feat: Add optional runner.post_task_script hook after task cleanup (#1026)

- Adds `runner.post_task_script` and `runner.post_task_script_timeout` (default `5m`) to run a host executable after each task’s built-in cleanup (post-steps, container teardown, bind-workdir removal).
- Stops task heartbeats via `Reporter.StopHeartbeats()` while the script runs so Gitea won’t assign overlapping work; the final task acknowledgement still happens in `reporter.Close()`.
- Script output goes to the runner process log; non-zero exits are warned only and do not change the job result.
- Documents lifecycle, offline behavior, timeouts, and Windows limits (`.ps1` not supported yet) in `docs/post-task-script.md`.

Reviewed-on: https://gitea.com/gitea/runner/pulls/1026
Reviewed-by: Zettat123 <39446+zettat123@noreply.gitea.com>
This commit is contained in:
Nicolas
2026-06-19 19:28:10 +00:00
parent df0370f8bf
commit 007717956a
28 changed files with 922 additions and 263 deletions

View File

@@ -83,6 +83,21 @@ runner:
# terminal; tools like `docker build` emit redrawing progress frames into the captured log
# when a TTY is present.
allocate_pty: false
# Optional executable on the host, run once after each task's built-in cleanup
# (post-steps, container teardown, bind-workdir removal). Additive only.
#
# IMPORTANT: While this script runs the runner stops task heartbeats and stays
# offline from Gitea's perspective until the script exits. A script that never
# returns blocks new work until post_task_script_timeout kills it (default 5m).
# Keep scripts short; set post_task_script_timeout to a safe upper bound.
#
# Output -> runner process log (not the job log). Non-zero exit -> warning only.
# Windows: use .exe, .bat, or .cmd. PowerShell (.ps1) is not supported yet as
# the configured path; wrap PowerShell commands in a .cmd file instead.
# Full guide: docs/post-task-script.md
post_task_script: ''
# Hard limit on post_task_script runtime. Default if omitted: 5m.
post_task_script_timeout: 5m
cache:
# Enable the built-in cache server (used by actions/cache and similar actions).

View File

@@ -16,6 +16,12 @@ import (
"go.yaml.in/yaml/v4"
)
// DefaultPostTaskScriptTimeout is the fallback cap on how long the post-task
// script may run when post_task_script is set without an explicit timeout. It is
// applied both at config load (for a configured script) and at the point of use
// (so a programmatically built config still gets a sane bound).
const DefaultPostTaskScriptTimeout = 5 * time.Minute
// Log represents the configuration for logging.
type Log struct {
Level string `yaml:"level"` // Level indicates the logging level.
@@ -23,26 +29,28 @@ type Log struct {
// 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.
WorkdirCleanupAge time.Duration `yaml:"workdir_cleanup_age"` // WorkdirCleanupAge removes stale bind-workdir task directories and orphaned host-mode scratch dirs older than this duration during idle cleanup.
IdleCleanupInterval time.Duration `yaml:"idle_cleanup_interval"` // IdleCleanupInterval runs stale-directory cleanup periodically while the runner is idle. Set to 0 to disable cleanup cadence.
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.
ReportCloseTimeout time.Duration `yaml:"report_close_timeout"` // ReportCloseTimeout caps each RPC attempt when flushing the final logs and task state at job completion, on a detached context so a server cancel can't block the acknowledgement.
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
AllocatePTY bool `yaml:"allocate_pty"` // AllocatePTY allocates a pseudo-TTY for each step's process. Default is false, matching GitHub's actions/runner. Enable only for jobs that need an interactive terminal; tools like docker build emit redrawing progress frames into the captured log when a TTY is present. Applies to both host and docker backends.
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.
WorkdirCleanupAge time.Duration `yaml:"workdir_cleanup_age"` // WorkdirCleanupAge removes stale bind-workdir task directories and orphaned host-mode scratch dirs older than this duration during idle cleanup.
IdleCleanupInterval time.Duration `yaml:"idle_cleanup_interval"` // IdleCleanupInterval runs stale-directory cleanup periodically while the runner is idle. Set to 0 to disable cleanup cadence.
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.
ReportCloseTimeout time.Duration `yaml:"report_close_timeout"` // ReportCloseTimeout caps each RPC attempt when flushing the final logs and task state at job completion, on a detached context so a server cancel can't block the acknowledgement.
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
AllocatePTY bool `yaml:"allocate_pty"` // AllocatePTY allocates a pseudo-TTY for each step's process. Default is false, matching GitHub's actions/runner. Enable only for jobs that need an interactive terminal; tools like docker build emit redrawing progress frames into the captured log when a TTY is present. Applies to both host and docker backends.
PostTaskScript string `yaml:"post_task_script"` // PostTaskScript is the path to an executable script run on the host after each task's cleanup completes. Empty disables the hook. On Windows use .exe/.bat/.cmd; PowerShell (.ps1) is not supported yet as the configured path.
PostTaskScriptTimeout time.Duration `yaml:"post_task_script_timeout"` // PostTaskScriptTimeout caps how long the post-task script may run. Default is 5m when post_task_script is set.
}
// Cache represents the configuration for caching.
@@ -193,6 +201,9 @@ func LoadDefault(file string) (*Config, error) {
if cfg.Runner.ReportCloseTimeout <= 0 {
cfg.Runner.ReportCloseTimeout = 10 * time.Second
}
if cfg.Runner.PostTaskScript != "" && cfg.Runner.PostTaskScriptTimeout <= 0 {
cfg.Runner.PostTaskScriptTimeout = DefaultPostTaskScriptTimeout
}
if cfg.Metrics.Addr == "" {
cfg.Metrics.Addr = "127.0.0.1:9101"
}

View File

@@ -107,6 +107,34 @@ runner:
// TestLoadDefault_MalformedYAMLReturnsParseError pins the error surfaced for
// invalid YAML to the canonical "parse config file" message rather than the
// "for defaults metadata" variant — i.e. the main yaml.Unmarshal runs first.
func TestLoadDefault_LoadsPostTaskScript(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "config.yaml")
require.NoError(t, os.WriteFile(path, []byte(`
runner:
post_task_script: /usr/local/bin/post-task.sh
post_task_script_timeout: 2m
`), 0o600))
cfg, err := LoadDefault(path)
require.NoError(t, err)
assert.Equal(t, "/usr/local/bin/post-task.sh", cfg.Runner.PostTaskScript)
assert.Equal(t, 2*time.Minute, cfg.Runner.PostTaskScriptTimeout)
}
func TestLoadDefault_DefaultsPostTaskScriptTimeout(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "config.yaml")
require.NoError(t, os.WriteFile(path, []byte(`
runner:
post_task_script: /usr/local/bin/post-task.sh
`), 0o600))
cfg, err := LoadDefault(path)
require.NoError(t, err)
assert.Equal(t, 5*time.Minute, cfg.Runner.PostTaskScriptTimeout)
}
func TestLoadDefault_MalformedYAMLReturnsParseError(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "config.yaml")