockito::Matcher::Regex(format!("/{service}$")))
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.match_header("content-digest", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.create();
|
||||
let post_url = format!("{repo_base}/{service}");
|
||||
let resp = build_pack_post_request(&client, &post_url, service, &body, Some(&kp))
|
||||
.body(body.clone())
|
||||
.send()
|
||||
.unwrap();
|
||||
assert!(resp.status().is_success());
|
||||
post_mock.assert();
|
||||
}
|
||||
}
|
||||
|
||||
/// Without an identity, the pack POST must go out UNSIGNED so public fetch (and
|
||||
/// alpha unsigned push) still work. `Matcher::Missing` matches only when the
|
||||
/// header is absent, so the mock is hit only if NO signature was attached, for
|
||||
/// BOTH services (the receive-pack iteration also exercises the no-keypair warn
|
||||
/// branch and confirms it does not block the request).
|
||||
#[test]
|
||||
fn pack_post_is_unsigned_without_keypair_for_both_services() {
|
||||
let client = reqwest::blocking::Client::new();
|
||||
let body = b"0009done\n".to_vec();
|
||||
|
||||
for service in ["git-upload-pack", "git-receive-pack"] {
|
||||
let mut server = mockito::Server::new();
|
||||
let post_url = format!("{}/zOwner/myrepo/{service}", server.url());
|
||||
|
||||
let post_mock = server
|
||||
.mock("POST", mockito::Matcher::Regex(format!("/{service}$")))
|
||||
.match_header("signature", mockito::Matcher::Missing)
|
||||
.match_header("signature-input", mockito::Matcher::Missing)
|
||||
.match_header("content-digest", mockito::Matcher::Missing)
|
||||
.with_status(200)
|
||||
.create();
|
||||
let resp = build_pack_post_request(&client, &post_url, service, &body, None)
|
||||
.body(body.clone())
|
||||
.send()
|
||||
.unwrap();
|
||||
assert!(resp.status().is_success());
|
||||
post_mock.assert();
|
||||
}
|
||||
}
|
||||
|
||||
/// Symmetric negative case for Phase 1: with no identity the advertisement GET
|
||||
/// carries no signature, so public clones stay anonymous.
|
||||
#[test]
|
||||
fn advertisement_get_is_unsigned_without_keypair() {
|
||||
let client = reqwest::blocking::Client::new();
|
||||
let mut server = mockito::Server::new();
|
||||
let refs_url = format!(
|
||||
"{}/zOwner/myrepo/info/refs?service=git-upload-pack",
|
||||
server.url()
|
||||
);
|
||||
|
||||
let get_mock = server
|
||||
.mock("GET", mockito::Matcher::Regex(r"/info/refs".to_string()))
|
||||
.match_header("signature", mockito::Matcher::Missing)
|
||||
.match_header("signature-input", mockito::Matcher::Missing)
|
||||
.match_header("content-digest", mockito::Matcher::Missing)
|
||||
.with_status(200)
|
||||
.create();
|
||||
let resp = build_advertisement_request(&client, &refs_url, None)
|
||||
.send()
|
||||
.unwrap();
|
||||
assert!(resp.status().is_success());
|
||||
get_mock.assert();
|
||||
}
|
||||
|
||||
// ── Phase-1 retry-on-404 (P2, #119): fetch stays anonymous until the node
|
||||
// denies it, then escalates to ONE signed retry. Drives handle_connect end to
|
||||
// end against the recording mock, asserting what actually goes on the wire.
|
||||
// A request is "signed" iff it carries the `signature-input` header.
|
||||
|
||||
/// Public fetch: the node serves the anonymous advertisement (200), so the
|
||||
/// client never signs — not the advertisement GET, not the upload-pack POST —
|
||||
/// even though an identity is present. This is the privacy fix: a public clone
|
||||
/// must not disclose the caller's DID.
|
||||
#[test]
|
||||
fn fetch_public_stays_anonymous_even_with_keypair() {
|
||||
let kp = Keypair::generate();
|
||||
let (base_url, server) = serve_http(vec![
|
||||
TestResponse {
|
||||
request_line: "GET /zOwner/myrepo/info/refs?service=git-upload-pack",
|
||||
status: "200 OK",
|
||||
body: "0000",
|
||||
},
|
||||
TestResponse {
|
||||
request_line: "POST /zOwner/myrepo/git-upload-pack",
|
||||
status: "200 OK",
|
||||
body: "",
|
||||
},
|
||||
]);
|
||||
let repo_base = format!("{base_url}/zOwner/myrepo");
|
||||
let mut stdin = std::io::Cursor::new(b"0009done\n".to_vec());
|
||||
handle_connect(&repo_base, "git-upload-pack", Some(&kp), &mut stdin)
|
||||
.expect("public fetch should succeed");
|
||||
let requests = server.join().unwrap();
|
||||
assert_eq!(requests.len(), 2, "public fetch must not retry");
|
||||
assert!(
|
||||
!requests[0].to_lowercase().contains("signature-input"),
|
||||
"the advertisement GET must be anonymous for a public fetch"
|
||||
);
|
||||
assert!(
|
||||
!requests[1].to_lowercase().contains("signature-input"),
|
||||
"the upload-pack POST must be anonymous for a public fetch"
|
||||
);
|
||||
}
|
||||
|
||||
/// Private fetch: the anonymous advertisement is denied (404); with an identity
|
||||
/// present the client retries the GET signed and — because Phase 1 needed
|
||||
/// signing — also signs the Phase-2 upload-pack POST. The FIRST request is still
|
||||
/// anonymous: the DID is not disclosed until the node demands authentication.
|
||||
#[test]
|
||||
fn fetch_private_retries_signed_on_404_and_signs_the_pack_post() {
|
||||
let kp = Keypair::generate();
|
||||
let (base_url, server) = serve_http(vec![
|
||||
TestResponse {
|
||||
request_line: "GET /zOwner/myrepo/info/refs?service=git-upload-pack",
|
||||
status: "404 Not Found",
|
||||
body: r#"{"message":"repository is not registered on this node"}"#,
|
||||
},
|
||||
TestResponse {
|
||||
request_line: "GET /zOwner/myrepo/info/refs?service=git-upload-pack",
|
||||
status: "200 OK",
|
||||
body: "0000",
|
||||
},
|
||||
TestResponse {
|
||||
request_line: "POST /zOwner/myrepo/git-upload-pack",
|
||||
status: "200 OK",
|
||||
body: "",
|
||||
},
|
||||
]);
|
||||
let repo_base = format!("{base_url}/zOwner/myrepo");
|
||||
let mut stdin = std::io::Cursor::new(b"0009done\n".to_vec());
|
||||
handle_connect(&repo_base, "git-upload-pack", Some(&kp), &mut stdin)
|
||||
.expect("signed retry should succeed");
|
||||
let requests = server.join().unwrap();
|
||||
assert_eq!(
|
||||
requests.len(),
|
||||
3,
|
||||
"expected anon GET, signed GET retry, signed POST"
|
||||
);
|
||||
assert!(
|
||||
!requests[0].to_lowercase().contains("signature-input"),
|
||||
"the first advertisement GET must be anonymous"
|
||||
);
|
||||
assert!(
|
||||
requests[1].to_lowercase().contains("signature-input"),
|
||||
"the retry advertisement GET must be signed"
|
||||
);
|
||||
assert!(
|
||||
requests[2].to_lowercase().contains("signature-input"),
|
||||
"the upload-pack POST must be signed once the fetch needed auth"
|
||||
);
|
||||
}
|
||||
|
||||
/// Private fetch with no identity: the anonymous advertisement 404s and there is
|
||||
/// no keypair to retry with, so the client surfaces the error after exactly one
|
||||
/// request — no retry, no hang.
|
||||
#[test]
|
||||
fn fetch_without_keypair_does_not_retry_on_404() {
|
||||
let (base_url, server) = serve_http(vec![TestResponse {
|
||||
request_line: "GET /zOwner/myrepo/info/refs?service=git-upload-pack",
|
||||
status: "404 Not Found",
|
||||
body: r#"{"message":"not found"}"#,
|
||||
}]);
|
||||
let repo_base = format!("{base_url}/zOwner/myrepo");
|
||||
let mut stdin = std::io::Cursor::new(Vec::<u8>::new());
|
||||
let err = handle_connect(&repo_base, "git-upload-pack", None, &mut stdin).unwrap_err();
|
||||
assert!(err.to_string().contains("returned 404 Not Found"));
|
||||
let requests = server.join().unwrap();
|
||||
assert_eq!(requests.len(), 1, "no keypair means no signed retry");
|
||||
assert!(!requests[0].to_lowercase().contains("signature-input"));
|
||||
}
|
||||
|
||||
/// Private fetch where the SIGNED retry is also denied (caller is not a reader):
|
||||
/// the client retries exactly once, then surfaces the 404 rather than looping.
|
||||
/// Bounds the escalation to a single signed attempt.
|
||||
#[test]
|
||||
fn fetch_signed_retry_still_denied_surfaces_error_once() {
|
||||
let kp = Keypair::generate();
|
||||
let (base_url, server) = serve_http(vec![
|
||||
TestResponse {
|
||||
request_line: "GET /zOwner/myrepo/info/refs?service=git-upload-pack",
|
||||
status: "404 Not Found",
|
||||
body: r#"{"message":"not found"}"#,
|
||||
},
|
||||
TestResponse {
|
||||
request_line: "GET /zOwner/myrepo/info/refs?service=git-upload-pack",
|
||||
status: "404 Not Found",
|
||||
body: r#"{"message":"not found"}"#,
|
||||
},
|
||||
]);
|
||||
let repo_base = format!("{base_url}/zOwner/myrepo");
|
||||
let mut stdin = std::io::Cursor::new(Vec::<u8>::new());
|
||||
let err = handle_connect(&repo_base, "git-upload-pack", Some(&kp), &mut stdin).unwrap_err();
|
||||
assert!(err.to_string().contains("returned 404 Not Found"));
|
||||
let requests = server.join().unwrap();
|
||||
assert_eq!(requests.len(), 2, "exactly one signed retry, then surface");
|
||||
assert!(!requests[0].to_lowercase().contains("signature-input"));
|
||||
assert!(requests[1].to_lowercase().contains("signature-input"));
|
||||
}
|
||||
|
||||
/// Push (git-receive-pack) is unchanged: it signs from the FIRST request — you
|
||||
/// cannot push anonymously — so there is no anonymous-first probe for push.
|
||||
#[test]
|
||||
fn push_advertisement_is_signed_from_the_first_request() {
|
||||
let kp = Keypair::generate();
|
||||
let (base_url, server) = serve_http(vec![
|
||||
TestResponse {
|
||||
request_line: "GET /zOwner/myrepo/info/refs?service=git-receive-pack",
|
||||
status: "200 OK",
|
||||
body: "0000",
|
||||
},
|
||||
TestResponse {
|
||||
request_line: "POST /zOwner/myrepo/git-receive-pack",
|
||||
status: "200 OK",
|
||||
body: "",
|
||||
},
|
||||
]);
|
||||
let repo_base = format!("{base_url}/zOwner/myrepo");
|
||||
let mut stdin = std::io::Cursor::new(b"0000".to_vec());
|
||||
handle_connect(&repo_base, "git-receive-pack", Some(&kp), &mut stdin)
|
||||
.expect("push should succeed");
|
||||
let requests = server.join().unwrap();
|
||||
assert_eq!(requests.len(), 2);
|
||||
assert!(
|
||||
requests[0].to_lowercase().contains("signature-input"),
|
||||
"push advertisement must be signed from the first request"
|
||||
);
|
||||
assert!(
|
||||
requests[1].to_lowercase().contains("signature-input"),
|
||||
"push POST must be signed"
|
||||
);
|
||||
}
|
||||
|
||||
/// Cross-crate seam: the signature the CLIENT actually emits (via the real
|
||||
/// request builders) verifies under the SAME `gitlawb_core::http_sig`
|
||||
/// primitives the node's `require_signature` uses, over the `@path` the client
|
||||
/// genuinely transmits (derived from the built reqwest request, exactly as the
|
||||
/// node derives it from `uri.path_and_query()`). A tampered `@path` must fail:
|
||||
/// this is the byte-match the whole A1 client fix depends on, now executed end
|
||||
/// to end (sign here, verify with the node's verifier), not reasoned.
|
||||
#[test]
|
||||
fn client_signature_verifies_under_node_verification_for_both_services() {
|
||||
use gitlawb_core::http_sig::{build_signing_string, compute_content_digest, HttpSignature};
|
||||
use gitlawb_core::identity::verify;
|
||||
use std::collections::HashMap;
|
||||
|
||||
let kp = Keypair::generate();
|
||||
let client = reqwest::blocking::Client::new();
|
||||
let body = b"0009done\n".to_vec();
|
||||
|
||||
// Re-implements the node's require_signature verification (auth/mod.rs):
|
||||
// parse headers, recompute content-digest from the body, rebuild the signing
|
||||
// string over @method/@path/content-digest, Ed25519-verify. Ok iff the node
|
||||
// would accept it.
|
||||
let node_verifies = |method: &str,
|
||||
path_and_query: &str,
|
||||
body: &[u8],
|
||||
sig_input: &str,
|
||||
sig_header: &str,
|
||||
content_digest: &str|
|
||||
-> anyhow::Result<()> {
|
||||
let sig = HttpSignature::parse(sig_input, sig_header)?;
|
||||
sig.check_created()?;
|
||||
assert!(
|
||||
sig.missing_components().is_empty(),
|
||||
"signature must cover all required components"
|
||||
);
|
||||
assert_eq!(sig.alg, "ed25519");
|
||||
assert_eq!(
|
||||
content_digest,
|
||||
compute_content_digest(body),
|
||||
"content-digest must match the body"
|
||||
);
|
||||
let vk = sig.key_id.to_verifying_key()?;
|
||||
let mut values = HashMap::new();
|
||||
values.insert("@method".to_string(), method.to_uppercase());
|
||||
values.insert("@path".to_string(), path_and_query.to_string());
|
||||
values.insert("content-digest".to_string(), content_digest.to_string());
|
||||
let sig_params_value = sig_input.strip_prefix("sig1=").unwrap_or(sig_input);
|
||||
let components: Vec<&str> = sig.components.iter().map(String::as_str).collect();
|
||||
let signing_string = build_signing_string(&components, sig_params_value, &values)?;
|
||||
let sig_array: [u8; 64] = sig.signature_bytes.as_slice().try_into()?;
|
||||
verify(&vk, signing_string.as_bytes(), &sig_array)?;
|
||||
Ok(())
|
||||
};
|
||||
// @path exactly as the node reconstructs it from the request it receives.
|
||||
let path_and_query = |req: &reqwest::blocking::Request| match req.url().query() {
|
||||
Some(q) => format!("{}?{}", req.url().path(), q),
|
||||
None => req.url().path().to_string(),
|
||||
};
|
||||
let header = |req: &reqwest::blocking::Request, name: &str| {
|
||||
req.headers()
|
||||
.get(name)
|
||||
.unwrap_or_else(|| panic!("missing {name}"))
|
||||
.to_str()
|
||||
.unwrap()
|
||||
.to_string()
|
||||
};
|
||||
|
||||
for service in ["git-upload-pack", "git-receive-pack"] {
|
||||
// Phase-1 advertisement GET (empty body).
|
||||
let refs_url = format!("http://node.example/zOwner/myrepo/info/refs?service={service}");
|
||||
let req = build_advertisement_request(&client, &refs_url, Some(&kp))
|
||||
.build()
|
||||
.unwrap();
|
||||
node_verifies(
|
||||
"GET",
|
||||
&path_and_query(&req),
|
||||
b"",
|
||||
&header(&req, "signature-input"),
|
||||
&header(&req, "signature"),
|
||||
&header(&req, "content-digest"),
|
||||
)
|
||||
.expect("client GET signature must verify under the node's verifier");
|
||||
|
||||
// Phase-2 pack POST (real body).
|
||||
let post_url = format!("http://node.example/zOwner/myrepo/{service}");
|
||||
let req = build_pack_post_request(&client, &post_url, service, &body, Some(&kp))
|
||||
.body(body.clone())
|
||||
.build()
|
||||
.unwrap();
|
||||
let pq = path_and_query(&req);
|
||||
node_verifies(
|
||||
"POST",
|
||||
&pq,
|
||||
&body,
|
||||
&header(&req, "signature-input"),
|
||||
&header(&req, "signature"),
|
||||
&header(&req, "content-digest"),
|
||||
)
|
||||
.expect("client POST signature must verify under the node's verifier");
|
||||
|
||||
// Negative: a tampered @path (the A1 attack surface) must NOT verify.
|
||||
let tampered = pq.replace(service, "git-evil");
|
||||
assert!(
|
||||
node_verifies(
|
||||
"POST",
|
||||
&tampered,
|
||||
&body,
|
||||
&header(&req, "signature-input"),
|
||||
&header(&req, "signature"),
|
||||
&header(&req, "content-digest"),
|
||||
)
|
||||
.is_err(),
|
||||
"a tampered @path must fail verification"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn parse_standard_url() {
|
||||
@@ -524,6 +1149,176 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn http_error_message_sanitizes_response_body_controls() {
|
||||
let message = http_error_message(
|
||||
"GET",
|
||||
"/info/refs",
|
||||
reqwest::StatusCode::BAD_GATEWAY,
|
||||
"\u{1b}[2Jrepository\r\nis\tblocked\u{7}",
|
||||
None,
|
||||
);
|
||||
|
||||
assert!(message.contains("repository is blocked"));
|
||||
assert!(!message.contains('\u{1b}'));
|
||||
assert!(!message.contains('\u{7}'));
|
||||
assert!(!message.contains('\r'));
|
||||
assert!(!message.contains('\n'));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn http_error_message_strips_bidi_format_controls() {
|
||||
// Each Cf bidi class must be stripped (INV-6, #183), not just U+202E:
|
||||
// override (RLO), embedding + pop (LRE/PDF), isolate (LRI/PDI), and marks
|
||||
// (LRM/ALM). Asserted per code point so a partial predicate fails loudly.
|
||||
// The visible words must survive and JOIN with no phantom space at the
|
||||
// strip points: a bidi char is dropped like a control byte, but unlike a
|
||||
// newline/tab it is not whitespace, so it must not set pending_space. The
|
||||
// leading bidi char (index 0) also exercises the empty-excerpt path.
|
||||
let body = "\u{202e}err\u{202a}\u{202c}\u{2066}\u{2069}\u{200e}\u{061c}ok";
|
||||
let message = http_error_message(
|
||||
"GET",
|
||||
"/info/refs",
|
||||
reqwest::StatusCode::BAD_GATEWAY,
|
||||
body,
|
||||
None,
|
||||
);
|
||||
for c in [
|
||||
'\u{202e}', '\u{202a}', '\u{202c}', '\u{2066}', '\u{2069}', '\u{200e}', '\u{061c}',
|
||||
] {
|
||||
assert!(
|
||||
!message.contains(c),
|
||||
"bidi U+{:04X} leaked: {message:?}",
|
||||
c as u32
|
||||
);
|
||||
}
|
||||
assert!(
|
||||
message.contains("errok"),
|
||||
"words should join with no phantom space: {message:?}"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn http_error_message_preserves_legitimate_and_rtl_text() {
|
||||
// Must not over-strip: plain text, a genuine RTL SCRIPT letter (Arabic
|
||||
// U+0627, category Lo), and ZWJ (U+200D, a legitimate Cf char) survive.
|
||||
let message = http_error_message(
|
||||
"GET",
|
||||
"/info/refs",
|
||||
reqwest::StatusCode::BAD_GATEWAY,
|
||||
"ok \u{0627}\u{200D}b",
|
||||
None,
|
||||
);
|
||||
assert!(
|
||||
message.ends_with("ok \u{0627}\u{200D}b"),
|
||||
"legitimate text was altered: {message:?}"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn http_error_message_truncates_long_response_body() {
|
||||
let body = "x".repeat(MAX_ERROR_BODY_CHARS + 100);
|
||||
let message = http_error_message(
|
||||
"POST",
|
||||
"/git-receive-pack",
|
||||
reqwest::StatusCode::FORBIDDEN,
|
||||
&body,
|
||||
None,
|
||||
);
|
||||
let prefix = "POST /git-receive-pack returned 403 Forbidden: ";
|
||||
|
||||
assert_eq!(message.len(), prefix.len() + MAX_ERROR_BODY_CHARS);
|
||||
assert!(message.starts_with(prefix));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn connect_get_error_includes_response_body() {
|
||||
let (base_url, server) = serve_http(vec![TestResponse {
|
||||
request_line: "GET /z6Mk/myrepo/info/refs?service=git-upload-pack HTTP/1.1",
|
||||
status: "404 Not Found",
|
||||
body: r#"{"message":"repository is not registered on this node"}"#,
|
||||
}]);
|
||||
|
||||
let repo_base = format!("{base_url}/z6Mk/myrepo");
|
||||
let mut stdin = std::io::Cursor::new(Vec::<u8>::new());
|
||||
let err = handle_connect(&repo_base, "git-upload-pack", None, &mut stdin).unwrap_err();
|
||||
let message = err.to_string();
|
||||
|
||||
assert!(message.contains("GET /info/refs returned 404 Not Found"));
|
||||
assert!(message.contains("repository is not registered on this node"));
|
||||
let requests = server.join().unwrap();
|
||||
assert_eq!(requests.len(), 1);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn connect_error_strips_bidi_from_response_body() {
|
||||
// Transport-path proof: a bidi override in the node's real HTTP error body
|
||||
// must not reach the surfaced error text. Drives the full handle_connect
|
||||
// error path, not just the safe_error_body_excerpt unit boundary (INV-6).
|
||||
let (base_url, server) = serve_http(vec![TestResponse {
|
||||
request_line: "GET /z6Mk/myrepo/info/refs?service=git-upload-pack HTTP/1.1",
|
||||
status: "404 Not Found",
|
||||
body: "not\u{202e}found",
|
||||
}]);
|
||||
|
||||
let repo_base = format!("{base_url}/z6Mk/myrepo");
|
||||
let mut stdin = std::io::Cursor::new(Vec::<u8>::new());
|
||||
let err = handle_connect(&repo_base, "git-upload-pack", None, &mut stdin).unwrap_err();
|
||||
let message = err.to_string();
|
||||
|
||||
assert!(
|
||||
!message.contains('\u{202e}'),
|
||||
"bidi override reached the terminal: {message:?}"
|
||||
);
|
||||
assert!(
|
||||
message.contains("notfound"),
|
||||
"body should survive with the bidi char stripped: {message:?}"
|
||||
);
|
||||
let _ = server.join();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn connect_post_error_includes_response_body() {
|
||||
let (base_url, server) = serve_http(vec![
|
||||
TestResponse {
|
||||
request_line: "GET /z6Mk/myrepo/info/refs?service=git-receive-pack HTTP/1.1",
|
||||
status: "200 OK",
|
||||
body: "",
|
||||
},
|
||||
TestResponse {
|
||||
request_line: "POST /z6Mk/myrepo/git-receive-pack HTTP/1.1",
|
||||
status: "403 Forbidden",
|
||||
body: r#"{"error":"forbidden","message":"push rejected: only the repo owner may push"}"#,
|
||||
},
|
||||
]);
|
||||
|
||||
let repo_base = format!("{base_url}/z6Mk/myrepo");
|
||||
let mut stdin = std::io::Cursor::new(b"0000".to_vec());
|
||||
let err = handle_connect(&repo_base, "git-receive-pack", None, &mut stdin).unwrap_err();
|
||||
let message = err.to_string();
|
||||
|
||||
assert!(message.contains("POST /git-receive-pack returned 403 Forbidden"));
|
||||
assert!(message.contains("push rejected: only the repo owner may push"));
|
||||
let requests = server.join().unwrap();
|
||||
assert_eq!(requests.len(), 2);
|
||||
assert!(requests[1].contains("\r\n\r\n0000"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn url_path_preserves_query_for_signed_advertisement() {
|
||||
// The Phase-1 advertisement GET is signed over url_path(refs_url), and the
|
||||
// node verifies the signature over its path_and_query, so the ?service=
|
||||
// query MUST survive verbatim or the signatures will not byte-match.
|
||||
assert_eq!(
|
||||
url_path("http://127.0.0.1:7545/z6Mk/myrepo/info/refs?service=git-upload-pack"),
|
||||
"/z6Mk/myrepo/info/refs?service=git-upload-pack"
|
||||
);
|
||||
assert_eq!(
|
||||
url_path("http://127.0.0.1:7545/z6Mk/myrepo/info/refs?service=git-receive-pack"),
|
||||
"/z6Mk/myrepo/info/refs?service=git-receive-pack"
|
||||
);
|
||||
}
|
||||
|
||||
fn args(items: &[&str]) -> Vec<String> {
|
||||
items.iter().map(|s| s.to_string()).collect()
|
||||
}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
[package]
|
||||
name = "gitlawb-attest"
|
||||
description = "External Attestation v1: pluggable provenance attachments for gitlawb ref-update certs"
|
||||
version = "0.4.0" # x-release-please-version
|
||||
version = "0.7.1" # x-release-please-version
|
||||
edition.workspace = true
|
||||
rust-version.workspace = true
|
||||
license.workspace = true
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
[package]
|
||||
name = "gitlawb-core"
|
||||
description = "Core cryptographic primitives for the gitlawb network: DIDs, CIDs, UCAN, HTTP Signatures, ref-update certificates"
|
||||
version = "0.4.0" # x-release-please-version
|
||||
version = "0.7.1" # x-release-please-version
|
||||
edition.workspace = true
|
||||
rust-version.workspace = true
|
||||
license.workspace = true
|
||||
|
||||
@@ -5,6 +5,7 @@ pub mod encrypt;
|
||||
pub mod error;
|
||||
pub mod http_sig;
|
||||
pub mod identity;
|
||||
pub mod sanitize;
|
||||
pub mod ucan;
|
||||
|
||||
pub use error::Error;
|
||||
|
||||
@@ -0,0 +1,69 @@
|
||||
//! Text sanitization predicates shared across the workspace.
|
||||
//!
|
||||
//! Untrusted peer/remote bytes that reach an operator's terminal (node error
|
||||
//! bodies, node-advertised strings) must be stripped of BOTH `Cc` control bytes
|
||||
//! (`char::is_control()`) AND `Cf` bidi/format controls before display: a
|
||||
//! right-to-left override or directional isolate can visually reorder the line
|
||||
//! and spoof the text (Trojan Source, CWE-451). This is INV-6.
|
||||
//!
|
||||
//! `is_bidi_format` is the single workspace definition of the second half of
|
||||
//! that obligation. It was split out of `gl`'s local copy so the two terminal
|
||||
//! sanitizers that shipped with only the `Cc` half (#183) — and any future
|
||||
//! sanitizer — reuse one audited predicate instead of re-deriving the set.
|
||||
|
||||
/// True for the Unicode bidirectional/directional-isolate format characters
|
||||
/// (the reordering subset of category `Cf`) that can visually reorder a terminal
|
||||
/// line. These are NOT matched by [`char::is_control()`], which covers `Cc` only.
|
||||
///
|
||||
/// This is deliberately the reordering subset, not the whole `Cf` category:
|
||||
/// legitimate `Cf` characters such as ZWJ (`U+200D`, emoji sequences) and the
|
||||
/// soft hyphen (`U+00AD`) are NOT matched, so honest international text passes
|
||||
/// through unchanged. Widening this set is a behavior change for every consumer.
|
||||
///
|
||||
/// Pair it with `!c.is_control()` in a terminal-bound sanitizer (INV-6); see the
|
||||
/// wrappers in `gl`, `git-remote-gitlawb`, and `icaptcha-client`.
|
||||
pub fn is_bidi_format(c: char) -> bool {
|
||||
matches!(c,
|
||||
'\u{200E}' | '\u{200F}' | '\u{061C}' // LRM, RLM, ALM
|
||||
| '\u{202A}'..='\u{202E}' // LRE, RLE, PDF, LRO, RLO
|
||||
| '\u{2066}'..='\u{2069}' // LRI, RLI, FSI, PDI
|
||||
)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn strips_every_reordering_code_point() {
|
||||
// Asserted individually so a partial predicate (e.g. one that covers the
|
||||
// marks but not the isolates) fails loudly rather than passing.
|
||||
for c in [
|
||||
'\u{200E}', '\u{200F}', '\u{061C}', // LRM, RLM, ALM
|
||||
'\u{202A}', '\u{202B}', '\u{202C}', '\u{202D}',
|
||||
'\u{202E}', // LRE, RLE, PDF, LRO, RLO
|
||||
'\u{2066}', '\u{2067}', '\u{2068}', '\u{2069}', // LRI, RLI, FSI, PDI
|
||||
] {
|
||||
assert!(
|
||||
is_bidi_format(c),
|
||||
"U+{:04X} must be a bidi-format char",
|
||||
c as u32
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn passes_legitimate_and_control_chars() {
|
||||
// Must NOT over-strip: plain text, a genuine RTL SCRIPT letter (Lo, not a
|
||||
// format char), ZWJ (legitimate Cf), and soft hyphen (legitimate Cf) are
|
||||
// not bidi-format. ESC is a Cc control char — owned by is_control(), not
|
||||
// this predicate, which is bidi-only.
|
||||
for c in ['a', '\u{0627}', '\u{200D}', '\u{00AD}', '\u{1b}'] {
|
||||
assert!(
|
||||
!is_bidi_format(c),
|
||||
"U+{:04X} must NOT be a bidi-format char",
|
||||
c as u32
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -187,11 +187,17 @@ impl Ucan {
|
||||
}
|
||||
|
||||
/// Check if this UCAN grants a specific capability on a resource.
|
||||
///
|
||||
/// Mirrors `Capability::is_attenuated_by`'s wildcard semantics: a stored
|
||||
/// capability of `with: "*"` or `can: "*"` / `"repo/admin"` covers any
|
||||
/// requested resource/action, since a valid delegation chain can produce
|
||||
/// exactly that capability (see `is_attenuated_by`).
|
||||
pub fn can(&self, resource: &str, action: &str) -> bool {
|
||||
self.payload
|
||||
.att
|
||||
.iter()
|
||||
.any(|cap| cap.with == resource && cap.can == action)
|
||||
self.payload.att.iter().any(|cap| {
|
||||
let resource_ok = cap.with == resource || cap.with == "*";
|
||||
let action_ok = cap.can == action || cap.can == "*" || cap.can == caps::REPO_ADMIN;
|
||||
resource_ok && action_ok
|
||||
})
|
||||
}
|
||||
|
||||
/// Encode to a compact JSON string (the wire format).
|
||||
@@ -312,6 +318,63 @@ mod tests {
|
||||
assert!(!ucan.can("gitlawb://repos/test/repo", caps::PR_MERGE));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn can_honors_resource_wildcard() {
|
||||
let issuer = Keypair::generate();
|
||||
let audience = Keypair::generate().did();
|
||||
|
||||
let ucan = Ucan::issue(
|
||||
&issuer,
|
||||
audience,
|
||||
vec![Capability::new("*", caps::GIT_PUSH)],
|
||||
None,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
assert!(ucan.can("gitlawb://repos/test/repo", caps::GIT_PUSH));
|
||||
assert!(ucan.can("gitlawb://repos/other/repo", caps::GIT_PUSH));
|
||||
assert!(!ucan.can("gitlawb://repos/test/repo", caps::PR_MERGE));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn can_honors_repo_admin_action_wildcard() {
|
||||
let issuer = Keypair::generate();
|
||||
let audience = Keypair::generate().did();
|
||||
|
||||
let ucan = Ucan::issue(
|
||||
&issuer,
|
||||
audience,
|
||||
vec![Capability::new(
|
||||
"gitlawb://repos/test/repo",
|
||||
caps::REPO_ADMIN,
|
||||
)],
|
||||
None,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
assert!(ucan.can("gitlawb://repos/test/repo", caps::GIT_PUSH));
|
||||
assert!(ucan.can("gitlawb://repos/test/repo", caps::PR_MERGE));
|
||||
assert!(!ucan.can("gitlawb://repos/other/repo", caps::GIT_PUSH));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn can_honors_action_wildcard() {
|
||||
let issuer = Keypair::generate();
|
||||
let audience = Keypair::generate().did();
|
||||
|
||||
let ucan = Ucan::issue(
|
||||
&issuer,
|
||||
audience,
|
||||
vec![Capability::new("gitlawb://repos/test/repo", "*")],
|
||||
None,
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
assert!(ucan.can("gitlawb://repos/test/repo", caps::GIT_PUSH));
|
||||
assert!(ucan.can("gitlawb://repos/test/repo", caps::PR_MERGE));
|
||||
assert!(!ucan.can("gitlawb://repos/other/repo", caps::GIT_PUSH));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn bootstrap_ucan() {
|
||||
let issuer = Keypair::generate();
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
[package]
|
||||
name = "gitlawb-node"
|
||||
description = "The gitlawb node daemon — git hosting over HTTP with DID auth"
|
||||
version = "0.4.0" # x-release-please-version
|
||||
version = "0.7.1" # x-release-please-version
|
||||
edition.workspace = true
|
||||
rust-version.workspace = true
|
||||
license.workspace = true
|
||||
|
||||
@@ -110,19 +110,28 @@ pub async fn create_bounty(
|
||||
Ok((StatusCode::CREATED, Json(bounty)))
|
||||
}
|
||||
|
||||
const MAX_BOUNTY_LIMIT: i64 = 200;
|
||||
|
||||
/// GET /api/v1/repos/{owner}/{repo}/bounties
|
||||
pub async fn list_repo_bounties(
|
||||
State(state): State<AppState>,
|
||||
Path((owner, repo)): Path<(String, String)>,
|
||||
Query(q): Query<ListBountiesQuery>,
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
) -> Result<Json<serde_json::Value>> {
|
||||
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
|
||||
crate::api::authorize_repo_read(&state, &owner, &repo, caller, "/").await?;
|
||||
|
||||
let limit = q.limit.unwrap_or(50).clamp(1, MAX_BOUNTY_LIMIT);
|
||||
let bounties = state
|
||||
.db
|
||||
.list_bounties(
|
||||
Some(&owner),
|
||||
Some(&repo),
|
||||
q.status.as_deref(),
|
||||
q.limit.unwrap_or(50),
|
||||
limit,
|
||||
None,
|
||||
None,
|
||||
)
|
||||
.await?;
|
||||
|
||||
@@ -133,25 +142,92 @@ pub async fn list_repo_bounties(
|
||||
pub async fn list_all_bounties(
|
||||
State(state): State<AppState>,
|
||||
Query(q): Query<ListBountiesQuery>,
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
) -> Result<Json<serde_json::Value>> {
|
||||
let bounties = state
|
||||
.db
|
||||
.list_bounties(None, None, q.status.as_deref(), q.limit.unwrap_or(50))
|
||||
.await?;
|
||||
let raw_limit = q.limit.unwrap_or(50);
|
||||
let limit = raw_limit.clamp(1, MAX_BOUNTY_LIMIT);
|
||||
|
||||
Ok(Json(serde_json::json!({ "bounties": bounties })))
|
||||
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
|
||||
let mut memo = std::collections::HashMap::new();
|
||||
let mut allowed: Vec<BountyRecord> = Vec::new();
|
||||
let page_size = (limit * 5).clamp(1, 200);
|
||||
let max_scanned = 10_000i64;
|
||||
let mut total_scanned: i64 = 0;
|
||||
let mut cursor: Option<(String, String)> = None;
|
||||
|
||||
while (allowed.len() as i64) < limit {
|
||||
let after = cursor.as_ref().map(|(ts, id)| (ts.as_str(), id.as_str()));
|
||||
let bounties = state
|
||||
.db
|
||||
.list_bounties(
|
||||
None,
|
||||
None,
|
||||
q.status.as_deref(),
|
||||
page_size,
|
||||
after.map(|(ts, _)| ts),
|
||||
after.map(|(_, id)| id),
|
||||
)
|
||||
.await?;
|
||||
if bounties.is_empty() {
|
||||
break;
|
||||
}
|
||||
|
||||
total_scanned += bounties.len() as i64;
|
||||
if total_scanned > max_scanned {
|
||||
return Err(AppError::Incomplete(
|
||||
"too many rows scanned; refine your filters".into(),
|
||||
));
|
||||
}
|
||||
|
||||
let last = bounties.last().unwrap();
|
||||
for b in &bounties {
|
||||
if (allowed.len() as i64) >= limit {
|
||||
break;
|
||||
}
|
||||
let key = format!("{}/{}", b.repo_owner, b.repo_name);
|
||||
let admitted = if let Some(&result) = memo.get(&key) {
|
||||
result
|
||||
} else {
|
||||
let result = crate::api::authorize_repo_read(
|
||||
&state,
|
||||
&b.repo_owner,
|
||||
&b.repo_name,
|
||||
caller,
|
||||
"/",
|
||||
)
|
||||
.await
|
||||
.is_ok();
|
||||
memo.insert(key, result);
|
||||
result
|
||||
};
|
||||
if admitted {
|
||||
allowed.push(b.clone());
|
||||
}
|
||||
}
|
||||
cursor = Some((last.created_at.clone(), last.id.clone()));
|
||||
}
|
||||
|
||||
Ok(Json(serde_json::json!({ "bounties": allowed })))
|
||||
}
|
||||
|
||||
/// GET /api/v1/bounties/{id}
|
||||
pub async fn get_bounty(
|
||||
State(state): State<AppState>,
|
||||
Path(id): Path<String>,
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
) -> Result<Json<BountyRecord>> {
|
||||
let bounty = state
|
||||
.db
|
||||
.get_bounty(&id)
|
||||
.await?
|
||||
.ok_or_else(|| AppError::NotFound(format!("bounty {id} not found")))?;
|
||||
let not_found = || AppError::NotFound(format!("bounty {id} not found"));
|
||||
|
||||
let bounty = state.db.get_bounty(&id).await?.ok_or_else(not_found)?;
|
||||
|
||||
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
|
||||
if crate::api::authorize_repo_read(&state, &bounty.repo_owner, &bounty.repo_name, caller, "/")
|
||||
.await
|
||||
.is_err()
|
||||
{
|
||||
return Err(not_found());
|
||||
}
|
||||
|
||||
Ok(Json(bounty))
|
||||
}
|
||||
|
||||
@@ -162,11 +238,22 @@ pub async fn claim_bounty(
|
||||
Path(id): Path<String>,
|
||||
Json(req): Json<ClaimBountyRequest>,
|
||||
) -> Result<Json<BountyRecord>> {
|
||||
let bounty = state
|
||||
.db
|
||||
.get_bounty(&id)
|
||||
.await?
|
||||
.ok_or_else(|| AppError::NotFound(format!("bounty {id} not found")))?;
|
||||
let not_found = || AppError::NotFound(format!("bounty {id} not found"));
|
||||
|
||||
let bounty = state.db.get_bounty(&id).await?.ok_or_else(not_found)?;
|
||||
|
||||
if crate::api::authorize_repo_read(
|
||||
&state,
|
||||
&bounty.repo_owner,
|
||||
&bounty.repo_name,
|
||||
Some(auth.0.as_str()),
|
||||
"/",
|
||||
)
|
||||
.await
|
||||
.is_err()
|
||||
{
|
||||
return Err(not_found());
|
||||
}
|
||||
|
||||
if bounty.status != "open" {
|
||||
return Err(AppError::BadRequest(format!(
|
||||
|
||||
@@ -1,23 +1,44 @@
|
||||
//! API handlers for ref certificates.
|
||||
|
||||
use axum::extract::{Path, State};
|
||||
use std::collections::HashMap;
|
||||
|
||||
use axum::extract::{Extension, Path, Query, State};
|
||||
use axum::Json;
|
||||
|
||||
use crate::auth::AuthenticatedDid;
|
||||
use crate::error::{AppError, Result};
|
||||
use crate::state::AppState;
|
||||
|
||||
/// GET /api/v1/repos/{owner}/{repo}/certs
|
||||
/// GET /api/v1/repos/{owner}/{repo}/certs?limit=50
|
||||
pub async fn list_certs(
|
||||
State(state): State<AppState>,
|
||||
Path((owner, name)): Path<(String, String)>,
|
||||
Query(params): Query<HashMap<String, String>>,
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
) -> Result<Json<serde_json::Value>> {
|
||||
let record = state
|
||||
.db
|
||||
.get_repo(&owner, &name)
|
||||
.await?
|
||||
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
|
||||
let limit = params
|
||||
.get("limit")
|
||||
.and_then(|v| v.parse::<i64>().ok())
|
||||
.map(|v| v.max(1))
|
||||
.unwrap_or(50)
|
||||
.min(200);
|
||||
|
||||
let certs = state.db.list_ref_certificates(&record.id).await?;
|
||||
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
|
||||
let (record, _rules) =
|
||||
crate::api::authorize_repo_read(&state, &owner, &name, caller, "/").await?;
|
||||
|
||||
// When a prefix is given (short-ID resolution from the CLI) use a
|
||||
// generous limit and delegate to the prefix-matched query so the
|
||||
// caller can resolve IDs regardless of how many certs exist.
|
||||
let prefix = params.get("prefix").filter(|p| !p.is_empty());
|
||||
let certs = if let Some(prefix) = prefix {
|
||||
state
|
||||
.db
|
||||
.list_ref_certificates_by_prefix(&record.id, prefix, 200)
|
||||
.await?
|
||||
} else {
|
||||
state.db.list_ref_certificates(&record.id, limit).await?
|
||||
};
|
||||
let certs_json: Vec<serde_json::Value> = certs
|
||||
.iter()
|
||||
.map(|c| {
|
||||
@@ -35,20 +56,21 @@ pub async fn list_certs(
|
||||
})
|
||||
.collect();
|
||||
|
||||
Ok(Json(serde_json::json!({ "certificates": certs_json })))
|
||||
let count = certs_json.len();
|
||||
Ok(Json(
|
||||
serde_json::json!({ "certificates": certs_json, "count": count }),
|
||||
))
|
||||
}
|
||||
|
||||
/// GET /api/v1/repos/{owner}/{repo}/certs/{id}
|
||||
pub async fn get_cert(
|
||||
State(state): State<AppState>,
|
||||
Path((owner, name, id)): Path<(String, String, String)>,
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
) -> Result<Json<serde_json::Value>> {
|
||||
// Verify the repo exists
|
||||
let _record = state
|
||||
.db
|
||||
.get_repo(&owner, &name)
|
||||
.await?
|
||||
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
|
||||
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
|
||||
let (record, _rules) =
|
||||
crate::api::authorize_repo_read(&state, &owner, &name, caller, "/").await?;
|
||||
|
||||
let cert = state
|
||||
.db
|
||||
@@ -56,6 +78,10 @@ pub async fn get_cert(
|
||||
.await?
|
||||
.ok_or_else(|| AppError::NotFound(format!("certificate {id}")))?;
|
||||
|
||||
if cert.repo_id != record.id {
|
||||
return Err(AppError::NotFound(format!("certificate {id}")));
|
||||
}
|
||||
|
||||
Ok(Json(serde_json::json!({
|
||||
"id": cert.id,
|
||||
"repo_id": cert.repo_id,
|
||||
|
||||
File diff suppressed because it is too large.
Load diff
@@ -27,7 +27,7 @@ use std::str::FromStr;
|
||||
use crate::auth::AuthenticatedDid;
|
||||
use crate::error::{AppError, Result};
|
||||
use crate::git::store;
|
||||
use crate::git::visibility_pack::{has_path_scoped_rule, withheld_blob_oids};
|
||||
use crate::git::visibility_pack::{allowed_blob_set_for_caller, has_path_scoped_rule};
|
||||
use crate::state::AppState;
|
||||
use crate::visibility::{visibility_check, Decision};
|
||||
|
||||
@@ -36,16 +36,24 @@ use crate::visibility::{visibility_check, Decision};
|
||||
/// Search all repos on the node for a git object whose SHA-256 hash matches
|
||||
/// the given CIDv1, returning its raw content if the caller may read it.
|
||||
///
|
||||
/// Visibility (#110): the object is served only from a repo row the caller
|
||||
/// passes. For each iterated row we gate against that row's OWN rules
|
||||
/// Visibility (#110, #126): the object is served only from a repo row the
|
||||
/// caller passes. For each iterated row we gate against that row's OWN rules
|
||||
/// (`visibility_check` at `"/"`), never re-resolving via `authorize_repo_read`
|
||||
/// — `get_repo`'s fuzzy match could otherwise authorize a different physical
|
||||
/// row than the one read (KTD2a). When the row carries path-scoped rules, a
|
||||
/// blob withheld from the caller (`withheld_blob_oids`) is skipped. Denial and
|
||||
/// genuine not-found both fall through to an opaque 404.
|
||||
/// row than the one read (KTD2a). We check object existence via
|
||||
/// `store::object_type` *before* the expensive reachability walk so random-CID
|
||||
/// spray cannot trigger full-history git walks on repos that don't carry the
|
||||
/// object. When the row carries path-scoped rules (KTD4) the served object
|
||||
/// must be either a non-blob (trees/commits are structural; KTD3) OR a blob
|
||||
/// in the caller's *reachable* allowed-set (`allowed_blob_set_for_caller`).
|
||||
/// The reachable allowed-set excludes dangling blobs — a blob written via
|
||||
/// `git hash-object -w` and never committed has no path to gate, so it is
|
||||
/// fail-closed 404'd under path-scoped rules (#126). Denial and genuine
|
||||
/// not-found both fall through to an opaque 404.
|
||||
///
|
||||
/// Scope: this closes the direct unauthenticated scan. A stale-public mirror
|
||||
/// row still serves withheld content (tracked separately, #124).
|
||||
/// Scope: this closes the direct unauthenticated scan, including the dangling
|
||||
/// case. A stale-public mirror row still serves withheld content (tracked
|
||||
/// separately, #124).
|
||||
pub async fn get_by_cid(
|
||||
Path(cid_str): Path<String>,
|
||||
State(state): State<AppState>,
|
||||
@@ -85,11 +93,16 @@ pub async fn get_by_cid(
|
||||
.await
|
||||
.map_err(AppError::Internal)?;
|
||||
|
||||
// Request-scoped memo of the per-repo withheld set (KTD1). The caller is
|
||||
// constant for one request, so `repo.id` alone is a safe, sufficient key —
|
||||
// never a coarse caller "class", which `visibility_check`'s exact full-DID
|
||||
// reader match would make unsafe.
|
||||
let mut withheld_memo: HashMap<String, HashSet<String>> = HashMap::new();
|
||||
// Request-scoped memo of the per-repo allowed-blob set (KTD1, #126). The
|
||||
// caller is constant for one request, so `repo.id` alone is a safe,
|
||||
// sufficient key — never a coarse caller "class", which
|
||||
// `visibility_check`'s exact full-DID reader match would make unsafe.
|
||||
//
|
||||
// We flipped from a deny-set (`withheld_blob_oids`) to an allowed-set
|
||||
// (`allowed_blob_set_for_caller`) so dangling blobs — never enumerated by
|
||||
// the reachable walk — fail closed instead of slipping through an empty
|
||||
// deny entry (#126).
|
||||
let mut allowed_memo: HashMap<String, HashSet<String>> = HashMap::new();
|
||||
|
||||
for repo in &repos {
|
||||
// Repo-level read gate against THIS row's own rules (KTD2a).
|
||||
@@ -106,9 +119,24 @@ pub async fn get_by_cid(
|
||||
Err(_) => continue,
|
||||
};
|
||||
|
||||
// Per-blob withholding only applies when a path-scoped rule exists (KTD4).
|
||||
if has_path_scoped_rule(rules) {
|
||||
if !withheld_memo.contains_key(&repo.id) {
|
||||
// Check whether the object exists in this repo before any expensive
|
||||
// reachability walk. This prevents random-CID spray from triggering
|
||||
// full-history git walks on repos that don't carry the object.
|
||||
let obj_type = match store::object_type(&repo_path, &sha256_hex) {
|
||||
Ok(Some(t)) => t,
|
||||
Ok(None) => continue,
|
||||
Err(e) => {
|
||||
tracing::warn!(repo = %repo.name, err = %e, "error checking git object type");
|
||||
continue;
|
||||
}
|
||||
};
|
||||
|
||||
// Per-blob gating only applies when a path-scoped rule exists (KTD4).
|
||||
// Without any path-scoped rule, the "/" gate above is the whole story.
|
||||
// Trees/commits are always served under path-scoped rules (KTD3).
|
||||
let path_scoped = has_path_scoped_rule(rules);
|
||||
if path_scoped && obj_type == "blob" {
|
||||
if !allowed_memo.contains_key(&repo.id) {
|
||||
let rp = repo_path.clone();
|
||||
let r = rules.to_vec();
|
||||
let is_public = repo.is_public;
|
||||
@@ -116,7 +144,13 @@ pub async fn get_by_cid(
|
||||
let caller_for_walk = caller_owned.clone();
|
||||
// Full-history walk shells out to git — keep it off the async runtime.
|
||||
let walk = tokio::task::spawn_blocking(move || {
|
||||
withheld_blob_oids(&rp, &r, is_public, &owner, caller_for_walk.as_deref())
|
||||
allowed_blob_set_for_caller(
|
||||
&rp,
|
||||
&r,
|
||||
is_public,
|
||||
&owner,
|
||||
caller_for_walk.as_deref(),
|
||||
)
|
||||
})
|
||||
.await;
|
||||
// Fail closed on EITHER a task panic (JoinError) or a walk error:
|
||||
@@ -125,51 +159,50 @@ pub async fn get_by_cid(
|
||||
let set = match walk {
|
||||
Ok(Ok(set)) => set,
|
||||
Ok(Err(e)) => {
|
||||
tracing::warn!(repo = %repo.name, err = %e, "withheld walk failed; skipping repo");
|
||||
tracing::warn!(repo = %repo.name, err = %e, "allowed-blob walk failed; skipping repo");
|
||||
continue;
|
||||
}
|
||||
Err(e) => {
|
||||
tracing::warn!(repo = %repo.name, err = %e, "withheld walk task panicked; skipping repo");
|
||||
tracing::warn!(repo = %repo.name, err = %e, "allowed-blob walk task panicked; skipping repo");
|
||||
continue;
|
||||
}
|
||||
};
|
||||
withheld_memo.insert(repo.id.clone(), set);
|
||||
allowed_memo.insert(repo.id.clone(), set);
|
||||
}
|
||||
if withheld_memo
|
||||
let in_allowed = allowed_memo
|
||||
.get(&repo.id)
|
||||
.is_some_and(|set| set.contains(&sha256_hex))
|
||||
{
|
||||
.is_some_and(|set| set.contains(&sha256_hex));
|
||||
if !in_allowed {
|
||||
continue;
|
||||
}
|
||||
}
|
||||
|
||||
match store::read_object(&repo_path, &sha256_hex) {
|
||||
Ok(Some((_obj_type, content))) => {
|
||||
// 3. Return the content with IPFS-style headers
|
||||
let mut headers = HeaderMap::new();
|
||||
headers.insert(
|
||||
HeaderName::from_static("content-type"),
|
||||
HeaderValue::from_static("application/octet-stream"),
|
||||
);
|
||||
headers.insert(
|
||||
HeaderName::from_static("x-content-cid"),
|
||||
HeaderValue::from_str(&cid_str)
|
||||
.unwrap_or_else(|_| HeaderValue::from_static("invalid")),
|
||||
);
|
||||
headers.insert(
|
||||
HeaderName::from_static("x-git-hash"),
|
||||
HeaderValue::from_str(&sha256_hex)
|
||||
.unwrap_or_else(|_| HeaderValue::from_static("invalid")),
|
||||
);
|
||||
|
||||
return Ok((StatusCode::OK, headers, content).into_response());
|
||||
}
|
||||
Ok(None) => continue,
|
||||
// Now that we've passed the gate, read the content.
|
||||
let content = match store::read_object_content(&repo_path, &sha256_hex, &obj_type) {
|
||||
Ok(c) => c,
|
||||
Err(e) => {
|
||||
tracing::warn!(repo = %repo.name, err = %e, "error reading git object");
|
||||
tracing::warn!(repo = %repo.name, err = %e, "error reading git object content");
|
||||
continue;
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
// 3. Return the content with IPFS-style headers
|
||||
let mut headers = HeaderMap::new();
|
||||
headers.insert(
|
||||
HeaderName::from_static("content-type"),
|
||||
HeaderValue::from_static("application/octet-stream"),
|
||||
);
|
||||
headers.insert(
|
||||
HeaderName::from_static("x-content-cid"),
|
||||
HeaderValue::from_str(&cid_str).unwrap_or_else(|_| HeaderValue::from_static("invalid")),
|
||||
);
|
||||
headers.insert(
|
||||
HeaderName::from_static("x-git-hash"),
|
||||
HeaderValue::from_str(&sha256_hex)
|
||||
.unwrap_or_else(|_| HeaderValue::from_static("invalid")),
|
||||
);
|
||||
|
||||
return Ok((StatusCode::OK, headers, content).into_response());
|
||||
}
|
||||
|
||||
// Not found in any repo
|
||||
|
||||
@@ -90,12 +90,11 @@ pub async fn create_issue(
|
||||
pub async fn list_issues(
|
||||
State(state): State<AppState>,
|
||||
Path((owner, repo)): Path<(String, String)>,
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
) -> Result<Json<serde_json::Value>> {
|
||||
let record = state
|
||||
.db
|
||||
.get_repo(&owner, &repo)
|
||||
.await?
|
||||
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
|
||||
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
|
||||
let (record, _rules) =
|
||||
crate::api::authorize_repo_read(&state, &owner, &repo, caller, "/").await?;
|
||||
|
||||
let disk_path = state
|
||||
.repo_store
|
||||
@@ -120,12 +119,11 @@ pub async fn list_issues(
|
||||
pub async fn get_issue(
|
||||
State(state): State<AppState>,
|
||||
Path((owner, repo, issue_id)): Path<(String, String, String)>,
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
) -> Result<Json<serde_json::Value>> {
|
||||
let record = state
|
||||
.db
|
||||
.get_repo(&owner, &repo)
|
||||
.await?
|
||||
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
|
||||
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
|
||||
let (record, _rules) =
|
||||
crate::api::authorize_repo_read(&state, &owner, &repo, caller, "/").await?;
|
||||
|
||||
let disk_path = state
|
||||
.repo_store
|
||||
@@ -191,14 +189,31 @@ pub async fn create_issue_comment(
|
||||
pub async fn list_issue_comments(
|
||||
State(state): State<AppState>,
|
||||
Path((owner, repo, issue_id)): Path<(String, String, String)>,
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
) -> Result<Json<serde_json::Value>> {
|
||||
let _record = state
|
||||
.db
|
||||
.get_repo(&owner, &repo)
|
||||
.await?
|
||||
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
|
||||
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
|
||||
let (record, _rules) =
|
||||
crate::api::authorize_repo_read(&state, &owner, &repo, caller, "/").await?;
|
||||
|
||||
let comments = state.db.list_issue_comments(&issue_id).await?;
|
||||
let disk_path = state
|
||||
.repo_store
|
||||
.acquire(&record.owner_did, &record.name)
|
||||
.await
|
||||
.map_err(|e| AppError::Git(e.to_string()))?;
|
||||
// Resolve the full issue ID (accepts 8-char prefix) so the DB fetch
|
||||
// below uses the same canonical id as the git ref.
|
||||
let full_id = match git_issues::resolve_issue_id(&disk_path, &issue_id)
|
||||
.map_err(|e| AppError::Git(e.to_string()))?
|
||||
{
|
||||
Some(id) => id,
|
||||
None => {
|
||||
return Err(AppError::RepoNotFound(format!(
|
||||
"issue {issue_id} not found"
|
||||
)))
|
||||
}
|
||||
};
|
||||
|
||||
let comments = state.db.list_issue_comments(&full_id).await?;
|
||||
Ok(Json(serde_json::json!({ "comments": comments })))
|
||||
}
|
||||
|
||||
|
||||
@@ -71,15 +71,18 @@ pub async fn remove_label(
|
||||
}
|
||||
|
||||
/// GET /api/v1/repos/:owner/:repo/labels
|
||||
///
|
||||
/// Read-visibility-gated (INV-2 root listing): a public repo's labels stay
|
||||
/// anonymously listable; a private repo's label names are hidden (404) from
|
||||
/// anyone who cannot read it at the root.
|
||||
pub async fn list_labels(
|
||||
State(state): State<AppState>,
|
||||
Path((owner, name)): Path<(String, String)>,
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
) -> Result<Json<serde_json::Value>> {
|
||||
let record = state
|
||||
.db
|
||||
.get_repo(&owner, &name)
|
||||
.await?
|
||||
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
|
||||
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
|
||||
let (record, _rules) =
|
||||
crate::api::authorize_repo_read(&state, &owner, &name, caller, "/").await?;
|
||||
|
||||
let labels = state.db.list_labels(&record.id).await?;
|
||||
Ok(Json(serde_json::json!({ "labels": labels })))
|
||||
|
||||
@@ -114,6 +114,12 @@ mod did_tests {
|
||||
assert!(!did_matches("did:key:zABC", "did:key:zXYZ"));
|
||||
assert!(!did_matches("zABC", "zXYZ"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn empty_did_matches() {
|
||||
assert!(did_matches("", ""));
|
||||
assert!(did_matches("", "did:key:"));
|
||||
}
|
||||
}
|
||||
|
||||
/// Drift guard (plan 002 §Gate-type table, Step 5). Every in-scope mutation
|
||||
@@ -166,6 +172,7 @@ mod authz_guard {
|
||||
let issues = include_str!("issues.rs");
|
||||
let bounties = include_str!("bounties.rs");
|
||||
let replicas = include_str!("replicas.rs");
|
||||
let events = include_str!("events.rs");
|
||||
let tasks = include_str!("tasks.rs");
|
||||
let stars = include_str!("stars.rs");
|
||||
let protect = include_str!("protect.rs");
|
||||
@@ -181,6 +188,13 @@ mod authz_guard {
|
||||
(pulls, "merge_pr", "require_repo_owner("),
|
||||
(webhooks, "create_webhook", "require_repo_owner("),
|
||||
(webhooks, "delete_webhook", "require_repo_owner("),
|
||||
// Bucket A/B hybrid — list_webhooks is read-visibility THEN owner:
|
||||
// authorize_repo_read 404s a non-reader of a private repo, then
|
||||
// require_repo_owner 403s a non-owner of a public one. Both halves
|
||||
// are pinned: the authorize_repo_read marker guards the read half
|
||||
// (existence hiding) and require_repo_owner guards the owner half.
|
||||
(webhooks, "list_webhooks", "authorize_repo_read("),
|
||||
(webhooks, "list_webhooks", "require_repo_owner("),
|
||||
(labels, "add_label", "require_repo_owner("),
|
||||
(labels, "remove_label", "require_repo_owner("),
|
||||
// Bucket A' — owner OR author (did_matches against the author)
|
||||
@@ -197,6 +211,12 @@ mod authz_guard {
|
||||
// get_by_cid gates each iterated repo row directly via visibility_check
|
||||
// (KTD2a: it must NOT route through authorize_repo_read's fuzzy re-resolve).
|
||||
(ipfs, "get_by_cid", "visibility_check("),
|
||||
// #94 sibling read surfaces: gate private-repo metadata on read
|
||||
// visibility (public repos stay anonymous; private repos 404).
|
||||
(replicas, "list_replicas", "authorize_repo_read("),
|
||||
(protect, "list_protected_branches", "authorize_repo_read("),
|
||||
(labels, "list_labels", "authorize_repo_read("),
|
||||
(events, "list_repo_events", "authorize_repo_read("),
|
||||
// Bucket C — signer-self: the acting DID is matched/bound to auth.0
|
||||
(tasks, "create_task", "did_matches("),
|
||||
(tasks, "claim_task", "did_matches("),
|
||||
@@ -324,6 +344,118 @@ mod authz_guard {
|
||||
})
|
||||
}
|
||||
|
||||
/// Collect `.rs` source files under `dir`. Recursive so the completeness scan
|
||||
/// covers nested API modules (`api/<module>/mod.rs` and deeper), not only the
|
||||
/// immediate `api/*.rs` children.
|
||||
fn collect_rs_files(dir: &std::path::Path) -> Vec<std::path::PathBuf> {
|
||||
let mut out = Vec::new();
|
||||
for entry in std::fs::read_dir(dir).expect("read api dir") {
|
||||
let path = entry.expect("dir entry").path();
|
||||
if path.is_dir() {
|
||||
out.extend(collect_rs_files(&path));
|
||||
} else if path.extension().is_some_and(|e| e == "rs") {
|
||||
out.push(path);
|
||||
}
|
||||
}
|
||||
out
|
||||
}
|
||||
|
||||
/// The `.rs` files under `api_root` (as paths RELATIVE to it) that the
|
||||
/// completeness scan must inspect: everything except the top-level `mod.rs` (the
|
||||
/// guard file itself) and the top-level files already covered by the per-handler
|
||||
/// `sources` loop. A nested `api/<module>/<name>.rs` is a distinct source file
|
||||
/// even when its basename matches a listed top-level file, so it stays in scope.
|
||||
fn unlisted_source_files(
|
||||
api_root: &std::path::Path,
|
||||
listed: &std::collections::HashSet<&str>,
|
||||
) -> Vec<String> {
|
||||
collect_rs_files(api_root)
|
||||
.iter()
|
||||
.filter_map(|path| {
|
||||
let rel = path
|
||||
.strip_prefix(api_root)
|
||||
.ok()?
|
||||
.to_string_lossy()
|
||||
.replace('\\', "/");
|
||||
if rel == "mod.rs" || listed.contains(rel.as_str()) {
|
||||
None
|
||||
} else {
|
||||
Some(rel)
|
||||
}
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn collect_rs_files_recurses_subdirs() {
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let root = tmp.path();
|
||||
std::fs::write(root.join("a.rs"), "").unwrap();
|
||||
std::fs::write(root.join("note.txt"), "").unwrap();
|
||||
std::fs::create_dir_all(root.join("sub/deep")).unwrap();
|
||||
std::fs::write(root.join("sub/mod.rs"), "").unwrap();
|
||||
std::fs::write(root.join("sub/deep/c.rs"), "").unwrap();
|
||||
let names: std::collections::HashSet<String> = collect_rs_files(root)
|
||||
.iter()
|
||||
.map(|p| {
|
||||
p.strip_prefix(root)
|
||||
.unwrap()
|
||||
.to_string_lossy()
|
||||
.replace('\\', "/")
|
||||
})
|
||||
.collect();
|
||||
assert!(names.contains("a.rs"));
|
||||
assert!(
|
||||
names.contains("sub/mod.rs"),
|
||||
"nested module file must be collected"
|
||||
);
|
||||
assert!(
|
||||
names.contains("sub/deep/c.rs"),
|
||||
"deeply nested file must be collected"
|
||||
);
|
||||
assert!(
|
||||
!names.iter().any(|n| n.ends_with(".txt")),
|
||||
"non-rs files excluded"
|
||||
);
|
||||
assert_eq!(names.len(), 3);
|
||||
}
|
||||
|
||||
// P3 (#119): the completeness scan must skip already-covered files by their path
|
||||
// RELATIVE to api_root, not by basename. A nested api/<module>/repos.rs is a
|
||||
// distinct source file from the covered top-level repos.rs and must still be
|
||||
// scanned, or a new nested module could smuggle in an ungated repo-scoped handler
|
||||
// behind a colliding filename.
|
||||
#[test]
|
||||
fn unlisted_source_files_scans_nested_file_with_colliding_basename() {
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let root = tmp.path();
|
||||
std::fs::write(root.join("repos.rs"), "").unwrap();
|
||||
std::fs::write(root.join("mod.rs"), "").unwrap();
|
||||
std::fs::create_dir_all(root.join("sub")).unwrap();
|
||||
std::fs::write(root.join("sub/repos.rs"), "").unwrap();
|
||||
std::fs::write(root.join("sub/fresh.rs"), "").unwrap();
|
||||
let listed: std::collections::HashSet<&str> = ["repos.rs"].into_iter().collect();
|
||||
|
||||
let unlisted = unlisted_source_files(root, &listed);
|
||||
|
||||
assert!(
|
||||
unlisted.contains(&"sub/repos.rs".to_string()),
|
||||
"a nested file whose basename matches a listed top-level file must still be scanned"
|
||||
);
|
||||
assert!(
|
||||
unlisted.contains(&"sub/fresh.rs".to_string()),
|
||||
"a nested file with a unique name must be scanned"
|
||||
);
|
||||
assert!(
|
||||
!unlisted.contains(&"repos.rs".to_string()),
|
||||
"the listed top-level file is covered by the per-handler loop"
|
||||
);
|
||||
assert!(
|
||||
!unlisted.contains(&"mod.rs".to_string()),
|
||||
"the top-level guard file is skipped"
|
||||
);
|
||||
}
|
||||
|
||||
/// Egress gate guard: every repo-scoped handler (`Path<(String, String..)>`)
|
||||
/// must carry an authz marker — a read gate (`authorize_repo_read` /
|
||||
/// `visibility_check`), or a write gate (`require_repo_owner` / `require_owner`
|
||||
@@ -376,42 +508,22 @@ mod authz_guard {
|
||||
"read-guard `sources` lists {f} but the file does not exist"
|
||||
);
|
||||
}
|
||||
for entry in std::fs::read_dir(api_dir).expect("read src/api") {
|
||||
let path = entry.expect("dir entry").path();
|
||||
let fname = path.file_name().unwrap().to_string_lossy().into_owned();
|
||||
if !fname.ends_with(".rs") || fname == "mod.rs" || listed.contains(fname.as_str()) {
|
||||
continue;
|
||||
}
|
||||
let src = std::fs::read_to_string(&path).expect("read api file");
|
||||
let api_root = std::path::Path::new(api_dir);
|
||||
for rel in unlisted_source_files(api_root, &listed) {
|
||||
let src = std::fs::read_to_string(api_root.join(&rel)).expect("read api file");
|
||||
let has_repo_handler = handler_names(&src)
|
||||
.iter()
|
||||
.any(|n| is_repo_scoped(&fn_body(&src, n)));
|
||||
assert!(
|
||||
!has_repo_handler,
|
||||
"api/{fname} declares a repo-scoped handler but is not in the egress \
|
||||
"api/{rel} declares a repo-scoped handler but is not in the egress \
|
||||
guard `sources` list — add it so its handlers are gate-checked"
|
||||
);
|
||||
}
|
||||
|
||||
// Repo-scoped reads known to be ungated today, each tracked by an issue.
|
||||
// Remove an entry the moment its gate lands (the staleness assert enforces it).
|
||||
let known_ungated: &[(&str, &str)] = &[
|
||||
// info/refs gates only git-upload-pack today; git-receive-pack
|
||||
// advertisement is ungated until #119 makes the gate unconditional.
|
||||
("git_info_refs", "#119"),
|
||||
("list_certs", "#120"),
|
||||
("get_cert", "#120"),
|
||||
("list_issues", "#120"),
|
||||
("get_issue", "#120"),
|
||||
("list_issue_comments", "#120"),
|
||||
("list_labels", "#120"),
|
||||
("list_repo_bounties", "#120"),
|
||||
("get_star_status", "#120"),
|
||||
("list_repo_events", "#94 (PR #113)"),
|
||||
("list_webhooks", "#94 (PR #113)"),
|
||||
("list_replicas", "PR #113"),
|
||||
("list_protected_branches", "PR #113"),
|
||||
];
|
||||
let known_ungated: &[(&str, &str)] = &[];
|
||||
let is_known = |n: &str| known_ungated.iter().any(|(k, _)| *k == n);
|
||||
// Any one of these = the handler binds the caller to an authz decision: the
|
||||
// first two are read gates, the rest are the write/owner/self-binding forms.
|
||||
|
||||
@@ -296,8 +296,8 @@ pub async fn trigger_sync(State(state): State<AppState>) -> Result<Json<serde_js
|
||||
repo.get("name").and_then(|v| v.as_str()),
|
||||
) {
|
||||
(Some(owner), Some(name)) => {
|
||||
// Use short owner (last colon segment) matching DB convention
|
||||
let short = owner.split(':').next_back().unwrap_or(owner);
|
||||
// Use short owner (did:key-only normalization) matching DB convention
|
||||
let short = crate::db::normalize_owner_key(owner);
|
||||
format!("{short}/{name}")
|
||||
}
|
||||
_ => continue,
|
||||
@@ -347,6 +347,10 @@ pub struct NotifyRequest {
|
||||
pub timestamp: Option<String>,
|
||||
#[serde(default)]
|
||||
pub cert_id: Option<String>,
|
||||
/// Full owner DID — added in #144 for DID-aware feed gating.
|
||||
/// Optional for backward compat with older senders.
|
||||
#[serde(default)]
|
||||
pub owner_did: Option<String>,
|
||||
}
|
||||
|
||||
pub async fn notify_sync(
|
||||
@@ -377,6 +381,14 @@ pub async fn notify_sync(
|
||||
)));
|
||||
}
|
||||
|
||||
// #272: the slug reaches a PathBuf::join in the sync worker, where an extra
|
||||
// separator or a traversal segment places the mirror outside repos_dir. Reject
|
||||
// it here, before the queue row and the ref-update row are written. The message
|
||||
// names the field and nothing about where repos live on disk.
|
||||
if let Err(e) = crate::git::repo_store::validate_repo_slug(&req.repo) {
|
||||
return Err(AppError::BadRequest(format!("invalid repo field: {e}")));
|
||||
}
|
||||
|
||||
state
|
||||
.db
|
||||
.enqueue_sync(&req.repo, &req.node_did, &req.ref_name, &req.new_sha, None)
|
||||
@@ -391,6 +403,7 @@ pub async fn notify_sync(
|
||||
node_did: req.node_did.clone(),
|
||||
pusher_did: req.pusher_did.clone().unwrap_or_default(),
|
||||
repo: req.repo.clone(),
|
||||
owner_did: req.owner_did.clone(),
|
||||
ref_name: req.ref_name.clone(),
|
||||
old_sha: req.old_sha.clone().unwrap_or_default(),
|
||||
new_sha: req.new_sha.clone(),
|
||||
@@ -537,4 +550,719 @@ mod tests {
|
||||
// pins the `o[0] == 0` check against an off-by-one into 1.x.
|
||||
assert!(is_public_http_url("http://1.0.0.0/"));
|
||||
}
|
||||
|
||||
// ── #82: /sync/trigger signature gate + per-IP brake on the peer-sync routes ──
|
||||
//
|
||||
// These drive the FULL production router (crate::server::build_router) so the
|
||||
// route wiring, layer order, and config-mode branching are all under test.
|
||||
// The positive-path and DID-agnostic cases mount the handler directly because
|
||||
// signed_request_as injects only an AuthenticatedDid extension (not a real
|
||||
// RFC-9421 signature), which require_signature rejects on the full router.
|
||||
use crate::rate_limit::{IpRateLimiter, RateLimiter, TrustedProxy};
|
||||
use crate::state::AppState;
|
||||
use crate::test_support::{signed_request_as, test_state};
|
||||
use axum::body::Body;
|
||||
use axum::extract::ConnectInfo;
|
||||
use axum::http::{header, Method, Request, StatusCode};
|
||||
use axum::routing::post;
|
||||
use axum::{middleware, Extension, Router};
|
||||
use gitlawb_core::http_sig::sign_request;
|
||||
use gitlawb_core::identity::Keypair;
|
||||
use sqlx::PgPool;
|
||||
use std::net::SocketAddr;
|
||||
use std::sync::Arc;
|
||||
use std::time::Duration;
|
||||
use tower::ServiceExt;
|
||||
|
||||
fn unsigned_post(uri: &str, body: &str, peer: &str) -> Request<Body> {
|
||||
let mut req = Request::builder()
|
||||
.method(Method::POST)
|
||||
.uri(uri)
|
||||
.header(header::CONTENT_TYPE, "application/json")
|
||||
.body(Body::from(body.to_string()))
|
||||
.unwrap();
|
||||
req.extensions_mut()
|
||||
.insert(ConnectInfo(peer.parse::<SocketAddr>().unwrap()));
|
||||
req
|
||||
}
|
||||
|
||||
fn require_signed_peer_writes(state: &mut AppState) {
|
||||
let mut cfg = (*state.config).clone();
|
||||
cfg.require_signed_peer_writes = true;
|
||||
state.config = Arc::new(cfg);
|
||||
}
|
||||
|
||||
// The slug must be a well-formed owner/name (#272); these brake tests are about
|
||||
// the rate limiter, so the body carries a valid slug and reaches the brake.
|
||||
const NOTIFY_BODY: &str = r#"{"repo":"z6Mkfoo/hello","ref_name":"refs/heads/main","new_sha":"0000000000000000000000000000000000000000","node_did":"PEER_DID"}"#;
|
||||
|
||||
// ── trigger: mandatory signature ──────────────────────────────────────────
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_trigger_rejects_unsigned_in_default_mode(pool: PgPool) {
|
||||
// The hole: with require_signed_peer_writes=false (default), an anonymous
|
||||
// caller reaches the fan-out. Must be 401 regardless of the flag.
|
||||
let state = test_state(pool).await;
|
||||
let router = crate::server::build_router(state);
|
||||
let resp = router
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/sync/trigger",
|
||||
"{}",
|
||||
"203.0.113.1:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), StatusCode::UNAUTHORIZED);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_trigger_rejects_unsigned_in_signed_writes_mode(pool: PgPool) {
|
||||
// The signature requirement must not depend on the flag.
|
||||
let mut state = test_state(pool).await;
|
||||
require_signed_peer_writes(&mut state);
|
||||
let router = crate::server::build_router(state);
|
||||
let resp = router
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/sync/trigger",
|
||||
"{}",
|
||||
"203.0.113.2:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), StatusCode::UNAUTHORIZED);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_trigger_admits_signed_caller(pool: PgPool) {
|
||||
// must-not-over-throttle: a signed caller reaches the handler and (with no
|
||||
// peers seeded) gets 200, not 429. Direct-mount because a real signature
|
||||
// cannot be forged through the full router in tests.
|
||||
let state = test_state(pool).await;
|
||||
let did = Keypair::generate().did().to_string();
|
||||
let app = Router::new()
|
||||
.route("/api/v1/sync/trigger", post(super::trigger_sync))
|
||||
.layer(middleware::from_fn(crate::rate_limit::rate_limit_by_ip))
|
||||
.layer(Extension(IpRateLimiter {
|
||||
limiter: RateLimiter::new(60, Duration::from_secs(3600)),
|
||||
trust: TrustedProxy::None,
|
||||
}))
|
||||
.with_state(state);
|
||||
let mut req =
|
||||
signed_request_as(&did, Method::POST, "/api/v1/sync/trigger", Body::from("{}"));
|
||||
req.extensions_mut().insert(ConnectInfo(
|
||||
"203.0.113.3:5000".parse::<SocketAddr>().unwrap(),
|
||||
));
|
||||
let resp = app.oneshot(req).await.unwrap();
|
||||
assert_eq!(resp.status(), StatusCode::OK);
|
||||
}
|
||||
|
||||
// ── trigger: IP brake ─────────────────────────────────────────────────────
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_trigger_ip_flood_is_throttled(pool: PgPool) {
|
||||
// The brake is outermost, so an over-limit request 429s before it ever
|
||||
// reaches require_signature — an unsigned request suffices to prove it.
|
||||
let mut state = test_state(pool).await;
|
||||
state.sync_trigger_rate_limiter = RateLimiter::new(1, Duration::from_secs(3600));
|
||||
state.push_limiter_trust = TrustedProxy::None;
|
||||
let peer = "203.0.113.4:5000";
|
||||
// Exhaust the single-request budget up front.
|
||||
assert!(
|
||||
state
|
||||
.sync_trigger_rate_limiter
|
||||
.check(&peer.parse::<SocketAddr>().unwrap().ip().to_string())
|
||||
.await
|
||||
);
|
||||
let router = crate::server::build_router(state);
|
||||
let resp = router
|
||||
.oneshot(unsigned_post("/api/v1/sync/trigger", "{}", peer))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), StatusCode::TOO_MANY_REQUESTS);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_trigger_brake_is_did_agnostic(pool: PgPool) {
|
||||
// Why per-IP, not per-DID: a DID farm (fresh did:key per request) does not
|
||||
// bypass an IP-keyed brake. Two DISTINCT DIDs from one IP, brake limit 1 →
|
||||
// the second is 429. A per-DID limiter would give each DID its own bucket.
|
||||
let state = test_state(pool).await;
|
||||
let app = Router::new()
|
||||
.route("/api/v1/sync/trigger", post(super::trigger_sync))
|
||||
.layer(middleware::from_fn(crate::rate_limit::rate_limit_by_ip))
|
||||
.layer(Extension(IpRateLimiter {
|
||||
limiter: RateLimiter::new(1, Duration::from_secs(3600)),
|
||||
trust: TrustedProxy::None,
|
||||
}))
|
||||
.with_state(state);
|
||||
let peer = "203.0.113.5:5000".parse::<SocketAddr>().unwrap();
|
||||
let mk = |did: &str| {
|
||||
let mut r =
|
||||
signed_request_as(did, Method::POST, "/api/v1/sync/trigger", Body::from("{}"));
|
||||
r.extensions_mut().insert(ConnectInfo(peer));
|
||||
r
|
||||
};
|
||||
let first = app
|
||||
.clone()
|
||||
.oneshot(mk(&Keypair::generate().did().to_string()))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(first.status(), StatusCode::OK);
|
||||
let second = app
|
||||
.oneshot(mk(&Keypair::generate().did().to_string()))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(second.status(), StatusCode::TOO_MANY_REQUESTS);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_trigger_forged_forwarded_header_cannot_bypass(pool: PgPool) {
|
||||
// TrustedProxy::None keys on the socket peer, so rotating X-Forwarded-For
|
||||
// from one socket peer does not refill the bucket. limit 1: first request
|
||||
// consumes it (then 401 unsigned), second from the same socket → 429
|
||||
// regardless of a different XFF value.
|
||||
let mut state = test_state(pool).await;
|
||||
state.sync_trigger_rate_limiter = RateLimiter::new(1, Duration::from_secs(3600));
|
||||
state.push_limiter_trust = TrustedProxy::None;
|
||||
let router = crate::server::build_router(state);
|
||||
let mut a = unsigned_post("/api/v1/sync/trigger", "{}", "203.0.113.6:5000");
|
||||
a.headers_mut()
|
||||
.insert("x-forwarded-for", "1.1.1.1".parse().unwrap());
|
||||
assert_eq!(
|
||||
router.clone().oneshot(a).await.unwrap().status(),
|
||||
StatusCode::UNAUTHORIZED
|
||||
);
|
||||
let mut b = unsigned_post("/api/v1/sync/trigger", "{}", "203.0.113.6:5000");
|
||||
b.headers_mut()
|
||||
.insert("x-forwarded-for", "2.2.2.2".parse().unwrap());
|
||||
assert_eq!(
|
||||
router.oneshot(b).await.unwrap().status(),
|
||||
StatusCode::TOO_MANY_REQUESTS
|
||||
);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_trigger_rate_limit_zero_disables_but_signature_holds(pool: PgPool) {
|
||||
// 0 disables the brake (RateLimiter::check early-returns), proving the two
|
||||
// halves are independent: no 429 even under a flood, but the signature gate
|
||||
// still 401s every unsigned request.
|
||||
let mut state = test_state(pool).await;
|
||||
state.sync_trigger_rate_limiter = RateLimiter::new(0, Duration::from_secs(3600));
|
||||
state.push_limiter_trust = TrustedProxy::None;
|
||||
let router = crate::server::build_router(state);
|
||||
for _ in 0..3 {
|
||||
let resp = router
|
||||
.clone()
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/sync/trigger",
|
||||
"{}",
|
||||
"203.0.113.7:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), StatusCode::UNAUTHORIZED);
|
||||
}
|
||||
}
|
||||
|
||||
// ── notify: braked, but signature behavior unchanged ──────────────────────
|
||||
|
||||
async fn seed_peer(state: &AppState) -> String {
|
||||
let did = Keypair::generate().did().to_string();
|
||||
state
|
||||
.db
|
||||
.upsert_peer(&did, "https://peer.example.com")
|
||||
.await
|
||||
.unwrap();
|
||||
did
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_notify_unsigned_flood_is_throttled(pool: PgPool) {
|
||||
// notify still accepts an unsigned known-peer notification (rolling-upgrade
|
||||
// compat), but a flood from one IP is now braked. brake limit 1: first
|
||||
// enqueues (200), second from the same IP → 429.
|
||||
let mut state = test_state(pool).await;
|
||||
state.peer_write_rate_limiter = RateLimiter::new(1, Duration::from_secs(3600));
|
||||
state.push_limiter_trust = TrustedProxy::None;
|
||||
let peer_did = seed_peer(&state).await;
|
||||
let body = NOTIFY_BODY.replace("PEER_DID", &peer_did);
|
||||
let router = crate::server::build_router(state);
|
||||
let first = router
|
||||
.clone()
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/sync/notify",
|
||||
&body,
|
||||
"203.0.113.8:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(first.status(), StatusCode::OK);
|
||||
let second = router
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/sync/notify",
|
||||
&body,
|
||||
"203.0.113.8:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(second.status(), StatusCode::TOO_MANY_REQUESTS);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_notify_distinct_ips_are_not_collaterally_throttled(pool: PgPool) {
|
||||
// must-not-over-throttle: per-IP keying means one peer's volume does not
|
||||
// throttle another. brake limit 1, two DIFFERENT source IPs → both 200.
|
||||
let mut state = test_state(pool).await;
|
||||
state.peer_write_rate_limiter = RateLimiter::new(1, Duration::from_secs(3600));
|
||||
state.push_limiter_trust = TrustedProxy::None;
|
||||
let peer_did = seed_peer(&state).await;
|
||||
let body = NOTIFY_BODY.replace("PEER_DID", &peer_did);
|
||||
let router = crate::server::build_router(state);
|
||||
for ip in ["203.0.113.20:5000", "203.0.113.21:5000"] {
|
||||
let resp = router
|
||||
.clone()
|
||||
.oneshot(unsigned_post("/api/v1/sync/notify", &body, ip))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
StatusCode::OK,
|
||||
"distinct IP {ip} must not be throttled"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn notify_flood_does_not_exhaust_trigger_bucket(pool: PgPool) {
|
||||
// Separate buckets: draining peer_write via an unsigned notify flood must
|
||||
// NOT throttle the signed trigger caller from the same IP. After the notify
|
||||
// bucket is spent, an unsigned trigger from that IP hits its own (unspent)
|
||||
// bucket and is rejected by the SIGNATURE gate (401), not the brake (429).
|
||||
let mut state = test_state(pool).await;
|
||||
state.peer_write_rate_limiter = RateLimiter::new(1, Duration::from_secs(3600));
|
||||
state.sync_trigger_rate_limiter = RateLimiter::new(60, Duration::from_secs(3600));
|
||||
state.push_limiter_trust = TrustedProxy::None;
|
||||
let peer_did = seed_peer(&state).await;
|
||||
let body = NOTIFY_BODY.replace("PEER_DID", &peer_did);
|
||||
let router = crate::server::build_router(state);
|
||||
let ip = "203.0.113.9:5000";
|
||||
assert_eq!(
|
||||
router
|
||||
.clone()
|
||||
.oneshot(unsigned_post("/api/v1/sync/notify", &body, ip))
|
||||
.await
|
||||
.unwrap()
|
||||
.status(),
|
||||
StatusCode::OK
|
||||
);
|
||||
assert_eq!(
|
||||
router
|
||||
.clone()
|
||||
.oneshot(unsigned_post("/api/v1/sync/notify", &body, ip))
|
||||
.await
|
||||
.unwrap()
|
||||
.status(),
|
||||
StatusCode::TOO_MANY_REQUESTS,
|
||||
"peer_write bucket should now be exhausted for this IP"
|
||||
);
|
||||
let trigger = router
|
||||
.oneshot(unsigned_post("/api/v1/sync/trigger", "{}", ip))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
trigger.status(),
|
||||
StatusCode::UNAUTHORIZED,
|
||||
"trigger must hit its own bucket (401 from the sig gate), not the drained peer_write bucket (429)"
|
||||
);
|
||||
}
|
||||
|
||||
// ── notify: repo slug validation (#272) ───────────────────────────────────
|
||||
//
|
||||
// An unsigned caller who has announced their own DID is a "known peer", so
|
||||
// the slug they send reaches the sync worker's path join. `a//tmp/probe`
|
||||
// resolved to /tmp/probe.git, outside repos_dir entirely. notify must reject
|
||||
// anything that is not a well-formed owner/name slug before it is queued.
|
||||
|
||||
/// Every slug shape the boundary must refuse. `a//tmp/gitlawb-probe` is the
|
||||
/// verified escape; the rest are the traversal and empty-half neighbours.
|
||||
const MALFORMED_SLUGS: [&str; 9] = [
|
||||
"a//tmp/gitlawb-probe",
|
||||
"../hello",
|
||||
"./hello",
|
||||
"../../etc/evil",
|
||||
"a/../../x",
|
||||
"..",
|
||||
"demo",
|
||||
"/hello",
|
||||
"z6Mkfoo/",
|
||||
];
|
||||
|
||||
fn notify_body(repo: &str, peer_did: &str) -> String {
|
||||
serde_json::json!({
|
||||
"repo": repo,
|
||||
"ref_name": "refs/heads/main",
|
||||
"new_sha": "0000000000000000000000000000000000000000",
|
||||
"node_did": peer_did,
|
||||
})
|
||||
.to_string()
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_notify_rejects_malformed_repo_slugs(pool: PgPool) {
|
||||
let state = test_state(pool).await;
|
||||
let db = state.db.clone();
|
||||
let peer_did = seed_peer(&state).await;
|
||||
let router = crate::server::build_router(state);
|
||||
for (i, slug) in MALFORMED_SLUGS.iter().enumerate() {
|
||||
// Distinct source IPs so the per-IP brake never masks the 400.
|
||||
let ip = format!("198.51.100.{}:5000", i + 1);
|
||||
let resp = router
|
||||
.clone()
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/sync/notify",
|
||||
¬ify_body(slug, &peer_did),
|
||||
&ip,
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
StatusCode::BAD_REQUEST,
|
||||
"slug {slug:?} must be rejected"
|
||||
);
|
||||
}
|
||||
let queued = db.dequeue_pending_syncs(100).await.unwrap();
|
||||
assert!(
|
||||
queued.is_empty(),
|
||||
"no malformed slug may be queued, got {:?}",
|
||||
queued.iter().map(|q| &q.repo).collect::<Vec<_>>()
|
||||
);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_notify_rejection_body_names_field_not_path(pool: PgPool) {
|
||||
// R3: the client learns which field was bad, never where repos live on
|
||||
// disk. A message carrying the resolved path would hand an unsigned
|
||||
// caller the server's layout.
|
||||
let state = test_state(pool).await;
|
||||
let repos_dir = state.config.repos_dir.display().to_string();
|
||||
let peer_did = seed_peer(&state).await;
|
||||
let router = crate::server::build_router(state);
|
||||
let resp = router
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/sync/notify",
|
||||
¬ify_body("a//tmp/gitlawb-probe", &peer_did),
|
||||
"198.51.100.20:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), StatusCode::BAD_REQUEST);
|
||||
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
|
||||
.await
|
||||
.unwrap();
|
||||
let body = String::from_utf8(bytes.to_vec()).unwrap();
|
||||
assert!(body.contains("repo"), "body must name the field: {body}");
|
||||
assert!(
|
||||
!body.contains(&repos_dir),
|
||||
"body must not leak repos_dir ({repos_dir}): {body}"
|
||||
);
|
||||
for trimmed in repos_dir.trim_start_matches("./").split('/') {
|
||||
assert!(
|
||||
trimmed.is_empty() || !body.contains(trimmed),
|
||||
"body must not leak a repos_dir segment ({trimmed}): {body}"
|
||||
);
|
||||
}
|
||||
// A rooted path is a leading '/' with something after it. A bare quoted
|
||||
// '/' is the separator the message is allowed to talk about.
|
||||
assert!(
|
||||
!body
|
||||
.split(|c: char| c.is_whitespace() || c == '"' || c == '\'')
|
||||
.any(|tok| tok.starts_with('/') && tok.len() > 1),
|
||||
"body must not contain a rooted filesystem path: {body}"
|
||||
);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_notify_rejection_writes_no_ref_update(pool: PgPool) {
|
||||
// The second half of R1: the ref-update feed row sits after enqueue_sync,
|
||||
// so the early return must skip it too. Asserted, not argued.
|
||||
let state = test_state(pool.clone()).await;
|
||||
let peer_did = seed_peer(&state).await;
|
||||
let router = crate::server::build_router(state);
|
||||
let resp = router
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/sync/notify",
|
||||
¬ify_body("a//tmp/gitlawb-probe", &peer_did),
|
||||
"198.51.100.21:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), StatusCode::BAD_REQUEST);
|
||||
let count: i64 = sqlx::query_scalar("SELECT COUNT(*) FROM received_ref_updates")
|
||||
.fetch_one(&pool)
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
count, 0,
|
||||
"a rejected notify must not seed the ref-update feed"
|
||||
);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_notify_accepts_valid_slug_and_records_ref_update(pool: PgPool) {
|
||||
// must-not-break, and the control that keeps the two negative assertions
|
||||
// above from being vacuous: a well-formed slug still queues and still
|
||||
// writes its ref-update row.
|
||||
let state = test_state(pool.clone()).await;
|
||||
let db = state.db.clone();
|
||||
let peer_did = seed_peer(&state).await;
|
||||
let router = crate::server::build_router(state);
|
||||
let resp = router
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/sync/notify",
|
||||
¬ify_body("z6Mkfoo/hello", &peer_did),
|
||||
"198.51.100.22:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), StatusCode::OK);
|
||||
let queued = db.dequeue_pending_syncs(100).await.unwrap();
|
||||
assert_eq!(queued.len(), 1);
|
||||
assert_eq!(queued[0].repo, "z6Mkfoo/hello");
|
||||
let count: i64 =
|
||||
sqlx::query_scalar("SELECT COUNT(*) FROM received_ref_updates WHERE repo = $1")
|
||||
.bind("z6Mkfoo/hello")
|
||||
.fetch_one(&pool)
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
count, 1,
|
||||
"the valid path must still write the ref-update row"
|
||||
);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_notify_unknown_peer_wins_over_malformed_slug(pool: PgPool) {
|
||||
// Ordering: the slug check sits after the peer gate, so an unknown peer
|
||||
// still gets the unknown-peer message rather than a slug complaint.
|
||||
let state = test_state(pool).await;
|
||||
let stranger = Keypair::generate().did().to_string();
|
||||
let router = crate::server::build_router(state);
|
||||
let resp = router
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/sync/notify",
|
||||
¬ify_body("a//tmp/gitlawb-probe", &stranger),
|
||||
"198.51.100.23:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), StatusCode::BAD_REQUEST);
|
||||
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
|
||||
.await
|
||||
.unwrap();
|
||||
let body = String::from_utf8(bytes.to_vec()).unwrap();
|
||||
assert!(
|
||||
body.contains("unknown peer DID"),
|
||||
"peer gate must still fire first: {body}"
|
||||
);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn unsigned_announce_then_notify_cannot_queue_a_repos_dir_escape(pool: PgPool) {
|
||||
// The reachability case for #272, committed in its attack form. Two
|
||||
// unsigned requests through the shipped router, no signature and no
|
||||
// config change: announce the attacker's own DID (which is what makes
|
||||
// them a "known peer"), then notify with `a/<abs>/gitlawb-probe`. That
|
||||
// slug used to reach PathBuf::join in the sync worker, where the
|
||||
// absolute second component discarded repos_dir and planted a mirror at
|
||||
// /<abs>/gitlawb-probe.git. The notify must now be refused outright.
|
||||
//
|
||||
// This has to run over crate::server::build_router rather than a
|
||||
// directly mounted handler: the point of the test is that the default
|
||||
// layer stack (optional_signature, not require_signature) leaves the
|
||||
// route open, so mounting the handler alone would assert nothing about
|
||||
// reachability.
|
||||
let state = test_state(pool).await;
|
||||
let db = state.db.clone();
|
||||
let attacker = Keypair::generate().did().to_string();
|
||||
let router = crate::server::build_router(state);
|
||||
|
||||
let announce =
|
||||
format!(r#"{{"did":"{attacker}","http_url":"https://attacker.example.com"}}"#);
|
||||
let resp = router
|
||||
.clone()
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/peers/announce",
|
||||
&announce,
|
||||
"198.51.100.40:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
// Asserted, not assumed: this plan does not change announce, and the
|
||||
// whole attack rests on an unsigned announce still succeeding.
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
StatusCode::OK,
|
||||
"unsigned announce still admits an attacker-generated DID"
|
||||
);
|
||||
|
||||
let outside = tempfile::TempDir::new().unwrap();
|
||||
let escape_dir = outside.path().join("gitlawb-probe");
|
||||
let slug = format!("a/{}", escape_dir.display());
|
||||
let resp = router
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/sync/notify",
|
||||
¬ify_body(&slug, &attacker),
|
||||
"198.51.100.41:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
StatusCode::BAD_REQUEST,
|
||||
"notify must refuse the escaping slug {slug:?}"
|
||||
);
|
||||
|
||||
let queued = db.dequeue_pending_syncs(100).await.unwrap();
|
||||
assert!(
|
||||
queued.is_empty(),
|
||||
"sync_queue must stay empty, got {:?}",
|
||||
queued.iter().map(|q| &q.repo).collect::<Vec<_>>()
|
||||
);
|
||||
assert!(
|
||||
!escape_dir.with_extension("git").exists(),
|
||||
"nothing may be written at the escape target"
|
||||
);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn announce_still_accepts_unsigned_in_default_mode(pool: PgPool) {
|
||||
// must-not-over-reach: adding the brake must not tighten announce's
|
||||
// rolling-upgrade behavior — an unsigned announce with a public URL still
|
||||
// succeeds (it only gains the brake, which a single request is under).
|
||||
let state = test_state(pool).await;
|
||||
let did = Keypair::generate().did().to_string();
|
||||
let body = format!(r#"{{"did":"{did}","http_url":"https://peer.example.com"}}"#);
|
||||
let router = crate::server::build_router(state);
|
||||
let resp = router
|
||||
.oneshot(unsigned_post(
|
||||
"/api/v1/peers/announce",
|
||||
&body,
|
||||
"203.0.113.10:5000",
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), StatusCode::OK);
|
||||
}
|
||||
|
||||
// Build a request carrying a REAL RFC 9421 signature (not just an injected
|
||||
// extension), so it passes require_signature on the full production router.
|
||||
fn real_signed_trigger(peer: &str) -> Request<Body> {
|
||||
let kp = Keypair::generate();
|
||||
let body = b"{}";
|
||||
let s = sign_request(&kp, "POST", "/api/v1/sync/trigger", body);
|
||||
let mut req = Request::builder()
|
||||
.method(Method::POST)
|
||||
.uri("/api/v1/sync/trigger")
|
||||
.header(header::CONTENT_TYPE, "application/json")
|
||||
.header("content-digest", s.content_digest)
|
||||
.header("signature-input", s.signature_input)
|
||||
.header("signature", s.signature)
|
||||
.body(Body::from(body.to_vec()))
|
||||
.unwrap();
|
||||
req.extensions_mut()
|
||||
.insert(ConnectInfo(peer.parse::<SocketAddr>().unwrap()));
|
||||
req
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_trigger_admits_real_signature_through_full_router(pool: PgPool) {
|
||||
// The positive path through the REAL gate: a validly-signed trigger passes
|
||||
// require_signature on the full router and reaches the handler (no peers
|
||||
// seeded → 200), in BOTH config modes.
|
||||
let state = test_state(pool.clone()).await;
|
||||
let resp = crate::server::build_router(state)
|
||||
.oneshot(real_signed_trigger("203.0.113.30:5000"))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
StatusCode::OK,
|
||||
"a real signature must reach the handler (default mode)"
|
||||
);
|
||||
|
||||
let mut state = test_state(pool).await;
|
||||
require_signed_peer_writes(&mut state);
|
||||
let resp = crate::server::build_router(state)
|
||||
.oneshot(real_signed_trigger("203.0.113.30:5001"))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
StatusCode::OK,
|
||||
"a real signature must reach the handler (signed-writes mode)"
|
||||
);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn announce_flood_is_throttled(pool: PgPool) {
|
||||
// The peer_write brake covers /peers/announce too (co-benefit): limit 1,
|
||||
// first unsigned announce from an IP is 200, the second from that IP 429.
|
||||
let mut state = test_state(pool).await;
|
||||
state.peer_write_rate_limiter = RateLimiter::new(1, Duration::from_secs(3600));
|
||||
state.push_limiter_trust = TrustedProxy::None;
|
||||
let did = Keypair::generate().did().to_string();
|
||||
let body = format!(r#"{{"did":"{did}","http_url":"https://peer.example.com"}}"#);
|
||||
let router = crate::server::build_router(state);
|
||||
let ip = "203.0.113.31:5000";
|
||||
assert_eq!(
|
||||
router
|
||||
.clone()
|
||||
.oneshot(unsigned_post("/api/v1/peers/announce", &body, ip))
|
||||
.await
|
||||
.unwrap()
|
||||
.status(),
|
||||
StatusCode::OK
|
||||
);
|
||||
assert_eq!(
|
||||
router
|
||||
.oneshot(unsigned_post("/api/v1/peers/announce", &body, ip))
|
||||
.await
|
||||
.unwrap()
|
||||
.status(),
|
||||
StatusCode::TOO_MANY_REQUESTS,
|
||||
"announce must be braked by the peer_write limiter"
|
||||
);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn sync_trigger_429_body_is_generic_not_push(pool: PgPool) {
|
||||
// The shared 429 middleware now serves the sync routes, so its body must
|
||||
// not claim "push" (RED before the message was genericized).
|
||||
let mut state = test_state(pool).await;
|
||||
state.sync_trigger_rate_limiter = RateLimiter::new(1, Duration::from_secs(3600));
|
||||
state.push_limiter_trust = TrustedProxy::None;
|
||||
let peer = "203.0.113.32:5000";
|
||||
assert!(
|
||||
state
|
||||
.sync_trigger_rate_limiter
|
||||
.check(&peer.parse::<SocketAddr>().unwrap().ip().to_string())
|
||||
.await
|
||||
);
|
||||
let router = crate::server::build_router(state);
|
||||
let resp = router
|
||||
.oneshot(unsigned_post("/api/v1/sync/trigger", "{}", peer))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), StatusCode::TOO_MANY_REQUESTS);
|
||||
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
|
||||
.await
|
||||
.unwrap();
|
||||
let s = String::from_utf8_lossy(&bytes);
|
||||
assert!(s.contains("rate limit exceeded"), "429 body: {s:?}");
|
||||
assert!(
|
||||
!s.contains("push"),
|
||||
"a 429 on a sync route must not say 'push': {s:?}"
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -98,7 +98,7 @@ pub async fn set_profile(
|
||||
&state.http_client,
|
||||
&state.config.pinata_upload_url,
|
||||
&state.config.pinata_jwt,
|
||||
&format!("profile-{}", &did),
|
||||
&format!("profile-{}", did),
|
||||
&profile_json,
|
||||
)
|
||||
.await
|
||||
|
||||
@@ -79,12 +79,14 @@ pub async fn unprotect_branch(
|
||||
pub async fn list_protected_branches(
|
||||
State(state): State<AppState>,
|
||||
Path((owner, repo)): Path<(String, String)>,
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
) -> Result<Json<serde_json::Value>> {
|
||||
let record = state
|
||||
.db
|
||||
.get_repo(&owner, &repo)
|
||||
.await?
|
||||
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
|
||||
// Read-visibility-gated (INV-2 root listing): a public repo's protected
|
||||
// branches stay anonymously listable; a private repo's branch names are
|
||||
// hidden (404) from anyone who cannot read it at the root.
|
||||
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
|
||||
let (record, _rules) =
|
||||
crate::api::authorize_repo_read(&state, &owner, &repo, caller, "/").await?;
|
||||
|
||||
let branches = state.db.list_protected_branches(&record.id).await?;
|
||||
|
||||
|
||||
@@ -113,16 +113,17 @@ pub async fn unregister_replica(
|
||||
}
|
||||
|
||||
/// GET /api/v1/repos/:owner/:repo/replicas
|
||||
/// Public — returns the list of replicas (DID + URL + registration timestamp).
|
||||
/// Read-visibility-gated: a PUBLIC repo's replica list stays anonymously
|
||||
/// listable (mirror-discovery), but a PRIVATE repo's replica URLs are hidden
|
||||
/// (404) from anyone who cannot read the repo at its root.
|
||||
pub async fn list_replicas(
|
||||
State(state): State<AppState>,
|
||||
Path((owner, repo)): Path<(String, String)>,
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
) -> Result<Json<serde_json::Value>> {
|
||||
let record = state
|
||||
.db
|
||||
.get_repo(&owner, &repo)
|
||||
.await?
|
||||
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
|
||||
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
|
||||
let (record, _rules) =
|
||||
crate::api::authorize_repo_read(&state, &owner, &repo, caller, "/").await?;
|
||||
|
||||
let replicas = state.db.list_replicas(&record.id).await?;
|
||||
|
||||
|
||||
@@ -211,7 +211,12 @@ pub async fn create_repo(
|
||||
.repo_store
|
||||
.init(&owner_did, &req.name)
|
||||
.await
|
||||
.map_err(|e| AppError::Git(e.to_string()))?;
|
||||
.map_err(|e| {
|
||||
// `{:#}` walks the anyhow chain to the leaf cause; the other git
|
||||
// handlers log their failures, this one didn't.
|
||||
tracing::error!(owner = %owner_did, repo = %req.name, err = %format!("{e:#}"), "repo create failed");
|
||||
AppError::Git(e.to_string())
|
||||
})?;
|
||||
|
||||
let now = Utc::now();
|
||||
let record = crate::db::RepoRecord {
|
||||
@@ -482,14 +487,27 @@ pub async fn get_tree(
|
||||
|
||||
// ── Git smart HTTP endpoints ──────────────────────────────────────────────
|
||||
|
||||
/// GET /:owner/:repo.git/info/refs?service=git-upload-pack
|
||||
fn smart_http_repo_name(repo: &str) -> Result<&str> {
|
||||
// Strip at most one ".git" suffix: trim_end_matches strips repeatedly,
|
||||
// which would misdirect a repo literally named "foo.git" (creatable via
|
||||
// the peer mirror path, which skips API name validation) to repo "foo".
|
||||
let name = repo.strip_suffix(".git").unwrap_or(repo);
|
||||
if name.is_empty() {
|
||||
return Err(AppError::BadRequest("missing repository name".into()));
|
||||
}
|
||||
Ok(name)
|
||||
}
|
||||
|
||||
/// GET /:owner/:repo.git/info/refs?service=git-upload-pack|git-receive-pack
|
||||
pub async fn git_info_refs(
|
||||
State(state): State<AppState>,
|
||||
Path((owner, repo)): Path<(String, String)>,
|
||||
Query(query): Query<InfoRefsQuery>,
|
||||
crate::rate_limit::PeerAddr(peer): crate::rate_limit::PeerAddr,
|
||||
headers: axum::http::HeaderMap,
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
) -> Result<Response> {
|
||||
let name = repo.trim_end_matches(".git");
|
||||
let name = smart_http_repo_name(&repo)?;
|
||||
tracing::info!(owner = %owner, repo = %name, "info/refs request");
|
||||
let record = state
|
||||
.db
|
||||
@@ -508,10 +526,14 @@ pub async fn git_info_refs(
|
||||
.ok_or_else(|| AppError::BadRequest("missing ?service= parameter".into()))?;
|
||||
tracing::debug!(service = %service, repo = %name, "info/refs service");
|
||||
|
||||
// Enforce read (clone/fetch) visibility. The push advertisement
|
||||
// (service=git-receive-pack) is authorized separately on the
|
||||
// git-receive-pack POST, so leave it untouched here.
|
||||
if service == "git-upload-pack" {
|
||||
// Enforce read visibility on the ref advertisement, for BOTH services. The
|
||||
// upload-pack (clone/fetch) and receive-pack (push) advertisements expose the
|
||||
// same ref metadata (branch/tag names and commit tips), so a private repo's
|
||||
// advertisement must be withheld from a non-reader regardless of which service
|
||||
// is requested. The push itself stays separately owner-gated on the
|
||||
// git-receive-pack POST; push access implies read access here, so a
|
||||
// legitimate pusher (the owner) always clears this gate.
|
||||
{
|
||||
let rules = state.db.list_visibility_rules(&record.id).await?;
|
||||
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
|
||||
// Subtree (mode B) rules do not gate the advertisement: refs expose commit
|
||||
@@ -519,11 +541,28 @@ pub async fn git_info_refs(
|
||||
if visibility_check(&rules, record.is_public, &record.owner_did, caller, "/")
|
||||
== Decision::Deny
|
||||
{
|
||||
tracing::debug!(repo = %name, caller = ?caller, "info/refs read denied by visibility");
|
||||
tracing::debug!(repo = %name, caller = ?caller, service = %service, "info/refs read denied by visibility");
|
||||
return Err(AppError::RepoNotFound(format!("{owner}/{name}")));
|
||||
}
|
||||
}
|
||||
|
||||
// Push flood brake on the advertisement phase. A push always hits this
|
||||
// GET first, and for receive-pack it forces a fresh Tigris download below;
|
||||
// throttling only the receive-pack POST would leave the expensive
|
||||
// fresh-acquire reachable unauthenticated and unlimited. Applied before the
|
||||
// acquire so a rejected request does no Tigris work. Same per-IP limiter and
|
||||
// trusted-proxy policy as the POST middleware (shared buckets).
|
||||
if service == "git-receive-pack" {
|
||||
if let Some(key) = crate::rate_limit::client_key(&headers, peer, state.push_limiter_trust) {
|
||||
if !state.push_rate_limiter.check(&key).await {
|
||||
tracing::warn!(repo = %name, key = %key, "receive-pack advertisement rate limited");
|
||||
return Err(AppError::TooManyRequests(
|
||||
"push rate limit exceeded — try again later".into(),
|
||||
));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// For receive-pack (push), download the latest from Tigris so the client
|
||||
// sees the same refs that acquire_write() will operate on.
|
||||
let disk_path = if service == "git-receive-pack" {
|
||||
@@ -550,6 +589,26 @@ pub async fn git_info_refs(
|
||||
})
|
||||
}
|
||||
|
||||
/// Map an error from a `smart_http` git service call to the right `AppError`:
|
||||
/// [`smart_http::GitServiceTimeout`] to 504, a malformed client request to 400,
|
||||
/// anything else to a 500 git error. Pure (no logging) so it is unit-testable;
|
||||
/// callers add their own tracing.
|
||||
fn git_service_app_error(err: &anyhow::Error) -> AppError {
|
||||
if err
|
||||
.downcast_ref::<smart_http::GitServiceTimeout>()
|
||||
.is_some()
|
||||
{
|
||||
AppError::Timeout("git service timed out".into())
|
||||
} else {
|
||||
let msg = err.to_string();
|
||||
if msg.contains("bad line length") || msg.contains("protocol error") {
|
||||
AppError::BadRequest(msg)
|
||||
} else {
|
||||
AppError::Git(msg)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// POST /:owner/:repo.git/git-upload-pack
|
||||
pub async fn git_upload_pack(
|
||||
State(state): State<AppState>,
|
||||
@@ -557,7 +616,7 @@ pub async fn git_upload_pack(
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
body: Bytes,
|
||||
) -> Result<Response> {
|
||||
let name = repo.trim_end_matches(".git");
|
||||
let name = smart_http_repo_name(&repo)?;
|
||||
let record = state
|
||||
.db
|
||||
.get_repo(&owner, name)
|
||||
@@ -587,8 +646,9 @@ pub async fn git_upload_pack(
|
||||
// No path-scoped rule can withhold an individual blob, and the whole-repo
|
||||
// "/" gate above already enforced repo-level access. Skip the per-blob
|
||||
// withheld walk and serve the pack directly.
|
||||
let git_timeout = std::time::Duration::from_secs(state.config.git_service_timeout_secs);
|
||||
let resp = if !visibility_pack::has_path_scoped_rule(&rules) {
|
||||
smart_http::upload_pack(&disk_path, body).await
|
||||
smart_http::upload_pack(&disk_path, body, git_timeout).await
|
||||
} else {
|
||||
// withheld_blob_oids walks every ref with blocking `git ls-tree`; keep
|
||||
// that off the async worker thread.
|
||||
@@ -613,21 +673,22 @@ pub async fn git_upload_pack(
|
||||
};
|
||||
|
||||
if withheld.is_empty() {
|
||||
smart_http::upload_pack(&disk_path, body).await
|
||||
smart_http::upload_pack(&disk_path, body, git_timeout).await
|
||||
} else {
|
||||
tracing::info!(repo = %name, caller = ?caller, withheld = withheld.len(), "serving filtered pack");
|
||||
smart_http::upload_pack_excluding(&disk_path, body, &withheld).await
|
||||
}
|
||||
}
|
||||
.map_err(|e| {
|
||||
let msg = e.to_string();
|
||||
if msg.contains("bad line length") || msg.contains("protocol error") {
|
||||
tracing::warn!(repo = %name, err = %msg, "git-upload-pack: bad client request");
|
||||
AppError::BadRequest(msg)
|
||||
} else {
|
||||
tracing::error!(repo = %name, err = %msg, "git-upload-pack failed");
|
||||
AppError::Git(msg)
|
||||
let app = git_service_app_error(&e);
|
||||
match &app {
|
||||
AppError::Timeout(_) => tracing::warn!(repo = %name, "git-upload-pack timed out"),
|
||||
AppError::BadRequest(msg) => {
|
||||
tracing::warn!(repo = %name, err = %msg, "git-upload-pack: bad client request")
|
||||
}
|
||||
_ => tracing::error!(repo = %name, err = %e, "git-upload-pack failed"),
|
||||
}
|
||||
app
|
||||
})?;
|
||||
crate::metrics::record_fetch(&format!("{owner}/{name}"));
|
||||
crate::metrics::observe_pack_size(body_len as f64);
|
||||
@@ -711,6 +772,7 @@ async fn notify_peer_of_ref(
|
||||
new_sha: &str,
|
||||
node_did: &str,
|
||||
pusher_did: &str,
|
||||
owner_did: &str,
|
||||
) {
|
||||
let body = serde_json::json!({
|
||||
"repo": repo_slug,
|
||||
@@ -720,6 +782,7 @@ async fn notify_peer_of_ref(
|
||||
"pusher_did": pusher_did,
|
||||
"old_sha": old_sha,
|
||||
"timestamp": chrono::Utc::now().to_rfc3339(),
|
||||
"owner_did": owner_did,
|
||||
});
|
||||
let body_bytes = match serde_json::to_vec(&body) {
|
||||
Ok(bytes) => bytes,
|
||||
@@ -767,6 +830,7 @@ async fn notify_peer_of_refs(
|
||||
ref_updates: &[(String, String, String)],
|
||||
node_did: &str,
|
||||
pusher_did: &str,
|
||||
owner_did: &str,
|
||||
) {
|
||||
for (ref_name, old_sha, new_sha) in ref_updates {
|
||||
notify_peer_of_ref(
|
||||
@@ -780,6 +844,7 @@ async fn notify_peer_of_refs(
|
||||
new_sha,
|
||||
node_did,
|
||||
pusher_did,
|
||||
owner_did,
|
||||
)
|
||||
.await;
|
||||
}
|
||||
@@ -792,7 +857,7 @@ pub async fn git_receive_pack(
|
||||
Extension(auth): Extension<AuthenticatedDid>,
|
||||
body: Bytes,
|
||||
) -> Result<Response> {
|
||||
let name = repo.trim_end_matches(".git");
|
||||
let name = smart_http_repo_name(&repo)?;
|
||||
tracing::info!(owner = %owner, repo = %name, "receive-pack request");
|
||||
let record = state
|
||||
.db
|
||||
@@ -874,7 +939,8 @@ pub async fn git_receive_pack(
|
||||
let disk_path = guard.path().to_path_buf();
|
||||
tracing::debug!(repo = %name, path = %disk_path.display(), "running git receive-pack");
|
||||
let body_len = body.len();
|
||||
let receive_result = smart_http::receive_pack(&disk_path, body).await;
|
||||
let git_timeout = std::time::Duration::from_secs(state.config.git_service_timeout_secs);
|
||||
let receive_result = smart_http::receive_pack(&disk_path, body, git_timeout).await;
|
||||
|
||||
// Always release the advisory lock — even on error — to prevent stale locks
|
||||
// from blocking subsequent pushes. Only upload to Tigris when the push
|
||||
@@ -882,8 +948,15 @@ pub async fn git_receive_pack(
|
||||
guard.release(receive_result.is_ok()).await;
|
||||
|
||||
let result = receive_result.map_err(|e| {
|
||||
tracing::error!(repo = %name, err = %e, "git receive-pack failed");
|
||||
AppError::Git(e.to_string())
|
||||
let app = git_service_app_error(&e);
|
||||
match &app {
|
||||
AppError::Timeout(_) => tracing::warn!(repo = %name, "git receive-pack timed out"),
|
||||
AppError::BadRequest(msg) => {
|
||||
tracing::warn!(repo = %name, err = %msg, "git receive-pack: bad client request")
|
||||
}
|
||||
_ => tracing::error!(repo = %name, err = %e, "git receive-pack failed"),
|
||||
}
|
||||
app
|
||||
})?;
|
||||
|
||||
// Update the repo's updated_at timestamp after a successful push
|
||||
@@ -945,11 +1018,7 @@ pub async fn git_receive_pack(
|
||||
.as_deref()
|
||||
.unwrap_or("http://127.0.0.1:7545")
|
||||
.trim_end_matches('/');
|
||||
let owner_short = record
|
||||
.owner_did
|
||||
.split(':')
|
||||
.next_back()
|
||||
.unwrap_or(&record.owner_did);
|
||||
let owner_short = crate::db::normalize_owner_key(&record.owner_did);
|
||||
let clone_url = format!("{}/{}/{}.git", base_url, owner_short, record.name);
|
||||
|
||||
for update in &ref_updates {
|
||||
@@ -1096,7 +1165,7 @@ pub async fn git_receive_pack(
|
||||
// this push to Arweave, so the oid->cid index survives total
|
||||
// node loss. Best-effort; never fails the push.
|
||||
if !delta.is_empty() && !irys_url.is_empty() {
|
||||
let owner_short = owner_did.split(':').next_back().unwrap_or(&owner_did);
|
||||
let owner_short = crate::db::normalize_owner_key(&owner_did);
|
||||
let repo_slug = format!("{owner_short}/{repo_name}");
|
||||
let ts = chrono::Utc::now().to_rfc3339();
|
||||
let manifest = crate::arweave::EncryptedManifest {
|
||||
@@ -1141,11 +1210,7 @@ pub async fn git_receive_pack(
|
||||
let node_did_str = state.node_did.to_string();
|
||||
let repo_slug = format!(
|
||||
"{}/{}",
|
||||
record
|
||||
.owner_did
|
||||
.split(':')
|
||||
.next_back()
|
||||
.unwrap_or(&record.owner_did),
|
||||
crate::db::normalize_owner_key(&record.owner_did),
|
||||
record.name
|
||||
);
|
||||
let ref_updates_clone = ref_updates
|
||||
@@ -1200,6 +1265,7 @@ pub async fn git_receive_pack(
|
||||
node_did: node_did_str.clone(),
|
||||
pusher_did: pusher_did_clone.clone(),
|
||||
repo: repo_slug.clone(),
|
||||
owner_did: Some(record.owner_did.clone()),
|
||||
ref_name: ref_name.clone(),
|
||||
old_sha: old_sha.clone(),
|
||||
new_sha: new_sha.clone(),
|
||||
@@ -1213,17 +1279,27 @@ pub async fn git_receive_pack(
|
||||
}
|
||||
|
||||
// Broadcast ref update to GraphQL subscription listeners — one per ref.
|
||||
// Gated on `announce`: /graphql/ws is unauthenticated (mounted after
|
||||
// the optional_signature layer), and the subscription resolver has no
|
||||
// caller to gate against, so only publicly-readable ref updates may
|
||||
// reach anonymous subscribers. Mirrors the gossip (above) and Arweave
|
||||
// (below) sends, which are already `announce`-gated. Without this a
|
||||
// private-repo push would leak live ref metadata over the socket —
|
||||
// the subscription analog of #112/#114.
|
||||
let now_ts = chrono::Utc::now().to_rfc3339();
|
||||
for (ref_name, old_sha, new_sha) in &ref_updates_clone {
|
||||
let _ = ref_update_tx.send(crate::state::RefUpdateBroadcast {
|
||||
repo: repo_slug.clone(),
|
||||
ref_name: ref_name.clone(),
|
||||
old_sha: old_sha.clone(),
|
||||
new_sha: new_sha.clone(),
|
||||
pusher_did: pusher_did_clone.clone(),
|
||||
node_did: node_did_str.clone(),
|
||||
timestamp: now_ts.clone(),
|
||||
});
|
||||
if announce {
|
||||
for (ref_name, old_sha, new_sha) in &ref_updates_clone {
|
||||
let _ = ref_update_tx.send(crate::state::RefUpdateBroadcast {
|
||||
repo: repo_slug.clone(),
|
||||
ref_name: ref_name.clone(),
|
||||
old_sha: old_sha.clone(),
|
||||
new_sha: new_sha.clone(),
|
||||
pusher_did: pusher_did_clone.clone(),
|
||||
node_did: node_did_str.clone(),
|
||||
timestamp: now_ts.clone(),
|
||||
owner_did: record.owner_did.clone(),
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// Arweave permanent anchoring — fire for each ref update.
|
||||
@@ -1292,6 +1368,7 @@ pub async fn git_receive_pack(
|
||||
&ref_updates_clone,
|
||||
&node_did_str,
|
||||
&pusher_did_clone,
|
||||
&record.owner_did,
|
||||
)
|
||||
.await;
|
||||
}
|
||||
@@ -1474,7 +1551,7 @@ pub async fn fork_repo(
|
||||
}
|
||||
|
||||
// Check no name conflict under the forker's ownership
|
||||
let forker_short = forker_did.split(':').next_back().unwrap_or(&forker_did);
|
||||
let forker_short = crate::db::normalize_owner_key(&forker_did);
|
||||
if state.db.get_repo(forker_short, &fork_name).await?.is_some() {
|
||||
return Err(AppError::BadRequest(format!(
|
||||
"you already have a repo named {fork_name}"
|
||||
@@ -1630,13 +1707,17 @@ fn parse_ref_updates(body: &[u8]) -> Vec<RefUpdate> {
|
||||
}
|
||||
|
||||
// ── Helpers ───────────────────────────────────────────────────────────────
|
||||
//
|
||||
// For a non-key DID owner, `normalize_owner_key` returns the full DID, so
|
||||
// `clone_url` becomes `/did:gitlawb:z6.../repo.git`. That resolves through
|
||||
// `get_repo`, but the colon-bearing path segment would break the `sync.rs`
|
||||
// disk-path join (`owner_slug/repo`). Not reachable today (auth is
|
||||
// did:key-only), so this is a forward constraint to handle before non-key
|
||||
// ownership lands: the owner-first disk layout must either reject colons or
|
||||
// encode them.
|
||||
|
||||
fn to_response(record: &crate::db::RepoRecord, state: &AppState, star_count: i64) -> RepoResponse {
|
||||
let owner_short = record
|
||||
.owner_did
|
||||
.split(':')
|
||||
.next_back()
|
||||
.unwrap_or(&record.owner_did);
|
||||
let owner_short = crate::db::normalize_owner_key(&record.owner_did);
|
||||
|
||||
let base_url = state
|
||||
.config
|
||||
@@ -1762,6 +1843,32 @@ mod tests {
|
||||
const OWNER_SHORT: &str = "z6MkpTHR8VNsBxYAAWHut2Geadd9jSwuBV8xRoAnwWsdvktH";
|
||||
const STRANGER_DID: &str = "did:key:z6Mkffonly5tranger0000000000000000000000000000000";
|
||||
|
||||
#[test]
|
||||
fn git_service_app_error_classifies_timeout_bad_request_and_git() {
|
||||
// GitServiceTimeout carried through anyhow -> 504 Timeout.
|
||||
let timeout_err: anyhow::Error = smart_http::GitServiceTimeout.into();
|
||||
assert!(matches!(
|
||||
git_service_app_error(&timeout_err),
|
||||
AppError::Timeout(_)
|
||||
));
|
||||
// A malformed client request -> 400.
|
||||
let bad = anyhow::anyhow!("fatal: bad line length character: 0000");
|
||||
assert!(matches!(
|
||||
git_service_app_error(&bad),
|
||||
AppError::BadRequest(_)
|
||||
));
|
||||
// The `protocol error` marker (with no "bad line length" substring) also
|
||||
// -> 400, exercising the second arm of the classifier independently.
|
||||
let proto = anyhow::anyhow!("fatal: protocol error: unexpected flush packet");
|
||||
assert!(matches!(
|
||||
git_service_app_error(&proto),
|
||||
AppError::BadRequest(_)
|
||||
));
|
||||
// Anything else -> 500 git error.
|
||||
let other = anyhow::anyhow!("some other git failure");
|
||||
assert!(matches!(git_service_app_error(&other), AppError::Git(_)));
|
||||
}
|
||||
|
||||
fn repo_owned_by(owner_did: &str) -> crate::db::RepoRecord {
|
||||
let now = chrono::Utc::now();
|
||||
crate::db::RepoRecord {
|
||||
@@ -1779,6 +1886,32 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
/// `announce` is the single boolean that gates every network-facing emission
|
||||
/// of a push: gossip, Arweave anchoring, and the GraphQL subscription
|
||||
/// broadcast (the last one added in this change). It must be false for a repo
|
||||
/// the anonymous public cannot read, or the unauthenticated `/graphql/ws`
|
||||
/// subscription leaks live private-repo ref metadata. Pin both directions of
|
||||
/// the decision the broadcast now sits behind. No disk access: a non-announce
|
||||
/// repo returns early, and a public repo with no path-scoped rule skips the
|
||||
/// withheld walk.
|
||||
#[tokio::test]
|
||||
async fn replication_announce_false_for_private_true_for_public() {
|
||||
let dummy = std::path::PathBuf::from("/nonexistent");
|
||||
|
||||
// Private: no rules at all.
|
||||
let (announce, _) = replication_withheld_set(None, OWNER_DID, false, dummy.clone()).await;
|
||||
assert!(!announce, "private repo (no rules) must not announce");
|
||||
|
||||
// Private: empty rule set, is_public=false → still not listable at root.
|
||||
let (announce, _) =
|
||||
replication_withheld_set(Some(vec![]), OWNER_DID, false, dummy.clone()).await;
|
||||
assert!(!announce, "private repo (empty rules) must not announce");
|
||||
|
||||
// Public: empty rule set, is_public=true → listable at root, announces.
|
||||
let (announce, _) = replication_withheld_set(Some(vec![]), OWNER_DID, true, dummy).await;
|
||||
assert!(announce, "public repo must announce");
|
||||
}
|
||||
|
||||
/// A rejection must be a 403 Forbidden (authenticated but not authorized),
|
||||
/// not a 400 — some git/CI clients retry 400s.
|
||||
fn assert_forbidden(rejection: Option<AppError>) {
|
||||
@@ -1788,6 +1921,23 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn smart_http_repo_name_rejects_empty_after_git_suffix() {
|
||||
assert_eq!(smart_http_repo_name("demo.git").unwrap(), "demo");
|
||||
assert_eq!(smart_http_repo_name("demo").unwrap(), "demo");
|
||||
// Only one suffix is stripped: a repo literally named "demo.git"
|
||||
// stays addressable and never aliases to "demo".
|
||||
assert_eq!(smart_http_repo_name("demo.git.git").unwrap(), "demo.git");
|
||||
assert!(matches!(
|
||||
smart_http_repo_name(".git"),
|
||||
Err(AppError::BadRequest(_))
|
||||
));
|
||||
assert!(matches!(
|
||||
smart_http_repo_name(""),
|
||||
Err(AppError::BadRequest(_))
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn enforced_allows_owner_full_did() {
|
||||
let repo = repo_owned_by(OWNER_DID);
|
||||
@@ -2259,6 +2409,9 @@ mod tests {
|
||||
mockito::Matcher::PartialJsonString(format!(r#"{{"ref_name":"{ref_a}"}}"#)),
|
||||
mockito::Matcher::PartialJsonString(format!(r#"{{"old_sha":"{old_a}"}}"#)),
|
||||
mockito::Matcher::PartialJsonString(format!(r#"{{"new_sha":"{new_a}"}}"#)),
|
||||
mockito::Matcher::PartialJsonString(
|
||||
r#"{"owner_did":"did:key:zOwner"}"#.to_string(),
|
||||
),
|
||||
]))
|
||||
.with_status(200)
|
||||
.expect(1)
|
||||
@@ -2270,6 +2423,9 @@ mod tests {
|
||||
mockito::Matcher::PartialJsonString(format!(r#"{{"ref_name":"{ref_b}"}}"#)),
|
||||
mockito::Matcher::PartialJsonString(format!(r#"{{"old_sha":"{old_b}"}}"#)),
|
||||
mockito::Matcher::PartialJsonString(format!(r#"{{"new_sha":"{new_b}"}}"#)),
|
||||
mockito::Matcher::PartialJsonString(
|
||||
r#"{"owner_did":"did:key:zOwner"}"#.to_string(),
|
||||
),
|
||||
]))
|
||||
.with_status(200)
|
||||
.expect(1)
|
||||
@@ -2291,6 +2447,7 @@ mod tests {
|
||||
&ref_updates,
|
||||
"did:key:zNode",
|
||||
"did:key:zPusher",
|
||||
"did:key:zOwner",
|
||||
)
|
||||
.await;
|
||||
|
||||
@@ -2313,6 +2470,9 @@ mod tests {
|
||||
.match_body(mockito::Matcher::AllOf(vec![
|
||||
mockito::Matcher::PartialJsonString(format!(r#"{{"old_sha":"{zero}"}}"#)),
|
||||
mockito::Matcher::PartialJsonString(format!(r#"{{"new_sha":"{new_sha}"}}"#)),
|
||||
mockito::Matcher::PartialJsonString(
|
||||
r#"{"owner_did":"did:key:zOwner"}"#.to_string(),
|
||||
),
|
||||
]))
|
||||
.with_status(200)
|
||||
.expect(1)
|
||||
@@ -2335,9 +2495,152 @@ mod tests {
|
||||
&ref_updates,
|
||||
"did:key:zNode",
|
||||
"did:key:zPusher",
|
||||
"did:key:zOwner",
|
||||
)
|
||||
.await;
|
||||
|
||||
_mock.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn to_response_generates_correct_clone_url_slug() {
|
||||
let state = crate::test_support::test_state_lazy();
|
||||
let now = chrono::Utc::now();
|
||||
|
||||
// 1. did:key owner (should strip did:key: prefix)
|
||||
let repo_key = crate::db::RepoRecord {
|
||||
id: "uuid-1".into(),
|
||||
name: "my-repo".into(),
|
||||
owner_did: "did:key:z6Mkwbud".into(),
|
||||
description: None,
|
||||
is_public: true,
|
||||
default_branch: "main".into(),
|
||||
created_at: now,
|
||||
updated_at: now,
|
||||
disk_path: "/tmp/my-repo".into(),
|
||||
forked_from: None,
|
||||
machine_id: None,
|
||||
};
|
||||
let response_key = to_response(&repo_key, &state, 5);
|
||||
assert!(
|
||||
response_key.clone_url.contains("/z6Mkwbud/my-repo.git"),
|
||||
"clone_url should use the bare did:key ID. got: {}",
|
||||
response_key.clone_url
|
||||
);
|
||||
|
||||
// 2. did:gitlawb owner (non-key DID method, should NOT strip)
|
||||
let repo_non_key = crate::db::RepoRecord {
|
||||
id: "uuid-2".into(),
|
||||
name: "other-repo".into(),
|
||||
owner_did: "did:gitlawb:z6Mkwbud".into(),
|
||||
description: None,
|
||||
is_public: true,
|
||||
default_branch: "main".into(),
|
||||
created_at: now,
|
||||
updated_at: now,
|
||||
disk_path: "/tmp/other-repo".into(),
|
||||
forked_from: None,
|
||||
machine_id: None,
|
||||
};
|
||||
let response_non_key = to_response(&repo_non_key, &state, 10);
|
||||
assert!(
|
||||
response_non_key
|
||||
.clone_url
|
||||
.contains("/did:gitlawb:z6Mkwbud/other-repo.git"),
|
||||
"clone_url should preserve the full non-key owner DID. got: {}",
|
||||
response_non_key.clone_url
|
||||
);
|
||||
}
|
||||
|
||||
/// The receive-pack *advertisement* (`GET info/refs?service=git-receive-pack`)
|
||||
/// must be throttled by the per-IP push limiter BEFORE it does the fresh
|
||||
/// Tigris acquire — otherwise the flood brake on the POST is bypassable via
|
||||
/// the cheaper unauthenticated GET (PR #152 review P1). Pre-filling the
|
||||
/// bucket makes the assertion deterministic and keeps the test off the
|
||||
/// acquire path entirely.
|
||||
#[sqlx::test]
|
||||
async fn receive_pack_advertisement_is_rate_limited(pool: sqlx::PgPool) {
|
||||
use axum::body::Body;
|
||||
use axum::extract::ConnectInfo;
|
||||
use axum::http::{Method, Request, StatusCode};
|
||||
use std::net::SocketAddr;
|
||||
use std::time::Duration;
|
||||
use tower::ServiceExt;
|
||||
|
||||
let mut state = crate::test_support::test_state(pool).await;
|
||||
// Tiny limit, keyed on the socket peer (no trusted proxy).
|
||||
state.push_rate_limiter = crate::rate_limit::RateLimiter::new(1, Duration::from_secs(60));
|
||||
state.push_limiter_trust = crate::rate_limit::TrustedProxy::None;
|
||||
state
|
||||
.db
|
||||
.upsert_mirror_repo("z6advowner", "adv", "/tmp/adv", None, false)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let peer: SocketAddr = "203.0.113.55:6000".parse().unwrap();
|
||||
// Exhaust this peer's single-request budget up front.
|
||||
assert!(state.push_rate_limiter.check(&peer.ip().to_string()).await);
|
||||
|
||||
let router = crate::server::build_router(state);
|
||||
let mut req = Request::builder()
|
||||
.method(Method::GET)
|
||||
.uri("/z6advowner/adv/info/refs?service=git-receive-pack")
|
||||
.body(Body::empty())
|
||||
.unwrap();
|
||||
req.extensions_mut().insert(ConnectInfo(peer));
|
||||
|
||||
let status = router.oneshot(req).await.unwrap().status();
|
||||
assert_eq!(
|
||||
status,
|
||||
StatusCode::TOO_MANY_REQUESTS,
|
||||
"receive-pack advertisement must be throttled before the Tigris acquire"
|
||||
);
|
||||
}
|
||||
|
||||
/// Repo creation must be throttled by the per-IP creation limiter BEFORE
|
||||
/// signature verification — otherwise a DID farm (one throwaway did:key per
|
||||
/// repo, each carrying a valid but machine-solved iCaptcha proof) walks past
|
||||
/// the per-DID limiter and floods the network, as in the recurring spam-repo
|
||||
/// incidents. A 429 (not a 401) on an unsigned request from an exhausted IP
|
||||
/// proves the IP brake runs outermost, ahead of auth.
|
||||
#[sqlx::test]
|
||||
async fn repo_creation_is_rate_limited_by_ip(pool: sqlx::PgPool) {
|
||||
use axum::body::Body;
|
||||
use axum::extract::ConnectInfo;
|
||||
use axum::http::{Method, Request, StatusCode};
|
||||
use std::net::SocketAddr;
|
||||
use std::time::Duration;
|
||||
use tower::ServiceExt;
|
||||
|
||||
let mut state = crate::test_support::test_state(pool).await;
|
||||
// Tiny limit, keyed on the socket peer (no trusted proxy).
|
||||
state.create_ip_rate_limiter =
|
||||
crate::rate_limit::RateLimiter::new(1, Duration::from_secs(60));
|
||||
state.push_limiter_trust = crate::rate_limit::TrustedProxy::None;
|
||||
|
||||
let peer: SocketAddr = "203.0.113.77:7000".parse().unwrap();
|
||||
// Exhaust this peer's single-request budget up front.
|
||||
assert!(
|
||||
state
|
||||
.create_ip_rate_limiter
|
||||
.check(&peer.ip().to_string())
|
||||
.await
|
||||
);
|
||||
|
||||
let router = crate::server::build_router(state);
|
||||
let mut req = Request::builder()
|
||||
.method(Method::POST)
|
||||
.uri("/api/v1/repos")
|
||||
.header("content-type", "application/json")
|
||||
.body(Body::from(r#"{"name":"flood","is_public":true}"#))
|
||||
.unwrap();
|
||||
req.extensions_mut().insert(ConnectInfo(peer));
|
||||
|
||||
let status = router.oneshot(req).await.unwrap().status();
|
||||
assert_eq!(
|
||||
status,
|
||||
StatusCode::TOO_MANY_REQUESTS,
|
||||
"repo creation must be IP-throttled before signature verification"
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -2,14 +2,14 @@
|
||||
//!
|
||||
//! Any authenticated agent can star or unstar a repo.
|
||||
//! One agent = one star per repo (enforced by UNIQUE constraint in repo_stars).
|
||||
//! Star count is public — no auth required on GET.
|
||||
//! Star count is gated on repo read access.
|
||||
|
||||
use axum::extract::{Extension, Path, State};
|
||||
use axum::http::StatusCode;
|
||||
use axum::Json;
|
||||
|
||||
use crate::auth::AuthenticatedDid;
|
||||
use crate::error::{AppError, Result};
|
||||
use crate::error::Result;
|
||||
use crate::state::AppState;
|
||||
|
||||
/// PUT /api/v1/repos/:owner/:repo/star
|
||||
@@ -19,11 +19,8 @@ pub async fn star_repo(
|
||||
Extension(auth): Extension<AuthenticatedDid>,
|
||||
Path((owner, repo)): Path<(String, String)>,
|
||||
) -> Result<(StatusCode, Json<serde_json::Value>)> {
|
||||
let record = state
|
||||
.db
|
||||
.get_repo(&owner, &repo)
|
||||
.await?
|
||||
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
|
||||
let (record, _rules) =
|
||||
crate::api::authorize_repo_read(&state, &owner, &repo, Some(auth.0.as_str()), "/").await?;
|
||||
|
||||
let caller = &auth.0;
|
||||
let inserted = state.db.star_repo(&record.id, caller).await?;
|
||||
@@ -54,11 +51,8 @@ pub async fn unstar_repo(
|
||||
Extension(auth): Extension<AuthenticatedDid>,
|
||||
Path((owner, repo)): Path<(String, String)>,
|
||||
) -> Result<Json<serde_json::Value>> {
|
||||
let record = state
|
||||
.db
|
||||
.get_repo(&owner, &repo)
|
||||
.await?
|
||||
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
|
||||
let (record, _rules) =
|
||||
crate::api::authorize_repo_read(&state, &owner, &repo, Some(auth.0.as_str()), "/").await?;
|
||||
|
||||
let caller = &auth.0;
|
||||
state.db.unstar_repo(&record.id, caller).await?;
|
||||
@@ -74,16 +68,15 @@ pub async fn unstar_repo(
|
||||
}
|
||||
|
||||
/// GET /api/v1/repos/:owner/:repo/star
|
||||
/// Returns star count — unauthenticated.
|
||||
/// Returns star count for callers who can read the repo.
|
||||
pub async fn get_star_status(
|
||||
State(state): State<AppState>,
|
||||
Path((owner, repo)): Path<(String, String)>,
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
) -> Result<Json<serde_json::Value>> {
|
||||
let record = state
|
||||
.db
|
||||
.get_repo(&owner, &repo)
|
||||
.await?
|
||||
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
|
||||
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
|
||||
let (record, _rules) =
|
||||
crate::api::authorize_repo_read(&state, &owner, &repo, caller, "/").await?;
|
||||
|
||||
let count = state.db.count_stars(&record.id).await?;
|
||||
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
//! Webhook CRUD API.
|
||||
//!
|
||||
//! POST /api/v1/repos/:owner/:repo/hooks — create (auth required)
|
||||
//! GET /api/v1/repos/:owner/:repo/hooks — list
|
||||
//! DELETE /api/v1/repos/:owner/:repo/hooks/:id — delete (auth required)
|
||||
//! POST /api/v1/repos/:owner/:repo/hooks — create (owner only)
|
||||
//! GET /api/v1/repos/:owner/:repo/hooks — list (owner only; auth required)
|
||||
//! DELETE /api/v1/repos/:owner/:repo/hooks/:id — delete (owner only)
|
||||
|
||||
use axum::extract::{Extension, Path, State};
|
||||
use axum::http::StatusCode;
|
||||
@@ -73,12 +73,26 @@ pub async fn create_webhook(
|
||||
pub async fn list_webhooks(
|
||||
State(state): State<AppState>,
|
||||
Path((owner, name)): Path<(String, String)>,
|
||||
auth: Option<Extension<AuthenticatedDid>>,
|
||||
) -> Result<Json<serde_json::Value>> {
|
||||
let record = state
|
||||
.db
|
||||
.get_repo(&owner, &name)
|
||||
.await?
|
||||
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
|
||||
// This route sits on `optional_signature`, so the DID is optional. Webhook
|
||||
// callback URLs are owner-secret config and there is no anonymous form, so a
|
||||
// headerless caller is rejected before any lookup (401, which fires for an
|
||||
// existing-private and an absent repo alike, so it leaks no existence).
|
||||
let Some(Extension(AuthenticatedDid(caller))) = auth else {
|
||||
return Err(AppError::Unauthorized(
|
||||
"listing webhooks requires authentication".into(),
|
||||
));
|
||||
};
|
||||
|
||||
// Read-visibility first, then owner. authorize_repo_read returns 404 on a
|
||||
// visibility deny, so a non-reader of a private repo cannot tell it exists
|
||||
// (uniform with the sibling read surfaces); require_repo_owner then yields
|
||||
// 403 only for a non-owner of a public/readable repo, where existence is not
|
||||
// secret.
|
||||
let (record, _rules) =
|
||||
crate::api::authorize_repo_read(&state, &owner, &name, Some(&caller), "/").await?;
|
||||
crate::api::require_repo_owner(&record, &caller)?;
|
||||
|
||||
let hooks = state.db.list_webhooks(&record.id).await?;
|
||||
// Redact secrets in list response
|
||||
|
||||
@@ -514,6 +514,11 @@ mod tests {
|
||||
machine_id: None,
|
||||
repo_store: crate::git::repo_store::RepoStore::for_testing(PathBuf::from("/tmp"), pool),
|
||||
rate_limiter: RateLimiter::new(100, Duration::from_secs(60)),
|
||||
create_ip_rate_limiter: RateLimiter::new(1000, Duration::from_secs(3600)),
|
||||
push_rate_limiter: RateLimiter::new(600, Duration::from_secs(3600)),
|
||||
push_limiter_trust: crate::rate_limit::TrustedProxy::None,
|
||||
sync_trigger_rate_limiter: RateLimiter::new(60, Duration::from_secs(3600)),
|
||||
peer_write_rate_limiter: RateLimiter::new(600, Duration::from_secs(3600)),
|
||||
shutdown_tx: tokio::sync::watch::channel(false).0,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -52,6 +52,7 @@ pub async fn issue_ref_certificate(
|
||||
issued_at,
|
||||
};
|
||||
|
||||
state.db.insert_ref_certificate(&cert).await?;
|
||||
Ok(cert)
|
||||
// Persist and return the row as it exists in the database (on a
|
||||
// conflict the existing row survives when it is newer).
|
||||
state.db.insert_ref_certificate(&cert).await
|
||||
}
|
||||
@@ -140,6 +140,20 @@ pub struct Config {
|
||||
#[arg(long, env = "GITLAWB_MAX_PACK_BYTES", default_value_t = 2_147_483_648)]
|
||||
pub max_pack_bytes: usize,
|
||||
|
||||
/// Per-client-IP rate limit for `POST /api/v1/sync/trigger`, in requests per
|
||||
/// hour. `/sync/trigger` requires a signature and drives an O(peers) outbound
|
||||
/// fan-out per call, so it gets a tight bucket. `0` disables. Default: 60.
|
||||
#[arg(long, env = "GITLAWB_SYNC_TRIGGER_RATE_LIMIT", default_value_t = 60)]
|
||||
pub sync_trigger_rate_limit: usize,
|
||||
|
||||
/// Per-client-IP rate limit for the peer-write routes (`/peers/announce`,
|
||||
/// `/sync/notify`), in requests per hour. These accept unsigned requests from
|
||||
/// known peers and run at higher frequency, so the bucket is generous. Keeping
|
||||
/// it separate from the trigger bucket stops an unsigned notify flood from
|
||||
/// draining the signed trigger caller's quota. `0` disables. Default: 600.
|
||||
#[arg(long, env = "GITLAWB_PEER_WRITE_RATE_LIMIT", default_value_t = 600)]
|
||||
pub peer_write_rate_limit: usize,
|
||||
|
||||
/// Optional address to bind a Prometheus `/metrics` exposition endpoint on.
|
||||
/// Example: `127.0.0.1:9091`. Leave empty (default) to disable.
|
||||
/// Bind to localhost or a private interface — the metrics endpoint is
|
||||
@@ -152,6 +166,74 @@ pub struct Config {
|
||||
/// in flight and exits. Default: 30s.
|
||||
#[arg(long, env = "GITLAWB_SHUTDOWN_GRACE_SECS", default_value_t = 30)]
|
||||
pub shutdown_grace_secs: u64,
|
||||
|
||||
/// Maximum wall-clock time a single served git operation (upload-pack /
|
||||
/// receive-pack through `run_git_service`) may run before it is aborted and
|
||||
/// its process group torn down, in seconds. Bounds a git that neither
|
||||
/// finishes nor disconnects. Must be positive; set it very large to
|
||||
/// effectively disable the bound. Default: 600s (10 min), generous for large
|
||||
/// clones. Does not cover the ref advertisement (`info/refs`) or the
|
||||
/// withheld-blob fetch path (`upload_pack_excluding`, a blocking
|
||||
/// `spawn_blocking` a tokio timeout cannot cancel); both remain unbounded.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_GIT_SERVICE_TIMEOUT_SECS",
|
||||
default_value_t = 600,
|
||||
value_parser = clap::value_parser!(u64).range(1..)
|
||||
)]
|
||||
pub git_service_timeout_secs: u64,
|
||||
|
||||
/// Maximum connections in the PostgreSQL pool. This is a cap, not a floor
|
||||
/// (connections open lazily). Size against the database server's
|
||||
/// max_connections, remembering admin tooling opens its own pool.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_DB_MAX_CONNECTIONS",
|
||||
default_value_t = 20,
|
||||
value_parser = clap::value_parser!(u32).range(1..)
|
||||
)]
|
||||
pub db_max_connections: u32,
|
||||
|
||||
/// Maximum time a request waits for a pool connection before failing with
|
||||
/// 503, in seconds. Bounds queueing when the database is slow or down.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_DB_ACQUIRE_TIMEOUT_SECS",
|
||||
default_value_t = 5,
|
||||
value_parser = clap::value_parser!(u64).range(1..)
|
||||
)]
|
||||
pub db_acquire_timeout_secs: u64,
|
||||
|
||||
/// Upper bound on each startup connect-and-migrate attempt, in seconds.
|
||||
/// Migrations wait on a cross-instance advisory lock, so this must be
|
||||
/// generous enough for a peer instance to finish migrating; on expiry the
|
||||
/// attempt is retried (migrations are idempotent).
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_DB_CONNECT_TIMEOUT_SECS",
|
||||
default_value_t = 60,
|
||||
value_parser = clap::value_parser!(u64).range(1..)
|
||||
)]
|
||||
pub db_connect_timeout_secs: u64,
|
||||
|
||||
/// First retry delay when the database is unavailable at startup, in
|
||||
/// seconds. Doubles each attempt up to --db-retry-max-secs.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_DB_RETRY_INITIAL_SECS",
|
||||
default_value_t = 5,
|
||||
value_parser = clap::value_parser!(u64).range(1..)
|
||||
)]
|
||||
pub db_retry_initial_secs: u64,
|
||||
|
||||
/// Ceiling on the startup retry delay, in seconds.
|
||||
#[arg(
|
||||
long,
|
||||
env = "GITLAWB_DB_RETRY_MAX_SECS",
|
||||
default_value_t = 60,
|
||||
value_parser = clap::value_parser!(u64).range(1..)
|
||||
)]
|
||||
pub db_retry_max_secs: u64,
|
||||
}
|
||||
|
||||
impl Config {
|
||||
@@ -169,3 +251,25 @@ impl Config {
|
||||
PathBuf::from(&self.key_path)
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn git_service_timeout_defaults_to_600_and_rejects_zero() {
|
||||
assert_eq!(
|
||||
Config::parse_from(["gitlawb-node"]).git_service_timeout_secs,
|
||||
600
|
||||
);
|
||||
assert_eq!(
|
||||
Config::parse_from(["gitlawb-node", "--git-service-timeout-secs", "30"])
|
||||
.git_service_timeout_secs,
|
||||
30
|
||||
);
|
||||
// 0 is a footgun (immediate-504 on every request); clap must reject it.
|
||||
assert!(
|
||||
Config::try_parse_from(["gitlawb-node", "--git-service-timeout-secs", "0"]).is_err()
|
||||
);
|
||||
}
|
||||
}
|
||||
+2476
-110
File diff suppressed because it is too large.
Load diff
@@ -23,24 +23,98 @@ pub enum AppError {
|
||||
#[allow(dead_code)]
|
||||
Forbidden(String),
|
||||
|
||||
#[error("icaptcha proof required: {0}")]
|
||||
IcaptchaProofRequired(String),
|
||||
#[error("icaptcha proof required: {message}")]
|
||||
IcaptchaProofRequired {
|
||||
message: String,
|
||||
/// iCaptcha service base URL the client should solve against.
|
||||
url: String,
|
||||
/// Minimum proof level this node requires.
|
||||
level: u32,
|
||||
},
|
||||
|
||||
#[error("invalid request: {0}")]
|
||||
BadRequest(String),
|
||||
|
||||
#[error("too many requests: {0}")]
|
||||
TooManyRequests(String),
|
||||
|
||||
#[error("incomplete: {0}")]
|
||||
Incomplete(String),
|
||||
|
||||
#[error("git error: {0}")]
|
||||
Git(String),
|
||||
|
||||
#[error("git service timed out: {0}")]
|
||||
Timeout(String),
|
||||
|
||||
#[error("database error: {0}")]
|
||||
Db(#[from] sqlx::Error),
|
||||
|
||||
#[error("internal error: {0}")]
|
||||
Internal(#[from] anyhow::Error),
|
||||
Internal(anyhow::Error),
|
||||
}
|
||||
|
||||
/// Shared error code/message for "the database is unreachable", also used by
|
||||
/// the degraded startup server (main.rs) and the readiness probe (server.rs)
|
||||
/// so clients see one vocabulary for the condition.
|
||||
pub const DB_UNAVAILABLE_CODE: &str = "db_unavailable";
|
||||
pub const DB_UNAVAILABLE_MESSAGE: &str = "database is temporarily unavailable";
|
||||
|
||||
/// Connection-level sqlx failures that mean the database is unreachable right
|
||||
/// now (retryable, 503), as opposed to server-reported query errors.
|
||||
fn db_unavailable(e: &sqlx::Error) -> bool {
|
||||
matches!(
|
||||
e,
|
||||
sqlx::Error::PoolTimedOut
|
||||
| sqlx::Error::PoolClosed
|
||||
| sqlx::Error::Io(_)
|
||||
| sqlx::Error::Tls(_)
|
||||
)
|
||||
}
|
||||
|
||||
/// The db layer returns `anyhow::Result`, so sqlx errors reach handlers inside
|
||||
/// anyhow chains. Downcast them back out so the status mapping below can see
|
||||
/// them — without this, every database outage surfaces as a 500 instead of a
|
||||
/// 503. anyhow preserves downcastability through `.context()` layers.
|
||||
impl From<anyhow::Error> for AppError {
|
||||
fn from(err: anyhow::Error) -> Self {
|
||||
match err.downcast::<sqlx::Error>() {
|
||||
Ok(sql) => AppError::Db(sql),
|
||||
Err(err) => AppError::Internal(err),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl IntoResponse for AppError {
|
||||
fn into_response(self) -> Response {
|
||||
// iCaptcha challenges carry structured discovery so clients don't have to
|
||||
// scrape the message: the service URL and required level are returned as
|
||||
// both JSON fields and `x-icaptcha-url` / `x-icaptcha-level` headers
|
||||
// (mirroring the header-bearing `human_detected` response in auth/mod.rs).
|
||||
if let AppError::IcaptchaProofRequired {
|
||||
message,
|
||||
url,
|
||||
level,
|
||||
} = &self
|
||||
{
|
||||
use axum::http::HeaderValue;
|
||||
let body = Json(json!({
|
||||
"error": "icaptcha_proof_required",
|
||||
"message": message,
|
||||
"icaptcha_url": url,
|
||||
"required_level": level,
|
||||
}));
|
||||
let mut resp = (StatusCode::FORBIDDEN, body).into_response();
|
||||
let headers = resp.headers_mut();
|
||||
if let Ok(v) = HeaderValue::from_str(url) {
|
||||
headers.insert("x-icaptcha-url", v);
|
||||
}
|
||||
if let Ok(v) = HeaderValue::from_str(&level.to_string()) {
|
||||
headers.insert("x-icaptcha-level", v);
|
||||
}
|
||||
return resp;
|
||||
}
|
||||
|
||||
let (status, code, message) = match &self {
|
||||
AppError::RepoNotFound(r) => (
|
||||
StatusCode::NOT_FOUND,
|
||||
@@ -55,17 +129,24 @@ impl IntoResponse for AppError {
|
||||
AppError::NotFound(msg) => (StatusCode::NOT_FOUND, "not_found", msg.clone()),
|
||||
AppError::Unauthorized(msg) => (StatusCode::UNAUTHORIZED, "not_an_agent", msg.clone()),
|
||||
AppError::Forbidden(msg) => (StatusCode::FORBIDDEN, "forbidden", msg.clone()),
|
||||
// 403, not 401: the caller IS an authenticated agent (credentials are
|
||||
// valid) but is forbidden from this action without a valid, fresh
|
||||
// iCaptcha proof. The distinct `icaptcha_proof_required` code — which
|
||||
// clients branch on — keeps it separable from a plain `forbidden`.
|
||||
AppError::IcaptchaProofRequired(msg) => (
|
||||
StatusCode::FORBIDDEN,
|
||||
"icaptcha_proof_required",
|
||||
msg.clone(),
|
||||
),
|
||||
// IcaptchaProofRequired is handled above (it carries extra headers/fields).
|
||||
AppError::IcaptchaProofRequired { .. } => unreachable!("handled before this match"),
|
||||
AppError::BadRequest(msg) => (StatusCode::BAD_REQUEST, "bad_request", msg.clone()),
|
||||
AppError::TooManyRequests(msg) => {
|
||||
(StatusCode::TOO_MANY_REQUESTS, "rate_limited", msg.clone())
|
||||
}
|
||||
AppError::Incomplete(msg) => {
|
||||
(StatusCode::UNPROCESSABLE_ENTITY, "incomplete", msg.clone())
|
||||
}
|
||||
AppError::Git(msg) => (StatusCode::INTERNAL_SERVER_ERROR, "git_error", msg.clone()),
|
||||
// 504, distinct from the 500 git_error and from the read-gate's 404 /
|
||||
// the auth 401, so the client can tell a deadline from a failure.
|
||||
AppError::Timeout(msg) => (StatusCode::GATEWAY_TIMEOUT, "git_timeout", msg.clone()),
|
||||
AppError::Db(e) if db_unavailable(e) => (
|
||||
StatusCode::SERVICE_UNAVAILABLE,
|
||||
DB_UNAVAILABLE_CODE,
|
||||
DB_UNAVAILABLE_MESSAGE.into(),
|
||||
),
|
||||
AppError::Db(e) => (StatusCode::INTERNAL_SERVER_ERROR, "db_error", e.to_string()),
|
||||
AppError::Internal(e) => (
|
||||
StatusCode::INTERNAL_SERVER_ERROR,
|
||||
@@ -84,3 +165,21 @@ impl IntoResponse for AppError {
|
||||
}
|
||||
|
||||
pub type Result<T> = std::result::Result<T, AppError>;
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn timeout_maps_to_504_distinct_from_git_500() {
|
||||
assert_eq!(
|
||||
AppError::Timeout("x".into()).into_response().status(),
|
||||
StatusCode::GATEWAY_TIMEOUT
|
||||
);
|
||||
// Guard against a swap with the generic git failure (500).
|
||||
assert_eq!(
|
||||
AppError::Git("x".into()).into_response().status(),
|
||||
StatusCode::INTERNAL_SERVER_ERROR
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -303,6 +303,131 @@ fn validate_path_components(owner_did: &str, repo_name: &str) -> Result<()> {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Validate a peer-supplied `owner/name` sync slug and return its two halves.
|
||||
///
|
||||
/// The sync queue carries a single `repo` string that peers control, and the
|
||||
/// worker turns it into a filesystem path. `PathBuf::join` does not normalize,
|
||||
/// and an absolute second component replaces the accumulated path, so an
|
||||
/// unvalidated `a//tmp/x` resolved to `/tmp/x.git` outside `repos_dir` (#272).
|
||||
///
|
||||
/// The halves are checked with the same validators that guard
|
||||
/// `RepoStore::local_path`, so there is one owner rule and one name rule in the
|
||||
/// crate. The one rule added here is the leading `.`/`-` check on the owner
|
||||
/// half: `validate_owner_did` has no such rule (it also serves full DIDs, which
|
||||
/// always start with `d`), and without it an owner half of `.` puts a
|
||||
/// peer-controlled mirror at the `repos_dir` root, which canonicalizes back
|
||||
/// inside the root and so passes containment.
|
||||
pub(crate) fn validate_repo_slug(slug: &str) -> Result<(&str, &str)> {
|
||||
let mut parts = slug.split('/');
|
||||
let (Some(owner), Some(name)) = (parts.next(), parts.next()) else {
|
||||
anyhow::bail!("repo slug must be 'owner/name'");
|
||||
};
|
||||
if parts.next().is_some() {
|
||||
anyhow::bail!("repo slug must contain exactly one '/'");
|
||||
}
|
||||
if owner.is_empty() || name.is_empty() {
|
||||
anyhow::bail!("repo slug has an empty owner or name");
|
||||
}
|
||||
if owner.starts_with('.') || owner.starts_with('-') {
|
||||
anyhow::bail!("repo slug owner must not start with '.' or '-'");
|
||||
}
|
||||
// The owner half becomes one path component, so it is bounded by NAME_MAX
|
||||
// (255), not by the DID column's 256. The two differ by exactly one, and
|
||||
// that one length is the gap that matters: validate_owner_did accepts 256,
|
||||
// create_dir_all then fails with ENAMETOOLONG on every attempt, and the
|
||||
// worker leaves such a row pending, so it is re-picked forever. Rejecting
|
||||
// it here means an undeliverable slug never enters the queue at all.
|
||||
if owner.len() > 255 {
|
||||
anyhow::bail!("repo slug owner exceeds 255 chars");
|
||||
}
|
||||
validate_owner_did(owner)?;
|
||||
validate_repo_name(name)?;
|
||||
Ok((owner, name))
|
||||
}
|
||||
|
||||
/// The answer from [`path_within_root`].
|
||||
///
|
||||
/// Three-valued rather than a bool because the two negative answers call for
|
||||
/// opposite handling. `Outside` is a deterministic verdict about a hostile or
|
||||
/// misconfigured path: the same input fails the same way forever, so the caller
|
||||
/// can retire the work. `IoError` says the question could not be answered at
|
||||
/// all (EACCES, an unmounted root), which is transient, so the caller must keep
|
||||
/// the work and try again rather than permanently retire a legitimate repo.
|
||||
#[derive(Debug)]
|
||||
pub(crate) enum Containment {
|
||||
/// The candidate resolves inside the root.
|
||||
Contained,
|
||||
/// The candidate resolves outside the root.
|
||||
Outside,
|
||||
/// The filesystem could not answer the question.
|
||||
IoError(std::io::Error),
|
||||
}
|
||||
|
||||
/// Does `candidate` canonically resolve inside `root`?
|
||||
///
|
||||
/// The third layer of path defence, after the character allowlist and the
|
||||
/// component walk on `RepoStore::local_path`. Those two read the path as text
|
||||
/// and cannot see a symlink standing between the root and the target (#272).
|
||||
///
|
||||
/// One contract covers both the clone and the fetch branch. `symlink_metadata`
|
||||
/// decides which:
|
||||
///
|
||||
/// * The candidate exists (including as a symlink), so the candidate itself is
|
||||
/// canonicalized. That resolves the link and catches a mirror path that is a
|
||||
/// symlink to a bare repo outside the root, which a parent-only check misses
|
||||
/// entirely: the parent canonicalizes clean, `exists()` follows the link, and
|
||||
/// the fetch then writes through it.
|
||||
/// * The candidate does not exist, so its parent is canonicalized instead.
|
||||
/// This is the first-clone case. Canonicalizing the candidate unconditionally
|
||||
/// would reject every first clone, since `canonicalize` errors on a path that
|
||||
/// does not exist.
|
||||
///
|
||||
/// Pure: it reads the filesystem and never creates, moves, or removes anything.
|
||||
/// Callers that need the parent directory to exist create it themselves before
|
||||
/// asking, because a predicate that created a directory as a side effect of
|
||||
/// being asked would be wrong for a caller asking about a path it is about to
|
||||
/// delete.
|
||||
pub(crate) fn path_within_root(candidate: &Path, root: &Path) -> Containment {
|
||||
let root = match root.canonicalize() {
|
||||
Ok(p) => p,
|
||||
// A root that cannot be resolved is an operator condition, never a
|
||||
// verdict on the candidate, so every error kind is retryable here.
|
||||
Err(e) => return Containment::IoError(e),
|
||||
};
|
||||
|
||||
let resolved = match std::fs::symlink_metadata(candidate) {
|
||||
// The candidate exists as an entry: resolve it, links and all. A failure
|
||||
// now (a dangling symlink, a permission change mid-flight) is an I/O
|
||||
// answer, since the entry was there a moment ago.
|
||||
Ok(_) => match candidate.canonicalize() {
|
||||
Ok(p) => p,
|
||||
Err(e) => return Containment::IoError(e),
|
||||
},
|
||||
Err(e) if e.kind() == std::io::ErrorKind::NotFound => {
|
||||
let Some(parent) = candidate.parent() else {
|
||||
return Containment::Outside;
|
||||
};
|
||||
match parent.canonicalize() {
|
||||
Ok(p) => p,
|
||||
// A parent that is not there is a real answer about where this
|
||||
// path sits; anything else is the filesystem failing to answer.
|
||||
Err(e) if e.kind() == std::io::ErrorKind::NotFound => {
|
||||
return Containment::Outside;
|
||||
}
|
||||
Err(e) => return Containment::IoError(e),
|
||||
}
|
||||
}
|
||||
// Neither "it is there" nor "it is not there": we cannot tell.
|
||||
Err(e) => return Containment::IoError(e),
|
||||
};
|
||||
|
||||
if resolved.starts_with(&root) {
|
||||
Containment::Contained
|
||||
} else {
|
||||
Containment::Outside
|
||||
}
|
||||
}
|
||||
|
||||
fn validate_owner_did(owner_did: &str) -> Result<()> {
|
||||
if owner_did.is_empty() {
|
||||
anyhow::bail!("owner_did is empty");
|
||||
@@ -405,6 +530,251 @@ fn advisory_lock_key(owner_slug: &str, repo_name: &str) -> i64 {
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
// ── sync slug validation (#272) ────────────────────────────────────────
|
||||
|
||||
#[test]
|
||||
fn slug_accepts_owner_and_name() {
|
||||
let (owner, name) = validate_repo_slug("z6Mkfoo/hello").expect("valid slug");
|
||||
assert_eq!(owner, "z6Mkfoo");
|
||||
assert_eq!(name, "hello");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn slug_rejects_traversal_in_owner_half() {
|
||||
assert!(validate_repo_slug("../hello").is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn slug_rejects_owner_half_only_the_did_validator_catches() {
|
||||
// These are the cases that isolate the `validate_owner_did` delegation.
|
||||
// `../hello` does NOT: the leading-character rule above rejects it
|
||||
// first, so deleting the delegation leaves that case green. Each owner
|
||||
// half here has exactly one separator, a non-empty name, and a leading
|
||||
// character the slug rules allow, so only the delegation can reject it.
|
||||
for bad in [
|
||||
"a..b/hello", // interior `..` sequence
|
||||
"a%2e%2e/hello", // percent-encoded, disallowed `%`
|
||||
"own\\er/hello", // backslash
|
||||
] {
|
||||
assert!(validate_repo_slug(bad).is_err(), "{bad:?} must be rejected");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn slug_rejects_extra_separator() {
|
||||
// The verified #272 escape: `a//tmp/x` joined to an absolute
|
||||
// `/tmp/x.git` outside repos_dir.
|
||||
assert!(validate_repo_slug("a//tmp/gitlawb-probe").is_err());
|
||||
assert!(validate_repo_slug("../../etc/evil").is_err());
|
||||
assert!(validate_repo_slug("a/../../x").is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn slug_rejects_trailing_segment_only_the_separator_count_catches() {
|
||||
// The case that isolates the separator-count rule. Every slug in
|
||||
// `slug_rejects_extra_separator` is caught by some earlier rule
|
||||
// instead: `a//tmp/...` has an empty name half, `../../etc/evil` trips
|
||||
// the leading-character rule, and `a/../../x` has `..` as its name. Here
|
||||
// both halves are individually valid, so only the count can reject it.
|
||||
// It matters because the worker would otherwise join
|
||||
// `repos_dir/z6Mkfoo/hello.git` while composing the remote URL from the
|
||||
// full three-segment slug, silently mirroring one repo under another's
|
||||
// path.
|
||||
assert!(validate_repo_slug("z6Mkfoo/hello/extra").is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn slug_rejects_missing_separator() {
|
||||
for bad in ["..", "demo", ""] {
|
||||
assert!(validate_repo_slug(bad).is_err(), "{bad:?} must be rejected");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn slug_rejects_empty_half() {
|
||||
for bad in ["/hello", "z6Mkfoo/"] {
|
||||
assert!(validate_repo_slug(bad).is_err(), "{bad:?} must be rejected");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn slug_rejects_leading_dot_or_dash_owner() {
|
||||
// `./hello` would otherwise resolve to a mirror at the repos_dir root,
|
||||
// which the containment check would approve.
|
||||
for bad in ["./hello", "-owner/hello"] {
|
||||
assert!(validate_repo_slug(bad).is_err(), "{bad:?} must be rejected");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn slug_rejects_bad_name_half() {
|
||||
for bad in [
|
||||
"z6Mkfoo/he\0llo",
|
||||
"z6Mkfoo/.hidden",
|
||||
"z6Mkfoo/-dash",
|
||||
"z6Mkfoo/a..b",
|
||||
] {
|
||||
assert!(validate_repo_slug(bad).is_err(), "{bad:?} must be rejected");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn slug_rejects_overlong_halves() {
|
||||
let long_owner = format!("{}/hello", "z".repeat(257));
|
||||
let long_name = format!("z6Mkfoo/{}", "n".repeat(101));
|
||||
assert!(validate_repo_slug(&long_owner).is_err());
|
||||
assert!(validate_repo_slug(&long_name).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn slug_rejects_owner_half_at_the_filesystem_name_limit() {
|
||||
// The owner half becomes a single path component, and Linux NAME_MAX is
|
||||
// 255, so 256 is accepted by validate_owner_did (which bails only above
|
||||
// 256) but can never be created on disk. That made the sync row
|
||||
// permanently un-runnable: create_dir_all failed with ENAMETOOLONG on
|
||||
// every pass and the worker left the row pending, so ten unsigned
|
||||
// requests could hold the whole oldest-first batch forever.
|
||||
assert!(validate_repo_slug(&format!("{}/hello", "z".repeat(256))).is_err());
|
||||
// 255 is the largest creatable component and must still be accepted, so
|
||||
// the bound is not quietly over-tightened.
|
||||
assert!(validate_repo_slug(&format!("{}/hello", "z".repeat(255))).is_ok());
|
||||
}
|
||||
|
||||
// ── canonical containment (#272) ───────────────────────────────────────
|
||||
|
||||
use tempfile::TempDir;
|
||||
|
||||
#[test]
|
||||
fn containment_accepts_a_path_inside_the_root() {
|
||||
let root = TempDir::new().unwrap();
|
||||
let inside = root.path().join("z6Mkfoo");
|
||||
std::fs::create_dir_all(&inside).unwrap();
|
||||
assert!(matches!(
|
||||
path_within_root(&inside.join("hello.git"), root.path()),
|
||||
Containment::Contained
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn containment_rejects_a_sibling_outside_the_root() {
|
||||
let base = TempDir::new().unwrap();
|
||||
let root = base.path().join("root");
|
||||
let sibling = base.path().join("other");
|
||||
std::fs::create_dir_all(&root).unwrap();
|
||||
std::fs::create_dir_all(&sibling).unwrap();
|
||||
assert!(matches!(
|
||||
path_within_root(&sibling, &root),
|
||||
Containment::Outside
|
||||
));
|
||||
}
|
||||
|
||||
#[cfg(unix)]
|
||||
#[test]
|
||||
fn containment_rejects_a_symlinked_directory_inside_the_root() {
|
||||
use std::os::unix::fs::symlink;
|
||||
let base = TempDir::new().unwrap();
|
||||
let root = base.path().join("root");
|
||||
let outside = base.path().join("outside");
|
||||
std::fs::create_dir_all(&root).unwrap();
|
||||
std::fs::create_dir_all(&outside).unwrap();
|
||||
let link = root.join("owner");
|
||||
symlink(&outside, &link).unwrap();
|
||||
assert!(matches!(
|
||||
path_within_root(&link, &root),
|
||||
Containment::Outside
|
||||
));
|
||||
}
|
||||
|
||||
#[cfg(unix)]
|
||||
#[test]
|
||||
fn containment_rejects_a_symlinked_file_inside_the_root() {
|
||||
use std::os::unix::fs::symlink;
|
||||
let base = TempDir::new().unwrap();
|
||||
let root = base.path().join("root");
|
||||
std::fs::create_dir_all(&root).unwrap();
|
||||
let outside = base.path().join("secret.txt");
|
||||
std::fs::write(&outside, b"x").unwrap();
|
||||
let link = root.join("hello.git");
|
||||
symlink(&outside, &link).unwrap();
|
||||
assert!(matches!(
|
||||
path_within_root(&link, &root),
|
||||
Containment::Outside
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn containment_accepts_a_missing_candidate_whose_parent_is_inside() {
|
||||
// The first-clone case: the mirror path does not exist yet, so only the
|
||||
// parent can be canonicalized. Rejecting this is total loss of mirroring.
|
||||
let root = TempDir::new().unwrap();
|
||||
let owner = root.path().join("z6Mkfoo");
|
||||
std::fs::create_dir_all(&owner).unwrap();
|
||||
let candidate = owner.join("hello.git");
|
||||
assert!(!candidate.exists());
|
||||
assert!(matches!(
|
||||
path_within_root(&candidate, root.path()),
|
||||
Containment::Contained
|
||||
));
|
||||
}
|
||||
|
||||
#[cfg(unix)]
|
||||
#[test]
|
||||
fn containment_rejects_a_missing_candidate_under_a_symlinked_parent() {
|
||||
use std::os::unix::fs::symlink;
|
||||
let base = TempDir::new().unwrap();
|
||||
let root = base.path().join("root");
|
||||
let outside = base.path().join("outside");
|
||||
std::fs::create_dir_all(&root).unwrap();
|
||||
std::fs::create_dir_all(&outside).unwrap();
|
||||
symlink(&outside, root.join("z6Mkfoo")).unwrap();
|
||||
let candidate = root.join("z6Mkfoo").join("hello.git");
|
||||
assert!(matches!(
|
||||
path_within_root(&candidate, &root),
|
||||
Containment::Outside
|
||||
));
|
||||
}
|
||||
|
||||
#[cfg(unix)]
|
||||
#[test]
|
||||
fn containment_reports_io_error_for_a_dangling_symlink() {
|
||||
// The link entry exists, so the candidate is the thing to resolve, and
|
||||
// resolving it fails. That is an I/O answer, not a verdict of Outside:
|
||||
// the worker must retry rather than permanently retire the row.
|
||||
use std::os::unix::fs::symlink;
|
||||
let root = TempDir::new().unwrap();
|
||||
let link = root.path().join("hello.git");
|
||||
symlink(root.path().join("nothing-here"), &link).unwrap();
|
||||
assert!(matches!(
|
||||
path_within_root(&link, root.path()),
|
||||
Containment::IoError(_)
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn containment_reports_io_error_for_an_uncanonicalizable_root() {
|
||||
// A repos_dir that cannot be resolved is an operator condition (an
|
||||
// unmounted volume, a bad config), not a hostile path.
|
||||
let base = TempDir::new().unwrap();
|
||||
let root = base.path().join("not-mounted");
|
||||
let candidate = base.path().join("not-mounted").join("hello.git");
|
||||
assert!(matches!(
|
||||
path_within_root(&candidate, &root),
|
||||
Containment::IoError(_)
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn containment_creates_nothing_on_disk() {
|
||||
// The predicate is pure: the admin purge path asks it about directories
|
||||
// it is about to delete, so creating one as a side effect would be wrong.
|
||||
let root = TempDir::new().unwrap();
|
||||
let candidate = root.path().join("z6Mkfoo").join("hello.git");
|
||||
let _ = path_within_root(&candidate, root.path());
|
||||
assert!(!candidate.exists());
|
||||
assert!(!root.path().join("z6Mkfoo").exists());
|
||||
assert_eq!(std::fs::read_dir(root.path()).unwrap().count(), 0);
|
||||
}
|
||||
|
||||
// ── repo_name validation ───────────────────────────────────────────────
|
||||
|
||||
#[test]
|
||||
|
||||
@@ -6,7 +6,8 @@ use bytes::Bytes;
|
||||
use std::collections::HashSet;
|
||||
use std::path::Path;
|
||||
use std::process::Stdio;
|
||||
use tokio::io::AsyncWriteExt;
|
||||
use std::time::Duration;
|
||||
use tokio::io::{AsyncReadExt, AsyncWriteExt};
|
||||
use tokio::process::Command;
|
||||
|
||||
/// Handle `GET /:owner/:repo/info/refs?service=git-upload-pack`
|
||||
@@ -51,8 +52,13 @@ pub async fn info_refs(repo_path: &Path, service: &str) -> Result<Response> {
|
||||
///
|
||||
/// Serves pack data for a clone or fetch. This is stateless — the entire
|
||||
/// negotiation happens in a single request/response.
|
||||
pub async fn upload_pack(repo_path: &Path, request_body: Bytes) -> Result<Response> {
|
||||
let output = run_git_service("git-upload-pack", repo_path, request_body).await?;
|
||||
pub async fn upload_pack(
|
||||
repo_path: &Path,
|
||||
request_body: Bytes,
|
||||
timeout: Duration,
|
||||
) -> Result<Response> {
|
||||
let output =
|
||||
run_git_service("git", "git-upload-pack", repo_path, request_body, timeout).await?;
|
||||
|
||||
Ok(Response::builder()
|
||||
.status(StatusCode::OK)
|
||||
@@ -65,8 +71,13 @@ pub async fn upload_pack(repo_path: &Path, request_body: Bytes) -> Result<Respon
|
||||
///
|
||||
/// Accepts a push. The caller MUST verify HTTP Signature auth before
|
||||
/// calling this function.
|
||||
pub async fn receive_pack(repo_path: &Path, request_body: Bytes) -> Result<Response> {
|
||||
let output = run_git_service("git-receive-pack", repo_path, request_body).await?;
|
||||
pub async fn receive_pack(
|
||||
repo_path: &Path,
|
||||
request_body: Bytes,
|
||||
timeout: Duration,
|
||||
) -> Result<Response> {
|
||||
let output =
|
||||
run_git_service("git", "git-receive-pack", repo_path, request_body, timeout).await?;
|
||||
|
||||
Ok(Response::builder()
|
||||
.status(StatusCode::OK)
|
||||
@@ -112,8 +123,87 @@ impl Drop for KillGroupOnDrop {
|
||||
}
|
||||
}
|
||||
|
||||
async fn run_git_service(service: &str, repo_path: &Path, input: Bytes) -> Result<Vec<u8>> {
|
||||
let mut command = Command::new("git");
|
||||
/// Error returned when [`run_git_service`] aborts a git op on its timeout.
|
||||
///
|
||||
/// Carried through the `anyhow` chain so the HTTP handler can `downcast_ref` it
|
||||
/// and map to 504 Gateway Timeout, distinct from the generic 500 git error.
|
||||
#[derive(Debug, thiserror::Error)]
|
||||
#[error("git service timed out")]
|
||||
pub struct GitServiceTimeout;
|
||||
|
||||
/// On a served-git timeout, tear the process group down AND reap the leader
|
||||
/// before returning, so a caller that releases a write lock (receive-pack) can't
|
||||
/// race a still-live git touching the same repo. SIGTERM first (lets git remove
|
||||
/// its `.git/*.lock` files), escalate to SIGKILL if the leader lingers past a
|
||||
/// grace, then reap. Bounded, so a git that ignores SIGTERM can't block the
|
||||
/// response unboundedly.
|
||||
#[cfg(unix)]
|
||||
async fn reap_group_on_timeout(child: &mut tokio::process::Child) {
|
||||
let Some(pid) = child.id() else {
|
||||
// Never got a pid; nothing to signal, best-effort reap.
|
||||
let _ = child.wait().await;
|
||||
return;
|
||||
};
|
||||
let pgid = pid as i32;
|
||||
// SAFETY: kill(2) takes only integers and borrows no Rust memory; ESRCH on an
|
||||
// already-gone group is ignored.
|
||||
unsafe {
|
||||
libc::kill(-pgid, libc::SIGTERM);
|
||||
}
|
||||
// Wait for the WHOLE group to exit before returning — not just the leader but
|
||||
// grandchildren (index-pack / pack-objects) that reparent to init and can
|
||||
// still be touching the repo, so a caller releasing a write lock can't race
|
||||
// them. Reap our direct child along the way (`try_wait`, else it lingers as a
|
||||
// zombie) and poll the group's liveness with `kill(-pgid, 0)` (ESRCH once
|
||||
// every member is gone). SIGTERM grace, then SIGKILL, then a hard cap so a
|
||||
// stuck process can never block the response unboundedly.
|
||||
for step in 0..400u32 {
|
||||
let _ = child.try_wait();
|
||||
if unsafe { libc::kill(-pgid, 0) } != 0 {
|
||||
return; // ESRCH: every group member has exited
|
||||
}
|
||||
if step == 200 {
|
||||
// ~2s SIGTERM grace elapsed; force the group down. `step == 200` fires
|
||||
// exactly once in the 0..400 loop, so no re-entry guard is needed.
|
||||
unsafe {
|
||||
libc::kill(-pgid, libc::SIGKILL);
|
||||
}
|
||||
}
|
||||
tokio::time::sleep(Duration::from_millis(10)).await;
|
||||
}
|
||||
// ~4s hard cap. Only reached if a group member survives SIGKILL, which means
|
||||
// it is wedged in uninterruptible (D-state) I/O — a fsync on stuck storage, a
|
||||
// hung mount — that no signal interrupts until the kernel returns. Nothing in
|
||||
// userspace can kill it; blocking here (or holding the write lock) would just
|
||||
// re-create the "hung git pins the repo" problem this bounds. Reap best-effort
|
||||
// (tokio's orphan reaper collects it once the syscall unblocks) and return;
|
||||
// git-level quarantine/ref-locking still guards the brief window before the
|
||||
// D-state process finishes.
|
||||
tracing::warn!(
|
||||
pid,
|
||||
"served git survived SIGKILL past the teardown cap (uninterruptible I/O?); \
|
||||
releasing without a confirmed group reap"
|
||||
);
|
||||
let _ = child.try_wait();
|
||||
}
|
||||
|
||||
/// Run a stateless-rpc git service and return its stdout.
|
||||
///
|
||||
/// `git_bin` is the git executable to spawn; production callers pass `"git"`
|
||||
/// (resolved via `PATH`). It is injectable purely so the process-group teardown
|
||||
/// wiring (`process_group(0)` + [`KillGroupOnDrop`]) can be driven end-to-end by
|
||||
/// a fake `git` in tests without mutating the process-global `PATH`.
|
||||
///
|
||||
/// `timeout` bounds the whole child interaction; on expiry the op is aborted with
|
||||
/// [`GitServiceTimeout`] and its process group is torn down.
|
||||
async fn run_git_service(
|
||||
git_bin: &str,
|
||||
service: &str,
|
||||
repo_path: &Path,
|
||||
input: Bytes,
|
||||
timeout: Duration,
|
||||
) -> Result<Vec<u8>> {
|
||||
let mut command = Command::new(git_bin);
|
||||
command
|
||||
.arg(service_to_command(service))
|
||||
.arg("--stateless-rpc")
|
||||
@@ -131,33 +221,85 @@ async fn run_git_service(service: &str, repo_path: &Path, input: Bytes) -> Resul
|
||||
|
||||
// Arm the group-kill guard for the lifetime of the request. With
|
||||
// process_group(0) the child is its own group leader, so pgid == its pid.
|
||||
// This fires on a client disconnect (the whole future is dropped mid-request).
|
||||
#[cfg(unix)]
|
||||
let mut group_guard = KillGroupOnDrop {
|
||||
pgid: child.id().map(|id| id as i32),
|
||||
};
|
||||
|
||||
// Write the request body to git's stdin, but don't early-return on a write
|
||||
// error: always reap the child first (below), so the guard only ever fires on
|
||||
// an actual future-drop (client disconnect), never on a pid we just reaped.
|
||||
let write_result: std::io::Result<()> = match child.stdin.take() {
|
||||
Some(mut stdin) => stdin.write_all(&input).await,
|
||||
None => Ok(()),
|
||||
// Own the pipes so `child` stays reap-able after a timeout: wait_with_output
|
||||
// would consume it, but on timeout we must actively reap the group before
|
||||
// returning (see reap_group_on_timeout).
|
||||
let mut stdin = child.stdin.take();
|
||||
let mut stdout = child.stdout.take().context("git stdout was not piped")?;
|
||||
let mut stderr = child.stderr.take().context("git stderr was not piped")?;
|
||||
let mut out = Vec::new();
|
||||
let mut err = Vec::new();
|
||||
|
||||
// Bound the whole child interaction: a git that neither finishes nor
|
||||
// disconnects would otherwise pin the pid forever. Write stdin, drain stdout
|
||||
// and stderr, and wait for the child all concurrently (draining while writing
|
||||
// avoids a pipe deadlock on a large body), under one deadline.
|
||||
let interact = async {
|
||||
// Don't early-return on a write error: the join still waits on the child,
|
||||
// so an error is surfaced only after the child has been waited on.
|
||||
let write = async {
|
||||
match stdin.take() {
|
||||
Some(mut s) => s.write_all(&input).await,
|
||||
None => Ok(()),
|
||||
}
|
||||
};
|
||||
let (write_result, r_out, r_err, status) = tokio::join!(
|
||||
write,
|
||||
stdout.read_to_end(&mut out),
|
||||
stderr.read_to_end(&mut err),
|
||||
child.wait(),
|
||||
);
|
||||
r_out?;
|
||||
r_err?;
|
||||
Ok::<_, anyhow::Error>((write_result, status?))
|
||||
};
|
||||
|
||||
let output = child.wait_with_output().await?;
|
||||
let timed = tokio::time::timeout(timeout, interact).await;
|
||||
let (write_result, status) = match timed {
|
||||
Ok(result) => {
|
||||
// The join runs all arms to completion, so the child is reaped: disarm
|
||||
// before surfacing any interaction error (a read/wait error), else the
|
||||
// guard's drop would fire SIGTERM on the reaped, possibly-reused pgid.
|
||||
#[cfg(unix)]
|
||||
group_guard.disarm();
|
||||
result?
|
||||
}
|
||||
Err(_elapsed) => {
|
||||
// Timeout: tear the whole group down and reap it before returning so a
|
||||
// caller releasing a write lock can't race a still-live git. Then disarm
|
||||
// the (now redundant) guard so its drop can't hit a reused pgid.
|
||||
#[cfg(unix)]
|
||||
{
|
||||
reap_group_on_timeout(&mut child).await;
|
||||
group_guard.disarm();
|
||||
}
|
||||
#[cfg(not(unix))]
|
||||
{
|
||||
let _ = child.start_kill();
|
||||
let _ = tokio::time::timeout(Duration::from_secs(2), child.wait()).await;
|
||||
}
|
||||
return Err(GitServiceTimeout.into());
|
||||
}
|
||||
};
|
||||
|
||||
// Child reaped, so its group is gone: disarm before surfacing any error.
|
||||
#[cfg(unix)]
|
||||
group_guard.disarm();
|
||||
|
||||
write_result.context("failed to write to git stdin")?;
|
||||
|
||||
if !output.status.success() {
|
||||
let stderr = String::from_utf8_lossy(&output.stderr);
|
||||
// Surface git's own failure (its stderr, which the handler may classify as a
|
||||
// 400) before any stdin-write error: when git rejects a malformed body it
|
||||
// exits non-zero and closes stdin, so the write's EPIPE would otherwise mask
|
||||
// the real cause.
|
||||
if !status.success() {
|
||||
let stderr = String::from_utf8_lossy(&err);
|
||||
bail!("{service} failed: {stderr}");
|
||||
}
|
||||
|
||||
Ok(output.stdout)
|
||||
write_result.context("failed to write to git stdin")?;
|
||||
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
fn service_to_command(service: &str) -> &str {
|
||||
@@ -876,4 +1018,499 @@ mod tests {
|
||||
let _ = child.kill().await;
|
||||
let _ = child.wait().await;
|
||||
}
|
||||
|
||||
// ── #62 PR1: end-to-end teardown wiring through run_git_service ─────────
|
||||
//
|
||||
// The kill_group_guard_* tests above build a KillGroupOnDrop by hand and
|
||||
// never call run_git_service, so deleting `process_group(0)` (spawn site) or
|
||||
// the guard-arming, or the post-reap disarm, would leave them green. These
|
||||
// drive the REAL run_git_service via an injected fake `git` (the `git_bin`
|
||||
// seam) and assert the production spawn path actually wires the teardown up.
|
||||
// Faithful to the real invocation: run_git_service spawns
|
||||
// `<git_bin> <cmd> --stateless-rpc <repo_path>` in its own process group.
|
||||
|
||||
/// SIGKILLs the given pids on drop (ignoring all kill errors, e.g. ESRCH for
|
||||
/// an already-dead pid) so a panicking assertion can't leak the fake `git` or
|
||||
/// its grandchild onto the test runner.
|
||||
#[cfg(unix)]
|
||||
struct ReapOnPanic(Vec<i32>);
|
||||
|
||||
#[cfg(unix)]
|
||||
impl Drop for ReapOnPanic {
|
||||
fn drop(&mut self) {
|
||||
for &pid in &self.0 {
|
||||
unsafe {
|
||||
libc::kill(pid, libc::SIGKILL);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Write an executable fake `git` (named `git`) into `dir`; return its path.
|
||||
#[cfg(unix)]
|
||||
fn write_fake_git(dir: &std::path::Path, body: &str) -> std::path::PathBuf {
|
||||
use std::os::unix::fs::PermissionsExt as _;
|
||||
let path = dir.join("git");
|
||||
std::fs::write(&path, body).unwrap();
|
||||
std::fs::set_permissions(&path, std::fs::Permissions::from_mode(0o755)).unwrap();
|
||||
path
|
||||
}
|
||||
|
||||
/// Read a two-line `leader\ngrandchild` pidfile once both lines are present.
|
||||
#[cfg(unix)]
|
||||
fn read_two_pids(pidfile: &std::path::Path) -> Option<(i32, i32)> {
|
||||
let s = std::fs::read_to_string(pidfile).ok()?;
|
||||
let mut lines = s.lines();
|
||||
let leader: i32 = lines.next()?.trim().parse().ok()?;
|
||||
let grandchild: i32 = lines.next()?.trim().parse().ok()?;
|
||||
Some((leader, grandchild))
|
||||
}
|
||||
|
||||
/// Retry policy for the fake-git spawn race, shared by `fake_git_run_with_pids`
|
||||
/// and the drop test's inline loop (which can't use the helper — it must keep
|
||||
/// the winning future pending). `nth` retry waits `n * STEP_MS` ms.
|
||||
#[cfg(unix)]
|
||||
const FAKE_GIT_RETRY_ATTEMPTS: u64 = 12;
|
||||
#[cfg(unix)]
|
||||
const FAKE_GIT_BACKOFF_STEP_MS: u64 = 100;
|
||||
|
||||
/// Run a fake-git-based `run` under the parallel test runner, retrying if the
|
||||
/// fake transiently fails to record its pids. Under `cargo test --workspace`
|
||||
/// fork-storm load a freshly-written fake `git` can fail to exec (ETXTBSY: a
|
||||
/// concurrent worker forked while its write fd was still open) or be killed by
|
||||
/// the service timeout before it is scheduled to write its pidfile; both leave
|
||||
/// no pids. These misses are *correlated* (bursty) under fork pressure, so each
|
||||
/// retry backs off (growing) to let a spike subside rather than burning every
|
||||
/// attempt inside one. `pidfile` is removed before each attempt. Returns the
|
||||
/// successful attempt's outcome together with the recorded pids; a genuine
|
||||
/// never-spawns bug still fails loudly after the cap. Retried attempts don't
|
||||
/// leak in practice: a miss almost always means the fake never exec'd (nothing
|
||||
/// to clean up), and a spawn that got far enough is reaped by the timeout/drop
|
||||
/// path before this returns.
|
||||
#[cfg(unix)]
|
||||
async fn fake_git_run_with_pids<R, F, Fut>(
|
||||
pidfile: &std::path::Path,
|
||||
mut run: F,
|
||||
) -> (R, (i32, i32))
|
||||
where
|
||||
F: FnMut() -> Fut,
|
||||
Fut: std::future::Future<Output = R>,
|
||||
{
|
||||
for i in 0..FAKE_GIT_RETRY_ATTEMPTS {
|
||||
let _ = std::fs::remove_file(pidfile);
|
||||
let outcome = run().await;
|
||||
// A successful run writes its pids before it returns, so a short poll
|
||||
// catches them (allowing only for fs-visibility lag).
|
||||
for _ in 0..50 {
|
||||
if let Some(p) = read_two_pids(pidfile) {
|
||||
return (outcome, p);
|
||||
}
|
||||
tokio::time::sleep(std::time::Duration::from_millis(10)).await;
|
||||
}
|
||||
// Miss: back off before retrying so a bursty fork-pressure spike
|
||||
// subsides (see the doc note on correlated ETXTBSY/EAGAIN failures).
|
||||
tokio::time::sleep(std::time::Duration::from_millis(
|
||||
FAKE_GIT_BACKOFF_STEP_MS * (i + 1),
|
||||
))
|
||||
.await;
|
||||
}
|
||||
panic!(
|
||||
"fake git failed to spawn and record its pids after {FAKE_GIT_RETRY_ATTEMPTS} \
|
||||
attempts (persistent failure, not a transient parallel-runner miss)"
|
||||
);
|
||||
}
|
||||
|
||||
// Dropping the request future mid-flight (client disconnect) must SIGTERM the
|
||||
// whole group so git AND its pack-objects grandchild die together. Goes RED
|
||||
// if `process_group(0)` or the guard-arming is removed: without its own
|
||||
// group, kill(-pgid) hits no group and the grandchild survives.
|
||||
#[cfg(unix)]
|
||||
#[tokio::test]
|
||||
async fn run_git_service_tears_down_group_when_future_dropped() {
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let pidfile = tmp.path().join("pids");
|
||||
// Fork a grandchild (stands in for pack-objects), record leader+grandchild
|
||||
// pids, then hang so run_git_service parks in wait_with_output.
|
||||
let body = format!(
|
||||
"#!/bin/sh\nsleep 300 &\nprintf '%s\\n%s\\n' \"$$\" \"$!\" > \"{}\"\nwait\n",
|
||||
pidfile.display()
|
||||
);
|
||||
let git_bin = write_fake_git(tmp.path(), &body);
|
||||
|
||||
// Retry under fork-storm load: a freshly-written fake `git` can transiently
|
||||
// fail to exec (ETXTBSY) or exit before recording its pids; both leave no
|
||||
// pids and are independent per attempt (see fake_git_run_with_pids). The
|
||||
// winning attempt's future is kept PENDING so the drop below exercises the
|
||||
// client-disconnect teardown. Dropping a losing attempt's future makes its
|
||||
// guard reap anything that spawned, so retries don't leak.
|
||||
let (fut, grandchild) = {
|
||||
let mut attempt = 0u64;
|
||||
loop {
|
||||
attempt += 1;
|
||||
let _ = std::fs::remove_file(&pidfile);
|
||||
let mut fut = Box::pin(run_git_service(
|
||||
git_bin.to_str().unwrap(),
|
||||
"git-upload-pack",
|
||||
tmp.path(),
|
||||
Bytes::new(),
|
||||
Duration::from_secs(60),
|
||||
));
|
||||
|
||||
// Advance the future a slice at a time until the fake records its
|
||||
// pids. `Ok(_)` means run_git_service returned before the pidfile
|
||||
// appeared (spawn error / early exit); stop polling then, since
|
||||
// re-polling a completed future panics with `async fn resumed after
|
||||
// completion`. Read the pidfile first so a fake that wrote its pids
|
||||
// and then exited is still captured.
|
||||
let mut pids = None;
|
||||
for _ in 0..500 {
|
||||
let finished =
|
||||
tokio::time::timeout(std::time::Duration::from_millis(10), &mut fut)
|
||||
.await
|
||||
.is_ok();
|
||||
if let Some(p) = read_two_pids(&pidfile) {
|
||||
pids = Some(p);
|
||||
break;
|
||||
}
|
||||
if finished {
|
||||
break;
|
||||
}
|
||||
}
|
||||
// Only the grandchild needs panic-cleanup: dropping the future makes
|
||||
// tokio reap the fake leader, and carrying the reaped leader pid
|
||||
// risks SIGKILLing a recycled pid under parallel test load.
|
||||
match pids {
|
||||
Some((_leader, g)) => break (fut, g),
|
||||
None => {
|
||||
// Transient spawn miss: drop the still-armed future so its
|
||||
// guard reaps anything that spawned, then back off (growing)
|
||||
// so a bursty fork-pressure spike subsides before retrying.
|
||||
drop(fut);
|
||||
assert!(
|
||||
attempt < FAKE_GIT_RETRY_ATTEMPTS,
|
||||
"fake git failed to spawn and record its pids after \
|
||||
{FAKE_GIT_RETRY_ATTEMPTS} attempts (persistent failure, \
|
||||
not a transient parallel-runner miss)"
|
||||
);
|
||||
tokio::time::sleep(std::time::Duration::from_millis(
|
||||
FAKE_GIT_BACKOFF_STEP_MS * attempt,
|
||||
))
|
||||
.await;
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
let _cleanup = ReapOnPanic(vec![grandchild]);
|
||||
assert!(
|
||||
alive(grandchild),
|
||||
"grandchild should be running before the drop"
|
||||
);
|
||||
|
||||
// Client disconnect: drop the request future. The armed KillGroupOnDrop
|
||||
// must SIGTERM the whole group.
|
||||
drop(fut);
|
||||
|
||||
let mut gone = false;
|
||||
for _ in 0..500 {
|
||||
if !alive(grandchild) {
|
||||
gone = true;
|
||||
break;
|
||||
}
|
||||
tokio::time::sleep(std::time::Duration::from_millis(10)).await;
|
||||
}
|
||||
assert!(
|
||||
gone,
|
||||
"grandchild must be torn down via the process group on future-drop \
|
||||
(proves run_git_service sets process_group(0) and arms the guard)"
|
||||
);
|
||||
}
|
||||
|
||||
// A request that runs to completion must DISARM the guard after reaping, so
|
||||
// no stray group SIGTERM fires. The fake exits non-zero (surfacing as Err)
|
||||
// but leaves a grandchild alive; the grandchild must survive. Goes RED if the
|
||||
// post-reap disarm is removed: the guard would then fire on return and, since
|
||||
// the grandchild still holds the group open, sweep it.
|
||||
#[cfg(unix)]
|
||||
#[tokio::test]
|
||||
async fn run_git_service_disarms_on_completion_leaving_group_alive() {
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let pidfile = tmp.path().join("pids");
|
||||
// The grandchild is long-lived with stdio redirected to /dev/null:
|
||||
// /dev/null so it doesn't inherit (and hold open) run_git_service's stdout
|
||||
// pipe (which would block wait_with_output until it exits); long-lived so
|
||||
// the "still alive" assertion below can't race the sleep exiting on its own
|
||||
// under a starved scheduler. ReapOnPanic cleans it up.
|
||||
let body = format!(
|
||||
"#!/bin/sh\nsleep 300 >/dev/null 2>&1 &\nprintf '%s\\n%s\\n' \"$$\" \"$!\" > \"{}\"\nexit 1\n",
|
||||
pidfile.display()
|
||||
);
|
||||
let git_bin = write_fake_git(tmp.path(), &body);
|
||||
|
||||
// wait_with_output already reaped the fake leader, so only the grandchild
|
||||
// needs panic-cleanup — SIGKILLing the reaped leader pid could hit a
|
||||
// recycled pid under parallel test load. Retry the run so a transient spawn
|
||||
// miss under fork-storm load doesn't fail the test (see fake_git_run_with_pids).
|
||||
let (result, (_leader, grandchild)) = fake_git_run_with_pids(&pidfile, || {
|
||||
run_git_service(
|
||||
git_bin.to_str().unwrap(),
|
||||
"git-upload-pack",
|
||||
tmp.path(),
|
||||
Bytes::new(),
|
||||
Duration::from_secs(60),
|
||||
)
|
||||
})
|
||||
.await;
|
||||
let _cleanup = ReapOnPanic(vec![grandchild]);
|
||||
|
||||
assert!(result.is_err(), "non-zero git exit must surface as Err");
|
||||
// A mutant that left the guard armed fires SIGTERM on return; poll a short
|
||||
// window so a killed grandchild is reliably observed dead — a single
|
||||
// alive() check can race the SIGTERM+reap and miss it.
|
||||
for _ in 0..30 {
|
||||
assert!(
|
||||
alive(grandchild),
|
||||
"grandchild must survive: run_git_service must disarm the guard after \
|
||||
reaping, not fire a group SIGTERM on the completion path"
|
||||
);
|
||||
tokio::time::sleep(std::time::Duration::from_millis(10)).await;
|
||||
}
|
||||
}
|
||||
|
||||
// The SUCCESS path (exit 0, Ok) must disarm too — the disarm test above only
|
||||
// exercises the exit-1/Err branch. Goes RED if disarm is gated on failure
|
||||
// (e.g. moved inside the `!status.success()` branch): the guard would then
|
||||
// fire after a clean completion and sweep the still-live grandchild.
|
||||
#[cfg(unix)]
|
||||
#[tokio::test]
|
||||
async fn run_git_service_disarms_on_success_leaving_group_alive() {
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let pidfile = tmp.path().join("pids");
|
||||
// Long-lived, stdio to /dev/null (same reasons as the exit-1 test).
|
||||
let body = format!(
|
||||
"#!/bin/sh\nsleep 300 >/dev/null 2>&1 &\nprintf '%s\\n%s\\n' \"$$\" \"$!\" > \"{}\"\nexit 0\n",
|
||||
pidfile.display()
|
||||
);
|
||||
let git_bin = write_fake_git(tmp.path(), &body);
|
||||
|
||||
// Retry the run so a transient spawn miss under fork-storm load doesn't
|
||||
// fail the test (see fake_git_run_with_pids).
|
||||
let (result, (_leader, grandchild)) = fake_git_run_with_pids(&pidfile, || {
|
||||
run_git_service(
|
||||
git_bin.to_str().unwrap(),
|
||||
"git-upload-pack",
|
||||
tmp.path(),
|
||||
Bytes::new(),
|
||||
Duration::from_secs(60),
|
||||
)
|
||||
})
|
||||
.await;
|
||||
let _cleanup = ReapOnPanic(vec![grandchild]);
|
||||
|
||||
assert!(result.is_ok(), "zero-exit git must surface as Ok");
|
||||
// Poll a short window (see the exit-1 test): a mutant that disarms only on
|
||||
// failure fires the guard on this success path, and a single alive() check
|
||||
// can race the SIGTERM+reap.
|
||||
for _ in 0..30 {
|
||||
assert!(
|
||||
alive(grandchild),
|
||||
"grandchild must survive: run_git_service must disarm on the success \
|
||||
path too, not fire a group SIGTERM after a clean completion"
|
||||
);
|
||||
tokio::time::sleep(std::time::Duration::from_millis(10)).await;
|
||||
}
|
||||
}
|
||||
|
||||
// A git that hangs (never finishes, never disconnects) must be bounded: it
|
||||
// returns GitServiceTimeout (the handler maps that to 504) and its process
|
||||
// group is torn down. Goes RED if the timeout wrap is removed — the OUTER
|
||||
// bound below then fires instead of run_git_service's own, so the test fails
|
||||
// loudly rather than hanging CI.
|
||||
#[cfg(unix)]
|
||||
#[tokio::test]
|
||||
async fn run_git_service_times_out_and_tears_down_a_hung_git() {
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let pidfile = tmp.path().join("pids");
|
||||
// Fork a grandchild, then hang forever.
|
||||
let body = format!(
|
||||
"#!/bin/sh\nsleep 300 &\nprintf '%s\\n%s\\n' \"$$\" \"$!\" > \"{}\"\nwait\n",
|
||||
pidfile.display()
|
||||
);
|
||||
let git_bin = write_fake_git(tmp.path(), &body);
|
||||
|
||||
// Outer bound well above git_timeout: if run_git_service's own timeout is
|
||||
// broken it hangs, and this fires instead so we assert-fail, not hang.
|
||||
// fake_git_run_with_pids retries a transient spawn/schedule miss under
|
||||
// fork-storm load and returns the pidfile the fake recorded.
|
||||
let git_timeout = Duration::from_millis(1000);
|
||||
let (outcome, (_leader, grandchild)) = fake_git_run_with_pids(&pidfile, || {
|
||||
tokio::time::timeout(
|
||||
Duration::from_secs(5),
|
||||
run_git_service(
|
||||
git_bin.to_str().unwrap(),
|
||||
"git-upload-pack",
|
||||
tmp.path(),
|
||||
Bytes::new(),
|
||||
git_timeout,
|
||||
),
|
||||
)
|
||||
})
|
||||
.await;
|
||||
|
||||
assert!(
|
||||
outcome.is_ok(),
|
||||
"run_git_service must return via its own timeout, not hang"
|
||||
);
|
||||
let err = outcome
|
||||
.unwrap()
|
||||
.expect_err("a hung git must surface as Err");
|
||||
assert!(
|
||||
err.downcast_ref::<GitServiceTimeout>().is_some(),
|
||||
"the error must be GitServiceTimeout (maps to 504), got: {err:#}"
|
||||
);
|
||||
|
||||
// The hung git's group must be torn down (the armed guard fires on the
|
||||
// timeout return), not leaked.
|
||||
let _cleanup = ReapOnPanic(vec![grandchild]);
|
||||
let mut gone = false;
|
||||
for _ in 0..500 {
|
||||
if !alive(grandchild) {
|
||||
gone = true;
|
||||
break;
|
||||
}
|
||||
tokio::time::sleep(Duration::from_millis(10)).await;
|
||||
}
|
||||
assert!(
|
||||
gone,
|
||||
"a timed-out git's process group must be torn down, not leaked"
|
||||
);
|
||||
}
|
||||
|
||||
// On timeout, run_git_service must REAP the group before returning, so a
|
||||
// caller releasing a write lock (receive-pack) can't race a still-live git.
|
||||
// The fake traps SIGTERM and lingers ~1s (git-cleanup stand-in): with the
|
||||
// reap the call waits for it to exit, so the leader is dead by the time we
|
||||
// return; without it, the call returns while the fake is still mid-trap.
|
||||
// Goes RED if the timeout arm's reap is removed.
|
||||
#[cfg(unix)]
|
||||
#[tokio::test]
|
||||
async fn run_git_service_reaps_the_group_before_returning_on_timeout() {
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let pidfile = tmp.path().join("pids");
|
||||
// Leader traps SIGTERM and exits after ~1s. The grandchild (a sub-shell)
|
||||
// IGNORES SIGTERM entirely (`trap "" TERM`) and sleeps far past the ~4s reap
|
||||
// cap, so nothing but the untrappable SIGKILL escalation can kill it within
|
||||
// the cap. That makes the escalation load-bearing: neuter the SIGKILL and
|
||||
// this test goes RED. (A grandchild that merely trapped-and-slept UNDER the
|
||||
// cap would self-exit and hide a broken escalation.) "Wait for the whole
|
||||
// group" (leader AND grandchild) is observable because both must be dead
|
||||
// before run_git_service returns.
|
||||
let body = format!(
|
||||
"#!/bin/sh\ntrap 'sleep 1; exit 0' TERM\nsh -c 'trap \"\" TERM; sleep 300' >/dev/null 2>&1 &\nprintf '%s\\n%s\\n' \"$$\" \"$!\" > \"{}\"\nwait\n",
|
||||
pidfile.display()
|
||||
);
|
||||
let git_bin = write_fake_git(tmp.path(), &body);
|
||||
|
||||
// fake_git_run_with_pids retries a transient spawn/schedule miss under
|
||||
// fork-storm load and returns the pids the fake recorded; the outer 10s
|
||||
// bound fires only if run_git_service's own timeout is broken (so we
|
||||
// assert-fail rather than hang), well above the git_timeout plus the
|
||||
// SIGKILL-escalation reap of the SIGTERM-ignoring grandchild.
|
||||
let git_timeout = Duration::from_millis(300);
|
||||
let (outcome, (leader, grandchild)) = fake_git_run_with_pids(&pidfile, || {
|
||||
tokio::time::timeout(
|
||||
Duration::from_secs(10),
|
||||
run_git_service(
|
||||
git_bin.to_str().unwrap(),
|
||||
"git-upload-pack",
|
||||
tmp.path(),
|
||||
Bytes::new(),
|
||||
git_timeout,
|
||||
),
|
||||
)
|
||||
})
|
||||
.await;
|
||||
assert!(outcome.is_ok(), "must return via its own timeout, not hang");
|
||||
assert!(outcome.unwrap().is_err(), "a hung git must surface as Err");
|
||||
|
||||
// The WHOLE group (leader AND the lingering grandchild) must be gone by the
|
||||
// time we get here.
|
||||
let _cleanup = ReapOnPanic(vec![grandchild]);
|
||||
assert!(
|
||||
!alive(leader) && !alive(grandchild),
|
||||
"run_git_service must reap the whole git process group (leader AND \
|
||||
grandchildren) before returning on a timeout, so a write-lock release \
|
||||
can't race a still-live git"
|
||||
);
|
||||
}
|
||||
|
||||
// The timeout bounds git-receive-pack too, not just upload-pack: on the push
|
||||
// path a hung git also holds the repo's write lock, so an unbounded receive-pack
|
||||
// pins the repo until the process dies. run_git_service must return
|
||||
// Err(GitServiceTimeout) for the receive-pack service exactly as it does for
|
||||
// upload-pack. Goes RED if the internal timeout is removed (the fake never
|
||||
// exits, so the outer bound trips and the outcome is not Ok).
|
||||
#[cfg(unix)]
|
||||
#[tokio::test]
|
||||
async fn run_git_service_times_out_a_hung_receive_pack() {
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let git_bin = write_fake_git(tmp.path(), "#!/bin/sh\nsleep 300\n");
|
||||
let outcome = tokio::time::timeout(
|
||||
Duration::from_secs(5),
|
||||
run_git_service(
|
||||
git_bin.to_str().unwrap(),
|
||||
"git-receive-pack",
|
||||
tmp.path(),
|
||||
Bytes::new(),
|
||||
Duration::from_millis(200),
|
||||
),
|
||||
)
|
||||
.await;
|
||||
assert!(
|
||||
outcome.is_ok(),
|
||||
"receive-pack must return via its own timeout, not hang"
|
||||
);
|
||||
let err = outcome
|
||||
.unwrap()
|
||||
.expect_err("a hung receive-pack must surface as Err");
|
||||
assert!(
|
||||
err.downcast_ref::<GitServiceTimeout>().is_some(),
|
||||
"a hung receive-pack must time out as GitServiceTimeout (maps to 504); \
|
||||
got: {err:#}"
|
||||
);
|
||||
}
|
||||
|
||||
// A malformed request: git exits non-zero with a recognizable pkt-line error
|
||||
// on stderr AND does not read stdin, so a body larger than the pipe buffer
|
||||
// makes the write EPIPE. run_git_service must surface git's stderr (which the
|
||||
// handler classifies as a 400), not the EPIPE write error (a generic 500).
|
||||
// Goes RED if the stdin-write check runs before the exit-status check.
|
||||
#[cfg(unix)]
|
||||
#[tokio::test]
|
||||
async fn run_git_service_surfaces_git_stderr_over_a_stdin_epipe() {
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let git_bin = write_fake_git(
|
||||
tmp.path(),
|
||||
"#!/bin/sh\necho 'fatal: bad line length character: 0000' >&2\nexit 128\n",
|
||||
);
|
||||
|
||||
// Larger than a pipe buffer (~64 KiB) so the write blocks then EPIPEs when
|
||||
// the fake exits without draining stdin, exercising the ordering.
|
||||
let big = Bytes::from(vec![0u8; 256 * 1024]);
|
||||
let result = run_git_service(
|
||||
git_bin.to_str().unwrap(),
|
||||
"git-upload-pack",
|
||||
tmp.path(),
|
||||
big,
|
||||
Duration::from_secs(60),
|
||||
)
|
||||
.await;
|
||||
|
||||
let err = result.expect_err("non-zero git must surface as Err");
|
||||
let msg = format!("{err:#}");
|
||||
assert!(
|
||||
msg.contains("bad line length"),
|
||||
"run_git_service must surface git's stderr (a classifiable 400), not the \
|
||||
stdin-write EPIPE (a generic 500); got: {msg}"
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -271,9 +271,8 @@ pub struct TreeEntry {
|
||||
/// `/ipfs/<cid>` is computed from these same content bytes via
|
||||
/// `gitlawb_core::cid::Cid::from_git_object_bytes`.
|
||||
///
|
||||
/// Returns `None` if the object does not exist in this repo.
|
||||
pub fn read_object(repo_path: &Path, sha256_hex: &str) -> Result<Option<(String, Vec<u8>)>> {
|
||||
// First check if the object exists and get its type
|
||||
/// Get just the object type. Returns `None` if the object doesn't exist.
|
||||
pub fn object_type(repo_path: &Path, sha256_hex: &str) -> Result<Option<String>> {
|
||||
let type_output = Command::new("git")
|
||||
.args(["cat-file", "-t", sha256_hex])
|
||||
.current_dir(repo_path)
|
||||
@@ -284,13 +283,17 @@ pub fn read_object(repo_path: &Path, sha256_hex: &str) -> Result<Option<(String,
|
||||
return Ok(None);
|
||||
}
|
||||
|
||||
let obj_type = String::from_utf8_lossy(&type_output.stdout)
|
||||
.trim()
|
||||
.to_string();
|
||||
Ok(Some(
|
||||
String::from_utf8_lossy(&type_output.stdout)
|
||||
.trim()
|
||||
.to_string(),
|
||||
))
|
||||
}
|
||||
|
||||
// Read the raw content bytes
|
||||
/// Read an object's content if its type is already known.
|
||||
pub fn read_object_content(repo_path: &Path, sha256_hex: &str, obj_type: &str) -> Result<Vec<u8>> {
|
||||
let content_output = Command::new("git")
|
||||
.args(["cat-file", &obj_type, sha256_hex])
|
||||
.args(["cat-file", obj_type, sha256_hex])
|
||||
.current_dir(repo_path)
|
||||
.output()
|
||||
.context("failed to run git cat-file <type>")?;
|
||||
@@ -300,7 +303,24 @@ pub fn read_object(repo_path: &Path, sha256_hex: &str) -> Result<Option<(String,
|
||||
bail!("git cat-file failed: {stderr}");
|
||||
}
|
||||
|
||||
Ok(Some((obj_type, content_output.stdout)))
|
||||
Ok(content_output.stdout)
|
||||
}
|
||||
|
||||
/// Read a git object by its SHA-256 hex object ID.
|
||||
///
|
||||
/// Returns `(object_type, content_bytes)` where `content_bytes` is the raw
|
||||
/// object content (without the git framing header). The CID served over
|
||||
/// `/ipfs/<cid>` is computed from these same content bytes via
|
||||
/// `gitlawb_core::cid::Cid::from_git_object_bytes`.
|
||||
///
|
||||
/// Returns `None` if the object does not exist in this repo.
|
||||
pub fn read_object(repo_path: &Path, sha256_hex: &str) -> Result<Option<(String, Vec<u8>)>> {
|
||||
let obj_type = match object_type(repo_path, sha256_hex)? {
|
||||
Some(t) => t,
|
||||
None => return Ok(None),
|
||||
};
|
||||
let content = read_object_content(repo_path, sha256_hex, &obj_type)?;
|
||||
Ok(Some((obj_type, content)))
|
||||
}
|
||||
|
||||
/// Get the diff between two branches: changes on source_branch not in target_branch.
|
||||
|
||||
@@ -309,11 +309,33 @@ pub fn replicable_blob_set(
|
||||
rules: &[VisibilityRule],
|
||||
is_public: bool,
|
||||
owner_did: &str,
|
||||
) -> Result<HashSet<String>> {
|
||||
allowed_blob_set_for_caller(repo_path, rules, is_public, owner_did, None)
|
||||
}
|
||||
|
||||
/// Reachable blob OIDs that visibility ALLOWS `caller` at some path. The
|
||||
/// caller-aware generalization of `replicable_blob_set` (which is the anonymous
|
||||
/// `caller = None` case). Used by `GET /ipfs/{cid}` to gate fail-closed against
|
||||
/// dangling/unreachable blobs (#126): a blob written via `git hash-object -w`
|
||||
/// but unreferenced is absent from the reachable walk, so it is never in this
|
||||
/// set and the IPFS serve path drops it — even from the owner, who has no path
|
||||
/// to authorize the blob at.
|
||||
///
|
||||
/// A blob reachable at an allowed path is included even when also denied
|
||||
/// elsewhere (its content is readable to this caller elsewhere). Trees and
|
||||
/// commits are NOT included here; the caller decides per object type whether
|
||||
/// the allow-set applies (it does not for trees/commits — KTD3).
|
||||
pub fn allowed_blob_set_for_caller(
|
||||
repo_path: &Path,
|
||||
rules: &[VisibilityRule],
|
||||
is_public: bool,
|
||||
owner_did: &str,
|
||||
caller: Option<&str>,
|
||||
) -> Result<HashSet<String>> {
|
||||
let pairs = blob_paths(repo_path)?;
|
||||
let mut allowed = HashSet::new();
|
||||
for (oid, path) in &pairs {
|
||||
if visibility_check(rules, is_public, owner_did, None, path) == Decision::Allow {
|
||||
if visibility_check(rules, is_public, owner_did, caller, path) == Decision::Allow {
|
||||
allowed.insert(oid.clone());
|
||||
}
|
||||
}
|
||||
@@ -743,6 +765,78 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn allowed_set_excludes_dangling_blob_for_every_caller() {
|
||||
// #126: a blob written via `git hash-object -w` but never referenced has
|
||||
// no path to gate on, so it is absent from the reachable allowed-set —
|
||||
// for anonymous callers, listed readers, AND the owner. The IPFS serve
|
||||
// path relies on this fail-closed property to drop dangling withheld
|
||||
// blobs that the deny-set model leaked.
|
||||
let td = TempDir::new().unwrap();
|
||||
let work = td.path().join("work");
|
||||
std::fs::create_dir_all(work.join("public")).unwrap();
|
||||
std::fs::write(work.join("public/a.txt"), b"public bytes\n").unwrap();
|
||||
let run = |args: &[&str]| {
|
||||
assert!(
|
||||
Command::new("git")
|
||||
.args(args)
|
||||
.current_dir(&work)
|
||||
.status()
|
||||
.unwrap()
|
||||
.success(),
|
||||
"git {args:?} failed"
|
||||
);
|
||||
};
|
||||
run(&["init", "-q"]);
|
||||
run(&["config", "user.email", "t@t"]);
|
||||
run(&["config", "user.name", "t"]);
|
||||
run(&["add", "."]);
|
||||
run(&["commit", "-qm", "init"]);
|
||||
let oid_of = |rev: &str| {
|
||||
let out = Command::new("git")
|
||||
.args(["rev-parse", rev])
|
||||
.current_dir(&work)
|
||||
.output()
|
||||
.unwrap();
|
||||
String::from_utf8_lossy(&out.stdout).trim().to_string()
|
||||
};
|
||||
let public_oid = oid_of("HEAD:public/a.txt");
|
||||
|
||||
std::fs::write(work.join("orphan.bin"), b"DANGLING SECRET\n").unwrap();
|
||||
let dangling_oid = {
|
||||
let out = Command::new("git")
|
||||
.args(["hash-object", "-w", "orphan.bin"])
|
||||
.current_dir(&work)
|
||||
.output()
|
||||
.unwrap();
|
||||
String::from_utf8_lossy(&out.stdout).trim().to_string()
|
||||
};
|
||||
assert!(
|
||||
matches!(dangling_oid.len(), 40 | 64),
|
||||
"precondition: hash-object stored the dangling blob"
|
||||
);
|
||||
|
||||
// Path-scoped rule: /secret/** denied to anon, allowed to a listed reader.
|
||||
let reader = "did:key:zReader";
|
||||
let rules = [rule("/secret/**", &[reader])];
|
||||
|
||||
// Every gate-relevant caller: anonymous, listed reader, owner. None of
|
||||
// them can put the dangling blob in the allowed set — it has no path.
|
||||
for caller in [None, Some(reader), Some(OWNER)] {
|
||||
let allowed = allowed_blob_set_for_caller(&work, &rules, true, OWNER, caller).unwrap();
|
||||
assert!(
|
||||
!allowed.contains(&dangling_oid),
|
||||
"dangling blob must be absent from allowed-set (caller={caller:?})"
|
||||
);
|
||||
// Sanity: the reachable public blob is still in the set for every
|
||||
// caller (the rule does not deny /public/**).
|
||||
assert!(
|
||||
allowed.contains(&public_oid),
|
||||
"reachable public blob must be in allowed-set (caller={caller:?})"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn recipients_are_owner_plus_allowed_readers_only() {
|
||||
let (_td, repo, secret_oid, public_oid) = fixture();
|
||||
|
||||
@@ -49,16 +49,49 @@ impl QueryRoot {
|
||||
&self,
|
||||
ctx: &Context<'_>,
|
||||
repo: Option<String>,
|
||||
#[graphql(default = 20)] limit: i64,
|
||||
#[graphql(
|
||||
default = 20,
|
||||
desc = "Max 200; larger requests return the newest 200 rows (no continuation cursor)."
|
||||
)]
|
||||
limit: i64,
|
||||
) -> Result<Vec<RefUpdateType>> {
|
||||
let db = ctx.data_unchecked::<Arc<Db>>();
|
||||
let updates = db
|
||||
.list_ref_updates_filtered(repo.as_deref(), limit)
|
||||
|
||||
// Gate each row on the same "/" visibility decision the repos resolver
|
||||
// uses, so anonymous callers get no row for a local repo they can't read
|
||||
// (#112). The shared collector applies the fail-closed gate *before* the
|
||||
// limit (paging past dropped private rows) so a small limit still returns
|
||||
// the latest visible events, and keeps this surface byte-identical to the
|
||||
// REST feed (#114). The row slug is peer-supplied, so the pure filter
|
||||
// treats it as untrusted input; remote (no local match) rows pass.
|
||||
let caller = ctx
|
||||
.data::<crate::auth::AuthenticatedDid>()
|
||||
.ok()
|
||||
.map(|d| d.0.as_str());
|
||||
let updates =
|
||||
crate::api::events::collect_visible_ref_updates(db, repo.as_deref(), limit, caller)
|
||||
.await
|
||||
.map_err(|e| async_graphql::Error::new(e.to_string()))?;
|
||||
|
||||
// Resolve the trusted display owner_did per row, identical to the REST
|
||||
// feed: the stored wire value is untrusted, so it is echoed only when it
|
||||
// matches the canonical owner of the local repo the slug names (#P1);
|
||||
// legacy None rows are attributed via an exact unique local match (#P3).
|
||||
// The batch resolver issues at most one query per distinct local repo
|
||||
// rather than one per event row (#P2).
|
||||
let pairs: Vec<(&str, Option<&str>)> = updates
|
||||
.iter()
|
||||
.map(|u| (u.repo.as_str(), u.owner_did.as_deref()))
|
||||
.collect();
|
||||
let owner_dids = db
|
||||
.resolve_ref_update_owner_dids(&pairs)
|
||||
.await
|
||||
.map_err(|e| async_graphql::Error::new(e.to_string()))?;
|
||||
Ok(updates
|
||||
|
||||
let resolved: Vec<RefUpdateType> = updates
|
||||
.into_iter()
|
||||
.map(|u| RefUpdateType {
|
||||
.zip(owner_dids)
|
||||
.map(|(u, owner_did)| RefUpdateType {
|
||||
repo: u.repo,
|
||||
ref_name: u.ref_name,
|
||||
old_sha: u.old_sha,
|
||||
@@ -66,8 +99,10 @@ impl QueryRoot {
|
||||
pusher_did: u.pusher_did,
|
||||
node_did: u.node_did,
|
||||
timestamp: u.timestamp,
|
||||
owner_did,
|
||||
})
|
||||
.collect())
|
||||
.collect();
|
||||
Ok(resolved)
|
||||
}
|
||||
|
||||
async fn tasks(
|
||||
@@ -94,3 +129,294 @@ impl QueryRoot {
|
||||
Ok(t.map(AgentTaskType::from))
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use crate::db::{Db, ReceivedRefUpdate, RepoRecord};
|
||||
use chrono::Utc;
|
||||
use sqlx::PgPool;
|
||||
use std::sync::Arc;
|
||||
|
||||
const OWNER: &str = "did:key:z6MkOwner";
|
||||
|
||||
async fn db(pool: PgPool) -> Arc<Db> {
|
||||
let db = Db::for_testing(pool);
|
||||
db.run_migrations().await.unwrap();
|
||||
Arc::new(db)
|
||||
}
|
||||
|
||||
fn schema(db: Arc<Db>) -> super::super::GitlawbSchema {
|
||||
let (ref_tx, _) = tokio::sync::broadcast::channel(16);
|
||||
let (task_tx, _) = tokio::sync::broadcast::channel(16);
|
||||
super::super::build_schema(db, ref_tx, task_tx)
|
||||
}
|
||||
|
||||
fn repo(id: &str, owner_did: &str, name: &str, is_public: bool) -> RepoRecord {
|
||||
RepoRecord {
|
||||
id: id.into(),
|
||||
name: name.into(),
|
||||
owner_did: owner_did.into(),
|
||||
description: None,
|
||||
is_public,
|
||||
default_branch: "main".into(),
|
||||
created_at: Utc::now(),
|
||||
updated_at: Utc::now(),
|
||||
disk_path: format!("/srv/{id}"),
|
||||
forked_from: None,
|
||||
machine_id: None,
|
||||
}
|
||||
}
|
||||
|
||||
fn ref_row(id: &str, slug: &str) -> ReceivedRefUpdate {
|
||||
ReceivedRefUpdate {
|
||||
id: id.into(),
|
||||
node_did: "did:key:z6MkNode".into(),
|
||||
pusher_did: "did:key:z6MkPusher".into(),
|
||||
repo: slug.into(),
|
||||
ref_name: "refs/heads/main".into(),
|
||||
old_sha: "0".repeat(40),
|
||||
new_sha: "a".repeat(40),
|
||||
timestamp: Utc::now().to_rfc3339(),
|
||||
cert_id: None,
|
||||
received_at: Utc::now().to_rfc3339(),
|
||||
from_peer: "peer1".into(),
|
||||
owner_did: None,
|
||||
}
|
||||
}
|
||||
|
||||
/// Count `refUpdates` rows in a GraphQL response.
|
||||
fn count(resp: &async_graphql::Response) -> usize {
|
||||
assert!(resp.errors.is_empty(), "graphql errors: {:?}", resp.errors);
|
||||
let async_graphql::Value::Object(obj) = &resp.data else {
|
||||
panic!("data not an object: {:?}", resp.data);
|
||||
};
|
||||
let async_graphql::Value::List(rows) = obj.get("refUpdates").expect("refUpdates key")
|
||||
else {
|
||||
panic!("refUpdates not a list");
|
||||
};
|
||||
rows.len()
|
||||
}
|
||||
|
||||
async fn anon(schema: &super::super::GitlawbSchema, query: &str) -> async_graphql::Response {
|
||||
schema.execute(async_graphql::Request::new(query)).await
|
||||
}
|
||||
|
||||
async fn authed(
|
||||
schema: &super::super::GitlawbSchema,
|
||||
query: &str,
|
||||
did: &str,
|
||||
) -> async_graphql::Response {
|
||||
schema
|
||||
.execute(
|
||||
async_graphql::Request::new(query)
|
||||
.data(crate::auth::AuthenticatedDid(did.to_string())),
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
// Scenario 1 — anon must not get a private local repo's row on the
|
||||
// repo:Some branch. This is the load-bearing RED→GREEN case.
|
||||
#[sqlx::test]
|
||||
async fn ref_updates_private_repo_dropped_for_anon(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
db.create_repo(&repo("r1", OWNER, "widget", false))
|
||||
.await
|
||||
.unwrap();
|
||||
db.insert_ref_update(&ref_row("u1", "z6MkOwner/widget"))
|
||||
.await
|
||||
.unwrap();
|
||||
let schema = schema(db);
|
||||
// The GraphQL `repo` arg is the raw slug DB filter, so it must equal the
|
||||
// stored slug to select the row at all — this is the exact leak path.
|
||||
let q = r#"{ refUpdates(repo: "z6MkOwner/widget") { refName newSha pusherDid } }"#;
|
||||
assert_eq!(count(&anon(&schema, q).await), 0);
|
||||
}
|
||||
|
||||
// Scenario 2 — owner still sees their own private repo's row.
|
||||
#[sqlx::test]
|
||||
async fn ref_updates_private_repo_kept_for_owner(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
db.create_repo(&repo("r1", OWNER, "widget", false))
|
||||
.await
|
||||
.unwrap();
|
||||
db.insert_ref_update(&ref_row("u1", "z6MkOwner/widget"))
|
||||
.await
|
||||
.unwrap();
|
||||
let schema = schema(db);
|
||||
let q = r#"{ refUpdates(repo: "z6MkOwner/widget") { refName } }"#;
|
||||
assert_eq!(count(&authed(&schema, q, OWNER).await), 1);
|
||||
}
|
||||
|
||||
// Scenario 3 — unfiltered (repo:None): anon gets only the public row.
|
||||
#[sqlx::test]
|
||||
async fn ref_updates_unfiltered_anon_gets_only_public(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
db.create_repo(&repo("pub", OWNER, "openrepo", true))
|
||||
.await
|
||||
.unwrap();
|
||||
db.create_repo(&repo("priv", OWNER, "secret", false))
|
||||
.await
|
||||
.unwrap();
|
||||
db.insert_ref_update(&ref_row("u_pub", "z6MkOwner/openrepo"))
|
||||
.await
|
||||
.unwrap();
|
||||
db.insert_ref_update(&ref_row("u_priv", "z6MkOwner/secret"))
|
||||
.await
|
||||
.unwrap();
|
||||
let schema = schema(db);
|
||||
let q = r#"{ refUpdates { repo refName ownerDid } }"#;
|
||||
let resp = anon(&schema, q).await;
|
||||
assert_eq!(count(&resp), 1);
|
||||
// The one row returned must be the public repo's with owner_did echoed.
|
||||
let async_graphql::Value::Object(obj) = &resp.data else {
|
||||
unreachable!()
|
||||
};
|
||||
let async_graphql::Value::List(rows) = obj.get("refUpdates").unwrap() else {
|
||||
unreachable!()
|
||||
};
|
||||
let async_graphql::Value::Object(row) = &rows[0] else {
|
||||
unreachable!()
|
||||
};
|
||||
assert_eq!(
|
||||
row.get("repo").unwrap(),
|
||||
&async_graphql::Value::from("z6MkOwner/openrepo")
|
||||
);
|
||||
assert_eq!(
|
||||
row.get("ownerDid").unwrap(),
|
||||
&async_graphql::Value::from(OWNER),
|
||||
"ownerDid must fall back to the local record's owner for legacy rows"
|
||||
);
|
||||
}
|
||||
|
||||
// Scenario 4 — alias fail-closed: private repo's row stored full-DID form.
|
||||
#[sqlx::test]
|
||||
async fn ref_updates_full_did_slug_dropped_for_anon(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
db.create_repo(&repo("r1", "did:key:zABC", "widget", false))
|
||||
.await
|
||||
.unwrap();
|
||||
db.insert_ref_update(&ref_row("u1", "did:key:zABC/widget"))
|
||||
.await
|
||||
.unwrap();
|
||||
let schema = schema(db);
|
||||
// repo:None so the slug is not the DB filter key (which is verbatim);
|
||||
// the gate must still drop it.
|
||||
let q = r#"{ refUpdates { repo } }"#;
|
||||
assert_eq!(count(&anon(&schema, q).await), 0);
|
||||
}
|
||||
|
||||
// Scenario 5 — truncated-key fail-closed: 8-char-prefix owner form.
|
||||
#[sqlx::test]
|
||||
async fn ref_updates_truncated_key_slug_dropped_for_anon(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
db.create_repo(&repo("r1", "did:key:zABCDEFGH", "widget", false))
|
||||
.await
|
||||
.unwrap();
|
||||
db.insert_ref_update(&ref_row("u1", "zABCDEF/widget"))
|
||||
.await
|
||||
.unwrap();
|
||||
let schema = schema(db);
|
||||
let q = r#"{ refUpdates { repo } }"#;
|
||||
assert_eq!(count(&anon(&schema, q).await), 0);
|
||||
}
|
||||
|
||||
// Scenario 6 — remote slug (no local match) is returned to anon.
|
||||
#[sqlx::test]
|
||||
async fn ref_updates_remote_slug_kept_for_anon(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
db.create_repo(&repo("r1", OWNER, "widget", false))
|
||||
.await
|
||||
.unwrap();
|
||||
// Row whose slug matches no local repo (different owner + name).
|
||||
db.insert_ref_update(&ref_row("u1", "zZZZOTHER/gadget"))
|
||||
.await
|
||||
.unwrap();
|
||||
let schema = schema(db);
|
||||
let q = r#"{ refUpdates { repo } }"#;
|
||||
assert_eq!(count(&anon(&schema, q).await), 1);
|
||||
}
|
||||
|
||||
// Scenario 7 (#114 P2) — a small limit must page past the newest rows when
|
||||
// they are private, so the older public rows are still returned. Before the
|
||||
// gate moved ahead of the limit this returned 0 (the newest `limit` rows were
|
||||
// all private and got filtered after the SQL LIMIT). RED→GREEN.
|
||||
#[sqlx::test]
|
||||
async fn ref_updates_small_limit_pages_past_newest_private(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
db.create_repo(&repo("pub", OWNER, "openrepo", true))
|
||||
.await
|
||||
.unwrap();
|
||||
db.create_repo(&repo("priv", OWNER, "secret", false))
|
||||
.await
|
||||
.unwrap();
|
||||
// 3 older PUBLIC rows …
|
||||
for i in 0..3 {
|
||||
let mut r = ref_row(&format!("pub{i}"), "z6MkOwner/openrepo");
|
||||
r.timestamp = format!("2026-07-01T10:00:0{i}+00:00");
|
||||
db.insert_ref_update(&r).await.unwrap();
|
||||
}
|
||||
// … then 5 NEWER PRIVATE rows (the newest in the feed).
|
||||
for i in 0..5 {
|
||||
let mut r = ref_row(&format!("priv{i}"), "z6MkOwner/secret");
|
||||
r.timestamp = format!("2026-07-01T10:00:1{i}+00:00");
|
||||
db.insert_ref_update(&r).await.unwrap();
|
||||
}
|
||||
let schema = schema(db);
|
||||
// limit 3 < the 5 newest (all private): anon must still get 3 public rows.
|
||||
let q = r#"{ refUpdates(limit: 3) { repo } }"#;
|
||||
let resp = anon(&schema, q).await;
|
||||
assert_eq!(count(&resp), 3, "paging must reach the older public rows");
|
||||
let async_graphql::Value::Object(obj) = &resp.data else {
|
||||
unreachable!()
|
||||
};
|
||||
let async_graphql::Value::List(rows) = obj.get("refUpdates").unwrap() else {
|
||||
unreachable!()
|
||||
};
|
||||
for row in rows {
|
||||
let async_graphql::Value::Object(r) = row else {
|
||||
unreachable!()
|
||||
};
|
||||
assert_eq!(
|
||||
r.get("repo").unwrap(),
|
||||
&async_graphql::Value::from("z6MkOwner/openrepo"),
|
||||
"every returned row must be the public repo's"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// Scenario 8 — a quarantined mirror is withheld on the GraphQL surface too.
|
||||
// Guards that the resolver keeps delegating to the shared collector (where the
|
||||
// quarantine fold lives); a REST-only test would miss a resolver that stopped.
|
||||
#[sqlx::test]
|
||||
async fn ref_updates_quarantined_mirror_dropped_for_anon(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
db.upsert_mirror_repo("z6MkQuar", "secret", "/tmp/q", None, true)
|
||||
.await
|
||||
.unwrap();
|
||||
db.insert_ref_update(&ref_row("u1", "z6MkQuar/secret"))
|
||||
.await
|
||||
.unwrap();
|
||||
let schema = schema(db);
|
||||
let q = r#"{ refUpdates { repo } }"#;
|
||||
assert_eq!(count(&anon(&schema, q).await), 0);
|
||||
}
|
||||
|
||||
// Scenario 8b — the GraphQL surface also withholds a quarantined repo from an
|
||||
// authenticated OWNER, not just anon. Without the collector's quarantine drop
|
||||
// the owner short-circuit in visibility_check keeps the row on this surface
|
||||
// too, so the REST owner test alone would not guard the resolver.
|
||||
#[sqlx::test]
|
||||
async fn ref_updates_quarantined_repo_dropped_for_owner(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
db.create_repo(&repo("q1", "did:key:z6MkQuar", "secret", false))
|
||||
.await
|
||||
.unwrap();
|
||||
db.set_repo_quarantine("q1", true).await.unwrap();
|
||||
db.insert_ref_update(&ref_row("u1", "z6MkQuar/secret"))
|
||||
.await
|
||||
.unwrap();
|
||||
let schema = schema(db);
|
||||
let q = r#"{ refUpdates { repo } }"#;
|
||||
assert_eq!(count(&authed(&schema, q, "did:key:z6MkQuar").await), 0);
|
||||
}
|
||||
}
|
||||
@@ -11,6 +11,15 @@ pub struct SubscriptionRoot;
|
||||
|
||||
#[Subscription]
|
||||
impl SubscriptionRoot {
|
||||
/// Live ref-update stream. `/graphql/ws` is mounted outside the
|
||||
/// `optional_signature` layer, so this resolver has NO caller identity and
|
||||
/// cannot gate per-subscriber — it relays whatever enters the broadcast
|
||||
/// channel to any anonymous client. Its visibility safety therefore rests
|
||||
/// entirely on the WRITE side: the push handler only sends a
|
||||
/// `RefUpdateBroadcast` for repos the anonymous public may read (inside its
|
||||
/// `if announce` block, `api/repos.rs`). This is a single-point invariant —
|
||||
/// any new sender to `ref_update_tx` MUST be `announce`-gated, or private-repo
|
||||
/// ref metadata leaks here to unauthenticated subscribers (#112/#114 class).
|
||||
async fn ref_updates(
|
||||
&self,
|
||||
ctx: &Context<'_>,
|
||||
@@ -30,6 +39,7 @@ impl SubscriptionRoot {
|
||||
pusher_did: ev.pusher_did,
|
||||
node_did: ev.node_did,
|
||||
timestamp: ev.timestamp,
|
||||
owner_did: Some(ev.owner_did),
|
||||
}),
|
||||
_ => None,
|
||||
}
|
||||
|
||||
@@ -57,6 +57,7 @@ pub struct RefUpdateType {
|
||||
pub pusher_did: String,
|
||||
pub node_did: String,
|
||||
pub timestamp: String,
|
||||
pub owner_did: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(SimpleObject, Clone)]
|
||||
|
||||
@@ -237,9 +237,13 @@ impl ProofGuard {
|
||||
match self.0 {
|
||||
Some(p) => {
|
||||
if !db.consume_proof_jti(&p.jti, p.exp).await? {
|
||||
return Err(AppError::IcaptchaProofRequired(
|
||||
"iCaptcha proof already used (replay); solve a fresh challenge".to_string(),
|
||||
));
|
||||
let (url, level) = url_and_level();
|
||||
return Err(AppError::IcaptchaProofRequired {
|
||||
message: "iCaptcha proof already used (replay); solve a fresh challenge"
|
||||
.to_string(),
|
||||
url,
|
||||
level,
|
||||
});
|
||||
}
|
||||
Ok(Some(p))
|
||||
}
|
||||
@@ -265,10 +269,23 @@ pub fn verify_request(headers: &HeaderMap, did: &str) -> Result<ProofGuard, AppE
|
||||
}
|
||||
|
||||
fn reject_error(v: &Verifier, reason: &str) -> AppError {
|
||||
AppError::IcaptchaProofRequired(format!(
|
||||
"iCaptcha proof required ({reason}). Solve a challenge at {} for level >= {} and resend with the {} header.",
|
||||
v.url, v.required_level, PROOF_HEADER
|
||||
))
|
||||
AppError::IcaptchaProofRequired {
|
||||
message: format!(
|
||||
"iCaptcha proof required ({reason}). Solve a challenge at {} for level >= {} and resend with the {} header.",
|
||||
v.url, v.required_level, PROOF_HEADER
|
||||
),
|
||||
url: v.url.clone(),
|
||||
level: v.required_level,
|
||||
}
|
||||
}
|
||||
|
||||
/// iCaptcha service url + required level for error responses, read from the
|
||||
/// initialized verifier (falls back to defaults if somehow uninitialized).
|
||||
fn url_and_level() -> (String, u32) {
|
||||
VERIFIER
|
||||
.get()
|
||||
.map(|v| (v.url.clone(), v.required_level))
|
||||
.unwrap_or_else(|| ("https://icaptcha.gitlawb.com".to_string(), 3))
|
||||
}
|
||||
|
||||
/// Mode-aware decision. Pure and IO-free (no DB; clock injected via `now`) so it
|
||||
|
||||
+533
-91
@@ -24,8 +24,14 @@ mod test_support;
|
||||
mod visibility;
|
||||
mod webhooks;
|
||||
|
||||
use anyhow::{Context, Result};
|
||||
use anyhow::{anyhow, Context, Result};
|
||||
use axum::extract::State;
|
||||
use axum::http::StatusCode;
|
||||
use axum::response::IntoResponse;
|
||||
use axum::routing::get;
|
||||
use axum::{Json, Router};
|
||||
use clap::Parser;
|
||||
use std::sync::atomic::{AtomicU64, Ordering};
|
||||
use std::sync::Arc;
|
||||
use tokio::net::TcpListener;
|
||||
use tokio::sync::watch;
|
||||
@@ -38,6 +44,20 @@ use config::Config;
|
||||
use db::Db;
|
||||
use state::AppState;
|
||||
|
||||
#[derive(Clone)]
|
||||
struct DegradedState {
|
||||
node_did: String,
|
||||
db_startup: Arc<DbStartupStatus>,
|
||||
}
|
||||
|
||||
/// Two independent counters with no cross-field invariant — atomics, not a
|
||||
/// lock, so the retry loop and the degraded handlers never contend.
|
||||
#[derive(Default)]
|
||||
struct DbStartupStatus {
|
||||
attempts: AtomicU64,
|
||||
next_retry_secs: AtomicU64,
|
||||
}
|
||||
|
||||
#[tokio::main]
|
||||
async fn main() -> Result<()> {
|
||||
tracing_subscriber::fmt()
|
||||
@@ -76,21 +96,101 @@ async fn main() -> Result<()> {
|
||||
env!("CARGO_PKG_VERSION")
|
||||
);
|
||||
info!("╚══════════════════════════════════════════╝");
|
||||
info!(did = %node_did, "node identity");
|
||||
info!(addr = %config.bind_addr(), "listening");
|
||||
|
||||
// Process-wide shutdown signal. One sender lives in AppState (cloned
|
||||
// into every handler); main() keeps a clone and flips it on SIGINT
|
||||
// or SIGTERM. Tasks that hold a watch::Receiver get notified at
|
||||
// their next await point.
|
||||
let (shutdown_tx, _shutdown_rx_for_main) = watch::channel(false);
|
||||
spawn_shutdown_signal(shutdown_tx.clone());
|
||||
|
||||
// Connect to PostgreSQL database
|
||||
let db = Arc::new(
|
||||
Db::connect(&config.database_url)
|
||||
.await
|
||||
.context("failed to connect to database")?,
|
||||
);
|
||||
info!(did = %node_did, "node identity");
|
||||
info!(addr = %config.bind_addr(), "binding HTTP listener");
|
||||
|
||||
// Bind HTTP once, before dependency initialization, and keep this socket
|
||||
// for the life of the process. The degraded server accepts on a dup of the
|
||||
// same socket, so the degraded→full handoff never closes the port: while
|
||||
// the full server initializes, connections queue in the shared backlog
|
||||
// instead of being refused.
|
||||
let listener = TcpListener::bind(config.bind_addr())
|
||||
.await
|
||||
.with_context(|| format!("failed to bind to {}", config.bind_addr()))?;
|
||||
let full_std_listener = listener.into_std()?;
|
||||
let degraded_listener = TcpListener::from_std(
|
||||
full_std_listener
|
||||
.try_clone()
|
||||
.context("failed to clone HTTP listener for degraded server")?,
|
||||
)?;
|
||||
|
||||
// Metrics must stay observable during a database outage — the degraded
|
||||
// window is exactly when dashboards need data — so this listener starts
|
||||
// before the DB connects.
|
||||
let metrics_handle = if !config.metrics_addr.is_empty() {
|
||||
match spawn_metrics_server(&config.metrics_addr, shutdown_tx.subscribe()).await {
|
||||
Ok(handle) => {
|
||||
info!(addr = %config.metrics_addr, "metrics endpoint listening");
|
||||
Some(handle)
|
||||
}
|
||||
Err(e) => {
|
||||
warn!(err = %e, addr = %config.metrics_addr, "failed to start metrics endpoint — continuing without");
|
||||
None
|
||||
}
|
||||
}
|
||||
} else {
|
||||
info!("metrics endpoint disabled (GITLAWB_METRICS_ADDR not set)");
|
||||
None
|
||||
};
|
||||
|
||||
let db_startup = Arc::new(DbStartupStatus::default());
|
||||
let (db_ready_tx, db_ready_rx) = watch::channel(false);
|
||||
let mut degraded_handle = tokio::spawn(run_degraded_server(
|
||||
degraded_listener,
|
||||
node_did.to_string(),
|
||||
Arc::clone(&db_startup),
|
||||
db_ready_rx,
|
||||
shutdown_tx.subscribe(),
|
||||
));
|
||||
|
||||
// Connect to PostgreSQL database. A transient outage or bad secret should
|
||||
// not crash-loop the process and hammer the database provider; permanent
|
||||
// misconfiguration surfaces through error-level logs and the /ready check.
|
||||
let db = tokio::select! {
|
||||
db = connect_db_with_retry(&config, Arc::clone(&db_startup), shutdown_tx.subscribe()) => {
|
||||
match db {
|
||||
Some(db) => db,
|
||||
None => {
|
||||
// Shutdown requested while waiting for the database. The
|
||||
// degraded server only serves one-shot 503s — abort it
|
||||
// rather than drain, so a slow client can't stall exit.
|
||||
degraded_handle.abort();
|
||||
return Ok(());
|
||||
}
|
||||
}
|
||||
}
|
||||
degraded = &mut degraded_handle => {
|
||||
if *shutdown_tx.borrow() {
|
||||
return Ok(());
|
||||
}
|
||||
return match degraded {
|
||||
Ok(Ok(())) => Err(anyhow!("degraded HTTP server stopped before database became ready")),
|
||||
Ok(Err(err)) => Err(err.context("degraded HTTP server failed")),
|
||||
Err(err) => Err(anyhow!("degraded HTTP server task failed: {err}")),
|
||||
};
|
||||
}
|
||||
};
|
||||
|
||||
// Flip the degraded server into graceful shutdown, but do NOT await the
|
||||
// drain: one slow in-flight request must not delay the full server, and
|
||||
// the shared socket means there is no port gap to cover. The drain
|
||||
// finishes (and logs) in the background.
|
||||
db_ready_tx.send(true).ok();
|
||||
tokio::spawn(async move {
|
||||
match degraded_handle.await {
|
||||
Ok(Ok(())) => {}
|
||||
Ok(Err(err)) => warn!(err = %err, "degraded HTTP server exited with error"),
|
||||
Err(err) => warn!(err = %err, "degraded HTTP server task failed"),
|
||||
}
|
||||
});
|
||||
info!(addr = %config.bind_addr(), "database ready; starting full HTTP server");
|
||||
|
||||
// Prune peer rows that point back at this node (stale self-loop entries)
|
||||
if let Some(public_url) = config.public_url.as_deref() {
|
||||
@@ -145,16 +245,8 @@ async fn main() -> Result<()> {
|
||||
None
|
||||
};
|
||||
|
||||
// Do not follow redirects: this client fans out to peer-supplied URLs
|
||||
// (sync trigger, profile/repo fetches). A peer answering `302 Location:
|
||||
// http://127.0.0.1/` would otherwise bypass the announce-time public-URL
|
||||
// check and turn the redirect into an SSRF.
|
||||
let http_client = Arc::new(
|
||||
reqwest::Client::builder()
|
||||
.timeout(std::time::Duration::from_secs(10))
|
||||
.redirect(reqwest::redirect::Policy::none())
|
||||
.build()?,
|
||||
);
|
||||
// Shared no-redirect HTTP client. See build_http_client for the SSRF rationale.
|
||||
let http_client = Arc::new(build_http_client()?);
|
||||
|
||||
let (ref_update_tx, _) = tokio::sync::broadcast::channel::<state::RefUpdateBroadcast>(256);
|
||||
let (task_event_tx, _) = tokio::sync::broadcast::channel::<state::TaskEventBroadcast>(256);
|
||||
@@ -190,7 +282,79 @@ async fn main() -> Result<()> {
|
||||
let repo_store =
|
||||
git::repo_store::RepoStore::new(config.repos_dir.clone(), tigris, db.pool().clone());
|
||||
|
||||
let rate_limiter = rate_limit::RateLimiter::new(10, std::time::Duration::from_secs(3600));
|
||||
// Per-DID limiter for the creation endpoints. Keyed on the authenticated
|
||||
// DID (attacker-varied), so bound its key set to cap memory.
|
||||
let rate_limiter =
|
||||
rate_limit::RateLimiter::new_bounded(10, std::time::Duration::from_secs(3600), 200_000);
|
||||
|
||||
// Per-client-IP flood brake for the creation endpoints. The per-DID limiter
|
||||
// above is bypassed by a DID farm (one throwaway did:key per repo), which is
|
||||
// exactly how the recurring spam-repo floods get past both it and the
|
||||
// iCaptcha gate. Keyed on the resolved client IP so a single-source flood is
|
||||
// capped regardless of how many identities it mints. Sized well above any
|
||||
// legitimate per-IP creation rate; GITLAWB_CREATE_RATE_LIMIT overrides, 0
|
||||
// disables. Bounded key set — the key is a client-influenced IP.
|
||||
let create_limit = std::env::var("GITLAWB_CREATE_RATE_LIMIT")
|
||||
.ok()
|
||||
.and_then(|v| v.trim().parse::<usize>().ok())
|
||||
.unwrap_or(120);
|
||||
let create_ip_rate_limiter = rate_limit::RateLimiter::new_bounded(
|
||||
create_limit,
|
||||
std::time::Duration::from_secs(3600),
|
||||
200_000,
|
||||
);
|
||||
if create_limit == 0 {
|
||||
tracing::warn!("GITLAWB_CREATE_RATE_LIMIT=0 — per-IP creation rate limiting disabled");
|
||||
}
|
||||
|
||||
// Push-path flood brake: max git-receive-pack requests per client IP per
|
||||
// hour (counts both the info/refs advertisement and the push POST). Sized
|
||||
// for heavy agent automation while still stopping flood traffic (the June
|
||||
// 2026 attack pushed several times per second per IP). GITLAWB_PUSH_RATE_LIMIT
|
||||
// overrides; 0 disables. Bounded key set — the key is a client-influenced IP.
|
||||
let push_limit = std::env::var("GITLAWB_PUSH_RATE_LIMIT")
|
||||
.ok()
|
||||
.and_then(|v| v.trim().parse::<usize>().ok())
|
||||
.unwrap_or(600);
|
||||
let push_rate_limiter = rate_limit::RateLimiter::new_bounded(
|
||||
push_limit,
|
||||
std::time::Duration::from_secs(3600),
|
||||
200_000,
|
||||
);
|
||||
if push_limit == 0 {
|
||||
tracing::warn!("GITLAWB_PUSH_RATE_LIMIT=0 — per-IP push rate limiting disabled");
|
||||
}
|
||||
|
||||
// Which forwarded header the edge is trusted to set. Default None (trust
|
||||
// nothing, key on the socket peer). Fly nodes set GITLAWB_TRUSTED_PROXY=fly;
|
||||
// a node behind Caddy/NGINX sets it to x-forwarded-for.
|
||||
let push_limiter_trust = rate_limit::TrustedProxy::from_env_value(
|
||||
&std::env::var("GITLAWB_TRUSTED_PROXY").unwrap_or_default(),
|
||||
);
|
||||
tracing::info!(trust = ?push_limiter_trust, push_limit, "push rate limiter configured");
|
||||
|
||||
// Peer-sync flood brakes, keyed on the resolved client IP (per-DID is useless
|
||||
// here — a did:key farm self-registers). Two buckets so an unsigned notify
|
||||
// flood can't drain the signed trigger caller's quota (#82). Bounded key sets
|
||||
// (the key is a client-influenced IP); 0 disables each.
|
||||
let sync_trigger_rate_limiter = rate_limit::RateLimiter::new_bounded(
|
||||
config.sync_trigger_rate_limit,
|
||||
std::time::Duration::from_secs(3600),
|
||||
200_000,
|
||||
);
|
||||
let peer_write_rate_limiter = rate_limit::RateLimiter::new_bounded(
|
||||
config.peer_write_rate_limit,
|
||||
std::time::Duration::from_secs(3600),
|
||||
200_000,
|
||||
);
|
||||
if config.sync_trigger_rate_limit == 0 {
|
||||
tracing::warn!(
|
||||
"GITLAWB_SYNC_TRIGGER_RATE_LIMIT=0 — /sync/trigger IP rate limiting disabled"
|
||||
);
|
||||
}
|
||||
if config.peer_write_rate_limit == 0 {
|
||||
tracing::warn!("GITLAWB_PEER_WRITE_RATE_LIMIT=0 — peer-write IP rate limiting disabled");
|
||||
}
|
||||
|
||||
// Initialize the iCaptcha proof gate (inert unless ICAPTCHA_MODE is set).
|
||||
icaptcha::init().await;
|
||||
@@ -208,6 +372,11 @@ async fn main() -> Result<()> {
|
||||
machine_id,
|
||||
repo_store,
|
||||
rate_limiter,
|
||||
create_ip_rate_limiter,
|
||||
push_rate_limiter,
|
||||
push_limiter_trust,
|
||||
sync_trigger_rate_limiter,
|
||||
peer_write_rate_limiter,
|
||||
shutdown_tx: shutdown_tx.clone(),
|
||||
};
|
||||
|
||||
@@ -237,37 +406,13 @@ async fn main() -> Result<()> {
|
||||
});
|
||||
}
|
||||
|
||||
// Spawn a task that flips the shutdown signal on SIGINT or SIGTERM.
|
||||
// On Unix, both signals are handled. On Windows, only Ctrl-C is
|
||||
// supported by tokio::signal::ctrl_c.
|
||||
{
|
||||
let tx = shutdown_tx.clone();
|
||||
tokio::spawn(async move {
|
||||
#[cfg(unix)]
|
||||
{
|
||||
use tokio::signal::unix::{signal as unix_signal, SignalKind};
|
||||
let mut sigterm =
|
||||
unix_signal(SignalKind::terminate()).expect("install SIGTERM handler");
|
||||
let mut sigint =
|
||||
unix_signal(SignalKind::interrupt()).expect("install SIGINT handler");
|
||||
tokio::select! {
|
||||
_ = sigterm.recv() => info!("SIGTERM received, shutting down"),
|
||||
_ = sigint.recv() => info!("SIGINT received, shutting down"),
|
||||
}
|
||||
}
|
||||
#[cfg(not(unix))]
|
||||
{
|
||||
use tokio::signal;
|
||||
let _ = signal::ctrl_c().await;
|
||||
info!("Ctrl-C received, shutting down");
|
||||
}
|
||||
tx.send(true).ok();
|
||||
});
|
||||
}
|
||||
|
||||
// Periodic cleanup of expired rate limit entries + consumed-proof ledger
|
||||
{
|
||||
let rl = state.rate_limiter.clone();
|
||||
let create_ip_rl = state.create_ip_rate_limiter.clone();
|
||||
let push_rl = state.push_rate_limiter.clone();
|
||||
let sync_trigger_rl = state.sync_trigger_rate_limiter.clone();
|
||||
let peer_write_rl = state.peer_write_rate_limiter.clone();
|
||||
let db = state.db.clone();
|
||||
let mut shutdown_rx = state.subscribe_shutdown();
|
||||
tokio::spawn(async move {
|
||||
@@ -275,6 +420,10 @@ async fn main() -> Result<()> {
|
||||
tokio::select! {
|
||||
_ = tokio::time::sleep(std::time::Duration::from_secs(300)) => {
|
||||
rl.cleanup().await;
|
||||
create_ip_rl.cleanup().await;
|
||||
push_rl.cleanup().await;
|
||||
sync_trigger_rl.cleanup().await;
|
||||
peer_write_rl.cleanup().await;
|
||||
let now = std::time::SystemTime::now()
|
||||
.duration_since(std::time::UNIX_EPOCH)
|
||||
.map(|d| d.as_secs() as i64)
|
||||
@@ -294,9 +443,10 @@ async fn main() -> Result<()> {
|
||||
}
|
||||
|
||||
let router = server::build_router(state.clone());
|
||||
let listener = TcpListener::bind(config.bind_addr())
|
||||
.await
|
||||
.with_context(|| format!("failed to bind to {}", config.bind_addr()))?;
|
||||
// Re-register the socket bound at startup — same fd, so there was never a
|
||||
// moment with the port closed between the degraded and full servers.
|
||||
let listener = TcpListener::from_std(full_std_listener)
|
||||
.context("failed to re-register HTTP listener with the runtime")?;
|
||||
|
||||
info!("✓ node started — did:{}", node_did);
|
||||
info!(" repos dir: {}", config.repos_dir.display());
|
||||
@@ -305,23 +455,6 @@ async fn main() -> Result<()> {
|
||||
&config.database_url.split('@').next_back().unwrap_or("?")
|
||||
);
|
||||
|
||||
// Optional Prometheus metrics listener on a separate port.
|
||||
let metrics_handle = if !config.metrics_addr.is_empty() {
|
||||
match spawn_metrics_server(&config.metrics_addr, state.clone()).await {
|
||||
Ok(handle) => {
|
||||
info!(addr = %config.metrics_addr, "metrics endpoint listening");
|
||||
Some(handle)
|
||||
}
|
||||
Err(e) => {
|
||||
warn!(err = %e, addr = %config.metrics_addr, "failed to start metrics endpoint — continuing without");
|
||||
None
|
||||
}
|
||||
}
|
||||
} else {
|
||||
info!("metrics endpoint disabled (GITLAWB_METRICS_ADDR not set)");
|
||||
None
|
||||
};
|
||||
|
||||
// Publish our DID record to the Kademlia DHT shortly after startup
|
||||
if let Some(p2p) = &state.p2p {
|
||||
let did_record = p2p::DidRecord {
|
||||
@@ -399,19 +532,25 @@ async fn main() -> Result<()> {
|
||||
let grace = std::time::Duration::from_secs(config.shutdown_grace_secs);
|
||||
info!(grace_secs = config.shutdown_grace_secs, "axum server ready");
|
||||
|
||||
let serve_result = axum::serve(listener, router)
|
||||
.with_graceful_shutdown(async move {
|
||||
let mut rx = shutdown_signal_for_axum;
|
||||
// Wait until the watcher flips to true, then return so axum
|
||||
// can begin draining.
|
||||
while !*rx.borrow_and_update() {
|
||||
if rx.changed().await.is_err() {
|
||||
// Sender dropped — treat as shutdown.
|
||||
break;
|
||||
}
|
||||
// `into_make_service_with_connect_info` exposes the socket peer address as
|
||||
// `ConnectInfo<SocketAddr>` so the push limiter can key on the real client
|
||||
// when no trusted proxy header applies (see `rate_limit::client_key`).
|
||||
let serve_result = axum::serve(
|
||||
listener,
|
||||
router.into_make_service_with_connect_info::<std::net::SocketAddr>(),
|
||||
)
|
||||
.with_graceful_shutdown(async move {
|
||||
let mut rx = shutdown_signal_for_axum;
|
||||
// Wait until the watcher flips to true, then return so axum
|
||||
// can begin draining.
|
||||
while !*rx.borrow_and_update() {
|
||||
if rx.changed().await.is_err() {
|
||||
// Sender dropped — treat as shutdown.
|
||||
break;
|
||||
}
|
||||
})
|
||||
.await;
|
||||
}
|
||||
})
|
||||
.await;
|
||||
|
||||
// Server has stopped accepting new connections and drained in-flight
|
||||
// requests. Tear the rest of the system down.
|
||||
@@ -425,12 +564,224 @@ async fn main() -> Result<()> {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn spawn_shutdown_signal(tx: watch::Sender<bool>) {
|
||||
tokio::spawn(async move {
|
||||
#[cfg(unix)]
|
||||
{
|
||||
use tokio::signal::unix::{signal as unix_signal, SignalKind};
|
||||
let mut sigterm =
|
||||
unix_signal(SignalKind::terminate()).expect("install SIGTERM handler");
|
||||
let mut sigint = unix_signal(SignalKind::interrupt()).expect("install SIGINT handler");
|
||||
tokio::select! {
|
||||
_ = sigterm.recv() => info!("SIGTERM received, shutting down"),
|
||||
_ = sigint.recv() => info!("SIGINT received, shutting down"),
|
||||
}
|
||||
}
|
||||
#[cfg(not(unix))]
|
||||
{
|
||||
use tokio::signal;
|
||||
let _ = signal::ctrl_c().await;
|
||||
info!("Ctrl-C received, shutting down");
|
||||
}
|
||||
tx.send(true).ok();
|
||||
});
|
||||
}
|
||||
|
||||
async fn connect_db_with_retry(
|
||||
config: &Config,
|
||||
db_startup: Arc<DbStartupStatus>,
|
||||
mut shutdown_rx: watch::Receiver<bool>,
|
||||
) -> Option<Arc<Db>> {
|
||||
let initial_retry_secs = config.db_retry_initial_secs;
|
||||
let max_retry_secs = config.db_retry_max_secs.max(initial_retry_secs);
|
||||
let acquire_timeout = std::time::Duration::from_secs(config.db_acquire_timeout_secs);
|
||||
let attempt_timeout = std::time::Duration::from_secs(config.db_connect_timeout_secs);
|
||||
let mut attempts = 0_u64;
|
||||
|
||||
loop {
|
||||
if *shutdown_rx.borrow() {
|
||||
return None;
|
||||
}
|
||||
|
||||
attempts = attempts.saturating_add(1);
|
||||
db_startup.attempts.store(attempts, Ordering::Relaxed);
|
||||
|
||||
// Bound the whole attempt, not just the pool connect: migrations
|
||||
// block on a cross-instance advisory lock, and an unbounded wait
|
||||
// there would wedge this loop — no retries, no logs, no recovery.
|
||||
// Timing out and retrying is safe; migrations are idempotent.
|
||||
let attempt = match tokio::time::timeout(
|
||||
attempt_timeout,
|
||||
Db::connect(
|
||||
&config.database_url,
|
||||
config.db_max_connections,
|
||||
acquire_timeout,
|
||||
),
|
||||
)
|
||||
.await
|
||||
{
|
||||
Ok(result) => result,
|
||||
Err(_) => Err(anyhow!(
|
||||
"connect + migrate attempt exceeded {}s (GITLAWB_DB_CONNECT_TIMEOUT_SECS); \
|
||||
is another instance holding the migration lock?",
|
||||
attempt_timeout.as_secs()
|
||||
)),
|
||||
};
|
||||
|
||||
match attempt {
|
||||
Ok(db) => {
|
||||
info!(attempts, "database connection established");
|
||||
return Some(Arc::new(db));
|
||||
}
|
||||
Err(err) => {
|
||||
// A bad DATABASE_URL or rejected credentials won't heal on
|
||||
// their own. Still retry (exiting would crash-loop and hammer
|
||||
// the provider — and take liveness down with it), but log at
|
||||
// error level and skip straight to the maximum backoff; the
|
||||
// /ready health check is what surfaces this to deploys.
|
||||
let permanent = is_likely_permanent_db_error(&err);
|
||||
let retry_secs = if permanent {
|
||||
max_retry_secs
|
||||
} else {
|
||||
database_retry_delay_secs(initial_retry_secs, max_retry_secs, attempts)
|
||||
};
|
||||
db_startup
|
||||
.next_retry_secs
|
||||
.store(retry_secs, Ordering::Relaxed);
|
||||
if permanent {
|
||||
tracing::error!(
|
||||
attempts,
|
||||
retry_secs,
|
||||
err = %err,
|
||||
"database rejected our configuration (bad DATABASE_URL or credentials?) — retrying, but operator action is likely required"
|
||||
);
|
||||
} else {
|
||||
warn!(
|
||||
attempts,
|
||||
retry_secs,
|
||||
err = %err,
|
||||
"database unavailable during startup; retrying"
|
||||
);
|
||||
}
|
||||
|
||||
tokio::select! {
|
||||
_ = tokio::time::sleep(std::time::Duration::from_secs(retry_secs)) => {}
|
||||
changed = shutdown_rx.changed() => {
|
||||
if changed.is_err() || *shutdown_rx.borrow() {
|
||||
return None;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Errors that indicate misconfiguration rather than a transient outage: a
|
||||
/// malformed DATABASE_URL, or a server that answered and rejected us —
|
||||
/// Postgres error class 28xxx (invalid authorization) or 3D000 (database
|
||||
/// does not exist). Best-effort: an error that anyhow can't downcast back to
|
||||
/// sqlx just counts as transient.
|
||||
fn is_likely_permanent_db_error(err: &anyhow::Error) -> bool {
|
||||
match err.downcast_ref::<sqlx::Error>() {
|
||||
Some(sqlx::Error::Configuration(_)) => true,
|
||||
Some(sqlx::Error::Database(db)) => db
|
||||
.code()
|
||||
.map(|c| c.starts_with("28") || c.starts_with("3D"))
|
||||
.unwrap_or(false),
|
||||
_ => false,
|
||||
}
|
||||
}
|
||||
|
||||
fn database_retry_delay_secs(initial_secs: u64, max_secs: u64, attempts: u64) -> u64 {
|
||||
// The exponent bound only keeps the u32 cast safe — max_secs is the real
|
||||
// (operator-configurable) cap, and saturating math handles overflow.
|
||||
let exponent = attempts.saturating_sub(1).min(63) as u32;
|
||||
initial_secs
|
||||
.saturating_mul(2_u64.saturating_pow(exponent))
|
||||
.min(max_secs)
|
||||
}
|
||||
|
||||
async fn run_degraded_server(
|
||||
listener: TcpListener,
|
||||
node_did: String,
|
||||
db_startup: Arc<DbStartupStatus>,
|
||||
mut db_ready_rx: watch::Receiver<bool>,
|
||||
mut shutdown_rx: watch::Receiver<bool>,
|
||||
) -> Result<()> {
|
||||
let addr = listener.local_addr().ok();
|
||||
let router = build_degraded_router(node_did, db_startup);
|
||||
info!(?addr, "degraded HTTP server ready");
|
||||
|
||||
axum::serve(listener, router)
|
||||
.with_graceful_shutdown(async move {
|
||||
// wait_for resolves on predicate-true or sender-drop; either way
|
||||
// this phase is over.
|
||||
tokio::select! {
|
||||
_ = db_ready_rx.wait_for(|ready| *ready) => {}
|
||||
_ = shutdown_rx.wait_for(|stop| *stop) => {}
|
||||
}
|
||||
})
|
||||
.await?;
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn build_degraded_router(node_did: String, db_startup: Arc<DbStartupStatus>) -> Router {
|
||||
let state = DegradedState {
|
||||
node_did,
|
||||
db_startup,
|
||||
};
|
||||
// Everything answers 503 with the same body — including /health and
|
||||
// /ready, so peer pings (which treat any 2xx /health as alive) and
|
||||
// uptime monitors correctly see a node that cannot serve traffic.
|
||||
// `/` additionally carries the node identity for probing peers.
|
||||
Router::new()
|
||||
.route("/", get(degraded_node_info))
|
||||
.fallback(degraded_unavailable)
|
||||
.with_state(state)
|
||||
}
|
||||
|
||||
/// One source of truth for the degraded 503 body, sharing the error
|
||||
/// vocabulary with error.rs so clients see the same code/message for
|
||||
/// "database unavailable" regardless of which phase produced it.
|
||||
fn degraded_body(db_startup: &DbStartupStatus) -> serde_json::Value {
|
||||
serde_json::json!({
|
||||
"status": "degraded",
|
||||
"database": "initializing",
|
||||
"error": error::DB_UNAVAILABLE_CODE,
|
||||
"message": error::DB_UNAVAILABLE_MESSAGE,
|
||||
"db_attempts": db_startup.attempts.load(Ordering::Relaxed),
|
||||
"db_next_retry_secs": db_startup.next_retry_secs.load(Ordering::Relaxed),
|
||||
})
|
||||
}
|
||||
|
||||
async fn degraded_node_info(State(state): State<DegradedState>) -> impl IntoResponse {
|
||||
let mut body = degraded_body(&state.db_startup);
|
||||
if let Some(obj) = body.as_object_mut() {
|
||||
obj.insert("name".into(), "gitlawb-node".into());
|
||||
obj.insert("version".into(), env!("CARGO_PKG_VERSION").into());
|
||||
obj.insert("did".into(), state.node_did.clone().into());
|
||||
}
|
||||
(StatusCode::SERVICE_UNAVAILABLE, Json(body))
|
||||
}
|
||||
|
||||
async fn degraded_unavailable(State(state): State<DegradedState>) -> impl IntoResponse {
|
||||
(
|
||||
StatusCode::SERVICE_UNAVAILABLE,
|
||||
Json(degraded_body(&state.db_startup)),
|
||||
)
|
||||
}
|
||||
|
||||
/// Spawn a small axum router that exposes only `GET /metrics` on its own
|
||||
/// listener. Returns the JoinHandle so `main()` can abort it on shutdown.
|
||||
/// This is deliberately separate from the main router so the metrics port
|
||||
/// can be firewalled differently from the API port — bind to localhost
|
||||
/// or a private interface only.
|
||||
async fn spawn_metrics_server(addr: &str, state: AppState) -> Result<tokio::task::JoinHandle<()>> {
|
||||
async fn spawn_metrics_server(
|
||||
addr: &str,
|
||||
mut shutdown_rx: watch::Receiver<bool>,
|
||||
) -> Result<tokio::task::JoinHandle<()>> {
|
||||
use axum::{response::IntoResponse, routing::get, Router};
|
||||
|
||||
async fn metrics_handler() -> impl IntoResponse {
|
||||
@@ -454,7 +805,6 @@ async fn spawn_metrics_server(addr: &str, state: AppState) -> Result<tokio::task
|
||||
}
|
||||
}
|
||||
|
||||
let mut shutdown_rx = state.subscribe_shutdown();
|
||||
let listener = TcpListener::bind(addr)
|
||||
.await
|
||||
.with_context(|| format!("failed to bind metrics listener to {addr}"))?;
|
||||
@@ -515,7 +865,12 @@ async fn gossip_task(
|
||||
}
|
||||
}
|
||||
|
||||
let client = reqwest::Client::new();
|
||||
// Reuse the shared no-redirect client for every gossip outbound call (the
|
||||
// bootstrap announce POST and the periodic peer /health ping). Peer URLs are
|
||||
// attacker-influenceable, so a 3xx to a private address must not be followed.
|
||||
// Do NOT fall back to reqwest::Client::new(): its default follows redirects
|
||||
// and would reintroduce the SSRF closed here (#93).
|
||||
let client = state.http_client.clone();
|
||||
let my_did = state.node_did.to_string();
|
||||
let my_url = state.config.public_url.clone().unwrap_or_default();
|
||||
|
||||
@@ -590,13 +945,7 @@ async fn gossip_task(
|
||||
Err(_) => continue,
|
||||
};
|
||||
for peer in peers {
|
||||
let url = format!("{}/health", peer.http_url.trim_end_matches('/'));
|
||||
let ok = client
|
||||
.get(&url)
|
||||
.send()
|
||||
.await
|
||||
.map(|r| r.status().is_success())
|
||||
.unwrap_or(false);
|
||||
let ok = ping_peer_health(&client, &peer.http_url).await;
|
||||
let _ = state.db.mark_peer_ping(&peer.did, ok).await;
|
||||
}
|
||||
}
|
||||
@@ -610,6 +959,38 @@ async fn gossip_task(
|
||||
}
|
||||
}
|
||||
|
||||
/// Build the shared node HTTP client used for every outbound fan-out (sync
|
||||
/// trigger, profile/repo fetches, gossip announce + peer pings).
|
||||
///
|
||||
/// No redirects: peer URLs are attacker-influenceable, so a `3xx` to a private
|
||||
/// address must not be followed (SSRF guard, #78/#93). Do NOT replace with
|
||||
/// `reqwest::Client::new()` — its default follows redirects. Kept as a named
|
||||
/// builder so tests bind the redirect guarantee to the real client the node
|
||||
/// runs, not a hand-rolled equivalent.
|
||||
fn build_http_client() -> reqwest::Result<reqwest::Client> {
|
||||
reqwest::Client::builder()
|
||||
.timeout(std::time::Duration::from_secs(10))
|
||||
.redirect(reqwest::redirect::Policy::none())
|
||||
.build()
|
||||
}
|
||||
|
||||
/// Ping a peer's `/health` endpoint and report whether it answered 2xx.
|
||||
///
|
||||
/// Takes the client by reference so callers supply the shared, no-redirect
|
||||
/// `state.http_client`. Peer URLs are attacker-influenceable, so a `3xx` to a
|
||||
/// private address must not be followed. Do NOT call this with a bare
|
||||
/// `reqwest::Client::new()`: its default follows redirects and would
|
||||
/// reintroduce the SSRF this guards against (#93).
|
||||
async fn ping_peer_health(client: &reqwest::Client, http_url: &str) -> bool {
|
||||
let url = format!("{}/health", http_url.trim_end_matches('/'));
|
||||
client
|
||||
.get(&url)
|
||||
.send()
|
||||
.await
|
||||
.map(|r| r.status().is_success())
|
||||
.unwrap_or(false)
|
||||
}
|
||||
|
||||
fn load_or_create_keypair(config: &Config) -> Result<Keypair> {
|
||||
let key_path = config.resolved_key_path();
|
||||
|
||||
@@ -642,3 +1023,64 @@ fn load_or_create_keypair(config: &Config) -> Result<Keypair> {
|
||||
Ok(kp)
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod gossip_ssrf_tests {
|
||||
use super::ping_peer_health;
|
||||
|
||||
// Build the client exactly as production does (super::build_http_client) so
|
||||
// these tests bind the redirect guarantee to the real shared client the
|
||||
// node runs. A regression that makes build_http_client follow redirects
|
||||
// fails ping_peer_health_does_not_follow_redirect.
|
||||
fn production_http_client() -> reqwest::Client {
|
||||
super::build_http_client().expect("failed to build production http client")
|
||||
}
|
||||
|
||||
// A peer answering `/health` with a 302 toward an internal address must not
|
||||
// be followed: the redirect target must never be requested (#93).
|
||||
#[tokio::test]
|
||||
async fn ping_peer_health_does_not_follow_redirect() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let internal = server
|
||||
.mock("GET", "/internal-metadata")
|
||||
.with_status(200)
|
||||
.expect(0)
|
||||
.create_async()
|
||||
.await;
|
||||
let _health = server
|
||||
.mock("GET", "/health")
|
||||
.with_status(302)
|
||||
.with_header("location", &format!("{}/internal-metadata", server.url()))
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let ok = ping_peer_health(&production_http_client(), &server.url()).await;
|
||||
|
||||
assert!(!ok, "a 302 must not count as a healthy peer");
|
||||
// expect(0) is enforced only at assert time; this fails if the redirect
|
||||
// was followed to the internal target.
|
||||
internal.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn ping_peer_health_reports_success_on_200() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _health = server
|
||||
.mock("GET", "/health")
|
||||
.with_status(200)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let ok = ping_peer_health(&production_http_client(), &server.url()).await;
|
||||
|
||||
assert!(ok, "a 200 /health must count as a healthy peer");
|
||||
}
|
||||
|
||||
// A transport error (nothing listening) must map to unhealthy, never a
|
||||
// spurious healthy — the .unwrap_or(false) arm.
|
||||
#[tokio::test]
|
||||
async fn ping_peer_health_reports_unhealthy_on_connection_error() {
|
||||
let ok = ping_peer_health(&production_http_client(), "http://127.0.0.1:1").await;
|
||||
assert!(!ok, "a connection error must count as an unhealthy peer");
|
||||
}
|
||||
}
|
||||
@@ -235,7 +235,11 @@ pub fn record_auth_failure(route: &str, reason: &str) {
|
||||
}
|
||||
}
|
||||
|
||||
/// Record one sync_queue item outcome. `status` ∈ {done, failed, skipped}.
|
||||
/// Record one sync_queue item outcome. `status` ∈ {done, failed, skipped,
|
||||
/// rejected, deferred}. `rejected` is terminal and caused by a guard (a
|
||||
/// malformed slug, or a path resolving outside repos_dir); `deferred` leaves
|
||||
/// the row pending for a later pass, so a queue stalled on an operator
|
||||
/// condition is visible rather than looking idle.
|
||||
pub fn record_sync_processed(status: &str) {
|
||||
if let Some(c) = SYNC_PROCESSED.get() {
|
||||
c.with_label_values(&[status]).inc();
|
||||
|
||||
@@ -39,6 +39,11 @@ pub struct RefUpdateEvent {
|
||||
pub pusher_did: String,
|
||||
/// Repository identifier (owner/name)
|
||||
pub repo: String,
|
||||
/// Full owner DID — added in #144 for display and storage; not yet
|
||||
/// wired into the feed gate matcher. Optional for backward compat with
|
||||
/// older peers that don't include it.
|
||||
#[serde(default)]
|
||||
pub owner_did: Option<String>,
|
||||
/// Git ref that changed (e.g., "refs/heads/main")
|
||||
pub ref_name: String,
|
||||
/// SHA before the push (all-zeros for new ref)
|
||||
@@ -307,6 +312,7 @@ pub async fn start(
|
||||
node_did: event.node_did.clone(),
|
||||
pusher_did: event.pusher_did.clone(),
|
||||
repo: event.repo.clone(),
|
||||
owner_did: event.owner_did.clone(),
|
||||
ref_name: event.ref_name.clone(),
|
||||
old_sha: event.old_sha.clone(),
|
||||
new_sha: event.new_sha.clone(),
|
||||
@@ -432,3 +438,67 @@ pub async fn start(
|
||||
|
||||
Ok(handle)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn ref_update_event_round_trip_with_owner_did() {
|
||||
let event = RefUpdateEvent {
|
||||
node_did: "did:key:zNode".into(),
|
||||
pusher_did: "did:key:zPusher".into(),
|
||||
repo: "zOwner/myrepo".into(),
|
||||
owner_did: Some("did:key:zOwner".into()),
|
||||
ref_name: "refs/heads/main".into(),
|
||||
old_sha: "0000000000000000000000000000000000000000".into(),
|
||||
new_sha: "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa".into(),
|
||||
timestamp: "2026-07-02T12:00:00Z".into(),
|
||||
cert_id: None,
|
||||
cid: None,
|
||||
};
|
||||
let json = serde_json::to_value(&event).unwrap();
|
||||
// owner_did must be present in the serialized output
|
||||
assert_eq!(json["owner_did"], "did:key:zOwner");
|
||||
assert_eq!(json["repo"], "zOwner/myrepo");
|
||||
|
||||
let deserialized: RefUpdateEvent = serde_json::from_value(json).unwrap();
|
||||
assert_eq!(deserialized.owner_did, Some("did:key:zOwner".into()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn ref_update_event_backward_compat_no_owner_did() {
|
||||
let old_json = serde_json::json!({
|
||||
"node_did": "did:key:zNode",
|
||||
"pusher_did": "did:key:zPusher",
|
||||
"repo": "zOwner/myrepo",
|
||||
"ref_name": "refs/heads/main",
|
||||
"old_sha": "0000000000000000000000000000000000000000",
|
||||
"new_sha": "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
||||
"timestamp": "2026-07-02T12:00:00Z",
|
||||
"cert_id": null,
|
||||
"cid": null
|
||||
});
|
||||
let deserialized: RefUpdateEvent = serde_json::from_value(old_json).unwrap();
|
||||
assert_eq!(deserialized.owner_did, None);
|
||||
assert_eq!(deserialized.repo, "zOwner/myrepo");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn ref_update_event_backward_compat_null_owner_did() {
|
||||
let with_null = serde_json::json!({
|
||||
"node_did": "did:key:zNode",
|
||||
"pusher_did": "did:key:zPusher",
|
||||
"repo": "zOwner/myrepo",
|
||||
"owner_did": null,
|
||||
"ref_name": "refs/heads/main",
|
||||
"old_sha": "0000000000000000000000000000000000000000",
|
||||
"new_sha": "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
||||
"timestamp": "2026-07-02T12:00:00Z",
|
||||
"cert_id": null,
|
||||
"cid": null
|
||||
});
|
||||
let deserialized: RefUpdateEvent = serde_json::from_value(with_null).unwrap();
|
||||
assert_eq!(deserialized.owner_did, None);
|
||||
}
|
||||
}
|
||||
@@ -1,15 +1,21 @@
|
||||
use std::collections::HashMap;
|
||||
use std::net::SocketAddr;
|
||||
use std::sync::Arc;
|
||||
use std::time::{Duration, Instant};
|
||||
|
||||
use axum::extract::Request;
|
||||
use axum::http::StatusCode;
|
||||
use axum::extract::{ConnectInfo, Request};
|
||||
use axum::http::{HeaderMap, StatusCode};
|
||||
use axum::middleware::Next;
|
||||
use axum::response::{IntoResponse, Response};
|
||||
use tokio::sync::Mutex;
|
||||
|
||||
use crate::auth::AuthenticatedDid;
|
||||
|
||||
/// Default ceiling on the number of distinct keys a limiter tracks. Bounds the
|
||||
/// limiter's own memory so a caller that can vary the key (many DIDs, or a
|
||||
/// spoofable IP header) cannot grow the map without limit.
|
||||
const DEFAULT_MAX_KEYS: usize = 100_000;
|
||||
|
||||
#[derive(Clone)]
|
||||
struct Window {
|
||||
timestamps: Vec<Instant>,
|
||||
@@ -20,38 +26,98 @@ pub struct RateLimiter {
|
||||
state: Arc<Mutex<HashMap<String, Window>>>,
|
||||
max_requests: usize,
|
||||
window: Duration,
|
||||
/// Hard cap on tracked keys. When full, expired keys are evicted (at most
|
||||
/// once per [`sweep_interval`](Self::sweep_interval), see below); if still
|
||||
/// full, a request under a *new* key is rejected rather than inserted — so
|
||||
/// the map can never exceed this bound and a rejected request never
|
||||
/// allocates a new entry.
|
||||
max_keys: usize,
|
||||
/// Timestamp of the last inline capacity sweep. The eviction scan is
|
||||
/// O(max_keys), so under a distinct-key flood (when the map sits at the
|
||||
/// cap) running it on every miss would serialize all traffic behind a full
|
||||
/// scan. Gating it to at most once per interval amortizes that cost; the
|
||||
/// background [`cleanup`](Self::cleanup) loop still reclaims on its own.
|
||||
last_sweep: Arc<Mutex<Instant>>,
|
||||
}
|
||||
|
||||
impl RateLimiter {
|
||||
// Retained for tests and callers that don't need a tight key bound;
|
||||
// production limiters use `new_bounded`.
|
||||
#[allow(dead_code)]
|
||||
pub fn new(max_requests: usize, window: Duration) -> Self {
|
||||
Self::new_bounded(max_requests, window, DEFAULT_MAX_KEYS)
|
||||
}
|
||||
|
||||
/// Like [`new`] but with an explicit cap on the number of distinct keys.
|
||||
/// Production limiters keyed on client-influenced values (per-DID, per-IP)
|
||||
/// set this so the limiter's own state cannot be turned into a
|
||||
/// memory-exhaustion vector.
|
||||
pub fn new_bounded(max_requests: usize, window: Duration, max_keys: usize) -> Self {
|
||||
Self {
|
||||
state: Arc::new(Mutex::new(HashMap::new())),
|
||||
max_requests,
|
||||
window,
|
||||
max_keys: max_keys.max(1),
|
||||
last_sweep: Arc::new(Mutex::new(Instant::now())),
|
||||
}
|
||||
}
|
||||
|
||||
async fn check(&self, key: &str) -> bool {
|
||||
/// How often the inline capacity sweep may run: at most once per second, or
|
||||
/// once per window when the window is shorter. Bounds post-flood staleness
|
||||
/// (a full map self-heals within one interval) without paying the O(max_keys)
|
||||
/// scan on every capacity miss.
|
||||
fn sweep_interval(&self) -> Duration {
|
||||
self.window.min(Duration::from_secs(1))
|
||||
}
|
||||
|
||||
pub(crate) async fn check(&self, key: &str) -> bool {
|
||||
// max_requests == 0 means the limiter is disabled, not "block all".
|
||||
if self.max_requests == 0 {
|
||||
return true;
|
||||
}
|
||||
let now = Instant::now();
|
||||
let mut state = self.state.lock().await;
|
||||
// Look up before inserting so the common case (key already tracked)
|
||||
// doesn't allocate a String per request.
|
||||
if !state.contains_key(key) {
|
||||
state.insert(
|
||||
key.to_string(),
|
||||
Window {
|
||||
timestamps: Vec::new(),
|
||||
},
|
||||
);
|
||||
|
||||
// Fast path: an already-tracked key never allocates and never grows the
|
||||
// map, so it is unaffected by the key cap.
|
||||
if let Some(window) = state.get_mut(key) {
|
||||
window
|
||||
.timestamps
|
||||
.retain(|t| now.duration_since(*t) < self.window);
|
||||
if window.timestamps.len() >= self.max_requests {
|
||||
return false;
|
||||
}
|
||||
window.timestamps.push(now);
|
||||
return true;
|
||||
}
|
||||
let window = state.get_mut(key).expect("window just ensured");
|
||||
window
|
||||
.timestamps
|
||||
.retain(|t| now.duration_since(*t) < self.window);
|
||||
if window.timestamps.len() >= self.max_requests {
|
||||
return false;
|
||||
|
||||
// New key. Enforce the cap BEFORE inserting so a flood of distinct keys
|
||||
// cannot grow the map, and a rejected request never allocates an entry.
|
||||
if state.len() >= self.max_keys {
|
||||
// Reclaim expired keys, but at most once per sweep interval — the
|
||||
// scan is O(max_keys) and the map sits at the cap precisely during a
|
||||
// distinct-key flood, so sweeping per miss would serialize traffic
|
||||
// behind a full scan. Between sweeps a new key is simply rejected.
|
||||
let mut last_sweep = self.last_sweep.lock().await;
|
||||
if now.duration_since(*last_sweep) >= self.sweep_interval() {
|
||||
state.retain(|_, w| {
|
||||
w.timestamps
|
||||
.retain(|t| now.duration_since(*t) < self.window);
|
||||
!w.timestamps.is_empty()
|
||||
});
|
||||
*last_sweep = now;
|
||||
}
|
||||
drop(last_sweep);
|
||||
if state.len() >= self.max_keys {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
window.timestamps.push(now);
|
||||
state.insert(
|
||||
key.to_string(),
|
||||
Window {
|
||||
timestamps: vec![now],
|
||||
},
|
||||
);
|
||||
true
|
||||
}
|
||||
|
||||
@@ -88,6 +154,136 @@ pub async fn rate_limit_by_did(request: Request, next: Next) -> Response {
|
||||
next.run(request).await
|
||||
}
|
||||
|
||||
/// Which forwarded header (if any) the operator's edge is trusted to set. Only
|
||||
/// a proxy the operator controls may be believed; a raw client can put any
|
||||
/// value in `Fly-Client-IP` / `X-Forwarded-For`, so trusting them unconditionally
|
||||
/// lets a flooder rotate the header and never fill a bucket. Configured via
|
||||
/// `GITLAWB_TRUSTED_PROXY`.
|
||||
#[derive(Clone, Copy, PartialEq, Eq, Debug)]
|
||||
pub enum TrustedProxy {
|
||||
/// No trusted proxy: ignore forwarded headers, key on the socket peer IP.
|
||||
/// Safe default for direct/self-hosted nodes.
|
||||
None,
|
||||
/// Behind Fly's edge, which sets (and overwrites any client-supplied)
|
||||
/// `Fly-Client-IP`.
|
||||
Fly,
|
||||
/// Behind a single reverse proxy (e.g. Caddy on the AWS image) that appends
|
||||
/// the real client as the rightmost `X-Forwarded-For` hop.
|
||||
XForwardedFor,
|
||||
}
|
||||
|
||||
impl TrustedProxy {
|
||||
/// Parse `GITLAWB_TRUSTED_PROXY`. Unknown/empty → `None` (trust nothing).
|
||||
pub fn from_env_value(s: &str) -> Self {
|
||||
match s.trim().to_ascii_lowercase().as_str() {
|
||||
"fly" | "fly-client-ip" => TrustedProxy::Fly,
|
||||
"xff" | "x-forwarded-for" | "caddy" => TrustedProxy::XForwardedFor,
|
||||
_ => TrustedProxy::None,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn trimmed_nonempty(v: &str) -> Option<String> {
|
||||
let t = v.trim();
|
||||
(!t.is_empty()).then(|| t.to_string())
|
||||
}
|
||||
|
||||
/// Resolve the rate-limit key for a request. In a trusted-proxy mode the
|
||||
/// operator's edge header is preferred; when that header is missing or empty we
|
||||
/// fall back to the socket peer address rather than skipping the limiter (a
|
||||
/// malformed header must never disable the brake). With no trusted proxy the
|
||||
/// socket peer is always used and forwarded headers are ignored entirely.
|
||||
/// Returns `None` only when neither a trusted header nor a peer address is
|
||||
/// available (e.g. a synthetic test request with no `ConnectInfo`).
|
||||
pub fn client_key(
|
||||
headers: &HeaderMap,
|
||||
peer: Option<SocketAddr>,
|
||||
trust: TrustedProxy,
|
||||
) -> Option<String> {
|
||||
let from_header = match trust {
|
||||
TrustedProxy::None => None,
|
||||
TrustedProxy::Fly => headers
|
||||
.get("fly-client-ip")
|
||||
.and_then(|v| v.to_str().ok())
|
||||
.and_then(trimmed_nonempty),
|
||||
// Rightmost hop = the value appended by the immediately-upstream trusted
|
||||
// proxy. The leftmost hop is client-controlled and must not be trusted.
|
||||
TrustedProxy::XForwardedFor => headers
|
||||
.get("x-forwarded-for")
|
||||
.and_then(|v| v.to_str().ok())
|
||||
.and_then(|v| v.rsplit(',').next())
|
||||
.and_then(trimmed_nonempty),
|
||||
};
|
||||
from_header.or_else(|| peer.map(|p| p.ip().to_string()))
|
||||
}
|
||||
|
||||
/// Per-client-IP limiter for the git push path, carrying the trusted-proxy
|
||||
/// policy. A newtype so it can live in request extensions (keyed by type)
|
||||
/// alongside the per-DID [`RateLimiter`]. Per-DID limits are useless against a
|
||||
/// push flood from a DID farm (one throwaway DID per repo), so the push path
|
||||
/// throttles on the resolved client IP instead.
|
||||
#[derive(Clone)]
|
||||
pub struct IpRateLimiter {
|
||||
pub limiter: RateLimiter,
|
||||
pub trust: TrustedProxy,
|
||||
}
|
||||
|
||||
/// Infallible extractor for the socket peer address from `ConnectInfo`. Yields
|
||||
/// `None` when the server was started without connect-info (e.g. `oneshot` in
|
||||
/// tests), so a handler never 500s on its absence — the limiter simply falls
|
||||
/// back per [`client_key`].
|
||||
pub struct PeerAddr(pub Option<SocketAddr>);
|
||||
|
||||
impl<S: Send + Sync> axum::extract::FromRequestParts<S> for PeerAddr {
|
||||
type Rejection = std::convert::Infallible;
|
||||
|
||||
async fn from_request_parts(
|
||||
parts: &mut axum::http::request::Parts,
|
||||
_state: &S,
|
||||
) -> Result<Self, Self::Rejection> {
|
||||
Ok(PeerAddr(
|
||||
parts
|
||||
.extensions
|
||||
.get::<ConnectInfo<SocketAddr>>()
|
||||
.map(|c| c.0),
|
||||
))
|
||||
}
|
||||
}
|
||||
|
||||
/// The shared 429 response for the per-IP flood brakes. Route-agnostic: this
|
||||
/// middleware now serves the push path AND the peer-sync routes, so the message
|
||||
/// stays generic (the offending path is recorded in the warn log below).
|
||||
pub fn too_many_requests() -> Response {
|
||||
(
|
||||
StatusCode::TOO_MANY_REQUESTS,
|
||||
[("retry-after", "60")],
|
||||
"rate limit exceeded — try again later",
|
||||
)
|
||||
.into_response()
|
||||
}
|
||||
|
||||
/// Throttle the git push path by resolved client IP. The socket peer address is
|
||||
/// read from `ConnectInfo` (see `into_make_service_with_connect_info` in
|
||||
/// `main`). Only skips the limiter when no key can be resolved at all.
|
||||
pub async fn rate_limit_by_ip(request: Request, next: Next) -> Response {
|
||||
let limiter = request.extensions().get::<IpRateLimiter>().cloned();
|
||||
let peer = request
|
||||
.extensions()
|
||||
.get::<ConnectInfo<SocketAddr>>()
|
||||
.map(|c| c.0);
|
||||
|
||||
if let Some(limiter) = limiter {
|
||||
if let Some(key) = client_key(request.headers(), peer, limiter.trust) {
|
||||
if !limiter.limiter.check(&key).await {
|
||||
tracing::warn!(key = %key, path = %request.uri().path(), "per-IP rate limit exceeded");
|
||||
return too_many_requests();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
next.run(request).await
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
@@ -134,4 +330,279 @@ mod tests {
|
||||
let state = limiter.state.lock().await;
|
||||
assert!(state.is_empty());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn zero_limit_disables() {
|
||||
let limiter = RateLimiter::new(0, Duration::from_secs(60));
|
||||
for _ in 0..1000 {
|
||||
assert!(limiter.check("k").await);
|
||||
}
|
||||
}
|
||||
|
||||
// ── key-cap / memory-bound (P2) ──────────────────────────────────────
|
||||
|
||||
#[tokio::test]
|
||||
async fn caps_tracked_keys_and_rejects_new_ones_when_full() {
|
||||
// Cap of 2 distinct keys; generous request budget so rejection is due to
|
||||
// the key cap, not the per-key limit.
|
||||
let limiter = RateLimiter::new_bounded(100, Duration::from_secs(60), 2);
|
||||
assert!(limiter.check("a").await);
|
||||
assert!(limiter.check("b").await);
|
||||
// Third distinct key would grow the map past the cap → rejected.
|
||||
assert!(!limiter.check("c").await);
|
||||
// The map never exceeded the cap, and the rejected key was NOT inserted.
|
||||
let state = limiter.state.lock().await;
|
||||
assert_eq!(state.len(), 2);
|
||||
assert!(!state.contains_key("c"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn known_key_unaffected_by_cap() {
|
||||
let limiter = RateLimiter::new_bounded(100, Duration::from_secs(60), 1);
|
||||
assert!(limiter.check("a").await); // fills the single slot
|
||||
assert!(limiter.check("a").await); // same key still served
|
||||
assert!(!limiter.check("b").await); // new key rejected — cap full
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn expired_keys_evicted_to_admit_new_when_full() {
|
||||
let limiter = RateLimiter::new_bounded(100, Duration::from_millis(40), 1);
|
||||
assert!(limiter.check("old").await);
|
||||
tokio::time::sleep(Duration::from_millis(55)).await;
|
||||
// "old" is now expired; a new key triggers inline eviction and is admitted.
|
||||
assert!(limiter.check("new").await);
|
||||
let state = limiter.state.lock().await;
|
||||
assert!(state.contains_key("new"));
|
||||
assert!(!state.contains_key("old"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn capacity_sweep_is_amortized_within_interval() {
|
||||
// The O(max_keys) eviction scan must not run on every capacity miss.
|
||||
// With a 1s sweep interval, the resident (unexpired) key is never
|
||||
// evicted by a burst of misses, so repeated new keys are all rejected
|
||||
// without disturbing existing state.
|
||||
let limiter = RateLimiter::new_bounded(100, Duration::from_secs(1), 1);
|
||||
assert!(limiter.check("resident").await);
|
||||
for i in 0..100 {
|
||||
assert!(
|
||||
!limiter.check(&format!("flood-{i}")).await,
|
||||
"new key must be rejected while the single slot is held"
|
||||
);
|
||||
}
|
||||
let state = limiter.state.lock().await;
|
||||
assert_eq!(state.len(), 1, "no flood key was ever inserted");
|
||||
assert!(state.contains_key("resident"));
|
||||
}
|
||||
|
||||
// ── client_key / trusted-proxy resolution (P1 + P2) ─────────────────
|
||||
|
||||
fn headers(pairs: &[(&str, &str)]) -> HeaderMap {
|
||||
let mut h = HeaderMap::new();
|
||||
for (k, v) in pairs {
|
||||
h.insert(
|
||||
axum::http::HeaderName::from_bytes(k.as_bytes()).unwrap(),
|
||||
v.parse().unwrap(),
|
||||
);
|
||||
}
|
||||
h
|
||||
}
|
||||
|
||||
fn peer(s: &str) -> Option<SocketAddr> {
|
||||
Some(s.parse().unwrap())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn none_mode_ignores_headers_and_uses_peer() {
|
||||
// Even a well-formed Fly header is ignored without a trusted proxy.
|
||||
let h = headers(&[("fly-client-ip", "203.0.113.7")]);
|
||||
assert_eq!(
|
||||
client_key(&h, peer("198.51.100.9:4000"), TrustedProxy::None).as_deref(),
|
||||
Some("198.51.100.9")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn fly_mode_trusts_fly_header() {
|
||||
let h = headers(&[
|
||||
("fly-client-ip", "203.0.113.7"),
|
||||
("x-forwarded-for", "1.2.3.4"),
|
||||
]);
|
||||
assert_eq!(
|
||||
client_key(&h, peer("10.0.0.1:1"), TrustedProxy::Fly).as_deref(),
|
||||
Some("203.0.113.7")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn fly_mode_empty_header_falls_back_to_peer_not_skip() {
|
||||
// Empty Fly-Client-IP must NOT collapse traffic onto Some("") nor skip
|
||||
// the limiter — it falls back to the real peer.
|
||||
let h = headers(&[("fly-client-ip", "")]);
|
||||
assert_eq!(
|
||||
client_key(&h, peer("198.51.100.9:4000"), TrustedProxy::Fly).as_deref(),
|
||||
Some("198.51.100.9")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn xff_mode_uses_rightmost_hop_not_client_controlled_first() {
|
||||
// Client prepends spoofed hops; only the rightmost (proxy-appended) is trusted.
|
||||
let h = headers(&[("x-forwarded-for", "9.9.9.9, 8.8.8.8, 198.51.100.9")]);
|
||||
assert_eq!(
|
||||
client_key(&h, peer("10.0.0.1:1"), TrustedProxy::XForwardedFor).as_deref(),
|
||||
Some("198.51.100.9")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn xff_mode_empty_leading_hop_does_not_disable_brake() {
|
||||
// "X-Forwarded-For: ,1.2.3.4" — rightmost hop is used; never None-skips.
|
||||
let h = headers(&[("x-forwarded-for", ",1.2.3.4")]);
|
||||
assert_eq!(
|
||||
client_key(&h, peer("10.0.0.1:1"), TrustedProxy::XForwardedFor).as_deref(),
|
||||
Some("1.2.3.4")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn malformed_xff_falls_back_to_peer() {
|
||||
let h = headers(&[("x-forwarded-for", " , ")]);
|
||||
assert_eq!(
|
||||
client_key(&h, peer("198.51.100.9:4000"), TrustedProxy::XForwardedFor).as_deref(),
|
||||
Some("198.51.100.9")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn trusted_proxy_parsing() {
|
||||
assert_eq!(TrustedProxy::from_env_value("fly"), TrustedProxy::Fly);
|
||||
assert_eq!(
|
||||
TrustedProxy::from_env_value("X-Forwarded-For"),
|
||||
TrustedProxy::XForwardedFor
|
||||
);
|
||||
assert_eq!(
|
||||
TrustedProxy::from_env_value("caddy"),
|
||||
TrustedProxy::XForwardedFor
|
||||
);
|
||||
assert_eq!(TrustedProxy::from_env_value(""), TrustedProxy::None);
|
||||
assert_eq!(TrustedProxy::from_env_value("garbage"), TrustedProxy::None);
|
||||
}
|
||||
|
||||
// ── middleware 429 path ─────────────────────────────────────────────
|
||||
|
||||
/// A minimal router with the push limiter layered over an OK handler,
|
||||
/// driven via `oneshot`. `ConnectInfo` is attached to each request directly
|
||||
/// (as the production make-service does) so the middleware resolves a peer.
|
||||
fn ip_limited_router(limiter: IpRateLimiter) -> axum::Router {
|
||||
axum::Router::new()
|
||||
.route(
|
||||
"/o/r/git-receive-pack",
|
||||
axum::routing::post(|| async { StatusCode::OK }),
|
||||
)
|
||||
.layer(axum::middleware::from_fn(rate_limit_by_ip))
|
||||
.layer(axum::Extension(limiter))
|
||||
}
|
||||
|
||||
async fn post_from(router: &axum::Router, peer: SocketAddr) -> StatusCode {
|
||||
use tower::ServiceExt;
|
||||
let mut req = axum::http::Request::builder()
|
||||
.method(axum::http::Method::POST)
|
||||
.uri("/o/r/git-receive-pack")
|
||||
.body(axum::body::Body::empty())
|
||||
.unwrap();
|
||||
req.extensions_mut().insert(ConnectInfo(peer));
|
||||
router.clone().oneshot(req).await.unwrap().status()
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn middleware_returns_429_over_limit() {
|
||||
let router = ip_limited_router(IpRateLimiter {
|
||||
limiter: RateLimiter::new(2, Duration::from_secs(60)),
|
||||
trust: TrustedProxy::None,
|
||||
});
|
||||
let peer: SocketAddr = "203.0.113.7:5000".parse().unwrap();
|
||||
// Two requests inside the budget, the third over it (shared Arc state).
|
||||
assert_eq!(post_from(&router, peer).await, StatusCode::OK);
|
||||
assert_eq!(post_from(&router, peer).await, StatusCode::OK);
|
||||
assert_eq!(
|
||||
post_from(&router, peer).await,
|
||||
StatusCode::TOO_MANY_REQUESTS
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn middleware_isolates_distinct_peers() {
|
||||
let router = ip_limited_router(IpRateLimiter {
|
||||
limiter: RateLimiter::new(1, Duration::from_secs(60)),
|
||||
trust: TrustedProxy::None,
|
||||
});
|
||||
let a: SocketAddr = "203.0.113.1:1".parse().unwrap();
|
||||
let b: SocketAddr = "203.0.113.2:1".parse().unwrap();
|
||||
assert_eq!(post_from(&router, a).await, StatusCode::OK);
|
||||
assert_eq!(post_from(&router, b).await, StatusCode::OK); // independent bucket
|
||||
assert_eq!(post_from(&router, a).await, StatusCode::TOO_MANY_REQUESTS);
|
||||
}
|
||||
|
||||
// ── creation-route layering: IP brake runs BEFORE auth ──────────────
|
||||
|
||||
/// A minimal stand-in for the creation route group: an inner "auth" layer
|
||||
/// that rejects every request with 401 (as signature verification would for
|
||||
/// an unsigned caller), wrapped by the per-IP creation limiter as the
|
||||
/// outermost layer — exactly the ordering `server::build_router` applies to
|
||||
/// `/api/v1/repos` et al. Lets us assert the security-relevant property
|
||||
/// (flood traffic is braked before auth burns CPU) without a database, which
|
||||
/// the full `#[sqlx::test]` route test in `api::repos` cannot cover in the
|
||||
/// plain unit-test pass.
|
||||
fn ip_limited_over_auth_router(limiter: IpRateLimiter) -> axum::Router {
|
||||
async fn always_unauthorized(_req: Request, _next: Next) -> Response {
|
||||
StatusCode::UNAUTHORIZED.into_response()
|
||||
}
|
||||
axum::Router::new()
|
||||
.route(
|
||||
"/api/v1/repos",
|
||||
axum::routing::post(|| async { StatusCode::CREATED }),
|
||||
)
|
||||
.layer(axum::middleware::from_fn(always_unauthorized))
|
||||
.layer(axum::middleware::from_fn(rate_limit_by_ip))
|
||||
.layer(axum::Extension(limiter))
|
||||
}
|
||||
|
||||
async fn post_repos_from(router: &axum::Router, peer: SocketAddr) -> StatusCode {
|
||||
use tower::ServiceExt;
|
||||
let mut req = axum::http::Request::builder()
|
||||
.method(axum::http::Method::POST)
|
||||
.uri("/api/v1/repos")
|
||||
.body(axum::body::Body::empty())
|
||||
.unwrap();
|
||||
req.extensions_mut().insert(ConnectInfo(peer));
|
||||
router.clone().oneshot(req).await.unwrap().status()
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn creation_ip_brake_rejects_before_auth() {
|
||||
// A DID farm mints a fresh signature per repo, so the per-DID limiter
|
||||
// never trips; the per-IP brake is what stops the flood. It must run
|
||||
// outermost, ahead of auth, so a flood is rejected with 429 before
|
||||
// signature verification — otherwise every request would reach (and pay
|
||||
// for) auth and merely 401.
|
||||
let router = ip_limited_over_auth_router(IpRateLimiter {
|
||||
limiter: RateLimiter::new(1, Duration::from_secs(60)),
|
||||
trust: TrustedProxy::None,
|
||||
});
|
||||
let peer: SocketAddr = "203.0.113.42:7000".parse().unwrap();
|
||||
|
||||
// First request passes the IP brake and reaches the (failing) auth layer.
|
||||
assert_eq!(
|
||||
post_repos_from(&router, peer).await,
|
||||
StatusCode::UNAUTHORIZED
|
||||
);
|
||||
// Budget now exhausted: the IP brake short-circuits with 429 *before*
|
||||
// auth — proving the limiter is the outermost layer.
|
||||
assert_eq!(
|
||||
post_repos_from(&router, peer).await,
|
||||
StatusCode::TOO_MANY_REQUESTS,
|
||||
"an exhausted IP must be braked with 429 before auth runs, not leak to 401"
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -81,8 +81,19 @@ pub fn build_router(state: AppState) -> Router {
|
||||
.route("/api/v1/tasks", get(tasks::list_tasks))
|
||||
.route("/api/v1/tasks/{id}", get(tasks::get_task));
|
||||
|
||||
// ── Rate-limited creation routes — require HTTP Signature + per-DID throttle
|
||||
// ── Rate-limited creation routes — require HTTP Signature, plus a per-DID
|
||||
// throttle AND a per-IP flood brake. The per-DID limiter (inner) caps a
|
||||
// single identity; the per-IP limiter (outer) caps a DID farm that mints a
|
||||
// fresh throwaway did:key per repo to slip past both the per-DID limit and
|
||||
// the iCaptcha gate — the mechanism behind the recurring spam-repo floods.
|
||||
// The per-IP layer wraps the auth layer (outermost = runs first) so flood
|
||||
// traffic is rejected before signature verification burns CPU, matching the
|
||||
// push path.
|
||||
let limiter = state.rate_limiter.clone();
|
||||
let create_ip_limiter = rate_limit::IpRateLimiter {
|
||||
limiter: state.create_ip_rate_limiter.clone(),
|
||||
trust: state.push_limiter_trust,
|
||||
};
|
||||
let creation_routes = add_auth_layers(
|
||||
Router::new()
|
||||
.route("/api/v1/repos", post(repos::create_repo))
|
||||
@@ -96,7 +107,9 @@ pub fn build_router(state: AppState) -> Router {
|
||||
.layer(middleware::from_fn(rate_limit::rate_limit_by_did))
|
||||
.layer(axum::Extension(limiter)),
|
||||
state.clone(),
|
||||
);
|
||||
)
|
||||
.layer(middleware::from_fn(rate_limit::rate_limit_by_ip))
|
||||
.layer(axum::Extension(create_ip_limiter));
|
||||
|
||||
// ── Write routes — require HTTP Signature (no rate limit) ─────────────
|
||||
let write_routes = add_auth_layers(
|
||||
@@ -175,6 +188,14 @@ pub fn build_router(state: AppState) -> Router {
|
||||
// HTTP Signature is enforced on receive-pack (push) — the git-remote-gitlawb
|
||||
// helper signs requests with RFC 9421 signatures using the agent's keypair.
|
||||
let pack_limit = state.config.max_pack_bytes;
|
||||
// Per-IP throttle wraps the auth layer (outermost = runs first): flood
|
||||
// traffic is rejected before signature verification burns CPU. Per-DID
|
||||
// limiting is deliberately NOT used here — a DID farm (one throwaway
|
||||
// identity per repo, as in the June 2026 push flood) never trips it.
|
||||
let push_limiter = rate_limit::IpRateLimiter {
|
||||
limiter: state.push_rate_limiter.clone(),
|
||||
trust: state.push_limiter_trust,
|
||||
};
|
||||
let git_write_routes = add_auth_layers(
|
||||
Router::new()
|
||||
.route(
|
||||
@@ -184,7 +205,9 @@ pub fn build_router(state: AppState) -> Router {
|
||||
.layer(DefaultBodyLimit::disable())
|
||||
.layer(RequestBodyLimitLayer::new(pack_limit)),
|
||||
state.clone(),
|
||||
);
|
||||
)
|
||||
.layer(middleware::from_fn(rate_limit::rate_limit_by_ip))
|
||||
.layer(axum::Extension(push_limiter));
|
||||
|
||||
// ── IPFS content-addressed retrieval and pin listing ──────────────────
|
||||
// `/ipfs/{cid}` carries `optional_signature` so `get_by_cid` sees the caller
|
||||
@@ -238,7 +261,8 @@ pub fn build_router(state: AppState) -> Router {
|
||||
.route(
|
||||
"/api/v1/agents/{did}/bounties",
|
||||
get(bounties::agent_bounty_stats),
|
||||
);
|
||||
)
|
||||
.layer(middleware::from_fn(auth::optional_signature));
|
||||
|
||||
// ── Profile routes (write — require HTTP Signature) ─────────────────
|
||||
let profile_write_routes = add_auth_layers(
|
||||
@@ -267,15 +291,41 @@ pub fn build_router(state: AppState) -> Router {
|
||||
.route("/api/v1/peers", get(peers::list_peers))
|
||||
.route("/api/v1/peers/{did}/ping", get(peers::ping_peer));
|
||||
|
||||
// /sync/trigger drives an O(peers) outbound fan-out + per-repo enqueue, so it
|
||||
// ALWAYS requires a signature (both config modes) and carries a tight per-IP
|
||||
// brake. A signature alone does not cap cost — a did:key farm self-registers
|
||||
// (INV-10) — so the IP brake is a separate, load-bearing half. The brake is
|
||||
// outermost (runs before signature verification burns CPU) and is keyed on the
|
||||
// client IP before any DID is read, so DID rotation cannot bypass it.
|
||||
let sync_trigger_routes = add_auth_layers(
|
||||
Router::new().route("/api/v1/sync/trigger", post(peers::trigger_sync)),
|
||||
state.clone(),
|
||||
)
|
||||
.layer(middleware::from_fn(rate_limit::rate_limit_by_ip))
|
||||
.layer(axum::Extension(rate_limit::IpRateLimiter {
|
||||
limiter: state.sync_trigger_rate_limiter.clone(),
|
||||
trust: state.push_limiter_trust,
|
||||
}));
|
||||
|
||||
// announce + notify keep their rolling-upgrade signature behavior (unsigned
|
||||
// accepted until all peers upgrade), but both reach peer-write side effects —
|
||||
// notify hits the same enqueue_sync sink as trigger — so they carry a per-IP
|
||||
// brake too, on a SEPARATE bucket from trigger's, so an unsigned notify flood
|
||||
// cannot drain the signed trigger caller's quota.
|
||||
let mut peer_write_routes = Router::new()
|
||||
.route("/api/v1/peers/announce", post(peers::announce))
|
||||
.route("/api/v1/sync/trigger", post(peers::trigger_sync))
|
||||
.route("/api/v1/sync/notify", post(peers::notify_sync));
|
||||
peer_write_routes = if state.config.require_signed_peer_writes {
|
||||
add_auth_layers(peer_write_routes, state.clone())
|
||||
} else {
|
||||
peer_write_routes.layer(middleware::from_fn(auth::optional_signature))
|
||||
};
|
||||
let peer_write_routes = peer_write_routes
|
||||
.layer(middleware::from_fn(rate_limit::rate_limit_by_ip))
|
||||
.layer(axum::Extension(rate_limit::IpRateLimiter {
|
||||
limiter: state.peer_write_rate_limiter.clone(),
|
||||
trust: state.push_limiter_trust,
|
||||
}));
|
||||
|
||||
// ── Read routes — open for public repos ───────────────────────────────
|
||||
let read_routes = Router::new()
|
||||
@@ -405,6 +455,7 @@ pub fn build_router(state: AppState) -> Router {
|
||||
let meta_routes = Router::new()
|
||||
.route("/", get(node_info))
|
||||
.route("/health", get(health))
|
||||
.route("/ready", get(ready))
|
||||
.route("/api/v1/p2p/info", get(p2p_info))
|
||||
.route("/api/v1/stats", get(stats))
|
||||
.route("/api/v1/contracts", get(contracts_info));
|
||||
@@ -424,6 +475,7 @@ pub fn build_router(state: AppState) -> Router {
|
||||
.merge(read_routes)
|
||||
.merge(peer_read_routes)
|
||||
.merge(peer_write_routes)
|
||||
.merge(sync_trigger_routes)
|
||||
.merge(ipfs_routes)
|
||||
.merge(arweave_routes)
|
||||
.merge(meta_routes)
|
||||
@@ -446,6 +498,26 @@ async fn health() -> Json<serde_json::Value> {
|
||||
Json(json!({ "status": "ok" }))
|
||||
}
|
||||
|
||||
/// Readiness = "this node can serve real traffic", and every real endpoint
|
||||
/// depends on the database, so probe it rather than reporting a constant.
|
||||
/// The probe gets its own short bound so a wedged pool can't hang the health
|
||||
/// check for the full acquire timeout.
|
||||
async fn ready(State(state): State<AppState>) -> axum::response::Response {
|
||||
let probe = tokio::time::timeout(std::time::Duration::from_secs(2), state.db.ping()).await;
|
||||
match probe {
|
||||
Ok(Ok(())) => Json(json!({ "status": "ready" })).into_response(),
|
||||
_ => (
|
||||
axum::http::StatusCode::SERVICE_UNAVAILABLE,
|
||||
Json(json!({
|
||||
"status": "degraded",
|
||||
"error": crate::error::DB_UNAVAILABLE_CODE,
|
||||
"message": crate::error::DB_UNAVAILABLE_MESSAGE,
|
||||
})),
|
||||
)
|
||||
.into_response(),
|
||||
}
|
||||
}
|
||||
|
||||
async fn node_info(State(state): State<AppState>) -> Json<serde_json::Value> {
|
||||
let p2p_peer_id = state.p2p.as_ref().map(|h| h.local_peer_id.to_string());
|
||||
Json(json!({
|
||||
|
||||
@@ -17,6 +17,7 @@ pub struct RefUpdateBroadcast {
|
||||
pub pusher_did: String,
|
||||
pub node_did: String,
|
||||
pub timestamp: String,
|
||||
pub owner_did: String,
|
||||
}
|
||||
|
||||
#[derive(Clone, Debug)]
|
||||
@@ -51,6 +52,35 @@ pub struct AppState {
|
||||
pub repo_store: RepoStore,
|
||||
/// Per-DID rate limiter for creation endpoints (repos, issues, PRs)
|
||||
pub rate_limiter: RateLimiter,
|
||||
/// Per-client-IP rate limiter for the same creation endpoints. The per-DID
|
||||
/// limiter above cannot brake a creation flood from a DID farm — one
|
||||
/// throwaway `did:key` per repo means each DID makes a single create call
|
||||
/// and never trips its own bucket. A valid iCaptcha proof does not cap this
|
||||
/// either: the enforced level draws only machine-solvable deterministic
|
||||
/// challenges (and the caller can pin the easy type), so a bot mints a fresh
|
||||
/// DID, solves a proof, and creates a repo unthrottled. Braking on the
|
||||
/// resolved client IP is what actually stops a single-source flood (same
|
||||
/// rationale as `push_rate_limiter`). Keyed by `push_limiter_trust`.
|
||||
pub create_ip_rate_limiter: RateLimiter,
|
||||
/// Per-client-IP rate limiter for git-receive-pack. Per-DID limits cannot
|
||||
/// brake a push flood from a DID farm (one throwaway DID per repo), so the
|
||||
/// push path throttles on the resolved client IP instead.
|
||||
pub push_rate_limiter: RateLimiter,
|
||||
/// Which forwarded header (if any) the edge is trusted to set, for
|
||||
/// resolving the push limiter's client-IP key. See `GITLAWB_TRUSTED_PROXY`.
|
||||
/// Node-wide; also keys the two peer-sync limiters below.
|
||||
pub push_limiter_trust: crate::rate_limit::TrustedProxy,
|
||||
/// Per-client-IP limiter for `POST /api/v1/sync/trigger` (tight). The route
|
||||
/// requires a signature, but a signature does not cap cost (a did:key farm
|
||||
/// self-registers), and its per-call cost is an O(peers) fan-out, so the IP
|
||||
/// brake is a separate, load-bearing half. Its own bucket so an unsigned
|
||||
/// `/sync/notify` flood cannot drain the signed trigger caller's quota.
|
||||
pub sync_trigger_rate_limiter: RateLimiter,
|
||||
/// Per-client-IP limiter for the peer-write routes (`/peers/announce`,
|
||||
/// `/sync/notify`) (generous). `/sync/notify` reaches the same `enqueue_sync`
|
||||
/// sink as trigger and accepts unsigned requests from known peers, so it is
|
||||
/// braked too; each peer's distinct IP gets its own bucket.
|
||||
pub peer_write_rate_limiter: RateLimiter,
|
||||
/// Process-wide graceful-shutdown signal. Sending `true` causes every
|
||||
/// task that holds a `watch::Receiver` to exit at its next await point.
|
||||
/// Used by:
|
||||
|
||||
File diff suppressed because it is too large.
Load diff
File diff suppressed because it is too large.
Load diff
@@ -4,7 +4,8 @@
|
||||
//! based on the repo's visibility rules with a fallback to the legacy
|
||||
//! `is_public` flag. It performs no I/O so it is exhaustively unit tested.
|
||||
|
||||
use crate::db::VisibilityRule;
|
||||
use crate::db::{RepoRecord, VisibilityRule};
|
||||
use std::collections::HashMap;
|
||||
use unicode_normalization::UnicodeNormalization;
|
||||
|
||||
#[derive(Debug, PartialEq, Eq)]
|
||||
@@ -24,11 +25,12 @@ fn nfc(s: &str) -> String {
|
||||
s.nfc().collect()
|
||||
}
|
||||
|
||||
/// True if `caller` is the repo owner (matches full did:key or its short form),
|
||||
/// mirroring the owner-match idiom in `api/protect.rs`.
|
||||
/// True if `caller` is the repo owner. Uses [`crate::api::did_matches`] so the
|
||||
/// owner check is representation-agnostic within `did:key` (full `did:key:z...`
|
||||
/// matches bare `z...` stored by mirror rows) while still denying cross-method
|
||||
/// collisions (`did:gitlawb:z...` vs bare `z...`).
|
||||
fn is_owner(owner_did: &str, caller: &str) -> bool {
|
||||
let owner_short = owner_did.split(':').next_back().unwrap_or(owner_did);
|
||||
caller == owner_did || caller == owner_short
|
||||
crate::api::did_matches(owner_did, caller)
|
||||
}
|
||||
|
||||
/// The match prefix for a glob: "/" stays "/", "/secret/**" becomes "/secret".
|
||||
@@ -127,6 +129,105 @@ pub fn listable_at_root(
|
||||
visibility_check(rules, is_public, owner_did, caller, "/") == Decision::Allow
|
||||
}
|
||||
|
||||
/// Whether a single `received_ref_updates` row (identified by its peer-supplied
|
||||
/// `row_repo` slug) should be shown to `caller` (None = anonymous) on the
|
||||
/// cross-repo ref-updates feeds (#112 GraphQL, #114 REST).
|
||||
///
|
||||
/// Pure and I/O-free: both call sites load the deduped local repo set and its
|
||||
/// visibility rules once per request and pass them in, so the gate logic lives
|
||||
/// here and visibility.rs keeps its "no I/O" property.
|
||||
///
|
||||
/// The slug is written verbatim from the inbound gossip/notify message, so it is
|
||||
/// untrusted input, not a canonical key. The decision is fail-closed by
|
||||
/// construction: the only KEEP paths are (a) a slug with no `/` (cannot name a
|
||||
/// local `owner/name` pair, so remote by definition), (b) all matched local
|
||||
/// records are readable, and (c) no local record matches (remote/gossip-only).
|
||||
/// Any local match the caller cannot read at root DROPs the row. There is no
|
||||
/// catch-all keep on unexpected state.
|
||||
///
|
||||
/// Slug/record owner keys are matched prefix-tolerantly (one is a prefix of the
|
||||
/// other), covering the exact short-key, the full `did:key:` form, and the
|
||||
/// URL-truncated 8-char form. Prefix over-match can only over-drop a genuinely
|
||||
/// remote row (fail-safe), never over-serve a private local one.
|
||||
///
|
||||
/// The live call sites are the #112 (GraphQL) and #114 (REST) feed handlers,
|
||||
/// added in the following units; exercised by the unit tests below meanwhile.
|
||||
pub fn ref_update_row_visible(
|
||||
deduped: &[RepoRecord],
|
||||
rules_by_repo: &HashMap<String, Vec<VisibilityRule>>,
|
||||
caller: Option<&str>,
|
||||
row_repo: &str,
|
||||
) -> bool {
|
||||
// A slug with no '/' cannot name a local owner/name pair — remote by
|
||||
// definition (same branch as "matches nothing local") → KEEP.
|
||||
if row_repo.rsplit_once('/').is_none() {
|
||||
return true;
|
||||
}
|
||||
|
||||
// Match each local record with the shared slug predicate (one matcher, so
|
||||
// this gate and the collector's quarantine drop cannot disagree about which
|
||||
// rows a repo owns), then fail closed on any matched record the caller
|
||||
// cannot read at root.
|
||||
for record in deduped {
|
||||
if !ref_update_row_names_repo(record, row_repo) {
|
||||
continue;
|
||||
}
|
||||
let rules = rules_by_repo
|
||||
.get(&record.id)
|
||||
.map(Vec::as_slice)
|
||||
.unwrap_or(&[]);
|
||||
if !listable_at_root(rules, record.is_public, &record.owner_did, caller) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
// Reached only if every matched local record is readable, or nothing local
|
||||
// matched (remote/gossip-only). Both are the KEEP paths; there is no
|
||||
// default-keep on unexpected state — an unreadable match already returned.
|
||||
true
|
||||
}
|
||||
|
||||
/// Whether `row_repo`'s peer-supplied slug names the local `record`. The single
|
||||
/// match predicate shared by the feed gate ([`ref_update_row_visible`]) and the
|
||||
/// quarantine hard-drop in the ref-update collector, so the two cannot diverge
|
||||
/// about which rows a repo owns — a second, drifting matcher is exactly the #134
|
||||
/// slug-collision class.
|
||||
///
|
||||
/// A record matches when the slug's `name` half is equal and one owner key is a
|
||||
/// prefix of the other (prefix-tolerant: exact short key, full `did:key:` form,
|
||||
/// and the URL-truncated 8-char form). Both the slug owner and the record owner
|
||||
/// are reduced to their last ':'-delimited segment before comparing. The node's
|
||||
/// own emitter builds the wire slug via `normalize_owner_key` (bare short key for
|
||||
/// a single-segment `did:key:`, the full DID for every other method; see
|
||||
/// api/repos.rs), but the stored slug is UNTRUSTED: a peer can broadcast a row
|
||||
/// under any owner form, including a method-stripped `user/name`. Reducing both
|
||||
/// sides to the trailing segment matches a repo's own rows whichever form keyed
|
||||
/// them, and still catches an attacker-planted short slug.
|
||||
///
|
||||
/// This intentionally diverges from `did_matches` / `DEDUP_CTE`, which strip only
|
||||
/// bare `did:key:` and keep other DID methods whole: those compare trusted,
|
||||
/// canonical DIDs, while this slug is untrusted. Applying the keep-whole rule here
|
||||
/// would fail open: a hostile `user/name` slug would not prefix-match a private
|
||||
/// `did:web:host:user` record and would leak. The price is a fail-SAFE over-match
|
||||
/// when a remote owner shares both a trailing segment and a repo name with a local
|
||||
/// private repo (negligible for full did:key ids; only did:web / truncated forms
|
||||
/// collide): it can hide a genuinely remote row, never serve a private one.
|
||||
pub fn ref_update_row_names_repo(record: &RepoRecord, row_repo: &str) -> bool {
|
||||
let Some((owner_part, name)) = row_repo.rsplit_once('/') else {
|
||||
return false;
|
||||
};
|
||||
if record.name != name {
|
||||
return false;
|
||||
}
|
||||
let row_key = owner_part.split(':').next_back().unwrap_or(owner_part);
|
||||
let record_key = record
|
||||
.owner_did
|
||||
.split(':')
|
||||
.next_back()
|
||||
.unwrap_or(&record.owner_did);
|
||||
record_key.starts_with(row_key) || row_key.starts_with(record_key)
|
||||
}
|
||||
|
||||
/// The subtree path globs that `caller` (None = anonymous) may NOT read, given
|
||||
/// the repo's rules. Whole-repo ("/") rules are excluded: a denied whole-repo
|
||||
/// read is handled by the 404 gate before a clone ever starts. Each remaining
|
||||
@@ -299,6 +400,60 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn non_key_owner_bare_short_does_not_match() {
|
||||
// A non-key DID owner (did:gitlawb:z6MkFoo) probed with the bare last
|
||||
// segment (z6MkFoo) must NOT match — the old is_owner would return true
|
||||
// via split(':').next_back(), which this PR tightens.
|
||||
let rules = [rule("/", VisibilityMode::A, &[])];
|
||||
assert_eq!(
|
||||
visibility_check(&rules, false, "did:gitlawb:z6MkFoo", Some("z6MkFoo"), "/"),
|
||||
Decision::Deny,
|
||||
"bare short must not match a non-key DID owner"
|
||||
);
|
||||
// The full non-key DID still matches itself.
|
||||
assert_eq!(
|
||||
visibility_check(
|
||||
&rules,
|
||||
false,
|
||||
"did:gitlawb:z6MkFoo",
|
||||
Some("did:gitlawb:z6MkFoo"),
|
||||
"/"
|
||||
),
|
||||
Decision::Allow,
|
||||
"full non-key DID still matches itself"
|
||||
);
|
||||
}
|
||||
|
||||
// #153 forward guard: is_owner must match across bare-key / full-did:key
|
||||
// representations should someone revert to single-side normalize_owner_key.
|
||||
#[test]
|
||||
fn bare_owner_full_caller_allows_owner() {
|
||||
let rules = [rule("/", VisibilityMode::A, &[])];
|
||||
assert_eq!(
|
||||
visibility_check(&rules, false, "z6MkOwner", Some("did:key:z6MkOwner"), "/"),
|
||||
Decision::Allow,
|
||||
"bare owner + full did:key caller must match (guard against single-side revert)"
|
||||
);
|
||||
}
|
||||
|
||||
// #153 regression: cross-method DID must still be denied even when the
|
||||
// trailing segment collides with a bare owner key.
|
||||
#[test]
|
||||
fn cross_method_did_denied_with_bare_owner() {
|
||||
let rules = [rule("/", VisibilityMode::A, &[])];
|
||||
assert_eq!(
|
||||
visibility_check(&rules, false, "z6MkFoo", Some("did:gitlawb:z6MkFoo"), "/"),
|
||||
Decision::Deny,
|
||||
"cross-method DID must not match a bare did:key owner"
|
||||
);
|
||||
assert_eq!(
|
||||
visibility_check(&rules, false, "z6MkFoo", Some("did:web:z6MkFoo"), "/"),
|
||||
Decision::Deny,
|
||||
"did:web must not match a bare did:key owner"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn root_rule_allows_listed_reader() {
|
||||
let rules = [rule("/", VisibilityMode::A, &["did:key:z6MkFriend"])];
|
||||
@@ -403,6 +558,260 @@ mod tests {
|
||||
));
|
||||
}
|
||||
|
||||
// ── ref_update_row_visible (feed gate) ──────────────────────────────────
|
||||
|
||||
fn rec(id: &str, owner_did: &str, name: &str, is_public: bool) -> RepoRecord {
|
||||
RepoRecord {
|
||||
id: id.into(),
|
||||
name: name.into(),
|
||||
owner_did: owner_did.into(),
|
||||
description: None,
|
||||
is_public,
|
||||
default_branch: "main".into(),
|
||||
created_at: Utc::now(),
|
||||
updated_at: Utc::now(),
|
||||
disk_path: format!("/srv/{id}"),
|
||||
forked_from: None,
|
||||
machine_id: None,
|
||||
}
|
||||
}
|
||||
|
||||
fn rules_for(entries: &[(&str, &[VisibilityRule])]) -> HashMap<String, Vec<VisibilityRule>> {
|
||||
entries
|
||||
.iter()
|
||||
.map(|(id, rs)| (id.to_string(), rs.to_vec()))
|
||||
.collect()
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feed_public_local_repo_kept_for_anon() {
|
||||
let deduped = [rec("r1", "did:key:z6MkOwner", "widget", true)];
|
||||
let rules = HashMap::new();
|
||||
assert!(ref_update_row_visible(
|
||||
&deduped,
|
||||
&rules,
|
||||
None,
|
||||
"z6MkOwner/widget"
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feed_private_local_repo_dropped_for_anon_kept_for_owner() {
|
||||
let deduped = [rec("r1", "did:key:z6MkOwner", "widget", false)];
|
||||
let rules = HashMap::new();
|
||||
// Anonymous → drop.
|
||||
assert!(!ref_update_row_visible(
|
||||
&deduped,
|
||||
&rules,
|
||||
None,
|
||||
"z6MkOwner/widget"
|
||||
));
|
||||
// Owner (full DID) → keep.
|
||||
assert!(ref_update_row_visible(
|
||||
&deduped,
|
||||
&rules,
|
||||
Some("did:key:z6MkOwner"),
|
||||
"z6MkOwner/widget"
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feed_root_rule_reader_reincluded() {
|
||||
// Private repo (is_public=false) with a root rule granting a named
|
||||
// reader. Delegates to listable_at_root: anon and non-reader denied,
|
||||
// named reader allowed.
|
||||
let deduped = [rec("r1", OWNER, "widget", false)];
|
||||
let root = [rule("/", VisibilityMode::A, &["did:key:z6MkFriend"])];
|
||||
let rules = rules_for(&[("r1", &root)]);
|
||||
assert!(!ref_update_row_visible(
|
||||
&deduped,
|
||||
&rules,
|
||||
None,
|
||||
"z6MkOwner/widget"
|
||||
));
|
||||
assert!(!ref_update_row_visible(
|
||||
&deduped,
|
||||
&rules,
|
||||
Some("did:key:z6MkStranger"),
|
||||
"z6MkOwner/widget"
|
||||
));
|
||||
assert!(ref_update_row_visible(
|
||||
&deduped,
|
||||
&rules,
|
||||
Some("did:key:z6MkFriend"),
|
||||
"z6MkOwner/widget"
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feed_alias_full_did_slug_dropped_for_anon() {
|
||||
// Owner stored full-DID; slug also carries the full-DID form. Still
|
||||
// matches (row_key normalizes to the short key) → drop. Round 1's
|
||||
// string-match would have leaked this.
|
||||
let deduped = [rec("r1", "did:key:zABC", "widget", false)];
|
||||
let rules = HashMap::new();
|
||||
assert!(!ref_update_row_visible(
|
||||
&deduped,
|
||||
&rules,
|
||||
None,
|
||||
"did:key:zABC/widget"
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feed_truncated_key_slug_dropped_for_anon() {
|
||||
// Slug carries an 8-char URL-truncated prefix of the owner key; still
|
||||
// matches via prefix tolerance → drop. Round 2's get_repo path leaked.
|
||||
let deduped = [rec("r1", "did:key:zABCDEFGH", "widget", false)];
|
||||
let rules = HashMap::new();
|
||||
assert!(!ref_update_row_visible(
|
||||
&deduped,
|
||||
&rules,
|
||||
None,
|
||||
"zABCDEF/widget"
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feed_mirror_coexistence_private_canonical_dropped_for_anon() {
|
||||
// Pure-level mirror-coexistence: the deduped set contains only the
|
||||
// private canonical record for (owner,name). A matching slug drops for
|
||||
// anon. (DB-level dedup survivor property is pinned separately.)
|
||||
let deduped = [rec("uuid-canonical", "did:key:z6Mkwbud", "nipmod", false)];
|
||||
let rules = HashMap::new();
|
||||
assert!(!ref_update_row_visible(
|
||||
&deduped,
|
||||
&rules,
|
||||
None,
|
||||
"z6Mkwbud/nipmod"
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feed_empty_owner_slug_matches_and_drops() {
|
||||
// Slug "/name": empty owner_part → row_key "" → starts_with("") matches
|
||||
// every same-named record. Fail-safe pin for a private repo.
|
||||
let deduped = [rec("r1", "did:key:z6MkOwner", "widget", false)];
|
||||
let rules = HashMap::new();
|
||||
assert!(!ref_update_row_visible(&deduped, &rules, None, "/widget"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feed_one_char_owner_slug_matches_and_drops() {
|
||||
// 1-char owner prefix that the private repo's key starts with → match.
|
||||
let deduped = [rec("r1", "did:key:z6MkOwner", "widget", false)];
|
||||
let rules = HashMap::new();
|
||||
assert!(!ref_update_row_visible(&deduped, &rules, None, "z/widget"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feed_remote_slug_no_match_kept() {
|
||||
// Different owner key, no prefix relation → no local match → keep.
|
||||
let deduped = [rec("r1", "did:key:z6MkOwner", "widget", false)];
|
||||
let rules = HashMap::new();
|
||||
assert!(ref_update_row_visible(
|
||||
&deduped,
|
||||
&rules,
|
||||
None,
|
||||
"zZZZOTHER/widget"
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feed_private_didweb_short_slug_dropped_for_anon() {
|
||||
// A private did:web repo must drop its row for anon when the slug arrives
|
||||
// in the short `{last-segment}/{name}` form. Post-#141 the emitter no longer
|
||||
// produces this form for did:web (normalize_owner_key keeps the full DID),
|
||||
// so this is the untrusted/crafted variant a peer can broadcast; the full-DID
|
||||
// variant the emitter now sends is covered by the next test. A did:key-aware
|
||||
// (keep-whole) rule would fail to match `alice` against `did:web:host:alice`
|
||||
// and leak.
|
||||
let deduped = [rec("r1", "did:web:host:alice", "widget", false)];
|
||||
let rules = HashMap::new();
|
||||
assert!(!ref_update_row_visible(
|
||||
&deduped,
|
||||
&rules,
|
||||
None,
|
||||
"alice/widget"
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feed_multi_segment_did_slug_dropped_for_anon() {
|
||||
// A private repo owned by a multi-segment DID must also fail closed under
|
||||
// the full-DID slug form. Post-#141 this IS the form the emitter broadcasts
|
||||
// (normalize_owner_key keeps non-did:key methods whole), and a peer can craft
|
||||
// it too. The gate drops it: both sides reduce to the last ':' segment
|
||||
// ("user"), so they match. Fail-safe regardless of which form keyed the row.
|
||||
let deduped = [rec("r1", "did:web:host:user", "widget", false)];
|
||||
let rules = HashMap::new();
|
||||
assert!(!ref_update_row_visible(
|
||||
&deduped,
|
||||
&rules,
|
||||
None,
|
||||
"did:web:host:user/widget"
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feed_multi_segment_did_slug_kept_for_public() {
|
||||
// Symmetric keep-side: a PUBLIC multi-segment-DID repo's row must still be
|
||||
// returned to anon after the last-':'-segment normalization — guards
|
||||
// against a regression that over-drops legitimate did:web rows.
|
||||
let deduped = [rec("r1", "did:web:host:user", "widget", true)];
|
||||
let rules = HashMap::new();
|
||||
assert!(ref_update_row_visible(
|
||||
&deduped,
|
||||
&rules,
|
||||
None,
|
||||
"did:web:host:user/widget"
|
||||
));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feed_malformed_slug_no_slash_kept_no_panic() {
|
||||
let deduped = [rec("r1", "did:key:z6MkOwner", "widget", false)];
|
||||
let rules = HashMap::new();
|
||||
assert!(ref_update_row_visible(&deduped, &rules, None, "noslug"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn feed_empty_deduped_set_keeps_any_slug() {
|
||||
let deduped: [RepoRecord; 0] = [];
|
||||
let rules = HashMap::new();
|
||||
assert!(ref_update_row_visible(
|
||||
&deduped,
|
||||
&rules,
|
||||
None,
|
||||
"z6MkOwner/widget"
|
||||
));
|
||||
assert!(ref_update_row_visible(&deduped, &rules, None, "anything"));
|
||||
}
|
||||
|
||||
// The shared slug matcher underpinning both the feed gate and the collector's
|
||||
// quarantine drop: it must recognize a repo's own row across every owner-DID
|
||||
// form (bare short key, full did:key, URL-truncated prefix) and must not
|
||||
// over-match a different name or an unrelated owner. The quarantine drop calls
|
||||
// this directly, so its match contract is load-bearing for withholding a
|
||||
// quarantined mirror from a caller who matches the mirror's owner_did.
|
||||
#[test]
|
||||
fn names_repo_matches_owner_forms_and_rejects_mismatches() {
|
||||
// Bare short owner key (the form upsert_mirror_repo stores).
|
||||
let bare = rec("m", "z6MkQuar", "secret", false);
|
||||
assert!(ref_update_row_names_repo(&bare, "z6MkQuar/secret"));
|
||||
// Full did:key owner; the short-segment slug still matches via last-segment.
|
||||
let full = rec("c", "did:key:z6MkQuar", "secret", false);
|
||||
assert!(ref_update_row_names_repo(&full, "z6MkQuar/secret"));
|
||||
assert!(ref_update_row_names_repo(&full, "did:key:z6MkQuar/secret"));
|
||||
// URL-truncated 8-char prefix slug → prefix-tolerant match.
|
||||
let long = rec("l", "did:key:z6MkQuarLONGKEY", "secret", false);
|
||||
assert!(ref_update_row_names_repo(&long, "z6MkQuar/secret"));
|
||||
// Different name, different owner, and no-slash → no match.
|
||||
assert!(!ref_update_row_names_repo(&bare, "z6MkQuar/other"));
|
||||
assert!(!ref_update_row_names_repo(&bare, "z6MkOther/secret"));
|
||||
assert!(!ref_update_row_names_repo(&bare, "noslash"));
|
||||
}
|
||||
|
||||
// #101: a deny rule must withhold a path that denotes the same characters in
|
||||
// a different Unicode normalization form. Without NFC normalization at the
|
||||
// matcher seam, an NFC-authored rule byte-compares unequal to an NFD-stored
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
[package]
|
||||
name = "gl"
|
||||
description = "The gitlawb CLI — identity management, node control, MCP server"
|
||||
version = "0.4.0" # x-release-please-version
|
||||
version = "0.7.1" # x-release-please-version
|
||||
edition.workspace = true
|
||||
rust-version.workspace = true
|
||||
license.workspace = true
|
||||
@@ -12,6 +12,8 @@ path = "src/main.rs"
|
||||
|
||||
[dependencies]
|
||||
gitlawb-core = { path = "../gitlawb-core" }
|
||||
icaptcha-client = { path = "../icaptcha-client" }
|
||||
base64 = { workspace = true }
|
||||
tokio = { workspace = true }
|
||||
serde = { workspace = true }
|
||||
serde_json = { workspace = true }
|
||||
|
||||
+28
-10
@@ -8,6 +8,10 @@ use std::path::PathBuf;
|
||||
use crate::http::NodeClient;
|
||||
use crate::identity::load_keypair_from_dir;
|
||||
|
||||
fn signed_client(node: &str, dir: Option<&std::path::Path>) -> NodeClient {
|
||||
NodeClient::new(node, load_keypair_from_dir(dir).ok())
|
||||
}
|
||||
|
||||
#[derive(Args)]
|
||||
pub struct BountyArgs {
|
||||
#[command(subcommand)]
|
||||
@@ -49,6 +53,8 @@ pub enum BountyCmd {
|
||||
status: Option<String>,
|
||||
#[arg(long, default_value = "https://node.gitlawb.com", env = "GITLAWB_NODE")]
|
||||
node: String,
|
||||
#[arg(long)]
|
||||
dir: Option<PathBuf>,
|
||||
},
|
||||
/// Show details of a specific bounty
|
||||
Show {
|
||||
@@ -56,6 +62,8 @@ pub enum BountyCmd {
|
||||
id: String,
|
||||
#[arg(long, default_value = "https://node.gitlawb.com", env = "GITLAWB_NODE")]
|
||||
node: String,
|
||||
#[arg(long)]
|
||||
dir: Option<PathBuf>,
|
||||
},
|
||||
/// Claim an open bounty
|
||||
Claim {
|
||||
@@ -121,8 +129,13 @@ pub async fn run(args: BountyArgs) -> Result<()> {
|
||||
node,
|
||||
dir,
|
||||
} => cmd_create(repo, title, amount, issue, tx_hash, deadline, node, dir).await,
|
||||
BountyCmd::List { repo, status, node } => cmd_list(repo, status, node).await,
|
||||
BountyCmd::Show { id, node } => cmd_show(id, node).await,
|
||||
BountyCmd::List {
|
||||
repo,
|
||||
status,
|
||||
node,
|
||||
dir,
|
||||
} => cmd_list(repo, status, node, dir).await,
|
||||
BountyCmd::Show { id, node, dir } => cmd_show(id, node, dir).await,
|
||||
BountyCmd::Claim {
|
||||
id,
|
||||
wallet,
|
||||
@@ -192,8 +205,13 @@ async fn cmd_create(
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn cmd_list(repo: Option<String>, status: Option<String>, node: String) -> Result<()> {
|
||||
let client = NodeClient::new(&node, None);
|
||||
async fn cmd_list(
|
||||
repo: Option<String>,
|
||||
status: Option<String>,
|
||||
node: String,
|
||||
dir: Option<PathBuf>,
|
||||
) -> Result<()> {
|
||||
let client = signed_client(&node, dir.as_deref());
|
||||
|
||||
let url = if let Some(ref repo) = repo {
|
||||
let (owner, name) = repo
|
||||
@@ -214,7 +232,7 @@ async fn cmd_list(repo: Option<String>, status: Option<String>, node: String) ->
|
||||
};
|
||||
|
||||
let resp = client
|
||||
.get(&url)
|
||||
.get_authed(&url)
|
||||
.await
|
||||
.context("failed to connect to node")?;
|
||||
let body: Value = resp.json().await.unwrap_or_default();
|
||||
@@ -237,9 +255,9 @@ async fn cmd_list(repo: Option<String>, status: Option<String>, node: String) ->
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn cmd_show(id: String, node: String) -> Result<()> {
|
||||
let client = NodeClient::new(&node, None);
|
||||
let resp = client.get(&format!("/api/v1/bounties/{id}")).await?;
|
||||
async fn cmd_show(id: String, node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
let client = signed_client(&node, dir.as_deref());
|
||||
let resp = client.get_authed(&format!("/api/v1/bounties/{id}")).await?;
|
||||
|
||||
let status = resp.status();
|
||||
let body: Value = resp.json().await.unwrap_or_default();
|
||||
@@ -462,7 +480,7 @@ mod tests {
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
cmd_list(None, None, server.url()).await.unwrap();
|
||||
cmd_list(None, None, server.url(), None).await.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
@@ -506,7 +524,7 @@ mod tests {
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let err = cmd_show("nonexistent".to_string(), server.url())
|
||||
let err = cmd_show("nonexistent".to_string(), server.url(), None)
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(err.to_string().contains("not found"));
|
||||
|
||||
+248
-42
@@ -5,10 +5,15 @@
|
||||
use anyhow::{Context, Result};
|
||||
use clap::{Args, Subcommand};
|
||||
use serde_json::Value;
|
||||
use std::path::PathBuf;
|
||||
|
||||
use crate::http::NodeClient;
|
||||
use crate::identity::load_keypair_from_dir;
|
||||
|
||||
fn signed_client(node: &str, dir: Option<&std::path::Path>) -> NodeClient {
|
||||
NodeClient::new(node, load_keypair_from_dir(dir).ok())
|
||||
}
|
||||
|
||||
#[derive(Args)]
|
||||
pub struct CertArgs {
|
||||
#[command(subcommand)]
|
||||
@@ -23,6 +28,8 @@ pub enum CertCmd {
|
||||
repo: String,
|
||||
#[arg(long, default_value = "https://node.gitlawb.com", env = "GITLAWB_NODE")]
|
||||
node: String,
|
||||
#[arg(long)]
|
||||
dir: Option<PathBuf>,
|
||||
},
|
||||
/// Show a specific ref certificate and verify its signature
|
||||
Show {
|
||||
@@ -32,28 +39,51 @@ pub enum CertCmd {
|
||||
id: String,
|
||||
#[arg(long, default_value = "https://node.gitlawb.com", env = "GITLAWB_NODE")]
|
||||
node: String,
|
||||
#[arg(long)]
|
||||
dir: Option<PathBuf>,
|
||||
/// Exit non-zero unless the Ed25519 signature verifies AND the
|
||||
/// issuing node matches the queried node (or --expect-node)
|
||||
#[arg(long)]
|
||||
verify: bool,
|
||||
/// Expected issuing node DID for --verify. A valid signature alone
|
||||
/// only proves the cert is internally consistent — signed by whatever
|
||||
/// key it names — so --verify also anchors the issuer to a DID you
|
||||
/// trust: this value when given, else the queried node's DID.
|
||||
#[arg(long, requires = "verify")]
|
||||
expect_node: Option<String>,
|
||||
},
|
||||
}
|
||||
|
||||
pub async fn run(args: CertArgs) -> Result<()> {
|
||||
match args.cmd {
|
||||
CertCmd::List { repo, node } => cmd_list(repo, node).await,
|
||||
CertCmd::Show { repo, id, node } => cmd_show(repo, id, node).await,
|
||||
CertCmd::List { repo, node, dir } => cmd_list(repo, node, dir).await,
|
||||
CertCmd::Show {
|
||||
repo,
|
||||
id,
|
||||
node,
|
||||
dir,
|
||||
verify,
|
||||
expect_node,
|
||||
} => cmd_show(repo, id, node, dir, verify, expect_node).await,
|
||||
}
|
||||
}
|
||||
|
||||
/// Resolve "repo" into (owner, name) using the caller's DID when no slash is given.
|
||||
async fn resolve_repo(repo: &str, node: &str) -> Result<(String, String)> {
|
||||
async fn resolve_repo(
|
||||
repo: &str,
|
||||
node: &str,
|
||||
dir: Option<&std::path::Path>,
|
||||
) -> Result<(String, String)> {
|
||||
if let Some((owner, name)) = repo.split_once('/') {
|
||||
Ok((owner.to_string(), name.to_string()))
|
||||
} else {
|
||||
let short = if let Ok(kp) = load_keypair_from_dir(None) {
|
||||
let short = if let Ok(kp) = load_keypair_from_dir(dir) {
|
||||
let did = kp.did().to_string();
|
||||
did.split(':').next_back().unwrap_or(&did).to_string()
|
||||
} else {
|
||||
let client = NodeClient::new(node, None);
|
||||
let client = signed_client(node, dir);
|
||||
let info: Value = client
|
||||
.get("/")
|
||||
.get_authed("/")
|
||||
.await?
|
||||
.json()
|
||||
.await
|
||||
@@ -65,13 +95,13 @@ async fn resolve_repo(repo: &str, node: &str) -> Result<(String, String)> {
|
||||
}
|
||||
}
|
||||
|
||||
async fn cmd_list(repo: String, node: String) -> Result<()> {
|
||||
let (owner, name) = resolve_repo(&repo, &node).await?;
|
||||
async fn cmd_list(repo: String, node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
let (owner, name) = resolve_repo(&repo, &node, dir.as_deref()).await?;
|
||||
|
||||
let client = NodeClient::new(&node, None);
|
||||
let client = signed_client(&node, dir.as_deref());
|
||||
let path = format!("/api/v1/repos/{owner}/{name}/certs");
|
||||
let resp: Value = client
|
||||
.get(&path)
|
||||
.get_authed(&path)
|
||||
.await?
|
||||
.json()
|
||||
.await
|
||||
@@ -96,16 +126,23 @@ async fn cmd_list(repo: String, node: String) -> Result<()> {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn cmd_show(repo: String, id: String, node: String) -> Result<()> {
|
||||
let (owner, name) = resolve_repo(&repo, &node).await?;
|
||||
async fn cmd_show(
|
||||
repo: String,
|
||||
id: String,
|
||||
node: String,
|
||||
dir: Option<PathBuf>,
|
||||
require_valid: bool,
|
||||
expect_node: Option<String>,
|
||||
) -> Result<()> {
|
||||
let (owner, name) = resolve_repo(&repo, &node, dir.as_deref()).await?;
|
||||
|
||||
let client = NodeClient::new(&node, None);
|
||||
let client = signed_client(&node, dir.as_deref());
|
||||
let id = resolve_cert_id(&client, &owner, &name, &id).await?;
|
||||
|
||||
// Fetch the certificate
|
||||
let path = format!("/api/v1/repos/{owner}/{name}/certs/{id}");
|
||||
let resp = client
|
||||
.get(&path)
|
||||
.get_authed(&path)
|
||||
.await?
|
||||
.error_for_status()
|
||||
.context("certificate not found")?;
|
||||
@@ -130,47 +167,132 @@ async fn cmd_show(repo: String, id: String, node: String) -> Result<()> {
|
||||
println!(" Signature: {signature}");
|
||||
println!();
|
||||
|
||||
// Reconstruct the signing payload and verify
|
||||
// Fetch the node's current public key to verify
|
||||
let info: Value = client
|
||||
.get("/")
|
||||
.await?
|
||||
.json()
|
||||
.await
|
||||
.context("failed to fetch node info")?;
|
||||
let current_node_did = info["did"].as_str().unwrap_or("");
|
||||
// Verify the Ed25519 signature: rebuild the exact canonical payload the
|
||||
// node signed (see gitlawb-node/src/cert.rs::issue_ref_certificate) and
|
||||
// check it against the public key embedded in the certificate's node DID.
|
||||
// This proves the cert is internally authentic — signed by the key it
|
||||
// names; the node-DID comparison below covers *which* node that is.
|
||||
let repo_id = cert["repo_id"].as_str().unwrap_or("");
|
||||
let verdict = verify_signature(
|
||||
repo_id, ref_name, old_sha, new_sha, pusher, node_did, issued_at, signature,
|
||||
);
|
||||
|
||||
println!("Signature verification:");
|
||||
println!(" Signing payload would be:");
|
||||
println!(" {{\"repo_id\": ..., \"ref\": \"{ref_name}\", \"old\": \"{old_sha}\",");
|
||||
println!(" \"new\": \"{new_sha}\", \"pusher\": \"{pusher}\",");
|
||||
println!(" \"node\": \"{node_did}\", \"ts\": \"{issued_at}\"}}");
|
||||
println!();
|
||||
|
||||
if current_node_did == node_did {
|
||||
println!(" Node DID matches current node. Signature is an Ed25519/base64url value.");
|
||||
println!(" To verify offline, use the node's Ed25519 public key derived from:");
|
||||
println!(" did:key → {node_did}");
|
||||
} else {
|
||||
println!(" WARNING: Certificate node DID ({node_did}) does not match");
|
||||
println!(" current node DID ({current_node_did}).");
|
||||
println!(" This certificate was issued by a different node.");
|
||||
match &verdict {
|
||||
Ok(()) => {
|
||||
println!(
|
||||
" VALID — Ed25519 signature verified against the key the certificate names ({node_did})"
|
||||
);
|
||||
}
|
||||
Err(reason) => {
|
||||
println!(" INVALID — {reason}");
|
||||
}
|
||||
}
|
||||
|
||||
println!();
|
||||
println!(" Signature (base64url): {signature}");
|
||||
// Contextual only — the verdict above stands on its own, so a node-info
|
||||
// hiccup here must not turn a successfully displayed certificate into an
|
||||
// error exit.
|
||||
let current_node_did = match client.get("/").await {
|
||||
Ok(resp) => resp
|
||||
.json::<Value>()
|
||||
.await
|
||||
.ok()
|
||||
.and_then(|info| info["did"].as_str().map(str::to_string)),
|
||||
Err(_) => None,
|
||||
};
|
||||
match current_node_did.as_deref() {
|
||||
Some(current) if current == node_did => {
|
||||
println!(" Issuing node DID matches the node being queried.");
|
||||
}
|
||||
Some(current) => {
|
||||
println!(" WARNING: Certificate node DID ({node_did}) does not match");
|
||||
println!(" current node DID ({current}).");
|
||||
println!(" This certificate was issued by a different node.");
|
||||
}
|
||||
None => {
|
||||
println!(" NOTE: could not fetch current node info — skipping node-DID comparison.");
|
||||
}
|
||||
}
|
||||
|
||||
if require_valid {
|
||||
if let Err(reason) = verdict {
|
||||
anyhow::bail!("certificate signature did not verify: {reason}");
|
||||
}
|
||||
// A valid signature proves internal consistency only: the payload was
|
||||
// signed by whatever key the certificate itself names. A hostile
|
||||
// source can mint a keypair, put its DID in node_did, and self-sign.
|
||||
// --verify therefore also anchors the issuer to a trusted DID:
|
||||
// --expect-node when given, else the DID of the node being queried.
|
||||
let expected = expect_node.as_deref().or(current_node_did.as_deref());
|
||||
match expected {
|
||||
Some(expected) if expected == node_did => {}
|
||||
Some(expected) => anyhow::bail!(
|
||||
"certificate is signed by {node_did}, but the expected issuer is {expected} — \
|
||||
a valid signature alone proves internal consistency, not a trusted issuer"
|
||||
),
|
||||
None => anyhow::bail!(
|
||||
"cannot anchor the issuer: node info is unreachable and no --expect-node was given"
|
||||
),
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Rebuild the node's canonical signing payload (field order must match
|
||||
/// gitlawb-node/src/cert.rs::issue_ref_certificate exactly) and verify the
|
||||
/// certificate's Ed25519 signature against the key embedded in `node_did`.
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
fn verify_signature(
|
||||
repo_id: &str,
|
||||
ref_name: &str,
|
||||
old_sha: &str,
|
||||
new_sha: &str,
|
||||
pusher: &str,
|
||||
node_did: &str,
|
||||
issued_at: &str,
|
||||
signature_b64: &str,
|
||||
) -> std::result::Result<(), String> {
|
||||
use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine};
|
||||
use std::str::FromStr;
|
||||
|
||||
let payload = serde_json::json!({
|
||||
"repo_id": repo_id,
|
||||
"ref": ref_name,
|
||||
"old": old_sha,
|
||||
"new": new_sha,
|
||||
"pusher": pusher,
|
||||
"node": node_did,
|
||||
"ts": issued_at,
|
||||
});
|
||||
let payload_bytes =
|
||||
serde_json::to_vec(&payload).map_err(|e| format!("could not serialize payload: {e}"))?;
|
||||
|
||||
let did =
|
||||
gitlawb_core::did::Did::from_str(node_did).map_err(|e| format!("bad node DID: {e}"))?;
|
||||
let verifying_key = did
|
||||
.to_verifying_key()
|
||||
.map_err(|e| format!("cannot derive a public key from {node_did}: {e}"))?;
|
||||
|
||||
let sig_vec = URL_SAFE_NO_PAD
|
||||
.decode(signature_b64)
|
||||
.map_err(|e| format!("signature is not valid base64url: {e}"))?;
|
||||
let sig_bytes: [u8; 64] = sig_vec
|
||||
.try_into()
|
||||
.map_err(|_| "signature is not 64 bytes".to_string())?;
|
||||
|
||||
gitlawb_core::identity::verify(&verifying_key, &payload_bytes, &sig_bytes)
|
||||
.map_err(|_| "Ed25519 signature does not match the signed payload".to_string())
|
||||
}
|
||||
|
||||
async fn resolve_cert_id(client: &NodeClient, owner: &str, name: &str, id: &str) -> Result<String> {
|
||||
if id.len() >= 36 {
|
||||
return Ok(id.to_string());
|
||||
}
|
||||
|
||||
let path = format!("/api/v1/repos/{owner}/{name}/certs");
|
||||
let path = format!("/api/v1/repos/{owner}/{name}/certs?prefix={id}");
|
||||
let resp: Value = client
|
||||
.get(&path)
|
||||
.get_authed(&path)
|
||||
.await?
|
||||
.error_for_status()
|
||||
.context("failed to list certificates")?
|
||||
@@ -182,7 +304,6 @@ async fn resolve_cert_id(client: &NodeClient, owner: &str, name: &str, id: &str)
|
||||
let matches: Vec<String> = certs
|
||||
.iter()
|
||||
.filter_map(|cert| cert["id"].as_str())
|
||||
.filter(|cert_id| cert_id.starts_with(id))
|
||||
.map(ToString::to_string)
|
||||
.collect();
|
||||
|
||||
@@ -192,3 +313,88 @@ async fn resolve_cert_id(client: &NodeClient, owner: &str, name: &str, id: &str)
|
||||
_ => anyhow::bail!("certificate prefix {id} matches multiple certificates"),
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
/// Pins gl's payload reconstruction to the frozen canonical byte form the
|
||||
/// node signs (default serde_json maps = alphabetically ordered keys). If
|
||||
/// serialization drifts — a field added, or a preserve_order feature
|
||||
/// landing anywhere in the workspace (feature unification flips every
|
||||
/// crate at once) — this literal stops matching and the test fails,
|
||||
/// instead of every real certificate silently rendering INVALID.
|
||||
#[test]
|
||||
fn payload_serialization_matches_frozen_canonical_form() {
|
||||
let payload = serde_json::json!({
|
||||
"repo_id": "repo-1",
|
||||
"ref": "refs/heads/main",
|
||||
"old": "oldsha",
|
||||
"new": "newsha",
|
||||
"pusher": "did:key:z6MkPusher",
|
||||
"node": "did:key:z6MkNode",
|
||||
"ts": "2026-07-22T00:00:00+00:00",
|
||||
});
|
||||
let frozen = concat!(
|
||||
r#"{"new":"newsha","node":"did:key:z6MkNode","old":"oldsha","#,
|
||||
r#""pusher":"did:key:z6MkPusher","ref":"refs/heads/main","#,
|
||||
r#""repo_id":"repo-1","ts":"2026-07-22T00:00:00+00:00"}"#,
|
||||
);
|
||||
assert_eq!(serde_json::to_string(&payload).unwrap(), frozen);
|
||||
}
|
||||
|
||||
/// Signing exactly as the node does must round-trip through
|
||||
/// verify_signature; any field tampering must fail it.
|
||||
#[test]
|
||||
fn verify_signature_round_trip_and_tamper() {
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let node_did = kp.did().as_str().to_string();
|
||||
|
||||
let payload = serde_json::json!({
|
||||
"repo_id": "repo-1",
|
||||
"ref": "refs/heads/main",
|
||||
"old": "0".repeat(40),
|
||||
"new": "a".repeat(40),
|
||||
"pusher": "did:key:z6MkPusher",
|
||||
"node": node_did,
|
||||
"ts": "2026-07-22T00:00:00+00:00",
|
||||
});
|
||||
let sig = kp.sign_b64(&serde_json::to_vec(&payload).unwrap());
|
||||
|
||||
let ok = verify_signature(
|
||||
"repo-1",
|
||||
"refs/heads/main",
|
||||
&"0".repeat(40),
|
||||
&"a".repeat(40),
|
||||
"did:key:z6MkPusher",
|
||||
&node_did,
|
||||
"2026-07-22T00:00:00+00:00",
|
||||
&sig,
|
||||
);
|
||||
assert!(ok.is_ok(), "expected valid signature, got: {ok:?}");
|
||||
|
||||
let tampered = verify_signature(
|
||||
"repo-1",
|
||||
"refs/heads/main",
|
||||
&"0".repeat(40),
|
||||
&"b".repeat(40), // new_sha changed after signing
|
||||
"did:key:z6MkPusher",
|
||||
&node_did,
|
||||
"2026-07-22T00:00:00+00:00",
|
||||
&sig,
|
||||
);
|
||||
assert!(tampered.is_err(), "tampered payload must not verify");
|
||||
|
||||
let garbage = verify_signature(
|
||||
"repo-1",
|
||||
"refs/heads/main",
|
||||
&"0".repeat(40),
|
||||
&"a".repeat(40),
|
||||
"did:key:z6MkPusher",
|
||||
&node_did,
|
||||
"2026-07-22T00:00:00+00:00",
|
||||
"not-base64url!!!",
|
||||
);
|
||||
assert!(garbage.is_err(), "malformed signature must not verify");
|
||||
}
|
||||
}
|
||||
+276
-11
@@ -16,6 +16,7 @@ use std::path::PathBuf;
|
||||
use crate::http::NodeClient;
|
||||
|
||||
const PUBLIC_NODE: &str = "https://node.gitlawb.com";
|
||||
const GITHUB_API_BASE: &str = "https://api.github.com";
|
||||
|
||||
#[derive(Args)]
|
||||
pub struct DoctorArgs {
|
||||
@@ -141,18 +142,20 @@ pub async fn run(args: DoctorArgs) -> Result<()> {
|
||||
|
||||
// ── 3. GITLAWB_NODE env var ───────────────────────────────────────────
|
||||
match std::env::var("GITLAWB_NODE") {
|
||||
Ok(v) if !v.is_empty() && !v.contains("127.0.0.1") && !v.contains("localhost") => {
|
||||
checks.push(Check::pass("GITLAWB_NODE", v.to_string()));
|
||||
}
|
||||
Ok(v) if v.contains("127.0.0.1") || v.contains("localhost") => {
|
||||
checks.push(Check::fail(
|
||||
// A loopback host is a legitimate setup (self-hosted node, dev
|
||||
// harness) — the connectivity check below fails loudly if it is not
|
||||
// actually reachable, so don't red-flag the configuration itself.
|
||||
Ok(v) if is_loopback_url(&v) => {
|
||||
checks.push(Check::pass(
|
||||
"GITLAWB_NODE",
|
||||
format!(
|
||||
"set to local address ({v}) — git push/clone will fail against remote nodes"
|
||||
"{v} (local node — intentional for self-hosting/dev; unset to target the public network)"
|
||||
),
|
||||
"export GITLAWB_NODE=https://node.gitlawb.com",
|
||||
));
|
||||
}
|
||||
Ok(v) if !v.is_empty() => {
|
||||
checks.push(Check::pass("GITLAWB_NODE", v.to_string()));
|
||||
}
|
||||
_ => {
|
||||
checks.push(Check::fail(
|
||||
"GITLAWB_NODE",
|
||||
@@ -174,6 +177,19 @@ pub async fn run(args: DoctorArgs) -> Result<()> {
|
||||
"node",
|
||||
format!("{} — v{version} ({short_did}…)", args.node),
|
||||
));
|
||||
// Capability drift: a node newer than this CLI may require features
|
||||
// (RFC 9421 signing, iCaptcha) the CLI doesn't speak.
|
||||
let gl_ver = env!("CARGO_PKG_VERSION");
|
||||
if version != "?" && is_newer(version, gl_ver) {
|
||||
checks.push(Check::warn(
|
||||
"gl version",
|
||||
format!(
|
||||
"node is v{version} but gl is v{gl_ver} — your CLI may be missing \
|
||||
features (signing / iCaptcha) this node requires"
|
||||
),
|
||||
"upgrade gl: curl -sSf https://gitlawb.com/install.sh | sh",
|
||||
));
|
||||
}
|
||||
}
|
||||
Ok(resp) => {
|
||||
checks.push(Check::fail(
|
||||
@@ -191,6 +207,31 @@ pub async fn run(args: DoctorArgs) -> Result<()> {
|
||||
}
|
||||
}
|
||||
|
||||
// ── 4b. iCaptcha capability ───────────────────────────────────────────
|
||||
// Gated writes (repo create / register / fork) auto-solve a challenge at the
|
||||
// iCaptcha service; check it's reachable so the failure mode is obvious.
|
||||
let icaptcha_url = std::env::var("GITLAWB_ICAPTCHA_URL")
|
||||
.unwrap_or_else(|_| icaptcha_client::DEFAULT_URL.to_string());
|
||||
match NodeClient::new(&icaptcha_url, None).get("/v1/pubkey").await {
|
||||
Ok(resp) if resp.status().is_success() => {
|
||||
checks.push(Check::pass("iCaptcha", format!("{icaptcha_url} reachable")));
|
||||
}
|
||||
Ok(resp) => {
|
||||
checks.push(Check::warn(
|
||||
"iCaptcha",
|
||||
format!("{icaptcha_url} returned HTTP {}", resp.status()),
|
||||
"gated writes (repo create / register) may fail until iCaptcha is reachable",
|
||||
));
|
||||
}
|
||||
Err(e) => {
|
||||
checks.push(Check::warn(
|
||||
"iCaptcha",
|
||||
format!("{icaptcha_url} unreachable: {e}"),
|
||||
"set GITLAWB_ICAPTCHA_URL or check connectivity — repo create / register solve a challenge there",
|
||||
));
|
||||
}
|
||||
}
|
||||
|
||||
// ── 5. git-remote-gitlawb helper ──────────────────────────────────────
|
||||
// Use PATH lookup only — invoking the binary directly triggers git internals
|
||||
// that error with "fatal: not a git repository" outside of a git repo.
|
||||
@@ -204,6 +245,15 @@ pub async fn run(args: DoctorArgs) -> Result<()> {
|
||||
));
|
||||
}
|
||||
|
||||
// ── 5b. shell alias shadowing ─────────────────────────────────────────
|
||||
// oh-my-zsh's default `git` plugin aliases gl='git pull', which silently
|
||||
// shadows this binary in every interactive zsh — the classic symptom is
|
||||
// `gl` printing "fatal: not a git repository". Aliases beat PATH, so no
|
||||
// install method can fix it; the user's rc file has to unalias.
|
||||
if let Some(check) = check_shell_alias_shadowing(dirs::home_dir()) {
|
||||
checks.push(check);
|
||||
}
|
||||
|
||||
// ── 6. git ────────────────────────────────────────────────────────────
|
||||
match std::process::Command::new("git")
|
||||
.arg("--version")
|
||||
@@ -225,7 +275,7 @@ pub async fn run(args: DoctorArgs) -> Result<()> {
|
||||
|
||||
// ── 7. Version up to date ─────────────────────────────────────────────
|
||||
let current = env!("CARGO_PKG_VERSION");
|
||||
checks.push(check_version(current).await);
|
||||
checks.push(check_version(current, GITHUB_API_BASE).await);
|
||||
|
||||
// ── Render ────────────────────────────────────────────────────────────
|
||||
for check in &checks {
|
||||
@@ -270,6 +320,83 @@ pub async fn run(args: DoctorArgs) -> Result<()> {
|
||||
}
|
||||
|
||||
/// Check if a binary name exists anywhere on PATH.
|
||||
/// True when the rc file contains a real `unalias` command naming `gl` —
|
||||
/// not a comment, and not a longer word like `unalias global`. Ordering
|
||||
/// relative to oh-my-zsh loading is not modeled (an unalias placed before the
|
||||
/// plugin loads would be ineffective); acceptable slack for a warning check.
|
||||
fn rc_unaliases_gl(rc: &str) -> bool {
|
||||
rc.lines().any(|line| {
|
||||
let line = line.trim_start();
|
||||
if line.starts_with('#') {
|
||||
return false;
|
||||
}
|
||||
line.split([';', '&', '|']).any(|cmd| {
|
||||
// A trailing comment must not count: `unalias foo # gl`
|
||||
let cmd = cmd.split('#').next().unwrap_or("");
|
||||
let mut tokens = cmd.split_whitespace();
|
||||
tokens.next() == Some("unalias") && tokens.any(|t| t == "gl")
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
/// True when the URL's host is exactly a loopback address. Substring checks
|
||||
/// misclassify hosts like `localhost.example` or URLs with "localhost" in the
|
||||
/// path, so parse and compare the actual host.
|
||||
fn is_loopback_url(value: &str) -> bool {
|
||||
reqwest::Url::parse(value)
|
||||
.ok()
|
||||
.and_then(|u| {
|
||||
u.host_str()
|
||||
.map(|h| h == "localhost" || h == "127.0.0.1" || h == "[::1]" || h == "::1")
|
||||
})
|
||||
.unwrap_or(false)
|
||||
}
|
||||
|
||||
/// Detect interactive-shell setups where an alias shadows `gl` (aliases beat
|
||||
/// PATH, so no install method can fix this). Best-effort heuristic over
|
||||
/// ~/.zshrc: an explicit `alias gl=`, or oh-my-zsh's `git` plugin (which
|
||||
/// ships gl='git pull'). Returns None when nothing suspicious is found or the
|
||||
/// rc file already contains an `unalias gl`.
|
||||
fn check_shell_alias_shadowing(home: Option<PathBuf>) -> Option<Check> {
|
||||
let home = home?;
|
||||
let rc = std::fs::read_to_string(home.join(".zshrc")).ok()?;
|
||||
if rc_unaliases_gl(&rc) {
|
||||
return None;
|
||||
}
|
||||
|
||||
let explicit_alias = rc.lines().any(|l| l.trim_start().starts_with("alias gl="));
|
||||
// Single-line `plugins=(git ...)` is the overwhelmingly common form; a
|
||||
// multi-line plugins array slips past this heuristic, which is acceptable
|
||||
// for a warning-level check.
|
||||
let omz_git_plugin = home.join(".oh-my-zsh/plugins/git").exists()
|
||||
&& rc.lines().any(|l| {
|
||||
let l = l.trim_start();
|
||||
l.starts_with("plugins=")
|
||||
&& l.trim_start_matches("plugins=(")
|
||||
.trim_end_matches(')')
|
||||
.split_whitespace()
|
||||
.any(|p| p == "git")
|
||||
});
|
||||
|
||||
if explicit_alias || omz_git_plugin {
|
||||
let source = if explicit_alias {
|
||||
"~/.zshrc defines `alias gl=`"
|
||||
} else {
|
||||
"oh-my-zsh's git plugin aliases gl='git pull'"
|
||||
};
|
||||
Some(Check::warn(
|
||||
"shell alias",
|
||||
format!(
|
||||
"{source} — interactive shells run that instead of this binary \
|
||||
(symptom: `gl` prints \"fatal: not a git repository\")"
|
||||
),
|
||||
"echo 'unalias gl 2>/dev/null' >> ~/.zshrc && source ~/.zshrc (must come after oh-my-zsh loads)",
|
||||
))
|
||||
} else {
|
||||
None
|
||||
}
|
||||
}
|
||||
|
||||
fn which_in_path(name: &str) -> bool {
|
||||
std::env::var_os("PATH")
|
||||
.map(|paths| {
|
||||
@@ -281,8 +408,9 @@ fn which_in_path(name: &str) -> bool {
|
||||
.unwrap_or(false)
|
||||
}
|
||||
|
||||
/// Fetch the latest release tag from gitlawb/releases and compare to current version.
|
||||
async fn check_version(current: &'static str) -> Check {
|
||||
/// Fetch the latest release tag from Gitlawb/node (the actual release repo — see install.sh's
|
||||
/// `GITLAWB_RELEASE_REPO` default) and compare to current version.
|
||||
async fn check_version(current: &'static str, github_api_base: &str) -> Check {
|
||||
let client = match reqwest::Client::builder()
|
||||
.user_agent(format!("gl/{current}"))
|
||||
.timeout(std::time::Duration::from_secs(5))
|
||||
@@ -293,7 +421,9 @@ async fn check_version(current: &'static str) -> Check {
|
||||
};
|
||||
|
||||
let resp = match client
|
||||
.get("https://api.github.com/repos/gitlawb/releases/releases/latest")
|
||||
.get(format!(
|
||||
"{github_api_base}/repos/Gitlawb/node/releases/latest"
|
||||
))
|
||||
.send()
|
||||
.await
|
||||
{
|
||||
@@ -301,6 +431,13 @@ async fn check_version(current: &'static str) -> Check {
|
||||
Err(_) => return Check::pass("version", format!("v{current} (offline — could not check)")),
|
||||
};
|
||||
|
||||
if !resp.status().is_success() {
|
||||
return Check::pass(
|
||||
"version",
|
||||
format!("v{current} (GitHub API returned HTTP {})", resp.status()),
|
||||
);
|
||||
}
|
||||
|
||||
let body: serde_json::Value = match resp.json().await {
|
||||
Ok(v) => v,
|
||||
Err(_) => return Check::pass("version", format!("v{current} (invalid response)")),
|
||||
@@ -344,6 +481,88 @@ fn is_newer(latest: &str, current: &str) -> bool {
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn fake_home(zshrc: Option<&str>, with_omz_git: bool) -> tempfile::TempDir {
|
||||
let home = tempfile::TempDir::new().unwrap();
|
||||
if let Some(rc) = zshrc {
|
||||
std::fs::write(home.path().join(".zshrc"), rc).unwrap();
|
||||
}
|
||||
if with_omz_git {
|
||||
std::fs::create_dir_all(home.path().join(".oh-my-zsh/plugins/git")).unwrap();
|
||||
}
|
||||
home
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn alias_shadowing_flags_omz_git_plugin() {
|
||||
let home = fake_home(Some("plugins=(git z)\nsource $ZSH/oh-my-zsh.sh\n"), true);
|
||||
let check = check_shell_alias_shadowing(Some(home.path().to_path_buf()));
|
||||
assert!(check.is_some(), "omz git plugin without unalias must warn");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn alias_shadowing_flags_explicit_alias() {
|
||||
let home = fake_home(Some("alias gl='git pull'\n"), false);
|
||||
assert!(check_shell_alias_shadowing(Some(home.path().to_path_buf())).is_some());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn alias_shadowing_silent_when_unaliased() {
|
||||
let home = fake_home(
|
||||
Some("plugins=(git z)\nsource $ZSH/oh-my-zsh.sh\nunalias gl 2>/dev/null\n"),
|
||||
true,
|
||||
);
|
||||
assert!(check_shell_alias_shadowing(Some(home.path().to_path_buf())).is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn alias_shadowing_ignores_fake_unaliases() {
|
||||
// None of these actually free `gl` — the warning must survive them.
|
||||
for rc in [
|
||||
"plugins=(git)\n# unalias gl\n", // commented out
|
||||
"plugins=(git)\nunalias global\n", // longer word
|
||||
"plugins=(git)\nunalias foo # gl\n", // gl only in a comment
|
||||
"plugins=(git)\necho unalias-gl-later\n", // not an unalias command
|
||||
] {
|
||||
let home = fake_home(Some(rc), true);
|
||||
assert!(
|
||||
check_shell_alias_shadowing(Some(home.path().to_path_buf())).is_some(),
|
||||
"must still warn for rc: {rc:?}"
|
||||
);
|
||||
}
|
||||
// Real unalias forms that do free it — all must silence the warning.
|
||||
for rc in [
|
||||
"plugins=(git)\nunalias gl\n",
|
||||
"plugins=(git)\nunalias gl 2>/dev/null\n",
|
||||
"plugins=(git)\ntrue; unalias gl\n",
|
||||
"plugins=(git)\nunalias glog gl gst\n",
|
||||
] {
|
||||
let home = fake_home(Some(rc), true);
|
||||
assert!(
|
||||
check_shell_alias_shadowing(Some(home.path().to_path_buf())).is_none(),
|
||||
"must be silent for rc: {rc:?}"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn loopback_url_detection_is_host_exact() {
|
||||
assert!(is_loopback_url("http://127.0.0.1:7545"));
|
||||
assert!(is_loopback_url("http://localhost:7545"));
|
||||
assert!(is_loopback_url("http://[::1]:7545"));
|
||||
assert!(!is_loopback_url("https://localhost.example"));
|
||||
assert!(!is_loopback_url("https://node.gitlawb.com/localhost"));
|
||||
assert!(!is_loopback_url("not a url"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn alias_shadowing_silent_without_signals() {
|
||||
let home = fake_home(Some("plugins=(z)\nexport EDITOR=vim\n"), false);
|
||||
assert!(check_shell_alias_shadowing(Some(home.path().to_path_buf())).is_none());
|
||||
let no_rc = fake_home(None, false);
|
||||
assert!(check_shell_alias_shadowing(Some(no_rc.path().to_path_buf())).is_none());
|
||||
assert!(check_shell_alias_shadowing(None).is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_is_newer_minor_bump() {
|
||||
assert!(is_newer("0.2.0", "0.1.0"));
|
||||
@@ -379,4 +598,50 @@ mod tests {
|
||||
fn test_which_in_path_missing_binary() {
|
||||
assert!(!which_in_path("this-binary-does-not-exist-gl-test-12345"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_check_version_queries_gitlawb_node_releases() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock("GET", "/repos/Gitlawb/node/releases/latest")
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"tag_name":"v9.9.9"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let check = check_version("0.1.0", &server.url()).await;
|
||||
assert!(matches!(check.state, CheckState::Warn));
|
||||
assert!(check.detail.contains("v9.9.9"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_check_version_up_to_date() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock("GET", "/repos/Gitlawb/node/releases/latest")
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"tag_name":"v0.1.0"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let check = check_version("0.1.0", &server.url()).await;
|
||||
assert!(matches!(check.state, CheckState::Ok));
|
||||
assert!(check.detail.contains("up to date"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_check_version_http_error() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock("GET", "/repos/Gitlawb/node/releases/latest")
|
||||
.with_status(403)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let check = check_version("0.1.0", &server.url()).await;
|
||||
assert!(matches!(check.state, CheckState::Ok));
|
||||
assert!(check.detail.contains("GitHub API returned HTTP 403"));
|
||||
}
|
||||
}
|
||||
+514
-38
@@ -1,8 +1,19 @@
|
||||
//! Signed HTTP client for gitlawb API calls (async).
|
||||
//!
|
||||
//! Writes are signed with RFC 9421 HTTP Signatures. When the node gates a write
|
||||
//! behind iCaptcha (HTTP 403 `icaptcha_proof_required`, advertised via the
|
||||
//! `x-icaptcha-url` / `x-icaptcha-level` headers), the client transparently
|
||||
//! solves the challenge and retries the same signed request with the
|
||||
//! `x-icaptcha-proof` header — see `crates/icaptcha-client`.
|
||||
|
||||
use anyhow::{Context, Result};
|
||||
use gitlawb_core::http_sig::sign_request;
|
||||
use gitlawb_core::identity::Keypair;
|
||||
use icaptcha_client::IcaptchaCfg;
|
||||
|
||||
/// Max times we'll fetch a fresh proof and retry a 403-iCaptcha response
|
||||
/// (absorbs proof expiry / first-seen replay).
|
||||
const MAX_ICAPTCHA_RETRIES: usize = 2;
|
||||
|
||||
pub struct NodeClient {
|
||||
inner: reqwest::Client,
|
||||
@@ -34,6 +45,15 @@ impl NodeClient {
|
||||
.with_context(|| format!("GET {url}"))
|
||||
}
|
||||
|
||||
/// GET that signs when a keypair is available; falls back to unsigned for public repos.
|
||||
pub async fn get_authed(&self, path: &str) -> Result<reqwest::Response> {
|
||||
if self.keypair.is_some() {
|
||||
self.get_signed(path).await
|
||||
} else {
|
||||
self.get(path).await
|
||||
}
|
||||
}
|
||||
|
||||
/// GET with RFC 9421 HTTP Signature auth, for owner-only read endpoints.
|
||||
/// Signs over the empty body (same shape the node verifies for signed reads).
|
||||
pub async fn get_signed(&self, path: &str) -> Result<reqwest::Response> {
|
||||
@@ -52,63 +72,519 @@ impl NodeClient {
|
||||
req.send().await.with_context(|| format!("GET {url}"))
|
||||
}
|
||||
|
||||
/// POST with JSON body + RFC 9421 HTTP Signature auth.
|
||||
/// GET that signs when an identity keypair is present and falls back to an
|
||||
/// anonymous GET otherwise — for read-visibility endpoints, where a public
|
||||
/// repo is readable anonymously but a private repo requires the owner/reader
|
||||
/// to be authenticated. Mirrors the conditional signing of post/put/delete.
|
||||
pub async fn get_maybe_signed(&self, path: &str) -> Result<reqwest::Response> {
|
||||
let url = format!("{}{}", self.node_url, path);
|
||||
let mut req = self.inner.get(&url);
|
||||
if let Some(kp) = &self.keypair {
|
||||
let signed = sign_request(kp, "GET", path, b"");
|
||||
req = req
|
||||
.header("Content-Digest", signed.content_digest)
|
||||
.header("Signature-Input", signed.signature_input)
|
||||
.header("Signature", signed.signature);
|
||||
}
|
||||
req.send().await.with_context(|| format!("GET {url}"))
|
||||
}
|
||||
|
||||
/// POST with JSON body + RFC 9421 signing + transparent iCaptcha solve/retry.
|
||||
pub async fn post(&self, path: &str, body: &[u8]) -> Result<reqwest::Response> {
|
||||
let url = format!("{}{}", self.node_url, path);
|
||||
let mut req = self
|
||||
.inner
|
||||
.post(&url)
|
||||
.header("Content-Type", "application/json")
|
||||
.body(body.to_vec());
|
||||
|
||||
if let Some(kp) = &self.keypair {
|
||||
let signed = sign_request(kp, "POST", path, body);
|
||||
req = req
|
||||
.header("Content-Digest", signed.content_digest)
|
||||
.header("Signature-Input", signed.signature_input)
|
||||
.header("Signature", signed.signature);
|
||||
}
|
||||
|
||||
req.send().await.with_context(|| format!("POST {url}"))
|
||||
self.send_signed("POST", path, body).await
|
||||
}
|
||||
|
||||
/// PUT with RFC 9421 HTTP Signature auth (idempotent write).
|
||||
/// PUT with RFC 9421 signing + transparent iCaptcha solve/retry.
|
||||
pub async fn put(&self, path: &str, body: &[u8]) -> Result<reqwest::Response> {
|
||||
let url = format!("{}{}", self.node_url, path);
|
||||
let mut req = self
|
||||
.inner
|
||||
.put(&url)
|
||||
.header("Content-Type", "application/json")
|
||||
.body(body.to_vec());
|
||||
|
||||
if let Some(kp) = &self.keypair {
|
||||
let signed = sign_request(kp, "PUT", path, body);
|
||||
req = req
|
||||
.header("Content-Digest", signed.content_digest)
|
||||
.header("Signature-Input", signed.signature_input)
|
||||
.header("Signature", signed.signature);
|
||||
}
|
||||
|
||||
req.send().await.with_context(|| format!("PUT {url}"))
|
||||
self.send_signed("PUT", path, body).await
|
||||
}
|
||||
|
||||
/// DELETE with RFC 9421 HTTP Signature auth.
|
||||
/// DELETE with RFC 9421 signing + transparent iCaptcha solve/retry.
|
||||
pub async fn delete(&self, path: &str, body: &[u8]) -> Result<reqwest::Response> {
|
||||
self.send_signed("DELETE", path, body).await
|
||||
}
|
||||
|
||||
/// Sign + send a write. On a 403 iCaptcha challenge (detected via the
|
||||
/// `x-icaptcha-*` headers) solve it and retry the same signed request with
|
||||
/// the proof header, up to [`MAX_ICAPTCHA_RETRIES`]. Emits an actionable
|
||||
/// hint on a 401 "not an agent" (the old-CLI / unregistered failure mode).
|
||||
async fn send_signed(
|
||||
&self,
|
||||
method: &str,
|
||||
path: &str,
|
||||
body: &[u8],
|
||||
) -> Result<reqwest::Response> {
|
||||
let mut proof: Option<String> = None;
|
||||
let mut attempts = 0;
|
||||
loop {
|
||||
let resp = self.send_once(method, path, body, proof.as_deref()).await?;
|
||||
let status = resp.status();
|
||||
|
||||
if status == reqwest::StatusCode::UNAUTHORIZED
|
||||
&& resp
|
||||
.headers()
|
||||
.get("x-gitlawb-error")
|
||||
.and_then(|v| v.to_str().ok())
|
||||
== Some("human_detected")
|
||||
{
|
||||
eprintln!(
|
||||
"note: this node requires signed requests (RFC 9421). If writes keep \
|
||||
failing, your `gl` may be too old — upgrade it — or you're not registered: \
|
||||
run `gl register`."
|
||||
);
|
||||
}
|
||||
|
||||
if status == reqwest::StatusCode::FORBIDDEN && attempts < MAX_ICAPTCHA_RETRIES {
|
||||
if let Some(cfg) = self.icaptcha_cfg(resp.headers())? {
|
||||
attempts += 1;
|
||||
proof = Some(obtain_proof(cfg).await?);
|
||||
continue;
|
||||
}
|
||||
}
|
||||
return Ok(resp);
|
||||
}
|
||||
}
|
||||
|
||||
/// Build, sign, and send one request, optionally attaching a proof header.
|
||||
async fn send_once(
|
||||
&self,
|
||||
method: &str,
|
||||
path: &str,
|
||||
body: &[u8],
|
||||
proof: Option<&str>,
|
||||
) -> Result<reqwest::Response> {
|
||||
let url = format!("{}{}", self.node_url, path);
|
||||
let mut req = self
|
||||
.inner
|
||||
.delete(&url)
|
||||
.request(method.parse().expect("valid HTTP method"), &url)
|
||||
.header("Content-Type", "application/json")
|
||||
.body(body.to_vec());
|
||||
|
||||
if let Some(kp) = &self.keypair {
|
||||
let signed = sign_request(kp, "DELETE", path, body);
|
||||
let signed = sign_request(kp, method, path, body);
|
||||
req = req
|
||||
.header("Content-Digest", signed.content_digest)
|
||||
.header("Signature-Input", signed.signature_input)
|
||||
.header("Signature", signed.signature);
|
||||
}
|
||||
if let Some(p) = proof {
|
||||
req = req.header(icaptcha_client::PROOF_HEADER, p);
|
||||
}
|
||||
|
||||
req.send().await.with_context(|| format!("DELETE {url}"))
|
||||
req.send().await.with_context(|| format!("{method} {url}"))
|
||||
}
|
||||
|
||||
/// If `headers` describe an iCaptcha 403, build the solve config (binding the
|
||||
/// proof's `sub` to our DID). Returns `None` for a non-iCaptcha 403.
|
||||
fn icaptcha_cfg(&self, headers: &reqwest::header::HeaderMap) -> Result<Option<IcaptchaCfg>> {
|
||||
let url = headers.get("x-icaptcha-url").and_then(|v| v.to_str().ok());
|
||||
let level = headers
|
||||
.get("x-icaptcha-level")
|
||||
.and_then(|v| v.to_str().ok());
|
||||
if url.is_none() && level.is_none() {
|
||||
return Ok(None); // not an iCaptcha challenge
|
||||
}
|
||||
let kp = self
|
||||
.keypair
|
||||
.as_ref()
|
||||
.context("iCaptcha challenge requires an identity keypair (run `gl identity new`)")?;
|
||||
Ok(Some(IcaptchaCfg::new(
|
||||
kp.did().to_string(),
|
||||
url.map(str::to_string),
|
||||
level.and_then(|l| l.parse().ok()),
|
||||
)))
|
||||
}
|
||||
}
|
||||
|
||||
/// Run the (blocking) iCaptcha solve loop off the async runtime.
|
||||
async fn obtain_proof(cfg: IcaptchaCfg) -> Result<String> {
|
||||
tokio::task::spawn_blocking(move || icaptcha_client::obtain_proof(&cfg, None))
|
||||
.await
|
||||
.context("iCaptcha solver task panicked")?
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use gitlawb_core::identity::Keypair;
|
||||
use mockito::Server;
|
||||
use std::ffi::OsString;
|
||||
use std::sync::{Mutex, MutexGuard};
|
||||
|
||||
/// Serializes the two integration tests that touch the process-global
|
||||
/// `GITLAWB_ICAPTCHA_URL` / `GITLAWB_ICAPTCHA_INSECURE` env vars so they
|
||||
/// never race.
|
||||
static ICAPTCHA_ENV_LOCK: Mutex<()> = Mutex::new(());
|
||||
|
||||
fn test_keypair() -> Keypair {
|
||||
Keypair::generate()
|
||||
}
|
||||
|
||||
fn headers_from_pairs(pairs: &[(&str, &str)]) -> reqwest::header::HeaderMap {
|
||||
let mut h = reqwest::header::HeaderMap::new();
|
||||
for (k, v) in pairs {
|
||||
h.insert(
|
||||
k.parse::<reqwest::header::HeaderName>().unwrap(),
|
||||
v.parse::<reqwest::header::HeaderValue>().unwrap(),
|
||||
);
|
||||
}
|
||||
h
|
||||
}
|
||||
|
||||
// ── icaptcha_cfg ────────────────────────────────────────────────────
|
||||
|
||||
#[test]
|
||||
fn icaptcha_cfg_returns_some_when_both_headers_present() {
|
||||
let kp = test_keypair();
|
||||
let client = NodeClient::new("http://localhost", Some(kp.clone()));
|
||||
let headers = headers_from_pairs(&[
|
||||
("x-icaptcha-url", "https://icaptcha.gitlawb.com"),
|
||||
("x-icaptcha-level", "3"),
|
||||
]);
|
||||
let cfg = client.icaptcha_cfg(&headers).unwrap().unwrap();
|
||||
assert_eq!(cfg.did, kp.did().to_string());
|
||||
assert_eq!(cfg.level, 3);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn icaptcha_cfg_defaults_level_when_only_url_present() {
|
||||
let kp = test_keypair();
|
||||
let client = NodeClient::new("http://localhost", Some(kp));
|
||||
let headers = headers_from_pairs(&[("x-icaptcha-url", "https://icaptcha.gitlawb.com")]);
|
||||
let cfg = client.icaptcha_cfg(&headers).unwrap().unwrap();
|
||||
assert_eq!(cfg.level, icaptcha_client::DEFAULT_LEVEL);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn icaptcha_cfg_defaults_url_when_only_level_present() {
|
||||
let kp = test_keypair();
|
||||
let client = NodeClient::new("http://localhost", Some(kp));
|
||||
let headers = headers_from_pairs(&[("x-icaptcha-level", "5")]);
|
||||
let cfg = client.icaptcha_cfg(&headers).unwrap().unwrap();
|
||||
assert_eq!(cfg.level, 5);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn icaptcha_cfg_returns_none_without_icaptcha_headers() {
|
||||
let client = NodeClient::new("http://localhost", Some(test_keypair()));
|
||||
let headers = reqwest::header::HeaderMap::new();
|
||||
assert!(client.icaptcha_cfg(&headers).unwrap().is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn icaptcha_cfg_returns_none_with_unrelated_headers() {
|
||||
let client = NodeClient::new("http://localhost", Some(test_keypair()));
|
||||
let headers = headers_from_pairs(&[("content-type", "application/json")]);
|
||||
assert!(client.icaptcha_cfg(&headers).unwrap().is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn icaptcha_cfg_errors_when_no_keypair() {
|
||||
let client = NodeClient::new("http://localhost", None);
|
||||
let headers = headers_from_pairs(&[("x-icaptcha-level", "3")]);
|
||||
let err = client.icaptcha_cfg(&headers).unwrap_err();
|
||||
assert!(err.to_string().contains("identity keypair"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn icaptcha_cfg_ignores_unparseable_level() {
|
||||
let client = NodeClient::new("http://localhost", Some(test_keypair()));
|
||||
let headers = headers_from_pairs(&[
|
||||
("x-icaptcha-url", "https://icaptcha.gitlawb.com"),
|
||||
("x-icaptcha-level", "not-a-number"),
|
||||
]);
|
||||
let cfg = client.icaptcha_cfg(&headers).unwrap().unwrap();
|
||||
assert_eq!(cfg.level, icaptcha_client::DEFAULT_LEVEL);
|
||||
}
|
||||
|
||||
// ── send_once ───────────────────────────────────────────────────────
|
||||
|
||||
#[tokio::test]
|
||||
async fn send_once_attaches_proof_header_when_provided() {
|
||||
let mut server = Server::new_async().await;
|
||||
let m = server
|
||||
.mock("POST", "/api/test")
|
||||
.match_header("x-icaptcha-proof", "test.proof.token")
|
||||
.with_status(200)
|
||||
.with_body("ok")
|
||||
.create_async()
|
||||
.await;
|
||||
let client = NodeClient::new(server.url(), None);
|
||||
let resp = client
|
||||
.send_once("POST", "/api/test", b"{}", Some("test.proof.token"))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), 200);
|
||||
m.assert();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn send_once_omits_proof_header_when_not_provided() {
|
||||
let mut server = Server::new_async().await;
|
||||
let m = server
|
||||
.mock("POST", "/api/test")
|
||||
.match_header("x-icaptcha-proof", mockito::Matcher::Missing)
|
||||
.with_status(200)
|
||||
.with_body("ok")
|
||||
.create_async()
|
||||
.await;
|
||||
let client = NodeClient::new(server.url(), None);
|
||||
let resp = client
|
||||
.send_once("POST", "/api/test", b"{}", None)
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), 200);
|
||||
m.assert();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn send_once_signs_request_when_keypair_present() {
|
||||
let mut server = Server::new_async().await;
|
||||
let m = server
|
||||
.mock("POST", "/api/test")
|
||||
.match_header("Signature", mockito::Matcher::Any)
|
||||
.match_header("Signature-Input", mockito::Matcher::Any)
|
||||
.match_header("Content-Digest", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_body("ok")
|
||||
.create_async()
|
||||
.await;
|
||||
let client = NodeClient::new(server.url(), Some(test_keypair()));
|
||||
let resp = client
|
||||
.send_once("POST", "/api/test", b"{}", None)
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), 200);
|
||||
m.assert();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn send_once_does_not_sign_when_no_keypair() {
|
||||
let mut server = Server::new_async().await;
|
||||
let m = server
|
||||
.mock("POST", "/api/test")
|
||||
.match_header("Signature", mockito::Matcher::Missing)
|
||||
.match_header("Signature-Input", mockito::Matcher::Missing)
|
||||
.match_header("Content-Digest", mockito::Matcher::Missing)
|
||||
.with_status(200)
|
||||
.with_body("ok")
|
||||
.create_async()
|
||||
.await;
|
||||
let client = NodeClient::new(server.url(), None);
|
||||
let resp = client
|
||||
.send_once("POST", "/api/test", b"{}", None)
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), 200);
|
||||
m.assert();
|
||||
}
|
||||
|
||||
// ── send_signed ─────────────────────────────────────────────────────
|
||||
|
||||
#[tokio::test]
|
||||
async fn send_signed_returns_non_icaptcha_403_without_retry() {
|
||||
let mut server = Server::new_async().await;
|
||||
let m = server
|
||||
.mock("POST", "/api/register")
|
||||
.with_status(403)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"error":"forbidden"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
let client = NodeClient::new(server.url(), Some(test_keypair()));
|
||||
let resp = client
|
||||
.send_signed("POST", "/api/register", b"{}")
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), 403);
|
||||
m.assert();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn send_signed_returns_first_response_on_success() {
|
||||
let mut server = Server::new_async().await;
|
||||
let m = server
|
||||
.mock("POST", "/api/register")
|
||||
.with_status(201)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"status":"created"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
let client = NodeClient::new(server.url(), Some(test_keypair()));
|
||||
let resp = client
|
||||
.send_signed("POST", "/api/register", b"{}")
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), 201);
|
||||
m.assert();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn send_signed_handles_405_not_icaptcha() {
|
||||
let mut server = Server::new_async().await;
|
||||
let m = server
|
||||
.mock("POST", "/api/register")
|
||||
.with_status(405)
|
||||
.with_body(r#"{"error":"method not allowed"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
let client = NodeClient::new(server.url(), Some(test_keypair()));
|
||||
let resp = client
|
||||
.send_signed("POST", "/api/register", b"{}")
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), 405);
|
||||
m.assert();
|
||||
}
|
||||
|
||||
// ── send_signed iCaptcha retry (full integration) ────────────────────
|
||||
|
||||
/// Set GITLAWB_ICAPTCHA_URL and GITLAWB_ICAPTCHA_INSECURE so the iCaptcha
|
||||
/// client trusts a local mockito HTTP server, restoring any prior values on
|
||||
/// drop so a test run launched with those variables keeps working.
|
||||
/// Holds [`ICAPTCHA_ENV_LOCK`] for its lifetime so concurrent tests don't
|
||||
/// race on the process-global env vars.
|
||||
struct IcaptchaEnv {
|
||||
_lock: MutexGuard<'static, ()>,
|
||||
prev_url: Option<OsString>,
|
||||
prev_insecure: Option<OsString>,
|
||||
}
|
||||
|
||||
impl IcaptchaEnv {
|
||||
fn new(url: &str) -> Self {
|
||||
let lock = ICAPTCHA_ENV_LOCK.lock().unwrap();
|
||||
let prev_url = std::env::var_os("GITLAWB_ICAPTCHA_URL");
|
||||
let prev_insecure = std::env::var_os("GITLAWB_ICAPTCHA_INSECURE");
|
||||
std::env::set_var("GITLAWB_ICAPTCHA_URL", url);
|
||||
std::env::set_var("GITLAWB_ICAPTCHA_INSECURE", "1");
|
||||
IcaptchaEnv {
|
||||
_lock: lock,
|
||||
prev_url,
|
||||
prev_insecure,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl Drop for IcaptchaEnv {
|
||||
fn drop(&mut self) {
|
||||
match self.prev_url.take() {
|
||||
Some(v) => std::env::set_var("GITLAWB_ICAPTCHA_URL", v),
|
||||
None => std::env::remove_var("GITLAWB_ICAPTCHA_URL"),
|
||||
}
|
||||
match self.prev_insecure.take() {
|
||||
Some(v) => std::env::set_var("GITLAWB_ICAPTCHA_INSECURE", v),
|
||||
None => std::env::remove_var("GITLAWB_ICAPTCHA_INSECURE"),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Set up a mock iCaptcha server that responds to challenge + answer.
|
||||
/// `hits` sets the expected call count for both endpoints so the test can
|
||||
/// verify the solve loop was entered the correct number of times.
|
||||
struct MockIcaptcha {
|
||||
challenge: mockito::Mock,
|
||||
answer: mockito::Mock,
|
||||
_guard: IcaptchaEnv,
|
||||
url: String,
|
||||
}
|
||||
|
||||
impl MockIcaptcha {
|
||||
async fn new(server: &mut mockito::ServerGuard, hits: usize) -> Self {
|
||||
let url = server.url();
|
||||
let guard = IcaptchaEnv::new(&url);
|
||||
let challenge = server
|
||||
.mock("POST", "/v1/challenge")
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(
|
||||
r#"{"challengeId":"c1","type":"arithmetic","difficulty":1,"prompt":"What is 1 + 1?","token":"tk1"}"#,
|
||||
)
|
||||
.expect(hits)
|
||||
.create_async()
|
||||
.await;
|
||||
let answer = server
|
||||
.mock("POST", "/v1/answer")
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"status":"passed","proof":"mock.proof"}"#)
|
||||
.expect(hits)
|
||||
.create_async()
|
||||
.await;
|
||||
Self {
|
||||
challenge,
|
||||
answer,
|
||||
_guard: guard,
|
||||
url,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn send_signed_solves_icaptcha_and_retries_to_success() {
|
||||
let mut node = Server::new_async().await;
|
||||
let mut icaptcha = Server::new_async().await;
|
||||
let ic = MockIcaptcha::new(&mut icaptcha, 1).await;
|
||||
|
||||
let n1 = node
|
||||
.mock("POST", "/api/register")
|
||||
.with_status(403)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_header("x-icaptcha-url", &ic.url)
|
||||
.with_header("x-icaptcha-level", "3")
|
||||
.with_body(r#"{"error":"icaptcha_proof_required"}"#)
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
let n2 = node
|
||||
.mock("POST", "/api/register")
|
||||
.match_header("x-icaptcha-proof", "mock.proof")
|
||||
.with_status(201)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"status":"created"}"#)
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let client = NodeClient::new(node.url(), Some(test_keypair()));
|
||||
let resp = client
|
||||
.send_signed("POST", "/api/register", b"{}")
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), 201);
|
||||
n1.assert();
|
||||
n2.assert();
|
||||
ic.challenge.assert();
|
||||
ic.answer.assert();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn send_signed_returns_403_after_icaptcha_retries_exhausted() {
|
||||
let mut node = Server::new_async().await;
|
||||
let mut icaptcha = Server::new_async().await;
|
||||
// MAX_ICAPTCHA_RETRIES = 2, so with every call returning 403 with
|
||||
// iCaptcha headers the solve loop runs twice (2 challenge + 2 answer).
|
||||
let ic = MockIcaptcha::new(&mut icaptcha, 2).await;
|
||||
|
||||
// The original + 2 retries = 3 node calls before the loop gives up.
|
||||
let n = node
|
||||
.mock("POST", "/api/register")
|
||||
.with_status(403)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_header("x-icaptcha-url", &ic.url)
|
||||
.with_header("x-icaptcha-level", "3")
|
||||
.with_body(r#"{"error":"icaptcha_proof_required"}"#)
|
||||
.expect(3)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let client = NodeClient::new(node.url(), Some(test_keypair()));
|
||||
let resp = client
|
||||
.send_signed("POST", "/api/register", b"{}")
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(resp.status(), 403);
|
||||
n.assert();
|
||||
ic.challenge.assert();
|
||||
ic.answer.assert();
|
||||
}
|
||||
}
|
||||
+52
-4
@@ -38,13 +38,23 @@ pub async fn run(args: InitArgs) -> Result<()> {
|
||||
let git_dir = cwd.join(".git");
|
||||
if !git_dir.exists() {
|
||||
println!("Initializing git repository...");
|
||||
// -b main: the push flow targets `main`; without it a fresh repo uses
|
||||
// the user's init.defaultBranch (often `master`). Older git (<2.28)
|
||||
// lacks the flag, so fall back to a plain init.
|
||||
let status = std::process::Command::new("git")
|
||||
.args(["init"])
|
||||
.args(["init", "-b", "main"])
|
||||
.current_dir(&cwd)
|
||||
.status()
|
||||
.context("failed to run git init")?;
|
||||
if !status.success() {
|
||||
anyhow::bail!("git init failed");
|
||||
let status = std::process::Command::new("git")
|
||||
.args(["init"])
|
||||
.current_dir(&cwd)
|
||||
.status()
|
||||
.context("failed to run git init")?;
|
||||
if !status.success() {
|
||||
anyhow::bail!("git init failed");
|
||||
}
|
||||
}
|
||||
} else {
|
||||
println!("Git repository detected.");
|
||||
@@ -165,9 +175,47 @@ pub async fn run(args: InitArgs) -> Result<()> {
|
||||
}
|
||||
}
|
||||
|
||||
// The hint must match the repo's actual state: with no commits yet, a bare
|
||||
// `git push` fails with "src refspec ... does not match any" — exactly the
|
||||
// trap a zero-to-push command must not set.
|
||||
let has_commits = std::process::Command::new("git")
|
||||
.args(["rev-parse", "--verify", "HEAD"])
|
||||
.current_dir(&cwd)
|
||||
.stdout(std::process::Stdio::null())
|
||||
.stderr(std::process::Stdio::null())
|
||||
.status()
|
||||
.map(|s| s.success())
|
||||
.unwrap_or(false);
|
||||
// symbolic-ref succeeds on a branch (including an unborn one) and fails
|
||||
// on a detached HEAD — where guessing "main" could push the wrong ref.
|
||||
let branch = std::process::Command::new("git")
|
||||
.args(["symbolic-ref", "--short", "HEAD"])
|
||||
.current_dir(&cwd)
|
||||
.stderr(std::process::Stdio::null())
|
||||
.output()
|
||||
.ok()
|
||||
.filter(|o| o.status.success())
|
||||
.and_then(|o| String::from_utf8(o.stdout).ok())
|
||||
.map(|s| s.trim().to_string())
|
||||
.filter(|s| !s.is_empty());
|
||||
|
||||
println!();
|
||||
println!("Ready! Push with:");
|
||||
println!(" git push gitlawb main");
|
||||
match (branch, has_commits) {
|
||||
(Some(branch), true) => {
|
||||
println!("Ready! Push with:");
|
||||
println!(" git push gitlawb {branch}");
|
||||
}
|
||||
(Some(branch), false) => {
|
||||
println!("Ready! Nothing is committed yet — commit, then push:");
|
||||
println!(" git add -A && git commit -m \"initial commit\"");
|
||||
println!(" git push gitlawb {branch}");
|
||||
}
|
||||
(None, _) => {
|
||||
println!("Ready! HEAD is detached — create or switch to a branch, then push:");
|
||||
println!(" git switch -c main");
|
||||
println!(" git push gitlawb main");
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
+137
-9
@@ -3,6 +3,8 @@
|
||||
//! Communicates with the gitlawb node to list pinned CIDs and retrieve git
|
||||
//! objects by their content-addressed CID.
|
||||
|
||||
use std::path::PathBuf;
|
||||
|
||||
use anyhow::{Context, Result};
|
||||
use clap::{Args, Subcommand};
|
||||
use serde_json::Value;
|
||||
@@ -21,6 +23,9 @@ pub enum IpfsCmd {
|
||||
List {
|
||||
#[arg(long, default_value = "https://node.gitlawb.com", env = "GITLAWB_NODE")]
|
||||
node: String,
|
||||
/// Identity directory (default: ~/.gitlawb)
|
||||
#[arg(long)]
|
||||
dir: Option<PathBuf>,
|
||||
},
|
||||
/// Retrieve and display a git object from the node by its CIDv1
|
||||
Get {
|
||||
@@ -33,19 +38,24 @@ pub enum IpfsCmd {
|
||||
|
||||
pub async fn run(args: IpfsArgs) -> Result<()> {
|
||||
match args.cmd {
|
||||
IpfsCmd::List { node } => cmd_list(node).await,
|
||||
IpfsCmd::List { node, dir } => cmd_list(node, dir).await,
|
||||
IpfsCmd::Get { cid, node } => cmd_get(cid, node).await,
|
||||
}
|
||||
}
|
||||
|
||||
async fn cmd_list(node: String) -> Result<()> {
|
||||
let client = NodeClient::new(&node, None);
|
||||
let resp: Value = client
|
||||
.get("/api/v1/ipfs/pins")
|
||||
.await?
|
||||
.json()
|
||||
.await
|
||||
.context("failed to parse pins response")?;
|
||||
async fn cmd_list(node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
// #134 gates /api/v1/ipfs/pins behind auth: sign the request with the
|
||||
// caller's identity. On no identity, propagate load_keypair_from_dir's
|
||||
// error (it already names `gl identity new`) rather than a bare 401.
|
||||
let keypair = crate::identity::load_keypair_from_dir(dir.as_deref())?;
|
||||
let client = NodeClient::new(&node, Some(keypair));
|
||||
let resp = client.get_signed("/api/v1/ipfs/pins").await?;
|
||||
if !resp.status().is_success() {
|
||||
let status = resp.status();
|
||||
let body = resp.text().await.unwrap_or_default();
|
||||
anyhow::bail!("node returned {status} for pins listing: {body}");
|
||||
}
|
||||
let resp: Value = resp.json().await.context("failed to parse pins response")?;
|
||||
|
||||
let pins = resp["pins"].as_array().cloned().unwrap_or_default();
|
||||
let count = resp["count"].as_u64().unwrap_or(pins.len() as u64);
|
||||
@@ -108,3 +118,121 @@ async fn cmd_get(cid: String, node: String) -> Result<()> {
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
/// Seed a keypair into a temp dir the way `load_keypair_from_dir` expects,
|
||||
/// then return the dir handle (keeps it alive for the test's duration).
|
||||
fn seed_keystore() -> tempfile::TempDir {
|
||||
let dir = tempfile::TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
std::fs::write(
|
||||
dir.path().join("identity.pem"),
|
||||
kp.to_pem().unwrap().as_bytes(),
|
||||
)
|
||||
.unwrap();
|
||||
dir
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_cmd_list_signs_request_and_renders_pins() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let keystore = seed_keystore();
|
||||
|
||||
// Happy path: signed GET to /api/v1/ipfs/pins carrying the RFC 9421
|
||||
// signature headers, node returns a populated pins body.
|
||||
let m = server
|
||||
.mock("GET", "/api/v1/ipfs/pins")
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.match_header("content-digest", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(
|
||||
r#"{"pins":[{"cid":"bafyone","sha256_hex":"abc123","pinned_at":"2026-07-02T12:00:00.123456Z"}],"count":1}"#,
|
||||
)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
cmd_list(server.url(), Some(keystore.path().to_path_buf()))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
m.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_cmd_list_empty_pins() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let keystore = seed_keystore();
|
||||
|
||||
let m = server
|
||||
.mock("GET", "/api/v1/ipfs/pins")
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"pins":[],"count":0}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
cmd_list(server.url(), Some(keystore.path().to_path_buf()))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
m.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_cmd_list_no_identity_errors_without_request() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
// Empty keystore dir: no identity.pem present.
|
||||
let empty = tempfile::TempDir::new().unwrap();
|
||||
|
||||
// The endpoint must never be hit when there is no identity.
|
||||
let m = server
|
||||
.mock("GET", "/api/v1/ipfs/pins")
|
||||
.expect(0)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let err = cmd_list(server.url(), Some(empty.path().to_path_buf()))
|
||||
.await
|
||||
.expect_err("no identity should be an error");
|
||||
assert!(
|
||||
err.to_string().contains("gl identity new")
|
||||
|| err.to_string().contains("no identity found"),
|
||||
"error should name `gl identity new`, got: {err}"
|
||||
);
|
||||
|
||||
m.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_cmd_list_non_success_status_is_error_not_empty() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let keystore = seed_keystore();
|
||||
|
||||
// A signed request the node rejects (401) must surface as an error,
|
||||
// not be silently parsed into an empty pin list.
|
||||
let m = server
|
||||
.mock("GET", "/api/v1/ipfs/pins")
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.with_status(401)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"error":"unauthorized"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let err = cmd_list(server.url(), Some(keystore.path().to_path_buf()))
|
||||
.await
|
||||
.expect_err("non-2xx status should be an error");
|
||||
assert!(
|
||||
err.to_string().contains("401"),
|
||||
"error should mention the status, got: {err}"
|
||||
);
|
||||
|
||||
m.assert_async().await;
|
||||
}
|
||||
}
|
||||
+10
-6
@@ -10,6 +10,10 @@ use uuid::Uuid;
|
||||
use crate::http::NodeClient;
|
||||
use crate::identity::load_keypair_from_dir;
|
||||
|
||||
fn signed_client(node: &str, dir: Option<&std::path::Path>) -> NodeClient {
|
||||
NodeClient::new(node, load_keypair_from_dir(dir).ok())
|
||||
}
|
||||
|
||||
#[derive(Args)]
|
||||
pub struct IssueArgs {
|
||||
#[command(subcommand)]
|
||||
@@ -215,10 +219,10 @@ async fn cmd_create(
|
||||
async fn cmd_list(repo: String, node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
let (owner, name) = resolve_repo(&repo, &node, dir.as_deref()).await?;
|
||||
|
||||
let client = NodeClient::new(&node, None);
|
||||
let client = signed_client(&node, dir.as_deref());
|
||||
let path = format!("/api/v1/repos/{owner}/{name}/issues");
|
||||
let resp: Value = client
|
||||
.get(&path)
|
||||
.get_authed(&path)
|
||||
.await?
|
||||
.json()
|
||||
.await
|
||||
@@ -254,10 +258,10 @@ async fn cmd_list(repo: String, node: String, dir: Option<PathBuf>) -> Result<()
|
||||
async fn cmd_show(repo: String, id: String, node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
let (owner, name) = resolve_repo(&repo, &node, dir.as_deref()).await?;
|
||||
|
||||
let client = NodeClient::new(&node, None);
|
||||
let client = signed_client(&node, dir.as_deref());
|
||||
let path = format!("/api/v1/repos/{owner}/{name}/issues/{id}");
|
||||
let resp = client
|
||||
.get(&path)
|
||||
.get_authed(&path)
|
||||
.await
|
||||
.context("failed to connect to node")?;
|
||||
let status = resp.status();
|
||||
@@ -347,10 +351,10 @@ async fn cmd_issue_comments(
|
||||
dir: Option<PathBuf>,
|
||||
) -> Result<()> {
|
||||
let (owner, name) = resolve_repo(&repo, &node, dir.as_deref()).await?;
|
||||
let client = NodeClient::new(&node, None);
|
||||
let client = signed_client(&node, dir.as_deref());
|
||||
|
||||
let resp: Value = client
|
||||
.get(&format!(
|
||||
.get_authed(&format!(
|
||||
"/api/v1/repos/{owner}/{name}/issues/{id}/comments"
|
||||
))
|
||||
.await?
|
||||
|
||||
+210
-9
@@ -932,13 +932,33 @@ async fn call_tool(
|
||||
|
||||
"webhook_list" => {
|
||||
let repo = args["repo"].as_str().context("missing 'repo'")?;
|
||||
let owner = resolve_owner(&args, &client).await?;
|
||||
let resp: Value = client
|
||||
.get(&format!("/api/v1/repos/{owner}/{repo}/hooks"))
|
||||
.await?
|
||||
.json()
|
||||
// Owner-gated route: an explicit `owner` arg wins, otherwise default to
|
||||
// the signing keypair's short DID (NOT the node DID). The request is
|
||||
// signed by this keypair, so the path owner must match it or the node
|
||||
// returns 403/404.
|
||||
let owner = if let Some(o) = args.get("owner").and_then(|v| v.as_str()) {
|
||||
o.to_string()
|
||||
} else {
|
||||
let kp = keypair
|
||||
.as_ref()
|
||||
.context("no identity found — run `gl identity new` first")?;
|
||||
let did = kp.did().to_string();
|
||||
did.split(':').next_back().unwrap_or(&did).to_string()
|
||||
};
|
||||
// Owner-gated route: must be signed (get_signed), not a plain get().
|
||||
let resp = client
|
||||
.get_signed(&format!("/api/v1/repos/{owner}/{repo}/hooks"))
|
||||
.await?;
|
||||
Ok(serde_json::to_string_pretty(&resp)?)
|
||||
// Check the HTTP status before deserializing: a 401/403/404 JSON error
|
||||
// body (missing identity, wrong owner, private/deleted repo) must fail
|
||||
// the tool call, not be returned as a successful result.
|
||||
let status = resp.status();
|
||||
let body: Value = resp.json().await?;
|
||||
if !status.is_success() {
|
||||
let msg = body["message"].as_str().unwrap_or("unknown error");
|
||||
anyhow::bail!("webhook_list failed ({status}): {msg}");
|
||||
}
|
||||
Ok(serde_json::to_string_pretty(&body)?)
|
||||
}
|
||||
|
||||
"webhook_delete" => {
|
||||
@@ -970,14 +990,14 @@ async fn call_tool(
|
||||
}
|
||||
u
|
||||
};
|
||||
let resp: Value = client.get(&url).await?.json().await?;
|
||||
let resp: Value = client.get_authed(&url).await?.json().await?;
|
||||
Ok(serde_json::to_string_pretty(&resp)?)
|
||||
}
|
||||
|
||||
"bounty_show" => {
|
||||
let id = args["id"].as_str().context("missing 'id'")?;
|
||||
let resp: Value = client
|
||||
.get(&format!("/api/v1/bounties/{id}"))
|
||||
.get_authed(&format!("/api/v1/bounties/{id}"))
|
||||
.await?
|
||||
.json()
|
||||
.await?;
|
||||
@@ -1165,7 +1185,7 @@ async fn call_tool(
|
||||
(owner, repo.to_string())
|
||||
};
|
||||
let resp: Value = client
|
||||
.get(&format!("/api/v1/repos/{owner}/{name}/issues"))
|
||||
.get_authed(&format!("/api/v1/repos/{owner}/{name}/issues"))
|
||||
.await?
|
||||
.json()
|
||||
.await?;
|
||||
@@ -1825,6 +1845,187 @@ mod tests {
|
||||
assert_eq!(parsed["body"], "looks good");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_webhook_list_via_mcp_signs_the_request() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let dir = tempfile::TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
std::fs::write(
|
||||
dir.path().join("identity.pem"),
|
||||
kp.to_pem().unwrap().as_bytes(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
// /hooks is owner-gated, so the MCP webhook_list tool must send a SIGNED
|
||||
// request (get_signed). Requiring the header catches a regression to get().
|
||||
// Passing `owner` in args makes resolve_owner skip the node-root lookup.
|
||||
let _m = server
|
||||
.mock("GET", mockito::Matcher::Regex(r"/hooks$".to_string()))
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"webhooks":[],"count":0}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let result = call_tool(
|
||||
"webhook_list",
|
||||
json!({"owner": "alice", "repo": "myrepo"}),
|
||||
&server.url(),
|
||||
Some(dir.path()),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(result.contains("webhooks"), "got: {result}");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_webhook_list_default_owner_is_keypair_not_node_did() {
|
||||
// When `owner` is omitted, the owner segment must come from the signing
|
||||
// keypair's short DID, NOT the node root DID. The "/" mock returns a
|
||||
// different DID; the /hooks mock only matches the keypair's short DID,
|
||||
// so a regression to the node DID would leave the request unmatched.
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let dir = tempfile::TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
std::fs::write(
|
||||
dir.path().join("identity.pem"),
|
||||
kp.to_pem().unwrap().as_bytes(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let _root = server
|
||||
.mock("GET", "/")
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"did":"did:key:z6MkNodeRootDid"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let did = kp.did().to_string();
|
||||
let short = did.split(':').next_back().unwrap_or(&did).to_string();
|
||||
|
||||
let _m = server
|
||||
.mock(
|
||||
"GET",
|
||||
mockito::Matcher::Regex(format!(r"/api/v1/repos/{short}/myrepo/hooks$")),
|
||||
)
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"webhooks":[],"count":0}"#)
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let result = call_tool(
|
||||
"webhook_list",
|
||||
json!({"repo": "myrepo"}),
|
||||
&server.url(),
|
||||
Some(dir.path()),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(result.contains("webhooks"), "got: {result}");
|
||||
_m.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_webhook_list_explicit_owner_overrides_keypair() {
|
||||
// An explicit `owner` arg must win over the keypair default and the node
|
||||
// DID. The path must use the supplied owner; "/" must not even be hit.
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let dir = tempfile::TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
std::fs::write(
|
||||
dir.path().join("identity.pem"),
|
||||
kp.to_pem().unwrap().as_bytes(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let _m = server
|
||||
.mock(
|
||||
"GET",
|
||||
mockito::Matcher::Regex(r"/api/v1/repos/someoneelse/myrepo/hooks$".to_string()),
|
||||
)
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"webhooks":[],"count":0}"#)
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let result = call_tool(
|
||||
"webhook_list",
|
||||
json!({"repo": "myrepo", "owner": "someoneelse"}),
|
||||
&server.url(),
|
||||
Some(dir.path()),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(result.contains("webhooks"), "got: {result}");
|
||||
_m.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_webhook_list_non_success_status_errors() {
|
||||
// A 403 (or any non-2xx) JSON error body for a missing identity, wrong
|
||||
// owner, or private/deleted repo must fail the tool call, NOT be returned
|
||||
// as a successful result. Mirrors the `gl webhook list` status check.
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let dir = tempfile::TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
std::fs::write(
|
||||
dir.path().join("identity.pem"),
|
||||
kp.to_pem().unwrap().as_bytes(),
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let _m = server
|
||||
.mock("GET", mockito::Matcher::Regex(r"/hooks$".to_string()))
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.with_status(403)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"message":"only the repo owner can perform this action"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let err = call_tool(
|
||||
"webhook_list",
|
||||
json!({"owner": "alice", "repo": "myrepo"}),
|
||||
&server.url(),
|
||||
Some(dir.path()),
|
||||
)
|
||||
.await
|
||||
.expect_err("non-2xx must error, not return the error body as success");
|
||||
let msg = err.to_string();
|
||||
assert!(msg.contains("webhook_list failed (403"), "got: {msg}");
|
||||
assert!(
|
||||
msg.contains("only the repo owner"),
|
||||
"must surface the node message, got: {msg}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_webhook_list_without_keypair_errors() {
|
||||
// No identity loaded and no explicit owner → the tool must error rather
|
||||
// than fall back to the node DID and issue an unsigned, mis-scoped GET.
|
||||
let server = mockito::Server::new_async().await;
|
||||
let dir = tempfile::TempDir::new().unwrap(); // empty: no identity.pem
|
||||
|
||||
let err = call_tool(
|
||||
"webhook_list",
|
||||
json!({"repo": "myrepo"}),
|
||||
&server.url(),
|
||||
Some(dir.path()),
|
||||
)
|
||||
.await
|
||||
.expect_err("must error without an identity");
|
||||
assert!(err.to_string().contains("no identity found"), "got: {err}");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_tool_count_is_42() {
|
||||
let tools = tool_definitions();
|
||||
|
||||
+379
-12
@@ -2,10 +2,12 @@
|
||||
|
||||
use anyhow::Result;
|
||||
use clap::{Args, Subcommand};
|
||||
use gitlawb_core::identity::Keypair;
|
||||
use serde_json::Value;
|
||||
use std::path::PathBuf;
|
||||
|
||||
use crate::http::NodeClient;
|
||||
use crate::identity::load_keypair_from_dir;
|
||||
use crate::node_stake;
|
||||
|
||||
#[derive(Args)]
|
||||
@@ -20,6 +22,9 @@ pub enum NodeCmd {
|
||||
Status {
|
||||
#[arg(long, default_value = "https://node.gitlawb.com", env = "GITLAWB_NODE")]
|
||||
node: String,
|
||||
/// Identity directory (default: ~/.gitlawb)
|
||||
#[arg(long)]
|
||||
dir: Option<PathBuf>,
|
||||
},
|
||||
/// Check trust score for a DID
|
||||
Trust {
|
||||
@@ -121,7 +126,7 @@ pub enum NodeCmd {
|
||||
|
||||
pub async fn run(args: NodeArgs) -> Result<()> {
|
||||
match args.cmd {
|
||||
NodeCmd::Status { node } => cmd_status(node).await,
|
||||
NodeCmd::Status { node, dir } => cmd_status(node, dir).await,
|
||||
NodeCmd::Trust { did, node } => cmd_trust(did, node).await,
|
||||
NodeCmd::Resolve { did, node } => cmd_resolve(did, node).await,
|
||||
NodeCmd::Register {
|
||||
@@ -177,7 +182,101 @@ async fn try_get_json(client: &NodeClient, path: &str) -> Option<Value> {
|
||||
resp.json::<Value>().await.ok()
|
||||
}
|
||||
|
||||
async fn cmd_status(node: String) -> Result<()> {
|
||||
/// Outcome of fetching the IPFS pins panel for `gl node status`.
|
||||
///
|
||||
/// #134 gates `/api/v1/ipfs/pins` behind auth, so this panel signs its request
|
||||
/// when an identity is available and otherwise reports that the caller must
|
||||
/// sign in. A pins failure never aborts the dashboard.
|
||||
#[derive(Debug)]
|
||||
enum PinsPanel {
|
||||
/// Signed read succeeded and returned pins (carries the resolved count).
|
||||
Pins(u64),
|
||||
/// Signed read succeeded but the node has no pins recorded.
|
||||
Empty,
|
||||
/// Signed read was rejected (401/other) or errored.
|
||||
Unavailable,
|
||||
/// No identity available; no request was issued.
|
||||
NeedsIdentity,
|
||||
/// An explicit `--dir` was given but held no usable identity; carries the dir
|
||||
/// so the panel can name it instead of the misleading "sign in" prompt.
|
||||
IdentityError(PathBuf),
|
||||
}
|
||||
|
||||
/// Identity resolved for the signed pins read, decided before the request so the
|
||||
/// dashboard can distinguish "no identity at all" from "an explicit `--dir` that
|
||||
/// could not be loaded".
|
||||
enum PinsAuth {
|
||||
/// A usable keypair; the read will be signed.
|
||||
Keyed(Keypair),
|
||||
/// No identity requested and none in the default keystore.
|
||||
Anonymous,
|
||||
/// An explicit `--dir` was given but held no usable identity (carries the dir).
|
||||
DirUnusable(PathBuf),
|
||||
}
|
||||
|
||||
/// Resolve the pins-panel identity from an optional `--dir`. Mirrors `gl ipfs
|
||||
/// list`'s identity selection: an explicit `--dir` that fails to load is reported
|
||||
/// as `DirUnusable` (so the panel names the bad path) rather than collapsing to
|
||||
/// the misleading "sign in to view"; a missing default keystore (no `--dir`)
|
||||
/// degrades quietly to `Anonymous`.
|
||||
fn resolve_pins_auth(dir: Option<&std::path::Path>) -> PinsAuth {
|
||||
match load_keypair_from_dir(dir) {
|
||||
Ok(kp) => PinsAuth::Keyed(kp),
|
||||
Err(_) => match dir {
|
||||
Some(d) => PinsAuth::DirUnusable(d.to_path_buf()),
|
||||
None => PinsAuth::Anonymous,
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
/// Fetch the pins panel state. With a keypair, signs the `/api/v1/ipfs/pins`
|
||||
/// read and maps the outcome; with no identity it returns `NeedsIdentity`, and
|
||||
/// with an unusable explicit `--dir` it returns `IdentityError` — both without
|
||||
/// issuing a request. Injectable (node URL + resolved auth) so tests drive it
|
||||
/// with a mock server and never touch the default keystore.
|
||||
async fn fetch_pins(node: &str, auth: PinsAuth) -> PinsPanel {
|
||||
let kp = match auth {
|
||||
PinsAuth::Keyed(kp) => kp,
|
||||
PinsAuth::Anonymous => return PinsPanel::NeedsIdentity,
|
||||
PinsAuth::DirUnusable(dir) => return PinsPanel::IdentityError(dir),
|
||||
};
|
||||
let client = NodeClient::new(node, Some(kp));
|
||||
let resp = match client.get_signed("/api/v1/ipfs/pins").await {
|
||||
Ok(r) => r,
|
||||
Err(_) => return PinsPanel::Unavailable,
|
||||
};
|
||||
if !resp.status().is_success() {
|
||||
return PinsPanel::Unavailable;
|
||||
}
|
||||
let Ok(body) = resp.json::<Value>().await else {
|
||||
return PinsPanel::Unavailable;
|
||||
};
|
||||
let count = body["count"]
|
||||
.as_u64()
|
||||
.unwrap_or_else(|| body["pins"].as_array().map(|a| a.len() as u64).unwrap_or(0));
|
||||
if count == 0 {
|
||||
PinsPanel::Empty
|
||||
} else {
|
||||
PinsPanel::Pins(count)
|
||||
}
|
||||
}
|
||||
|
||||
/// Render the one-line pins-panel status for the `gl node status` dashboard.
|
||||
fn pins_status_line(panel: &PinsPanel) -> String {
|
||||
match panel {
|
||||
PinsPanel::Pins(count) => format!(" Pinned CIDs: {count}"),
|
||||
PinsPanel::Empty => " Pinned CIDs: 0".to_string(),
|
||||
PinsPanel::Unavailable => " IPFS pins: unavailable".to_string(),
|
||||
PinsPanel::NeedsIdentity => {
|
||||
" IPFS pins: sign in to view (run `gl identity new`)".to_string()
|
||||
}
|
||||
PinsPanel::IdentityError(dir) => {
|
||||
format!(" IPFS pins: no usable identity in {}", dir.display())
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async fn cmd_status(node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
let client = NodeClient::new(&node, None);
|
||||
|
||||
// ── Fetch node info (required — bail if unreachable) ──────────────────
|
||||
@@ -194,13 +293,21 @@ async fn cmd_status(node: String) -> Result<()> {
|
||||
let version = info["version"].as_str().unwrap_or("unknown");
|
||||
let network = info["network"].as_str().unwrap_or("unknown");
|
||||
|
||||
// The pins panel signs its read (#134 gates /api/v1/ipfs/pins behind auth).
|
||||
// `--dir` selects the same identity directory as `gl ipfs list` (#146); an
|
||||
// explicit --dir that can't be loaded is surfaced in the panel rather than
|
||||
// masquerading as "no identity", while a missing default keystore degrades
|
||||
// quietly. A pins failure never aborts the dashboard.
|
||||
let pins_auth = resolve_pins_auth(dir.as_deref());
|
||||
|
||||
// ── Fetch remaining endpoints in parallel ─────────────────────────────
|
||||
let (peers_val, repos_val, p2p_val, events_val, pins_val) = tokio::join!(
|
||||
// Peers/repos/p2p/events stay anonymous; only pins is signed.
|
||||
let (peers_val, repos_val, p2p_val, events_val, pins_panel) = tokio::join!(
|
||||
try_get_json(&client, "/api/v1/peers"),
|
||||
try_get_json(&client, "/api/v1/repos"),
|
||||
try_get_json(&client, "/api/v1/p2p/info"),
|
||||
try_get_json(&client, "/api/v1/events/ref-updates?limit=5"),
|
||||
try_get_json(&client, "/api/v1/ipfs/pins"),
|
||||
fetch_pins(&node, pins_auth),
|
||||
);
|
||||
|
||||
// ── Render dashboard ──────────────────────────────────────────────────
|
||||
@@ -307,14 +414,7 @@ async fn cmd_status(node: String) -> Result<()> {
|
||||
|
||||
// Pins
|
||||
println!("Pins");
|
||||
if let Some(ref pins) = pins_val {
|
||||
let count = pins["count"]
|
||||
.as_u64()
|
||||
.unwrap_or_else(|| pins["pins"].as_array().map(|a| a.len() as u64).unwrap_or(0));
|
||||
println!(" Pinned CIDs: {count}");
|
||||
} else {
|
||||
println!(" IPFS not configured");
|
||||
}
|
||||
println!("{}", pins_status_line(&pins_panel));
|
||||
println!();
|
||||
|
||||
Ok(())
|
||||
@@ -409,3 +509,270 @@ async fn cmd_resolve(did: String, node: String) -> Result<()> {
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use gitlawb_core::identity::Keypair;
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_fetch_pins_keyed_happy_signs_and_returns_pins() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let kp = Keypair::generate();
|
||||
|
||||
// A keyed fetch must sign the request (RFC 9421 headers) and, on a
|
||||
// populated 200 body, land in the Pins state carrying the pins.
|
||||
let m = server
|
||||
.mock("GET", "/api/v1/ipfs/pins")
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.match_header("content-digest", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(
|
||||
r#"{"pins":[{"cid":"bafyone","sha256_hex":"abc123","pinned_at":"2026-07-02T12:00:00Z"}],"count":1}"#,
|
||||
)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let panel = fetch_pins(&server.url(), PinsAuth::Keyed(kp)).await;
|
||||
match panel {
|
||||
PinsPanel::Pins(count) => assert_eq!(count, 1),
|
||||
other => panic!("expected Pins, got {other:?}"),
|
||||
}
|
||||
|
||||
m.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_fetch_pins_keyed_empty_returns_empty() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let kp = Keypair::generate();
|
||||
|
||||
let m = server
|
||||
.mock("GET", "/api/v1/ipfs/pins")
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"pins":[],"count":0}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let panel = fetch_pins(&server.url(), PinsAuth::Keyed(kp)).await;
|
||||
assert!(
|
||||
matches!(panel, PinsPanel::Empty),
|
||||
"expected Empty, got {panel:?}"
|
||||
);
|
||||
|
||||
m.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_fetch_pins_keyed_rejected_returns_unavailable() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let kp = Keypair::generate();
|
||||
|
||||
// Node rejects the signed read (401): the panel must degrade to
|
||||
// Unavailable without panicking, so cmd_status still completes.
|
||||
let m = server
|
||||
.mock("GET", "/api/v1/ipfs/pins")
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.with_status(401)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"error":"unauthorized"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let panel = fetch_pins(&server.url(), PinsAuth::Keyed(kp)).await;
|
||||
assert!(
|
||||
matches!(panel, PinsPanel::Unavailable),
|
||||
"expected Unavailable, got {panel:?}"
|
||||
);
|
||||
|
||||
m.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_fetch_pins_unkeyed_needs_identity_without_request() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
|
||||
// With no keypair the endpoint must never be hit.
|
||||
let m = server
|
||||
.mock("GET", "/api/v1/ipfs/pins")
|
||||
.expect(0)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let panel = fetch_pins(&server.url(), PinsAuth::Anonymous).await;
|
||||
assert!(
|
||||
matches!(panel, PinsPanel::NeedsIdentity),
|
||||
"expected NeedsIdentity, got {panel:?}"
|
||||
);
|
||||
|
||||
m.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_fetch_pins_malformed_body_returns_unavailable() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let kp = Keypair::generate();
|
||||
|
||||
// 2xx but the body is not valid JSON: must degrade to Unavailable,
|
||||
// never panic.
|
||||
let m = server
|
||||
.mock("GET", "/api/v1/ipfs/pins")
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body("not json{{{")
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let panel = fetch_pins(&server.url(), PinsAuth::Keyed(kp)).await;
|
||||
assert!(
|
||||
matches!(panel, PinsPanel::Unavailable),
|
||||
"malformed body -> Unavailable, got {panel:?}"
|
||||
);
|
||||
|
||||
m.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_fetch_pins_transport_error_returns_unavailable() {
|
||||
// Bind then drop to obtain a definitely-closed port -> connection
|
||||
// refused -> get_signed Err -> Unavailable (no panic).
|
||||
let port = {
|
||||
let l = std::net::TcpListener::bind("127.0.0.1:0").unwrap();
|
||||
l.local_addr().unwrap().port()
|
||||
};
|
||||
let kp = Keypair::generate();
|
||||
|
||||
let panel = fetch_pins(&format!("http://127.0.0.1:{port}"), PinsAuth::Keyed(kp)).await;
|
||||
assert!(
|
||||
matches!(panel, PinsPanel::Unavailable),
|
||||
"transport error -> Unavailable, got {panel:?}"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_pins_status_line_renders_each_state() {
|
||||
assert_eq!(pins_status_line(&PinsPanel::Pins(3)), " Pinned CIDs: 3");
|
||||
assert_eq!(pins_status_line(&PinsPanel::Empty), " Pinned CIDs: 0");
|
||||
assert_eq!(
|
||||
pins_status_line(&PinsPanel::Unavailable),
|
||||
" IPFS pins: unavailable"
|
||||
);
|
||||
assert_eq!(
|
||||
pins_status_line(&PinsPanel::NeedsIdentity),
|
||||
" IPFS pins: sign in to view (run `gl identity new`)"
|
||||
);
|
||||
assert_eq!(
|
||||
pins_status_line(&PinsPanel::IdentityError(PathBuf::from("/tmp/id"))),
|
||||
" IPFS pins: no usable identity in /tmp/id"
|
||||
);
|
||||
}
|
||||
|
||||
// Adversarial follow-up to jatmn #146 P2: an explicit `--dir` that holds no
|
||||
// usable identity must resolve to DirUnusable (which names the path), NOT the
|
||||
// Anonymous "sign in to view / run `gl identity new`" case — otherwise a user
|
||||
// who did supply an identity dir is misdirected to create one they may have.
|
||||
#[test]
|
||||
fn resolve_pins_auth_reports_explicit_bad_dir_as_unusable() {
|
||||
let bad = PathBuf::from("/nonexistent/gl-id-xyz");
|
||||
match resolve_pins_auth(Some(&bad)) {
|
||||
PinsAuth::DirUnusable(d) => assert_eq!(d, bad),
|
||||
_ => panic!("explicit unusable --dir must be DirUnusable, not Anonymous"),
|
||||
}
|
||||
}
|
||||
|
||||
// Mirror of the above for the absent-`--dir` case: `None` must never resolve to
|
||||
// DirUnusable — it degrades to Anonymous (no default keystore) or Keyed (one
|
||||
// present). Env-independent: only the None->DirUnusable mapping is guarded, so it
|
||||
// holds whether or not the runner has a default `~/.gitlawb` identity.
|
||||
#[test]
|
||||
fn resolve_pins_auth_none_is_never_dir_unusable() {
|
||||
assert!(
|
||||
!matches!(resolve_pins_auth(None), PinsAuth::DirUnusable(_)),
|
||||
"absent --dir must degrade to Anonymous (or Keyed), never DirUnusable"
|
||||
);
|
||||
}
|
||||
|
||||
// The success wiring for #146: an explicit --dir with a valid identity must
|
||||
// load that key (dir -> load_keypair_from_dir -> Keyed), so the pins read is
|
||||
// signed with the selected identity rather than the default keystore.
|
||||
#[test]
|
||||
fn resolve_pins_auth_loads_keyed_identity_from_explicit_dir() {
|
||||
let dir = tempfile::TempDir::new().unwrap();
|
||||
let kp = Keypair::generate();
|
||||
std::fs::write(
|
||||
dir.path().join("identity.pem"),
|
||||
kp.to_pem().unwrap().as_bytes(),
|
||||
)
|
||||
.unwrap();
|
||||
let PinsAuth::Keyed(loaded) = resolve_pins_auth(Some(dir.path())) else {
|
||||
panic!("an explicit --dir with a valid identity must resolve to Keyed");
|
||||
};
|
||||
// A bare `Keyed(_)` match would also pass if load fell through to the default
|
||||
// keystore; assert the loaded identity is the one written to --dir so the pins
|
||||
// read signs with the selected key, never the default.
|
||||
assert_eq!(
|
||||
loaded.did(),
|
||||
kp.did(),
|
||||
"must sign with the identity from --dir, not the default keystore"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_fetch_pins_dir_unusable_reports_identity_error_without_request() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
// An unusable explicit --dir must render the identity error and never hit
|
||||
// the endpoint (no identity to sign with).
|
||||
let m = server
|
||||
.mock("GET", "/api/v1/ipfs/pins")
|
||||
.expect(0)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let bad = PathBuf::from("/nonexistent/gl-id-xyz");
|
||||
let panel = fetch_pins(&server.url(), PinsAuth::DirUnusable(bad.clone())).await;
|
||||
match panel {
|
||||
PinsPanel::IdentityError(d) => assert_eq!(d, bad),
|
||||
other => panic!("expected IdentityError, got {other:?}"),
|
||||
}
|
||||
|
||||
m.assert_async().await;
|
||||
}
|
||||
|
||||
// jatmn #146 P2: `gl node status` must accept the same `--dir` identity
|
||||
// selector as `gl ipfs list`, so a user who selected an identity via --dir can
|
||||
// authenticate the status pins panel instead of seeing "sign in to view".
|
||||
#[test]
|
||||
fn status_accepts_dir_identity_selector() {
|
||||
use clap::Parser;
|
||||
#[derive(Parser)]
|
||||
struct TestCli {
|
||||
#[command(flatten)]
|
||||
args: NodeArgs,
|
||||
}
|
||||
let cli = TestCli::try_parse_from([
|
||||
"gl",
|
||||
"status",
|
||||
"--node",
|
||||
"http://example",
|
||||
"--dir",
|
||||
"/tmp/id",
|
||||
])
|
||||
.expect("`node status` must accept --dir");
|
||||
let NodeCmd::Status { dir, .. } = cli.args.cmd else {
|
||||
panic!("expected the Status subcommand");
|
||||
};
|
||||
assert_eq!(dir, Some(PathBuf::from("/tmp/id")));
|
||||
|
||||
// Absent --dir must stay None so the default keystore path is unchanged.
|
||||
let cli = TestCli::try_parse_from(["gl", "status"]).expect("status parses without --dir");
|
||||
let NodeCmd::Status { dir, .. } = cli.args.cmd else {
|
||||
panic!("expected the Status subcommand");
|
||||
};
|
||||
assert_eq!(dir, None);
|
||||
}
|
||||
}
|
||||
@@ -154,10 +154,12 @@ async fn cmd_remove(
|
||||
|
||||
async fn cmd_list(repo: String, node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
let (owner, name) = resolve_owner_repo(&repo, &node, dir.as_deref()).await?;
|
||||
let client = NodeClient::new(&node, None);
|
||||
// Read-visibility-gated on the node: public repos list anonymously, private
|
||||
// repos need the owner's signature. Sign when an identity is available.
|
||||
let client = NodeClient::new(&node, load_keypair_from_dir(dir.as_deref()).ok());
|
||||
|
||||
let resp = client
|
||||
.get(&format!("/api/v1/repos/{owner}/{name}/branches/protected"))
|
||||
.get_maybe_signed(&format!("/api/v1/repos/{owner}/{name}/branches/protected"))
|
||||
.await
|
||||
.context("failed to connect to node")?;
|
||||
|
||||
@@ -307,6 +309,9 @@ mod tests {
|
||||
"GET",
|
||||
mockito::Matcher::Regex(r"branches/protected".to_string()),
|
||||
)
|
||||
// An identity is supplied, so get_maybe_signed must sign the request.
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"protected_branches":[],"count":0}"#)
|
||||
@@ -338,6 +343,8 @@ mod tests {
|
||||
"GET",
|
||||
mockito::Matcher::Regex(r"branches/protected".to_string()),
|
||||
)
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"protected_branches":["main","release"],"count":2}"#)
|
||||
|
||||
+471
-63
@@ -146,6 +146,8 @@ pub enum RepoCmd {
|
||||
repo: String,
|
||||
#[arg(long, default_value = "https://node.gitlawb.com", env = "GITLAWB_NODE")]
|
||||
node: String,
|
||||
#[arg(long)]
|
||||
dir: Option<PathBuf>,
|
||||
},
|
||||
}
|
||||
|
||||
@@ -203,25 +205,21 @@ pub async fn run(args: RepoArgs) -> Result<()> {
|
||||
RepoCmd::ReplicaUnregister { repo, node, dir } => {
|
||||
cmd_replica_unregister(repo, node, dir).await
|
||||
}
|
||||
RepoCmd::Replicas { repo, node } => cmd_replicas(repo, node).await,
|
||||
RepoCmd::Replicas { repo, node, dir } => cmd_replicas(repo, node, dir).await,
|
||||
}
|
||||
}
|
||||
|
||||
/// Derive the short DID key segment from a keypair, or fall back to the node's DID.
|
||||
async fn resolve_owner_did(node: &str, dir: Option<&std::path::Path>) -> Result<String> {
|
||||
if let Ok(kp) = load_keypair_from_dir(dir) {
|
||||
let did = kp.did().to_string();
|
||||
return Ok(did.split(':').next_back().unwrap_or(&did).to_string());
|
||||
}
|
||||
let client = NodeClient::new(node, None);
|
||||
let info: Value = client
|
||||
.get("/")
|
||||
.await?
|
||||
.json()
|
||||
.await
|
||||
.context("failed to fetch node info")?;
|
||||
let did = info["did"].as_str().context("node missing DID")?;
|
||||
Ok(did.split(':').next_back().unwrap_or(did).to_string())
|
||||
/// Resolve the owner short-DID for a bare repo name from the LOCAL identity.
|
||||
/// Never falls back to the node's own DID (that produced bogus "owned by the
|
||||
/// node" results for repos that don't exist) — if there's no local identity the
|
||||
/// caller must pass an explicit `owner/name`.
|
||||
async fn resolve_owner_did(_node: &str, dir: Option<&std::path::Path>) -> Result<String> {
|
||||
let kp = load_keypair_from_dir(dir).context(
|
||||
"no local identity to resolve the repo owner — pass `owner/name`, or run `gl identity new`",
|
||||
)?;
|
||||
let did = kp.did().to_string();
|
||||
Ok(did.split(':').next_back().unwrap_or(&did).to_string())
|
||||
}
|
||||
|
||||
async fn cmd_create(
|
||||
@@ -306,31 +304,37 @@ async fn cmd_list(node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
}
|
||||
|
||||
async fn cmd_clone(name: String, node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
let did = if let Ok(kp) = load_keypair_from_dir(dir.as_deref()) {
|
||||
kp.did().to_string()
|
||||
// Owner is taken from an explicit `owner/name`, else the LOCAL identity —
|
||||
// never the node's own DID. A missing repo then surfaces as the helper's
|
||||
// clear 404 rather than a clone under an invented owner.
|
||||
let (did, repo_name) = if let Some((owner, rest)) = name.split_once('/') {
|
||||
(owner.to_string(), rest.to_string())
|
||||
} else {
|
||||
let client = NodeClient::new(&node, None);
|
||||
let info: Value = client.get("/").await?.json().await?;
|
||||
info["did"]
|
||||
.as_str()
|
||||
.context("node missing DID")?
|
||||
.to_string()
|
||||
// Bare name: derive the SHORT owner key via the same helper the other
|
||||
// commands use, so the URL is `gitlawb://z6Mk.../name` — not the full
|
||||
// `did:key:z6Mk...` form, whose colons in the authority break the helper.
|
||||
(resolve_owner_did(&node, dir.as_deref()).await?, name)
|
||||
};
|
||||
let url = format!("gitlawb://{did}/{name}");
|
||||
let url = format!("gitlawb://{did}/{repo_name}");
|
||||
println!(" cloning {url}");
|
||||
let status = std::process::Command::new("git")
|
||||
.arg("clone")
|
||||
.arg(&url)
|
||||
// Point the remote helper at the same node the user selected.
|
||||
.env("GITLAWB_NODE", &node)
|
||||
.status()
|
||||
.context("failed to run git clone — is git installed?")?;
|
||||
if !status.success() {
|
||||
anyhow::bail!("git clone failed");
|
||||
anyhow::bail!("git clone failed — does the repo exist on this node?");
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn cmd_info(repo: String, node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
let client = NodeClient::new(&node, None);
|
||||
// Sign when an identity is available so the read-visibility-gated replica
|
||||
// sub-fetch below resolves for a private repo's owner (public repos still
|
||||
// work anonymously).
|
||||
let client = NodeClient::new(&node, load_keypair_from_dir(dir.as_deref()).ok());
|
||||
|
||||
let (owner, name) = if repo.contains('/') {
|
||||
let (o, n) = repo.split_once('/').unwrap();
|
||||
@@ -340,12 +344,27 @@ async fn cmd_info(repo: String, node: String, dir: Option<PathBuf>) -> Result<()
|
||||
(short, repo)
|
||||
};
|
||||
|
||||
let r: Value = client
|
||||
.get(&format!("/api/v1/repos/{owner}/{name}"))
|
||||
.await?
|
||||
.json()
|
||||
let resp = client
|
||||
.get_maybe_signed(&format!("/api/v1/repos/{owner}/{name}"))
|
||||
.await
|
||||
.context("repo not found")?;
|
||||
.context("failed to connect to node")?;
|
||||
// A non-existent (or unreadable/quarantined) repo is a real 404 from the
|
||||
// node — surface it plainly instead of printing a stub card with `?` fields
|
||||
// and a placeholder owner DID.
|
||||
if !resp.status().is_success() {
|
||||
if resp.status().as_u16() == 404 {
|
||||
anyhow::bail!("repository '{owner}/{name}' not found");
|
||||
}
|
||||
let status = resp.status();
|
||||
let msg = resp
|
||||
.json::<Value>()
|
||||
.await
|
||||
.ok()
|
||||
.and_then(|v| v["message"].as_str().map(String::from))
|
||||
.unwrap_or_else(|| "request failed".to_string());
|
||||
anyhow::bail!("repo info failed ({status}): {msg}");
|
||||
}
|
||||
let r: Value = resp.json().await.context("parse repo info")?;
|
||||
|
||||
let owner_did = r["owner_did"].as_str().unwrap_or(&owner);
|
||||
let gitlawb_url = format!("gitlawb://{owner_did}/{name}");
|
||||
@@ -368,7 +387,7 @@ async fn cmd_info(repo: String, node: String, dir: Option<PathBuf>) -> Result<()
|
||||
|
||||
// Replica count — failure to fetch is non-fatal (older nodes don't expose this).
|
||||
if let Ok(resp) = client
|
||||
.get(&format!("/api/v1/repos/{owner}/{name}/replicas"))
|
||||
.get_maybe_signed(&format!("/api/v1/repos/{owner}/{name}/replicas"))
|
||||
.await
|
||||
{
|
||||
if resp.status().is_success() {
|
||||
@@ -448,15 +467,17 @@ async fn cmd_replica_unregister(repo: String, node: String, dir: Option<PathBuf>
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn cmd_replicas(repo: String, node: String) -> Result<()> {
|
||||
async fn cmd_replicas(repo: String, node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
let (owner, name) = repo
|
||||
.split_once('/')
|
||||
.map(|(o, n)| (o.to_string(), n.to_string()))
|
||||
.context("use owner/repo format")?;
|
||||
|
||||
let client = NodeClient::new(&node, None);
|
||||
// Read-visibility-gated: public repos list anonymously, private repos need
|
||||
// the owner's signature. Sign when an identity is available.
|
||||
let client = NodeClient::new(&node, load_keypair_from_dir(dir.as_deref()).ok());
|
||||
let resp = client
|
||||
.get(&format!("/api/v1/repos/{owner}/{name}/replicas"))
|
||||
.get_maybe_signed(&format!("/api/v1/repos/{owner}/{name}/replicas"))
|
||||
.await
|
||||
.context("failed to connect to node")?;
|
||||
let status = resp.status();
|
||||
@@ -574,7 +595,7 @@ async fn cmd_fork(
|
||||
}
|
||||
|
||||
/// Returns (owner, repo_name) — if repo contains '/', splits on it; otherwise uses caller's DID.
|
||||
async fn resolve_owner_repo_pair(
|
||||
pub(crate) async fn resolve_owner_repo_pair(
|
||||
repo: &str,
|
||||
node: &str,
|
||||
dir: Option<&std::path::Path>,
|
||||
@@ -647,16 +668,23 @@ async fn cmd_label_remove(
|
||||
|
||||
async fn cmd_label_list(repo: String, node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
let (owner, name) = resolve_owner_repo_pair(&repo, &node, dir.as_deref()).await?;
|
||||
let client = NodeClient::new(&node, None);
|
||||
// Read-visibility-gated like the sibling read surfaces (replicas, protected
|
||||
// branches): sign when an identity is available so a private-repo owner can
|
||||
// read their own labels, while public repos stay anonymously listable.
|
||||
let client = NodeClient::new(&node, load_keypair_from_dir(dir.as_deref()).ok());
|
||||
|
||||
let resp: Value = client
|
||||
.get(&format!("/api/v1/repos/{owner}/{name}/labels"))
|
||||
.await?
|
||||
.json()
|
||||
let resp = client
|
||||
.get_maybe_signed(&format!("/api/v1/repos/{owner}/{name}/labels"))
|
||||
.await
|
||||
.context("invalid JSON")?;
|
||||
.context("failed to connect to node")?;
|
||||
let status = resp.status();
|
||||
let body: Value = resp.json().await.unwrap_or_default();
|
||||
if !status.is_success() {
|
||||
let msg = body["message"].as_str().unwrap_or("unknown error");
|
||||
anyhow::bail!("list labels failed ({status}): {msg}");
|
||||
}
|
||||
|
||||
let labels = resp["labels"].as_array().cloned().unwrap_or_default();
|
||||
let labels = body["labels"].as_array().cloned().unwrap_or_default();
|
||||
if labels.is_empty() {
|
||||
println!("No labels on {owner}/{name}");
|
||||
} else {
|
||||
@@ -668,17 +696,39 @@ async fn cmd_label_list(repo: String, node: String, dir: Option<PathBuf>) -> Res
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Parse the protected-branch list from the node's `GET /branches/protected`
|
||||
/// response. The endpoint returns `{"protected_branches": [...], "count": N}`
|
||||
/// (see `crates/gitlawb-node/src/api/protect.rs`); each entry may be a plain
|
||||
/// branch-name string or an object carrying a `name` field.
|
||||
fn parse_protected_branches(val: &Value) -> Vec<String> {
|
||||
val["protected_branches"]
|
||||
.as_array()
|
||||
.map(|arr| {
|
||||
arr.iter()
|
||||
.filter_map(|b| {
|
||||
b.as_str()
|
||||
.map(String::from)
|
||||
.or_else(|| b["name"].as_str().map(String::from))
|
||||
})
|
||||
.collect()
|
||||
})
|
||||
.unwrap_or_default()
|
||||
}
|
||||
|
||||
async fn cmd_owner(repo: String, node: String, dir: Option<PathBuf>, json_out: bool) -> Result<()> {
|
||||
let keypair = load_keypair_from_dir(dir.as_deref())?;
|
||||
let my_did = keypair.did().to_string();
|
||||
let my_short = my_did.split(':').next_back().unwrap_or(&my_did).to_string();
|
||||
|
||||
let (owner, name) = resolve_owner_repo_pair(&repo, &node, dir.as_deref()).await?;
|
||||
let client = NodeClient::new(&node, None);
|
||||
// Sign with the loaded identity so the read-visibility-gated protected-branch
|
||||
// fetch below works on the owner's own private repos.
|
||||
let client = NodeClient::new(&node, Some(keypair));
|
||||
|
||||
// Fetch repo info
|
||||
// Fetch repo info (get_repo is read-visibility-gated; sign so the owner can
|
||||
// inspect their own private repo).
|
||||
let resp = client
|
||||
.get(&format!("/api/v1/repos/{owner}/{name}"))
|
||||
.get_maybe_signed(&format!("/api/v1/repos/{owner}/{name}"))
|
||||
.await
|
||||
.context("failed to connect to node")?;
|
||||
if !resp.status().is_success() {
|
||||
@@ -693,25 +743,14 @@ async fn cmd_owner(repo: String, node: String, dir: Option<PathBuf>, json_out: b
|
||||
.to_string();
|
||||
let is_owner = my_did == owner_did || my_short == owner_short;
|
||||
|
||||
// Fetch protected branches
|
||||
// Fetch protected branches (read-visibility-gated; signed via the client).
|
||||
let protected: Vec<String> = match client
|
||||
.get(&format!("/api/v1/repos/{owner}/{name}/branches/protected"))
|
||||
.get_maybe_signed(&format!("/api/v1/repos/{owner}/{name}/branches/protected"))
|
||||
.await
|
||||
{
|
||||
Ok(resp) if resp.status().is_success() => {
|
||||
let val: Value = resp.json().await.unwrap_or_default();
|
||||
val.as_array()
|
||||
.or_else(|| val["branches"].as_array())
|
||||
.map(|arr| {
|
||||
arr.iter()
|
||||
.filter_map(|b| {
|
||||
b.as_str()
|
||||
.map(String::from)
|
||||
.or_else(|| b["name"].as_str().map(String::from))
|
||||
})
|
||||
.collect()
|
||||
})
|
||||
.unwrap_or_default()
|
||||
parse_protected_branches(&val)
|
||||
}
|
||||
_ => Vec::new(),
|
||||
};
|
||||
@@ -749,6 +788,20 @@ mod tests {
|
||||
use super::*;
|
||||
use tempfile::TempDir;
|
||||
|
||||
#[test]
|
||||
fn parse_protected_branches_reads_node_shape() {
|
||||
use serde_json::json;
|
||||
assert_eq!(
|
||||
parse_protected_branches(&json!({"protected_branches":["main","release"],"count":2})),
|
||||
vec!["main".to_string(), "release".to_string()]
|
||||
);
|
||||
assert!(parse_protected_branches(&json!({"count":0})).is_empty());
|
||||
assert_eq!(
|
||||
parse_protected_branches(&json!({"protected_branches":[{"name":"main"}]})),
|
||||
vec!["main".to_string()]
|
||||
);
|
||||
}
|
||||
|
||||
fn write_identity(dir: &TempDir) {
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let pem = kp.to_pem().unwrap();
|
||||
@@ -1086,6 +1139,10 @@ mod tests {
|
||||
"GET",
|
||||
mockito::Matcher::Regex(r"^/api/v1/repos/[^/]+/myrepo/labels$".to_string()),
|
||||
)
|
||||
// Identity is loaded, so get_maybe_signed must sign — requiring the
|
||||
// header guards against a regression back to bare get().
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"labels":[]}"#)
|
||||
@@ -1112,6 +1169,10 @@ mod tests {
|
||||
"GET",
|
||||
mockito::Matcher::Regex(r"^/api/v1/repos/[^/]+/myrepo/labels$".to_string()),
|
||||
)
|
||||
// Identity is loaded, so get_maybe_signed must sign — requiring the
|
||||
// header guards against a regression back to bare get().
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"labels":["language:rust","topic:defi"]}"#)
|
||||
@@ -1127,6 +1188,97 @@ mod tests {
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_cmd_label_list_anonymous_when_no_identity() {
|
||||
// Empty dir → no identity → get_maybe_signed must fall back to an
|
||||
// anonymous GET (the public-repo path). Assert NO signature header.
|
||||
let dir = TempDir::new().unwrap();
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock("GET", mockito::Matcher::Regex(r"/labels$".to_string()))
|
||||
.match_header("signature", mockito::Matcher::Missing)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"labels":[]}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
cmd_label_list(
|
||||
"owner/pubrepo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_cmd_label_list_404_errors() {
|
||||
// A non-reader of a private repo gets 404 from the now-gated endpoint.
|
||||
// The client must surface that as an error, not print "No labels" and
|
||||
// exit 0 (the error body has no `labels` key).
|
||||
let dir = TempDir::new().unwrap();
|
||||
write_identity(&dir);
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock(
|
||||
"GET",
|
||||
mockito::Matcher::Regex(r"^/api/v1/repos/[^/]+/myrepo/labels$".to_string()),
|
||||
)
|
||||
.with_status(404)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"message":"repo not found"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let err = cmd_label_list(
|
||||
"myrepo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(
|
||||
err.to_string().contains("list labels failed (404")
|
||||
&& err.to_string().contains("repo not found"),
|
||||
"got: {err}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_cmd_label_list_non_json_error_surfaces_status() {
|
||||
// A non-2xx response with a non-JSON body (e.g. a proxy 502) must still
|
||||
// surface the HTTP status, not collapse to a bare JSON-parse error.
|
||||
let dir = TempDir::new().unwrap();
|
||||
write_identity(&dir);
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock(
|
||||
"GET",
|
||||
mockito::Matcher::Regex(r"^/api/v1/repos/[^/]+/myrepo/labels$".to_string()),
|
||||
)
|
||||
.with_status(502)
|
||||
.with_header("content-type", "text/html")
|
||||
.with_body("<html>502 Bad Gateway</html>")
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let err = cmd_label_list(
|
||||
"myrepo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(
|
||||
err.to_string().contains("list labels failed (502"),
|
||||
"got: {err}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_cmd_owner_is_owner() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
@@ -1137,11 +1289,15 @@ mod tests {
|
||||
let short = did.split(':').next_back().unwrap().to_string();
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
// Both fetches are read-visibility-gated; with an identity loaded they
|
||||
// must be signed. Requiring the header guards a regression to get().
|
||||
let _repo = server
|
||||
.mock(
|
||||
"GET",
|
||||
mockito::Matcher::Regex(format!(r"^/api/v1/repos/{short}/myrepo$")),
|
||||
)
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(format!(
|
||||
@@ -1156,9 +1312,11 @@ mod tests {
|
||||
r"^/api/v1/repos/{short}/myrepo/branches/protected$"
|
||||
)),
|
||||
)
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"["main"]"#)
|
||||
.with_body(r#"{"protected_branches":["main"],"count":1}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
@@ -1199,7 +1357,7 @@ mod tests {
|
||||
)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"["main","release"]"#)
|
||||
.with_body(r#"{"protected_branches":["main","release"],"count":2}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
@@ -1240,7 +1398,7 @@ mod tests {
|
||||
)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"["main"]"#)
|
||||
.with_body(r#"{"protected_branches":["main"],"count":1}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
@@ -1281,4 +1439,254 @@ mod tests {
|
||||
.unwrap_err();
|
||||
assert!(err.to_string().contains("not found"), "got: {err}");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_cmd_replicas_signs_when_identity_present() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
write_identity(&dir);
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
// Read-visibility-gated: with an identity the request must be signed.
|
||||
let _m = server
|
||||
.mock("GET", mockito::Matcher::Regex(r"/replicas$".to_string()))
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"repo":"owner/myrepo","replica_count":0,"replicas":[]}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
cmd_replicas(
|
||||
"owner/myrepo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_cmd_replicas_anonymous_when_no_identity() {
|
||||
// Empty dir → no identity → get_maybe_signed must fall back to an
|
||||
// anonymous GET (the public-repo path). Assert NO signature header.
|
||||
let dir = TempDir::new().unwrap();
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock("GET", mockito::Matcher::Regex(r"/replicas$".to_string()))
|
||||
.match_header("signature", mockito::Matcher::Missing)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"repo":"owner/pubrepo","replica_count":0,"replicas":[]}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
cmd_replicas(
|
||||
"owner/pubrepo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_cmd_info_signs_repo_and_replica_fetches() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
write_identity(&dir);
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
// Both the primary repo fetch and the replica sub-fetch are
|
||||
// read-visibility-gated; with an identity loaded both must be signed.
|
||||
let _repo = server
|
||||
.mock(
|
||||
"GET",
|
||||
mockito::Matcher::Regex(r"^/api/v1/repos/owner/myrepo$".to_string()),
|
||||
)
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(
|
||||
r#"{"id":"r1","name":"myrepo","owner_did":"did:key:zOwner","is_public":false,"default_branch":"main"}"#,
|
||||
)
|
||||
.create_async()
|
||||
.await;
|
||||
let _replicas = server
|
||||
.mock("GET", mockito::Matcher::Regex(r"/replicas$".to_string()))
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"replica_count":0,"replicas":[]}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
cmd_info(
|
||||
"owner/myrepo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_cmd_info_404_surfaces_error_not_fake_repo() {
|
||||
// A non-reader of a private repo gets a JSON 404 from the now-gated
|
||||
// GET /api/v1/repos/{owner}/{name}. The command must surface that as an
|
||||
// error, not parse the error body and print a fabricated repo summary
|
||||
// (owner / "?" / public=true / main) before exiting 0.
|
||||
let dir = TempDir::new().unwrap();
|
||||
write_identity(&dir);
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _repo = server
|
||||
.mock(
|
||||
"GET",
|
||||
mockito::Matcher::Regex(r"^/api/v1/repos/owner/myrepo$".to_string()),
|
||||
)
|
||||
.with_status(404)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"message":"repo not found"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let err = cmd_info(
|
||||
"owner/myrepo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
// The merged cmd_info maps a 404 to a generic "not found" (it does not
|
||||
// echo the server's message body on 404), which still surfaces the error
|
||||
// rather than fabricating a repo card, and avoids leaking any
|
||||
// server-provided detail on a private-repo denial.
|
||||
assert!(
|
||||
err.to_string()
|
||||
.contains("repository 'owner/myrepo' not found"),
|
||||
"got: {err}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_cmd_info_non_json_error_surfaces_status() {
|
||||
// A non-2xx response with a non-JSON body (e.g. a proxy 502) must still
|
||||
// surface the HTTP status, not collapse to a bare JSON-parse error.
|
||||
let dir = TempDir::new().unwrap();
|
||||
write_identity(&dir);
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _repo = server
|
||||
.mock(
|
||||
"GET",
|
||||
mockito::Matcher::Regex(r"^/api/v1/repos/owner/myrepo$".to_string()),
|
||||
)
|
||||
.with_status(502)
|
||||
.with_header("content-type", "text/html")
|
||||
.with_body("<html>502 Bad Gateway</html>")
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let err = cmd_info(
|
||||
"owner/myrepo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(
|
||||
err.to_string().contains("repo info failed (502"),
|
||||
"got: {err}"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
// Drives the three deny/negative arms that the merge reconciliation changed but
|
||||
// that no existing test executed (they were only reasoned): resolve_owner_did
|
||||
// with no identity, cmd_info on an authenticated-but-denied 403, and
|
||||
// get_maybe_signed with no keypair. Each asserts the must-not case.
|
||||
#[cfg(test)]
|
||||
mod vet_merge_deny_arms {
|
||||
use super::*;
|
||||
use tempfile::TempDir;
|
||||
|
||||
fn write_identity(dir: &TempDir) {
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let pem = kp.to_pem().unwrap();
|
||||
std::fs::write(dir.path().join("identity.pem"), pem.as_bytes()).unwrap();
|
||||
}
|
||||
|
||||
// No local identity must hard-error, never fall back to the node's own DID.
|
||||
// (Load-bearing: #113's pre-merge resolve_owner_did returned Ok via a node
|
||||
// fetch here; a reintroduced fallback makes this go red.)
|
||||
#[tokio::test]
|
||||
async fn resolve_owner_did_no_identity_errors_not_fallback() {
|
||||
let empty = TempDir::new().unwrap(); // no identity.pem written
|
||||
let err = resolve_owner_did("http://unused.invalid", Some(empty.path()))
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(
|
||||
err.to_string()
|
||||
.contains("no local identity to resolve the repo owner"),
|
||||
"got: {err}"
|
||||
);
|
||||
}
|
||||
|
||||
// An authenticated caller DENIED with a 403 must surface an error, never
|
||||
// render a repo card (deny-as-success is the INV-8 client-contract break).
|
||||
#[tokio::test]
|
||||
async fn cmd_info_403_denied_surfaces_error_not_card() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
write_identity(&dir);
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock(
|
||||
"GET",
|
||||
mockito::Matcher::Regex(r"^/api/v1/repos/owner/myrepo$".to_string()),
|
||||
)
|
||||
.with_status(403)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"message":"forbidden"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
let err = cmd_info(
|
||||
"owner/myrepo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(
|
||||
err.to_string().contains("repo info failed (403"),
|
||||
"got: {err}"
|
||||
);
|
||||
}
|
||||
|
||||
// No keypair must send an unsigned GET; the mock only matches when the
|
||||
// Signature header is absent, so a wrongly-signed request fails to match.
|
||||
#[tokio::test]
|
||||
async fn get_maybe_signed_no_keypair_sends_unsigned() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock("GET", "/api/v1/repos/owner/pub")
|
||||
.match_header("signature", mockito::Matcher::Missing)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body("{}")
|
||||
.create_async()
|
||||
.await;
|
||||
let client = NodeClient::new(server.url(), None);
|
||||
let resp = client
|
||||
.get_maybe_signed("/api/v1/repos/owner/pub")
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(
|
||||
resp.status().is_success(),
|
||||
"unsigned GET should match the Missing-signature mock; got {}",
|
||||
resp.status()
|
||||
);
|
||||
}
|
||||
}
|
||||
+15
-9
@@ -34,12 +34,14 @@ pub enum StarCmd {
|
||||
#[arg(long)]
|
||||
dir: Option<PathBuf>,
|
||||
},
|
||||
/// Show star count for a repository (no auth required)
|
||||
/// Show star count for a repository
|
||||
Count {
|
||||
/// Repository in owner/repo format
|
||||
repo: String,
|
||||
#[arg(long, default_value = "https://node.gitlawb.com", env = "GITLAWB_NODE")]
|
||||
node: String,
|
||||
#[arg(long)]
|
||||
dir: Option<PathBuf>,
|
||||
},
|
||||
}
|
||||
|
||||
@@ -47,7 +49,7 @@ pub async fn run(args: StarArgs) -> Result<()> {
|
||||
match args.cmd {
|
||||
StarCmd::Add { repo, node, dir } => cmd_add(repo, node, dir).await,
|
||||
StarCmd::Remove { repo, node, dir } => cmd_remove(repo, node, dir).await,
|
||||
StarCmd::Count { repo, node } => cmd_count(repo, node).await,
|
||||
StarCmd::Count { repo, node, dir } => cmd_count(repo, node, dir).await,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -110,15 +112,15 @@ async fn cmd_remove(repo: String, node: String, dir: Option<PathBuf>) -> Result<
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn cmd_count(repo: String, node: String) -> Result<()> {
|
||||
async fn cmd_count(repo: String, node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
let (owner, name) = repo
|
||||
.split_once('/')
|
||||
.map(|(o, n)| (o.to_string(), n.to_string()))
|
||||
.context("use owner/repo format for count (e.g. alice/myrepo)")?;
|
||||
let client = NodeClient::new(&node, None);
|
||||
let client = NodeClient::new(&node, load_keypair_from_dir(dir.as_deref()).ok());
|
||||
|
||||
let resp = client
|
||||
.get(&format!("/api/v1/repos/{owner}/{name}/star"))
|
||||
.get_authed(&format!("/api/v1/repos/{owner}/{name}/star"))
|
||||
.await
|
||||
.context("failed to connect to node")?;
|
||||
|
||||
@@ -310,16 +312,20 @@ mod tests {
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
cmd_count("alice/myrepo".to_string(), server.url())
|
||||
cmd_count("alice/myrepo".to_string(), server.url(), None)
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_cmd_count_requires_slash() {
|
||||
let err = cmd_count("noslash".to_string(), "http://127.0.0.1:1".to_string())
|
||||
.await
|
||||
.unwrap_err();
|
||||
let err = cmd_count(
|
||||
"noslash".to_string(),
|
||||
"http://127.0.0.1:1".to_string(),
|
||||
None,
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(err.to_string().contains("owner/repo format"));
|
||||
}
|
||||
|
||||
|
||||
+52
-13
@@ -59,7 +59,7 @@ pub async fn run(args: StatusArgs) -> Result<()> {
|
||||
println!(" repo {short_did}/{repo}");
|
||||
}
|
||||
None => {
|
||||
println!(" repo (not in a gitlawb repo — no gitlawb:// origin)");
|
||||
println!(" repo (not in a gitlawb repo — no gitlawb:// remote)");
|
||||
}
|
||||
}
|
||||
|
||||
@@ -143,29 +143,68 @@ fn trust_bar(score: f64) -> String {
|
||||
format!("{}{}", "█".repeat(filled), "░".repeat(empty))
|
||||
}
|
||||
|
||||
/// Parse `gitlawb://<did>/<repo>` from the git origin remote.
|
||||
/// Find a `gitlawb://<did>/<repo>` remote in the current repo.
|
||||
///
|
||||
/// Checks `origin` first (clones), then `gitlawb` (the name `gl init` adds),
|
||||
/// then any other remote with a gitlawb:// URL.
|
||||
fn detect_gitlawb_remote() -> Option<(String, String)> {
|
||||
let out = std::process::Command::new("git")
|
||||
.args(["remote", "get-url", "origin"])
|
||||
.args(["remote"])
|
||||
.stderr(std::process::Stdio::null())
|
||||
.output()
|
||||
.ok()?;
|
||||
if !out.status.success() {
|
||||
return None;
|
||||
}
|
||||
let url = String::from_utf8(out.stdout).ok()?;
|
||||
let rest = url.trim().strip_prefix("gitlawb://")?;
|
||||
let slash = rest.rfind('/')?;
|
||||
let did = rest[..slash].to_string();
|
||||
let repo = rest[slash + 1..].to_string();
|
||||
if did.is_empty() || repo.is_empty() {
|
||||
return None;
|
||||
let names: Vec<String> = String::from_utf8(out.stdout)
|
||||
.ok()?
|
||||
.lines()
|
||||
.map(str::trim)
|
||||
.filter(|l| !l.is_empty())
|
||||
.map(str::to_string)
|
||||
.collect();
|
||||
|
||||
let preferred = ["origin", "gitlawb"];
|
||||
let ordered = preferred
|
||||
.iter()
|
||||
.filter(|p| names.iter().any(|n| n == *p))
|
||||
.map(|p| p.to_string())
|
||||
.chain(
|
||||
names
|
||||
.iter()
|
||||
.filter(|n| !preferred.contains(&n.as_str()))
|
||||
.cloned(),
|
||||
);
|
||||
|
||||
for name in ordered {
|
||||
// A remote can carry several URLs, and the gitlawb:// one may be a
|
||||
// push URL behind an https fetch URL — check every fetch and push URL.
|
||||
for extra in [&["--all"][..], &["--push", "--all"][..]] {
|
||||
let mut args = vec!["remote", "get-url"];
|
||||
args.extend_from_slice(extra);
|
||||
args.push(&name);
|
||||
let Ok(out) = std::process::Command::new("git")
|
||||
.args(&args)
|
||||
.stderr(std::process::Stdio::null())
|
||||
.output()
|
||||
else {
|
||||
continue;
|
||||
};
|
||||
if !out.status.success() {
|
||||
continue;
|
||||
}
|
||||
let Ok(urls) = String::from_utf8(out.stdout) else {
|
||||
continue;
|
||||
};
|
||||
if let Some(parsed) = urls.lines().find_map(parse_gitlawb_url) {
|
||||
return Some(parsed);
|
||||
}
|
||||
}
|
||||
}
|
||||
Some((did, repo))
|
||||
None
|
||||
}
|
||||
|
||||
/// Parse a gitlawb:// URL string into (did, repo) — extracted for testing.
|
||||
#[cfg(test)]
|
||||
/// Parse a gitlawb:// URL string into (did, repo).
|
||||
fn parse_gitlawb_url(url: &str) -> Option<(String, String)> {
|
||||
let rest = url.trim().strip_prefix("gitlawb://")?;
|
||||
let slash = rest.rfind('/')?;
|
||||
|
||||
+283
-10
@@ -1,4 +1,4 @@
|
||||
use anyhow::Result;
|
||||
use anyhow::{Context, Result};
|
||||
use clap::{Args, Subcommand};
|
||||
use std::path::PathBuf;
|
||||
|
||||
@@ -30,15 +30,39 @@ pub enum SyncCmd {
|
||||
pub async fn run(args: SyncArgs) -> Result<()> {
|
||||
match args.cmd {
|
||||
SyncCmd::Trigger => {
|
||||
let keypair = load_keypair_from_dir(args.dir.as_deref()).ok();
|
||||
let client = NodeClient::new(&args.node, keypair);
|
||||
let resp: serde_json::Value = client
|
||||
.post("/api/v1/sync/trigger", b"{}")
|
||||
.await?
|
||||
.json()
|
||||
.await?;
|
||||
let peers = resp["peers_reached"].as_u64().unwrap_or(0);
|
||||
let enqueued = resp["repos_enqueued"].as_u64().unwrap_or(0);
|
||||
// /api/v1/sync/trigger always requires a signature, so a missing or
|
||||
// unreadable identity must fail here, locally, rather than sending an
|
||||
// unsigned request that can only 401 remotely (matches the other
|
||||
// signed CLI writes).
|
||||
let keypair = load_keypair_from_dir(args.dir.as_deref())
|
||||
.context("identity not found — run `gl identity new` first")?;
|
||||
let client = NodeClient::new(&args.node, Some(keypair));
|
||||
let resp = client.post("/api/v1/sync/trigger", b"{}").await?;
|
||||
// The node now requires a signature on this route and rate-limits it,
|
||||
// so a denial (401/429/…) is expected. Check the status BEFORE parsing:
|
||||
// otherwise a JSON-ish error body deserializes into a zero-count struct
|
||||
// and prints a fabricated "✓ sync triggered / 0 peers" success.
|
||||
let status = resp.status();
|
||||
if !status.is_success() {
|
||||
// Bound the read: a hostile or broken node must not force an
|
||||
// unbounded allocation just to surface a denial (INV-6, read half).
|
||||
let raw = read_body_capped(resp, 8 * 1024).await;
|
||||
let msg = serde_json::from_str::<serde_json::Value>(&raw)
|
||||
.ok()
|
||||
.and_then(|v| {
|
||||
v.get("message")
|
||||
.or_else(|| v.get("error"))
|
||||
.and_then(|m| m.as_str())
|
||||
.map(str::to_string)
|
||||
})
|
||||
.unwrap_or(raw);
|
||||
anyhow::bail!(
|
||||
"sync trigger failed ({status}): {}",
|
||||
sanitize_node_msg(&msg)
|
||||
);
|
||||
}
|
||||
let resp: serde_json::Value = resp.json().await?;
|
||||
let (peers, enqueued) = trigger_counts(&resp);
|
||||
println!("✓ sync triggered");
|
||||
println!(" peers reached: {peers}");
|
||||
println!(" repos enqueued: {enqueued}");
|
||||
@@ -69,3 +93,252 @@ pub async fn run(args: SyncArgs) -> Result<()> {
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Extract `(peers_reached, repos_enqueued)` from a successful sync-trigger
|
||||
/// response. Split out so the extraction is unit-testable (missing or malformed
|
||||
/// fields default to 0 rather than panicking).
|
||||
fn trigger_counts(resp: &serde_json::Value) -> (u64, u64) {
|
||||
(
|
||||
resp["peers_reached"].as_u64().unwrap_or(0),
|
||||
resp["repos_enqueued"].as_u64().unwrap_or(0),
|
||||
)
|
||||
}
|
||||
|
||||
/// Read at most `cap` bytes of a response body. Bounds the allocation from a
|
||||
/// hostile or broken node returning a huge error body — the display is capped
|
||||
/// separately, but the read itself must not be unbounded (INV-6, read half).
|
||||
async fn read_body_capped(mut resp: reqwest::Response, cap: usize) -> String {
|
||||
let mut buf: Vec<u8> = Vec::new();
|
||||
while buf.len() < cap {
|
||||
match resp.chunk().await {
|
||||
Ok(Some(chunk)) => {
|
||||
let take = (cap - buf.len()).min(chunk.len());
|
||||
buf.extend_from_slice(&chunk[..take]);
|
||||
if take < chunk.len() {
|
||||
break; // hit the cap mid-chunk
|
||||
}
|
||||
}
|
||||
_ => break, // end of body or read error — return what we have
|
||||
}
|
||||
}
|
||||
String::from_utf8_lossy(&buf).into_owned()
|
||||
}
|
||||
|
||||
/// Strip terminal-dangerous characters from (and cap the length of) a
|
||||
/// node-supplied error string before surfacing it. The node a caller talks to
|
||||
/// could be hostile and embed escape sequences in its error body; those must not
|
||||
/// reach the terminal verbatim (INV-6). We drop the C0/C1 control bytes (which
|
||||
/// defangs ANSI/OSC escapes) AND the Unicode bidi/format controls (which
|
||||
/// `char::is_control` does not cover — they can reorder the displayed line).
|
||||
fn sanitize_node_msg(s: &str) -> String {
|
||||
s.chars()
|
||||
.filter(|c| !c.is_control() && !gitlawb_core::sanitize::is_bidi_format(*c))
|
||||
.take(200)
|
||||
.collect()
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn trigger_args(node: String) -> (SyncArgs, tempfile::TempDir) {
|
||||
// Seed a real identity so `run` gets past the mandatory-keypair check and
|
||||
// reaches the status-handling path. The mocks below return a fixed status
|
||||
// regardless of the signature, so these tests exercise the client's
|
||||
// status-check-before-parse, not signature verification (that is proved
|
||||
// server-side). Return the TempDir so the caller keeps it alive.
|
||||
let dir = tempfile::TempDir::new().unwrap();
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
std::fs::write(
|
||||
dir.path().join("identity.pem"),
|
||||
kp.to_pem().unwrap().as_bytes(),
|
||||
)
|
||||
.unwrap();
|
||||
let args = SyncArgs {
|
||||
cmd: SyncCmd::Trigger,
|
||||
node,
|
||||
dir: Some(dir.path().to_path_buf()),
|
||||
};
|
||||
(args, dir)
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn trigger_requires_identity_fails_before_request() {
|
||||
// Empty identity dir → no keypair. `sync trigger` must fail locally with
|
||||
// a clear identity error BEFORE issuing any request. The node URL points
|
||||
// at an unreachable port, so a request attempt would surface a different
|
||||
// (connection) error; getting the identity error proves we never dialed.
|
||||
let dir = tempfile::TempDir::new().unwrap();
|
||||
let args = SyncArgs {
|
||||
cmd: SyncCmd::Trigger,
|
||||
node: "http://127.0.0.1:1".to_string(),
|
||||
dir: Some(dir.path().to_path_buf()),
|
||||
};
|
||||
let err = run(args).await.unwrap_err();
|
||||
assert!(
|
||||
err.to_string().contains("identity not found"),
|
||||
"expected a local identity error before any request, got: {err}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn trigger_surfaces_401_as_error_not_fake_success() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock("POST", "/api/v1/sync/trigger")
|
||||
.with_status(401)
|
||||
.with_header("content-type", "application/json")
|
||||
// Valid JSON: the parse-without-status-check bug deserializes this
|
||||
// into a zero-count success struct and prints "✓ sync triggered".
|
||||
.with_body(r#"{"message":"unauthorized"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
let (args, _dir) = trigger_args(server.url());
|
||||
let err = run(args).await.unwrap_err();
|
||||
assert!(
|
||||
err.to_string().contains("401"),
|
||||
"expected 401 surfaced, got: {err}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn trigger_surfaces_429_as_error() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock("POST", "/api/v1/sync/trigger")
|
||||
.with_status(429)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"message":"slow down"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
let (args, _dir) = trigger_args(server.url());
|
||||
let err = run(args).await.unwrap_err();
|
||||
assert!(
|
||||
err.to_string().contains("429"),
|
||||
"expected 429 surfaced, got: {err}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn trigger_sanitizes_control_chars_in_node_error() {
|
||||
// A hostile node embeds an ANSI color escape (ESC) and a bell (BEL) in
|
||||
// the JSON message field. The surfaced error must contain neither raw
|
||||
// control byte, while keeping the printable text.
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock("POST", "/api/v1/sync/trigger")
|
||||
.with_status(401)
|
||||
.with_header("content-type", "application/json")
|
||||
// Valid JSON whose message carries JSON-escaped ESC (\u001b) and
|
||||
// BEL (\u0007); serde decodes them to real control bytes a naive
|
||||
// client would print. (The status-check bug fake-successes here.)
|
||||
.with_body("{\"message\":\"pwned\\u001b[31m\\u0007bad\"}")
|
||||
.create_async()
|
||||
.await;
|
||||
let (args, _dir) = trigger_args(server.url());
|
||||
let err = run(args).await.unwrap_err();
|
||||
let s = err.to_string();
|
||||
assert!(!s.contains('\u{1b}'), "ESC leaked to terminal: {s:?}");
|
||||
assert!(!s.contains('\u{07}'), "BEL leaked to terminal: {s:?}");
|
||||
assert!(
|
||||
s.contains("pwned") && s.contains("bad"),
|
||||
"message text dropped: {s:?}"
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn trigger_ok_prints_counts() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock("POST", "/api/v1/sync/trigger")
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"peers_reached":2,"repos_enqueued":5}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
let (args, _dir) = trigger_args(server.url());
|
||||
run(args).await.unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sanitize_strips_controls_bidi_and_caps_length() {
|
||||
// C0 (ESC/BEL) and the Cf bidi override (U+202E) are both removed; the
|
||||
// printable text survives. (Note: a stripped ESC leaves any following
|
||||
// "[31m" as inert literal text — that is the point, so the input here
|
||||
// avoids that residue to keep the expectation unambiguous.)
|
||||
let out = sanitize_node_msg("a\u{1b}\u{07}b\u{202e}c");
|
||||
assert!(
|
||||
!out.chars().any(|c| c.is_control()),
|
||||
"control char leaked: {out:?}"
|
||||
);
|
||||
assert!(
|
||||
!out.contains('\u{202e}'),
|
||||
"RLO bidi override leaked: {out:?}"
|
||||
);
|
||||
assert_eq!(out, "abc");
|
||||
// Length is capped at 200 chars regardless of input size.
|
||||
let long = "x".repeat(250);
|
||||
assert_eq!(sanitize_node_msg(&long).chars().count(), 200);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sanitize_preserves_legitimate_and_rtl_text() {
|
||||
// Must not over-strip: a plain word, a genuine RTL SCRIPT letter (Arabic
|
||||
// U+0627, category Lo — NOT a format char), and ZWJ (U+200D, a legitimate
|
||||
// Cf char, e.g. emoji sequences) all survive. Guards the shared predicate
|
||||
// against being widened into a blanket Cf stripper.
|
||||
let out = sanitize_node_msg("ok \u{0627}\u{200D}b");
|
||||
assert_eq!(out, "ok \u{0627}\u{200D}b");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn trigger_handles_oversized_error_body_without_unbounded_output() {
|
||||
// A hostile/broken node returns a 2 MB error body. The command must still
|
||||
// surface the denial with a bounded message, not hang or dump the body.
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock("POST", "/api/v1/sync/trigger")
|
||||
.with_status(401)
|
||||
.with_body("A".repeat(2_000_000))
|
||||
.create_async()
|
||||
.await;
|
||||
let (args, _dir) = trigger_args(server.url());
|
||||
let err = run(args).await.unwrap_err();
|
||||
let s = err.to_string();
|
||||
assert!(s.contains("401"), "denial not surfaced: {s:.80?}");
|
||||
assert!(
|
||||
s.len() < 500,
|
||||
"error message not bounded: {} chars",
|
||||
s.len()
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn read_body_capped_bounds_the_read() {
|
||||
// The read must stop at the cap — a 2 MB body yields at most `cap` bytes,
|
||||
// not the whole thing (which resp.text() would return).
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let _m = server
|
||||
.mock("GET", "/big")
|
||||
.with_status(200)
|
||||
.with_body("A".repeat(2_000_000))
|
||||
.create_async()
|
||||
.await;
|
||||
let resp = reqwest::get(format!("{}/big", server.url())).await.unwrap();
|
||||
let out = read_body_capped(resp, 8192).await;
|
||||
assert!(out.len() <= 8192, "read not bounded: {} bytes", out.len());
|
||||
assert!(!out.is_empty(), "expected some body");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn trigger_counts_extracts_both_values() {
|
||||
let v = serde_json::json!({"peers_reached": 2, "repos_enqueued": 5});
|
||||
assert_eq!(trigger_counts(&v), (2, 5));
|
||||
// Missing/malformed fields default to 0, never panic.
|
||||
assert_eq!(trigger_counts(&serde_json::json!({})), (0, 0));
|
||||
assert_eq!(
|
||||
trigger_counts(&serde_json::json!({"peers_reached": "x"})),
|
||||
(0, 0)
|
||||
);
|
||||
}
|
||||
}
|
||||
+169
-26
@@ -42,6 +42,8 @@ pub enum WebhookCmd {
|
||||
repo: String,
|
||||
#[arg(long, default_value = "https://node.gitlawb.com", env = "GITLAWB_NODE")]
|
||||
node: String,
|
||||
#[arg(long)]
|
||||
dir: Option<PathBuf>,
|
||||
},
|
||||
/// Delete a webhook
|
||||
Delete {
|
||||
@@ -66,7 +68,7 @@ pub async fn run(args: WebhookArgs) -> Result<()> {
|
||||
node,
|
||||
dir,
|
||||
} => cmd_create(repo, url, events, secret, node, dir).await,
|
||||
WebhookCmd::List { repo, node } => cmd_list(repo, node).await,
|
||||
WebhookCmd::List { repo, node, dir } => cmd_list(repo, node, dir).await,
|
||||
WebhookCmd::Delete {
|
||||
repo,
|
||||
id,
|
||||
@@ -76,15 +78,6 @@ pub async fn run(args: WebhookArgs) -> Result<()> {
|
||||
}
|
||||
}
|
||||
|
||||
async fn resolve_owner(client: &NodeClient) -> Result<String> {
|
||||
let info: Value = client.get("/").await?.json().await?;
|
||||
let did = info["did"]
|
||||
.as_str()
|
||||
.context("node missing DID")?
|
||||
.to_string();
|
||||
Ok(did.split(':').next_back().unwrap_or(&did).to_string())
|
||||
}
|
||||
|
||||
async fn cmd_create(
|
||||
repo: String,
|
||||
url: String,
|
||||
@@ -94,8 +87,8 @@ async fn cmd_create(
|
||||
dir: Option<PathBuf>,
|
||||
) -> Result<()> {
|
||||
let keypair = load_keypair_from_dir(dir.as_deref())?;
|
||||
let (owner, name) = crate::repo::resolve_owner_repo_pair(&repo, &node, dir.as_deref()).await?;
|
||||
let client = NodeClient::new(&node, Some(keypair));
|
||||
let owner = resolve_owner(&client).await?;
|
||||
|
||||
let event_list: Vec<&str> = events.split(',').map(str::trim).collect();
|
||||
|
||||
@@ -106,7 +99,7 @@ async fn cmd_create(
|
||||
}))?;
|
||||
|
||||
let resp = client
|
||||
.post(&format!("/api/v1/repos/{owner}/{repo}/hooks"), &payload)
|
||||
.post(&format!("/api/v1/repos/{owner}/{name}/hooks"), &payload)
|
||||
.await
|
||||
.context("failed to connect to node")?;
|
||||
let status = resp.status();
|
||||
@@ -143,18 +136,31 @@ async fn cmd_create(
|
||||
Ok(())
|
||||
}
|
||||
|
||||
async fn cmd_list(repo: String, node: String) -> Result<()> {
|
||||
let client = NodeClient::new(&node, None);
|
||||
let owner = resolve_owner(&client).await?;
|
||||
async fn cmd_list(repo: String, node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
// The node owner-gates GET /hooks (callback URLs are owner-secret), so the
|
||||
// list request must be signed — anonymous callers get 401.
|
||||
let keypair = load_keypair_from_dir(dir.as_deref())?;
|
||||
let (owner, name) = crate::repo::resolve_owner_repo_pair(&repo, &node, dir.as_deref()).await?;
|
||||
let client = NodeClient::new(&node, Some(keypair));
|
||||
|
||||
let resp: Value = client
|
||||
.get(&format!("/api/v1/repos/{owner}/{repo}/hooks"))
|
||||
.await?
|
||||
.json()
|
||||
.await
|
||||
.context("invalid JSON")?;
|
||||
// get_signed (not get) attaches the RFC 9421 signature — plain get() never
|
||||
// signs, and the node owner-gates this route, so an unsigned GET 401s.
|
||||
let resp = client
|
||||
.get_signed(&format!("/api/v1/repos/{owner}/{name}/hooks"))
|
||||
.await?;
|
||||
let status = resp.status();
|
||||
let body: Value = resp.json().await.context("invalid JSON")?;
|
||||
|
||||
let hooks = resp["webhooks"].as_array().cloned().unwrap_or_default();
|
||||
if !status.is_success() {
|
||||
let msg = body["message"].as_str().unwrap_or("unknown error");
|
||||
anyhow::bail!("list webhooks failed ({status}): {msg}");
|
||||
}
|
||||
|
||||
let hooks = body
|
||||
.get("webhooks")
|
||||
.and_then(Value::as_array)
|
||||
.cloned()
|
||||
.context("node response missing webhooks array")?;
|
||||
if hooks.is_empty() {
|
||||
println!("No webhooks for {repo}");
|
||||
return Ok(());
|
||||
@@ -185,13 +191,13 @@ async fn cmd_list(repo: String, node: String) -> Result<()> {
|
||||
|
||||
async fn cmd_delete(repo: String, id: String, node: String, dir: Option<PathBuf>) -> Result<()> {
|
||||
let keypair = load_keypair_from_dir(dir.as_deref())?;
|
||||
let (owner, name) = crate::repo::resolve_owner_repo_pair(&repo, &node, dir.as_deref()).await?;
|
||||
let client = NodeClient::new(&node, Some(keypair));
|
||||
let owner = resolve_owner(&client).await?;
|
||||
|
||||
let payload = serde_json::to_vec(&serde_json::json!({}))?;
|
||||
let resp = client
|
||||
.delete(
|
||||
&format!("/api/v1/repos/{owner}/{repo}/hooks/{id}"),
|
||||
&format!("/api/v1/repos/{owner}/{name}/hooks/{id}"),
|
||||
&payload,
|
||||
)
|
||||
.await
|
||||
@@ -337,33 +343,170 @@ mod tests {
|
||||
#[tokio::test]
|
||||
async fn test_list_webhooks_empty() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let (dir, _kp) = tmp_identity();
|
||||
let _root = mock_root(&mut server).await;
|
||||
|
||||
let _m = server
|
||||
.mock("GET", mockito::Matcher::Regex(r"/hooks$".to_string()))
|
||||
// The route is owner-gated, so the list request must be signed.
|
||||
// Requiring the header here is what catches a regression to plain get().
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"webhooks":[]}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
cmd_list("my-repo".to_string(), server.url()).await.unwrap();
|
||||
cmd_list(
|
||||
"my-repo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_list_webhooks_with_items() {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let (dir, _kp) = tmp_identity();
|
||||
let _root = mock_root(&mut server).await;
|
||||
|
||||
let _m = server
|
||||
.mock("GET", mockito::Matcher::Regex(r"/hooks$".to_string()))
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"webhooks":[{"id":"h1","url":"https://a.com","events":["push"],"active":true},{"id":"h2","url":"https://b.com","events":["*"],"active":false}]}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
cmd_list("my-repo".to_string(), server.url()).await.unwrap();
|
||||
cmd_list(
|
||||
"my-repo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_list_owner_comes_from_keypair_not_node_did() {
|
||||
// The owner segment must be derived from the caller's keypair (loaded
|
||||
// from --dir), NOT the node root DID. mock_root returns a different DID;
|
||||
// if the code regressed to using it, this path mock would not match.
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let (dir, kp) = tmp_identity();
|
||||
let _root = mock_root(&mut server).await;
|
||||
|
||||
let did = kp.did().to_string();
|
||||
let short = did.split(':').next_back().unwrap_or(&did).to_string();
|
||||
|
||||
let _m = server
|
||||
.mock(
|
||||
"GET",
|
||||
mockito::Matcher::Regex(format!(r"/api/v1/repos/{short}/my-repo/hooks$")),
|
||||
)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"webhooks":[]}"#)
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
cmd_list(
|
||||
"my-repo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
_m.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_list_honors_owner_repo_arg() {
|
||||
// An explicit `owner/repo` argument is split and used verbatim.
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let (dir, _kp) = tmp_identity();
|
||||
let _root = mock_root(&mut server).await;
|
||||
|
||||
let _m = server
|
||||
.mock(
|
||||
"GET",
|
||||
mockito::Matcher::Regex(r"/api/v1/repos/someoneelse/their-repo/hooks$".to_string()),
|
||||
)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"webhooks":[]}"#)
|
||||
.expect(1)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
cmd_list(
|
||||
"someoneelse/their-repo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
_m.assert_async().await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_list_webhooks_non_success_status_errors() {
|
||||
// A 403 (or any non-2xx) JSON body has no `webhooks` field; cmd_list must
|
||||
// surface the failure, not print "No webhooks" and exit 0.
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let (dir, _kp) = tmp_identity();
|
||||
let _root = mock_root(&mut server).await;
|
||||
|
||||
let _m = server
|
||||
.mock("GET", mockito::Matcher::Regex(r"/hooks$".to_string()))
|
||||
.with_status(403)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"message":"not the owner"}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let err = cmd_list(
|
||||
"my-repo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(err.to_string().contains("not the owner"));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn test_list_webhooks_2xx_missing_array_errors() {
|
||||
// A 2xx body without a `webhooks` array signals a node/API contract
|
||||
// regression. cmd_list must error rather than print "No webhooks".
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let (dir, _kp) = tmp_identity();
|
||||
let _root = mock_root(&mut server).await;
|
||||
|
||||
let _m = server
|
||||
.mock("GET", mockito::Matcher::Regex(r"/hooks$".to_string()))
|
||||
.match_header("signature", mockito::Matcher::Any)
|
||||
.match_header("signature-input", mockito::Matcher::Any)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"ok":true}"#)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let err = cmd_list(
|
||||
"my-repo".to_string(),
|
||||
server.url(),
|
||||
Some(dir.path().to_path_buf()),
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(err.to_string().contains("missing webhooks array"));
|
||||
}
|
||||
|
||||
// ── delete ───────────────────────────────────────────────────────
|
||||
|
||||
@@ -0,0 +1,21 @@
|
||||
[package]
|
||||
name = "icaptcha-client"
|
||||
version = "0.4.0" # x-release-please-version
|
||||
edition.workspace = true
|
||||
rust-version.workspace = true
|
||||
license.workspace = true
|
||||
authors.workspace = true
|
||||
repository.workspace = true
|
||||
|
||||
[dependencies]
|
||||
gitlawb-core = { path = "../gitlawb-core" }
|
||||
reqwest = { workspace = true }
|
||||
serde = { workspace = true }
|
||||
serde_json = { workspace = true }
|
||||
anyhow = { workspace = true }
|
||||
thiserror = { workspace = true }
|
||||
tracing = { workspace = true }
|
||||
sha2 = { workspace = true }
|
||||
|
||||
[dev-dependencies]
|
||||
mockito = "1"
|
||||
@@ -0,0 +1,723 @@
|
||||
//! Client for the iCaptcha proof-of-intelligence service.
|
||||
//!
|
||||
//! The node gates spam-prone writes (repo create / fork / register) behind an
|
||||
//! iCaptcha proof. This crate implements the *sanctioned client flow*: on a
|
||||
//! `403 icaptcha_proof_required`, request a challenge for the required level,
|
||||
//! solve the deterministic computational types locally, obtain the signed
|
||||
//! proof, and hand it back so the caller can retry the original signed request
|
||||
//! with the `x-icaptcha-proof` header.
|
||||
//!
|
||||
//! `requesterId` is always the caller's DID, so the proof's `sub` claim matches
|
||||
//! the authenticated signer (the node enforces `sub == authenticated DID`).
|
||||
//!
|
||||
//! Blocking HTTP (reqwest::blocking) so the git remote helper can use it
|
||||
//! directly; `gl` (async) calls it via `tokio::task::spawn_blocking`.
|
||||
|
||||
use std::io::Read;
|
||||
|
||||
use anyhow::{anyhow, bail, Context, Result};
|
||||
use serde::Deserialize;
|
||||
use serde_json::json;
|
||||
|
||||
pub mod pow;
|
||||
pub mod solvers;
|
||||
|
||||
/// Default iCaptcha service base URL (used when the node doesn't advertise one).
|
||||
pub const DEFAULT_URL: &str = "https://icaptcha.gitlawb.com";
|
||||
/// Default required level (the node's default floor).
|
||||
pub const DEFAULT_LEVEL: u32 = 3;
|
||||
/// Header the gated write must echo the proof back in.
|
||||
pub const PROOF_HEADER: &str = "x-icaptcha-proof";
|
||||
|
||||
/// Cap on bytes read from an error response, and characters kept in the excerpt.
|
||||
/// The iCaptcha origin is only as trusted as the node that advertised it (a MITM
|
||||
/// on the default transport qualifies), so its error bodies are attacker-
|
||||
/// influenceable bytes that reach the TTY — they must be bounded and stripped of
|
||||
/// control characters before printing (CWE-150, same treatment as #137).
|
||||
const MAX_ERR_BYTES: u64 = 4096;
|
||||
const MAX_ERR_CHARS: usize = 500;
|
||||
|
||||
/// Read a bounded error body and return a control-char-stripped, length-capped
|
||||
/// single-line excerpt safe to print to a terminal.
|
||||
fn error_excerpt(resp: reqwest::blocking::Response) -> String {
|
||||
let mut buf = Vec::new();
|
||||
if resp.take(MAX_ERR_BYTES).read_to_end(&mut buf).is_err() {
|
||||
return String::new();
|
||||
}
|
||||
sanitize_excerpt(&String::from_utf8_lossy(&buf))
|
||||
}
|
||||
|
||||
/// Strip C0/C1 control characters, collapse whitespace runs to single spaces,
|
||||
/// and cap the length — so a hostile response body cannot inject terminal
|
||||
/// escapes or flood the TTY.
|
||||
fn sanitize_excerpt(s: &str) -> String {
|
||||
let mut out = String::new();
|
||||
let mut pending_space = false;
|
||||
let mut kept = 0;
|
||||
for ch in s.trim().chars() {
|
||||
if kept >= MAX_ERR_CHARS {
|
||||
break;
|
||||
}
|
||||
if ch.is_control() {
|
||||
if matches!(ch, '\n' | '\r' | '\t') {
|
||||
pending_space = true;
|
||||
}
|
||||
continue;
|
||||
}
|
||||
if gitlawb_core::sanitize::is_bidi_format(ch) {
|
||||
// Drop Cf bidi/format controls (INV-6, #183) without setting
|
||||
// pending_space: they are not whitespace, so stripping leaves no
|
||||
// phantom gap.
|
||||
continue;
|
||||
}
|
||||
if ch.is_whitespace() {
|
||||
pending_space = true;
|
||||
continue;
|
||||
}
|
||||
if pending_space && !out.is_empty() {
|
||||
out.push(' ');
|
||||
kept += 1;
|
||||
if kept >= MAX_ERR_CHARS {
|
||||
break;
|
||||
}
|
||||
}
|
||||
out.push(ch);
|
||||
kept += 1;
|
||||
pending_space = false;
|
||||
}
|
||||
out
|
||||
}
|
||||
|
||||
/// Whether `u` parses as a trusted URL.
|
||||
///
|
||||
/// Production trusts only `https`. When `GITLAWB_ICAPTCHA_INSECURE` is set (a
|
||||
/// runtime escape hatch for integration tests) the function also trusts
|
||||
/// `http://127.0.0.1` and `http://localhost` so the full iCaptcha retry path
|
||||
/// can be exercised against a local mockito server.
|
||||
fn is_https(u: &str) -> bool {
|
||||
let Ok(parsed) = reqwest::Url::parse(u) else {
|
||||
return false;
|
||||
};
|
||||
if parsed.scheme() == "https" {
|
||||
return true;
|
||||
}
|
||||
if std::env::var_os("GITLAWB_ICAPTCHA_INSECURE").is_some()
|
||||
&& parsed.scheme() == "http"
|
||||
&& matches!(parsed.host_str(), Some("127.0.0.1" | "localhost"))
|
||||
{
|
||||
return true;
|
||||
}
|
||||
false
|
||||
}
|
||||
|
||||
/// Lowercased origin string (`scheme://host[:port]`) of a URL.
|
||||
///
|
||||
/// Includes the effective port so that `http://localhost:3000` and
|
||||
/// `http://localhost:9000` are treated as distinct origins — a hostile node
|
||||
/// cannot redirect the iCaptcha solve to a different loopback port.
|
||||
fn origin_key(u: &str) -> Option<String> {
|
||||
let parsed = reqwest::Url::parse(u).ok()?;
|
||||
let scheme = parsed.scheme();
|
||||
let host = parsed.host_str()?.to_ascii_lowercase();
|
||||
let port = parsed
|
||||
.port_or_known_default()
|
||||
.map(|p| format!(":{p}"))
|
||||
.unwrap_or_default();
|
||||
Some(format!("{scheme}://{host}{port}"))
|
||||
}
|
||||
|
||||
/// Decide which iCaptcha origin to actually talk to, and whether it is trusted
|
||||
/// enough to receive the operator's API key.
|
||||
///
|
||||
/// The node-advertised `x-icaptcha-url` is untrusted: a hostile node could point
|
||||
/// it at an attacker origin (client-side SSRF) or capture a bearer token on the
|
||||
/// first hop. So an advertised URL is honored only when it is `https` AND its
|
||||
/// host is allowlisted — the public default host, or the operator's own
|
||||
/// `GITLAWB_ICAPTCHA_URL`. Otherwise we fall back to the operator/default origin.
|
||||
///
|
||||
/// The API key is attached only when the resolved origin is the operator's
|
||||
/// explicitly-configured host (never a node-discovered one), so a key is never
|
||||
/// exfiltrated to an origin the operator did not choose.
|
||||
fn resolve_solver_url(advertised: Option<&str>, operator: Option<&str>) -> (String, bool) {
|
||||
let operator = operator.filter(|u| is_https(u));
|
||||
let operator_origin = operator.as_ref().and_then(|u| origin_key(u));
|
||||
let default_origin = origin_key(DEFAULT_URL);
|
||||
|
||||
let allowed = |origin: &Option<String>| -> bool {
|
||||
origin
|
||||
.as_ref()
|
||||
.map(|o| Some(o) == default_origin.as_ref() || Some(o) == operator_origin.as_ref())
|
||||
.unwrap_or(false)
|
||||
};
|
||||
|
||||
let fallback = || {
|
||||
operator
|
||||
.map(String::from)
|
||||
.unwrap_or_else(|| DEFAULT_URL.to_string())
|
||||
};
|
||||
|
||||
let chosen = match advertised {
|
||||
Some(a) if is_https(a) && allowed(&origin_key(a)) => a.to_string(),
|
||||
Some(a) => {
|
||||
tracing::warn!(
|
||||
advertised = %a,
|
||||
"ignoring iCaptcha URL advertised by node (must be https with an allowlisted host); using trusted origin"
|
||||
);
|
||||
fallback()
|
||||
}
|
||||
None => fallback(),
|
||||
};
|
||||
|
||||
// Key goes only to the operator's own configured origin.
|
||||
let key_trusted = operator_origin.is_some() && origin_key(&chosen) == operator_origin;
|
||||
(chosen, key_trusted)
|
||||
}
|
||||
|
||||
/// Computational challenge types this client solves locally. Restricting the
|
||||
/// request to these avoids dictionary (anagram/logic) and LLM (wordproblem/
|
||||
/// riddle) types, which can't be auto-solved.
|
||||
const SOLVABLE_TYPES: [&str; 3] = ["arithmetic", "algebra", "sequence"];
|
||||
|
||||
/// Bound on challenge/answer rounds (the service escalates difficulty on a miss;
|
||||
/// correct solvers shouldn't escalate, but cap it regardless).
|
||||
const MAX_ROUNDS: usize = 8;
|
||||
|
||||
/// Where + at what level to solve. `did` becomes the proof's `sub`.
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct IcaptchaCfg {
|
||||
pub url: String,
|
||||
pub did: String,
|
||||
pub level: u32,
|
||||
/// Optional bearer token for an API-key-protected iCaptcha deployment.
|
||||
pub api_key: Option<String>,
|
||||
}
|
||||
|
||||
impl IcaptchaCfg {
|
||||
/// Build config from the caller DID plus an optionally node-advertised
|
||||
/// url/level (e.g. the `x-icaptcha-url` / `x-icaptcha-level` headers) and
|
||||
/// optional level.
|
||||
///
|
||||
/// The advertised URL is validated and allowlisted (see [`resolve_solver_url`])
|
||||
/// so a hostile node cannot redirect the solve to an attacker origin. The
|
||||
/// `GITLAWB_ICAPTCHA_API_KEY` bearer token is attached only when the resolved
|
||||
/// origin is the operator's own `GITLAWB_ICAPTCHA_URL`, never a
|
||||
/// node-discovered one.
|
||||
pub fn new(did: impl Into<String>, url: Option<String>, level: Option<u32>) -> Self {
|
||||
let operator = std::env::var("GITLAWB_ICAPTCHA_URL")
|
||||
.ok()
|
||||
.filter(|s| !s.is_empty());
|
||||
let (resolved_url, key_trusted) = resolve_solver_url(url.as_deref(), operator.as_deref());
|
||||
let api_key = if key_trusted {
|
||||
std::env::var("GITLAWB_ICAPTCHA_API_KEY")
|
||||
.ok()
|
||||
.filter(|s| !s.is_empty())
|
||||
} else {
|
||||
None
|
||||
};
|
||||
Self {
|
||||
url: resolved_url,
|
||||
did: did.into(),
|
||||
level: level.unwrap_or(DEFAULT_LEVEL),
|
||||
api_key,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// A challenge handed back by the service (mirrors `icaptcha` `Challenge`).
|
||||
#[derive(Debug, Clone, Deserialize)]
|
||||
#[serde(rename_all = "camelCase")]
|
||||
pub struct Challenge {
|
||||
pub challenge_id: String,
|
||||
#[serde(rename = "type")]
|
||||
pub kind: String,
|
||||
pub difficulty: u32,
|
||||
pub prompt: String,
|
||||
pub token: String,
|
||||
/// Proof-of-work to solve and echo back as `powNonce` on the answer. Present
|
||||
/// only when the service has PoW enabled; absent/None means no PoW required.
|
||||
#[serde(default)]
|
||||
pub pow: Option<pow::PowChallenge>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
#[serde(tag = "status", rename_all = "lowercase")]
|
||||
enum AnswerResult {
|
||||
Passed { proof: String },
|
||||
Continue { challenge: Challenge },
|
||||
Failed { reason: String },
|
||||
}
|
||||
|
||||
/// Solver callback for types this crate can't solve deterministically.
|
||||
pub type Solver<'a> = dyn Fn(&Challenge) -> Option<String> + 'a;
|
||||
|
||||
/// Run the full challenge → solve → answer loop and return a fresh proof token.
|
||||
///
|
||||
/// `solver` is consulted for challenge types the built-in solvers don't handle
|
||||
/// (anagram/logic/LLM); pass `None` to fall back to an interactive stdin prompt.
|
||||
pub fn obtain_proof(cfg: &IcaptchaCfg, solver: Option<&Solver>) -> Result<String> {
|
||||
let client = reqwest::blocking::Client::builder()
|
||||
.timeout(std::time::Duration::from_secs(30))
|
||||
.build()
|
||||
.context("build iCaptcha http client")?;
|
||||
|
||||
let mut challenge = request_challenge(&client, cfg)?;
|
||||
for _ in 0..MAX_ROUNDS {
|
||||
let answer = solvers::solve(&challenge.kind, &challenge.prompt)
|
||||
.or_else(|| solver.and_then(|s| s(&challenge)))
|
||||
.or_else(|| interactive_prompt(&challenge))
|
||||
.ok_or_else(|| {
|
||||
anyhow!(
|
||||
"cannot solve iCaptcha challenge type '{}' automatically; \
|
||||
set GITLAWB_ICAPTCHA_API_KEY/solver or solve interactively",
|
||||
challenge.kind
|
||||
)
|
||||
})?;
|
||||
|
||||
// Solve the proof-of-work bound to this challenge, if the service
|
||||
// requires one. A required-but-unsolvable PoW (unknown algorithm or a
|
||||
// difficulty above our cap) is a hard error — submitting without it
|
||||
// would just be rejected.
|
||||
let pow_nonce = match &challenge.pow {
|
||||
Some(p) => Some(pow::solve(p).ok_or_else(|| {
|
||||
anyhow!(
|
||||
"cannot solve iCaptcha proof-of-work (algorithm '{}', difficulty {})",
|
||||
p.algorithm,
|
||||
p.difficulty
|
||||
)
|
||||
})?),
|
||||
None => None,
|
||||
};
|
||||
|
||||
match submit_answer(
|
||||
&client,
|
||||
cfg,
|
||||
&challenge.token,
|
||||
&answer,
|
||||
pow_nonce.as_deref(),
|
||||
)? {
|
||||
AnswerResult::Passed { proof } => return Ok(proof),
|
||||
AnswerResult::Continue { challenge: next } => challenge = next,
|
||||
AnswerResult::Failed { reason } => {
|
||||
bail!("iCaptcha challenge failed: {}", sanitize_excerpt(&reason))
|
||||
}
|
||||
}
|
||||
}
|
||||
bail!("iCaptcha not solved within {MAX_ROUNDS} rounds")
|
||||
}
|
||||
|
||||
fn request_challenge(client: &reqwest::blocking::Client, cfg: &IcaptchaCfg) -> Result<Challenge> {
|
||||
let url = format!("{}/v1/challenge", cfg.url.trim_end_matches('/'));
|
||||
let body = json!({
|
||||
"requesterId": cfg.did,
|
||||
"requiredLevel": cfg.level,
|
||||
"types": SOLVABLE_TYPES,
|
||||
});
|
||||
let mut req = client.post(&url).json(&body);
|
||||
if let Some(key) = &cfg.api_key {
|
||||
req = req.bearer_auth(key);
|
||||
}
|
||||
let resp = req.send().with_context(|| format!("POST {url}"))?;
|
||||
if !resp.status().is_success() {
|
||||
let status = resp.status();
|
||||
let text = error_excerpt(resp);
|
||||
bail!("iCaptcha challenge request failed ({status}): {text}");
|
||||
}
|
||||
resp.json::<Challenge>().context("parse iCaptcha challenge")
|
||||
}
|
||||
|
||||
fn submit_answer(
|
||||
client: &reqwest::blocking::Client,
|
||||
cfg: &IcaptchaCfg,
|
||||
token: &str,
|
||||
answer: &str,
|
||||
pow_nonce: Option<&str>,
|
||||
) -> Result<AnswerResult> {
|
||||
let url = format!("{}/v1/answer", cfg.url.trim_end_matches('/'));
|
||||
let mut body = json!({ "token": token, "answer": answer });
|
||||
if let Some(nonce) = pow_nonce {
|
||||
body["powNonce"] = json!(nonce);
|
||||
}
|
||||
let mut req = client.post(&url).json(&body);
|
||||
if let Some(key) = &cfg.api_key {
|
||||
req = req.bearer_auth(key);
|
||||
}
|
||||
let resp = req.send().with_context(|| format!("POST {url}"))?;
|
||||
if !resp.status().is_success() {
|
||||
let status = resp.status();
|
||||
let text = error_excerpt(resp);
|
||||
bail!("iCaptcha answer request failed ({status}): {text}");
|
||||
}
|
||||
resp.json::<AnswerResult>()
|
||||
.context("parse iCaptcha answer result")
|
||||
}
|
||||
|
||||
/// Last-resort fallback: show the prompt and read an answer from the terminal.
|
||||
/// Returns `None` when stdin isn't a usable interactive source (e.g. an agent),
|
||||
/// so the caller surfaces a clear "couldn't auto-solve" error instead.
|
||||
fn interactive_prompt(challenge: &Challenge) -> Option<String> {
|
||||
use std::io::{stderr, stdin, Write};
|
||||
let mut err = stderr();
|
||||
let _ = writeln!(
|
||||
err,
|
||||
"iCaptcha challenge ({}, level {}): {}\nAnswer: ",
|
||||
challenge.kind, challenge.difficulty, challenge.prompt
|
||||
);
|
||||
let _ = err.flush();
|
||||
let mut line = String::new();
|
||||
match stdin().read_line(&mut line) {
|
||||
Ok(0) | Err(_) => None,
|
||||
Ok(_) => {
|
||||
let a = line.trim().to_string();
|
||||
if a.is_empty() {
|
||||
None
|
||||
} else {
|
||||
Some(a)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use std::ffi::OsString;
|
||||
use std::sync::{Mutex, MutexGuard};
|
||||
|
||||
/// Serializes tests that touch the process-global
|
||||
/// `GITLAWB_ICAPTCHA_INSECURE` env var so they never race.
|
||||
static ICAPTCHA_ENV_LOCK: Mutex<()> = Mutex::new(());
|
||||
|
||||
/// Set `GITLAWB_ICAPTCHA_INSECURE` for the test lifetime, restoring any
|
||||
/// prior value on drop.
|
||||
struct InsecureEnv {
|
||||
_lock: MutexGuard<'static, ()>,
|
||||
prev: Option<OsString>,
|
||||
}
|
||||
|
||||
impl InsecureEnv {
|
||||
fn new() -> Self {
|
||||
let lock = ICAPTCHA_ENV_LOCK.lock().unwrap();
|
||||
let prev = std::env::var_os("GITLAWB_ICAPTCHA_INSECURE");
|
||||
std::env::set_var("GITLAWB_ICAPTCHA_INSECURE", "1");
|
||||
InsecureEnv { _lock: lock, prev }
|
||||
}
|
||||
}
|
||||
|
||||
impl Drop for InsecureEnv {
|
||||
fn drop(&mut self) {
|
||||
match self.prev.take() {
|
||||
Some(v) => std::env::set_var("GITLAWB_ICAPTCHA_INSECURE", v),
|
||||
None => std::env::remove_var("GITLAWB_ICAPTCHA_INSECURE"),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// ── P1: hostile error bodies must not reach the terminal raw ──────────
|
||||
|
||||
#[test]
|
||||
fn sanitize_strips_control_chars_and_escapes() {
|
||||
// ESC-based terminal escape + NUL + bell must all be removed.
|
||||
let hostile = "\x1b[2J\x1b[31mowned\x07\0 done";
|
||||
let clean = sanitize_excerpt(hostile);
|
||||
assert!(!clean.contains('\x1b'), "ESC survived: {clean:?}");
|
||||
assert!(
|
||||
!clean.chars().any(|c| c.is_control()),
|
||||
"control survived: {clean:?}"
|
||||
);
|
||||
assert!(clean.contains("owned") && clean.contains("done"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sanitize_strips_bidi_format_controls() {
|
||||
// The Cc-only test above is vacuous for Cf: it passes whether or not bidi
|
||||
// controls survive, which is why this gap shipped (#183). Here every Cf
|
||||
// bidi class is stripped — override (RLO), embedding + pop (LRE/PDF),
|
||||
// isolate (LRI/PDI), marks (LRM/ALM) — asserted per code point, and the
|
||||
// visible words JOIN with no phantom space (a bidi char is dropped like a
|
||||
// control byte, but unlike a newline/tab it is not whitespace). The leading
|
||||
// bidi char (index 0) also exercises the empty-out path.
|
||||
let out = sanitize_excerpt("\u{202e}err\u{202a}\u{202c}\u{2066}\u{2069}\u{200e}\u{061c}ok");
|
||||
for c in [
|
||||
'\u{202e}', '\u{202a}', '\u{202c}', '\u{2066}', '\u{2069}', '\u{200e}', '\u{061c}',
|
||||
] {
|
||||
assert!(!out.contains(c), "bidi U+{:04X} leaked: {out:?}", c as u32);
|
||||
}
|
||||
assert_eq!(out, "errok");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sanitize_preserves_legitimate_and_rtl_text() {
|
||||
// Must not over-strip: plain text, a genuine RTL SCRIPT letter (Arabic
|
||||
// U+0627, category Lo), and ZWJ (U+200D, a legitimate Cf char) survive.
|
||||
assert_eq!(
|
||||
sanitize_excerpt("ok \u{0627}\u{200D}b"),
|
||||
"ok \u{0627}\u{200D}b"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sanitize_collapses_whitespace_and_caps_length() {
|
||||
let collapsed = sanitize_excerpt("a\n\n\t b");
|
||||
assert_eq!(collapsed, "a b");
|
||||
let long = "x".repeat(MAX_ERR_CHARS + 500);
|
||||
assert_eq!(sanitize_excerpt(&long).chars().count(), MAX_ERR_CHARS);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sanitize_bidi_chars_do_not_consume_the_length_cap() {
|
||||
// A dropped bidi char must not count toward MAX_ERR_CHARS: it is dropped
|
||||
// before `kept` increments, so interleaving bidi controls cannot truncate
|
||||
// the visible output early. MAX_ERR_CHARS + 100 visible 'x', each trailed by
|
||||
// a bidi override, must still yield exactly MAX_ERR_CHARS visible 'x' with
|
||||
// no phantom spaces. (Would regress to fewer 'x' if bidi consumed budget, or
|
||||
// to spaces if the drop branch wrongly set pending_space.)
|
||||
let body = "x\u{202e}".repeat(MAX_ERR_CHARS + 100);
|
||||
assert_eq!(sanitize_excerpt(&body), "x".repeat(MAX_ERR_CHARS));
|
||||
}
|
||||
|
||||
// ── P2: never talk to (or hand a key to) an untrusted node-chosen URL ──
|
||||
|
||||
#[test]
|
||||
fn rejects_non_https_advertised_url() {
|
||||
// A plaintext node-advertised URL is ignored; we fall back to default.
|
||||
let (url, key_trusted) = resolve_solver_url(Some("http://evil.example/x"), None);
|
||||
assert_eq!(url, DEFAULT_URL);
|
||||
assert!(!key_trusted);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_https_url_with_non_allowlisted_host() {
|
||||
let (url, key_trusted) = resolve_solver_url(Some("https://evil.example"), None);
|
||||
assert_eq!(url, DEFAULT_URL, "attacker host must not be honored");
|
||||
assert!(!key_trusted);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn honors_advertised_default_host_but_withholds_key_without_operator() {
|
||||
// Default public host is allowlisted for talking, but with no operator
|
||||
// origin configured the API key has no trusted destination.
|
||||
let (url, key_trusted) = resolve_solver_url(Some("https://icaptcha.gitlawb.com/v2"), None);
|
||||
assert_eq!(url, "https://icaptcha.gitlawb.com/v2");
|
||||
assert!(!key_trusted);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn key_trusted_only_for_operator_configured_origin() {
|
||||
let op = "https://icap.mynode.example";
|
||||
// Node advertises the operator's own origin → talk there, key allowed.
|
||||
let (url, key_trusted) =
|
||||
resolve_solver_url(Some("https://icap.mynode.example/v1"), Some(op));
|
||||
assert_eq!(url, "https://icap.mynode.example/v1");
|
||||
assert!(key_trusted);
|
||||
|
||||
// Node advertises an attacker origin while an operator is configured →
|
||||
// ignore the advert, fall back to the operator origin, key stays with it.
|
||||
let (url, key_trusted) = resolve_solver_url(Some("https://evil.example"), Some(op));
|
||||
assert_eq!(url, op);
|
||||
assert!(key_trusted);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_advert_uses_operator_or_default() {
|
||||
let op = "https://icap.mynode.example";
|
||||
assert_eq!(resolve_solver_url(None, Some(op)), (op.to_string(), true));
|
||||
assert_eq!(
|
||||
resolve_solver_url(None, None),
|
||||
(DEFAULT_URL.to_string(), false)
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn non_https_operator_is_not_trusted() {
|
||||
// A misconfigured plaintext operator URL is not a valid key destination.
|
||||
let (url, key_trusted) = resolve_solver_url(None, Some("http://icap.mynode.example"));
|
||||
assert_eq!(url, DEFAULT_URL);
|
||||
assert!(!key_trusted);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_insecure_advertised_url_on_different_port() {
|
||||
// With GITLAWB_ICAPTCHA_INSECURE=1, two loopback URLs on different
|
||||
// ports must be treated as distinct origins so a hostile node cannot
|
||||
// redirect the bearer key to a different listener on localhost.
|
||||
let _env = InsecureEnv::new();
|
||||
|
||||
let op = "http://localhost:3000";
|
||||
let (url, key_trusted) = resolve_solver_url(Some("http://localhost:9000"), Some(op));
|
||||
assert_eq!(
|
||||
url, op,
|
||||
"must fall back to operator origin, not use different port"
|
||||
);
|
||||
assert!(key_trusted, "key stays trusted with operator origin");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn new_withholds_key_from_untrusted_origin_but_attaches_for_operator() {
|
||||
let guard = ICAPTCHA_ENV_LOCK.lock().unwrap();
|
||||
let prev_key = std::env::var_os("GITLAWB_ICAPTCHA_API_KEY");
|
||||
let prev_op = std::env::var_os("GITLAWB_ICAPTCHA_URL");
|
||||
std::env::set_var("GITLAWB_ICAPTCHA_API_KEY", "secret-bearer");
|
||||
|
||||
// Arm 1: No operator configured, node advertises an attacker origin.
|
||||
// The key has no trusted destination; the advert is rejected.
|
||||
std::env::remove_var("GITLAWB_ICAPTCHA_URL");
|
||||
let untrusted =
|
||||
IcaptchaCfg::new("did:key:zTEST", Some("https://evil.example".into()), None);
|
||||
|
||||
// Arm 1b: No operator configured, no URL advertised. The fallback goes
|
||||
// to the default public origin, and with no operator to trust, the key
|
||||
// must not ride.
|
||||
let no_operator_no_advert = IcaptchaCfg::new("did:key:zTEST", None, None);
|
||||
|
||||
// Arm 2: Operator origin configured and advertised — key attached.
|
||||
std::env::set_var("GITLAWB_ICAPTCHA_URL", "https://icap.mynode.example");
|
||||
let operator_match = IcaptchaCfg::new(
|
||||
"did:key:zTEST",
|
||||
Some("https://icap.mynode.example/v1".into()),
|
||||
None,
|
||||
);
|
||||
|
||||
// Arm 3: Operator configured, default host advertised. The default host
|
||||
// is allowlisted and selected, but its origin differs from the
|
||||
// operator's, so key must not ride.
|
||||
let default_advert = IcaptchaCfg::new(
|
||||
"did:key:zTEST",
|
||||
Some("https://icaptcha.gitlawb.com/v2".into()),
|
||||
None,
|
||||
);
|
||||
|
||||
// Arm 4: Operator configured, no URL advertised (the node sent only
|
||||
// x-icaptcha-level, not x-icaptcha-url). resolve_solver_url falls back
|
||||
// to the operator origin and marks the key trusted. This is the common
|
||||
// API-key deployment path — a regression that additionally required
|
||||
// url.is_some() for key attachment would leave all current tests green
|
||||
// but make these fallback challenge/answer requests omit Authorization
|
||||
// and fail against the protected operator service.
|
||||
let operator_fallback = IcaptchaCfg::new("did:key:zTEST", None, Some(3));
|
||||
|
||||
// Arm 5: Operator configured, node advertises an attacker origin.
|
||||
// The advert is rejected and the solver falls back to the operator's
|
||||
// own origin, which keeps the key trusted — this is the exfiltration
|
||||
// scenario the test name describes (withhold key from *untrusted*
|
||||
// origin, not from the operator's fallback).
|
||||
let operator_hostile_advert =
|
||||
IcaptchaCfg::new("did:key:zTEST", Some("https://evil.example".into()), None);
|
||||
|
||||
// Arm 6: Operator configured, same host but different port.
|
||||
// origin_key includes the port, so :8443 must not match the
|
||||
// operator origin at the default :443 — the advert is rejected
|
||||
// and the solver falls back to the operator origin.
|
||||
let operator_diff_port = IcaptchaCfg::new(
|
||||
"did:key:zTEST",
|
||||
Some("https://icap.mynode.example:8443/evil".into()),
|
||||
None,
|
||||
);
|
||||
|
||||
// Restore env and release the lock BEFORE asserting, so a failing
|
||||
// assertion can't poison the shared lock or cascade into a sibling.
|
||||
match prev_key {
|
||||
Some(v) => std::env::set_var("GITLAWB_ICAPTCHA_API_KEY", v),
|
||||
None => std::env::remove_var("GITLAWB_ICAPTCHA_API_KEY"),
|
||||
}
|
||||
match prev_op {
|
||||
Some(v) => std::env::set_var("GITLAWB_ICAPTCHA_URL", v),
|
||||
None => std::env::remove_var("GITLAWB_ICAPTCHA_URL"),
|
||||
}
|
||||
drop(guard);
|
||||
|
||||
let mut failures: Vec<String> = Vec::new();
|
||||
|
||||
if untrusted.api_key.is_some() {
|
||||
failures.push(format!(
|
||||
"arm 1 (no operator, attacker advert): expected api_key=None, got {:?}",
|
||||
untrusted.api_key
|
||||
));
|
||||
}
|
||||
if untrusted.url != DEFAULT_URL {
|
||||
failures.push(format!(
|
||||
"arm 1 (no operator, attacker advert): expected url={DEFAULT_URL}, got {}",
|
||||
untrusted.url
|
||||
));
|
||||
}
|
||||
|
||||
if no_operator_no_advert.api_key.is_some() {
|
||||
failures.push(format!(
|
||||
"arm 1b (no operator, no advert): expected api_key=None, got {:?}",
|
||||
no_operator_no_advert.api_key
|
||||
));
|
||||
}
|
||||
if no_operator_no_advert.url != DEFAULT_URL {
|
||||
failures.push(format!(
|
||||
"arm 1b (no operator, no advert): expected url={DEFAULT_URL}, got {}",
|
||||
no_operator_no_advert.url
|
||||
));
|
||||
}
|
||||
|
||||
if operator_match.api_key.as_deref() != Some("secret-bearer") {
|
||||
failures.push(format!(
|
||||
"arm 2 (operator match): expected api_key=Some(\"secret-bearer\"), got {:?}",
|
||||
operator_match.api_key
|
||||
));
|
||||
}
|
||||
if operator_match.url != "https://icap.mynode.example/v1" {
|
||||
failures.push(format!(
|
||||
"arm 2 (operator match): expected url=https://icap.mynode.example/v1, got {}",
|
||||
operator_match.url
|
||||
));
|
||||
}
|
||||
|
||||
if default_advert.api_key.is_some() {
|
||||
failures.push(format!(
|
||||
"arm 3 (operator + default advert): expected api_key=None, got {:?}",
|
||||
default_advert.api_key
|
||||
));
|
||||
}
|
||||
if default_advert.url != "https://icaptcha.gitlawb.com/v2" {
|
||||
failures.push(format!(
|
||||
"arm 3 (operator + default advert): expected url=https://icaptcha.gitlawb.com/v2, got {}",
|
||||
default_advert.url
|
||||
));
|
||||
}
|
||||
|
||||
if operator_fallback.api_key.as_deref() != Some("secret-bearer") {
|
||||
failures.push(format!(
|
||||
"arm 4 (operator fallback, no advert): expected api_key=Some(\"secret-bearer\"), got {:?}",
|
||||
operator_fallback.api_key
|
||||
));
|
||||
}
|
||||
if operator_fallback.url != "https://icap.mynode.example" {
|
||||
failures.push(format!(
|
||||
"arm 4 (operator fallback, no advert): expected url=https://icap.mynode.example, got {}",
|
||||
operator_fallback.url
|
||||
));
|
||||
}
|
||||
|
||||
if operator_hostile_advert.api_key.as_deref() != Some("secret-bearer") {
|
||||
failures.push(format!(
|
||||
"arm 5 (operator + hostile advert): expected api_key=Some(\"secret-bearer\"), got {:?}",
|
||||
operator_hostile_advert.api_key
|
||||
));
|
||||
}
|
||||
if operator_hostile_advert.url != "https://icap.mynode.example" {
|
||||
failures.push(format!(
|
||||
"arm 5 (operator + hostile advert): expected url=https://icap.mynode.example, got {}",
|
||||
operator_hostile_advert.url
|
||||
));
|
||||
}
|
||||
|
||||
if operator_diff_port.api_key.as_deref() != Some("secret-bearer") {
|
||||
failures.push(format!(
|
||||
"arm 6 (operator + different port advert): expected api_key=Some(\"secret-bearer\"), got {:?}",
|
||||
operator_diff_port.api_key
|
||||
));
|
||||
}
|
||||
if operator_diff_port.url != "https://icap.mynode.example" {
|
||||
failures.push(format!(
|
||||
"arm 6 (operator + different port advert): expected url=https://icap.mynode.example, got {}",
|
||||
operator_diff_port.url
|
||||
));
|
||||
}
|
||||
|
||||
assert!(failures.is_empty(), "\n{}", failures.join("\n"));
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,130 @@
|
||||
//! Proof-of-work solver for the iCaptcha answer step.
|
||||
//!
|
||||
//! iCaptcha requires a small proof-of-work with each answer so that minting a
|
||||
//! proof costs CPU — a per-proof cost a distributed abuser cannot dodge by
|
||||
//! rotating IPs. The work is bound to the per-challenge id: find a `nonce` such
|
||||
//! that `sha256("{challenge}:{nonce}")` has at least `difficulty` leading zero
|
||||
//! bits. This mirrors `icaptcha/src/pow.ts`.
|
||||
//!
|
||||
//! At the service default (~20 bits) this is well under a second for a single
|
||||
//! solve; we still cap the search so a hostile/misconfigured difficulty can
|
||||
//! never hang the client.
|
||||
|
||||
use sha2::{Digest, Sha256};
|
||||
|
||||
/// PoW parameters advertised by the service in a challenge (mirrors the
|
||||
/// service's `PowChallenge`).
|
||||
#[derive(Debug, Clone, serde::Deserialize)]
|
||||
pub struct PowChallenge {
|
||||
/// Only `sha256-leading-zero-bits` is understood; other algorithms are
|
||||
/// rejected by [`solve`] rather than silently mis-solved.
|
||||
pub algorithm: String,
|
||||
/// The string to hash against (the per-challenge id).
|
||||
pub challenge: String,
|
||||
/// Required leading zero bits.
|
||||
pub difficulty: u32,
|
||||
}
|
||||
|
||||
/// Hard cap on nonce search iterations. 2^26 ≈ 67M keeps a ~20-bit target (~1M
|
||||
/// expected hashes) comfortably solvable while bounding worst-case work if the
|
||||
/// service ever advertises an unexpectedly high difficulty.
|
||||
const MAX_ITERS: u64 = 1 << 26;
|
||||
|
||||
const ALGORITHM: &str = "sha256-leading-zero-bits";
|
||||
|
||||
/// Leading zero bits of a byte slice.
|
||||
fn leading_zero_bits(bytes: &[u8]) -> u32 {
|
||||
let mut bits = 0;
|
||||
for &b in bytes {
|
||||
if b == 0 {
|
||||
bits += 8;
|
||||
} else {
|
||||
bits += b.leading_zeros();
|
||||
break;
|
||||
}
|
||||
}
|
||||
bits
|
||||
}
|
||||
|
||||
/// sha256(`{challenge}:{nonce}`).
|
||||
fn pow_hash(challenge: &str, nonce: &str) -> [u8; 32] {
|
||||
let mut hasher = Sha256::new();
|
||||
hasher.update(challenge.as_bytes());
|
||||
hasher.update(b":");
|
||||
hasher.update(nonce.as_bytes());
|
||||
hasher.finalize().into()
|
||||
}
|
||||
|
||||
/// Solve the PoW, returning a nonce whose hash meets the difficulty. Returns
|
||||
/// `None` for an unknown algorithm or if no nonce is found within the cap (a
|
||||
/// difficulty far above what the service uses in practice).
|
||||
pub fn solve(pow: &PowChallenge) -> Option<String> {
|
||||
if pow.algorithm != ALGORITHM {
|
||||
tracing::warn!(algorithm = %pow.algorithm, "unknown iCaptcha PoW algorithm; cannot solve");
|
||||
return None;
|
||||
}
|
||||
if pow.difficulty == 0 {
|
||||
return Some("0".to_string());
|
||||
}
|
||||
for i in 0..MAX_ITERS {
|
||||
let nonce = format!("{i:x}");
|
||||
if leading_zero_bits(&pow_hash(&pow.challenge, &nonce)) >= pow.difficulty {
|
||||
return Some(nonce);
|
||||
}
|
||||
}
|
||||
tracing::warn!(
|
||||
difficulty = pow.difficulty,
|
||||
max_iters = MAX_ITERS,
|
||||
"iCaptcha PoW not solved within iteration cap"
|
||||
);
|
||||
None
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn pow(challenge: &str, difficulty: u32) -> PowChallenge {
|
||||
PowChallenge {
|
||||
algorithm: ALGORITHM.to_string(),
|
||||
challenge: challenge.to_string(),
|
||||
difficulty,
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn leading_zero_bits_counts_across_bytes() {
|
||||
assert_eq!(leading_zero_bits(&[0xff]), 0);
|
||||
assert_eq!(leading_zero_bits(&[0x7f]), 1);
|
||||
assert_eq!(leading_zero_bits(&[0x01]), 7);
|
||||
assert_eq!(leading_zero_bits(&[0x00, 0xff]), 8);
|
||||
assert_eq!(leading_zero_bits(&[0x00, 0x01]), 15);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn solves_and_the_solution_verifies() {
|
||||
let p = pow("challenge-abc", 12);
|
||||
let nonce = solve(&p).expect("should solve a 12-bit target");
|
||||
assert!(leading_zero_bits(&pow_hash(&p.challenge, &nonce)) >= 12);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn solution_is_bound_to_the_challenge() {
|
||||
// A nonce solving one challenge should (overwhelmingly) not solve another
|
||||
// at the same difficulty — the work is challenge-specific.
|
||||
let nonce = solve(&pow("challenge-A", 12)).unwrap();
|
||||
assert!(leading_zero_bits(&pow_hash("challenge-B", &nonce)) < 12);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_unknown_algorithm() {
|
||||
let mut p = pow("c", 8);
|
||||
p.algorithm = "scrypt".to_string();
|
||||
assert!(solve(&p).is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn zero_difficulty_is_trivially_solved() {
|
||||
assert_eq!(solve(&pow("c", 0)).as_deref(), Some("0"));
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,270 @@
|
||||
//! Deterministic solvers for the computational iCaptcha challenge types.
|
||||
//!
|
||||
//! Prompt/answer formats mirror the iCaptcha service generators
|
||||
//! (`icaptcha/src/generators/{arithmetic,algebra,sequence}.ts`). The service
|
||||
//! grades numerics by value (`Number(a) === Number(b)`), so returning the plain
|
||||
//! integer string is sufficient. Anagram/logic (need a dictionary/parser) and
|
||||
//! the LLM types are intentionally NOT solved here — the client requests only
|
||||
//! these three types and falls back to a hook/interactive prompt otherwise.
|
||||
|
||||
/// Solve a challenge of the given `type` from its prompt. Returns `None` for
|
||||
/// types we don't solve locally or when the prompt can't be parsed.
|
||||
pub fn solve(challenge_type: &str, prompt: &str) -> Option<String> {
|
||||
match challenge_type {
|
||||
"arithmetic" => solve_arithmetic(prompt).map(|n| n.to_string()),
|
||||
"algebra" => solve_algebra(prompt).map(|n| n.to_string()),
|
||||
"sequence" => solve_sequence(prompt).map(|n| n.to_string()),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
/// `What is 12 + 7 - 3?` -> evaluate the additive chain left to right.
|
||||
fn solve_arithmetic(prompt: &str) -> Option<i64> {
|
||||
let expr = prompt
|
||||
.trim()
|
||||
.strip_prefix("What is ")?
|
||||
.trim_end_matches('?')
|
||||
.trim();
|
||||
let mut tokens = expr.split_whitespace();
|
||||
let mut acc: i64 = tokens.next()?.parse().ok()?;
|
||||
while let Some(op) = tokens.next() {
|
||||
let n: i64 = tokens.next()?.parse().ok()?;
|
||||
match op {
|
||||
"+" => acc += n,
|
||||
"-" => acc -= n,
|
||||
_ => return None,
|
||||
}
|
||||
}
|
||||
Some(acc)
|
||||
}
|
||||
|
||||
/// `Solve for x: 3x + 4 = 19` (and the `=`-both-sides and `a(x + b)` variants).
|
||||
/// Parses each side into `coeff*x + const`, then x = (cR - cL) / (aL - aR).
|
||||
fn solve_algebra(prompt: &str) -> Option<i64> {
|
||||
let eq = prompt.trim().strip_prefix("Solve for x:")?.trim();
|
||||
let (lhs, rhs) = eq.split_once('=')?;
|
||||
let (al, cl) = parse_linear(lhs.trim())?;
|
||||
let (ar, cr) = parse_linear(rhs.trim())?;
|
||||
let denom = al - ar;
|
||||
if denom == 0 {
|
||||
return None;
|
||||
}
|
||||
let num = cr - cl;
|
||||
if num % denom != 0 {
|
||||
return None;
|
||||
}
|
||||
Some(num / denom)
|
||||
}
|
||||
|
||||
/// Parse a linear expression in `x` into `(coeff_of_x, constant)`.
|
||||
/// Handles `Nx`, `x`, integer constants, and a single `N(x ± M)` product,
|
||||
/// with `+`/`-` separators (the formats the generator emits).
|
||||
fn parse_linear(s: &str) -> Option<(i64, i64)> {
|
||||
let s = s.trim();
|
||||
// Parenthesized product: a(x ± b) -> coeff a, const a*(±b).
|
||||
if let Some(open) = s.find('(') {
|
||||
let a: i64 = s[..open].trim().parse().ok()?;
|
||||
let close = s.find(')')?;
|
||||
let inner = &s[open + 1..close]; // "x + 4" / "x - 4"
|
||||
let mut it = inner.split_whitespace();
|
||||
if it.next()? != "x" {
|
||||
return None;
|
||||
}
|
||||
let (coeff_inner, const_inner) = match it.next() {
|
||||
None => (1, 0),
|
||||
Some(op) => {
|
||||
let m: i64 = it.next()?.parse().ok()?;
|
||||
match op {
|
||||
"+" => (1, m),
|
||||
"-" => (1, -m),
|
||||
_ => return None,
|
||||
}
|
||||
}
|
||||
};
|
||||
return Some((a * coeff_inner, a * const_inner));
|
||||
}
|
||||
|
||||
// Sum of `±`-separated terms.
|
||||
let mut coeff = 0i64;
|
||||
let mut konst = 0i64;
|
||||
let mut sign = 1i64;
|
||||
for tok in s.split_whitespace() {
|
||||
match tok {
|
||||
"+" => sign = 1,
|
||||
"-" => sign = -1,
|
||||
t => {
|
||||
if let Some(cpart) = t.strip_suffix('x') {
|
||||
let c: i64 = match cpart {
|
||||
"" | "+" => 1,
|
||||
"-" => -1,
|
||||
_ => cpart.parse().ok()?,
|
||||
};
|
||||
coeff += sign * c;
|
||||
} else {
|
||||
let n: i64 = t.parse().ok()?;
|
||||
konst += sign * n;
|
||||
}
|
||||
sign = 1;
|
||||
}
|
||||
}
|
||||
}
|
||||
Some((coeff, konst))
|
||||
}
|
||||
|
||||
/// `What is the next number in this sequence? 2, 4, 6, 8, 10, ?`
|
||||
fn solve_sequence(prompt: &str) -> Option<i64> {
|
||||
let tail = prompt.split_once("sequence?")?.1;
|
||||
let nums: Vec<i64> = tail
|
||||
.split(',')
|
||||
.filter_map(|t| t.trim().parse::<i64>().ok())
|
||||
.collect();
|
||||
if nums.len() < 3 {
|
||||
return None;
|
||||
}
|
||||
next_in_sequence(&nums)
|
||||
}
|
||||
|
||||
fn next_in_sequence(n: &[i64]) -> Option<i64> {
|
||||
let last = *n.last()?;
|
||||
|
||||
// Arithmetic: constant first difference.
|
||||
let d = n[1] - n[0];
|
||||
if n.windows(2).all(|w| w[1] - w[0] == d) {
|
||||
return Some(last + d);
|
||||
}
|
||||
|
||||
// Geometric: constant integer ratio.
|
||||
if n.iter().all(|&v| v != 0) && n[0] != 0 && n[1] % n[0] == 0 {
|
||||
let r = n[1] / n[0];
|
||||
if r != 0 && n.windows(2).all(|w| w[1] == w[0] * r) {
|
||||
return Some(last * r);
|
||||
}
|
||||
}
|
||||
|
||||
// Fibonacci-like: each term is the sum of the two before it.
|
||||
if n.len() >= 3 && (2..n.len()).all(|i| n[i] == n[i - 1] + n[i - 2]) {
|
||||
return Some(n[n.len() - 1] + n[n.len() - 2]);
|
||||
}
|
||||
|
||||
// Squares: all perfect squares with consecutive roots.
|
||||
let roots: Option<Vec<i64>> = n.iter().map(|&v| isqrt_exact(v)).collect();
|
||||
if let Some(roots) = roots {
|
||||
if roots.windows(2).all(|w| w[1] == w[0] + 1) {
|
||||
let nr = roots[roots.len() - 1] + 1;
|
||||
return Some(nr * nr);
|
||||
}
|
||||
}
|
||||
|
||||
// Alternating sign over an arithmetic magnitude (generator starts positive).
|
||||
let signs_alternate = n
|
||||
.iter()
|
||||
.enumerate()
|
||||
.all(|(i, &v)| if i % 2 == 0 { v >= 0 } else { v < 0 });
|
||||
let mags: Vec<i64> = n.iter().map(|v| v.abs()).collect();
|
||||
let md = mags[1] - mags[0];
|
||||
if signs_alternate && mags.windows(2).all(|w| w[1] - w[0] == md) {
|
||||
let next_mag = mags[mags.len() - 1] + md;
|
||||
let next_sign = if last >= 0 { -1 } else { 1 };
|
||||
return Some(next_sign * next_mag);
|
||||
}
|
||||
|
||||
None
|
||||
}
|
||||
|
||||
/// Exact integer square root, or `None` if `v` isn't a perfect square.
|
||||
fn isqrt_exact(v: i64) -> Option<i64> {
|
||||
if v < 0 {
|
||||
return None;
|
||||
}
|
||||
let r = (v as f64).sqrt().round() as i64;
|
||||
[r - 1, r, r + 1]
|
||||
.into_iter()
|
||||
.find(|&cand| cand >= 0 && cand * cand == v)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn arithmetic_chains() {
|
||||
assert_eq!(
|
||||
solve("arithmetic", "What is 12 + 7 - 3?").as_deref(),
|
||||
Some("16")
|
||||
);
|
||||
assert_eq!(solve("arithmetic", "What is 5?").as_deref(), Some("5"));
|
||||
assert_eq!(
|
||||
solve("arithmetic", "What is 100 - 40 - 35 + 2?").as_deref(),
|
||||
Some("27")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn algebra_linear() {
|
||||
assert_eq!(
|
||||
solve("algebra", "Solve for x: 3x + 4 = 19").as_deref(),
|
||||
Some("5")
|
||||
);
|
||||
assert_eq!(
|
||||
solve("algebra", "Solve for x: 5x - 8 = 12").as_deref(),
|
||||
Some("4")
|
||||
);
|
||||
// both sides: 2x + 16 = 5x - 8 -> 3x = 24 -> x=8
|
||||
assert_eq!(
|
||||
solve("algebra", "Solve for x: 2x + 16 = 5x - 8").as_deref(),
|
||||
Some("8")
|
||||
);
|
||||
// parenthesized: 3(x - 4) = 9 -> x-4=3 -> x=7
|
||||
assert_eq!(
|
||||
solve("algebra", "Solve for x: 3(x - 4) = 9").as_deref(),
|
||||
Some("7")
|
||||
);
|
||||
// negative solution: 2x + 10 = 4 -> x=-3
|
||||
assert_eq!(
|
||||
solve("algebra", "Solve for x: 2x + 10 = 4").as_deref(),
|
||||
Some("-3")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn sequence_patterns() {
|
||||
assert_eq!(
|
||||
solve(
|
||||
"sequence",
|
||||
"What is the next number in this sequence? 2, 4, 6, 8, 10, ?"
|
||||
)
|
||||
.as_deref(),
|
||||
Some("12")
|
||||
);
|
||||
assert_eq!(
|
||||
solve(
|
||||
"sequence",
|
||||
"What is the next number in this sequence? 3, 6, 12, 24, 48, ?"
|
||||
)
|
||||
.as_deref(),
|
||||
Some("96")
|
||||
);
|
||||
assert_eq!(
|
||||
solve(
|
||||
"sequence",
|
||||
"What is the next number in this sequence? 1, 4, 9, 16, 25, ?"
|
||||
)
|
||||
.as_deref(),
|
||||
Some("36")
|
||||
);
|
||||
assert_eq!(
|
||||
solve(
|
||||
"sequence",
|
||||
"What is the next number in this sequence? 1, 1, 2, 3, 5, ?"
|
||||
)
|
||||
.as_deref(),
|
||||
Some("8")
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn unsupported_types_return_none() {
|
||||
assert_eq!(solve("anagram", "Unscramble: tca"), None);
|
||||
assert_eq!(solve("riddle", "What has keys but no locks?"), None);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,94 @@
|
||||
//! INV-19 guard: the icaptcha flow must actually call the service (consume the
|
||||
//! mock), not short-circuit or make a live call. If a future change let
|
||||
//! `obtain_proof` skip the network (e.g. a stray `cfg(test)` relaxation, which
|
||||
//! INV-19/INV-20 warn is inert across crates), the `.assert()` calls below go
|
||||
//! RED because the mocked endpoints were never hit.
|
||||
//!
|
||||
//! The mock-consumed assertions alone only prove the mock was hit; they cannot
|
||||
//! see a request that ALSO leaks the DID / answer / API key to `DEFAULT_URL` or
|
||||
//! any other origin (a different host the mock never observes). To make the
|
||||
//! "no live call" half of the guard load-bearing, the test blackholes every
|
||||
//! non-loopback destination: `NO_PROXY` lets the loopback mock through while a
|
||||
//! closed proxy port routes any other host nowhere, so the client contacting
|
||||
//! anything but the injected mock fails the request instead of silently
|
||||
//! succeeding. Point `cfg.url` at `DEFAULT_URL` and this test goes RED.
|
||||
//!
|
||||
//! `ALL_PROXY` alone is NOT enough: reqwest honors the scheme-specific
|
||||
//! `HTTPS_PROXY` / `https_proxy` (and the http equivalents) OVER `ALL_PROXY`, so
|
||||
//! a runner with a working `HTTPS_PROXY` in its environment would route an https
|
||||
//! leak to `DEFAULT_URL` (which is https) through that proxy while the loopback
|
||||
//! mock is still consumed and this test stayed green. So we blackhole the
|
||||
//! scheme-specific variables too. No restore is needed: this file has a single
|
||||
//! `#[test]`, so it runs in its own process and the override never races a
|
||||
//! sibling test.
|
||||
|
||||
use icaptcha_client::{obtain_proof, Challenge, IcaptchaCfg};
|
||||
|
||||
#[test]
|
||||
fn obtain_proof_consumes_the_mocked_service_and_makes_no_live_call() {
|
||||
// Blackhole every non-loopback origin: the loopback mock bypasses the proxy
|
||||
// (NO_PROXY); any other host is forced through a closed port and fails.
|
||||
// reqwest reads these at client-build time, and obtain_proof builds its
|
||||
// client fresh, so this bounds the transport for the whole flow.
|
||||
//
|
||||
// Set the scheme-specific vars too (both cases), not just ALL_PROXY: reqwest
|
||||
// gives HTTPS_PROXY/https_proxy precedence over ALL_PROXY for https URLs, so
|
||||
// an ALL_PROXY-only blackhole leaves an https leak to DEFAULT_URL open on a
|
||||
// runner whose environment already has a working HTTPS_PROXY.
|
||||
let blackhole = "http://127.0.0.1:1";
|
||||
std::env::set_var("NO_PROXY", "127.0.0.1,localhost");
|
||||
std::env::set_var("no_proxy", "127.0.0.1,localhost");
|
||||
for var in [
|
||||
"ALL_PROXY",
|
||||
"all_proxy",
|
||||
"HTTPS_PROXY",
|
||||
"https_proxy",
|
||||
"HTTP_PROXY",
|
||||
"http_proxy",
|
||||
] {
|
||||
std::env::set_var(var, blackhole);
|
||||
}
|
||||
|
||||
let mut server = mockito::Server::new();
|
||||
|
||||
// The two endpoints the flow hits, each expected exactly once.
|
||||
let challenge = server
|
||||
.mock("POST", "/v1/challenge")
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(
|
||||
r#"{"challengeId":"c1","type":"anagram","difficulty":1,"prompt":"listen","token":"tok-1"}"#,
|
||||
)
|
||||
.expect(1)
|
||||
.create();
|
||||
|
||||
let answer = server
|
||||
.mock("POST", "/v1/answer")
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(r#"{"status":"passed","proof":"PROOF-XYZ"}"#)
|
||||
.expect(1)
|
||||
.create();
|
||||
|
||||
let cfg = IcaptchaCfg {
|
||||
url: server.url(),
|
||||
did: "did:key:zTEST".to_string(),
|
||||
level: 1,
|
||||
api_key: None,
|
||||
};
|
||||
|
||||
// "anagram" is not a built-in solvable type, so the flow consults this
|
||||
// solver callback. The answer body itself does not matter: the mocked
|
||||
// /v1/answer returns "passed" regardless of what is submitted.
|
||||
let solve = |_c: &Challenge| Some("silent".to_string());
|
||||
let solver: &dyn Fn(&Challenge) -> Option<String> = &solve;
|
||||
|
||||
let proof = obtain_proof(&cfg, Some(solver))
|
||||
.expect("obtain_proof should complete against the mocked service");
|
||||
assert_eq!(proof, "PROOF-XYZ");
|
||||
|
||||
// INV-19: prove the client actually called the mocked endpoints. Had it made
|
||||
// a live call or skipped the network, these would fail (mock never hit).
|
||||
challenge.assert();
|
||||
answer.assert();
|
||||
}
|
||||
@@ -120,7 +120,7 @@ Positive:
|
||||
Risks:
|
||||
|
||||
- Many commands default to the public node; `git-remote-gitlawb` defaults to localhost. This split should be called out in README examples.
|
||||
- `gl sync trigger` signs the request when a local identity is available and falls back to the legacy unsigned request for live compatibility.
|
||||
- `gl sync trigger` requires a local identity and always sends a signed request; the `/api/v1/sync/trigger` route rejects unsigned calls, so the command fails locally when no identity is configured.
|
||||
- Several CLI commands parse dynamic JSON responses permissively; good for compatibility, but error messages can hide response-shape regressions.
|
||||
|
||||
## CI and release readiness
|
||||
|
||||
@@ -58,6 +58,16 @@ services:
|
||||
GITLAWB_P2P_PORT: "${p2p_port}"
|
||||
GITLAWB_REPOS_DIR: /data/repos
|
||||
GITLAWB_KEY: /data/keys/identity.pem
|
||||
# Only trust X-Forwarded-For when the Caddy sidecar above is actually
|
||||
# deployed (domain_name != ""). Caddy appends the real client as the
|
||||
# rightmost hop, letting the push rate limiter key on the true client IP
|
||||
# rather than Caddy's container address. Without Caddy, this header is
|
||||
# fully client-controlled and must not be trusted.
|
||||
GITLAWB_TRUSTED_PROXY: "${domain_name != "" ? "x-forwarded-for" : ""}"
|
||||
# iCaptcha proof-of-intelligence gate (spam protection on create/fork/register)
|
||||
ICAPTCHA_MODE: ${icaptcha_mode}
|
||||
ICAPTCHA_PUBKEY: ${icaptcha_pubkey}
|
||||
ICAPTCHA_REQUIRED_LEVEL: "${icaptcha_required_level}"
|
||||
GITLAWB_PUBLIC_URL: $${GITLAWB_PUBLIC_URL}
|
||||
GITLAWB_BOOTSTRAP_PEERS: $${GITLAWB_BOOTSTRAP_PEERS}
|
||||
GITLAWB_AUTO_SYNC: $${GITLAWB_AUTO_SYNC}
|
||||
|
||||
+13
-10
@@ -290,16 +290,19 @@ locals {
|
||||
)
|
||||
|
||||
compose_yaml = templatefile("${path.module}/compose.yaml.tftpl", {
|
||||
image_repo = local.image_repo
|
||||
image_tag = var.image_tag
|
||||
domain_name = var.domain_name
|
||||
db_host = var.use_rds ? aws_db_instance.node[0].address : ""
|
||||
gitlawb_port = var.gitlawb_port
|
||||
p2p_port = var.gitlawb_p2p_port
|
||||
metrics_port = var.metrics_port
|
||||
expose_metrics = local.expose_metrics
|
||||
pg_user = var.postgres_user
|
||||
pg_db = var.postgres_db
|
||||
image_repo = local.image_repo
|
||||
image_tag = var.image_tag
|
||||
domain_name = var.domain_name
|
||||
db_host = var.use_rds ? aws_db_instance.node[0].address : ""
|
||||
gitlawb_port = var.gitlawb_port
|
||||
p2p_port = var.gitlawb_p2p_port
|
||||
metrics_port = var.metrics_port
|
||||
expose_metrics = local.expose_metrics
|
||||
pg_user = var.postgres_user
|
||||
pg_db = var.postgres_db
|
||||
icaptcha_mode = var.icaptcha_mode
|
||||
icaptcha_pubkey = var.icaptcha_pubkey
|
||||
icaptcha_required_level = var.icaptcha_required_level
|
||||
})
|
||||
|
||||
user_data = templatefile("${path.module}/user-data.sh.tftpl", {
|
||||
|
||||
@@ -81,6 +81,28 @@ variable "image_tag" {
|
||||
default = "latest"
|
||||
}
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# iCaptcha proof-of-intelligence gate (spam protection on writes)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
variable "icaptcha_mode" {
|
||||
description = "iCaptcha gate mode: off | shadow | enforce. The live gitlawb network enforces."
|
||||
type = string
|
||||
default = "enforce"
|
||||
}
|
||||
|
||||
variable "icaptcha_pubkey" {
|
||||
description = "base64url Ed25519 public key of the iCaptcha service, pinned so startup doesn't depend on fetching it. This is the live icaptcha.gitlawb.com key."
|
||||
type = string
|
||||
default = "xjyPNqIbvc9U-kwXW6u9mDqRJ7E2UUMOaJdUWhpEXq8"
|
||||
}
|
||||
|
||||
variable "icaptcha_required_level" {
|
||||
description = "Minimum iCaptcha proof level required to pass the gate."
|
||||
type = number
|
||||
default = 3
|
||||
}
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Networking / ingress
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@@ -16,6 +16,10 @@ primary_region = "iad"
|
||||
GITLAWB_BOOTSTRAP_PEERS = "https://node.gitlawb.com,https://node2.gitlawb.com,https://node3.gitlawb.com"
|
||||
GITLAWB_AUTO_SYNC = "true"
|
||||
GITLAWB_MAX_PACK_BYTES = "524288000"
|
||||
# On Fly: the edge sets Fly-Client-IP (overwriting any client-supplied value),
|
||||
# so the push rate limiter keys on the real client. Without this the limiter
|
||||
# would fall back to the socket peer (Fly's proxy) and over-throttle.
|
||||
GITLAWB_TRUSTED_PROXY = "fly"
|
||||
|
||||
[http_service]
|
||||
internal_port = 7545
|
||||
@@ -34,6 +38,16 @@ primary_region = "iad"
|
||||
# slots (hard_limit) — root factor in the 2026-06-12 prod outage
|
||||
idle_timeout = 120
|
||||
|
||||
[[http_service.checks]]
|
||||
# Gate routing (and deploys) on real readiness: /ready probes the DB, so a
|
||||
# node stuck retrying a dead or misconfigured database is never routed to,
|
||||
# and a deploy with a bad DATABASE_URL fails visibly instead of going green.
|
||||
interval = "15s"
|
||||
timeout = "5s"
|
||||
grace_period = "75s"
|
||||
method = "GET"
|
||||
path = "/ready"
|
||||
|
||||
[[services]]
|
||||
protocol = "udp"
|
||||
internal_port = 7546
|
||||
|
||||
@@ -0,0 +1,65 @@
|
||||
# fly.toml app configuration file generated for gitlawb-node-2 on 2026-07-22T09:47:18+08:00
|
||||
#
|
||||
# See https://fly.io/docs/reference/configuration/ for information about how to use this file.
|
||||
#
|
||||
|
||||
app = 'gitlawb-node-2'
|
||||
primary_region = 'sjc'
|
||||
|
||||
[build]
|
||||
dockerfile = '../../Dockerfile'
|
||||
|
||||
[env]
|
||||
GITLAWB_AUTO_SYNC = 'true'
|
||||
GITLAWB_BOOTSTRAP_PEERS = 'https://node.gitlawb.com,https://node3.gitlawb.com'
|
||||
GITLAWB_HOST = '0.0.0.0'
|
||||
GITLAWB_KEY = '/data/keys/identity.pem'
|
||||
GITLAWB_MAX_PACK_BYTES = '524288000'
|
||||
GITLAWB_P2P_PORT = '7546'
|
||||
GITLAWB_PORT = '7545'
|
||||
GITLAWB_PUBLIC_URL = 'https://node2.gitlawb.com'
|
||||
GITLAWB_REPOS_DIR = '/data/repos'
|
||||
ICAPTCHA_MODE = 'enforce'
|
||||
ICAPTCHA_PUBKEY = 'xjyPNqIbvc9U-kwXW6u9mDqRJ7E2UUMOaJdUWhpEXq8'
|
||||
ICAPTCHA_REQUIRED_LEVEL = '3'
|
||||
|
||||
[[mounts]]
|
||||
source = 'gitlawb_data'
|
||||
destination = '/data'
|
||||
|
||||
[http_service]
|
||||
internal_port = 7545
|
||||
force_https = true
|
||||
auto_stop_machines = 'off'
|
||||
auto_start_machines = true
|
||||
min_machines_running = 1
|
||||
|
||||
[http_service.concurrency]
|
||||
type = 'connections'
|
||||
hard_limit = 500
|
||||
soft_limit = 400
|
||||
|
||||
[http_service.http_options]
|
||||
idle_timeout = 120
|
||||
|
||||
[[http_service.checks]]
|
||||
interval = '15s'
|
||||
timeout = '5s'
|
||||
grace_period = '30s'
|
||||
method = 'GET'
|
||||
path = '/ready'
|
||||
|
||||
[[services]]
|
||||
protocol = 'udp'
|
||||
internal_port = 7546
|
||||
|
||||
[[services.ports]]
|
||||
port = 7546
|
||||
|
||||
[[vm]]
|
||||
size = 'shared-cpu-1x'
|
||||
memory = '1024'
|
||||
|
||||
[[metrics]]
|
||||
port = 9091
|
||||
path = '/metrics'
|
||||
@@ -0,0 +1,65 @@
|
||||
# fly.toml app configuration file generated for gitlawb-node-3 on 2026-07-22T09:47:19+08:00
|
||||
#
|
||||
# See https://fly.io/docs/reference/configuration/ for information about how to use this file.
|
||||
#
|
||||
|
||||
app = 'gitlawb-node-3'
|
||||
primary_region = 'nrt'
|
||||
|
||||
[build]
|
||||
dockerfile = '../../Dockerfile'
|
||||
|
||||
[env]
|
||||
GITLAWB_AUTO_SYNC = 'true'
|
||||
GITLAWB_BOOTSTRAP_PEERS = 'https://node.gitlawb.com,https://node2.gitlawb.com'
|
||||
GITLAWB_HOST = '0.0.0.0'
|
||||
GITLAWB_KEY = '/data/keys/identity.pem'
|
||||
GITLAWB_MAX_PACK_BYTES = '524288000'
|
||||
GITLAWB_P2P_PORT = '7546'
|
||||
GITLAWB_PORT = '7545'
|
||||
GITLAWB_PUBLIC_URL = 'https://node3.gitlawb.com'
|
||||
GITLAWB_REPOS_DIR = '/data/repos'
|
||||
ICAPTCHA_MODE = 'enforce'
|
||||
ICAPTCHA_PUBKEY = 'xjyPNqIbvc9U-kwXW6u9mDqRJ7E2UUMOaJdUWhpEXq8'
|
||||
ICAPTCHA_REQUIRED_LEVEL = '3'
|
||||
|
||||
[[mounts]]
|
||||
source = 'gitlawb_data'
|
||||
destination = '/data'
|
||||
|
||||
[http_service]
|
||||
internal_port = 7545
|
||||
force_https = true
|
||||
auto_stop_machines = 'off'
|
||||
auto_start_machines = true
|
||||
min_machines_running = 1
|
||||
|
||||
[http_service.concurrency]
|
||||
type = 'connections'
|
||||
hard_limit = 500
|
||||
soft_limit = 400
|
||||
|
||||
[http_service.http_options]
|
||||
idle_timeout = 120
|
||||
|
||||
[[http_service.checks]]
|
||||
interval = '15s'
|
||||
timeout = '5s'
|
||||
grace_period = '30s'
|
||||
method = 'GET'
|
||||
path = '/ready'
|
||||
|
||||
[[services]]
|
||||
protocol = 'udp'
|
||||
internal_port = 7546
|
||||
|
||||
[[services.ports]]
|
||||
port = 7546
|
||||
|
||||
[[vm]]
|
||||
size = 'shared-cpu-1x'
|
||||
memory = '1024'
|
||||
|
||||
[[metrics]]
|
||||
port = 9091
|
||||
path = '/metrics'
|
||||
+14
@@ -193,5 +193,19 @@ else
|
||||
echo " gl quickstart"
|
||||
fi
|
||||
|
||||
# oh-my-zsh's default git plugin aliases gl='git pull', which silently shadows
|
||||
# the gl binary in every interactive zsh (aliases beat PATH). Detect the common
|
||||
# setup and say so now, at install time, instead of letting the first `gl`
|
||||
# print git's baffling "fatal: not a git repository".
|
||||
if [ -f "$HOME/.zshrc" ] && [ -d "$HOME/.oh-my-zsh/plugins/git" ] \
|
||||
&& grep -Eq '^[[:space:]]*plugins=\(([^)]*[[:space:]])?git([[:space:]][^)]*)?\)' "$HOME/.zshrc" \
|
||||
&& ! grep -Eq '^([^#]*[[:space:];&|])?unalias[[:space:]]+([^;&|#]*[[:space:]])?gl([[:space:]]|$)' "$HOME/.zshrc"; then
|
||||
echo ""
|
||||
echo "NOTE: oh-my-zsh's git plugin aliases gl='git pull', which will shadow"
|
||||
echo "the gl command in interactive shells. To use gl by name, run:"
|
||||
echo ""
|
||||
echo " echo 'unalias gl 2>/dev/null' >> ~/.zshrc && source ~/.zshrc"
|
||||
fi
|
||||
|
||||
echo ""
|
||||
echo "Docs: https://docs.gitlawb.com"
|
||||
@@ -46,7 +46,7 @@ build_darwin_arm64() {
|
||||
echo "==> Building darwin-arm64 (native cargo)..."
|
||||
cd "$ROOT"
|
||||
export PATH="$HOME/.cargo/bin:$PATH"
|
||||
cargo build --release -p gl -p git-remote-gitlawb
|
||||
cargo build --release --locked -p gl -p git-remote-gitlawb
|
||||
cp target/release/gl "$OUT/gl-darwin-arm64"
|
||||
cp target/release/git-remote-gitlawb "$OUT/git-remote-gitlawb-darwin-arm64"
|
||||
chmod +x "$OUT/gl-darwin-arm64" "$OUT/git-remote-gitlawb-darwin-arm64"
|
||||
|
||||
Executable
+75
@@ -0,0 +1,75 @@
|
||||
#!/usr/bin/env bash
|
||||
#
|
||||
# Dependency-purity gate for the `gitlawb-core` crate.
|
||||
#
|
||||
# gitlawb-core is embedded by every consumer (the gl CLI, git-remote-gitlawb,
|
||||
# the node daemon), so it must stay lean. This script recomputes gitlawb-core's
|
||||
# NORMAL (non-dev, non-build) transitive dependency set and fails if it contains
|
||||
# any crate not present in ci/gitlawb-core-allowed-deps.txt.
|
||||
#
|
||||
# Hard-fail direction: a crate present now but NOT allowlisted. That is the case
|
||||
# the gate exists to catch (core silently gaining a heavy dependency).
|
||||
# Informational only: an allowlisted crate no longer present (stale entry) — a
|
||||
# legitimate dependency removal should not red CI, so it is reported, not failed.
|
||||
#
|
||||
# Runnable from anywhere in the repo.
|
||||
set -euo pipefail
|
||||
|
||||
ROOT="$(git rev-parse --show-toplevel)"
|
||||
ALLOW="$ROOT/ci/gitlawb-core-allowed-deps.txt"
|
||||
|
||||
if [ ! -f "$ALLOW" ]; then
|
||||
echo "ERROR: allowlist not found at $ALLOW" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# `cargo tree` resolves WITHOUT --locked on purpose, unlike the blocking cargo
|
||||
# jobs in pr-checks. This gate answers one question, whether gitlawb-core's
|
||||
# dependency closure gained something unallowlisted, and a stale Cargo.lock
|
||||
# would red it for a reason that has nothing to do with that closure. Lock
|
||||
# staleness is already caught by the --locked cargo jobs, so it does not need a
|
||||
# second gate here.
|
||||
#
|
||||
# Resolving can refresh Cargo.lock as a side effect, so snapshot and restore
|
||||
# it: this check must never leave the working tree dirty when run locally.
|
||||
lock_backup="$(mktemp)"
|
||||
cp "$ROOT/Cargo.lock" "$lock_backup"
|
||||
restore_lock() { cp "$lock_backup" "$ROOT/Cargo.lock"; rm -f "$lock_backup"; }
|
||||
trap restore_lock EXIT
|
||||
|
||||
# Current normal-dependency closure of gitlawb-core, one crate name per line.
|
||||
# Must match the regen command documented in the allowlist header exactly.
|
||||
current="$(
|
||||
cargo tree -p gitlawb-core --edges normal --prefix none --manifest-path "$ROOT/Cargo.toml" \
|
||||
| sed -E 's/ v[0-9].*$//' \
|
||||
| grep -v '^gitlawb-core$' \
|
||||
| sort -u
|
||||
)"
|
||||
|
||||
# Allowlist with comments and blank lines stripped.
|
||||
allowed="$(grep -vE '^[[:space:]]*(#|$)' "$ALLOW" | sort -u)"
|
||||
|
||||
# comm needs sorted input; both sides are sorted above.
|
||||
offenders="$(comm -23 <(printf '%s\n' "$current") <(printf '%s\n' "$allowed"))"
|
||||
stale="$(comm -13 <(printf '%s\n' "$current") <(printf '%s\n' "$allowed"))"
|
||||
|
||||
if [ -n "$stale" ]; then
|
||||
echo "NOTE: allowlisted crates no longer in gitlawb-core's dependency tree"
|
||||
echo " (safe to prune from ci/gitlawb-core-allowed-deps.txt):"
|
||||
printf ' %s\n' $stale
|
||||
echo
|
||||
fi
|
||||
|
||||
if [ -n "$offenders" ]; then
|
||||
{
|
||||
echo "ERROR: gitlawb-core gained dependencies not on the allowlist:"
|
||||
printf ' %s\n' $offenders
|
||||
echo
|
||||
echo "gitlawb-core must stay embeddable and lean. If a new dependency is"
|
||||
echo "intentional, add it to ci/gitlawb-core-allowed-deps.txt (regen command"
|
||||
echo "is in that file's header). Otherwise, drop the dependency."
|
||||
} >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "gitlawb-core dependency purity: OK ($(printf '%s\n' "$current" | wc -l | tr -d ' ') normal deps, all allowlisted)."
|
||||
Reference in new issue
Block a user