mirror of
https://github.com/Elysola/WebHooker.git
synced 2026-11-20 17:13:49 +00:00
* fix(log): preserve structured error details Error objects lose their useful details when serialized as plain JSON. Keep the message, stack and cause in structured log output. * fix(runtime): bound shared in-flight waits A canceled request can leave its shared promise pending forever. Bound joins and coordinate a single replacement so later requests make progress without multiplying upstream work. * fix(bot): reject oversized callback bodies Reject declared oversized bot callbacks before reading their bodies. This keeps unauthenticated requests from wasting worker resources. * test(d1): exercise real sqlite transactions Exercise real foreign keys, transactions and conditional statements instead of mocks that cannot reproduce lost updates or cascades. * fix(storage): preserve claims across kv fallback Only missing tables justify KV fallback; other failures must surface. Remember fallback writes so migration to D1 cannot forget claims and replay completed work. Share marker checks without extra writes. * fix(filter): use isolated linear-time patterns Backtracking patterns can exhaust worker CPU on untrusted payloads. Use linear-time matching and separate bounded cache namespaces so glob and regex entries cannot corrupt each other. * fix(filter): read each event branch correctly Deployment and check branches live in event-specific nested fields. Read those fields and remove only the actual leading ref prefix. * fix(filter): read only own payload properties Inherited object properties are not webhook payload data. Read own properties only so JSONPath cannot traverse prototypes. * fix(filter): validate executable condition trees Malformed trees and unsupported patterns must not silently turn an exclude rule into a pass. Validate the shape and only the patterns the evaluator actually executes. * fix(i18n): bound and cache translation loads Repeated misses and simultaneous override loads spend KV reads for the same language. Cache confirmed misses and share bounded loads without caching read failures as missing translations. * i18n(bot): explain command and account failures Explain account linking, command failures and skipped delivery outcomes consistently in both supported languages. * fix(github): bound and reuse app token fetches Repeated token exchanges waste requests and JWT work for every event. Reuse valid installation tokens, share refreshes and back off briefly after failures while keeping every shared wait bounded. * fix(github): restrict enrichment request urls Webhook-provided URLs must never receive an installation token on another host. Restrict enrichment to GitHub repository API paths, reject redirects and bound optional requests. * fix(formatter): preserve invalid code points Out-of-range numeric entities can throw while formatting a delivery. Keep invalid code points verbatim instead of aborting the message. * fix(formatter): preserve bounded markdown text Code spans, fences, indentation and autolinks are Markdown content, not HTML tags to strip. Preserve them while bounding cleanup input and reusing results across routes for the same event. * fix(formatter): strip only leading ref prefixes A short branch or tag may itself contain refs/heads or refs/tags. Strip one leading full-ref prefix at the caller and keep short names unchanged when generating labels and links. * fix(gitea): link push authors to their forge A Gitea author is not the same-named GitHub account. Build author profile links from the originating forge. * fix(formatter): render deployment state values The deployment status object stringifies as [object Object]. Render its actual state in the status field. * fix(formatter): read security severity levels The scanner severity is not the security severity of an alert. Prefer the security level so critical and high alerts get the right label and color. * fix(formatter): hide actions on other forges Action buttons call the GitHub API as the linked user. Hide them for other forges to avoid operating on a same-named GitHub repository. * fix(check): isolate updates by check suite Same-named checks from different suites must not edit one message. Include the suite or app identity and retain the former key for controlled adoption of existing tracked messages. * fix(logs): scope queries before limiting results Filter authorized groups in SQL before LIMIT and aggregate only visible rows. Preserve current group attribution for late writes, surface read failures and combine related totals in one scan. * perf(d1): index pruning and failed send queries Pruning and failure views should not scan all historical rows. Index the high-value access paths without adding a write-heavy index for infrequent delivery-detail lookups. * fix(discord): bound individual api requests An unbounded API request can outlive an update-chain lock. Bound each request so another holder cannot race a late edit. * fix(discord): defer long rate-limit waits Long rate-limit sleeps block delivery progress inside a worker. Return a retryable 429 for the queue when the wait exceeds the bound. * fix(discord): encode channel path segments Stored channel and message ids are path segments, not URL paths. Encode them so aliases cannot address another Discord resource. * fix(discord): reuse nonces after lost responses A successful create may lose its response. Reuse a stable nonce with enforce_nonce so retries recover that message instead of posting duplicates or accepting an unreadable success. * fix(discord): constrain embeds and role mentions Respect combined embed and component limits as well as field caps. Restrict allowed mentions to validated route roles so payload text cannot notify everyone. * fix(discord): resume bounded command syncs Application changes, command rollbacks and large guild lists can leave commands stale indefinitely. Track the current hash per app and resume bounded paginated work without needless KV writes. * fix(github): verify installation management An installation id is user-controlled, and repository access is not installation management. Verify the owning account or an active organization admin using the user token and read:org scope. * fix(github): resolve immutable member ids A login can be renamed and reclaimed before its first sign-in. Resolve the current immutable user id when membership is granted so a future holder of the login cannot inherit access. * fix(auth): revoke stale sessions and tokens Revoked or rotated credentials must stop working despite stale KV replicas. Track the live token and revocations in D1 and preserve immutable identity bindings rather than trusting a recycled login. * fix(auth): bind sessions and tokens to identity Automatic retries can repeat non-idempotent user actions. Disable those retries and expose a write hook so bot handlers can record completion immediately before the GitHub write. * fix(discord): defer and deduplicate interactions Acknowledge slow actions before Discord times out and deduplicate interaction writes. Preserve comment text and reject edits whose source changed after the modal opened. * fix(telegram): always verify webhook secrets Webhook verification must not silently disable itself when the optional secret is absent. Derive a stable secret from the bot token and reject callbacks when verification is unavailable. * fix(telegram): bound individual api requests Bound individual platform calls so they cannot outlive the lock protecting a message update or stall a whole delivery invocation. * fix(telegram): honor nested rate-limit delays Telegram places retry_after inside parameters, not at the top level. Read that value and defer long waits to the delivery queue. * fix(telegram): report unreadable send results An unreadable successful response may already have sent the message. Report an explicit uncertain result instead of retrying a create without an idempotency key or pretending it succeeded. * fix(telegram): keep editable messages as text Guessing photo versus text from message content makes later edits use the wrong API and a smaller caption budget. Always send text and use the avatar as a link preview. * fix(telegram): render hard breaks as newlines Telegram HTML does not support br tags. Render Markdown hard breaks as plain newlines so otherwise valid messages are accepted. * fix(telegram): clamp visible html characters Telegram counts visible characters, not HTML source bytes. Truncate without splitting tags, entities or surrogate pairs. * fix(telegram): honor the author emoji toggle The author marker must obey the group emoji preference just like formatter-added decoration. * fix(telegram): keep completed commands claimed Redelivery after a completed write must never post another comment. Keep completion claims despite reply failures, scope updates per bot and only issue account-login links in private chats. * fix(feishu): bound individual api requests Bound individual platform calls so they cannot outlive the lock protecting a message update or stall a whole delivery invocation. * fix(feishu): classify retryable api failures Business error codes can be transient even in HTTP 200 responses. Classify token and rate-limit errors for retry and defer long waits. * fix(feishu): retry sends with stable uuids An unreadable response does not prove a send failed. Reuse the same uuid for retries so recovering the result cannot create a second Feishu message. * fix(feishu): refresh and evict tokens safely Separate app token caches, stop reusing refused tokens and share refreshes. Cache failures briefly and keep valid tokens in memory when a best-effort KV cache write fails. * fix(feishu): use the card update endpoint Delayed card updates use the card update endpoint; the config endpoint cannot update an interaction response. * fix(feishu): neutralize untrusted mentions Forge text is untrusted and can contain at-all tags. Neutralize mentions in card bodies and footers before rendering. * fix(feishu): authenticate and dedupe callbacks Authenticate signed or token-verified callbacks before dispatching commands. Decode encrypted envelopes and handle card actions using the correct fields without claiming irrelevant chat events. * fix(target): normalize actual destinations Different target spellings can name the same actual destination. Normalize channel, thread and topic identities for ownership checks and per-route duplicate suppression. * fix(config): transact per-group configuration Whole-table writes and cached snapshots can overwrite other groups or resurrect removed configuration. Use per-group guarded writes, one-time identity migration and explicit unreadable-row failures. * fix(group): preserve identity through lifecycle Group names are mutable and reusable, so they cannot own durable state. Preserve immutable identities across lifecycle operations and commit invite use with membership under transaction-time guards. * fix(oauth): confirm account links and installs A login link or installation id is not proof of account ownership. Verify installation management, bind browser state and require an explicit account-link confirmation before granting chat access. * fix(queue): fence leases and record target outcomes Retries must remember completed targets and distinguish active lease holders. Fence state updates, preserve permanent outcomes and reject missing parked payloads instead of dispatching empty data. * fix(dispatch): isolate and resume tenant sends Check tenant sources before filters and never dispatch orphan routes. Record each target outcome, isolate update chains by forge and group identity, and keep stale events from overwriting newer messages. * fix(queue): bound batches and resume deliveries A queue invocation has shared query and subrequest limits. Use a small batch and shared send budget, renew fenced leases and resume only unfinished work without exhausting unstarted messages. * fix(admin): guard revisions and tenant targets Read-time authorization alone cannot protect concurrent edits. Guard revisions, current roles and destination ownership in the write transaction, and use per-group endpoints for isolated changes. * fix(webhook): confirm only accepted deliveries Acknowledging before queue acceptance permanently loses deliveries. Confirm only accepted work, release failed claims, scope replay identities and strip tenant-supplied installation authority. * fix(storage): prune abandoned parked payloads Oversized payloads can remain after interrupted enqueue attempts. Prune objects beyond their retry lifetime without deleting payloads that a current delivery may still need. * fix(console): expose api conflict statuses Callers need the HTTP status to distinguish stale edits from other failures and reload current data after a conflict. * refactor(console): model group revisions Carry server revisions explicitly so console writes can reject changes based on an outdated group snapshot. * fix(console): send loaded route revisions Send the revision actually loaded with the route list and adopt the server response after a save. Reload on conflict instead of silently overwriting another editor. * fix(console): guard fragment saves by revision Fragments share a group version with other configuration writes. Submit the loaded revision and reload on conflict to preserve concurrent edits. * fix(console): save groups with guarded writes Whole-list saves can overwrite unrelated groups. Use per-group revision-aware writes, retain rename results and confirm deletion on the exact group, routes and version shown to the user. * fix(console): reject edits of stale routes A conflict reload can leave an older route editor open. Compare its original value before saving so it cannot overwrite the newly loaded route. * fix(console): show overview loading failures Failed overview requests must not look like an empty dashboard or a successful refresh. Show the reason while retaining prior data. * fix(console): explain rejected install bindings Explain why an installation binding was refused instead of silently returning to the console with no visible outcome. * fix(console): allow selecting a group named all The all sentinel collides with a valid group id. Use a value that cannot be a group id so that group stays selectable. * fix(console): discard stale log detail responses An older detail request can finish after a newer selection or close. Discard it so the dialog never shows the previously clicked record. * fix(console): retain legacy group owners Groups predating member roles store owners in adminIds. Load those as owners so adding a member never drops all old owners. * fix(console): lock member edits during saves Edits made during a save are overwritten by its result. Disable member controls and guard handlers until the write settles. * fix(console): show invite loading failures Failed invite loads must not look like no pending invites. Show the error and discard responses from a previously shown group. * fix(console): retain legacy discord log targets A stored log target without platform means Discord. Keep that meaning in the editor instead of clearing the target. * fix(console): retain undisplayed forge sources An editor that only displays some providers must preserve the others. Keep stored custom sources when saving unrelated group settings. * fix(console): lock the group editor while saving Prevent edits while a group save is in flight and make super-only installation settings readonly instead of silently ignoring edits. * fix(console): lock route edits and show failures Lock the route editor while saving and show fragment load failures with a retry action rather than presenting a false empty list. * fix(config): expose the legal contact override Declare the public runtime key so the documented environment override reaches legal pages in deployed Nuxt builds. * build(deploy): migrate d1 before deployment Apply pending D1 migrations before deploying code that requires them. Stop deployment when migration fails instead of running against an incomplete schema. * docs(worker): align guides with runtime behavior Synchronize both language guides, API references and examples with the implemented authorization, storage and delivery behavior. Document migration requirements and accepted operational limits. * fix(storage): repair orphaned KV routes Repair orphaned KV routes before serving KV-only configuration. * fix(security): fully escape forge HTML --------- Co-authored-by: RhenCloud <i@rhen.cloud>
427 lines
17 KiB
TypeScript
427 lines
17 KiB
TypeScript
import type { H3Event } from "h3";
|
|
import { getHeader, readRawBody, setResponseStatus } from "h3";
|
|
import type { Env, Group } from "./types";
|
|
import { detectProvider } from "./providers";
|
|
import { dispatchEvent } from "./core/dispatch";
|
|
import { loadConfigSnapshot, loadGroupFresh, initConfigStore } from "./config";
|
|
import { ensureInstallationGroup } from "./web/groups";
|
|
import { getTenantSecret } from "./web/tenants";
|
|
import { NONCE_TTL_SECONDS, ReplayPendingError, replayNonceKey } from "./providers/custom";
|
|
import { recordAudit } from "./lib/audit";
|
|
import { cfEnv, cfWaitUntil, headersFrom } from "./cf";
|
|
import { log } from "./lib/log";
|
|
import { claimOnce, confirmClaim, deliveryKey, idempotencyStore } from "./lib/idempotency";
|
|
import { newCorrelationId } from "./lib/correlation";
|
|
import {
|
|
deliveryStateKey,
|
|
enqueueWebhook,
|
|
hadPermanentFailure,
|
|
isRetryableFailure,
|
|
markTargetsDone,
|
|
targetDoneChecker,
|
|
type DeliveryMessage,
|
|
} from "./queue/delivery";
|
|
|
|
const MAX_BODY_SIZE = 1024 * 1024;
|
|
/** How long a delivery's dedup claim lasts when it is queued. */
|
|
const QUEUED_CLAIM_SECONDS = 120;
|
|
/** How long it lasts for an inline dispatch, which may run for minutes. */
|
|
const INLINE_CLAIM_SECONDS = 600;
|
|
/** An installation's auto-provisioning is remembered as long as delivery state (7 days). */
|
|
const PROVISIONED_TTL_SECONDS = 7 * 86400;
|
|
/** Sending time of one inline dispatch: within its claim, with a margin. */
|
|
const INLINE_SEND_BUDGET_MS = 8 * 60_000;
|
|
|
|
/** Result of an inline dispatch: whether the sender should retry. */
|
|
interface InlineOutcome {
|
|
retry: boolean;
|
|
/** A target failed for good (in this or an earlier attempt). */
|
|
failed: boolean;
|
|
}
|
|
|
|
export interface WebhookResult {
|
|
status: 200 | 400 | 401 | 404 | 413 | 503;
|
|
body: unknown;
|
|
}
|
|
|
|
/**
|
|
* Core webhook processing. Without `tenantId` this is the legacy global
|
|
* endpoint (`POST /webhook`): events verify against the operator's global
|
|
* secrets and may dispatch into every route. With a `tenantId` (a group id,
|
|
* `POST /webhook/{groupId}`) the group's own secret is used for verification
|
|
* (GITHUB_WEBHOOK_SECRET/GITEA_WEBHOOK_SECRET are overridden per request) and
|
|
* only that group's routes are eligible.
|
|
*
|
|
* A tenant-signed payload is only as trustworthy as the tenant: its claimed
|
|
* GitHub App installation is dropped, so it can neither borrow the operator's
|
|
* App credentials nor provision or rebind installation groups.
|
|
*/
|
|
export async function processWebhook(
|
|
env: Env,
|
|
body: string,
|
|
headers: Record<string, string>,
|
|
waitUntil: (promise: Promise<unknown>) => void,
|
|
tenantId?: string,
|
|
): Promise<WebhookResult> {
|
|
const requestId = newCorrelationId();
|
|
let effectiveEnv = env;
|
|
initConfigStore(env);
|
|
// Until the request is verified, nothing but the receiving group's own row
|
|
// is read (fresh): an unsigned flood must not read the whole configuration
|
|
// each time. The full snapshot is read once the event is accepted.
|
|
const provider = detectProvider(headers);
|
|
if (!provider) {
|
|
return { status: 400, body: { error: "Unknown webhook provider" } };
|
|
}
|
|
let tenant: Group | undefined;
|
|
if (tenantId) {
|
|
const found = await loadGroupFresh(env, tenantId);
|
|
if (!found.group) {
|
|
// Unreadable is not missing: the sender is asked to retry.
|
|
if (found.unreadable) {
|
|
return { status: 503, body: { error: "Group configuration unreadable; retry later" } };
|
|
}
|
|
return { status: 404, body: { error: "Group not found" } };
|
|
}
|
|
tenant = found.group;
|
|
const secret = await getTenantSecret(env.KV, tenant);
|
|
if (!secret) {
|
|
return { status: 404, body: { error: "Webhook disabled for this group" } };
|
|
}
|
|
effectiveEnv = { ...env, GITHUB_WEBHOOK_SECRET: secret, GITEA_WEBHOOK_SECRET: secret };
|
|
}
|
|
|
|
let verified = false;
|
|
try {
|
|
verified = await provider.verify(body, headers, effectiveEnv);
|
|
} catch (err) {
|
|
if (err instanceof ReplayPendingError) {
|
|
// The nonce is held by an attempt not (yet) accepted: not a replay.
|
|
return { status: 503, body: { error: "Request is already being processed; retry later" } };
|
|
}
|
|
// A malformed secret or an unavailable crypto implementation must fail as
|
|
// a clean 401, never an uncaught 500.
|
|
log.warn(
|
|
{ provider: provider.id, requestId, err: String(err) },
|
|
"Webhook signature verification failed",
|
|
);
|
|
return { status: 401, body: { error: "Invalid signature" } };
|
|
}
|
|
if (!verified) {
|
|
// Log the actual cause: a missing provider secret is a deployment problem,
|
|
// while a mismatched signature usually means the sender used the wrong secret.
|
|
const secret =
|
|
provider.id === "gitea"
|
|
? effectiveEnv.GITEA_WEBHOOK_SECRET
|
|
: effectiveEnv.GITHUB_WEBHOOK_SECRET;
|
|
if (!secret) {
|
|
log.warn(
|
|
{ provider: provider.id, requestId },
|
|
"Webhook rejected: provider secret is not configured",
|
|
);
|
|
} else {
|
|
log.warn({ provider: provider.id, requestId }, "Webhook rejected: invalid signature");
|
|
}
|
|
return { status: 401, body: { error: "Invalid signature" } };
|
|
}
|
|
|
|
// From here on, one-time claims are held (the custom-webhook nonce taken
|
|
// by `verify`, the delivery dedup key). Only once the event is accepted
|
|
// (queued, or dispatched without a transient failure) are they confirmed;
|
|
// otherwise they are given back, so the sender's retry is not refused. A
|
|
// claim that could not be given back is never mistaken for an accepted
|
|
// event: a retry finds it unconfirmed and is asked to come back later.
|
|
const claims = idempotencyStore(env.DB, env.KV);
|
|
const held: { key: string; ttl: number }[] = [];
|
|
const nonce = headers["x-webhooker-nonce"];
|
|
if (provider.id === "custom" && nonce && headers["x-webhooker-timestamp"]) {
|
|
held.push({
|
|
key: await replayNonceKey(effectiveEnv.GITHUB_WEBHOOK_SECRET, nonce),
|
|
ttl: NONCE_TTL_SECONDS,
|
|
});
|
|
}
|
|
const releaseClaims = async (): Promise<void> => {
|
|
for (const { key } of held.splice(0)) {
|
|
await claims.release(key).catch((err: unknown) => {
|
|
log.warn({ requestId, key, err }, "Failed to release a webhook claim");
|
|
});
|
|
}
|
|
};
|
|
const confirmClaims = async (): Promise<void> => {
|
|
for (const { key, ttl } of held.splice(0)) {
|
|
// Unconfirmed, a claim only delays a duplicate until it expires.
|
|
await confirmClaim(claims, key, ttl).catch((err: unknown) => {
|
|
log.warn({ requestId, key, err }, "Failed to confirm a webhook claim");
|
|
});
|
|
}
|
|
};
|
|
const retryLater = (error: string): WebhookResult => ({
|
|
status: 503,
|
|
body: { error, requestId },
|
|
});
|
|
|
|
try {
|
|
const event = provider.parse(body, headers);
|
|
if (!event) {
|
|
await releaseClaims();
|
|
return { status: 400, body: { error: "Invalid event" } };
|
|
}
|
|
if (tenantId) event.installationId = undefined;
|
|
|
|
// Dedup via the idempotency store: a provider/tenant-scoped key means
|
|
// different accounts may reuse a delivery id without colliding, while
|
|
// retries of the same delivery never dispatch twice. An inline dispatch
|
|
// holds its claim for as long as it may run.
|
|
// A custom sender's ids are namespaced (`d:`) as its delivery identity is
|
|
// below: no id it picks can take the key of a nonce-identified request.
|
|
const dedupKey = event.deliveryId
|
|
? deliveryKey(
|
|
provider.id,
|
|
tenantId,
|
|
provider.id === "custom" ? `d:${event.deliveryId}` : event.deliveryId,
|
|
tenant?.instance,
|
|
)
|
|
: null;
|
|
if (dedupKey) {
|
|
const ttl = env.QUEUE ? QUEUED_CLAIM_SECONDS : INLINE_CLAIM_SECONDS;
|
|
const state = await claimOnce(claims, dedupKey, ttl);
|
|
if (state === "done") {
|
|
// Already accepted: this request's own nonce is used up as well.
|
|
await confirmClaims();
|
|
return { status: 200, body: { ok: true, duplicate: true, requestId } };
|
|
}
|
|
if (state === "pending") {
|
|
// Still in flight elsewhere, or left over from an attempt that was
|
|
// not accepted: the event may not be on its way yet.
|
|
await releaseClaims();
|
|
return retryLater("Delivery is already being processed; retry later");
|
|
}
|
|
held.push({ key: dedupKey, ttl });
|
|
}
|
|
|
|
// Provisioning runs only for an event not yet accepted (a duplicate
|
|
// returned above): a redelivery must not redo a binding an admin undid.
|
|
// Auto-provision GitHub App installations so tenant isolation is
|
|
// configured without manual id entry: a group is created (or existing
|
|
// matching groups are bound) before the event is dispatched. Only events
|
|
// signed with the operator's own secret (the global endpoint) may do this.
|
|
if (
|
|
!tenantId &&
|
|
provider.id === "github" &&
|
|
event.event === "installation" &&
|
|
event.payload.action === "created" &&
|
|
event.installationId != null
|
|
) {
|
|
const install = event.payload.installation as { account?: { login?: string } } | undefined;
|
|
const account = install?.account?.login ?? "";
|
|
// Done once per installation, on record as long as delivery state is
|
|
// kept: a redelivery after the dedup claim lapsed (minutes) must not
|
|
// redo a binding an admin undid since. Recorded only once it succeeded,
|
|
// so a provisioning that failed midway is completed by the retry.
|
|
const doneKey = `installation-provisioned:${event.installationId}`;
|
|
try {
|
|
if (!(await claims.has(doneKey))) {
|
|
const group = await ensureInstallationGroup(
|
|
env.KV,
|
|
event.installationId,
|
|
account,
|
|
env.DB,
|
|
);
|
|
await claims.claim(doneKey, PROVISIONED_TTL_SECONDS);
|
|
if (group) {
|
|
await recordAudit(env.DB, {
|
|
ts: Date.now(),
|
|
actorLogin: account || undefined,
|
|
action: "installation.created",
|
|
targetType: "group",
|
|
targetId: group.id,
|
|
groupId: group.id,
|
|
groupInstance: group.instance,
|
|
});
|
|
}
|
|
}
|
|
} catch (err) {
|
|
// Not accepted: the consumer never provisions, so a sender retry is
|
|
// the only way the group gets created (provisioning is idempotent).
|
|
log.warn(
|
|
{ err, installationId: event.installationId },
|
|
"Failed to auto-provision installation group",
|
|
);
|
|
await releaseClaims();
|
|
return retryLater("Installation provisioning failed; retry later");
|
|
}
|
|
}
|
|
|
|
// A stable identity across the sender's retries: the delivery id, else the
|
|
// replay-protection nonce of a signed request. Queued or inline, it keys
|
|
// the delivery's state and target ledger, so a retry of a request whose
|
|
// first attempt went through after all is recognized, not sent again.
|
|
// A custom sender picks its delivery ids freely: they get a namespace of
|
|
// their own, so none can coincide with a nonce-derived identity.
|
|
const nonceKey = held.find((h) => h.key.startsWith("nonce:"))?.key;
|
|
const identity =
|
|
event.deliveryId != null
|
|
? provider.id === "custom"
|
|
? `d:${event.deliveryId}`
|
|
: event.deliveryId
|
|
: nonceKey
|
|
? `n:${nonceKey}`
|
|
: undefined;
|
|
|
|
// Inline, a request identified by its nonce alone is held for the whole
|
|
// dispatch, as a delivery id is above: its nonce claim is short (shorter
|
|
// than a long dispatch), and a copy arriving meanwhile must not send the
|
|
// targets not yet on the ledger a second time.
|
|
if (!env.QUEUE && event.deliveryId == null && identity) {
|
|
const key = deliveryKey(provider.id, tenantId, identity, tenant?.instance);
|
|
const state = await claimOnce(claims, key, INLINE_CLAIM_SECONDS);
|
|
if (state === "done") {
|
|
await confirmClaims();
|
|
return { status: 200, body: { ok: true, duplicate: true, requestId } };
|
|
}
|
|
if (state === "pending") {
|
|
await releaseClaims();
|
|
return retryLater("Delivery is already being processed; retry later");
|
|
}
|
|
held.push({ key, ttl: INLINE_CLAIM_SECONDS });
|
|
}
|
|
|
|
if (env.QUEUE) {
|
|
const message: DeliveryMessage = {
|
|
deliveryId: identity ?? requestId,
|
|
groupId: tenantId,
|
|
groupInstance: tenant?.instance,
|
|
provider: provider.id,
|
|
event: event.event,
|
|
payload: event.payload,
|
|
installationId: event.installationId,
|
|
receivedAt: Date.now(),
|
|
requestId,
|
|
stateVersion: 2,
|
|
};
|
|
// Acknowledge only once the event is durably queued.
|
|
await enqueueWebhook(env, message);
|
|
await confirmClaims();
|
|
return { status: 200, body: { ok: true, requestId } };
|
|
}
|
|
|
|
// Inline dispatch (no queue): there is no durable retry, so the sender
|
|
// is answered only after the dispatch, and asked to retry while a target
|
|
// failed transiently. A delivery id gets a target ledger, so targets
|
|
// already sent are skipped when the sender redelivers.
|
|
// One consistent snapshot of routes and groups serves the dispatch — read
|
|
// fresh: a route or target removed moments ago in another isolate must
|
|
// not still be dispatched to from this isolate's cache.
|
|
const snapshot = await loadConfigSnapshot(env, { fresh: true });
|
|
if (tenantId) {
|
|
const current = snapshot.groups.find((g) => g.id === tenantId);
|
|
if (!current || current.instance !== tenant?.instance) {
|
|
// Gone or replaced since its row was read: not this group's event now.
|
|
await releaseClaims();
|
|
if (snapshot.config.unreadableGroups?.includes(tenantId)) {
|
|
return retryLater("Group configuration unreadable; retry later");
|
|
}
|
|
return { status: 404, body: { error: "Group not found" } };
|
|
}
|
|
}
|
|
const scoped = tenantId
|
|
? {
|
|
...snapshot.config,
|
|
routes: snapshot.config.routes.filter((r) => r.groupId === tenantId),
|
|
}
|
|
: snapshot.config;
|
|
const ledgerKey = identity
|
|
? deliveryStateKey(provider.id, tenantId, identity, tenant?.instance)
|
|
: null;
|
|
const run = (async (): Promise<InlineOutcome> => {
|
|
const recorded = new Set<string>();
|
|
// Dispatched under the delivery's identity (as a queued copy is), so the
|
|
// platform idempotency keys stay the same when the sender retries.
|
|
const delivered = identity ? { ...event, deliveryId: identity } : event;
|
|
// Sending stops well before the claim held for this dispatch expires
|
|
// (a target takes under a minute at worst): a copy arriving after that
|
|
// could otherwise send the targets still in flight. What is left is a
|
|
// transient failure, so the sender retries it (the ledger skips the rest).
|
|
const sendUntil = Date.now() + INLINE_SEND_BUDGET_MS;
|
|
const summary = await dispatchEvent(scoped, delivered, env, snapshot.groups, {
|
|
tenantId,
|
|
beforeTarget: async (): Promise<boolean> => Date.now() < sendUntil,
|
|
skipTarget: ledgerKey ? targetDoneChecker(env, ledgerKey) : undefined,
|
|
afterTarget: ledgerKey
|
|
? async (targetKey): Promise<void> => {
|
|
await markTargetsDone(env, ledgerKey, [targetKey]);
|
|
recorded.add(targetKey);
|
|
}
|
|
: undefined,
|
|
});
|
|
const permanent = summary.failures.filter((f) => !isRetryableFailure(f));
|
|
if (ledgerKey) {
|
|
await markTargetsDone(
|
|
env,
|
|
ledgerKey,
|
|
[...(summary.succeeded ?? []), ...permanent.flatMap((f) => f.key ?? [])].filter(
|
|
(k) => !recorded.has(k),
|
|
),
|
|
{ permanentFailure: permanent.length > 0 },
|
|
);
|
|
}
|
|
// A transient failure is always retried: without a ledger the retry
|
|
// sends the other targets again too — duplicates rather than a loss.
|
|
return {
|
|
retry: summary.failures.some(isRetryableFailure),
|
|
// Targets that failed for good in an earlier attempt still count.
|
|
failed:
|
|
permanent.length > 0 ||
|
|
(ledgerKey != null && (await hadPermanentFailure(env, ledgerKey))),
|
|
};
|
|
})();
|
|
// The dispatch keeps running should the sender hang up meanwhile.
|
|
waitUntil(run.catch(() => undefined));
|
|
let outcome: InlineOutcome;
|
|
try {
|
|
outcome = await run;
|
|
} catch (err) {
|
|
log.error({ requestId, err }, "Dispatch failed");
|
|
await releaseClaims();
|
|
return retryLater("Dispatch failed; retry later");
|
|
}
|
|
if (outcome.retry) {
|
|
log.warn({ requestId }, "Inline dispatch failed transiently");
|
|
await releaseClaims();
|
|
return retryLater("Some targets failed temporarily; retry later");
|
|
}
|
|
await confirmClaims();
|
|
// Accepted for good; a target that can never take the event is reported.
|
|
return outcome.failed
|
|
? { status: 200, body: { ok: true, requestId, failed: true } }
|
|
: { status: 200, body: { ok: true, requestId } };
|
|
} catch (err) {
|
|
log.error({ requestId, err }, "Failed to accept webhook");
|
|
await releaseClaims();
|
|
return retryLater("Temporarily unable to accept webhook");
|
|
}
|
|
}
|
|
|
|
/** h3 wrapper for `POST /webhook` / `POST /webhook/:groupId`. */
|
|
export async function handleWebhookRequest(event: H3Event, tenantId?: string): Promise<unknown> {
|
|
const contentLength = Number(getHeader(event, "content-length") ?? 0);
|
|
if (contentLength > MAX_BODY_SIZE) {
|
|
setResponseStatus(event, 413);
|
|
return { error: "Request too large" };
|
|
}
|
|
const body = (await readRawBody(event, "utf8")) ?? "";
|
|
if (body.length > MAX_BODY_SIZE) {
|
|
setResponseStatus(event, 413);
|
|
return { error: "Request too large" };
|
|
}
|
|
const result = await processWebhook(
|
|
cfEnv(event),
|
|
body,
|
|
headersFrom(event),
|
|
cfWaitUntil(event),
|
|
tenantId,
|
|
);
|
|
setResponseStatus(event, result.status);
|
|
return result.body;
|
|
}
|