Files
act_runner/internal/pkg/config/config.go
silverwind 5edc4ba550 Authenticate cache requests via ACTIONS_RUNTIME_TOKEN and scope by repo (#849)
Closes #848. Addresses [GHSA-82g9-637c-2fx2](https://github.com/go-gitea/gitea/security/advisories/GHSA-82g9-637c-2fx2) and the follow-up points raised by @ChristopherHX and @haroutp in that thread.

The change is breaking only for `cache.external_server` which uses auth via a pre-shared secret.

## How auth works now

1. **Runner starts** → opens the embedded cache server on `:port`. Loads / creates a 32-byte HMAC signing key in `<cache-dir>/.secret`.
2. **Runner receives a task** → calls `handler.RegisterJob(ACTIONS_RUNTIME_TOKEN, repository)` before the job runs, defers a revoker that removes the credential on completion. Registrations are reference-counted so a stray re-register cannot revoke a live job.
3. **Job container runs `actions/cache`** → the toolkit sends `Authorization: Bearer $ACTIONS_RUNTIME_TOKEN` on every management call (`reserve`, `upload`, `commit`, `find`, `clean`). The cache server's middleware looks the token up in the registered-jobs map: miss → 401; hit → the job's repository is injected into the request context.
4. **Repository scoping** — every cache entry is stamped with `Repo` on reserve; `find`, `upload`, `commit` all verify the caller's repo matches. A job in repo A cannot see or poison a cache entry owned by repo B, even when both reach the server over the same docker bridge. GC dedup also groups by `(Repo, Key, Version)` so one repo can't age out another.
5. **Archive downloads** — `@actions/cache` does not attach Authorization when downloading `archiveLocation`, so the `find` response is a short-lived HMAC-signed URL: `…/artifacts/:id?exp=<unix>&sig=<hmac>`, 10-minute TTL, signature binds `cacheID:exp`. Tampered, expired, or foreign-secret URLs get 401.
6. **Defence-in-depth** — `ACTIONS_RUNTIME_TOKEN` is added to `task.Secrets` so the runner's log masker scrubs it from step output.

## `cache.external_server` (standalone `act_runner cache-server`)

Operators set `cache.external_secret` to the same value on the runner config and the `act_runner cache-server` config. The `cache-server` then runs with bearer auth on the cache API and exposes a control-plane at `POST /_internal/{register,revoke}` (gated by the shared secret). The runner pre-registers each task's `ACTIONS_RUNTIME_TOKEN` with the remote server before the job runs and revokes it on completion. Same per-job auth + repo scoping as the embedded handler, just over the network.

`cache-server` refuses to start without `cache.external_secret`; runner config load also fails when `cache.external_server` is set without `cache.external_secret`.

## User-facing changes

- **One-time cache miss after upgrade.** Pre-existing entries in `bolt.db` have no `Repo` stamp and won't match any job — they'll be evicted by the normal GC. First job per cache key rebuilds its cache.
- **`cache.external_server` deployments must add `cache.external_secret`.** Breaking change for anyone running a standalone `act_runner cache-server`: set the same `cache.external_secret` in both the runner config and the cache-server config. Without it neither side starts.
- **No config changes required for the default setup.** Runners using the embedded cache server (the common case) keep working without any yaml edits; the auth mechanism is invisible to workflows.

---
This PR was written with the help of Claude Opus 4.7

---------

Co-authored-by: Nicolas <bircni@icloud.com>
Co-authored-by: Christopher Homberger <christopher.homberger@web.de>
Reviewed-on: https://gitea.com/gitea/act_runner/pulls/849
Reviewed-by: ChristopherHX <38043+christopherhx@noreply.gitea.com>
2026-04-27 23:59:20 +00:00

202 lines
10 KiB
Go

// Copyright 2022 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package config
import (
"errors"
"fmt"
"maps"
"os"
"path/filepath"
"time"
"github.com/joho/godotenv"
log "github.com/sirupsen/logrus"
"go.yaml.in/yaml/v4"
)
// Log represents the configuration for logging.
type Log struct {
Level string `yaml:"level"` // Level indicates the logging level.
}
// Runner represents the configuration for the runner.
type Runner struct {
File string `yaml:"file"` // File specifies the file path for the runner.
Capacity int `yaml:"capacity"` // Capacity specifies the capacity of the runner.
Envs map[string]string `yaml:"envs"` // Envs stores environment variables for the runner.
EnvFile string `yaml:"env_file"` // EnvFile specifies the path to the file containing environment variables for the runner.
Timeout time.Duration `yaml:"timeout"` // Timeout specifies the duration for runner timeout.
ShutdownTimeout time.Duration `yaml:"shutdown_timeout"` // ShutdownTimeout specifies the duration to wait for running jobs to complete during a shutdown of the runner.
Insecure bool `yaml:"insecure"` // Insecure indicates whether the runner operates in an insecure mode.
FetchTimeout time.Duration `yaml:"fetch_timeout"` // FetchTimeout specifies the timeout duration for fetching resources.
FetchInterval time.Duration `yaml:"fetch_interval"` // FetchInterval specifies the interval duration for fetching resources.
FetchIntervalMax time.Duration `yaml:"fetch_interval_max"` // FetchIntervalMax specifies the maximum backoff interval when idle.
LogReportInterval time.Duration `yaml:"log_report_interval"` // LogReportInterval specifies the base interval for periodic log flush.
LogReportMaxLatency time.Duration `yaml:"log_report_max_latency"` // LogReportMaxLatency specifies the max time a log row can wait before being sent.
LogReportBatchSize int `yaml:"log_report_batch_size"` // LogReportBatchSize triggers immediate log flush when buffer reaches this size.
StateReportInterval time.Duration `yaml:"state_report_interval"` // StateReportInterval specifies the interval for state reporting.
Labels []string `yaml:"labels"` // Labels specify the labels of the runner. Labels are declared on each startup
GithubMirror string `yaml:"github_mirror"` // GithubMirror defines what mirrors should be used when using github
}
// Cache represents the configuration for caching.
type Cache struct {
Enabled *bool `yaml:"enabled"` // Enabled indicates whether caching is enabled. It is a pointer to distinguish between false and not set. If not set, it will be true.
Dir string `yaml:"dir"` // Dir specifies the directory path for caching.
Host string `yaml:"host"` // Host specifies the caching host.
Port uint16 `yaml:"port"` // Port specifies the caching port.
ExternalServer string `yaml:"external_server"` // ExternalServer specifies the URL of external cache server
ExternalSecret string `yaml:"external_secret"` // ExternalSecret is a shared secret between this runner and an external act_runner cache-server, enabling per-job ACTIONS_RUNTIME_TOKEN authentication and repo scoping over the network. Leave empty to keep the legacy unauthenticated behavior.
}
// Container represents the configuration for the container.
type Container struct {
Network string `yaml:"network"` // Network specifies the network for the container.
NetworkMode string `yaml:"network_mode"` // Deprecated: use Network instead. Could be removed after Gitea 1.20
Privileged bool `yaml:"privileged"` // Privileged indicates whether the container runs in privileged mode.
Options string `yaml:"options"` // Options specifies additional options for the container.
WorkdirParent string `yaml:"workdir_parent"` // WorkdirParent specifies the parent directory for the container's working directory.
ValidVolumes []string `yaml:"valid_volumes"` // ValidVolumes specifies the volumes (including bind mounts) can be mounted to containers.
DockerHost string `yaml:"docker_host"` // DockerHost specifies the Docker host. It overrides the value specified in environment variable DOCKER_HOST.
ForcePull bool `yaml:"force_pull"` // Pull docker image(s) even if already present
ForceRebuild bool `yaml:"force_rebuild"` // Rebuild docker image(s) even if already present
RequireDocker bool `yaml:"require_docker"` // Always require a reachable docker daemon, even if not required by act_runner
DockerTimeout time.Duration `yaml:"docker_timeout"` // Timeout to wait for the docker daemon to be reachable, if docker is required by require_docker or act_runner
BindWorkdir bool `yaml:"bind_workdir"` // BindWorkdir binds the workspace to the host filesystem instead of using Docker volumes. Required for DinD when jobs use docker compose with bind mounts.
}
// Host represents the configuration for the host.
type Host struct {
WorkdirParent string `yaml:"workdir_parent"` // WorkdirParent specifies the parent directory for the host's working directory.
}
// Metrics represents the configuration for the Prometheus metrics endpoint.
type Metrics struct {
Enabled bool `yaml:"enabled"` // Enabled indicates whether the metrics endpoint is exposed.
Addr string `yaml:"addr"` // Addr specifies the listen address for the metrics HTTP server (e.g., ":9101").
}
// Config represents the overall configuration.
type Config struct {
Log Log `yaml:"log"` // Log represents the configuration for logging.
Runner Runner `yaml:"runner"` // Runner represents the configuration for the runner.
Cache Cache `yaml:"cache"` // Cache represents the configuration for caching.
Container Container `yaml:"container"` // Container represents the configuration for the container.
Host Host `yaml:"host"` // Host represents the configuration for the host.
Metrics Metrics `yaml:"metrics"` // Metrics represents the configuration for the Prometheus metrics endpoint.
}
// LoadDefault returns the default configuration.
// If file is not empty, it will be used to load the configuration.
func LoadDefault(file string) (*Config, error) {
cfg := &Config{}
if file != "" {
content, err := os.ReadFile(file)
if err != nil {
return nil, fmt.Errorf("open config file %q: %w", file, err)
}
if err := yaml.Unmarshal(content, cfg); err != nil {
return nil, fmt.Errorf("parse config file %q: %w", file, err)
}
}
compatibleWithOldEnvs(file != "", cfg)
if cfg.Runner.EnvFile != "" {
if stat, err := os.Stat(cfg.Runner.EnvFile); err == nil && !stat.IsDir() {
envs, err := godotenv.Read(cfg.Runner.EnvFile)
if err != nil {
return nil, fmt.Errorf("read env file %q: %w", cfg.Runner.EnvFile, err)
}
if cfg.Runner.Envs == nil {
cfg.Runner.Envs = map[string]string{}
}
maps.Copy(cfg.Runner.Envs, envs)
}
}
if cfg.Log.Level == "" {
cfg.Log.Level = "info"
}
if cfg.Runner.File == "" {
cfg.Runner.File = ".runner"
}
if cfg.Runner.Capacity <= 0 {
cfg.Runner.Capacity = 1
}
if cfg.Runner.Timeout <= 0 {
cfg.Runner.Timeout = 3 * time.Hour
}
if cfg.Cache.Enabled == nil {
b := true
cfg.Cache.Enabled = &b
}
if *cfg.Cache.Enabled {
if cfg.Cache.Dir == "" {
home, _ := os.UserHomeDir()
cfg.Cache.Dir = filepath.Join(home, ".cache", "actcache")
}
if cfg.Cache.ExternalServer != "" && cfg.Cache.ExternalSecret == "" {
return nil, errors.New("cache.external_server is set but cache.external_secret is empty; configure the same external_secret on this runner and the act_runner cache-server")
}
}
if cfg.Container.WorkdirParent == "" {
cfg.Container.WorkdirParent = "workspace"
}
if cfg.Host.WorkdirParent == "" {
home, _ := os.UserHomeDir()
cfg.Host.WorkdirParent = filepath.Join(home, ".cache", "act")
}
if cfg.Runner.FetchTimeout <= 0 {
cfg.Runner.FetchTimeout = 5 * time.Second
}
if cfg.Runner.FetchInterval <= 0 {
cfg.Runner.FetchInterval = 2 * time.Second
}
if cfg.Runner.FetchIntervalMax <= 0 {
cfg.Runner.FetchIntervalMax = 60 * time.Second
}
if cfg.Runner.LogReportInterval <= 0 {
cfg.Runner.LogReportInterval = 5 * time.Second
}
if cfg.Runner.LogReportMaxLatency <= 0 {
cfg.Runner.LogReportMaxLatency = 3 * time.Second
}
if cfg.Runner.LogReportBatchSize <= 0 {
cfg.Runner.LogReportBatchSize = 100
}
if cfg.Runner.StateReportInterval <= 0 {
cfg.Runner.StateReportInterval = 5 * time.Second
}
if cfg.Metrics.Addr == "" {
cfg.Metrics.Addr = "127.0.0.1:9101"
}
// Validate and fix invalid config combinations to prevent confusing behavior.
if cfg.Runner.FetchIntervalMax < cfg.Runner.FetchInterval {
log.Warnf("fetch_interval_max (%v) is less than fetch_interval (%v), setting fetch_interval_max to fetch_interval",
cfg.Runner.FetchIntervalMax, cfg.Runner.FetchInterval)
cfg.Runner.FetchIntervalMax = cfg.Runner.FetchInterval
}
if cfg.Runner.LogReportMaxLatency >= cfg.Runner.LogReportInterval {
log.Warnf("log_report_max_latency (%v) >= log_report_interval (%v), the max-latency timer will never fire before the periodic ticker; consider lowering log_report_max_latency",
cfg.Runner.LogReportMaxLatency, cfg.Runner.LogReportInterval)
}
// although `container.network_mode` will be deprecated, but we have to be compatible with it for now.
if cfg.Container.NetworkMode != "" && cfg.Container.Network == "" {
log.Warn("You are trying to use deprecated configuration item of `container.network_mode`, please use `container.network` instead.")
if cfg.Container.NetworkMode == "bridge" {
// Previously, if the value of `container.network_mode` is `bridge`, we will create a new network for job.
// But “bridge” is easily confused with the bridge network created by Docker by default.
// So we set the value of `container.network` to empty string to make `act_runner` automatically create a new network for job.
cfg.Container.Network = ""
} else {
cfg.Container.Network = cfg.Container.NetworkMode
}
}
return cfg, nil
}