Compare commits

..
Author SHA1 Message Date
Kevin CodexandOpenClaude 7175409d02 fix(security): reject path traversal in repo_store local_path
Closes CodeQL alert #4 (Uncontrolled data used in path expression).

Both `owner_did` and `repo_name` come from URL parameters and were used
unsanitized to build a filesystem path, so a request like
`/did:key:foo/../../../etc/passwd.git/info/refs` could escape the repos
directory.

Fix:

- New `validate_owner_did` and `validate_repo_name` enforce a strict
  allowlist before path construction (alphanumeric + `: . _ -` for DIDs;
  alphanumeric + `. _ -` for repo names; rejects empty, `..`, leading
  `.` or `-`, slashes, backslashes, null bytes, overlong inputs).
- `RepoStore::local_path` now returns `Result<…>` and the 5 callers
  propagate the error.
- Defence in depth: even after the allowlist passes, the joined path is
  checked to still be rooted at `repos_dir`.
- 17 unit tests cover normal DIDs/repo names plus every malicious shape
  (`..`, `/`, `\`, leading dot/dash, null byte, overlong, did:web with
  dots).

Co-Authored-By: OpenClaude <[email protected]>
2026-05-04 22:15:17 +08:00
180 changed files with 3193 additions and 41424 deletions

No files matched your search

-38
View File
@@ -1,38 +0,0 @@
# cargo-audit configuration.
#
# cargo-audit reads its config from .cargo/audit.toml (relative to the working
# directory) or ~/.cargo/audit.toml. It does NOT read a repo-root audit.toml,
# and there is no CLI flag to point at a config file (`-f` is the lockfile path).
# This file lives at .cargo/audit.toml for that reason.
#
# The audit job stays hard-fail: only the advisories explicitly listed below are
# suppressed, so any NEW advisory still breaks CI. Each entry below has no
# available upstream fix; everything fixable is fixed in Cargo.lock instead.
#
# Tracking: the hickory ignores are reachable accepted risk. A scheduled re-check
# (.github/workflows/audit-schedule.yml) runs without these ignores and fails if
# the lockfile moves off the pinned vulnerable versions while the ignores remain.
[advisories]
ignore = [
# hickory-proto 0.25.2 (pulled by libp2p-dns 0.44 -> hickory-resolver 0.25).
# REACHABLE: the node wraps its QUIC transport in the system DNS resolver
# (crates/gitlawb-node/src/p2p/mod.rs:238), so a malicious DNS response can
# trigger these DoS paths. No fix is available: the latest libp2p-dns on
# crates.io is 0.44 and pins hickory 0.25; the fix requires hickory >=0.26.1.
# REMOVE both once libp2p-dns ships a release using hickory 0.26 (verified
# 2026-06-21: cargo update -p hickory-proto locks 0 packages; still 0.25.2).
# Tracking: https://github.com/Gitlawb/node/issues/76
"RUSTSEC-2026-0118", # hickory NSEC3 closest-encloser unbounded loop
"RUSTSEC-2026-0119", # hickory O(n^2) name-compression CPU exhaustion
# rsa 0.9.10 (Marvin timing sidechannel). Present in Cargo.lock because sqlx
# resolves sqlx-mysql unconditionally, and sqlx-mysql depends on rsa. cargo
# audit scans the lockfile, so it flags rsa even though it is NOT linked into
# our binary: sqlx is built postgres-only (crates/gitlawb-node/Cargo.toml),
# so the MySQL RSA auth path is never compiled and there is no RSA oracle to
# attack. No upstream fix exists regardless. REMOVE this ignore if sqlx is
# ever built with the `mysql` feature, or any other consumer of rsa enters
# the build, at which point it becomes a real reachable advisory.
"RUSTSEC-2023-0071", # rsa Marvin attack (no fix; not linked in our build)
]
+2 -97
View File
@@ -21,23 +21,6 @@ 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=
@@ -80,91 +63,13 @@ POSTGRES_PASSWORD=changeme
# ── P2P networking ────────────────────────────────────────────────────────
GITLAWB_P2P_PORT=7546
# Comma-separated HTTP peer URLs to announce to on startup.
# The binary also ships with bootstrap-peers.json; set
# GITLAWB_BOOTSTRAP_DISABLE_SEEDS=true for isolated dev/test networks.
# Comma-separated multiaddrs of bootstrap peers
GITLAWB_BOOTSTRAP_PEERS=
GITLAWB_BOOTSTRAP_DISABLE_SEEDS=false
# Require signatures on peer announce/sync write routes. Keep false during
# rolling upgrades so existing live nodes can still communicate.
GITLAWB_REQUIRE_SIGNED_PEER_WRITES=false
# Require the authenticated pusher to be the repo owner on git-receive-pack.
# A valid did:key signature is authentication, not authorization: anyone can
# sign as their own DID. When true, pushes from a non-owner DID are rejected.
# Keep false until the repo owner is ready for owner-only writes.
GITLAWB_ENFORCE_OWNER_PUSH=false
# Comma-separated libp2p multiaddrs.
# Example: /ip4/1.2.3.4/udp/7546/quic-v1/p2p/12D3KooW...
GITLAWB_P2P_BOOTSTRAP=
# ── Access control ────────────────────────────────────────────────────────
# Reserved for private-read mode. Public/private repo read enforcement is not
# wired in the current live release; do not rely on this for private repositories.
# Set to false to require auth on all read endpoints
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
# ── iCaptcha proof-of-intelligence gate ───────────────────────────────────
# Optional gate on create_repo + register: require callers to present an
# iCaptcha proof (X-ICaptcha-Proof header) earned at icaptcha.gitlawb.com.
# Default off = fully inert (no behavior change).
# off - gate disabled (default)
# shadow - verify + log would-be rejections, but always allow
# enforce - reject requests without a valid, strong-enough proof
ICAPTCHA_MODE=off
# Optional base64url Ed25519 public key override; if unset it is fetched from
# ICAPTCHA_URL/v1/pubkey at startup. Recommended in production: pinning the key
# removes the startup dependency on the iCaptcha service being reachable and
# avoids silently running inert if that one-time fetch fails.
ICAPTCHA_PUBKEY=
# Minimum proof difficulty level required to pass.
ICAPTCHA_REQUIRED_LEVEL=3
# Base URL of the iCaptcha service.
ICAPTCHA_URL=https://icaptcha.gitlawb.com
-11
View File
@@ -1,11 +0,0 @@
# Ownership for CI, release, and security-sensitive infrastructure.
# A PR that edits these paths requires review from a code owner once
# branch protection's "Require review from Code Owners" is enabled.
/.github/ @beardthelion
/Dockerfile @beardthelion
/Dockerfile.bins @beardthelion
/docker-compose.yml @beardthelion
/release-please-config.json @beardthelion
/.release-please-manifest.json @beardthelion
/SECURITY.md @beardthelion
-66
View File
@@ -1,66 +0,0 @@
name: Bug report
description: Report a defect in a Gitlawb crate or node behavior
labels: ["bug"]
body:
- type: markdown
attributes:
value: |
Thanks for the report. Please fill in the fields below so we can reproduce the issue.
For security vulnerabilities, do NOT open an issue — follow SECURITY.md instead.
- type: textarea
id: what-happened
attributes:
label: What happened?
description: A clear description of the bug.
validations:
required: true
- type: textarea
id: expected
attributes:
label: Expected behavior
validations:
required: true
- type: textarea
id: repro
attributes:
label: Steps to reproduce
placeholder: |
1. ...
2. ...
3. ...
validations:
required: true
- type: dropdown
id: crate
attributes:
label: Affected crate
options:
- gitlawb-node
- gl
- git-remote-gitlawb
- gitlawb-core
- not sure / other
validations:
required: true
- type: input
id: version
attributes:
label: Version or commit
description: Output of the binary's `--version`, or the git commit you built.
validations:
required: true
- type: textarea
id: environment
attributes:
label: Environment
description: OS, Rust version (`rustc --version`), and anything else relevant.
validations:
required: false
- type: textarea
id: logs
attributes:
label: Relevant logs
description: Paste logs or errors. This will be rendered as code, no need for backticks.
render: shell
validations:
required: false
-8
View File
@@ -1,8 +0,0 @@
blank_issues_enabled: false
contact_links:
- name: Security vulnerability
url: https://github.com/Gitlawb/node/blob/main/SECURITY.md
about: Please report security issues privately per our security policy, not as a public issue.
- name: Questions & discussion
url: https://github.com/Gitlawb/node/discussions
about: For usage questions and open-ended discussion.
@@ -1,34 +0,0 @@
name: Feature request
description: Suggest an improvement or new capability
labels: ["enhancement"]
body:
- type: textarea
id: problem
attributes:
label: Problem / use case
description: What are you trying to do that's hard or impossible today?
validations:
required: true
- type: textarea
id: proposal
attributes:
label: Proposed solution
validations:
required: true
- type: textarea
id: alternatives
attributes:
label: Alternatives considered
validations:
required: false
- type: dropdown
id: protocol
attributes:
label: Does this touch the protocol?
description: Identity, signatures, UCAN, ref certs, or P2P wire formats. Protocol changes need an issue discussion before any PR.
options:
- "No"
- "Yes"
- "Not sure"
validations:
required: true
-63
View File
@@ -1,63 +0,0 @@
<!--
Thanks for contributing to Gitlawb. Keep PRs focused on one change.
Protocol-level changes (identity, signatures, wire format) should start
as an issue before code — see CONTRIBUTING.md.
-->
## Summary
<!-- One or two sentences: what changes and why it matters. -->
## Motivation & context
<!-- What problem does this solve? Link prior discussion if any. -->
Closes #
## Kind of change
- [ ] Bug fix
- [ ] Feature
- [ ] Security fix
- [ ] Docs
- [ ] Tests / CI
- [ ] Refactor (no behavior change)
- [ ] Breaking or protocol change (issue required first)
## What changed
<!-- Bullet the concrete changes. Note the crate(s) touched:
gitlawb-core / gitlawb-node / gl / git-remote-gitlawb -->
-
## How a reviewer can verify
<!-- Commands to run, or repro steps for a bug plus proof it's fixed. -->
```sh
```
## Before you request review
- [ ] Scope is one logical change; no unrelated churn
- [ ] `cargo test --workspace` passes locally
- [ ] New behavior is covered by tests (required for fixes)
- [ ] `cargo fmt --all` and `cargo clippy --workspace --all-targets -- -D warnings` are clean
- [ ] Commit titles use Conventional Commits (`feat(...)`, `fix(...)`, `docs(...)`)
- [ ] Docs / `.env.example` updated if behavior or config changed (or N/A)
- [ ] Checked existing PRs so this isn't a duplicate
## Protocol & signing impact
<!-- Delete this block if your change doesn't touch the protocol. -->
- [ ] Touches DID / `did:key`, Ed25519 / RFC 9421 signatures, UCAN, ref certs, or P2P wire formats
- [ ] Discussed in an issue before implementation
- [ ] Backward-compatible with existing nodes and previously signed history
## Notes for reviewers
<!-- Anything out of scope, follow-ups, or known limitations. Optional. -->
-88
View File
@@ -1,88 +0,0 @@
name: Scheduled Audit
# Self-expiring suppression check (companion to the PR-blocking audit gate in
# pr-checks.yml). Runs weekly. It re-runs cargo audit WITHOUT the .cargo/audit.toml
# ignore list to surface the full advisory set for visibility, and it hard-fails
# if the lockfile has moved off the pinned vulnerable versions while the ignores
# are still present, i.e. the upstream fix landed but the ignore was not dropped.
on:
schedule:
- cron: "0 6 * * 1" # Mondays 06:00 UTC
workflow_dispatch:
permissions:
contents: read
env:
CARGO_TERM_COLOR: always
jobs:
scheduled-audit:
name: scheduled audit (no ignores)
runs-on: ubuntu-latest
timeout-minutes: 30
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: audit-schedule
- 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
# has no .cargo/audit.toml so the ignore list does not apply; never fail
# the build on this step, it is visibility only.
- name: Full audit report (ignores not applied)
run: |
mkdir -p "$RUNNER_TEMP/full-audit"
cp Cargo.lock "$RUNNER_TEMP/full-audit/Cargo.lock"
cd "$RUNNER_TEMP/full-audit"
{
echo '### Full cargo audit (no ignores applied)'
echo '```'
cargo audit -f Cargo.lock || true
echo '```'
} >> "$GITHUB_STEP_SUMMARY"
# Drift guard: the hickory ignores are only valid while hickory-proto is
# pinned at 0.25.x. If the lockfile has moved past that, the upstream fix
# is in and the ignores in .cargo/audit.toml must be removed. Fail loudly.
- name: Fail if hickory moved past 0.25.x while ignores remain
run: |
set -euo pipefail
version="$(grep -A1 'name = "hickory-proto"' Cargo.lock | grep '^version' | head -1 | cut -d'"' -f2)"
echo "hickory-proto in Cargo.lock: ${version:-not present}"
ignores_present=false
if grep -q 'RUSTSEC-2026-011' .cargo/audit.toml; then
ignores_present=true
fi
# Drift = the lockfile no longer matches what the ignores assume:
# hickory moved off 0.25.x (fix shipped) OR was removed entirely
# (dead ignore entries left behind). Both must fail.
if [ "$ignores_present" = true ] && { [ -z "${version}" ] || [[ "${version}" != 0.25.* ]]; }; then
echo "::error::hickory-proto is ${version:-absent from Cargo.lock} but the RUSTSEC-2026-0118/0119 ignores are still in .cargo/audit.toml. The upstream fix appears to be available or the dependency is gone; remove the ignores."
exit 1
fi
echo "No drift: ignore list is consistent with the pinned hickory-proto version."
+3 -176
View File
@@ -9,25 +9,18 @@ on:
permissions:
contents: read
# Cancel superseded runs on the same PR/branch; never cancel runs on main.
concurrency:
group: pr-checks-${{ github.ref }}
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
env:
CARGO_TERM_COLOR: always
RUST_BACKTRACE: 1
jobs:
fmt-clippy:
name: fmt + clippy
fmt-clippy-test:
name: fmt + clippy + test
runs-on: ubuntu-latest
timeout-minutes: 30
steps:
- name: Check out repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
persist-credentials: false
- name: Set up Rust toolchain
uses: dtolnay/rust-toolchain@b3b07ba8b418998c39fb20f53e8b695cdcc8de1b # stable
@@ -44,171 +37,5 @@ jobs:
- name: cargo clippy
run: cargo clippy --workspace --all-targets -- -D warnings
test:
name: test (${{ matrix.toolchain }})
runs-on: ubuntu-latest
timeout-minutes: 45
strategy:
fail-fast: false
matrix:
toolchain: [stable, beta]
# Beta is informational: an upstream beta regression should warn, not block merges.
continue-on-error: ${{ matrix.toolchain == 'beta' }}
# Postgres for the DB-backed integration tests (#[sqlx::test] provisions an
# isolated database per test off this connection). The health-check gate keeps
# `cargo test` from racing a not-yet-ready server.
services:
postgres:
image: postgres:16
env:
POSTGRES_USER: postgres
POSTGRES_PASSWORD: postgres
POSTGRES_DB: gitlawb_test
ports:
- 5432:5432
options: >-
--health-cmd pg_isready
--health-interval 10s
--health-timeout 5s
--health-retries 5
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: ${{ matrix.toolchain }}
- name: Cache cargo
uses: Swatinem/rust-cache@98c8021b550208e191a6a3145459bfc9fb29c4c0 # v2.8.0
with:
key: ${{ matrix.toolchain }}
- name: cargo test
env:
DATABASE_URL: postgres://postgres:postgres@localhost:5432/gitlawb_test
run: cargo test --workspace
build-release:
name: build --release
runs-on: ubuntu-latest
timeout-minutes: 45
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: release
- name: cargo build --release
run: cargo build --release --workspace
audit:
name: cargo audit
runs-on: ubuntu-latest
timeout-minutes: 30
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: audit-0.22.2
- 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
# here means "no NEW advisories", not "advisory-clean": surface the active
# ignore list so a reviewer sees exactly what is being accepted.
- name: Show active audit ignores
run: |
{
echo '### cargo audit: accepted advisories (.cargo/audit.toml)'
echo '```toml'
sed -n '/^\[advisories\]/,$p' .cargo/audit.toml
echo '```'
} >> "$GITHUB_STEP_SUMMARY"
- name: cargo audit
run: cargo audit
msrv:
name: MSRV (Rust 1.91)
runs-on: ubuntu-latest
timeout-minutes: 30
steps:
- name: Check out repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
persist-credentials: false
- name: Set up Rust 1.91
uses: dtolnay/rust-toolchain@b3b07ba8b418998c39fb20f53e8b695cdcc8de1b # 1.91
with:
toolchain: "1.91"
- name: Cache cargo
uses: Swatinem/rust-cache@98c8021b550208e191a6a3145459bfc9fb29c4c0 # v2.8.0
with:
key: msrv
- name: cargo check on MSRV
run: cargo check --workspace --all-targets
docker-build:
name: Docker build smoke test
runs-on: ubuntu-latest
timeout-minutes: 30
steps:
- name: Check out repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
persist-credentials: false
- name: Build image
run: docker build -t gitlawb-node:ci-test .
- name: Smoke test --version
run: docker run --rm gitlawb-node:ci-test --version
-124
View File
@@ -1,124 +0,0 @@
name: PR Triage
# Runs on pull_request_target, not pull_request: fork PRs get a read-only
# GITHUB_TOKEN under pull_request regardless of the permissions below, so the
# label/comment writes 403. This job never checks out or runs PR head code (it
# only reads context.payload and the files API), so pull_request_target is safe.
on:
pull_request_target:
types: [opened, edited, synchronize, reopened]
permissions:
contents: read
pull-requests: write
issues: write
concurrency:
group: pr-triage-${{ github.event.pull_request.number }}
cancel-in-progress: true
jobs:
triage:
name: Quality-signal triage
runs-on: ubuntu-latest
timeout-minutes: 10
steps:
- name: Label and guide
uses: actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b # v7
with:
script: |
const pr = context.payload.pull_request;
const { owner, repo } = context.repo;
const prNumber = pr.number;
// Trusted authors bypass triage entirely.
const trusted = ["OWNER", "MEMBER", "COLLABORATOR"];
if (trusted.includes(pr.author_association)) {
core.info(`Author association ${pr.author_association} is trusted; skipping triage.`);
return;
}
// Labels this workflow owns. Anything here may be added or removed each run.
const MANAGED = ["needs-issue", "needs-description", "needs-tests", "workflow-change"];
const want = new Set();
const body = pr.body || "";
// Linked issue: look for "closes/fixes/resolves #N" or any bare #N reference.
const hasLinkedIssue =
/\b(close[sd]?|fix(e[sd])?|resolve[sd]?)\b[^\n]*#\d+/i.test(body) ||
/#\d+/.test(body);
if (!hasLinkedIssue) want.add("needs-issue");
// Description substance: strip HTML comments and markdown headings, then measure.
const stripped = body
.replace(/<!--[\s\S]*?-->/g, "")
.replace(/^#+.*$/gm, "")
.trim();
if (stripped.length < 50) want.add("needs-description");
// File-based signals.
const files = await github.paginate(github.rest.pulls.listFiles, {
owner, repo, pull_number: prNumber, per_page: 100,
});
const names = files.map(f => f.filename);
const isFork = pr.head.repo && pr.head.repo.full_name !== pr.base.repo.full_name;
const touchesWorkflows = names.some(n => n.startsWith(".github/workflows/"));
if (isFork && touchesWorkflows) want.add("workflow-change");
const changedRust = names.some(n => n.startsWith("crates/") && n.endsWith(".rs"));
// A test can live in a tests/ dir, a *_test.rs file, or (the common Rust
// pattern) an inline #[test] / #[cfg(test)] block added inside the source file.
const addsInlineTest = files.some(f =>
f.filename.endsWith(".rs") && f.patch &&
/^\+.*#\[(test\]|cfg\(test\))/m.test(f.patch));
const touchedTests =
names.some(n => n.includes("/tests/") || n.endsWith("_test.rs")) || addsInlineTest;
if (changedRust && !touchedTests) want.add("needs-tests");
// Reconcile labels: add wanted managed labels, remove managed labels no longer wanted.
const current = (await github.rest.issues.listLabelsOnIssue({
owner, repo, issue_number: prNumber,
})).data.map(l => l.name);
const toAdd = [...want].filter(l => !current.includes(l));
const toRemove = MANAGED.filter(l => current.includes(l) && !want.has(l));
if (toAdd.length) {
await github.rest.issues.addLabels({ owner, repo, issue_number: prNumber, labels: toAdd });
}
for (const name of toRemove) {
await github.rest.issues.removeLabel({ owner, repo, issue_number: prNumber, name })
.catch(() => {}); // ignore if already gone
}
// Guidance comment: only for advisory signals, and only once.
const advisory = ["needs-issue", "needs-description", "needs-tests"].filter(l => want.has(l));
if (!advisory.length) return;
const MARKER = "<!-- gitlawb-triage -->";
const comments = await github.paginate(github.rest.issues.listComments, {
owner, repo, issue_number: prNumber, per_page: 100,
});
if (comments.some(c => c.body && c.body.includes(MARKER))) {
core.info("Guidance comment already present; not reposting.");
return;
}
const reasons = {
"needs-issue": "Link the issue this addresses (`Closes #123`). For protocol changes, open an issue first.",
"needs-description": "Add a short summary of what changes and why: the template's Summary and Motivation sections.",
"needs-tests": "This changes Rust source but no tests changed. Tests are required for fixes and strongly encouraged for features.",
};
const lines = advisory.map(l => `- ${reasons[l]}`).join("\n");
const comment = [
MARKER,
"Thanks for the contribution. A couple of things will help us review this faster:",
"",
lines,
"",
"See [CONTRIBUTING.md](https://github.com/Gitlawb/node/blob/main/CONTRIBUTING.md). Update the PR and these notes will clear automatically.",
].join("\n");
await github.rest.issues.createComment({ owner, repo, issue_number: prNumber, body: comment });
+20 -410
View File
@@ -9,9 +9,6 @@ concurrency:
group: release-${{ github.ref }}
cancel-in-progress: false
# Least privilege by default; every job opts in to exactly what it needs.
permissions: {}
jobs:
release-please:
if: ${{ github.repository == 'Gitlawb/node' }}
@@ -27,7 +24,7 @@ jobs:
steps:
- name: Run release-please
id: release
uses: googleapis/release-please-action@45996ed1f6d02564a971a2fa1b5860e934307cf7 # v5.0.0
uses: googleapis/release-please-action@16a9c90856f42705d54a6fda1823352bdc62cf38 # v4.3.0
with:
token: ${{ secrets.GITHUB_TOKEN }}
@@ -44,7 +41,6 @@ jobs:
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ needs.release-please.outputs.tag_name }}
persist-credentials: false
- name: Set up QEMU
uses: docker/setup-qemu-action@29109295f81e9208d7d86ff1c6c12d2833863392 # v3.6.0
@@ -105,9 +101,6 @@ jobs:
needs: release-please
if: ${{ needs.release-please.outputs.release_created == 'true' }}
runs-on: ${{ matrix.os }}
# Windows is best-effort: a failure there must not fail the job or block the
# downstream npm/Homebrew jobs that only consume the unix artifacts.
continue-on-error: ${{ startsWith(matrix.target, 'x86_64-pc-windows') }}
permissions:
contents: write
strategy:
@@ -116,24 +109,17 @@ 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-24.04-arm
# macos-13 (the last plain Intel image) is retired and queues forever;
# macos-15-intel is GitHub's supported Intel label.
os: ubuntu-latest
- target: x86_64-apple-darwin
os: macos-15-intel
os: macos-13
- target: aarch64-apple-darwin
os: macos-14
- target: x86_64-pc-windows-msvc
os: windows-latest
steps:
- name: Checkout release tag
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ needs.release-please.outputs.tag_name }}
persist-credentials: false
- name: Set up Rust toolchain
uses: dtolnay/rust-toolchain@b3b07ba8b418998c39fb20f53e8b695cdcc8de1b # stable
@@ -141,422 +127,46 @@ 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
with:
key: ${{ matrix.target }}
# The gitlawb-node daemon is a Linux/macOS service; on Windows we ship only
# the two CLI binaries. A Windows-only failure must not block the release.
- name: Determine binaries
shell: bash
run: |
BINS="gl git-remote-gitlawb gitlawb-node"
case "${{ matrix.target }}" in *windows*) BINS="gl git-remote-gitlawb" ;; esac
echo "BINS=$BINS" >> "$GITHUB_ENV"
- name: Build
shell: bash
run: |
set -euo pipefail
args=""
for b in $BINS; do args="$args -p $b"; done
cargo build --release --target ${{ matrix.target }} $args
# Run each packaged binary's --version so a broken release artifact fails the
# build instead of shipping. Every target builds on a matching-arch runner,
# so all of them can execute here.
- name: Smoke test binaries
shell: bash
run: |
set -euo pipefail
VERSION="${{ needs.release-please.outputs.version }}"
BIN_DIR="target/${{ matrix.target }}/release"
EXE=""
case "${{ matrix.target }}" in *windows*) EXE=".exe" ;; esac
for bin in $BINS; do
echo "== $bin --version =="
out="$("$BIN_DIR/$bin$EXE" --version)"
echo "$out"
# Each binary prints "<name> <version>"; assert the released version is present.
grep -qF "$VERSION" <<<"$out" || {
echo "::error::$bin --version did not report expected version $VERSION (got: $out)"
exit 1
}
done
run: cargo build --release --target ${{ matrix.target }} -p gl -p git-remote-gitlawb -p gitlawb-node
- name: Package
id: pkg
shell: bash
run: |
set -euo pipefail
TARGET="${{ matrix.target }}"
NAME="gitlawb-node-${{ needs.release-please.outputs.version }}-${TARGET}"
BIN_DIR="target/${TARGET}/release"
EXE=""
case "$TARGET" in *windows*) EXE=".exe" ;; esac
# Portable sha256 → "<hash> <file>" so install scripts and brew can parse it.
sha256_file() {
local f="$1"
if command -v sha256sum >/dev/null 2>&1; then
sha256sum "$f"
elif command -v shasum >/dev/null 2>&1; then
shasum -a 256 "$f"
else
local h
h=$(certutil -hashfile "$f" SHA256 | sed -n 2p | tr -d ' \r')
printf '%s %s\n' "$h" "$f"
fi
}
NAME="gitlawb-node-${{ needs.release-please.outputs.version }}-${{ matrix.target }}"
mkdir -p "dist/$NAME"
for bin in $BINS; do
cp "$BIN_DIR/$bin$EXE" "dist/$NAME/"
done
cp "target/${{ matrix.target }}/release/gl" "dist/$NAME/"
cp "target/${{ matrix.target }}/release/git-remote-gitlawb" "dist/$NAME/"
cp "target/${{ matrix.target }}/release/gitlawb-node" "dist/$NAME/"
cp README.md LICENSE-MIT LICENSE-APACHE "dist/$NAME/"
cd dist
case "$TARGET" in
*windows*)
# 7z is preinstalled on windows-latest runners.
7z a -tzip "$NAME.zip" "$NAME" >/dev/null
sha256_file "$NAME.zip" > "$NAME.zip.sha256"
;;
*)
tar czf "$NAME.tar.gz" "$NAME"
sha256_file "$NAME.tar.gz" > "$NAME.tar.gz.sha256"
;;
esac
tar czf "$NAME.tar.gz" "$NAME"
shasum -a 256 "$NAME.tar.gz" > "$NAME.tar.gz.sha256"
echo "asset=dist/$NAME.tar.gz" >> "$GITHUB_OUTPUT"
echo "checksum=dist/$NAME.tar.gz.sha256" >> "$GITHUB_OUTPUT"
- name: Attach to release
uses: softprops/action-gh-release@72f2c25fcb47643c292f7107632f7a47c1df5cd8 # v2.3.2
with:
tag_name: ${{ needs.release-please.outputs.tag_name }}
files: |
dist/*.tar.gz
dist/*.zip
dist/*.sha256
npm-publish:
name: Publish to npm
needs: [release-please, release-binaries]
if: ${{ needs.release-please.outputs.release_created == 'true' }}
runs-on: ubuntu-latest
permissions:
contents: read
id-token: write # npm provenance
steps:
- name: Guard on secret
id: guard
env:
NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
run: |
if [ -z "${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
- 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 }}
persist-credentials: false
- 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 }}
run: |
set -euo pipefail
# npm platform package -> Rust target triple (unix only; Windows is not
# published to npm).
MAP="
gl-darwin-arm64:aarch64-apple-darwin
gl-darwin-x64:x86_64-apple-darwin
gl-linux-arm64:aarch64-unknown-linux-musl
gl-linux-x64:x86_64-unknown-linux-musl
"
mkdir -p _dl
for entry in $MAP; do
pkg="${entry%%:*}"
target="${entry#*:}"
archive="gitlawb-node-${VERSION}-${target}.tar.gz"
echo "==> $pkg <- $archive"
gh release download "$TAG" --repo "$GITHUB_REPOSITORY" \
--pattern "$archive" --dir _dl --clobber
tar -xzf "_dl/$archive" -C _dl
src="_dl/gitlawb-node-${VERSION}-${target}"
cp "$src/gl" "npm/packages/$pkg/gl"
cp "$src/git-remote-gitlawb" "npm/packages/$pkg/git-remote-gitlawb"
chmod +x "npm/packages/$pkg/gl" "npm/packages/$pkg/git-remote-gitlawb"
done
- name: Set versions
if: ${{ steps.guard.outputs.enabled == 'true' }}
env:
VERSION: ${{ needs.release-please.outputs.version }}
run: |
set -euo pipefail
node -e '
const fs = require("fs");
const v = process.env.VERSION;
for (const p of fs.readdirSync("npm/packages")) {
const f = `npm/packages/${p}/package.json`;
const pkg = JSON.parse(fs.readFileSync(f, "utf8"));
pkg.version = v;
if (pkg.optionalDependencies) {
for (const k of Object.keys(pkg.optionalDependencies)) {
pkg.optionalDependencies[k] = v;
}
}
fs.writeFileSync(f, JSON.stringify(pkg, null, 2) + "\n");
}
'
- name: Publish
if: ${{ steps.guard.outputs.enabled == 'true' }}
env:
NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
VERSION: ${{ needs.release-please.outputs.version }}
run: |
set -euo pipefail
echo "//registry.npmjs.org/:_authToken=${NPM_TOKEN}" > ~/.npmrc
# 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.
for pkg in gl-darwin-arm64 gl-darwin-x64 gl-linux-arm64 gl-linux-x64 gl; do
name="@gitlawb/$pkg"
if npm view "$name@$VERSION" version >/dev/null 2>&1; then
echo "==> $name@$VERSION already published, skipping"
continue
fi
echo "==> npm publish $name@$VERSION"
npm publish "npm/packages/$pkg" --provenance --access public
done
homebrew-bump:
name: Bump Homebrew tap
needs: [release-please, release-binaries]
if: ${{ needs.release-please.outputs.release_created == 'true' }}
runs-on: ubuntu-latest
permissions:
contents: read # GITHUB_TOKEN downloads release assets; the tap push uses HOMEBREW_TAP_PAT
steps:
- name: Guard on secret
id: guard
env:
HOMEBREW_TAP_PAT: ${{ secrets.HOMEBREW_TAP_PAT }}
run: |
if [ -z "${HOMEBREW_TAP_PAT:-}" ]; then
echo "::warning::HOMEBREW_TAP_PAT is not set — skipping Homebrew bump."
echo "enabled=false" >> "$GITHUB_OUTPUT"
else
echo "enabled=true" >> "$GITHUB_OUTPUT"
fi
- name: Checkout tap repo
if: ${{ steps.guard.outputs.enabled == 'true' }}
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
repository: Gitlawb/homebrew-tap
token: ${{ secrets.HOMEBREW_TAP_PAT }}
path: tap
persist-credentials: false
- name: Regenerate formula
if: ${{ steps.guard.outputs.enabled == 'true' }}
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
VERSION: ${{ needs.release-please.outputs.version }}
TAG: ${{ needs.release-please.outputs.tag_name }}
run: |
set -euo pipefail
base="https://github.com/${GITHUB_REPOSITORY}/releases/download/${TAG}"
mkdir -p _sums
gh release download "$TAG" --repo "$GITHUB_REPOSITORY" \
--pattern '*.tar.gz.sha256' --dir _sums --clobber
sha() { awk '{print $1}' "_sums/gitlawb-node-${VERSION}-$1.tar.gz.sha256"; }
SHA_MAC_ARM="$(sha aarch64-apple-darwin)"
SHA_MAC_X64="$(sha x86_64-apple-darwin)"
SHA_LNX_ARM="$(sha aarch64-unknown-linux-musl)"
SHA_LNX_X64="$(sha x86_64-unknown-linux-musl)"
mkdir -p tap/Formula
cat > tap/Formula/gl.rb <<EOF
class Gl < Formula
desc "Gitlawb CLI — decentralized git for AI agents and developers"
homepage "https://gitlawb.com"
version "${VERSION}"
license "MIT OR Apache-2.0"
on_macos do
on_arm do
url "${base}/gitlawb-node-${VERSION}-aarch64-apple-darwin.tar.gz"
sha256 "${SHA_MAC_ARM}"
end
on_intel do
url "${base}/gitlawb-node-${VERSION}-x86_64-apple-darwin.tar.gz"
sha256 "${SHA_MAC_X64}"
end
end
on_linux do
on_arm do
url "${base}/gitlawb-node-${VERSION}-aarch64-unknown-linux-musl.tar.gz"
sha256 "${SHA_LNX_ARM}"
end
on_intel do
url "${base}/gitlawb-node-${VERSION}-x86_64-unknown-linux-musl.tar.gz"
sha256 "${SHA_LNX_X64}"
end
end
def install
bin.install "gl"
bin.install "git-remote-gitlawb"
end
test do
assert_match version.to_s, shell_output("#{bin}/gl --version")
end
end
EOF
- name: Commit and push
if: ${{ steps.guard.outputs.enabled == 'true' }}
working-directory: tap
env:
HOMEBREW_TAP_PAT: ${{ secrets.HOMEBREW_TAP_PAT }}
VERSION: ${{ needs.release-please.outputs.version }}
run: |
set -euo pipefail
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
# Stage first so a brand-new (untracked) formula is detected by the no-op check.
git add Formula/gl.rb
if git diff --cached --quiet; then
echo "Formula already up to date."
exit 0
fi
git commit -m "gl ${VERSION}"
# Credentials are not persisted in .git/config; supply the token only for the push.
git push "https://x-access-token:${HOMEBREW_TAP_PAT}@github.com/Gitlawb/homebrew-tap.git" HEAD:main
web-sync:
name: Sync web (install scripts + version)
needs: [release-please, release-binaries]
if: ${{ needs.release-please.outputs.release_created == 'true' }}
runs-on: ubuntu-latest
permissions:
contents: read # GITHUB_TOKEN checks out node; the web PR uses WEB_SYNC_PAT
steps:
- name: Guard on secret
id: guard
env:
WEB_SYNC_PAT: ${{ secrets.WEB_SYNC_PAT }}
run: |
if [ -z "${WEB_SYNC_PAT:-}" ]; then
echo "::warning::WEB_SYNC_PAT is not set — skipping web sync."
echo "enabled=false" >> "$GITHUB_OUTPUT"
else
echo "enabled=true" >> "$GITHUB_OUTPUT"
fi
- name: Checkout node (release tag)
if: ${{ steps.guard.outputs.enabled == 'true' }}
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ needs.release-please.outputs.tag_name }}
path: node
persist-credentials: false
- name: Checkout web
if: ${{ steps.guard.outputs.enabled == 'true' }}
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
repository: Gitlawb/web
token: ${{ secrets.WEB_SYNC_PAT }}
path: web
persist-credentials: false
# web-sync publishes install.ps1 + version.json, so the Windows ZIP must exist.
# Windows is best-effort for npm/Homebrew (continue-on-error), so verify the
# asset is present before advertising a release the site can't actually serve.
- name: Verify website release assets
if: ${{ steps.guard.outputs.enabled == 'true' }}
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
VERSION: ${{ needs.release-please.outputs.version }}
TAG: ${{ needs.release-please.outputs.tag_name }}
run: |
set -euo pipefail
gh release view "$TAG" --repo "$GITHUB_REPOSITORY" --json assets \
--jq '.assets[].name' > /tmp/release-assets
for asset in \
"gitlawb-node-${VERSION}-x86_64-pc-windows-msvc.zip" \
"gitlawb-node-${VERSION}-x86_64-pc-windows-msvc.zip.sha256"; do
grep -Fxq "$asset" /tmp/release-assets || {
echo "::error::release asset missing: $asset (Windows build likely failed); not syncing web"
exit 1
}
done
- name: Sync and open PR
if: ${{ steps.guard.outputs.enabled == 'true' }}
env:
GH_TOKEN: ${{ secrets.WEB_SYNC_PAT }}
VERSION: ${{ needs.release-please.outputs.version }}
TAG: ${{ needs.release-please.outputs.tag_name }}
run: |
set -euo pipefail
# Canonical install scripts (source of truth lives in the node repo).
cp node/install.sh web/public/install.sh
cp node/install.ps1 web/public/install.ps1
# Single version source the site can read.
printf '{\n "version": "%s",\n "tag": "%s"\n}\n' "$VERSION" "$TAG" > web/public/version.json
# One-time, idempotent drift fixes: drop orphaned binaries, fix stale link.
rm -rf web/public/bin
if [ -f web/public/skill.md ]; then
sed -i 's#github.com/gitlawb/releases#github.com/Gitlawb/node/releases#g' web/public/skill.md
fi
cd web
# Stage first so brand-new (untracked) files are caught by the no-op check.
git add -A
if git diff --cached --quiet; then
echo "web already up to date."
exit 0
fi
branch="release-sync/${TAG}"
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
git checkout -b "$branch"
git commit -m "chore: sync gitlawb ${TAG} (install scripts + version)"
# Credentials are not persisted in .git/config; supply the token only for the push.
git push --force "https://x-access-token:${GH_TOKEN}@github.com/Gitlawb/web.git" "HEAD:$branch"
gh pr create --repo Gitlawb/web --head "$branch" \
--title "Sync gitlawb ${TAG}" \
--body "Automated sync from Gitlawb/node ${TAG}: install.sh, install.ps1, public/version.json, and one-time drift fixes (removed orphaned public/bin, fixed skill.md releases link). Review and merge to deploy via Vercel." \
|| {
# Only swallow the "PR already exists" case; surface auth/API failures
# (a failed gh pr list must not be misread as "PR exists").
pr_count="$(gh pr list --repo Gitlawb/web --head "$branch" --state open --json number --jq 'length')" || exit 1
if [ "$pr_count" != "0" ]; then
echo "PR for $branch already exists; branch was updated."
else
exit 1
fi
}
${{ steps.pkg.outputs.asset }}
${{ steps.pkg.outputs.checksum }}
-40
View File
@@ -1,40 +0,0 @@
name: Stale PRs
on:
schedule:
- cron: "30 1 * * *" # daily at 01:30 UTC
workflow_dispatch:
permissions:
contents: read
pull-requests: write
issues: write
jobs:
stale:
name: Flag and close ignored PRs
runs-on: ubuntu-latest
timeout-minutes: 10
steps:
- uses: actions/stale@5bef64f19d7facfb25b37b414482c7164d639639 # v9
with:
days-before-stale: 14
days-before-close: 7
# Act on PRs only; never on issues.
days-before-issue-stale: -1
days-before-issue-close: -1
# Only PRs the triage step flagged as missing a real description.
# needs-issue is advisory-only (linking an issue is a SHOULD, and many
# legitimate small PRs have none) so it does not drive auto-close.
only-pr-labels: "needs-description"
stale-pr-label: "stale"
exempt-pr-labels: "workflow-change,security,pinned"
remove-stale-when-updated: true
stale-pr-message: >
This PR has been inactive for 14 days and is still missing a description.
It will be closed in 7 days if there's no update. Push a change or leave a
comment to keep it open. No hard feelings, you can reopen anytime.
close-pr-message: >
Closing due to inactivity. Reopen whenever you're ready to update it. See
CONTRIBUTING.md for what helps us review quickly.
ascending: true
-5
View File
@@ -1,7 +1,6 @@
/target
**/*.rs.bk
Cargo.lock.bak
dist/
# Local node data
/data
@@ -22,7 +21,3 @@ keys/
# Logs
*.log
.openclaude-profile.json
# Per-operator Fly config (node1 prod config is pulled from Fly, not tracked)
infra/fly/node1.fly.toml
+1 -1
View File
@@ -1,3 +1,3 @@
{
".": "0.5.1"
".": "0.3.8"
}
-86
View File
@@ -1,86 +0,0 @@
# Changelog
## [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)
### Features
* agent profiles (display name, bio, avatar, social links) ([#23](https://github.com/Gitlawb/node/issues/23)) ([09a3397](https://github.com/Gitlawb/node/commit/09a339745eca40a2567d911e947e3fc7426fc621))
* **db:** versioned schema migrations with idempotent backfill ([#21](https://github.com/Gitlawb/node/issues/21)) ([927e4d0](https://github.com/Gitlawb/node/commit/927e4d0cfb4ea11dca6930780939afaa067797ba))
* encrypted replication for private subtrees (B1/B2/B3) for [#18](https://github.com/Gitlawb/node/issues/18) ([#36](https://github.com/Gitlawb/node/issues/36)) ([5ff7af8](https://github.com/Gitlawb/node/commit/5ff7af84fa21fab53a12dfa04a0e7fb7e7d672e6))
* **git-remote-gitlawb:** add --version and --help flags ([#30](https://github.com/Gitlawb/node/issues/30)) ([3a401eb](https://github.com/Gitlawb/node/commit/3a401eb0792f9c5f5a10de6c16861655ab3836e0))
* **gitlawb-attest:** External Attestation v1 for ref-update certs ([#20](https://github.com/Gitlawb/node/issues/20)) ([924bccd](https://github.com/Gitlawb/node/commit/924bccd8e53e9be2dc9d6d4e4f1376952d6462bb))
* **node:** blind recipient identities at rest and gate B1 by repo readability ([#40](https://github.com/Gitlawb/node/issues/40)) ([abdc775](https://github.com/Gitlawb/node/commit/abdc7757708d2bbb2bfda99bb65d50756142a42e))
* **node:** enforce per-route authorization across the REST and GraphQL surface ([#87](https://github.com/Gitlawb/node/issues/87)) ([2202b00](https://github.com/Gitlawb/node/commit/2202b0097fab6976ab366a2cdc385f1146a72f86))
* **node:** graceful shutdown + Prometheus metrics endpoint ([#22](https://github.com/Gitlawb/node/issues/22)) ([2ce4da9](https://github.com/Gitlawb/node/commit/2ce4da9cc5a4791e8ae5a1cd90270b67f60d9ec3))
* **node:** iCaptcha proof-of-intelligence gate on create_repo + register ([#108](https://github.com/Gitlawb/node/issues/108)) ([adc20f9](https://github.com/Gitlawb/node/commit/adc20f9effad7b42fab55002875d209c4ed79518))
* **node:** iCaptcha-aware repo propagation gate with quarantine ([#125](https://github.com/Gitlawb/node/issues/125)) ([8b9ceec](https://github.com/Gitlawb/node/commit/8b9ceec25ef338965d1db72d39a7f2adb5300cc9))
* **node:** owner-only push enforcement behind GITLAWB_ENFORCE_OWNER_PUSH ([#31](https://github.com/Gitlawb/node/issues/31)) ([#68](https://github.com/Gitlawb/node/issues/68)) ([0a15e76](https://github.com/Gitlawb/node/commit/0a15e763d2ab46737a3831715facbe51045b33ba))
* **node:** peer partial-mirrors for repos with private subtrees ([#35](https://github.com/Gitlawb/node/issues/35)) ([e365a57](https://github.com/Gitlawb/node/commit/e365a57b51c167abf06e87bfeb0565c80ed1b849))
* **node:** pin the per-push object delta instead of re-enumerating the whole repo ([#90](https://github.com/Gitlawb/node/issues/90)) ([1af4fdf](https://github.com/Gitlawb/node/commit/1af4fdf485c7084cd160551b757b1ad1eed65cc6))
* **node:** replication enforcement (Phase 2) for [#18](https://github.com/Gitlawb/node/issues/18) ([#34](https://github.com/Gitlawb/node/issues/34)) ([8680d0f](https://github.com/Gitlawb/node/commit/8680d0f9d6600bba1a52d15624f8a2802a169511))
* **node:** signature-gated agent self-deregister ([#29](https://github.com/Gitlawb/node/issues/29)) ([#63](https://github.com/Gitlawb/node/issues/63)) ([ff492b4](https://github.com/Gitlawb/node/commit/ff492b452126f5568dac4286a7249f0cadb8b380))
* **node:** subtree content withholding (Phase 3) for [#18](https://github.com/Gitlawb/node/issues/18) ([#28](https://github.com/Gitlawb/node/issues/28)) ([61b3830](https://github.com/Gitlawb/node/commit/61b383019fd895a1a6adfad934ad6c626e0f095e))
* path-scoped repository visibility (Phase 1) for [#18](https://github.com/Gitlawb/node/issues/18) ([#25](https://github.com/Gitlawb/node/issues/25)) ([6abaf1d](https://github.com/Gitlawb/node/commit/6abaf1d7ed8fc55c6547568ae7247131311bde98))
* per-DID rate limiting on creation endpoints (10/hour) ([#13](https://github.com/Gitlawb/node/issues/13)) ([b12c6bc](https://github.com/Gitlawb/node/commit/b12c6bc3283c2647224a62fb520a3cb7acf4a747))
* **sync:** auto-register as replica with origin after successful mirror ([#56](https://github.com/Gitlawb/node/issues/56)) ([c03c9af](https://github.com/Gitlawb/node/commit/c03c9af8fadafe262a2bf3cf25e19edf7160d376))
### Bug Fixes
* **api:** blob endpoint returns 400/404 instead of 500 on bad paths ([#37](https://github.com/Gitlawb/node/issues/37)) ([b61a1bd](https://github.com/Gitlawb/node/commit/b61a1bd46ffe78b39c0967e97b0ad349eba0b046))
* **core:** route seed access through the zeroizing wrapper ([#41](https://github.com/Gitlawb/node/issues/41)) ([#64](https://github.com/Gitlawb/node/issues/64)) ([c9f43b0](https://github.com/Gitlawb/node/commit/c9f43b010576edb3c92a3be3d935cad232250344))
* **core:** zeroize the derived X25519 secret ([#65](https://github.com/Gitlawb/node/issues/65)) ([#91](https://github.com/Gitlawb/node/issues/91)) ([2f6611a](https://github.com/Gitlawb/node/commit/2f6611a30fbb66cef9991cf4c6e507548acc5038))
* **gl:** paginate gl-clone Arweave recovery and make /encrypted-blobs parsing schema-strict ([#49](https://github.com/Gitlawb/node/issues/49)) ([#70](https://github.com/Gitlawb/node/issues/70)) ([2153b0b](https://github.com/Gitlawb/node/commit/2153b0b7a67a48c29a33cd70b80cfbb69760805d))
* **infra:** drop fly idle_timeout 600 -&gt; 120 ([#38](https://github.com/Gitlawb/node/issues/38)) ([a2217bf](https://github.com/Gitlawb/node/commit/a2217bff27ff3d6cae02bd8a12f8a0af7ce2b0a1))
* **node:** anchor the real old_sha and issue a per-ref certificate ([#72](https://github.com/Gitlawb/node/issues/72)) ([6809201](https://github.com/Gitlawb/node/commit/6809201daa223d6f833be6e95876a7b4e1f2b0b5))
* **node:** close under-withholding via full ref scope and full-history classification ([#42](https://github.com/Gitlawb/node/issues/42)) ([#84](https://github.com/Gitlawb/node/issues/84)) ([3e1e904](https://github.com/Gitlawb/node/commit/3e1e9045e4e3aa5ea0aee69767ceb01637920d2a))
* **node:** dedupe mirror and canonical repo rows on list surfaces ([#6](https://github.com/Gitlawb/node/issues/6)) ([#73](https://github.com/Gitlawb/node/issues/73)) ([3e8e333](https://github.com/Gitlawb/node/commit/3e8e333aa03d7a2fe455d5d83f23089d58feb8c9))
* **node:** enforce path-scoped visibility on the REST read API ([#52](https://github.com/Gitlawb/node/issues/52)) ([e37ea7f](https://github.com/Gitlawb/node/commit/e37ea7fec6d5a3171b526c84f884670bbbd258fb))
* **node:** fail closed when a recipient DID can't be resolved ([#47](https://github.com/Gitlawb/node/issues/47)) ([#67](https://github.com/Gitlawb/node/issues/67)) ([abc9ad0](https://github.com/Gitlawb/node/commit/abc9ad03acb48e608234650a25049622673fa53a))
* **node:** gate fork_repo on per-caller path-scoped visibility ([#98](https://github.com/Gitlawb/node/issues/98)) ([#109](https://github.com/Gitlawb/node/issues/109)) ([6ae316c](https://github.com/Gitlawb/node/commit/6ae316cc88521747cbacb2a612b9433897d2e490))
* **node:** gate GET /ipfs/{cid} on per-caller path-scoped visibility ([#110](https://github.com/Gitlawb/node/issues/110)) ([#128](https://github.com/Gitlawb/node/issues/128)) ([174f25a](https://github.com/Gitlawb/node/commit/174f25a206380b26796b8782e1bd860b0a409fc9))
* **node:** gate repo-listing and stats surfaces on visibility ([#97](https://github.com/Gitlawb/node/issues/97), [#99](https://github.com/Gitlawb/node/issues/99), [#101](https://github.com/Gitlawb/node/issues/101), [#104](https://github.com/Gitlawb/node/issues/104)) ([#111](https://github.com/Gitlawb/node/issues/111)) ([828dd27](https://github.com/Gitlawb/node/commit/828dd279a286f58bbb3c73627b2a1e23778b25cf))
* **node:** make Tigris repo hydration resilient to corrupt archives & failed writes ([#54](https://github.com/Gitlawb/node/issues/54)) ([7a99d0f](https://github.com/Gitlawb/node/commit/7a99d0f27cfa869e9f8a803f16cff30191745a51))
* **node:** preserve promisor mirror mode on unknown withheld-paths lookup ([#48](https://github.com/Gitlawb/node/issues/48)) ([#69](https://github.com/Gitlawb/node/issues/69)) ([96fcfdb](https://github.com/Gitlawb/node/commit/96fcfdb1ca6d4cd27226670068702c9f177e283a))
* **node:** reap leaked git child processes ([#53](https://github.com/Gitlawb/node/issues/53)) ([#61](https://github.com/Gitlawb/node/issues/61)) ([803d83e](https://github.com/Gitlawb/node/commit/803d83efdbcfa9d98affac1c5aaf8aacc511ae64))
* **node:** reject malformed path globs with non-trailing or empty-segment wildcards ([#74](https://github.com/Gitlawb/node/issues/74)) ([#75](https://github.com/Gitlawb/node/issues/75)) ([3d880cd](https://github.com/Gitlawb/node/commit/3d880cd56fed10e4c5ae787b52ce411384950f5e))
* **node:** skip withheld-walk when no path-scoped rule can withhold ([#60](https://github.com/Gitlawb/node/issues/60)) ([338ff83](https://github.com/Gitlawb/node/commit/338ff83584f2ab960be7e42ecec64191f5aaeb95))
* **release:** give crates explicit versions for release-please ([#129](https://github.com/Gitlawb/node/issues/129)) ([788a868](https://github.com/Gitlawb/node/commit/788a8686c1deafe03573703d72eb927cde81f54d))
* **release:** use simple release-type + generic Cargo.toml updaters ([#130](https://github.com/Gitlawb/node/issues/130)) ([12bfb1b](https://github.com/Gitlawb/node/commit/12bfb1b3c86b38f0b22d488cd6e85dfd96e0c37f))
* **security:** gate webhook creation through the public-host validator ([#81](https://github.com/Gitlawb/node/issues/81)) ([#92](https://github.com/Gitlawb/node/issues/92)) ([f28fa02](https://github.com/Gitlawb/node/commit/f28fa02236bd65c6a4fb690131ab14640cc53a12))
* **security:** reject non-public peer URLs + prune poisoned peers ([#78](https://github.com/Gitlawb/node/issues/78)) ([a8cc33a](https://github.com/Gitlawb/node/commit/a8cc33a185f2649d3fe100ec271ee5739a55eba7))
+1 -20
View File
@@ -55,29 +55,10 @@ Smart contracts live in a separate repo: [github.com/Gitlawb/contracts](https://
4. **Conventional commits.** Use `feat:`, `fix:`, `docs:`, `refactor:`, `test:`, `chore:`. Releases are automated by [release-please](https://github.com/googleapis/release-please) — your commit prefixes drive the next version bump.
5. **Format and lint.** Run `cargo fmt --all` and `cargo clippy --workspace --all-targets -- -D warnings` before submitting. CI will reject anything that fails these.
## What gets merged, what gets closed
We welcome contributions from humans and agents alike. To keep review sustainable, PRs are
expected to clear a basic quality bar:
- **Link an issue.** Bug fixes and features should reference an issue (`Closes #123`). For
protocol-level changes (identity, signatures, UCAN, ref certs, wire formats), open the
issue *before* writing code.
- **One change per PR.** Unrelated churn slows review and gets sent back.
- **Tests and a green pipeline.** New behavior needs tests; `cargo fmt`, `cargo clippy`,
and the full CI suite must pass.
- **A real description.** Say what changes and why. "Update code" is not a description.
A triage bot labels PRs that are missing these and leaves a short note. Nothing is closed
automatically while you're engaging. A flagged PR still missing a description after 14 days of
inactivity gets a stale warning, and is closed 7 days later if still untouched. A missing issue
link alone never triggers closure; that label stays advisory. Closed PRs can be reopened at any
time once updated.
## Development environment
**Requirements:**
- Rust stable (≥ 1.91) — install via [rustup](https://rustup.rs)
- Rust stable (≥ 1.85) — install via [rustup](https://rustup.rs)
- PostgreSQL — required for the node. Use the bundled `docker-compose.yml` for local dev.
- Docker (optional, for full-stack local testing)
Generated
+588 -230
View File
File diff suppressed because it is too large. Load diff
+2 -16
View File
@@ -5,20 +5,11 @@ members = [
"crates/gitlawb-node",
"crates/gl",
"crates/git-remote-gitlawb",
"crates/gitlawb-attest",
"crates/icaptcha-client",
]
[workspace.package]
# Per-crate versions live in each crate's [package] so release-please can manage
# them (it cannot rewrite an inherited `version.workspace = true`). They are kept
# in lockstep by release-please's generic updater: each crate's `version` line
# carries an `# x-release-please-version` annotation and is listed under
# `extra-files` in release-please-config.json. The release type is `simple`
# (not `rust`) because the rust strategy unconditionally tries to rewrite this
# virtual workspace root as a package manifest and errors out.
version = "0.3.8"
edition = "2021"
rust-version = "1.91"
license = "MIT OR Apache-2.0"
authors = ["gitlawb contributors"]
repository = "https://github.com/gitlawb/node"
@@ -29,13 +20,12 @@ tokio = { version = "1", features = ["full"] }
# serialization
serde = { version = "1", features = ["derive"] }
serde_json = "1"
serde_jcs = "0.2"
# errors
thiserror = "2"
anyhow = "1"
# crypto
ed25519-dalek = { version = "2", features = ["rand_core", "pkcs8", "pem"] }
rand = "0.8.6"
rand = "0.8"
sha2 = "0.10"
# encoding
hex = "0.4.3"
@@ -55,7 +45,3 @@ uuid = { version = "1", features = ["v4"] }
reqwest = { version = "0.12", features = ["blocking", "json", "multipart", "rustls-tls"], default-features = false }
# HMAC
hmac = "0.12"
[profile.release]
lto = "thin"
strip = "symbols"
+2 -11
View File
@@ -28,7 +28,6 @@ RUN mkdir -p crates/gitlawb-core/src crates/gitlawb-node/src crates/gl/src crate
# cargo can keep the dummy `fn main() {}` binaries from the cache layer above
# and the runtime container exits immediately with code 0.
COPY crates/ crates/
COPY bootstrap-peers.json ./
RUN find crates -name "*.rs" -exec touch {} + && \
rm -f target/release/gitlawb-node target/release/gl target/release/git-remote-gitlawb && \
rm -rf target/release/.fingerprint/gitlawb-node-* \
@@ -44,7 +43,6 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
git \
ca-certificates \
curl \
tini \
&& rm -rf /var/lib/apt/lists/*
# Non-root user for runtime
@@ -66,18 +64,11 @@ ENV GITLAWB_REPOS_DIR=/data/repos \
GITLAWB_PORT=7545 \
GITLAWB_P2P_PORT=7546
EXPOSE 7545 7546/udp
EXPOSE 7545 7546
VOLUME ["/data"]
HEALTHCHECK --interval=30s --timeout=5s --start-period=15s --retries=3 \
CMD curl -fsS http://127.0.0.1:${GITLAWB_PORT}/health || exit 1
# Run under tini so the node is never PID 1. As PID 1 a process must reap
# reparented orphans itself; the node does not, so git's reparented grandchildren
# (e.g. pack-objects orphaned when a served upload-pack dies on a client
# disconnect) would accumulate as zombies until fork() fails with EAGAIN (#53).
# tini reaps them and forwards SIGTERM/SIGINT to the node, which runs its own
# graceful shutdown. (No `-g`: the node manages its own children, so group-wide
# signalling would only disturb in-flight git helpers during shutdown.)
ENTRYPOINT ["tini", "--", "gitlawb-node"]
ENTRYPOINT ["gitlawb-node"]
+54 -436
View File
@@ -1,321 +1,49 @@
# Gitlawb Node
# gitlawb node
**Decentralized git infrastructure for developers, AI agents, and app delivery.**
**Decentralized git for AI agents and developers.** Run your own node, host repos under your own DID, and connect to the gitlawb network.
Gitlawb Node is the open-source node software behind the Gitlawb network. It lets anyone run a self-hosted node, publish repositories under a DID, sign writes with Ed25519 HTTP signatures, replicate git activity across peers, and move toward a resilient app-delivery network where code and build assets can be served closer to users.
This repository contains the open-source node software:
Gitlawb is not trying to be only “another git host.” The long-term direction is:
```txt
Decentralized GitHub
+ signed agent-native workflows
+ resilient repo replication
+ CDN-style app/code delivery
```
The mission is simple: once code is pushed to the network, it should not disappear because one server went down.
- `gitlawb-node` — Axum HTTP server, git smart-HTTP, libp2p gossip, optional S3-compatible storage
- `gl` — CLI for identity, repos, PRs, MCP server
- `git-remote-gitlawb` — `git remote helper` for `gitlawb://` URLs
- `gitlawb-core` — shared crypto primitives (DID, CID, HTTP signatures, UCAN)
---
## What is in this repository?
## Quickstart
This is a Rust workspace with four crates:
| Crate | Purpose |
|---|---|
| `gitlawb-node` | The node daemon: Axum HTTP server, git smart-HTTP, Postgres metadata, libp2p gossip, optional S3/Tigris/IPFS/Arweave/Base PoS hooks. |
| `gl` | The Gitlawb CLI for identity, repos, issues, PRs, bounties, tasks, peers, node status, MCP, and setup flows. |
| `git-remote-gitlawb` | Git remote helper for `gitlawb://` URLs, so normal `git clone`, `git fetch`, and `git push` can talk to Gitlawb nodes. |
| `gitlawb-core` | Shared primitives: Ed25519 identities, `did:key`, CIDs, RFC 9421 HTTP signatures, certificates, and UCAN tokens. |
---
## Why Gitlawb Nodes?
Most git hosting today depends on a small number of centralized platforms. Gitlawb Nodes are designed for a different model:
- **Own your identity** — every user, agent, and node is an Ed25519 keypair represented as `did:key:z6Mk...`.
- **Signed writes by default** — write requests use RFC 9421 HTTP Signatures instead of passwords.
- **Git-native transport** — repositories are still real git repositories served over smart HTTP.
- **Agent-native workflows** — the `gl` CLI and MCP server expose repo, issue, task, PR, and UCAN flows to AI agents.
- **Peer-aware delivery** — nodes can announce, discover, gossip, and sync with each other.
- **App CDN direction** — the network can evolve from decentralized code storage into code + asset + app delivery.
---
## Current status
Gitlawb Node is live early infrastructure. It is useful today, but some security and reliability features are intentionally staged for compatibility with existing nodes.
Good today:
- Local or Docker node startup.
- Postgres-backed repo metadata.
- Bare git repository storage.
- Git smart-HTTP clone/fetch/push.
- RFC 9421-signed writes.
- DID identities.
- `gl` CLI workflows.
- libp2p peer discovery/gossip foundation.
- Optional Tigris/S3 storage.
- Optional IPFS/Pinata and Arweave/Irys hooks.
- Optional Base node-operator staking/heartbeat hooks.
Known limitations:
- Private repository read enforcement is not wired yet. Treat public nodes as public infrastructure unless you restrict access at your proxy/firewall.
- UCAN chain validation and revocation are not complete.
- Repository write authorization is not capability-complete yet; HTTP signatures prove identity, not full authorization policy.
- Peer writes are signed by upgraded nodes, but strict signed-peer enforcement is opt-in during rolling upgrades.
- GraphQL mutations need mutation-aware auth before becoming a public write surface.
See:
- [`SECURITY.md`](SECURITY.md)
- [`docs/OSS-READINESS-AUDIT.md`](docs/OSS-READINESS-AUDIT.md)
- [`docs/MAINTAINER-ROADMAP.md`](docs/MAINTAINER-ROADMAP.md)
---
## Quickstart: run a local node
The fastest path is Docker Compose. It starts a node and Postgres.
The fastest way to run a node is via Docker. You'll get a node + Postgres locally with one command.
```bash
git clone https://github.com/Gitlawb/node.git
git clone https://github.com/gitlawb/node.git
cd node
cp .env.example .env
docker compose up -d
```
Your local node will serve:
Your node is now serving:
| Service | Default |
|---|---|
| HTTP API + git smart-HTTP | `http://localhost:7545` |
| libp2p QUIC/UDP | `7546` |
| Postgres | compose-managed |
- HTTP + git smart-HTTP on `:7545`
- libp2p gossip on `:7546`
Verify:
```bash
curl http://localhost:7545/health
curl http://localhost:7545/api/v1/stats
```
Expected health response:
```json
{ "status": "ok" }
```
Stop it:
```bash
docker compose down
```
---
## Install the CLI
## How it works
```bash
# npm (macOS / Linux)
npm install -g @gitlawb/gl
- **Identity** — every actor (human or agent) is an Ed25519 keypair → `did:key:z6Mk...`. No accounts, no passwords.
- **Auth** — every write is signed via HTTP Signatures (RFC 9421).
- **Delegation** — UCAN capability tokens.
- **Storage** — local disk + optional S3-compatible bucket (Tigris, MinIO, AWS S3).
- **Networking** — libp2p Gossipsub for ref-update events, Kademlia DHT for node discovery.
# Homebrew (macOS / Linux)
brew install gitlawb/tap/gl
# curl (macOS / Linux)
curl -fsSL https://gitlawb.com/install.sh | sh
# PowerShell (Windows)
irm https://gitlawb.com/install.ps1 | iex
```
Or build from source:
```bash
cargo build --release -p gl -p git-remote-gitlawb -p gitlawb-node
```
Put these binaries on your `PATH`:
```txt
target/release/gl
target/release/git-remote-gitlawb
target/release/gitlawb-node
```
Check your setup:
```bash
gl doctor
```
---
## First repo flow
Create an identity:
```bash
gl identity new
gl identity show
```
Register against your local node:
```bash
gl register --node http://localhost:7545
```
Create a repo:
```bash
gl repo create my-repo --description "My first Gitlawb repo" --node http://localhost:7545
```
Use the git remote helper:
```bash
export GITLAWB_NODE=http://localhost:7545
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
```txt
┌──────────────────────────┐
│ gl CLI / git / AI agents │
└────────────┬─────────────┘
│ signed HTTP writes / git smart-HTTP
↓
┌──────────────────────────┐
│ gitlawb-node │
│ Axum API + git routes │
└────────────┬─────────────┘
│
┌────────┴────────┐
↓ ↓
Postgres Bare git repos
metadata local disk / optional S3
│ │
└────────┬────────┘
↓
libp2p peers
gossip + discovery + sync
↓
optional IPFS / Arweave / Base PoS
```
### Core concepts
| Concept | Meaning |
|---|---|
| DID | A user, agent, or node identity derived from an Ed25519 public key. |
| HTTP Signature | RFC 9421 signature proving control of the DID key for write requests. |
| Ref certificate | Signed record of a ref update. Useful for audit and replication. |
| UCAN | Delegation token for future capability-based workflows. |
| Peer announce | Node-to-node HTTP announcement of DID + public URL. |
| Gossipsub | libp2p topic for ref-update events. |
| Smart HTTP | Standard git protocol over HTTP for clone/fetch/push. |
---
## API surface
The node exposes both git smart-HTTP routes and JSON APIs.
Common public read routes:
```txt
GET /health
GET /
GET /api/v1/stats
GET /api/v1/contracts
GET /api/v1/repos
GET /api/v1/repos/{owner}/{repo}
GET /api/v1/repos/{owner}/{repo}/tree
GET /api/v1/repos/{owner}/{repo}/blob/{path}
GET /api/v1/repos/{owner}/{repo}/issues
GET /api/v1/repos/{owner}/{repo}/pulls
GET /api/v1/peers
GET /{owner}/{repo}/info/refs
POST /{owner}/{repo}/git-upload-pack
```
Signed write routes include:
```txt
POST /api/v1/repos
POST /api/register
POST /api/v1/repos/{owner}/{repo}/fork
POST /api/v1/repos/{owner}/{repo}/issues
POST /api/v1/repos/{owner}/{repo}/pulls
POST /api/v1/repos/{owner}/{repo}/pulls/{number}/merge
POST /api/v1/repos/{owner}/{repo}/hooks
POST /api/v1/bounties/{id}/...
POST /{owner}/{repo}/git-receive-pack
```
These peer write routes support staged rollout:
```txt
POST /api/v1/peers/announce
POST /api/v1/sync/notify
```
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.
The node is **stateless beyond Postgres + the repos directory.** You can scale horizontally by pointing multiple nodes at a shared S3 bucket and database.
---
@@ -323,186 +51,76 @@ GITLAWB_REQUIRE_SIGNED_PEER_WRITES=true
All configuration is via environment variables. See [`.env.example`](.env.example) for the full reference.
Minimum required for a persistent node:
The minimum required:
```env
DATABASE_URL=postgresql://gitlawb:changeme@localhost:5432/gitlawb
```
- `DATABASE_URL` — Postgres connection string
Important node settings:
Everything else has sensible defaults. Optional features:
| Variable | Purpose |
|---|---|
| `GITLAWB_HOST` / `GITLAWB_PORT` | HTTP bind address and port. |
| `GITLAWB_REPOS_DIR` | Local bare repo storage directory. |
| `GITLAWB_PUBLIC_URL` | Public HTTP URL announced to peers. |
| `GITLAWB_P2P_PORT` | libp2p QUIC/UDP port. Use `0` to disable. |
| `GITLAWB_BOOTSTRAP_PEERS` | Comma-separated HTTP peer URLs. |
| `GITLAWB_P2P_BOOTSTRAP` | Comma-separated libp2p multiaddrs. |
| `GITLAWB_BOOTSTRAP_DISABLE_SEEDS` | Disable embedded seed peers for isolated dev/test networks. |
| `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. |
- `GITLAWB_TIGRIS_BUCKET` (+ AWS credentials) — S3-compatible shared storage
- `GITLAWB_PINATA_JWT` — IPFS warm-storage pinning
- `GITLAWB_IRYS_URL` — Arweave permanent anchoring
- `GITLAWB_BOOTSTRAP_PEERS` — comma-separated peer URLs to announce to on startup
- `GITLAWB_P2P_BOOTSTRAP` — comma-separated libp2p multiaddrs
Production note: change the default Postgres password before exposing a node publicly.
### On-chain Proof-of-Stake (advanced, optional)
The node supports an optional on-chain PoS layer where operators register their DID, stake $GITLAWB on Base L2, and receive a share of protocol fees. Smart contracts are in a separate repository at [github.com/gitlawb/contracts](https://github.com/gitlawb/contracts).
PoS is **disabled by default** and currently paused pending external audit. To enable, set `GITLAWB_CONTRACT_NODE_STAKING` and `GITLAWB_OPERATOR_PRIVATE_KEY`. See [`docs/RUN-A-NODE.md`](docs/RUN-A-NODE.md) for details.
---
## Optional node staking
## Build from source
Gitlawb Node includes optional Base L2 node-operator hooks. Operators can register a node DID, stake `$GITLAWB`, and post heartbeats.
PoS is disabled unless these are configured:
```env
GITLAWB_CONTRACT_NODE_STAKING=0x...
GITLAWB_OPERATOR_PRIVATE_KEY=0x...
GITLAWB_CHAIN_RPC_URL=https://mainnet.base.org
```
Recommended for operators:
```env
GITLAWB_OPERATOR_STRICT_MODE=true
GITLAWB_HEARTBEAT_INTERVAL_HOURS=20
```
Read:
- [`docs/RUN-A-NODE.md`](docs/RUN-A-NODE.md)
- [`docs/ECONOMICS.md`](docs/ECONOMICS.md)
Use a dedicated low-balance operator wallet. Do not use a treasury wallet as the heartbeat key.
---
## Building from source
Requires Rust 1.91+.
Requires Rust 1.85+ and a Postgres instance.
```bash
cargo build --release -p gitlawb-node -p gl -p git-remote-gitlawb
```
Run tests:
```bash
cargo fmt --all -- --check
cargo clippy --workspace --all-targets -- -D warnings
cargo test --workspace
```
Run the node from source:
```bash
DATABASE_URL=postgresql://gitlawb:changeme@localhost:5432/gitlawb \
cargo run -p gitlawb-node --release
```
Binaries are placed in `target/release/`. The `gl` and `git-remote-gitlawb` binaries should be on your `$PATH` for client use.
---
## macOS menu bar app
A native Swift/AppKit menu bar app is included for managing a local Docker Compose stack without living in the terminal.
Requirements:
- macOS 26+
- Xcode Command Line Tools
- Docker Desktop, OrbStack, or Colima
Build:
## CLI usage
```bash
./scripts/build-macos-app.sh
gl identity new
gl register --node http://localhost:7545
gl repo create my-repo --description "..."
git clone gitlawb://did:key:z6Mk.../my-repo
```
Output:
```txt
dist/Gitlawb Node.app
dist/Gitlawb Node.dmg
```
Features:
- Start/stop local node stack.
- Status indicator.
- Settings GUI.
- Auto-start on login.
- Docker runtime detection.
Unsigned local build:
```bash
xattr -cr "dist/Gitlawb Node.app"
```
Full CLI reference: `gl --help`.
---
## Roadmap
## Architecture
The current maintainer focus is live-network stability first.
Short-term priorities:
1. Keep CI green: fmt, clippy, tests, release build.
2. Add Docker and installer smoke tests.
3. Improve operator docs and `gl doctor` checks.
4. Harden peer writes and publish the signed-peer rollout plan.
5. Implement repo write authorization: owner checks, protected branches, and UCAN capability checks.
6. Implement private-read enforcement or remove private repo affordances until it exists.
7. Add metrics for pushes, fetches, pack sizes, peer sync, failed auth, and webhooks.
Product direction:
1. Reliable repo replication.
2. Health-aware peer syncing.
3. CDN-style clone/fetch routing to healthy replicas.
4. App asset/build delivery from nodes.
5. Operator dashboard and desktop UX.
Read the maintainer roadmap:
```txt
docs/MAINTAINER-ROADMAP.md
```
crates/
├── gitlawb-core/ crypto primitives (DID, CID, HTTP sigs, UCAN)
├── gitlawb-node/ node daemon (Axum + git smart-HTTP)
├── gl/ CLI
└── git-remote-gitlawb/ git remote helper
```
---
## Contributing
Start here:
- [`CONTRIBUTING.md`](CONTRIBUTING.md)
- [`docs/MAINTAINER-ROADMAP.md`](docs/MAINTAINER-ROADMAP.md)
- [`docs/OSS-READINESS-AUDIT.md`](docs/OSS-READINESS-AUDIT.md)
- [`SECURITY.md`](SECURITY.md)
Good first contribution areas:
- docs and install polish
- Docker smoke tests
- CLI error messages
- `gl doctor` checks
- operator dashboard UX
- test coverage for peer sync and signed writes
Security issues should follow [`SECURITY.md`](SECURITY.md).
---
See [`CONTRIBUTING.md`](CONTRIBUTING.md). Security issues: see [`SECURITY.md`](SECURITY.md).
## License
Licensed under either of:
Licensed under either of
- Apache License, Version 2.0 ([LICENSE-APACHE](LICENSE-APACHE) or http://www.apache.org/licenses/LICENSE-2.0)
- MIT license ([LICENSE-MIT](LICENSE-MIT) or http://opensource.org/licenses/MIT)
at your option.
Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in this project shall be dual licensed as above, without any additional terms or conditions.
### Contribution
Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in the work by you, as defined in the Apache-2.0 license, shall be dual licensed as above, without any additional terms or conditions.
+11 -22
View File
@@ -16,7 +16,7 @@ We will acknowledge receipt within 48 hours and aim to release a fix within 14 d
## Current Security Architecture
### Current live security controls
### What is production-ready (v0.1)
**Ed25519 identity and HTTP Signatures**
- Every write operation is signed with RFC 9421 HTTP Signatures
@@ -42,46 +42,35 @@ We will acknowledge receipt within 48 hours and aim to release a fix within 14 d
## Dependency Vulnerability Status
| Area | Status |
|------|--------|
| Dependabot alerts | Current open Rust alerts were addressed by updating vulnerable dependencies, removing libp2p mDNS, and moving P2P transport from TCP/Yamux to QUIC/UDP. |
| Crate | Advisory | Severity | Status |
|-------|----------|----------|--------|
| `rsa 0.9.x` | RUSTSEC-2023-0071 Marvin Attack | Medium | Unexploitable — bundled via `sqlx-mysql` internals; gitlawb uses PostgreSQL only, MySQL auth code is never executed. No upstream fix available. |
| `lru 0.12.x` | RUSTSEC-2026-0002 unsound IterMut | Warning | In `libp2p-swarm`; the specific unsafe code path is internal to libp2p and not reachable through gitlawb's usage. No upstream fix yet. |
---
## Known Limitations (Planned for v0.2)
These are **documented, accepted limitations** for the current live release and should be prioritized without breaking existing nodes during rolling upgrades.
These are **documented, accepted limitations** for the current testnet release. They will be addressed before mainnet.
### UCAN chain validation
- The auth middleware verifies HTTP Signatures and token structure, but does not yet walk the full UCAN delegation chain.
- **Impact:** A node cannot yet enforce fine-grained capability delegation. Currently, any registered agent with a valid HTTP Signature can push.
- **Mitigation:** Keep write endpoints signed, treat public nodes as public infrastructure, and treat trust scores as soft rate-limiting signals rather than authorization.
- **Mitigation:** Nodes can set `GITLAWB_PUBLIC_READ=false` to restrict access. The v0.1 trust score system provides soft rate limiting.
- **Fix target:** v0.2
### UCAN revocation
- Issued UCAN tokens cannot be revoked before expiry.
- **Impact:** If a keypair is compromised, the attacker retains access until the UCAN expires (default: 30 days).
- **Mitigation:** Regenerate your identity (`gl identity new --force`) and re-register to issue a new UCAN. Until revocation/blocklisting is implemented, operators should remove compromised DIDs directly from their local database.
- **Mitigation:** Regenerate your identity (`gl identity new --force`) and re-register to issue a new UCAN. Nodes will reject the old DID on sight if manually blocklisted.
- **Fix target:** v0.2
### git-receive-pack authentication
- The `git-receive-pack` endpoint enforces HTTP Signature auth. Plain Git smart-HTTP clients do not generate those headers, so the `git-remote-gitlawb` helper is required for pushes.
- **Impact:** Direct HTTP pushes without RFC 9421 headers are rejected; users need `gitlawb://` remotes or equivalent signed clients.
- **Mitigation:** Use `gitlawb://` remote URLs and keep `git-remote-gitlawb` on the user's `PATH`.
- The `git-receive-pack` endpoint enforces HTTP Signature auth via the `git-remote-gitlawb` remote helper. Direct HTTP push without the helper is currently unauthenticated on v0.1 nodes.
- **Impact:** A node operator accepting direct HTTP git pushes (not via `gitlawb://`) cannot verify the pusher's identity.
- **Mitigation:** Use `gitlawb://` remote URLs. Do not expose `POST /*/git-receive-pack` to untrusted networks.
- **Fix target:** v0.2
### Private repository reads
- Repository records have an `is_public` field and the node exposes `GITLAWB_PUBLIC_READ`, but per-repository private-read enforcement is not wired in the current live release.
- **Impact:** Do not store private repositories or secrets on public nodes.
- **Mitigation:** Run isolated nodes for non-public data and restrict network access at the reverse proxy or firewall layer.
- **Fix target:** v0.2
### Peer route hardening rollout
- Peer announce and sync notification routes accept signed requests and verify DID matches when a signature is present.
- **Impact:** Unsigned peer writes are still accepted by default so existing live nodes can keep communicating during rolling upgrades.
- **Mitigation:** After all active peers run signed-node builds, operators can set `GITLAWB_REQUIRE_SIGNED_PEER_WRITES=true`.
- **Fix target:** staged rollout
---
## Supported Versions
-47
View File
@@ -1,47 +0,0 @@
{
"$comment": "Canonical seed list for the Gitlawb network. Merged with GITLAWB_BOOTSTRAP_PEERS at startup. PRs to add public nodes welcome.",
"version": 1,
"updated": "2026-06-30",
"peers": [
{
"name": "gitlawb",
"operator": "Gitlawb",
"did": "did:key:z6MkqDnb7Siv3Cwj7pGJq4T5EsUisECqR8KpnDLwcaZq5TPr",
"http_url": "https://node.gitlawb.com",
"p2p_multiaddr": null,
"added": "2026-04-29"
},
{
"name": "gitlawb-node2",
"operator": "Gitlawb",
"did": null,
"http_url": "https://node2.gitlawb.com",
"p2p_multiaddr": null,
"added": "2026-06-30"
},
{
"name": "gitlawb-node3",
"operator": "Gitlawb",
"did": null,
"http_url": "https://node3.gitlawb.com",
"p2p_multiaddr": null,
"added": "2026-06-30"
},
{
"name": "gitlawb-manila",
"operator": "Gitlawb",
"did": null,
"http_url": "https://manila.gitlawb.com",
"p2p_multiaddr": null,
"added": "2026-06-30"
},
{
"name": "rapybus-gitlawb",
"operator": "RapyBus S.A.C.",
"did": "did:key:z6MktERLyhFpjUyN7dnkf7CYY5RXKJ6BTZiKohoi37YVBS7R",
"http_url": "https://rapybus-gitlawb.com",
"p2p_multiaddr": null,
"added": "2026-05-16"
}
]
}
+1 -5
View File
@@ -1,9 +1,8 @@
[package]
name = "git-remote-gitlawb"
description = "Git remote helper — enables 'git clone gitlawb://did:gitlawb:...'"
version = "0.5.1" # x-release-please-version
version.workspace = true
edition.workspace = true
rust-version.workspace = true
license.workspace = true
[[bin]]
@@ -16,6 +15,3 @@ anyhow = { workspace = true }
reqwest = { workspace = true }
tracing = { workspace = true }
tracing-subscriber = { workspace = true }
[dev-dependencies]
mockito = "1"
File diff suppressed because it is too large. Load diff
-22
View File
@@ -1,22 +0,0 @@
[package]
name = "gitlawb-attest"
description = "External Attestation v1: pluggable provenance attachments for gitlawb ref-update certs"
version = "0.5.1" # x-release-please-version
edition.workspace = true
rust-version.workspace = true
license.workspace = true
[dependencies]
serde = { workspace = true }
serde_json = { workspace = true }
serde_jcs = { workspace = true }
thiserror = { workspace = true }
ed25519-dalek = { workspace = true }
sha2 = { workspace = true }
hex = { workspace = true }
base64 = { workspace = true }
multibase = { workspace = true }
[dev-dependencies]
gitlawb-core = { path = "../gitlawb-core" }
rand = { workspace = true }
-557
View File
@@ -1,557 +0,0 @@
//! One typed, signed, cert-bound provenance blob.
//!
//! Fields: `type` (discriminator), `payload` (opaque, type-specific JSON),
//! `cert_hash` (binds to one ref-update cert), `signer` (`did:key`), and
//! `sig` (base64url-no-pad ed25519).
//!
//! The signature covers the domain-separated input
//! `b"gitlawb-attest-sig/v1\n"` followed by JCS-encoded `{type, payload,
//! cert_hash}` per RFC 8785. The domain tag is in the byte stream rather
//! than the canonical JSON so the wire shape stays additive: an `Attestation`
//! deserialized today and one constructed by a future `v2` signer differ only
//! by which tag the verifier prepends.
//!
//! Type discriminators are slash-separated namespace + version strings
//! (`covenant/exec/v1`, `slsa/v1.0`, `sigstore/dsse/v1`); verifiers register
//! by exact match.
use base64::{engine::general_purpose::URL_SAFE_NO_PAD as B64U, Engine};
use ed25519_dalek::{Signature, Signer, SigningKey, Verifier, VerifyingKey};
use serde::{de::DeserializeOwned, Deserialize, Serialize};
use crate::error::{Error, Result};
/// Domain-separation tag prepended to the JCS signing input. Bumped to
/// `v2` if the signing-input shape changes.
const SIGNING_DOMAIN: &[u8] = b"gitlawb-attest-sig/v1\n";
/// Multicodec varint prefix for Ed25519 public keys (0xed 0x01).
const ED25519_MULTICODEC: [u8; 2] = [0xed, 0x01];
/// A signed provenance blob attached to a ref-update cert.
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
pub struct Attestation {
/// Type discriminator, e.g. `covenant/exec/v1`.
#[serde(rename = "type")]
pub type_: String,
/// Type-specific payload. The verifier reparses into its concrete shape.
pub payload: serde_json::Value,
/// Lowercase SHA-256 hex of the cert body. Binds this attestation to one
/// cert. The lowercase form is canonical because the JCS signing input
/// includes this field verbatim — accepting mixed case on the wire would
/// require both signer and verifier to normalize before computing the
/// JCS bytes, an easy spec rule to miss across language ports.
pub cert_hash: String,
/// `did:key` of the signer; the verifying key is recoverable from it.
pub signer: String,
/// base64url-no-pad ed25519 signature over the JCS signing input.
pub sig: String,
}
/// Type-specific payload. Implement on a struct that is `Serialize +
/// DeserializeOwned` to participate.
pub trait AttestationPayload: Serialize + DeserializeOwned + Send + Sync {
/// The discriminator string written on the wire.
fn payload_type() -> &'static str;
}
#[derive(Serialize)]
struct SigningInput<'a> {
#[serde(rename = "type")]
type_: &'a str,
payload: &'a serde_json::Value,
cert_hash: &'a str,
}
impl Attestation {
/// Sign a fresh attestation. `cert_hash_bytes` comes from
/// [`crate::cert::cert_hash`].
pub fn sign<P: AttestationPayload>(
signing_key: &SigningKey,
payload: P,
cert_hash_bytes: [u8; 32],
) -> Result<Self> {
let type_ = P::payload_type().to_string();
validate_type(&type_)?;
let payload_value = serde_json::to_value(payload)?;
let cert_hash_hex = hex::encode(cert_hash_bytes);
let bytes = canonical_signing_bytes(&type_, &payload_value, &cert_hash_hex)?;
let sig: Signature = signing_key.sign(&bytes);
Ok(Self {
type_,
payload: payload_value,
cert_hash: cert_hash_hex,
signer: did_key_from_verifying_key(&signing_key.verifying_key()),
sig: B64U.encode(sig.to_bytes()),
})
}
/// Verify the signature and check that `cert_hash` matches
/// `expected_cert_hash`. Returns the recovered verifying key so the caller
/// can check it against an allowlist.
pub fn verify_signature(&self, expected_cert_hash: [u8; 32]) -> Result<VerifyingKey> {
let expected_hex = hex::encode(expected_cert_hash);
if self.cert_hash != expected_hex {
return Err(Error::CertHashMismatch);
}
validate_type(&self.type_)?;
let bytes = canonical_signing_bytes(&self.type_, &self.payload, &self.cert_hash)?;
let vk = verifying_key_from_did_key(&self.signer)?;
let sig_bytes: [u8; 64] = B64U
.decode(&self.sig)
.map_err(|e| Error::Signature(format!("base64url: {e}")))?
.try_into()
.map_err(|_| Error::Signature("signature must be 64 bytes".to_string()))?;
let sig = Signature::from_bytes(&sig_bytes);
vk.verify(&bytes, &sig)
.map_err(|e| Error::Signature(format!("ed25519: {e}")))?;
Ok(vk)
}
/// Reparse `payload` as `P`. Errors if the type discriminator does not
/// match `P::payload_type()`.
pub fn payload_as<P: AttestationPayload>(&self) -> Result<P> {
if self.type_ != P::payload_type() {
return Err(Error::Type(format!(
"expected '{}', got '{}'",
P::payload_type(),
self.type_
)));
}
Ok(P::deserialize(&self.payload)?)
}
}
/// Discriminator grammar: nonempty, ASCII-graphic only, slash-separated
/// segments of `[a-zA-Z0-9._+-]`, no empty segment, capped at 128 bytes.
/// Matches `covenant/exec/v1`, `slsa/v1.0`, `sigstore/dsse/v1`.
fn validate_type(t: &str) -> Result<()> {
if t.is_empty() {
return Err(Error::Type("empty discriminator".to_string()));
}
if t.len() > 128 {
return Err(Error::Type(format!(
"discriminator longer than 128 bytes ({})",
t.len()
)));
}
if !t.is_ascii() {
return Err(Error::Type(format!("discriminator must be ASCII: '{t}'")));
}
for segment in t.split('/') {
if segment.is_empty() {
return Err(Error::Type(format!(
"discriminator has an empty segment: '{t}'"
)));
}
for c in segment.chars() {
if !(c.is_ascii_alphanumeric() || c == '.' || c == '_' || c == '+' || c == '-') {
return Err(Error::Type(format!(
"discriminator segment '{segment}' has disallowed character '{c}'"
)));
}
}
}
Ok(())
}
fn canonical_signing_bytes(
type_: &str,
payload: &serde_json::Value,
cert_hash_hex: &str,
) -> Result<Vec<u8>> {
let input = SigningInput {
type_,
payload,
cert_hash: cert_hash_hex,
};
let jcs = serde_jcs::to_vec(&input).map_err(|e| Error::Jcs(e.to_string()))?;
let mut out = Vec::with_capacity(SIGNING_DOMAIN.len() + jcs.len());
out.extend_from_slice(SIGNING_DOMAIN);
out.extend_from_slice(&jcs);
Ok(out)
}
fn did_key_from_verifying_key(key: &VerifyingKey) -> String {
let mut buf = Vec::with_capacity(ED25519_MULTICODEC.len() + 32);
buf.extend_from_slice(&ED25519_MULTICODEC);
buf.extend_from_slice(&key.to_bytes());
let encoded = multibase::encode(multibase::Base::Base58Btc, &buf);
format!("did:key:{encoded}")
}
/// The DID:key spec mandates base58btc (multibase `z`-prefix). Other multibase
/// encodings of the same key bytes are rejected so allowlists, dedup, and
/// signer-pinning policies that compare `signer` strings remain consistent
/// across peers.
fn verifying_key_from_did_key(did: &str) -> Result<VerifyingKey> {
let method_id = did
.strip_prefix("did:key:")
.ok_or_else(|| Error::Did(format!("not a did:key: {did}")))?;
if !method_id.starts_with('z') {
return Err(Error::Did(format!(
"did:key must use base58btc (z-prefix): {did}"
)));
}
let (base, bytes) =
multibase::decode(method_id).map_err(|e| Error::Did(format!("multibase: {e}")))?;
if base != multibase::Base::Base58Btc {
return Err(Error::Did(format!(
"did:key must use base58btc (z-prefix): {did}"
)));
}
if bytes.len() != ED25519_MULTICODEC.len() + 32
|| bytes[..ED25519_MULTICODEC.len()] != ED25519_MULTICODEC
{
return Err(Error::Did("not an ed25519 did:key".to_string()));
}
let key_bytes: [u8; 32] = bytes[ED25519_MULTICODEC.len()..]
.try_into()
.expect("length checked above");
VerifyingKey::from_bytes(&key_bytes)
.map_err(|e| Error::Did(format!("invalid ed25519 key: {e}")))
}
#[cfg(test)]
mod tests {
use super::*;
use ed25519_dalek::SigningKey;
use rand::rngs::OsRng;
use serde::{Deserialize, Serialize};
fn fresh() -> SigningKey {
SigningKey::generate(&mut OsRng)
}
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
struct DummyPayload {
agent: String,
commit: String,
}
impl AttestationPayload for DummyPayload {
fn payload_type() -> &'static str {
"test/dummy/v1"
}
}
fn sample_cert_hash() -> [u8; 32] {
let mut h = [0u8; 32];
for (i, b) in h.iter_mut().enumerate() {
*b = i as u8;
}
h
}
fn dummy_attestation(sk: &SigningKey, cert_hash: [u8; 32]) -> Attestation {
Attestation::sign(
sk,
DummyPayload {
agent: "a".to_string(),
commit: "b".to_string(),
},
cert_hash,
)
.unwrap()
}
#[test]
fn sign_then_verify_roundtrip() {
let sk = fresh();
let cert_hash = sample_cert_hash();
let payload = DummyPayload {
agent: "did:key:z6MkTest".to_string(),
commit: "deadbeef".to_string(),
};
let att = Attestation::sign(&sk, payload.clone(), cert_hash).unwrap();
let vk = att.verify_signature(cert_hash).unwrap();
assert_eq!(vk.to_bytes(), sk.verifying_key().to_bytes());
assert_eq!(att.payload_as::<DummyPayload>().unwrap(), payload);
}
#[test]
fn cross_cert_replay_fails() {
let sk = fresh();
let cert_a = sample_cert_hash();
let mut cert_b = sample_cert_hash();
cert_b[0] ^= 0xff;
let att = dummy_attestation(&sk, cert_a);
let err = att.verify_signature(cert_b).unwrap_err();
assert!(matches!(err, Error::CertHashMismatch));
}
#[test]
fn tampered_payload_fails_verify() {
let sk = fresh();
let cert_hash = sample_cert_hash();
let mut att = dummy_attestation(&sk, cert_hash);
att.payload = serde_json::json!({ "agent": "evil", "commit": "b" });
let err = att.verify_signature(cert_hash).unwrap_err();
assert!(matches!(err, Error::Signature(_)));
}
#[test]
fn payload_as_wrong_type_errors() {
let sk = fresh();
let att = dummy_attestation(&sk, sample_cert_hash());
#[derive(Debug, Serialize, Deserialize)]
struct Wrong {
#[allow(dead_code)]
x: String,
}
impl AttestationPayload for Wrong {
fn payload_type() -> &'static str {
"test/other/v1"
}
}
let err = att.payload_as::<Wrong>().unwrap_err();
assert!(matches!(err, Error::Type(_)));
}
#[test]
fn json_roundtrip_preserves_signature() {
let sk = fresh();
let cert_hash = sample_cert_hash();
let att = dummy_attestation(&sk, cert_hash);
let json = serde_json::to_string(&att).unwrap();
let back: Attestation = serde_json::from_str(&json).unwrap();
back.verify_signature(cert_hash).unwrap();
}
/// Wire shape is part of the public protocol — pin field names so an
/// accidental rename surfaces as a test failure, not silent interop drift.
#[test]
fn wire_shape_pins_field_names() {
let sk = fresh();
let att = dummy_attestation(&sk, sample_cert_hash());
let v: serde_json::Value = serde_json::to_value(&att).unwrap();
let obj = v.as_object().expect("attestation must serialize as object");
let keys: std::collections::BTreeSet<&str> = obj.keys().map(String::as_str).collect();
let expected: std::collections::BTreeSet<&str> =
["type", "payload", "cert_hash", "signer", "sig"]
.into_iter()
.collect();
assert_eq!(keys, expected);
assert!(obj["type"].is_string());
assert!(obj["cert_hash"].is_string());
assert!(obj["signer"].is_string());
assert!(obj["sig"].is_string());
}
/// The spec mandates lowercase hex on the wire. An uppercase cert_hash
/// is rejected as `CertHashMismatch` so a non-canonical signer can't
/// produce attestations that verify against some peers but not others.
#[test]
fn uppercase_cert_hash_is_rejected_as_non_canonical() {
let sk = fresh();
let cert_hash = sample_cert_hash();
let mut att = dummy_attestation(&sk, cert_hash);
att.cert_hash = att.cert_hash.to_uppercase();
let err = att.verify_signature(cert_hash).unwrap_err();
assert!(matches!(err, Error::CertHashMismatch));
}
#[test]
fn empty_type_rejected_at_signing() {
#[derive(Serialize, Deserialize)]
struct Empty {}
impl AttestationPayload for Empty {
fn payload_type() -> &'static str {
""
}
}
let sk = fresh();
let err = Attestation::sign(&sk, Empty {}, sample_cert_hash()).unwrap_err();
assert!(matches!(err, Error::Type(_)));
}
#[test]
fn validate_type_grammar() {
validate_type("covenant/exec/v1").unwrap();
validate_type("slsa/v1.0").unwrap();
validate_type("sigstore/dsse/v1").unwrap();
validate_type("a").unwrap();
validate_type("a.b-c_d+e/x").unwrap();
for bad in [
"",
" ",
"covenant/exec/v1 ",
"covenant//v1",
"/covenant/v1",
"covenant/v1/",
"covenant\x00exec/v1",
"covenant/exec\nv1",
"сovenant/exec/v1",
"covenant/ex ec/v1",
"covenant/exec/v1#frag",
] {
let err = validate_type(bad).unwrap_err();
assert!(matches!(err, Error::Type(_)), "must reject '{bad}'");
}
let too_long = "a/".repeat(70);
let err = validate_type(&too_long).unwrap_err();
assert!(matches!(err, Error::Type(_)));
}
#[test]
fn did_key_must_be_base58btc() {
// Sign with a real key, then re-encode the public-key bytes in a
// different multibase. Verification must reject.
let sk = fresh();
let mut att = dummy_attestation(&sk, sample_cert_hash());
let mut buf = Vec::with_capacity(34);
buf.extend_from_slice(&ED25519_MULTICODEC);
buf.extend_from_slice(&sk.verifying_key().to_bytes());
for base in [
multibase::Base::Base64Url,
multibase::Base::Base32Lower,
multibase::Base::Base16Lower,
] {
att.signer = format!("did:key:{}", multibase::encode(base, &buf));
let err = att.verify_signature(sample_cert_hash()).unwrap_err();
assert!(matches!(err, Error::Did(_)), "must reject base {base:?}");
}
}
#[test]
fn verify_rejects_did_without_did_key_prefix() {
let sk = fresh();
let mut att = dummy_attestation(&sk, sample_cert_hash());
att.signer = "ed25519:abc".to_string();
let err = att.verify_signature(sample_cert_hash()).unwrap_err();
assert!(matches!(err, Error::Did(_)));
}
#[test]
fn verify_rejects_did_with_wrong_multicodec() {
let sk = fresh();
let mut att = dummy_attestation(&sk, sample_cert_hash());
// 0x12 0x00 = sha2-256 multicodec — wrong for an ed25519 public key.
let mut buf = vec![0x12, 0x00];
buf.extend_from_slice(&sk.verifying_key().to_bytes());
att.signer = format!(
"did:key:{}",
multibase::encode(multibase::Base::Base58Btc, &buf)
);
let err = att.verify_signature(sample_cert_hash()).unwrap_err();
assert!(matches!(err, Error::Did(_)));
}
#[test]
fn verify_rejects_did_with_wrong_key_length() {
let sk = fresh();
let mut att = dummy_attestation(&sk, sample_cert_hash());
let mut buf = Vec::with_capacity(33);
buf.extend_from_slice(&ED25519_MULTICODEC);
// 31 bytes instead of 32.
buf.extend_from_slice(&sk.verifying_key().to_bytes()[..31]);
att.signer = format!(
"did:key:{}",
multibase::encode(multibase::Base::Base58Btc, &buf)
);
let err = att.verify_signature(sample_cert_hash()).unwrap_err();
assert!(matches!(err, Error::Did(_)));
}
#[test]
fn verify_rejects_bad_signature_base64() {
let sk = fresh();
let mut att = dummy_attestation(&sk, sample_cert_hash());
att.sig = "!!not-base64!!".to_string();
let err = att.verify_signature(sample_cert_hash()).unwrap_err();
assert!(matches!(err, Error::Signature(_)));
}
#[test]
fn verify_rejects_signature_wrong_length() {
let sk = fresh();
let mut att = dummy_attestation(&sk, sample_cert_hash());
att.sig = B64U.encode([0u8; 32]); // valid base64, wrong size.
let err = att.verify_signature(sample_cert_hash()).unwrap_err();
assert!(matches!(err, Error::Signature(_)));
}
/// A payload that happens to contain a `cert_hash` field of its own does
/// not interfere with the outer binding: the attestation envelope's
/// `cert_hash` is the only field consulted by `verify_signature`, and the
/// payload is treated as opaque JSON throughout. A reviewer worried about
/// shadowing or smuggling can verify this directly.
#[test]
fn payload_cert_hash_field_does_not_shadow_outer_binding() {
#[derive(Serialize, Deserialize)]
struct Sneaky {
cert_hash: String,
x: String,
}
impl AttestationPayload for Sneaky {
fn payload_type() -> &'static str {
"test/sneaky/v1"
}
}
let sk = fresh();
let outer_hash = sample_cert_hash();
let att = Attestation::sign(
&sk,
Sneaky {
cert_hash: "forged-by-the-attacker".to_string(),
x: "y".to_string(),
},
outer_hash,
)
.unwrap();
// Envelope's cert_hash is the outer (real) hash, lowercase hex.
assert_eq!(att.cert_hash, hex::encode(outer_hash));
// Payload retains its own field — opaque to the protocol.
assert_eq!(
att.payload.get("cert_hash").and_then(|v| v.as_str()),
Some("forged-by-the-attacker"),
);
// Verification binds to the outer envelope's cert_hash.
att.verify_signature(outer_hash).unwrap();
// And rejects when the outer cert hash differs.
let mut wrong = outer_hash;
wrong[0] ^= 0xff;
let err = att.verify_signature(wrong).unwrap_err();
assert!(matches!(err, Error::CertHashMismatch));
}
/// A different protocol that also signs `{type, payload, cert_hash}` with
/// the same key would still fail attestation verification because the
/// signing input carries a domain tag the other protocol does not include.
#[test]
fn cross_protocol_replay_is_rejected_by_domain_separation() {
let sk = fresh();
let cert_hash = sample_cert_hash();
let att = dummy_attestation(&sk, cert_hash);
// Sign the same JCS bytes WITHOUT the domain tag and graft the
// signature back onto the attestation.
let cert_hash_hex = hex::encode(cert_hash);
let bare = serde_jcs::to_vec(&SigningInput {
type_: &att.type_,
payload: &att.payload,
cert_hash: &cert_hash_hex,
})
.unwrap();
let other_sig: Signature = sk.sign(&bare);
let mut tampered = att.clone();
tampered.sig = B64U.encode(other_sig.to_bytes());
let err = tampered.verify_signature(cert_hash).unwrap_err();
assert!(matches!(err, Error::Signature(_)));
}
}
-327
View File
@@ -1,327 +0,0 @@
//! Envelope around a `gitlawb/ref-update/v1` cert plus optional attestations,
//! and the cert-hash helper attestations bind to.
//!
//! An empty envelope serializes to the same bytes as the underlying bare cert.
//! `cert_hash` strips `signatures` and `attestations`, JCS-encodes the rest,
//! and SHA-256s; the result is what every attestation binds to.
use serde::{Deserialize, Serialize};
use sha2::{Digest, Sha256};
use crate::attestation::Attestation;
use crate::error::{Error, Result};
use crate::verifier::{Registry, VerifiedAttestation};
/// The discriminator the wrapped cert must carry. Matches the constant of the
/// same name in `gitlawb-core::cert`.
pub const CERT_TYPE: &str = "gitlawb/ref-update/v1";
/// A ref-update cert with optional attestations.
///
/// The cert is flattened into the top-level JSON, so an empty envelope
/// produces the same bytes as a bare cert and existing decoders ignore the
/// extra `attestations` field. The cert is held as `serde_json::Value` so
/// this crate has no runtime dependency on `gitlawb-core::cert::RefUpdateCert`.
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct AttestedRefUpdateCert {
/// The cert body and signatures, flattened to the top level.
#[serde(flatten)]
pub cert: serde_json::Value,
/// Attached attestations. Empty when absent on the wire.
#[serde(default, skip_serializing_if = "Vec::is_empty")]
pub attestations: Vec<Attestation>,
}
impl AttestedRefUpdateCert {
/// Wrap a cert. No attestations are attached yet.
///
/// The serialized cert must be a JSON object whose `type` field equals
/// [`CERT_TYPE`] and which does **not** already carry an `attestations`
/// field. The second rule catches two cases that would otherwise leave
/// the envelope in an inconsistent in-memory state:
///
/// - Double-wrap: `from_cert(&previously_wrapped_envelope)` would put the
/// inner attestations on `self.cert` and leave `self.attestations` empty.
/// - Pre-attested cert from a peer: a malformed or malicious cert with an
/// attached `attestations` field would survive `cert_hash` (which strips
/// the field) but bypass the wrapper's append-and-verify path entirely.
///
/// Both are rejected with [`Error::Payload`]. To re-wrap, deserialize the
/// envelope as `AttestedRefUpdateCert` directly.
pub fn from_cert<T: Serialize>(cert: &T) -> Result<Self> {
let value = serde_json::to_value(cert)?;
let obj = value
.as_object()
.ok_or_else(|| Error::Payload("cert must serialize as a JSON object".to_string()))?;
match obj.get("type").and_then(|v| v.as_str()) {
Some(t) if t == CERT_TYPE => {}
Some(other) => {
return Err(Error::Payload(format!(
"cert type must be '{CERT_TYPE}', got '{other}'"
)));
}
None => {
return Err(Error::Payload(format!(
"cert missing 'type' field (expected '{CERT_TYPE}')"
)));
}
}
if obj.contains_key("attestations") {
return Err(Error::Payload(
"cert already carries an 'attestations' field; deserialize as \
AttestedRefUpdateCert directly instead of re-wrapping"
.to_string(),
));
}
Ok(Self {
cert: value,
attestations: Vec::new(),
})
}
/// The 32-byte cert hash every attached attestation must bind to.
pub fn cert_hash(&self) -> Result<[u8; 32]> {
cert_hash(&self.cert)
}
/// Append an already-signed attestation.
pub fn attach(&mut self, attestation: Attestation) {
self.attestations.push(attestation);
}
/// Verify every attached attestation against this envelope's cert hash,
/// applying the registry's policy. Equivalent to
/// `registry.verify_all(&self.attestations, self.cert_hash()?)` but
/// reads as one operation at call sites.
pub fn verify_attestations(&self, registry: &Registry) -> Result<Vec<VerifiedAttestation>> {
registry.verify_all(&self.attestations, self.cert_hash()?)
}
}
/// SHA-256 of the cert body. The body must be a JSON object; `signatures` and
/// `attestations` are stripped before JCS encoding (RFC 8785), so the hash is
/// reproducible across languages and JSON libraries and is stable across
/// countersignatures.
pub fn cert_hash(cert: &serde_json::Value) -> Result<[u8; 32]> {
let mut body = cert.clone();
let obj = body
.as_object_mut()
.ok_or_else(|| Error::Payload("cert body must be a JSON object".to_string()))?;
obj.remove("signatures");
obj.remove("attestations");
let bytes = serde_jcs::to_vec(&body).map_err(|e| Error::Jcs(e.to_string()))?;
let mut h = Sha256::new();
h.update(&bytes);
let out = h.finalize();
let mut arr = [0u8; 32];
arr.copy_from_slice(&out);
Ok(arr)
}
#[cfg(test)]
mod tests {
use super::*;
use serde_json::json;
fn bare_cert() -> serde_json::Value {
json!({
"type": CERT_TYPE,
"repo": "did:key:z6MkRepo",
"ref_name": "refs/heads/main",
"from": "0".repeat(64),
"to": "a".repeat(64),
"seq": 1,
"timestamp": "2026-01-01T00:00:00Z",
"nonce": "n1",
"signatures": [{"signer": "did:key:z6MkRepo", "sig": "abc"}]
})
}
#[test]
fn empty_envelope_serializes_as_bare_cert() {
let bare = bare_cert();
let env = AttestedRefUpdateCert::from_cert(&bare).unwrap();
let env_json: serde_json::Value =
serde_json::from_str(&serde_json::to_string(&env).unwrap()).unwrap();
let bare_keys: std::collections::BTreeSet<&String> =
bare.as_object().unwrap().keys().collect();
let env_keys: std::collections::BTreeSet<&String> =
env_json.as_object().unwrap().keys().collect();
assert_eq!(bare_keys, env_keys);
}
#[test]
fn bare_cert_parses_as_envelope_with_no_attestations() {
let bare = bare_cert();
let env: AttestedRefUpdateCert = serde_json::from_value(bare.clone()).unwrap();
assert!(env.attestations.is_empty());
assert_eq!(env.cert, bare);
}
#[test]
fn cert_hash_is_stable_across_countersignatures() {
let base_body = json!({
"type": CERT_TYPE,
"repo": "did:key:z6MkRepo",
"ref_name": "refs/heads/main",
"from": "0".repeat(64),
"to": "a".repeat(64),
"seq": 1,
"timestamp": "2026-01-01T00:00:00Z",
"nonce": "n1"
});
let mut one_sig = base_body.clone();
one_sig["signatures"] = json!([{"signer": "x", "sig": "y"}]);
let mut two_sigs = base_body.clone();
two_sigs["signatures"] = json!([
{"signer": "x", "sig": "y"},
{"signer": "a", "sig": "b"}
]);
assert_eq!(cert_hash(&one_sig).unwrap(), cert_hash(&two_sigs).unwrap());
}
#[test]
fn cert_hash_changes_when_body_changes() {
let body_a = json!({
"type": CERT_TYPE,
"repo": "did:key:z6MkRepo",
"ref_name": "refs/heads/main",
"from": "0".repeat(64),
"to": "a".repeat(64),
"seq": 1,
"timestamp": "2026-01-01T00:00:00Z",
"nonce": "n1",
"signatures": []
});
let mut body_b = body_a.clone();
body_b["to"] = json!("b".repeat(64));
assert_ne!(cert_hash(&body_a).unwrap(), cert_hash(&body_b).unwrap());
}
#[test]
fn cert_hash_rejects_non_object_root() {
let err = cert_hash(&json!(null)).unwrap_err();
assert!(matches!(err, Error::Payload(_)));
let err = cert_hash(&json!([1, 2, 3])).unwrap_err();
assert!(matches!(err, Error::Payload(_)));
let err = cert_hash(&json!("scalar")).unwrap_err();
assert!(matches!(err, Error::Payload(_)));
}
#[test]
fn from_cert_rejects_wrong_type() {
let wrong = json!({"type": "gitlawb/ref-update/v0", "repo": "did:key:z"});
let err = AttestedRefUpdateCert::from_cert(&wrong).unwrap_err();
assert!(matches!(err, Error::Payload(_)));
}
#[test]
fn from_cert_rejects_missing_type() {
let no_type = json!({"repo": "did:key:z"});
let err = AttestedRefUpdateCert::from_cert(&no_type).unwrap_err();
assert!(matches!(err, Error::Payload(_)));
}
#[test]
fn from_cert_rejects_non_object() {
let arr = json!([1, 2, 3]);
let err = AttestedRefUpdateCert::from_cert(&arr).unwrap_err();
assert!(matches!(err, Error::Payload(_)));
}
#[test]
fn mutating_env_cert_changes_the_hash() {
let mut env = AttestedRefUpdateCert::from_cert(&bare_cert()).unwrap();
let hash_before = env.cert_hash().unwrap();
env.cert.as_object_mut().unwrap().insert(
"nonce".to_string(),
serde_json::Value::String("mutated".to_string()),
);
let hash_after = env.cert_hash().unwrap();
assert_ne!(hash_before, hash_after);
}
/// A cert that already carries an `attestations` field is rejected
/// regardless of the field's contents. Catches double-wrap (where the
/// inner attestations would otherwise be smuggled into `self.cert`) and
/// peer-supplied "pre-attested" certs that would bypass the wrapper.
#[test]
fn from_cert_rejects_preexisting_attestations_field() {
let mut sneaky = bare_cert();
sneaky["attestations"] = json!([{"smuggled": true}]);
let err = AttestedRefUpdateCert::from_cert(&sneaky).unwrap_err();
assert!(matches!(err, Error::Payload(_)));
// Empty array still rejected — the field's mere presence is the signal.
let mut empty = bare_cert();
empty["attestations"] = json!([]);
let err = AttestedRefUpdateCert::from_cert(&empty).unwrap_err();
assert!(matches!(err, Error::Payload(_)));
}
/// `from_cert` on an already-wrapped envelope is the same case as
/// `from_cert` on a cert with a pre-existing `attestations` field: serde
/// flattens the envelope back into a JSON object that carries the field.
#[test]
fn from_cert_rejects_a_previously_wrapped_envelope() {
let mut env = AttestedRefUpdateCert::from_cert(&bare_cert()).unwrap();
// Inject an attestation-shaped value so the wire round-trip would
// actually re-emit the field.
env.cert
.as_object_mut()
.unwrap()
.insert("attestations".to_string(), json!([]));
let err = AttestedRefUpdateCert::from_cert(&env).unwrap_err();
assert!(matches!(err, Error::Payload(_)));
}
/// `attestations: null` is explicitly not the same as missing. The
/// `#[serde(default)]` attribute only fills in when the key is absent —
/// a present-but-null wire field is rejected, which surfaces malformed
/// payloads early instead of silently treating them as empty.
#[test]
fn attestations_null_on_wire_is_rejected() {
let mut with_null = bare_cert();
with_null["attestations"] = serde_json::Value::Null;
let err = serde_json::from_value::<AttestedRefUpdateCert>(with_null).unwrap_err();
let msg = format!("{err}");
assert!(
msg.contains("expected a sequence") || msg.contains("invalid type"),
"unexpected error: {msg}"
);
}
#[test]
fn attestations_string_on_wire_is_rejected() {
let mut with_str = bare_cert();
with_str["attestations"] = serde_json::Value::String("oops".to_string());
let err = serde_json::from_value::<AttestedRefUpdateCert>(with_str).unwrap_err();
let msg = format!("{err}");
assert!(msg.contains("expected a sequence") || msg.contains("invalid type"));
}
/// `attach` does not deduplicate. Duplicate attestations are a verifier-
/// policy concern (e.g., "at most one SLSA provenance"), not a wrapper
/// concern. Pinning the behavior so a future deduplication change is an
/// intentional break.
#[test]
fn attach_does_not_deduplicate() {
let mut env = AttestedRefUpdateCert::from_cert(&bare_cert()).unwrap();
let att = Attestation {
type_: "demo/v1".to_string(),
payload: serde_json::json!({}),
cert_hash: "deadbeef".to_string(),
signer: "did:key:z6MkDup".to_string(),
sig: "AAAA".to_string(),
};
env.attach(att.clone());
env.attach(att);
assert_eq!(env.attestations.len(), 2);
}
}
-46
View File
@@ -1,46 +0,0 @@
use thiserror::Error;
/// Errors from building or verifying an attestation.
#[derive(Debug, Error)]
pub enum Error {
/// Discriminator failed validation (empty, whitespace, control char,
/// disallowed grammar).
#[error("attestation type: {0}")]
Type(String),
/// Attestation was signed against a different cert.
#[error("cert hash mismatch")]
CertHashMismatch,
/// Ed25519 signature failed verification.
#[error("signature: {0}")]
Signature(String),
/// DID could not be parsed.
#[error("did: {0}")]
Did(String),
/// Payload structure check failed, or the cert body was not a JSON object.
#[error("payload: {0}")]
Payload(String),
/// No verifier registered for the type and policy required one.
#[error("no verifier registered for type '{0}'")]
UnknownType(String),
/// `RequireAll` policy did not find an entry for a required type, or the
/// entry was not fully verified.
#[error("required attestation type missing or unverified: '{0}'")]
RequiredMissing(String),
/// JSON failure.
#[error("json: {0}")]
Json(#[from] serde_json::Error),
/// JCS encoding failure.
#[error("jcs: {0}")]
Jcs(String),
}
/// Crate result alias.
pub type Result<T> = std::result::Result<T, Error>;
-132
View File
@@ -1,132 +0,0 @@
//! Pluggable provenance attachments for gitlawb ref-update certs.
//!
//! A `gitlawb/ref-update/v1` cert proves who pushed and where a ref moved to.
//! It does not say how the commit was produced. This crate adds an optional
//! `attestations` field that lets any provenance system (SLSA, Sigstore,
//! in-toto, agent runtimes) attach a typed, signed blob bound to the cert by
//! its hash.
//!
//! The cert format stays additive. A cert with no attestations serializes the
//! same bytes it does today, and existing decoders (which do not set
//! `deny_unknown_fields`) silently drop the new `attestations` field rather
//! than reject the cert.
//!
//! ## Wire shape
//!
//! ```json
//! {
//! "type": "gitlawb/ref-update/v1",
//! // ...standard cert fields...,
//! "signatures": [...],
//! "attestations": [
//! {
//! "type": "covenant/exec/v1",
//! "payload": { /* opaque, type-specific */ },
//! "cert_hash": "<sha256 hex of JCS-encoded cert body>",
//! "signer": "did:key:z6Mk...",
//! "sig": "<base64url ed25519 over the signing input>"
//! }
//! ]
//! }
//! ```
//!
//! ## Canonical bytes
//!
//! Hashing and signing inputs use JCS (RFC 8785) so they reproduce across
//! implementations regardless of struct field order or JSON library.
//!
//! The cert hash is `SHA-256(JCS(cert_body_without_signatures_or_attestations))`,
//! expressed as lowercase hex on the wire. Uppercase is non-canonical and
//! rejected on verify so the JCS signing input is uniquely determined by the
//! cert bytes alone — there is no implicit normalization rule that
//! cross-language signers might miss.
//!
//! The attestation signing input is the byte string
//! `b"gitlawb-attest-sig/v1\n" || JCS({type, payload, cert_hash})`. The
//! domain tag is in the byte stream, not the canonical JSON, so an attestation
//! cannot be confused with a same-shape JCS document signed for a different
//! protocol that uses the same Ed25519 key.
//!
//! ## DID:key
//!
//! Signers are `did:key` DIDs over Ed25519, encoded with the multibase
//! base58btc (`z`) prefix per the W3C DID:key specification. Non-base58btc
//! encodings of the same public key are rejected on verify so allowlists,
//! deduplication, and signer-pinning policies that compare `signer` strings
//! stay consistent across peers.
//!
//! ## Verification
//!
//! [`Registry`] looks up a verifier by type discriminator. [`Policy`] decides
//! what to do when no verifier matches: `AcceptKnown` (default) lets unknown
//! types pass without trust; `RequireAll` enforces a per-repo allowlist while
//! still letting unrelated attached attestations through unverified (so a
//! third-party attachment cannot DoS the cert); `RejectUnknown` rejects
//! anything unregistered.
//!
//! ## Quick start
//!
//! ```
//! use ed25519_dalek::SigningKey;
//! use gitlawb_attest::{
//! Attestation, AttestationPayload, AttestationVerifier, AttestedRefUpdateCert,
//! Error, Policy, Registry, Result, CERT_TYPE,
//! };
//! use serde::{Deserialize, Serialize};
//!
//! #[derive(Serialize, Deserialize)]
//! struct ExecPayload { agent: String }
//! impl AttestationPayload for ExecPayload {
//! fn payload_type() -> &'static str { "covenant/exec/v1" }
//! }
//!
//! struct ExecVerifier;
//! impl AttestationVerifier for ExecVerifier {
//! fn type_(&self) -> &'static str { "covenant/exec/v1" }
//! fn verify_payload(&self, payload: &serde_json::Value) -> Result<()> {
//! payload.get("agent").and_then(|v| v.as_str())
//! .ok_or_else(|| Error::Payload("missing agent".into()))?;
//! Ok(())
//! }
//! }
//!
//! # fn run() -> Result<()> {
//! let cert = serde_json::json!({
//! "type": CERT_TYPE, "repo": "did:key:z6MkRepo",
//! "ref_name": "refs/heads/main",
//! "from": "0".repeat(64), "to": "a".repeat(64),
//! "seq": 1, "timestamp": "2026-01-01T00:00:00Z", "nonce": "n1",
//! "signatures": []
//! });
//! let mut env = AttestedRefUpdateCert::from_cert(&cert)?;
//!
//! let sk = SigningKey::from_bytes(&[7u8; 32]);
//! let payload = ExecPayload { agent: "did:key:z6MkAgent".into() };
//! let att = Attestation::sign(&sk, payload, env.cert_hash()?)?;
//! env.attach(att);
//!
//! let mut registry = Registry::new().with_policy(Policy::RejectUnknown);
//! registry.register(ExecVerifier);
//! let verified = env.verify_attestations(&registry)?;
//! assert_eq!(verified[0].type_, "covenant/exec/v1");
//! assert!(verified[0].fully_verified);
//! # Ok(()) }
//! # run().unwrap();
//! ```
pub mod attestation;
pub mod cert;
pub mod error;
pub mod verifier;
pub use attestation::{Attestation, AttestationPayload};
pub use cert::{cert_hash, AttestedRefUpdateCert, CERT_TYPE};
pub use error::{Error, Result};
pub use verifier::{AttestationVerifier, Policy, Registry, VerifiedAttestation};
/// Version string for the attestation envelope wire shape.
///
/// Bumped only when the binding rules — JCS input shape, domain-separation
/// tag, hash algorithm — change. Independent of [`CERT_TYPE`], which versions
/// the underlying ref-update cert.
pub const ATTEST_ENVELOPE_VERSION: &str = "v1";
-377
View File
@@ -1,377 +0,0 @@
//! Verifier trait, registry, and policy.
//!
//! A [`Registry`] maps a type discriminator to a verifier. [`Policy`] decides
//! what happens for types nothing is registered for: accept without trust,
//! reject, or require an allowlist.
//!
//! Under [`Policy::RequireAll`] the registry never short-circuits on unknown
//! types — any attestation can be attached by any third party, so blocking
//! the cert because an attacker added an unrelated `attacker/spam/v1` would
//! be a denial-of-service vector. Unknown types are silently treated as
//! `fully_verified = false`; the allowlist is enforced only by the
//! presence-and-verified check on `required_types` after the batch runs.
use std::collections::HashMap;
use crate::attestation::Attestation;
use crate::error::{Error, Result};
/// Verifier for one attestation type. Implementors declare the discriminator
/// they handle and validate the payload's shape. The signature and cert-hash
/// binding are checked by [`Registry::verify`] before `verify_payload` runs.
pub trait AttestationVerifier: Send + Sync {
/// The discriminator this verifier handles. Must be a `'static` literal
/// so the registry can key on it without copying.
fn type_(&self) -> &'static str;
/// Validate payload structure. Signature is already verified.
fn verify_payload(&self, payload: &serde_json::Value) -> Result<()>;
}
/// What to do for attestation types with no registered verifier.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Default)]
pub enum Policy {
/// Unknown types pass but are flagged `fully_verified = false`. Default.
#[default]
AcceptKnown,
/// Every entry in `required_types` must be present and fully verified.
/// Unknown types beyond the required set are still accepted unverified,
/// so a malicious extra attestation cannot DoS the cert.
RequireAll,
/// Reject every attestation whose type is not registered.
RejectUnknown,
}
/// Result of verifying one attestation.
#[derive(Debug, Clone)]
pub struct VerifiedAttestation {
/// Type discriminator.
pub type_: String,
/// Signer's `did:key`.
pub signer: String,
/// Lowercase SHA-256 hex of the cert body the attestation bound to.
pub cert_hash: String,
/// `true` when a verifier ran a payload check and accepted it. `false`
/// when the policy let an unknown type through without one.
pub fully_verified: bool,
}
/// Verifiers keyed by type discriminator.
#[derive(Default)]
pub struct Registry {
by_type: HashMap<&'static str, Box<dyn AttestationVerifier>>,
policy: Policy,
required_types: Vec<String>,
}
impl Registry {
/// Empty registry with the default policy.
pub fn new() -> Self {
Self::default()
}
/// Register a verifier by value. Returns the prior verifier for the same
/// type, if any, so callers can detect double-registration.
pub fn register<V: AttestationVerifier + 'static>(
&mut self,
verifier: V,
) -> Option<Box<dyn AttestationVerifier>> {
self.register_boxed(Box::new(verifier))
}
/// Like [`Self::register`] but takes an already-boxed trait object — useful
/// when verifiers are constructed dynamically.
pub fn register_boxed(
&mut self,
verifier: Box<dyn AttestationVerifier>,
) -> Option<Box<dyn AttestationVerifier>> {
let key = verifier.type_();
self.by_type.insert(key, verifier)
}
/// Switch policy.
pub fn with_policy(mut self, policy: Policy) -> Self {
self.policy = policy;
self
}
/// Type discriminators that must be present and verified under
/// `Policy::RequireAll`. Ignored under other policies.
pub fn require_types<I, S>(mut self, types: I) -> Self
where
I: IntoIterator<Item = S>,
S: Into<String>,
{
self.required_types = types.into_iter().map(Into::into).collect();
self
}
/// Active policy.
pub fn policy(&self) -> Policy {
self.policy
}
/// Verify signature, cert-hash binding, and (if a verifier is registered)
/// payload structure. Under `RequireAll` this is lenient on unknown types
/// — see the module docstring.
pub fn verify(
&self,
attestation: &Attestation,
expected_cert_hash: [u8; 32],
) -> Result<VerifiedAttestation> {
attestation.verify_signature(expected_cert_hash)?;
let fully = match self.by_type.get(attestation.type_.as_str()) {
Some(v) => {
v.verify_payload(&attestation.payload)?;
true
}
None => match self.policy {
Policy::AcceptKnown | Policy::RequireAll => false,
Policy::RejectUnknown => {
return Err(Error::UnknownType(attestation.type_.clone()));
}
},
};
Ok(VerifiedAttestation {
type_: attestation.type_.clone(),
signer: attestation.signer.clone(),
cert_hash: attestation.cert_hash.clone(),
fully_verified: fully,
})
}
/// Verify a batch, then enforce `RequireAll`.
pub fn verify_all(
&self,
attestations: &[Attestation],
expected_cert_hash: [u8; 32],
) -> Result<Vec<VerifiedAttestation>> {
let mut verified = Vec::with_capacity(attestations.len());
for a in attestations {
verified.push(self.verify(a, expected_cert_hash)?);
}
if self.policy == Policy::RequireAll {
for required in &self.required_types {
let present = verified
.iter()
.any(|v| &v.type_ == required && v.fully_verified);
if !present {
return Err(Error::RequiredMissing(required.clone()));
}
}
}
Ok(verified)
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::attestation::{Attestation, AttestationPayload};
use ed25519_dalek::SigningKey;
use rand::rngs::OsRng;
use serde::{Deserialize, Serialize};
fn fresh() -> SigningKey {
SigningKey::generate(&mut OsRng)
}
#[derive(Serialize, Deserialize)]
struct Demo {
a: String,
}
impl AttestationPayload for Demo {
fn payload_type() -> &'static str {
"demo/v1"
}
}
struct DemoVerifier;
impl AttestationVerifier for DemoVerifier {
fn type_(&self) -> &'static str {
"demo/v1"
}
fn verify_payload(&self, payload: &serde_json::Value) -> Result<()> {
payload
.get("a")
.and_then(|v| v.as_str())
.filter(|s| !s.is_empty())
.map(|_| ())
.ok_or_else(|| Error::Payload("missing or empty 'a'".to_string()))
}
}
/// A second verifier that has the same discriminator as `DemoVerifier` —
/// used to test last-wins on `register`.
struct DemoVerifierAlt;
impl AttestationVerifier for DemoVerifierAlt {
fn type_(&self) -> &'static str {
"demo/v1"
}
fn verify_payload(&self, _payload: &serde_json::Value) -> Result<()> {
Err(Error::Payload("alt always rejects".to_string()))
}
}
#[derive(Serialize, Deserialize)]
struct Other {
x: u32,
}
impl AttestationPayload for Other {
fn payload_type() -> &'static str {
"other/v1"
}
}
fn sample_hash() -> [u8; 32] {
let mut h = [0u8; 32];
for (i, b) in h.iter_mut().enumerate() {
*b = (i + 1) as u8;
}
h
}
fn signed_demo(sk: &SigningKey, cert_hash: [u8; 32], a: &str) -> Attestation {
Attestation::sign(sk, Demo { a: a.to_string() }, cert_hash).unwrap()
}
fn signed_other(sk: &SigningKey, cert_hash: [u8; 32], x: u32) -> Attestation {
Attestation::sign(sk, Other { x }, cert_hash).unwrap()
}
#[test]
fn registry_accepts_registered_type() {
let sk = fresh();
let cert_hash = sample_hash();
let mut reg = Registry::new();
reg.register(DemoVerifier);
let att = signed_demo(&sk, cert_hash, "ok");
let v = reg.verify(&att, cert_hash).unwrap();
assert!(v.fully_verified);
assert_eq!(v.type_, "demo/v1");
assert_eq!(v.cert_hash, hex::encode(cert_hash));
}
#[test]
fn accept_known_lets_unknown_pass_unverified() {
let sk = fresh();
let cert_hash = sample_hash();
let reg = Registry::new().with_policy(Policy::AcceptKnown);
let att = signed_demo(&sk, cert_hash, "ok");
let v = reg.verify(&att, cert_hash).unwrap();
assert!(!v.fully_verified);
}
#[test]
fn reject_unknown_blocks_unregistered_types() {
let sk = fresh();
let cert_hash = sample_hash();
let reg = Registry::new().with_policy(Policy::RejectUnknown);
let att = signed_demo(&sk, cert_hash, "ok");
let err = reg.verify(&att, cert_hash).unwrap_err();
assert!(matches!(err, Error::UnknownType(_)));
}
#[test]
fn require_all_enforces_presence() {
let sk = fresh();
let cert_hash = sample_hash();
let mut reg = Registry::new()
.with_policy(Policy::RequireAll)
.require_types(["demo/v1"]);
reg.register(DemoVerifier);
let err = reg.verify_all(&[], cert_hash).unwrap_err();
assert!(matches!(err, Error::RequiredMissing(t) if t == "demo/v1"));
let att = signed_demo(&sk, cert_hash, "ok");
let v = reg.verify_all(&[att], cert_hash).unwrap();
assert_eq!(v.len(), 1);
}
/// Even when a junk attestation of an unrelated type is attached first, a
/// `RequireAll` registry must still accept the cert as long as the
/// required type is present and fully verified — the attacker shouldn't
/// be able to DoS the cert by attaching `attacker/spam/v1` before
/// `covenant/exec/v1`.
#[test]
fn require_all_is_lenient_on_unknown_types_in_the_batch() {
let sk = fresh();
let cert_hash = sample_hash();
let mut reg = Registry::new()
.with_policy(Policy::RequireAll)
.require_types(["demo/v1"]);
reg.register(DemoVerifier);
let spam = signed_other(&sk, cert_hash, 7);
let real = signed_demo(&sk, cert_hash, "ok");
let verified = reg.verify_all(&[spam, real], cert_hash).unwrap();
assert_eq!(verified.len(), 2);
assert!(verified
.iter()
.any(|v| v.type_ == "demo/v1" && v.fully_verified));
assert!(verified
.iter()
.any(|v| v.type_ == "other/v1" && !v.fully_verified));
}
/// A required type that is present but unverified (no verifier registered
/// even though the type appears in `required_types`) must fail
/// `verify_all` with `RequiredMissing`. Catches a misconfiguration where
/// the operator listed a type but forgot to register a verifier.
#[test]
fn require_all_rejects_present_but_unverified_required_type() {
let sk = fresh();
let cert_hash = sample_hash();
let reg = Registry::new()
.with_policy(Policy::RequireAll)
.require_types(["demo/v1"]); // type listed, but no verifier registered.
let att = signed_demo(&sk, cert_hash, "ok");
let err = reg.verify_all(&[att], cert_hash).unwrap_err();
assert!(matches!(err, Error::RequiredMissing(t) if t == "demo/v1"));
}
#[test]
fn payload_check_failure_rejects() {
let sk = fresh();
let cert_hash = sample_hash();
let mut reg = Registry::new();
reg.register(DemoVerifier);
// Sign an empty `a` so the signature verifies but the payload check fails.
let att = Attestation::sign(&sk, Demo { a: String::new() }, cert_hash).unwrap();
let err = reg.verify(&att, cert_hash).unwrap_err();
assert!(matches!(err, Error::Payload(_)));
}
/// `RequireAll` with an empty allowlist degenerates to "no required types
/// to check" — the loop over `required_types` is a no-op, so an empty
/// batch verifies successfully. Pinned so operators relying on the empty
/// allowlist as a default-permissive RequireAll see consistent behavior.
#[test]
fn require_all_with_empty_allowlist_and_empty_batch_succeeds() {
let reg = Registry::new().with_policy(Policy::RequireAll);
let verified = reg.verify_all(&[], sample_hash()).unwrap();
assert!(verified.is_empty());
}
#[test]
fn register_returns_the_prior_verifier_on_double_register() {
let mut reg = Registry::new();
assert!(reg.register(DemoVerifier).is_none());
let prior = reg.register(DemoVerifierAlt);
let prior = prior.expect("second register must return the previous verifier");
assert_eq!(prior.type_(), "demo/v1");
// Last-wins semantics confirmed by behavior.
let sk = fresh();
let cert_hash = sample_hash();
let att = signed_demo(&sk, cert_hash, "ok");
let err = reg.verify(&att, cert_hash).unwrap_err();
assert!(matches!(err, Error::Payload(_)));
}
}
@@ -1,150 +0,0 @@
//! Canonical test vectors.
//!
//! Ed25519 signatures are deterministic (RFC 8032). JCS canonicalization is
//! deterministic (RFC 8785). SHA-256 is deterministic. Given fixed inputs the
//! cert hash, signature, signer DID, and full wire JSON are therefore exactly
//! reproducible across implementations. This file pins those values so a
//! port to Go, JS, Python, or any other language has a concrete oracle to
//! check against without reading Rust.
//!
//! If a vector changes, that is a wire-protocol break. The change is either
//! intentional (bump `ATTEST_ENVELOPE_VERSION` and document the migration) or
//! a regression that broke interoperability with every other implementation.
use ed25519_dalek::SigningKey;
use gitlawb_attest::{Attestation, AttestationPayload, AttestedRefUpdateCert, Registry, CERT_TYPE};
use serde::{Deserialize, Serialize};
/// Fixed seed for the attestation signer. Real signers use a CSPRNG; this is a
/// test-vector convention only.
const SIGNER_SEED: [u8; 32] = [
0x01, 0x23, 0x45, 0x67, 0x89, 0xab, 0xcd, 0xef, 0xfe, 0xdc, 0xba, 0x98, 0x76, 0x54, 0x32, 0x10,
0x00, 0x11, 0x22, 0x33, 0x44, 0x55, 0x66, 0x77, 0x88, 0x99, 0xaa, 0xbb, 0xcc, 0xdd, 0xee, 0xff,
];
/// Fixed cert body for the vectors. Mirrors the field layout of a
/// `gitlawb-core::cert::RefUpdateBody` plus a `signatures` array. The
/// signatures array is deliberately non-empty to test that it is stripped
/// before hashing.
fn fixture_cert_body() -> serde_json::Value {
serde_json::json!({
"type": CERT_TYPE,
"repo": "did:key:z6MkpYqTAt8jq3SExeUiVdyTrDdocy9j2NjGxFE6S6ZBh1Yt",
"ref_name": "refs/heads/main",
"from": "0000000000000000000000000000000000000000000000000000000000000000",
"to": "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
"seq": 1,
"timestamp": "2026-01-01T00:00:00Z",
"nonce": "vector-nonce-1",
"signatures": [
{"signer": "did:key:z6MkpYqTAt8jq3SExeUiVdyTrDdocy9j2NjGxFE6S6ZBh1Yt", "sig": "ignored"}
]
})
}
/// Fixed attestation payload. Shape mirrors what Covenant's runtime would
/// produce for a `covenant/exec/v1` attestation.
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
struct ExecPayload {
agent: String,
capability: String,
sandbox_digest: String,
}
impl AttestationPayload for ExecPayload {
fn payload_type() -> &'static str {
"covenant/exec/v1"
}
}
fn fixture_payload() -> ExecPayload {
ExecPayload {
agent: "did:key:z6MkAgentTestVector".to_string(),
capability: "code.write+sandbox.exec".to_string(),
sandbox_digest: "sha256:c0ffee".to_string(),
}
}
/// The expected lowercase-hex SHA-256 of `JCS(cert_body \ {signatures})`.
/// Any port that produces a different value is not JCS-canonicalizing the
/// same way (likely culprits: key ordering, integer or string escaping).
const EXPECTED_CERT_HASH_HEX: &str =
"5898d7c7a7d32a5faaaf9a52bfc92e0eff98027554adeefba0c575816f43ce56";
/// The expected `did:key` of the signer derived from `SIGNER_SEED`. Any port
/// that produces a different value has a multibase or multicodec encoding bug.
const EXPECTED_SIGNER_DID: &str = "did:key:z6MkqkKY69DYo23W4YFDoCNgjr7cMvmJqHtJVoQkEzrbaopZ";
/// The expected base64url-no-pad Ed25519 signature over
/// `b"gitlawb-attest-sig/v1\n" || JCS({type, payload, cert_hash})`. Any port
/// that produces a different value is missing the domain tag, JCS-encoding
/// the input differently, or using a different Ed25519 implementation.
const EXPECTED_SIGNATURE_B64URL: &str =
"4L3ONbhrksB9pn--u86lMeAdePSiZZplAsxuN2Cy6vgI30ndle7gDUVuoGRJr4Ylhz7ipQvUzXaDTvZGFLPXBQ";
#[test]
fn cert_hash_is_deterministic_from_jcs() {
let env = AttestedRefUpdateCert::from_cert(&fixture_cert_body()).unwrap();
let actual_hex = hex::encode(env.cert_hash().unwrap());
assert_eq!(
actual_hex, EXPECTED_CERT_HASH_HEX,
"cert hash drifted — JCS encoding or hash algorithm changed",
);
}
#[test]
fn signer_did_is_deterministic_from_seed() {
let sk = SigningKey::from_bytes(&SIGNER_SEED);
let env = AttestedRefUpdateCert::from_cert(&fixture_cert_body()).unwrap();
let cert_hash = env.cert_hash().unwrap();
let att = Attestation::sign(&sk, fixture_payload(), cert_hash).unwrap();
assert_eq!(
att.signer, EXPECTED_SIGNER_DID,
"signer DID drifted — multibase or multicodec encoding changed",
);
}
#[test]
fn attestation_signature_is_deterministic() {
let sk = SigningKey::from_bytes(&SIGNER_SEED);
let env = AttestedRefUpdateCert::from_cert(&fixture_cert_body()).unwrap();
let cert_hash = env.cert_hash().unwrap();
let att = Attestation::sign(&sk, fixture_payload(), cert_hash).unwrap();
assert_eq!(
att.sig, EXPECTED_SIGNATURE_B64URL,
"signature drifted — domain tag, JCS shape, or Ed25519 implementation changed",
);
}
#[test]
fn vector_attestation_verifies_through_the_public_api() {
// Round-trip the entire pipeline using only the public API on the fixed
// vectors. A non-Rust implementor should be able to:
// 1. Compute cert_hash and check against EXPECTED_CERT_HASH_HEX.
// 2. Derive signer DID and check against EXPECTED_SIGNER_DID.
// 3. Sign a payload identical to fixture_payload() and check against
// EXPECTED_SIGNATURE_B64URL.
// 4. Reconstruct the wire envelope and verify it round-trips.
let sk = SigningKey::from_bytes(&SIGNER_SEED);
let mut env = AttestedRefUpdateCert::from_cert(&fixture_cert_body()).unwrap();
let cert_hash = env.cert_hash().unwrap();
let att = Attestation::sign(&sk, fixture_payload(), cert_hash).unwrap();
env.attach(att);
let wire = serde_json::to_string(&env).unwrap();
let back: AttestedRefUpdateCert = serde_json::from_str(&wire).unwrap();
assert_eq!(back.attestations.len(), 1);
assert_eq!(back.attestations[0].sig, EXPECTED_SIGNATURE_B64URL);
let recovered = back.attestations[0]
.verify_signature(back.cert_hash().unwrap())
.unwrap();
assert_eq!(recovered.to_bytes(), sk.verifying_key().to_bytes());
// And through a registry, with the convenience method.
let reg = Registry::new();
let verified = back.verify_attestations(&reg).unwrap();
assert_eq!(verified.len(), 1);
assert_eq!(verified[0].cert_hash, EXPECTED_CERT_HASH_HEX);
assert_eq!(verified[0].signer, EXPECTED_SIGNER_DID);
}
@@ -1,251 +0,0 @@
//! End-to-end integration with `gitlawb-core`.
//!
//! Proves the attest envelope composes with the real `RefUpdateCert` from
//! `gitlawb-core`: a cert built and signed through the core API wraps cleanly,
//! survives signing and verifying an attestation, and round-trips back to a
//! `RefUpdateCert` that core still verifies. None of this is exercised by the
//! unit tests in `cert.rs`, which use hand-written JSON literals to keep the
//! crate's runtime deps minimal.
use ed25519_dalek::SigningKey;
use gitlawb_attest::{
Attestation, AttestationPayload, AttestationVerifier, AttestedRefUpdateCert, Error, Policy,
Registry, Result as AttestResult,
};
use gitlawb_core::cert::RefUpdateCert;
use gitlawb_core::identity::Keypair;
use rand::rngs::OsRng;
use serde::{Deserialize, Serialize};
fn zero_hash() -> String {
"0".repeat(64)
}
fn commit_hash(c: char) -> String {
c.to_string().repeat(64)
}
fn fresh_signing_key() -> SigningKey {
SigningKey::generate(&mut OsRng)
}
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
struct CovenantExecPayload {
agent: String,
capability: String,
sandbox_digest: String,
}
impl AttestationPayload for CovenantExecPayload {
fn payload_type() -> &'static str {
"covenant/exec/v1"
}
}
struct CovenantExecVerifier;
impl AttestationVerifier for CovenantExecVerifier {
fn type_(&self) -> &'static str {
"covenant/exec/v1"
}
fn verify_payload(&self, payload: &serde_json::Value) -> AttestResult<()> {
for field in ["agent", "capability", "sandbox_digest"] {
payload
.get(field)
.and_then(|v| v.as_str())
.filter(|s| !s.is_empty())
.ok_or_else(|| Error::Payload(format!("missing or empty '{field}'")))?;
}
Ok(())
}
}
#[test]
fn wraps_real_cert_signs_and_verifies_attestation_then_unwraps_cleanly() {
// 1. Build a real cert through gitlawb-core. The pusher is the repo owner
// in this minimal setup; the cert is single-signature.
let pusher = Keypair::generate();
let repo_did = pusher.did();
let cert = RefUpdateCert::new(
repo_did,
"refs/heads/main".to_string(),
zero_hash(),
commit_hash('a'),
1,
&pusher,
)
.unwrap();
cert.validate_structure().unwrap();
let valid_signers = cert.verify_all().unwrap();
assert_eq!(valid_signers.len(), 1);
// 2. Wrap. With no attestations attached the envelope is byte-identical to
// the underlying cert — that's the additive-on-the-wire promise.
let cert_json = serde_json::to_value(&cert).unwrap();
let mut env = AttestedRefUpdateCert::from_cert(&cert).unwrap();
assert_eq!(
serde_json::to_value(&env).unwrap(),
cert_json,
"empty envelope must serialize as the bare cert"
);
// 3. A separate party (here, an agent runtime) attests to how the commit
// was produced. The attestation signer is intentionally not the cert
// pusher: trust in the attestation is evaluated independently of trust
// in the push.
let agent_signer = fresh_signing_key();
let payload = CovenantExecPayload {
agent: "did:key:z6MkAgent".to_string(),
capability: "code.write+sandbox.exec".to_string(),
sandbox_digest: "sha256:c0ffee".to_string(),
};
let cert_hash = env.cert_hash().unwrap();
let attestation = Attestation::sign(&agent_signer, payload.clone(), cert_hash).unwrap();
env.attach(attestation);
// 4. Verify through a registry that knows `covenant/exec/v1`. Strict
// policy so an unknown discriminator would have been rejected.
let mut registry = Registry::new().with_policy(Policy::RejectUnknown);
registry.register(CovenantExecVerifier);
let verified = registry
.verify_all(&env.attestations, env.cert_hash().unwrap())
.unwrap();
assert_eq!(verified.len(), 1);
assert!(verified[0].fully_verified);
assert_eq!(verified[0].type_, "covenant/exec/v1");
assert_eq!(verified[0].cert_hash, hex::encode(cert_hash));
// 5. Round-trip through JSON and back. The wrapped cert with one
// attestation must parse back into the same envelope, and stripping
// the attestations must yield a `RefUpdateCert` core still verifies.
let on_wire = serde_json::to_string(&env).unwrap();
let back: AttestedRefUpdateCert = serde_json::from_str(&on_wire).unwrap();
assert_eq!(back.attestations.len(), 1);
assert_eq!(
back.attestations[0]
.payload_as::<CovenantExecPayload>()
.unwrap(),
payload
);
let mut unwrapped = back.cert.clone();
if let Some(obj) = unwrapped.as_object_mut() {
obj.remove("attestations");
}
let unwrapped_cert: RefUpdateCert = serde_json::from_value(unwrapped).unwrap();
let revalidated = unwrapped_cert.verify_all().unwrap();
assert_eq!(revalidated, valid_signers);
}
#[test]
fn cert_hash_is_stable_when_a_maintainer_countersigns() {
// The cert hash strips `signatures` before hashing, so countersignatures
// added after an attestation is signed must not invalidate the
// attestation's binding.
let pusher = Keypair::generate();
let maintainer = Keypair::generate();
let mut cert = RefUpdateCert::new(
pusher.did(),
"refs/heads/main".to_string(),
zero_hash(),
commit_hash('b'),
7,
&pusher,
)
.unwrap();
let env_before = AttestedRefUpdateCert::from_cert(&cert).unwrap();
let hash_before = env_before.cert_hash().unwrap();
cert.countersign(&maintainer).unwrap();
let env_after = AttestedRefUpdateCert::from_cert(&cert).unwrap();
let hash_after = env_after.cert_hash().unwrap();
assert_eq!(
hash_before, hash_after,
"cert hash must be stable across countersignatures"
);
// An attestation signed against the pre-countersign hash still verifies
// against the post-countersign cert.
let agent = fresh_signing_key();
let payload = CovenantExecPayload {
agent: "did:key:z6MkAgent2".to_string(),
capability: "code.write".to_string(),
sandbox_digest: "sha256:deadbeef".to_string(),
};
let attestation = Attestation::sign(&agent, payload, hash_before).unwrap();
attestation.verify_signature(hash_after).unwrap();
}
#[test]
fn cross_cert_replay_is_rejected_against_a_real_cert() {
// Negative case: an attestation signed for one cert must not verify on a
// different cert built through the core API.
let pusher = Keypair::generate();
let cert_a = RefUpdateCert::new(
pusher.did(),
"refs/heads/main".to_string(),
zero_hash(),
commit_hash('a'),
1,
&pusher,
)
.unwrap();
let cert_b = RefUpdateCert::new(
pusher.did(),
"refs/heads/main".to_string(),
commit_hash('a'),
commit_hash('b'),
2,
&pusher,
)
.unwrap();
let env_a = AttestedRefUpdateCert::from_cert(&cert_a).unwrap();
let env_b = AttestedRefUpdateCert::from_cert(&cert_b).unwrap();
let hash_a = env_a.cert_hash().unwrap();
let hash_b = env_b.cert_hash().unwrap();
assert_ne!(hash_a, hash_b);
let agent = fresh_signing_key();
let payload = CovenantExecPayload {
agent: "did:key:z6MkAgent3".to_string(),
capability: "code.write".to_string(),
sandbox_digest: "sha256:cafe".to_string(),
};
let attestation = Attestation::sign(&agent, payload, hash_a).unwrap();
let err = attestation.verify_signature(hash_b).unwrap_err();
assert!(matches!(err, Error::CertHashMismatch));
}
/// A cert deserialized from JSON and a cert built through the core API must
/// hash identically. JCS canonicalization is what makes the additive-on-wire
/// promise hold across the serialize/deserialize boundary — without it, the
/// hash would depend on which side built the `serde_json::Value`.
#[test]
fn cert_hash_is_identical_across_the_deserialize_boundary() {
let pusher = Keypair::generate();
let cert = RefUpdateCert::new(
pusher.did(),
"refs/heads/main".to_string(),
zero_hash(),
commit_hash('c'),
9,
&pusher,
)
.unwrap();
let direct_hash = AttestedRefUpdateCert::from_cert(&cert)
.unwrap()
.cert_hash()
.unwrap();
let wire = serde_json::to_string(&cert).unwrap();
let parsed_value: serde_json::Value = serde_json::from_str(&wire).unwrap();
let parsed_env: AttestedRefUpdateCert = serde_json::from_value(parsed_value).unwrap();
let parsed_hash = parsed_env.cert_hash().unwrap();
assert_eq!(direct_hash, parsed_hash);
}
+1 -5
View File
@@ -1,9 +1,8 @@
[package]
name = "gitlawb-core"
description = "Core cryptographic primitives for the gitlawb network: DIDs, CIDs, UCAN, HTTP Signatures, ref-update certificates"
version = "0.5.1" # x-release-please-version
version.workspace = true
edition.workspace = true
rust-version.workspace = true
license.workspace = true
[dependencies]
@@ -24,9 +23,6 @@ chrono = { workspace = true }
uuid = { workspace = true }
zeroize = { version = "1", features = ["derive"] }
pkcs8 = { version = "0.10", features = ["pem", "std"] }
curve25519-dalek = "4"
crypto_box = { version = "0.9", features = ["std", "chacha20"] }
chacha20poly1305 = "0.10"
[dev-dependencies]
tokio = { workspace = true }
+14 -117
View File
@@ -10,9 +10,9 @@ use chrono::{DateTime, Utc};
use serde::{Deserialize, Serialize};
use uuid::Uuid;
use crate::did::Did;
use crate::identity::{verify, Keypair};
use crate::{Error, Result};
use crate::did::Did;
use crate::identity::{Keypair, verify};
/// The certificate type discriminant. Always `"gitlawb/ref-update/v1"`.
pub const CERT_TYPE: &str = "gitlawb/ref-update/v1";
@@ -110,7 +110,7 @@ impl RefUpdateCert {
///
/// Returns the list of DIDs whose signatures are valid.
pub fn verify_all(&self) -> Result<Vec<Did>> {
use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine};
use base64::{Engine, engine::general_purpose::URL_SAFE_NO_PAD};
let signing_bytes = self.body.to_signing_bytes()?;
let mut valid = Vec::new();
@@ -118,12 +118,10 @@ impl RefUpdateCert {
// Resolve the verifying key from the DID
let vk = cert_sig.signer.to_verifying_key()?;
let sig_bytes_vec = URL_SAFE_NO_PAD
.decode(&cert_sig.sig)
let sig_bytes_vec = URL_SAFE_NO_PAD.decode(&cert_sig.sig)
.map_err(|e| Error::RefCert(format!("invalid base64 sig: {e}")))?;
let sig_bytes: [u8; 64] = sig_bytes_vec
.try_into()
let sig_bytes: [u8; 64] = sig_bytes_vec.try_into()
.map_err(|_| Error::RefCert("signature must be 64 bytes".to_string()))?;
verify(&vk, &signing_bytes, &sig_bytes)?;
@@ -135,7 +133,11 @@ impl RefUpdateCert {
/// Check if this certificate satisfies a threshold of valid signatures
/// from the provided set of authorized maintainer DIDs.
pub fn satisfies_threshold(&self, maintainers: &[Did], threshold: usize) -> Result<bool> {
pub fn satisfies_threshold(
&self,
maintainers: &[Did],
threshold: usize,
) -> Result<bool> {
let valid = self.verify_all()?;
let count = valid.iter().filter(|d| maintainers.contains(d)).count();
Ok(count >= threshold)
@@ -185,8 +187,7 @@ mod tests {
dummy_hash('a'),
1,
&kp,
)
.unwrap();
).unwrap();
cert.validate_structure().unwrap();
let valid = cert.verify_all().unwrap();
@@ -207,8 +208,7 @@ mod tests {
dummy_hash('a'),
1,
&kp1,
)
.unwrap();
).unwrap();
cert.countersign(&kp2).unwrap();
let valid = cert.verify_all().unwrap();
@@ -228,8 +228,7 @@ mod tests {
dummy_hash('a'),
1,
&kp1,
)
.unwrap();
).unwrap();
cert.countersign(&kp2).unwrap();
let maintainers = vec![kp1.did(), kp2.did()];
@@ -247,8 +246,7 @@ mod tests {
dummy_hash('b'),
42,
&kp,
)
.unwrap();
).unwrap();
let json = serde_json::to_string_pretty(&cert).unwrap();
assert!(json.contains("gitlawb/ref-update/v1"));
@@ -257,105 +255,4 @@ mod tests {
// Round-trip
let _: RefUpdateCert = serde_json::from_str(&json).unwrap();
}
#[test]
fn validate_structure_rejects_wrong_cert_type() {
let kp = Keypair::generate();
let mut cert = RefUpdateCert::new(
kp.did(),
"refs/heads/main".to_string(),
dummy_hash('0'),
dummy_hash('a'),
1,
&kp,
)
.unwrap();
cert.body.type_ = "gitlawb/ref-update/v0".to_string();
assert!(cert.validate_structure().is_err());
}
#[test]
fn validate_structure_rejects_invalid_to_hash() {
let kp = Keypair::generate();
let mut cert = RefUpdateCert::new(
kp.did(),
"refs/heads/main".to_string(),
dummy_hash('0'),
dummy_hash('a'),
1,
&kp,
)
.unwrap();
cert.body.to = "not-a-valid-sha256".to_string();
assert!(cert.validate_structure().is_err());
}
#[test]
fn validate_structure_rejects_empty_signatures() {
let kp = Keypair::generate();
let mut cert = RefUpdateCert::new(
kp.did(),
"refs/heads/main".to_string(),
dummy_hash('0'),
dummy_hash('a'),
1,
&kp,
)
.unwrap();
cert.signatures.clear();
assert!(cert.validate_structure().is_err());
}
#[test]
fn tampered_signature_fails_verify_all() {
let kp = Keypair::generate();
let kp2 = Keypair::generate();
let mut cert = RefUpdateCert::new(
kp.did(),
"refs/heads/main".to_string(),
dummy_hash('0'),
dummy_hash('a'),
1,
&kp,
)
.unwrap();
// Replace kp's signature with a signature from kp2 over different bytes.
// The signer DID still points to kp, so verification must fail.
cert.signatures[0].sig = kp2.sign_b64(b"unrelated bytes");
assert!(cert.verify_all().is_err());
}
#[test]
fn threshold_not_met_when_signer_outside_maintainer_list() {
let kp_pusher = Keypair::generate();
let kp_maintainer = Keypair::generate();
let cert = RefUpdateCert::new(
kp_pusher.did(),
"refs/heads/main".to_string(),
dummy_hash('0'),
dummy_hash('a'),
1,
&kp_pusher,
)
.unwrap();
let maintainers = vec![kp_maintainer.did()];
assert!(!cert.satisfies_threshold(&maintainers, 1).unwrap());
}
#[test]
fn threshold_zero_is_always_satisfied() {
let kp = Keypair::generate();
let cert = RefUpdateCert::new(
kp.did(),
"refs/heads/main".to_string(),
dummy_hash('0'),
dummy_hash('a'),
1,
&kp,
)
.unwrap();
assert!(cert.satisfies_threshold(&[], 0).unwrap());
}
}
+5 -65
View File
@@ -11,7 +11,7 @@
use cid::CidGeneric;
use multihash_codetable::{Code, MultihashDigest};
use serde::{Deserialize, Serialize};
use sha2::{Digest, Sha256};
use sha2::{Sha256, Digest};
use std::fmt;
use crate::{Error, Result};
@@ -87,9 +87,9 @@ pub fn sha256_bytes(bytes: &[u8]) -> [u8; 32] {
/// Parse a 64-character hex SHA-256 string into raw bytes.
pub fn sha256_hex_to_bytes(hex_str: &str) -> Result<[u8; 32]> {
let bytes = hex::decode(hex_str).map_err(|e| Error::InvalidCid(format!("invalid hex: {e}")))?;
bytes
.try_into()
let bytes = hex::decode(hex_str)
.map_err(|e| Error::InvalidCid(format!("invalid hex: {e}")))?;
bytes.try_into()
.map_err(|_| Error::InvalidCid("sha256 hash must be 32 bytes (64 hex chars)".to_string()))
}
@@ -110,10 +110,7 @@ mod tests {
// CIDv1 base32 strings start with 'b'
let data = b"blob 13\0hello gitlawb";
let c = Cid::from_git_object_bytes(data);
assert!(
c.to_string().starts_with('b'),
"CIDv1 should be base32 (starts with 'b')"
);
assert!(c.to_string().starts_with('b'), "CIDv1 should be base32 (starts with 'b')");
}
#[test]
@@ -129,61 +126,4 @@ mod tests {
let bytes = sha256_hex_to_bytes(&hex).unwrap();
assert_eq!(sha256_bytes(data), bytes);
}
#[test]
fn from_sha256_bytes_matches_object_bytes() {
// from_sha256_bytes must produce the same CID as from_git_object_bytes
// when given the SHA-256 of those bytes — the two construction paths
// must be equivalent for self-verifying content addressing to hold.
let data = b"blob 5\0hello";
let cid_from_object = Cid::from_git_object_bytes(data);
let hash = sha256_bytes(data);
let cid_from_hash = Cid::from_sha256_bytes(&hash);
assert_eq!(cid_from_object, cid_from_hash);
}
#[test]
fn from_str_parses_valid_cid() {
let data = b"tree content for test";
let cid = Cid::from_git_object_bytes(data);
let parsed = Cid::from_str(cid.as_str()).unwrap();
assert_eq!(cid, parsed);
}
#[test]
fn from_str_rejects_invalid_string() {
let result = Cid::from_str("not-a-valid-cid");
assert!(result.is_err());
}
#[test]
fn different_data_produces_different_cids() {
let c1 = Cid::from_git_object_bytes(b"blob 5\0hello");
let c2 = Cid::from_git_object_bytes(b"blob 5\0world");
assert_ne!(c1, c2);
}
#[test]
fn sha256_hex_to_bytes_rejects_non_hex() {
let non_hex = "zzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzz";
assert_eq!(non_hex.len(), 64);
let result = sha256_hex_to_bytes(non_hex);
assert!(result.is_err());
}
#[test]
fn sha256_hex_to_bytes_rejects_wrong_length() {
let result = sha256_hex_to_bytes("deadbeef");
assert!(result.is_err());
}
#[test]
fn sha256_hex_of_empty_input_is_well_known() {
// SHA-256("") is a fixed constant; verifies the hasher is wired correctly.
let h = sha256_hex(b"");
assert_eq!(
h,
"e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
);
}
}
+7 -67
View File
@@ -75,13 +75,12 @@ impl Did {
pub fn to_verifying_key(&self) -> Result<VerifyingKey> {
if !self.is_did_key() {
return Err(Error::InvalidDid(format!(
"expected did:key, got did:{}",
self.method()
"expected did:key, got did:{}", self.method()
)));
}
let (_, bytes) =
multibase::decode(self.method_id()).map_err(|e| Error::InvalidDid(e.to_string()))?;
let (_, bytes) = multibase::decode(self.method_id())
.map_err(|e| Error::InvalidDid(e.to_string()))?;
if !bytes.starts_with(ED25519_MULTICODEC) {
return Err(Error::InvalidDid(
@@ -93,7 +92,8 @@ impl Did {
.try_into()
.map_err(|_| Error::InvalidDid("ed25519 key must be 32 bytes".to_string()))?;
VerifyingKey::from_bytes(&key_bytes).map_err(|e| Error::InvalidDid(e.to_string()))
VerifyingKey::from_bytes(&key_bytes)
.map_err(|e| Error::InvalidDid(e.to_string()))
}
/// Return the full DID string as a `&str`.
@@ -105,9 +105,7 @@ impl Did {
pub fn validate(&self) -> Result<()> {
match self.method() {
"key" | "web" | "gitlawb" => Ok(()),
other => Err(Error::InvalidDid(format!(
"unsupported DID method: {other}"
))),
other => Err(Error::InvalidDid(format!("unsupported DID method: {other}"))),
}
}
}
@@ -123,9 +121,7 @@ impl FromStr for Did {
fn from_str(s: &str) -> Result<Self> {
if !s.starts_with("did:") {
return Err(Error::InvalidDid(format!(
"'{s}' does not start with 'did:'"
)));
return Err(Error::InvalidDid(format!("'{s}' does not start with 'did:'")));
}
let did = Self(s.to_string());
did.validate()?;
@@ -252,60 +248,4 @@ mod tests {
let json = serde_json::to_string_pretty(&doc).unwrap();
assert!(json.contains("Ed25519VerificationKey2020"));
}
#[test]
fn to_verifying_key_fails_for_did_web() {
let web = Did::web("example.com");
let result = web.to_verifying_key();
assert!(
result.is_err(),
"did:web cannot resolve to a verifying key locally"
);
}
#[test]
fn to_verifying_key_fails_for_did_gitlawb() {
let gl = Did::gitlawb("z6MkSomeKey");
let result = gl.to_verifying_key();
assert!(
result.is_err(),
"did:gitlawb cannot resolve to a verifying key locally"
);
}
#[test]
fn from_str_rejects_missing_did_prefix() {
let result = "key:z6MkABCD".parse::<Did>();
assert!(result.is_err());
}
#[test]
fn from_str_rejects_unsupported_method() {
let result = "did:ethr:0x1234abcd".parse::<Did>();
assert!(result.is_err());
}
#[test]
fn validate_accepts_all_supported_methods() {
Did::web("example.com").validate().unwrap();
Did::gitlawb("z6MkSomeKey").validate().unwrap();
Keypair::generate().did().validate().unwrap();
}
#[test]
fn is_did_key_and_is_did_gitlawb_predicates() {
let key_did = Keypair::generate().did();
assert!(key_did.is_did_key());
assert!(!key_did.is_did_gitlawb());
let gl = Did::gitlawb("z6MkSomeKey");
assert!(!gl.is_did_key());
assert!(gl.is_did_gitlawb());
}
#[test]
fn method_id_extraction() {
assert_eq!(Did::web("example.com").method_id(), "example.com");
assert_eq!(Did::gitlawb("z6MkSomeKey").method_id(), "z6MkSomeKey");
}
}
-296
View File
@@ -1,296 +0,0 @@
//! Envelope encryption for withheld blobs (Option B). A random content key
//! encrypts the blob (XChaCha20-Poly1305); the content key is wrapped to each
//! recipient via an X25519 box keyed from their Ed25519 `did:key`. The node
//! seals with public keys only; readers open with their own private key.
use crate::identity::Keypair;
use anyhow::{Context, Result};
use ed25519_dalek::VerifyingKey;
use zeroize::Zeroizing;
/// X25519 public key (Montgomery u) for an Ed25519 verifying key.
fn x25519_public(vk: &VerifyingKey) -> Result<[u8; 32]> {
use curve25519_dalek::edwards::CompressedEdwardsY;
let edwards = CompressedEdwardsY::from_slice(vk.as_bytes())
.ok()
.and_then(|c| c.decompress())
.context("verifying key is not a valid edwards point")?;
Ok(edwards.to_montgomery().to_bytes())
}
/// X25519 secret scalar for an Ed25519 seed (SHA-512 of seed, lower 32, clamped).
/// Returns the scalar wrapped in `Zeroizing`, and scrubs the intermediate
/// SHA-512 digest, so no copy of this secret material lingers in freed memory.
fn x25519_secret_from_seed(seed: &[u8; 32]) -> Zeroizing<[u8; 32]> {
use sha2::{Digest, Sha512};
use zeroize::Zeroize;
let mut h = Sha512::digest(seed);
let mut s = Zeroizing::new([0u8; 32]);
s.copy_from_slice(&h[..32]);
s[0] &= 248;
s[31] &= 127;
s[31] |= 64;
h.as_mut_slice().zeroize();
s
}
use base64::{engine::general_purpose::STANDARD as B64, Engine};
use chacha20poly1305::{
aead::{Aead, KeyInit},
XChaCha20Poly1305, XNonce,
};
use crypto_box::{
aead::{AeadCore, OsRng},
ChaChaBox, PublicKey as XPublic, SecretKey as XSecret,
};
use rand::RngCore;
use serde::{Deserialize, Serialize};
const MAGIC: &[u8] = b"GLENC";
const VERSION: u8 = 2;
#[derive(Serialize, Deserialize)]
struct Recipient {
eph: String, // base64 ephemeral x25519 pubkey (32B)
nonce: String, // base64 box nonce (24B)
wrap: String, // base64 wrapped content key
}
#[derive(Serialize, Deserialize)]
struct Header {
alg: String,
nonce: String, // base64 body nonce (24B)
recipients: Vec<Recipient>,
}
/// Encrypt `plaintext` so any of `recipients` (Ed25519 keys) can decrypt.
pub fn seal_blob(plaintext: &[u8], recipients: &[VerifyingKey]) -> Result<Vec<u8>> {
if recipients.is_empty() {
return Err(anyhow::anyhow!("seal_blob: no recipients"));
}
let mut content_key = [0u8; 32];
OsRng.fill_bytes(&mut content_key);
let body_cipher = XChaCha20Poly1305::new_from_slice(&content_key)
.map_err(|e| anyhow::anyhow!("content key: {e}"))?;
let mut body_nonce = [0u8; 24];
OsRng.fill_bytes(&mut body_nonce);
let body = body_cipher
.encrypt(XNonce::from_slice(&body_nonce), plaintext)
.map_err(|e| anyhow::anyhow!("body encrypt: {e}"))?;
let mut wrapped = Vec::with_capacity(recipients.len());
for vk in recipients {
let recip_x = XPublic::from(x25519_public(vk)?);
let eph = XSecret::generate(&mut OsRng);
let abox = ChaChaBox::new(&recip_x, &eph);
let nonce = ChaChaBox::generate_nonce(&mut OsRng);
let ct = abox
.encrypt(&nonce, &content_key[..])
.map_err(|e| anyhow::anyhow!("wrap: {e}"))?;
wrapped.push(Recipient {
eph: B64.encode(eph.public_key().as_bytes()),
nonce: B64.encode(nonce),
wrap: B64.encode(ct),
});
}
let header = Header {
alg: "xchacha20poly1305".into(),
nonce: B64.encode(body_nonce),
recipients: wrapped,
};
let header_json = serde_json::to_vec(&header).context("encode header")?;
let mut out = Vec::new();
out.extend_from_slice(MAGIC);
out.push(VERSION);
out.extend_from_slice(&(header_json.len() as u32).to_le_bytes());
out.extend_from_slice(&header_json);
out.extend_from_slice(&body);
Ok(out)
}
/// Decrypt an envelope with `keypair`. Errors if not a recipient or on auth fail.
pub fn open_blob(envelope: &[u8], keypair: &Keypair) -> Result<Vec<u8>> {
let mut p = 0;
if envelope.len() < MAGIC.len() + 1 + 4 || &envelope[..MAGIC.len()] != MAGIC {
return Err(anyhow::anyhow!("bad envelope magic"));
}
p += MAGIC.len();
if envelope[p] != VERSION {
return Err(anyhow::anyhow!("unsupported envelope version"));
}
p += 1;
let hlen = u32::from_le_bytes(envelope[p..p + 4].try_into().unwrap()) as usize;
p += 4;
let header: Header =
serde_json::from_slice(envelope.get(p..p + hlen).context("truncated header")?)
.context("decode header")?;
let body = &envelope[p + hlen..];
let my_x = XSecret::from(*x25519_secret_from_seed(&keypair.to_seed()));
// Identities are blinded: no entry says which recipient it belongs to, so
// try each one. The ChaChaBox AEAD tag authenticates, so exactly the
// reader's own entry unwraps; every other entry fails cleanly.
let mut content_key: Option<Vec<u8>> = None;
for entry in &header.recipients {
let eph = match B64
.decode(&entry.eph)
.ok()
.and_then(|b| <[u8; 32]>::try_from(b.as_slice()).ok())
{
Some(b) => XPublic::from(b),
None => continue,
};
// from_slice panics on a wrong length, and the envelope is attacker
// controlled, so validate the 24-byte box nonce before using it.
let nonce = match B64
.decode(&entry.nonce)
.ok()
.and_then(|n| <[u8; 24]>::try_from(n.as_slice()).ok())
{
Some(n) => n,
None => continue,
};
let wrap = match B64.decode(&entry.wrap) {
Ok(w) => w,
Err(_) => continue,
};
let abox = ChaChaBox::new(&eph, &my_x);
if let Ok(ck) = abox.decrypt(
crypto_box::aead::generic_array::GenericArray::from_slice(&nonce),
wrap.as_slice(),
) {
content_key = Some(ck);
break;
}
}
let content_key = content_key.context("not a recipient of this envelope")?;
let body_cipher = XChaCha20Poly1305::new_from_slice(&content_key)
.map_err(|e| anyhow::anyhow!("content key: {e}"))?;
let body_nonce = B64
.decode(&header.nonce)
.ok()
.and_then(|n| <[u8; 24]>::try_from(n.as_slice()).ok())
.context("invalid body nonce")?;
body_cipher
.decrypt(XNonce::from_slice(&body_nonce), body)
.map_err(|_| anyhow::anyhow!("body decrypt failed"))
}
#[cfg(test)]
mod tests {
use super::*;
use crate::identity::Keypair;
#[test]
fn ed25519_to_x25519_keypair_agrees() {
// The X25519 public derived from the Ed25519 public must equal the
// X25519 public of the X25519 secret derived from the same seed.
let kp = Keypair::generate();
let seed = kp.to_seed();
let xpub_from_public = x25519_public(&kp.verifying_key()).unwrap();
let xsec = x25519_secret_from_seed(&seed);
let xpub_from_secret = crypto_box::SecretKey::from(*xsec).public_key().to_bytes();
assert_eq!(xpub_from_public, xpub_from_secret);
}
#[test]
fn seal_open_round_trip_for_recipients() {
let owner = Keypair::generate();
let reader_a = Keypair::generate();
let reader_b = Keypair::generate();
let msg = b"private blob contents";
let env = seal_blob(msg, &[owner.verifying_key(), reader_a.verifying_key()]).unwrap();
assert_eq!(open_blob(&env, &owner).unwrap(), msg);
assert_eq!(open_blob(&env, &reader_a).unwrap(), msg);
assert!(
open_blob(&env, &reader_b).is_err(),
"non-recipient must fail"
);
}
#[test]
fn tampered_envelope_fails() {
let owner = Keypair::generate();
let mut env = seal_blob(b"hi", &[owner.verifying_key()]).unwrap();
let last = env.len() - 1;
env[last] ^= 0x01;
assert!(open_blob(&env, &owner).is_err());
}
#[test]
fn v2_header_contains_no_recipient_pubkey() {
// The blinded envelope header must not carry any recipient's public key.
let reader = Keypair::generate();
let env = seal_blob(b"private blob contents", &[reader.verifying_key()]).unwrap();
// Slice out the header bytes using the envelope framing:
// MAGIC | version(1B) | header_len(4B LE) | header_json | body
let mut p = MAGIC.len() + 1; // skip MAGIC + version byte
let hlen = u32::from_le_bytes(env[p..p + 4].try_into().unwrap()) as usize;
p += 4;
let header = &env[p..p + hlen];
let header_str = String::from_utf8_lossy(header);
let pubkey_b64 = B64.encode(reader.verifying_key().as_bytes());
assert!(
!header_str.contains(&pubkey_b64),
"recipient public key must not appear in the blinded header"
);
}
#[test]
fn v1_envelope_is_rejected() {
let reader = Keypair::generate();
let mut env = seal_blob(b"hi", &[reader.verifying_key()]).unwrap();
// Flip the version byte (immediately after MAGIC) from 2 to 1.
env[MAGIC.len()] = 1;
let err = open_blob(&env, &reader).unwrap_err();
assert!(
err.to_string().contains("unsupported envelope version"),
"expected version-rejection error, got: {err}"
);
}
#[test]
fn malformed_nonce_returns_err_not_panic() {
// from_slice panics on wrong-length input; a crafted envelope on the
// public recovery path must surface an error, never panic.
let reader = Keypair::generate();
let env = seal_blob(b"private blob contents", &[reader.verifying_key()]).unwrap();
// Split the envelope framing into header JSON and body.
let mut p = MAGIC.len() + 1;
let hlen = u32::from_le_bytes(env[p..p + 4].try_into().unwrap()) as usize;
p += 4;
let header_bytes = &env[p..p + hlen];
let body = &env[p + hlen..];
let reframe = |header: &serde_json::Value| -> Vec<u8> {
let hj = serde_json::to_vec(header).unwrap();
let mut out = Vec::new();
out.extend_from_slice(MAGIC);
out.push(VERSION);
out.extend_from_slice(&(hj.len() as u32).to_le_bytes());
out.extend_from_slice(&hj);
out.extend_from_slice(body);
out
};
let bad_nonce = serde_json::Value::String(B64.encode([0u8; 12]));
// Corrupted per-recipient nonce: entry is skipped, no match.
let mut header: serde_json::Value = serde_json::from_slice(header_bytes).unwrap();
header["recipients"][0]["nonce"] = bad_nonce.clone();
assert!(open_blob(&reframe(&header), &reader).is_err());
// Corrupted body nonce: unwrap succeeds, body nonce is rejected.
let mut header: serde_json::Value = serde_json::from_slice(header_bytes).unwrap();
header["nonce"] = bad_nonce;
assert!(open_blob(&reframe(&header), &reader).is_err());
}
}
+26 -35
View File
@@ -11,14 +11,14 @@
//! Signature-Input: sig1=("@method" "@path" "content-digest");keyid="did:key:z6Mk...";alg="ed25519";created=<unix>
//! Signature: sig1=:base64signature:
use base64::{engine::general_purpose::STANDARD, Engine};
use base64::{Engine, engine::general_purpose::STANDARD};
use chrono::Utc;
use sha2::{Digest, Sha256};
use sha2::{Sha256, Digest};
use std::collections::HashMap;
use crate::{Error, Result};
use crate::did::Did;
use crate::identity::Keypair;
use crate::{Error, Result};
/// The component identifiers covered by every gitlawb signature.
pub const COVERED_COMPONENTS: &[&str] = &["@method", "@path", "content-digest"];
@@ -53,16 +53,16 @@ impl HttpSignature {
let sig_input = sig_input.trim();
// Expect: sig1=("@method" "@path" "content-digest");keyid="...";alg="...";created=...
let rest = sig_input.strip_prefix("sig1=").ok_or_else(|| {
Error::HttpSignature("Signature-Input must start with 'sig1='".into())
})?;
let rest = sig_input
.strip_prefix("sig1=")
.ok_or_else(|| Error::HttpSignature("Signature-Input must start with 'sig1='".into()))?;
let open = rest
.find('(')
.ok_or_else(|| Error::HttpSignature("missing '(' in Signature-Input".into()))?;
let close = rest
.find(')')
.ok_or_else(|| Error::HttpSignature("missing ')' in Signature-Input".into()))?;
let open = rest.find('(').ok_or_else(|| {
Error::HttpSignature("missing '(' in Signature-Input".into())
})?;
let close = rest.find(')').ok_or_else(|| {
Error::HttpSignature("missing ')' in Signature-Input".into())
})?;
let components_str = &rest[open + 1..close];
let params_str = &rest[close + 1..]; // starts with ';'
@@ -98,19 +98,15 @@ impl HttpSignature {
.trim()
.strip_prefix("sig1=:")
.and_then(|s| s.strip_suffix(':'))
.ok_or_else(|| Error::HttpSignature("Signature must be 'sig1=:base64:'".into()))?;
.ok_or_else(|| {
Error::HttpSignature("Signature must be 'sig1=:base64:'".into())
})?;
let signature_bytes = STANDARD
.decode(sig_b64)
.map_err(|e| Error::HttpSignature(format!("invalid base64 in Signature: {e}")))?;
Ok(Self {
key_id,
alg,
created,
components,
signature_bytes,
})
Ok(Self { key_id, alg, created, components, signature_bytes })
}
/// Reject if the `created` timestamp is more than 5 minutes from now.
@@ -129,7 +125,7 @@ impl HttpSignature {
pub fn missing_components(&self) -> Vec<&str> {
COVERED_COMPONENTS
.iter()
.filter(|c| !self.components.iter().any(|s| s.as_str() == **c))
.filter(|c| !self.components.contains(&c.to_string()))
.copied()
.collect()
}
@@ -182,9 +178,12 @@ pub fn sign_request(
request_values.insert("@path".to_string(), path_and_query.to_string());
request_values.insert("content-digest".to_string(), content_digest.clone());
let signing_string =
build_signing_string(COVERED_COMPONENTS, sig_params_value, &request_values)
.expect("required components always present when building");
let signing_string = build_signing_string(
COVERED_COMPONENTS,
sig_params_value,
&request_values,
)
.expect("required components always present when building");
let sig_bytes = keypair.sign(signing_string.as_bytes());
let sig_b64 = STANDARD.encode(sig_bytes.to_bytes());
@@ -291,16 +290,10 @@ mod tests {
request_values.insert("content-digest".to_string(), headers.content_digest.clone());
let components_ref: Vec<&str> = sig.components.iter().map(String::as_str).collect();
let signing_string =
build_signing_string(&components_ref, sig_params_value, &request_values).unwrap();
let signing_string = build_signing_string(&components_ref, sig_params_value, &request_values).unwrap();
let vk = sig.key_id.to_verifying_key().unwrap();
let sig_b64 = headers
.signature
.strip_prefix("sig1=:")
.unwrap()
.strip_suffix(':')
.unwrap();
let sig_b64 = headers.signature.strip_prefix("sig1=:").unwrap().strip_suffix(':').unwrap();
let sig_bytes: [u8; 64] = STANDARD.decode(sig_b64).unwrap().try_into().unwrap();
assert!(verify(&vk, signing_string.as_bytes(), &sig_bytes).is_ok());
@@ -328,9 +321,7 @@ mod tests {
let kp = Keypair::generate();
let did = kp.did();
// created=1 is way in the past — should fail clock skew check
let sig_input = format!(
r#"sig1=("@method" "@path" "content-digest");keyid="{did}";alg="ed25519";created=1"#
);
let sig_input = format!(r#"sig1=("@method" "@path" "content-digest");keyid="{did}";alg="ed25519";created=1"#);
let sig = HttpSignature::parse(&sig_input, "sig1=:AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA:").unwrap();
assert!(sig.check_created().is_err());
}
+15 -92
View File
@@ -3,13 +3,13 @@
//! A gitlawb identity is an Ed25519 keypair. The public key encodes into a
//! `did:key` DID. The private key is stored as PKCS#8 PEM on disk.
use ed25519_dalek::{Signature, Signer, SigningKey, VerifyingKey};
use ed25519_dalek::{SigningKey, VerifyingKey, Signer, Signature};
use rand::rngs::OsRng;
use serde::{Deserialize, Serialize};
use zeroize::Zeroizing;
use crate::did::Did;
use crate::{Error, Result};
use crate::did::Did;
/// An Ed25519 keypair that is the root identity for a gitlawb actor.
#[derive(Clone)]
@@ -47,14 +47,12 @@ impl Keypair {
/// Sign and return base64url-encoded signature string.
pub fn sign_b64(&self, msg: &[u8]) -> String {
use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine};
use base64::{Engine, engine::general_purpose::URL_SAFE_NO_PAD};
let sig = self.sign(msg);
URL_SAFE_NO_PAD.encode(sig.to_bytes())
}
/// The raw 32-byte Ed25519 seed, wrapped in `Zeroizing` so the copy is
/// scrubbed on drop. This is the only seed accessor; it is used to derive
/// the X25519 secret for envelope decryption (see `crate::encrypt`).
/// Export the signing key as raw 32-byte seed (wrapped in Zeroizing).
pub fn to_seed(&self) -> Zeroizing<[u8; 32]> {
Zeroizing::new(self.signing_key.to_bytes())
}
@@ -71,13 +69,18 @@ impl Keypair {
/// Load from PEM-encoded PKCS#8 private key string.
pub fn from_pem(pem: &str) -> Result<Self> {
use pkcs8::DecodePrivateKey;
let signing_key = SigningKey::from_pkcs8_pem(pem).map_err(|e| Error::Key(e.to_string()))?;
let signing_key = SigningKey::from_pkcs8_pem(pem)
.map_err(|e| Error::Key(e.to_string()))?;
Ok(Self { signing_key })
}
}
/// Verify an Ed25519 signature.
pub fn verify(verifying_key: &VerifyingKey, msg: &[u8], sig_bytes: &[u8; 64]) -> Result<()> {
pub fn verify(
verifying_key: &VerifyingKey,
msg: &[u8],
sig_bytes: &[u8; 64],
) -> Result<()> {
use ed25519_dalek::Verifier;
let sig = Signature::from_bytes(sig_bytes);
verifying_key
@@ -114,8 +117,8 @@ impl<T: Serialize> Signed<T> {
}
mod sig_b64 {
use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine};
use serde::{Deserialize, Deserializer, Serializer};
use base64::{Engine, engine::general_purpose::URL_SAFE_NO_PAD};
use serde::{Deserializer, Serializer, Deserialize};
pub fn serialize<S: Serializer>(bytes: &[u8; 64], s: S) -> Result<S::Ok, S::Error> {
s.serialize_str(&URL_SAFE_NO_PAD.encode(bytes))
@@ -123,12 +126,8 @@ mod sig_b64 {
pub fn deserialize<'de, D: Deserializer<'de>>(d: D) -> Result<[u8; 64], D::Error> {
let s = String::deserialize(d)?;
let bytes = URL_SAFE_NO_PAD
.decode(&s)
.map_err(serde::de::Error::custom)?;
bytes
.try_into()
.map_err(|_| serde::de::Error::custom("expected 64 bytes"))
let bytes = URL_SAFE_NO_PAD.decode(&s).map_err(serde::de::Error::custom)?;
bytes.try_into().map_err(|_| serde::de::Error::custom("expected 64 bytes"))
}
}
@@ -159,80 +158,4 @@ mod tests {
let did = kp.did();
assert!(did.to_string().starts_with("did:key:z6Mk"));
}
#[test]
fn from_seed_round_trip() {
let kp = Keypair::generate();
let seed = kp.to_seed();
let kp2 = Keypair::from_seed(&seed).unwrap();
assert_eq!(kp.verifying_key(), kp2.verifying_key());
}
// `to_seed()` is the only seed accessor on `Keypair` (the raw, unzeroized
// `seed_bytes()` was removed in #41). Pin its return type so a bare-array
// accessor can't slip back in, and confirm it is deterministic. The
// from_seed -> verifying_key round-trip is already covered by
// `from_seed_round_trip`.
#[test]
fn to_seed_returns_zeroizing_and_is_deterministic() {
let kp = Keypair::generate();
// The type annotation is the regression guard: the seed must be handed
// out wrapped in `Zeroizing`, never as a bare `[u8; 32]`.
let seed: Zeroizing<[u8; 32]> = kp.to_seed();
assert_eq!(*kp.to_seed(), *seed); // stable across calls
}
#[test]
fn sign_b64_decodes_to_valid_signature() {
use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine};
let kp = Keypair::generate();
let msg = b"test payload for b64 signing";
let b64 = kp.sign_b64(msg);
let sig_bytes: [u8; 64] = URL_SAFE_NO_PAD
.decode(&b64)
.expect("sign_b64 must produce valid base64url")
.try_into()
.expect("Ed25519 signature must be 64 bytes");
verify(&kp.verifying_key(), msg, &sig_bytes).unwrap();
}
#[test]
fn verify_rejects_wrong_key() {
let kp1 = Keypair::generate();
let kp2 = Keypair::generate();
let msg = b"some message";
let sig = kp1.sign(msg);
let result = verify(&kp2.verifying_key(), msg, &sig.to_bytes());
assert!(
result.is_err(),
"signature from kp1 must not verify under kp2"
);
}
#[test]
fn signed_payload_round_trip() {
let kp = Keypair::generate();
let payload = serde_json::json!({"action": "push", "repo": "my-repo"});
let signed = Signed::new(payload, &kp).unwrap();
signed.verify(&kp.verifying_key()).unwrap();
}
#[test]
fn signed_payload_wrong_key_fails() {
let kp1 = Keypair::generate();
let kp2 = Keypair::generate();
let payload = serde_json::json!({"action": "push"});
let signed = Signed::new(payload, &kp1).unwrap();
let result = signed.verify(&kp2.verifying_key());
assert!(
result.is_err(),
"Signed payload must not verify under a different key"
);
}
#[test]
fn from_pem_invalid_input_fails() {
let result = Keypair::from_pem("this is not valid PEM at all");
assert!(result.is_err());
}
}
+4 -5
View File
@@ -1,11 +1,10 @@
pub mod cert;
pub mod cid;
pub mod did;
pub mod encrypt;
pub mod error;
pub mod http_sig;
pub mod cid;
pub mod identity;
pub mod http_sig;
pub mod ucan;
pub mod cert;
pub mod error;
pub use error::Error;
pub type Result<T> = std::result::Result<T, Error>;
+23 -247
View File
@@ -12,9 +12,9 @@
use chrono::{DateTime, Utc};
use serde::{Deserialize, Serialize};
use crate::{Error, Result};
use crate::did::Did;
use crate::identity::Keypair;
use crate::{Error, Result};
/// A UCAN capability: what resource the token grants access to.
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq)]
@@ -30,31 +30,13 @@ pub struct Capability {
impl Capability {
pub fn new(with: impl Into<String>, can: impl Into<String>) -> Self {
Self {
with: with.into(),
can: can.into(),
constraints: None,
}
Self { with: with.into(), can: can.into(), constraints: None }
}
pub fn with_constraints(mut self, constraints: serde_json::Value) -> Self {
self.constraints = Some(constraints);
self
}
/// Returns `true` if `self` is a valid attenuation of `parent`.
///
/// A delegated capability is only valid if it is at most as permissive as
/// the parent capability backing it. `"*"` on the **parent**'s resource or
/// action field and `repo/admin` in the parent's action position act as
/// wildcards that cover any delegated value; wildcards on `self` carry no
/// special meaning.
pub fn is_attenuated_by(&self, parent: &Capability) -> bool {
let resource_ok = parent.with == self.with || parent.with == "*";
let action_ok =
parent.can == self.can || parent.can == "*" || parent.can == caps::REPO_ADMIN;
resource_ok && action_ok
}
}
/// Well-known gitlawb capability strings.
@@ -146,40 +128,18 @@ impl Ucan {
}
}
/// Check if this UCAN's not-before time is in the future (token not yet valid).
pub fn is_before_valid(&self) -> bool {
if let Some(nbf) = self.payload.nbf {
Utc::now().timestamp() < nbf
} else {
false
}
}
/// Verify this UCAN's audience matches `expected`.
pub fn verify_audience(&self, expected: &Did) -> Result<()> {
if &self.payload.aud != expected {
return Err(Error::Ucan(format!(
"audience mismatch: expected {expected}, got {}",
self.payload.aud
)));
}
Ok(())
}
/// Verify the signature on this UCAN.
pub fn verify_signature(&self) -> Result<()> {
use base64::{Engine, engine::general_purpose::URL_SAFE_NO_PAD};
use crate::identity::verify;
use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine};
let vk = self.payload.iss.to_verifying_key()?;
let signing_bytes = serde_json::to_vec(&self.payload)?;
let sig_bytes_vec = URL_SAFE_NO_PAD
.decode(&self.s)
let sig_bytes_vec = URL_SAFE_NO_PAD.decode(&self.s)
.map_err(|e| Error::Ucan(format!("invalid base64 signature: {e}")))?;
let sig_bytes: [u8; 64] = sig_bytes_vec
.try_into()
let sig_bytes: [u8; 64] = sig_bytes_vec.try_into()
.map_err(|_| Error::Ucan("signature must be 64 bytes".to_string()))?;
verify(&vk, &signing_bytes, &sig_bytes)
@@ -188,10 +148,9 @@ impl Ucan {
/// Check if this UCAN grants a specific capability on a resource.
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| {
cap.with == resource && cap.can == action
})
}
/// Encode to a compact JSON string (the wire format).
@@ -251,10 +210,6 @@ impl Ucan {
return Err(Error::Ucan("token is expired".to_string()));
}
if self.is_before_valid() {
return Err(Error::Ucan("token is not yet valid".to_string()));
}
for proof_token in &self.payload.prf {
let proof = Self::decode(proof_token)
.map_err(|e| Error::Ucan(format!("failed to decode proof: {e}")))?;
@@ -267,17 +222,6 @@ impl Ucan {
)));
}
// Every delegated capability must be covered by the proof (attenuation).
for cap in &self.payload.att {
let covered = proof.payload.att.iter().any(|p| cap.is_attenuated_by(p));
if !covered {
return Err(Error::Ucan(format!(
"capability attenuation violated: '{}' on '{}' not covered by proof",
cap.can, cap.with
)));
}
}
// Verify the proof's signature and chain recursively
proof.verify_chain()?;
}
@@ -301,8 +245,7 @@ mod tests {
audience.clone(),
vec![Capability::new("gitlawb://repos/test/repo", caps::GIT_PUSH)],
None,
)
.unwrap();
).unwrap();
ucan.verify_signature().unwrap();
assert!(!ucan.is_expired());
@@ -348,12 +291,10 @@ mod tests {
let issuer = Keypair::generate();
let audience = Keypair::generate().did();
let ucan = Ucan::issue(
&issuer,
audience,
&issuer, audience,
vec![Capability::new("gitlawb://repos/test", caps::GIT_PUSH)],
None,
)
.unwrap();
).unwrap();
// Root UCAN (no proofs) should verify fine
ucan.verify_chain().unwrap();
}
@@ -366,22 +307,18 @@ mod tests {
// Alice grants Bob push access
let root = Ucan::issue(
&alice,
bob.did(),
&alice, bob.did(),
vec![Capability::new("gitlawb://repos/test", caps::GIT_PUSH)],
None,
)
.unwrap();
).unwrap();
// Bob delegates to Charlie (with proof from Alice)
let delegated = Ucan::delegate(
&bob,
charlie.did(),
&bob, charlie.did(),
vec![Capability::new("gitlawb://repos/test", caps::GIT_PUSH)],
None,
&root,
)
.unwrap();
).unwrap();
// Chain should verify: Charlie's token → Bob's proof → Alice signed it
delegated.verify_chain().unwrap();
@@ -397,22 +334,18 @@ mod tests {
// Alice grants Bob access
let root = Ucan::issue(
&alice,
bob.did(),
&alice, bob.did(),
vec![Capability::new("gitlawb://repos/test", caps::GIT_PUSH)],
None,
)
.unwrap();
).unwrap();
// Eve (NOT Bob) tries to delegate using Alice's proof
let bad = Ucan::delegate(
&eve,
charlie.did(),
&eve, charlie.did(),
vec![Capability::new("gitlawb://repos/test", caps::GIT_PUSH)],
None,
&root,
)
.unwrap();
).unwrap();
// Should fail: proof audience (Bob) != UCAN issuer (Eve)
let err = bad.verify_chain().unwrap_err();
@@ -428,177 +361,20 @@ mod tests {
// Alice grants Bob access with expiry in the past
let exp = chrono::Utc::now() - chrono::Duration::hours(1);
let root = Ucan::issue(
&alice,
bob.did(),
&alice, bob.did(),
vec![Capability::new("gitlawb://repos/test", caps::GIT_PUSH)],
Some(exp),
)
.unwrap();
).unwrap();
let delegated = Ucan::delegate(
&bob,
charlie.did(),
&bob, charlie.did(),
vec![Capability::new("gitlawb://repos/test", caps::GIT_PUSH)],
None,
&root,
)
.unwrap();
).unwrap();
// Should fail: the proof is expired
let err = delegated.verify_chain().unwrap_err();
assert!(err.to_string().contains("expired"));
}
#[test]
fn is_before_valid_future_nbf() {
let issuer = Keypair::generate();
let audience = Keypair::generate().did();
let nbf_future = chrono::Utc::now() + chrono::Duration::hours(1);
let payload = UcanPayload {
ucan: "1.0.0".to_string(),
iss: issuer.did(),
aud: audience,
att: vec![],
exp: None,
nbf: Some(nbf_future.timestamp()),
prf: vec![],
};
let signing_bytes = serde_json::to_vec(&payload).unwrap();
let sig = issuer.sign_b64(&signing_bytes);
let ucan = Ucan { payload, s: sig };
assert!(ucan.is_before_valid());
let err = ucan.verify_chain().unwrap_err();
assert!(err.to_string().contains("not yet valid"));
}
#[test]
fn is_before_valid_past_nbf() {
let issuer = Keypair::generate();
let audience = Keypair::generate().did();
let nbf_past = chrono::Utc::now() - chrono::Duration::hours(1);
let payload = UcanPayload {
ucan: "1.0.0".to_string(),
iss: issuer.did(),
aud: audience,
att: vec![Capability::new("gitlawb://repos/test", caps::GIT_PUSH)],
exp: None,
nbf: Some(nbf_past.timestamp()),
prf: vec![],
};
let signing_bytes = serde_json::to_vec(&payload).unwrap();
let sig = issuer.sign_b64(&signing_bytes);
let ucan = Ucan { payload, s: sig };
assert!(!ucan.is_before_valid());
ucan.verify_chain().unwrap();
}
#[test]
fn verify_audience_matches() {
let issuer = Keypair::generate();
let audience = Keypair::generate().did();
let ucan = Ucan::issue(&issuer, audience.clone(), vec![], None).unwrap();
ucan.verify_audience(&audience).unwrap();
}
#[test]
fn verify_audience_mismatch() {
let issuer = Keypair::generate();
let audience = Keypair::generate().did();
let wrong = Keypair::generate().did();
let ucan = Ucan::issue(&issuer, audience, vec![], None).unwrap();
let err = ucan.verify_audience(&wrong).unwrap_err();
assert!(err.to_string().contains("audience mismatch"));
}
#[test]
fn attenuation_valid_subset() {
let alice = Keypair::generate();
let bob = Keypair::generate();
let charlie = Keypair::generate();
// Alice grants Bob push on a specific repo
let root = Ucan::issue(
&alice,
bob.did(),
vec![Capability::new("gitlawb://repos/org/repo", caps::GIT_PUSH)],
None,
)
.unwrap();
// Bob delegates the same capability (exact subset) to Charlie
let delegated = Ucan::delegate(
&bob,
charlie.did(),
vec![Capability::new("gitlawb://repos/org/repo", caps::GIT_PUSH)],
None,
&root,
)
.unwrap();
delegated.verify_chain().unwrap();
}
#[test]
fn attenuation_exceeds_parent_is_rejected() {
let alice = Keypair::generate();
let bob = Keypair::generate();
let charlie = Keypair::generate();
// Alice grants Bob push on one repo only
let root = Ucan::issue(
&alice,
bob.did(),
vec![Capability::new("gitlawb://repos/org/repo", caps::GIT_PUSH)],
None,
)
.unwrap();
// Bob tries to delegate merge (not in the original grant) to Charlie
let delegated = Ucan::delegate(
&bob,
charlie.did(),
vec![Capability::new("gitlawb://repos/org/repo", caps::PR_MERGE)],
None,
&root,
)
.unwrap();
let err = delegated.verify_chain().unwrap_err();
assert!(err.to_string().contains("attenuation violated"));
}
#[test]
fn attenuation_repo_admin_covers_all() {
let alice = Keypair::generate();
let bob = Keypair::generate();
let charlie = Keypair::generate();
// Alice grants Bob repo/admin (superpower)
let root = Ucan::issue(
&alice,
bob.did(),
vec![Capability::new(
"gitlawb://repos/org/repo",
caps::REPO_ADMIN,
)],
None,
)
.unwrap();
// Bob delegates a more specific capability — covered by repo/admin
let delegated = Ucan::delegate(
&bob,
charlie.did(),
vec![Capability::new("gitlawb://repos/org/repo", caps::GIT_PUSH)],
None,
&root,
)
.unwrap();
delegated.verify_chain().unwrap();
}
}
+4 -23
View File
@@ -1,9 +1,8 @@
[package]
name = "gitlawb-node"
description = "The gitlawb node daemon — git hosting over HTTP with DID auth"
version = "0.5.1" # x-release-please-version
version.workspace = true
edition.workspace = true
rust-version.workspace = true
license.workspace = true
[[bin]]
@@ -12,8 +11,6 @@ path = "src/main.rs"
[dependencies]
gitlawb-core = { path = "../gitlawb-core" }
ed25519-dalek = { workspace = true }
base64 = { workspace = true }
tokio = { workspace = true }
serde = { workspace = true }
serde_json = { workspace = true }
@@ -29,10 +26,9 @@ async-graphql-axum = "7"
tokio-stream = { version = "0.1", features = ["sync"] }
tower = "0.5"
tower-http = { version = "0.6", features = ["cors", "trace", "request-id", "limit"] }
sqlx = { version = "0.8", features = ["postgres", "runtime-tokio-rustls", "chrono", "uuid", "macros", "migrate"] }
sqlx = { version = "0.8", features = ["postgres", "runtime-tokio-rustls", "chrono", "uuid"] }
clap = { version = "4", features = ["derive", "env"] }
bytes = "1"
libc = "0.2"
cid = { workspace = true }
hex = { workspace = true }
sha2 = { workspace = true }
@@ -40,28 +36,14 @@ hmac = { workspace = true }
http-body-util = "0.1"
tokio-util = { version = "0.7", features = ["io"] }
dirs-next = "2"
# NFC-normalize visibility globs/paths at the matcher seam so a deny rule
# withholds a canonically-equivalent path regardless of NFC/NFD form (#101).
unicode-normalization = "0.1"
reqwest = { workspace = true }
libp2p-core = "0.43"
libp2p-gossipsub = "0.49.4"
libp2p-identify = "0.47"
libp2p-identity = { version = "0.2", features = ["ed25519", "peerid", "rand"] }
libp2p-kad = "0.48"
libp2p-quic = { version = "0.13", features = ["tokio"] }
libp2p-swarm = { version = "0.47", features = ["macros", "tokio"] }
multiaddr = "0.18"
libp2p = { version = "0.55", features = ["gossipsub", "kad", "mdns", "noise", "tcp", "tokio", "yamux", "identify", "macros"] }
futures = "0.3"
aws-sdk-s3 = { version = "1", default-features = false, features = ["sigv4a", "default-https-client", "rt-tokio"] }
aws-sdk-s3 = "1"
aws-config = { version = "1", features = ["behavior-version-latest"] }
async-compression = { version = "0.4", features = ["tokio", "zstd"] }
tar = "0.4"
zstd = "0.13"
# Prometheus metrics. Used to expose a /metrics endpoint for ops/observability
# on the opt-in GITLAWB_METRICS_ADDR listener. The crate is also the de-facto
# exposition format encoder in the Rust ecosystem.
prometheus = { version = "0.13", default-features = false }
alloy = { version = "1", default-features = false, features = [
"contract",
"provider-http",
@@ -72,7 +54,6 @@ alloy = { version = "1", default-features = false, features = [
"network",
"rpc-types-eth",
] }
libp2p-dns = { version = "0.44.0", features = ["tokio"] }
[dev-dependencies]
mockito = "1"
+20 -186
View File
@@ -2,52 +2,12 @@
use axum::extract::{Path, Query, State};
use axum::http::StatusCode;
use axum::{Extension, Json};
use axum::Json;
use serde::{Deserialize, Serialize};
use crate::auth::AuthenticatedDid;
use crate::error::{AppError, Result};
use crate::state::AppState;
fn normalize_agent_did(did: &str) -> String {
if did.starts_with("did:") {
did.to_string()
} else {
format!("did:key:{did}")
}
}
fn agent_key_segment(did: &str) -> &str {
did.split(':').next_back().unwrap_or(did)
}
/// Whether `caller` (the verified `AuthenticatedDid`) is the same identity as
/// `target` (the DID being acted on), tolerant of full `did:key:...` vs short
/// key-only forms on either side. Used to gate self-deregistration so a DID
/// can only retire itself.
fn caller_matches_did(caller: &str, target: &str) -> bool {
agent_key_segment(caller) == agent_key_segment(target)
}
async fn resolve_agent_did(state: &AppState, did: &str) -> Result<String> {
let normalized_did = normalize_agent_did(did);
if state.db.get_agent(&normalized_did).await?.is_some() {
return Ok(normalized_did);
}
let requested_key = agent_key_segment(&normalized_did);
let matching_agent = state
.db
.list_agents(None)
.await?
.into_iter()
.find(|agent| agent_key_segment(&agent.did).starts_with(requested_key));
Ok(matching_agent
.map(|agent| agent.did)
.unwrap_or(normalized_did))
}
#[derive(Debug, Serialize)]
pub struct TrustResponse {
pub did: String,
@@ -80,8 +40,6 @@ pub struct AgentResponse {
pub capabilities: Vec<String>,
pub registered_at: String,
pub last_seen: Option<String>,
/// Lifecycle status: `active` or `revoked`.
pub status: String,
}
/// GET /api/v1/agents
@@ -90,17 +48,13 @@ pub async fn list_agents(
Query(params): Query<AgentListQuery>,
) -> Result<Json<serde_json::Value>> {
let agents = state.db.list_agents(params.capability.as_deref()).await?;
let list: Vec<AgentResponse> = agents
.into_iter()
.map(|a| AgentResponse {
did: a.did,
trust_score: a.trust_score,
capabilities: a.capabilities,
registered_at: a.registered_at,
last_seen: a.last_seen,
status: a.status,
})
.collect();
let list: Vec<AgentResponse> = agents.into_iter().map(|a| AgentResponse {
did: a.did,
trust_score: a.trust_score,
capabilities: a.capabilities,
registered_at: a.registered_at,
last_seen: a.last_seen,
}).collect();
Ok(Json(serde_json::json!({ "agents": list })))
}
@@ -109,23 +63,15 @@ pub async fn show_agent(
State(state): State<AppState>,
Path(did): Path<String>,
) -> Result<(StatusCode, Json<AgentResponse>)> {
let normalized_did = resolve_agent_did(&state, &did).await?;
let agent = state
.db
.get_agent(&normalized_did)
.await?
.ok_or_else(|| AppError::NotFound(format!("agent {normalized_did} not found")))?;
Ok((
StatusCode::OK,
Json(AgentResponse {
did: agent.did,
trust_score: agent.trust_score,
capabilities: agent.capabilities,
registered_at: agent.registered_at,
last_seen: agent.last_seen,
status: agent.status,
}),
))
let agent = state.db.get_agent(&did).await?
.ok_or_else(|| AppError::NotFound(format!("agent {did} not found")))?;
Ok((StatusCode::OK, Json(AgentResponse {
did: agent.did,
trust_score: agent.trust_score,
capabilities: agent.capabilities,
registered_at: agent.registered_at,
last_seen: agent.last_seen,
})))
}
/// GET /api/v1/agents/{did}/trust
@@ -133,126 +79,14 @@ pub async fn get_trust(
State(state): State<AppState>,
Path(did): Path<String>,
) -> Result<Json<TrustResponse>> {
let normalized_did = resolve_agent_did(&state, &did).await?;
let trust_score = state.db.get_trust_score(&normalized_did).await?;
let push_count = state.db.get_push_count(&normalized_did).await?;
let trust_score = state.db.get_trust_score(&did).await?;
let push_count = state.db.get_push_count(&did).await?;
let level = trust_level(trust_score);
Ok(Json(TrustResponse {
did: normalized_did,
did,
trust_score,
push_count,
level,
}))
}
/// DELETE /api/v1/agents/{did}
///
/// Self-deregistration: the holder of a DID's key marks their own agent
/// `revoked`, removing it from discovery (issue #29). Authenticated by the
/// rfc9421 signature middleware; a caller may only retire its own DID.
pub async fn deregister_agent(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
Path(did): Path<String>,
) -> Result<StatusCode> {
// Authorize on the verified identity, and act on it too. The path DID is
// only an intent check (it must name the caller); the row we revoke is the
// authenticated DID itself, never a value derived from the untrusted path.
// Revoking `resolve_agent_did(did)` instead would let the fuzzy prefix
// resolver act on a different identity than the one just authorized.
if !caller_matches_did(&auth.0, &did) {
return Err(AppError::BadRequest(
"an agent can only deregister itself".into(),
));
}
if state.db.revoke_agent(&auth.0).await? {
Ok(StatusCode::NO_CONTENT)
} else {
Err(AppError::NotFound(format!("agent {} not found", auth.0)))
}
}
#[cfg(test)]
mod tests {
use super::{agent_key_segment, caller_matches_did, normalize_agent_did, AgentResponse};
#[test]
fn caller_matches_own_did_full_form() {
assert!(caller_matches_did(
"did:key:z6MkExample",
"did:key:z6MkExample"
));
}
#[test]
fn caller_matches_own_did_short_form() {
// Authenticated full DID vs short path form, and vice versa.
assert!(caller_matches_did("did:key:z6MkExample", "z6MkExample"));
assert!(caller_matches_did("z6MkExample", "did:key:z6MkExample"));
}
#[test]
fn caller_cannot_revoke_a_different_did() {
// The core authorization property for issue #29.
assert!(!caller_matches_did(
"did:key:z6MkAttacker",
"did:key:z6MkVictim"
));
assert!(!caller_matches_did("did:key:z6MkAttacker", "z6MkVictim"));
}
#[test]
fn agent_response_surfaces_status() {
// A revoked DID's response must carry its status so callers can see it
// is retired (issue #29).
let resp = AgentResponse {
did: "did:key:orphan".to_string(),
trust_score: 0.1,
capabilities: vec!["reputation:score".to_string()],
registered_at: "2026-06-19T00:00:00Z".to_string(),
last_seen: None,
status: "revoked".to_string(),
};
let json = serde_json::to_value(&resp).unwrap();
assert_eq!(json["status"], "revoked");
assert!(json.get("replaced_by").is_none());
}
#[test]
fn agent_response_active_status() {
let resp = AgentResponse {
did: "did:key:active".to_string(),
trust_score: 0.5,
capabilities: vec![],
registered_at: "2026-06-19T00:00:00Z".to_string(),
last_seen: None,
status: "active".to_string(),
};
let json = serde_json::to_value(&resp).unwrap();
assert_eq!(json["status"], "active");
}
#[test]
fn normalize_agent_did_preserves_full_did() {
let did = "did:key:z6MkExample";
assert_eq!(normalize_agent_did(did), did);
}
#[test]
fn normalize_agent_did_expands_bare_key() {
assert_eq!(normalize_agent_did("z6MkExample"), "did:key:z6MkExample");
}
#[test]
fn agent_key_segment_extracts_did_key_material() {
assert_eq!(agent_key_segment("did:key:z6MkExample"), "z6MkExample");
assert_eq!(agent_key_segment("z6MkExample"), "z6MkExample");
}
}
+1 -1
View File
@@ -30,7 +30,7 @@ pub async fn list_anchors(
.db
.list_arweave_anchors(q.repo.as_deref(), limit)
.await
.map_err(crate::error::AppError::Internal)?;
.map_err(|e| crate::error::AppError::Internal(e.into()))?;
Ok(Json(serde_json::json!({
"anchors": anchors,
+54 -229
View File
@@ -79,9 +79,9 @@ pub async fn create_bounty(
return Err(AppError::BadRequest("amount must be positive".into()));
}
// Read-gate: anyone who can read the repo may fund a bounty on it (this closes
// the private-repo bounty leak); ownership is not required.
crate::api::authorize_repo_read(&state, &owner, &repo, Some(auth.0.as_str()), "/").await?;
// Verify repo exists
let _ = state.db.get_repo(&owner, &repo).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
let now = Utc::now().to_rfc3339();
let bounty = BountyRecord {
@@ -110,30 +110,18 @@ 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(),
limit,
None,
None,
)
.await?;
let bounties = state.db.list_bounties(
Some(&owner),
Some(&repo),
q.status.as_deref(),
q.limit.unwrap_or(50),
).await?;
Ok(Json(serde_json::json!({ "bounties": bounties })))
}
@@ -142,92 +130,24 @@ 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 raw_limit = q.limit.unwrap_or(50);
let limit = raw_limit.clamp(1, MAX_BOUNTY_LIMIT);
let bounties = state.db.list_bounties(
None,
None,
q.status.as_deref(),
q.limit.unwrap_or(50),
).await?;
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 })))
Ok(Json(serde_json::json!({ "bounties": bounties })))
}
/// 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 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());
}
let bounty = state.db.get_bounty(&id).await?
.ok_or_else(|| AppError::NotFound(format!("bounty {id} not found")))?;
Ok(Json(bounty))
}
@@ -238,42 +158,19 @@ pub async fn claim_bounty(
Path(id): Path<String>,
Json(req): Json<ClaimBountyRequest>,
) -> Result<Json<BountyRecord>> {
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());
}
let bounty = state.db.get_bounty(&id).await?
.ok_or_else(|| AppError::NotFound(format!("bounty {id} not found")))?;
if bounty.status != "open" {
return Err(AppError::BadRequest(format!(
"bounty is {}, not open",
bounty.status
)));
return Err(AppError::BadRequest(format!("bounty is {}, not open", bounty.status)));
}
let now = Utc::now().to_rfc3339();
state
.db
.claim_bounty(&id, &auth.0, req.wallet.as_deref(), &now)
.await?;
state.db.claim_bounty(&id, &auth.0, req.wallet.as_deref(), &now).await?;
tracing::info!(bounty_id = %id, agent = %auth.0, "bounty claimed");
let updated = state
.db
.get_bounty(&id)
.await?
let updated = state.db.get_bounty(&id).await?
.ok_or_else(|| AppError::NotFound(format!("bounty {id} not found")))?;
Ok(Json(updated))
}
@@ -285,24 +182,14 @@ pub async fn submit_bounty(
Path(id): Path<String>,
Json(req): Json<SubmitBountyRequest>,
) -> Result<Json<BountyRecord>> {
let bounty = state
.db
.get_bounty(&id)
.await?
let bounty = state.db.get_bounty(&id).await?
.ok_or_else(|| AppError::NotFound(format!("bounty {id} not found")))?;
if bounty.status != "claimed" {
return Err(AppError::BadRequest(format!(
"bounty is {}, not claimed",
bounty.status
)));
return Err(AppError::BadRequest(format!("bounty is {}, not claimed", bounty.status)));
}
let is_claimant = bounty
.claimant_did
.as_deref()
.is_some_and(|c| crate::api::did_matches(&auth.0, c));
if !is_claimant {
return Err(AppError::Forbidden("only the claimant can submit".into()));
if bounty.claimant_did.as_deref() != Some(&auth.0) {
return Err(AppError::BadRequest("only the claimant can submit".into()));
}
let now = Utc::now().to_rfc3339();
@@ -310,10 +197,7 @@ pub async fn submit_bounty(
tracing::info!(bounty_id = %id, pr_id = %req.pr_id, "bounty submission");
let updated = state
.db
.get_bounty(&id)
.await?
let updated = state.db.get_bounty(&id).await?
.ok_or_else(|| AppError::NotFound(format!("bounty {id} not found")))?;
Ok(Json(updated))
}
@@ -325,29 +209,18 @@ pub async fn approve_bounty(
Path(id): Path<String>,
Json(req): Json<ApproveBountyRequest>,
) -> Result<Json<BountyRecord>> {
let bounty = state
.db
.get_bounty(&id)
.await?
let bounty = state.db.get_bounty(&id).await?
.ok_or_else(|| AppError::NotFound(format!("bounty {id} not found")))?;
if bounty.status != "submitted" {
return Err(AppError::BadRequest(format!(
"bounty is {}, not submitted",
bounty.status
)));
return Err(AppError::BadRequest(format!("bounty is {}, not submitted", bounty.status)));
}
if !crate::api::did_matches(&auth.0, &bounty.creator_did) {
return Err(AppError::Forbidden(
"only the bounty creator can approve".into(),
));
if bounty.creator_did != auth.0 {
return Err(AppError::BadRequest("only the bounty creator can approve".into()));
}
let now = Utc::now().to_rfc3339();
state
.db
.approve_bounty(&id, &now, req.tx_hash.as_deref())
.await?;
state.db.approve_bounty(&id, &now, req.tx_hash.as_deref()).await?;
// Bump claimant trust score
if let Some(ref agent_did) = bounty.claimant_did {
@@ -358,10 +231,7 @@ pub async fn approve_bounty(
tracing::info!(bounty_id = %id, "bounty approved");
let updated = state
.db
.get_bounty(&id)
.await?
let updated = state.db.get_bounty(&id).await?
.ok_or_else(|| AppError::NotFound(format!("bounty {id} not found")))?;
Ok(Json(updated))
}
@@ -372,31 +242,20 @@ pub async fn cancel_bounty(
Extension(auth): Extension<AuthenticatedDid>,
Path(id): Path<String>,
) -> Result<Json<BountyRecord>> {
let bounty = state
.db
.get_bounty(&id)
.await?
let bounty = state.db.get_bounty(&id).await?
.ok_or_else(|| AppError::NotFound(format!("bounty {id} not found")))?;
if bounty.status != "open" {
return Err(AppError::BadRequest(format!(
"can only cancel open bounties, status is {}",
bounty.status
)));
return Err(AppError::BadRequest(format!("can only cancel open bounties, status is {}", bounty.status)));
}
if !crate::api::did_matches(&auth.0, &bounty.creator_did) {
return Err(AppError::Forbidden(
"only the bounty creator can cancel".into(),
));
if bounty.creator_did != auth.0 {
return Err(AppError::BadRequest("only the bounty creator can cancel".into()));
}
state.db.cancel_bounty(&id).await?;
tracing::info!(bounty_id = %id, "bounty cancelled");
let updated = state
.db
.get_bounty(&id)
.await?
let updated = state.db.get_bounty(&id).await?
.ok_or_else(|| AppError::NotFound(format!("bounty {id} not found")))?;
Ok(Json(updated))
}
@@ -404,33 +263,13 @@ pub async fn cancel_bounty(
/// POST /api/v1/bounties/{id}/dispute
pub async fn dispute_bounty(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
Path(id): Path<String>,
) -> Result<Json<BountyRecord>> {
let bounty = state
.db
.get_bounty(&id)
.await?
let bounty = state.db.get_bounty(&id).await?
.ok_or_else(|| AppError::NotFound(format!("bounty {id} not found")))?;
if bounty.status != "claimed" && bounty.status != "submitted" {
return Err(AppError::BadRequest(format!(
"can only dispute claimed/submitted bounties, status is {}",
bounty.status
)));
}
// Only the bounty creator or the current claimant may dispute (N19 — this
// endpoint had no identity check at all).
let is_creator = crate::api::did_matches(&auth.0, &bounty.creator_did);
let is_claimant = bounty
.claimant_did
.as_deref()
.is_some_and(|c| crate::api::did_matches(&auth.0, c));
if !is_creator && !is_claimant {
return Err(AppError::Forbidden(
"only the bounty creator or claimant can dispute this bounty".into(),
));
return Err(AppError::BadRequest(format!("can only dispute claimed/submitted bounties, status is {}", bounty.status)));
}
// Check if deadline exceeded
@@ -438,47 +277,33 @@ pub async fn dispute_bounty(
if let Ok(claimed) = chrono::DateTime::parse_from_rfc3339(claimed_at) {
let deadline = claimed + chrono::Duration::seconds(bounty.deadline_secs);
if Utc::now() < deadline {
return Err(AppError::BadRequest(
"deadline has not been exceeded yet".into(),
));
return Err(AppError::BadRequest("deadline has not been exceeded yet".into()));
}
}
}
state.db.dispute_bounty(&id).await?;
tracing::info!(bounty_id = %id, actor = %auth.0, "bounty disputed - reopened");
tracing::info!(bounty_id = %id, "bounty disputed — reopened");
let updated = state
.db
.get_bounty(&id)
.await?
let updated = state.db.get_bounty(&id).await?
.ok_or_else(|| AppError::NotFound(format!("bounty {id} not found")))?;
Ok(Json(updated))
}
/// GET /api/v1/bounties/stats
pub async fn bounty_stats(State(state): State<AppState>) -> Result<Json<BountyStatsResponse>> {
pub async fn bounty_stats(
State(state): State<AppState>,
) -> Result<Json<BountyStatsResponse>> {
let open = state.db.count_bounties_by_status("open").await.unwrap_or(0);
let claimed = state
.db
.count_bounties_by_status("claimed")
.await
.unwrap_or(0);
let completed = state
.db
.count_bounties_by_status("completed")
.await
.unwrap_or(0);
let claimed = state.db.count_bounties_by_status("claimed").await.unwrap_or(0);
let completed = state.db.count_bounties_by_status("completed").await.unwrap_or(0);
let leaders = state.db.bounty_leaderboard(10).await.unwrap_or_default();
let leaderboard = leaders
.into_iter()
.map(|(did, cnt, total)| AgentBountyEntry {
did,
completed: cnt,
total_earned: total,
})
.collect();
let leaderboard = leaders.into_iter().map(|(did, cnt, total)| AgentBountyEntry {
did,
completed: cnt,
total_earned: total,
}).collect();
Ok(Json(BountyStatsResponse {
open,
+21 -61
View File
@@ -1,87 +1,47 @@
//! API handlers for ref certificates.
use std::collections::HashMap;
use axum::extract::{Extension, Path, Query, State};
use axum::extract::{Path, State};
use axum::Json;
use crate::auth::AuthenticatedDid;
use crate::error::{AppError, Result};
use crate::state::AppState;
/// GET /api/v1/repos/{owner}/{repo}/certs?limit=50
/// GET /api/v1/repos/{owner}/{repo}/certs
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 limit = params
.get("limit")
.and_then(|v| v.parse::<i64>().ok())
.map(|v| v.max(1))
.unwrap_or(50)
.min(200);
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 certs = state.db.list_ref_certificates(&record.id).await?;
let certs_json: Vec<serde_json::Value> = certs.iter().map(|c| serde_json::json!({
"id": c.id,
"repo_id": c.repo_id,
"ref_name": c.ref_name,
"old_sha": c.old_sha,
"new_sha": c.new_sha,
"pusher_did": c.pusher_did,
"node_did": c.node_did,
"signature": c.signature,
"issued_at": c.issued_at,
})).collect();
// 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| {
serde_json::json!({
"id": c.id,
"repo_id": c.repo_id,
"ref_name": c.ref_name,
"old_sha": c.old_sha,
"new_sha": c.new_sha,
"pusher_did": c.pusher_did,
"node_did": c.node_did,
"signature": c.signature,
"issued_at": c.issued_at,
})
})
.collect();
let count = certs_json.len();
Ok(Json(
serde_json::json!({ "certificates": certs_json, "count": count }),
))
Ok(Json(serde_json::json!({ "certificates": certs_json })))
}
/// 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>> {
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?;
// Verify the repo exists
let _record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
let cert = state
.db
.get_ref_certificate(&id)
.await?
let cert = state.db.get_ref_certificate(&id).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,
+14 -25
View File
@@ -1,10 +1,9 @@
//! Changelog endpoint — unified timeline of commits, merged PRs, and closed issues.
use axum::extract::{Extension, Path, Query, State};
use axum::extract::{Path, Query, State};
use axum::Json;
use serde::Deserialize;
use crate::auth::AuthenticatedDid;
use crate::error::{AppError, Result};
use crate::git::store;
use crate::state::AppState;
@@ -15,9 +14,7 @@ pub struct ChangelogQuery {
pub limit: usize,
}
fn default_limit() -> usize {
20
}
fn default_limit() -> usize { 20 }
/// GET /api/v1/repos/:owner/:repo/changelog[?limit=N]
///
@@ -28,36 +25,28 @@ pub async fn get_changelog(
State(state): State<AppState>,
Path((owner, repo)): Path<(String, String)>,
Query(query): Query<ChangelogQuery>,
auth: Option<Extension<AuthenticatedDid>>,
) -> Result<Json<serde_json::Value>> {
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 record = state.db.get_repo(&owner, &repo).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
let limit = query.limit.min(100);
// ── Commits from git log ─────────────────────────────────────────────
let disk_path = state
.repo_store
.acquire(&record.owner_did, &record.name)
.await
let disk_path = state.repo_store.acquire(&record.owner_did, &record.name).await
.map_err(|e| AppError::Git(e.to_string()))?;
let head_ref = store::resolve_head(&disk_path, &record.default_branch);
let commits = store::log(&disk_path, &head_ref, limit).unwrap_or_default();
let mut events: Vec<serde_json::Value> = commits
.into_iter()
.map(|c| {
serde_json::json!({
"type": "commit",
"sha": c.hash,
"message": c.subject,
"author": c.author_name,
"timestamp": c.timestamp,
"branch": record.default_branch,
})
let mut events: Vec<serde_json::Value> = commits.into_iter().map(|c| {
serde_json::json!({
"type": "commit",
"sha": c.hash,
"message": c.subject,
"author": c.author_name,
"timestamp": c.timestamp,
"branch": record.default_branch,
})
.collect();
}).collect();
// ── Merged PRs ───────────────────────────────────────────────────────
let prs = state.db.list_prs(&record.id).await.unwrap_or_default();
-123
View File
@@ -1,123 +0,0 @@
//! Authenticated discovery + fetch for encrypted withheld blobs (Option B1).
use axum::extract::{Extension, Path, State};
use axum::Json;
use crate::auth::AuthenticatedDid;
use crate::error::{AppError, Result};
use crate::state::AppState;
use crate::visibility::{visibility_check, Decision};
/// GET /api/v1/repos/{owner}/{repo}/encrypted-blobs
/// Returns [{oid, cid}] for every encrypted blob in the repo, to any caller who
/// can read the repo. Not recipient-scoped: recipient identities are not stored,
/// so access control here is repo readability and decryption is gated by the
/// envelope crypto (only a real recipient can open an envelope).
pub async fn list_encrypted_blobs(
State(state): State<AppState>,
auth: Option<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 caller = auth.as_ref().map(|e| e.0 .0.as_str());
let rules = state.db.list_visibility_rules(&record.id).await?;
if visibility_check(&rules, record.is_public, &record.owner_did, caller, "/") == Decision::Deny
{
return Err(AppError::RepoNotFound(format!("{owner}/{repo}")));
}
let rows = state.db.list_all_encrypted_blobs(&record.id).await?;
let blobs: Vec<_> = rows
.into_iter()
.map(|(oid, cid)| serde_json::json!({ "oid": oid, "cid": cid }))
.collect();
Ok(Json(serde_json::json!({ "blobs": blobs })))
}
/// GET /api/v1/repos/{owner}/{repo}/encrypted-blob/{oid}
/// Returns raw envelope bytes to callers who can read the repo; the envelope
/// crypto still ensures only true recipients can decrypt.
pub async fn get_encrypted_blob(
State(state): State<AppState>,
auth: Option<Extension<AuthenticatedDid>>,
Path((owner, repo, oid)): Path<(String, String, String)>,
) -> Result<Vec<u8>> {
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 rules = state.db.list_visibility_rules(&record.id).await?;
if visibility_check(&rules, record.is_public, &record.owner_did, caller, "/") == Decision::Deny
{
return Err(AppError::RepoNotFound(format!("{owner}/{repo}/{oid}")));
}
let cid = state
.db
.encrypted_blob_cid(&record.id, &oid)
.await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}/{oid}")))?;
let bytes = crate::ipfs_pin::cat(&state.config.ipfs_api, &cid)
.await
.map_err(|e| AppError::Git(e.to_string()))?;
Ok(bytes)
}
/// GET /api/v1/repos/{owner}/{repo}/encrypted-blobs/replicate
/// Returns [{oid, cid}] for every encrypted blob in the repo, for peer-mirror
/// replication (Option B2). Gated by repo readability, like discovery, so a
/// non-readable repo does not expose its blob index; for the intended case (a
/// public repo with withheld subtrees) the public root keeps this open to peers.
/// Recipient identities are deliberately withheld: the v2 envelopes no longer
/// carry recipient public keys, so peers must not learn the reader set either. A
/// mirror detects a re-seal by the CID changing (the OID is stable across
/// re-seals). Ciphertext metadata only, never plaintext.
pub async fn replicate_encrypted_blobs(
State(state): State<AppState>,
auth: Option<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 caller = auth.as_ref().map(|e| e.0 .0.as_str());
let rules = state.db.list_visibility_rules(&record.id).await?;
if visibility_check(&rules, record.is_public, &record.owner_did, caller, "/") == Decision::Deny
{
return Err(AppError::RepoNotFound(format!("{owner}/{repo}")));
}
let rows = state.db.list_all_encrypted_blobs(&record.id).await?;
let blobs: Vec<_> = rows
.into_iter()
.map(|(oid, cid)| replicate_blob_json(oid, cid))
.collect();
Ok(Json(serde_json::json!({ "blobs": blobs })))
}
/// Serialize one blob for the replication wire. Recipient identities are
/// intentionally absent so a mirror never learns the reader set.
fn replicate_blob_json(oid: String, cid: String) -> serde_json::Value {
serde_json::json!({ "oid": oid, "cid": cid })
}
#[cfg(test)]
mod tests {
use super::replicate_blob_json;
#[test]
fn replicate_blob_json_omits_recipients() {
let v = replicate_blob_json("oid1".into(), "cidA".into());
assert_eq!(v["oid"], "oid1");
assert_eq!(v["cid"], "cidA");
assert!(
v.get("recipients").is_none(),
"replication wire must not carry recipient identities"
);
}
}
File diff suppressed because it is too large. Load diff
+32 -148
View File
@@ -9,55 +9,28 @@
//! `git cat-file <type> <sha256>` (i.e. without the git framing header).
//! This is consistent with how `gitlawb_core::cid::Cid::from_git_object_bytes`
//! computes CIDs when objects are pushed.
//!
//! Serving is access-controlled: an object is returned only from a repo row the
//! requesting caller is permitted to read (per-caller path-scoped visibility,
//! see `get_by_cid`).
use axum::{
extract::{Path, State},
http::{HeaderMap, HeaderName, HeaderValue, StatusCode},
response::{IntoResponse, Response},
Extension, Json,
Json,
};
use cid::CidGeneric;
use std::collections::{HashMap, HashSet};
use std::str::FromStr;
use crate::auth::AuthenticatedDid;
use crate::error::{AppError, Result};
use crate::git::store;
use crate::git::visibility_pack::{allowed_blob_set_for_caller, has_path_scoped_rule};
use crate::state::AppState;
use crate::visibility::{visibility_check, Decision};
/// GET /ipfs/{cid}
///
/// 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, #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). 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, including the dangling
/// case. A stale-public mirror row still serves withheld content (tracked
/// separately, #124).
/// the given CIDv1. Returns the raw object content bytes with appropriate
/// headers if found, or 404 if not found.
pub async fn get_by_cid(
Path(cid_str): Path<String>,
State(state): State<AppState>,
auth: Option<Extension<AuthenticatedDid>>,
) -> Result<Response> {
// 1. Decode the CID and extract the SHA-256 digest
let cid = CidGeneric::<64>::from_str(&cid_str)
@@ -73,136 +46,46 @@ pub async fn get_by_cid(
}
let sha256_hex = hex::encode(mh.digest());
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
let caller_owned = caller.map(|c| c.to_string());
// 2. Search all repos for an object with this SHA-256
let repos = state
.db
.list_all_repos()
.await
.map_err(AppError::Internal)?;
// Fetch every repo's visibility rules in one query rather than one per row
// (the gate runs each row against its OWN rules — KTD2a). A row absent from
// the map has no rules.
let repo_ids: Vec<String> = repos.iter().map(|r| r.id.clone()).collect();
let rules_by_repo = state
.db
.list_visibility_rules_for_repos(&repo_ids)
.await
.map_err(AppError::Internal)?;
// 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();
.list_all_repos().await
.map_err(|e| AppError::Internal(e.into()))?;
for repo in &repos {
// Repo-level read gate against THIS row's own rules (KTD2a).
let rules: &[crate::db::VisibilityRule] = rules_by_repo
.get(&repo.id)
.map(Vec::as_slice)
.unwrap_or(&[]);
if visibility_check(rules, repo.is_public, &repo.owner_did, caller, "/") == Decision::Deny {
continue;
}
let repo_path = match state.repo_store.acquire(&repo.owner_did, &repo.name).await {
Ok(p) => p,
Err(_) => continue,
};
// 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,
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,
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;
let owner = repo.owner_did.clone();
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 || {
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:
// we cannot prove the caller may read here, so skip this repo and
// let a public copy (if any) serve. Never serve on an unproven gate.
let set = match walk {
Ok(Ok(set)) => set,
Ok(Err(e)) => {
tracing::warn!(repo = %repo.name, err = %e, "allowed-blob walk failed; skipping repo");
continue;
}
Err(e) => {
tracing::warn!(repo = %repo.name, err = %e, "allowed-blob walk task panicked; skipping repo");
continue;
}
};
allowed_memo.insert(repo.id.clone(), set);
}
let in_allowed = allowed_memo
.get(&repo.id)
.is_some_and(|set| set.contains(&sha256_hex));
if !in_allowed {
tracing::warn!(repo = %repo.name, err = %e, "error reading git object");
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 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
@@ -216,12 +99,13 @@ pub async fn get_by_cid(
/// Returns all CIDs that have been pinned to the local IPFS node from git
/// objects received via push. Each entry includes the git SHA-256 hex, the
/// CIDv1 string, and the timestamp when it was pinned.
pub async fn list_pins(State(state): State<AppState>) -> Result<Json<serde_json::Value>> {
pub async fn list_pins(
State(state): State<AppState>,
) -> Result<Json<serde_json::Value>> {
let pins = state
.db
.list_pinned_cids()
.await
.map_err(AppError::Internal)?;
.list_pinned_cids().await
.map_err(|e| AppError::Internal(e.into()))?;
Ok(Json(serde_json::json!({
"pins": pins,
+26 -101
View File
@@ -10,8 +10,8 @@ use uuid::Uuid;
use crate::auth::AuthenticatedDid;
use crate::db::IssueComment;
use crate::error::{AppError, Result};
use crate::git::issues as git_issues;
use crate::state::AppState;
use crate::git::issues as git_issues;
#[derive(Debug, Deserialize)]
pub struct CreateIssueRequest {
@@ -39,11 +39,8 @@ pub async fn create_issue(
Path((owner, repo)): Path<(String, String)>,
Json(req): Json<CreateIssueRequest>,
) -> Result<(StatusCode, Json<IssueRecord>)> {
// Authorize the caller as a reader before accepting an issue: a non-reader
// must not be able to file an issue against a private repo they cannot read.
// Mirrors create_issue_comment / create_review / create_bounty.
let (record, _rules) =
crate::api::authorize_repo_read(&state, &owner, &repo, Some(auth.0.as_str()), "/").await?;
let record = state.db.get_repo(&owner, &repo).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
let issue_id = Uuid::new_v4().to_string();
let now = Utc::now().to_rfc3339();
@@ -61,17 +58,14 @@ pub async fn create_issue(
let json_str = serde_json::to_string(&issue)
.map_err(|e| AppError::BadRequest(format!("serialization error: {e}")))?;
let guard = state
.repo_store
.acquire_write(&record.owner_did, &record.name)
.await
let guard = state.repo_store.acquire_write(&record.owner_did, &record.name).await
.map_err(|e| AppError::Git(e.to_string()))?;
let disk_path = guard.path().to_path_buf();
let create_result = git_issues::create_issue(&disk_path, &issue_id, &json_str);
// Always release the advisory lock — even on error; upload to Tigris only on success.
guard.release(create_result.is_ok()).await;
// Always release the advisory lock — even on error
guard.release().await;
create_result.map_err(|e| AppError::Git(e.to_string()))?;
@@ -90,20 +84,15 @@ 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 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 record = state.db.get_repo(&owner, &repo).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
let disk_path = state
.repo_store
.acquire(&record.owner_did, &record.name)
.await
let disk_path = state.repo_store.acquire(&record.owner_did, &record.name).await
.map_err(|e| AppError::Git(e.to_string()))?;
let raw_issues =
git_issues::list_issues(&disk_path).map_err(|e| AppError::Git(e.to_string()))?;
let raw_issues = git_issues::list_issues(&disk_path)
.map_err(|e| AppError::Git(e.to_string()))?;
let mut issues: Vec<serde_json::Value> = Vec::new();
for raw in raw_issues {
@@ -119,16 +108,11 @@ 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 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 record = state.db.get_repo(&owner, &repo).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
let disk_path = state
.repo_store
.acquire(&record.owner_did, &record.name)
.await
let disk_path = state.repo_store.acquire(&record.owner_did, &record.name).await
.map_err(|e| AppError::Git(e.to_string()))?;
let raw = git_issues::get_issue(&disk_path, &issue_id)
@@ -154,19 +138,13 @@ pub async fn create_issue_comment(
Json(req): Json<CreateIssueCommentRequest>,
) -> Result<(StatusCode, Json<IssueComment>)> {
if req.body.trim().is_empty() {
return Err(AppError::BadRequest(
"comment body must not be empty".into(),
));
return Err(AppError::BadRequest("comment body must not be empty".into()));
}
// Read-gate: a commenter must be able to read the repo, but need not own it.
let (record, _rules) =
crate::api::authorize_repo_read(&state, &owner, &repo, Some(auth.0.as_str()), "/").await?;
let record = state.db.get_repo(&owner, &repo).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
let disk_path = state
.repo_store
.acquire(&record.owner_did, &record.name)
.await
let disk_path = state.repo_store.acquire(&record.owner_did, &record.name).await
.map_err(|e| AppError::Git(e.to_string()))?;
// Verify issue exists
crate::git::issues::get_issue(&disk_path, &issue_id)
@@ -189,84 +167,31 @@ 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 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 _record = state.db.get_repo(&owner, &repo).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
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?;
let comments = state.db.list_issue_comments(&issue_id).await?;
Ok(Json(serde_json::json!({ "comments": comments })))
}
/// POST /api/v1/repos/{owner}/{repo}/issues/{id}/close
pub async fn close_issue(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
Extension(_auth): Extension<AuthenticatedDid>,
Path((owner, repo, issue_id)): Path<(String, String, String)>,
) -> Result<Json<serde_json::Value>> {
let record = state
.db
.get_repo(&owner, &repo)
.await?
let record = state.db.get_repo(&owner, &repo).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
let guard = state
.repo_store
.acquire_write(&record.owner_did, &record.name)
.await
let guard = state.repo_store.acquire_write(&record.owner_did, &record.name).await
.map_err(|e| AppError::Git(e.to_string()))?;
let disk_path = guard.path().to_path_buf();
// Owner OR issue author may close. The author lives in the issue's git-JSON
// blob (not a DB column); a None author (legacy issues) falls back to
// owner-only. Read it under the write guard, before mutating.
let author_did: Option<String> = match git_issues::get_issue(&disk_path, &issue_id) {
Ok(Some(raw)) => serde_json::from_str::<IssueRecord>(&raw)
.ok()
.and_then(|i| i.author),
Ok(None) => {
guard.release(false).await;
return Err(AppError::NotFound(format!("issue {issue_id} not found")));
}
Err(e) => {
guard.release(false).await;
return Err(AppError::Git(e.to_string()));
}
};
let is_owner = crate::api::require_repo_owner(&record, &auth.0).is_ok();
let is_author = author_did
.as_deref()
.is_some_and(|a| crate::api::did_matches(&auth.0, a));
if !is_owner && !is_author {
guard.release(false).await;
return Err(AppError::Forbidden(
"only the repo owner or the issue author can close this issue".into(),
));
}
let close_result = git_issues::close_issue(&disk_path, &issue_id);
// Always release the advisory lock — even on error; upload to Tigris only on success.
guard.release(close_result.is_ok()).await;
// Always release the advisory lock — even on error
guard.release().await;
let updated = close_result
.map_err(|e| AppError::Git(e.to_string()))?
+9 -29
View File
@@ -17,7 +17,7 @@ pub struct LabelRequest {
/// POST /api/v1/repos/:owner/:repo/labels
pub async fn add_label(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
Extension(_auth): Extension<AuthenticatedDid>,
Path((owner, name)): Path<(String, String)>,
Json(req): Json<LabelRequest>,
) -> Result<(StatusCode, Json<serde_json::Value>)> {
@@ -25,46 +25,28 @@ pub async fn add_label(
if label.is_empty() || label.len() > 50 {
return Err(AppError::BadRequest("label must be 1–50 characters".into()));
}
if !label
.chars()
.all(|c| c.is_alphanumeric() || c == '-' || c == ':')
{
if !label.chars().all(|c| c.is_alphanumeric() || c == '-' || c == ':') {
return Err(AppError::BadRequest(
"label must contain only alphanumeric characters, hyphens, and colons".into(),
));
}
let record = state
.db
.get_repo(&owner, &name)
.await?
let record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
crate::api::require_repo_owner(&record, &auth.0)?;
let added = state.db.add_label(&record.id, &label).await?;
let status = if added {
StatusCode::CREATED
} else {
StatusCode::OK
};
Ok((
status,
Json(serde_json::json!({ "label": label, "added": added })),
))
let status = if added { StatusCode::CREATED } else { StatusCode::OK };
Ok((status, Json(serde_json::json!({ "label": label, "added": added }))))
}
/// DELETE /api/v1/repos/:owner/:repo/labels/:label
pub async fn remove_label(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
Extension(_auth): Extension<AuthenticatedDid>,
Path((owner, name, label)): Path<(String, String, String)>,
) -> Result<Json<serde_json::Value>> {
let record = state
.db
.get_repo(&owner, &name)
.await?
let record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
crate::api::require_repo_owner(&record, &auth.0)?;
state.db.remove_label(&record.id, &label).await?;
Ok(Json(serde_json::json!({ "label": label, "removed": true })))
@@ -74,11 +56,9 @@ pub async fn remove_label(
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 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 record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
let labels = state.db.list_labels(&record.id).await?;
Ok(Json(serde_json::json!({ "labels": labels })))
-655
View File
@@ -1,673 +1,18 @@
use crate::db::{RepoRecord, VisibilityRule};
use crate::error::{AppError, Result};
use crate::state::AppState;
use crate::visibility::{visibility_check, Decision};
pub mod agents;
pub mod arweave;
pub mod bounties;
pub mod certs;
pub mod changelog;
pub mod encrypted;
pub mod events;
pub mod ipfs;
pub mod issues;
pub mod labels;
pub mod peers;
pub mod profiles;
pub mod protect;
pub mod pulls;
pub mod register;
pub mod replicas;
pub mod repos;
pub mod resolve;
pub mod stars;
pub mod tasks;
pub mod visibility;
pub mod webhooks;
/// Resolve a repo for a read request and enforce path-scoped visibility.
///
/// Returns 404 (`RepoNotFound`) if the repo does not exist or the caller may not
/// read `path`, using the same opaque response the git serve path returns so
/// existence is not confirmed. Returns the record and its visibility rules so a
/// content handler can apply an extra per-path check without a second DB query.
///
/// Callers pass `"/"` for repo-level reads (listings); content endpoints pass the
/// specific path so a withheld subtree is denied even on an otherwise-public repo.
pub(crate) async fn authorize_repo_read(
state: &AppState,
owner: &str,
name: &str,
caller: Option<&str>,
path: &str,
) -> Result<(RepoRecord, Vec<VisibilityRule>)> {
let record = state
.db
.get_repo(owner, name)
.await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
// A quarantined mirror (admitted by the iCaptcha propagation gate but not
// validated) is hidden from every reader — serve/clone and fork alike — as if
// it did not exist, until an operator releases it. Checked before the
// visibility gate so its existence is never disclosed.
if state.db.is_repo_quarantined(&record.id).await? {
return Err(AppError::RepoNotFound(format!("{owner}/{name}")));
}
let rules = state.db.list_visibility_rules(&record.id).await?;
if visibility_check(&rules, record.is_public, &record.owner_did, caller, path) == Decision::Deny
{
return Err(AppError::RepoNotFound(format!("{owner}/{name}")));
}
Ok((record, rules))
}
/// Match a presented DID against a stored DID that may be the full `did:key:<id>`
/// form or the bare `<id>` short form (mirror rows store the bare key). Collapse
/// representation only within `did:key`; never let a bare id match across methods —
/// `did:web` / `did:gitlawb` share the base58 space with `did:key`, so a
/// trailing-segment compare would treat `did:key:X` and `did:gitlawb:X` as equal.
pub(crate) fn did_matches(a: &str, b: &str) -> bool {
if a == b {
return true;
}
fn key_id(d: &str) -> &str {
d.strip_prefix("did:key:").unwrap_or(d)
}
let (ka, kb) = (key_id(a), key_id(b));
// After stripping `did:key:`, a value still containing ':' is a non-key full
// DID — do not let it match a bare `did:key` id.
!ka.contains(':') && !kb.contains(':') && ka == kb
}
/// 403 unless `caller` is the repo owner. Uses [`did_matches`] so the owner check
/// and the author check (close policy) share one normalization.
pub(crate) fn require_repo_owner(record: &RepoRecord, caller: &str) -> Result<()> {
if did_matches(caller, &record.owner_did) {
Ok(())
} else {
Err(AppError::Forbidden(
"only the repo owner can perform this action".into(),
))
}
}
#[cfg(test)]
mod did_tests {
use super::did_matches;
#[test]
fn full_matches_bare_same_key() {
assert!(did_matches("did:key:zABC", "zABC"));
assert!(did_matches("zABC", "did:key:zABC"));
}
#[test]
fn rejects_cross_method_collision() {
assert!(!did_matches("did:key:zABC", "did:gitlawb:zABC"));
assert!(!did_matches("did:key:zABC", "did:web:zABC"));
}
#[test]
fn exact_match_and_distinct_keys() {
assert!(did_matches("did:key:zABC", "did:key:zABC"));
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
/// handler must contain its expected gate marker in its own body; removing a
/// gate fails this test. Source-level (no DB), so it runs everywhere. When a new
/// route is added to an in-scope group, add its row here with a deliberate gate
/// type — that forced decision is the point.
///
/// Markers are gate-SHAPED — a call (`require_repo_owner(`, `did_matches(`) or a
/// binding/comparison expression (`caller != &record.owner_did`,
/// `let owner_did = auth.0`) — never a bare identifier that could also appear in
/// a log line. Full-line comments are stripped before matching, so a marker that
/// survives only as a comment above a deleted gate does NOT satisfy a row.
#[cfg(test)]
mod authz_guard {
/// The body of `func` with full-line comments removed. Bounds the slice at the
/// next top-level fn item so a marker in a later handler can't leak in,
/// tolerating `pub async`, `pub(crate) async`, `async`, `pub`, and bare `fn`
/// declarations (the old single-`pub async fn` delimiter over-ran on any other
/// form).
fn fn_body(src: &str, func: &str) -> String {
let needle = format!("fn {func}(");
let start = src
.find(&needle)
.unwrap_or_else(|| panic!("handler `{func}` not found (renamed or removed?)"));
let rest = &src[start..];
let end = [
"\npub async fn ",
"\npub(crate) async fn ",
"\nasync fn ",
"\npub fn ",
"\nfn ",
]
.iter()
.filter_map(|p| rest[1..].find(p).map(|i| i + 1))
.min()
.unwrap_or(rest.len());
rest[..end]
.lines()
.filter(|l| !l.trim_start().starts_with("//"))
.collect::<Vec<_>>()
.join("\n")
}
#[test]
fn every_in_scope_mutation_has_its_gate() {
let pulls = include_str!("pulls.rs");
let webhooks = include_str!("webhooks.rs");
let labels = include_str!("labels.rs");
let issues = include_str!("issues.rs");
let bounties = include_str!("bounties.rs");
let replicas = include_str!("replicas.rs");
let tasks = include_str!("tasks.rs");
let stars = include_str!("stars.rs");
let protect = include_str!("protect.rs");
let visibility = include_str!("visibility.rs");
let profiles = include_str!("profiles.rs");
let repos = include_str!("repos.rs");
let register = include_str!("register.rs");
let ipfs = include_str!("ipfs.rs");
// (source, handler, expected gate marker)
let rows: &[(&str, &str, &str)] = &[
// Bucket A — owner-gate (require_repo_owner -> 403)
(pulls, "merge_pr", "require_repo_owner("),
(webhooks, "create_webhook", "require_repo_owner("),
(webhooks, "delete_webhook", "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)
(pulls, "close_pr", "did_matches("),
(issues, "close_issue", "did_matches("),
// Bucket B — read-gate (authorize_repo_read)
(pulls, "create_review", "authorize_repo_read("),
(pulls, "create_comment", "authorize_repo_read("),
(pulls, "create_pr", "authorize_repo_read("),
(issues, "create_issue_comment", "authorize_repo_read("),
(issues, "create_issue", "authorize_repo_read("),
(bounties, "create_bounty", "authorize_repo_read("),
(repos, "fork_repo", "authorize_repo_read("),
// 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("),
// Bucket C — signer-self: the acting DID is matched/bound to auth.0
(tasks, "create_task", "did_matches("),
(tasks, "claim_task", "did_matches("),
(tasks, "complete_task", "did_matches("),
(tasks, "fail_task", "did_matches("),
(repos, "create_repo", "let owner_did = auth.0"),
(profiles, "set_profile", "let did = auth.0"),
(register, "register", "did_matches("),
(stars, "star_repo", "caller = &auth.0"),
(stars, "unstar_repo", "caller = &auth.0"),
// Bucket D — non-owner-by-design, positive per-route marker
(bounties, "claim_bounty", "claim_bounty(&id, &auth.0"),
(bounties, "submit_bounty", "did_matches("),
(bounties, "approve_bounty", "did_matches("),
(bounties, "cancel_bounty", "did_matches("),
(bounties, "dispute_bounty", "did_matches("),
(replicas, "register_replica", "did_matches("),
(replicas, "unregister_replica", "replica_did = &auth.0"),
// PRE-GATED — already owner-gated, in-scope group; guard the gate itself
(protect, "protect_branch", "did_matches("),
(protect, "unprotect_branch", "did_matches("),
(visibility, "set_visibility", "require_owner("),
(visibility, "remove_visibility", "require_owner("),
(visibility, "list_visibility", "require_owner("),
];
// The visibility rows prove require_owner is CALLED; this proves the helper
// itself does DID-safe matching, not a raw/trailing-segment compare.
assert!(
fn_body(visibility, "require_owner").contains("did_matches("),
"visibility::require_owner must use did_matches for DID-safe owner matching"
);
for (src, func, marker) in rows {
let body = fn_body(src, func);
assert!(
body.contains(marker),
"handler `{func}` is missing its gate marker `{marker}` — gate removed or route reclassified"
);
}
}
/// Proves the comment-stripping that GUARD-1 added: a marker that appears only
/// in a full-line comment (the real `replicas.rs` false-pass shape) must NOT
/// satisfy a row.
#[test]
fn comment_only_marker_does_not_satisfy_a_row() {
let src = "pub async fn demo() {\n // did_matches( handles the owner form\n do_thing();\n}\n";
assert!(
!fn_body(src, "demo").contains("did_matches("),
"a marker present only in a comment must not count as an enforced gate"
);
}
/// All `pub async fn` / `pub(crate) async fn` handler names declared in `src`.
/// Verb-agnostic on purpose: a repo-scoped read of any name is in scope, so a
/// handler named `fetch_*` / `replicate_*` / `info_refs` cannot escape the gate
/// check by not being called `list_*` / `get_*`.
fn handler_names(src: &str) -> Vec<String> {
["pub async fn ", "pub(crate) async fn "]
.iter()
.flat_map(|decl| {
src.match_indices(decl).map(move |(i, _)| {
src[i + decl.len()..]
.chars()
.take_while(|c| c.is_alphanumeric() || *c == '_')
.collect::<String>()
})
})
.collect()
}
/// True when the handler's signature takes an owner+repo path
/// (`Path<(String, String...)>`), i.e. it is a repo-scoped read rather than a
/// node-wide aggregate (`/stats`, `/ipfs/pins`, the global feeds).
fn is_repo_scoped(body: &str) -> bool {
let header = &body[..body.find('{').unwrap_or(body.len())];
header.contains("Path<(String, String")
}
/// True when at least one gate marker runs for EVERY service — i.e. some
/// marker sits outside any `if service == ...` discriminator block. A gate
/// that appears ONLY inside such a block (as the info/refs advertisement gate
/// did before #119: `visibility_check` ran under `if service ==
/// "git-upload-pack"`, leaving `git-receive-pack` ungated) covers a subset of
/// services and must NOT count as a full gate. Other handlers carry no
/// `service ==` discriminator, so for them this matches the plain
/// substring check. NOTE: only `if service ==` is detected — a
/// `match service { .. }` discriminator is NOT tracked and a gate inside one
/// arm would pass as full; avoid that shape, or extend the span loop below.
fn gate_runs_unconditionally(body: &str, markers: &[&str]) -> bool {
// Brace-matched spans of each `if service == ...` block.
let mut cond_spans: Vec<(usize, usize)> = Vec::new();
let mut search = 0;
while let Some(rel) = body[search..].find("if service ==") {
let cond_start = search + rel;
let Some(brace_rel) = body[cond_start..].find('{') else {
break;
};
let open = cond_start + brace_rel;
let mut depth = 0i32;
let mut end = body.len();
for (i, c) in body[open..].char_indices() {
match c {
'{' => depth += 1,
'}' => {
depth -= 1;
if depth == 0 {
end = open + i;
break;
}
}
_ => {}
}
}
cond_spans.push((open, end));
// On an unclosed block `end` stays at body.len() (the fail-safe
// direction: treat the rest as conditional rather than mask a gate);
// clamp so the next slice can't index past the end and panic.
search = (end + 1).min(body.len());
}
markers.iter().any(|m| {
body.match_indices(m)
.any(|(pos, _)| !cond_spans.iter().any(|(s, e)| pos >= *s && pos <= *e))
})
}
/// 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`
/// / `did_matches` / a `&auth.0` self-binding) — or be listed in KNOWN_UNGATED
/// (the tracked, ungated reads). A new ungated handler of ANY verb trips this,
/// and a completeness scan over `src/api/` trips it for a whole new module that
/// adds a repo-scoped handler without being wired into `sources`. Mutations are
/// also checked precisely, per handler, by the mutation guard above; here they
/// only need *some* binding so the net stays verb-agnostic.
///
/// Scope and limits (this is a source scrape; the runtime route guard covers
/// behaviour):
/// - It proves a gate is CALLED, not that it runs on the requested path: a
/// content handler gating `"/"` instead of the subtree still passes here.
/// - It sees handlers taking the owner+repo tuple `Path<(String, String..)>`; a
/// repo identified by a struct/custom extractor would be missed (the helper
/// unit tests pin these boundaries).
/// - KNOWN_UNGATED entries need a real open issue and review; the staleness
/// assert removes one only once its gate lands.
#[test]
fn every_repo_scoped_handler_is_gated() {
let sources: &[(&str, &str)] = &[
(include_str!("bounties.rs"), "bounties.rs"),
(include_str!("certs.rs"), "certs.rs"),
(include_str!("changelog.rs"), "changelog.rs"),
(include_str!("encrypted.rs"), "encrypted.rs"),
(include_str!("events.rs"), "events.rs"),
(include_str!("issues.rs"), "issues.rs"),
(include_str!("labels.rs"), "labels.rs"),
(include_str!("protect.rs"), "protect.rs"),
(include_str!("pulls.rs"), "pulls.rs"),
(include_str!("replicas.rs"), "replicas.rs"),
(include_str!("repos.rs"), "repos.rs"),
(include_str!("stars.rs"), "stars.rs"),
(include_str!("visibility.rs"), "visibility.rs"),
(include_str!("webhooks.rs"), "webhooks.rs"),
];
let listed: std::collections::HashSet<&str> = sources.iter().map(|(_, f)| *f).collect();
assert!(!listed.is_empty(), "read-guard `sources` is empty");
// Completeness: every api/*.rs NOT already in `sources` must declare no
// repo-scoped handler, so a brand-new module cannot add an ungated handler
// the scrape never looks at. Reads the directory at test time (so the list
// cannot silently drift from the filesystem) and only inspects unlisted
// files — listed files are covered by the per-handler loop below.
let api_dir = concat!(env!("CARGO_MANIFEST_DIR"), "/src/api");
for (_, f) in sources {
assert!(
std::path::Path::new(api_dir).join(f).exists(),
"read-guard `sources` lists {f} but the file does not exist"
);
}
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/{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)] = &[
("list_webhooks", "#94 (PR #113)"),
("list_replicas", "PR #113"),
("list_protected_branches", "PR #113"),
];
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.
// A repo-scoped mutation passes here on its write gate; the mutation guard
// above additionally verifies the exact gate type per handler. NOTE: a local
// rename of `caller`/`replica_did` must be paired with a marker update here.
let markers = [
"authorize_repo_read(",
"visibility_check(",
"require_repo_owner(",
"require_owner(",
"did_matches(",
"caller = &auth.0",
"replica_did = &auth.0",
];
// Every KNOWN_UNGATED name must be a real handler (catch typos / renames).
let all: std::collections::HashSet<String> =
sources.iter().flat_map(|(s, _)| handler_names(s)).collect();
for (n, _) in known_ungated {
assert!(
all.contains(*n),
"KNOWN_UNGATED lists `{n}`, which is not a real handler (renamed or removed?)"
);
}
let mut checked = 0usize;
for (src, file) in sources {
for name in handler_names(src) {
let body = fn_body(src, &name);
if !is_repo_scoped(&body) {
continue; // node-wide aggregate, not a repo-scoped surface
}
checked += 1;
let gated = gate_runs_unconditionally(&body, &markers);
assert!(
gated || is_known(&name),
"repo-scoped handler `{name}` ({file}) has no authz gate and is \
not in KNOWN_UNGATED — add the visibility/owner gate with the \
caller, or track it there"
);
assert!(
!(gated && is_known(&name)),
"handler `{name}` ({file}) is now gated — remove it from \
KNOWN_UNGATED so the allowlist stays an accurate gap list"
);
}
}
// Tripwire: if the scrape silently stopped finding handlers (e.g. a parser
// regression in handler_names/is_repo_scoped), this floor fails loudly
// instead of the guard passing vacuously. Current count is ~54 repo-scoped
// handlers; 20 is a deliberate floor that trips only on a gross regression.
assert!(
checked >= 20,
"egress guard only checked {checked} repo-scoped handlers — the scrape likely broke"
);
}
/// Pins the `handler_names` boundary: it collects every `pub`/`pub(crate)
/// async fn` regardless of verb (so a `fetch_*` read cannot escape), and skips
/// private `async fn` and sync `fn` helpers.
#[test]
fn handler_names_finds_all_pub_async_and_skips_others() {
let src = "pub async fn list_things() {}\n\
pub async fn fetch_thing() {}\n\
pub(crate) async fn get_crate_thing() {}\n\
async fn private_helper() {}\n\
fn sync_helper() {}\n";
let names = handler_names(src);
// Verb-agnostic: a non-list/get read verb is still seen.
assert!(names.contains(&"list_things".to_string()));
assert!(names.contains(&"fetch_thing".to_string()));
// pub(crate) routed handlers are in scope too.
assert!(names.contains(&"get_crate_thing".to_string()));
// Private/sync helpers are not routed handlers and are skipped.
assert!(!names
.iter()
.any(|n| n == "private_helper" || n == "sync_helper"));
}
/// Pins the `is_repo_scoped` boundary: an owner+repo tuple Path is repo-scoped;
/// a single-segment or absent Path is a node-wide aggregate.
#[test]
fn is_repo_scoped_requires_owner_repo_path() {
let repo =
"fn get_x(s: State, Path((owner, name)): Path<(String, String)>) {\n body();\n}";
let three = "fn get_y(Path((o, n, id)): Path<(String, String, String)>) {\n body();\n}";
let node_wide = "fn list_z(s: State<AppState>) {\n body();\n}";
let single = "fn get_w(Path(cid): Path<String>) {\n body();\n}";
assert!(is_repo_scoped(repo), "owner+repo tuple is repo-scoped");
assert!(is_repo_scoped(three), "owner+repo+id tuple is repo-scoped");
assert!(!is_repo_scoped(node_wide), "no Path is node-wide");
assert!(
!is_repo_scoped(single),
"single-segment Path is not repo-scoped"
);
}
/// Pins `gate_runs_unconditionally`: a gate nested only inside an
/// `if service == ...` block is conditional (does NOT count), while the same
/// gate at the top level — or an additional unconditional one — does.
#[test]
fn conditional_service_gate_is_not_a_full_gate() {
let markers = ["visibility_check("];
// Gate runs only for one service: not a full gate.
let conditional = "fn f() {\n \
if service == \"git-upload-pack\" {\n \
visibility_check(rules, caller);\n \
}\n \
if service == \"git-receive-pack\" { acquire_fresh(); }\n}";
assert!(
!gate_runs_unconditionally(conditional, &markers),
"a gate only inside `if service ==` covers a subset of services"
);
// Same gate at top level: full gate.
let unconditional = "fn f() {\n \
visibility_check(rules, caller);\n \
if service == \"git-receive-pack\" { acquire_fresh(); }\n}";
assert!(
gate_runs_unconditionally(unconditional, &markers),
"an unconditional gate runs for every service"
);
// A gate inside EACH of two service blocks, none outside: still a
// subset (no service clears it unconditionally), so not a full gate.
let both_conditional = "fn f() {\n \
if service == \"git-upload-pack\" { visibility_check(a); }\n \
if service == \"git-receive-pack\" { visibility_check(b); }\n}";
assert!(
!gate_runs_unconditionally(both_conditional, &markers),
"a gate inside every service block is still conditional"
);
// A marker inside one block AND again unconditionally: the
// unconditional occurrence makes it a full gate (exercises the
// match_indices scan past the in-block hit).
let inside_and_outside = "fn f() {\n \
if service == \"git-upload-pack\" { visibility_check(a); }\n \
visibility_check(b);\n}";
assert!(
gate_runs_unconditionally(inside_and_outside, &markers),
"an unconditional occurrence counts even when another is conditional"
);
// No marker at all: not gated.
assert!(!gate_runs_unconditionally(
"fn f() { do_thing(); }",
&markers
));
// An unclosed `if service ==` block (e.g. phantom brace from a string
// literal) must not panic on the slice advance; the span runs to EOF, so
// the in-block marker reads as conditional. Real Rust source is balanced,
// so this only guards the scraper against a future pathological body.
let unclosed = "fn f() { if service == \"x\" { visibility_check(a);";
assert!(
!gate_runs_unconditionally(unclosed, &markers),
"an unclosed service block must not panic and stays conditional"
);
}
}
+44 -820
View File
@@ -10,13 +10,11 @@
//! POST /api/v1/sync/notify — receive push notification from a peer node
//! POST /api/v1/sync/trigger — manually pull all repos from known peers
use axum::extract::{Extension, Path, State};
use axum::extract::{Path, State};
use axum::http::StatusCode;
use axum::Json;
use gitlawb_core::did::Did;
use serde::{Deserialize, Serialize};
use crate::auth::AuthenticatedDid;
use crate::error::{AppError, Result};
use crate::state::AppState;
@@ -40,123 +38,6 @@ pub struct PeerResponse {
pub reachable: bool,
}
/// Extract an IPv4 address embedded in an IPv6 literal across the transition
/// formats that carry one: IPv4-mapped (`::ffff:a.b.c.d`), IPv4-compatible
/// (`::a.b.c.d`), 6to4 (`2002:WWXX:YYZZ::/16`), and the NAT64 well-known prefix
/// (`64:ff9b::/96`). Returns `None` for native IPv6. Callers fold the result
/// back through the v4 range checks so loopback/private addresses smuggled in
/// via any of these encodings are rejected, not just the mapped/compatible pair.
///
/// INCOMPLETE-NAT64 CONTRACT: non-well-known NAT64 prefixes (e.g. the RFC 8215
/// local-use `64:ff9b:1::/48`) are deliberately **not** decoded here — their v4
/// sits at a prefix-length-dependent offset (RFC 6052 §2.2) — so they return
/// `None`. Any caller that needs them blocked must reject the wider
/// `64:ff9b::/32` itself; `is_public_http_url` does this in its native-v6 arm.
fn embedded_ipv4(v6: std::net::Ipv6Addr) -> Option<std::net::Ipv4Addr> {
if let Some(v4) = v6.to_ipv4_mapped().or_else(|| v6.to_ipv4()) {
return Some(v4);
}
let s = v6.segments();
// 6to4 (2002::/16) embeds W.X.Y.Z in the next two segments.
if s[0] == 0x2002 {
let [a, b] = s[1].to_be_bytes();
let [c, d] = s[2].to_be_bytes();
return Some(std::net::Ipv4Addr::new(a, b, c, d));
}
// NAT64 well-known prefix (64:ff9b::/96) embeds the IPv4 in the low 32 bits.
if s[0] == 0x0064 && s[1] == 0xff9b && s[2..6] == [0, 0, 0, 0] {
let [a, b] = s[6].to_be_bytes();
let [c, d] = s[7].to_be_bytes();
return Some(std::net::Ipv4Addr::new(a, b, c, d));
}
None
}
/// Whether a peer `http_url` is a public http(s) endpoint safe to register.
/// Rejects non-http(s) schemes, loopback/unspecified/private/link-local IPs,
/// and `localhost` / `.local` / `.internal` hostnames. Used at announce time
/// and by the boot-time prune of already-poisoned rows.
pub fn is_public_http_url(raw: &str) -> bool {
let url = match reqwest::Url::parse(raw) {
Ok(u) => u,
Err(_) => return false,
};
if !matches!(url.scheme(), "http" | "https") {
return false;
}
let mut host = match url.host_str() {
Some(h) => h.to_ascii_lowercase(),
None => return false,
};
// Drop a single trailing dot (FQDN root): `localhost.` resolves the same as
// `localhost`, so normalize before the suffix/equality checks below.
if let Some(stripped) = host.strip_suffix('.') {
host = stripped.to_string();
}
if host.is_empty()
|| host == "localhost"
|| host.ends_with(".local")
|| host.ends_with(".internal")
{
return false;
}
// host_str() keeps brackets on IPv6 literals (e.g. "[::1]"); strip them
// before parsing as an IP.
let ip_candidate = host.trim_start_matches('[').trim_end_matches(']');
if let Ok(ip) = ip_candidate.parse::<std::net::IpAddr>() {
// Reject loopback/unspecified on the literal as given — catches `::1`
// and `::` before the IPv4-folding below (`::1`.to_ipv4() would
// otherwise map to a non-loopback `0.0.0.1`).
if ip.is_loopback() || ip.is_unspecified() {
return false;
}
// Fold any IPv6 literal that embeds an IPv4 address (mapped, compatible,
// 6to4, NAT64) down to that IPv4 so the v4 range checks catch
// loopback/private addresses smuggled in via an IPv6 encoding, then
// re-check loopback/unspecified.
let ip = match ip {
std::net::IpAddr::V6(v6) => embedded_ipv4(v6).map(std::net::IpAddr::V4).unwrap_or(ip),
v4 => v4,
};
if ip.is_loopback() || ip.is_unspecified() {
return false;
}
match ip {
std::net::IpAddr::V4(v4) => {
let o = v4.octets();
// RFC1918 private, link-local, CGNAT (100.64.0.0/10), or the
// RFC1122 "this host" block 0.0.0.0/8 (never a valid destination;
// 0.0.0.0 itself is already caught by the is_unspecified check).
if v4.is_private()
|| v4.is_link_local()
|| (o[0] == 100 && (o[1] & 0xc0) == 64)
|| o[0] == 0
{
return false;
}
}
std::net::IpAddr::V6(v6) => {
let s = v6.segments();
// fc00::/7 (unique-local) or fe80::/10 (link-local)
if (s[0] & 0xfe00) == 0xfc00 || (s[0] & 0xffc0) == 0xfe80 {
return false;
}
// Any NAT64 address (64:ff9b::/32) that is not the cleanly
// decodable well-known /96 — e.g. the RFC 8215 local-use
// 64:ff9b:1::/48 — carries a translated target whose embedded v4
// sits at a prefix-length-dependent offset (RFC 6052 §2.2).
// Rather than risk a wrong decode across every prefix length we
// reject the whole NAT64 space here. The well-known /96 was
// already folded to its v4 above and never reaches this arm.
if s[0] == 0x0064 && s[1] == 0xff9b {
return false;
}
}
}
}
true
}
/// GET /api/v1/peers
pub async fn list_peers(State(state): State<AppState>) -> Result<Json<serde_json::Value>> {
let peers = state.db.list_peers().await?;
@@ -169,9 +50,7 @@ pub async fn list_peers(State(state): State<AppState>) -> Result<Json<serde_json
reachable: p.last_ping_ok,
})
.collect();
Ok(Json(
serde_json::json!({ "peers": resp, "count": resp.len() }),
))
Ok(Json(serde_json::json!({ "peers": resp, "count": resp.len() })))
}
/// POST /api/v1/peers/announce (auth required)
@@ -180,52 +59,11 @@ pub async fn list_peers(State(state): State<AppState>) -> Result<Json<serde_json
/// The Authorization header's DID must match the `did` in the body.
pub async fn announce(
State(state): State<AppState>,
auth: Option<Extension<AuthenticatedDid>>,
Json(req): Json<AnnounceRequest>,
) -> Result<(StatusCode, Json<serde_json::Value>)> {
let announced_did: Did = req
.did
.parse()
.map_err(|e: gitlawb_core::Error| AppError::BadRequest(e.to_string()))?;
if let Some(Extension(auth)) = auth {
if auth.0 != announced_did.to_string() {
return Err(AppError::BadRequest(
"Signature keyid must match announced DID".into(),
));
}
} else {
tracing::warn!(
did = %announced_did,
"accepted unsigned peer announce; set GITLAWB_REQUIRE_SIGNED_PEER_WRITES=true after all peers upgrade"
);
}
// Validate the URL is a public http(s) endpoint. The announce route is
// reachable unauthenticated (until all peers sign), so without this an
// attacker can register loopback/private "peers" (localhost:5432, etc.)
// and turn our outbound sync-notify fan-out into an SSRF probe — and bury
// the real peers under junk so node-origin repos stop replicating.
if !is_public_http_url(&req.http_url) {
return Err(AppError::BadRequest(
"http_url must be a public http(s) URL (no loopback, private, or .internal/.local hosts)".into(),
));
}
// Reject self-announcements: a peer row whose http_url is our own public
// URL makes the HTTP-notify path fan out to ourselves. Seen in prod when
// misconfigured dev nodes announce with their upstream's URL.
// prune_self_peers clears stale rows at boot; this stops new ones.
if let Some(self_url) = state.config.public_url.as_deref() {
if req.http_url.trim_end_matches('/') == self_url.trim_end_matches('/') {
return Err(AppError::BadRequest(
"http_url is this node's own public URL; refusing to register self as peer".into(),
));
}
}
if announced_did.to_string() == state.node_did.to_string() {
return Err(AppError::BadRequest(
"did is this node's own DID; refusing to register self as peer".into(),
));
// Validate the URL is HTTP/HTTPS
if !req.http_url.starts_with("http://") && !req.http_url.starts_with("https://") {
return Err(AppError::BadRequest("http_url must start with http:// or https://".into()));
}
state.db.upsert_peer(&req.did, &req.http_url).await?;
@@ -233,16 +71,13 @@ pub async fn announce(
tracing::info!(did = %req.did, url = %req.http_url, "peer announced");
// Return our own info so the peer can add us back
Ok((
StatusCode::OK,
Json(serde_json::json!({
"status": "accepted",
"node_did": state.node_did.to_string(),
"node_url": state.config.public_url.as_deref().unwrap_or(""),
"peer_count": state.db.list_peers().await.map(|p| p.len()).unwrap_or(0),
"message": "added to peer list",
})),
))
Ok((StatusCode::OK, Json(serde_json::json!({
"status": "accepted",
"node_did": state.node_did.to_string(),
"node_url": state.config.public_url.as_deref().unwrap_or(""),
"peer_count": state.db.list_peers().await.map(|p| p.len()).unwrap_or(0),
"message": "added to peer list",
}))))
}
/// POST /api/v1/sync/trigger
@@ -251,7 +86,9 @@ pub async fn announce(
/// peer's repo list over HTTP and enqueues any repos we don't have or are
/// behind on into the sync_queue. This is the HTTP fallback when Gossipsub
/// p2p is not yet connected.
pub async fn trigger_sync(State(state): State<AppState>) -> Result<Json<serde_json::Value>> {
pub async fn trigger_sync(
State(state): State<AppState>,
) -> Result<Json<serde_json::Value>> {
let peers = state.db.list_peers().await?;
let client = &state.http_client;
let mut enqueued = 0u32;
@@ -262,56 +99,39 @@ pub async fn trigger_sync(State(state): State<AppState>) -> Result<Json<serde_js
continue;
}
let url = format!("{}/api/v1/repos", peer.http_url.trim_end_matches('/'));
// 30s with the body read inside the timeout: 5s only covered the
// response headers, so canonical nodes serving large unpaginated repo
// lists (and transpacific round trips) aborted mid-body.
let result = tokio::time::timeout(std::time::Duration::from_secs(30), async {
let resp = client.get(&url).send().await?;
if !resp.status().is_success() {
return Err(anyhow::anyhow!("peer returned status {}", resp.status()));
}
let repos: Vec<serde_json::Value> = resp.json().await?;
Ok::<_, anyhow::Error>(repos)
})
.await;
let result = tokio::time::timeout(
std::time::Duration::from_secs(5),
client.get(&url).send(),
).await;
let repos = match result {
Ok(Ok(repos)) => {
let repos: Vec<serde_json::Value> = match result {
Ok(Ok(resp)) if resp.status().is_success() => {
peers_reached += 1;
repos
resp.json().await.unwrap_or_default()
}
Ok(Err(e)) => {
tracing::warn!(peer = %peer.did, err = %e, "trigger_sync: peer fetch failed");
continue;
}
Err(_) => {
tracing::warn!(peer = %peer.did, "trigger_sync: peer timed out");
_ => {
tracing::warn!(peer = %peer.did, "trigger_sync: could not reach peer");
continue;
}
};
for repo in repos {
let repo_slug = match (
repo.get("owner_did").and_then(|v| v.as_str()),
repo.get("name").and_then(|v| v.as_str()),
) {
let repo_slug = match (repo.get("owner_did").and_then(|v| v.as_str()),
repo.get("name").and_then(|v| v.as_str())) {
(Some(owner), Some(name)) => {
// Use short owner (did:key-only normalization) matching DB convention
let short = crate::db::normalize_owner_key(owner);
// Use short owner (last colon segment) matching DB convention
let short = owner.split(':').last().unwrap_or(owner);
format!("{short}/{name}")
}
_ => continue,
};
let _ = state
.db
.enqueue_sync(
&repo_slug,
&peer.did,
"refs/heads/main",
"0000000000000000000000000000000000000000",
None,
)
.await;
let _ = state.db.enqueue_sync(
&repo_slug,
&peer.did,
"refs/heads/main",
"0000000000000000000000000000000000000000",
None,
).await;
enqueued += 1;
}
}
@@ -335,38 +155,12 @@ pub struct NotifyRequest {
pub ref_name: String,
pub new_sha: String,
pub node_did: String,
// Optional fields — older senders only included the four above. New
// senders include these so received_ref_updates has full provenance
// even when the libp2p mesh isn't delivering and the HTTP fallback
// is the only path that fired.
#[serde(default)]
pub pusher_did: Option<String>,
#[serde(default)]
pub old_sha: Option<String>,
#[serde(default)]
pub timestamp: Option<String>,
#[serde(default)]
pub cert_id: Option<String>,
}
pub async fn notify_sync(
State(state): State<AppState>,
auth: Option<Extension<AuthenticatedDid>>,
Json(req): Json<NotifyRequest>,
) -> Result<Json<serde_json::Value>> {
if let Some(Extension(auth)) = auth {
if auth.0 != req.node_did {
return Err(AppError::BadRequest(
"Signature keyid must match notification node_did".into(),
));
}
} else {
tracing::warn!(
did = %req.node_did,
"accepted unsigned sync notify; set GITLAWB_REQUIRE_SIGNED_PEER_WRITES=true after all peers upgrade"
);
}
// Only accept notifications from known peers
let peers = state.db.list_peers().await?;
let known = peers.iter().any(|p| p.did == req.node_did);
@@ -377,31 +171,13 @@ pub async fn notify_sync(
)));
}
state
.db
.enqueue_sync(&req.repo, &req.node_did, &req.ref_name, &req.new_sha, None)
.await?;
// Mirror the gossipsub-receive handler: insert the same record we'd
// get from the libp2p path, so /api/v1/events/ref-updates reflects
// pushes that arrive over either transport.
let now = chrono::Utc::now().to_rfc3339();
let update = crate::db::ReceivedRefUpdate {
id: uuid::Uuid::new_v4().to_string(),
node_did: req.node_did.clone(),
pusher_did: req.pusher_did.clone().unwrap_or_default(),
repo: req.repo.clone(),
ref_name: req.ref_name.clone(),
old_sha: req.old_sha.clone().unwrap_or_default(),
new_sha: req.new_sha.clone(),
timestamp: req.timestamp.clone().unwrap_or_else(|| now.clone()),
cert_id: req.cert_id.clone(),
received_at: now,
from_peer: format!("http:{}", req.node_did),
};
if let Err(e) = state.db.insert_ref_update(&update).await {
tracing::warn!(err = %e, repo = %req.repo, "failed to insert ref-update from sync notify");
}
state.db.enqueue_sync(
&req.repo,
&req.node_did,
&req.ref_name,
&req.new_sha,
None,
).await?;
tracing::info!(
repo = %req.repo,
@@ -425,23 +201,12 @@ pub async fn ping_peer(
Path(did): Path<String>,
) -> Result<Json<serde_json::Value>> {
let peers = state.db.list_peers().await?;
let peer = peers
.into_iter()
.find(|p| p.did == did)
let peer = peers.into_iter().find(|p| p.did == did)
.ok_or_else(|| AppError::RepoNotFound(format!("peer {did} not found")))?;
// Async ping
let url = format!("{}/health", peer.http_url.trim_end_matches('/'));
// Use the shared no-redirect client: bare `reqwest::get` follows redirects,
// so a peer could answer with `302 -> http://127.0.0.1/` and turn the ping
// into an SSRF probe.
let ok = state
.http_client
.get(&url)
.send()
.await
.map(|r| r.status().is_success())
.unwrap_or(false);
let ok = reqwest::get(&url).await.map(|r| r.status().is_success()).unwrap_or(false);
let _ = state.db.mark_peer_ping(&did, ok).await;
@@ -451,544 +216,3 @@ pub async fn ping_peer(
"reachable": ok,
})))
}
#[cfg(test)]
mod tests {
use super::is_public_http_url;
#[test]
fn accepts_public_https_and_http() {
assert!(is_public_http_url("https://node.gitlawb.com"));
assert!(is_public_http_url("https://manila.gitlawb.com/"));
assert!(is_public_http_url("http://203.0.113.10:7545"));
}
#[test]
fn rejects_loopback_private_and_internal() {
for bad in [
"http://localhost:7545",
"http://127.0.0.1:5432/",
"http://localhost:22/",
"http://0.0.0.0:7545",
// RFC1122 "this host" block 0.0.0.0/8 beyond 0.0.0.0 itself,
// including the upper boundary (1.0.0.0 is public, tested below).
"http://0.0.0.1:7545",
"http://0.1.2.3/",
"http://0.255.255.255/",
"http://10.0.0.5:7545",
"http://192.168.1.10/",
"http://172.16.0.1:7545",
"http://169.254.1.1/",
"http://[::1]:7545",
"http://gitlawb-node.internal:7545",
"http://my-node.local/",
"ftp://node.gitlawb.com",
"not-a-url",
"",
// Trailing-dot FQDN of an internal host.
"http://localhost./",
// CGNAT (100.64.0.0/10).
"http://100.64.0.1:7545",
"http://100.127.255.255/",
// IPv4-mapped / IPv4-compatible IPv6 smuggling private/loopback v4.
"http://[::ffff:127.0.0.1]:7545",
"http://[::ffff:10.0.0.1]/",
"http://[::ffff:192.168.1.1]:7545",
"http://[::127.0.0.1]/",
// 6to4 (2002::/16) embedding loopback/private v4.
"http://[2002:7f00:1::]:7545",
"http://[2002:a00:1::]/",
"http://[2002:c0a8:101::]/",
// NAT64 well-known prefix (64:ff9b::/96) embedding loopback/private v4.
"http://[64:ff9b::7f00:1]/",
"http://[64:ff9b::a00:1]:7545",
// NAT64 local-use prefix (64:ff9b:1::/48, RFC 8215) — rejected
// outright rather than decoded, so the whole NAT64 space is closed.
"http://[64:ff9b:1::7f00:1]/",
"http://[64:ff9b:1::a00:1]:7545",
"http://[64:ff9b:1:a00::]/",
// Local-use NAT64 wrapping a *public* v4 (203.0.113.10) is still
// rejected: the block is prefix-based, not payload-based.
"http://[64:ff9b:1::cb00:710a]/",
] {
assert!(!is_public_http_url(bad), "{bad:?} must be rejected");
}
}
#[test]
fn accepts_6to4_and_nat64_wrapping_public_v4() {
// Fold-and-recheck stays consistent with the mapped/compatible handling:
// a transition address that wraps a public v4 is allowed, only the
// private/loopback-wrapping forms above are rejected. 203.0.113.10.
assert!(is_public_http_url("http://[2002:cb00:710a::]/"));
assert!(is_public_http_url("http://[64:ff9b::cb00:710a]/"));
}
#[test]
fn accepts_public_outside_cgnat_range() {
// 100.0.0.0/10 boundary: .63 and .128 are public, only 100.64-127 is CGNAT.
assert!(is_public_http_url("http://100.63.255.255:7545"));
assert!(is_public_http_url("http://100.128.0.1/"));
}
#[test]
fn accepts_first_address_above_this_host_block() {
// 1.0.0.0 is the first address above the rejected 0.0.0.0/8 block;
// 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);
}
const NOTIFY_BODY: &str = r#"{"repo":"demo","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)"
);
}
#[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:?}"
);
}
}
-171
View File
@@ -1,171 +0,0 @@
//! Agent profile API handlers.
//!
//! - `PUT /api/v1/profile` — upsert the caller's profile (requires HTTP Signature)
//! - `GET /api/v1/agents/{did}/profile` — read any agent's profile (public)
use axum::{
extract::{Path, State},
http::StatusCode,
Json,
};
use serde::{Deserialize, Serialize};
use serde_json::{json, Value};
use crate::auth::AuthenticatedDid;
use crate::pinata;
use crate::state::AppState;
#[derive(Debug, Deserialize)]
pub struct SetProfileRequest {
pub display_name: Option<String>,
pub bio: Option<String>,
pub avatar_url: Option<String>,
pub website: Option<String>,
pub socials: Option<SocialsInput>,
pub pin_to_ipfs: Option<bool>,
}
#[derive(Debug, Deserialize, Serialize)]
pub struct SocialsInput {
pub twitter: Option<String>,
pub github: Option<String>,
pub farcaster: Option<String>,
pub telegram: Option<String>,
}
pub async fn set_profile(
State(state): State<AppState>,
axum::Extension(auth): axum::Extension<AuthenticatedDid>,
Json(req): Json<SetProfileRequest>,
) -> Result<(StatusCode, Json<Value>), (StatusCode, Json<Value>)> {
let did = auth.0;
if let Some(ref bio) = req.bio {
if bio.len() > 280 {
return Err((
StatusCode::BAD_REQUEST,
Json(json!({ "message": "bio must be 280 characters or fewer" })),
));
}
}
if let Some(ref name) = req.display_name {
if name.len() > 50 {
return Err((
StatusCode::BAD_REQUEST,
Json(json!({ "message": "display_name must be 50 characters or fewer" })),
));
}
}
let socials_json = req
.socials
.as_ref()
.map(|s| serde_json::to_string(s).unwrap_or_else(|_| "{}".to_string()));
let result = state
.db
.upsert_profile(
&did,
req.display_name.as_deref(),
req.bio.as_deref(),
req.avatar_url.as_deref(),
req.website.as_deref(),
socials_json.as_deref(),
)
.await;
match result {
Ok(profile) => {
let mut resp = json!({
"did": profile.did,
"display_name": profile.display_name,
"bio": profile.bio,
"avatar_url": profile.avatar_url,
"website": profile.website,
"updated_at": profile.updated_at,
});
if let Some(ref socials_str) = profile.socials {
if let Ok(socials) = serde_json::from_str::<Value>(socials_str) {
resp["socials"] = socials;
}
}
if req.pin_to_ipfs.unwrap_or(false) && !state.config.pinata_jwt.is_empty() {
let profile_json = serde_json::to_vec(&resp).unwrap_or_default();
match pinata::pin_object(
&state.http_client,
&state.config.pinata_upload_url,
&state.config.pinata_jwt,
&format!("profile-{}", did),
&profile_json,
)
.await
{
Ok(cid) if !cid.is_empty() => {
if let Err(e) = state.db.set_profile_cid(&did, &cid).await {
tracing::warn!(did = %did, err = %e, "failed to store profile CID");
}
resp["profile_cid"] = json!(cid);
}
Ok(_) => {}
Err(e) => {
tracing::warn!(did = %did, err = %e, "IPFS pin failed — profile saved without CID");
}
}
} else if let Some(cid) = profile.profile_cid {
resp["profile_cid"] = json!(cid);
}
Ok((StatusCode::OK, Json(resp)))
}
Err(e) => {
tracing::error!(did = %did, error = %e, "failed to upsert profile");
Err((
StatusCode::INTERNAL_SERVER_ERROR,
Json(json!({ "message": "failed to save profile" })),
))
}
}
}
pub async fn get_profile(
State(state): State<AppState>,
Path(did): Path<String>,
) -> Result<Json<Value>, (StatusCode, Json<Value>)> {
let profile = state.db.get_profile(&did).await.map_err(|e| {
tracing::error!(did = %did, error = %e, "failed to fetch profile");
(
StatusCode::INTERNAL_SERVER_ERROR,
Json(json!({ "message": "failed to fetch profile" })),
)
})?;
match profile {
Some(p) => {
let mut resp = json!({
"did": p.did,
"display_name": p.display_name,
"bio": p.bio,
"avatar_url": p.avatar_url,
"website": p.website,
"profile_cid": p.profile_cid,
"created_at": p.created_at,
"updated_at": p.updated_at,
});
if let Some(ref socials_str) = p.socials {
if let Ok(socials) = serde_json::from_str::<Value>(socials_str) {
resp["socials"] = socials;
}
}
Ok(Json(resp))
}
None => Err((
StatusCode::NOT_FOUND,
Json(json!({ "message": "profile not found" })),
)),
}
}
+15 -25
View File
@@ -17,16 +17,14 @@ pub async fn protect_branch(
Extension(auth): Extension<AuthenticatedDid>,
Path((owner, repo, branch)): Path<(String, String, String)>,
) -> Result<(StatusCode, Json<serde_json::Value>)> {
let record = state
.db
.get_repo(&owner, &repo)
.await?
let record = state.db.get_repo(&owner, &repo).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
// Only the repo owner can protect branches (DID-safe match, shared idiom).
// Only the repo owner can protect branches
let caller = &auth.0;
if !crate::api::did_matches(caller, &record.owner_did) {
return Err(AppError::Forbidden(
let owner_short = record.owner_did.split(':').next_back().unwrap_or(&record.owner_did);
if caller != &record.owner_did && caller != owner_short {
return Err(AppError::BadRequest(
"only the repo owner can protect branches".into(),
));
}
@@ -35,14 +33,11 @@ pub async fn protect_branch(
tracing::info!(repo = %repo, branch = %branch, caller = %caller, "branch protected");
Ok((
StatusCode::CREATED,
Json(serde_json::json!({
"status": "protected",
"repo": format!("{owner}/{repo}"),
"branch": branch,
})),
))
Ok((StatusCode::CREATED, Json(serde_json::json!({
"status": "protected",
"repo": format!("{owner}/{repo}"),
"branch": branch,
}))))
}
/// DELETE /api/v1/repos/:owner/:repo/branches/:branch/protect
@@ -51,15 +46,13 @@ pub async fn unprotect_branch(
Extension(auth): Extension<AuthenticatedDid>,
Path((owner, repo, branch)): Path<(String, String, String)>,
) -> Result<Json<serde_json::Value>> {
let record = state
.db
.get_repo(&owner, &repo)
.await?
let record = state.db.get_repo(&owner, &repo).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
let caller = &auth.0;
if !crate::api::did_matches(caller, &record.owner_did) {
return Err(AppError::Forbidden(
let owner_short = record.owner_did.split(':').next_back().unwrap_or(&record.owner_did);
if caller != &record.owner_did && caller != owner_short {
return Err(AppError::BadRequest(
"only the repo owner can unprotect branches".into(),
));
}
@@ -80,10 +73,7 @@ pub async fn list_protected_branches(
State(state): State<AppState>,
Path((owner, repo)): Path<(String, String)>,
) -> Result<Json<serde_json::Value>> {
let record = state
.db
.get_repo(&owner, &repo)
.await?
let record = state.db.get_repo(&owner, &repo).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
let branches = state.db.list_protected_branches(&record.id).await?;
+37 -140
View File
@@ -8,7 +8,7 @@ use serde::Deserialize;
use uuid::Uuid;
use crate::auth::AuthenticatedDid;
use crate::db::{PrComment, PrReview, PullRequest};
use crate::db::{PullRequest, PrComment, PrReview};
use crate::error::{AppError, Result};
use crate::git::store;
use crate::state::AppState;
@@ -40,16 +40,11 @@ pub async fn create_pr(
Path((owner, name)): Path<(String, String)>,
Json(req): Json<CreatePrRequest>,
) -> Result<(StatusCode, Json<PullRequest>)> {
// Authorize the caller as a reader before accepting a PR: a non-reader must
// not be able to open a PR (and fire its webhooks) against a private repo
// they cannot read. Mirrors create_review / create_comment / create_bounty.
let (record, _rules) =
crate::api::authorize_repo_read(&state, &owner, &name, Some(auth.0.as_str()), "/").await?;
let record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
let author_did = auth.0;
let target_branch = req
.target_branch
.unwrap_or_else(|| record.default_branch.clone());
let target_branch = req.target_branch.unwrap_or_else(|| record.default_branch.clone());
let number = state.db.next_pr_number(&record.id).await?;
let now = Utc::now().to_rfc3339();
@@ -73,11 +68,7 @@ pub async fn create_pr(
// Bump trust score for the PR author — increment current score by 0.05
// (avoids the push_count=0 stuck-at-0.05 bug for agents who only open PRs)
let current = state
.db
.get_trust_score(&pr.author_did)
.await
.unwrap_or(0.05);
let current = state.db.get_trust_score(&pr.author_did).await.unwrap_or(0.05);
let new_score = (current + 0.05).min(1.0);
let _ = state.db.update_trust_score(&pr.author_did, new_score).await;
@@ -101,32 +92,23 @@ pub async fn create_pr(
pub async fn list_prs(
State(state): State<AppState>,
Path((owner, name)): Path<(String, String)>,
auth: Option<Extension<AuthenticatedDid>>,
) -> Result<Json<serde_json::Value>> {
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 record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
let prs = state.db.list_prs(&record.id).await?;
Ok(Json(
serde_json::json!({ "pulls": prs, "count": prs.len() }),
))
Ok(Json(serde_json::json!({ "pulls": prs, "count": prs.len() })))
}
/// GET /api/v1/repos/:owner/:repo/pulls/:number
pub async fn get_pr(
State(state): State<AppState>,
Path((owner, name, number)): Path<(String, String, i64)>,
auth: Option<Extension<AuthenticatedDid>>,
) -> Result<Json<PullRequest>> {
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 record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
let pr = state
.db
.get_pr(&record.id, number)
.await?
let pr = state.db.get_pr(&record.id, number).await?
.ok_or_else(|| AppError::NotFound(format!("PR #{number} not found")))?;
Ok(Json(pr))
@@ -136,42 +118,15 @@ pub async fn get_pr(
pub async fn get_pr_diff(
State(state): State<AppState>,
Path((owner, name, number)): Path<(String, String, i64)>,
auth: Option<Extension<AuthenticatedDid>>,
) -> Result<Json<serde_json::Value>> {
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 record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
let pr = state
.db
.get_pr(&record.id, number)
.await?
let pr = state.db.get_pr(&record.id, number).await?
.ok_or_else(|| AppError::NotFound(format!("PR #{number} not found")))?;
let disk_path = state
.repo_store
.acquire(&record.owner_did, &record.name)
.await
let disk_path = state.repo_store.acquire(&record.owner_did, &record.name).await
.map_err(|e| AppError::Git(e.to_string()))?;
// Withhold the entire diff if it touches a path the caller cannot read, so a
// PR diff cannot leak private-subtree content of an otherwise-public repo.
let touched = store::branch_diff_names(&disk_path, &pr.target_branch, &pr.source_branch)
.map_err(|e| AppError::Git(e.to_string()))?;
for p in &touched {
let gate = format!("/{}", p.trim_start_matches('/'));
if crate::visibility::visibility_check(
&rules,
record.is_public,
&record.owner_did,
caller,
&gate,
) == crate::visibility::Decision::Deny
{
return Err(AppError::NotFound(format!("PR #{number} not found")));
}
}
let diff = store::branch_diff(&disk_path, &pr.target_branch, &pr.source_branch)
.map_err(|e| AppError::Git(e.to_string()))?;
@@ -188,44 +143,24 @@ pub async fn merge_pr(
Extension(auth): Extension<AuthenticatedDid>,
Path((owner, name, number)): Path<(String, String, i64)>,
) -> Result<Json<serde_json::Value>> {
let record = state
.db
.get_repo(&owner, &name)
.await?
let record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
// Owner-only merge (N7). Merging writes the served tree, so this is the same
// trust boundary as owner-only push; it subsumes branch protection (a
// non-owner cannot merge to any branch, protected or not).
crate::api::require_repo_owner(&record, &auth.0)?;
let pr = state
.db
.get_pr(&record.id, number)
.await?
let pr = state.db.get_pr(&record.id, number).await?
.ok_or_else(|| AppError::NotFound(format!("PR #{number} not found")))?;
if pr.status != "open" {
return Err(AppError::BadRequest(format!("PR is already {}", pr.status)));
}
let guard = state
.repo_store
.acquire_write(&record.owner_did, &record.name)
.await
let guard = state.repo_store.acquire_write(&record.owner_did, &record.name).await
.map_err(|e| AppError::Git(e.to_string()))?;
let disk_path = guard.path().to_path_buf();
let merger_did = auth.0;
let merge_result = store::merge_branch(
&disk_path,
&pr.target_branch,
&pr.source_branch,
&merger_did,
&pr.title,
);
let merge_result = store::merge_branch(&disk_path, &pr.target_branch, &pr.source_branch, &merger_did, &pr.title);
// Always release the advisory lock — even on error; upload to Tigris only on success.
guard.release(merge_result.is_ok()).await;
// Always release the advisory lock — even on error
guard.release().await;
let merge_sha = merge_result.map_err(|e| AppError::Git(e.to_string()))?;
@@ -257,30 +192,14 @@ pub async fn merge_pr(
/// POST /api/v1/repos/:owner/:repo/pulls/:number/close
pub async fn close_pr(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
Path((owner, name, number)): Path<(String, String, i64)>,
) -> Result<Json<serde_json::Value>> {
let record = state
.db
.get_repo(&owner, &name)
.await?
let record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
let pr = state
.db
.get_pr(&record.id, number)
.await?
let pr = state.db.get_pr(&record.id, number).await?
.ok_or_else(|| AppError::NotFound(format!("PR #{number} not found")))?;
// Owner OR author may close (forge norm).
let is_owner = crate::api::require_repo_owner(&record, &auth.0).is_ok();
let is_author = crate::api::did_matches(&auth.0, &pr.author_did);
if !is_owner && !is_author {
return Err(AppError::Forbidden(
"only the repo owner or the PR author can close this PR".into(),
));
}
state.db.close_pr(&pr.id).await?;
webhooks::fire_event(
@@ -305,21 +224,15 @@ pub async fn create_review(
Path((owner, name, number)): Path<(String, String, i64)>,
Json(req): Json<CreateReviewRequest>,
) -> Result<(StatusCode, Json<PrReview>)> {
// Read-gate: a reviewer must be able to read the repo, but need not own it.
let (record, _rules) =
crate::api::authorize_repo_read(&state, &owner, &name, Some(auth.0.as_str()), "/").await?;
let record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
let pr = state
.db
.get_pr(&record.id, number)
.await?
let pr = state.db.get_pr(&record.id, number).await?
.ok_or_else(|| AppError::NotFound(format!("PR #{number} not found")))?;
let valid_statuses = ["approved", "changes_requested", "comment"];
if !valid_statuses.contains(&req.status.as_str()) {
return Err(AppError::BadRequest(
"status must be approved, changes_requested, or comment".into(),
));
return Err(AppError::BadRequest("status must be approved, changes_requested, or comment".into()));
}
let review = PrReview {
@@ -353,16 +266,11 @@ pub async fn create_review(
pub async fn list_reviews(
State(state): State<AppState>,
Path((owner, name, number)): Path<(String, String, i64)>,
auth: Option<Extension<AuthenticatedDid>>,
) -> Result<Json<serde_json::Value>> {
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 record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
let pr = state
.db
.get_pr(&record.id, number)
.await?
let pr = state.db.get_pr(&record.id, number).await?
.ok_or_else(|| AppError::NotFound(format!("PR #{number} not found")))?;
let reviews = state.db.list_pr_reviews(&pr.id).await?;
@@ -377,19 +285,13 @@ pub async fn create_comment(
Json(req): Json<CreateCommentRequest>,
) -> Result<(StatusCode, Json<PrComment>)> {
if req.body.trim().is_empty() {
return Err(AppError::BadRequest(
"comment body must not be empty".into(),
));
return Err(AppError::BadRequest("comment body must not be empty".into()));
}
// Read-gate: a commenter must be able to read the repo, but need not own it.
let (record, _rules) =
crate::api::authorize_repo_read(&state, &owner, &name, Some(auth.0.as_str()), "/").await?;
let record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
let pr = state
.db
.get_pr(&record.id, number)
.await?
let pr = state.db.get_pr(&record.id, number).await?
.ok_or_else(|| AppError::NotFound(format!("PR #{number} not found")))?;
let comment = PrComment {
@@ -409,16 +311,11 @@ pub async fn create_comment(
pub async fn list_comments(
State(state): State<AppState>,
Path((owner, name, number)): Path<(String, String, i64)>,
auth: Option<Extension<AuthenticatedDid>>,
) -> Result<Json<serde_json::Value>> {
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 record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
let pr = state
.db
.get_pr(&record.id, number)
.await?
let pr = state.db.get_pr(&record.id, number).await?
.ok_or_else(|| AppError::NotFound(format!("PR #{number} not found")))?;
let comments = state.db.list_pr_comments(&pr.id).await?;
+16 -44
View File
@@ -1,8 +1,8 @@
use axum::extract::State;
use axum::http::StatusCode;
use axum::Json;
use chrono::Utc;
use serde::{Deserialize, Serialize};
use chrono::Utc;
use gitlawb_core::did::Did;
use gitlawb_core::ucan::Ucan;
@@ -35,66 +35,38 @@ pub struct RegisterResponse {
/// Accepts only requests with a valid HTTP Signature (enforced by middleware).
pub async fn register(
State(state): State<AppState>,
axum::Extension(auth): axum::Extension<crate::auth::AuthenticatedDid>,
headers: axum::http::HeaderMap,
Json(req): Json<RegisterRequest>,
) -> Result<(StatusCode, Json<RegisterResponse>)> {
// iCaptcha gate (inert unless ICAPTCHA_MODE is set). Verify up front; spend
// the proof only once the request is admissible, just before the write, so a
// rejected request never burns a valid proof.
let proof = crate::icaptcha::verify_request(&headers, &auth.0)?;
// Parse and validate the DID
let agent_did: Did = req
.did
.parse()
let agent_did: Did = req.did.parse()
.map_err(|e: gitlawb_core::Error| AppError::BadRequest(e.to_string()))?;
// Bind registration to the authenticated signer: an agent may only register
// itself, not create or refresh a trust row for a DID it does not control.
if !crate::api::did_matches(&auth.0, agent_did.as_str()) {
return Err(AppError::Forbidden(
"did must be the authenticated signer".into(),
));
}
// Request is admissible — spend the proof now, immediately before the write.
proof.consume(&state.db).await?;
// Store the agent in the local index
state
.db
.register_agent(agent_did.as_str(), &req.capabilities)
.await?;
state.db.register_agent(agent_did.as_str(), &req.capabilities).await?;
// Grant a small baseline trust score on first registration (verified via HTTP Signature).
// Score grows further with pushes, PRs, and issue activity.
let initial_trust = 0.05;
let _ = state
.db
.update_trust_score(agent_did.as_str(), initial_trust)
.await;
let _ = state.db.update_trust_score(agent_did.as_str(), initial_trust).await;
// Issue a bootstrap UCAN from the node's identity
let ucan = Ucan::bootstrap(&state.node_keypair, agent_did.clone())
.map_err(|e| AppError::Internal(e.into()))?;
let exp = Utc::now() + chrono::Duration::days(30);
let ucan_encoded = ucan.encode().map_err(|e| AppError::Internal(e.into()))?;
let ucan_encoded = ucan.encode()
.map_err(|e| AppError::Internal(e.into()))?;
tracing::info!(did = %agent_did, "registered new agent");
Ok((
StatusCode::CREATED,
Json(RegisterResponse {
status: "accepted".to_string(),
did: agent_did.to_string(),
ucan: ucan_encoded,
node: format!("{}:{}", state.config.host, state.config.port),
expires: exp.to_rfc3339(),
trust_score: initial_trust,
capabilities: req.capabilities,
message: "welcome to the network, agent.".to_string(),
}),
))
Ok((StatusCode::CREATED, Json(RegisterResponse {
status: "accepted".to_string(),
did: agent_did.to_string(),
ucan: ucan_encoded,
node: format!("{}:{}", state.config.host, state.config.port),
expires: exp.to_rfc3339(),
trust_score: initial_trust,
capabilities: req.capabilities,
message: "welcome to the network, agent.".to_string(),
})))
}
-203
View File
@@ -1,203 +0,0 @@
//! Repo replica registration API.
//!
//! Lets a node tell the origin "I'm hosting a replica of your repo." The
//! origin records the (replica DID, replica URL) pair and exposes the list
//! publicly so anyone can see how many nodes are mirroring a given repo.
//!
//! Endpoints:
//! - `PUT /api/v1/repos/:owner/:repo/replicas` (auth) register
//! - `DELETE /api/v1/repos/:owner/:repo/replicas` (auth) unregister
//! - `GET /api/v1/repos/:owner/:repo/replicas` (public) list
//!
//! Auth model: the caller's DID (verified via HTTP Signatures) is the
//! replica's identity. There's no separate "claim this URL" check — replicas
//! self-report their public URL. Operators viewing the list should treat
//! replica URLs as advisory until they actually reach out and verify.
use axum::extract::{Extension, Path, State};
use axum::http::StatusCode;
use axum::Json;
use serde::Deserialize;
use crate::auth::AuthenticatedDid;
use crate::error::{AppError, Result};
use crate::state::AppState;
#[derive(Debug, Deserialize)]
pub struct RegisterReplicaRequest {
/// Publicly reachable URL of the replica node (e.g. `https://my-node.example.com`).
pub url: String,
}
/// PUT /api/v1/repos/:owner/:repo/replicas
/// Idempotent — first registration returns 201, subsequent ones update the URL and return 200.
pub async fn register_replica(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
Path((owner, repo)): Path<(String, String)>,
Json(req): Json<RegisterReplicaRequest>,
) -> Result<(StatusCode, Json<serde_json::Value>)> {
validate_replica_url(&req.url)?;
let record = state
.db
.get_repo(&owner, &repo)
.await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
let replica_did = &auth.0;
// Don't let an owner register themselves as a replica of their own repo
// (did_matches handles the full vs bare did:key owner form).
if crate::api::did_matches(replica_did, &record.owner_did) {
return Err(AppError::BadRequest(
"the repo owner is not a replica of their own repo".into(),
));
}
let inserted = state
.db
.register_replica(&record.id, replica_did, &req.url)
.await?;
let count = state.db.count_replicas(&record.id).await?;
let status = if inserted {
StatusCode::CREATED
} else {
StatusCode::OK
};
tracing::info!(
repo = %repo,
replica = %replica_did,
url = %req.url,
"replica registered"
);
Ok((
status,
Json(serde_json::json!({
"status": "registered",
"repo": format!("{owner}/{repo}"),
"replica_did": replica_did,
"replica_url": req.url,
"replica_count": count,
})),
))
}
/// DELETE /api/v1/repos/:owner/:repo/replicas
/// Idempotent — no error if the caller wasn't registered.
pub async fn unregister_replica(
State(state): State<AppState>,
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 replica_did = &auth.0;
state.db.unregister_replica(&record.id, replica_did).await?;
let count = state.db.count_replicas(&record.id).await?;
tracing::info!(repo = %repo, replica = %replica_did, "replica unregistered");
Ok(Json(serde_json::json!({
"status": "unregistered",
"repo": format!("{owner}/{repo}"),
"replica_count": count,
})))
}
/// GET /api/v1/repos/:owner/:repo/replicas
/// Public — returns the list of replicas (DID + URL + registration timestamp).
pub async fn list_replicas(
State(state): State<AppState>,
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 replicas = state.db.list_replicas(&record.id).await?;
Ok(Json(serde_json::json!({
"repo": format!("{owner}/{repo}"),
"replica_count": replicas.len(),
"replicas": replicas,
})))
}
/// Basic URL hygiene — must be http(s), parseable, length-bounded.
fn validate_replica_url(url: &str) -> Result<()> {
if url.is_empty() {
return Err(AppError::BadRequest("replica url is empty".into()));
}
if url.len() > 512 {
return Err(AppError::BadRequest("replica url exceeds 512 chars".into()));
}
if !(url.starts_with("http://") || url.starts_with("https://")) {
return Err(AppError::BadRequest(
"replica url must start with http:// or https://".into(),
));
}
// No spaces / control chars / newlines.
if url.chars().any(|c| c.is_whitespace() || c.is_control()) {
return Err(AppError::BadRequest(
"replica url contains whitespace or control characters".into(),
));
}
Ok(())
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn url_accepts_normal_https() {
validate_replica_url("https://node.example.com").unwrap();
validate_replica_url("https://my-node.example.com:7545").unwrap();
validate_replica_url("http://localhost:7545").unwrap();
}
#[test]
fn url_rejects_empty() {
assert!(validate_replica_url("").is_err());
}
#[test]
fn url_rejects_non_http_scheme() {
for bad in [
"ftp://host",
"file:///etc/passwd",
"javascript:alert(1)",
"/path",
] {
assert!(validate_replica_url(bad).is_err(), "{bad:?} must reject");
}
}
#[test]
fn url_rejects_whitespace_and_control() {
for bad in [
"https://host .com",
"https://host\n.com",
"https://host\t.com",
"https://host\0evil.com",
] {
assert!(validate_replica_url(bad).is_err(), "{bad:?} must reject");
}
}
#[test]
fn url_rejects_overlong() {
let long = format!("https://{}.com", "a".repeat(600));
assert!(validate_replica_url(&long).is_err());
}
}
File diff suppressed because it is too large. Load diff
+15 -24
View File
@@ -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 gated on repo read access.
//! Star count is public — no auth required on GET.
use axum::extract::{Extension, Path, State};
use axum::http::StatusCode;
use axum::Json;
use crate::auth::AuthenticatedDid;
use crate::error::Result;
use crate::error::{AppError, Result};
use crate::state::AppState;
/// PUT /api/v1/repos/:owner/:repo/star
@@ -19,29 +19,22 @@ pub async fn star_repo(
Extension(auth): Extension<AuthenticatedDid>,
Path((owner, repo)): Path<(String, String)>,
) -> Result<(StatusCode, Json<serde_json::Value>)> {
let (record, _rules) =
crate::api::authorize_repo_read(&state, &owner, &repo, Some(auth.0.as_str()), "/").await?;
let record = state.db.get_repo(&owner, &repo).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
let caller = &auth.0;
let inserted = state.db.star_repo(&record.id, caller).await?;
let count = state.db.count_stars(&record.id).await?;
let status = if inserted {
StatusCode::CREATED
} else {
StatusCode::OK
};
let status = if inserted { StatusCode::CREATED } else { StatusCode::OK };
tracing::info!(repo = %repo, caller = %caller, "repo starred");
Ok((
status,
Json(serde_json::json!({
"status": "starred",
"repo": format!("{owner}/{repo}"),
"star_count": count,
})),
))
Ok((status, Json(serde_json::json!({
"status": "starred",
"repo": format!("{owner}/{repo}"),
"star_count": count,
}))))
}
/// DELETE /api/v1/repos/:owner/:repo/star
@@ -51,8 +44,8 @@ pub async fn unstar_repo(
Extension(auth): Extension<AuthenticatedDid>,
Path((owner, repo)): Path<(String, String)>,
) -> Result<Json<serde_json::Value>> {
let (record, _rules) =
crate::api::authorize_repo_read(&state, &owner, &repo, Some(auth.0.as_str()), "/").await?;
let record = state.db.get_repo(&owner, &repo).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
let caller = &auth.0;
state.db.unstar_repo(&record.id, caller).await?;
@@ -68,15 +61,13 @@ pub async fn unstar_repo(
}
/// GET /api/v1/repos/:owner/:repo/star
/// Returns star count for callers who can read the repo.
/// Returns star count — unauthenticated.
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 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 record = state.db.get_repo(&owner, &repo).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
let count = state.db.count_stars(&record.id).await?;
+19 -85
View File
@@ -9,7 +9,7 @@
//! POST /api/v1/tasks/{id}/fail — fail task
use axum::{
extract::{Extension, Path, Query, State},
extract::{Path, Query, State},
http::StatusCode,
Json,
};
@@ -18,18 +18,9 @@ use serde::Deserialize;
use serde_json::{json, Value};
use uuid::Uuid;
use crate::auth::AuthenticatedDid;
use crate::db::AgentTask;
use crate::state::{AppState, TaskEventBroadcast};
/// 403 in this module's error shape (`(StatusCode, Json<Value>)`, not `AppError`).
fn forbidden(msg: &str) -> (StatusCode, Json<Value>) {
(
StatusCode::FORBIDDEN,
Json(json!({ "error": "forbidden", "message": msg })),
)
}
// ── Request / response types ──────────────────────────────────────────────────
#[derive(Deserialize)]
@@ -64,11 +55,13 @@ pub struct ClaimTaskBody {
#[derive(Deserialize)]
pub struct CompleteTaskBody {
pub result: Option<String>,
pub by_did: Option<String>,
}
#[derive(Deserialize)]
pub struct FailTaskBody {
pub reason: Option<String>,
pub by_did: Option<String>,
}
fn task_to_json(t: &AgentTask) -> Value {
@@ -94,20 +87,15 @@ fn task_to_json(t: &AgentTask) -> Value {
/// POST /api/v1/tasks
pub async fn create_task(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
Json(body): Json<CreateTaskBody>,
) -> Result<(StatusCode, Json<Value>), (StatusCode, Json<Value>)> {
// Bind the delegator to the authenticated signer (N13).
if !crate::api::did_matches(&auth.0, &body.delegator_did) {
return Err(forbidden("delegator_did must be the authenticated signer"));
}
let now = Utc::now().to_rfc3339();
let task = AgentTask {
id: Uuid::new_v4().to_string(),
repo_id: body.repo_id,
kind: body.kind,
status: "pending".to_string(),
delegator_did: auth.0,
delegator_did: body.delegator_did,
assignee_did: body.assignee_did,
capability: body.capability,
ucan_token: body.ucan_token,
@@ -166,25 +154,24 @@ pub async fn get_task(
/// POST /api/v1/tasks/{id}/claim
pub async fn claim_task(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
Path(id): Path<String>,
Json(body): Json<ClaimTaskBody>,
) -> Result<Json<Value>, (StatusCode, Json<Value>)> {
// Bind the assignee to the authenticated signer (N13).
if !crate::api::did_matches(&auth.0, &body.assignee_did) {
return Err(forbidden("assignee_did must be the authenticated signer"));
}
let task = state.db.claim_task(&id, &auth.0).await.map_err(|e| {
(
StatusCode::CONFLICT,
Json(json!({ "error": e.to_string() })),
)
})?;
let task = state
.db
.claim_task(&id, &body.assignee_did)
.await
.map_err(|e| {
(
StatusCode::CONFLICT,
Json(json!({ "error": e.to_string() })),
)
})?;
let _ = state.task_event_tx.send(TaskEventBroadcast {
task_id: id,
old_status: "pending".to_string(),
new_status: "claimed".to_string(),
by_did: auth.0,
by_did: body.assignee_did,
at: Utc::now().to_rfc3339(),
});
Ok(Json(task_to_json(&task)))
@@ -193,44 +180,17 @@ pub async fn claim_task(
/// POST /api/v1/tasks/{id}/complete
pub async fn complete_task(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
Path(id): Path<String>,
Json(body): Json<CompleteTaskBody>,
) -> Result<Json<Value>, (StatusCode, Json<Value>)> {
// Authorize the actor, not just bind their identity: the N13 signer-binding
// proved the caller was whoever they claimed, but never that they were the
// task's assignee. Load the task and require the caller to be its assignee;
// finish_task then transitions only a claimed task.
let existing = state
.db
.get_task(&id)
.await
.map_err(|e| {
(
StatusCode::INTERNAL_SERVER_ERROR,
Json(json!({ "error": e.to_string() })),
)
})?
.ok_or_else(|| {
(
StatusCode::NOT_FOUND,
Json(json!({ "error": "task not found" })),
)
})?;
if !crate::api::did_matches(
&auth.0,
existing.assignee_did.as_deref().unwrap_or_default(),
) {
return Err(forbidden("only the task assignee can complete it"));
}
let by_did = auth.0;
let by_did = body.by_did.unwrap_or_default();
let task = state
.db
.finish_task(&id, "completed", body.result.as_deref())
.await
.map_err(|e| {
(
StatusCode::CONFLICT,
StatusCode::UNPROCESSABLE_ENTITY,
Json(json!({ "error": e.to_string() })),
)
})?;
@@ -247,36 +207,10 @@ pub async fn complete_task(
/// POST /api/v1/tasks/{id}/fail
pub async fn fail_task(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
Path(id): Path<String>,
Json(body): Json<FailTaskBody>,
) -> Result<Json<Value>, (StatusCode, Json<Value>)> {
// Authorize the actor, not just bind their identity (see complete_task): only
// the task's assignee may fail it, and finish_task transitions only a claimed
// task.
let existing = state
.db
.get_task(&id)
.await
.map_err(|e| {
(
StatusCode::INTERNAL_SERVER_ERROR,
Json(json!({ "error": e.to_string() })),
)
})?
.ok_or_else(|| {
(
StatusCode::NOT_FOUND,
Json(json!({ "error": "task not found" })),
)
})?;
if !crate::api::did_matches(
&auth.0,
existing.assignee_did.as_deref().unwrap_or_default(),
) {
return Err(forbidden("only the task assignee can fail it"));
}
let by_did = auth.0;
let by_did = body.by_did.unwrap_or_default();
let reason = body.reason.unwrap_or_default();
let task = state
.db
@@ -284,7 +218,7 @@ pub async fn fail_task(
.await
.map_err(|e| {
(
StatusCode::CONFLICT,
StatusCode::UNPROCESSABLE_ENTITY,
Json(json!({ "error": e.to_string() })),
)
})?;
-275
View File
@@ -1,275 +0,0 @@
//! Path-scoped visibility management API. Owner-only, mirrors `api/protect.rs`.
use axum::extract::{Extension, Path, State};
use axum::http::StatusCode;
use axum::Json;
use serde::Deserialize;
use crate::auth::AuthenticatedDid;
use crate::db::VisibilityMode;
use crate::error::{AppError, Result};
use crate::state::AppState;
#[derive(Deserialize)]
pub struct SetVisibilityRequest {
pub path_glob: String,
/// "a" or "b"; defaults to "b" if absent or unrecognized.
#[serde(default)]
pub mode: Option<String>,
#[serde(default)]
pub reader_dids: Vec<String>,
}
#[derive(Deserialize)]
pub struct RemoveVisibilityRequest {
pub path_glob: String,
}
fn require_owner(record: &crate::db::RepoRecord, caller: &str) -> Result<()> {
// DID-safe owner match (collapses did:key full vs bare on both sides, never
// across methods), shared with require_repo_owner — not a trailing-segment
// compare that only normalized the owner side.
if crate::api::did_matches(caller, &record.owner_did) {
Ok(())
} else {
Err(AppError::Forbidden(
"only the repo owner can manage visibility".into(),
))
}
}
/// Reject malformed globs before they reach the store, where they would
/// silently misconfigure access (an empty glob behaves like "/", and a glob
/// without a leading "/" never matches a real repo path). The accepted forms
/// match what `visibility_check` understands: "/", "/prefix", or "/prefix/**".
fn validate_path_glob(path_glob: &str) -> Result<()> {
if !path_glob.starts_with('/') {
return Err(AppError::BadRequest("path_glob must start with '/'".into()));
}
if path_glob == "/**" {
return Err(AppError::BadRequest(
"use '/' for whole-repo scope, not '/**'".into(),
));
}
if path_glob != "/" && path_glob.ends_with('/') {
return Err(AppError::BadRequest(
"path_glob must not end with '/'".into(),
));
}
// Reject empty path segments. `glob_prefix` collapses "//**" to "/" (whole
// repo), so without this an operator could bypass the "/**" guard above and
// grant repo-wide read with "//**", or set a dead rule like "//secret/**"
// whose prefix never matches a real single-slash path and silently leaves
// the subtree readable.
if path_glob.contains("//") {
return Err(AppError::BadRequest(
"path_glob must not contain empty path segments".into(),
));
}
// Strip the one permitted trailing "/**" before checking for stray
// wildcards, otherwise a "*" elsewhere in the prefix (e.g. "/a*b/**" or
// "/a/**/**") slips through because the string still ends with "/**".
let prefix = path_glob.strip_suffix("/**").unwrap_or(path_glob);
if prefix.contains('*') {
return Err(AppError::BadRequest(
"the only supported wildcard is a single trailing '/**'".into(),
));
}
Ok(())
}
/// PUT /api/v1/repos/{owner}/{repo}/visibility
pub async fn set_visibility(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
Path((owner, repo)): Path<(String, String)>,
Json(req): Json<SetVisibilityRequest>,
) -> Result<(StatusCode, Json<serde_json::Value>)> {
let record = state
.db
.get_repo(&owner, &repo)
.await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
require_owner(&record, &auth.0)?;
validate_path_glob(&req.path_glob)?;
let mode = match req.mode.as_deref() {
Some("a") => VisibilityMode::A,
_ => VisibilityMode::B,
};
// Mode A hides existence and is only coherent for the whole repo; a subtree
// cannot hide its existence without rewriting git history (see spec).
if mode == VisibilityMode::A && req.path_glob != "/" {
return Err(AppError::BadRequest(
"mode 'a' (hide) is only allowed for the whole repo (path_glob '/'); use mode 'b' for subtrees".into(),
));
}
// An empty reader_dids list is valid and intentional: the owner is always
// allowed by visibility_check, so a "/" rule with no readers is exactly the
// whole-repo "private to owner only" case.
state
.db
.set_visibility_rule(&record.id, &req.path_glob, mode, &req.reader_dids, &auth.0)
.await?;
let subtree_warning = req.path_glob != "/";
tracing::info!(
repo = %repo, caller = %auth.0, path_glob = %req.path_glob, mode = %mode.as_str(),
subtree_pending = subtree_warning,
"visibility rule set"
);
Ok((
StatusCode::CREATED,
Json(serde_json::json!({
"status": "set",
"repo": format!("{owner}/{repo}"),
"path_glob": req.path_glob,
"mode": mode.as_str(),
"reader_dids": req.reader_dids,
"subtree_clone_enforcement_pending": subtree_warning,
})),
))
}
/// DELETE /api/v1/repos/{owner}/{repo}/visibility
pub async fn remove_visibility(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
Path((owner, repo)): Path<(String, String)>,
Json(req): Json<RemoveVisibilityRequest>,
) -> Result<Json<serde_json::Value>> {
let record = state
.db
.get_repo(&owner, &repo)
.await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{repo}")))?;
require_owner(&record, &auth.0)?;
state
.db
.remove_visibility_rule(&record.id, &req.path_glob)
.await?;
tracing::info!(
repo = %repo, caller = %auth.0, path_glob = %req.path_glob,
"visibility rule removed"
);
Ok(Json(serde_json::json!({
"status": "removed",
"repo": format!("{owner}/{repo}"),
"path_glob": req.path_glob,
})))
}
/// GET /api/v1/repos/{owner}/{repo}/visibility
pub async fn list_visibility(
State(state): State<AppState>,
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}")))?;
require_owner(&record, &auth.0)?;
let rules = state.db.list_visibility_rules(&record.id).await?;
let rules_json: Vec<_> = rules
.into_iter()
.map(|r| {
serde_json::json!({
"path_glob": r.path_glob,
"mode": r.mode.as_str(),
"reader_dids": r.reader_dids,
"created_by": r.created_by,
})
})
.collect();
Ok(Json(serde_json::json!({
"repo": format!("{owner}/{repo}"),
"count": rules_json.len(),
"rules": rules_json,
})))
}
/// GET /api/v1/repos/{owner}/{repo}/withheld-paths
///
/// Returns the path globs the (optionally authenticated) caller is denied
/// (`withheld`) plus any more-specific globs that are allowed underneath a
/// denied one (`reinclude`), so a clean-clone client can sparse-exclude the
/// denied subtrees while re-including the allowed nested paths. Unlike
/// `list_visibility` this is not owner-gated and never exposes reader_dids.
pub async fn withheld_paths(
State(state): State<AppState>,
auth: Option<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 rules = state.db.list_visibility_rules(&record.id).await?;
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
// Whole-repo read gate: a caller who cannot read "/" gets repo-not-found,
// matching the git read endpoints, so this never discloses a private repo's
// existence or its path layout to an unauthorized caller.
if crate::visibility::visibility_check(&rules, record.is_public, &record.owner_did, caller, "/")
== crate::visibility::Decision::Deny
{
return Err(AppError::RepoNotFound(format!("{owner}/{repo}")));
}
let withheld =
crate::visibility::withheld_globs(&rules, record.is_public, &record.owner_did, caller);
let reinclude =
crate::visibility::reincluded_globs(&rules, record.is_public, &record.owner_did, caller);
Ok(Json(serde_json::json!({
"repo": format!("{owner}/{repo}"),
"withheld": withheld,
"reinclude": reinclude,
})))
}
#[cfg(test)]
mod tests {
use super::validate_path_glob;
#[test]
fn accepts_supported_globs() {
for g in ["/", "/secret", "/secret/**", "/a/b/c", "/a/b/**"] {
assert!(validate_path_glob(g).is_ok(), "{g} should be valid");
}
}
#[test]
fn rejects_malformed_globs() {
// empty, no leading slash, whole-repo via "/**", trailing slash,
// non-trailing wildcards, double wildcards, and empty path segments
// (which would collapse to whole-repo or a dead rule) are all rejected.
for g in [
"",
"secret/**",
"/**",
"/**/**",
"/secret/",
"/a*b",
"/*/x",
"/a*b/**",
"/a/**/**",
"//**",
"//secret/**",
] {
assert!(validate_path_glob(g).is_err(), "{g} should be rejected");
}
}
}
+12 -72
View File
@@ -33,22 +33,12 @@ pub async fn create_webhook(
Path((owner, name)): Path<(String, String)>,
Json(req): Json<CreateWebhookRequest>,
) -> Result<(StatusCode, Json<Webhook>)> {
let record = state
.db
.get_repo(&owner, &name)
.await?
let record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
crate::api::require_repo_owner(&record, &auth.0)?;
// Gate the target through the same hardened public-host validator the peer
// announce path uses, so an authenticated owner cannot register a webhook
// that makes the node POST to loopback/private/link-local/metadata
// endpoints (SSRF). Delivery runs on the shared no-redirect client
// (main.rs), which closes the 3xx-to-internal bounce.
if !crate::api::peers::is_public_http_url(&req.url) {
return Err(AppError::BadRequest(
"webhook URL must be a public http(s) URL (no loopback, private, or .internal/.local hosts)".into(),
));
// Validate URL is http/https
if !req.url.starts_with("http://") && !req.url.starts_with("https://") {
return Err(AppError::BadRequest("webhook URL must be http:// or https://".into()));
}
let events = req.events.unwrap_or_else(|| vec!["*".into()]);
@@ -74,47 +64,29 @@ pub async fn list_webhooks(
State(state): State<AppState>,
Path((owner, name)): Path<(String, String)>,
) -> Result<Json<serde_json::Value>> {
let record = state
.db
.get_repo(&owner, &name)
.await?
let record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
let hooks = state.db.list_webhooks(&record.id).await?;
// Redact secrets in list response
let redacted: Vec<_> = hooks
.into_iter()
.map(|mut h| {
if h.secret.is_some() {
h.secret = Some("***".into());
}
h
})
.collect();
let redacted: Vec<_> = hooks.into_iter().map(|mut h| {
if h.secret.is_some() { h.secret = Some("***".into()); }
h
}).collect();
Ok(Json(
serde_json::json!({ "webhooks": redacted, "count": redacted.len() }),
))
Ok(Json(serde_json::json!({ "webhooks": redacted, "count": redacted.len() })))
}
/// DELETE /api/v1/repos/:owner/:repo/hooks/:id
pub async fn delete_webhook(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
Path((owner, name, id)): Path<(String, String, String)>,
) -> Result<Json<serde_json::Value>> {
let record = state
.db
.get_repo(&owner, &name)
.await?
let record = state.db.get_repo(&owner, &name).await?
.ok_or_else(|| AppError::RepoNotFound(format!("{owner}/{name}")))?;
crate::api::require_repo_owner(&record, &auth.0)?;
// Verify the webhook belongs to this repo
let hook = state
.db
.get_webhook(&id)
.await?
let hook = state.db.get_webhook(&id).await?
.ok_or_else(|| AppError::NotFound(format!("webhook {id} not found")))?;
if hook.repo_id != record.id {
@@ -124,35 +96,3 @@ pub async fn delete_webhook(
state.db.delete_webhook(&id).await?;
Ok(Json(serde_json::json!({ "deleted": true, "id": id })))
}
#[cfg(test)]
mod tests {
use crate::api::peers::is_public_http_url;
// create_webhook gates req.url through is_public_http_url. Pin the exact
// SSRF targets from issue #81 so the webhook path can never regress to the
// old scheme-only check, independent of the validator's own peer tests.
#[test]
fn webhook_url_gate_rejects_ssrf_targets() {
for bad in [
"http://127.0.0.1:5432/",
"http://169.254.169.254/latest/meta-data/",
"http://localhost/",
"http://10.0.0.5/",
"http://[::1]/",
// IPv6 transition encodings smuggling loopback v4 (6to4 / NAT64).
"http://[2002:7f00:1::]/",
"http://[64:ff9b::7f00:1]/",
"ftp://example.com/",
"not-a-url",
] {
assert!(!is_public_http_url(bad), "{bad:?} must be rejected");
}
}
#[test]
fn webhook_url_gate_allows_public_targets() {
assert!(is_public_http_url("https://hooks.example.com/gitlawb"));
assert!(is_public_http_url("http://203.0.113.10:7545/"));
}
}
+8 -226
View File
@@ -20,6 +20,7 @@
use anyhow::Result;
use serde_json::json;
/// Data describing a ref-update event to be anchored.
#[derive(Debug, Clone)]
pub struct RefAnchor {
@@ -103,108 +104,6 @@ pub async fn anchor_ref_update(
Ok(tx_id)
}
/// A per-push manifest of the blobs encrypted this push (Option B3). The
/// `blobs` slice is `(oid, cid)` tuples. Anchored directly to Arweave as its JSON
/// body so the discovery index survives total node loss. Recipient identities are
/// never part of the manifest.
pub struct EncryptedManifest<'a> {
pub repo: &'a str,
pub owner_did: &'a str,
pub node_did: &'a str,
pub timestamp: &'a str,
pub blobs: &'a [(String, String)],
}
/// Anchor a per-push encrypted-blob manifest to Arweave via Irys. The manifest
/// JSON body is the payload (not a CID pointer to IPFS), so the index is
/// permanent and self-contained. Recipient identities are deliberately omitted:
/// the anchor is permanent and public, and the v2 envelopes no longer expose
/// recipients, so the reader set must not be written to Arweave either.
///
/// Returns the Irys/Arweave transaction ID, or `Ok("")` when `irys_url` is empty
/// (anchoring disabled) or there are no blobs to anchor.
pub async fn anchor_encrypted_manifest(
client: &reqwest::Client,
irys_url: &str,
manifest: &EncryptedManifest<'_>,
) -> Result<String> {
if irys_url.is_empty() || manifest.blobs.is_empty() {
return Ok(String::new());
}
let blobs_json: Vec<serde_json::Value> = manifest
.blobs
.iter()
.map(|(oid, cid)| manifest_blob_json(oid, cid))
.collect();
let payload = json!({
"schema": "gitlawb/encrypted-manifest/v1",
"repo": manifest.repo,
"owner_did": manifest.owner_did,
"node_did": manifest.node_did,
"timestamp": manifest.timestamp,
"blobs": blobs_json,
});
let body = serde_json::to_vec(&payload)?;
let url = format!("{}/upload", irys_url.trim_end_matches('/'));
let resp = client
.post(&url)
.header("Content-Type", "application/json")
.header("x-irys-tags", build_manifest_tags_header(manifest))
.body(body)
.send()
.await
.map_err(|e| anyhow::anyhow!("Irys upload failed: {e}"))?;
if !resp.status().is_success() {
let status = resp.status();
let body = resp.text().await.unwrap_or_default();
return Err(anyhow::anyhow!("Irys returned {status}: {body}"));
}
let json: serde_json::Value = resp
.json()
.await
.map_err(|e| anyhow::anyhow!("failed to parse Irys response: {e}"))?;
let tx_id = json["id"]
.as_str()
.ok_or_else(|| anyhow::anyhow!("no 'id' in Irys response: {json}"))?
.to_string();
tracing::info!(
repo = %manifest.repo,
tx_id = %tx_id,
blobs = manifest.blobs.len(),
"anchored encrypted manifest to Arweave"
);
Ok(tx_id)
}
/// Serialize one blob for the Arweave manifest. Recipient identities are
/// intentionally absent so the permanent public anchor never records who can
/// read a blob.
fn manifest_blob_json(oid: &str, cid: &str) -> serde_json::Value {
json!({ "oid": oid, "cid": cid })
}
/// Build the Irys tag header for an encrypted-blob manifest. `Repo` and `Schema`
/// are the tags the `gl` recovery query filters on.
fn build_manifest_tags_header(manifest: &EncryptedManifest<'_>) -> String {
[
"App-Name:gitlawb".to_string(),
"Schema:gitlawb/encrypted-manifest/v1".to_string(),
format!("Repo:{}", sanitize_tag(manifest.repo)),
format!("Owner-DID:{}", sanitize_tag(manifest.owner_did)),
format!("Node-DID:{}", sanitize_tag(manifest.node_did)),
]
.join(",")
}
/// Arweave permanent URL for a given Irys transaction ID.
pub fn arweave_url(tx_id: &str) -> String {
format!("https://arweave.net/{tx_id}")
@@ -213,9 +112,9 @@ pub fn arweave_url(tx_id: &str) -> String {
/// Build the Irys tag header value for Arweave indexing.
/// Format: comma-separated "name:value" pairs.
fn build_tags_header(anchor: &RefAnchor) -> String {
[
"App-Name:gitlawb".to_string(),
"Schema:gitlawb/ref-update/v1".to_string(),
vec![
format!("App-Name:gitlawb"),
format!("Schema:gitlawb/ref-update/v1"),
format!("Repo:{}", sanitize_tag(&anchor.repo)),
format!("Ref:{}", sanitize_tag(&anchor.ref_name)),
format!("SHA:{}", &anchor.new_sha[..anchor.new_sha.len().min(16)]),
@@ -243,7 +142,7 @@ mod tests {
repo: "alice/myrepo".into(),
owner_did: "did:key:z6Mk...".into(),
ref_name: "refs/heads/main".into(),
old_sha: "0000000000000000000000000000000000000000".into(),
old_sha: "0000000000000000000000000000000000000000000000000000000000000000".into(),
new_sha: "a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2".into(),
cid: Some("bafyreib5...".into()),
timestamp: "2026-03-14T00:00:00Z".into(),
@@ -270,7 +169,7 @@ mod tests {
repo: "alice/myrepo".into(),
owner_did: "did:key:z6Mk...".into(),
ref_name: "refs/heads/main".into(),
old_sha: "0".repeat(40),
old_sha: "0".repeat(64),
new_sha: "a1b2c3d4".repeat(8),
cid: None,
timestamp: "2026-03-14T00:00:00Z".into(),
@@ -279,131 +178,14 @@ mod tests {
let result = anchor_ref_update(&client, &server.url(), &anchor).await;
assert!(result.is_ok(), "anchor should succeed: {result:?}");
assert_eq!(
result.unwrap(),
"7xGpIoHUQ8j9GhD3Y2mKzP1NsVtXwRcFe4bEaLnMuOk"
);
_mock.assert_async().await;
}
#[tokio::test]
async fn test_anchor_body_carries_real_old_sha() {
// The anchored body must serialize the real old→new transition the
// node was handed, never a zero placeholder. Regression guard for the
// push handler that used to hardcode `old_sha` to 64 zeros (#26).
let mut server = mockito::Server::new_async().await;
let real_old = "1111111111111111111111111111111111111111";
let real_new = "2222222222222222222222222222222222222222";
let _mock = server
.mock("POST", "/upload")
.match_body(mockito::Matcher::AllOf(vec![
mockito::Matcher::PartialJsonString(format!(r#"{{"old_sha":"{real_old}"}}"#)),
mockito::Matcher::PartialJsonString(format!(r#"{{"new_sha":"{real_new}"}}"#)),
]))
.with_status(200)
.with_header("content-type", "application/json")
.with_body(r#"{"id":"TX_REAL_OLD_SHA","timestamp":1710000000000,"version":"1.0.0"}"#)
.create_async()
.await;
let client = reqwest::Client::new();
let anchor = RefAnchor {
repo: "alice/myrepo".into(),
owner_did: "did:key:z6Mk...".into(),
ref_name: "refs/heads/main".into(),
old_sha: real_old.into(),
new_sha: real_new.into(),
cid: None,
timestamp: "2026-03-14T00:00:00Z".into(),
node_did: "did:key:z6Mknnd...".into(),
};
let result = anchor_ref_update(&client, &server.url(), &anchor).await;
assert_eq!(result.unwrap(), "TX_REAL_OLD_SHA");
// The mock only matches when the posted JSON carries both real SHAs.
assert_eq!(result.unwrap(), "7xGpIoHUQ8j9GhD3Y2mKzP1NsVtXwRcFe4bEaLnMuOk");
_mock.assert_async().await;
}
#[test]
fn test_arweave_url() {
let url = arweave_url("7xGpIoHUQ8j9GhD3Y2mKzP1NsVtXwRcFe4bEaLnMuOk");
assert_eq!(
url,
"https://arweave.net/7xGpIoHUQ8j9GhD3Y2mKzP1NsVtXwRcFe4bEaLnMuOk"
);
}
#[tokio::test]
async fn test_manifest_anchor_noop_when_url_empty() {
let client = reqwest::Client::new();
let blobs = vec![("oid1".to_string(), "cid1".to_string())];
let m = EncryptedManifest {
repo: "alice/r",
owner_did: "did:key:zO",
node_did: "did:key:zN",
timestamp: "2026-06-11T00:00:00Z",
blobs: &blobs,
};
assert_eq!(
anchor_encrypted_manifest(&client, "", &m).await.unwrap(),
""
);
}
#[tokio::test]
async fn test_manifest_anchor_noop_when_no_blobs() {
let client = reqwest::Client::new();
let blobs: Vec<(String, String)> = vec![];
let m = EncryptedManifest {
repo: "alice/r",
owner_did: "did:key:zO",
node_did: "did:key:zN",
timestamp: "2026-06-11T00:00:00Z",
blobs: &blobs,
};
// Non-empty URL, but no blobs: still a no-op.
assert_eq!(
anchor_encrypted_manifest(&client, "https://example.invalid", &m)
.await
.unwrap(),
""
);
}
#[tokio::test]
async fn test_manifest_anchor_success() {
let mut server = mockito::Server::new_async().await;
let _mock = server
.mock("POST", "/upload")
.with_status(200)
.with_header("content-type", "application/json")
.with_body(r#"{"id":"MANIFESTTX123","timestamp":1710000000000,"version":"1.0.0"}"#)
.create_async()
.await;
let client = reqwest::Client::new();
let blobs = vec![("oid1".to_string(), "cid1".to_string())];
let m = EncryptedManifest {
repo: "alice/r",
owner_did: "did:key:zO",
node_did: "did:key:zN",
timestamp: "2026-06-11T00:00:00Z",
blobs: &blobs,
};
let r = anchor_encrypted_manifest(&client, &server.url(), &m).await;
assert_eq!(r.unwrap(), "MANIFESTTX123");
_mock.assert_async().await;
}
#[test]
fn manifest_blob_json_omits_recipients() {
let v = manifest_blob_json("oid1", "cidA");
assert_eq!(v["oid"], "oid1");
assert_eq!(v["cid"], "cidA");
assert!(
v.get("recipients").is_none(),
"Arweave manifest must not anchor recipient identities"
);
assert_eq!(url, "https://arweave.net/7xGpIoHUQ8j9GhD3Y2mKzP1NsVtXwRcFe4bEaLnMuOk");
}
#[test]
+26 -398
View File
@@ -1,5 +1,5 @@
use axum::body::Body;
use axum::extract::{Request, State};
use axum::extract::Request;
use axum::http::StatusCode;
use axum::middleware::Next;
use axum::response::{IntoResponse, Response};
@@ -8,27 +8,10 @@ use http_body_util::BodyExt;
use serde_json::json;
use std::collections::HashMap;
use gitlawb_core::did::Did;
use gitlawb_core::ucan::Ucan;
use crate::state::AppState;
/// The authenticated agent's DID, injected into request extensions by `require_signature`.
#[derive(Clone, Debug)]
pub struct AuthenticatedDid(pub String);
/// Whether `caller` is authorized to push to `record`.
///
/// Phase 1 (`GITLAWB_ENFORCE_OWNER_PUSH`): owner-only, via the canonical
/// [`crate::api::did_matches`] owner comparison (DID-safe on both sides). This is
/// intentionally a distinct, intent-named gate rather than a bare owner check so
/// that Phase 2 can extend it to honor a verified UCAN `git/push` capability as a
/// pure addition (`did_matches(..) || ucan_grants_push(..)`) without rewriting
/// call sites.
pub fn caller_authorized_to_push(record: &crate::db::RepoRecord, caller: &str) -> bool {
crate::api::did_matches(caller, &record.owner_did)
}
use gitlawb_core::http_sig::{
build_signing_string, compute_content_digest, HttpSignature, COVERED_COMPONENTS,
};
@@ -51,17 +34,16 @@ use gitlawb_core::identity::verify;
pub async fn require_signature(request: Request, next: Next) -> Response {
// Buffer the body so we can verify content-digest and pass it downstream
let (parts, body) = request.into_parts();
let body_bytes =
match body.collect().await {
Ok(collected) => collected.to_bytes(),
Err(_) => return (
let body_bytes = match body.collect().await {
Ok(collected) => collected.to_bytes(),
Err(_) => {
return (
StatusCode::BAD_REQUEST,
Json(
json!({ "error": "unreadable_body", "message": "could not read request body" }),
),
Json(json!({ "error": "unreadable_body", "message": "could not read request body" })),
)
.into_response(),
};
.into_response()
}
};
let sig_input = parts
.headers
@@ -79,9 +61,8 @@ pub async fn require_signature(request: Request, next: Next) -> Response {
(Some(i), Some(s)) => (i, s),
_ => {
return human_detected(
"missing Signature-Input or Signature headers — use RFC 9421 HTTP Signatures",
)
.into_response();
"missing Signature-Input or Signature headers — use RFC 9421 HTTP Signatures"
).into_response();
}
};
@@ -175,21 +156,22 @@ pub async fn require_signature(request: Request, next: Next) -> Response {
request_values.insert("content-digest".to_string(), content_digest);
// The @signature-params value is the part of Signature-Input after "sig1="
let sig_params_value = sig_input.strip_prefix("sig1=").unwrap_or(&sig_input);
let sig_params_value = sig_input
.strip_prefix("sig1=")
.unwrap_or(&sig_input);
let components_ref: Vec<&str> = sig.components.iter().map(String::as_str).collect();
let signing_string =
match build_signing_string(&components_ref, sig_params_value, &request_values) {
Ok(s) => s,
Err(e) => {
return (
StatusCode::BAD_REQUEST,
Json(json!({ "error": "signing_string_error", "message": e.to_string() })),
)
.into_response()
}
};
let signing_string = match build_signing_string(&components_ref, sig_params_value, &request_values) {
Ok(s) => s,
Err(e) => {
return (
StatusCode::BAD_REQUEST,
Json(json!({ "error": "signing_string_error", "message": e.to_string() })),
)
.into_response()
}
};
// Verify Ed25519 signature
let sig_array: [u8; 64] = match sig.signature_bytes.as_slice().try_into() {
@@ -218,11 +200,7 @@ pub async fn require_signature(request: Request, next: Next) -> Response {
}
// Verify Content-Digest matches the actual request body
if let Some(claimed) = parts
.headers
.get("content-digest")
.and_then(|v| v.to_str().ok())
{
if let Some(claimed) = parts.headers.get("content-digest").and_then(|v| v.to_str().ok()) {
let actual = compute_content_digest(&body_bytes);
if claimed != actual {
return (
@@ -239,130 +217,7 @@ pub async fn require_signature(request: Request, next: Next) -> Response {
tracing::info!(did = %sig.key_id, "✓ authenticated request");
let mut request = Request::from_parts(parts, Body::from(body_bytes));
request
.extensions_mut()
.insert(AuthenticatedDid(sig.key_id.to_string()));
next.run(request).await
}
/// Optional variant for rolling upgrades: verify and inject `AuthenticatedDid` when
/// RFC 9421 signature headers are present, but allow legacy unsigned requests to
/// continue when no signature attempt was made.
pub async fn optional_signature(request: Request, next: Next) -> Response {
let has_signature_headers = request.headers().contains_key("signature-input")
|| request.headers().contains_key("signature");
if has_signature_headers {
return require_signature(request, next).await;
}
next.run(request).await
}
/// Validate a raw UCAN token string supplied in `X-Ucan`.
///
/// Checks performed:
/// 1. The token decodes to a valid [`Ucan`] structure.
/// 2. The UCAN issuer (`iss`) matches `signer_did` — the DID that signed the
/// HTTP request — preventing replay of another agent's UCAN.
/// 3. The UCAN audience (`aud`) matches `expected_aud` — the node's own DID.
/// 4. The full proof chain is cryptographically valid (signatures, expiry,
/// not-before, chain linkage, and capability attenuation).
fn validate_ucan_chain(
token: &str,
expected_aud: &Did,
signer_did: &Did,
) -> Result<(), (StatusCode, Json<serde_json::Value>)> {
let ucan = Ucan::decode(token).map_err(|e| {
(
StatusCode::UNAUTHORIZED,
Json(json!({ "error": "invalid_ucan", "message": e.to_string() })),
)
})?;
if &ucan.payload.iss != signer_did {
return Err((
StatusCode::UNAUTHORIZED,
Json(json!({
"error": "invalid_ucan",
"message": format!(
"UCAN issuer {} does not match request signer {}",
ucan.payload.iss, signer_did
),
})),
));
}
ucan.verify_audience(expected_aud).map_err(|e| {
(
StatusCode::UNAUTHORIZED,
Json(json!({ "error": "invalid_ucan", "message": e.to_string() })),
)
})?;
ucan.verify_chain().map_err(|e| {
(
StatusCode::UNAUTHORIZED,
Json(json!({ "error": "invalid_ucan", "message": e.to_string() })),
)
})?;
Ok(())
}
/// Axum middleware that validates a UCAN chain when `X-Ucan` is present.
///
/// Must be layered so that it runs after [`require_signature`], which sets the
/// [`AuthenticatedDid`] extension consumed here.
///
/// When `X-Ucan` is absent the request passes through unchanged, preserving
/// backward compatibility for agents that pre-date UCAN delegation. When the
/// header is present the full chain is validated: the UCAN issuer must match
/// the HTTP Signature identity, the audience must be this node's DID, and
/// every proof in the chain must be cryptographically sound with no capability
/// escalation.
pub async fn require_ucan_chain(
State(state): State<AppState>,
request: Request,
next: Next,
) -> Response {
let token = match request
.headers()
.get("x-ucan")
.and_then(|v| v.to_str().ok())
.map(str::to_owned)
{
Some(t) => t,
None => return next.run(request).await,
};
let signer_did: Did = match request.extensions().get::<AuthenticatedDid>() {
Some(a) => match a.0.parse() {
Ok(did) => did,
Err(e) => {
tracing::warn!(raw_did = %a.0, err = %e, "failed to parse DID from authenticated identity");
return (
StatusCode::UNAUTHORIZED,
Json(json!({ "error": "invalid_identity", "message": "invalid DID in token" })),
)
.into_response();
}
},
None => {
return (
StatusCode::UNAUTHORIZED,
Json(json!({
"error": "invalid_ucan",
"message": "UCAN validation requires a valid HTTP Signature",
})),
)
.into_response()
}
};
if let Err((status, body)) = validate_ucan_chain(&token, &state.node_did, &signer_did) {
return (status, body).into_response();
}
tracing::debug!(did = %signer_did, "UCAN chain validated");
request.extensions_mut().insert(AuthenticatedDid(sig.key_id.to_string()));
next.run(request).await
}
@@ -384,230 +239,3 @@ fn human_detected(message: &str) -> impl IntoResponse {
})),
)
}
#[cfg(test)]
mod tests {
use super::*;
use axum::{middleware, Router};
use gitlawb_core::identity::Keypair;
use gitlawb_core::ucan::{caps, Capability, Ucan};
use std::{path::PathBuf, sync::Arc, time::Duration};
use tower::ServiceExt;
fn bootstrap_ucan(node: &Keypair, agent_did: Did) -> Ucan {
Ucan::bootstrap(node, agent_did).unwrap()
}
fn delegation_ucan(agent: &Keypair, node_did: Did, proof: &Ucan) -> Ucan {
Ucan::delegate(
agent,
node_did,
vec![Capability::new("gitlawb://alpha", caps::NETWORK_JOIN)],
None,
proof,
)
.unwrap()
}
#[test]
fn validate_ucan_chain_valid() {
let node = Keypair::generate();
let agent = Keypair::generate();
let node_did = node.did();
let agent_did = agent.did();
let proof = bootstrap_ucan(&node, agent_did.clone());
let delegation = delegation_ucan(&agent, node_did.clone(), &proof);
let token = delegation.encode().unwrap();
assert!(validate_ucan_chain(&token, &node_did, &agent_did).is_ok());
}
#[test]
fn validate_ucan_chain_wrong_issuer() {
let node = Keypair::generate();
let agent = Keypair::generate();
let other = Keypair::generate();
let node_did = node.did();
let agent_did = agent.did();
let proof = bootstrap_ucan(&node, agent_did.clone());
let delegation = delegation_ucan(&agent, node_did.clone(), &proof);
let token = delegation.encode().unwrap();
// signer_did is `other` but UCAN iss is `agent` — must be rejected
let err = validate_ucan_chain(&token, &node_did, &other.did()).unwrap_err();
assert_eq!(err.0, StatusCode::UNAUTHORIZED);
let body = err.1 .0.to_string();
assert!(body.contains("does not match request signer"));
}
#[test]
fn validate_ucan_chain_wrong_audience() {
let node = Keypair::generate();
let agent = Keypair::generate();
let other_node = Keypair::generate();
let node_did = node.did();
let agent_did = agent.did();
let proof = bootstrap_ucan(&node, agent_did.clone());
let delegation = delegation_ucan(&agent, node_did.clone(), &proof);
let token = delegation.encode().unwrap();
// expected_aud is a different node — must be rejected
let err = validate_ucan_chain(&token, &other_node.did(), &agent_did).unwrap_err();
assert_eq!(err.0, StatusCode::UNAUTHORIZED);
let body = err.1 .0.to_string();
assert!(body.contains("audience mismatch"));
}
#[test]
fn validate_ucan_chain_expired_proof() {
let node = Keypair::generate();
let agent = Keypair::generate();
let node_did = node.did();
let agent_did = agent.did();
let exp = chrono::Utc::now() - chrono::Duration::hours(1);
let proof = Ucan::issue(
&node,
agent_did.clone(),
vec![Capability::new("gitlawb://alpha", caps::NETWORK_JOIN)],
Some(exp),
)
.unwrap();
let delegation = delegation_ucan(&agent, node_did.clone(), &proof);
let token = delegation.encode().unwrap();
let err = validate_ucan_chain(&token, &node_did, &agent_did).unwrap_err();
assert_eq!(err.0, StatusCode::UNAUTHORIZED);
let body = err.1 .0.to_string();
assert!(body.contains("expired"));
}
fn make_test_state(node_did: gitlawb_core::did::Did) -> crate::state::AppState {
use crate::{config::Config, graphql, rate_limit::RateLimiter};
use clap::Parser;
let keypair = Keypair::generate();
let (ref_tx, _) = tokio::sync::broadcast::channel(1);
let (task_tx, _) = tokio::sync::broadcast::channel(1);
let pool = sqlx::postgres::PgPoolOptions::new()
.connect_lazy("postgres://localhost/gitlawb_test_placeholder")
.expect("lazy pool creation should not fail");
let db = Arc::new(crate::db::Db::for_testing(pool.clone()));
let schema = Arc::new(graphql::build_schema(
db.clone(),
ref_tx.clone(),
task_tx.clone(),
));
crate::state::AppState {
config: Arc::new(Config::parse_from(["gitlawb-node"])),
db,
node_did,
node_keypair: Arc::new(keypair),
p2p: None,
http_client: Arc::new(reqwest::Client::new()),
ref_update_tx: ref_tx,
task_event_tx: task_tx,
graphql_schema: schema,
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,
}
}
#[tokio::test]
async fn require_ucan_chain_no_header_passes_through() {
let state = make_test_state(Keypair::generate().did());
let app = Router::new()
.route("/", axum::routing::get(|| async { StatusCode::OK }))
.layer(middleware::from_fn_with_state(state, require_ucan_chain));
let req = Request::builder()
.uri("/")
.body(axum::body::Body::empty())
.unwrap();
let resp = app.oneshot(req).await.unwrap();
assert_eq!(resp.status(), StatusCode::OK);
}
#[tokio::test]
async fn require_ucan_chain_missing_did_returns_401() {
let state = make_test_state(Keypair::generate().did());
let app = Router::new()
.route("/", axum::routing::get(|| async { StatusCode::OK }))
.layer(middleware::from_fn_with_state(state, require_ucan_chain));
// x-ucan present but no AuthenticatedDid extension → 401
let req = Request::builder()
.uri("/")
.header("x-ucan", "any-token")
.body(axum::body::Body::empty())
.unwrap();
let resp = app.oneshot(req).await.unwrap();
assert_eq!(resp.status(), StatusCode::UNAUTHORIZED);
}
#[tokio::test]
async fn require_ucan_chain_wrong_issuer_returns_401() {
let node = Keypair::generate();
let agent = Keypair::generate();
let other = Keypair::generate();
let node_did = node.did();
let agent_did = agent.did();
// Build a valid token where iss = agent, but supply `other` as the signer.
let proof = bootstrap_ucan(&node, agent_did.clone());
let token = delegation_ucan(&agent, node_did.clone(), &proof)
.encode()
.unwrap();
let state = make_test_state(node_did);
let app = Router::new()
.route("/", axum::routing::get(|| async { StatusCode::OK }))
.layer(middleware::from_fn_with_state(state, require_ucan_chain));
// AuthenticatedDid is `other`, UCAN iss is `agent` → issuer mismatch → 401
let req = Request::builder()
.uri("/")
.header("x-ucan", token)
.extension(AuthenticatedDid(other.did().to_string()))
.body(axum::body::Body::empty())
.unwrap();
let resp = app.oneshot(req).await.unwrap();
assert_eq!(resp.status(), StatusCode::UNAUTHORIZED);
}
#[tokio::test]
async fn require_ucan_chain_malformed_token_returns_401() {
let state = make_test_state(Keypair::generate().did());
let app = Router::new()
.route("/", axum::routing::get(|| async { StatusCode::OK }))
.layer(middleware::from_fn_with_state(state, require_ucan_chain));
// Malformed x-ucan (invalid JSON)
let req = Request::builder()
.uri("/")
.header("x-ucan", "invalid-token-structure")
.extension(AuthenticatedDid(Keypair::generate().did().to_string()))
.body(axum::body::Body::empty())
.unwrap();
let resp = app.oneshot(req).await.unwrap();
assert_eq!(resp.status(), StatusCode::UNAUTHORIZED);
let body_bytes = axum::body::to_bytes(resp.into_body(), 2048).await.unwrap();
let body_json: serde_json::Value = serde_json::from_slice(&body_bytes).unwrap();
assert_eq!(body_json["error"], "invalid_ucan");
}
}
-316
View File
@@ -1,316 +0,0 @@
//! Embedded seed list of public Gitlawb network nodes.
//!
//! This module parses `bootstrap-peers.json` (embedded at compile time) and
//! merges its contents into the runtime config so a fresh `docker compose up`
//! joins the network without any manual peer configuration.
//!
//! Operators can opt out by setting `GITLAWB_BOOTSTRAP_DISABLE_SEEDS=true` in
//! their environment — useful for isolated dev networks or testing.
//!
//! Add a node to the canonical list via PR to `bootstrap-peers.json`.
use std::str::FromStr;
use libp2p_core::Multiaddr;
use serde::Deserialize;
use tracing::{info, warn};
use crate::config::Config;
const EMBEDDED_PEERS_JSON: &str = include_str!("../../../bootstrap-peers.json");
const SUPPORTED_VERSION: u32 = 1;
#[derive(Debug, Deserialize)]
struct BootstrapList {
version: u32,
#[serde(default)]
peers: Vec<BootstrapPeer>,
}
#[derive(Debug, Deserialize)]
struct BootstrapPeer {
name: String,
#[allow(dead_code)]
operator: Option<String>,
#[allow(dead_code)]
did: Option<String>,
http_url: Option<String>,
p2p_multiaddr: Option<String>,
#[allow(dead_code)]
added: Option<String>,
}
/// Counts of newly-added entries returned by `merge_into_vecs`.
#[derive(Debug, Default, PartialEq, Eq)]
struct MergeCounts {
http: usize,
p2p: usize,
}
/// Returns true when `GITLAWB_BOOTSTRAP_DISABLE_SEEDS` is set to a truthy value.
fn seeds_disabled() -> bool {
std::env::var("GITLAWB_BOOTSTRAP_DISABLE_SEEDS")
.ok()
.filter(|v| !v.is_empty() && v != "0" && !v.eq_ignore_ascii_case("false"))
.is_some()
}
/// Parse the seed list from a JSON string, rejecting unsupported versions.
fn parse_seed_list(json: &str) -> Result<BootstrapList, String> {
let list: BootstrapList = serde_json::from_str(json).map_err(|e| e.to_string())?;
if list.version != SUPPORTED_VERSION {
return Err(format!(
"unsupported bootstrap-peers.json version: {} (expected {})",
list.version, SUPPORTED_VERSION
));
}
Ok(list)
}
/// Pure merge: appends entries from `list` to the two vectors, deduping.
/// Returns counts of entries actually added (i.e. not already present).
fn merge_into_vecs(
list: BootstrapList,
http_peers: &mut Vec<String>,
p2p_bootstrap: &mut Vec<String>,
) -> MergeCounts {
let mut counts = MergeCounts::default();
for peer in list.peers {
if let Some(url) = peer
.http_url
.as_ref()
.filter(|u| !u.is_empty() && !http_peers.contains(u))
{
http_peers.push(url.clone());
counts.http += 1;
}
if let Some(addr_str) = peer.p2p_multiaddr.as_ref().filter(|s| !s.is_empty()) {
match Multiaddr::from_str(addr_str) {
Ok(_) => {
if !p2p_bootstrap.contains(addr_str) {
p2p_bootstrap.push(addr_str.clone());
counts.p2p += 1;
}
}
Err(e) => warn!(
name = %peer.name,
addr = %addr_str,
err = %e,
"invalid p2p_multiaddr in bootstrap-peers.json — skipping"
),
}
}
}
counts
}
/// Merge the embedded seed list into the runtime config.
///
/// - Appends any `http_url` to `config.bootstrap_peers` (used by gossip_task)
/// - Appends any valid `p2p_multiaddr` to `config.p2p_bootstrap` (used by libp2p)
/// - Dedupes against entries already present (env / CLI takes precedence)
/// - No-op when `GITLAWB_BOOTSTRAP_DISABLE_SEEDS` is set to a truthy value
pub fn merge_seeds(config: &mut Config) {
if seeds_disabled() {
info!("bootstrap seed list disabled via GITLAWB_BOOTSTRAP_DISABLE_SEEDS");
return;
}
let list = match parse_seed_list(EMBEDDED_PEERS_JSON) {
Ok(l) => l,
Err(e) => {
warn!(err = %e, "failed to load embedded bootstrap-peers.json — skipping");
return;
}
};
let counts = merge_into_vecs(list, &mut config.bootstrap_peers, &mut config.p2p_bootstrap);
if counts.http > 0 || counts.p2p > 0 {
info!(
http_peers = counts.http,
p2p_peers = counts.p2p,
"merged bootstrap seed list into config"
);
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn parse_valid_v1_list() {
let json = r#"{
"version": 1,
"updated": "2026-04-29",
"peers": [
{
"name": "alpha",
"operator": "Alice",
"did": "did:key:z6MkAlice",
"http_url": "https://alpha.example.com",
"p2p_multiaddr": "/ip4/1.2.3.4/tcp/7546",
"added": "2026-04-29"
}
]
}"#;
let list = parse_seed_list(json).expect("should parse");
assert_eq!(list.version, 1);
assert_eq!(list.peers.len(), 1);
assert_eq!(list.peers[0].name, "alpha");
}
#[test]
fn parse_rejects_unknown_version() {
let json = r#"{ "version": 99, "peers": [] }"#;
let err = parse_seed_list(json).expect_err("should reject");
assert!(err.contains("unsupported"));
}
#[test]
fn parse_rejects_malformed_json() {
let err = parse_seed_list("{ not json").expect_err("should reject");
assert!(!err.is_empty());
}
#[test]
fn parse_accepts_empty_peers_array() {
let json = r#"{ "version": 1, "peers": [] }"#;
let list = parse_seed_list(json).expect("should parse");
assert!(list.peers.is_empty());
}
#[test]
fn parse_treats_missing_peers_as_empty() {
let json = r#"{ "version": 1 }"#;
let list = parse_seed_list(json).expect("should parse");
assert!(list.peers.is_empty());
}
#[test]
fn merge_appends_new_http_and_p2p() {
let list = parse_seed_list(
r#"{
"version": 1,
"peers": [
{
"name": "alpha",
"http_url": "https://alpha.example.com",
"p2p_multiaddr": "/ip4/1.2.3.4/tcp/7546"
}
]
}"#,
)
.unwrap();
let mut http = Vec::new();
let mut p2p = Vec::new();
let counts = merge_into_vecs(list, &mut http, &mut p2p);
assert_eq!(counts, MergeCounts { http: 1, p2p: 1 });
assert_eq!(http, vec!["https://alpha.example.com"]);
assert_eq!(p2p, vec!["/ip4/1.2.3.4/tcp/7546"]);
}
#[test]
fn merge_dedupes_existing_entries() {
let list = parse_seed_list(
r#"{
"version": 1,
"peers": [
{ "name": "alpha", "http_url": "https://alpha.example.com" }
]
}"#,
)
.unwrap();
let mut http = vec!["https://alpha.example.com".to_string()];
let mut p2p = Vec::new();
let counts = merge_into_vecs(list, &mut http, &mut p2p);
assert_eq!(counts.http, 0, "should not double-add");
assert_eq!(http.len(), 1);
}
#[test]
fn merge_skips_invalid_p2p_multiaddr() {
let list = parse_seed_list(
r#"{
"version": 1,
"peers": [
{
"name": "bad",
"http_url": "https://bad.example.com",
"p2p_multiaddr": "this is not a multiaddr"
}
]
}"#,
)
.unwrap();
let mut http = Vec::new();
let mut p2p = Vec::new();
let counts = merge_into_vecs(list, &mut http, &mut p2p);
assert_eq!(counts.http, 1, "http still added");
assert_eq!(counts.p2p, 0, "invalid p2p skipped");
assert!(p2p.is_empty());
}
#[test]
fn merge_skips_empty_strings() {
let list = parse_seed_list(
r#"{
"version": 1,
"peers": [
{ "name": "blank", "http_url": "", "p2p_multiaddr": "" }
]
}"#,
)
.unwrap();
let mut http = Vec::new();
let mut p2p = Vec::new();
let counts = merge_into_vecs(list, &mut http, &mut p2p);
assert_eq!(counts, MergeCounts::default());
}
#[test]
fn merge_handles_null_optional_fields() {
let list = parse_seed_list(
r#"{
"version": 1,
"peers": [
{
"name": "alpha",
"operator": null,
"did": null,
"http_url": "https://alpha.example.com",
"p2p_multiaddr": null,
"added": null
}
]
}"#,
)
.unwrap();
let mut http = Vec::new();
let mut p2p = Vec::new();
let counts = merge_into_vecs(list, &mut http, &mut p2p);
assert_eq!(counts, MergeCounts { http: 1, p2p: 0 });
}
#[test]
fn embedded_seed_list_parses_successfully() {
// Regression: the canonical bootstrap-peers.json shipped in the repo
// must always be valid, since it's compiled into the binary.
parse_seed_list(EMBEDDED_PEERS_JSON)
.expect("embedded bootstrap-peers.json must always parse");
}
}
+7 -8
View File
@@ -41,18 +41,17 @@ pub async fn issue_ref_certificate(
let signature = state.node_keypair.sign_b64(&payload_bytes);
let cert = RefCertificate {
id: Uuid::new_v4().to_string(),
repo_id: repo_id.to_string(),
ref_name: ref_name.to_string(),
old_sha: old_sha.to_string(),
new_sha: new_sha.to_string(),
id: Uuid::new_v4().to_string(),
repo_id: repo_id.to_string(),
ref_name: ref_name.to_string(),
old_sha: old_sha.to_string(),
new_sha: new_sha.to_string(),
pusher_did: pusher_did.to_string(),
node_did,
signature,
issued_at,
};
// 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
state.db.insert_ref_certificate(&cert).await?;
Ok(cert)
}
+7 -153
View File
@@ -1,5 +1,5 @@
use clap::Parser;
use std::path::PathBuf;
use clap::Parser;
#[derive(Parser, Debug, Clone)]
#[command(name = "gitlawb-node", about = "gitlawb node daemon", version)]
@@ -9,11 +9,7 @@ pub struct Config {
pub repos_dir: PathBuf,
/// PostgreSQL connection URL (Supabase or any Postgres instance)
#[arg(
long,
env = "DATABASE_URL",
default_value = "postgresql://localhost/gitlawb"
)]
#[arg(long, env = "DATABASE_URL", default_value = "postgresql://localhost/gitlawb")]
pub database_url: String,
/// Host to bind to
@@ -28,7 +24,7 @@ pub struct Config {
#[arg(long, env = "GITLAWB_KEY", default_value = "~/.gitlawb/identity.pem")]
pub key_path: String,
/// Reserved for private-read mode; per-repo read enforcement is not wired in alpha
/// Allow unauthenticated reads (default: true for public repos)
#[arg(long, env = "GITLAWB_PUBLIC_READ", default_value_t = true)]
pub public_read: bool,
@@ -40,23 +36,6 @@ pub struct Config {
#[arg(long, env = "GITLAWB_BOOTSTRAP_PEERS", value_delimiter = ',')]
pub bootstrap_peers: Vec<String>,
/// Require RFC 9421 signatures on peer announce/sync write routes.
/// Keep false during rolling upgrades so existing live nodes can still gossip.
#[arg(
long,
env = "GITLAWB_REQUIRE_SIGNED_PEER_WRITES",
default_value_t = false
)]
pub require_signed_peer_writes: bool,
/// Require the authenticated pusher to be the repo owner on `git-receive-pack`.
/// Authentication (a valid did:key signature) is not authorization on its own:
/// any party can sign as their own DID. When true, pushes whose authenticated
/// DID is not the repo owner are rejected. Keep false during rolling upgrades;
/// flip it on once owners are ready for owner-only writes.
#[arg(long, env = "GITLAWB_ENFORCE_OWNER_PUSH", default_value_t = false)]
pub enforce_owner_push: bool,
/// URL of local IPFS/Kubo node HTTP API (e.g. http://127.0.0.1:5001)
#[arg(long, env = "GITLAWB_IPFS_API", default_value = "")]
pub ipfs_api: String,
@@ -66,19 +45,15 @@ pub struct Config {
pub pinata_jwt: String,
/// Pinata v3 upload URL
#[arg(
long,
env = "GITLAWB_PINATA_UPLOAD_URL",
default_value = "https://uploads.pinata.cloud/v3/files"
)]
#[arg(long, env = "GITLAWB_PINATA_UPLOAD_URL", default_value = "https://uploads.pinata.cloud/v3/files")]
pub pinata_upload_url: String,
/// libp2p QUIC/UDP port (0 = disabled)
/// libp2p TCP port (0 = disabled)
#[arg(long, env = "GITLAWB_P2P_PORT", default_value_t = 7546)]
pub p2p_port: u16,
/// libp2p bootstrap multiaddrs (comma-separated)
/// Example: /ip4/1.2.3.4/udp/7546/quic-v1/p2p/12D3KooW...
/// Example: /ip4/1.2.3.4/tcp/7546/p2p/12D3KooW...
#[arg(long, env = "GITLAWB_P2P_BOOTSTRAP", value_delimiter = ',')]
pub p2p_bootstrap: Vec<String>,
@@ -100,11 +75,7 @@ pub struct Config {
pub contract_name_registry: String,
/// Base L2 RPC URL
#[arg(
long,
env = "GITLAWB_CHAIN_RPC_URL",
default_value = "https://sepolia.base.org"
)]
#[arg(long, env = "GITLAWB_CHAIN_RPC_URL", default_value = "https://sepolia.base.org")]
pub chain_rpc_url: String,
/// Base L2 node staking contract address (GitlawbNodeStaking). When set
@@ -139,101 +110,6 @@ pub struct Config {
/// Default: 2 GB. Set lower on resource-constrained nodes.
#[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
/// unauthenticated.
#[arg(long, env = "GITLAWB_METRICS_ADDR", default_value = "")]
pub metrics_addr: String,
/// Maximum time to wait for in-flight requests to drain on shutdown, in
/// seconds. After this elapses, the server returns 503 to anything still
/// 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 {
@@ -251,25 +127,3 @@ 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()
);
}
}
File diff suppressed because it is too large. Load diff
-362
View File
@@ -1,362 +0,0 @@
//! Encrypt-then-pin for withheld blobs (Option B1). Each withheld blob is sealed
//! to its recipient DIDs and the envelope pinned to IPFS, recorded in
//! `encrypted_blobs`. Best-effort per blob: a failure is logged and skipped,
//! never pinned in plaintext.
use std::collections::{BTreeSet, HashMap};
use std::path::Path;
use std::str::FromStr;
use ed25519_dalek::VerifyingKey;
use gitlawb_core::did::Did;
use gitlawb_core::encrypt::seal_blob;
use crate::db::Db;
use hmac::{Hmac, Mac};
use sha2::Sha256;
type HmacSha256 = Hmac<Sha256>;
/// Opaque, node-keyed fingerprint of a blob's recipient set. Stored in place of
/// the cleartext DID list so a DB compromise cannot reveal the reader set; used
/// only to detect a recipient-set change so an unchanged blob is not re-sealed.
/// Order-insensitive (the input `BTreeSet` is already sorted).
pub fn recipients_tag(node_seed: &[u8; 32], dids: &BTreeSet<String>) -> String {
let mut mac = HmacSha256::new_from_slice(node_seed).expect("HMAC accepts any key length");
mac.update(b"gitlawb/recipients-tag/v1");
for did in dids {
mac.update(b"\n");
mac.update(did.as_bytes());
}
hex::encode(mac.finalize().into_bytes())
}
/// Resolve a DID string to its Ed25519 verifying key, or None if it carries no
/// inline key (e.g. did:web / did:gitlawb).
fn did_to_key(did: &str) -> Option<VerifyingKey> {
Did::from_str(did).ok()?.to_verifying_key().ok()
}
/// Resolve every recipient DID to its verifying key, all-or-nothing.
///
/// Returns `Ok(keys)` only when every DID resolves. If any DID fails, returns
/// `Err(unresolved)` listing the unresolvable DID strings so the caller can fail
/// closed rather than seal to a partial recipient set (#47): sealing to a subset
/// while recording the full set as covered permanently locks out the dropped
/// readers. Resolution is local-only, so `did:web`/`did:gitlawb` recipients (and
/// any malformed `did:key`) land in the unresolved set until off-`did:key`
/// resolution exists.
fn resolve_all_recipients(dids: &BTreeSet<String>) -> Result<Vec<VerifyingKey>, Vec<String>> {
let mut keys = Vec::with_capacity(dids.len());
let mut unresolved = Vec::new();
for did in dids {
match did_to_key(did) {
Some(k) => keys.push(k),
None => unresolved.push(did.clone()),
}
}
if unresolved.is_empty() {
Ok(keys)
} else {
Err(unresolved)
}
}
/// What to do with a single withheld blob, decided without any DB or IO so the
/// fail-closed invariant (#47) is unit-testable in isolation.
#[derive(Debug)]
enum SealPlan {
/// An existing envelope already covers exactly this recipient set; nothing to do.
SkipUnchanged,
/// No recipient DID resolved to a key, so there is nothing to seal to.
SkipNoRecipients,
/// At least one recipient DID is unresolvable. Fail closed: never seal to a
/// partial set. Carries the unresolvable DIDs for logging.
SkipUnresolvable(Vec<String>),
/// Seal to `keys` and record coverage under `tag`.
Seal {
keys: Vec<VerifyingKey>,
tag: String,
},
}
/// Decide what to do with one blob given its desired recipient set and the tag
/// already stored for it (if any). Pure: no DB, no IO.
///
/// This is the #47 fail-closed gate in isolation: it returns `Seal` only when
/// EVERY recipient DID resolves, so no caller can seal to a partial set. A
/// changed recipient set (different tag) re-seals so a newly added reader can
/// recover the blob; reader removal is not retroactive (the old envelope is
/// already public). The comparison is on the opaque node-keyed tag, never the
/// DID list.
fn plan_seal(node_seed: &[u8; 32], dids: &BTreeSet<String>, stored_tag: Option<&str>) -> SealPlan {
let tag = recipients_tag(node_seed, dids);
if stored_tag == Some(tag.as_str()) {
return SealPlan::SkipUnchanged;
}
match resolve_all_recipients(dids) {
Ok(keys) if keys.is_empty() => SealPlan::SkipNoRecipients,
Ok(keys) => SealPlan::Seal { keys, tag },
Err(unresolved) => SealPlan::SkipUnresolvable(unresolved),
}
}
/// Encrypt and pin every withheld blob. `recipients` maps blob oid -> DID set;
/// `node_seed` keys the opaque recipients tag. Returns `(oid, cid)` for each blob
/// actually sealed and recorded this call (the per-push delta), used by Option B3
/// to anchor a manifest. Recipient identities are never stored or returned.
pub async fn encrypt_and_pin(
ipfs_api: &str,
repo_path: &Path,
db: &Db,
repo_id: &str,
node_seed: &[u8; 32],
recipients: &HashMap<String, BTreeSet<String>>,
) -> Vec<(String, String)> {
let mut sealed = Vec::new();
let mut skipped_unresolvable = 0usize;
for (oid, dids) in recipients {
// A DB read failure is not a cache miss: re-sealing here would do an
// avoidable IPFS write during a partial outage. Skip and retry next push.
let stored_tag = match db.encrypted_blob_recipients_tag(repo_id, oid).await {
Ok(t) => t,
Err(e) => {
tracing::warn!(oid = %oid, err = %e, "recipients_tag lookup failed; skipping reseal");
continue;
}
};
// Fail closed: plan_seal returns Seal only when every recipient DID
// resolves, so we never seal to a partial set and record the full set as
// covered (which would permanently lock out the dropped readers, #47).
let (keys, tag) = match plan_seal(node_seed, dids, stored_tag.as_deref()) {
SealPlan::SkipUnchanged => continue,
SealPlan::SkipNoRecipients => {
tracing::warn!(oid = %oid, "no resolvable recipient keys; skipping encrypted pin");
continue;
}
SealPlan::SkipUnresolvable(unresolved) => {
skipped_unresolvable += 1;
// DIDs are user-controlled (rule reader_dids); log a bounded
// sample, not an unbounded dump. Wording stays neutral about the
// cause: a malformed did:key is not DHT-pending and never will
// resolve, unlike a did:gitlawb awaiting anchoring.
let sample: Vec<&String> = unresolved.iter().take(3).collect();
tracing::warn!(
oid = %oid,
unresolved_count = unresolved.len(),
unresolved_sample = ?sample,
"unresolvable recipient DID(s); skipping encrypted pin to avoid sealing to a partial set"
);
continue;
}
SealPlan::Seal { keys, tag } => (keys, tag),
};
let data = match crate::git::store::read_object(repo_path, oid) {
Ok(Some((_t, bytes))) => bytes,
Ok(None) => {
tracing::warn!(oid = %oid, "git object not found; skipping encrypted pin");
continue;
}
Err(e) => {
tracing::warn!(oid = %oid, err = %e, "read_object failed; skipping encrypted pin");
continue;
}
};
let envelope = match seal_blob(&data, &keys) {
Ok(e) => e,
Err(e) => {
tracing::warn!(oid = %oid, err = %e, "seal_blob failed; skipping");
continue;
}
};
let cid = match crate::ipfs_pin::pin_git_object(ipfs_api, oid, &envelope).await {
Ok(c) if !c.is_empty() => c,
Ok(_) => {
tracing::warn!(oid = %oid, "pin_git_object returned no cid; skipping");
continue;
}
Err(e) => {
tracing::warn!(oid = %oid, err = %e, "pin_git_object failed; skipping");
continue;
}
};
if let Err(e) = db.record_encrypted_blob(repo_id, oid, &cid, &tag).await {
tracing::warn!(oid = %oid, err = %e, "record_encrypted_blob failed");
continue;
}
sealed.push((oid.clone(), cid.clone()));
}
// One aggregate signal so a coverage collapse is a single greppable line, not
// a per-oid scrape. In a fully-migrated did:gitlawb org every blob skips and
// recovery coverage silently drops to zero; this is the operator's cue that
// the gap is the deliberate fail-closed posture, not a malfunction.
if skipped_unresolvable > 0 {
tracing::warn!(
sealed = sealed.len(),
skipped = skipped_unresolvable,
"encrypted-pin coverage reduced: blobs skipped for unresolvable recipients"
);
}
sealed
}
#[cfg(test)]
mod tests {
use super::*;
use ed25519_dalek::SigningKey;
fn did_key(seed: u8) -> String {
let vk = SigningKey::from_bytes(&[seed; 32]).verifying_key();
Did::from_verifying_key(&vk).to_string()
}
// Accepts both `&[String]` (resolve tests, built from `did_key`) and
// `&[&str]` (tag tests, built from literals).
fn set<S: AsRef<str>>(dids: &[S]) -> BTreeSet<String> {
dids.iter().map(|s| s.as_ref().to_string()).collect()
}
#[test]
fn all_did_key_recipients_resolve() {
let dids = set(&[did_key(1), did_key(2)]);
let keys = resolve_all_recipients(&dids).expect("all did:key resolve");
assert_eq!(keys.len(), 2);
}
#[test]
fn mixed_set_with_did_gitlawb_fails_closed() {
// Core #47 regression: a resolvable subset must never yield a sealable
// key set. Two did:key plus one did:gitlawb -> Err naming only the
// unresolvable DID.
let gitlawb = Did::gitlawb("zSomeDhtKey").to_string();
let dids = set(&[did_key(1), did_key(2), gitlawb.clone()]);
let unresolved = resolve_all_recipients(&dids).expect_err("must fail closed");
assert_eq!(unresolved, vec![gitlawb]);
}
#[test]
fn did_web_recipient_fails_closed() {
let web = Did::web("example.com").to_string();
let dids = set(&[did_key(1), web.clone()]);
let unresolved = resolve_all_recipients(&dids).expect_err("did:web cannot resolve locally");
assert_eq!(unresolved, vec![web]);
}
#[test]
fn malformed_did_key_fails_closed() {
// The third state: not a method-resolution gap but a permanently broken
// did:key (invalid multibase). Must also fail closed.
let broken = "did:key:z!!!invalid".to_string();
let dids = set(&[did_key(1), broken.clone()]);
let unresolved = resolve_all_recipients(&dids).expect_err("malformed did:key fails");
assert_eq!(unresolved, vec![broken]);
}
#[test]
fn empty_set_resolves_to_empty_keys() {
let dids = BTreeSet::new();
let keys = resolve_all_recipients(&dids).expect("empty set is not an error");
assert!(keys.is_empty());
}
#[test]
fn single_unresolvable_did_returns_that_did() {
let gitlawb = Did::gitlawb("zOnlyOne").to_string();
let dids: BTreeSet<String> = [gitlawb.clone()].into_iter().collect();
let unresolved = resolve_all_recipients(&dids).expect_err("must fail closed");
assert_eq!(unresolved, vec![gitlawb]);
}
#[test]
fn tag_is_order_insensitive() {
let seed = [7u8; 32];
let a = recipients_tag(&seed, &set(&["did:key:zA", "did:key:zB"]));
let b = recipients_tag(&seed, &set(&["did:key:zB", "did:key:zA"]));
assert_eq!(a, b);
}
#[test]
fn tag_differs_for_different_sets() {
let seed = [7u8; 32];
let a = recipients_tag(&seed, &set(&["did:key:zA"]));
let b = recipients_tag(&seed, &set(&["did:key:zA", "did:key:zB"]));
assert_ne!(a, b);
}
#[test]
fn tag_is_keyed_by_node_seed() {
let dids = set(&["did:key:zA", "did:key:zB"]);
let a = recipients_tag(&[1u8; 32], &dids);
let b = recipients_tag(&[2u8; 32], &dids);
assert_ne!(
a, b,
"tag must depend on the node seed, not be a plain hash"
);
}
// plan_seal is the seal/skip decision `encrypt_and_pin` acts on. Testing it
// directly pins the #47 fail-closed invariant at the function that owns it,
// which a unit test of `resolve_all_recipients` alone cannot do (it can't
// catch the caller falling through to a partial seal).
const SEED: [u8; 32] = [9u8; 32];
#[test]
fn plan_seal_seals_when_all_recipients_resolve() {
let dids = set(&[did_key(1), did_key(2)]);
match plan_seal(&SEED, &dids, None) {
SealPlan::Seal { keys, tag } => {
assert_eq!(keys.len(), 2, "must seal to the full recipient set");
assert_eq!(
tag,
recipients_tag(&SEED, &dids),
"records the full-set tag"
);
}
other => panic!("expected Seal, got {other:?}"),
}
}
#[test]
fn plan_seal_fails_closed_on_any_unresolvable_recipient() {
// The #47 invariant at the decision boundary: one unresolvable DID among
// resolvable ones must NOT yield a Seal (which would seal a partial set).
let gitlawb = Did::gitlawb("zPending").to_string();
let dids = set(&[did_key(1), did_key(2), gitlawb.clone()]);
match plan_seal(&SEED, &dids, None) {
SealPlan::SkipUnresolvable(unresolved) => assert_eq!(unresolved, vec![gitlawb]),
other => panic!("must fail closed, never seal a partial set; got {other:?}"),
}
}
#[test]
fn plan_seal_skips_empty_recipient_set() {
let dids = BTreeSet::new();
assert!(matches!(
plan_seal(&SEED, &dids, None),
SealPlan::SkipNoRecipients
));
}
#[test]
fn plan_seal_skips_when_tag_unchanged() {
let dids = set(&[did_key(1)]);
let stored = recipients_tag(&SEED, &dids);
assert!(matches!(
plan_seal(&SEED, &dids, Some(&stored)),
SealPlan::SkipUnchanged
));
}
#[test]
fn plan_seal_reseals_when_recipient_set_changed() {
// A stored tag for a DIFFERENT set is a miss: a newly added reader must
// trigger a re-seal, not be skipped as unchanged.
let dids = set(&[did_key(1), did_key(2)]);
let stale = recipients_tag(&SEED, &set(&[did_key(1)]));
match plan_seal(&SEED, &dids, Some(&stale)) {
SealPlan::Seal { keys, .. } => assert_eq!(keys.len(), 2),
other => panic!("changed recipient set must re-seal; got {other:?}"),
}
}
}
+30 -117
View File
@@ -23,98 +23,21 @@ pub enum AppError {
#[allow(dead_code)]
Forbidden(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(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),
}
}
Internal(#[from] anyhow::Error),
}
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,
@@ -126,28 +49,36 @@ impl IntoResponse for AppError {
"repo_exists",
format!("repository '{r}' already exists"),
),
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()),
// 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::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(),
),
AppError::BadRequest(msg) => (
StatusCode::BAD_REQUEST,
"bad_request",
msg.clone(),
),
AppError::Git(msg) => (
StatusCode::INTERNAL_SERVER_ERROR,
"git_error",
msg.clone(),
),
AppError::Db(e) => (
StatusCode::INTERNAL_SERVER_ERROR,
"db_error",
e.to_string(),
),
AppError::Db(e) => (StatusCode::INTERNAL_SERVER_ERROR, "db_error", e.to_string()),
AppError::Internal(e) => (
StatusCode::INTERNAL_SERVER_ERROR,
"internal_error",
@@ -165,21 +96,3 @@ 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
);
}
}
+27 -51
View File
@@ -23,26 +23,19 @@ pub fn create_issue(repo_path: &Path, issue_id: &str, json: &str) -> Result<()>
use std::io::Write;
let mut child = hash_output;
// Write the blob to stdin, but always reap the child afterward even if the
// write fails, so a stdin-write error can't drop the Child unwaited and leak
// a zombie (#53).
let write_result = match child.stdin.take() {
Some(mut stdin) => stdin.write_all(json.as_bytes()),
None => Err(std::io::Error::new(
std::io::ErrorKind::BrokenPipe,
"git hash-object stdin unavailable",
)),
};
if let Some(stdin) = child.stdin.take() {
let mut stdin = stdin;
stdin.write_all(json.as_bytes()).context("failed to write to git hash-object stdin")?;
}
let output = child.wait_with_output().context("git hash-object failed")?;
write_result.context("failed to write to git hash-object stdin")?;
if !output.status.success() {
let stderr = String::from_utf8_lossy(&output.stderr);
anyhow::bail!("git hash-object failed: {stderr}");
}
let hash =
String::from_utf8(output.stdout).context("git hash-object output is not valid UTF-8")?;
let hash = String::from_utf8(output.stdout)
.context("git hash-object output is not valid UTF-8")?;
let hash = hash.trim();
// Update the ref
@@ -65,11 +58,7 @@ pub fn create_issue(repo_path: &Path, issue_id: &str, json: &str) -> Result<()>
pub fn list_issues(repo_path: &Path) -> Result<Vec<String>> {
// List all refs under refs/gitlawb/issues/
let list_output = Command::new("git")
.args([
"for-each-ref",
"--format=%(refname)",
"refs/gitlawb/issues/",
])
.args(["for-each-ref", "--format=%(refname)", "refs/gitlawb/issues/"])
.current_dir(repo_path)
.output()
.context("failed to run git for-each-ref")?;
@@ -132,7 +121,10 @@ pub fn resolve_issue_id(repo_path: &Path, id_or_prefix: &str) -> Result<Option<S
}
let output = String::from_utf8_lossy(&list.stdout);
let matches: Vec<&str> = output.lines().filter(|l| !l.trim().is_empty()).collect();
let matches: Vec<&str> = output
.lines()
.filter(|l| !l.trim().is_empty())
.collect();
match matches.len() {
0 => Ok(None),
@@ -164,8 +156,8 @@ pub fn close_issue(repo_path: &Path, issue_id: &str) -> Result<Option<String>> {
let raw = get_issue(repo_path, &full_id)?
.expect("ref existed in resolve but not in get — should be impossible");
let mut issue: serde_json::Value =
serde_json::from_str(&raw).context("invalid issue JSON in git ref")?;
let mut issue: serde_json::Value = serde_json::from_str(&raw)
.context("invalid issue JSON in git ref")?;
issue["status"] = serde_json::Value::String("closed".to_string());
let updated = serde_json::to_string(&issue).context("failed to serialize updated issue")?;
@@ -201,6 +193,15 @@ mod tests {
use std::process::Command;
use tempfile::TempDir;
fn init_bare_repo(dir: &TempDir) {
Command::new("git")
.args(["init", "--bare"])
.current_dir(dir.path())
.output()
.unwrap();
// git hash-object -w needs a non-bare repo; use a working repo instead
}
fn init_repo(dir: &TempDir) {
Command::new("git")
.args(["init"])
@@ -224,12 +225,7 @@ mod tests {
let dir = TempDir::new().unwrap();
init_repo(&dir);
let full_id = "abc12345-0000-0000-0000-000000000000";
create_issue(
dir.path(),
full_id,
r#"{"id":"abc12345-0000-0000-0000-000000000000","status":"open"}"#,
)
.unwrap();
create_issue(dir.path(), full_id, r#"{"id":"abc12345-0000-0000-0000-000000000000","status":"open"}"#).unwrap();
let resolved = resolve_issue_id(dir.path(), full_id).unwrap();
assert_eq!(resolved, Some(full_id.to_string()));
}
@@ -239,12 +235,7 @@ mod tests {
let dir = TempDir::new().unwrap();
init_repo(&dir);
let full_id = "abc12345-0000-0000-0000-000000000000";
create_issue(
dir.path(),
full_id,
r#"{"id":"abc12345-0000-0000-0000-000000000000","status":"open"}"#,
)
.unwrap();
create_issue(dir.path(), full_id, r#"{"id":"abc12345-0000-0000-0000-000000000000","status":"open"}"#).unwrap();
let resolved = resolve_issue_id(dir.path(), "abc12345").unwrap();
assert_eq!(resolved, Some(full_id.to_string()));
}
@@ -261,18 +252,8 @@ mod tests {
fn test_resolve_ambiguous_prefix_errors() {
let dir = TempDir::new().unwrap();
init_repo(&dir);
create_issue(
dir.path(),
"abc12345-aaaa-0000-0000-000000000000",
r#"{"status":"open"}"#,
)
.unwrap();
create_issue(
dir.path(),
"abc12345-bbbb-0000-0000-000000000000",
r#"{"status":"open"}"#,
)
.unwrap();
create_issue(dir.path(), "abc12345-aaaa-0000-0000-000000000000", r#"{"status":"open"}"#).unwrap();
create_issue(dir.path(), "abc12345-bbbb-0000-0000-000000000000", r#"{"status":"open"}"#).unwrap();
let result = resolve_issue_id(dir.path(), "abc12345");
assert!(result.is_err());
assert!(result.unwrap_err().to_string().contains("ambiguous"));
@@ -283,12 +264,7 @@ mod tests {
let dir = TempDir::new().unwrap();
init_repo(&dir);
let full_id = "def99999-0000-0000-0000-000000000000";
create_issue(
dir.path(),
full_id,
r#"{"id":"def99999-0000-0000-0000-000000000000","status":"open"}"#,
)
.unwrap();
create_issue(dir.path(), full_id, r#"{"id":"def99999-0000-0000-0000-000000000000","status":"open"}"#).unwrap();
let updated = close_issue(dir.path(), "def99999").unwrap().unwrap();
let v: serde_json::Value = serde_json::from_str(&updated).unwrap();
+3 -5
View File
@@ -1,7 +1,5 @@
pub mod issues;
pub mod push_delta;
pub mod repo_store;
pub mod smart_http;
pub mod store;
pub mod smart_http;
pub mod issues;
pub mod tigris;
pub mod visibility_pack;
pub mod repo_store;
-663
View File
@@ -1,663 +0,0 @@
//! Push-delta object enumeration for the IPFS/Pinata pin path.
//!
//! The pin path needs the set of git objects to consider for pinning after a
//! push. Historically both pin functions enumerated the *whole* repo
//! (`git cat-file --batch-all-objects`) on every push, so cost scaled with
//! repo size rather than push size (finding N16). This module computes the
//! per-push *delta* instead — the objects a push introduced — and keeps the
//! whole-repo lister for the reconciliation sweep and the fail-closed fallback.
//!
//! ## Correctness framing (do not confuse with the #84 withholding direction)
//!
//! The pin enumeration is part of the *exposure* set, not the withheld filter.
//! On the *delta* path, narrowing per push only *shrinks* what is pinned, so it
//! cannot create an under-withholding leak — the reachable-only withheld filter
//! (`visibility_pack`) still subtracts from the smaller set we feed it. The only
//! risk there is *under-pinning* (a durability gap) the sweep backstops.
//!
//! The *full-scan* path is different: `list_all_objects` includes dangling
//! objects the reachable withheld set never classified, so subtracting that set
//! is not enough — a dangling private blob would slip through (#99). The caller
//! signals a full scan via [`PinCandidateSet::full_scan`] and must then apply
//! the fail-closed blob filter (`visibility_pack::replicable_objects_fail_closed`)
//! instead of the plain reachable-only subtraction.
//!
//! Because the pin candidate set needs only the OID *set* (never the per-path
//! information the withheld classifier needs), `git rev-list --objects
//! --no-object-names` is safe here. The "rev-list reports one path per object"
//! trap from #84 applies only to `visibility_pack`'s per-path `ls-tree` walk.
use std::collections::HashSet;
use std::path::{Path, PathBuf};
use std::process::Command;
use anyhow::{bail, Context, Result};
/// Env var that forces the push path to always full-scan, bypassing the delta
/// optimization (KTD7 kill-switch). Reuses the already-tested fallback branch
/// rather than introducing a second enumeration path. Does not gate the sweep.
const FORCE_FULL_SCAN_ENV: &str = "GITLAWB_PIN_FORCE_FULLSCAN";
/// The objects a push introduced, or a signal that the delta could not be
/// computed safely and the caller should fall back to a full scan.
///
/// Three-valued by design: `Delta(vec![])` (a no-op push — pin nothing) is a
/// *different* fact from `FullScanRequired` (could not compute — fall back),
/// and they drive different actions.
#[derive(Debug, Clone, PartialEq, Eq)]
pub enum PinCandidates {
/// Objects reachable from the new tips but not the old tips.
Delta(Vec<String>),
/// The delta is not safe to use; the caller must enumerate the whole repo
/// with [`list_all_objects`] instead. Returned on a non-commit tip, any git
/// error, or the force-full-scan kill-switch.
FullScanRequired,
}
/// Resolve the set of objects introduced by a push from its ref updates.
///
/// `new_tips` / `old_tips` are the non-zero new/old SHAs of the push's ref
/// updates (the caller strips the all-zeros create/delete sentinel). Keeping
/// the helper on plain SHA slices (not the `api` `RefUpdate` type) keeps it
/// unit-testable without the HTTP layer.
///
/// Fail-closed: any condition where the introduced set cannot be safely
/// determined returns [`PinCandidates::FullScanRequired`] rather than a partial
/// set, so the caller full-scans instead of silently under-pinning.
pub fn resolve_push_delta(repo_path: &Path, new_tips: &[&str], old_tips: &[&str]) -> PinCandidates {
// KTD7 kill-switch: force the (already-tested) full-scan fallback. The env
// read is split out from the pure logic so the resolver stays unit-testable
// without touching process-global state.
resolve_push_delta_inner(repo_path, new_tips, old_tips, force_full_scan())
}
/// Whether the force-full-scan kill-switch env var is set.
fn force_full_scan() -> bool {
std::env::var_os(FORCE_FULL_SCAN_ENV).is_some()
}
// Intentionally private but reachable from the test module (via `use super::*`)
// so the kill-switch can be exercised without mutating process-global env.
fn resolve_push_delta_inner(
repo_path: &Path,
new_tips: &[&str],
old_tips: &[&str],
force_full_scan: bool,
) -> PinCandidates {
if force_full_scan {
tracing::debug!("{FORCE_FULL_SCAN_ENV} set — forcing full scan");
return PinCandidates::FullScanRequired;
}
// A push that only deleted refs introduces no objects.
if new_tips.is_empty() {
return PinCandidates::Delta(Vec::new());
}
// Ref-type guard (the fail-closed mechanism). `git rev-list` does NOT error
// on a non-commit tip — a blob/tree/tag-of-non-commit all exit 0 and walk
// the object — so the rev-list exit code cannot catch this. Check each new
// tip's *fully-peeled* type with `cat-file -t '<sha>^{}'` (recursive peel:
// tag-of-commit -> commit, tag-of-tree -> tree, tag-of-tag-of-commit ->
// commit). Bare `cat-file -t` returns `tag` for an annotated tag, and
// `for-each-ref %(*objecttype)` peels only one level — neither is correct.
for tip in new_tips {
match peeled_object_type(repo_path, tip) {
Some(t) if t == "commit" => {}
other => {
tracing::debug!(
tip = %tip,
peeled_type = ?other,
"push tip is not a commit (or type lookup failed) — forcing full scan"
);
return PinCandidates::FullScanRequired;
}
}
}
match rev_list_delta(repo_path, new_tips, old_tips) {
Ok(oids) => PinCandidates::Delta(oids),
Err(e) => {
tracing::debug!(err = %e, "push-delta rev-list failed — forcing full scan");
PinCandidates::FullScanRequired
}
}
}
/// Return the fully-peeled object type of `sha` (e.g. `commit`, `tree`,
/// `blob`), or `None` if the object is missing/unpeelable or git errored.
fn peeled_object_type(repo_path: &Path, sha: &str) -> Option<String> {
let output = Command::new("git")
.args(["cat-file", "-t", &format!("{sha}^{{}}")])
.current_dir(repo_path)
.output()
.ok()?;
if !output.status.success() {
return None;
}
Some(String::from_utf8_lossy(&output.stdout).trim().to_string())
}
/// Run `git rev-list --objects --no-object-names <new> --not <old>` and return
/// the bare OID set. Decides on `status.success()` *before* parsing stdout, so
/// a walk that prints a valid prefix then errors mid-walk is discarded.
fn rev_list_delta(repo_path: &Path, new_tips: &[&str], old_tips: &[&str]) -> Result<Vec<String>> {
let mut args: Vec<&str> = vec!["rev-list", "--objects", "--no-object-names"];
args.extend_from_slice(new_tips);
if !old_tips.is_empty() {
args.push("--not");
args.extend_from_slice(old_tips);
}
let output = Command::new("git")
.args(&args)
.current_dir(repo_path)
.output()
.context("failed to run git rev-list for push delta")?;
if !output.status.success() {
let stderr = String::from_utf8_lossy(&output.stderr);
bail!("git rev-list failed: {stderr}");
}
let stdout = String::from_utf8_lossy(&output.stdout);
Ok(stdout
.lines()
.map(|l| l.trim().to_string())
.filter(|l| !l.is_empty())
.collect())
}
/// List every object in the repository via
/// `git cat-file --batch-all-objects --batch-check='%(objectname)'`.
///
/// This is the whole-repo enumeration the push path falls back to and the
/// reconciliation sweep relies on. It returns *all* objects (including
/// unreachable/dangling ones), which is what the sweep needs to catch
/// stragglers — do not swap it for a reachability walk.
pub fn list_all_objects(repo_path: &Path) -> Result<Vec<String>> {
let output = Command::new("git")
.args([
"cat-file",
"--batch-all-objects",
"--batch-check=%(objectname)",
])
.current_dir(repo_path)
.output()
.context("failed to run git cat-file")?;
if !output.status.success() {
let stderr = String::from_utf8_lossy(&output.stderr);
bail!("git cat-file failed: {stderr}");
}
let stdout = String::from_utf8_lossy(&output.stdout);
Ok(stdout
.lines()
.map(|l| l.trim().to_string())
.filter(|l| !l.is_empty())
.collect())
}
/// Like [`list_all_objects`] but pairs each OID with its object type, via
/// `--batch-check='%(objectname) %(objecttype)'`. The pin path's fail-closed
/// filter needs to tell blobs (content, withholdable) from commits/trees
/// (structural, never withheld) without typing the candidate list itself.
pub fn list_all_objects_with_type(repo_path: &Path) -> Result<Vec<(String, String)>> {
let output = Command::new("git")
.args([
"cat-file",
"--batch-all-objects",
"--batch-check=%(objectname) %(objecttype)",
])
.current_dir(repo_path)
.output()
.context("failed to run git cat-file")?;
if !output.status.success() {
let stderr = String::from_utf8_lossy(&output.stderr);
bail!("git cat-file failed: {stderr}");
}
let stdout = String::from_utf8_lossy(&output.stdout);
Ok(stdout
.lines()
.filter_map(|l| {
let mut it = l.split_whitespace();
let oid = it.next()?;
let ty = it.next()?;
Some((oid.to_string(), ty.to_string()))
})
.collect())
}
/// Every blob OID in the repo, including unreachable/dangling ones. The
/// fail-closed pin filter drops any candidate blob absent from the reachable,
/// visibility-allowed set; a dangling private blob is in this set but not the
/// allowed set, so it never replicates (#99).
pub fn all_blob_oids(repo_path: &Path) -> Result<HashSet<String>> {
Ok(list_all_objects_with_type(repo_path)?
.into_iter()
.filter(|(_, ty)| ty == "blob")
.map(|(oid, _)| oid)
.collect())
}
/// The pin candidate OIDs for a push plus whether they came from a full-repo
/// scan. `full_scan` is true when the delta could not be used and the whole
/// object DB (including dangling objects) was enumerated — the caller must then
/// apply the fail-closed blob filter, because the reachable-only withheld set
/// cannot classify dangling blobs (#99).
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct PinCandidateSet {
pub candidates: Vec<String>,
pub full_scan: bool,
}
/// Resolve the pin candidate OID set for a push, off the async worker.
///
/// Runs [`resolve_push_delta`] in `spawn_blocking` (git subprocess) and applies
/// the full-scan fallback for [`PinCandidates::FullScanRequired`]. Owns the
/// dispatch so the push call site stays thin and this wiring is unit-testable
/// without the HTTP layer.
///
/// Every degraded path is **logged**, not silent: a full-scan fallback, a
/// failed full scan, and a panicked blocking task each emit a warning. On a
/// failed full scan or a task panic the candidate set is empty (pin nothing
/// this push); that is a durability gap the reconciliation sweep backstops, and
/// it can never leak because the withheld/fail-closed filter still runs on
/// whatever set is returned. `full_scan` rides on the returned set so the caller
/// knows when the dangling-inclusive filter is required.
pub async fn resolve_candidates_for_push(
repo_path: PathBuf,
new_tips: Vec<String>,
old_tips: Vec<String>,
) -> PinCandidateSet {
tokio::task::spawn_blocking(move || {
let new_refs: Vec<&str> = new_tips.iter().map(String::as_str).collect();
let old_refs: Vec<&str> = old_tips.iter().map(String::as_str).collect();
match resolve_push_delta(&repo_path, &new_refs, &old_refs) {
PinCandidates::Delta(objs) => {
tracing::info!(delta = objs.len(), repo = %repo_path.display(), "pin candidate set from push delta");
PinCandidateSet { candidates: objs, full_scan: false }
}
PinCandidates::FullScanRequired => {
tracing::warn!(repo = %repo_path.display(), "pin delta unavailable (non-commit tip, git error, or force-full-scan) — full-scan fallback");
match list_all_objects(&repo_path) {
Ok(objs) => PinCandidateSet { candidates: objs, full_scan: true },
Err(e) => {
tracing::warn!(repo = %repo_path.display(), err = %e, "full-scan fallback failed; pinning nothing this push (reconciliation sweep backstops)");
PinCandidateSet { candidates: Vec::new(), full_scan: false }
}
}
}
}
})
.await
.unwrap_or_else(|e| {
tracing::warn!(err = %e, "pin candidate computation task panicked; pinning nothing this push (reconciliation sweep backstops)");
PinCandidateSet { candidates: Vec::new(), full_scan: false }
})
}
#[cfg(test)]
mod tests {
use super::*;
use std::collections::HashSet;
use tempfile::TempDir;
/// Minimal git helper for building test repos.
struct Repo {
_td: TempDir,
path: std::path::PathBuf,
}
impl Repo {
fn new() -> Self {
let td = TempDir::new().unwrap();
let path = td.path().to_path_buf();
let r = Repo { _td: td, path };
r.git(&["init", "-q", "-b", "main"]);
r.git(&["config", "user.email", "t@t"]);
r.git(&["config", "user.name", "t"]);
r
}
fn git(&self, args: &[&str]) -> String {
let out = Command::new("git")
.args(args)
.current_dir(&self.path)
.output()
.unwrap();
assert!(
out.status.success(),
"git {args:?} failed: {}",
String::from_utf8_lossy(&out.stderr)
);
String::from_utf8_lossy(&out.stdout).trim().to_string()
}
fn commit_file(&self, name: &str, body: &str) -> String {
std::fs::write(self.path.join(name), body).unwrap();
self.git(&["add", name]);
self.git(&["commit", "-qm", &format!("add {name}")]);
self.git(&["rev-parse", "HEAD"])
}
fn rev(&self, r: &str) -> String {
self.git(&["rev-parse", r])
}
}
const ZERO: &str = "0000000000000000000000000000000000000000";
fn delta(c: PinCandidates) -> Vec<String> {
match c {
PinCandidates::Delta(v) => v,
PinCandidates::FullScanRequired => panic!("expected Delta, got FullScanRequired"),
}
}
#[test]
fn single_new_commit_delta_excludes_preexisting_objects() {
let repo = Repo::new();
let c1 = repo.commit_file("a.txt", "one\n");
let c2 = repo.commit_file("b.txt", "two\n");
let got: HashSet<String> = delta(resolve_push_delta(&repo.path, &[&c2], &[&c1]))
.into_iter()
.collect();
// The new blob b.txt and commit c2 are in the delta; the old blob a.txt
// and commit c1 are not.
let new_blob = repo.rev("HEAD:b.txt");
let old_blob = repo.rev(&format!("{c1}:a.txt"));
assert!(got.contains(&c2), "new commit in delta");
assert!(got.contains(&new_blob), "new blob in delta");
assert!(!got.contains(&c1), "old commit excluded");
assert!(!got.contains(&old_blob), "old blob excluded");
}
#[test]
fn created_ref_is_superset_of_new_objects() {
// A created ref (old tip all-zeros, filtered out by caller) with no old
// tips walks everything reachable from the new tip — a superset of the
// genuinely new objects, never fewer.
let repo = Repo::new();
let c1 = repo.commit_file("a.txt", "one\n");
let got: HashSet<String> = delta(resolve_push_delta(&repo.path, &[&c1], &[]))
.into_iter()
.collect();
assert!(got.contains(&c1));
assert!(got.contains(&repo.rev("HEAD:a.txt")));
assert!(got.contains(&repo.rev("HEAD^{tree}")));
}
#[test]
fn force_push_delta_is_objects_unique_to_new_tip() {
let repo = Repo::new();
let base = repo.commit_file("a.txt", "one\n");
let old_tip = repo.commit_file("b.txt", "two\n");
// Rewrite history: reset to base, commit a different file.
repo.git(&["reset", "-q", "--hard", &base]);
let new_tip = repo.commit_file("c.txt", "three\n");
let got: HashSet<String> = delta(resolve_push_delta(&repo.path, &[&new_tip], &[&old_tip]))
.into_iter()
.collect();
assert!(got.contains(&new_tip), "new tip in delta");
assert!(got.contains(&repo.rev(&format!("{new_tip}:c.txt"))));
// No error; force-push computes new-minus-old cleanly.
}
#[test]
fn deleted_ref_only_yields_empty_delta_without_git() {
let repo = Repo::new();
repo.commit_file("a.txt", "one\n");
// All updates were deletions => new_tips empty after the caller strips zeros.
assert_eq!(
resolve_push_delta(&repo.path, &[], &[ZERO]),
PinCandidates::Delta(Vec::new())
);
}
#[test]
fn blob_tip_forces_full_scan() {
let repo = Repo::new();
repo.commit_file("a.txt", "one\n");
let blob = repo.rev("HEAD:a.txt");
assert_eq!(
resolve_push_delta(&repo.path, &[&blob], &[]),
PinCandidates::FullScanRequired,
"a blob tip must force full scan (rev-list would exit 0 and walk it)"
);
}
#[test]
fn tree_tip_forces_full_scan() {
let repo = Repo::new();
repo.commit_file("a.txt", "one\n");
let tree = repo.rev("HEAD^{tree}");
assert_eq!(
resolve_push_delta(&repo.path, &[&tree], &[]),
PinCandidates::FullScanRequired
);
}
#[test]
fn annotated_tag_of_tree_forces_full_scan() {
let repo = Repo::new();
repo.commit_file("a.txt", "one\n");
let tree = repo.rev("HEAD^{tree}");
repo.git(&["tag", "-a", "treetag", "-m", "x", &tree]);
let tag = repo.rev("treetag");
assert_eq!(
resolve_push_delta(&repo.path, &[&tag], &[]),
PinCandidates::FullScanRequired,
"annotated tag peeling to a tree must force full scan"
);
}
#[test]
fn tag_of_tag_of_noncommit_forces_full_scan() {
let repo = Repo::new();
repo.commit_file("a.txt", "one\n");
let blob = repo.rev("HEAD:a.txt");
repo.git(&["tag", "-a", "t1", "-m", "x", &blob]);
let t1 = repo.rev("t1");
repo.git(&["tag", "-a", "t2", "-m", "x", &t1]);
let t2 = repo.rev("t2");
assert_eq!(
resolve_push_delta(&repo.path, &[&t2], &[]),
PinCandidates::FullScanRequired
);
}
#[test]
fn annotated_tag_of_commit_proceeds_as_delta() {
// DISCRIMINATING positive-path regression: an annotated tag whose peeled
// target is a commit must return Delta, not FullScanRequired. A
// FullScanRequired here means the guard used bare `cat-file -t` (returns
// `tag`) instead of the `^{}` peel.
let repo = Repo::new();
let c1 = repo.commit_file("a.txt", "one\n");
repo.git(&["tag", "-a", "rel", "-m", "release", &c1]);
let tag = repo.rev("rel");
let got: HashSet<String> = delta(resolve_push_delta(&repo.path, &[&tag], &[]))
.into_iter()
.collect();
assert!(
got.contains(&c1),
"peeled commit's objects are in the delta"
);
}
#[test]
fn tag_of_tag_of_commit_proceeds_as_delta() {
// Deep-peel positive path: tag -> tag -> commit must recurse to `commit`
// via `^{}` and return Delta. Complements tag_of_tag_of_noncommit (which
// forces full scan) — guards against a regression in peel depth that
// would silently downgrade a legitimate nested-tag push to full scan.
let repo = Repo::new();
let c1 = repo.commit_file("a.txt", "one\n");
repo.git(&["tag", "-a", "t1", "-m", "x", &c1]);
let t1 = repo.rev("t1");
repo.git(&["tag", "-a", "t2", "-m", "x", &t1]);
let t2 = repo.rev("t2");
let got: HashSet<String> = delta(resolve_push_delta(&repo.path, &[&t2], &[]))
.into_iter()
.collect();
assert!(
got.contains(&c1),
"peeled commit's objects are in the delta"
);
}
#[tokio::test]
async fn resolve_candidates_for_push_returns_delta() {
// The extracted wiring returns the per-push delta on the happy path.
let repo = Repo::new();
let c1 = repo.commit_file("a.txt", "one\n");
let c2 = repo.commit_file("b.txt", "two\n");
let set =
resolve_candidates_for_push(repo.path.clone(), vec![c2.clone()], vec![c1.clone()])
.await;
assert!(!set.full_scan, "happy-path delta is not a full scan");
let got: HashSet<String> = set.candidates.into_iter().collect();
let new_blob = repo.rev("HEAD:b.txt");
assert!(
got.contains(&c2) && got.contains(&new_blob),
"new objects pinned"
);
assert!(!got.contains(&c1), "old commit excluded from delta");
}
#[tokio::test]
async fn resolve_candidates_for_push_falls_back_to_full_scan_on_noncommit_tip() {
// A non-commit tip forces FullScanRequired, and the wiring resolves that
// to the whole-repo list (a superset), never an empty set.
let repo = Repo::new();
repo.commit_file("a.txt", "one\n");
let blob = repo.rev("HEAD:a.txt");
let all: HashSet<String> = list_all_objects(&repo.path).unwrap().into_iter().collect();
let set = resolve_candidates_for_push(repo.path.clone(), vec![blob], vec![]).await;
assert!(set.full_scan, "non-commit tip is signalled as a full scan");
let got: HashSet<String> = set.candidates.into_iter().collect();
assert_eq!(got, all, "non-commit tip falls back to full repo scan");
}
#[test]
fn missing_oid_tip_forces_full_scan() {
let repo = Repo::new();
repo.commit_file("a.txt", "one\n");
let bogus = "deadbeefdeadbeefdeadbeefdeadbeefdeadbeef";
assert_eq!(
resolve_push_delta(&repo.path, &[bogus], &[]),
PinCandidates::FullScanRequired,
"a missing/corrupt tip OID must force full scan"
);
}
#[test]
fn present_noncommit_old_tip_is_safe() {
// A present-but-non-commit old_sha (a --not arg) must not under-pin:
// either rev-list errors (FullScanRequired) or it over-lists (Delta).
// Either way the new tip's objects are covered; never fewer.
let repo = Repo::new();
let c1 = repo.commit_file("a.txt", "one\n");
let c2 = repo.commit_file("b.txt", "two\n");
let old_tree = repo.rev(&format!("{c1}^{{tree}}"));
let result = resolve_push_delta(&repo.path, &[&c2], &[&old_tree]);
match result {
PinCandidates::FullScanRequired => {} // safe: caller full-scans
PinCandidates::Delta(objs) => {
// Safe direction: must still contain the new commit (over-list ok).
assert!(objs.contains(&c2), "new tip objects must be covered");
}
}
}
#[test]
fn multi_ref_push_unions_ranges() {
let repo = Repo::new();
let base = repo.commit_file("a.txt", "one\n");
// branch1 advances
let b1 = repo.commit_file("b.txt", "two\n");
// branch2 from base advances independently
repo.git(&["checkout", "-q", "-b", "branch2", &base]);
let b2 = repo.commit_file("c.txt", "three\n");
let got: HashSet<String> =
delta(resolve_push_delta(&repo.path, &[&b1, &b2], &[&base, &base]))
.into_iter()
.collect();
assert!(got.contains(&b1), "branch1 new commit");
assert!(got.contains(&b2), "branch2 new commit");
}
#[test]
fn empty_repo_no_tips_yields_empty_delta() {
let repo = Repo::new();
assert_eq!(
resolve_push_delta(&repo.path, &[], &[]),
PinCandidates::Delta(Vec::new())
);
}
#[test]
fn force_full_scan_flag_overrides() {
// Test the kill-switch via the pure inner fn so we never touch
// process-global env (which would race with parallel tests, and is
// unsafe in Rust 2024). The public resolve_push_delta wires the env
// read into this same flag.
let repo = Repo::new();
let c1 = repo.commit_file("a.txt", "one\n");
assert_eq!(
resolve_push_delta_inner(&repo.path, &[&c1], &[], true),
PinCandidates::FullScanRequired
);
// And with the flag off, the same push yields a Delta.
assert!(matches!(
resolve_push_delta_inner(&repo.path, &[&c1], &[], false),
PinCandidates::Delta(_)
));
}
#[test]
fn list_all_objects_returns_full_repo() {
let repo = Repo::new();
repo.commit_file("a.txt", "one\n");
repo.commit_file("b.txt", "two\n");
let all = list_all_objects(&repo.path).unwrap();
// 2 commits + 2 trees + 2 blobs = 6 objects.
assert_eq!(all.len(), 6, "got: {all:?}");
}
#[test]
fn all_blob_oids_includes_dangling_and_excludes_nonblobs() {
// The all-blob universe must include a dangling blob (the #99 hazard) and
// exclude commits/trees, so the fail-closed filter can tell a blob from a
// structural object without typing the candidate list.
let repo = Repo::new();
let c1 = repo.commit_file("a.txt", "one\n");
let reachable_blob = repo.rev("HEAD:a.txt");
let tree = repo.rev("HEAD^{tree}");
// Write a blob referenced by no tree/commit — dangling.
std::fs::write(repo.path.join("orphan.bin"), b"dangling\n").unwrap();
let dangling = repo.git(&["hash-object", "-w", "orphan.bin"]);
let blobs = all_blob_oids(&repo.path).unwrap();
assert!(blobs.contains(&reachable_blob), "reachable blob present");
assert!(
blobs.contains(&dangling),
"dangling blob present in the all-blob universe"
);
assert!(!blobs.contains(&c1), "commit is not a blob");
assert!(!blobs.contains(&tree), "tree is not a blob");
// The typed lister tags each object; spot-check the dangling blob's type.
let typed = list_all_objects_with_type(&repo.path).unwrap();
assert!(
typed
.iter()
.any(|(oid, ty)| oid == &dangling && ty == "blob"),
"dangling object is typed as a blob"
);
}
}
+23 -77
View File
@@ -33,16 +33,6 @@ pub struct RepoStore {
}
impl RepoStore {
#[cfg(test)]
pub fn for_testing(repos_dir: PathBuf, pool: PgPool) -> Self {
Self {
repos_dir,
tigris: None,
pool,
migrated: Arc::new(tokio::sync::Mutex::new(std::collections::HashSet::new())),
}
}
pub fn new(repos_dir: PathBuf, tigris: Option<TigrisClient>, pool: PgPool) -> Self {
Self {
repos_dir,
@@ -130,19 +120,10 @@ impl RepoStore {
if let Some(ref tigris) = self.tigris {
if tigris.exists(&owner_slug, repo_name).await.unwrap_or(false) {
debug!(repo = %repo_name, "acquire_fresh: downloading latest from tigris");
if let Err(e) = tigris.download(&owner_slug, repo_name, &local_path).await {
// The Tigris archive is present (HEAD ok) but unreadable — a
// corrupt/partial upload, or a transient GET failure. If we have a
// valid local copy, proceed with it rather than blocking the write;
// the post-write upload re-syncs (self-heals) Tigris. Only hard-fail
// when there is no local copy to fall back to.
if local_path.exists() {
warn!(repo = %repo_name, err = %e,
"acquire_fresh: tigris download failed — falling back to local copy");
return Ok(local_path);
}
return Err(e).context("downloading repo from tigris (fresh)");
}
tigris
.download(&owner_slug, repo_name, &local_path)
.await
.context("downloading repo from tigris (fresh)")?;
return Ok(local_path);
}
}
@@ -183,17 +164,10 @@ impl RepoStore {
if let Some(ref tigris) = self.tigris {
if tigris.exists(&owner_slug, repo_name).await.unwrap_or(false) {
debug!(repo = %repo_name, "write acquire: downloading latest from tigris");
if let Err(e) = tigris.download(&owner_slug, repo_name, &local_path).await {
// Same self-healing fallback as acquire_fresh: a corrupt/unreadable
// Tigris archive must not block a write when a valid local copy
// exists — release(success) will re-upload a good archive.
if local_path.exists() {
warn!(repo = %repo_name, err = %e,
"write acquire: tigris download failed — falling back to local copy");
} else {
return Err(e).context("downloading repo from tigris for write");
}
}
tigris
.download(&owner_slug, repo_name, &local_path)
.await
.context("downloading repo from tigris for write")?;
}
}
@@ -248,23 +222,20 @@ impl RepoStore {
/// Compute the local disk path and owner slug for a repo.
///
/// Three-layer defence against path traversal:
/// 1. Strict allowlist on `owner_did` and `repo_name` (no `..`, slashes,
/// null bytes, leading dots; length-bounded).
/// 2. The joined path must remain rooted at `repos_dir`.
/// 3. Every component of the joined path must be `Component::Normal`
/// (or the prefix/root from `repos_dir`); any `ParentDir`/`CurDir`
/// segment is rejected. This is the CodeQL-recognised barrier
/// pattern for `rust/path-injection`.
/// Rejects any input that could be used for path traversal — strict
/// allowlist on both `owner_did` and `repo_name`, length-bounded, and
/// the resulting path must remain inside `repos_dir`.
fn local_path(&self, owner_did: &str, repo_name: &str) -> Result<(String, PathBuf)> {
validate_path_components(owner_did, repo_name)?;
let owner_slug = owner_did.replace([':', '/'], "_");
let owner_slug = owner_did.replace(':', "_").replace('/', "_");
let local_path = self
.repos_dir
.join(&owner_slug)
.join(format!("{repo_name}.git"));
// Defence in depth: even though both inputs are allowlisted, verify
// the joined path is still rooted at repos_dir.
if !local_path.starts_with(&self.repos_dir) {
anyhow::bail!(
"computed repo path escaped repos_dir: {}",
@@ -272,23 +243,6 @@ impl RepoStore {
);
}
// Explicit component walk — sanitisation barrier that static analysers
// (CodeQL `rust/path-injection`) recognise. The path must be composed
// entirely of Normal segments after the root prefix; any ParentDir or
// CurDir component is a traversal attempt.
for component in local_path.components() {
use std::path::Component;
match component {
Component::Prefix(_) | Component::RootDir | Component::Normal(_) => {}
Component::ParentDir => {
anyhow::bail!("path contains parent-directory component");
}
Component::CurDir => {
anyhow::bail!("path contains current-directory component");
}
}
}
Ok((owner_slug, local_path))
}
}
@@ -364,24 +318,16 @@ impl RepoWriteGuard {
&self.local_path
}
/// Upload to Tigris (only when the write succeeded) and release the advisory
/// lock. Pass `success = false` when the write operation failed — uploading a
/// half-applied or otherwise inconsistent repo would propagate corruption to
/// Tigris (and to every node that later downloads it). The lock is always
/// released regardless, to avoid stale locks blocking future writes.
pub async fn release(self, success: bool) {
// Upload to Tigris only on success.
if success {
if let Some(ref tigris) = self.tigris {
if let Err(e) = tigris
.upload(&self.owner_slug, &self.repo_name, &self.local_path)
.await
{
warn!(repo = %self.repo_name, err = %e, "failed to upload repo to tigris after write");
}
/// Upload to Tigris and release the advisory lock. Call this when the write is done.
pub async fn release(self) {
// Upload to Tigris
if let Some(ref tigris) = self.tigris {
if let Err(e) = tigris
.upload(&self.owner_slug, &self.repo_name, &self.local_path)
.await
{
warn!(repo = %self.repo_name, err = %e, "failed to upload repo to tigris after write");
}
} else {
warn!(repo = %self.repo_name, "write failed — skipping tigris upload to avoid propagating an inconsistent repo");
}
// Release advisory lock
File diff suppressed because it is too large. Load diff
+19 -151
View File
@@ -1,6 +1,6 @@
use anyhow::{bail, Context, Result};
use std::path::{Path, PathBuf};
use std::process::Command;
use anyhow::{Result, Context, bail};
/// Initialize a new bare git repository with SHA-1 object format (default).
///
@@ -107,8 +107,7 @@ pub fn resolve_head(repo_path: &Path, preferred_branch: &str) -> String {
// 3. Walk all refs — prefer main/master, then take the first one
if let Ok(refs) = list_refs(repo_path) {
let branches: Vec<_> = refs
.iter()
let branches: Vec<_> = refs.iter()
.filter(|(r, _)| r.starts_with("refs/heads/"))
.collect();
// Preferred names in order
@@ -200,13 +199,7 @@ pub fn ls_tree(repo_path: &Path, refname: &str, tree_path: &str) -> Result<Vec<T
let kind = parts.next()?.to_string();
let hash = parts.next()?.to_string();
let size: Option<u64> = parts.next().and_then(|s| s.parse().ok());
Some(TreeEntry {
mode,
kind,
hash,
path: name.to_string(),
size,
})
Some(TreeEntry { mode, kind, hash, path: name.to_string(), size })
})
.collect();
@@ -246,9 +239,7 @@ pub struct CommitInfo {
fn serialize_timestamp<S: serde::Serializer>(ts: &i64, s: S) -> Result<S::Ok, S::Error> {
use chrono::TimeZone;
let dt = chrono::Utc
.timestamp_opt(*ts, 0)
.single()
let dt = chrono::Utc.timestamp_opt(*ts, 0).single()
.unwrap_or_else(chrono::Utc::now);
s.serialize_str(&dt.to_rfc3339())
}
@@ -271,8 +262,9 @@ pub struct TreeEntry {
/// `/ipfs/<cid>` is computed from these same content bytes via
/// `gitlawb_core::cid::Cid::from_git_object_bytes`.
///
/// 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>> {
/// 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
let type_output = Command::new("git")
.args(["cat-file", "-t", sha256_hex])
.current_dir(repo_path)
@@ -283,17 +275,11 @@ pub fn object_type(repo_path: &Path, sha256_hex: &str) -> Result<Option<String>>
return Ok(None);
}
Ok(Some(
String::from_utf8_lossy(&type_output.stdout)
.trim()
.to_string(),
))
}
let obj_type = String::from_utf8_lossy(&type_output.stdout).trim().to_string();
/// 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>> {
// Read the raw content bytes
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>")?;
@@ -303,24 +289,7 @@ pub fn read_object_content(repo_path: &Path, sha256_hex: &str, obj_type: &str) -
bail!("git cat-file failed: {stderr}");
}
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)))
Ok(Some((obj_type, content_output.stdout)))
}
/// Get the diff between two branches: changes on source_branch not in target_branch.
@@ -334,48 +303,9 @@ pub fn branch_diff(repo_path: &Path, target_branch: &str, source_branch: &str) -
Ok(String::from_utf8_lossy(&output.stdout).to_string())
}
/// The repo-relative paths changed by `git diff target...source` (the same range
/// as `branch_diff`). Used to enforce per-path visibility on a PR diff: if the
/// caller cannot read one of these paths, the diff is withheld.
pub fn branch_diff_names(
repo_path: &Path,
target_branch: &str,
source_branch: &str,
) -> Result<Vec<String>> {
let output = Command::new("git")
.args([
"diff",
"--name-only",
"-z",
&format!("{target_branch}...{source_branch}"),
])
.current_dir(repo_path)
.output()
.context("failed to run git diff --name-only")?;
if !output.status.success() {
let stderr = String::from_utf8_lossy(&output.stderr);
bail!("git diff --name-only failed: {stderr}");
}
// Split on NUL (`-z`) so paths containing newlines keep their exact bytes;
// `--name-only` without `-z` would quote/escape such paths and they would no
// longer match the visibility globs in get_pr_diff, leaking the diff.
Ok(output
.stdout
.split(|b| *b == b'\0')
.filter(|s| !s.is_empty())
.map(|s| String::from_utf8_lossy(s).into_owned())
.collect())
}
/// Merge source_branch into target_branch in a bare repo using a temporary worktree.
/// Returns the new merge commit hash.
pub fn merge_branch(
repo_path: &Path,
target_branch: &str,
source_branch: &str,
author_did: &str,
pr_title: &str,
) -> Result<String> {
pub fn merge_branch(repo_path: &Path, target_branch: &str, source_branch: &str, author_did: &str, pr_title: &str) -> Result<String> {
let worktree_path = repo_path.join("_merge_worktree");
// Clean up any leftover worktree
@@ -394,24 +324,13 @@ pub fn merge_branch(
.output()
.context("failed to create worktree")?;
if !wt.status.success() {
bail!(
"git worktree add failed: {}",
String::from_utf8_lossy(&wt.stderr)
);
bail!("git worktree add failed: {}", String::from_utf8_lossy(&wt.stderr));
}
// Run merge in worktree
let merge = Command::new("git")
.args([
"merge",
"--no-ff",
source_branch,
"-m",
&format!(
"Merge branch '{}' into {} ({})",
source_branch, target_branch, pr_title
),
])
.args(["merge", "--no-ff", source_branch, "-m",
&format!("Merge branch '{}' into {} ({})", source_branch, target_branch, pr_title)])
.current_dir(&worktree_path)
.env("GIT_AUTHOR_NAME", author_did)
.env("GIT_AUTHOR_EMAIL", format!("{}@gitlawb", author_did))
@@ -430,10 +349,7 @@ pub fn merge_branch(
let _ = std::fs::remove_dir_all(&worktree_path);
if !success {
bail!(
"git merge failed: {}",
String::from_utf8_lossy(&merge.stderr)
);
bail!("git merge failed: {}", String::from_utf8_lossy(&merge.stderr));
}
// Get new HEAD of target branch
@@ -449,56 +365,8 @@ pub fn merge_branch(
/// Resolve a repo disk path: {repos_dir}/{owner_slug}/{repo_name}.git
pub fn repo_disk_path(repos_dir: &Path, owner_did: &str, repo_name: &str) -> PathBuf {
// Sanitize the DID for use as a directory name
let owner_slug = owner_did.replace([':', '/'], "_");
let owner_slug = owner_did
.replace(':', "_")
.replace('/', "_");
repos_dir.join(owner_slug).join(format!("{repo_name}.git"))
}
#[cfg(test)]
mod tests {
use super::branch_diff_names;
use std::path::Path;
use std::process::Command;
#[test]
fn branch_diff_names_lists_changed_paths() {
let td = tempfile::TempDir::new().unwrap();
let work: &Path = td.path();
let g = |args: &[&str]| {
assert!(Command::new("git")
.args(args)
.current_dir(work)
.status()
.unwrap()
.success());
};
g(&["init", "-q"]);
g(&["config", "user.email", "t@t"]);
g(&["config", "user.name", "t"]);
std::fs::write(work.join("base.txt"), b"base\n").unwrap();
g(&["add", "."]);
g(&["commit", "-qm", "base"]);
let main = {
let o = Command::new("git")
.args(["symbolic-ref", "--short", "HEAD"])
.current_dir(work)
.output()
.unwrap();
String::from_utf8_lossy(&o.stdout).trim().to_string()
};
g(&["checkout", "-q", "-b", "feature"]);
std::fs::create_dir_all(work.join("secret")).unwrap();
std::fs::write(work.join("secret/x.txt"), b"secret\n").unwrap();
g(&["add", "."]);
g(&["commit", "-qm", "feat"]);
let names = branch_diff_names(work, &main, "feature").unwrap();
assert!(
names.iter().any(|p| p == "secret/x.txt"),
"expected secret/x.txt in changed paths, got {names:?}"
);
assert!(
!names.iter().any(|p| p == "base.txt"),
"unchanged file must not appear: {names:?}"
);
}
}
+18 -89
View File
@@ -3,9 +3,7 @@
//! Repos are stored as `repos/v1/{owner_slug}/{repo_name}.tar.zst` — a
//! zstd-compressed tar archive of the bare repo directory.
use std::collections::HashMap;
use std::path::{Path, PathBuf};
use std::sync::{Arc, Mutex, OnceLock};
use std::path::Path;
use anyhow::{Context, Result};
use aws_sdk_s3::Client as S3Client;
@@ -25,10 +23,7 @@ impl TigrisClient {
let config = aws_config::load_defaults(aws_config::BehaviorVersion::latest()).await;
let s3 = S3Client::new(&config);
info!(bucket = %bucket, "tigris storage client initialized");
Ok(Self {
s3,
bucket: bucket.to_string(),
})
Ok(Self { s3, bucket: bucket.to_string() })
}
/// S3 key for a given repo: `repos/v1/{owner_slug}/{repo_name}.tar.zst`
@@ -39,9 +34,7 @@ impl TigrisClient {
/// Check if a repo archive exists in Tigris.
pub async fn exists(&self, owner_slug: &str, repo_name: &str) -> Result<bool> {
let key = Self::repo_key(owner_slug, repo_name);
match self
.s3
.head_object()
match self.s3.head_object()
.bucket(&self.bucket)
.key(&key)
.send()
@@ -49,7 +42,7 @@ impl TigrisClient {
{
Ok(_) => Ok(true),
Err(e) => {
if e.as_service_error().is_some_and(|e| e.is_not_found()) {
if e.as_service_error().map_or(false, |e| e.is_not_found()) {
Ok(false)
} else {
Err(anyhow::anyhow!("tigris HEAD {key}: {e}"))
@@ -74,8 +67,7 @@ impl TigrisClient {
let body = aws_sdk_s3::primitives::ByteStream::from(archive_bytes);
self.s3
.put_object()
self.s3.put_object()
.bucket(&self.bucket)
.key(&key)
.body(body)
@@ -89,30 +81,21 @@ impl TigrisClient {
}
/// Download a repo archive from Tigris and extract to local disk.
pub async fn download(
&self,
owner_slug: &str,
repo_name: &str,
local_path: &Path,
) -> Result<()> {
pub async fn download(&self, owner_slug: &str, repo_name: &str, local_path: &Path) -> Result<()> {
let key = Self::repo_key(owner_slug, repo_name);
debug!(key = %key, path = %local_path.display(), "downloading repo from tigris");
let resp = self
.s3
.get_object()
let resp = self.s3.get_object()
.bucket(&self.bucket)
.key(&key)
.send()
.await
.context(format!("tigris GET {key}"))?;
let data = resp
.body
.collect()
.await
let data = resp.body.collect().await
.context("reading tigris response body")?
.into_bytes();
.into_bytes()
.to_vec();
// Extract tar.zst to local path
tokio::task::spawn_blocking({
@@ -131,8 +114,7 @@ impl TigrisClient {
#[allow(dead_code)]
pub async fn delete(&self, owner_slug: &str, repo_name: &str) -> Result<()> {
let key = Self::repo_key(owner_slug, repo_name);
self.s3
.delete_object()
self.s3.delete_object()
.bucket(&self.bucket)
.key(&key)
.send()
@@ -157,70 +139,17 @@ fn compress_repo(repo_path: &Path) -> Result<Vec<u8>> {
Ok(compressed)
}
/// Per-repo-path lock serializing the publish (swap-into-place) step of
/// `decompress_repo`. Concurrent extractions unpack into isolated temp dirs in
/// parallel, but the final `remove_dir_all` + `rename` must not interleave for
/// the same `local_path`, or they race to a nondeterministic overwrite/failure.
fn publish_lock(local_path: &Path) -> Arc<Mutex<()>> {
// KNOWN LIMITATION: this map is never evicted — one (PathBuf, Arc<Mutex>)
// entry accrues per distinct repo path for the process lifetime. Bounded by
// the number of repos a node hosts, so it's negligible for normal use, but
// high-volume/churning deployments may want LRU or weak-ref eviction here.
static LOCKS: OnceLock<Mutex<HashMap<PathBuf, Arc<Mutex<()>>>>> = OnceLock::new();
let locks = LOCKS.get_or_init(|| Mutex::new(HashMap::new()));
let mut map = locks.lock().expect("publish lock map poisoned");
map.entry(local_path.to_path_buf())
.or_insert_with(|| Arc::new(Mutex::new(())))
.clone()
}
/// Decompress a tar.zst byte vector into a local directory.
///
/// Extraction is atomic with respect to `local_path`: the archive is unpacked
/// into a sibling temp directory first, and only swapped into place once it
/// fully succeeds. A corrupt or truncated archive therefore can never clobber a
/// good existing copy at `local_path` — on failure we discard the temp dir and
/// leave `local_path` exactly as it was.
fn decompress_repo(data: &[u8], local_path: &Path) -> Result<()> {
let parent = local_path.parent().context("repo path has no parent")?;
std::fs::create_dir_all(parent).context("creating parent dir")?;
let file_name = local_path
.file_name()
.context("repo path has no file name")?
.to_string_lossy();
// Unique per-extraction temp dir: a fixed name would let two concurrent
// extractions of the same repo share one dir and clobber each other's
// in-progress unpack. A fresh UUID also means it can't collide with a
// leftover dir from a previously-interrupted run.
let tmp_dir = parent.join(format!(".{file_name}.tmp-extract.{}", uuid::Uuid::new_v4()));
std::fs::create_dir_all(&tmp_dir).context("creating temp extract dir")?;
// Unpack into the temp dir; on any failure, clean up and bail without
// touching local_path.
let unpack = (|| -> Result<()> {
let decoder = zstd::stream::Decoder::new(data)?;
let mut archive = tar::Archive::new(decoder);
archive.unpack(&tmp_dir).context("unpacking tar.zst")?;
Ok(())
})();
if let Err(e) = unpack {
let _ = std::fs::remove_dir_all(&tmp_dir);
return Err(e);
// Ensure parent directory exists
if let Some(parent) = local_path.parent() {
std::fs::create_dir_all(parent).context("creating parent dir")?;
}
std::fs::create_dir_all(local_path).context("creating repo dir")?;
// Swap the freshly-extracted repo into place. rename within the same parent
// is effectively atomic, but most platforms refuse to rename onto a
// non-empty dir, so remove the old copy first. Serialize this per repo path:
// concurrent extractions unpack into isolated temp dirs, but their swaps
// must not interleave or they race to a nondeterministic overwrite/failure.
let lock = publish_lock(local_path);
let _publish = lock.lock().expect("publish lock poisoned");
if local_path.exists() {
std::fs::remove_dir_all(local_path).context("removing stale repo dir")?;
}
std::fs::rename(&tmp_dir, local_path).context("swapping extracted repo into place")?;
let decoder = zstd::stream::Decoder::new(data)?;
let mut archive = tar::Archive::new(decoder);
archive.unpack(local_path).context("unpacking tar.zst")?;
Ok(())
}
File diff suppressed because it is too large. Load diff
+6 -184
View File
@@ -3,21 +3,11 @@ use chrono::Utc;
use std::sync::Arc;
use uuid::Uuid;
use crate::auth::AuthenticatedDid;
use crate::db::{AgentTask, Db};
use crate::state::TaskEventBroadcast;
use super::types::{AgentTaskType, CreateTaskInput, FinishTaskInput};
/// The verified signer DID for this request, or an auth error (N2). The DID is
/// attached request-scoped by the `/graphql` `optional_signature` layer; its
/// absence means the request was unsigned, so every mutation rejects.
fn require_signer<'a>(ctx: &'a Context<'_>) -> Result<&'a str> {
ctx.data::<AuthenticatedDid>()
.map(|d| d.0.as_str())
.map_err(|_| async_graphql::Error::new("authentication required"))
}
pub struct MutationRoot;
#[Object]
@@ -28,13 +18,6 @@ impl MutationRoot {
delegator_did: String,
input: CreateTaskInput,
) -> Result<AgentTaskType> {
let caller = require_signer(ctx)?;
if !crate::api::did_matches(caller, &delegator_did) {
return Err(async_graphql::Error::new(
"delegator_did must be the authenticated signer",
));
}
let delegator_did = caller.to_string();
let db = ctx.data_unchecked::<Arc<Db>>();
let now = Utc::now().to_rfc3339();
let task = AgentTask {
@@ -64,15 +47,9 @@ impl MutationRoot {
id: String,
assignee_did: String,
) -> Result<AgentTaskType> {
let caller = require_signer(ctx)?;
if !crate::api::did_matches(caller, &assignee_did) {
return Err(async_graphql::Error::new(
"assignee_did must be the authenticated signer",
));
}
let assignee_did = caller.to_string();
let db = ctx.data_unchecked::<Arc<Db>>();
let tx = ctx.data_unchecked::<tokio::sync::broadcast::Sender<TaskEventBroadcast>>();
let tx = ctx
.data_unchecked::<tokio::sync::broadcast::Sender<TaskEventBroadcast>>();
let task = db
.claim_task(&id, &assignee_did)
.await
@@ -94,27 +71,9 @@ impl MutationRoot {
by_did: String,
input: FinishTaskInput,
) -> Result<AgentTaskType> {
let caller = require_signer(ctx)?;
if !crate::api::did_matches(caller, &by_did) {
return Err(async_graphql::Error::new(
"by_did must be the authenticated signer",
));
}
let by_did = caller.to_string();
let db = ctx.data_unchecked::<Arc<Db>>();
let tx = ctx.data_unchecked::<tokio::sync::broadcast::Sender<TaskEventBroadcast>>();
// Authorize the actor: binding by_did to the signer is necessary but not
// sufficient — only the task's assignee may finish it.
let existing = db
.get_task(&id)
.await
.map_err(|e| async_graphql::Error::new(e.to_string()))?
.ok_or_else(|| async_graphql::Error::new("task not found"))?;
if !crate::api::did_matches(caller, existing.assignee_did.as_deref().unwrap_or_default()) {
return Err(async_graphql::Error::new(
"only the task assignee can complete it",
));
}
let tx = ctx
.data_unchecked::<tokio::sync::broadcast::Sender<TaskEventBroadcast>>();
let task = db
.finish_task(&id, "completed", input.result.as_deref())
.await
@@ -136,26 +95,9 @@ impl MutationRoot {
by_did: String,
input: FinishTaskInput,
) -> Result<AgentTaskType> {
let caller = require_signer(ctx)?;
if !crate::api::did_matches(caller, &by_did) {
return Err(async_graphql::Error::new(
"by_did must be the authenticated signer",
));
}
let by_did = caller.to_string();
let db = ctx.data_unchecked::<Arc<Db>>();
let tx = ctx.data_unchecked::<tokio::sync::broadcast::Sender<TaskEventBroadcast>>();
// Authorize the actor: only the task's assignee may fail it.
let existing = db
.get_task(&id)
.await
.map_err(|e| async_graphql::Error::new(e.to_string()))?
.ok_or_else(|| async_graphql::Error::new("task not found"))?;
if !crate::api::did_matches(caller, existing.assignee_did.as_deref().unwrap_or_default()) {
return Err(async_graphql::Error::new(
"only the task assignee can fail it",
));
}
let tx = ctx
.data_unchecked::<tokio::sync::broadcast::Sender<TaskEventBroadcast>>();
let reason = input.reason.unwrap_or_default();
let task = db
.finish_task(&id, "failed", Some(&reason))
@@ -171,123 +113,3 @@ impl MutationRoot {
Ok(AgentTaskType::from(task))
}
}
#[cfg(test)]
mod tests {
use crate::auth::AuthenticatedDid;
use async_graphql::{Request, Response};
use sqlx::PgPool;
fn errors(resp: &Response) -> String {
resp.errors
.iter()
.map(|e| e.message.clone())
.collect::<Vec<_>>()
.join("; ")
}
/// N2: GraphQL mutations require a verified signer and bind the acting DID to
/// it. Unsigned is rejected; a signer other than the claimed actor is
/// rejected; the matching signer passes the auth gate.
#[sqlx::test]
async fn mutation_requires_and_binds_signer(pool: PgPool) {
let state = crate::test_support::test_state(pool).await;
let schema = state.graphql_schema.as_ref();
let assignee = "did:key:zASSIGNEEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA";
let q = format!(
r#"mutation {{ claimTask(id: "no-such-task", assigneeDid: "{assignee}") {{ id }} }}"#
);
// 1. Unsigned → rejected before any DB work.
let resp = schema.execute(Request::new(&q)).await;
assert!(
errors(&resp).contains("authentication required"),
"unsigned mutation must be rejected: {}",
errors(&resp)
);
// 2. Signed as someone other than the claimed assignee → rejected.
let resp = schema
.execute(Request::new(&q).data(AuthenticatedDid(
"did:key:zOTHERBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBB".into(),
)))
.await;
assert!(
errors(&resp).contains("authenticated signer"),
"DID mismatch must be rejected: {}",
errors(&resp)
);
// 3. Signed as the claimed assignee → passes the auth gate (any remaining
// error is the missing task, not an auth error).
let resp = schema
.execute(Request::new(&q).data(AuthenticatedDid(assignee.into())))
.await;
let errs = errors(&resp);
assert!(
!errs.contains("authentication required") && !errs.contains("authenticated signer"),
"matching signer must pass the auth gate: {errs}"
);
}
/// Adversarial-review GATE-1 (GraphQL): completing a task requires being its
/// assignee, not merely signing as the by_did you pass. A signer who is not
/// the assignee is rejected even though the by_did binding passes; the
/// assignee completes.
#[sqlx::test]
async fn complete_task_requires_assignee(pool: PgPool) {
let state = crate::test_support::test_state(pool).await;
let assignee = "did:key:zGQLASSIGNEEAAAAAAAAAAAAAAAAAAAAAAAAAAAA";
let stranger = "did:key:zGQLSTRANGERBBBBBBBBBBBBBBBBBBBBBBBBBBBB";
let now = chrono::Utc::now().to_rfc3339();
let task = crate::db::AgentTask {
id: "task-g".into(),
repo_id: None,
kind: "build".into(),
status: "pending".into(),
delegator_did: "did:key:zGQLDELEGATORCCCCCCCCCCCCCCCCCCCCCCCCCC".into(),
assignee_did: None,
capability: "repo:write".into(),
ucan_token: None,
payload: None,
result: None,
created_at: now.clone(),
updated_at: now,
deadline: None,
};
state.db.create_task(&task).await.expect("seed task");
state
.db
.claim_task("task-g", assignee)
.await
.expect("claim");
let schema = state.graphql_schema.as_ref();
let q = |actor: &str| {
format!(
r#"mutation {{ completeTask(id: "task-g", byDid: "{actor}", input: {{}}) {{ id status }} }}"#
)
};
// Stranger signs as themselves and passes byDid=self (so the signer
// binding passes), but is not the assignee → rejected by authorization.
let resp = schema
.execute(Request::new(q(stranger)).data(AuthenticatedDid(stranger.into())))
.await;
assert!(
errors(&resp).contains("assignee"),
"a non-assignee signer must be rejected: {}",
errors(&resp)
);
// The assignee completes with no error.
let resp = schema
.execute(Request::new(q(assignee)).data(AuthenticatedDid(assignee.into())))
.await;
assert!(
errors(&resp).is_empty(),
"the assignee should complete the task: {}",
errors(&resp)
);
}
}
+6 -326
View File
@@ -12,29 +12,11 @@ impl QueryRoot {
async fn repos(&self, ctx: &Context<'_>) -> Result<Vec<RepoType>> {
let db = ctx.data_unchecked::<Arc<Db>>();
let repos = db
.list_all_repos_deduped()
.list_all_repos()
.await
.map_err(|e| async_graphql::Error::new(e.to_string()))?;
// Apply the same "/" visibility gate the REST/per-repo endpoints use so
// this surface does not enumerate private repos (#97). The caller DID is
// threaded onto the context by optional_signature; absent = anonymous.
let caller = ctx
.data::<crate::auth::AuthenticatedDid>()
.ok()
.map(|d| d.0.as_str());
let ids: Vec<String> = repos.iter().map(|r| r.id.clone()).collect();
let rules_by_repo = db
.list_visibility_rules_for_repos(&ids)
.await
.map_err(|e| async_graphql::Error::new(e.to_string()))?;
Ok(repos
.into_iter()
.filter(|r| {
let rules = rules_by_repo.get(&r.id).map(Vec::as_slice).unwrap_or(&[]);
crate::visibility::listable_at_root(rules, r.is_public, &r.owner_did, caller)
})
.map(|r| RepoType {
name: r.name,
owner_did: r.owner_did,
@@ -49,30 +31,13 @@ impl QueryRoot {
&self,
ctx: &Context<'_>,
repo: Option<String>,
#[graphql(
default = 20,
desc = "Max 200; larger requests return the newest 200 rows (no continuation cursor)."
)]
limit: i64,
#[graphql(default = 20)] limit: i64,
) -> Result<Vec<RefUpdateType>> {
let db = ctx.data_unchecked::<Arc<Db>>();
// 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()))?;
let updates = db
.list_ref_updates_filtered(repo.as_deref(), limit)
.await
.map_err(|e| async_graphql::Error::new(e.to_string()))?;
Ok(updates
.into_iter()
.map(|u| RefUpdateType {
@@ -111,288 +76,3 @@ 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(),
}
}
/// 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 } }"#;
let resp = anon(&schema, q).await;
assert_eq!(count(&resp), 1);
// The one row returned must be the public repo's.
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")
);
}
// 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 -18
View File
@@ -1,5 +1,5 @@
use async_graphql::futures_util::Stream;
use async_graphql::{Context, Subscription};
use async_graphql::futures_util::Stream;
use tokio_stream::wrappers::BroadcastStream;
use tokio_stream::StreamExt as _;
@@ -11,15 +11,6 @@ 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<'_>,
@@ -31,7 +22,7 @@ impl SubscriptionRoot {
BroadcastStream::new(rx).filter_map(move |r| {
let rf = repo.clone();
match r {
Ok(ev) if rf.as_deref().is_none_or(|r| ev.repo == r) => Some(RefUpdateType {
Ok(ev) if rf.as_deref().map_or(true, |r| ev.repo == r) => Some(RefUpdateType {
repo: ev.repo,
ref_name: ev.ref_name,
old_sha: ev.old_sha,
@@ -56,13 +47,15 @@ impl SubscriptionRoot {
BroadcastStream::new(rx).filter_map(move |r| {
let tf = task_id.clone();
match r {
Ok(ev) if tf.as_deref().is_none_or(|id| ev.task_id == id) => Some(TaskEventType {
task_id: ev.task_id,
old_status: ev.old_status,
new_status: ev.new_status,
by_did: ev.by_did,
at: ev.at,
}),
Ok(ev) if tf.as_deref().map_or(true, |id| ev.task_id == id) => {
Some(TaskEventType {
task_id: ev.task_id,
old_status: ev.old_status,
new_status: ev.new_status,
by_did: ev.by_did,
at: ev.at,
})
}
_ => None,
}
})
-650
View File
@@ -1,650 +0,0 @@
//! iCaptcha proof-of-intelligence gate.
//!
//! Spam-prone endpoints (repo creation, agent registration) can require the
//! caller to present an iCaptcha proof: a small Ed25519-signed token minted by
//! <https://icaptcha.gitlawb.com> after the caller solves an escalating
//! challenge. We verify the proof OFFLINE (no per-request call to iCaptcha)
//! using its published public key, and bind each proof to the authenticated
//! agent DID so a proof cannot be shared between identities.
//!
//! Behaviour is controlled by `ICAPTCHA_MODE`:
//! * `off` (default) — gate is inert, nothing is checked.
//! * `shadow` — verify and log would-be rejections, but always allow.
//! * `enforce` — reject requests without a valid, sufficiently-strong proof.
//!
//! Config (env):
//! ICAPTCHA_MODE off | shadow | enforce (default off)
//! ICAPTCHA_URL base URL (default https://icaptcha.gitlawb.com)
//! ICAPTCHA_PUBKEY base64url Ed25519 public key (optional; else fetched from /v1/pubkey)
//! ICAPTCHA_REQUIRED_LEVEL minimum proof level (default 3)
use std::sync::OnceLock;
use std::time::{Duration, SystemTime, UNIX_EPOCH};
use axum::http::HeaderMap;
use base64::engine::general_purpose::URL_SAFE_NO_PAD;
use base64::Engine;
use ed25519_dalek::{Signature, VerifyingKey};
use serde::Deserialize;
use crate::error::AppError;
const PROOF_HEADER: &str = "x-icaptcha-proof";
/// How long a mirror-admission `jti` stays in the replay ledger. The direct
/// request path spends a proof against its own `exp` (it can't be presented once
/// expired). The propagation path deliberately accepts already-expired proofs,
/// so spending against `exp` would store an already-past expiry that the next
/// sweep deletes — letting the same token admit another mirror minutes later.
/// We instead retain the mirror replay record for a long, fixed window so the
/// per-node single-use property is durable.
const MIRROR_REPLAY_RETENTION_SECS: i64 = 365 * 24 * 60 * 60;
#[derive(Clone, Copy, PartialEq, Eq, Debug)]
pub enum Mode {
Off,
Shadow,
Enforce,
}
impl Mode {
fn as_str(self) -> &'static str {
match self {
Mode::Off => "off",
Mode::Shadow => "shadow",
Mode::Enforce => "enforce",
}
}
}
/// Parse `ICAPTCHA_MODE`. Returns `None` for unrecognized values so the caller
/// can surface the typo instead of silently disabling the gate.
fn parse_mode(s: &str) -> Option<Mode> {
match s.trim().to_ascii_lowercase().as_str() {
"" | "off" => Some(Mode::Off),
"shadow" => Some(Mode::Shadow),
"enforce" => Some(Mode::Enforce),
_ => None,
}
}
/// Parse `ICAPTCHA_REQUIRED_LEVEL`. Defaults to 3; warns (rather than silently
/// lowering the threshold) when a non-empty value fails to parse.
fn parse_required_level() -> u32 {
const DEFAULT: u32 = 3;
match std::env::var("ICAPTCHA_REQUIRED_LEVEL") {
Ok(v) if !v.trim().is_empty() => v.trim().parse().unwrap_or_else(|_| {
tracing::warn!(
value = %v,
default = DEFAULT,
"invalid ICAPTCHA_REQUIRED_LEVEL; using default"
);
DEFAULT
}),
_ => DEFAULT,
}
}
struct Verifier {
mode: Mode,
url: String,
required_level: u32,
key: Option<VerifyingKey>,
}
static VERIFIER: OnceLock<Verifier> = OnceLock::new();
#[derive(Deserialize, Debug)]
struct ProofClaims {
sub: String,
level: u32,
exp: i64,
/// Unique proof id, consumed once so a proof cannot be replayed.
jti: String,
}
#[derive(Deserialize)]
struct Jwk {
x: String,
}
#[derive(Deserialize)]
struct Jwks {
keys: Vec<Jwk>,
}
fn now_secs() -> i64 {
SystemTime::now()
.duration_since(UNIX_EPOCH)
.map(|d| d.as_secs() as i64)
.unwrap_or(0)
}
fn decode_key(b64url: &str) -> Option<VerifyingKey> {
let bytes = URL_SAFE_NO_PAD.decode(b64url.trim()).ok()?;
let arr: [u8; 32] = bytes.try_into().ok()?;
VerifyingKey::from_bytes(&arr).ok()
}
async fn fetch_key(url: &str) -> Option<VerifyingKey> {
let endpoint = format!("{}/v1/pubkey", url.trim_end_matches('/'));
// Bounded request: a hung /v1/pubkey must never block node startup. On
// timeout/error we return None and the gate stays inert (fail safe).
let client = reqwest::Client::builder()
.timeout(Duration::from_secs(5))
.build()
.ok()?;
let jwks: Jwks = client.get(&endpoint).send().await.ok()?.json().await.ok()?;
decode_key(&jwks.keys.first()?.x)
}
/// Initialize the gate from the environment. Call once at startup. Never panics;
/// if the gate is active but no key can be loaded, it stays inert and warns.
pub async fn init() {
let raw_mode = std::env::var("ICAPTCHA_MODE").unwrap_or_default();
let mode = parse_mode(&raw_mode).unwrap_or_else(|| {
tracing::warn!(value = %raw_mode, "invalid ICAPTCHA_MODE; disabling iCaptcha gate");
Mode::Off
});
let url = std::env::var("ICAPTCHA_URL")
.unwrap_or_else(|_| "https://icaptcha.gitlawb.com".to_string());
let required_level = parse_required_level();
let key = if mode == Mode::Off {
None
} else {
match std::env::var("ICAPTCHA_PUBKEY") {
Ok(b64) if !b64.is_empty() => decode_key(&b64),
_ => fetch_key(&url).await,
}
};
if mode != Mode::Off {
if key.is_some() {
tracing::info!(mode = mode.as_str(), required_level, "iCaptcha gate active");
} else {
tracing::warn!(
mode = mode.as_str(),
"iCaptcha gate enabled but no public key could be loaded; staying inert"
);
}
}
let _ = VERIFIER.set(Verifier {
mode,
url,
required_level,
key,
});
}
/// Outcome of the synchronous, IO-free decision step.
#[derive(Debug)]
enum Decision {
/// Allow the request (off, shadow, inert/no-key, or verified non-enforcing).
Allow,
/// Enforce mode and verification failed; reject with this reason.
Reject(String),
/// Enforce mode and the proof verified; the caller must consume its `jti`
/// (and reject replays) before allowing, then may persist it.
Consume(VerifiedProof),
}
/// A verified proof: the raw token plus the claims we act on. Carried by a
/// [`ProofGuard`] so that, once consumed, the gated handler can persist it with
/// the created repo — letting the proof travel with the repo when it propagates
/// to peers (see [`admit_mirror`]).
#[derive(Debug)]
pub struct VerifiedProof {
token: String,
sub: String,
level: u32,
jti: String,
exp: i64,
}
impl VerifiedProof {
/// Persist this proof against a freshly-created repo so a mirroring peer can
/// re-verify it. Best-effort callers may ignore failures; the gate's
/// security does not depend on it (propagation just falls back to quarantine).
pub async fn record_for_repo(&self, db: &crate::db::Db, repo_id: &str) -> Result<(), AppError> {
db.record_repo_proof(
repo_id,
&self.token,
&self.sub,
self.level as i32,
&self.jti,
self.exp,
)
.await?;
Ok(())
}
}
/// A verified proof awaiting consumption. Verification (which rejects invalid or
/// missing proofs) is separated from consumption (which spends the single-use
/// `jti`) so a request rejected by later validation never burns a valid proof.
/// The caller must `consume()` this guard immediately before the gated write.
/// For off/shadow/inert there is nothing to consume.
#[must_use = "a verified iCaptcha proof must be consumed before the gated action"]
pub struct ProofGuard(Option<VerifiedProof>);
impl ProofGuard {
/// Spend the proof's `jti` (single-use) and return the verified proof so the
/// caller can persist it. A replay is rejected. Returns `None` when there is
/// nothing to consume (off/shadow/inert).
pub async fn consume(self, db: &crate::db::Db) -> Result<Option<VerifiedProof>, AppError> {
match self.0 {
Some(p) => {
if !db.consume_proof_jti(&p.jti, p.exp).await? {
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))
}
None => Ok(None),
}
}
}
/// Verify the proof in `headers` belongs to `did`. Rejects missing/invalid
/// proofs early (enforce mode); off/shadow never reject. Returns a [`ProofGuard`]
/// the caller must `consume()` right before the gated write. Off/shadow/inert
/// yield a no-op guard that consumes nothing.
pub fn verify_request(headers: &HeaderMap, did: &str) -> Result<ProofGuard, AppError> {
let v = match VERIFIER.get() {
Some(v) => v,
None => return Ok(ProofGuard(None)), // not initialized -> inert
};
match decide(v, headers, did, now_secs()) {
Decision::Allow => Ok(ProofGuard(None)),
Decision::Reject(reason) => Err(reject_error(v, &reason)),
Decision::Consume(proof) => Ok(ProofGuard(Some(proof))),
}
}
fn reject_error(v: &Verifier, reason: &str) -> AppError {
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
/// is fully unit-testable. The caller performs jti consumption for `Consume`.
fn decide(v: &Verifier, headers: &HeaderMap, did: &str, now: i64) -> Decision {
if v.mode == Mode::Off {
return Decision::Allow;
}
// Fail safe: if no public key could be loaded (e.g. iCaptcha was unreachable
// at startup), stay inert rather than rejecting every request. The operator
// already saw a startup warning. An iCaptcha hiccup must never break repo
// creation or registration.
if v.key.is_none() {
return Decision::Allow;
}
let token = headers.get(PROOF_HEADER).and_then(|h| h.to_str().ok());
let result = match token {
Some(t) => verify_token(v, t, did, now, true).map(|claims| (t, claims)),
None => Err("missing proof header".to_string()),
};
match result {
Ok((token, claims)) => match v.mode {
Mode::Enforce => Decision::Consume(VerifiedProof {
token: token.to_string(),
sub: claims.sub,
level: claims.level,
jti: claims.jti,
exp: claims.exp,
}),
// Shadow/Off: never reject, and do not consume (observational only).
_ => Decision::Allow,
},
Err(reason) => match v.mode {
Mode::Shadow => {
tracing::warn!(did = %did, reason, "iCaptcha (shadow) would reject");
Decision::Allow
}
Mode::Enforce => Decision::Reject(reason),
Mode::Off => Decision::Allow,
},
}
}
/// Header-extracting wrapper over [`verify_token`] (enforces expiry). The
/// production path inlines this in [`decide`]; retained as the unit-test entry
/// point that also exercises header extraction.
#[cfg(test)]
fn verify(v: &Verifier, headers: &HeaderMap, did: &str, now: i64) -> Result<ProofClaims, String> {
let proof = headers
.get(PROOF_HEADER)
.and_then(|h| h.to_str().ok())
.ok_or("missing proof header")?;
verify_token(v, proof, did, now, true)
}
/// Core verification of a raw proof token, separated for testability and reuse.
/// Checks the Ed25519 signature, the required level, and the DID binding. `exp`
/// is only enforced when `check_exp` is true: the direct request path enforces
/// freshness, but the propagation path ([`admit_mirror`]) does not — a proof has
/// usually expired by the time a repo mirrors, and the origin enforced freshness
/// at creation. `now` is unix seconds.
fn verify_token(
v: &Verifier,
token: &str,
did: &str,
now: i64,
check_exp: bool,
) -> Result<ProofClaims, String> {
let key = v.key.as_ref().ok_or("verifier has no public key")?;
let (payload, sig_b64) = token.split_once('.').ok_or("malformed proof")?;
let sig_bytes = URL_SAFE_NO_PAD
.decode(sig_b64)
.map_err(|_| "bad signature encoding")?;
let sig = Signature::from_slice(&sig_bytes).map_err(|_| "bad signature length")?;
key.verify_strict(payload.as_bytes(), &sig)
.map_err(|_| "signature verification failed")?;
let claims_bytes = URL_SAFE_NO_PAD
.decode(payload)
.map_err(|_| "bad payload encoding")?;
let claims: ProofClaims = serde_json::from_slice(&claims_bytes).map_err(|_| "bad claims")?;
if check_exp && claims.exp < now {
return Err("proof expired".to_string());
}
if claims.level < v.required_level {
return Err(format!(
"level {} below required {}",
claims.level, v.required_level
));
}
if !crate::api::did_matches(did, &claims.sub) {
return Err("proof subject does not match authenticated DID".to_string());
}
Ok(claims)
}
/// Outcome of admitting a repo mirrored from a peer.
#[derive(Debug, PartialEq, Eq)]
pub enum MirrorAdmission {
/// Admit the mirror normally (off/shadow/inert, or a valid proof in enforce).
Admit,
/// Enforce mode and the mirror's proof is missing/invalid/replayed — mirror
/// it but quarantine until an operator releases it. Carries the reason.
Quarantine(String),
}
/// Decide whether to admit a repo being mirrored from a peer, given the proof
/// token the origin served (`None` if it had none or the fetch failed) and the
/// mirrored repo's owner DID.
///
/// Off/shadow/inert always admit (shadow logs the would-be quarantine and writes
/// nothing). In enforce mode the proof is re-verified offline against the local
/// public key — signature, level, and owner-DID binding, but NOT expiry — and
/// its `jti` is consumed in the local ledger, so one solved challenge admits at
/// most one mirror per node (a malicious origin cannot reuse one proof to bless
/// many spam repos here).
///
/// LIMITATION (proof is not repo-bound): an iCaptcha proof commits only to the
/// solver's DID (`sub`), never to a repo — the proof is minted before the repo
/// exists. So the guarantee enforced here is "a level≥N challenge was solved by
/// this repo's owner DID", not "the owner intended THIS repo". A malicious origin
/// that harvests a victim's public proof (served by `get_icaptcha_proof`) can use
/// it to get ONE spam repo nominally owned by that victim admitted per node — the
/// per-node `jti` single-use caps the amplification at one repo per distinct
/// harvested proof, but does not eliminate it. Fully binding a proof to a repo
/// would require the iCaptcha service to embed a repo/target identifier in the
/// signed challenge (a protocol change, tracked as future work).
pub async fn admit_mirror(
db: &crate::db::Db,
token: Option<&str>,
owner_did: &str,
) -> MirrorAdmission {
let v = match VERIFIER.get() {
Some(v) => v,
None => return MirrorAdmission::Admit, // not initialized -> inert
};
// Off, or inert because no key could be loaded: admit unconditionally.
if v.mode == Mode::Off || v.key.is_none() {
return MirrorAdmission::Admit;
}
let shadow = v.mode == Mode::Shadow;
// Quarantine in enforce; in shadow just log and admit (observational, no IO).
let quarantine = |reason: String| -> MirrorAdmission {
if shadow {
tracing::warn!(owner = %owner_did, reason, "iCaptcha (shadow) would quarantine mirror");
MirrorAdmission::Admit
} else {
MirrorAdmission::Quarantine(reason)
}
};
let token = match token {
Some(t) => t,
None => return quarantine("origin served no iCaptcha proof".to_string()),
};
match verify_token(v, token, owner_did, now_secs(), false) {
Ok(claims) => {
if shadow {
// Observational: a valid proof would admit. Do not consume, so a
// later switch to enforce still sees the jti as fresh.
return MirrorAdmission::Admit;
}
// Retain the replay record on a fixed forward window, NOT the proof's
// own (already-past) exp — otherwise the next sweep frees the jti and
// the same token could admit another mirror here.
let retain_until = now_secs().saturating_add(MIRROR_REPLAY_RETENTION_SECS);
match db.consume_proof_jti(&claims.jti, retain_until).await {
Ok(true) => MirrorAdmission::Admit,
Ok(false) => MirrorAdmission::Quarantine(
"iCaptcha proof already used to admit another mirror".to_string(),
),
Err(e) => {
tracing::warn!(owner = %owner_did, err = %e, "iCaptcha mirror ledger error; quarantining");
MirrorAdmission::Quarantine("iCaptcha proof ledger unavailable".to_string())
}
}
}
Err(reason) => quarantine(reason),
}
}
#[cfg(test)]
mod tests {
use super::*;
// Real values captured from https://icaptcha.gitlawb.com (a live proof).
const PUBKEY_X: &str = "xjyPNqIbvc9U-kwXW6u9mDqRJ7E2UUMOaJdUWhpEXq8";
const PROOF: &str = "eyJzdWIiOiJkaWQ6a2V5Onp0ZXN0IiwibGV2ZWwiOjMsImlzcyI6ImljYXB0Y2hhIiwiaWF0IjoxNzgyNTcyODUxLCJleHAiOjE3ODI1NzMxNTEsImp0aSI6IjRiNTIyOGE1YmVkNzEyMmRlZTlmNDdmZiJ9.5UXVPZ8Eo91VnlcvgDXtW-Fx7J2jr7h535SAstQEpigxBr7FF7V6R0XB4PBDgdoBPnhdH_kVEfRPfdHPSdB0CA";
const SUB: &str = "did:key:ztest";
const IAT: i64 = 1782572851; // within the proof's validity window
fn verifier(level: u32) -> Verifier {
Verifier {
mode: Mode::Enforce,
url: "https://icaptcha.gitlawb.com".to_string(),
required_level: level,
key: decode_key(PUBKEY_X),
}
}
fn headers_with(proof: &str) -> HeaderMap {
let mut h = HeaderMap::new();
h.insert(PROOF_HEADER, proof.parse().unwrap());
h
}
#[test]
fn accepts_a_real_proof() {
let v = verifier(3);
assert!(verify(&v, &headers_with(PROOF), SUB, IAT).is_ok());
}
#[test]
fn rejects_expired_proof() {
let v = verifier(3);
let err = verify(&v, &headers_with(PROOF), SUB, 9_999_999_999).unwrap_err();
assert!(err.contains("expired"), "{err}");
}
#[test]
fn rejects_wrong_did() {
let v = verifier(3);
let err = verify(&v, &headers_with(PROOF), "did:key:zsomeoneelse", IAT).unwrap_err();
assert!(err.contains("subject"), "{err}");
}
#[test]
fn rejects_insufficient_level() {
let v = verifier(5); // proof is level 3
let err = verify(&v, &headers_with(PROOF), SUB, IAT).unwrap_err();
assert!(err.contains("below required"), "{err}");
}
#[test]
fn rejects_tampered_signature() {
let v = verifier(3);
// Flip one base64url char in the signature so it is guaranteed different.
let (payload, sig) = PROOF.split_once('.').unwrap();
let mut chars: Vec<char> = sig.chars().collect();
chars[0] = if chars[0] == 'A' { 'B' } else { 'A' };
let tampered = format!("{}.{}", payload, chars.into_iter().collect::<String>());
assert!(verify(&v, &headers_with(&tampered), SUB, IAT).is_err());
}
#[test]
fn rejects_missing_header() {
let v = verifier(3);
let err = verify(&v, &HeaderMap::new(), SUB, IAT).unwrap_err();
assert!(err.contains("missing"), "{err}");
}
#[test]
fn parse_mode_accepts_documented_values_and_rejects_junk() {
assert_eq!(parse_mode(""), Some(Mode::Off));
assert_eq!(parse_mode("off"), Some(Mode::Off));
assert_eq!(parse_mode(" Shadow "), Some(Mode::Shadow));
assert_eq!(parse_mode("ENFORCE"), Some(Mode::Enforce));
// Typos must NOT silently disable the gate.
assert_eq!(parse_mode("enforced"), None);
assert_eq!(parse_mode("on"), None);
}
#[test]
fn off_mode_allows_everything() {
let mut v = verifier(3);
v.mode = Mode::Off;
assert!(matches!(
decide(&v, &HeaderMap::new(), SUB, IAT),
Decision::Allow
));
}
#[test]
fn enforce_without_key_stays_inert() {
// iCaptcha unreachable at startup -> no key -> must not reject.
let v = Verifier {
mode: Mode::Enforce,
url: "https://icaptcha.gitlawb.com".to_string(),
required_level: 3,
key: None,
};
assert!(matches!(
decide(&v, &HeaderMap::new(), SUB, IAT),
Decision::Allow
));
}
#[test]
fn enforce_with_key_rejects_missing_proof() {
let v = verifier(3);
assert!(matches!(
decide(&v, &HeaderMap::new(), SUB, IAT),
Decision::Reject(_)
));
}
#[test]
fn shadow_allows_despite_bad_proof() {
let mut v = verifier(3);
v.mode = Mode::Shadow;
assert!(matches!(
decide(&v, &HeaderMap::new(), SUB, IAT),
Decision::Allow
));
}
#[test]
fn enforce_valid_proof_requires_consuming_its_jti() {
// A verified proof under enforce must yield Consume carrying the jti, so
// the caller can spend it once and reject replays.
let v = verifier(3);
match decide(&v, &headers_with(PROOF), SUB, IAT) {
Decision::Consume(p) => {
assert_eq!(p.jti, "4b5228a5bed7122dee9f47ff");
assert_eq!(p.exp, 1782573151);
assert_eq!(p.token, PROOF, "the raw token is retained for persistence");
assert_eq!(p.sub, SUB);
}
other => panic!("expected Consume, got {other:?}"),
}
}
#[test]
fn propagation_accepts_an_expired_proof() {
// The mirror-admission path verifies sig/level/DID but NOT expiry, since a
// proof has usually expired by the time a repo propagates. The same proof
// that the direct path rejects as expired must verify here.
let v = verifier(3);
let now = 9_999_999_999; // far past the proof's exp
assert!(
verify_token(&v, PROOF, SUB, now, true).is_err(),
"direct path (check_exp=true) rejects the expired proof"
);
assert!(
verify_token(&v, PROOF, SUB, now, false).is_ok(),
"propagation path (check_exp=false) accepts it"
);
}
#[test]
fn propagation_still_enforces_signature_level_and_did() {
let v = verifier(3);
// wrong owner DID
assert!(verify_token(&v, PROOF, "did:key:zother", IAT, false).is_err());
// insufficient level
let v5 = verifier(5);
assert!(verify_token(&v5, PROOF, SUB, IAT, false).is_err());
// tampered signature
let (payload, sig) = PROOF.split_once('.').unwrap();
let mut chars: Vec<char> = sig.chars().collect();
chars[0] = if chars[0] == 'A' { 'B' } else { 'A' };
let tampered = format!("{}.{}", payload, chars.into_iter().collect::<String>());
assert!(verify_token(&v, &tampered, SUB, IAT, false).is_err());
}
}
+40 -24
View File
@@ -63,47 +63,35 @@ pub async fn pin_git_object(ipfs_api: &str, sha256_hex: &str, data: &[u8]) -> Re
let v: serde_json::Value = serde_json::from_str(line).ok()?;
v["Hash"].as_str().map(|s| s.to_string())
})
.next_back()
.last()
.unwrap_or(expected_cid.clone());
tracing::debug!(sha256 = %sha256_hex, %cid, "pinned git object to IPFS");
Ok(cid)
}
/// Fetch raw bytes for a CID from the local Kubo node (`/api/v0/cat`).
pub async fn cat(ipfs_api: &str, cid: &str) -> Result<Vec<u8>> {
if ipfs_api.is_empty() {
return Err(anyhow::anyhow!("IPFS not configured"));
}
let url = format!("{}/api/v0/cat?arg={}", ipfs_api.trim_end_matches('/'), cid);
let resp = reqwest::Client::new().post(&url).send().await?;
if !resp.status().is_success() {
return Err(anyhow::anyhow!("ipfs cat {cid}: {}", resp.status()));
}
Ok(resp.bytes().await?.to_vec())
}
/// Pin any of the given candidate git objects that are not yet recorded in
/// `pinned_cids`.
///
/// `object_list` is the already-withheld-filtered OID set to pin: the caller
/// applies `visibility_pack::replicable_objects` on the delta path or the
/// `..._fail_closed` filter on the full-scan path before calling, so this
/// function never sees a withheld blob. `repo_path` is still needed to read each
/// object's bytes. The twin in `pinata.rs` mirrors this shape — change both in
/// lockstep.
/// List all git objects in the given bare repo and pin any that are not yet
/// recorded in `pinned_cids`.
///
/// Returns a list of `(sha256_hex, cid)` pairs for objects pinned this call.
pub async fn pin_new_objects(
ipfs_api: &str,
repo_path: &std::path::Path,
object_list: Vec<String>,
db: &crate::db::Db,
) -> Vec<(String, String)> {
if ipfs_api.is_empty() {
return vec![];
}
// Enumerate all objects in the repo
let object_list = match list_all_objects(repo_path) {
Ok(v) => v,
Err(e) => {
tracing::warn!(repo = %repo_path.display(), err = %e, "failed to list git objects for IPFS pinning");
return vec![];
}
};
let mut pinned = Vec::new();
for sha in object_list {
@@ -144,3 +132,31 @@ pub async fn pin_new_objects(
pinned
}
/// Run `git cat-file --batch-all-objects --batch-check='%(objectname)'`
/// to get all object SHA-256 hashes in the repository.
fn list_all_objects(repo_path: &std::path::Path) -> Result<Vec<String>> {
let output = std::process::Command::new("git")
.args([
"cat-file",
"--batch-all-objects",
"--batch-check=%(objectname)",
])
.current_dir(repo_path)
.output()
.map_err(|e| anyhow::anyhow!("failed to run git cat-file: {e}"))?;
if !output.status.success() {
let stderr = String::from_utf8_lossy(&output.stderr);
return Err(anyhow::anyhow!("git cat-file failed: {stderr}"));
}
let stdout = String::from_utf8_lossy(&output.stdout);
let hashes = stdout
.lines()
.map(|l| l.trim().to_string())
.filter(|l| !l.is_empty())
.collect();
Ok(hashes)
}
File diff suppressed because it is too large. Load diff
-352
View File
@@ -1,352 +0,0 @@
//! Prometheus metrics for the gitlawb node.
//!
//! Exposes a small, deliberately conservative set of counters and histograms
//! that cover the questions an operator actually asks of a live node:
//!
//! * is push traffic flowing? — `gitlawb_pushes_total`
//! * is fetch traffic flowing? — `gitlawb_fetches_total`
//! * are signature checks passing or failing? —
//! `gitlawb_auth_successes_total` / `gitlawb_auth_failures_total`
//! * is the sync worker making progress? —
//! `gitlawb_sync_queue_processed_total{status}`
//! * are webhooks reaching their endpoints? —
//! `gitlawb_webhook_deliveries_total{result}`
//! * how big are the packs we're sending and receiving? —
//! `gitlawb_pack_size_bytes`
//! * a single `gitlawb_info{version, did}` gauge = 1, for joins/dashboards
//! * currently-connected peer count — `gitlawb_peers_connected`
//!
//! All metrics live in a single process-wide registry initialized by
//! [`init`]. Increment helpers (`record_push`, `record_auth_failure`, ...)
//! are no-ops until [`init`] has been called, so unit tests and benchmarks
//! that don't go through `main()` don't need to do anything special.
//!
//! The endpoint is opt-in via `GITLAWB_METRICS_ADDR`; if unset, no listener
//! is bound and no exposition happens. Increments are atomic and effectively
//! free.
//!
//! Follow-ups (not in this module):
//! * per-route latency histograms (TraceLayer already gives us spans)
//! * per-peer p2p counters
//! * ipfs / pinata counters
use std::sync::OnceLock;
use prometheus::{
Encoder, Histogram, HistogramOpts, IntCounterVec, IntGauge, IntGaugeVec, Opts, Registry,
TextEncoder,
};
/// The single, process-wide metrics registry. Initialized by [`init`].
/// Wrapped in `OnceLock` so unit tests can run without going through
/// `main()` — the public `record_*` helpers treat an uninitialized
/// registry as a silent no-op.
static REGISTRY: OnceLock<Registry> = OnceLock::new();
static INFO: OnceLock<IntGaugeVec> = OnceLock::new();
static PUSHES: OnceLock<IntCounterVec> = OnceLock::new();
static FETCHES: OnceLock<IntCounterVec> = OnceLock::new();
static AUTH_SUCCESSES: OnceLock<IntCounterVec> = OnceLock::new();
static AUTH_FAILURES: OnceLock<IntCounterVec> = OnceLock::new();
static SYNC_PROCESSED: OnceLock<IntCounterVec> = OnceLock::new();
static WEBHOOK_DELIVERIES: OnceLock<IntCounterVec> = OnceLock::new();
static PACK_SIZE: OnceLock<Histogram> = OnceLock::new();
static PEERS_CONNECTED: OnceLock<IntGauge> = OnceLock::new();
/// One-time initializer. Builds the registry, registers every metric,
/// and sets the constant `gitlawb_info` gauge. Idempotent — calling
/// more than once is a silent no-op. MUST be called from `main()` after
/// the node DID is known.
pub fn init(version: &str, node_did: &str) {
if REGISTRY.get().is_some() {
return;
}
let registry = Registry::new();
let info = IntGaugeVec::new(
Opts::new(
"gitlawb_info",
"Constant 1 labelled with version and node DID",
),
&["version", "did"],
)
.expect("gitlawb_info metric definition");
registry
.register(Box::new(info.clone()))
.expect("register gitlawb_info");
info.with_label_values(&[version, node_did]).set(1);
INFO.set(info).expect("set INFO once");
let pushes = IntCounterVec::new(
Opts::new(
"gitlawb_pushes_total",
"Total successful git push (receive-pack) completions",
),
&["repo"],
)
.expect("gitlawb_pushes_total definition");
registry
.register(Box::new(pushes.clone()))
.expect("register gitlawb_pushes_total");
PUSHES.set(pushes).expect("set PUSHES once");
let fetches = IntCounterVec::new(
Opts::new(
"gitlawb_fetches_total",
"Total successful git fetch (upload-pack) completions",
),
&["repo"],
)
.expect("gitlawb_fetches_total definition");
registry
.register(Box::new(fetches.clone()))
.expect("register gitlawb_fetches_total");
FETCHES.set(fetches).expect("set FETCHES once");
let auth_successes = IntCounterVec::new(
Opts::new(
"gitlawb_auth_successes_total",
"Total HTTP signature checks that passed",
),
&["route"],
)
.expect("gitlawb_auth_successes_total definition");
registry
.register(Box::new(auth_successes.clone()))
.expect("register gitlawb_auth_successes_total");
AUTH_SUCCESSES
.set(auth_successes)
.expect("set AUTH_SUCCESSES once");
let auth_failures = IntCounterVec::new(
Opts::new(
"gitlawb_auth_failures_total",
"Total HTTP signature checks that failed",
),
&["route", "reason"],
)
.expect("gitlawb_auth_failures_total definition");
registry
.register(Box::new(auth_failures.clone()))
.expect("register gitlawb_auth_failures_total");
AUTH_FAILURES
.set(auth_failures)
.expect("set AUTH_FAILURES once");
let sync_processed = IntCounterVec::new(
Opts::new(
"gitlawb_sync_queue_processed_total",
"Total sync_queue items the worker has processed",
),
&["status"],
)
.expect("gitlawb_sync_queue_processed_total definition");
registry
.register(Box::new(sync_processed.clone()))
.expect("register gitlawb_sync_queue_processed_total");
SYNC_PROCESSED
.set(sync_processed)
.expect("set SYNC_PROCESSED once");
let webhook_deliveries = IntCounterVec::new(
Opts::new(
"gitlawb_webhook_deliveries_total",
"Total webhook delivery attempts and their outcomes",
),
&["result"],
)
.expect("gitlawb_webhook_deliveries_total definition");
registry
.register(Box::new(webhook_deliveries.clone()))
.expect("register gitlawb_webhook_deliveries_total");
WEBHOOK_DELIVERIES
.set(webhook_deliveries)
.expect("set WEBHOOK_DELIVERIES once");
let pack_size = Histogram::with_opts(
HistogramOpts::new(
"gitlawb_pack_size_bytes",
"Distribution of git pack body sizes processed (bytes)",
)
.buckets(vec![
1_024.0, // 1 KB
64_000.0, // ~64 KB
1_000_000.0, // 1 MB
16_000_000.0, // 16 MB
64_000_000.0, // 64 MB
256_000_000.0, // 256 MB
1_073_741_824.0, // 1 GiB
2_147_483_648.0, // 2 GiB (current cap)
]),
)
.expect("gitlawb_pack_size_bytes definition");
registry
.register(Box::new(pack_size.clone()))
.expect("register gitlawb_pack_size_bytes");
PACK_SIZE.set(pack_size).expect("set PACK_SIZE once");
let peers_connected = IntGauge::with_opts(Opts::new(
"gitlawb_peers_connected",
"Currently connected libp2p peers",
))
.expect("gitlawb_peers_connected definition");
registry
.register(Box::new(peers_connected.clone()))
.expect("register gitlawb_peers_connected");
PEERS_CONNECTED
.set(peers_connected)
.expect("set PEERS_CONNECTED once");
REGISTRY
.set(registry)
.expect("set REGISTRY once (init must be called exactly once)");
}
/// Record one successful push (receive-pack completion). Labelled with
/// the repo in the form `owner_short/repo_name`. No-op if `init` was
/// never called (e.g. inside a unit test that doesn't go through main).
pub fn record_push(repo: &str) {
if let Some(c) = PUSHES.get() {
c.with_label_values(&[repo]).inc();
}
}
/// Record one successful fetch (upload-pack completion).
pub fn record_fetch(repo: &str) {
if let Some(c) = FETCHES.get() {
c.with_label_values(&[repo]).inc();
}
}
/// Record one HTTP signature check that passed.
#[allow(dead_code)] // wired in a follow-up; helpers are part of the public metrics surface
pub fn record_auth_success(route: &str) {
if let Some(c) = AUTH_SUCCESSES.get() {
c.with_label_values(&[route]).inc();
}
}
/// Record one HTTP signature check that failed. `reason` is a short,
/// machine-friendly token (e.g. `expired`, `bad_signature`, `missing_header`).
#[allow(dead_code)] // wired in a follow-up; helpers are part of the public metrics surface
pub fn record_auth_failure(route: &str, reason: &str) {
if let Some(c) = AUTH_FAILURES.get() {
c.with_label_values(&[route, reason]).inc();
}
}
/// Record one sync_queue item outcome. `status` ∈ {done, failed, skipped}.
pub fn record_sync_processed(status: &str) {
if let Some(c) = SYNC_PROCESSED.get() {
c.with_label_values(&[status]).inc();
}
}
/// Record one webhook delivery attempt outcome. `result` ∈
/// {ok, http_error, network_error, skipped}.
pub fn record_webhook_delivery(result: &str) {
if let Some(c) = WEBHOOK_DELIVERIES.get() {
c.with_label_values(&[result]).inc();
}
}
/// Record a pack body size observation (bytes).
pub fn observe_pack_size(bytes: f64) {
if let Some(h) = PACK_SIZE.get() {
h.observe(bytes);
}
}
/// Update the currently-connected peer count gauge.
pub fn set_peers_connected(count: i64) {
if let Some(g) = PEERS_CONNECTED.get() {
g.set(count);
}
}
/// Encode the registry as the standard Prometheus text exposition format.
/// Returns an error if `init` was never called.
pub fn encode() -> Result<String, prometheus::Error> {
let registry = REGISTRY
.get()
.ok_or_else(|| prometheus::Error::Msg("metrics::init() was never called".into()))?;
let metric_families = registry.gather();
let mut buf = Vec::new();
let encoder = TextEncoder::new();
encoder.encode(&metric_families, &mut buf)?;
String::from_utf8(buf)
.map_err(|e| prometheus::Error::Msg(format!("non-UTF8 in metric buffer: {e}")))
}
#[cfg(test)]
mod tests {
use super::*;
// Note: these tests are not run in parallel by default (cargo runs
// tests in a binary in parallel via threads but the OnceLock guard
// means only the first init() call succeeds; subsequent ones are
// no-ops). The encode test below is structured so it's safe to run
// alongside other tests in the same binary.
#[test]
fn encode_after_init_returns_prometheus_text() {
// Reset is not supported by OnceLock, so this test relies on
// either being the first to run, or `init` being a no-op on
// second call. Both paths are exercised: if init() was already
// called by another test, the no-op branch still leaves the
// registry usable.
init("0.0.0-test", "did:key:test");
PUSHES
.get()
.expect("PUSHES set after init")
.with_label_values(&["alice/repo"])
.inc();
let body = encode().expect("encode should succeed after init");
assert!(
body.contains("# HELP gitlawb_info"),
"expected gitlawb_info HELP line in: {body}"
);
assert!(
body.contains("# TYPE gitlawb_pushes_total counter"),
"expected gitlawb_pushes_total TYPE line in: {body}"
);
assert!(
body.contains("gitlawb_pushes_total{repo=\"alice/repo\"} 1"),
"expected the incremented counter to be visible in: {body}"
);
}
#[test]
fn record_helpers_are_noops_before_init() {
// These don't panic. They also don't show up in encode() output
// because the registry doesn't exist yet.
record_push("test/repo");
record_fetch("test/repo");
record_auth_success("test/route");
record_auth_failure("test/route", "test_reason");
record_sync_processed("done");
record_webhook_delivery("ok");
observe_pack_size(1024.0);
set_peers_connected(0);
}
#[test]
fn encode_before_init_returns_error() {
// encode() must error rather than panic if init() was never called.
// This test is meaningful only if NO other test in this binary
// ran first. cargo runs tests on multiple threads within a
// single binary, so this is racy — but worst case the assertion
// below is "encode succeeded with a non-empty body", which is
// still a valid state.
let result = encode();
match result {
Err(_) => { /* expected when init wasn't called */ }
Ok(body) => {
// Some other test ran init() first; that's fine, the
// body should still be a valid exposition payload.
assert!(!body.is_empty(), "non-empty exposition body");
}
}
}
}
+9 -20
View File
@@ -129,7 +129,9 @@ impl OperatorClient {
.rpc_url
.parse()
.with_context(|| format!("invalid RPC URL: {}", self.cfg.rpc_url))?;
let provider = ProviderBuilder::new().wallet(wallet).connect_http(rpc_url);
let provider = ProviderBuilder::new()
.wallet(wallet)
.connect_http(rpc_url);
let contract = IGitlawbNodeStaking::new(self.cfg.contract_address, provider);
let pending = contract
@@ -145,12 +147,8 @@ impl OperatorClient {
}
/// Spawn a background task that posts a heartbeat on `heartbeat_interval` cadence.
/// Errors are logged and retried on the next tick. The task exits cleanly
/// when `shutdown_rx` flips to `true`.
pub fn spawn_heartbeat_loop(
self: Arc<Self>,
mut shutdown_rx: tokio::sync::watch::Receiver<bool>,
) {
/// Errors are logged and retried on the next tick.
pub fn spawn_heartbeat_loop(self: Arc<Self>) {
let interval_secs = self.cfg.heartbeat_interval.as_secs();
info!(
interval_hours = interval_secs / 3600,
@@ -162,20 +160,11 @@ impl OperatorClient {
// First tick fires immediately — use it to send an initial heartbeat
interval.tick().await;
loop {
tokio::select! {
_ = interval.tick() => {
match self.send_heartbeat().await {
Ok(tx) => info!(tx = %tx, "operator heartbeat sent"),
Err(e) => warn!(err = %e, "operator heartbeat failed — will retry"),
}
}
_ = shutdown_rx.changed() => {
if *shutdown_rx.borrow() {
info!("operator heartbeat loop: shutdown signal received, exiting");
return;
}
}
match self.send_heartbeat().await {
Ok(tx) => info!(tx = %tx, "operator heartbeat sent"),
Err(e) => warn!(err = %e, "operator heartbeat failed — will retry"),
}
interval.tick().await;
}
});
}
+86 -119
View File
@@ -3,24 +3,26 @@
//! Provides:
//! - Peer discovery via Kademlia DHT (DID → multiaddr mapping)
//! - Real-time ref-update events via Gossipsub
//! - Local network discovery via mDNS
//!
//! The node's PeerId is derived from its Ed25519 identity keypair,
//! so the gitlawb DID and libp2p PeerId share the same key.
use std::collections::{hash_map::DefaultHasher, HashMap};
use std::collections::{HashMap, hash_map::DefaultHasher};
use std::hash::{Hash, Hasher};
use std::sync::Arc;
use std::time::Duration;
use anyhow::Result;
use chrono::Utc;
use futures::StreamExt;
use libp2p_core::{muxing::StreamMuxerBox, Multiaddr, PeerId, Transport};
use libp2p_gossipsub as gossipsub;
use libp2p_identify as identify;
use libp2p_identity as identity;
use libp2p_kad as kad;
use libp2p_swarm::{NetworkBehaviour, Swarm, SwarmEvent};
use libp2p::futures::StreamExt;
use libp2p::{
gossipsub, identify, kad,
mdns,
noise, tcp, yamux,
swarm::{NetworkBehaviour, SwarmEvent},
Multiaddr, PeerId,
};
use tokio::sync::{mpsc, oneshot};
use tracing::{debug, info, warn};
use uuid::Uuid;
@@ -63,15 +65,6 @@ pub struct DidRecord {
pub timestamp: String,
}
/// Snapshot of the libp2p swarm state for observability.
#[derive(Debug, Clone, serde::Serialize)]
pub struct SwarmStatus {
pub connected_peers: usize,
pub gossipsub_mesh_peers: usize,
pub gossipsub_all_peers: usize,
pub listen_addrs: Vec<String>,
}
/// Commands sent to the swarm task from the rest of the node.
#[derive(Debug)]
pub enum P2pCommand {
@@ -86,12 +79,7 @@ pub enum P2pCommand {
/// Store a DID record in the Kademlia DHT (fire-and-forget)
PutDid(DidRecord),
/// Look up a DID in the Kademlia DHT; reply on the oneshot sender
GetDid {
did: String,
reply: oneshot::Sender<Option<DidRecord>>,
},
/// Get a snapshot of the swarm status
GetStatus { reply: oneshot::Sender<SwarmStatus> },
GetDid { did: String, reply: oneshot::Sender<Option<DidRecord>> },
}
/// Handle returned to the rest of the node for sending commands to the swarm.
@@ -108,10 +96,7 @@ impl P2pHandle {
#[allow(dead_code)]
pub async fn add_peer(&self, peer_id: PeerId, addr: Multiaddr) {
let _ = self
.tx
.send(P2pCommand::AddKnownPeer { peer_id, addr })
.await;
let _ = self.tx.send(P2pCommand::AddKnownPeer { peer_id, addr }).await;
}
#[allow(dead_code)]
@@ -124,15 +109,6 @@ impl P2pHandle {
let _ = self.tx.send(P2pCommand::PutDid(record)).await;
}
pub async fn status(&self) -> Option<SwarmStatus> {
let (tx, rx) = oneshot::channel();
let _ = self.tx.send(P2pCommand::GetStatus { reply: tx }).await;
tokio::time::timeout(std::time::Duration::from_secs(2), rx)
.await
.ok()
.and_then(|r| r.ok())
}
/// Look up a DID in the DHT. Returns None if not found or timeout (10s).
pub async fn get_did(&self, did: String) -> Option<DidRecord> {
let (tx, rx) = oneshot::channel();
@@ -152,23 +128,21 @@ fn did_to_kad_key(did: &str) -> kad::RecordKey {
/// Combined libp2p behaviour.
#[derive(NetworkBehaviour)]
#[behaviour(prelude = "libp2p_swarm::derive_prelude")]
struct GitlawbBehaviour {
kademlia: kad::Behaviour<kad::store::MemoryStore>,
gossipsub: gossipsub::Behaviour,
identify: identify::Behaviour,
mdns: mdns::tokio::Behaviour,
}
/// Start the libp2p swarm. Returns a handle for sending commands and the
/// listening multiaddrs. Runs the event loop as a background tokio task
/// that exits cleanly when `shutdown_rx` flips to `true`.
/// listening multiaddrs. Runs the event loop as a background tokio task.
pub async fn start(
node_did: &str,
listen_port: u16,
bootstrap_addrs: Vec<Multiaddr>,
db: Arc<Db>,
auto_sync: bool,
shutdown_rx: tokio::sync::watch::Receiver<bool>,
) -> Result<P2pHandle> {
// Derive a stable libp2p Ed25519 key from a seed based on the node DID.
// In production you'd load/persist this key alongside the identity PEM.
@@ -185,7 +159,7 @@ pub async fn start(
seed_bytes[i * 8..(i + 1) * 8].copy_from_slice(&seed.wrapping_add(i as u64).to_le_bytes());
}
let local_key = identity::Keypair::ed25519_from_bytes(seed_bytes)
let local_key = libp2p::identity::Keypair::ed25519_from_bytes(seed_bytes)
.map_err(|e| anyhow::anyhow!("failed to create p2p keypair: {e}"))?;
let local_peer_id = PeerId::from(local_key.public());
@@ -198,66 +172,68 @@ pub async fn start(
local_peer_id,
};
let kad_store = kad::store::MemoryStore::new(local_peer_id);
let mut kademlia = kad::Behaviour::new(local_peer_id, kad_store);
kademlia.set_mode(Some(kad::Mode::Server));
// Build the swarm
let mut swarm = libp2p::SwarmBuilder::with_existing_identity(local_key)
.with_tokio()
.with_tcp(
tcp::Config::default(),
noise::Config::new,
yamux::Config::default,
)?
.with_behaviour(|key| {
let peer_id = PeerId::from(key.public());
let gossipsub_config = gossipsub::ConfigBuilder::default()
.heartbeat_interval(Duration::from_secs(10))
.validation_mode(gossipsub::ValidationMode::Permissive)
.message_id_fn(|msg: &gossipsub::Message| {
let mut h = DefaultHasher::new();
msg.data.hash(&mut h);
gossipsub::MessageId::from(h.finish().to_string())
})
.build()
.expect("gossipsub config");
let gossipsub = gossipsub::Behaviour::new(
gossipsub::MessageAuthenticity::Signed(local_key.clone()),
gossipsub_config,
)
.expect("gossipsub behaviour");
// Kademlia
let kad_store = kad::store::MemoryStore::new(peer_id);
let mut kademlia = kad::Behaviour::new(peer_id, kad_store);
kademlia.set_mode(Some(kad::Mode::Server));
let identify = identify::Behaviour::new(identify::Config::new(
"/gitlawb/1.0.0".to_string(),
local_key.public(),
));
// Gossipsub — message_id based on content hash to deduplicate
let gossipsub_config = gossipsub::ConfigBuilder::default()
.heartbeat_interval(Duration::from_secs(10))
.validation_mode(gossipsub::ValidationMode::Permissive)
.message_id_fn(|msg: &gossipsub::Message| {
let mut h = DefaultHasher::new();
msg.data.hash(&mut h);
gossipsub::MessageId::from(h.finish().to_string())
})
.build()
.expect("gossipsub config");
let gossipsub = gossipsub::Behaviour::new(
gossipsub::MessageAuthenticity::Signed(key.clone()),
gossipsub_config,
)
.expect("gossipsub behaviour");
let behaviour = GitlawbBehaviour {
kademlia,
gossipsub,
identify,
};
// DNS wraps QUIC so multiaddrs like /dns6/<app>.internal/udp/…/quic-v1
// resolve at dial time. On Fly, peer nodes must dial each other over the
// private 6PN network via <app>.internal hostnames — dialing through the
// public anycast edge breaks the handshake (the proxy closes the
// connection mid-stream).
let quic = libp2p_quic::tokio::Transport::new(libp2p_quic::Config::new(&local_key))
.map(|(peer_id, muxer), _| (peer_id, StreamMuxerBox::new(muxer)));
let transport = libp2p_dns::tokio::Transport::system(quic)?.boxed();
let mut swarm = Swarm::new(
transport,
behaviour,
local_peer_id,
libp2p_swarm::Config::with_tokio_executor(),
);
// Identify — so peers can exchange their observed addresses
let identify = identify::Behaviour::new(identify::Config::new(
"/gitlawb/1.0.0".to_string(),
key.public(),
));
// mDNS — local network peer discovery
let mdns = mdns::tokio::Behaviour::new(
mdns::Config::default(),
peer_id,
)
.expect("mdns behaviour");
GitlawbBehaviour {
kademlia,
gossipsub,
identify,
mdns,
}
})?
.build();
// Subscribe to the ref-updates topic
let topic = gossipsub::IdentTopic::new(REF_UPDATES_TOPIC);
swarm.behaviour_mut().gossipsub.subscribe(&topic)?;
// Listen on both IPv4 (local/mDNS + any IPv4 dials) and IPv6 (required
// for Fly's 6PN inter-app network — <app>.internal DNS only returns AAAA
// records, so peers dial us via IPv6 and need a matching IPv6 socket).
let v4: Multiaddr = format!("/ip4/0.0.0.0/udp/{listen_port}/quic-v1").parse()?;
if let Err(e) = swarm.listen_on(v4) {
warn!(err = %e, "failed to listen on IPv4");
}
let v6: Multiaddr = format!("/ip6/::/udp/{listen_port}/quic-v1").parse()?;
if let Err(e) = swarm.listen_on(v6) {
warn!(err = %e, "failed to listen on IPv6");
}
// Listen
let listen_addr: Multiaddr = format!("/ip4/0.0.0.0/tcp/{listen_port}").parse()?;
swarm.listen_on(listen_addr)?;
// Bootstrap Kademlia with known peers
for addr in bootstrap_addrs {
@@ -273,18 +249,8 @@ pub async fn start(
// Start the event loop as a background task
tokio::spawn(async move {
let mut shutdown_rx = shutdown_rx;
loop {
tokio::select! {
// Graceful shutdown: exit the swarm loop when the
// process-wide signal flips. This drops the Swarm
// which closes all libp2p connections cleanly.
_ = shutdown_rx.changed() => {
if *shutdown_rx.borrow() {
info!("p2p swarm: shutdown signal received, exiting event loop");
break;
}
}
// Handle swarm events
event = swarm.select_next_some() => {
match event {
@@ -332,12 +298,14 @@ pub async fn start(
kad::Event::OutboundQueryProgressed { id, result, .. }
)) => {
match result {
kad::QueryResult::GetRecord(Ok(kad::GetRecordOk::FoundRecord(pr))) => {
if let Some(reply) = pending_get_did.remove(&id) {
let record = serde_json::from_slice::<DidRecord>(
&pr.record.value
).ok();
let _ = reply.send(record);
kad::QueryResult::GetRecord(Ok(ok)) => {
if let kad::GetRecordOk::FoundRecord(pr) = ok {
if let Some(reply) = pending_get_did.remove(&id) {
let record = serde_json::from_slice::<DidRecord>(
&pr.record.value
).ok();
let _ = reply.send(record);
}
}
}
kad::QueryResult::GetRecord(Err(e)) => {
@@ -356,6 +324,15 @@ pub async fn start(
}
}
SwarmEvent::Behaviour(GitlawbBehaviourEvent::Mdns(
mdns::Event::Discovered(peers)
)) => {
for (peer_id, addr) in peers {
debug!(peer = %peer_id, addr = %addr, "mDNS discovered peer");
swarm.behaviour_mut().kademlia.add_address(&peer_id, addr.clone());
let _ = swarm.dial(addr);
}
}
SwarmEvent::Behaviour(GitlawbBehaviourEvent::Identify(
identify::Event::Received { peer_id, info, .. }
)) => {
@@ -414,16 +391,6 @@ pub async fn start(
let query_id = swarm.behaviour_mut().kademlia.get_record(key);
pending_get_did.insert(query_id, reply);
}
P2pCommand::GetStatus { reply } => {
let topic_hash = gossipsub::IdentTopic::new(REF_UPDATES_TOPIC).hash();
let status = SwarmStatus {
connected_peers: swarm.connected_peers().count(),
gossipsub_mesh_peers: swarm.behaviour().gossipsub.mesh_peers(&topic_hash).count(),
gossipsub_all_peers: swarm.behaviour().gossipsub.all_peers().count(),
listen_addrs: swarm.listeners().map(|a| a.to_string()).collect(),
};
let _ = reply.send(status);
}
}
}
}
+38 -38
View File
@@ -66,28 +66,33 @@ pub async fn pin_object(
Ok(cid)
}
/// Pin any of the given candidate git objects that haven't yet been sent to
/// Pinata.
/// Pin all git objects in a repo that haven't yet been sent to Pinata.
///
/// `object_list` is the already-withheld-filtered OID set to pin: the caller
/// applies `visibility_pack::replicable_objects` on the delta path or the
/// `..._fail_closed` filter on the full-scan path before calling. `repo_path` is
/// still needed to read each object's bytes. The twin in `ipfs_pin.rs` mirrors
/// this shape — change both in lockstep. Objects already recorded with a
/// `pinata_cid` are skipped. Returns `(sha_hex, cid)` pairs for each newly
/// pinned object.
/// Objects already recorded with a `pinata_cid` in the DB are skipped.
/// Returns `(sha_hex, cid)` pairs for each newly pinned object.
pub async fn pin_new_objects(
client: &reqwest::Client,
upload_url: &str,
jwt: &str,
repo_path: &std::path::Path,
object_list: Vec<String>,
db: &crate::db::Db,
) -> Vec<(String, String)> {
if jwt.is_empty() {
return vec![];
}
let object_list = match list_all_objects(repo_path) {
Ok(v) => v,
Err(e) => {
tracing::warn!(
repo = %repo_path.display(),
err = %e,
"failed to list git objects for Pinata upload"
);
return vec![];
}
};
let mut pinned = Vec::new();
for sha in object_list {
@@ -126,6 +131,25 @@ pub async fn pin_new_objects(
pinned
}
fn list_all_objects(repo_path: &std::path::Path) -> Result<Vec<String>> {
let out = std::process::Command::new("git")
.args(["cat-file", "--batch-all-objects", "--batch-check=%(objectname)"])
.current_dir(repo_path)
.output()
.map_err(|e| anyhow::anyhow!("failed to run git cat-file: {e}"))?;
if !out.status.success() {
let stderr = String::from_utf8_lossy(&out.stderr);
return Err(anyhow::anyhow!("git cat-file failed: {stderr}"));
}
Ok(String::from_utf8_lossy(&out.stdout)
.lines()
.map(|l| l.trim().to_string())
.filter(|l| !l.is_empty())
.collect())
}
// ── Tests ─────────────────────────────────────────────────────────────────────
#[cfg(test)]
@@ -135,14 +159,7 @@ mod tests {
#[tokio::test]
async fn test_pin_skipped_when_jwt_empty() {
let client = reqwest::Client::new();
let result = pin_object(
&client,
"https://uploads.pinata.cloud/v3/files",
"",
"deadbeef",
b"data",
)
.await;
let result = pin_object(&client, "https://uploads.pinata.cloud/v3/files", "", "deadbeef", b"data").await;
assert!(result.is_ok());
assert_eq!(result.unwrap(), "", "empty JWT must return empty CID");
}
@@ -169,10 +186,7 @@ mod tests {
.await;
assert!(result.is_ok(), "pin should succeed: {result:?}");
assert_eq!(
result.unwrap(),
"QmYwAPJzv5CZsnA625s3Xf2nemtYgPpHdWEz79ojWnPbdG"
);
assert_eq!(result.unwrap(), "QmYwAPJzv5CZsnA625s3Xf2nemtYgPpHdWEz79ojWnPbdG");
_mock.assert_async().await;
}
@@ -187,14 +201,7 @@ mod tests {
.await;
let client = reqwest::Client::new();
let result = pin_object(
&client,
&server.url(),
"bad-jwt",
"deadbeef00000000",
b"data",
)
.await;
let result = pin_object(&client, &server.url(), "bad-jwt", "deadbeef00000000", b"data").await;
assert!(result.is_err());
assert!(result.unwrap_err().to_string().contains("401"));
@@ -248,14 +255,7 @@ mod tests {
.await;
let client = reqwest::Client::new();
let result = pin_object(
&client,
&server.url(),
"my-pinata-jwt",
"deadbeef00000000",
b"data",
)
.await;
let result = pin_object(&client, &server.url(), "my-pinata-jwt", "deadbeef00000000", b"data").await;
assert!(result.is_ok());
_mock.assert_async().await;
-608
View File
@@ -1,608 +0,0 @@
use std::collections::HashMap;
use std::net::SocketAddr;
use std::sync::Arc;
use std::time::{Duration, Instant};
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>,
}
#[derive(Clone)]
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())),
}
}
/// 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;
// 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;
}
// 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;
}
}
state.insert(
key.to_string(),
Window {
timestamps: vec![now],
},
);
true
}
pub async fn cleanup(&self) {
let now = Instant::now();
let mut state = self.state.lock().await;
state.retain(|_, w| {
w.timestamps
.retain(|t| now.duration_since(*t) < self.window);
!w.timestamps.is_empty()
});
}
}
pub async fn rate_limit_by_did(request: Request, next: Next) -> Response {
let limiter = request.extensions().get::<RateLimiter>().cloned();
let did = request
.extensions()
.get::<AuthenticatedDid>()
.map(|a| a.0.clone());
if let (Some(limiter), Some(did)) = (limiter, did) {
if !limiter.check(&did).await {
return (
StatusCode::TOO_MANY_REQUESTS,
[("retry-after", "60")],
"rate limit exceeded — try again later",
)
.into_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::*;
#[tokio::test]
async fn allows_within_limit() {
let limiter = RateLimiter::new(3, Duration::from_secs(60));
assert!(limiter.check("did:key:test1").await);
assert!(limiter.check("did:key:test1").await);
assert!(limiter.check("did:key:test1").await);
}
#[tokio::test]
async fn blocks_over_limit() {
let limiter = RateLimiter::new(2, Duration::from_secs(60));
assert!(limiter.check("did:key:test2").await);
assert!(limiter.check("did:key:test2").await);
assert!(!limiter.check("did:key:test2").await);
}
#[tokio::test]
async fn separate_keys_independent() {
let limiter = RateLimiter::new(1, Duration::from_secs(60));
assert!(limiter.check("did:key:alice").await);
assert!(limiter.check("did:key:bob").await);
assert!(!limiter.check("did:key:alice").await);
}
#[tokio::test]
async fn window_expires() {
let limiter = RateLimiter::new(1, Duration::from_millis(50));
assert!(limiter.check("did:key:test3").await);
assert!(!limiter.check("did:key:test3").await);
tokio::time::sleep(Duration::from_millis(60)).await;
assert!(limiter.check("did:key:test3").await);
}
#[tokio::test]
async fn cleanup_removes_expired() {
let limiter = RateLimiter::new(1, Duration::from_millis(50));
limiter.check("did:key:stale").await;
tokio::time::sleep(Duration::from_millis(60)).await;
limiter.cleanup().await;
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"
);
}
}
+87 -432
View File
@@ -1,5 +1,4 @@
use async_graphql_axum::{GraphQLRequest, GraphQLResponse, GraphQLSubscription};
use axum::extract::DefaultBodyLimit;
use axum::{
extract::State,
middleware,
@@ -7,32 +6,21 @@ use axum::{
routing::{get, post},
Json, Router,
};
use serde_json::json;
use axum::extract::DefaultBodyLimit;
use tower_http::limit::RequestBodyLimitLayer;
use tower_http::trace::{DefaultOnFailure, DefaultOnResponse, TraceLayer};
use serde_json::json;
use tower_http::trace::{DefaultOnResponse, DefaultOnFailure, TraceLayer};
use tracing::Level;
use crate::api::{
agents, arweave, bounties, certs, changelog, events, ipfs, issues, labels, peers, profiles,
protect, pulls, register, replicas, repos, resolve, stars, tasks, visibility, webhooks,
};
use crate::api::{agents, arweave, bounties, certs, changelog, events, ipfs, issues, labels, peers, protect, pulls, register, repos, resolve, stars, tasks, webhooks};
use crate::auth;
use crate::rate_limit;
use crate::state::AppState;
async fn graphql_handler(
State(state): State<AppState>,
auth: Option<axum::Extension<crate::auth::AuthenticatedDid>>,
req: GraphQLRequest,
) -> GraphQLResponse {
// `optional_signature` attaches the verified DID when a signature is present.
// Thread it into request-scoped GraphQL data; mutations enforce its presence
// in-resolver (N2) while queries stay open.
let mut inner = req.into_inner();
if let Some(axum::Extension(did)) = auth {
inner = inner.data(did);
}
state.graphql_schema.execute(inner).await.into()
state.graphql_schema.execute(req.into_inner()).await.into()
}
async fn graphql_playground() -> impl IntoResponse {
@@ -42,420 +30,145 @@ async fn graphql_playground() -> impl IntoResponse {
))
}
/// Applies the standard auth middleware pair to a router: HTTP Signature verification
/// followed by UCAN chain validation. The two layers run in this order for every
/// matched request: `require_signature` first (sets `AuthenticatedDid`), then
/// `require_ucan_chain` (reads it).
fn add_auth_layers(router: Router<AppState>, state: AppState) -> Router<AppState> {
router
.layer(middleware::from_fn_with_state(
state,
auth::require_ucan_chain,
))
.layer(middleware::from_fn(auth::require_signature))
}
pub fn build_router(state: AppState) -> Router {
// ── GraphQL routes ─────────────────────────────────────────────────────
let schema = state.graphql_schema.as_ref().clone();
let graphql_routes = Router::new()
.route("/graphql", get(graphql_playground).post(graphql_handler))
// Attach the verified DID to /graphql when a signature is present. The
// layer covers only routes added before it, so /graphql/ws (added after,
// read-only subscriptions) stays open.
.layer(middleware::from_fn(auth::optional_signature))
.route_service("/graphql/ws", GraphQLSubscription::new(schema));
// ── Task routes (write — require HTTP Signature) ───────────────────────
let task_write_routes = add_auth_layers(
Router::new()
.route("/api/v1/tasks", post(tasks::create_task))
.route("/api/v1/tasks/{id}/claim", post(tasks::claim_task))
.route("/api/v1/tasks/{id}/complete", post(tasks::complete_task))
.route("/api/v1/tasks/{id}/fail", post(tasks::fail_task)),
state.clone(),
);
let task_write_routes = Router::new()
.route("/api/v1/tasks", post(tasks::create_task))
.route("/api/v1/tasks/{id}/claim", post(tasks::claim_task))
.route("/api/v1/tasks/{id}/complete", post(tasks::complete_task))
.route("/api/v1/tasks/{id}/fail", post(tasks::fail_task))
.layer(middleware::from_fn(auth::require_signature));
// ── Task routes (read — open) ──────────────────────────────────────────
let task_read_routes = Router::new()
.route("/api/v1/tasks", get(tasks::list_tasks))
.route("/api/v1/tasks/{id}", get(tasks::get_task));
// ── 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))
.route("/api/register", post(register::register))
.route("/api/v1/repos/{owner}/{repo}/fork", post(repos::fork_repo))
.route(
"/api/v1/repos/{owner}/{repo}/issues",
post(issues::create_issue),
)
.route("/api/v1/repos/{owner}/{repo}/pulls", post(pulls::create_pr))
.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(
Router::new()
.route(
"/api/v1/repos/{owner}/{repo}/pulls/{number}/merge",
post(pulls::merge_pr),
)
.route(
"/api/v1/repos/{owner}/{repo}/pulls/{number}/close",
post(pulls::close_pr),
)
.route(
"/api/v1/repos/{owner}/{repo}/pulls/{number}/reviews",
post(pulls::create_review),
)
.route(
"/api/v1/repos/{owner}/{repo}/pulls/{number}/comments",
post(pulls::create_comment),
)
.route(
"/api/v1/repos/{owner}/{repo}/hooks",
post(webhooks::create_webhook),
)
.route(
"/api/v1/repos/{owner}/{repo}/hooks/{id}",
axum::routing::delete(webhooks::delete_webhook),
)
.route(
"/api/v1/repos/{owner}/{repo}/branches/{branch}/protect",
post(protect::protect_branch),
)
.route(
"/api/v1/repos/{owner}/{repo}/branches/{branch}/protect",
axum::routing::delete(protect::unprotect_branch),
)
.route(
"/api/v1/repos/{owner}/{repo}/star",
axum::routing::put(stars::star_repo),
)
.route(
"/api/v1/repos/{owner}/{repo}/star",
axum::routing::delete(stars::unstar_repo),
)
.route(
"/api/v1/repos/{owner}/{repo}/replicas",
axum::routing::put(replicas::register_replica),
)
.route(
"/api/v1/repos/{owner}/{repo}/replicas",
axum::routing::delete(replicas::unregister_replica),
)
.route(
"/api/v1/repos/{owner}/{repo}/labels",
post(labels::add_label),
)
.route(
"/api/v1/repos/{owner}/{repo}/labels/{label}",
axum::routing::delete(labels::remove_label),
)
.route(
"/api/v1/repos/{owner}/{repo}/visibility",
axum::routing::put(visibility::set_visibility)
.delete(visibility::remove_visibility)
.get(visibility::list_visibility),
)
.route(
"/api/v1/agents/{did}",
axum::routing::delete(agents::deregister_agent),
),
state.clone(),
);
// ── Write routes — require HTTP Signature ──────────────────────────────
let write_routes = Router::new()
.route("/api/v1/repos", post(repos::create_repo))
.route("/api/register", post(register::register))
.route("/api/v1/repos/{owner}/{repo}/pulls", post(pulls::create_pr))
.route("/api/v1/repos/{owner}/{repo}/pulls/{number}/merge", post(pulls::merge_pr))
.route("/api/v1/repos/{owner}/{repo}/pulls/{number}/close", post(pulls::close_pr))
.route("/api/v1/repos/{owner}/{repo}/pulls/{number}/reviews", post(pulls::create_review))
.route("/api/v1/repos/{owner}/{repo}/pulls/{number}/comments", post(pulls::create_comment))
.route("/api/v1/repos/{owner}/{repo}/hooks", post(webhooks::create_webhook))
.route("/api/v1/repos/{owner}/{repo}/hooks/{id}", axum::routing::delete(webhooks::delete_webhook))
.route("/api/v1/repos/{owner}/{repo}/branches/{branch}/protect", post(protect::protect_branch))
.route("/api/v1/repos/{owner}/{repo}/branches/{branch}/protect", axum::routing::delete(protect::unprotect_branch))
.route("/api/v1/repos/{owner}/{repo}/star", axum::routing::put(stars::star_repo))
.route("/api/v1/repos/{owner}/{repo}/star", axum::routing::delete(stars::unstar_repo))
.route("/api/v1/repos/{owner}/{repo}/fork", post(repos::fork_repo))
.route("/api/v1/repos/{owner}/{repo}/labels", post(labels::add_label))
.route("/api/v1/repos/{owner}/{repo}/labels/{label}", axum::routing::delete(labels::remove_label))
.layer(middleware::from_fn(auth::require_signature));
// Body limit is raised to GITLAWB_MAX_PACK_BYTES (default 2 GB) for git
// routes only — all other API routes keep axum's default 2 MB cap.
// 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(
"/{owner}/{repo}/git-receive-pack",
post(repos::git_receive_pack),
)
.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));
let git_write_routes = Router::new()
.route("/{owner}/{repo}/git-receive-pack", post(repos::git_receive_pack))
.layer(DefaultBodyLimit::disable())
.layer(RequestBodyLimitLayer::new(pack_limit))
.layer(middleware::from_fn(auth::require_signature));
// ── IPFS content-addressed retrieval and pin listing ──────────────────
// `/ipfs/{cid}` carries `optional_signature` so `get_by_cid` sees the caller
// identity and can apply per-repo visibility (#110); anonymous callers stay
// anonymous and still read genuinely public content. `/api/v1/ipfs/pins`
// stays unsigned — gating the pin index is tracked separately (#121).
let ipfs_routes = Router::new()
.route("/ipfs/{cid}", get(ipfs::get_by_cid))
.layer(middleware::from_fn(auth::optional_signature))
.merge(Router::new().route("/api/v1/ipfs/pins", get(ipfs::list_pins)));
.route("/api/v1/ipfs/pins", get(ipfs::list_pins));
// ── Arweave permanent anchors ──────────────────────────────────────────
let arweave_routes = Router::new().route("/api/v1/arweave/anchors", get(arweave::list_anchors));
let arweave_routes = Router::new()
.route("/api/v1/arweave/anchors", get(arweave::list_anchors));
// ── Bounty routes (write — require HTTP Signature) ─────────────────
let bounty_write_routes = add_auth_layers(
Router::new()
.route(
"/api/v1/repos/{owner}/{repo}/bounties",
post(bounties::create_bounty),
)
.route("/api/v1/bounties/{id}/claim", post(bounties::claim_bounty))
.route(
"/api/v1/bounties/{id}/submit",
post(bounties::submit_bounty),
)
.route(
"/api/v1/bounties/{id}/approve",
post(bounties::approve_bounty),
)
.route(
"/api/v1/bounties/{id}/cancel",
post(bounties::cancel_bounty),
)
.route(
"/api/v1/bounties/{id}/dispute",
post(bounties::dispute_bounty),
),
state.clone(),
);
let bounty_write_routes = Router::new()
.route("/api/v1/repos/{owner}/{repo}/bounties", post(bounties::create_bounty))
.route("/api/v1/bounties/{id}/claim", post(bounties::claim_bounty))
.route("/api/v1/bounties/{id}/submit", post(bounties::submit_bounty))
.route("/api/v1/bounties/{id}/approve", post(bounties::approve_bounty))
.route("/api/v1/bounties/{id}/cancel", post(bounties::cancel_bounty))
.layer(middleware::from_fn(auth::require_signature));
// ── Bounty routes (read — open) ──────────────────────────────────────
let bounty_read_routes = Router::new()
.route(
"/api/v1/repos/{owner}/{repo}/bounties",
get(bounties::list_repo_bounties),
)
.route("/api/v1/repos/{owner}/{repo}/bounties", get(bounties::list_repo_bounties))
.route("/api/v1/bounties", get(bounties::list_all_bounties))
.route("/api/v1/bounties/{id}", get(bounties::get_bounty))
.route("/api/v1/bounties/{id}/dispute", post(bounties::dispute_bounty))
.route("/api/v1/bounties/stats", get(bounties::bounty_stats))
.route(
"/api/v1/agents/{did}/bounties",
get(bounties::agent_bounty_stats),
)
.layer(middleware::from_fn(auth::optional_signature));
.route("/api/v1/agents/{did}/bounties", get(bounties::agent_bounty_stats));
// ── Profile routes (write — require HTTP Signature) ─────────────────
let profile_write_routes = add_auth_layers(
Router::new().route("/api/v1/profile", axum::routing::put(profiles::set_profile)),
state.clone(),
);
// ── Issue routes (write — require HTTP Signature, no rate limit) ─────
let issue_write_routes = add_auth_layers(
Router::new()
.route(
"/api/v1/repos/{owner}/{repo}/issues/{id}/close",
post(issues::close_issue),
)
.route(
"/api/v1/repos/{owner}/{repo}/issues/{id}/comments",
post(issues::create_issue_comment),
),
state.clone(),
);
// ── Issue routes ──────────────────────────────────────────────────────
let issue_write_routes = Router::new()
.route("/api/v1/repos/{owner}/{repo}/issues", post(issues::create_issue))
.route("/api/v1/repos/{owner}/{repo}/issues/{id}/close", post(issues::close_issue))
.route("/api/v1/repos/{owner}/{repo}/issues/{id}/comments", post(issues::create_issue_comment))
.layer(middleware::from_fn(auth::require_signature));
// ── Peer discovery routes ─────────────────────────────────────────────
// Peer writes accept signatures when present and can require them after a
// coordinated live-network upgrade.
// announce is intentionally unauthenticated — nodes announce by DID which
// is self-proving; rate-limiting and blocklisting are handled elsewhere.
let peer_read_routes = Router::new()
.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/peers/{did}/ping", get(peers::ping_peer))
.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()
.route("/api/v1/repos", get(repos::list_repos))
.route("/api/v1/repos/federated", get(repos::list_federated_repos))
.route("/api/v1/repos/{owner}/{repo}", get(repos::get_repo))
.route(
"/api/v1/repos/{owner}/{repo}/commits",
get(repos::list_commits),
)
.route(
"/api/v1/repos/{owner}/{repo}/tree",
get(repos::get_tree_root),
)
.route(
"/api/v1/repos/{owner}/{repo}/tree/{*path}",
get(repos::get_tree),
)
.route(
"/api/v1/repos/{owner}/{repo}/blob/{*path}",
get(repos::get_blob),
)
.route(
"/api/v1/repos/{owner}/{repo}/issues",
get(issues::list_issues),
)
.route(
"/api/v1/repos/{owner}/{repo}/issues/{id}",
get(issues::get_issue),
)
.route(
"/api/v1/repos/{owner}/{repo}/issues/{id}/comments",
get(issues::list_issue_comments),
)
.route(
"/api/v1/repos/{owner}/{repo}/labels",
get(labels::list_labels),
)
.route("/api/v1/repos/{owner}/{repo}/commits", get(repos::list_commits))
.route("/api/v1/repos/{owner}/{repo}/tree", get(repos::get_tree_root))
.route("/api/v1/repos/{owner}/{repo}/tree/{*path}", get(repos::get_tree))
.route("/api/v1/repos/{owner}/{repo}/blob/{*path}", get(repos::get_blob))
.route("/api/v1/repos/{owner}/{repo}/issues", get(issues::list_issues))
.route("/api/v1/repos/{owner}/{repo}/issues/{id}", get(issues::get_issue))
.route("/api/v1/repos/{owner}/{repo}/issues/{id}/comments", get(issues::list_issue_comments))
.route("/api/v1/repos/{owner}/{repo}/labels", get(labels::list_labels))
.route("/api/v1/repos/{owner}/{repo}/certs", get(certs::list_certs))
.route(
"/api/v1/repos/{owner}/{repo}/certs/{id}",
get(certs::get_cert),
)
.route(
"/api/v1/repos/{owner}/{repo}/events",
get(events::list_repo_events),
)
.route("/api/v1/repos/{owner}/{repo}/certs/{id}", get(certs::get_cert))
.route("/api/v1/repos/{owner}/{repo}/events", get(events::list_repo_events))
.route("/api/v1/agents", get(agents::list_agents))
.route("/api/v1/agents/{did}", get(agents::show_agent))
.route("/api/v1/agents/{did}/trust", get(agents::get_trust))
.route("/api/v1/agents/{did}/profile", get(profiles::get_profile))
.route("/api/v1/events/ref-updates", get(events::list_ref_updates))
.route("/api/v1/resolve/{did}", get(resolve::resolve_did))
.route("/api/v1/repos/{owner}/{repo}/pulls", get(pulls::list_prs))
.route(
"/api/v1/repos/{owner}/{repo}/pulls/{number}",
get(pulls::get_pr),
)
.route(
"/api/v1/repos/{owner}/{repo}/pulls/{number}/diff",
get(pulls::get_pr_diff),
)
.route(
"/api/v1/repos/{owner}/{repo}/pulls/{number}/reviews",
get(pulls::list_reviews),
)
.route(
"/api/v1/repos/{owner}/{repo}/pulls/{number}/comments",
get(pulls::list_comments),
)
.route(
"/api/v1/repos/{owner}/{repo}/hooks",
get(webhooks::list_webhooks),
)
.route("/api/v1/repos/{owner}/{repo}/pulls/{number}", get(pulls::get_pr))
.route("/api/v1/repos/{owner}/{repo}/pulls/{number}/diff", get(pulls::get_pr_diff))
.route("/api/v1/repos/{owner}/{repo}/pulls/{number}/reviews", get(pulls::list_reviews))
.route("/api/v1/repos/{owner}/{repo}/pulls/{number}/comments", get(pulls::list_comments))
.route("/api/v1/repos/{owner}/{repo}/hooks", get(webhooks::list_webhooks))
.route("/api/v1/repos/{owner}/{repo}/refs", get(repos::list_refs))
.route(
"/api/v1/repos/{owner}/{repo}/branches/protected",
get(protect::list_protected_branches),
)
.route(
"/api/v1/repos/{owner}/{repo}/changelog",
get(changelog::get_changelog),
)
.route(
"/api/v1/repos/{owner}/{repo}/star",
get(stars::get_star_status),
)
.route(
"/api/v1/repos/{owner}/{repo}/replicas",
get(replicas::list_replicas),
)
.layer(middleware::from_fn(auth::optional_signature));
.route("/api/v1/repos/{owner}/{repo}/branches/protected", get(protect::list_protected_branches))
.route("/api/v1/repos/{owner}/{repo}/changelog", get(changelog::get_changelog))
.route("/api/v1/repos/{owner}/{repo}/star", get(stars::get_star_status))
.route("/{owner}/{repo}/info/refs", get(repos::git_info_refs));
// git-upload-pack (clone/fetch) — same raised body limit as receive-pack so
// large pack responses from the server don't get truncated on the client side.
let git_read_routes = Router::new()
.route("/{owner}/{repo}/info/refs", get(repos::git_info_refs))
.route(
"/{owner}/{repo}/git-upload-pack",
post(repos::git_upload_pack),
)
.route(
"/api/v1/repos/{owner}/{repo}/withheld-paths",
axum::routing::get(visibility::withheld_paths),
)
.route(
"/api/v1/repos/{owner}/{repo}/icaptcha-proof",
axum::routing::get(repos::get_icaptcha_proof),
)
.route(
"/api/v1/repos/{owner}/{repo}/encrypted-blobs",
axum::routing::get(crate::api::encrypted::list_encrypted_blobs),
)
.route(
"/api/v1/repos/{owner}/{repo}/encrypted-blob/{oid}",
axum::routing::get(crate::api::encrypted::get_encrypted_blob),
)
.route(
"/api/v1/repos/{owner}/{repo}/encrypted-blobs/replicate",
axum::routing::get(crate::api::encrypted::replicate_encrypted_blobs),
)
.route("/{owner}/{repo}/git-upload-pack", post(repos::git_upload_pack))
.layer(DefaultBodyLimit::disable())
.layer(RequestBodyLimitLayer::new(pack_limit))
.layer(middleware::from_fn(auth::optional_signature));
.layer(RequestBodyLimitLayer::new(pack_limit));
// ── Meta ──────────────────────────────────────────────────────────────
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));
@@ -466,16 +179,12 @@ pub fn build_router(state: AppState) -> Router {
.merge(task_read_routes)
.merge(bounty_write_routes)
.merge(bounty_read_routes)
.merge(profile_write_routes)
.merge(creation_routes)
.merge(write_routes)
.merge(git_write_routes)
.merge(git_read_routes)
.merge(issue_write_routes)
.merge(read_routes)
.merge(peer_read_routes)
.merge(peer_write_routes)
.merge(sync_trigger_routes)
.merge(ipfs_routes)
.merge(arweave_routes)
.merge(meta_routes)
@@ -498,26 +207,6 @@ 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!({
@@ -532,31 +221,8 @@ async fn node_info(State(state): State<AppState>) -> Json<serde_json::Value> {
}))
}
pub(crate) async fn stats(State(state): State<AppState>) -> Json<serde_json::Value> {
// Count only the repos an anonymous caller could list, so the aggregate does
// not leak the existence of private/mode-A repos (#104 count oracle). Mirror
// the listing seam (api/repos.rs): over-fetch the deduped set, batch-load the
// visibility rules, and keep rows that pass listable_at_root. The caller is
// always None — meta_routes carries no auth layer (see the route group in this
// file). Fail closed: any DB error collapses the whole count to 0 (an
// under-count never leaks existence), preserving the prior `.unwrap_or(0)`.
let repos = async {
// stats only needs the count, so use the no-stars deduped list (same
// DEDUP_CTE) and skip the repo_stars aggregation the listing path needs.
let rows = state.db.list_all_repos_deduped().await?;
let ids: Vec<String> = rows.iter().map(|r| r.id.clone()).collect();
let rules_by_repo = state.db.list_visibility_rules_for_repos(&ids).await?;
let count = rows
.iter()
.filter(|r| {
let rules = rules_by_repo.get(&r.id).map(Vec::as_slice).unwrap_or(&[]);
crate::visibility::listable_at_root(rules, r.is_public, &r.owner_did, None)
})
.count() as i64;
Ok::<i64, anyhow::Error>(count)
}
.await
.unwrap_or(0);
async fn stats(State(state): State<AppState>) -> Json<serde_json::Value> {
let repos = state.db.list_all_repos().await.map(|r| r.len() as i64).unwrap_or(0);
let agents = state.db.count_agents().await.unwrap_or(0);
let pushes = state.db.count_pushes().await.unwrap_or(0);
Json(json!({
@@ -571,11 +237,7 @@ async fn contracts_info(State(state): State<AppState>) -> Json<serde_json::Value
let did_registry = &state.config.contract_did_registry;
let name_registry = &state.config.contract_name_registry;
let rpc_url = &state.config.chain_rpc_url;
let chain_id: u64 = if rpc_url.contains("sepolia") {
84532
} else {
8453
};
let chain_id: u64 = if rpc_url.contains("sepolia") { 84532 } else { 8453 };
Json(serde_json::json!({
"chain": if chain_id == 8453 { "base" } else { "base-sepolia" },
"chain_id": chain_id,
@@ -593,18 +255,11 @@ async fn contracts_info(State(state): State<AppState>) -> Json<serde_json::Value
async fn p2p_info(State(state): State<AppState>) -> Json<serde_json::Value> {
match &state.p2p {
Some(h) => {
let status = h.status().await;
Json(json!({
"enabled": true,
"peer_id": h.local_peer_id.to_string(),
"topics": [crate::p2p::REF_UPDATES_TOPIC],
"connected_peers": status.as_ref().map(|s| s.connected_peers),
"gossipsub_mesh_peers": status.as_ref().map(|s| s.gossipsub_mesh_peers),
"gossipsub_all_peers": status.as_ref().map(|s| s.gossipsub_all_peers),
"listen_addrs": status.as_ref().map(|s| s.listen_addrs.clone()),
}))
}
Some(h) => Json(json!({
"enabled": true,
"peer_id": h.local_peer_id.to_string(),
"topics": [crate::p2p::REF_UPDATES_TOPIC],
})),
None => Json(json!({ "enabled": false })),
}
}
+1 -70
View File
@@ -1,12 +1,11 @@
use std::sync::Arc;
use gitlawb_core::did::Did;
use gitlawb_core::identity::Keypair;
use std::sync::Arc;
use crate::config::Config;
use crate::db::Db;
use crate::git::repo_store::RepoStore;
use crate::p2p::P2pHandle;
use crate::rate_limit::RateLimiter;
#[derive(Clone, Debug)]
pub struct RefUpdateBroadcast {
@@ -49,72 +48,4 @@ pub struct AppState {
pub machine_id: Option<String>,
/// Centralized repo storage: local disk cache + optional Tigris backend
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:
/// * the SIGINT/SIGTERM handler in `main()`
/// * axum's `with_graceful_shutdown` to drain in-flight HTTP requests
/// * the libp2p swarm task
/// * the gossip, sync, operator heartbeat, and rate-limit cleanup loops
pub shutdown_tx: tokio::sync::watch::Sender<bool>,
}
impl AppState {
/// Subscribe to the shutdown signal. Returns a fresh receiver whose
/// initial value matches the current state.
pub fn subscribe_shutdown(&self) -> tokio::sync::watch::Receiver<bool> {
self.shutdown_tx.subscribe()
}
/// Trigger graceful shutdown. Idempotent — calling more than once
/// has no effect. Returns `true` if this call was the one that
/// flipped the signal.
#[allow(dead_code)] // used by tests; main() drives the signal directly
pub fn shutdown(&self) -> bool {
self.shutdown_tx.send_if_modified(|v| {
if *v {
false
} else {
*v = true;
true
}
})
}
/// `true` once shutdown has been signalled.
#[allow(dead_code)] // used by tests and any future handler that wants to short-circuit
pub fn is_shutting_down(&self) -> bool {
*self.shutdown_tx.borrow()
}
}
File diff suppressed because it is too large. Load diff
File diff suppressed because it is too large. Load diff
-848
View File
@@ -1,848 +0,0 @@
//! Pure read-authorization logic for path-scoped visibility.
//!
//! `visibility_check` decides whether a caller may read a given path in a repo,
//! 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::{RepoRecord, VisibilityRule};
use std::collections::HashMap;
use unicode_normalization::UnicodeNormalization;
#[derive(Debug, PartialEq, Eq)]
pub enum Decision {
Allow,
Deny,
}
/// NFC-normalize a glob prefix or path so the matcher compares canonically
/// equivalent strings byte-for-byte. Without this, a deny rule authored NFC
/// (`é` = U+00E9) byte-compares unequal to a path committed NFD (`e` + U+0301)
/// and the blob slips past the rule on the replication path (#101). NFC, not
/// NFKC: compatibility folding (ligatures, full-width forms) would merge paths
/// the filesystem treats as distinct and over-withhold. Both sides of every
/// comparison must pass through this, or the skew just moves.
fn nfc(s: &str) -> String {
s.nfc().collect()
}
/// 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 {
crate::api::did_matches(owner_did, caller)
}
/// The match prefix for a glob: "/" stays "/", "/secret/**" becomes "/secret".
fn glob_prefix(glob: &str) -> &str {
let p = glob.trim_end_matches("**").trim_end_matches('/');
if p.is_empty() {
"/"
} else {
p
}
}
/// Does `glob` match `path`? "/" matches everything; "/secret" matches
/// "/secret" and any "/secret/..." descendant.
fn glob_matches(glob: &str, path: &str) -> bool {
let prefix = glob_prefix(glob);
if prefix == "/" {
return true;
}
// Compare in NFC so an NFC rule matches a canonically-equivalent NFD path
// (and vice versa). Both sides normalized here — the single matcher seam.
let prefix = nfc(prefix);
let path = nfc(path);
path == prefix || path.starts_with(&format!("{prefix}/"))
}
/// Specificity = length of the (normalized) match prefix; longer is more
/// specific. Normalized so ranking stays consistent with `glob_matches`.
fn specificity(glob: &str) -> usize {
nfc(glob_prefix(glob)).len()
}
/// Decide whether `caller` (None = anonymous) may read `path` in a repo.
/// `path` is "/" for a whole-repo clone/fetch.
///
/// Reader DIDs in a rule are matched exactly, so they must be stored in full
/// `did:key:...` form. The owner is the only identity matched in both full and
/// short form.
pub fn visibility_check(
rules: &[VisibilityRule],
is_public: bool,
owner_did: &str,
caller: Option<&str>,
path: &str,
) -> Decision {
// The owner can always read everything.
if let Some(c) = caller {
if is_owner(owner_did, c) {
return Decision::Allow;
}
}
// Most-specific matching rule wins. On equal specificity the last rule in
// DB order is chosen; `list_visibility_rules` orders by `path_glob`, so this
// is deterministic.
let best = rules
.iter()
.filter(|r| glob_matches(&r.path_glob, path))
.max_by_key(|r| specificity(&r.path_glob));
match best {
Some(rule) => {
// Phase 1 treats every matching rule as an allow-list keyed by
// `reader_dids`. `rule.mode` (A vs B) is stored from day one but not
// acted on here; it governs replication behavior in Phases 2-3.
let allowed = caller
.map(|c| rule.reader_dids.iter().any(|d| d == c))
.unwrap_or(false);
if allowed {
Decision::Allow
} else {
Decision::Deny
}
}
None => {
if is_public {
Decision::Allow
} else {
Decision::Deny
}
}
}
}
/// Whether `caller` (None = anonymous) may see a repo in a listing — the `"/"`
/// visibility decision, shared by every repo-listing surface (REST list,
/// federated list, GraphQL `repos`) so they enforce one rule, not three drifting
/// copies. Not a bare `is_public` test: a repo can be `is_public=false` with a
/// root rule granting readers, or `is_public=true` with a root deny (#97).
pub fn listable_at_root(
rules: &[VisibilityRule],
is_public: bool,
owner_did: &str,
caller: Option<&str>,
) -> bool {
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
/// rule is reported when `visibility_check` denies the caller at the glob's
/// representative path. Used by the clean-clone client to sparse-exclude the
/// private paths from checkout.
pub fn withheld_globs(
rules: &[VisibilityRule],
is_public: bool,
owner_did: &str,
caller: Option<&str>,
) -> Vec<String> {
rules
.iter()
.filter(|r| r.path_glob != "/")
.filter(|r| {
let probe = glob_prefix(&r.path_glob);
visibility_check(rules, is_public, owner_did, caller, probe) == Decision::Deny
})
.map(|r| r.path_glob.clone())
.collect()
}
/// The allowed globs that sit strictly underneath a denied glob. A clean-clone
/// client sparse-excludes everything in `withheld_globs`, which would also hide
/// these nested allowed paths; re-including them restores the caller's access.
/// Example: with `/secret/**` denied and `/secret/public/**` allowed for the
/// same caller, `/secret/public/**` is returned here so the client re-includes
/// it after excluding `/secret/`.
pub fn reincluded_globs(
rules: &[VisibilityRule],
is_public: bool,
owner_did: &str,
caller: Option<&str>,
) -> Vec<String> {
let denied: Vec<&str> = rules
.iter()
.filter(|r| r.path_glob != "/")
.filter(|r| {
visibility_check(
rules,
is_public,
owner_did,
caller,
glob_prefix(&r.path_glob),
) == Decision::Deny
})
.map(|r| glob_prefix(&r.path_glob))
.collect();
rules
.iter()
.filter(|r| r.path_glob != "/")
.filter(|r| {
visibility_check(
rules,
is_public,
owner_did,
caller,
glob_prefix(&r.path_glob),
) == Decision::Allow
})
.filter(|r| {
let p = glob_prefix(&r.path_glob);
denied
.iter()
.any(|d| *d != p && p.starts_with(&format!("{d}/")))
})
.map(|r| r.path_glob.clone())
.collect()
}
#[cfg(test)]
mod tests {
use super::*;
use crate::db::VisibilityMode;
use chrono::Utc;
fn rule(path_glob: &str, mode: VisibilityMode, readers: &[&str]) -> VisibilityRule {
VisibilityRule {
id: "x".into(),
repo_id: "r1".into(),
path_glob: path_glob.into(),
mode,
reader_dids: readers.iter().map(|s| s.to_string()).collect(),
created_by: "did:key:z6MkOwner".into(),
created_at: Utc::now(),
}
}
const OWNER: &str = "did:key:z6MkOwner";
#[test]
fn withheld_globs_lists_only_denied_subtrees() {
let rules = [
rule("/secret/**", VisibilityMode::B, &["did:key:z6MkFriend"]),
rule("/docs/**", VisibilityMode::B, &["did:key:z6MkStranger"]),
];
// Stranger is denied /secret but allowed /docs.
let mut got = withheld_globs(&rules, true, OWNER, Some("did:key:z6MkStranger"));
got.sort();
assert_eq!(got, vec!["/secret/**".to_string()]);
// Owner is denied nothing.
assert!(withheld_globs(&rules, true, OWNER, Some(OWNER)).is_empty());
// Anonymous is denied both.
let mut anon = withheld_globs(&rules, true, OWNER, None);
anon.sort();
assert_eq!(anon, vec!["/docs/**".to_string(), "/secret/**".to_string()]);
}
#[test]
fn reincluded_globs_restores_allowed_nested_path() {
let rules = [
rule("/secret/**", VisibilityMode::B, &["did:key:z6MkFriend"]),
rule(
"/secret/public/**",
VisibilityMode::B,
&["did:key:z6MkFriend", "did:key:z6MkStranger"],
),
];
// Stranger is denied /secret/** but allowed the nested /secret/public/**.
let withheld = withheld_globs(&rules, true, OWNER, Some("did:key:z6MkStranger"));
assert_eq!(withheld, vec!["/secret/**".to_string()]);
let reinc = reincluded_globs(&rules, true, OWNER, Some("did:key:z6MkStranger"));
assert_eq!(reinc, vec!["/secret/public/**".to_string()]);
// Owner is denied nothing, so there is nothing to re-include.
assert!(reincluded_globs(&rules, true, OWNER, Some(OWNER)).is_empty());
}
#[test]
fn no_rules_public_allows_anonymous() {
assert_eq!(
visibility_check(&[], true, OWNER, None, "/"),
Decision::Allow
);
}
#[test]
fn no_rules_private_denies_anonymous() {
assert_eq!(
visibility_check(&[], false, OWNER, None, "/"),
Decision::Deny
);
}
#[test]
fn root_rule_denies_anonymous() {
let rules = [rule("/", VisibilityMode::A, &[])];
assert_eq!(
visibility_check(&rules, true, OWNER, None, "/"),
Decision::Deny
);
}
#[test]
fn root_rule_allows_owner() {
let rules = [rule("/", VisibilityMode::A, &[])];
assert_eq!(
visibility_check(&rules, true, OWNER, Some(OWNER), "/"),
Decision::Allow
);
}
#[test]
fn root_rule_allows_owner_short_form() {
let rules = [rule("/", VisibilityMode::A, &[])];
assert_eq!(
visibility_check(&rules, true, OWNER, Some("z6MkOwner"), "/"),
Decision::Allow
);
}
#[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"])];
assert_eq!(
visibility_check(&rules, true, OWNER, Some("did:key:z6MkFriend"), "/"),
Decision::Allow
);
}
#[test]
fn root_rule_denies_unlisted_reader() {
let rules = [rule("/", VisibilityMode::A, &["did:key:z6MkFriend"])];
assert_eq!(
visibility_check(&rules, true, OWNER, Some("did:key:z6MkStranger"), "/"),
Decision::Deny
);
}
#[test]
fn subtree_rule_matches_descendant_path() {
let rules = [rule(
"/secret/**",
VisibilityMode::B,
&["did:key:z6MkFriend"],
)];
assert_eq!(
visibility_check(
&rules,
true,
OWNER,
Some("did:key:z6MkStranger"),
"/secret/a.rs"
),
Decision::Deny
);
assert_eq!(
visibility_check(
&rules,
true,
OWNER,
Some("did:key:z6MkFriend"),
"/secret/a.rs"
),
Decision::Allow
);
}
#[test]
fn subtree_rule_does_not_affect_root_clone() {
// A subtree rule must not gate a whole-repo (path "/") read: the public
// fallback applies because the subtree glob does not match "/".
let rules = [rule("/secret/**", VisibilityMode::B, &[])];
assert_eq!(
visibility_check(&rules, true, OWNER, None, "/"),
Decision::Allow
);
}
#[test]
fn most_specific_rule_wins() {
// Public repo, but /secret is locked. A stranger reading /secret is denied
// by the more specific rule even though "/" would allow.
let rules = [
rule("/", VisibilityMode::A, &["did:key:z6MkStranger"]),
rule("/secret/**", VisibilityMode::B, &["did:key:z6MkFriend"]),
];
// stranger is a root reader but not a /secret reader
assert_eq!(
visibility_check(
&rules,
true,
OWNER,
Some("did:key:z6MkStranger"),
"/secret/a.rs"
),
Decision::Deny
);
// stranger can still read root
assert_eq!(
visibility_check(&rules, true, OWNER, Some("did:key:z6MkStranger"), "/"),
Decision::Allow
);
}
// Mirrors the gossip-announce gate in git_receive_pack: announce iff an
// anonymous caller can read "/".
#[test]
fn announce_gate_matches_public_readability() {
let announce = |rules: &[VisibilityRule], is_public: bool| {
visibility_check(rules, is_public, OWNER, None, "/") == Decision::Allow
};
// Public repo, no rules → announce.
assert!(announce(&[], true));
// Legacy private repo (is_public false, no rules) → silent.
assert!(!announce(&[], false));
// Mode A whole-repo rule with no public readers → silent.
assert!(!announce(&[rule("/", VisibilityMode::A, &[])], true));
// Mode B public repo with a private subtree → still announce.
assert!(announce(
&[rule("/secret/**", VisibilityMode::B, &[])],
true
));
}
// ── 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
// path and the blob leaks on the replication path.
#[test]
fn matcher_withholds_across_nfc_nfd_normalization_skew() {
// "é" composed (NFC, U+00E9) in the rule; decomposed (NFD, e + U+0301)
// in the committed path.
let nfc_rule = "/s\u{00e9}cret/**";
let nfd_path = "/se\u{0301}cret/key.pem";
let rules = [rule(nfc_rule, VisibilityMode::B, &["did:key:z6MkFriend"])];
assert_eq!(
visibility_check(&rules, true, OWNER, None, nfd_path),
Decision::Deny,
"NFC-authored deny rule must withhold the canonically-equivalent NFD path"
);
// Mirror: rule authored NFD, path committed NFC.
let nfd_rule = "/se\u{0301}cret/**";
let nfc_path = "/s\u{00e9}cret/key.pem";
let rules2 = [rule(nfd_rule, VisibilityMode::B, &["did:key:z6MkFriend"])];
assert_eq!(
visibility_check(&rules2, true, OWNER, None, nfc_path),
Decision::Deny,
"NFD-authored deny rule must withhold the canonically-equivalent NFC path"
);
// A genuinely different path is still allowed (no over-withholding).
assert_eq!(
visibility_check(&rules, true, OWNER, None, "/public/x.txt"),
Decision::Allow
);
}
}
+14 -25
View File
@@ -24,8 +24,8 @@ type HmacSha256 = Hmac<Sha256>;
/// Compute `sha256=<hex>` HMAC signature for a webhook payload.
fn sign_payload(secret: &str, payload: &[u8]) -> String {
let mut mac =
HmacSha256::new_from_slice(secret.as_bytes()).expect("HMAC accepts any key length");
let mut mac = HmacSha256::new_from_slice(secret.as_bytes())
.expect("HMAC accepts any key length");
mac.update(payload);
format!("sha256={}", hex::encode(mac.finalize().into_bytes()))
}
@@ -93,29 +93,18 @@ async fn fire_event_async(
}
match req.send().await {
Ok(resp) => {
let result_label = if resp.status().is_success() {
"ok"
} else {
"http_error"
};
crate::metrics::record_webhook_delivery(result_label);
tracing::info!(
url = %hook.url,
event = %event_name,
status = %resp.status(),
"webhook delivered"
)
}
Err(e) => {
crate::metrics::record_webhook_delivery("network_error");
tracing::warn!(
url = %hook.url,
event = %event_name,
err = %e,
"webhook delivery failed"
)
}
Ok(resp) => tracing::info!(
url = %hook.url,
event = %event_name,
status = %resp.status(),
"webhook delivered"
),
Err(e) => tracing::warn!(
url = %hook.url,
event = %event_name,
err = %e,
"webhook delivery failed"
),
}
});
}
+1 -3
View File
@@ -1,9 +1,8 @@
[package]
name = "gl"
description = "The gitlawb CLI — identity management, node control, MCP server"
version = "0.5.1" # x-release-please-version
version.workspace = true
edition.workspace = true
rust-version.workspace = true
license.workspace = true
[[bin]]
@@ -12,7 +11,6 @@ path = "src/main.rs"
[dependencies]
gitlawb-core = { path = "../gitlawb-core" }
icaptcha-client = { path = "../icaptcha-client" }
tokio = { workspace = true }
serde = { workspace = true }
serde_json = { workspace = true }
+13 -50
View File
@@ -36,11 +36,7 @@ pub enum AgentCmd {
pub async fn run(args: AgentArgs) -> Result<()> {
match args.cmd {
AgentCmd::List {
node,
capability,
dir: _,
} => cmd_list(node, capability).await,
AgentCmd::List { node, capability, dir: _ } => cmd_list(node, capability).await,
AgentCmd::Show { did, node } => cmd_show(did, node).await,
}
}
@@ -53,10 +49,7 @@ async fn cmd_list(node: String, capability: Option<String>) -> Result<()> {
None => "/api/v1/agents".to_string(),
};
let resp = client
.get(&path)
.await
.context("failed to connect to node")?;
let resp = client.get(&path).await.context("failed to connect to node")?;
let status = resp.status();
if status == reqwest::StatusCode::NOT_FOUND {
@@ -66,10 +59,7 @@ async fn cmd_list(node: String, capability: Option<String>) -> Result<()> {
);
}
let body: Value = resp
.json()
.await
.context("invalid JSON from node — is GITLAWB_NODE correct?")?;
let body: Value = resp.json().await.context("invalid JSON from node — is GITLAWB_NODE correct?")?;
if !status.is_success() {
let msg = body["message"].as_str().unwrap_or("unknown error");
@@ -86,20 +76,10 @@ async fn cmd_list(node: String, capability: Option<String>) -> Result<()> {
println!("Agents on {} ({} total)\n", node, agents.len());
for agent in &agents {
let did = agent["did"].as_str().unwrap_or("?");
let short = did
.split(':')
.next_back()
.map(|s| &s[..s.len().min(16)])
.unwrap_or("?");
let short = did.split(':').next_back().map(|s| &s[..s.len().min(16)]).unwrap_or("?");
let trust = agent["trust_score"].as_f64().unwrap_or(0.0);
let caps = agent["capabilities"]
.as_array()
.map(|a| {
a.iter()
.filter_map(|v| v.as_str())
.collect::<Vec<_>>()
.join(", ")
})
let caps = agent["capabilities"].as_array()
.map(|a| a.iter().filter_map(|v| v.as_str()).collect::<Vec<_>>().join(", "))
.unwrap_or_default();
let model = agent["model"].as_str().unwrap_or("");
println!(" {short}… trust={trust:.2} {caps}");
@@ -126,10 +106,7 @@ async fn cmd_show(did: String, node: String) -> Result<()> {
);
}
let agent: Value = resp
.json()
.await
.context("invalid JSON from node — is GITLAWB_NODE correct?")?;
let agent: Value = resp.json().await.context("invalid JSON from node — is GITLAWB_NODE correct?")?;
if !status.is_success() {
let msg = agent["message"].as_str().unwrap_or("unknown error");
@@ -138,14 +115,8 @@ async fn cmd_show(did: String, node: String) -> Result<()> {
let full_did = agent["did"].as_str().unwrap_or("?");
let trust = agent["trust_score"].as_f64().unwrap_or(0.0);
let caps = agent["capabilities"]
.as_array()
.map(|a| {
a.iter()
.filter_map(|v| v.as_str())
.collect::<Vec<_>>()
.join(", ")
})
let caps = agent["capabilities"].as_array()
.map(|a| a.iter().filter_map(|v| v.as_str()).collect::<Vec<_>>().join(", "))
.unwrap_or_default();
let registered = agent["registered_at"].as_str().unwrap_or("?");
let model = agent["model"].as_str().unwrap_or("(none)");
@@ -201,9 +172,7 @@ mod tests {
.create_async()
.await;
cmd_list(server.url(), Some("git:push".to_string()))
.await
.unwrap();
cmd_list(server.url(), Some("git:push".to_string())).await.unwrap();
_m.assert_async().await;
}
@@ -248,9 +217,7 @@ mod tests {
.create_async()
.await;
cmd_show("did:key:z6MkTest".to_string(), server.url())
.await
.unwrap();
cmd_show("did:key:z6MkTest".to_string(), server.url()).await.unwrap();
}
#[tokio::test]
@@ -264,9 +231,7 @@ mod tests {
.create_async()
.await;
let err = cmd_show("did:key:z6MkMissing".to_string(), server.url())
.await
.unwrap_err();
let err = cmd_show("did:key:z6MkMissing".to_string(), server.url()).await.unwrap_err();
assert!(err.to_string().contains("agents API") || err.to_string().contains("not found"));
}
@@ -281,8 +246,6 @@ mod tests {
.create_async()
.await;
cmd_show("did:key:z6MkHigh".to_string(), server.url())
.await
.unwrap();
cmd_show("did:key:z6MkHigh".to_string(), server.url()).await.unwrap();
}
}
+34 -128
View File
@@ -8,10 +8,6 @@ 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)]
@@ -53,8 +49,6 @@ 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 {
@@ -62,8 +56,6 @@ 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 {
@@ -119,36 +111,14 @@ pub enum BountyCmd {
pub async fn run(args: BountyArgs) -> Result<()> {
match args.cmd {
BountyCmd::Create {
repo,
title,
amount,
issue,
tx_hash,
deadline,
node,
dir,
} => cmd_create(repo, title, amount, issue, tx_hash, deadline, node, dir).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,
node,
dir,
} => cmd_claim(id, wallet, node, dir).await,
BountyCmd::Create { repo, title, amount, issue, tx_hash, deadline, 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::Claim { id, wallet, node, dir } => cmd_claim(id, wallet, node, dir).await,
BountyCmd::Submit { id, pr, node, dir } => cmd_submit(id, pr, node, dir).await,
BountyCmd::Approve {
id,
tx_hash,
node,
dir,
} => cmd_approve(id, tx_hash, node, dir).await,
BountyCmd::Approve { id, tx_hash, node, dir } => cmd_approve(id, tx_hash, node, dir).await,
BountyCmd::Cancel { id, node, dir } => cmd_cancel(id, node, dir).await,
BountyCmd::Stats { node } => cmd_stats(node).await,
}
@@ -156,19 +126,12 @@ pub async fn run(args: BountyArgs) -> Result<()> {
#[allow(clippy::too_many_arguments)]
async fn cmd_create(
repo: String,
title: String,
amount: i64,
issue: Option<String>,
tx_hash: Option<String>,
deadline: Option<i64>,
node: String,
dir: Option<PathBuf>,
repo: String, title: String, amount: i64, issue: Option<String>,
tx_hash: Option<String>, deadline: Option<i64>, node: String, dir: Option<PathBuf>,
) -> Result<()> {
let kp = load_keypair_from_dir(dir.as_deref())
.context("identity not found — run `gl identity new` first")?;
let (owner, name) = repo
.split_once('/')
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, Some(kp));
@@ -182,10 +145,7 @@ async fn cmd_create(
});
let resp = client
.post(
&format!("/api/v1/repos/{owner}/{name}/bounties"),
&serde_json::to_vec(&body)?,
)
.post(&format!("/api/v1/repos/{owner}/{name}/bounties"), &serde_json::to_vec(&body)?)
.await
.context("failed to connect to node")?;
@@ -205,17 +165,11 @@ async fn cmd_create(
Ok(())
}
async fn cmd_list(
repo: Option<String>,
status: Option<String>,
node: String,
dir: Option<PathBuf>,
) -> Result<()> {
let client = signed_client(&node, dir.as_deref());
async fn cmd_list(repo: Option<String>, status: Option<String>, node: String) -> Result<()> {
let client = NodeClient::new(&node, None);
let url = if let Some(ref repo) = repo {
let (owner, name) = repo
.split_once('/')
let (owner, name) = repo.split_once('/')
.map(|(o, n)| (o.to_string(), n.to_string()))
.context("use owner/repo format")?;
let mut u = format!("/api/v1/repos/{owner}/{name}/bounties");
@@ -231,10 +185,7 @@ async fn cmd_list(
u
};
let resp = client
.get_authed(&url)
.await
.context("failed to connect to node")?;
let resp = client.get(&url).await.context("failed to connect to node")?;
let body: Value = resp.json().await.unwrap_or_default();
let bounties = body["bounties"].as_array();
@@ -255,9 +206,9 @@ async fn cmd_list(
Ok(())
}
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?;
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?;
let status = resp.status();
let body: Value = resp.json().await.unwrap_or_default();
@@ -271,22 +222,14 @@ async fn cmd_show(id: String, node: String, dir: Option<PathBuf>) -> Result<()>
Ok(())
}
async fn cmd_claim(
id: String,
wallet: Option<String>,
node: String,
dir: Option<PathBuf>,
) -> Result<()> {
async fn cmd_claim(id: String, wallet: Option<String>, node: String, dir: Option<PathBuf>) -> Result<()> {
let kp = load_keypair_from_dir(dir.as_deref())
.context("identity not found — run `gl identity new` first")?;
let client = NodeClient::new(&node, Some(kp));
let body = serde_json::json!({ "wallet": wallet });
let resp = client
.post(
&format!("/api/v1/bounties/{id}/claim"),
&serde_json::to_vec(&body)?,
)
.post(&format!("/api/v1/bounties/{id}/claim"), &serde_json::to_vec(&body)?)
.await?;
let status = resp.status();
@@ -308,10 +251,7 @@ async fn cmd_submit(id: String, pr: String, node: String, dir: Option<PathBuf>)
let body = serde_json::json!({ "pr_id": pr });
let resp = client
.post(
&format!("/api/v1/bounties/{id}/submit"),
&serde_json::to_vec(&body)?,
)
.post(&format!("/api/v1/bounties/{id}/submit"), &serde_json::to_vec(&body)?)
.await?;
let status = resp.status();
@@ -326,22 +266,14 @@ async fn cmd_submit(id: String, pr: String, node: String, dir: Option<PathBuf>)
Ok(())
}
async fn cmd_approve(
id: String,
tx_hash: Option<String>,
node: String,
dir: Option<PathBuf>,
) -> Result<()> {
async fn cmd_approve(id: String, tx_hash: Option<String>, node: String, dir: Option<PathBuf>) -> Result<()> {
let kp = load_keypair_from_dir(dir.as_deref())
.context("identity not found — run `gl identity new` first")?;
let client = NodeClient::new(&node, Some(kp));
let body = serde_json::json!({ "tx_hash": tx_hash });
let resp = client
.post(
&format!("/api/v1/bounties/{id}/approve"),
&serde_json::to_vec(&body)?,
)
.post(&format!("/api/v1/bounties/{id}/approve"), &serde_json::to_vec(&body)?)
.await?;
let status = resp.status();
@@ -363,10 +295,7 @@ async fn cmd_cancel(id: String, node: String, dir: Option<PathBuf>) -> Result<()
let body = serde_json::json!({});
let resp = client
.post(
&format!("/api/v1/bounties/{id}/cancel"),
&serde_json::to_vec(&body)?,
)
.post(&format!("/api/v1/bounties/{id}/cancel"), &serde_json::to_vec(&body)?)
.await?;
let status = resp.status();
@@ -403,10 +332,7 @@ async fn cmd_stats(node: String) -> Result<()> {
let count = entry["completed"].as_i64().unwrap_or(0);
let earned = entry["total_earned"].as_i64().unwrap_or(0);
let short = &did[did.len().saturating_sub(8)..];
println!(
" {}. ...{short} {count} bounties {earned} $GITLAWB",
i + 1
);
println!(" {}. ...{short} {count} bounties {earned} $GITLAWB", i + 1);
}
}
}
@@ -422,11 +348,7 @@ mod tests {
let mut server = mockito::Server::new_async().await;
let dir = tempfile::TempDir::new().unwrap();
let kp = gitlawb_core::identity::Keypair::generate();
std::fs::write(
dir.path().join("identity.pem"),
kp.to_pem().unwrap().as_bytes(),
)
.unwrap();
std::fs::write(dir.path().join("identity.pem"), kp.to_pem().unwrap().as_bytes()).unwrap();
let _m = server
.mock("POST", mockito::Matcher::Regex(r"/bounties$".to_string()))
@@ -440,14 +362,10 @@ mod tests {
"owner/repo".to_string(),
"Fix bug".to_string(),
50000,
None,
None,
None,
None, None, None,
server.url(),
Some(dir.path().to_path_buf()),
)
.await
.unwrap();
).await.unwrap();
}
#[tokio::test]
@@ -457,14 +375,10 @@ mod tests {
"owner/repo".to_string(),
"Fix bug".to_string(),
50000,
None,
None,
None,
None, None, None,
"http://127.0.0.1:1".to_string(),
Some(dir.path().to_path_buf()),
)
.await
.unwrap_err();
).await.unwrap_err();
assert!(err.to_string().contains("identity not found"));
}
@@ -480,7 +394,7 @@ mod tests {
.create_async()
.await;
cmd_list(None, None, server.url(), None).await.unwrap();
cmd_list(None, None, server.url()).await.unwrap();
}
#[tokio::test]
@@ -488,11 +402,7 @@ mod tests {
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();
std::fs::write(dir.path().join("identity.pem"), kp.to_pem().unwrap().as_bytes()).unwrap();
let _m = server
.mock("POST", mockito::Matcher::Regex(r"/claim$".to_string()))
@@ -507,9 +417,7 @@ mod tests {
Some("0xWALLET".to_string()),
server.url(),
Some(dir.path().to_path_buf()),
)
.await
.unwrap();
).await.unwrap();
}
#[tokio::test]
@@ -524,9 +432,7 @@ mod tests {
.create_async()
.await;
let err = cmd_show("nonexistent".to_string(), server.url(), None)
.await
.unwrap_err();
let err = cmd_show("nonexistent".to_string(), server.url()).await.unwrap_err();
assert!(err.to_string().contains("not found"));
}
Loaded 100 of 180 files, more files were not shown because too many files have changed in this diff. Show more