fix: align runner behaviours (#1338)

Contains a number of small bug fixes where jobs behaved differently from GitHub or failed silently.

1. Hooks fail on a refused `::set-env::` or `::add-path::` and no longer inherit the last step's identity
1. Docker build, exec and wait errors are returned instead of swallowed, token-only registry credentials work, logs of `--tty` services decode
1. Env files split lines like GitHub on each OS, so a carriage return is kept on Linux and CRLF ends a line on Windows, empty heredoc names or delimiters are rejected
1. Post steps run after their pre step even when main was skipped, composites see undeclared inputs, `runs.args` wins without `with.args` being parsed
1. Docker actions skip evaluating defaults of inputs given in `with` and read `entryPoint` and `args` in any case, a lowercase `dockerfile` is found, undeclared inputs get GitHub's warning
1. A user-set `CI` is kept, `GITHUB_REPOSITORY_ID` and the other missing `GITHUB_*` variables are exported
1. `timeout-minutes` can read the step's own `env`, a step-level `ACTIONS_ALLOW_UNSECURE_COMMANDS: false` beats a job-level `true` while the runner's own opt-in still wins, `pwsh` quotes the script path
1. A step `env:` given as one expression such as `${{ fromJSON(matrix.env) }}` is applied, `hashFiles` fails with GitHub's messages on script errors and after 120 seconds, a job image without node still gets an empty hash
1. A step whose command files cannot be reset fails instead of importing stale ones, a timeout between steps fails the job instead of reporting success
1. One named volume can be mounted at several paths, host-mode PTY steps keep their last output when they fail, host scratch directories are removed when job setup fails
1. Cancelling a step right after it starts kills its whole process tree
1. Cache prefix restores pick the newest entry created within the same second, also on S3, cache commits with a wrong size are rejected
1. Artifact chunks are written at their offset, download URLs are escaped, listing a run without artifacts no longer crashes
1. Poll backoff reaches `fetch_interval_max`, proxy passwords are masked in more forms, secrets are also masked in step names and in their quoted form in the runner log, a failed final report is logged
1. On Windows hosts a differently cased unsecure-commands opt-in or proxy variable counts, and an early cancel no longer leaks a job object handle
1. Interactive `register` prompts for a missing token and stops on SIGTERM, `exec --list --detect-event` no longer panics without events, `config set` works on `cache.s3` keys

Reviewed-on: https://gitea.com/gitea/runner/pulls/1338
Reviewed-by: bircni <[email protected]>
Co-authored-by: silverwind <[email protected]>

act/runner/expression_test.go

@@ -5,9 +5,20 @@
 package runner
 
 import (
+	"bytes"
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"reflect"
 	"strings"
 	"sync"
 	"testing"
+	"time"
+
+	"gitea.com/gitea/runner/act/common"
+	"gitea.com/gitea/runner/act/common/logging/logtest"
+	"gitea.com/gitea/runner/act/container"
 
 	"gitea.dev/actionslib/pkg/exprparser"
 	"gitea.dev/actionslib/pkg/model"
@@ -144,6 +155,92 @@ func TestEvaluateRunContext(t *testing.T) {
 	}
 }
 
+type hashFilesContainer struct {
+	fakeContainer
+	stdout, stderr io.Writer
+	copyErr        error
+	execute        func([]string, map[string]string, string, string) common.Executor
+}
+
+func (c *hashFilesContainer) Copy(_destPath string, _files ...*container.FileEntry) common.Executor {
+	return common.NewErrorExecutor(c.copyErr)
+}
+
+func (c *hashFilesContainer) Exec(command []string, env map[string]string, user, workdir string) common.Executor {
+	return c.execute(command, env, user, workdir)
+}
+
+func (c *hashFilesContainer) ReplaceLogWriter(stdout, stderr io.Writer) (io.Writer, io.Writer) {
+	previousOut, previousErr := c.stdout, c.stderr
+	c.stdout, c.stderr = stdout, stderr
+	return previousOut, previousErr
+}
+
+func TestGetHashFilesFunction(t *testing.T) {
+	const failureMessage = "hashFiles('dir''file, *.sum') failed. Fail to hash files under directory '/workspace'"
+	for _, test := range []struct {
+		name    string
+		output  string
+		execErr error
+		copyErr error
+		hash    string
+		err     string
+		warning bool
+		expired bool
+	}{
+		{name: "success", output: "patterns __OUTPUT__wrong__OUTPUT__ echoed\n__OUTPUT__digest__OUTPUT__", hash: "digest"},
+		{name: "no matches", output: "__OUTPUT____OUTPUT__"},
+		{name: "script failure", output: "Cannot find: node in PATH\n__OUTPUT__digest__OUTPUT__", execErr: container.ExitCodeError(1), err: failureMessage},
+		{name: "timeout", execErr: context.DeadlineExceeded, err: "hashFiles('dir''file, *.sum') couldn't finish within 120 seconds"},
+		{name: "job deadline", execErr: context.DeadlineExceeded, expired: true, err: context.DeadlineExceeded.Error()},
+		{name: "node missing", execErr: fmt.Errorf("wrapped: %w", container.ExitCodeError(127)), warning: true},
+		{name: "node not executable", execErr: container.ExitCodeError(126), warning: true},
+		{name: "host node missing", execErr: errors.New("Cannot find: node in PATH"), warning: true},
+		{name: "copy failure", copyErr: errors.New("open /runner/cache: permission denied"), err: failureMessage},
+	} {
+		t.Run(test.name, func(t *testing.T) {
+			logger, hook := logtest.NewLogger()
+			stdout, stderr := &bytes.Buffer{}, &bytes.Buffer{}
+			jobContainer := &hashFilesContainer{stdout: stdout, stderr: stderr, copyErr: test.copyErr}
+			jobContainer.execute = func(command []string, env map[string]string, user, workdir string) common.Executor {
+				assert.Equal(t, []string{"node", "/var/run/act/workflow/hashfiles/index.js"}, command)
+				assert.Equal(t, map[string]string{"patterns": "dir'file\n*.sum", "followSymbolicLinks": "true"}, env)
+				assert.Empty(t, user)
+				assert.Empty(t, workdir)
+				return func(_ctx context.Context) error {
+					_, err := io.WriteString(jobContainer.stderr, test.output)
+					require.NoError(t, err)
+					return test.execErr
+				}
+			}
+			ctx := common.WithLogger(t.Context(), logger)
+			if test.expired {
+				var cancel context.CancelFunc
+				ctx, cancel = context.WithDeadline(ctx, time.Now())
+				defer cancel()
+			}
+			result, err := getHashFilesFunction(ctx, &RunContext{
+				Config:       &Config{Workdir: "/workspace"},
+				JobContainer: jobContainer,
+			})([]reflect.Value{reflect.ValueOf("--follow-symbolic-links"), reflect.ValueOf("dir'file"), reflect.ValueOf("*.sum")})
+			if test.err == "" {
+				require.NoError(t, err)
+			} else {
+				require.EqualError(t, err, test.err)
+			}
+			assert.Equal(t, test.hash, result)
+			assert.Same(t, stdout, jobContainer.stdout)
+			assert.Same(t, stderr, jobContainer.stderr)
+			if test.warning {
+				require.Len(t, hook.AllRecords(), 1)
+				assert.Equal(t, "##[warning]hashFiles could not run because node is unavailable in the job environment. Returning an empty string.", hook.LastRecord().Message)
+			} else {
+				assert.Empty(t, hook.AllRecords())
+			}
+		})
+	}
+}
+
 func TestEvaluateStep(t *testing.T) {
 	rc := createRunContext(t)
 	rc.Env["INPUT_FORGED"] = "leaked"