Compare commits
38
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
ee2160d00c | ||
|
|
0e7d9e74d2 | ||
|
|
1d8a244ba4 | ||
|
|
2edef5a00a | ||
|
|
fadf5025cc | ||
|
|
baa5ef802e | ||
|
|
5b20e419ec | ||
|
|
7e3e62062b | ||
|
|
7e0001e304 | ||
|
|
d94764f001 | ||
|
|
482232e8c5 | ||
|
|
e223262408 | ||
|
|
dbe2949f84 | ||
|
|
b7d9590fdc | ||
|
|
7ee2869d60 | ||
|
|
0b74c04aa8 | ||
|
|
e1c8965ddb | ||
|
|
47ef2644ac | ||
|
|
cb7bf94a77 | ||
|
|
8e821ef449 | ||
|
|
07b9bd0ed4 | ||
|
|
02427a60ef | ||
|
|
8661bcfa22 | ||
|
|
6049537655 | ||
|
|
bf3e801f67 | ||
|
|
50861c74f8 | ||
|
|
b15846dd6e | ||
|
|
a44d490d97 | ||
|
|
af5cf53a34 | ||
|
|
2bb5d344f6 | ||
|
|
e846c289c8 | ||
|
|
0fcc560fec | ||
|
|
acf8a76646 | ||
|
|
b62bb15839 | ||
|
|
ff9d3ee6a0 | ||
|
|
c8255eb15d | ||
|
|
4ded07bc63 | ||
|
|
054dc9618c |
+1
-1
@@ -1,4 +1,4 @@
|
||||
66
|
||||
62
|
||||
The long-running resources of this catalogue that do not say how they are ready (`health`, novox/hq ADR 0240
|
||||
rule 8), as `module check` counts them. It may only go down: merge-check.sh fails a change that raises it, and
|
||||
one that lowers it writes the new number on the first line. From 2026-11-18, or once it is 0, a long-running
|
||||
|
||||
@@ -14,7 +14,7 @@ WORKDIR /src
|
||||
COPY go.mod go.sum ./
|
||||
RUN go mod download
|
||||
COPY . .
|
||||
RUN CGO_ENABLED=0 GOOS=linux go build -trimpath -o /mesh-builder ./cmd/mesh-builder
|
||||
RUN CGO_ENABLED=0 GOOS=linux go build -trimpath -buildvcs=false -ldflags=-buildid= -o /mesh-builder ./cmd/mesh-builder
|
||||
|
||||
# Unlike mesh-controller's own FROM scratch (ADR 0006: nothing to audit but one binary), the build
|
||||
# machine's whole job is shelling out to git and docker — it needs a real userland to do that in,
|
||||
|
||||
@@ -115,3 +115,57 @@ func TestTheGenesisDocumentIsDeclaredAndIssuedOutside(t *testing.T) {
|
||||
}
|
||||
t.Fatal("the build agent has no environment file")
|
||||
}
|
||||
|
||||
// **The judge cache is the agent's own, beside its workspace and never in it** (novox/hq ADR 0358 §6, issue 704): a
|
||||
// directory resource of its own, kept as the agent's data, mounted into the agent at the same path as on the host —
|
||||
// the container runtime resolves a judge build's mounts on the host — and handed to the agent as MESH_JUDGE_CACHE.
|
||||
func TestTheJudgeCacheIsADirectoryOfItsOwnMountedAtTheSamePath(t *testing.T) {
|
||||
raw, err := os.ReadFile("module.json")
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var m struct {
|
||||
Data struct {
|
||||
Own []struct {
|
||||
ID string `json:"id"`
|
||||
Path string `json:"path"`
|
||||
Class string `json:"class"`
|
||||
} `json:"own"`
|
||||
} `json:"data"`
|
||||
Resources []struct {
|
||||
ID string `json:"id"`
|
||||
Type string `json:"type"`
|
||||
Content string `json:"content"`
|
||||
Volumes []string `json:"volumes"`
|
||||
} `json:"resources"`
|
||||
}
|
||||
if err := json.Unmarshal(raw, &m); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
dir, data, env, mounted := false, false, false, false
|
||||
for _, d := range m.Data.Own {
|
||||
if d.ID == "judge-cache" && d.Path == "${dir:judge-cache}" && d.Class == "cache" {
|
||||
data = true
|
||||
}
|
||||
}
|
||||
for _, r := range m.Resources {
|
||||
switch {
|
||||
case r.ID == "judge-cache" && r.Type == "directory":
|
||||
dir = true
|
||||
case r.ID == "agent-env":
|
||||
env = strings.Contains(r.Content, "MESH_JUDGE_CACHE=${dir:judge-cache}\n")
|
||||
case r.ID == "server":
|
||||
for _, v := range r.Volumes {
|
||||
if v == "${dir:judge-cache}:${dir:judge-cache}" {
|
||||
mounted = true
|
||||
}
|
||||
if strings.HasPrefix(v, "${dir:workspace}") && strings.Contains(v, "judge-cache") {
|
||||
t.Errorf("the judge cache is mounted inside the workspace: %s", v)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
if !dir || !data || !env || !mounted {
|
||||
t.Fatalf("the judge cache: directory %v, data %v, env %v, mounted at the same path %v", dir, data, env, mounted)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -39,6 +39,12 @@
|
||||
"path": "${dir:workspace}",
|
||||
"class": "cache",
|
||||
"why": "a build's working copy, cloned again for every build"
|
||||
},
|
||||
{
|
||||
"id": "judge-cache",
|
||||
"path": "${dir:judge-cache}",
|
||||
"class": "cache",
|
||||
"why": "the Go cache every merge check's judge is built with and the release-branch judges kept per head; mounted into judge builds only, never into a check's containers (novox/hq ADR 0358 §6)"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -54,12 +60,17 @@
|
||||
"type": "directory",
|
||||
"mode": "0700"
|
||||
},
|
||||
{
|
||||
"id": "judge-cache",
|
||||
"type": "directory",
|
||||
"mode": "0700"
|
||||
},
|
||||
{
|
||||
"id": "agent-env",
|
||||
"type": "file",
|
||||
"path": "${dir:mesh-state}/build-agent.env",
|
||||
"mode": "0600",
|
||||
"content": "MESH_BROKER_FILE=/run/mesh/broker\nMESH_NODE=${machine:name}\nMESH_REGISTRY=${bound:artifact-store:at}:${bound:artifact-store:port}\nMESH_PACKAGE_BINDING=/run/mesh/package-registry.json\nMESH_NPM_TOKEN_FILE=/run/mesh/package-registry.secret\nMESH_GENESIS_PACKAGE_REGISTRY=/run/mesh/genesis-package-registry.json\nMESH_WORKSPACE=${dir:workspace}\n"
|
||||
"content": "MESH_BROKER_FILE=/run/mesh/broker\nMESH_NODE=${machine:name}\nMESH_REGISTRY=${bound:artifact-store:at}:${bound:artifact-store:port}\nMESH_PACKAGE_BINDING=/run/mesh/package-registry.json\nMESH_NPM_TOKEN_FILE=/run/mesh/package-registry.secret\nMESH_GENESIS_PACKAGE_REGISTRY=/run/mesh/genesis-package-registry.json\nMESH_WORKSPACE=${dir:workspace}\nMESH_JUDGE_CACHE=${dir:judge-cache}\n"
|
||||
},
|
||||
{
|
||||
"id": "server",
|
||||
@@ -72,6 +83,7 @@
|
||||
"volumes": [
|
||||
"${dir:mesh-state}:/run/mesh:ro",
|
||||
"${dir:workspace}:${dir:workspace}",
|
||||
"${dir:judge-cache}:${dir:judge-cache}",
|
||||
"/var/run/docker.sock:/var/run/docker.sock"
|
||||
],
|
||||
"restart-on": [
|
||||
|
||||
+121
-5
@@ -101,6 +101,92 @@ export interface OpenPull {
|
||||
/** The head's statuses by context, the newest of each, with its state (novox/hq issue 438): what tells a check
|
||||
* that started and never answered — pending — from one that answered. */
|
||||
checks: Record<string, HeadCheck>;
|
||||
/** The pull request's labels, by name. */
|
||||
labels?: string[];
|
||||
/** Its ready mark (novox/hq issue 722): the label `mesh/ready` and the newest comment "ready at <full head sha>", the
|
||||
* head a reviewer approved. Absent without the label; `head` empty when the label names no head in a comment. */
|
||||
ready?: ReadyMark;
|
||||
}
|
||||
|
||||
/** The label that marks a pull request ready to merge at the head a comment names (novox/hq issue 722). */
|
||||
export const READY_LABEL = "mesh/ready";
|
||||
|
||||
/** A comment that names the head a pull request is marked ready at: "ready at <full sha>", on a line of its own. */
|
||||
const READY_AT = /^\s*ready at ([0-9a-f]{40}|[0-9a-f]{64})\b/im;
|
||||
|
||||
/** A pull request's ready mark: the head it names, who said it and when, and the label's id, to take it off. */
|
||||
export interface ReadyMark {
|
||||
head: string;
|
||||
by?: string;
|
||||
at?: string;
|
||||
label_id: number;
|
||||
}
|
||||
|
||||
/** **The accounts whose "ready at" comment counts** (novox/hq issue 722): the trusted setting ready-authors, which
|
||||
* the mesh writes to the file MESH_GITEA_READY_AUTHORS_FILE names as a line `authors=<account> <account> …`. A file
|
||||
* that cannot be read leaves the mesh's own forge account alone, said; never an empty list read as everyone. */
|
||||
export function readyAuthors(file = process.env.MESH_GITEA_READY_AUTHORS_FILE, own = process.env.MESH_GITEA_ADMIN_USER,
|
||||
read: (f: string) => string = (f) => readFileSync(f, "utf8")): string[] {
|
||||
const fallback = own ? [own] : [];
|
||||
if (!file) return fallback;
|
||||
try {
|
||||
const line = read(file).split("\n").find((l) => l.startsWith("authors="));
|
||||
const authors = (line ?? "").slice("authors=".length).split(/[\s,]+/).filter(Boolean);
|
||||
if (authors.length) return authors;
|
||||
console.error(`[gitea] ${file} names no account that may mark a pull request ready; only ${fallback.join(", ") || "none"} may`);
|
||||
} catch (err) {
|
||||
console.error(`[gitea] ${file} cannot be read (${err instanceof Error ? err.message : err}); only ` +
|
||||
`${fallback.join(", ") || "none"} may mark a pull request ready`);
|
||||
}
|
||||
return fallback;
|
||||
}
|
||||
|
||||
/** One event of an issue's or pull request's timeline, as the forge keeps it, oldest first: a comment, a push to a
|
||||
* pull request's branch (`pull_push`), a label added (body "1") or taken off (body ""), and the rest. */
|
||||
export interface TimelineEvent {
|
||||
id: number;
|
||||
type: string;
|
||||
body: string;
|
||||
created_at?: string;
|
||||
user?: string;
|
||||
label?: { id: number; name: string };
|
||||
}
|
||||
|
||||
/** The comments that wrote "ready at" without counting, by id: each said once in the log (novox/hq issue 722). */
|
||||
const ignoredSaid = new Set<number>();
|
||||
|
||||
/** **The ready mark a pull request's timeline makes** (novox/hq issue 722), read in the forge's order — every event is
|
||||
* one row of one table, numbered as it happened, so the order is exact where times share a second. A "ready at"
|
||||
* comment counts only when its author is one of the accounts given, and only when it was written after the label
|
||||
* mesh/ready was last added and after the last push to the pull request's branch: a push or the label taken off
|
||||
* undoes every mark before it, so a mark older than the latest push never counts, even with the label still on. A
|
||||
* comment by any other account is ignored, and said once. */
|
||||
export function readyMarkOf(labelID: number, events: TimelineEvent[], authors: string[],
|
||||
say: (line: string) => void = (l) => console.error(l)): ReadyMark {
|
||||
const listed = new Set(authors.map((a) => a.toLowerCase()));
|
||||
let labelled = false;
|
||||
let mark: ReadyMark | undefined;
|
||||
for (const e of [...events].sort((x, y) => x.id - y.id)) {
|
||||
if (e.type === "pull_push") {
|
||||
mark = undefined;
|
||||
} else if (e.type === "label" && e.label?.name === READY_LABEL) {
|
||||
labelled = e.body === "1";
|
||||
mark = undefined;
|
||||
} else if (e.type === "comment") {
|
||||
const m = READY_AT.exec(e.body);
|
||||
if (!m) continue;
|
||||
if (!listed.has(String(e.user ?? "").toLowerCase())) {
|
||||
if (!ignoredSaid.has(e.id)) {
|
||||
ignoredSaid.add(e.id);
|
||||
say(`[gitea] a "ready at ${m[1].slice(0, 12)}" comment (${e.id}) by ${e.user ?? "an unknown account"} is ignored: ` +
|
||||
`only ${authors.join(", ") || "no account"} may mark a pull request ready (novox/hq issue 722)`);
|
||||
}
|
||||
continue;
|
||||
}
|
||||
if (labelled) mark = { head: m[1].toLowerCase(), by: e.user, at: e.created_at, label_id: labelID };
|
||||
}
|
||||
}
|
||||
return mark ?? { head: "", label_id: labelID };
|
||||
}
|
||||
|
||||
/** One status on a head, the newest of its context: its state, what it said, and when it was set. */
|
||||
@@ -332,8 +418,9 @@ export class GiteaClient {
|
||||
|
||||
/** The open pull requests of every repository the mesh's account sees, updated since a moment when one is given,
|
||||
* page by page (novox/hq issue 347): each with its repository and its own update time. */
|
||||
async searchOpenPulls(since?: string): Promise<{ owner: string; name: string; number: number; updated_at?: string }[]> {
|
||||
const out: { owner: string; name: string; number: number; updated_at?: string }[] = [];
|
||||
async searchOpenPulls(since?: string): Promise<{ owner: string; name: string; number: number; updated_at?: string;
|
||||
labels?: { id: number; name: string }[] }[]> {
|
||||
const out: { owner: string; name: string; number: number; updated_at?: string; labels?: { id: number; name: string }[] }[] = [];
|
||||
for (let page = 1; page <= 20; page++) {
|
||||
const qs = new URLSearchParams({ type: "pulls", state: "open", limit: "50", page: String(page) });
|
||||
if (since) qs.set("since", since);
|
||||
@@ -343,7 +430,8 @@ export class GiteaClient {
|
||||
const [fo, fn] = String(r.full_name ?? "").split("/");
|
||||
const owner = String(r.owner ?? fo ?? "");
|
||||
const name = String(r.name ?? fn ?? "");
|
||||
if (owner && name && i?.number) out.push({ owner, name, number: Number(i.number), updated_at: i.updated_at });
|
||||
const labels = (Array.isArray(i?.labels) ? i.labels : []).map((l: any) => ({ id: Number(l?.id ?? 0), name: String(l?.name ?? "") }));
|
||||
if (owner && name && i?.number) out.push({ owner, name, number: Number(i.number), updated_at: i.updated_at, labels });
|
||||
}
|
||||
if (!found || found.length < 50) break;
|
||||
}
|
||||
@@ -354,7 +442,7 @@ export class GiteaClient {
|
||||
* requires and the contexts its head has a status of, in any state. What mesh-delivery reads to say a pull
|
||||
* request the mesh was never asked to check; asked of the forge, never of what the announcer remembers, so a
|
||||
* fault in the announcer cannot hide itself. Reads only. */
|
||||
async openPulls(): Promise<OpenPull[]> {
|
||||
async openPulls(readyAuthors: string[] = []): Promise<OpenPull[]> {
|
||||
const out: OpenPull[] = [];
|
||||
const rules = new Map<string, BranchProtection[] | undefined>();
|
||||
for (const found of await this.searchOpenPulls()) {
|
||||
@@ -364,9 +452,14 @@ export class GiteaClient {
|
||||
if (!rules.has(full)) rules.set(full, await this.branchProtections(found.owner, found.name).catch(() => undefined));
|
||||
const rule = rules.get(full)?.find((p) => (p.rule_name ?? p.branch_name) === (pull.base || "main"));
|
||||
const checks = await this.headChecks(found.owner, found.name, pull.head_sha);
|
||||
const labels = found.labels ?? [];
|
||||
// The ready mark (novox/hq issue 722): its timeline is read, whole, only for a pull request that carries the label.
|
||||
const label = labels.find((l) => l.name === READY_LABEL);
|
||||
const ready = label ? readyMarkOf(label.id, await this.timeline(found.owner, found.name, pull.number), readyAuthors)
|
||||
: undefined;
|
||||
out.push({ owner: found.owner, repo: found.name, number: pull.number, base: pull.base ?? "", head_sha: pull.head_sha,
|
||||
html_url: pull.html_url, required: rule?.enable_status_check ? (rule.status_check_contexts ?? []) : [],
|
||||
statuses: Object.keys(checks), checks });
|
||||
statuses: Object.keys(checks), checks, labels: labels.map((l) => l.name), ...(ready ? { ready } : {}) });
|
||||
}
|
||||
return out;
|
||||
}
|
||||
@@ -639,6 +732,24 @@ export class GiteaClient {
|
||||
return this.requestText(`${repoPath(owner, repo)}/pulls/${index}.diff`);
|
||||
}
|
||||
|
||||
/** **Every event of an issue's or pull request's timeline**, oldest first, page by page (novox/hq issue 722): a long
|
||||
* thread hides nothing. Bounded at 100 pages of 50; a longer one is said, and its first 5000 events read. */
|
||||
async timeline(owner: string, repo: string, index: number): Promise<TimelineEvent[]> {
|
||||
indexOf(index);
|
||||
const out: TimelineEvent[] = [];
|
||||
for (let page = 1; page <= 100; page++) {
|
||||
const raw = await this.request<any[]>(`${repoPath(owner, repo)}/issues/${index}/timeline?page=${page}&limit=50`);
|
||||
for (const e of raw ?? []) {
|
||||
out.push({ id: Number(e?.id ?? 0), type: String(e?.type ?? ""), body: String(e?.body ?? ""),
|
||||
created_at: e?.created_at, user: e?.user?.login,
|
||||
...(e?.label ? { label: { id: Number(e.label.id ?? 0), name: String(e.label.name ?? "") } } : {}) });
|
||||
}
|
||||
if (!raw || raw.length < 50) return out;
|
||||
}
|
||||
console.error(`[gitea] ${owner}/${repo}#${index} has more than 5000 timeline events; only the first 5000 are read`);
|
||||
return out;
|
||||
}
|
||||
|
||||
/** Every comment on an issue or pull request, oldest first. */
|
||||
async listComments(owner: string, repo: string, index: number): Promise<GiteaComment[]> {
|
||||
indexOf(index);
|
||||
@@ -803,6 +914,11 @@ export class GiteaAdmin {
|
||||
return { status: res.status, body };
|
||||
}
|
||||
|
||||
/** One admin-API call with a JSON body, answering the status and body (the system webhook, novox/hq issue 729). */
|
||||
call(method: string, path: string, body?: unknown): Promise<AdminResponse> {
|
||||
return this.request(path, { method, ...(body === undefined ? {} : { body: JSON.stringify(body) }) });
|
||||
}
|
||||
|
||||
/** Fail with the forge's own message when a status the caller did not expect comes back. */
|
||||
private static fail(path: string, res: AdminResponse): never {
|
||||
const detail = typeof res.body === "string" ? res.body : JSON.stringify(res.body);
|
||||
|
||||
+152
-64
@@ -40,10 +40,11 @@ import { emit, on } from "@novox/mesh-sdk/events";
|
||||
import { registerModuleTools } from "@novox/mesh-sdk/tools";
|
||||
import { commitStatusTool } from "./delivery.js";
|
||||
import { mergeTool } from "./merge.js";
|
||||
import { GiteaClient, movedSince } from "./client.js";
|
||||
import { GiteaAdmin, GiteaClient, movedSince } from "./client.js";
|
||||
import { CHECK_CONTEXT, REPO_CHECK_CONTEXT, commentFor, headsToAnnounce, statusesFor, type Announced, type Checked,
|
||||
type RepoCheckFacts, reposToLook } from "./pulls.js";
|
||||
import { GateWriter, clonedAs, type BuildStarted } from "./gate.js";
|
||||
import { HOOK_PATH, HOOK_PORT, Pace, claimHead, ensureSystemHook, keptSecret, receiver, type ForgeEvent } from "./webhook.js";
|
||||
import { announcementOf, keepTook, lateVerdictComment, outOfDateWords, sameCommit, tookFile, weighTrunks } from "./trunk.js";
|
||||
|
||||
// Without a way to a token — configured, or mintable with the admin account (token.ts) — there is
|
||||
@@ -145,57 +146,9 @@ async function pollMerged(client: GiteaClient): Promise<void> {
|
||||
// at once.
|
||||
const fresh = !!pull.merged_at && !!since && pull.merged_at > since;
|
||||
if (primedMerges && fresh) {
|
||||
// What it changed, asked for only now: a module is rebuilt because a file inside its own
|
||||
// directory moved, and without this every module built from a repository is rebuilt for a
|
||||
// change to any of them (novox/hq 04-ISSUES/131).
|
||||
const changed = await client.listPullFiles(repo.owner, repo.name, pull.number);
|
||||
// Which of the directories they are in hold a module at the merge commit (novox/hq issue 278): a
|
||||
// change inside one is that module's, held or not, and only a file in none is shared code. Not
|
||||
// said when the list is cut or the forge could not be asked; the mesh then keeps its old rule.
|
||||
let moduleDirs: string[] | null = null;
|
||||
if (!changed.truncated) {
|
||||
try {
|
||||
moduleDirs = await client.moduleDirsAt(repo.owner, repo.name, pull.merge_commit_sha, changed.paths);
|
||||
} catch (err) {
|
||||
console.error(`[gitea] ${repo.full_name}#${pull.number}: which directories hold a module could not be read, ` +
|
||||
`so the mesh reads its files by the old rule — ${err instanceof Error ? err.message : String(err)}`);
|
||||
}
|
||||
}
|
||||
// The head it merged, and what its head was checked as (novox/hq ADR 0239): the delivery it was, made
|
||||
// from the forge's word when its owner never heard the head.
|
||||
let headChecks: Record<string, string> | null = null;
|
||||
if (pull.head_sha) {
|
||||
try {
|
||||
headChecks = await client.commitStatuses(repo.owner, repo.name, pull.head_sha);
|
||||
} catch (err) {
|
||||
console.error(`[gitea] ${repo.full_name}#${pull.number}: its head's statuses could not be read — ${err instanceof Error ? err.message : err}`);
|
||||
}
|
||||
}
|
||||
await emit("pull.merged", {
|
||||
owner: repo.owner,
|
||||
repo: repo.name,
|
||||
number: pull.number,
|
||||
title: pull.title,
|
||||
body: pull.body,
|
||||
head_sha: pull.head_sha,
|
||||
...(headChecks ? { head_checks: headChecks } : {}),
|
||||
head: pull.head,
|
||||
base: pull.base,
|
||||
merge_commit_sha: pull.merge_commit_sha,
|
||||
merged_at: pull.merged_at,
|
||||
clone_url: repo.clone_url,
|
||||
html_url: pull.html_url,
|
||||
paths: changed.paths,
|
||||
paths_truncated: changed.truncated,
|
||||
// Which of them the merge deleted (novox/hq ADR 0236): a module whose manifest went is forgotten,
|
||||
// not built.
|
||||
removed: changed.removed,
|
||||
...(moduleDirs ? { module_dirs: moduleDirs, module_dirs_said: true } : {}),
|
||||
});
|
||||
// Said, because a trigger that fires silently is indistinguishable from one that did not
|
||||
// fire (novox/hq 04-ISSUES/131) — this line is how an operator knows the mesh was told.
|
||||
console.log(`[gitea] announced merge ${repo.full_name}#${pull.number} (${pull.merge_commit_sha.slice(0, 8)}) into ${pull.base}`);
|
||||
if (await announceMerge(client, repo, pull)) pace.miss(`the merge of ${repo.full_name}#${pull.number}`);
|
||||
}
|
||||
else announced.add(pull.merge_commit_sha);
|
||||
announced.add(pull.merge_commit_sha);
|
||||
changed = true;
|
||||
}
|
||||
@@ -206,6 +159,73 @@ async function pollMerged(client: GiteaClient): Promise<void> {
|
||||
lastLook = began;
|
||||
}
|
||||
|
||||
type RepoOf = { owner: string; name: string; full_name: string; clone_url?: string };
|
||||
type PullOf = Awaited<ReturnType<GiteaClient["listPullRequests"]>>[number];
|
||||
|
||||
/** **A merge, announced once, whichever path saw it first** (novox/hq issue 729): the poll or the forge's event. */
|
||||
async function announceMerge(client: GiteaClient, repo: RepoOf, pull: PullOf): Promise<boolean> {
|
||||
if (!pull.merged || !pull.merge_commit_sha || announced.has(pull.merge_commit_sha)) return false;
|
||||
// Recorded before the first wait, so the other path finds it taken while this one is still asking the forge.
|
||||
announced.add(pull.merge_commit_sha);
|
||||
try {
|
||||
// What it changed, asked for only now: a module is rebuilt because a file inside its own
|
||||
// directory moved, and without this every module built from a repository is rebuilt for a
|
||||
// change to any of them (novox/hq 04-ISSUES/131).
|
||||
const changed = await client.listPullFiles(repo.owner, repo.name, pull.number);
|
||||
// Which of the directories they are in hold a module at the merge commit (novox/hq issue 278): a
|
||||
// change inside one is that module's, held or not, and only a file in none is shared code. Not
|
||||
// said when the list is cut or the forge could not be asked; the mesh then keeps its old rule.
|
||||
let moduleDirs: string[] | null = null;
|
||||
if (!changed.truncated) {
|
||||
try {
|
||||
moduleDirs = await client.moduleDirsAt(repo.owner, repo.name, pull.merge_commit_sha, changed.paths);
|
||||
} catch (err) {
|
||||
console.error(`[gitea] ${repo.full_name}#${pull.number}: which directories hold a module could not be read, ` +
|
||||
`so the mesh reads its files by the old rule — ${err instanceof Error ? err.message : String(err)}`);
|
||||
}
|
||||
}
|
||||
// The head it merged, and what its head was checked as (novox/hq ADR 0239): the delivery it was, made
|
||||
// from the forge's word when its owner never heard the head.
|
||||
let headChecks: Record<string, string> | null = null;
|
||||
if (pull.head_sha) {
|
||||
try {
|
||||
headChecks = await client.commitStatuses(repo.owner, repo.name, pull.head_sha);
|
||||
} catch (err) {
|
||||
console.error(`[gitea] ${repo.full_name}#${pull.number}: its head's statuses could not be read — ${err instanceof Error ? err.message : err}`);
|
||||
}
|
||||
}
|
||||
await emit("pull.merged", {
|
||||
owner: repo.owner,
|
||||
repo: repo.name,
|
||||
number: pull.number,
|
||||
title: pull.title,
|
||||
body: pull.body,
|
||||
head_sha: pull.head_sha,
|
||||
...(headChecks ? { head_checks: headChecks } : {}),
|
||||
head: pull.head,
|
||||
base: pull.base,
|
||||
merge_commit_sha: pull.merge_commit_sha,
|
||||
merged_at: pull.merged_at,
|
||||
clone_url: repo.clone_url,
|
||||
html_url: pull.html_url,
|
||||
paths: changed.paths,
|
||||
paths_truncated: changed.truncated,
|
||||
// Which of them the merge deleted (novox/hq ADR 0236): a module whose manifest went is forgotten,
|
||||
// not built.
|
||||
removed: changed.removed,
|
||||
...(moduleDirs ? { module_dirs: moduleDirs, module_dirs_said: true } : {}),
|
||||
});
|
||||
// Said, because a trigger that fires silently is indistinguishable from one that did not
|
||||
// fire (novox/hq 04-ISSUES/131) — this line is how an operator knows the mesh was told.
|
||||
console.log(`[gitea] announced merge ${repo.full_name}#${pull.number} (${pull.merge_commit_sha.slice(0, 8)}) into ${pull.base}`);
|
||||
} catch (err) {
|
||||
announced.delete(pull.merge_commit_sha);
|
||||
throw err;
|
||||
}
|
||||
keepAnnounced();
|
||||
return true;
|
||||
}
|
||||
|
||||
// **Every new head of an open pull request is announced, once** (novox/hq to-be 45 §9): the mesh checks it
|
||||
// against every machine of its facts before it merges. Kept beside the merges' record, so a restart
|
||||
// announces nothing twice; the first look on a machine with no record announces only what moved in the
|
||||
@@ -228,6 +248,31 @@ function keepHeads(): void {
|
||||
writeFileSync(tmp, JSON.stringify({ heads }));
|
||||
renameSync(tmp, pullsRecord);
|
||||
}
|
||||
/** **A head, announced once, whichever path saw it first** (novox/hq issue 729): the poll or the forge's event. */
|
||||
async function announceHead(client: GiteaClient, repo: RepoOf, pull: OpenOf): Promise<boolean> {
|
||||
const key = `${repo.full_name}#${pull.number}`;
|
||||
const sha = String(pull.head_sha ?? "");
|
||||
const before = heads[key];
|
||||
// Claimed before the first wait, so the other path finds it taken while this one is still announcing.
|
||||
if (!claimHead(heads, key, sha)) return false;
|
||||
try {
|
||||
// The announcement the merge tool makes too when it asks a check (trunk.ts, novox/hq ADR 0323 §5).
|
||||
await emit("pull.updated", await announcementOf(client, repo.owner, repo.name, repo.clone_url ?? "", pull));
|
||||
} catch (err) {
|
||||
if (before === undefined) delete heads[key];
|
||||
else heads[key] = before;
|
||||
throw err;
|
||||
}
|
||||
keepHeads();
|
||||
// Said, so an operator knows the mesh was asked to check it.
|
||||
console.log(`[gitea] announced ${key} at ${sha.slice(0, 8)} to be checked before it merges`);
|
||||
// Pending until the verdict comes, so the pull request says a check is running rather than nothing — and
|
||||
// where it is: in the build queue from now, until a build machine takes it (novox/hq issue 446).
|
||||
await gates.pending(repo.owner, repo.name, sha);
|
||||
return true;
|
||||
}
|
||||
type OpenOf = Awaited<ReturnType<GiteaClient["listOpenPullsSince"]>>[number];
|
||||
|
||||
let lastPullLook = "";
|
||||
// **A sweep now and then looks at every repository** (novox/hq issue 347), whatever moved: the floor is a
|
||||
// heuristic, and a heuristic that misses is caught by the next sweep rather than never.
|
||||
@@ -259,15 +304,8 @@ async function pollPulls(client: GiteaClient): Promise<void> {
|
||||
const key = `${repo.full_name}#${pull.number}`;
|
||||
const fresh = primedPulls || (!!pull.updated_at && pull.updated_at > dayAgo);
|
||||
if (fresh) {
|
||||
// The announcement the merge tool makes too when it asks a check (trunk.ts, novox/hq ADR 0323 §5).
|
||||
await emit("pull.updated", await announcementOf(client, repo.owner, repo.name, repo.clone_url, pull));
|
||||
// Said, so an operator knows the mesh was asked to check it.
|
||||
console.log(`[gitea] announced ${key} at ${String(pull.head_sha).slice(0, 8)} to be checked before it merges`);
|
||||
// Pending until the verdict comes, so the pull request says a check is running rather than nothing — and
|
||||
// where it is: in the build queue from now, until a build machine takes it (novox/hq issue 446).
|
||||
await gates.pending(repo.owner, repo.name, String(pull.head_sha));
|
||||
}
|
||||
heads[key] = String(pull.head_sha);
|
||||
if (await announceHead(client, repo, pull)) pace.miss(`${key} at ${String(pull.head_sha).slice(0, 8)}`);
|
||||
} else heads[key] = String(pull.head_sha);
|
||||
changed = true;
|
||||
}
|
||||
if (await trunksMoved(client, repo.owner, repo.name)) changedTrunks = true;
|
||||
@@ -413,12 +451,59 @@ async function buildStarted(event: { body: unknown }): Promise<void> {
|
||||
}
|
||||
}
|
||||
|
||||
/** How fast the polls look: 30 s until the forge's events are heard, five minutes while they are (webhook.ts). */
|
||||
const pace = new Pace();
|
||||
|
||||
/** What the forge's event asks of the announcer at once (issue 729): a new head is announced, and a merge. */
|
||||
async function actOn(client: GiteaClient, event: ForgeEvent): Promise<void> {
|
||||
const b = event.body as { owner?: string; repo?: string; number?: number };
|
||||
if (!b.owner || !b.repo || !b.number) return;
|
||||
const head = ["forge.pull-request.opened", "forge.pull-request.synchronized", "forge.pull-request.reopened"].includes(event.name);
|
||||
const merged = event.name === "forge.pull-request.merged";
|
||||
if (!head && !merged) return;
|
||||
const [repo, pull] = await Promise.all([client.getRepo(b.owner, b.repo), client.getPullRequest(b.owner, b.repo, b.number)]);
|
||||
if (head && pull.state === "open") await announceHead(client, repo, pull);
|
||||
if (merged) await announceMerge(client, repo, pull);
|
||||
}
|
||||
|
||||
/**
|
||||
* **The receiver, and the forge's one system webhook pointing at it** (issue 729). The secret is minted and kept beside
|
||||
* the token; the webhook is made or corrected with the admin account (ADR 0266: the tools' token holds no admin scope).
|
||||
* Answers whether events are heard; a forge that refuses is said, and the polls keep their pace.
|
||||
*/
|
||||
async function listenForForge(client: GiteaClient): Promise<boolean> {
|
||||
const stateDir = process.env.MESH_GITEA_STATE_DIR;
|
||||
const url = process.env.MESH_GITEA_HOOK_URL;
|
||||
if (!stateDir || !url) {
|
||||
console.log("[gitea] no webhook receiver: MESH_GITEA_STATE_DIR or MESH_GITEA_HOOK_URL unset, so the polls alone watch the forge");
|
||||
return false;
|
||||
}
|
||||
try {
|
||||
const secret = keptSecret(join(stateDir, "webhook.secret"));
|
||||
const port = Number(process.env.MESH_GITEA_HOOK_PORT ?? HOOK_PORT);
|
||||
const server = receiver({ secret, port, heard: () => pace.heard(),
|
||||
publish: (event) => emit(event.name, event.body),
|
||||
act: (event) => actOn(client, event) });
|
||||
await new Promise<void>((resolve, reject) => {
|
||||
server.once("error", reject);
|
||||
server.listen(port, process.env.MESH_GITEA_HOOK_HOST ?? "0.0.0.0", () => resolve());
|
||||
});
|
||||
const did = await ensureSystemHook(GiteaAdmin.fromEnv(), url.replace(/\/+$/, "") + HOOK_PATH, secret);
|
||||
console.log(`[gitea] listening for the forge's events on port ${port}; its system webhook ${did}, every event, signed`);
|
||||
return true;
|
||||
} catch (err) {
|
||||
console.error(`[gitea] the forge's events are not heard, so the polls keep their pace — ${err instanceof Error ? err.message : err}`);
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
if (gitea) {
|
||||
const client = gitea;
|
||||
// A poll that fails says so once, not once a minute: the same reason repeating (the forge not up
|
||||
// yet, the admin account refused on a restored forge) is one fact, and a recovery is worth a line.
|
||||
let failing: string | null = null;
|
||||
const tick = (fn: () => Promise<void>, everyMs: number): void => {
|
||||
const tick = (fn: () => Promise<void>, every: number | (() => number)): void => {
|
||||
const everyMs = (): number => (typeof every === "number" ? every : every());
|
||||
// **One pass at a time** (novox/hq issue 250): the next pass is scheduled when this one has ended, so a
|
||||
// pass that outlasts its interval delays the next instead of running beside it — two passes at once
|
||||
// could each announce the same merge before either recorded it.
|
||||
@@ -433,12 +518,15 @@ if (gitea) {
|
||||
if (why !== failing) console.error(`[gitea] not watching until this clears — ${why}`);
|
||||
failing = why;
|
||||
})
|
||||
.finally(() => setTimeout(run, everyMs));
|
||||
.finally(() => setTimeout(run, everyMs()));
|
||||
run();
|
||||
};
|
||||
// **The forge's events first, the polls as the safety net** (novox/hq issue 729): while verified deliveries arrive the
|
||||
// polls slow to every five minutes and announce only what no event said (Pace); otherwise they keep 30 s.
|
||||
await listenForForge(client);
|
||||
tick(() => pollRepos(client), 60_000);
|
||||
tick(() => pollMerged(client), 30_000);
|
||||
tick(() => pollPulls(client), 30_000);
|
||||
tick(() => pollMerged(client), () => pace.every());
|
||||
tick(() => pollPulls(client), () => pace.every());
|
||||
await on("mesh-controller.checked", (event) => {
|
||||
const c = (event.body ?? {}) as Checked;
|
||||
// A head's own verdict takes its turn after every write of that head's gate already asked for (gate.ts).
|
||||
|
||||
@@ -42,7 +42,47 @@
|
||||
"issue.opened",
|
||||
"pull.merged",
|
||||
"pull.updated",
|
||||
"pull.closed"
|
||||
"pull.closed",
|
||||
"forge.push",
|
||||
"forge.create",
|
||||
"forge.delete",
|
||||
"forge.fork",
|
||||
"forge.status",
|
||||
"forge.pull-request.opened",
|
||||
"forge.pull-request.reopened",
|
||||
"forge.pull-request.synchronized",
|
||||
"forge.pull-request.edited",
|
||||
"forge.pull-request.closed",
|
||||
"forge.pull-request.merged",
|
||||
"forge.pull-request.labeled",
|
||||
"forge.pull-request.unlabeled",
|
||||
"forge.pull-request.assigned",
|
||||
"forge.pull-request.unassigned",
|
||||
"forge.pull-request.reviewed",
|
||||
"forge.pull-request.review-requested",
|
||||
"forge.pull-request.commented",
|
||||
"forge.pull-request.changed",
|
||||
"forge.issue-comment.created",
|
||||
"forge.issue-comment.edited",
|
||||
"forge.issue-comment.deleted",
|
||||
"forge.issues.opened",
|
||||
"forge.issues.reopened",
|
||||
"forge.issues.closed",
|
||||
"forge.issues.edited",
|
||||
"forge.issues.labeled",
|
||||
"forge.issues.unlabeled",
|
||||
"forge.issues.assigned",
|
||||
"forge.issues.unassigned",
|
||||
"forge.issues.changed",
|
||||
"forge.release.published",
|
||||
"forge.release.updated",
|
||||
"forge.release.deleted",
|
||||
"forge.release.changed",
|
||||
"forge.repository.created",
|
||||
"forge.repository.deleted",
|
||||
"forge.repository.changed",
|
||||
"forge.wiki.changed",
|
||||
"forge.other"
|
||||
],
|
||||
"consumes": [
|
||||
"mesh-controller.checked",
|
||||
@@ -61,7 +101,14 @@
|
||||
"port": 22,
|
||||
"protocol": "tcp",
|
||||
"from": "mesh",
|
||||
"why": "git over ssh, gitea's own unmodified sshd. Published on the machine's own side at 222, the mesh's fixed public convention \u2014 not 22, which the machine's own daemon holds and a module does not take"
|
||||
"why": "git over ssh, gitea's own unmodified sshd. Published on the machine's own side at 222, the mesh's fixed public convention — not 22, which the machine's own daemon holds and a module does not take"
|
||||
},
|
||||
{
|
||||
"name": "forge-events",
|
||||
"port": 3047,
|
||||
"protocol": "tcp",
|
||||
"from": "machine",
|
||||
"why": "the forge's system webhook, every event signed with a secret the module keeps, from the forge's container on the docker bridge to the module's receiver at the bridge's gateway 172.17.0.1 (novox/hq issue 729)"
|
||||
}
|
||||
],
|
||||
"serves": {
|
||||
@@ -109,6 +156,13 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"settings": {
|
||||
"ready-authors": {
|
||||
"kind": "preference",
|
||||
"default": "mesh-admin jschoubben",
|
||||
"why": "the forge accounts whose comment \"ready at <full head sha>\" marks a pull request ready for mesh-delivery to merge, separated by spaces: the mesh's own forge account and the operator's (novox/hq issue 722). A comment by any other account is ignored and said in the forge's log. Trusted: who may have a change merged is the operator's word"
|
||||
}
|
||||
},
|
||||
"resources": [
|
||||
{
|
||||
"id": "mesh-state",
|
||||
@@ -122,6 +176,14 @@
|
||||
"path": "${dir:mesh-state}/state",
|
||||
"mode": "0700"
|
||||
},
|
||||
{
|
||||
"id": "ready-authors",
|
||||
"type": "file",
|
||||
"path": "${dir:mesh-state}/ready-authors",
|
||||
"mode": "0600",
|
||||
"trusted": true,
|
||||
"content": "# The accounts whose \"ready at <sha>\" comment marks a pull request ready (novox/hq issue 722), from the setting\n# ready-authors, written by the mesh. Replaced on every push; change the setting, never this file.\nauthors=${setting:ready-authors}\n"
|
||||
},
|
||||
{
|
||||
"id": "state",
|
||||
"type": "directory",
|
||||
@@ -138,7 +200,7 @@
|
||||
"type": "file",
|
||||
"path": "${dir:state}/server.env",
|
||||
"mode": "0600",
|
||||
"content": "GITEA__security__INTERNAL_TOKEN=${secret:internal-token}\nGITEA__database__DB_TYPE=postgres\nGITEA__database__HOST=${bound:postgres-database:at}:${bound:postgres-database:port}\nGITEA__database__NAME=${bound:postgres-database:as}\nGITEA__database__USER=${bound:postgres-database:as}\nGITEA__database__PASSWD=${secret:postgres-database}\n"
|
||||
"content": "GITEA__security__INTERNAL_TOKEN=${secret:internal-token}\nGITEA__database__DB_TYPE=postgres\nGITEA__database__HOST=${bound:postgres-database:at}:${bound:postgres-database:port}\nGITEA__database__NAME=${bound:postgres-database:as}\nGITEA__database__USER=${bound:postgres-database:as}\nGITEA__database__PASSWD=${secret:postgres-database}\nGITEA__webhook__ALLOWED_HOST_LIST=172.17.0.1\n"
|
||||
},
|
||||
{
|
||||
"id": "data",
|
||||
@@ -149,6 +211,13 @@
|
||||
{
|
||||
"id": "server",
|
||||
"type": "container",
|
||||
"health": {
|
||||
"kind": "http",
|
||||
"endpoint": "web",
|
||||
"path": "/api/healthz",
|
||||
"status": 200,
|
||||
"needs": "postgres-database"
|
||||
},
|
||||
"name": "gitea",
|
||||
"image": "gitea/gitea@sha256:87a67ee09d3ae0d1df5fda5dcda3e2a1f9236a45b0a59025d6e00e46adc43bef",
|
||||
"env": {
|
||||
@@ -200,7 +269,8 @@
|
||||
"path": "${dir:mesh-state}/config.json",
|
||||
"mode": "0600",
|
||||
"content": "{}\n",
|
||||
"merge": "json"
|
||||
"merge": "json",
|
||||
"takes-settings": []
|
||||
}
|
||||
],
|
||||
"provides": [
|
||||
@@ -239,7 +309,11 @@
|
||||
"MESH_GITEA_ADMIN_USER": "mesh-admin",
|
||||
"MESH_GITEA_ADMIN_PASSWORD_FILE": "${dir:state}/admin.secret",
|
||||
"MESH_GITEA_STATE_DIR": "${dir:runtime-state}",
|
||||
"MESH_RECEIVES": "${dir:grants}/npm.json"
|
||||
"MESH_RECEIVES": "${dir:grants}/npm.json",
|
||||
"MESH_GITEA_READY_AUTHORS_FILE": "${dir:mesh-state}/ready-authors",
|
||||
"MESH_GITEA_HOOK_URL": "http://172.17.0.1:3047",
|
||||
"MESH_GITEA_HOOK_PORT": "3047",
|
||||
"MESH_GITEA_HOOK_HOST": "172.17.0.1"
|
||||
}
|
||||
},
|
||||
{
|
||||
|
||||
@@ -137,3 +137,120 @@ test("a merged pull request whose branch was deleted is announced with its branc
|
||||
assert.equal(headBranchOf({ ref: "refs/pull/7/head" }), "refs/pull/7/head");
|
||||
assert.equal(headBranchOf(undefined), undefined);
|
||||
});
|
||||
|
||||
// **A pull request marked ready says the head it is marked at** (novox/hq issue 722): the label mesh/ready and the
|
||||
// newest comment "ready at <full head sha>" by a listed account, written after the label was added and after the last
|
||||
// push. Read from the pull request's whole timeline, page by page; without the label nothing is read.
|
||||
const head = "c".repeat(40), older = "d".repeat(40);
|
||||
const ev = (id: number, type: string, body: string, user = "mesh-admin", label?: { id: number; name: string }) =>
|
||||
({ id, type, body, user: { login: user }, created_at: `2026-10-14T10:${String(id % 60).padStart(2, "0")}:00Z`,
|
||||
...(label ? { label } : {}) });
|
||||
const readyLabel = { id: 31, name: "mesh/ready" };
|
||||
|
||||
function forgeWith(timeline: unknown[]) {
|
||||
const asked: string[] = [];
|
||||
const server = createServer((req, res) => {
|
||||
const url = req.url ?? "";
|
||||
asked.push(url);
|
||||
const send = (v: unknown) => res.end(JSON.stringify(v));
|
||||
if (url.startsWith("/api/v1/repos/issues/search")) {
|
||||
return send(url.includes("page=1") ? [
|
||||
{ number: 7, repository: { owner: "novox", name: "hq", full_name: "novox/hq" },
|
||||
labels: [{ id: 31, name: "mesh/ready" }, { id: 2, name: "bug" }] },
|
||||
{ number: 8, repository: { owner: "novox", name: "hq", full_name: "novox/hq" }, labels: [] },
|
||||
] : []);
|
||||
}
|
||||
if (url.startsWith("/api/v1/repos/novox/hq/pulls/7")) {
|
||||
return send({ number: 7, state: "open", base: { ref: "main" }, head: { ref: "x", sha: head }, html_url: "h" });
|
||||
}
|
||||
if (url.startsWith("/api/v1/repos/novox/hq/pulls/8")) {
|
||||
return send({ number: 8, state: "open", base: { ref: "main" }, head: { ref: "y", sha: older }, html_url: "h" });
|
||||
}
|
||||
const t = /\/issues\/7\/timeline\?page=(\d+)&limit=50/.exec(url);
|
||||
if (t) {
|
||||
const page = Number(t[1]);
|
||||
return send(timeline.slice((page - 1) * 50, page * 50));
|
||||
}
|
||||
if (url.includes("/branch_protections")) return send([]);
|
||||
if (url.includes("/status")) return send({ statuses: [] });
|
||||
res.statusCode = 404;
|
||||
res.end("{}");
|
||||
});
|
||||
return { server, asked };
|
||||
}
|
||||
|
||||
async function readOpen(timeline: unknown[], authors = ["mesh-admin", "jschoubben"]) {
|
||||
const { GiteaClient } = await import("../client.ts");
|
||||
const { server, asked } = forgeWith(timeline);
|
||||
await new Promise<void>((r) => server.listen(0, r));
|
||||
try {
|
||||
const client = new GiteaClient(`http://127.0.0.1:${(server.address() as any).port}`, "t");
|
||||
return { open: await client.openPulls(authors), asked };
|
||||
} finally {
|
||||
server.close();
|
||||
}
|
||||
}
|
||||
|
||||
test("a pull request's ready mark is read: the label and the head the newest listed ready comment names", async () => {
|
||||
const { open, asked } = await readOpen([
|
||||
ev(1, "pull_push", JSON.stringify({ commit_ids: [head] })),
|
||||
ev(2, "label", "1", "mesh-admin", readyLabel),
|
||||
ev(3, "comment", `ready at ${older}`),
|
||||
ev(4, "comment", `Reviewed: approve.\nready at ${head}\n`),
|
||||
ev(5, "comment", "thanks", "jschoubben"),
|
||||
]);
|
||||
assert.deepEqual(open[0].labels, ["mesh/ready", "bug"]);
|
||||
assert.deepEqual(open[0].ready, { head, by: "mesh-admin", at: "2026-10-14T10:04:00Z", label_id: 31 });
|
||||
assert.equal(open[1].ready, undefined, "no label, no mark");
|
||||
assert.ok(!asked.some((u) => u.includes("/issues/8/")), "no timeline read without the label");
|
||||
});
|
||||
|
||||
test("a ready comment by an account not listed is ignored, and said", async () => {
|
||||
const { readyMarkOf } = await import("../client.ts");
|
||||
const said: string[] = [];
|
||||
const mark = readyMarkOf(31, [
|
||||
ev(1, "pull_push", "{}") as any, ev(2, "label", "1", "mesh-admin", readyLabel) as any,
|
||||
{ ...ev(3, "comment", `ready at ${head}`, "outsider"), user: "outsider" },
|
||||
].map((e: any) => ({ ...e, user: typeof e.user === "string" ? e.user : e.user.login })), ["mesh-admin"], (l) => said.push(l));
|
||||
assert.equal(mark.head, "", "an outsider's mark counts");
|
||||
assert.equal(said.length, 1);
|
||||
assert.match(said[0], /by outsider is ignored/);
|
||||
});
|
||||
|
||||
test("a ready comment older than the latest push, or than the label, never counts", async () => {
|
||||
const pushedAfter = await readOpen([
|
||||
ev(1, "label", "1", "mesh-admin", readyLabel),
|
||||
ev(2, "comment", `ready at ${head}`),
|
||||
ev(3, "pull_push", JSON.stringify({ commit_ids: [head] })),
|
||||
]);
|
||||
assert.equal(pushedAfter.open[0].ready?.head, "", "a mark written before the latest push counts, the label still on");
|
||||
const beforeLabel = await readOpen([
|
||||
ev(1, "pull_push", "{}"),
|
||||
ev(2, "comment", `ready at ${head}`),
|
||||
ev(3, "label", "1", "mesh-admin", readyLabel),
|
||||
]);
|
||||
assert.equal(beforeLabel.open[0].ready?.head, "", "a mark written before the label was added counts");
|
||||
const takenOff = await readOpen([
|
||||
ev(1, "label", "1", "mesh-admin", readyLabel),
|
||||
ev(2, "comment", `ready at ${head}`),
|
||||
ev(3, "label", "", "mesh-admin", readyLabel),
|
||||
]);
|
||||
assert.equal(takenOff.open[0].ready?.head, "", "a mark whose label was taken off since counts");
|
||||
});
|
||||
|
||||
test("a long thread hides nothing: every page of the timeline is read", async () => {
|
||||
const events: unknown[] = [ev(1, "pull_push", "{}"), ev(2, "label", "1", "mesh-admin", readyLabel),
|
||||
ev(3, "comment", `ready at ${older}`)];
|
||||
for (let id = 4; id < 130; id++) events.push(ev(id, "comment", "a long discussion", "jschoubben"));
|
||||
events.push(ev(130, "comment", `ready at ${head}`, "jschoubben"));
|
||||
const { open, asked } = await readOpen(events);
|
||||
assert.equal(open[0].ready?.head, head, "the newest mark, on the third page, is not read");
|
||||
assert.equal(asked.filter((u) => u.includes("/issues/7/timeline")).length, 3);
|
||||
});
|
||||
|
||||
test("the accounts that may mark are the setting's, and only the mesh's own when it cannot be read", async () => {
|
||||
const { readyAuthors } = await import("../client.ts");
|
||||
assert.deepEqual(readyAuthors("f", "mesh-admin", () => "# x\nauthors=mesh-admin jschoubben\n"), ["mesh-admin", "jschoubben"]);
|
||||
assert.deepEqual(readyAuthors("f", "mesh-admin", () => { throw new Error("gone"); }), ["mesh-admin"]);
|
||||
assert.deepEqual(readyAuthors("f", "mesh-admin", () => "authors=\n"), ["mesh-admin"]);
|
||||
});
|
||||
|
||||
@@ -15,7 +15,7 @@ import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
|
||||
import { collectTools } from "@novox/mesh-sdk/tools";
|
||||
import { AdminRefused, MintedToken, TOKEN_SCOPES } from "../dist/token.js";
|
||||
import { AdminRefused, MINT_RETRY_AFTER_MS, MintedToken, TOKEN_SCOPES } from "../dist/token.js";
|
||||
import { GiteaClient } from "../dist/client.js";
|
||||
import { getGiteaTools } from "../dist/tools/index.js";
|
||||
|
||||
@@ -29,6 +29,9 @@ interface Forge {
|
||||
mints: number;
|
||||
lastScopes: string[] | null;
|
||||
tokens: Map<string, string>;
|
||||
/** Tokens beyond the one per name `tokens` holds, by id: what two mints racing leave (novox/hq issue 739). */
|
||||
twins: Map<number, { name: string; sha1: string }>;
|
||||
tokenCalls: number;
|
||||
scopesOf: Map<string, string[]>;
|
||||
admins: Map<string, string>;
|
||||
pullState: string;
|
||||
@@ -42,6 +45,9 @@ function fakeForge(): Promise<Forge> {
|
||||
mints: 0,
|
||||
lastScopes: null as string[] | null,
|
||||
tokens: new Map<string, string>(), // name -> value
|
||||
twins: new Map<number, { name: string; sha1: string }>(),
|
||||
idOf: new Map<string, number>(), // value -> id
|
||||
tokenCalls: 0,
|
||||
scopesOf: new Map<string, string[]>(), // value -> scopes, so a route can enforce them like gitea does
|
||||
admins: new Map([[ADMIN, PASSWORD]]),
|
||||
pullState: "open",
|
||||
@@ -73,21 +79,41 @@ function fakeForge(): Promise<Forge> {
|
||||
const tokens = url.pathname.match(/^\/api\/v1\/users\/([^/]+)\/tokens(?:\/([^/]+))?$/);
|
||||
if (tokens) {
|
||||
const user = basic(req);
|
||||
forge.tokenCalls++;
|
||||
if (user === null || user !== decodeURIComponent(tokens[1])) return json(res, 401, { message: "auth required" });
|
||||
const named = (name: string): number =>
|
||||
(forge.tokens.has(name) ? 1 : 0) + [...forge.twins.values()].filter((t) => t.name === name).length;
|
||||
if (req.method === "POST") {
|
||||
const { name, scopes } = await body(req);
|
||||
if (forge.tokens.has(name)) return json(res, 400, { message: "token name has already been used" });
|
||||
if (named(name) > 0) return json(res, 400, { message: "token name has already been used" });
|
||||
forge.mints++;
|
||||
forge.lastScopes = scopes;
|
||||
const sha1 = `minted-${forge.mints}-${Math.random().toString(36).slice(2)}`;
|
||||
forge.tokens.set(name, sha1);
|
||||
forge.idOf.set(sha1, forge.mints);
|
||||
forge.scopesOf.set(sha1, scopes);
|
||||
return json(res, 201, { id: forge.mints, name, sha1, scopes, token_last_eight: sha1.slice(-8) });
|
||||
}
|
||||
if (req.method === "GET" && !tokens[2]) {
|
||||
const page = Number(url.searchParams.get("page") ?? "1");
|
||||
const all = [...[...forge.tokens].map(([name, v]) => ({ id: forge.idOf.get(v) ?? 0, name })),
|
||||
...[...forge.twins].map(([id, t]) => ({ id, name: t.name }))];
|
||||
return json(res, 200, page === 1 ? all : []);
|
||||
}
|
||||
if (req.method === "DELETE" && tokens[2]) {
|
||||
const name = decodeURIComponent(tokens[2]);
|
||||
if (!forge.tokens.has(name)) return json(res, 404, { message: "token not found" });
|
||||
forge.tokens.delete(name);
|
||||
const key = decodeURIComponent(tokens[2]);
|
||||
// gitea: "identified by ID and if not available by name"
|
||||
if (/^\d+$/.test(key)) {
|
||||
const id = Number(key);
|
||||
if (forge.twins.delete(id)) return json(res, 204, null);
|
||||
const hit = [...forge.tokens].find(([, v]) => forge.idOf.get(v) === id);
|
||||
if (!hit) return json(res, 404, { message: "token not found" });
|
||||
forge.tokens.delete(hit[0]);
|
||||
return json(res, 204, null);
|
||||
}
|
||||
if (named(key) > 1) return json(res, 422, { message: `multiple matches for token name '${key}'` });
|
||||
if (!forge.tokens.has(key)) return json(res, 404, { message: "token not found" });
|
||||
forge.tokens.delete(key);
|
||||
return json(res, 204, null);
|
||||
}
|
||||
return json(res, 405, { message: "method not allowed" });
|
||||
@@ -180,7 +206,9 @@ function fakeForge(): Promise<Forge> {
|
||||
get pullState() { return forge.pullState; },
|
||||
get pullTitle() { return forge.pullTitle; },
|
||||
get branchDeleted() { return forge.branchDeleted; },
|
||||
get tokenCalls() { return forge.tokenCalls; },
|
||||
tokens: forge.tokens,
|
||||
twins: forge.twins,
|
||||
scopesOf: forge.scopesOf,
|
||||
admins: forge.admins,
|
||||
close: () => new Promise((r) => server.close(() => r())),
|
||||
@@ -209,8 +237,9 @@ async function delivered(forge: Forge): Promise<{ env: NodeJS.ProcessEnv; file:
|
||||
}
|
||||
|
||||
/** A client as a fresh process would build it: a new source over the kept file, its log captured. */
|
||||
function minted(env: NodeJS.ProcessEnv, logs: string[]): GiteaClient {
|
||||
function minted(env: NodeJS.ProcessEnv, logs: string[], now?: () => number): GiteaClient {
|
||||
const source = new MintedToken({
|
||||
now,
|
||||
url: env.MESH_GITEA_URL!,
|
||||
admin: env.MESH_GITEA_ADMIN_USER!,
|
||||
passwordFile: env.MESH_GITEA_ADMIN_PASSWORD_FILE!,
|
||||
@@ -325,6 +354,44 @@ test("the kept file is gone but the forge still holds a token by that name: repl
|
||||
assert.ok(logs.some((l) => l.includes('already holds a token named "mesh-tools"')), logs.join("\n"));
|
||||
});
|
||||
|
||||
test("two tokens carry the name (two mints raced): each is dropped by its id and one is minted, not a 422 for good (issue 739)", async () => {
|
||||
const { env, logs } = await delivered(forge);
|
||||
await minted(env, logs).listRepos();
|
||||
// What two processes minting at once leave: a second token by the same name, whose value nobody kept.
|
||||
// Two tokens by the name, neither of them the one kept.
|
||||
forge.tokens.clear();
|
||||
forge.twins.set(9001, { name: "mesh-tools", sha1: "raced-first" });
|
||||
forge.twins.set(9002, { name: "mesh-tools", sha1: "raced-second" });
|
||||
|
||||
const repos = await minted(env, logs).listRepos();
|
||||
|
||||
assert.equal(repos.length, 1);
|
||||
assert.equal(forge.twins.size, 0);
|
||||
assert.equal([...forge.tokens.keys()].filter((n) => n === "mesh-tools").length, 1);
|
||||
assert.ok(logs.some((l) => l.includes('holds 2 tokens named "mesh-tools"')), logs.join("\n"));
|
||||
});
|
||||
|
||||
test("a mint that failed is not asked of the forge again within the retry window: the same error, no basic-auth call (issue 739)", async () => {
|
||||
const { env, logs } = await delivered(forge);
|
||||
forge.admins.delete(ADMIN);
|
||||
try {
|
||||
let clock = 5_000_000;
|
||||
const client = minted(env, logs, () => clock);
|
||||
await assert.rejects(client.listRepos(), AdminRefused);
|
||||
const calls = forge.tokenCalls;
|
||||
|
||||
await assert.rejects(client.listRepos(), AdminRefused);
|
||||
await assert.rejects(client.listRepos(), AdminRefused);
|
||||
assert.equal(forge.tokenCalls, calls);
|
||||
|
||||
clock += MINT_RETRY_AFTER_MS;
|
||||
await assert.rejects(client.listRepos(), AdminRefused);
|
||||
assert.equal(forge.tokenCalls, calls + 1);
|
||||
} finally {
|
||||
forge.admins.set(ADMIN, PASSWORD);
|
||||
}
|
||||
});
|
||||
|
||||
test("concurrent first calls share one mint", async () => {
|
||||
const { env, logs } = await delivered(forge);
|
||||
const client = minted(env, logs);
|
||||
@@ -339,7 +406,8 @@ test("the admin account is refused: said plainly, nothing kept, and the next cal
|
||||
const { env, file, logs } = await delivered(forge);
|
||||
forge.admins.delete(ADMIN); // the forge's data came from a predecessor; mesh-admin was never created there
|
||||
try {
|
||||
const client = minted(env, logs);
|
||||
let clock = 1_000_000;
|
||||
const client = minted(env, logs, () => clock);
|
||||
const before = forge.mints;
|
||||
|
||||
await assert.rejects(client.listRepos(), (err: unknown) => {
|
||||
@@ -354,8 +422,9 @@ test("the admin account is refused: said plainly, nothing kept, and the next cal
|
||||
assert.equal(forge.mints, before);
|
||||
await assert.rejects(stat(file), /ENOENT/);
|
||||
|
||||
// The account appears (the operator created it): the very next call mints and works.
|
||||
// The account appears (the operator created it): the next call after the retry window mints and works.
|
||||
forge.admins.set(ADMIN, PASSWORD);
|
||||
clock += MINT_RETRY_AFTER_MS;
|
||||
assert.equal((await client.listRepos()).length, 1);
|
||||
assert.equal(forge.mints, before + 1);
|
||||
} finally {
|
||||
|
||||
@@ -173,3 +173,29 @@ test("a verdict that landed out of date keeps its account on the pull request",
|
||||
const bare = lateVerdictComment({ commit: HEAD, trunk: TRUNK.slice(0, 12), verdict: "pass" }, null, words);
|
||||
assert.match(bare, /head dfb1415aaaaa merged into trunk a2c2c35bbbbb, pass/);
|
||||
});
|
||||
|
||||
test("a release branch's move puts every open pull request into it out of date, as a trunk's does (ADR 0358 §5)", async () => {
|
||||
// novox/hq ADR 0358 §5: for a pull request into a release branch, the release branch takes the trunk's place in ADR
|
||||
// 0323 — the check merges the head onto the release branch's head and names it as the trunk commit, so the release
|
||||
// branch's move puts its open verdicts out of date, and leaves those into main alone.
|
||||
const release = "feat/57-config-and-provisioning";
|
||||
const heads: Record<string, string> = { main: TRUNK, [release]: "eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee" };
|
||||
const pulls = [{ number: 315, base: release, head: "3".repeat(40) }, { number: 1, base: "main", head: "1".repeat(40) }];
|
||||
const { forge, statuses } = aForge(pulls, heads);
|
||||
const gates = new GateWriter(forge);
|
||||
const trunks: Record<string, string> = {};
|
||||
await weighTrunks(forge, gates, trunks, "novox", "mesh-controller");
|
||||
|
||||
heads[release] = MOVED;
|
||||
assert.equal(await weighTrunks(forge, gates, trunks, "novox", "mesh-controller"), true);
|
||||
const s = statuses.get("3".repeat(40))!;
|
||||
assert.equal(s["mesh/merge-gate"].state, "pending");
|
||||
assert.match(s["mesh/merge-gate"].description!, /judged against trunk eeeeeeeeeeee, the trunk is now d28ca95ccccc/);
|
||||
assert.equal(s["mesh/repo-check"].state, "pending");
|
||||
assert.equal(statuses.get("1".repeat(40))!["mesh/merge-gate"].state, "success", "a pull request into main is left");
|
||||
assert.equal(trunks[`novox/mesh-controller:${release}`], MOVED);
|
||||
|
||||
// The merge tool's rule reads the same: a verdict judged against the release branch's old head is not current.
|
||||
assert.equal(verdictAtTrunk({ "mesh/merge-gate": { state: "success",
|
||||
description: "head x merged into trunk eeeeeeeeeeee — pass" } }, MOVED).current, false);
|
||||
});
|
||||
|
||||
@@ -0,0 +1,120 @@
|
||||
import assert from "node:assert/strict";
|
||||
import { test } from "node:test";
|
||||
import { createHmac } from "node:crypto";
|
||||
import type { AddressInfo } from "node:net";
|
||||
|
||||
// **The forge says every event on the bus** (novox/hq issue 729): a signed delivery is published once and acted on,
|
||||
// an unsigned or unverified one is refused, and an event and the poll seeing the same head announce it once.
|
||||
|
||||
const secret = "s".repeat(64);
|
||||
const sign = (body: string, key = secret) => createHmac("sha256", key).update(body).digest("hex");
|
||||
const opened = JSON.stringify({ action: "opened", number: 7, pull_request: { number: 7, title: "t", user: { login: "jo" },
|
||||
head: { ref: "feat/x", sha: "a".repeat(40) }, base: { ref: "main" }, merged: false },
|
||||
repository: { name: "hq", full_name: "novox/hq", owner: { login: "novox" } }, sender: { login: "jo" } });
|
||||
|
||||
async function serve(published: { name: string }[], acted: { name: string }[]) {
|
||||
const { receiver, HOOK_PATH } = await import("../webhook.ts");
|
||||
const server = receiver({ secret, port: 0, log: () => {},
|
||||
publish: async (e) => { published.push(e); }, act: async (e) => { acted.push(e); } });
|
||||
await new Promise<void>((r) => server.listen(0, "127.0.0.1", () => r()));
|
||||
const url = `http://127.0.0.1:${(server.address() as AddressInfo).port}${HOOK_PATH}`;
|
||||
return { server, url };
|
||||
}
|
||||
|
||||
test("a signed event is published on the bus and acted on once", async () => {
|
||||
const published: { name: string }[] = [], acted: { name: string }[] = [];
|
||||
const { server, url } = await serve(published, acted);
|
||||
try {
|
||||
const headers = { "X-Gitea-Event": "pull_request", "X-Gitea-Signature": sign(opened), "X-Gitea-Delivery": "d-1" };
|
||||
const res = await fetch(url, { method: "POST", body: opened, headers });
|
||||
assert.equal(res.status, 200);
|
||||
// The same delivery sent again is answered and published nowhere.
|
||||
const again = await fetch(url, { method: "POST", body: opened, headers });
|
||||
assert.equal(again.status, 200);
|
||||
await server.idle();
|
||||
assert.deepEqual(published.map((e) => e.name), ["forge.pull-request.opened"]);
|
||||
assert.deepEqual(acted.map((e) => e.name), ["forge.pull-request.opened"]);
|
||||
} finally { server.close(); }
|
||||
});
|
||||
|
||||
test("an unsigned event, or one whose signature does not verify, is refused and published nowhere", async () => {
|
||||
const published: { name: string }[] = [], acted: { name: string }[] = [];
|
||||
const { server, url } = await serve(published, acted);
|
||||
try {
|
||||
const unsigned = await fetch(url, { method: "POST", body: opened, headers: { "X-Gitea-Event": "pull_request" } });
|
||||
assert.equal(unsigned.status, 401);
|
||||
assert.match(await unsigned.text(), /unsigned/);
|
||||
const forged = await fetch(url, { method: "POST", body: opened,
|
||||
headers: { "X-Gitea-Event": "pull_request", "X-Gitea-Signature": sign(opened, "another secret") } });
|
||||
assert.equal(forged.status, 401);
|
||||
assert.match(await forged.text(), /does not verify/);
|
||||
const big = "x".repeat(5 * 1024 * 1024 + 1);
|
||||
const large = await fetch(url, { method: "POST", body: big,
|
||||
headers: { "X-Gitea-Event": "push", "X-Gitea-Signature": sign(big) } });
|
||||
assert.equal(large.status, 413);
|
||||
await server.idle();
|
||||
assert.deepEqual(published, []);
|
||||
assert.deepEqual(acted, []);
|
||||
} finally { server.close(); }
|
||||
});
|
||||
|
||||
test("an event and the poll seeing the same head announce it once", async () => {
|
||||
const { claimHead } = await import("../webhook.ts");
|
||||
const heads: Record<string, string> = {};
|
||||
const sha = "a".repeat(40);
|
||||
assert.equal(claimHead(heads, "novox/hq#7", sha), true, "the event claims the head and announces it");
|
||||
assert.equal(claimHead(heads, "novox/hq#7", sha), false, "the poll finds it taken");
|
||||
assert.equal(claimHead(heads, "novox/hq#7", "b".repeat(40)), true, "a new head is announced again");
|
||||
});
|
||||
|
||||
test("each forge event is named in the module's stream and trimmed", async () => {
|
||||
const { eventOf } = await import("../webhook.ts");
|
||||
const merged = eventOf("pull_request", { action: "closed", pull_request: { number: 3, merged: true, merge_commit_sha: "c".repeat(40),
|
||||
head: { sha: "a".repeat(40) }, base: { ref: "main" } }, repository: { name: "hq", owner: { login: "novox" } } });
|
||||
assert.equal(merged.name, "forge.pull-request.merged");
|
||||
assert.equal(merged.body.merge_commit_sha, "c".repeat(40));
|
||||
assert.equal(eventOf("pull_request", { action: "label_updated", pull_request: { number: 3 }, label: { name: "mesh/ready" } }).name,
|
||||
"forge.pull-request.labeled");
|
||||
const comment = eventOf("issue_comment", { action: "created", is_pull: true, issue: { number: 3 },
|
||||
comment: { id: 9, body: "ready at abc", user: { login: "jo" } } });
|
||||
assert.equal(comment.name, "forge.pull-request.commented");
|
||||
assert.equal(comment.body.comment, "ready at abc");
|
||||
assert.equal(eventOf("push", { ref: "refs/heads/main", after: "d".repeat(40) }).name, "forge.push");
|
||||
assert.equal(eventOf("pull_request_review_approved", {}).name, "forge.other");
|
||||
});
|
||||
|
||||
test("the system webhook is made when none points at the receiver, and corrected when one does", async () => {
|
||||
const { ensureSystemHook } = await import("../webhook.ts");
|
||||
const calls: string[] = [];
|
||||
let hooks: unknown[] = [];
|
||||
const admin = { call: async (method: string, path: string, body?: any) => {
|
||||
calls.push(`${method} ${path}`);
|
||||
if (method === "GET") return { status: 200, body: hooks };
|
||||
if (method === "POST") { assert.ok(body.events.includes("pull_request") && body.events.includes("push")); assert.equal(body.config.secret, secret); return { status: 201, body: {} }; }
|
||||
return { status: 200, body: {} };
|
||||
} };
|
||||
assert.equal(await ensureSystemHook(admin, "http://h:3047/forge-event", secret), "created");
|
||||
hooks = [{ id: 4, config: { url: "http://h:3047/forge-event" } }];
|
||||
assert.equal(await ensureSystemHook(admin, "http://h:3047/forge-event", secret), "corrected");
|
||||
assert.ok(calls.includes("PATCH /admin/hooks/4"));
|
||||
});
|
||||
|
||||
test("the polls look every 30 s until events are heard, every five minutes while they are, and 30 s again on a miss", async () => {
|
||||
const { Pace } = await import("../webhook.ts");
|
||||
let now = 1_000_000;
|
||||
const said: string[] = [];
|
||||
const pace = new Pace(() => now, (l) => said.push(l));
|
||||
assert.equal(pace.every(), 30_000, "no delivery yet");
|
||||
pace.heard();
|
||||
assert.equal(pace.every(), 300_000, "a delivery heard");
|
||||
now += 11 * 60_000;
|
||||
assert.equal(pace.every(), 30_000, "ten minutes without a delivery");
|
||||
pace.heard();
|
||||
now += 1000;
|
||||
pace.miss("novox/hq#7 at aaaaaaaa");
|
||||
assert.equal(pace.every(), 30_000, "the poll found what no event said");
|
||||
assert.match(said.join("\n"), /MISSED novox\/hq#7/);
|
||||
now += 1000;
|
||||
pace.heard();
|
||||
assert.equal(pace.every(), 300_000, "the next delivery");
|
||||
});
|
||||
+60
-4
@@ -97,13 +97,25 @@ export interface MintedTokenOptions {
|
||||
readonly scopes?: readonly string[];
|
||||
readonly log?: (line: string) => void;
|
||||
readonly fetch?: typeof fetch;
|
||||
/** The clock, in milliseconds; a test sets it. */
|
||||
readonly now?: () => number;
|
||||
}
|
||||
|
||||
/**
|
||||
* **How long a failed mint is not tried again** (novox/hq issue 739). Every call that finds no token mints, and a
|
||||
* mint is two or three calls over basic auth, each one hashing the admin password on the forge. A mint that keeps
|
||||
* failing, once per tool call, is a loop the forge pays for in CPU: on 2026-10-14 it ran several times a minute
|
||||
* on the control-node while it was already overloaded. Within this window the last failure is answered again,
|
||||
* without asking the forge.
|
||||
*/
|
||||
export const MINT_RETRY_AFTER_MS = 30_000;
|
||||
|
||||
/** The token the module mints for itself, kept in its state and renewed when the forge rejects it. */
|
||||
export class MintedToken implements TokenSource {
|
||||
private held: string | null = null;
|
||||
private readFile = false;
|
||||
private inflight: Promise<string> | null = null;
|
||||
private failed: { at: number; error: unknown } | null = null;
|
||||
private readonly name: string;
|
||||
private readonly scopes: readonly string[];
|
||||
private readonly log: (line: string) => void;
|
||||
@@ -114,8 +126,11 @@ export class MintedToken implements TokenSource {
|
||||
this.scopes = opts.scopes ?? TOKEN_SCOPES;
|
||||
this.log = opts.log ?? ((line) => console.log(`[gitea] ${line}`));
|
||||
this.fetchImpl = opts.fetch ?? fetch;
|
||||
this.now = opts.now ?? Date.now;
|
||||
}
|
||||
|
||||
private readonly now: () => number;
|
||||
|
||||
/**
|
||||
* Build from the runtime's environment: the forge's URL, the admin login and password file the
|
||||
* manifest hands the runtime, and the module's state directory (MESH_GITEA_STATE_DIR, a directory
|
||||
@@ -126,7 +141,10 @@ export class MintedToken implements TokenSource {
|
||||
const opts = MintedToken.optionsFromEnv(url, env);
|
||||
// One source per kept file in a process. The watcher and the tools entrypoint both build a
|
||||
// client in the same runtime; two sources over one file would each renew on a 401 and drop the
|
||||
// other's token by name, forever. Shared, a renewal is one renewal.
|
||||
// other's token by name, forever. Shared, a renewal is one renewal. Across processes it is not shared: the
|
||||
// runtime serves the watcher (index.js) and the tools (tools/index.js) as separate bundles, so two sources over
|
||||
// one file do exist. renew() reads the kept file before it mints, and a race that still leaves two tokens by
|
||||
// the name is undone by dropping each by its id (doMint; novox/hq issue 739).
|
||||
const shared = MintedToken.shared.get(opts.file);
|
||||
if (shared) return shared;
|
||||
const source = new MintedToken(opts);
|
||||
@@ -163,7 +181,7 @@ export class MintedToken implements TokenSource {
|
||||
}
|
||||
if (kept !== null) return this.mint("the kept token was minted with other scopes than the tools take now — minting one with them");
|
||||
}
|
||||
return this.mint("no token kept — minting one");
|
||||
return this.mint(this.failed ? "no token held since the last mint failed — minting one" : "no token kept — minting one");
|
||||
}
|
||||
|
||||
async renew(rejected: string): Promise<string> {
|
||||
@@ -188,8 +206,19 @@ export class MintedToken implements TokenSource {
|
||||
/** One mint at a time: concurrent first calls share it, rather than each minting its own. */
|
||||
private mint(why: string): Promise<string> {
|
||||
if (this.inflight === null) {
|
||||
// A mint that failed a moment ago is not asked of the forge again yet (novox/hq issue 739): its error stands.
|
||||
if (this.failed !== null && this.now() - this.failed.at < MINT_RETRY_AFTER_MS) return Promise.reject(this.failed.error);
|
||||
this.log(why);
|
||||
this.inflight = this.doMint().finally(() => {
|
||||
this.inflight = this.doMint().then(
|
||||
(token) => {
|
||||
this.failed = null;
|
||||
return token;
|
||||
},
|
||||
(err) => {
|
||||
this.failed = { at: this.now(), error: err };
|
||||
throw err;
|
||||
},
|
||||
).finally(() => {
|
||||
this.inflight = null;
|
||||
});
|
||||
}
|
||||
@@ -261,7 +290,12 @@ export class MintedToken implements TokenSource {
|
||||
// went while the forge's data stayed. It is ours to replace: drop it by name and mint again.
|
||||
this.log(`the forge already holds a token named "${this.name}" — replacing it`);
|
||||
const dropped = await call("DELETE", `/${encodeURIComponent(this.name)}`);
|
||||
if (dropped.status !== 204 && dropped.status !== 404) {
|
||||
if (dropped.status === 422) {
|
||||
// More than one token carries the name (novox/hq issue 739): two processes minted at once, and the forge's
|
||||
// check that a name is unused is not atomic. The forge refuses a delete by such a name for good, so every
|
||||
// one of them is dropped by its id — all are ours, and none of their values is kept.
|
||||
await this.dropEveryNamed(call, dropped);
|
||||
} else if (dropped.status !== 204 && dropped.status !== 404) {
|
||||
throw new Error(`Gitea DELETE /users/${this.opts.admin}/tokens/${this.name}: ${dropped.status} ${detail(dropped.body)}`);
|
||||
}
|
||||
res = await call("POST", "", { name: this.name, scopes: this.scopes });
|
||||
@@ -277,6 +311,28 @@ export class MintedToken implements TokenSource {
|
||||
this.log(`minted a token for "${this.opts.admin}" (${this.scopes.join(", ")}), kept at ${this.opts.file}`);
|
||||
return token;
|
||||
}
|
||||
|
||||
/** Drop, by id, every token of the admin account that carries this name; the forge listed them, page by page. */
|
||||
private async dropEveryNamed(call: (method: string, path?: string) => Promise<{ status: number; body: any }>,
|
||||
refused: { status: number; body: any }): Promise<void> {
|
||||
const ids: number[] = [];
|
||||
for (let page = 1; page <= 20; page++) {
|
||||
const listed = await call("GET", `?page=${page}&limit=50`);
|
||||
if (listed.status !== 200 || !Array.isArray(listed.body)) {
|
||||
throw new Error(`Gitea DELETE /users/${this.opts.admin}/tokens/${this.name}: ${refused.status} ${detail(refused.body)}; ` +
|
||||
`and its tokens could not be listed to drop them one by one: ${listed.status} ${detail(listed.body)}`);
|
||||
}
|
||||
for (const t of listed.body) if (t?.name === this.name && Number.isInteger(t?.id)) ids.push(t.id);
|
||||
if (listed.body.length < 50) break;
|
||||
}
|
||||
this.log(`the forge holds ${ids.length} tokens named "${this.name}" — dropping each by its id`);
|
||||
for (const id of ids) {
|
||||
const dropped = await call("DELETE", `/${id}`);
|
||||
if (dropped.status !== 204 && dropped.status !== 404) {
|
||||
throw new Error(`Gitea DELETE /users/${this.opts.admin}/tokens/${id}: ${dropped.status} ${detail(dropped.body)}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
function detail(body: unknown): string {
|
||||
|
||||
@@ -10,7 +10,7 @@
|
||||
|
||||
import { registerModuleTools, type ToolDefinition } from "@novox/mesh-sdk/tools";
|
||||
import { emit } from "@novox/mesh-sdk/events";
|
||||
import { GiteaClient, type BranchProtection } from "../client.js";
|
||||
import { GiteaClient, readyAuthors, type BranchProtection } from "../client.js";
|
||||
import { appendNote, run, viewBody, viewComment } from "../delivery.js";
|
||||
import { containedFrom, isCommit, mergeableUnder, newestByContext } from "../checks.js";
|
||||
import {
|
||||
@@ -514,9 +514,9 @@ function allGiteaTools(gitea: GiteaClient): ToolDefinition[] {
|
||||
},
|
||||
{
|
||||
name: "gitea_open_pulls",
|
||||
description: "Every open pull request of every repository, from the forge itself: its head, its base, the statuses the base's protection requires and the ones its head has, each with its state, description and when it was set. What mesh-delivery reads to say a pull request the mesh was never asked to check (novox/hq issue 347), or whose check started and never answered (issue 438). Reads only.",
|
||||
description: "Every open pull request of every repository, from the forge itself: its head, its base, the statuses the base's protection requires and the ones its head has, each with its state, description and when it was set. What mesh-delivery reads to say a pull request the mesh was never asked to check (novox/hq issue 347), or whose check started and never answered (issue 438), and each pull request's labels and ready mark — the label mesh/ready and the head named by the newest comment \"ready at <full head sha>\" that a listed account (the setting ready-authors) wrote after the label was added and after the last push — which mesh-delivery merges on (issue 722). Reads only.",
|
||||
input: {},
|
||||
run: async () => ({ pulls: await gitea.openPulls() }),
|
||||
run: async () => ({ pulls: await gitea.openPulls(readyAuthors()) }),
|
||||
},
|
||||
{
|
||||
name: "gitea_contains",
|
||||
|
||||
@@ -0,0 +1,314 @@
|
||||
// **The forge says every event on the bus** (novox/hq issue 729; to-be 10: an event makes it fast, nothing makes it
|
||||
// necessary). The module keeps one system webhook on its forge for every event, pointing at its own receiver, signed
|
||||
// with a secret it mints and keeps beside its token; the receiver refuses whatever is unsigned or does not verify, and
|
||||
// publishes each event, trimmed, on the module's events as forge.<kind>.<action> (forge.pull-request.opened, forge.push, …),
|
||||
// on the shared EVENTS path its other events take; its own stream (ADR 0363) is a follow-up once issue 725 ships.
|
||||
// The polls stay as the safety net, slowed; the announced-heads and announced-merges records keep anything from
|
||||
// being announced twice, whichever path saw it first.
|
||||
//
|
||||
// The secret is never logged: lines say it was minted or reused and where it is kept, never what it is.
|
||||
|
||||
import { createHmac, randomBytes, timingSafeEqual } from "node:crypto";
|
||||
import { chmodSync, mkdirSync, readFileSync, renameSync, writeFileSync } from "node:fs";
|
||||
import { createServer, type Server } from "node:http";
|
||||
import { dirname } from "node:path";
|
||||
|
||||
/** The name the receiver answers on, and the port it listens on unless the manifest says otherwise. */
|
||||
export const HOOK_PATH = "/forge-event";
|
||||
export const HOOK_PORT = 3047;
|
||||
|
||||
/** The secret the forge signs with: read from its 0600 file, or minted and kept there. */
|
||||
export function keptSecret(file: string, log: (line: string) => void = (l) => console.log(`[gitea] ${l}`)): string {
|
||||
try {
|
||||
const kept = readFileSync(file, "utf8").trim();
|
||||
if (kept.length >= 32) {
|
||||
log(`reusing the webhook secret kept at ${file}`);
|
||||
return kept;
|
||||
}
|
||||
} catch (err) {
|
||||
if ((err as NodeJS.ErrnoException).code !== "ENOENT") throw err;
|
||||
}
|
||||
const secret = randomBytes(32).toString("hex");
|
||||
mkdirSync(dirname(file), { recursive: true, mode: 0o700 });
|
||||
const tmp = `${file}.tmp`;
|
||||
writeFileSync(tmp, secret + "\n", { mode: 0o600 });
|
||||
chmodSync(tmp, 0o600);
|
||||
renameSync(tmp, file);
|
||||
log(`minted a webhook secret, kept at ${file}`);
|
||||
return secret;
|
||||
}
|
||||
|
||||
/** Whether a body carries the forge's HMAC-SHA256 signature (X-Gitea-Signature, hex) under the secret. */
|
||||
export function verified(secret: string, body: Buffer | string, signature: string | undefined): boolean {
|
||||
if (!secret || !signature || !/^[0-9a-f]{64}$/i.test(signature.trim())) return false;
|
||||
const want = createHmac("sha256", secret).update(body).digest();
|
||||
const got = Buffer.from(signature.trim(), "hex");
|
||||
return got.length === want.length && timingSafeEqual(got, want);
|
||||
}
|
||||
|
||||
/** One forge event as the bus carries it: its name inside the stream, and what is needed of it — no secrets. */
|
||||
export interface ForgeEvent {
|
||||
name: string;
|
||||
body: Record<string, unknown>;
|
||||
}
|
||||
|
||||
/** Every event name the module emits for the forge, without its forge. prefix (module.json `emits`). */
|
||||
export const EVENTS: readonly string[] = ["push", "create", "delete", "fork", "status", "pull-request.opened", "pull-request.reopened", "pull-request.synchronized", "pull-request.edited", "pull-request.closed", "pull-request.merged", "pull-request.labeled", "pull-request.unlabeled", "pull-request.assigned", "pull-request.unassigned", "pull-request.reviewed", "pull-request.review-requested", "pull-request.commented", "pull-request.changed", "issue-comment.created", "issue-comment.edited", "issue-comment.deleted", "issues.opened", "issues.reopened", "issues.closed", "issues.edited", "issues.labeled", "issues.unlabeled", "issues.assigned", "issues.unassigned", "issues.changed", "release.published", "release.updated", "release.deleted", "release.changed", "repository.created", "repository.deleted", "repository.changed", "wiki.changed", "other"];
|
||||
|
||||
/** The families the module's stream carries (module.json `streams`); any other kind is said as other.<kind>; underscores become hyphens. */
|
||||
export const FAMILIES = ["push", "create", "delete", "fork", "status", "pull_request", "issue_comment", "issues",
|
||||
"release", "repository", "wiki"] as const;
|
||||
|
||||
const ACTIONS: Record<string, string> = { label_updated: "labeled", label_cleared: "unlabeled", synchronized: "synchronized" };
|
||||
|
||||
function str(v: unknown): string | undefined {
|
||||
return typeof v === "string" && v ? v : undefined;
|
||||
}
|
||||
function num(v: unknown): number | undefined {
|
||||
return typeof v === "number" ? v : undefined;
|
||||
}
|
||||
function login(u: any): string | undefined {
|
||||
return str(u?.login) ?? str(u?.username);
|
||||
}
|
||||
|
||||
/**
|
||||
* The event a forge delivery is: its kind (X-Gitea-Event) and the payload's action, trimmed to ids, repository, refs,
|
||||
* shas, author, labels and a comment's body (a ready mark is one, ADR 0364). A merge is pull-request.merged, a comment on
|
||||
* a pull request pull-request.commented.
|
||||
*/
|
||||
export function eventOf(kind: string, payload: any): ForgeEvent {
|
||||
// The bus's event names take lower-case letters, digits and hyphens: the forge's underscores become hyphens.
|
||||
const event = forgeEventOf(kind, payload);
|
||||
const name = event.name.toLowerCase().replace(/_/g, "-").replace(/[^a-z0-9.-]/g, "-");
|
||||
// Published on the module's events as it publishes its others, each name declared in its `emits`: one the manifest
|
||||
// does not name is forge.other, saying what the forge called it. Its own stream (ADR 0363) follows issue 725.
|
||||
if (EVENTS.includes(name)) return { name: `forge.${name}`, body: event.body };
|
||||
return { name: "forge.other", body: { ...event.body, kind, said: name } };
|
||||
}
|
||||
|
||||
function forgeEventOf(said: string, payload: any): ForgeEvent {
|
||||
// The forge names some kinds finer than their family (pull_request_label, pull_request_sync): read by the payload.
|
||||
let kind = said;
|
||||
if (said.startsWith("pull_request") && payload?.pull_request) kind = "pull_request";
|
||||
if ((said.startsWith("issue") || said === "pull_request_comment") && payload?.comment) kind = "issue_comment";
|
||||
if (said.startsWith("issue") && !payload?.comment && payload?.issue) kind = "issues";
|
||||
const repo = payload?.repository ?? {};
|
||||
const base: Record<string, unknown> = {
|
||||
owner: login(repo.owner), repo: str(repo.name), full_name: str(repo.full_name), clone_url: str(repo.clone_url),
|
||||
sender: login(payload?.sender),
|
||||
};
|
||||
const family = (FAMILIES as readonly string[]).includes(kind) ? kind : `other`;
|
||||
let action = str(payload?.action);
|
||||
const pull = payload?.pull_request;
|
||||
if (kind === "push") {
|
||||
return { name: "push", body: { ...base, ref: str(payload.ref), before: str(payload.before), after: str(payload.after),
|
||||
commits: Array.isArray(payload.commits) ? payload.commits.length : undefined, pusher: login(payload.pusher) } };
|
||||
}
|
||||
if (kind === "pull_request" && pull) {
|
||||
if (action === "closed" && pull.merged) action = "merged";
|
||||
action = ACTIONS[action ?? ""] ?? action ?? "changed";
|
||||
return { name: `pull_request.${action}`, body: { ...base, number: num(pull.number ?? payload.number),
|
||||
title: str(pull.title), author: login(pull.user), head: str(pull.head?.ref), head_sha: str(pull.head?.sha),
|
||||
base: str(pull.base?.ref), merged: !!pull.merged, merge_commit_sha: str(pull.merge_commit_sha),
|
||||
merged_at: str(pull.merged_at), html_url: str(pull.html_url),
|
||||
labels: Array.isArray(pull.labels) ? pull.labels.map((l: any) => str(l?.name)).filter(Boolean) : undefined,
|
||||
label: str(payload.label?.name) } };
|
||||
}
|
||||
if (kind === "issue_comment") {
|
||||
const issue = payload.issue ?? {};
|
||||
const onPull = !!payload.is_pull || !!issue.pull_request;
|
||||
return { name: onPull ? "pull_request.commented" : `issue_comment.${action ?? "created"}`, body: { ...base,
|
||||
number: num(issue.number), comment_id: num(payload.comment?.id), author: login(payload.comment?.user),
|
||||
comment: str(payload.comment?.body), action } };
|
||||
}
|
||||
if (kind === "create" || kind === "delete") {
|
||||
return { name: kind, body: { ...base, ref: str(payload.ref), ref_type: str(payload.ref_type), sha: str(payload.sha) } };
|
||||
}
|
||||
if (kind === "status") {
|
||||
return { name: "status", body: { ...base, sha: str(payload.sha), context: str(payload.context), state: str(payload.state) } };
|
||||
}
|
||||
const name = family === "other" ? `other.${kind.replace(/[^a-z0-9_-]/gi, "_") || "unknown"}` :
|
||||
["fork"].includes(family) ? family : `${family}.${action ?? "changed"}`;
|
||||
return { name, body: { ...base, number: num(payload?.number ?? payload?.issue?.number), action } };
|
||||
}
|
||||
|
||||
export interface ReceiverOptions {
|
||||
secret: string;
|
||||
port: number;
|
||||
host?: string;
|
||||
/** Publishes one event on the bus. */
|
||||
publish: (event: ForgeEvent) => Promise<void>;
|
||||
/** Acts on it at once, beside publishing it (the announcer). */
|
||||
act?: (event: ForgeEvent) => Promise<void>;
|
||||
/** Told of every verified delivery, so the polls know events are heard. */
|
||||
heard?: () => void;
|
||||
log?: (line: string) => void;
|
||||
}
|
||||
|
||||
/** The most a delivery may carry: the forge's push of many commits stays well under it. */
|
||||
export const MAX_BODY = 5 * 1024 * 1024;
|
||||
/** How many deliveries' ids are remembered, so a delivery sent again is published once. */
|
||||
export const REMEMBERED = 2000;
|
||||
|
||||
/**
|
||||
* The receiver. A request without a signature is refused before its body is read, a body over MAX_BODY is refused, and
|
||||
* one whose signature does not verify is refused, each with 401 or 413 and a line saying so. A verified delivery is
|
||||
* answered 200 at once and queued: it is published and acted on after the reply, one at a time, so the forge's
|
||||
* delivery timeout is never reached. A delivery whose X-Gitea-Delivery id was already heard is answered and dropped.
|
||||
*/
|
||||
export function receiver(opts: ReceiverOptions): Server & { idle(): Promise<void> } {
|
||||
const log = opts.log ?? ((l) => console.log(`[gitea] ${l}`));
|
||||
const seen = new Set<string>();
|
||||
let queue: Promise<void> = Promise.resolve();
|
||||
const server = createServer((req, res) => {
|
||||
if (req.method !== "POST" || (req.url ?? "").split("?")[0] !== HOOK_PATH) {
|
||||
res.statusCode = 404;
|
||||
return res.end();
|
||||
}
|
||||
const from = req.socket.remoteAddress ?? "?";
|
||||
const signature = String(req.headers["x-gitea-signature"] ?? "").trim();
|
||||
if (!signature) {
|
||||
log(`refused a forge event from ${from}: it is unsigned`);
|
||||
res.writeHead(401, { Connection: "close" });
|
||||
res.end("unsigned\n");
|
||||
req.destroy();
|
||||
return;
|
||||
}
|
||||
if (Number(req.headers["content-length"] ?? 0) > MAX_BODY) {
|
||||
log(`refused a forge event from ${from}: its body is over ${MAX_BODY} bytes`);
|
||||
res.writeHead(413, { Connection: "close" });
|
||||
res.end("too large\n");
|
||||
req.destroy();
|
||||
return;
|
||||
}
|
||||
const chunks: Buffer[] = [];
|
||||
let size = 0;
|
||||
let over = false;
|
||||
req.on("data", (c: Buffer) => {
|
||||
size += c.length;
|
||||
if (size > MAX_BODY) {
|
||||
if (!over) {
|
||||
over = true;
|
||||
log(`refused a forge event from ${from}: its body is over ${MAX_BODY} bytes`);
|
||||
res.writeHead(413, { Connection: "close" });
|
||||
res.end("too large\n");
|
||||
req.destroy();
|
||||
}
|
||||
} else chunks.push(c);
|
||||
});
|
||||
req.on("end", () => {
|
||||
if (over) return;
|
||||
const body = Buffer.concat(chunks);
|
||||
if (!verified(opts.secret, body, signature)) {
|
||||
log(`refused a forge event from ${from}: its signature does not verify`);
|
||||
res.statusCode = 401;
|
||||
return res.end("signature does not verify\n");
|
||||
}
|
||||
let payload: unknown;
|
||||
try {
|
||||
payload = JSON.parse(body.toString("utf8"));
|
||||
} catch {
|
||||
res.statusCode = 400;
|
||||
return res.end("not JSON\n");
|
||||
}
|
||||
opts.heard?.();
|
||||
const delivery = String(req.headers["x-gitea-delivery"] ?? "");
|
||||
if (delivery && seen.has(delivery)) {
|
||||
res.statusCode = 200;
|
||||
return res.end("already heard\n");
|
||||
}
|
||||
if (delivery) {
|
||||
seen.add(delivery);
|
||||
if (seen.size > REMEMBERED) seen.delete(seen.values().next().value as string);
|
||||
}
|
||||
const event = eventOf(String(req.headers["x-gitea-event"] ?? "other"), payload);
|
||||
res.statusCode = 200;
|
||||
res.end("queued\n");
|
||||
queue = queue.then(async () => {
|
||||
try {
|
||||
await opts.publish(event);
|
||||
if (opts.act) await opts.act(event);
|
||||
} catch (err) {
|
||||
log(`a forge event ${event.name} could not be published or acted on; the polls catch it — ${err instanceof Error ? err.message : err}`);
|
||||
}
|
||||
});
|
||||
});
|
||||
});
|
||||
return Object.assign(server, { idle: () => queue });
|
||||
}
|
||||
|
||||
/** What ensuring the system webhook needs of the forge's administration (GiteaAdmin's login). */
|
||||
export interface HookAdmin {
|
||||
call(method: string, path: string, body?: unknown): Promise<{ status: number; body: any }>;
|
||||
}
|
||||
|
||||
/**
|
||||
* **How fast the polls look** (issue 729): every five minutes only while the forge's events are heard — a verified
|
||||
* delivery within the last ten minutes, and none missed since. Until the first delivery, after ten minutes without one,
|
||||
* or once the poll found something no event said, every thirty seconds.
|
||||
*/
|
||||
export class Pace {
|
||||
private last = 0;
|
||||
private missed = 0;
|
||||
private readonly now: () => number;
|
||||
private readonly log: (l: string) => void;
|
||||
constructor(now: () => number = Date.now, log: (l: string) => void = (l) => console.error(`[gitea] ${l}`)) {
|
||||
this.now = now;
|
||||
this.log = log;
|
||||
}
|
||||
heard(): void {
|
||||
this.last = this.now();
|
||||
}
|
||||
/** The poll found a head or merge no forge event announced. */
|
||||
miss(what: string): void {
|
||||
if (this.hearing()) this.log(`THE FORGE'S EVENTS MISSED ${what}: the poll found it, so the polls look every 30 s again until the next event`);
|
||||
this.missed = this.now();
|
||||
}
|
||||
hearing(): boolean {
|
||||
const t = this.now();
|
||||
return this.last > 0 && t - this.last < 10 * 60_000 && this.last > this.missed;
|
||||
}
|
||||
every(): number {
|
||||
return this.hearing() ? 5 * 60_000 : 30_000;
|
||||
}
|
||||
}
|
||||
|
||||
/** Every event family the forge (1.27) can send a webhook. */
|
||||
export const HOOK_EVENTS = ["create", "delete", "fork", "push", "issues", "issue_comment", "pull_request",
|
||||
"pull_request_review_request", "wiki", "repository", "release", "package", "status", "workflow_run", "workflow_job"];
|
||||
|
||||
/**
|
||||
* **One system webhook, for every event, at the receiver** (issue 729): created when none points there, corrected
|
||||
* when one does but differs (events, active, content type), and its secret set again each start — the forge never
|
||||
* hands a secret back, so a corrected secret cannot be told from a kept one. Answers what it did.
|
||||
*/
|
||||
export async function ensureSystemHook(admin: HookAdmin, url: string, secret: string): Promise<"created" | "corrected"> {
|
||||
// POST /admin/hooks makes a system webhook, and its options take no flag for it (the forge's 1.27.3 API schema). The
|
||||
// forge has no "every event" word: each family is named, and a family name (issues, pull_request) takes all of it.
|
||||
const want = { type: "gitea", active: true, events: HOOK_EVENTS, branch_filter: "*",
|
||||
config: { url, content_type: "json", secret } };
|
||||
const listed = await admin.call("GET", "/admin/hooks?type=system&limit=50");
|
||||
if (listed.status !== 200) throw new Error(`the forge's system webhooks could not be listed: ${listed.status}`);
|
||||
const hooks: any[] = Array.isArray(listed.body) ? listed.body : [];
|
||||
const ours = hooks.filter((h) => h?.config?.url === url);
|
||||
if (ours.length === 0) {
|
||||
const made = await admin.call("POST", "/admin/hooks", want);
|
||||
if (made.status !== 201 && made.status !== 200) throw new Error(`the forge's system webhook could not be made: ${made.status}`);
|
||||
return "created";
|
||||
}
|
||||
for (const extra of ours.slice(1)) await admin.call("DELETE", `/admin/hooks/${extra.id}`);
|
||||
const fixed = await admin.call("PATCH", `/admin/hooks/${ours[0].id}`, { active: true, events: HOOK_EVENTS, branch_filter: "*",
|
||||
config: { url, content_type: "json", secret } });
|
||||
if (fixed.status !== 200) throw new Error(`the forge's system webhook could not be corrected: ${fixed.status}`);
|
||||
return "corrected";
|
||||
}
|
||||
|
||||
/**
|
||||
* **Claim a head for announcing, once** (issue 729): true when `sha` is not already the head recorded for `key`, which
|
||||
* it then is. The poll and the forge's event both claim before they announce, so whichever comes second finds it taken.
|
||||
*/
|
||||
export function claimHead(heads: Record<string, string>, key: string, sha: string): boolean {
|
||||
if (!sha || heads[key] === sha) return false;
|
||||
heads[key] = sha;
|
||||
return true;
|
||||
}
|
||||
@@ -0,0 +1,198 @@
|
||||
import { test } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
import { mkdirSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
|
||||
import {
|
||||
BASE_IMAGE_ALIAS, BASE_MAX_AGE_DAYS, baseImageFrom, baseProblem, baseScript, buildingBase, cleanCredentials, credentialPath,
|
||||
describeBase, launchRebuild, launchRun, listBaseBuilds, listRuns, readStatus, runRefusal, running, staleBase,
|
||||
type BaseImage,
|
||||
} from "../tools/runs.ts";
|
||||
|
||||
// Defends novox/hq issue 698: the lab's base image was 44 days old, a bed machine raised from it carried a
|
||||
// package database the mirrors no longer served, and genesis-keeps-its-bus stopped on a 404 for
|
||||
// postgresql-libs. Nothing said how old the image was, nothing refused it, and no mesh tool rebuilt it.
|
||||
|
||||
const now = new Date("2026-10-14T01:00:00Z");
|
||||
const listed = (uploaded: string, alias = BASE_IMAGE_ALIAS) => JSON.stringify([
|
||||
{ aliases: [{ name: "images:other" }], uploaded_at: "2026-10-13T00:00:00Z" },
|
||||
{ aliases: [{ name: alias }], uploaded_at: uploaded, created_at: "2026-08-01T00:00:00Z" },
|
||||
]);
|
||||
|
||||
test("the base image's age is read from when this machine made it", () => {
|
||||
const b = baseImageFrom(listed("2026-08-31T09:00:00Z"), now);
|
||||
assert.equal(b.exists, true);
|
||||
assert.equal(b.built, "2026-08-31T09:00:00.000Z");
|
||||
assert.equal(b.ageDays, 43);
|
||||
assert.match(describeBase(b), /built 2026-08-31T09:00:00.000Z \(43 day\(s\) ago; the bound is 14\)/);
|
||||
});
|
||||
|
||||
test("an image older than the bound refuses a run, naming the tool that rebuilds it", () => {
|
||||
const stale = baseImageFrom(listed("2026-08-31T09:00:00Z"), now);
|
||||
const reason = runRefusal(stale);
|
||||
assert.ok(reason, "a 43-day-old base image was not refused");
|
||||
assert.match(reason, /older than the lab's bound of 14 days/);
|
||||
assert.match(reason, /lab_base \{"rebuild": true\}/);
|
||||
assert.equal(staleBase(stale), reason);
|
||||
});
|
||||
|
||||
test("an image within the bound runs", () => {
|
||||
const fresh = baseImageFrom(listed(new Date(now.getTime() - BASE_MAX_AGE_DAYS * 86_400_000).toISOString()), now);
|
||||
assert.equal(fresh.ageDays, BASE_MAX_AGE_DAYS);
|
||||
assert.equal(runRefusal(fresh), undefined);
|
||||
});
|
||||
|
||||
test("a missing image, or one whose age cannot be read, is said and not refused", () => {
|
||||
const none = baseImageFrom(listed("2026-10-01T00:00:00Z", "something-else"), now);
|
||||
assert.equal(none.exists, false);
|
||||
assert.equal(runRefusal(none), undefined);
|
||||
assert.match(describeBase(none), /is not on this machine; rebuild it with lab_base/);
|
||||
const unread = baseImageFrom(undefined, now);
|
||||
assert.equal(runRefusal(unread), undefined);
|
||||
assert.match(describeBase(unread), /its age is not known/);
|
||||
});
|
||||
|
||||
test("no run starts while the base image is rebuilt", () => {
|
||||
const fresh = baseImageFrom(listed("2026-10-13T00:00:00Z"), now);
|
||||
const reason = runRefusal(fresh, { id: "base-x", started: "2026-10-14T00:59:00Z" });
|
||||
assert.match(reason ?? "", /is being rebuilt \(base-x/);
|
||||
});
|
||||
|
||||
test("a rebuild is mesh-lab's base build from the forge's main, with no secret in its script", () => {
|
||||
const s = baseScript("/work/base-x", "https://forge.invalid", "/work/.base-x.git-credentials");
|
||||
assert.match(s, /clone --quiet --depth 1 'https:\/\/forge.invalid\/novox\/mesh-lab.git'/);
|
||||
assert.match(s, /src\/cli.ts base build/);
|
||||
assert.ok(s.indexOf("rm -f '/work/.base-x.git-credentials'") < s.indexOf("npm ci"), "the credential outlives the clone");
|
||||
});
|
||||
|
||||
test("a rebuild is known by its status, and is not a run", () => {
|
||||
const work = mkdtempSync(join(tmpdir(), "lab-base-"));
|
||||
try {
|
||||
mkdirSync(join(work, "base-1"));
|
||||
writeFileSync(join(work, "base-1", "status.json"), JSON.stringify({ id: "base-1", state: "built", started: "2026-10-13T00:00:00Z" }));
|
||||
mkdirSync(join(work, "base-2"));
|
||||
// A build whose process is gone while it says building was lost, and holds nothing up.
|
||||
writeFileSync(join(work, "base-2", "status.json"), JSON.stringify({ id: "base-2", state: "building", started: "2026-10-14T00:00:00Z", pid: 2 ** 22 + 7 }));
|
||||
assert.deepEqual(listBaseBuilds(work).map((b) => `${b.id} ${b.state}`), ["base-2 lost", "base-1 built"]);
|
||||
assert.equal(buildingBase(work), undefined);
|
||||
writeFileSync(join(work, "base-2", "status.json"), JSON.stringify({ id: "base-2", state: "building", started: "2026-10-14T00:00:00Z", pid: process.pid }));
|
||||
assert.equal(buildingBase(work)?.id, "base-2");
|
||||
assert.deepEqual(listRuns(work), []);
|
||||
assert.ok(readFileSync(join(work, "base-1", "status.json"), "utf8"));
|
||||
} finally {
|
||||
rmSync(work, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
// **A run and a rebuild asked together: one starts** (review 256). Each asks the package registry, which
|
||||
// waits, and each refused while the other was going; asked at once, both passed their checks before either
|
||||
// wrote its status. The registry is asked first now, and the check and the start are one step.
|
||||
function aLab(): string {
|
||||
return mkdtempSync(join(tmpdir(), "lab-launch-"));
|
||||
}
|
||||
const fresh: BaseImage = { alias: BASE_IMAGE_ALIAS, exists: true, built: "2026-10-13T00:00:00.000Z", ageDays: 1 };
|
||||
const slowRegistry = () => new Promise<{ registry: string }>((ok) => setTimeout(() => ok({ registry: "https://forge.invalid/r/" }), 20));
|
||||
const launch = { registry: slowRegistry, base: () => fresh };
|
||||
function beginRun(work: string, id: string) {
|
||||
return () => {
|
||||
mkdirSync(join(work, id));
|
||||
const s = { id, state: "running" as const, started: new Date().toISOString(), tests: [], refs: {}, pid: process.pid };
|
||||
writeFileSync(join(work, id, "status.json"), JSON.stringify(s));
|
||||
return s;
|
||||
};
|
||||
}
|
||||
function beginBuild(work: string, id: string) {
|
||||
return () => {
|
||||
mkdirSync(join(work, id));
|
||||
const b = { id, state: "building" as const, started: new Date().toISOString(), pid: process.pid };
|
||||
writeFileSync(join(work, id, "status.json"), JSON.stringify(b));
|
||||
return b;
|
||||
};
|
||||
}
|
||||
|
||||
test("a run and a rebuild asked at once: exactly one starts", async () => {
|
||||
for (const runFirst of [true, false]) {
|
||||
const work = aLab();
|
||||
try {
|
||||
// Both asked before either answers, in one order and then the other.
|
||||
const ask = { run: () => launchRun(work, launch, beginRun(work, "run-a")), build: () => launchRebuild(work, launch, beginBuild(work, "base-a")) };
|
||||
const [r, b] = runFirst ? await Promise.all([ask.run(), ask.build()])
|
||||
: (await Promise.all([ask.build(), ask.run()])).reverse() as [Awaited<ReturnType<typeof ask.run>>, Awaited<ReturnType<typeof ask.build>>];
|
||||
assert.equal([r.started, b.started].filter(Boolean).length, 1, `both or neither started: run ${r.started}, rebuild ${b.started}`);
|
||||
assert.equal(listRuns(work).length + listBaseBuilds(work).length, 1);
|
||||
} finally {
|
||||
rmSync(work, { recursive: true, force: true });
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
test("two runs, or two rebuilds, asked at once: one of each starts", async () => {
|
||||
const work = aLab();
|
||||
try {
|
||||
const runs = await Promise.all([launchRun(work, launch, beginRun(work, "run-a")), launchRun(work, launch, beginRun(work, "run-b"))]);
|
||||
assert.deepEqual(runs.map((r) => r.started).sort(), [false, true]);
|
||||
const other = aLab();
|
||||
const builds = await Promise.all([launchRebuild(other, launch, beginBuild(other, "base-a")), launchRebuild(other, launch, beginBuild(other, "base-b"))]);
|
||||
assert.deepEqual(builds.map((b) => b.started).sort(), [false, true]);
|
||||
rmSync(other, { recursive: true, force: true });
|
||||
} finally {
|
||||
rmSync(work, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
test("a run is refused on a stale base, and starts nothing", async () => {
|
||||
const work = aLab();
|
||||
try {
|
||||
const stale: BaseImage = { alias: BASE_IMAGE_ALIAS, exists: true, built: "2026-08-31T09:00:00.000Z", ageDays: 43 };
|
||||
const r = await launchRun(work, { registry: slowRegistry, base: () => stale }, beginRun(work, "run-a"));
|
||||
assert.equal(r.started, false);
|
||||
assert.match(r.started ? "" : r.reason, /lab_base \{"rebuild": true\}/);
|
||||
assert.deepEqual(listRuns(work), []);
|
||||
} finally {
|
||||
rmSync(work, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
test("a rebuild or a run that never recorded its process is lost, and holds nothing up", () => {
|
||||
const work = aLab();
|
||||
try {
|
||||
mkdirSync(join(work, "base-x"));
|
||||
writeFileSync(join(work, "base-x", "status.json"), JSON.stringify({ id: "base-x", state: "building", started: "2026-10-14T00:00:00Z" }));
|
||||
mkdirSync(join(work, "run-x"));
|
||||
writeFileSync(join(work, "run-x", "status.json"), JSON.stringify({ id: "run-x", state: "running", started: "2026-10-14T00:00:00Z", tests: [], refs: {} }));
|
||||
assert.equal(listBaseBuilds(work)[0]?.state, "lost");
|
||||
assert.equal(buildingBase(work), undefined);
|
||||
assert.equal(readStatus(work, "run-x")?.state, "lost");
|
||||
assert.equal(running(work), undefined);
|
||||
} finally {
|
||||
rmSync(work, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
test("a rebuild's credential left behind is cleaned, and a running one's is kept", () => {
|
||||
const work = aLab();
|
||||
try {
|
||||
for (const id of ["base-old", "base-now", "run-old", "run-now"]) writeFileSync(credentialPath(work, id), "x");
|
||||
const removed = cleanCredentials(work, [credentialPath(work, "base-now"), credentialPath(work, "run-now")]).sort();
|
||||
assert.deepEqual(removed, [credentialPath(work, "base-old"), credentialPath(work, "run-old")].sort());
|
||||
} finally {
|
||||
rmSync(work, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
test("lab_check's problem: a stale, missing or unread base image; a fresh one is none", () => {
|
||||
assert.match(baseProblem({ alias: BASE_IMAGE_ALIAS, exists: false }) ?? "", /is not on this machine/);
|
||||
assert.match(baseProblem({ alias: BASE_IMAGE_ALIAS, exists: false, problem: "incus could not list the lab's images" }) ?? "", /age is not known/);
|
||||
assert.match(baseProblem({ alias: BASE_IMAGE_ALIAS, exists: true, built: "x", ageDays: 30 }) ?? "", /older than the lab's bound/);
|
||||
assert.equal(baseProblem(fresh), undefined);
|
||||
});
|
||||
|
||||
// The tools use the gate and the check above (index.ts registers with the SDK when imported, so it is read).
|
||||
test("lab_run and lab_base start through the gate, and lab_check names what is wrong with the base", () => {
|
||||
const index = readFileSync(new URL("../tools/index.ts", import.meta.url), "utf8");
|
||||
assert.match(index, /await launchRun\(work,/);
|
||||
assert.match(index, /await launchRebuild\(work,/);
|
||||
assert.match(index, /const unfit = baseProblem\(base\);\s*if \(unfit\) problems\.push\(unfit\)/);
|
||||
assert.match(index, /if \(args\.rebuild !== true\) return reading;/);
|
||||
});
|
||||
@@ -5,7 +5,7 @@ import { spawnSync } from "node:child_process";
|
||||
import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
|
||||
import { installPlan, installStep, NPM_REPOSITORIES, REPOSITORIES, script } from "../tools/runs.ts";
|
||||
import { installPlan, installStep, NPM_REPOSITORIES, outcomeOf, readStatus, REPOSITORIES, script } from "../tools/runs.ts";
|
||||
|
||||
// Defends novox/hq issue 624: lab_run ran `npm ci` at the root of every checkout it installs, and
|
||||
// mesh-tools keeps its package in node-tools/ with no lock file at its root, so every run failed at its
|
||||
@@ -381,3 +381,108 @@ test("a forge setting that is not http(s) trusts no origin of its own", async ()
|
||||
packument("ftp://novox.internal/api/packages/novox/npm/x.tgz")).get, root);
|
||||
assert.match(viaRoot.problem ?? "", /neither/);
|
||||
});
|
||||
|
||||
// Defends novox/hq issue 693: a run whose only test skipped as NOT REACHED read "0 passed, 0 failed", exit 0,
|
||||
// and lab_status said passed. The log's tail, as run-2026-10-14T00-21-44-014Z on shanks wrote it.
|
||||
const oldLog = [
|
||||
"STOPPED at step 16 of 24, base: \t\t\t\tMake sure you have all the referenced content and try again.",
|
||||
"\ufe63 genesis adopts its bus as the nats module in place: one bus, its streams kept, the node connected (588152.016874ms) # ADR 0333 §5 NOT REACHED: the first run stopped at step 16 of 24, base, before the broker step:",
|
||||
" \t\t\t\tMake sure you have all the referenced content and try again.",
|
||||
"NotFound: content digest sha256:e2de96513ba9: not found",
|
||||
"ℹ tests 1", "ℹ suites 0", "ℹ pass 0", "ℹ fail 0", "ℹ cancelled 0", "ℹ skipped 1", "ℹ todo 0",
|
||||
"ℹ duration_ms 590254.163993",
|
||||
"",
|
||||
"recorded: test/integration/genesis-keeps-its-bus.test.ts — 0 passed, 0 failed, against mesh-lab 7ed7da1",
|
||||
].join("\n");
|
||||
|
||||
// The same run, as the lab's suite says it once it names its skips (mesh-lab, issue 693).
|
||||
const newLog = [
|
||||
"ℹ tests 1", "ℹ pass 0", "ℹ fail 0", "ℹ skipped 1",
|
||||
"",
|
||||
"recorded: test/integration/genesis-keeps-its-bus.test.ts — 0 passed, 0 failed, 1 skipped, against mesh-lab 7ed7da1",
|
||||
"NOT PASSED: no test passed: 1 skipped, 1 of them as NOT REACHED",
|
||||
"skipped: genesis adopts its bus — one bus (test/integration/genesis-keeps-its-bus.test.ts) # ADR 0333 §5 NOT REACHED: the first run stopped at step 16 of 24, base: NotFound: content digest",
|
||||
].join("\n");
|
||||
|
||||
function anEndedRun(log: string, state: "passed" | "failed", exit: number): { work: string; id: string } {
|
||||
const work = mkdtempSync(join(tmpdir(), "lab-runs-"));
|
||||
const id = "run-2026-10-14T00-21-44-014Z";
|
||||
mkdirSync(join(work, id));
|
||||
writeFileSync(join(work, id, "run.log"), log);
|
||||
writeFileSync(join(work, id, "status.json"), JSON.stringify({
|
||||
id, state, exit, started: "2026-10-14T00:21:44.014Z", ended: "2026-10-14T00:33:11.179Z",
|
||||
tests: ["test/integration/genesis-keeps-its-bus.test.ts"], refs: {},
|
||||
}));
|
||||
return { work, id };
|
||||
}
|
||||
|
||||
test("a run whose only test skipped as NOT REACHED, from a lab of before, reads as failed with the reason", () => {
|
||||
const { work, id } = anEndedRun(oldLog, "passed", 0);
|
||||
const s = readStatus(work, id);
|
||||
assert.equal(s?.state, "failed", JSON.stringify(s));
|
||||
assert.equal(s?.exit, 0);
|
||||
assert.equal(s?.outcome?.passed, 0);
|
||||
assert.equal(s?.outcome?.skipped, 1);
|
||||
assert.equal(s?.outcome?.notPassed, "no test passed: 1 skipped, 1 of them as NOT REACHED");
|
||||
assert.match(s?.outcome?.skips[0]?.reason ?? "", /^ADR 0333 §5 NOT REACHED: the first run stopped at step 16 of 24, base, before the broker step:$/);
|
||||
// Kept in the run's record, not only answered.
|
||||
const kept = JSON.parse(readFileSync(join(work, id, "status.json"), "utf8"));
|
||||
assert.equal(kept.state, "failed");
|
||||
assert.equal(kept.outcome.notPassed, "no test passed: 1 skipped, 1 of them as NOT REACHED");
|
||||
rmSync(work, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
test("the lab's own NOT PASSED and skipped lines are read, a test name's punctuation and all", () => {
|
||||
const { work, id } = anEndedRun(newLog, "failed", 1);
|
||||
const s = readStatus(work, id);
|
||||
assert.equal(s?.state, "failed");
|
||||
assert.equal(s?.outcome?.notPassed, "no test passed: 1 skipped, 1 of them as NOT REACHED");
|
||||
assert.deepEqual(s?.outcome?.skips, [{
|
||||
file: "test/integration/genesis-keeps-its-bus.test.ts",
|
||||
test: "genesis adopts its bus — one bus",
|
||||
reason: "ADR 0333 §5 NOT REACHED: the first run stopped at step 16 of 24, base: NotFound: content digest",
|
||||
}]);
|
||||
rmSync(work, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
test("a run that passed tests and skipped one for a declared reason stays passed, its skip listed", () => {
|
||||
const log = [
|
||||
"✔ a module lands (12ms)",
|
||||
"﹣ a builder builds (0.1ms) # set MESH_LAB_BUILDER to a built mesh-builder",
|
||||
"ℹ tests 2", "ℹ pass 1", "ℹ fail 0", "ℹ skipped 1",
|
||||
].join("\n");
|
||||
const { work, id } = anEndedRun(log, "passed", 0);
|
||||
const s = readStatus(work, id);
|
||||
assert.equal(s?.state, "passed");
|
||||
assert.equal(s?.outcome?.notPassed, undefined);
|
||||
assert.equal(s?.outcome?.skips[0]?.reason, "set MESH_LAB_BUILDER to a built mesh-builder");
|
||||
rmSync(work, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
test("a run that ran no test at all is not passed", () => {
|
||||
assert.equal(outcomeOf("ℹ tests 0\nℹ pass 0\nℹ fail 0\nℹ skipped 0\n").notPassed, "no test passed: none ran");
|
||||
});
|
||||
|
||||
// Review 254 on issue 693: a test's own output, printed before the suite reports, is not the suite's verdict.
|
||||
test("a line a test printed that looks like the suite's is not read as the suite's", () => {
|
||||
const log = [
|
||||
"NOT PASSED: a test printed this",
|
||||
"skipped: a forged skip (test/integration/x.test.ts) # FORGED NOT REACHED",
|
||||
"✔ a module lands (12ms)",
|
||||
"ℹ tests 1", "ℹ pass 1", "ℹ fail 0", "ℹ skipped 0",
|
||||
"",
|
||||
"recorded: test/integration/x.test.ts — 1 passed, 0 failed, 0 skipped, against mesh-lab 7ed7da1",
|
||||
].join("\n");
|
||||
const o = outcomeOf(log);
|
||||
assert.equal(o.notPassed, undefined, JSON.stringify(o));
|
||||
assert.deepEqual(o.skips, []);
|
||||
});
|
||||
|
||||
test("not reached is matched in any case", () => {
|
||||
const log = [
|
||||
"✔ a module lands (12ms)",
|
||||
"﹣ the broker step (0.1ms) # the broker step was not reached",
|
||||
"ℹ tests 2", "ℹ pass 1", "ℹ fail 0", "ℹ skipped 1",
|
||||
].join("\n");
|
||||
assert.equal(outcomeOf(log).notPassed, "1 test(s) skipped as NOT REACHED: their subject was not reached");
|
||||
});
|
||||
|
||||
+51
-12
@@ -9,7 +9,8 @@ import { tmpdir } from "node:os";
|
||||
import { join } from "node:path";
|
||||
import {
|
||||
checkDir, cleanCredentials, clearChecks, credentialArgs, forgeCredential, installPlan, listRuns, npmRegistry, NPM_REPOSITORIES, publicRootOf, readStatus, REPOSITORIES, running, start,
|
||||
stop, tail, writeCredential,
|
||||
stop, tail, writeCredential, baseBuildLog, buildingBase, listBaseBuilds, startBaseBuild, credentialPath, launchRun,
|
||||
launchRebuild, BASE_MAX_AGE_DAYS, describeBase, readBaseImage, baseProblem,
|
||||
} from "./runs.js";
|
||||
|
||||
export function getLabTools(env: NodeJS.ProcessEnv): ToolDefinition[] {
|
||||
@@ -59,12 +60,18 @@ export function getLabTools(env: NodeJS.ProcessEnv): ToolDefinition[] {
|
||||
// **And what a run would check out and install, before a run finds out** (novox/hq issue 624): every
|
||||
// repository it clones answers on the forge, and every one it installs has a lock file where the run
|
||||
// installs from.
|
||||
// A credential a stopped, crashed or rebooted run left behind is removed, and said; one still in use
|
||||
// by a running run is not.
|
||||
const busy = running(work);
|
||||
const left = cleanCredentials(work, busy ? `${work}/.${busy.id}.git-credentials` : undefined);
|
||||
const removed = left.length > 0 ? `removed ${left.length} forge credential(s) a run left behind: ${left.join(", ")}` : "";
|
||||
const output = [`${check.stdout}${check.stderr}`.trim(), removed, ...leftovers, ...problems].filter(Boolean).join("\n");
|
||||
// A credential a stopped, crashed or rebooted run or rebuild left behind is removed, and said; one still in
|
||||
// use by a running run or rebuild is not.
|
||||
const busy = [running(work)?.id, buildingBase(work)?.id].filter((id): id is string => !!id);
|
||||
const left = cleanCredentials(work, busy.map((id) => credentialPath(work, id)));
|
||||
const removed = left.length > 0 ? `removed ${left.length} forge credential(s) a run or rebuild left behind: ${left.join(", ")}` : "";
|
||||
// **And how old the base image is** (novox/hq issue 698): past the bound, missing, or of an age that cannot
|
||||
// be read is a problem here, though lab_run refuses only the first.
|
||||
const base = readBaseImage();
|
||||
const unfit = baseProblem(base);
|
||||
if (unfit) problems.push(unfit);
|
||||
const output = [`${check.stdout}${check.stderr}`.trim(), describeBase(base), removed, ...leftovers, ...problems]
|
||||
.filter(Boolean).join("\n");
|
||||
return { ok: check.status === 0 && problems.length === 0, output };
|
||||
},
|
||||
},
|
||||
@@ -96,11 +103,43 @@ export function getLabTools(env: NodeJS.ProcessEnv): ToolDefinition[] {
|
||||
}
|
||||
const stranger = Object.keys(refs).filter((r) => !REPOSITORIES.includes(r));
|
||||
if (stranger.length > 0) return { started: false, reason: `the lab does not build ${stranger.join(", ")}` };
|
||||
const busy = running(work);
|
||||
if (busy) return { started: false, reason: `${busy.id} is still ${busy.state}; one run at a time`, running: busy };
|
||||
const registry = await registryOf(forge);
|
||||
return { started: true, run: start(work, forge, tests, refs, credentialOf(forge), registry.registry),
|
||||
registry: registry.registry, ...(registry.problem ? { problem: registry.problem } : {}) };
|
||||
// **One job at a time, not on a base image past its bound, nor while it is rebuilt** (novox/hq issue 698,
|
||||
// review 256): the registry asked first, then the check and the start with nothing awaited between.
|
||||
const launched = await launchRun(work, { registry: () => registryOf(forge), base: () => readBaseImage() },
|
||||
(registry) => start(work, forge, tests, refs, credentialOf(forge), registry));
|
||||
if (!launched.started) return launched;
|
||||
return { started: true, run: launched.job, base: describeBase(launched.base), registry: launched.registry,
|
||||
...(launched.problem ? { problem: launched.problem } : {}) };
|
||||
},
|
||||
},
|
||||
{
|
||||
name: "lab_base",
|
||||
description:
|
||||
"The lab's base image, which every bed machine with a container runtime is raised from: when it was built, its " +
|
||||
`age, the bound lab_run refuses past (${BASE_MAX_AGE_DAYS} days), and the last rebuilds with the newest one's log. ` +
|
||||
"Reads only, unless rebuild is true: then it rebuilds the image with mesh-lab's `base build` from the forge's " +
|
||||
"main, in the background, and answers at once; ask again for the build's state and the image's new age.",
|
||||
input: {
|
||||
rebuild: { type: "boolean", description: "rebuild the image (default false: only read)" },
|
||||
},
|
||||
run: async (args) => {
|
||||
const before = readBaseImage();
|
||||
const builds = listBaseBuilds(work).slice(0, 3);
|
||||
const newest = builds[0];
|
||||
const reading = {
|
||||
base: before, said: describeBase(before), bound: BASE_MAX_AGE_DAYS,
|
||||
...(baseProblem(before) ? { problem: baseProblem(before) } : {}),
|
||||
builds, ...(newest ? { log: baseBuildLog(work, newest.id) } : {}),
|
||||
};
|
||||
if (args.rebuild !== true) return reading;
|
||||
const forge = forgeOf();
|
||||
if (!forge) return { ...reading, started: false, reason: "the lab's forge is not set: settings for lab, {\"forge\": \"<url>\"}" };
|
||||
// Not under a run, nor beside another rebuild: the registry asked first, then the check and the start with
|
||||
// nothing awaited between (review 256).
|
||||
const launched = await launchRebuild(work, { registry: () => registryOf(forge), base: () => before },
|
||||
(registry) => startBaseBuild(work, forge, credentialOf(forge), registry));
|
||||
if (launched.started === false) return { ...reading, started: false, reason: launched.reason };
|
||||
return { ...reading, started: true, build: launched.job };
|
||||
},
|
||||
},
|
||||
{
|
||||
|
||||
+364
-9
@@ -6,7 +6,7 @@
|
||||
// and that file is the whole of what the tools read back: a runtime that restarts mid-run still answers
|
||||
// for it, and says it was lost rather than pretending it is still going.
|
||||
|
||||
import { spawn } from "node:child_process";
|
||||
import { spawn, spawnSync } from "node:child_process";
|
||||
import { existsSync, mkdirSync, mkdtempSync, readFileSync, readdirSync, rmSync, writeFileSync } from "node:fs";
|
||||
import { join } from "node:path";
|
||||
|
||||
@@ -223,16 +223,18 @@ trap ${shellQuote(`${rm}; exit 129`)} HUP`;
|
||||
}
|
||||
|
||||
/**
|
||||
* cleanCredentials removes every run's credential file left in the work directory but the one named — what
|
||||
* a crash or a reboot left behind, which no trap could remove. Answers what it removed.
|
||||
* cleanCredentials removes every run's and every base rebuild's credential file left in the work directory
|
||||
* but the ones named — what a crash or a reboot left behind, which no trap could remove. Answers what it
|
||||
* removed.
|
||||
*/
|
||||
export function cleanCredentials(work: string, keep?: string): string[] {
|
||||
export function cleanCredentials(work: string, keep?: string | string[]): string[] {
|
||||
if (!existsSync(work)) return [];
|
||||
const kept = new Set([keep ?? []].flat());
|
||||
const removed: string[] = [];
|
||||
for (const name of readdirSync(work)) {
|
||||
if (!/^\.run-.*\.git-credentials$/.test(name)) continue;
|
||||
if (!/^\.(run|base)-.*\.git-credentials$/.test(name)) continue;
|
||||
const path = join(work, name);
|
||||
if (path === keep) continue;
|
||||
if (kept.has(path)) continue;
|
||||
rmSync(path, { force: true });
|
||||
removed.push(path);
|
||||
}
|
||||
@@ -286,6 +288,117 @@ export interface RunStatus {
|
||||
commits?: Record<string, string>;
|
||||
exit?: number;
|
||||
pid?: number;
|
||||
/** What the suite said of its tests, read from the run's log once it ended (novox/hq issue 693). */
|
||||
outcome?: Outcome;
|
||||
}
|
||||
|
||||
/** One skipped test, its file and the reason it gave. */
|
||||
export interface Skip {
|
||||
file: string;
|
||||
test: string;
|
||||
reason: string;
|
||||
}
|
||||
|
||||
/**
|
||||
* What a run's suite said of its tests: its totals, each skip with its reason, and — when the run did not
|
||||
* pass although its exit said 0 — why (`notPassed`). Totals the runner did not print are absent.
|
||||
*/
|
||||
export interface Outcome {
|
||||
passed?: number;
|
||||
failed?: number;
|
||||
skipped?: number;
|
||||
skips: Skip[];
|
||||
notPassed?: string;
|
||||
}
|
||||
|
||||
/**
|
||||
* outcomeOf reads what a run's log says of its tests (novox/hq issue 693).
|
||||
*
|
||||
* **A run in which no test passed has proven nothing**, and the runner exits 0 when every test skipped:
|
||||
* the genesis bed skipped its only test as "NOT REACHED", the suite printed "0 passed, 0 failed", and the
|
||||
* lab recorded the run as passed. The lab's suite now says it itself — a "NOT PASSED: <why>" line and a
|
||||
* "skipped: <test> (<file>) # <reason>" line per skip after its "recorded:" line, and an exit that is not
|
||||
* 0 — and this reads those lines. For a run of a lab from before (a branch, or an old log), the same rule is
|
||||
* read from the runner's own output: its summary totals, and its skip lines' first line of reason.
|
||||
*
|
||||
* The rule, the lab suite's (mesh-lab src/outcomes.ts): **not passed when no test passed**, or when a test
|
||||
* skipped as NOT REACHED (its subject was not reached); a skip for another reason beside tests that passed
|
||||
* leaves the run passed, its reason listed.
|
||||
*/
|
||||
export function outcomeOf(log: string): Outcome {
|
||||
const plain = log.replace(/\u001b\[[0-9;]*m/g, "");
|
||||
const total = (word: string) => {
|
||||
// The last summary in the log: the runner's own, once per run.
|
||||
const all = [...plain.matchAll(new RegExp(`^\\s*(?:\u2139|#)\\s*${word}\\s+(\\d+)\\s*$`, "gm"))];
|
||||
const last = all[all.length - 1];
|
||||
return last ? Number(last[1]) : undefined;
|
||||
};
|
||||
const outcome: Outcome = { skips: [] };
|
||||
const passed = total("pass");
|
||||
const failed = total("fail");
|
||||
const skipped = total("skipped");
|
||||
if (passed !== undefined) outcome.passed = passed;
|
||||
if (failed !== undefined) outcome.failed = failed;
|
||||
if (skipped !== undefined) outcome.skipped = skipped;
|
||||
|
||||
// **The suite's own lines are read only after its last "recorded:" line** (novox/hq issue 693, review
|
||||
// 254): a test prints what it likes before the suite reports, and a line of its that looked like the
|
||||
// suite's — "NOT PASSED: …", "skipped: … # NOT REACHED" — would otherwise stand for the suite's verdict.
|
||||
const recorded = [...plain.matchAll(/^recorded: .*$/gm)];
|
||||
const lastRecorded = recorded[recorded.length - 1];
|
||||
const suiteSaid = lastRecorded ? plain.slice((lastRecorded.index ?? 0) + lastRecorded[0].length) : "";
|
||||
|
||||
// The suite's own line, "skipped: <test> (<file>) # <reason>": the file in brackets, a .ts, parts it.
|
||||
for (const m of suiteSaid.matchAll(/^skipped: (.*?) \(([^()]+\.ts)\) # (.*)$/gm)) {
|
||||
outcome.skips.push({ file: m[2] ?? "", test: m[1] ?? "", reason: m[3] === "no reason given" ? "" : m[3] ?? "" });
|
||||
}
|
||||
if (outcome.skips.length === 0) {
|
||||
// A lab from before names no skip itself; its runner's spec line does: "﹣ <test> (<ms>ms) # <reason>".
|
||||
for (const m of plain.matchAll(/^\s*\ufe63 (.*?) \([\d.]+m?s\) # (.*)$/gm)) {
|
||||
const reason = (m[2] ?? "").trim();
|
||||
outcome.skips.push({ file: "", test: m[1] ?? "", reason: reason === "SKIP" ? "" : reason });
|
||||
}
|
||||
}
|
||||
|
||||
const said = suiteSaid.match(/^NOT PASSED: (.*)$/m);
|
||||
if (said) {
|
||||
outcome.notPassed = (said[1] ?? "").trim();
|
||||
} else if ((failed ?? 0) === 0) {
|
||||
// In any case: "not reached" says the same as "NOT REACHED".
|
||||
const unreached = outcome.skips.filter((s) => s.reason.toUpperCase().includes("NOT REACHED")).length;
|
||||
if (passed === 0) {
|
||||
outcome.notPassed = outcome.skips.length > 0 || (skipped ?? 0) > 0
|
||||
? `no test passed: ${skipped ?? outcome.skips.length} skipped${unreached > 0 ? `, ${unreached} of them as NOT REACHED` : ""}`
|
||||
: "no test passed: none ran";
|
||||
} else if (unreached > 0) {
|
||||
outcome.notPassed = `${unreached} test(s) skipped as NOT REACHED: their subject was not reached`;
|
||||
}
|
||||
}
|
||||
return outcome;
|
||||
}
|
||||
|
||||
/**
|
||||
* settled is a run that ended, with its outcome read from its log: a run whose exit said 0 and whose suite
|
||||
* proved nothing reads as failed, with why (novox/hq issue 693). Read once and kept in its status, so the
|
||||
* record says it too; a run still going, stopped or lost is left as it is.
|
||||
*/
|
||||
export function settled(work: string, s: RunStatus): RunStatus {
|
||||
if (s.outcome || !s.ended || (s.state !== "passed" && s.state !== "failed")) return s;
|
||||
let log: string;
|
||||
try {
|
||||
log = readFileSync(join(runDir(work, s.id), "run.log"), "utf8");
|
||||
} catch {
|
||||
return s;
|
||||
}
|
||||
const outcome = outcomeOf(log);
|
||||
const next: RunStatus = { ...s, outcome };
|
||||
if (next.state === "passed" && outcome.notPassed) next.state = "failed";
|
||||
try {
|
||||
writeFileSync(statusPath(work, s.id), JSON.stringify(next, null, 2));
|
||||
} catch {
|
||||
// Read again next time: what lab_status answers is the same either way.
|
||||
}
|
||||
return next;
|
||||
}
|
||||
|
||||
export function runDir(work: string, id: string): string {
|
||||
@@ -300,16 +413,23 @@ export function readStatus(work: string, id: string): RunStatus | undefined {
|
||||
try {
|
||||
const s = JSON.parse(readFileSync(statusPath(work, id), "utf8")) as RunStatus;
|
||||
// A run whose process is gone while its status still says it is going was lost — the runtime or
|
||||
// the machine restarted under it. Said, rather than left reading as running for ever.
|
||||
if (!["passed", "failed", "stopped", "lost"].includes(s.state) && s.pid && !alive(s.pid)) {
|
||||
// the machine restarted under it. Said, rather than left reading as running for ever. One that never
|
||||
// recorded a process (the runtime died between writing its status and starting it) is lost too: it
|
||||
// would otherwise hold up every run after it (review 256).
|
||||
if (!["passed", "failed", "stopped", "lost"].includes(s.state) && gone(s.pid)) {
|
||||
s.state = "lost";
|
||||
}
|
||||
return s;
|
||||
return settled(work, s);
|
||||
} catch {
|
||||
return undefined;
|
||||
}
|
||||
}
|
||||
|
||||
/** gone is whether a job's process is not running: none recorded, or none by that id. */
|
||||
function gone(pid: number | undefined): boolean {
|
||||
return !pid || !alive(pid);
|
||||
}
|
||||
|
||||
function alive(pid: number): boolean {
|
||||
try {
|
||||
process.kill(pid, 0);
|
||||
@@ -446,3 +566,238 @@ export function tail(work: string, id: string, lines: number): string {
|
||||
return "";
|
||||
}
|
||||
}
|
||||
|
||||
// ---- the base image (novox/hq issue 698)
|
||||
//
|
||||
// Every bed machine that needs a container runtime is a clone of one base image, `mesh-lab/base`, which
|
||||
// mesh-lab's `base build` makes from the distribution's current image. A machine raised from it carries the
|
||||
// package database the image was built with. On a rolling distribution the mirrors stop serving what an old
|
||||
// database names within weeks, and a bed that installs a package then fails on a 404 that reads as a mirror
|
||||
// outage (novox/hq issue 205; seen 2026-10-14 when genesis-keeps-its-bus installed postgresql-libs from a
|
||||
// database six weeks old). So the lab names the image's age wherever it is asked, refuses a run on an image
|
||||
// older than the bound, and rebuilds the image when asked to.
|
||||
//
|
||||
// **The bound is 14 days** (BASE_MAX_AGE_DAYS). Arch's mirrors keep a package version for as long as it is
|
||||
// current and drop it soon after it is replaced; an image a fortnight old has reliably installed what beds
|
||||
// install, and the one that failed was 44 days old. A rebuild takes minutes, so a short bound costs little;
|
||||
// a run refused is cheaper than a bed that fails an hour in for a reason that is not the change under test.
|
||||
|
||||
/** The image every bed machine with a runtime is raised from, as mesh-lab names it (src/lifecycle/place.ts). */
|
||||
export const BASE_IMAGE_ALIAS = "mesh-lab/base";
|
||||
|
||||
/** How old the base image may be, in days, before a run is refused (see the head of this file). */
|
||||
export const BASE_MAX_AGE_DAYS = 14;
|
||||
|
||||
const DAY = 24 * 60 * 60 * 1000;
|
||||
|
||||
export interface BaseImage {
|
||||
alias: string;
|
||||
/** Whether the image is there at all. */
|
||||
exists: boolean;
|
||||
/** When this machine made it, ISO. */
|
||||
built?: string;
|
||||
/** Its age in whole days. */
|
||||
ageDays?: number;
|
||||
/** Why its age could not be read, when it could not. */
|
||||
problem?: string;
|
||||
}
|
||||
|
||||
/**
|
||||
* baseImageFrom reads `incus image list <alias> --format json`: the image whose aliases hold the base's
|
||||
* name, and when it was made here (its upload, which a publish sets).
|
||||
*/
|
||||
export function baseImageFrom(listed: string | undefined, now: Date): BaseImage {
|
||||
const alias = BASE_IMAGE_ALIAS;
|
||||
if (listed === undefined) return { alias, exists: false, problem: "incus could not list the lab's images" };
|
||||
let images: Array<{ aliases?: Array<{ name?: string }>; uploaded_at?: string; created_at?: string }>;
|
||||
try {
|
||||
images = JSON.parse(listed);
|
||||
} catch {
|
||||
return { alias, exists: false, problem: "incus listed the lab's images as something that is not JSON" };
|
||||
}
|
||||
const image = (Array.isArray(images) ? images : []).find((i) => (i.aliases ?? []).some((a) => a.name === alias));
|
||||
if (!image) return { alias, exists: false };
|
||||
const made = [image.uploaded_at, image.created_at].map((t) => (t ? Date.parse(t) : NaN))
|
||||
.find((t) => Number.isFinite(t) && t > 0);
|
||||
if (made === undefined) return { alias, exists: true, problem: "incus gives no time the image was made" };
|
||||
return { alias, exists: true, built: new Date(made).toISOString(), ageDays: Math.floor((now.getTime() - made) / DAY) };
|
||||
}
|
||||
|
||||
/** readBaseImage asks incus, on this machine, for the base image. */
|
||||
export function readBaseImage(now = new Date()): BaseImage {
|
||||
const listed = spawnSync("incus", ["image", "list", BASE_IMAGE_ALIAS, "--format", "json"], { encoding: "utf8" });
|
||||
return baseImageFrom(listed.status === 0 ? listed.stdout : undefined, now);
|
||||
}
|
||||
|
||||
/** The base image's age in one sentence, as lab_check and lab_run say it. */
|
||||
export function describeBase(b: BaseImage): string {
|
||||
if (b.problem) return `the base image ${b.alias}: its age is not known: ${b.problem}`;
|
||||
if (!b.exists) return `the base image ${b.alias} is not on this machine; rebuild it with lab_base {"rebuild": true}`;
|
||||
return `the base image ${b.alias} was built ${b.built} (${b.ageDays} day(s) ago; the bound is ${BASE_MAX_AGE_DAYS})`;
|
||||
}
|
||||
|
||||
/**
|
||||
* staleBase is why a run is refused for its base image, or undefined when it is not: an image older than the
|
||||
* bound. An image that is missing or whose age cannot be read is not refused here — a bed that needs it says
|
||||
* so itself, and a bed that does not need it runs.
|
||||
*/
|
||||
export function staleBase(b: BaseImage): string | undefined {
|
||||
if (!b.exists || b.ageDays === undefined || b.ageDays <= BASE_MAX_AGE_DAYS) return undefined;
|
||||
return `the base image ${b.alias} was built ${b.built}, ${b.ageDays} days ago, older than the lab's bound of ` +
|
||||
`${BASE_MAX_AGE_DAYS} days: a bed machine raised from it carries a package database the mirrors no longer serve ` +
|
||||
`(novox/hq issues 205, 698). Rebuild it with lab_base {"rebuild": true}, then run again`;
|
||||
}
|
||||
|
||||
/**
|
||||
* baseProblem is what lab_check and lab_base say is wrong with the base image, or undefined: past the bound, not
|
||||
* on this machine, or of an age that cannot be read (review 256). Only the first refuses a run.
|
||||
*/
|
||||
export function baseProblem(b: BaseImage): string | undefined {
|
||||
if (b.problem || !b.exists) return describeBase(b);
|
||||
return staleBase(b);
|
||||
}
|
||||
|
||||
/**
|
||||
* runRefusal is why lab_run starts no run for the base image, or undefined: a rebuild still going, which
|
||||
* replaces the image a bed raises its machines from, or an image older than the bound.
|
||||
*/
|
||||
export function runRefusal(base: BaseImage, rebuilding?: { id: string; started: string }): string | undefined {
|
||||
if (rebuilding) return `the base image is being rebuilt (${rebuilding.id}, since ${rebuilding.started}); run once lab_base says it is built`;
|
||||
return staleBase(base);
|
||||
}
|
||||
|
||||
// ---- its rebuild: mesh-lab's `base build`, in the background, as a run is.
|
||||
|
||||
export interface BaseBuild {
|
||||
id: string;
|
||||
state: "building" | "built" | "failed" | "lost";
|
||||
started: string;
|
||||
ended?: string;
|
||||
exit?: number;
|
||||
pid?: number;
|
||||
}
|
||||
|
||||
function buildStatusPath(work: string, id: string): string {
|
||||
return join(work, id, "status.json");
|
||||
}
|
||||
|
||||
/** The base builds, newest first. A build whose process is gone while it says building was lost. */
|
||||
export function listBaseBuilds(work: string): BaseBuild[] {
|
||||
if (!existsSync(work)) return [];
|
||||
const builds: BaseBuild[] = [];
|
||||
for (const id of readdirSync(work).filter((d) => d.startsWith("base-"))) {
|
||||
try {
|
||||
const b = JSON.parse(readFileSync(buildStatusPath(work, id), "utf8")) as BaseBuild;
|
||||
if (b.state === "building" && gone(b.pid)) b.state = "lost";
|
||||
builds.push(b);
|
||||
} catch {
|
||||
// A directory without a status is not a build.
|
||||
}
|
||||
}
|
||||
return builds.sort((a, b) => b.started.localeCompare(a.started));
|
||||
}
|
||||
|
||||
/** The base build still going, if any. */
|
||||
export function buildingBase(work: string): BaseBuild | undefined {
|
||||
return listBaseBuilds(work).find((b) => b.state === "building");
|
||||
}
|
||||
|
||||
/** The last lines of a base build's log. */
|
||||
export function baseBuildLog(work: string, id: string, lines = 40): string {
|
||||
try {
|
||||
return readFileSync(join(work, id, "build.log"), "utf8").split("\n").slice(-Math.max(1, lines)).join("\n");
|
||||
} catch {
|
||||
return "";
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* baseScript is what one rebuild runs: mesh-lab's main from the forge, installed the way a run installs it,
|
||||
* then its `base build`, which replaces the image and reads back that it works before publishing it.
|
||||
*/
|
||||
export function baseScript(dir: string, forge: string, credential?: string, registry = `${forge}${NPM_PATH}`): string {
|
||||
const lab = join(dir, "mesh-lab");
|
||||
return `set -euo pipefail
|
||||
export GIT_TERMINAL_PROMPT=0
|
||||
${credentialGuard(credential)}
|
||||
cd ${shellQuote(dir)}
|
||||
git ${credentialArgs(credential)}clone --quiet --depth 1 ${shellQuote(`${forge}/novox/mesh-lab.git`)} ${shellQuote(lab)}
|
||||
${credential ? `rm -f ${shellQuote(credential)}` : ""}
|
||||
echo "mesh-lab $(git -C ${shellQuote(lab)} rev-parse HEAD)"
|
||||
printf '%s\\n' ${shellQuote(`@novox:registry=${registry}`)} > ${shellQuote(join(dir, ".npmrc"))}
|
||||
export NPM_CONFIG_USERCONFIG=${shellQuote(join(dir, ".npmrc"))}
|
||||
${installStep(lab, false)}
|
||||
cd ${shellQuote(lab)}
|
||||
node --experimental-strip-types src/cli.ts base build
|
||||
`;
|
||||
}
|
||||
|
||||
/** startBaseBuild rebuilds the base image in the background and answers at once with the build. */
|
||||
export function startBaseBuild(work: string, forge: string, credential?: string, registry?: string): BaseBuild {
|
||||
const id = `base-${new Date().toISOString().replace(/[:.]/g, "-")}`;
|
||||
const dir = join(work, id);
|
||||
mkdirSync(dir, { recursive: true });
|
||||
const build: BaseBuild = { id, state: "building", started: new Date().toISOString() };
|
||||
writeFileSync(buildStatusPath(work, id), JSON.stringify(build, null, 2));
|
||||
// What a crashed or rebooted run or rebuild left behind goes before this one writes its own.
|
||||
cleanCredentials(work);
|
||||
const credentials = writeCredential(credentialPath(work, id), credential);
|
||||
writeFileSync(join(dir, "build.sh"), baseScript(dir, forge, credentials, registry), { mode: 0o700 });
|
||||
const wrapper = `bash ${shellQuote(join(dir, "build.sh"))} > ${shellQuote(join(dir, "build.log"))} 2>&1; code=$?
|
||||
node -e ${shellQuote(
|
||||
`const f=${JSON.stringify(buildStatusPath(work, id))};const s=JSON.parse(require("fs").readFileSync(f,"utf8"));s.state=process.argv[1]==="0"?"built":"failed";s.exit=Number(process.argv[1]);s.ended=new Date().toISOString();require("fs").writeFileSync(f,JSON.stringify(s,null,2))`,
|
||||
)} "$code"
|
||||
rm -f ${shellQuote(credentialPath(work, id))}
|
||||
rm -rf ${shellQuote(join(dir, "mesh-lab"))}`;
|
||||
const child = spawn("bash", ["-c", wrapper], { detached: true, stdio: "ignore" });
|
||||
child.unref();
|
||||
build.pid = child.pid;
|
||||
writeFileSync(buildStatusPath(work, id), JSON.stringify(build, null, 2));
|
||||
return build;
|
||||
}
|
||||
|
||||
// ---- starting a run or a rebuild: one job on the lab's machine at a time (review 256).
|
||||
//
|
||||
// **Everything that waits is done first; the check and the start are one step.** A run and a rebuild each
|
||||
// refused while the other was going, but each asked the package registry — an await — between its check and
|
||||
// writing its status, so a run and a rebuild asked together could both pass their checks and both start: a
|
||||
// bed raising machines from an image being replaced under it. Here the registry is asked first, and nothing
|
||||
// is awaited between reading what is going and writing the new job's status, so in the one runtime that
|
||||
// serves the lab's tools no other call runs in between.
|
||||
|
||||
export interface Launch {
|
||||
/** The address a run or a rebuild names the package registry by, asked of the forge (npmRegistry). */
|
||||
registry: () => Promise<{ registry: string; problem?: string }>;
|
||||
/** The base image as it is now. */
|
||||
base: () => BaseImage;
|
||||
}
|
||||
|
||||
export type Launched<T> = { started: true; registry: string; problem?: string; base: BaseImage; job: T }
|
||||
| { started: false; reason: string; base: BaseImage };
|
||||
|
||||
/** launchRun starts a run unless a run or a rebuild is going, or the base image is past its bound. */
|
||||
export async function launchRun(work: string, launch: Launch, begin: (registry: string) => RunStatus):
|
||||
Promise<Launched<RunStatus>> {
|
||||
const registry = await launch.registry();
|
||||
// From here to begin(): nothing awaited.
|
||||
const base = launch.base();
|
||||
const busy = running(work);
|
||||
if (busy) return { started: false, reason: `${busy.id} is still ${busy.state}; one run at a time`, base };
|
||||
const refused = runRefusal(base, buildingBase(work));
|
||||
if (refused) return { started: false, reason: refused, base };
|
||||
return { started: true, ...registry, base, job: begin(registry.registry) };
|
||||
}
|
||||
|
||||
/** launchRebuild starts a rebuild of the base image unless a run or another rebuild is going. */
|
||||
export async function launchRebuild(work: string, launch: Launch, begin: (registry: string) => BaseBuild):
|
||||
Promise<Launched<BaseBuild>> {
|
||||
const registry = await launch.registry();
|
||||
// From here to begin(): nothing awaited.
|
||||
const base = launch.base();
|
||||
const rebuilding = buildingBase(work);
|
||||
if (rebuilding) return { started: false, reason: `${rebuilding.id} is still rebuilding it`, base };
|
||||
// A run raises its machines from the image; replacing it under one would change what the run tests.
|
||||
const busy = running(work);
|
||||
if (busy) return { started: false, reason: `${busy.id} is still ${busy.state}, and raises its machines from this image`, base };
|
||||
return { started: true, ...registry, base, job: begin(registry.registry) };
|
||||
}
|
||||
|
||||
@@ -0,0 +1,216 @@
|
||||
// Whether mail flows through mailu, as the node-engine asks it every interval (novox/hq ADR 0240, kind
|
||||
// `tool`; issue 690). Every container read healthy on 2026-10-14 while postfix could not resolve a name:
|
||||
// inbound mail was refused with 450 and outbound mail sat in the deferred queue for days. The parts'
|
||||
// checks judge parts; this judges the flow, from inside the postfix container, the way postfix sees it:
|
||||
//
|
||||
// 1. postfix runs (`postfix status`, standing in for the image's own check, `! /usr/libexec/postfix/master
|
||||
// -t`, which this one replaces);
|
||||
// 2. the deferred queue (`postqueue -j`) shows no fault of this side: a recipient deferred longer than the
|
||||
// bound because a lookup failed here, or overdue mail to three or more domains. One or two far domains
|
||||
// that do not answer are theirs, and can stay deferred for days: said, never unhealthy, so one dead
|
||||
// recipient does not page the operator for days;
|
||||
// 3. a public mail host's name resolves through the resolver postfix is given: a resolver that
|
||||
// SERVFAILs refuses inbound mail before anything reaches the queue.
|
||||
//
|
||||
// The answer is the health answer every health tool gives (mesh-sdk go/health): `state`, `healthy` beside
|
||||
// it for an older reader, and `why` in words — counts, the oldest message's age and its first reason —
|
||||
// never a bare false.
|
||||
|
||||
import { execFile } from "node:child_process";
|
||||
import { promisify } from "node:util";
|
||||
|
||||
const run = promisify(execFile);
|
||||
|
||||
/** How long a message may wait in the deferred queue before mail is said not to flow. */
|
||||
export const DEFERRED_BOUND_SECONDS = 30 * 60;
|
||||
|
||||
/** The public name resolved through postfix's resolver: gmail's mail exchanger, which mail needs. */
|
||||
export const PUBLIC_NAME = "gmail-smtp-in.l.google.com";
|
||||
|
||||
// The lookup postfix's own would make, through the resolver the container is given; a failure is said on one
|
||||
// line ("gaierror: [Errno -3] Try again" is what a SERVFAIL reads as), never as a traceback.
|
||||
const RESOLVE = [
|
||||
"import socket, sys",
|
||||
"try:",
|
||||
` socket.getaddrinfo(${JSON.stringify(PUBLIC_NAME)}, 25)`,
|
||||
"except Exception as e:",
|
||||
" sys.exit(type(e).__name__ + ': ' + str(e))",
|
||||
].join("\n");
|
||||
|
||||
/** Overdue mail to this many recipient domains or more is our side's fault, not one far server's. */
|
||||
export const SPREAD_DOMAINS = 3;
|
||||
|
||||
/**
|
||||
* What postfix writes when its own lookups fail, as on 2026-10-14 (issue 687): "Host or domain name not
|
||||
* found. Name service error for name=gmail.com type=MX: Host not found, try again", or "Temporary lookup
|
||||
* failure". A far server that is down reads otherwise ("Connection timed out", "Connection refused").
|
||||
*/
|
||||
export const LOCAL_LOOKUP_FAILURE =
|
||||
/Name service error|Temporary lookup failure|Host or domain name not found.*try again/is;
|
||||
|
||||
/** The domain of an address, lower-cased; "(no recipient)" when there is none. */
|
||||
function domainOf(address?: string): string {
|
||||
const at = address?.lastIndexOf("@") ?? -1;
|
||||
return address && at >= 0 ? address.slice(at + 1).toLowerCase() : "(no recipient)";
|
||||
}
|
||||
|
||||
/** Runs a command in a container: its stdout, or a rejection carrying stderr. */
|
||||
export type Exec = (container: string, command: string[]) => Promise<string>;
|
||||
|
||||
/** The health answer (mesh-sdk go/health): healthy, or unhealthy with why. */
|
||||
export interface HealthAnswer {
|
||||
state: "healthy" | "unhealthy";
|
||||
healthy: boolean;
|
||||
why: string;
|
||||
queue?: {
|
||||
messages: number;
|
||||
deferred: number;
|
||||
overdue: number;
|
||||
oldestDeferredSeconds?: number;
|
||||
overdueDomains?: string[];
|
||||
nameServiceFailures?: number;
|
||||
};
|
||||
}
|
||||
|
||||
/** One message as `postqueue -j` prints it, one JSON object a line (postfix 3.1 and later). */
|
||||
interface Queued {
|
||||
queue_name?: string;
|
||||
queue_id?: string;
|
||||
arrival_time?: number;
|
||||
recipients?: Array<{ address?: string; delay_reason?: string }>;
|
||||
}
|
||||
|
||||
/** docker exec, bounded: a hung container is an answer too. */
|
||||
export function dockerExec(timeoutMs = 10_000): Exec {
|
||||
return async (container, command) =>
|
||||
(await run("docker", ["exec", container, ...command], { timeout: timeoutMs })).stdout;
|
||||
}
|
||||
|
||||
/** What a failed exec said, on one line: its stderr when it has one, else its message. */
|
||||
function said(e: unknown): string {
|
||||
const err = e as { stderr?: string; message?: string; killed?: boolean; signal?: string };
|
||||
if (err?.killed || err?.signal === "SIGTERM") return "it did not answer in time";
|
||||
const text = (err?.stderr ?? "").trim() || (err?.message ?? String(e)).trim();
|
||||
return text.split("\n").map((l) => l.trim()).filter(Boolean)[0] ?? "it failed and said nothing";
|
||||
}
|
||||
|
||||
/** An age in words: "2 days 3 hours", "45 minutes". */
|
||||
export function age(seconds: number): string {
|
||||
const s = Math.max(0, Math.floor(seconds));
|
||||
const d = Math.floor(s / 86400), h = Math.floor((s % 86400) / 3600), m = Math.floor((s % 3600) / 60);
|
||||
const unit = (n: number, w: string) => `${n} ${w}${n === 1 ? "" : "s"}`;
|
||||
if (d > 0) return h > 0 ? `${unit(d, "day")} ${unit(h, "hour")}` : unit(d, "day");
|
||||
if (h > 0) return m > 0 ? `${unit(h, "hour")} ${unit(m, "minute")}` : unit(h, "hour");
|
||||
return unit(m, "minute");
|
||||
}
|
||||
|
||||
function parseQueue(output: string): Queued[] {
|
||||
const queued: Queued[] = [];
|
||||
for (const line of output.split("\n")) {
|
||||
const text = line.trim();
|
||||
if (!text.startsWith("{")) continue; // "Mail queue is empty" and the like
|
||||
queued.push(JSON.parse(text) as Queued);
|
||||
}
|
||||
return queued;
|
||||
}
|
||||
|
||||
/**
|
||||
* Judge whether mail flows. `now` is in seconds since the epoch. Every part is asked even when one
|
||||
* fails, so the answer says everything that is wrong at once.
|
||||
*/
|
||||
export async function mailFlows(
|
||||
exec: Exec,
|
||||
container: string,
|
||||
now: number = Date.now() / 1000,
|
||||
boundSeconds: number = DEFERRED_BOUND_SECONDS,
|
||||
): Promise<HealthAnswer> {
|
||||
const faults: string[] = [];
|
||||
const [status, queue, resolve] = await Promise.allSettled([
|
||||
exec(container, ["postfix", "status"]),
|
||||
exec(container, ["postqueue", "-j"]),
|
||||
exec(container, ["python3", "-c", RESOLVE]),
|
||||
]);
|
||||
|
||||
if (status.status === "rejected") {
|
||||
faults.push(`postfix in ${container} does not run: ${said(status.reason)}.`);
|
||||
}
|
||||
|
||||
let summary: HealthAnswer["queue"];
|
||||
const notes: string[] = [];
|
||||
if (queue.status === "rejected") {
|
||||
faults.push(`postfix's queue in ${container} could not be read: ${said(queue.reason)}.`);
|
||||
} else {
|
||||
let queued: Queued[] = [];
|
||||
try {
|
||||
queued = parseQueue(queue.value);
|
||||
} catch (e) {
|
||||
faults.push(`postfix's queue in ${container} printed a line that is not JSON: ${said(e)}.`);
|
||||
}
|
||||
const deferred = queued.filter((q) => q.queue_name === "deferred");
|
||||
const overdue = deferred
|
||||
.filter((q) => typeof q.arrival_time === "number" && now - q.arrival_time > boundSeconds)
|
||||
.sort((a, b) => (a.arrival_time ?? 0) - (b.arrival_time ?? 0));
|
||||
const oldest = deferred.reduce<number | undefined>(
|
||||
(o, q) => (typeof q.arrival_time === "number" && (o === undefined || q.arrival_time < o) ? q.arrival_time : o),
|
||||
undefined,
|
||||
);
|
||||
// Each overdue recipient, oldest message first: what our side is judged by, not one far host.
|
||||
const late = overdue.flatMap((q) =>
|
||||
(q.recipients?.length ? q.recipients : [{}]).map((r) => ({
|
||||
to: r.address,
|
||||
domain: domainOf(r.address),
|
||||
reason: r.delay_reason?.trim() || "postfix gave no reason",
|
||||
waited: now - (q.arrival_time ?? now),
|
||||
})),
|
||||
);
|
||||
const lookups = late.filter((r) => LOCAL_LOOKUP_FAILURE.test(r.reason));
|
||||
const domains = [...new Set(late.map((r) => r.domain))];
|
||||
summary = {
|
||||
messages: queued.length,
|
||||
deferred: deferred.length,
|
||||
overdue: overdue.length,
|
||||
...(oldest !== undefined ? { oldestDeferredSeconds: Math.max(0, Math.floor(now - oldest)) } : {}),
|
||||
...(domains.length > 0 ? { overdueDomains: domains } : {}),
|
||||
...(lookups.length > 0 ? { nameServiceFailures: lookups.length } : {}),
|
||||
};
|
||||
const one = (r: (typeof late)[number]) =>
|
||||
`the oldest, ${age(r.waited)} old${r.to ? ` to ${r.to}` : ""}, waits because: ${r.reason}`;
|
||||
const bound = age(boundSeconds);
|
||||
if (lookups.length > 0) {
|
||||
faults.push(
|
||||
`${lookups.length} deferred ${lookups.length === 1 ? "recipient has" : "recipients have"} waited longer ` +
|
||||
`than ${bound} on a name-service failure, which is this server's resolver; ${one(lookups[0])}.`,
|
||||
);
|
||||
} else if (domains.length >= SPREAD_DOMAINS) {
|
||||
faults.push(
|
||||
`${overdue.length} of ${deferred.length} deferred messages have waited longer than ${bound}, to ` +
|
||||
`${domains.length} domains (${domains.join(", ")}): more than one far server's fault; ${one(late[0])}.`,
|
||||
);
|
||||
} else if (late.length > 0) {
|
||||
notes.push(
|
||||
`${overdue.length} deferred ${overdue.length === 1 ? "message has" : "messages have"} waited longer than ` +
|
||||
`${bound}, only to ${domains.join(" and ")}, which reads as the far side's: ${one(late[0])}.`,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
if (resolve.status === "rejected") {
|
||||
faults.push(`${container} cannot resolve ${PUBLIC_NAME} through its resolver: ${said(resolve.reason)}.`);
|
||||
}
|
||||
|
||||
if (faults.length > 0) {
|
||||
const why = [`Mail does not flow.`, ...faults, ...notes].join(" ");
|
||||
return { state: "unhealthy", healthy: false, why, queue: summary };
|
||||
}
|
||||
const waiting = !summary || summary.deferred === 0
|
||||
? " The deferred queue is empty."
|
||||
: notes.length > 0
|
||||
? ` ${notes.join(" ")}`
|
||||
: ` ${summary.deferred} deferred, the oldest ${age(summary.oldestDeferredSeconds ?? 0)} old, within ${age(boundSeconds)}.`;
|
||||
return {
|
||||
state: "healthy",
|
||||
healthy: true,
|
||||
why: `Mail flows: postfix runs, ${PUBLIC_NAME} resolves.${waiting}`,
|
||||
queue: summary,
|
||||
};
|
||||
}
|
||||
@@ -5,6 +5,10 @@
|
||||
"policy": "record",
|
||||
"why": "people's mail: any change to how its containers are declared recreates them together in one send, and the mail is down for everyone until they are up again — a person chooses the moment (hq ADR 0242, issue 295)"
|
||||
},
|
||||
"unhealthy": {
|
||||
"severity": "urgent",
|
||||
"why": "while mailu is broken, mail is refused or stuck for everyone with a mailbox here (hq ADR 0355, issue 687)"
|
||||
},
|
||||
"capabilities": [
|
||||
"container-runtime"
|
||||
],
|
||||
@@ -56,6 +60,19 @@
|
||||
"api-token": "${dir:state}/api-token.secret"
|
||||
}
|
||||
},
|
||||
"tools": [
|
||||
"mailu_list_users",
|
||||
"mailu_create_user",
|
||||
"mailu_change_password",
|
||||
"mailu_delete_user",
|
||||
"mailu_list_aliases",
|
||||
"mailu_create_alias",
|
||||
"mailu_delete_alias",
|
||||
"mailu_list_domains",
|
||||
"mailu_read_mail",
|
||||
"mailu_search_mail",
|
||||
"mailu_health"
|
||||
],
|
||||
"emits": [
|
||||
"user.created",
|
||||
"user.deleted",
|
||||
@@ -371,7 +388,7 @@
|
||||
"id": "resolver",
|
||||
"type": "container",
|
||||
"name": "mailu-resolver",
|
||||
"image": "ghcr.io/mailu/unbound@sha256:3a0fdfb364a63f4f9259526e013c1ef40f5f14de3621ce1560804b3a5909584a",
|
||||
"image": "ghcr.io/mailu/unbound@sha256:2c037bc5c988b5c0ab7e1b6e6ffa762e14ba1e45c96281ac87f8b9be8eee8b6e",
|
||||
"health": {
|
||||
"kind": "runtime"
|
||||
},
|
||||
@@ -443,7 +460,12 @@
|
||||
"name": "mailu-smtp",
|
||||
"image": "ghcr.io/mailu/postfix@sha256:e2e49f39e53b80eac9e7a2f18d9df11edeb4914fd62dbba89b3155e8e034f62e",
|
||||
"health": {
|
||||
"kind": "runtime"
|
||||
"kind": "tool",
|
||||
"tool": "mailu_health",
|
||||
"interval": "60s",
|
||||
"timeout": "30s",
|
||||
"looks": 3,
|
||||
"grace": "120s"
|
||||
},
|
||||
"network": "mailu",
|
||||
"env-file": [
|
||||
@@ -560,7 +582,12 @@
|
||||
"name": "mailu-front",
|
||||
"image": "ghcr.io/mailu/nginx@sha256:36f98897cd1bc9d27628bbb4e04bdf60147af2ec7507d6da77f002c4f256896d",
|
||||
"health": {
|
||||
"kind": "runtime"
|
||||
"kind": "exec",
|
||||
"command": "curl -m3 -skfLo /dev/null http://127.0.0.1:10204/health && kill -0 $(cat /run/dovecot/master.pid) && python3 -c \"import smtplib; s = smtplib.SMTP('127.0.0.1', 25, timeout=5); s.ehlo('health'); s.quit()\" && openssl x509 -checkend 1209600 -noout -in /certs/letsencrypt/live/mailu/nginx-chain.pem",
|
||||
"interval": "60s",
|
||||
"timeout": "15s",
|
||||
"looks": 3,
|
||||
"grace": "120s"
|
||||
},
|
||||
"network": "mailu",
|
||||
"env-file": [
|
||||
@@ -637,6 +664,7 @@
|
||||
"MESH_MAILU_URL": "http://127.0.0.1:${port:8080}/api/v1",
|
||||
"MESH_MAILU_API_KEY_FILE": "${dir:state}/api-token.secret",
|
||||
"MESH_MAILU_IMAP_CONTAINER": "mailu-imap",
|
||||
"MESH_MAILU_SMTP_CONTAINER": "mailu-smtp",
|
||||
"MESH_MAILU_CONFIG_FILE": "${dir:mesh-state}/config.json",
|
||||
"MESH_RECEIVES": "${dir:grants}/mesh.json"
|
||||
}
|
||||
@@ -673,7 +701,7 @@
|
||||
"jails": [
|
||||
{
|
||||
"name": "mailu-front",
|
||||
"failregex": "^.*(?:imap|pop3|submission|managesieve)-login: .*\\(auth failed, \\d+ attempts(?: in \\d+ secs)?\\):.*rip=<HOST>(?:,|$)",
|
||||
"failregex": "^.*(?:imap|pop3|submission|managesieve)-login: .*\\(auth failed, \\d+ attempts(?: in \\d+ secs)?\\):.*rip=<HOST>(?:,|$)\n ^.*client login failed: \"AUTH not supported\" while in http auth state, client: <HOST>, server: \\S+:25,",
|
||||
"jail": "backend = systemd\njournalmatch = CONTAINER_NAME=mailu-front\nport = smtp,submission,submissions,imap,imaps,pop3,pop3s\nmaxretry = 3\nfindtime = 1d\nbantime = 1d"
|
||||
}
|
||||
]
|
||||
|
||||
@@ -0,0 +1,140 @@
|
||||
// Whether mail flows (novox/hq issue 690): the health tool is unhealthy, in words, when a message waits in
|
||||
// postfix's deferred queue longer than the bound, when postfix does not run, when a public name does not
|
||||
// resolve, and when the container cannot be reached — and healthy otherwise. Run against the compiled
|
||||
// module, the way the runtime loads it.
|
||||
|
||||
import { test } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
|
||||
import { mailFlows, DEFERRED_BOUND_SECONDS } from "../dist/health.js";
|
||||
|
||||
const NOW = 1_800_000_000;
|
||||
|
||||
type Answers = { status?: string | Error; queue?: string | Error; resolve?: string | Error };
|
||||
|
||||
/** A container that answers each command as told; an Error is a failed exec, with its stderr. */
|
||||
function container(a: Answers) {
|
||||
const asked: string[][] = [];
|
||||
const exec = async (_name: string, command: string[]) => {
|
||||
asked.push(command);
|
||||
const answer = command[0] === "postfix" ? a.status ?? "" : command[0] === "postqueue" ? a.queue ?? "" : a.resolve ?? "";
|
||||
if (answer instanceof Error) throw answer;
|
||||
return answer;
|
||||
};
|
||||
return { exec, asked };
|
||||
}
|
||||
|
||||
function failed(stderr: string): Error {
|
||||
return Object.assign(new Error("Command failed: docker exec"), { stderr });
|
||||
}
|
||||
|
||||
function deferred(id: string, ageSeconds: number, reason: string, to = "friend@example.com"): string {
|
||||
return JSON.stringify({
|
||||
queue_name: "deferred",
|
||||
queue_id: id,
|
||||
arrival_time: NOW - ageSeconds,
|
||||
message_size: 1234,
|
||||
sender: "someone@example.org",
|
||||
recipients: [{ address: to, delay_reason: reason }],
|
||||
});
|
||||
}
|
||||
|
||||
test("an empty queue is healthy, and says so", async () => {
|
||||
const c = container({ queue: "" });
|
||||
const a = await mailFlows(c.exec, "mailu-smtp", NOW);
|
||||
assert.equal(a.state, "healthy");
|
||||
assert.equal(a.healthy, true);
|
||||
assert.match(a.why, /deferred queue is empty/);
|
||||
assert.deepEqual(a.queue, { messages: 0, deferred: 0, overdue: 0 });
|
||||
assert.equal(c.asked.length, 3, "postfix, its queue and a lookup were each asked");
|
||||
});
|
||||
|
||||
test("a recipient overdue on a name-service failure is unhealthy, with counts, its age and its reason", async () => {
|
||||
const reason = "Host or domain name not found. Name service error for name=gmail.com type=MX: Host not found, try again";
|
||||
const queue = [
|
||||
deferred("AAA111", 3 * 86400 + 2 * 3600, reason),
|
||||
deferred("BBB222", 5 * 60, "connect to mx.example.net[192.0.2.1]:25: Connection timed out"),
|
||||
JSON.stringify({ queue_name: "active", queue_id: "CCC333", arrival_time: NOW - 10, recipients: [] }),
|
||||
].join("\n");
|
||||
const a = await mailFlows(container({ queue }).exec, "mailu-smtp", NOW);
|
||||
assert.equal(a.state, "unhealthy");
|
||||
assert.equal(a.healthy, false);
|
||||
assert.match(a.why, /^Mail does not flow\./);
|
||||
assert.match(a.why, /1 deferred recipient has waited longer than 30 minutes on a name-service failure/);
|
||||
assert.match(a.why, /3 days 2 hours old to friend@example\.com/);
|
||||
assert.ok(a.why.includes(reason), "the reason is said");
|
||||
assert.deepEqual(a.queue, {
|
||||
messages: 3, deferred: 2, overdue: 1, oldestDeferredSeconds: 3 * 86400 + 2 * 3600,
|
||||
overdueDomains: ["example.com"], nameServiceFailures: 1,
|
||||
});
|
||||
});
|
||||
|
||||
test("one dead far domain overdue is healthy, and said", async () => {
|
||||
const queue = [
|
||||
deferred("AAA111", 2 * 86400, "connect to mx.dead.example[192.0.2.9]:25: Connection timed out", "a@dead.example"),
|
||||
deferred("BBB222", 3600, "connect to mx.dead.example[192.0.2.9]:25: Connection timed out", "b@dead.example"),
|
||||
].join("\n");
|
||||
const a = await mailFlows(container({ queue }).exec, "mailu-smtp", NOW);
|
||||
assert.equal(a.state, "healthy");
|
||||
assert.equal(a.healthy, true);
|
||||
assert.match(a.why, /2 deferred messages have waited longer than 30 minutes, only to dead\.example, which reads as the far side's/);
|
||||
assert.match(a.why, /2 days old to a@dead\.example, waits because: connect to mx\.dead\.example/);
|
||||
assert.deepEqual(a.queue?.overdueDomains, ["dead.example"]);
|
||||
});
|
||||
|
||||
test("overdue mail to three domains is unhealthy, whatever the reason", async () => {
|
||||
const timedOut = "connect to mx[192.0.2.1]:25: Connection timed out";
|
||||
const queue = [
|
||||
deferred("AAA111", 7200, timedOut, "a@one.example"),
|
||||
deferred("BBB222", 3600, timedOut, "b@two.example"),
|
||||
deferred("CCC333", 3600, timedOut, "c@three.example"),
|
||||
].join("\n");
|
||||
const a = await mailFlows(container({ queue }).exec, "mailu-smtp", NOW);
|
||||
assert.equal(a.state, "unhealthy");
|
||||
assert.match(a.why, /3 of 3 deferred messages have waited longer than 30 minutes, to 3 domains \(one\.example, two\.example, three\.example\)/);
|
||||
assert.match(a.why, /the oldest, 2 hours old to a@one\.example/);
|
||||
});
|
||||
|
||||
test("a deferred message younger than the bound is healthy, and is said", async () => {
|
||||
const queue = deferred("BBB222", DEFERRED_BOUND_SECONDS - 60, "connect to mx.example.net: Connection timed out");
|
||||
const a = await mailFlows(container({ queue }).exec, "mailu-smtp", NOW);
|
||||
assert.equal(a.state, "healthy");
|
||||
assert.equal(a.healthy, true);
|
||||
assert.match(a.why, /1 deferred, the oldest 29 minutes old, within 30 minutes/);
|
||||
});
|
||||
|
||||
test("a container that cannot be reached is unhealthy, and says what docker said", async () => {
|
||||
const gone = failed("Error response from daemon: No such container: mailu-smtp\n");
|
||||
const a = await mailFlows(container({ status: gone, queue: gone, resolve: gone }).exec, "mailu-smtp", NOW);
|
||||
assert.equal(a.state, "unhealthy");
|
||||
assert.equal(a.healthy, false);
|
||||
assert.match(a.why, /postfix in mailu-smtp does not run: Error response from daemon: No such container: mailu-smtp\./);
|
||||
assert.match(a.why, /postfix's queue in mailu-smtp could not be read: Error response from daemon: No such container/);
|
||||
assert.equal(a.queue, undefined);
|
||||
});
|
||||
|
||||
test("a name that does not resolve is unhealthy, though the queue is empty", async () => {
|
||||
const a = await mailFlows(
|
||||
container({ queue: "", resolve: failed("gaierror: [Errno -3] Try again\n") }).exec,
|
||||
"mailu-smtp",
|
||||
NOW,
|
||||
);
|
||||
assert.equal(a.state, "unhealthy");
|
||||
assert.match(a.why, /mailu-smtp cannot resolve gmail-smtp-in\.l\.google\.com through its resolver: gaierror: \[Errno -3\] Try again\./);
|
||||
});
|
||||
|
||||
test("a container that does not answer in time is said so", async () => {
|
||||
const hung = Object.assign(new Error("Command failed"), { killed: true, signal: "SIGTERM" });
|
||||
const a = await mailFlows(container({ queue: hung }).exec, "mailu-smtp", NOW);
|
||||
assert.equal(a.state, "unhealthy");
|
||||
assert.match(a.why, /postfix's queue in mailu-smtp could not be read: it did not answer in time\./);
|
||||
});
|
||||
|
||||
test("the health tool is served without the admin API, on the smtp container it is told", async () => {
|
||||
const { collectTools } = await import("@novox/mesh-sdk/tools");
|
||||
await import("../dist/tools/index.js");
|
||||
const mailu = collectTools({ MESH_MAILU_SMTP_CONTAINER: "mailu-smtp" }).find((m) => m.module === "mailu");
|
||||
const names = (mailu?.tools ?? []).map((t) => t.name);
|
||||
assert.deepEqual(names, ["mailu_health"]);
|
||||
assert.match(mailu!.tools[0].description, /inside mailu-smtp/);
|
||||
});
|
||||
@@ -4,6 +4,27 @@
|
||||
|
||||
import { registerModuleTools, type ToolDefinition } from "@novox/mesh-sdk/tools";
|
||||
import { MailuClient } from "../client.js";
|
||||
import { dockerExec, mailFlows, DEFERRED_BOUND_SECONDS, PUBLIC_NAME, SPREAD_DOMAINS } from "../health.js";
|
||||
|
||||
/**
|
||||
* Whether mail flows (novox/hq ADR 0240, issue 690): the tool the node-engine asks as the smtp container's
|
||||
* check. It needs no admin API, only the postfix container, so it is served even when the API is not
|
||||
* configured — a check that vanished with the API would say unhealthy for the wrong reason.
|
||||
*/
|
||||
export function getHealthTool(env: NodeJS.ProcessEnv): ToolDefinition {
|
||||
const container = env.MESH_MAILU_SMTP_CONTAINER || "mailu-smtp";
|
||||
return {
|
||||
name: "mailu_health",
|
||||
description:
|
||||
`Whether mail flows through mailu, asked inside ${container}: postfix runs; no recipient has waited ` +
|
||||
`deferred longer than ${DEFERRED_BOUND_SECONDS / 60} minutes on a name-service failure here, and overdue ` +
|
||||
`deferred mail does not reach ${SPREAD_DOMAINS} or more domains (one or two far domains are said, not ` +
|
||||
`unhealthy); and ${PUBLIC_NAME} resolves through the resolver postfix uses. Says counts, domains, the ` +
|
||||
"oldest message's age and its reason (novox/hq ADR 0240, issue 690).",
|
||||
input: {},
|
||||
run: async () => mailFlows(dockerExec(), container),
|
||||
};
|
||||
}
|
||||
|
||||
export function getMailuTools(mailu: MailuClient): ToolDefinition[] {
|
||||
return [
|
||||
@@ -143,12 +164,14 @@ export function getMailuTools(mailu: MailuClient): ToolDefinition[] {
|
||||
];
|
||||
}
|
||||
|
||||
// The tools exist only when the admin API is configured; without it, mailu contributes none rather
|
||||
// than failing the whole runtime.
|
||||
// The admin tools exist only when the admin API is configured; without it, mailu contributes only its
|
||||
// health tool rather than failing the whole runtime.
|
||||
registerModuleTools("mailu", (env) => {
|
||||
let tools: ToolDefinition[] = [];
|
||||
try {
|
||||
return getMailuTools(MailuClient.fromEnv(env));
|
||||
tools = getMailuTools(MailuClient.fromEnv(env));
|
||||
} catch {
|
||||
return [];
|
||||
tools = [];
|
||||
}
|
||||
return [...tools, getHealthTool(env)];
|
||||
});
|
||||
|
||||
@@ -8,5 +8,5 @@
|
||||
"skipLibCheck": true,
|
||||
"noEmit": true
|
||||
},
|
||||
"include": ["client.ts", "index.ts", "tools/index.ts"]
|
||||
"include": ["client.ts", "health.ts", "index.ts", "tools/index.ts"]
|
||||
}
|
||||
|
||||
@@ -0,0 +1,96 @@
|
||||
// What the catalogue makes of a build outcome it hears (novox/hq issue 712).
|
||||
//
|
||||
// Kept apart from index.ts, which subscribes at its top level, so the decision can be tested without a bus.
|
||||
|
||||
import type { Made } from "./store.js";
|
||||
|
||||
/** What the build seat says when it has built something, and what the control plane replays. */
|
||||
export interface Built {
|
||||
module?: string;
|
||||
commit?: string;
|
||||
repository?: string;
|
||||
path?: string;
|
||||
ref?: string;
|
||||
manifest?: unknown;
|
||||
/** What this build published, each pinned as anything else would name it. */
|
||||
made?: Made[];
|
||||
/**
|
||||
* Every artifact this was built on top of, so the edge is derived rather than declared.
|
||||
*
|
||||
* References, not module names: the builder sees a pinned image and cannot see which module
|
||||
* produced it. Turning that into an edge between module-versions is this module's job.
|
||||
*/
|
||||
against?: string[];
|
||||
/**
|
||||
* This is history, not news — the mesh re-announcing a build this catalogue was not there for.
|
||||
*
|
||||
* Registered exactly as any other, and announced as nothing. A module that moved months ago is
|
||||
* not something anything should act on now: emitting `upgraded` would have the control plane
|
||||
* decide about a rollout, and `rebuild-needed` would ask for builds of things that are already
|
||||
* current.
|
||||
*/
|
||||
replay?: boolean;
|
||||
/** Why the build failed; a failed build made no module-version. */
|
||||
failed?: string;
|
||||
/** A dry run is looked at, never taken in (novox/hq issue 240). */
|
||||
"dry-run"?: boolean;
|
||||
/** A pull request's merge check or a branch tried before one (to-be 45 §9, issue 686): nothing merged. */
|
||||
"check-outcome"?: unknown;
|
||||
check?: unknown;
|
||||
/** The repository's default branch as the build seat read the forge at the build (ADR 0238); empty from a seat older than the rule. */
|
||||
trunk?: string;
|
||||
/** Whether the commit is on `trunk`. */
|
||||
"on-trunk"?: boolean;
|
||||
/** The branches the commit is on. */
|
||||
branches?: string[];
|
||||
}
|
||||
|
||||
/** The events a build outcome reaches this module on: the build seat's, as it happens, and the control plane's replay. */
|
||||
export const BUILD_EVENTS = [
|
||||
// **The build seat that builds now** (novox/hq ADR 0190). Until issue 712 the catalogue heard only the
|
||||
// retired seat below, so every build after the handover reached the graph only through the replay this
|
||||
// module asks for when it starts: a merge built and pushed stayed out of the catalogue until its next start.
|
||||
"node-build-agent.built",
|
||||
// The retired build role, while a machine still serves it (ADR 0190's handover). Goes with the seat row.
|
||||
"mesh-build-machine.built",
|
||||
// What the mesh already held, when this module asks what it missed (novox/hq ADR 0134).
|
||||
"mesh-controller.built-before",
|
||||
] as const;
|
||||
|
||||
/**
|
||||
* Whether a build outcome is a module-version to place in the graph, and why not when it is not.
|
||||
*
|
||||
* It mirrors two of the rules the controller keeps before it registers a build (mesh-controller
|
||||
* cmd/mesh-controller/main.go `builds.Built`, build.go `publishable`): a merge check, a try and a dry run are
|
||||
* never published, and **only a commit on its repository's trunk is** (ADR 0238) — a branch built through
|
||||
* the `build` verb is checked, never a module's version. Where the seat names no trunk (one older than the
|
||||
* rule) it is placed, as the controller lets it through. A failure made nothing and is passed over too.
|
||||
*
|
||||
* Not mirrored, because the catalogue cannot see what they read: the branch a module follows when it is not
|
||||
* the default one (the controller's `follows`; such a module's builds off the default branch are passed over
|
||||
* here and reach the graph by the replay), ADR 0266's rule that a module registers only from the repository
|
||||
* it is built from, a superseded request, a build in the scratch namespace, one that failed its gate, and a
|
||||
* build whose source is unchanged. Each needs the controller's records. This is safe for what the mesh
|
||||
* sends, which is chosen from the controller's own module table and never from this graph; that the graph
|
||||
* can still hold a build the controller refused under those rules is a follow-up (hq issue 712).
|
||||
*/
|
||||
export function placeable(body: Built):
|
||||
| { placed: "yes"; module: string; commit: string }
|
||||
| { placed: "no"; why: string; fault: boolean } {
|
||||
if (body["check-outcome"] != null || body.check != null) {
|
||||
return { placed: "no", why: "a merge check or a try: nothing of it merged", fault: false };
|
||||
}
|
||||
if (body["dry-run"]) {
|
||||
return { placed: "no", why: "a dry run is looked at, never taken in", fault: false };
|
||||
}
|
||||
if (body.failed) {
|
||||
return { placed: "no", why: "a failed build made no module-version", fault: false };
|
||||
}
|
||||
if (body.trunk && !body["on-trunk"] && !(body.branches ?? []).includes(body.trunk)) {
|
||||
return { placed: "no", why: `the commit is not on its repository's trunk ${body.trunk}: checked, never published (ADR 0238)`, fault: false };
|
||||
}
|
||||
if (!body.module || !body.commit) {
|
||||
return { placed: "no", why: "it named no module or no commit", fault: true };
|
||||
}
|
||||
return { placed: "yes", module: body.module, commit: body.commit };
|
||||
}
|
||||
@@ -10,7 +10,8 @@
|
||||
// diamond need no special handling, and nothing holds a plan.
|
||||
|
||||
import { on, emit } from "@novox/mesh-sdk/events";
|
||||
import { Graph, type Made } from "./store.js";
|
||||
import { Graph } from "./store.js";
|
||||
import { BUILD_EVENTS, placeable, type Built } from "./heard.js";
|
||||
|
||||
const graph = Graph.fromEnv();
|
||||
|
||||
@@ -21,54 +22,29 @@ const graph = Graph.fromEnv();
|
||||
// would block the very apply that brings the overlay up — stopped being true when a step's failure
|
||||
// became this module's business and not the machine's (ADR 0136).
|
||||
|
||||
/** What the builder says when it has built something. */
|
||||
interface Built {
|
||||
module?: string;
|
||||
commit?: string;
|
||||
repository?: string;
|
||||
path?: string;
|
||||
ref?: string;
|
||||
manifest?: unknown;
|
||||
/** What this build published, each pinned as anything else would name it. */
|
||||
made?: Made[];
|
||||
/**
|
||||
* Every artifact this was built on top of, so the edge is derived rather than declared.
|
||||
*
|
||||
* References, not module names: the builder sees a pinned image and cannot see which module
|
||||
* produced it. Turning that into an edge between module-versions is this module's job.
|
||||
*/
|
||||
against?: string[];
|
||||
/**
|
||||
* This is history, not news — the mesh re-announcing a build this catalogue was not there for.
|
||||
*
|
||||
* Registered exactly as any other, and announced as nothing. A module that moved months ago is
|
||||
* not something anything should act on now: emitting `upgraded` would have the control plane
|
||||
* decide about a rollout, and `rebuild-needed` would ask for builds of things that are already
|
||||
* current.
|
||||
*/
|
||||
replay?: boolean;
|
||||
}
|
||||
|
||||
/**
|
||||
* What a build means for the graph, wherever it came from.
|
||||
*
|
||||
* Two emitters say the same thing and neither is a mistake: the build machine says it as it happens,
|
||||
* and the control plane says what it already held when this module asks what it missed
|
||||
* (novox/hq ADR 0134). A replay is marked as one in its body, so nothing acts on a module that moved
|
||||
* months ago — see `replay` above.
|
||||
* months ago — see `replay` in heard.ts.
|
||||
*/
|
||||
const placeTheBuild = async (event: { body: unknown }): Promise<void> => {
|
||||
const body = (event.body ?? {}) as Built;
|
||||
if (!body.module || !body.commit) {
|
||||
// Said rather than dropped: a build that announced itself without saying what it built is a
|
||||
// fault in the builder, and a silent discard here would make it look like a missing event.
|
||||
console.error("mesh-catalog: a build event named no module or no commit; ignored", body);
|
||||
const placing = placeable(body);
|
||||
if (placing.placed === "no") {
|
||||
// A check, a try, a dry run and a failure are the build seat's ordinary outcomes: passed over. One
|
||||
// that names no module or commit is a fault in the builder, said rather than dropped, so it does
|
||||
// not look like a missing event.
|
||||
if (placing.fault) console.error(`mesh-catalog: a build event was not placed: ${placing.why}`, body);
|
||||
return;
|
||||
}
|
||||
const { module, commit } = placing;
|
||||
|
||||
const { upgraded, previous } = await graph.register({
|
||||
module: body.module,
|
||||
commit: body.commit,
|
||||
module,
|
||||
commit,
|
||||
repository: body.repository ?? "",
|
||||
path: body.path ?? "",
|
||||
ref: body.ref ?? "",
|
||||
@@ -80,7 +56,7 @@ const placeTheBuild = async (event: { body: unknown }): Promise<void> => {
|
||||
if (body.replay) return;
|
||||
|
||||
await emit("registered", {
|
||||
module: body.module, commit: body.commit, upgraded,
|
||||
module, commit, upgraded,
|
||||
});
|
||||
|
||||
// **A rebuild that changed nothing is not an upgrade.** Announcing it would ripple outward
|
||||
@@ -88,7 +64,7 @@ const placeTheBuild = async (event: { body: unknown }): Promise<void> => {
|
||||
if (!upgraded) return;
|
||||
|
||||
await emit("upgraded", {
|
||||
module: body.module, commit: body.commit, previous,
|
||||
module, commit, previous,
|
||||
});
|
||||
|
||||
// What can be built now — stale, and waiting on nothing that is itself stale.
|
||||
@@ -101,9 +77,9 @@ const placeTheBuild = async (event: { body: unknown }): Promise<void> => {
|
||||
}
|
||||
};
|
||||
|
||||
// As it happens, and what the mesh already held when this module asked what it missed.
|
||||
await on("mesh-build-machine.built", placeTheBuild);
|
||||
await on("mesh-controller.built-before", placeTheBuild);
|
||||
// As it happens — from the build seat that builds now, and the retired one while it still answers — and
|
||||
// what the mesh already held when this module asked what it missed (novox/hq issue 712).
|
||||
for (const heard of BUILD_EVENTS) await on(heard, placeTheBuild);
|
||||
|
||||
// **And ask for what was built before this catalogue existed** (novox/hq 04-ISSUES/050).
|
||||
//
|
||||
|
||||
@@ -26,6 +26,7 @@
|
||||
"postgres-database": "${dir:state}/database.secret"
|
||||
},
|
||||
"consumes": [
|
||||
"node-build-agent.built",
|
||||
"mesh-build-machine.built",
|
||||
"mesh-controller.built-before"
|
||||
],
|
||||
|
||||
@@ -0,0 +1,72 @@
|
||||
import { test } from "node:test";
|
||||
import assert from "node:assert/strict";
|
||||
import { readFile } from "node:fs/promises";
|
||||
|
||||
import { BUILD_EVENTS, placeable } from "../heard.js";
|
||||
|
||||
// A walk's build as the build seat says it (mesh-controller's link.BuildResult), here mailu's of novox/hq issue 712.
|
||||
const walkBuild = {
|
||||
id: "build-1791997333800041716",
|
||||
repository: "http://novox.internal:20000/novox/mesh-catalog.git",
|
||||
path: "modules/mailu",
|
||||
ref: "main",
|
||||
on: "shanks",
|
||||
trunk: "main",
|
||||
"on-trunk": true,
|
||||
branches: ["main"],
|
||||
module: "mailu",
|
||||
commit: "e1c8965ddbf1cf9af9cf1eed7a72ae9ffa6d5a87",
|
||||
manifest: { module: "mailu", unhealthy: { severity: "urgent", why: "mail stops" } },
|
||||
made: [{ name: "code", kind: "bundle", reference: "artifact-store://mailu/code/blobs/sha256:d041" }],
|
||||
};
|
||||
|
||||
test("the catalogue hears the build seat that builds now, not only the retired one (issue 712)", async () => {
|
||||
assert.ok(BUILD_EVENTS.includes("node-build-agent.built"));
|
||||
assert.ok(BUILD_EVENTS.includes("mesh-controller.built-before"));
|
||||
// Subscribing is not enough: the mesh grants and routes only what the manifest consumes.
|
||||
const manifest = JSON.parse(await readFile(new URL("../module.json", import.meta.url), "utf8"));
|
||||
for (const heard of BUILD_EVENTS) assert.ok(manifest.consumes.includes(heard), `${heard} is not consumed`);
|
||||
});
|
||||
|
||||
test("a walk's build is placed, under its module and commit", () => {
|
||||
assert.deepEqual(placeable(walkBuild), { placed: "yes", module: "mailu", commit: walkBuild.commit });
|
||||
// A walk that took the check's build of the same key says so, and is placed all the same (ADR 0350 §2).
|
||||
assert.equal(placeable({ ...walkBuild, reused: "the check's build" } as never).placed, "yes");
|
||||
});
|
||||
|
||||
test("a merge check, a try, a dry run and a failure are passed over without a fault", () => {
|
||||
for (const [body, why] of [
|
||||
[{ ...walkBuild, "check-outcome": { verdict: "passed" } }, "merge check"],
|
||||
[{ ...walkBuild, check: { try: true } }, "merge check or a try"],
|
||||
[{ ...walkBuild, "dry-run": true }, "dry run"],
|
||||
[{ ...walkBuild, failed: "exit status 1" }, "failed"],
|
||||
] as const) {
|
||||
const placing = placeable(body);
|
||||
assert.equal(placing.placed, "no");
|
||||
if (placing.placed === "no") {
|
||||
assert.match(placing.why, new RegExp(why));
|
||||
assert.equal(placing.fault, false);
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
test("an outcome that names no module or commit is said as the builder's fault", () => {
|
||||
const placing = placeable({ repository: walkBuild.repository, commit: walkBuild.commit });
|
||||
assert.equal(placing.placed, "no");
|
||||
if (placing.placed === "no") assert.equal(placing.fault, true);
|
||||
});
|
||||
|
||||
test("a branch built through the build verb is passed over; a commit on the trunk, or from a seat that names none, is placed (ADR 0238)", () => {
|
||||
const branch = { ...walkBuild, ref: "feature", "on-trunk": false, branches: ["feature"] };
|
||||
const placing = placeable(branch);
|
||||
assert.equal(placing.placed, "no");
|
||||
if (placing.placed === "no") {
|
||||
assert.match(placing.why, /not on its repository's trunk main/);
|
||||
assert.equal(placing.fault, false);
|
||||
}
|
||||
// On the trunk by its branches although the seat did not set on-trunk.
|
||||
assert.equal(placeable({ ...branch, branches: ["feature", "main"] }).placed, "yes");
|
||||
// A seat older than the rule says no trunk: placed, as the controller lets it through.
|
||||
const { trunk, "on-trunk": _on, branches, ...older } = walkBuild;
|
||||
assert.equal(placeable(older).placed, "yes");
|
||||
});
|
||||
@@ -11,6 +11,7 @@
|
||||
"include": [
|
||||
"pg.d.ts",
|
||||
"store.ts",
|
||||
"heard.ts",
|
||||
"index.ts",
|
||||
"tools/index.ts",
|
||||
"prepare/index.ts"
|
||||
|
||||
@@ -396,6 +396,9 @@ type fakeForge struct {
|
||||
// open is what OpenPulls answers; openDown a forge that cannot say.
|
||||
open []OpenPull
|
||||
openDown bool
|
||||
// merges, comments and unlabels are what was asked of the forge for ready marks (novox/hq issue 722).
|
||||
merges, comments, unlabels []string
|
||||
refuse error
|
||||
}
|
||||
|
||||
func (f *fakeForge) OpenPulls() ([]OpenPull, error) {
|
||||
@@ -649,3 +652,25 @@ func aWalk(id, repo, commit string, waits bool) Walk {
|
||||
}
|
||||
return w
|
||||
}
|
||||
|
||||
// Merge, Comment and Unlabel record what was asked (novox/hq issue 722); Merge answers refuse when set.
|
||||
func (f *fakeForge) Merge(owner, repo string, number int, head string) error {
|
||||
f.mu.Lock()
|
||||
defer f.mu.Unlock()
|
||||
f.merges = append(f.merges, fmt.Sprintf("%s/%s#%d@%s", owner, repo, number, head))
|
||||
return f.refuse
|
||||
}
|
||||
|
||||
func (f *fakeForge) Comment(owner, repo string, number int, body string) error {
|
||||
f.mu.Lock()
|
||||
defer f.mu.Unlock()
|
||||
f.comments = append(f.comments, fmt.Sprintf("%s/%s#%d: %s", owner, repo, number, body))
|
||||
return nil
|
||||
}
|
||||
|
||||
func (f *fakeForge) Unlabel(owner, repo string, number, label int) error {
|
||||
f.mu.Lock()
|
||||
defer f.mu.Unlock()
|
||||
f.unlabels = append(f.unlabels, fmt.Sprintf("%s/%s#%d-%d", owner, repo, number, label))
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -69,6 +69,8 @@ type Holder struct {
|
||||
leaveRefused map[string]string
|
||||
// tried counts the owed effects Flush tried since this owner started, by how each ended (novox/hq issue 407).
|
||||
tried owedTries
|
||||
// marks are the open pull requests read with a ready mark, by owner/repo#number (novox/hq issue 722, ready.go).
|
||||
marks map[string]*marked
|
||||
}
|
||||
|
||||
// owedTries is how many owed effects were tried since this owner started, and when the last was: three numbers
|
||||
@@ -120,6 +122,7 @@ func (h *Holder) init() {
|
||||
h.askTried = map[string]time.Time{}
|
||||
h.walkAsked = map[string]time.Time{}
|
||||
h.unchecked = map[string]unchecked{}
|
||||
h.marks = map[string]*marked{}
|
||||
h.walks = map[string]seenWalk{}
|
||||
h.orphans = map[string]time.Time{}
|
||||
h.asking = map[string]bool{}
|
||||
@@ -996,6 +999,12 @@ func (h *Holder) Tick() {
|
||||
for _, ask := range h.leaveStopped() {
|
||||
ask()
|
||||
}
|
||||
h.mu.Lock()
|
||||
asks := h.readyAsks(h.Now())
|
||||
h.mu.Unlock()
|
||||
for _, ask := range asks {
|
||||
ask()
|
||||
}
|
||||
}
|
||||
|
||||
// plan works out, under the lock, what to ask; each ask applies its own answer.
|
||||
|
||||
@@ -76,8 +76,9 @@ func run(h *Holder, l *listening) {
|
||||
logf("[mesh-delivery] the controller's walks cannot be read: %v", err)
|
||||
}
|
||||
}
|
||||
// Every open pull request, from the forge itself, every five minutes (novox/hq issue 347).
|
||||
if now.Sub(looked) >= 5*time.Minute {
|
||||
// Every open pull request, from the forge itself, every minute (novox/hq issues 347, 722): what says a
|
||||
// head nobody checks, and the ready marks a merge is asked on.
|
||||
if now.Sub(looked) >= time.Minute {
|
||||
looked = now
|
||||
h.SeeOpenPulls()
|
||||
}
|
||||
|
||||
@@ -65,7 +65,9 @@ func TestItClaimsTheDeliverySeatAndFollowsWhatItHandles(t *testing.T) {
|
||||
want = append(want, "seat:"+ControllerSeat+"."+v)
|
||||
}
|
||||
want = append(want, "gitea.gitea_note_append", "gitea.gitea_delivery_view", "gitea.gitea_commit_status",
|
||||
"gitea.gitea_commit_statuses", "gitea.gitea_contains", "gitea.gitea_open_pulls")
|
||||
"gitea.gitea_commit_statuses", "gitea.gitea_contains", "gitea.gitea_open_pulls",
|
||||
// The merge on a ready mark (novox/hq issue 722): the merge tool, a comment, a label taken off.
|
||||
"gitea.gitea_merge_pull_request", "gitea.gitea_add_comment", "gitea.gitea_api")
|
||||
if !reflect.DeepEqual(m.Invokes, want) {
|
||||
t.Fatalf("invokes %v, wanted %v", m.Invokes, want)
|
||||
}
|
||||
|
||||
@@ -110,6 +110,9 @@ type Delivery struct {
|
||||
LetGo time.Time `json:"let_go"`
|
||||
LetGoWhy string `json:"let_go_why,omitempty"`
|
||||
|
||||
// Ready is what this owner did with its pull request's ready mark (novox/hq issue 722, ready.go).
|
||||
Ready *ReadyRun `json:"ready,omitempty"`
|
||||
|
||||
Transitions []Transition `json:"transitions,omitempty"`
|
||||
// Owed are the forge's and the bus's effects of its transitions not yet done: said only after the
|
||||
// delivery is kept, retried until done.
|
||||
|
||||
@@ -91,6 +91,13 @@ type Forge interface {
|
||||
// OpenPulls is every open pull request, with what its base requires and what its head has (novox/hq issue
|
||||
// 347). Reads only.
|
||||
OpenPulls() ([]OpenPull, error)
|
||||
// Merge asks the forge's merge tool to merge a pull request at the head named (gitea_merge_pull_request, novox/hq
|
||||
// issue 722): the one path every merge takes. Its refusal is the error, in its words.
|
||||
Merge(owner, repo string, number int, head string) error
|
||||
// Comment adds a comment to a pull request.
|
||||
Comment(owner, repo string, number int, body string) error
|
||||
// Unlabel takes a label off a pull request, by the label's id.
|
||||
Unlabel(owner, repo string, number, label int) error
|
||||
}
|
||||
|
||||
// ForgeChecks is what the forge says of a commit's checks (the gitea module's gitea_commit_statuses).
|
||||
@@ -392,6 +399,19 @@ func (f toolForge) Statuses(owner, repo string, number int, commit, base string)
|
||||
return &c, nil
|
||||
}
|
||||
|
||||
func (f toolForge) Merge(owner, repo string, number int, head string) error {
|
||||
return f.tool("gitea_merge_pull_request", map[string]any{"owner": owner, "repo": repo, "number": number, "head": head})
|
||||
}
|
||||
|
||||
func (f toolForge) Comment(owner, repo string, number int, body string) error {
|
||||
return f.tool("gitea_add_comment", map[string]any{"owner": owner, "repo": repo, "number": number, "body": body})
|
||||
}
|
||||
|
||||
func (f toolForge) Unlabel(owner, repo string, number, label int) error {
|
||||
return f.tool("gitea_api", map[string]any{"method": "DELETE",
|
||||
"path": fmt.Sprintf("/repos/%s/%s/issues/%d/labels/%d", owner, repo, number, label)})
|
||||
}
|
||||
|
||||
func (f toolForge) OpenPulls() ([]OpenPull, error) {
|
||||
raw, err := f.ask("gitea.gitea_open_pulls", map[string]any{})
|
||||
if err != nil {
|
||||
|
||||
@@ -0,0 +1,323 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"strings"
|
||||
"time"
|
||||
)
|
||||
|
||||
// Merge on ready (novox/hq issue 722).
|
||||
//
|
||||
// The operator, 2026-10-14: "the reviewer task should merge the request or mark the MR as ready to merge in any case".
|
||||
// Before, a reviewed pull request with green checks waited until a session called the forge's merge tool, and again
|
||||
// after every check the tool asked because the trunk had moved. Now the independent reviewer marks the pull request
|
||||
// ready at the head it approved — the forge label `mesh/ready` and a comment "ready at <full head sha>" (approving
|
||||
// through the forge is the operator's) — and this owner merges it, through the forge's own merge tool
|
||||
// (gitea_merge_pull_request), the one path every merge takes:
|
||||
//
|
||||
// - only at the head the mark names, and only while that is the pull request's head: a push after the mark clears
|
||||
// it — the label taken off, and said on the pull request — and the new head needs a mark of its own;
|
||||
// - only when its delivery is ready here: its check passed against its trunk's head. A verdict out of date is judged
|
||||
// again by the merge tool, which asks the check against the trunk's head itself (novox/hq ADR 0323 §5); the merge
|
||||
// is asked again once a minute, and lands on the passing verdict;
|
||||
// - a group member only at its turn in the group's order, and only once the group's composed check passed for its
|
||||
// members' heads as they are;
|
||||
// - a check that failed merges nothing: it is said once on the pull request, and as a stalled line, which the
|
||||
// controller raises as the condition `delivery.<id>.stalled`. So is a mark the merge tool refused for an hour.
|
||||
//
|
||||
// What this owner does with a mark is kept on the delivery (Ready), said in its log, and the merge's transitions name
|
||||
// it as their author.
|
||||
|
||||
// ReadyMark is a pull request's ready mark as the forge reads it (the gitea module's gitea_open_pulls): the head the
|
||||
// newest "ready at" comment names, who wrote it and when, and the label's id. Head is empty when the label is on and
|
||||
// no comment names a head.
|
||||
type ReadyMark struct {
|
||||
Head string `json:"head"`
|
||||
By string `json:"by,omitempty"`
|
||||
At string `json:"at,omitempty"`
|
||||
LabelID int `json:"label_id"`
|
||||
}
|
||||
|
||||
// ReadyLabel is the label that marks a pull request ready.
|
||||
const ReadyLabel = "mesh/ready"
|
||||
|
||||
// readyTryEvery is how often a marked head's merge is asked while the merge tool refuses it: a check it asked takes
|
||||
// minutes, and a refusal costs the forge a few reads.
|
||||
const readyTryEvery = time.Minute
|
||||
|
||||
// readyRefusedFor is how long the merge tool may refuse a marked head before it is said as stalled: longer than a
|
||||
// check takes (the controller's checkTimeout is 45 minutes), so a check on its way is never said.
|
||||
const readyRefusedFor = time.Hour
|
||||
|
||||
// ReadyRun is what this owner did with a delivery's ready mark: kept on the delivery and shown whole by `show`.
|
||||
type ReadyRun struct {
|
||||
// Head, By and MarkedAt are the mark: the head it names, who marked it, when.
|
||||
Head string `json:"head"`
|
||||
By string `json:"by,omitempty"`
|
||||
MarkedAt string `json:"marked_at,omitempty"`
|
||||
// Seen is when this owner first read the mark.
|
||||
Seen time.Time `json:"seen"`
|
||||
// Waits is what the merge waits on, when it waits: a verdict, the group's turn or its composed check.
|
||||
Waits string `json:"waits,omitempty"`
|
||||
// Tries is how many times the merge was asked; LastTry when, and Answer what the merge tool last answered.
|
||||
Tries int `json:"tries,omitempty"`
|
||||
LastTry time.Time `json:"last_try"`
|
||||
Answer string `json:"answer,omitempty"`
|
||||
// RefusedSince is when the merge tool began refusing it without a break.
|
||||
RefusedSince *time.Time `json:"refused_since,omitempty"`
|
||||
// Merged is when the merge tool merged it.
|
||||
Merged *time.Time `json:"merged,omitempty"`
|
||||
// Failed is why it is not merged and will not be on this head: its check failed. Said once on the pull request.
|
||||
Failed string `json:"failed,omitempty"`
|
||||
}
|
||||
|
||||
// mergedBy is who a merge this owner made on a ready mark is said to be by, in its transitions.
|
||||
func (r *ReadyRun) mergedBy() string {
|
||||
if r == nil || r.Merged == nil {
|
||||
return ""
|
||||
}
|
||||
by := byOwner + ", on the ready mark at " + shortOf(r.Head, 12)
|
||||
if r.By != "" {
|
||||
by += " by " + r.By
|
||||
}
|
||||
return by
|
||||
}
|
||||
|
||||
// marked is a pull request read with a ready mark.
|
||||
type marked struct {
|
||||
pull OpenPull
|
||||
// cleared is when the mark was cleared, the label taken off: not cleared again within readyTryEvery.
|
||||
cleared time.Time
|
||||
}
|
||||
|
||||
// pullKey is a pull request as a key: owner/repo#number.
|
||||
func pullKey(p OpenPull) string {
|
||||
return strings.ToLower(p.Owner+"/"+p.Repo) + fmt.Sprintf("#%d", p.Number)
|
||||
}
|
||||
|
||||
// seeMarks keeps the open pull requests that carry a ready mark; under the lock. A pull request no longer open or
|
||||
// no longer marked drops out.
|
||||
func (h *Holder) seeMarks(open []OpenPull) {
|
||||
seen := map[string]*marked{}
|
||||
for _, p := range open {
|
||||
if p.Ready == nil || p.HeadSHA == "" {
|
||||
continue
|
||||
}
|
||||
k := pullKey(p)
|
||||
m := &marked{pull: p}
|
||||
if was := h.marks[k]; was != nil && was.pull.Ready != nil && was.pull.Ready.Head == p.Ready.Head &&
|
||||
was.pull.HeadSHA == p.HeadSHA {
|
||||
m.cleared = was.cleared
|
||||
}
|
||||
seen[k] = m
|
||||
}
|
||||
h.marks = seen
|
||||
}
|
||||
|
||||
// sameFull is whether a mark names a head: the whole sha, or — read from an older forge module — at least twelve
|
||||
// characters of it.
|
||||
func sameFull(mark, head string) bool {
|
||||
mark, head = strings.ToLower(mark), strings.ToLower(head)
|
||||
return len(mark) >= 12 && strings.HasPrefix(head, mark)
|
||||
}
|
||||
|
||||
// readyAsks works out, under the lock, what each ready mark needs: a mark cleared, a merge asked, a failure said.
|
||||
// The asking happens outside the lock.
|
||||
func (h *Holder) readyAsks(now time.Time) []func() {
|
||||
var asks []func()
|
||||
for k, m := range h.marks {
|
||||
p, mark := m.pull, *m.pull.Ready
|
||||
repository := strings.ToLower(p.Owner + "/" + p.Repo)
|
||||
if !sameFull(mark.Head, p.HeadSHA) {
|
||||
if !m.cleared.IsZero() && now.Sub(m.cleared) < readyTryEvery {
|
||||
continue
|
||||
}
|
||||
m.cleared = now
|
||||
asks = append(asks, h.clearMark(k, p, mark))
|
||||
continue
|
||||
}
|
||||
d := h.deliveries[IDOf(repository, p.HeadSHA)]
|
||||
if d == nil || d.State.Final() || d.MergedAs != "" {
|
||||
continue // not announced yet, or past its merge
|
||||
}
|
||||
if d.Ready == nil || d.Ready.Head != mark.Head {
|
||||
d.Ready = &ReadyRun{Head: mark.Head, By: mark.By, MarkedAt: mark.At, Seen: now}
|
||||
h.Logf("[mesh-delivery] %s is marked ready at %s by %s: merged once its check passes against its trunk's head",
|
||||
d.ID, shortOf(mark.Head, 12), orNone(mark.By))
|
||||
h.keep(d)
|
||||
}
|
||||
r := d.Ready
|
||||
if r.Merged != nil {
|
||||
continue
|
||||
}
|
||||
if d.State == Rejected {
|
||||
if r.Failed == "" {
|
||||
r.Failed = "its check failed"
|
||||
if d.Check != nil {
|
||||
r.Failed += ": " + oneLine(d.Check.Summary)
|
||||
if j := d.Check.Judged(); j != "" {
|
||||
r.Failed += " (" + j + ")"
|
||||
}
|
||||
}
|
||||
r.Waits = ""
|
||||
h.Logf("[mesh-delivery] %s is marked ready and not merged: %s", d.ID, r.Failed)
|
||||
h.keep(d)
|
||||
asks = append(asks, h.sayOn(d, fmt.Sprintf("mesh-delivery: **not merged.** This pull request is marked "+
|
||||
"ready at %s, and %s. A new head, marked ready once reviewed, or a recheck that passes, merges it.",
|
||||
mark.Head, r.Failed)))
|
||||
}
|
||||
continue
|
||||
}
|
||||
r.Failed = ""
|
||||
waits := h.readyWaits(d)
|
||||
if waits != r.Waits {
|
||||
r.Waits = waits
|
||||
if waits != "" {
|
||||
h.Logf("[mesh-delivery] %s is marked ready and waits: %s", d.ID, waits)
|
||||
}
|
||||
h.keep(d)
|
||||
}
|
||||
if waits != "" || (!r.LastTry.IsZero() && now.Sub(r.LastTry) < readyTryEvery) {
|
||||
continue
|
||||
}
|
||||
r.Tries++
|
||||
r.LastTry = now
|
||||
h.keep(d)
|
||||
asks = append(asks, h.askMerge(d.ID, p, mark.Head))
|
||||
}
|
||||
return asks
|
||||
}
|
||||
|
||||
// readyWaits is what a marked delivery's merge waits on; empty when it is asked now. A ready delivery is asked; so is
|
||||
// a proposed one whose verdict went out of date and whose check nobody asked again — the merge tool asks it.
|
||||
func (h *Holder) readyWaits(d *Delivery) string {
|
||||
switch {
|
||||
case d.State == Ready:
|
||||
case d.State == Proposed && d.outOfDate() != "" && d.AskedAgain == nil:
|
||||
case d.State == Proposed && d.AskedAgain != nil:
|
||||
return "its check against the trunk's head is asked and has not answered"
|
||||
default:
|
||||
return "its check has not passed yet (" + string(d.State) + ")"
|
||||
}
|
||||
if d.Group == "" {
|
||||
return ""
|
||||
}
|
||||
return h.groupTurnToMerge(d)
|
||||
}
|
||||
|
||||
// groupTurnToMerge is why a group member may not merge yet; empty at its turn: the group's composed check passed for
|
||||
// its members' heads as they are and is not out of date, and every member before it in the group's order merged.
|
||||
func (h *Holder) groupTurnToMerge(d *Delivery) string {
|
||||
g := h.groups[d.Group]
|
||||
if g == nil {
|
||||
return ""
|
||||
}
|
||||
members := h.membersOf(g)
|
||||
if state, why := GroupState(g, members); state != "ready" && state != "delivering" {
|
||||
return fmt.Sprintf("its group %s is %s: %s", g.ID, state, why)
|
||||
}
|
||||
if c := g.Check; c == nil || (c.Verdict != "pass" && c.Verdict != "warning") || c.OutOfDate != "" ||
|
||||
!sameMembers(c.Commits, commitsOf(members)) {
|
||||
return "its group " + g.ID + "'s composed check has not passed for its members' heads"
|
||||
}
|
||||
if !containsString(g.Order, d.ID) {
|
||||
return "its group " + g.ID + "'s order is not worked out for it yet"
|
||||
}
|
||||
for _, id := range g.Order {
|
||||
if id == d.ID {
|
||||
return ""
|
||||
}
|
||||
if o := h.deliveries[id]; o != nil && o.MergedAs == "" && !o.State.Final() {
|
||||
return "its group " + g.ID + "'s order merges " + id + " first"
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// askMerge asks the forge's merge tool to merge a marked head, and keeps its answer.
|
||||
func (h *Holder) askMerge(id string, p OpenPull, head string) func() {
|
||||
return func() {
|
||||
err := h.Forge.Merge(p.Owner, p.Repo, p.Number, head)
|
||||
h.mu.Lock()
|
||||
defer h.mu.Unlock()
|
||||
d := h.deliveries[id]
|
||||
if d == nil || d.Ready == nil {
|
||||
return
|
||||
}
|
||||
r, now := d.Ready, h.Now()
|
||||
if err == nil {
|
||||
r.Merged, r.Answer, r.RefusedSince = &now, "merged", nil
|
||||
h.Logf("[mesh-delivery] %s merged on its ready mark at %s, its check passed against its trunk's head", id,
|
||||
shortOf(head, 12))
|
||||
h.keep(d)
|
||||
return
|
||||
}
|
||||
answer := oneLine(err.Error())
|
||||
if r.RefusedSince == nil {
|
||||
r.RefusedSince = &now
|
||||
}
|
||||
if answer != r.Answer {
|
||||
h.Logf("[mesh-delivery] %s is marked ready, and the merge tool did not merge it (asked again in %s): %s", id,
|
||||
readyTryEvery, answer)
|
||||
}
|
||||
r.Answer = answer
|
||||
h.keep(d)
|
||||
}
|
||||
}
|
||||
|
||||
// clearMark takes a mark off a pull request whose head moved after it, and says so on it.
|
||||
func (h *Holder) clearMark(k string, p OpenPull, mark ReadyMark) func() {
|
||||
return func() {
|
||||
err := h.Forge.Unlabel(p.Owner, p.Repo, p.Number, mark.LabelID)
|
||||
if err == nil {
|
||||
err = h.Forge.Comment(p.Owner, p.Repo, p.Number, fmt.Sprintf("mesh-delivery: the ready mark at %s is cleared: "+
|
||||
"the head is now %s, pushed after it. Mark the new head ready once it is reviewed.", mark.Head, p.HeadSHA))
|
||||
}
|
||||
if err != nil {
|
||||
h.Logf("[mesh-delivery] %s's ready mark at %s names an older head than %s, and could not be cleared yet: %v",
|
||||
k, shortOf(mark.Head, 12), shortOf(p.HeadSHA, 12), err)
|
||||
return
|
||||
}
|
||||
h.Logf("[mesh-delivery] %s's ready mark at %s cleared: its head is now %s", k, shortOf(mark.Head, 12),
|
||||
shortOf(p.HeadSHA, 12))
|
||||
h.mu.Lock()
|
||||
delete(h.marks, k)
|
||||
h.mu.Unlock()
|
||||
}
|
||||
}
|
||||
|
||||
// sayOn comments on a delivery's pull request.
|
||||
func (h *Holder) sayOn(d *Delivery, body string) func() {
|
||||
owner, repo, number, id := d.Owner(), d.Repo(), d.Number, d.ID
|
||||
return func() {
|
||||
if err := h.Forge.Comment(owner, repo, number, body); err != nil {
|
||||
h.Logf("[mesh-delivery] %s: could not say on its pull request: %v", id, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// readyLines are the marked heads that will not merge: a check that failed at once, a merge refused past its bound;
|
||||
// as stalled lines, which the controller raises as conditions. Under the lock.
|
||||
func (h *Holder) readyLines(now time.Time) []StalledLine {
|
||||
var out []StalledLine
|
||||
for _, d := range h.deliveries {
|
||||
r := d.Ready
|
||||
if r == nil || r.Merged != nil || d.MergedAs != "" || d.State.Final() {
|
||||
continue
|
||||
}
|
||||
switch {
|
||||
case r.Failed != "" && d.State == Rejected:
|
||||
out = append(out, StalledLine{ID: d.ID, Number: d.Number, State: d.State, For: now.Sub(r.Seen).Round(time.Second).String(),
|
||||
Bound: "0s", H2: "none: a new head marked ready, or a recheck that passes — the operator's",
|
||||
Says: fmt.Sprintf("%s#%d is marked ready at %s and not merged: %s", d.Repository, d.Number,
|
||||
shortOf(r.Head, 12), r.Failed)})
|
||||
case r.RefusedSince != nil && now.Sub(*r.RefusedSince) >= readyRefusedFor:
|
||||
out = append(out, StalledLine{ID: d.ID, Number: d.Number, State: d.State,
|
||||
For: now.Sub(*r.RefusedSince).Round(time.Second).String(), Bound: readyRefusedFor.String(),
|
||||
H2: "none: the merge is asked again each minute — the operator's",
|
||||
Says: fmt.Sprintf("%s#%d is marked ready at %s, and the merge tool has refused it since %s: %s", d.Repository,
|
||||
d.Number, shortOf(r.Head, 12), r.RefusedSince.UTC().Format(time.RFC3339), r.Answer)})
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
@@ -0,0 +1,199 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
)
|
||||
|
||||
// **A pull request marked ready is merged by this owner** (novox/hq issue 722): before, a reviewed pull request with
|
||||
// green checks waited until a session called the merge tool, and again after every check the tool asked because the
|
||||
// trunk had moved. Each test below fails on a holder without the ready mark: nothing merged it.
|
||||
|
||||
const (
|
||||
readyHead = "1111111111111111111111111111111111111111"
|
||||
pushed = "2222222222222222222222222222222222222222"
|
||||
)
|
||||
|
||||
// markedPull is an open pull request as gitea_open_pulls reads it, labelled mesh/ready at the head named.
|
||||
func markedPull(repo string, number int, head, markedAt string) OpenPull {
|
||||
owner, name, _ := strings.Cut(repo, "/")
|
||||
return OpenPull{Owner: owner, Repo: name, Number: number, Base: "main", HeadSHA: head, Labels: []string{ReadyLabel},
|
||||
Ready: &ReadyMark{Head: markedAt, By: "reviewer", At: "2026-10-14T19:00:00Z", LabelID: 31}}
|
||||
}
|
||||
|
||||
func judgedAt(repo string, number int, sha, gate, trunk string) CheckedEvent {
|
||||
c := verdict(repo, number, sha, gate)
|
||||
c.Trunk = trunk
|
||||
return c
|
||||
}
|
||||
|
||||
func TestAReadyPullRequestMarkedAtItsHeadIsMergedThroughTheMergeTool(t *testing.T) {
|
||||
w := newWorld(t)
|
||||
id := IDOf("novox/app", readyHead)
|
||||
w.h.PullUpdated(pr("novox/app", 7, readyHead, "feat/x", "src/a.go"))
|
||||
w.h.Checked(judgedAt("novox/app", 7, readyHead, "pass", "t1t1t1t1t1t1"))
|
||||
w.settleAll()
|
||||
if len(w.forge.merges) != 0 {
|
||||
t.Fatalf("an unmarked pull request was merged: %v", w.forge.merges)
|
||||
}
|
||||
w.forge.open = []OpenPull{markedPull("novox/app", 7, readyHead, readyHead)}
|
||||
w.h.SeeOpenPulls()
|
||||
w.settleAll()
|
||||
if len(w.forge.merges) != 1 || w.forge.merges[0] != "novox/app#7@"+readyHead {
|
||||
t.Fatalf("a ready, marked pull request was merged %v; wanted once, at the marked head", w.forge.merges)
|
||||
}
|
||||
d := w.delivery(id)
|
||||
if d.Ready == nil || d.Ready.Merged == nil || d.Ready.By != "reviewer" || d.Ready.Tries != 1 {
|
||||
t.Fatalf("what was done with the mark is not kept: %+v", d.Ready)
|
||||
}
|
||||
// Its merge's transition names who merged it.
|
||||
w.h.PullMerged(merged("novox/app", 7, readyHead, "m7m7m7m7m7m7"))
|
||||
w.h.WalkMoved(w.ctl.put(aWalk("plan-7", "novox/app", "m7m7m7m7m7m7", true)))
|
||||
w.settleAll()
|
||||
d = w.delivery(id)
|
||||
var last Transition
|
||||
for _, tr := range d.Transitions {
|
||||
if tr.Event == EvMerged {
|
||||
last = tr
|
||||
}
|
||||
}
|
||||
if !strings.Contains(last.By, "ready mark at "+readyHead[:12]+" by reviewer") {
|
||||
t.Fatalf("the merge's transition does not name the mark: %+v", last)
|
||||
}
|
||||
if len(w.forge.merges) != 1 {
|
||||
t.Fatalf("merged again: %v", w.forge.merges)
|
||||
}
|
||||
}
|
||||
|
||||
func TestAPushAfterTheMarkClearsItAndNothingIsMerged(t *testing.T) {
|
||||
w := newWorld(t)
|
||||
w.h.PullUpdated(pr("novox/app", 7, readyHead, "feat/x", "src/a.go"))
|
||||
w.h.PullUpdated(pr("novox/app", 7, pushed, "feat/x", "src/a.go"))
|
||||
w.h.Checked(judgedAt("novox/app", 7, pushed, "pass", "t1t1t1t1t1t1"))
|
||||
w.forge.open = []OpenPull{markedPull("novox/app", 7, pushed, readyHead)}
|
||||
w.h.SeeOpenPulls()
|
||||
w.settleAll()
|
||||
if len(w.forge.merges) != 0 {
|
||||
t.Fatalf("a head pushed after the mark was merged: %v", w.forge.merges)
|
||||
}
|
||||
if len(w.forge.unlabels) != 1 || w.forge.unlabels[0] != "novox/app#7-31" {
|
||||
t.Fatalf("the stale mark's label was not taken off: %v", w.forge.unlabels)
|
||||
}
|
||||
if len(w.forge.comments) != 1 || !strings.Contains(w.forge.comments[0], "cleared") ||
|
||||
!strings.Contains(w.forge.comments[0], pushed) {
|
||||
t.Fatalf("the cleared mark is not said on the pull request: %v", w.forge.comments)
|
||||
}
|
||||
}
|
||||
|
||||
func TestAMovedTrunkIsJudgedAgainByTheMergeToolAndMergedOnItsVerdict(t *testing.T) {
|
||||
w := newWorld(t)
|
||||
id := IDOf("novox/app", readyHead)
|
||||
w.h.PullUpdated(pr("novox/app", 7, readyHead, "feat/x", "src/a.go"))
|
||||
w.h.Checked(judgedAt("novox/app", 7, readyHead, "pass", "t1t1t1t1t1t1"))
|
||||
// Another merge moves the trunk: its verdict is out of date, and it goes back to proposed.
|
||||
w.h.PullMerged(merged("novox/app", 9, "9999999999999999", "t2t2t2t2t2t2"))
|
||||
if w.state(id) != Proposed {
|
||||
t.Fatalf("out of date, it is %s", w.state(id))
|
||||
}
|
||||
// The merge tool asks the check against the trunk's head and refuses: nothing merged.
|
||||
w.forge.refuse = errors.New("the forge refused gitea_merge_pull_request: The check of head merged into trunk was asked")
|
||||
w.forge.open = []OpenPull{markedPull("novox/app", 7, readyHead, readyHead)}
|
||||
w.h.SeeOpenPulls()
|
||||
w.settleAll()
|
||||
if len(w.forge.merges) != 1 {
|
||||
t.Fatalf("the merge tool was not asked once to judge it again: %v", w.forge.merges)
|
||||
}
|
||||
// The tool's ask is the head announced again; it waits for that verdict, asking nothing.
|
||||
w.h.PullUpdated(pr("novox/app", 7, readyHead, "feat/x", "src/a.go"))
|
||||
w.later(5 * time.Minute)
|
||||
w.settleAll()
|
||||
if len(w.forge.merges) != 1 || !strings.Contains(w.delivery(id).Ready.Waits, "asked") {
|
||||
t.Fatalf("asked again while its check was on its way: %v (%+v)", w.forge.merges, w.delivery(id).Ready)
|
||||
}
|
||||
// It passes against the trunk's head: merged, without anyone asking.
|
||||
w.forge.refuse = nil
|
||||
w.h.Checked(judgedAt("novox/app", 7, readyHead, "pass", "t2t2t2t2t2t2"))
|
||||
w.settleAll()
|
||||
if w.state(id) != Ready || len(w.forge.merges) != 2 || w.delivery(id).Ready.Merged == nil {
|
||||
t.Fatalf("on its passing verdict it was not merged: %s %v %+v", w.state(id), w.forge.merges, w.delivery(id).Ready)
|
||||
}
|
||||
}
|
||||
|
||||
func TestAMarkedHeadWhoseCheckFailedIsNotMergedAndIsSaid(t *testing.T) {
|
||||
w := newWorld(t)
|
||||
id := IDOf("novox/app", readyHead)
|
||||
w.h.PullUpdated(pr("novox/app", 7, readyHead, "feat/x", "src/a.go"))
|
||||
w.h.Checked(judgedAt("novox/app", 7, readyHead, "fail", "t1t1t1t1t1t1"))
|
||||
w.forge.open = []OpenPull{markedPull("novox/app", 7, readyHead, readyHead)}
|
||||
w.h.SeeOpenPulls()
|
||||
w.settleAll()
|
||||
w.later(10 * time.Minute)
|
||||
w.h.SeeOpenPulls()
|
||||
w.settleAll()
|
||||
if len(w.forge.merges) != 0 {
|
||||
t.Fatalf("a head whose check failed was merged: %v", w.forge.merges)
|
||||
}
|
||||
if len(w.forge.comments) != 1 || !strings.Contains(w.forge.comments[0], "not merged") {
|
||||
t.Fatalf("the failure is not said once on the pull request: %v", w.forge.comments)
|
||||
}
|
||||
lines := w.h.Stalled()
|
||||
if len(lines) != 1 || lines[0].ID != id || lines[0].State != Rejected || !strings.Contains(lines[0].Says, "marked ready") {
|
||||
t.Fatalf("the failure is not a stalled line, which the controller raises as a condition: %+v", lines)
|
||||
}
|
||||
}
|
||||
|
||||
func TestAMarkRefusedForAnHourIsSaid(t *testing.T) {
|
||||
w := newWorld(t)
|
||||
w.h.PullUpdated(pr("novox/app", 7, readyHead, "feat/x", "src/a.go"))
|
||||
w.h.Checked(judgedAt("novox/app", 7, readyHead, "pass", "t1t1t1t1t1t1"))
|
||||
w.forge.refuse = errors.New("the forge refused gitea_merge_pull_request: mesh/repo-check is pending")
|
||||
w.forge.open = []OpenPull{markedPull("novox/app", 7, readyHead, readyHead)}
|
||||
w.h.SeeOpenPulls()
|
||||
w.settleAll()
|
||||
w.later(30 * time.Second)
|
||||
w.settleAll()
|
||||
if len(w.forge.merges) != 1 {
|
||||
t.Fatalf("asked again within the minute: %v", w.forge.merges)
|
||||
}
|
||||
w.later(readyRefusedFor)
|
||||
w.settleAll()
|
||||
if len(w.forge.merges) != 2 {
|
||||
t.Fatalf("not asked again after a minute: %v", w.forge.merges)
|
||||
}
|
||||
if lines := w.h.Stalled(); len(lines) != 1 || !strings.Contains(lines[0].Says, "refused it since") {
|
||||
t.Fatalf("a mark refused for an hour is not said: %+v", lines)
|
||||
}
|
||||
}
|
||||
|
||||
func TestAGroupMergesItsMarkedMembersInOrderOnlyOnceComposed(t *testing.T) {
|
||||
w := newWorld(t)
|
||||
const ctlHead, catHead = "c1c1c1c1c1c1c1c1c1c1c1c1c1c1c1c1c1c1c1c1", "d2d2d2d2d2d2d2d2d2d2d2d2d2d2d2d2d2d2d2d2"
|
||||
ctl, cat := IDOf("novox/mesh-controller", ctlHead), IDOf("novox/mesh-catalog", catHead)
|
||||
w.ctl.order = func(ms []Member) Order { return Order{Order: []string{ctl, cat}} }
|
||||
w.h.PullUpdated(pr("novox/mesh-controller", 1, ctlHead, "feat/x", "internal/a.go"))
|
||||
w.h.PullUpdated(pr("novox/mesh-catalog", 2, catHead, "feat/x", "modules/app/module.json"))
|
||||
w.h.Checked(judgedAt("novox/mesh-controller", 1, ctlHead, "pass", "t1t1t1t1t1t1"))
|
||||
w.h.Checked(judgedAt("novox/mesh-catalog", 2, catHead, "pass", "t3t3t3t3t3t3"))
|
||||
w.forge.open = []OpenPull{markedPull("novox/mesh-controller", 1, ctlHead, ctlHead),
|
||||
markedPull("novox/mesh-catalog", 2, catHead, catHead)}
|
||||
w.h.SeeOpenPulls()
|
||||
w.settleAll()
|
||||
if len(w.forge.merges) != 0 {
|
||||
t.Fatalf("a member merged before its group's composed check passed: %v", w.forge.merges)
|
||||
}
|
||||
w.h.Checked(CheckedEvent{Group: "feat/x", ID: "check-1", Verdict: "pass", Summary: "both compose"})
|
||||
w.settleAll()
|
||||
if len(w.forge.merges) != 1 || w.forge.merges[0] != "novox/mesh-controller#1@"+ctlHead {
|
||||
t.Fatalf("composed, the first member in the group's order was not merged alone: %v", w.forge.merges)
|
||||
}
|
||||
if waits := w.delivery(cat).Ready.Waits; !strings.Contains(waits, "merges "+ctl+" first") {
|
||||
t.Fatalf("the second member does not say it waits its turn: %q", waits)
|
||||
}
|
||||
w.h.PullMerged(merged("novox/mesh-controller", 1, ctlHead, "m1m1m1m1m1m1"))
|
||||
w.settleAll()
|
||||
if len(w.forge.merges) != 2 || w.forge.merges[1] != "novox/mesh-catalog#2@"+catHead {
|
||||
t.Fatalf("after the first member merged, the next was not: %v", w.forge.merges)
|
||||
}
|
||||
}
|
||||
@@ -498,7 +498,12 @@ func Apply(d *Delivery, ev Event, act bool, f Facts) (Transition, error) {
|
||||
if why == "" {
|
||||
why = r.Guard
|
||||
}
|
||||
t := Transition{At: f.Now, From: d.State, To: r.To, Event: ev, Why: why, By: f.By}
|
||||
by := f.By
|
||||
if by == "" && (ev == EvMerged || ev == EvDone) && d.MergedAs != "" {
|
||||
// A merge this owner made on a ready mark names it as its author (novox/hq issue 722).
|
||||
by = d.Ready.mergedBy()
|
||||
}
|
||||
t := Transition{At: f.Now, From: d.State, To: r.To, Event: ev, Why: why, By: by}
|
||||
d.State, d.Since = r.To, f.Now
|
||||
d.Transitions = append(d.Transitions, t)
|
||||
if len(d.Transitions) > keptTransitions {
|
||||
|
||||
@@ -72,6 +72,9 @@ type OpenPull struct {
|
||||
// than that says none: the head is then read by Statuses alone, as before, and a pending check is not told
|
||||
// from an answered one.
|
||||
Checks map[string]HeadCheck `json:"checks,omitempty"`
|
||||
// Labels are its labels by name, and Ready its ready mark, when it carries one (novox/hq issue 722).
|
||||
Labels []string `json:"labels,omitempty"`
|
||||
Ready *ReadyMark `json:"ready,omitempty"`
|
||||
}
|
||||
|
||||
// HeadCheck is one status on a head as the forge keeps it: pending, success, failure, error or warning.
|
||||
@@ -201,6 +204,7 @@ func (h *Holder) SeeOpenPulls() {
|
||||
seen[id] = u
|
||||
}
|
||||
h.unchecked = seen
|
||||
h.seeMarks(open)
|
||||
}
|
||||
|
||||
// started is whether the head's check started, rather than was never asked: it has any merge check, or a delivery
|
||||
|
||||
@@ -249,6 +249,7 @@ func (h *Holder) Stalled() []StalledLine {
|
||||
}
|
||||
out = append(out, h.withChecks(h.uncheckedLines(now))...)
|
||||
out = append(out, h.orphanLines(now)...)
|
||||
out = append(out, h.readyLines(now)...)
|
||||
sort.Slice(out, func(i, j int) bool { return out[i].ID < out[j].ID })
|
||||
return out
|
||||
}
|
||||
|
||||
@@ -47,7 +47,10 @@
|
||||
"gitea.gitea_commit_status",
|
||||
"gitea.gitea_commit_statuses",
|
||||
"gitea.gitea_contains",
|
||||
"gitea.gitea_open_pulls"
|
||||
"gitea.gitea_open_pulls",
|
||||
"gitea.gitea_merge_pull_request",
|
||||
"gitea.gitea_add_comment",
|
||||
"gitea.gitea_api"
|
||||
],
|
||||
"state": [
|
||||
"deliveries",
|
||||
|
||||
@@ -121,6 +121,12 @@ func TestItsProcessesAreThePreparationTheActAndTheJudge(t *testing.T) {
|
||||
!reflect.DeepEqual(m.Tools, []string{HealthTool, HighestTool}) {
|
||||
t.Fatalf("watch %v, tools %v", watch, m.Tools)
|
||||
}
|
||||
// The watch's verdict is whether the database serves, so its check names the provision it exercises: while the
|
||||
// database's provider is unhealthy, this finding is held under the provider's condition (hq ADR 0240 rule 5,
|
||||
// issue 145).
|
||||
if h["needs"] != "postgres-database" {
|
||||
t.Fatalf("watch's check needs %v; it exercises postgres-database", h["needs"])
|
||||
}
|
||||
if watch["env"].(map[string]any)["MESH_KNOWLEDGE_STATUS"] != m.Build.Artifacts[0].Env["MESH_KNOWLEDGE_STATUS"] {
|
||||
t.Fatal("watch writes another status file than the health tool reads")
|
||||
}
|
||||
|
||||
@@ -156,6 +156,7 @@
|
||||
"health": {
|
||||
"kind": "tool",
|
||||
"tool": "knowledge_health",
|
||||
"needs": "postgres-database",
|
||||
"interval": "60s",
|
||||
"timeout": "10s",
|
||||
"looks": 2,
|
||||
|
||||
@@ -49,8 +49,9 @@ channel's client and no channel's secret.
|
||||
warrant published to the asker alone. A warrant the bus did not take is published again every minute.
|
||||
- **What the operator sees when they answer** (issue 372): first, in reply to the answer where it was given,
|
||||
that it was recorded and whether its asker was told ("You chose Approve: recorded, and claude-code was
|
||||
told.") — said only once the ask's end is recorded — or, refused, why; then the ask's message edited to how
|
||||
it ended, as its title ("You chose Approve at 13:30 on Telegram · <headline>"), with no answers left on it.
|
||||
told.") — said only once the ask's end is recorded — or, refused, why; then the ask's message edited with no
|
||||
answers left on it: its question whole (headline, summary, points, link, Details), and below it how it ended
|
||||
("You chose Approve at 13:30 on Telegram.") and who acts on it (issue 714).
|
||||
What the asker then did is not said: the asks protocol carries no result back to the router, so the
|
||||
message says only that the asker was told and acts on it itself.
|
||||
- **An ask never defaults**: at its expiry it ends `expired` and its asker does what it said it would.
|
||||
@@ -138,8 +139,9 @@ and said in the log). Everything else is the message's note (`asks.Message.Note`
|
||||
smaller: who asked and when, with what happens if nobody answers; what each answer does; where else it is answered;
|
||||
and the asker's Details (who proposed it, a fingerprint, how to read it whole) — on a kind that proves who answers
|
||||
and was given the ask's answers, its Details whole (`asks.Ask.WholeDetails`): every value an approval sets, held to
|
||||
the secret rule alone, as the whole words are. Answered, the message is one line —
|
||||
"You chose Approve at 16:06 on Telegram · <headline>" — and the router's word on the asker is its note.
|
||||
the secret rule alone, as the whole words are. Answered, the message keeps its headline, body and Details, so the
|
||||
operator can read back what they answered (issue 714); its note becomes "You chose Approve at 16:06 on Telegram."
|
||||
with the router's word on the asker.
|
||||
|
||||
**An ask's values are shown whole where the sender is proven** (hq issue 383). An ask may carry its explanation
|
||||
twice: as it is held to the whole content rule, and whole (`asks.Ask.Whole`), its paths and addresses as they
|
||||
|
||||
@@ -365,10 +365,12 @@ func TestAnApproveFromTheLinkedAccountIsAWarrantForTheAskerAlone(t *testing.T) {
|
||||
for _, m := range ch.edits {
|
||||
edited = m
|
||||
}
|
||||
// The question's title is how it ended, read at a glance; then what the router knows of the asker (issue 372).
|
||||
if len(edited.Actions) != 0 || edited.Title != "You chose Release at 12:00 on Telegram · Delivery of hq held for 36 hours" ||
|
||||
edited.Body != "" || edited.Note != "Told to mesh-delivery, which acts on it itself." {
|
||||
t.Errorf("%s still offers %q, or does not say how it ended in one line (issue 639): %q / %q / %q", ch.name, labelsOf(edited), edited.Title, edited.Body, edited.Note)
|
||||
// The question stays whole (issue 714); below it, how it ended and what the router knows of the asker
|
||||
// (issue 372).
|
||||
if len(edited.Actions) != 0 || edited.Title != "Delivery of hq held for 36 hours" ||
|
||||
edited.Body != heldAsk(c, "d-1").Explanation ||
|
||||
edited.Note != "You chose Release at 12:00 on Telegram.\nTold to mesh-delivery, which acts on it itself." {
|
||||
t.Errorf("%s still offers %q, or does not keep the question and say how it ended (issue 714): %q / %q / %q", ch.name, labelsOf(edited), edited.Title, edited.Body, edited.Note)
|
||||
}
|
||||
}
|
||||
// The tap is confirmed where it was made, in reply to it, once the warrant stood — and before the question
|
||||
@@ -624,8 +626,8 @@ func TestAnAskExpiresAndNeverDefaults(t *testing.T) {
|
||||
for _, m := range tg.edits {
|
||||
edited = m
|
||||
}
|
||||
if len(edited.Actions) != 0 || !strings.HasPrefix(edited.Title, "No longer answerable: nobody answered in time · Delivery of hq") ||
|
||||
edited.Body != "" || edited.Note != "The delivery stays held." {
|
||||
if len(edited.Actions) != 0 || !strings.HasPrefix(edited.Title, "Delivery of hq") ||
|
||||
edited.Body == "" || edited.Note != "No longer answerable: nobody answered in time.\nThe delivery stays held." {
|
||||
t.Errorf("the copy still offers answers, or does not say how it ended: %+v", edited)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -51,7 +51,7 @@ func TestAnApprovalIsConfirmedWhereItWasGivenAndThenTheQuestionSaysHowItEnded(t
|
||||
}
|
||||
want := []string{
|
||||
"send You chose Release: recorded, and mesh-delivery was told.",
|
||||
"edit You chose Release at 12:00 on Telegram · Delivery of hq held for 36 hours",
|
||||
"edit Delivery of hq held for 36 hours",
|
||||
}
|
||||
if strings.Join(log, "\n") != strings.Join(want, "\n") {
|
||||
t.Fatalf("the operator saw, in order:\n%s\nwant:\n%s", strings.Join(log, "\n"), strings.Join(want, "\n"))
|
||||
@@ -122,7 +122,7 @@ func TestTheConfirmationNeverClaimsWhatDidNotHappen(t *testing.T) {
|
||||
for _, m := range tg.edits {
|
||||
edited = m
|
||||
}
|
||||
if !strings.HasPrefix(edited.Note, "Told to mesh-delivery as soon as the bus takes it") {
|
||||
if !strings.Contains(edited.Note, "\nTold to mesh-delivery as soon as the bus takes it") {
|
||||
t.Errorf("the question claims its asker was told: %q", edited.Note)
|
||||
}
|
||||
})
|
||||
|
||||
@@ -9,8 +9,8 @@ import (
|
||||
)
|
||||
|
||||
// novox/hq issue 639: an ask's message reads at a glance on the phone. Its body is the asker's summary and points
|
||||
// alone; who asked and when, what each answer does, the expiry and the asker's Details are its note; once answered
|
||||
// it is one line with the headline.
|
||||
// alone; who asked and when, what each answer does, the expiry and the asker's Details are its note. Once answered
|
||||
// it keeps the question whole, so the operator can read back what they answered (issue 714).
|
||||
|
||||
// decisionAsk is the ask for ADR 0343 as the knowledge base composes it now (its glance form).
|
||||
func decisionAsk(c *clock) asks.Ask {
|
||||
@@ -59,7 +59,8 @@ func TestAnAsksMessageIsItsSummaryWithTheRestInItsNote(t *testing.T) {
|
||||
if n := len(strings.Split(m.Text(), "\n")); n > 9 || len(m.Actions) != 2 {
|
||||
t.Errorf("the message is %d lines offering %s:\n%s", n, labelsOf(m), m.Text())
|
||||
}
|
||||
// Answered, it is one line with the headline; the body is not said again.
|
||||
// Answered, it keeps its headline, summary, points and Details; below them, how it ended and who acts on it;
|
||||
// its buttons are gone (issue 714: the one line issue 639 made left nothing to read back).
|
||||
if out, err := h.Chosen("telegram", choiceOf(ticketFor(m, "Approve"), "42", c.now())); err != nil || out != "chosen" {
|
||||
t.Fatalf("Approve: %q %v", out, err)
|
||||
}
|
||||
@@ -67,8 +68,9 @@ func TestAnAsksMessageIsItsSummaryWithTheRestInItsNote(t *testing.T) {
|
||||
for _, e := range tg.edits {
|
||||
edited = e
|
||||
}
|
||||
if edited.Title != "You chose Approve at "+asked+" on Telegram · "+a.Headline || edited.Body != "" ||
|
||||
strings.Contains(edited.Note, "What an agent learns") || len(edited.Actions) != 0 {
|
||||
if edited.Title != a.Headline || edited.Body != a.Explanation+"\n"+want[2]+"\n"+want[3] ||
|
||||
edited.Note != "You chose Approve at "+asked+" on Telegram.\nTold to mesh-knowledge, which acts on it itself." ||
|
||||
len(edited.Actions) != 0 {
|
||||
t.Errorf("the answered copy: %q\n%q\n%q", edited.Title, edited.Body, edited.Note)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -856,7 +856,7 @@ func (h *Holder) sayOn(r *Record, what, kind string) Message {
|
||||
}
|
||||
}
|
||||
if r.Answered != "" {
|
||||
m = h.answeredWords(r, m)
|
||||
m = h.answeredWords(r, m, kind)
|
||||
}
|
||||
if kind == "" {
|
||||
return m
|
||||
@@ -910,18 +910,24 @@ func (h *Holder) sayOn(r *Record, what, kind string) Message {
|
||||
return m
|
||||
}
|
||||
|
||||
// answeredWords is a message that says what came of its question. An ask's own message is the question
|
||||
// itself, so it becomes how it ended and what it was about — "You chose Approve at 13:30 on Telegram ·
|
||||
// <headline>" — one line, read at a glance on the phone, where the edit rings nothing (issue 372); the body
|
||||
// is not said again (issue 639), and what the router knows of the asker after it is the note. A condition's
|
||||
// message keeps its own title, and says it first.
|
||||
func (h *Holder) answeredWords(r *Record, m Message) Message {
|
||||
// answeredWords is a message that says what came of its question. An ask's own message keeps the question
|
||||
// whole — its headline as the title, the asker's summary, points and link as the body, its Details after them —
|
||||
// so the operator can read back what they answered (issue 714, which undid issue 639's one line). How it ended
|
||||
// ("You chose Approve at 13:30 on Telegram.") and what the router knows of the asker after it are the note,
|
||||
// below the question, and its answers are gone (issue 372). A channel that must shorten it cuts the body from
|
||||
// its end, the Details first; never the headline or the note. A condition's message keeps its own title, and
|
||||
// says how it ended first.
|
||||
func (h *Holder) answeredWords(r *Record, m Message, kind string) Message {
|
||||
if r.Origin == "ask" {
|
||||
first, rest, _ := strings.Cut(r.Answered, "\n")
|
||||
headline, _ := wordsOf(r)
|
||||
out := Message{Title: strings.TrimSuffix(first, ".") + " · " + headline, Note: strings.TrimSpace(rest),
|
||||
body := []string{}
|
||||
if b := strings.TrimSpace(m.Body); b != "" {
|
||||
body = append(body, b)
|
||||
}
|
||||
body = append(body, h.answeredDetails(r, kind)...)
|
||||
out := Message{Title: headline, Body: strings.Join(body, "\n"), Note: strings.TrimSpace(r.Answered),
|
||||
Urgent: m.Urgent, Quiet: m.Quiet}
|
||||
if _, ok := Check(out.Text()); ok {
|
||||
if _, ok := Check(out.Title + "\n" + out.Note); ok {
|
||||
return out
|
||||
}
|
||||
// Its headline refused (it is the asker's): the outcome is still said, before what may leave.
|
||||
@@ -930,6 +936,33 @@ func (h *Holder) answeredWords(r *Record, m Message) Message {
|
||||
return m
|
||||
}
|
||||
|
||||
// answeredDetails are an answered ask's Details, line by line, as its open message noted them (issue 714): whole
|
||||
// on a kind that proves who answers, a line that may not leave withheld and said so.
|
||||
func (h *Holder) answeredDetails(r *Record, kind string) []string {
|
||||
if r.Ask == "" {
|
||||
return nil
|
||||
}
|
||||
e := h.askOf(r.Ask)
|
||||
if e == nil {
|
||||
return nil
|
||||
}
|
||||
details, passes := e.rec.Ask.Details, Check
|
||||
if wd := h.wholeDetailsOf(r, kind); wd != "" {
|
||||
details, passes = wd, CheckSecret
|
||||
}
|
||||
var lines []string
|
||||
for _, line := range strings.Split(strings.TrimSpace(details), "\n") {
|
||||
if line = strings.TrimSpace(line); line == "" {
|
||||
continue
|
||||
}
|
||||
if refusal, ok := passes(line); !ok {
|
||||
line = withheldLine(line, refusal, passes)
|
||||
}
|
||||
lines = append(lines, line)
|
||||
}
|
||||
return lines
|
||||
}
|
||||
|
||||
// wholeWords is a record's message with the ask's whole words in place of its explanation, when they carry no
|
||||
// secret's shape once composed; else false, and the message under the whole content rule stands.
|
||||
func (h *Holder) wholeWords(r *Record, what, whole string) (Message, bool) {
|
||||
|
||||
@@ -91,7 +91,7 @@ func (h *Holder) Preview(key, what string) (map[string]any, error) {
|
||||
asking := h.openAsk(&r) != nil // askOf takes the same lock, so this is asked outside it
|
||||
m, line, refusal, ownWords := h.allowedWords(&r, what, now)
|
||||
if r.Answered != "" {
|
||||
m = h.answeredWords(&r, m)
|
||||
m = h.answeredWords(&r, m, "")
|
||||
}
|
||||
out := map[string]any{
|
||||
"key": key,
|
||||
|
||||
@@ -50,7 +50,7 @@ func TestAReplacedAsksMessageEndsWithIt(t *testing.T) {
|
||||
m, edited = r.m, true
|
||||
}
|
||||
}
|
||||
if !edited || len(m.Actions) != 0 || !strings.Contains(m.Title, "Replaced by a newer question") {
|
||||
if !edited || len(m.Actions) != 0 || !strings.HasPrefix(m.Note, "Replaced by a newer question") {
|
||||
t.Errorf("%s: the replaced ask's message still stands: edited %v, %q %v", ch.name, edited, m.Text(), labelsOf(m))
|
||||
}
|
||||
}
|
||||
@@ -86,7 +86,7 @@ func TestAnAsksMessageLeftOpenAfterItsAskEndedIsEndedOnTheNextTick(t *testing.T)
|
||||
if got := openAskRecords(h); len(got) != 0 {
|
||||
t.Fatalf("the message of an ended ask is still open: %v", got)
|
||||
}
|
||||
if m, ok := tg.edits["1"]; !ok || len(m.Actions) != 0 || !strings.Contains(m.Title, "Replaced by a newer question") {
|
||||
if m, ok := tg.edits["1"]; !ok || len(m.Actions) != 0 || !strings.HasPrefix(m.Note, "Replaced by a newer question") {
|
||||
t.Errorf("the leftover's copy was not ended: %v %q %v", ok, m.Text(), labelsOf(m))
|
||||
}
|
||||
}
|
||||
|
||||
@@ -61,8 +61,7 @@ func TestAnAsksWholeWordsAreShownWhereTheSenderIsProvenAndMaskedElsewhere(t *tes
|
||||
if got := w.of("mesh-controller"); len(got) != 0 || store.asks["mesh-controller.s-1"].State != StateOpen {
|
||||
t.Errorf("the ask was answered: %+v / %s", got, store.asks["mesh-controller.s-1"].State)
|
||||
}
|
||||
// Approved, the message is edited to one line that says so, with the headline; the body is not said again
|
||||
// (issue 639).
|
||||
// Approved, the message keeps its headline and words, and says below them how it ended (issue 714).
|
||||
if out, err := h.Chosen("telegram", choiceOf(ticketFor(phone, "Release"), "42", c.now())); err != nil || out != "chosen" {
|
||||
t.Fatalf("Release: %q %v", out, err)
|
||||
}
|
||||
@@ -70,8 +69,8 @@ func TestAnAsksWholeWordsAreShownWhereTheSenderIsProvenAndMaskedElsewhere(t *tes
|
||||
if !ok {
|
||||
t.Fatalf("the phone's message was not edited: %+v", tg.edits)
|
||||
}
|
||||
if !strings.HasPrefix(edited.Title, "You chose Release at ") || !strings.HasSuffix(edited.Title, " · Set mounts on shanks?") ||
|
||||
edited.Body != "" || len(edited.Actions) != 0 {
|
||||
if edited.Title != "Set mounts on shanks?" || edited.Body == "" ||
|
||||
!strings.HasPrefix(edited.Note, "You chose Release at ") || len(edited.Actions) != 0 {
|
||||
t.Errorf("the edited message: %q\n%s\nactions %+v", edited.Title, edited.Body, edited.Actions)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -97,6 +97,13 @@
|
||||
{
|
||||
"id": "server",
|
||||
"type": "container",
|
||||
"health": {
|
||||
"kind": "http",
|
||||
"endpoint": "web",
|
||||
"path": "/healthz/readiness",
|
||||
"status": 200,
|
||||
"needs": "postgres-database"
|
||||
},
|
||||
"name": "n8n",
|
||||
"artifact": "server",
|
||||
"network": "n8n",
|
||||
|
||||
@@ -83,6 +83,14 @@
|
||||
{
|
||||
"id": "server",
|
||||
"type": "container",
|
||||
"health": {
|
||||
"kind": "http",
|
||||
"endpoint": "web",
|
||||
"path": "/status.php",
|
||||
"status": 200,
|
||||
"body": "\"installed\":true",
|
||||
"needs": "postgres-database"
|
||||
},
|
||||
"name": "nextcloud",
|
||||
"image": "nextcloud@sha256:fb966733647ea03f0446b0c22eac9733c8eb616d37b960caca9d4c3010e14a08",
|
||||
"env-file": [
|
||||
|
||||
@@ -20,7 +20,7 @@ WORKDIR /src
|
||||
COPY go.mod go.sum ./
|
||||
RUN go mod download
|
||||
COPY . .
|
||||
RUN CGO_ENABLED=0 GOOS=linux go build -trimpath -o /mesh-route-proxy ./examples/route-proxy
|
||||
RUN CGO_ENABLED=0 GOOS=linux go build -trimpath -buildvcs=false -ldflags=-buildid= -o /mesh-route-proxy ./examples/route-proxy
|
||||
|
||||
# A small runtime with the public CA roots the ACME client needs to reach a real authority, and run
|
||||
# as root so it can bind :80 and :443 — the two privileged ports a public front door listens on.
|
||||
|
||||
@@ -4,10 +4,11 @@ package main
|
||||
// formatting", "too much text, no formatting, no summary"). The router's words are shown as given —
|
||||
// `exact-render` — and formatted, never reworded:
|
||||
//
|
||||
// - the title in bold: the headline, or how an answered ask ended;
|
||||
// - the title in bold: the headline, an answered ask's too (issue 714);
|
||||
// - the body as it is, a line that is a key with its value (as a settings proposal lists them, "+ key: value")
|
||||
// in monospace;
|
||||
// - the note — who asked, what each answer does, the expiry, the asker's details — apart, after a blank line,
|
||||
// - the note — who asked, what each answer does, the expiry, the asker's details; once answered, how it ended
|
||||
// and who acts on it — apart, after a blank line,
|
||||
// in a blockquote Telegram shows collapsed to its first lines, expanded on a tap.
|
||||
//
|
||||
// Every character Telegram's HTML would read as markup is escaped first, so a message carrying '<' neither
|
||||
|
||||
@@ -84,3 +84,20 @@ func TestTheNoteIsEscaped(t *testing.T) {
|
||||
t.Errorf("%q", got)
|
||||
}
|
||||
}
|
||||
|
||||
// novox/hq issue 714: an answered ask keeps its question whole, with how it ended below it. Over Telegram's bound,
|
||||
// the end of the body (the asker's Details) is cut; the headline and the answer are never.
|
||||
func TestAnAnsweredAskOverTheBoundKeepsItsHeadlineAndItsAnswer(t *testing.T) {
|
||||
answer := "You chose Approve at 20:03 on Telegram.\nTold to mesh-knowledge, which acts on it itself."
|
||||
m := asks.Message{Handle: "h-714", To: "42", Title: "Fixes reach every machine at once, unchecked",
|
||||
Body: "A fix goes to every machine in one step.\n• No machine goes first\n" + strings.Repeat("Details line. ", 400),
|
||||
Note: answer}
|
||||
s := partsOf(m)
|
||||
if n := len([]rune(s.plain())); n > MaxLength {
|
||||
t.Fatalf("the answered ask is %d characters, over %d", n, MaxLength)
|
||||
}
|
||||
if s.title != m.Title || s.note != answer || !strings.HasPrefix(s.body, "A fix goes to every machine in one step.\n• No machine goes first") ||
|
||||
!strings.HasSuffix(s.body, cutNote) {
|
||||
t.Errorf("the headline, the summary or the answer was cut:\n%s", s.plain())
|
||||
}
|
||||
}
|
||||
|
||||
@@ -89,6 +89,15 @@
|
||||
{
|
||||
"id": "server",
|
||||
"type": "container",
|
||||
"health": {
|
||||
"kind": "http",
|
||||
"endpoint": "web",
|
||||
"path": "/api/share/mesh-health",
|
||||
"status": 404,
|
||||
"body": "\"code\":\"not-found\"",
|
||||
"timeout": "10s",
|
||||
"needs": "postgres-database"
|
||||
},
|
||||
"name": "umami",
|
||||
"image": "ghcr.io/umami-software/umami@sha256:85909afc45bdcda1917394594a087421fdbb05610fded0fa9f6fb861abb2f367",
|
||||
"network": "umami",
|
||||
|
||||
Reference in New Issue
Block a user