mesh-controller/cmd/mesh-controller/try.go

package main

import (
	"context"
	"encoding/json"
	"errors"
	"flag"
	"fmt"
	"net/url"
	"os"
	"regexp"
	"strings"
	"time"

	"github.com/novox/mesh-controller/internal/link"
)

// A branch is tried before its pull request (novox/hq issue 686), by the checker (novox/hq ADR 0501 §5; issue 1851).
//
// A repository's store tests skip without a store, and no agent may start a database on its machine. So a builder
// pushed, a reviewer read, and only the pull request's merge check ran those tests for the first time: each failure
// there cost a round of fifteen to thirty minutes (mesh-controller #283, #310, #312).
//
// `try <owner>/<repository> <ref>` asks the checker (mesh-delivery-checker's `checker_try`) to judge the commit the ref
// names merged onto the trunk, as it judges a pull request's head: the build modules' fetch, digest and test steps,
// the unit level and then the integration level, each level's kept verdicts taken. From R4e build-agent is asked no
// try. It is a check and nothing more:
//
//   - **no pull request, so no status**: the checker owes the forge nothing for a try;
//   - **nothing registered, nothing built for delivery**: a try writes no verdict of a group and no preview;
//   - **bounded**: one try of a head at a time — a second ask answers the first's id — and at most four open, the
//     checker's own rule; a repository the checker judges no level of (hq) is refused by the checker, and said.
//
// A check outlasts a seat verb's one answer, so the ask answers its id at once and `try --id <id>` reads what came of
// it from the checker (`checker_try_read`), holding its answer up to tryWait for a verdict, like `plans wait`.

// tryWait is how long reading a try holds its answer for the verdict. A variable so a test need not wait.
var tryWait = 20 * time.Second

// A ref as the forge is asked for it — a branch or a commit, never an option — and a `go test -run` pattern.
var (
	tryID    = regexp.MustCompile(`^try-[0-9]+$`)
	tryRef   = regexp.MustCompile(`^[A-Za-z0-9][A-Za-z0-9._/-]*$`)
	tryTests = regexp.MustCompile(`^[A-Za-z0-9_^$|().*+?/\[\]-]+$`)
)

// tryAnswer is what `try` answers, asking or reading.
type tryAnswer struct {
	ID string `json:"id"`
	// State is asked (just now), waiting (nothing said of it yet: in the build queue), running, or the verdict:
	// pass, warning (the repository declares no merge-check.sh), fail, or error (it could not run).
	State      string   `json:"state"`
	Said       string   `json:"said"`
	Repository string   `json:"repository,omitempty"`
	Ref        string   `json:"ref,omitempty"`
	Commit     string   `json:"commit,omitempty"`
	Base       string   `json:"base,omitempty"`
	Trunk      string   `json:"trunk,omitempty"`
	On         string   `json:"on,omitempty"`
	Took       string   `json:"took,omitempty"`
	Failed     []string `json:"failed,omitempty"`
	// Last is the last thing the build seat said of one still running.
	Last string `json:"last,omitempty"`
}

// checkerModule is the module whose tools judge a try (mesh-delivery-checker).
const checkerModule = "mesh-delivery-checker"

// checkerTry is the checker's answer to a try's ask: the try's id.
type checkerTry struct {
	ID string `json:"id"`
}

// checkerTryRead is the checker's word on a try (`checker_try_read`): its state queued, running, pass, fail or error
// (could not run), what it said, the head and trunk judged, how long it took, what failed, and the machines it ran on.
type checkerTryRead struct {
	ID         string   `json:"id"`
	Repository string   `json:"repository"`
	Head       string   `json:"head"`
	Trunk      string   `json:"trunk"`
	Branch     string   `json:"branch,omitempty"`
	State      string   `json:"state"`
	Said       string   `json:"said"`
	Took       string   `json:"took,omitempty"`
	Failed     []string `json:"failed,omitempty"`
	Machines   []string `json:"machines,omitempty"`
}

// askChecker asks one of the checker's tools and reads its result into into. A variable so a test needs no checker.
var askChecker = func(ctx context.Context, tool string, args map[string]any, into any) error {
	js, err := aBus()
	if err != nil {
		return err
	}
	defer js.Close()
	raw, _ := json.Marshal(args)
	answer, err := link.Ask(ctx, link.OverNATS{Conn: js.Conn()}, checkerModule, tool, raw, 30*time.Second)
	if err != nil {
		return fmt.Errorf("%s.%s: %w", checkerModule, tool, err)
	}
	if answer.Error != "" {
		return fmt.Errorf("%s.%s: %s", checkerModule, tool, answer.Error)
	}
	var wrapped struct {
		Result json.RawMessage `json:"result"`
	}
	if err := json.Unmarshal(answer.Result, &wrapped); err == nil && len(wrapped.Result) > 0 {
		return json.Unmarshal(wrapped.Result, into)
	}
	return json.Unmarshal(answer.Result, into)
}

// tryOfChecker is the checker's word on a try as `try` answers it, today's answer unchanged (novox/hq issue 686): queued
// is waiting, and the machines it ran on are where.
func tryOfChecker(r checkerTryRead) tryAnswer {
	a := tryAnswer{ID: r.ID, State: r.State, Said: r.Said, Repository: r.Repository, Commit: r.Head, Trunk: r.Trunk,
		Took: r.Took, Failed: r.Failed, On: strings.Join(r.Machines, ", "), Base: r.Branch}
	switch r.State {
	case "queued":
		a.State = "waiting"
		if a.Said == "" {
			a.Said = "it waits for the checker; ask again"
		}
	case "running":
		if a.Said == "" {
			a.Said = "still running; ask again"
		}
	}
	return a
}

// forgeCommit asks the forge, through its module's tools on the bus, which commit a branch or commit of a
// repository is, and the repository's default branch. A variable so a test needs no forge.
var forgeCommit = func(ctx context.Context, owner, repo, ref string) (commit, trunk string, err error) {
	js, err := aBus()
	if err != nil {
		return "", "", err
	}
	defer js.Close()
	bus := link.OverNATS{Conn: js.Conn()}
	ask := func(path string, into any) error {
		raw, _ := json.Marshal(map[string]any{"path": path})
		answer, err := link.Ask(ctx, bus, "gitea", "gitea_api", raw, 30*time.Second)
		if err != nil {
			return err
		}
		if answer.Error != "" {
			return errors.New(answer.Error)
		}
		return json.Unmarshal(answer.Result, into)
	}
	var commits struct {
		Result []struct {
			SHA string `json:"sha"`
		} `json:"result"`
	}
	if err := ask("/repos/"+owner+"/"+repo+"/commits?limit=1&stat=false&verification=false&files=false&sha="+
		url.QueryEscape(ref), &commits); err != nil {
		return "", "", err
	}
	if len(commits.Result) == 0 || commits.Result[0].SHA == "" {
		return "", "", errors.New("the forge named no commit for it")
	}
	var found struct {
		Result struct {
			DefaultBranch string `json:"default_branch"`
		} `json:"result"`
	}
	if err := ask("/repos/"+owner+"/"+repo, &found); err != nil {
		return "", "", err
	}
	return commits.Result[0].SHA, found.Result.DefaultBranch, nil
}

// tryCommand is `try <owner>/<repository> <ref> [--base <branch>] [--tests <pattern>] [--store-only]`, and
// `try --id <id>` to read what came of one.
func tryCommand(ctx context.Context, args []string) error {
	set := flag.NewFlagSet("try", flag.ContinueOnError)
	base := set.String("base", "", "the branch it is merged into (the repository's default branch when none)")
	tests := set.String("tests", "", "only the tests this `go test -run` pattern names")
	storeOnly := set.Bool("store-only", false, "only the repository's store tests")
	id := set.String("id", "", "a try's id: what came of it")
	positionals, err := parseAround(set, args)
	if err != nil {
		return err
	}
	usage := errors.New("try <owner>/<repository> <branch or commit> [--base <branch>] [--tests <pattern>] " +
		"[--store-only], or try --id <id>")
	if *id != "" {
		if len(positionals) != 0 {
			return usage
		}
		// An id, never a pattern: the checker's `try-<n>`.
		if !tryID.MatchString(*id) {
			return fmt.Errorf("%q is not a try's id, try-<number>", *id)
		}
		return tryRead(ctx, *id)
	}
	if len(positionals) != 2 {
		return usage
	}
	owner, repo, isPath := strings.Cut(positionals[0], "/")
	ref := positionals[1]
	switch {
	case !isPath || !tryRef.MatchString(owner) || !tryRef.MatchString(repo) || strings.Contains(repo, "/"):
		return fmt.Errorf("%q is not a repository on the forge, owner/name; nothing was asked", positionals[0])
	case !tryRef.MatchString(ref):
		return fmt.Errorf("%q is not a branch or a commit; nothing was asked", ref)
	case *base != "" && !tryRef.MatchString(*base):
		return fmt.Errorf("%q is not a branch; nothing was asked", *base)
	case *tests != "" && !tryTests.MatchString(*tests):
		return fmt.Errorf("%q is not a `go test -run` pattern of test names; nothing was asked", *tests)
	}
	// **An unknown ref is refused here, loudly** — not sent to a machine to fail at its clone minutes later.
	commit, trunk, err := forgeCommit(ctx, owner, repo, ref)
	if err != nil {
		return fmt.Errorf("the forge holds no branch or commit %s in %s/%s — is it pushed? — so nothing was asked: %w",
			ref, owner, repo, err)
	}
	if *base != "" {
		trunk = *base
	}
	if trunk == "" {
		return fmt.Errorf("the forge named no default branch for %s/%s, and no --base says what %s is merged into; "+
			"nothing was asked", owner, repo, ref)
	}

	open, err := openStores(ctx)
	if err != nil {
		return err
	}
	defer open.Close()
	entries, read, edges, err := theGraph(ctx, open.inventory)
	if err != nil {
		return err
	}
	p := link.PullUpdated{Owner: owner, Repo: repo, Base: trunk, Commit: commit}
	// Whose repository it is, as a pull request's check reckons it: only the mesh's is tried, the code the
	// build seat runs for every pull request already.
	mesh := pullScope(p, entries, read, edges)
	if !mesh.Mesh {
		return fmt.Errorf("%s/%s is no repository of the mesh — no module is built from it and its owner is not "+
			"the core's — and only the mesh's are tried on the build seat; nothing was asked", owner, repo)
	}
	// **Asked of the checker, never of build-agent** (ADR 0501 §5): the head merged onto the trunk, as a pull request's.
	askArgs := map[string]any{"repository": strings.ToLower(owner + "/" + repo), "head": commit, "trunk": trunk}
	if *tests != "" {
		askArgs["tests"] = *tests
	}
	if *storeOnly {
		askArgs["level"] = "integration"
	}
	var asked checkerTry
	if err := askChecker(ctx, "checker_try", askArgs, &asked); err != nil {
		return fmt.Errorf("the checker did not take a try of %s/%s at %.12s; nothing was asked: %w", owner, repo, commit, err)
	}
	return printTry(tryAnswer{ID: asked.ID, State: "asked", Repository: owner + "/" + repo, Ref: ref, Commit: commit,
		Base: trunk, On: checkerModule, Said: fmt.Sprintf("asked %s to try %s/%s at %.12s (%s) merged into %s: the head "+
			"judged as a pull request's, unit level then integration level; no status is set and nothing is registered. "+
			"Read it with try id=%s", checkerModule, owner, repo, commit, ref, trunk, asked.ID)})
}

// tryRead answers what came of a try, holding the answer up to tryWait for its verdict.
func tryRead(ctx context.Context, id string) error {
	until := time.Now().Add(tryWait)
	for {
		var r checkerTryRead
		if err := askChecker(ctx, "checker_try_read", map[string]any{"id": id}, &r); err != nil {
			return printTry(tryAnswer{ID: id, State: "error", Said: "the checker's word on it cannot be read: " + err.Error()})
		}
		a := tryOfChecker(r)
		if (a.State != "waiting" && a.State != "running") || !time.Now().Add(2*time.Second).Before(until) {
			return printTry(a)
		}
		if err := sleepOrDone(ctx, 2*time.Second); err != nil {
			return err
		}
	}
}

func printTry(a tryAnswer) error {
	fmt.Fprintln(os.Stderr, a.Said)
	for _, l := range a.Failed {
		fmt.Fprintln(os.Stderr, "    "+l)
	}
	out, err := json.MarshalIndent(a, "", "  ")
	if err != nil {
		return err
	}
	fmt.Println(string(out))
	return nil
}