sneak/webhooker
1
0
Fork 0
Code Issues 12 Pull Requests 3 Actions 37 Packages Projects Releases Wiki Activity

Compare commits

base: sneak/webhooker:3ddc1a3a021244a377cd8b21981f13e161b18634
Branches Tags
sneak/webhooker:main sneak/webhooker:next sneak/webhooker:issue-535-query-log-comment sneak/webhooker:issue-539-retention-day-count sneak/webhooker:issue-540-max-attempts sneak/webhooker:prod sneak/webhooker:issue-70-log-target
sneak/webhooker:v1.0.0-rc1
...
compare: sneak/webhooker:issue-540-max-attempts
Branches Tags
sneak/webhooker:next sneak/webhooker:issue-535-query-log-comment sneak/webhooker:issue-539-retention-day-count sneak/webhooker:issue-540-max-attempts sneak/webhooker:main sneak/webhooker:prod sneak/webhooker:issue-70-log-target
sneak/webhooker:v1.0.0-rc1
10 Commits
3ddc1a3a02 ... issue-540-max-attempts
Author SHA1 Message Date
sneak 14a38df093 Store a target's number of delivery attempts, at least one (closes #540)
check / check (push) Waiting to run
Details 
Target.MaxRetries (max_retries) becomes Target.MaxAttempts
(max_attempts), and the form field, parser and ceiling are renamed to
match. 1 is a single attempt with no circuit breaker; above 1 retries
behind the breaker up to that many attempts. Both target forms refuse
0 and less; a blank field on the add target form gives 1, and on the
edit form keeps the stored value. The target page shows the plain
number, and the README's two paragraphs on 0 against 1 become one
sentence.

Model: opus-5-5
 2026-10-15 11:34:18 +00:00
clawbot c0f7cc29fd Leave a delivery cut off by a stop for the next start (closes #527)
check / check (push) Waiting to run
Details 
Stopping the engine cancels the context every http and slack request is
sent with. An attempt cut off that way was recorded as failed, which for
a target with no retries, or on a last retry, ended the delivery failed
and nothing sent it again.

The shared retry core now records nothing for a failed attempt when the
engine's context is cancelled: no result, no circuit breaker outcome, no
status change, no count in the attempt metrics. The delivery stays
pending or retrying and startup recovery sends it again. A target's own
timeout is still a failed attempt. The README says what happens to an
attempt in flight at a stop and no longer claims every attempt is
recorded.

Model: opus-5-5
 2026-10-15 12:29:17 +02:00
clawbot f14fe02011 Store delivery and archive times without the monotonic reading (closes #529)
check / check (push) Waiting to run
Details 
finished_at, archived_at and the updated_at stamp a re-dispatch
writes came from a bare time.Now(). The SQLite driver stores a time
as time.Time.String(), which appends the monotonic clock reading
(" m=+…") to a time read from time.Now(). All three now come from
GORM's own clock, NowFunc(), which stamps created_at, so they are
stored in the same form. The tests for each write read the stored
text back.

Model: opus-5-5
 2026-10-15 11:15:35 +02:00
clawbot 573f7f986a Build the image's static binary with netgo, osusergo and sqlite_omit_load_extension (closes #525)
check / check (push) Successful in 7m24s
Details 
The image's static relink linked glibc's getaddrinfo (from Go's cgo DNS
resolver) and dlopen (from SQLite extension loading). A static binary
still needs glibc's shared libraries at run time for both, and the
Alpine runtime has none. The relink now passes the standard build tags
netgo, osusergo and sqlite_omit_load_extension through a GO_TAGS
variable, which the Makefile's build target hands to go build as -tags
next to GO_LDFLAGS, so the version stamp is composed as before.

Model: opus-5-5
 2026-10-13 10:43:47 +02:00
clawbot 373a2f828d Describe code in its own terms, not by an earlier build's data (closes #522)
check / check (push) Successful in 8m12s
Details 
Several comments justified code by what an earlier build would have
left in a database or on disk. Each now says what the code does:
reserveSQLiteFile sets the mode on every open whoever created the
file, and expired treats a session lacking a deadline's timestamp as
expired. The comments on retention, resubmitted events, archive
pruning, target headers, the redactor and the delivery result view
drop their mentions of older rows. parseMaxRetries loses its
paragraph on targets saved before the ceiling existed, and neither
BeforeSave nor retentionCutoff cites a migration. Comments only.

Model: opus-5-5
 2026-10-13 09:57:24 +02:00
clawbot 267d5b12f2 Escape the database path in the SQLite connection string (closes #518)
check / check (push) Successful in 7m13s
Details 
SQLite reads a file: URI's path only up to the first ? or #, and
decodes %XX escapes in it. With a data directory such as
/srv/hooks#1, every database opened the one file /srv/hooks. The
connection string is now built with url.URL, which escapes the path,
and OmitHost keeps a relative path relative.

Tests open databases in a directory whose name holds #, ? and %, and
at a relative path, and check through PRAGMA database_list that each
opened the file asked for. A handlers test comment that blamed # in
the temporary directory's path is dropped, as that is no longer true.

Model: opus-5-5
 2026-10-13 09:30:24 +02:00
clawbot e73beb20df Remove upgrade and older-build text from the README (closes #520)
check / check (push) Canceled after 0s
Details 
The schema comes from 001_schema.sql, edited in place before 1.0, so the
README's upgrade procedure, downgrade note, BIND_ADDRESS upgrade note and
remarks about what older builds wrote are removed.

The description of the SQL schema files moves to a new Schema subsection
under Database Architecture, the health check command moves to Version
stamping, and the section is renamed Backup and Restore. The sentences on
session timestamps, file modes and the retention clamp now say only what
the code does.

Model: opus-5-5
 2026-10-13 08:31:51 +02:00
clawbot c8efbd41d4 Drop Completed Steps from TODO.md; the tracker is the record (closes #112)
check / check (push) Canceled after 0s
Details 
Every issue branch added an entry to the same list, so each branch
conflicted with `next` as soon as another one landed. The tracker already
records what is done, in more detail than the list did.

The Workflow section now says the tracker is that record, in place of the
rule that issue branches leave this file alone. Status points to the 1.0.0
milestone for what is open, and Next Step says @sneak tags `v1.0.0` after
running webhooker in limited production. In Future Steps, each item that
overlaps with what webhooker already does now says what exists and what is
still missing, and the delivery status and retry UI item is gone because the
event log, replay and resubmit cover it.

Model: opus-5-5
 2026-10-13 07:18:48 +02:00
clawbot 15377f792b Build every database's schema from embedded SQL files (closes #56)
check / check (push) Canceled after 0s
Details 
The main database, each webhook's event database and each archive file
get their schema from SQL files under internal/db/migrations/, one
directory per kind. Opening a file runs, in one transaction, each file
that schema_migrations does not list. GORM stays for queries.
AutoMigrate is gone, tests included.

An event database holds only its own tables now, so the sweep that
removed target rows copied into it is deleted. The association guard
stays: without it a delivery write fails on the missing targets table.

AutoMigrate also had GORM parse every model before a handle was shared.
That is now done on its own: GORM races when two goroutines first use
models that refer to each other.

Model: opus-5-5
 2026-10-13 06:34:05 +02:00
clawbot f86ab6321d Name Sentry transactions after the route they matched (closes #185)
check / check (push) Successful in 8m52s
Details 
sentryhttp names each transaction after the concrete path, which the
BeforeSendTransaction hook has to withhold, so with tracing on the
transactions would fall into one Sentry group per method, such as
POST /(redacted). A middleware installed beside every sentryhttp
handler now renames the transaction to the method and chi route
pattern once the request is routed, and sets its source to route. The
hook keeps a route-sourced name and withholds every other name as
before. A path that matches nothing at the top level keeps the
withheld name; one that matches no route inside a route group, or
that the group's middleware turns away, is named after the group's
pattern, such as GET /pages/*. Tracing stays off.

Model: opus-5-5
 2026-10-13 05:47:26 +02:00
77 changed files with 2218 additions and 1879 deletions
Expand all files Collapse all files
Dockerfile
+15 -9
View File
@@ -214,16 +214,22 @@ RUN version="$(make version VERSION="$VERSION")"; \
# (Alpine.js, extracted from its tarball in 3p/) first.
RUN make build VERSION="$VERSION"
# Rebuild with static linking for Alpine runtime.
# make build already verified compilation.
# The CGO binary from `make build` is dynamically linked against glibc,
# which doesn't exist on Alpine (musl). Rebuild with static linking so
# the binary runs on Alpine without glibc.
# Rebuild with static linking for the Alpine runtime. The cgo binary the
# step above builds is dynamically linked against glibc, which Alpine
# (musl) does not have.
#
# The static flags go in through GO_LDFLAGS rather than a -ldflags of
# their own: the build target composes them with the -X that stamps the
# version, so this relink cannot silently drop the stamp.
RUN CGO_ENABLED=1 make build VERSION="$VERSION" GO_LDFLAGS='-extldflags "-static"'
# A statically linked glibc still loads shared libraries at run time for
# getaddrinfo and dlopen, and Alpine has none to load, so the build tags
# keep both out of the binary: netgo and osusergo select Go's own DNS
# resolver and user lookup instead of glibc's, and
# sqlite_omit_load_extension leaves out SQLite extension loading, which
# webhooker never uses.
#
# The static flags and tags go in through GO_LDFLAGS and GO_TAGS rather
# than a -ldflags of their own: the build target composes them with the
# -X that stamps the version, so this relink cannot silently drop the
# stamp.
RUN CGO_ENABLED=1 make build VERSION="$VERSION" GO_TAGS=netgo,osusergo,sqlite_omit_load_extension GO_LDFLAGS='-extldflags "-static"'
# Runtime stage
# alpine:3.21, 2026-03-17
Makefile
+6 -4
View File
@@ -16,14 +16,16 @@ VERSION ?= $(shell script/version)
# exists to correct.
override VERSION := $(or $(strip $(VERSION)),$(shell script/version))
# Extra linker flags for the build target. The static relink in the
# Dockerfile adds -extldflags here rather than passing its own -ldflags,
# so composing flags cannot drop the version stamp.
# Extra linker flags and build tags for the build target. The static
# relink in the Dockerfile passes -extldflags and its build tags through
# these rather than a -ldflags of its own, so composing flags cannot drop
# the version stamp.
#
# The build target itself always passes -trimpath and -s -w, as the Go
# Dockerfile in REPO_POLICIES.md does: no build paths, symbol table or
# debug information in the binary.
GO_LDFLAGS ?=
GO_TAGS ?=
bootstrap:
@script/bootstrap
@@ -53,7 +55,7 @@ check:
@script/check
build: assets
go build -trimpath -ldflags '$(strip -s -w -X main.version=$(VERSION) $(GO_LDFLAGS))' -o bin/webhooker ./cmd/webhooker
go build -trimpath -tags '$(GO_TAGS)' -ldflags '$(strip -s -w -X main.version=$(VERSION) $(GO_LDFLAGS))' -o bin/webhooker ./cmd/webhooker
run: build
./bin/webhooker
README.md
+130 -149
View File
@@ -465,10 +465,7 @@ idle timestamp is rewritten at most once per tenth of the idle window rather
than on every request, which means a session may expire up to 10% early relative
to the user's true last request, but never late.
Both clocks are anchored by timestamps stored in the session cookie. Sessions
issued before this feature existed carry neither, so they are treated as
expired: upgrading to a build that has it logs every existing session out once,
and those users sign in again.
Both clocks are anchored by timestamps stored in the session cookie.
#### Invalid values abort startup
@@ -702,11 +699,11 @@ app as that user.
`webhooker.db` holds target configuration in plaintext — bearer tokens, API
keys, Slack webhook URLs — along with the session encryption key, so webhooker
creates every SQLite file it owns `0600`: each database and both of its `-wal`
and `-shm` sidecars, across all three tiers. Files an earlier build left `0644`
are tightened when they are opened. The directory's `0750` is defence in depth —
it stops other local users listing the directory and learning your webhook UUIDs
from the `events-{uuid}.db` filenames — not the barrier protecting the
credentials.
and `-shm` sidecars, across all three tiers. Any of them found at another mode
is set to `0600` when the database is opened. The directory's `0750` is defence
in depth — it stops other local users listing the directory and learning your
webhook UUIDs from the `events-{uuid}.db` filenames — not the barrier protecting
the credentials.
### Running under upaas
@@ -918,7 +915,7 @@ replaces the `max-age` it stored, so to end the policy sooner, set a short
`HSTS_MAX_AGE` such as `1s` and keep it until returning browsers have picked it
up, or have a reverse proxy send `max-age=0`.
## Backup, Restore, and Upgrades
## Backup and Restore
### What to back up
@@ -1071,59 +1068,14 @@ beside it, or wait until there are none.
4. Start the service. The container gives the directory and the restored files
to the `webhooker` user before the app starts, whoever restored them (see
[Running with Docker](#running-with-docker)). `AutoMigrate` runs against each
restored database as it is opened.
### Upgrades
**Back up before every upgrade.** Every start runs GORM `AutoMigrate`
unconditionally against whatever files it finds:
- the main database on connect — `Setting`, `User`, `APIKey`, `Webhook`,
`Entrypoint`, `Target`
- each event database when it is lazily opened — `Event`, `Delivery`,
`DeliveryResult`, `EventTotals`, `TargetTotals`, `EntrypointTotals`
- each archive database on every open and reopen
There is no schema version table, no migration ledger, and no down migrations.
Nothing in the files records which version wrote them, and no code path undoes a
migration.
Upgrade procedure:
1. Stop the service.
2. Back up `DATA_DIR` using one of the procedures above.
3. Pull the new image and start it.
4. Confirm `database migrations completed` in the logs before putting traffic
back on it.
5. Confirm the new build is the one running:
`curl -s http://host:8080/.well-known/healthcheck` reports the version it was
stamped with (see [Version stamping](#version-stamping)).
**Upgrading past the introduction of `BIND_ADDRESS`:** earlier versions always
bound every interface. **Container deployments are unaffected** — the image
ships `ENV BIND_ADDRESS=0.0.0.0`, so a `docker run` or Compose service that
worked before still works with nothing changed.
A **bare binary** is the case that changes: the listener now binds `127.0.0.1`
unless `BIND_ADDRESS` says otherwise, so a deployment that relied on reaching it
from another host becomes unreachable until it sets the address the proxy
connects to. Check the `bindAddress` field of the startup log to see what a
running process bound. See [Bind address](#bind-address).
**Downgrade is unsupported.** Once a newer binary has migrated the files there
is no way to move them back. `AutoMigrate` is additive — it adds tables, columns
and indexes and never drops or rewrites them — so an older binary will generally
open migrated files and appear to work while writing against a schema it does
not know about. The failure mode is silent divergence, not a startup error. The
only supported way back to an older version is restoring the pre-upgrade backup,
which discards everything received since that backup was taken.
[Running with Docker](#running-with-docker)).
### Version stamping
The binary reports its version at `/.well-known/healthcheck` (the `version`
field), in the UI footer, and in the startup log line (`msg=starting`,
`version=...`). It is also the Sentry release name, as `webhooker-{version}`.
`curl -s http://host:8080/.well-known/healthcheck` shows which build is running.
The value is stamped in at build time by the linker; it is not read from a file
at runtime, so it identifies the build itself.
@@ -1182,26 +1134,6 @@ at rest and restrict who can read them.
- `events-{uuid}.db` and `archive-….db` hold the **full payload body and
headers** of every event as received, including whatever the sending service
put in them — tokens, signatures, personal data.
- Event databases written before
[issue #206](https://git.eeqj.de/sneak/webhooker/issues/206) was fixed **also
contain target credentials**: a GORM association upsert on the delivery and
retry write path copied `targets` rows, `config` included, into the
per-webhook database. For a Slack target the `webhookUrl` _is_ the bearer
credential, and an `http` target's URL can embed userinfo. This version never
writes those rows; the first time it opens such a file it deletes them and
vacuums the file, which removes the credential bytes rather than only
unlinking the rows. Deleting alone would not: the bytes stay readable in the
file's free pages until it is rewritten. The sweep is recorded in the file's
`user_version` only once the vacuum returns, so a sweep that fails or is
interrupted fails the open and is retried on the next one, and a file this
version has opened without error holds no leaked rows and no recoverable bytes
from them. On upgrade this rewrites each existing `events-{uuid}.db` once, on
its first open. Two cases still hand over live delivery destinations: a backup
taken from an older build, and a backup of a file this version has not yet
opened successfully. Copies already made stay affected — the sweep only
rewrites the file it opens, and freed blocks may persist in filesystem
snapshots and on the underlying storage. Rotate any target credential that was
in a backup you cannot account for.
- `webhooker.db` stores target config **unencrypted**, tracked at
[issue #212](https://git.eeqj.de/sneak/webhooker/issues/212), next to the
session encryption key and the Argon2id password hashes.
@@ -1385,20 +1317,22 @@ webhooker solves this by acting as a durable intermediary:
nothing is lost if downstream targets are unavailable.
2. **Guaranteed delivery** — Events are queued for delivery to each configured
target. Failed deliveries are retried with configurable backoff. Every
delivery attempt is logged with status codes, response bodies, and timing.
target. Failed deliveries are retried with configurable backoff. Delivery
attempts are logged with status codes, response bodies, and timing.
**That guarantee is at-least-once, not exactly-once.** When a send reaches
its target but the write recording that outcome fails, the delivery is
deliberately left in a recoverable state rather than marked done — losing a
delivery is the worse failure — so the pending sweep picks it up about
fifteen minutes later, or the next restart does, and the target receives a
payload it already got. webhooker adds no delivery identifier of its own to
an outbound request, so **make your receiver idempotent** against whatever
the payload itself carries.
payload it already got. A send still in flight when the service stops is
left the same way: its attempt is not recorded, and the next start sends it
again (see Shutdown). webhooker adds no delivery identifier of its own to an
outbound request, so **make your receiver idempotent** against whatever the
payload itself carries.
3. **Observability** — Full request/response logging for every webhook received
and every delivery attempted. Prometheus metrics expose volume, latency, and
and for delivery attempts. Prometheus metrics expose volume, latency, and
error rates. The web UI provides real-time visibility into event flow.
4. **Fan-out** — A single incoming webhook can be delivered to multiple targets
@@ -1602,8 +1536,7 @@ The cap is not arbitrary: the reaper computes its cutoff as a `time.Duration`,
an int64 nanosecond count, and a longer period overflows it. An overflowed
cutoff lands in the future, where it matches every row, so the sweep would
delete every event the webhook has instead of none. The reaper also clamps the
value it is given, so a row written by an older version cannot trigger that
either.
value it reads to the cap, so no stored value can trigger that either.
#### Entrypoint
@@ -1635,29 +1568,27 @@ did not arrive on the URL and counts in neither.
A delivery destination for events. Each target defines where and how events
should be forwarded.
| Field | Type | Description |
| ------------- | ---------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `id` | UUID | Primary key |
| `webhook_id` | UUID | Foreign key → Webhook |
| `name` | string | Human-readable name |
| `type` | TargetType | One of: `http`, `slack`, `database`, `log` |
| `active` | boolean | Whether deliveries are enabled (default: true) |
| `config` | JSON text | Type-specific configuration |
| `max_retries` | integer | Total delivery attempts for `http` and `slack` targets, not retries on top of the first: 0 is a single fire-and-forget attempt with no retries and no circuit breaker, and a value of N makes N attempts in all, with exponential backoff and a per-target circuit breaker. Ignored by `database` and `log` targets. The web UI labels it Delivery attempts |
| Field | Type | Description |
| -------------- | ---------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `id` | UUID | Primary key |
| `webhook_id` | UUID | Foreign key → Webhook |
| `name` | string | Human-readable name |
| `type` | TargetType | One of: `http`, `slack`, `database`, `log` |
| `active` | boolean | Whether deliveries are enabled (default: true) |
| `config` | JSON text | Type-specific configuration |
| `max_attempts` | integer | How many times an `http` or `slack` target attempts each delivery in all: at least 1, and 1 by default. Ignored by `database` and `log` targets. The web UI labels it Delivery attempts |
**Relations:** Belongs to Webhook. Has many Deliveries.
**Target types:**
- **`http`** — Forward the event as an HTTP POST to a configured URL.
`max_retries` is the total number of delivery attempts, not retries on top of
the first: when `max_retries` is 0 (the default), the target operates in
fire-and-forget mode, a single attempt with no retries and no circuit breaker;
a value of N makes up to N attempts in all, retrying failed deliveries with
exponential backoff and protecting them with a per-target circuit breaker.
- **`http`** — Forward the event as an HTTP POST to a configured URL. With
`max_attempts` at 1 the target makes a single attempt; above 1 it retries a
failed delivery with exponential backoff, up to that many attempts in all,
behind a per-target circuit breaker.
- **`slack`** — Post the event as a formatted message to a Slack-compatible
incoming webhook URL (`webhookUrl` in `config`). It is built on the same HTTP
core as `http` and honours `max_retries` identically, circuit breaker
core as `http` and honours `max_attempts` identically, circuit breaker
included. See the Slack target section under "Per-Webhook Event Databases" for
the message format.
- **`database`** — Archive the full event as a row into the target's own archive
@@ -1837,7 +1768,7 @@ is what bounds it.
#### DeliveryResult
The result of a single delivery attempt. Every attempt (including retries) is
individually logged for full observability.
individually logged, except one cut off by a stop (see Shutdown).
| Field | Type | Description |
| --------------- | ------- | ----------------------------------------- |
@@ -1919,8 +1850,9 @@ Deliveries still `pending` or `retrying` count in neither.
#### Event-tier indexes
These indexes on the per-webhook event databases are declared in the model tags,
so `AutoMigrate` creates them on a fresh database:
These indexes on the per-webhook event databases are created by
`internal/db/migrations/events/001_schema.sql`, and declared in the model tags
to match:
| Table | Columns | Serves |
| ------------------ | ------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
@@ -1984,8 +1916,9 @@ and application state:
- **Targets** — delivery destination configurations
- **APIKeys** — programmatic access credentials
On first startup the main database is auto-migrated, a session encryption key is
generated and stored, and an `admin` user is created.
On first startup the main database is created from its SQL files (see
[Schema](#schema)), a session encryption key is generated and stored, and an
`admin` user is created.
**Per-Webhook Event Databases** (`{DATA_DIR}/events-{webhook_uuid}.db`) — each
webhook gets its own dedicated SQLite file containing:
@@ -1997,9 +1930,10 @@ webhook gets its own dedicated SQLite file containing:
the above, the deliveries per target, and each entrypoint's last event, kept
through retention
Per-webhook databases are created automatically when a webhook is created. They
are managed by the `WebhookDBManager` component, which handles connection
pooling, lazy opening, migrations, and cleanup.
Per-webhook databases are created automatically when a webhook is created, from
the SQL files in `internal/db/migrations/events/`. They hold no copy of the main
database's tables. They are managed by the `WebhookDBManager` component, which
handles connection pooling, lazy opening, migrations, and cleanup.
A per-webhook database that is missing or zero-length later means its webhook's
events and pending deliveries are gone. The next time it is opened, an empty one
@@ -2083,14 +2017,15 @@ the service again.
After each write the archive handle is closed and reopened, debounced to at most
once per second, so an operator can move the archive file away for offline
archiving without stopping the service; a moved or removed archive file is
recreated automatically on the next write. A zero-length archive file is written
to as a new archive: SQLite opens it as an empty database, so it holds nothing
to lose. An optional `expiry` in the target's config JSON (e.g.
`{"expiry":"720h"}`) is validated when the target is created — the default
(unset or the literal `never`) keeps rows forever — and rows older than the
expiry are pruned each time the archive is (re)opened. An archive write failure
is never silent success: the delivery records a failed attempt with the error
and is marked failed.
recreated automatically on the next write, from the SQL files in
`internal/db/migrations/archive/`. A zero-length archive file is written to as a
new archive: SQLite opens it as an empty database, so it holds nothing to lose.
An optional `expiry` in the target's config JSON (e.g. `{"expiry":"720h"}`) is
validated when the target is created — the default (unset or the literal
`never`) keeps rows forever — and rows older than the expiry are pruned each
time the archive is (re)opened. An archive write failure is never silent
success: the delivery records a failed attempt with the error and is marked
failed.
Because reopens only happen on writes, an archive whose target has stopped
receiving events would never be pruned. A background **archive sweeper** closes
@@ -2179,6 +2114,21 @@ The database uses the
though CGO is required at build time due to the transitive `mattn/go-sqlite3`
dependency from `gorm.io/driver/sqlite`.
#### Schema
Each kind of database file has its schema in SQL files built into the binary,
one directory per kind under `internal/db/migrations/`. In each,
`000_migration.sql` creates the `schema_migrations` table, which records the
number of every file the database has had, and `001_schema.sql` holds the whole
schema. Opening a database runs, in one transaction, every file in its directory
that `schema_migrations` does not list:
- `main/` for the main database, on connect — settings, users, API keys,
webhooks, entrypoints and targets
- `events/` for each event database, when it is lazily opened — events,
deliveries, delivery results and their running totals
- `archive/` for each archive database, on every open and reopen
### Request Flow
```
@@ -2213,11 +2163,11 @@ External Service
▼ ▼ ▼
┌────────────┐ ┌────────────┐ ┌────────────┐
│ HTTP Target│ │ HTTP Target│ │ Log Target │
│(max_retries│ │(max_retries│ │ (stdout) │
│ == 0) │ │ > 0, │ └────────────┘
│ fire+forget│ │ backoff + │
│max_attempts│ │max_attempts│ │ (stdout) │
│ == 1, │ │ > 1, │ └────────────┘
│ one attempt│ │ backoff + │
└────────────┘ │ circuit │
│ breaker) │
│ breaker │
└────────────┘
```
@@ -2256,12 +2206,16 @@ This means:
buffer rather than spawning more goroutines.
- **Independent results** — each worker records its own delivery result in the
per-webhook database without coordination.
- **Graceful shutdown** — cancel the context, workers finish their current task
and exit. The stop hook waits for the pool via `lifecycle.WaitForShutdown`,
which bounds that wait by fx's stop timeout rather than blocking forever on a
wedged worker. On timeout it logs at `ERROR` and returns an error, and the
goroutines that did not finish are still running — an unclean shutdown is
reported rather than hidden.
- **Graceful shutdown** — the stop hook cancels the workers' context. A worker
may still take tasks already queued before it exits. An `http` or `slack`
request in flight is cut off, and one started after the cancel fails at once.
Neither is recorded or counted in the metrics, and the next start sends the
delivery again (see Shutdown). A `database` or `log` task runs as normal. The
stop hook waits for the pool via `lifecycle.WaitForShutdown`, which bounds
that wait by fx's stop timeout rather than blocking forever on a wedged
worker. On timeout it logs at `ERROR` and returns an error, and the goroutines
that did not finish are still running — an unclean shutdown is reported rather
than hidden.
**Recovery paths:**
@@ -2290,7 +2244,7 @@ re-inject it to every currently active target.
### Circuit Breaker (HTTP and Slack Targets with Retries)
`http` and `slack` targets with `max_retries` > 0 are protected by a
`http` and `slack` targets with `max_attempts` > 1 are protected by a
**per-target circuit breaker** that prevents hammering a down target with
repeated failed delivery attempts. The circuit breaker is in-memory only and
resets on restart (which is fine — startup recovery rescans the database
@@ -2331,10 +2285,10 @@ anyway).
- **Cooldown:** 30 seconds in open state before probing
**Scope:** Circuit breakers apply to **`http` and `slack` targets with
`max_retries` > 0**. The Slack target is built on the same HTTP core and hands
its own `max_retries` to the same retry path, so it gets a breaker with the same
5-failure / 30-second defaults. Fire-and-forget targets of either type
(`max_retries` == 0), database targets (local operations), and log targets
`max_attempts` > 1**. The Slack target is built on the same HTTP core and hands
its own `max_attempts` to the same retry path, so it gets a breaker with the
same 5-failure / 30-second defaults. Single-attempt targets of either type
(`max_attempts` == 1), database targets (local operations), and log targets
(stdout) do not use circuit breakers.
When a circuit is open and a new delivery arrives, the engine marks the delivery
@@ -2367,7 +2321,7 @@ getting anywhere.
| Metric | Type | Meaning |
| -------------------------------------- | --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `webhooker_events_received_total` | counter | Events received and durably stored. Compare against the delivery counters on one dashboard |
| `webhooker_delivery_attempts_total` | counter | Delivery attempts actually dispatched to a target. A delivery a circuit breaker refused is not one: it is counted as a retry instead, but only when the refusal moves it into `retrying` |
| `webhooker_delivery_attempts_total` | counter | Delivery attempts actually dispatched to a target. A delivery a circuit breaker refused is not one: it is counted as a retry instead, but only when the refusal moves it into `retrying`. An attempt cut off by a stop is not counted (see Shutdown) |
| `webhooker_deliveries_succeeded_total` | counter | Deliveries that reached `delivered` |
| `webhooker_deliveries_failed_total` | counter | Deliveries that failed terminally and will not be retried |
| `webhooker_delivery_retries_total` | counter | Deliveries put back into `retrying` |
@@ -2551,10 +2505,23 @@ Where the pattern is out of reach — the transaction dispatch, an event capture
outside the router, or a request that matched no route — the fallback is never
the concrete path. The path becomes the literal `/(redacted)`, so the URL reads
`http://host/(redacted)`; a URL the rewrite cannot parse into a scheme is
withheld whole. A transaction event additionally carries the SDK's own
`METHOD /path` name, built from the concrete path as well; it is rewritten on
the same terms, to `POST /h/{uuid}` where the pattern is known and
`POST /(redacted)` where it is not.
withheld whole.
A transaction event also carries a name, which the SDK builds as `METHOD /path`
from the concrete path and gives the transaction source `url`. Sentry groups
transactions by name, so withholding it would put every request in the service
into one group per method, such as `POST /(redacted)`. Inside each Sentry
handler, a second middleware renames the transaction once the request has been
routed, to the method and the route pattern (`POST /h/{uuid}`), and sets its
source to `route`. The hook keeps a name whose source is `route` and rewrites
any other to `METHOD /(redacted)`. A path that matches nothing at the top level
has no pattern, so its transaction keeps the SDK's name and the hook withholds
it. Inside a route group, a path that matches no route in the group, and a
request the group's own middleware turns away before routing (a CSRF refusal,
the redirect to `/pages/login`), are named after the group's pattern, such as
`GET /pages/*` or `POST /hook/{sourceID}/*`, and the hook keeps that name. The
URL on a transaction event still falls back to `http://host/(redacted)`, because
the hook has no request there.
The headers are an allowlist for the same reason the rules above are
unconditional: the SDK's own filter removes four names and passes everything
@@ -3019,7 +2986,6 @@ webhooker/
│ ├── database/
│ │ ├── base_model.go # BaseModel with UUID primary keys
│ │ ├── database.go # GORM connection, migrations, admin seed
│ │ ├── models.go # AutoMigrate for config-tier models
│ │ ├── model_setting.go # Setting entity (key-value app config)
│ │ ├── model_user.go # User entity
│ │ ├── model_webhook.go # Webhook entity
@@ -3036,6 +3002,11 @@ webhooker/
│ │ └── databasetest/ # Test support: a WebhookDBManager for tests in other packages
│ ├── datadir/
│ │ └── lock.go # Exclusive advisory lock on DATA_DIR (one instance)
│ ├── db/migrations/
│ │ ├── migrations.go # Applies a database file's SQL files when it is opened
│ │ ├── main/ # 000_migration.sql and 001_schema.sql for webhooker.db
│ │ ├── events/ # The same for each events-{uuid}.db
│ │ └── archive/ # The same for each archive file
│ ├── globals/
│ │ └── globals.go # Build-time variables (appname, version, arch)
│ ├── gormlog/
@@ -3175,7 +3146,8 @@ Applied to all routes in this order:
7. **Recoverer** — Panic recovery: one `ERROR` record through `internal/logger`
and a `500`
8. **Sentry** — Error reporting to Sentry (if `SENTRY_DSN` is set; configured
with `Repanic: true` so panics still reach Recoverer)
with `Repanic: true` so panics still reach Recoverer), and inside it the
naming of the request's Sentry transaction after its route pattern
Recoverer sits seventh rather than first, and both neighbours are the reason. It
runs **inside** everything that observes the response, so the `500` it writes
@@ -3190,9 +3162,9 @@ set a header or start a timer.
Each admin page route group (`/pages`, `/user/*`, `/settings`, `/hooks`,
`/hook/*`) starts with its own **Recoverer** and, if `SENTRY_DSN` is set, its
own **Sentry** error reporting. That Recoverer answers a panic with the `500`
error page in the normal layout; the global one keeps the plain-text `500` for
every other route.
own **Sentry** error reporting and transaction naming. That Recoverer answers a
panic with the `500` error page in the normal layout; the global one keeps the
plain-text `500` for every other route.
Additionally, form endpoints (`/pages`, `/user/*`, `/settings`, `/hooks`,
`/hook/*`) apply a **MaxBodySize** middleware that limits POST/PUT/PATCH request
@@ -3316,7 +3288,8 @@ stop-hook log:
3. `server` — the HTTP drain, bounded by `server.ShutdownTimeout` (**3
seconds**) and by what the hooks before it left, then a Sentry flush if
`SENTRY_DSN` is set
4. `delivery.Engine` — waits for its workers, then closes the archive databases
4. `delivery.Engine` — cuts off any `http` or `slack` request in flight, waits
for its workers, then closes the archive databases
5. `healthcheck`
6. `WebhookDBManager`
7. the database close
@@ -3327,6 +3300,12 @@ by the stop context, so a wedge there consumes the 5 seconds before the HTTP
server hook is ever entered. The hooks after the server are microsecond-scale in
normal operation.
The delivery engine cancels a delivery request in flight. That attempt is not
recorded or counted in the metrics, and the delivery keeps its `pending` or
`retrying` status, so startup recovery sends it again on the next start (see
Recovery paths under Bounded Worker Pool). If the receiver already had it, it
receives it twice: the at-least-once duplicate described under Rationale.
The HTTP drain budget is deliberately **shorter** than the sequence budget. Were
the two equal, a drain that used its whole budget would exhaust the sequence
budget at the instant it finished, and every later hook — the delivery engine,
@@ -3451,12 +3430,14 @@ fixed independently of the compiler's:
phases and the `css-check` and `markdown-check` stages passing (it copies a
file from each), runs `make build` (which extracts Alpine.js from `3p/`
first), and then rebuilds the binary with `CGO_ENABLED=1` and static linking
so it runs on musl. Both builds go through `make build`, the relink adding
its `-extldflags` via `GO_LDFLAGS`, so neither can drop the `-X` that stamps
the version. The version is the `VERSION` build arg if one is given,
otherwise derived from the `.git` in the context, and the stage fails if a
context with `.git` would stamp an empty version, `dev` or `unknown` (see
[Version stamping](#version-stamping)).
so it runs on musl, with the build tags `netgo`, `osusergo` and
`sqlite_omit_load_extension` so it needs none of glibc's shared libraries at
run time. Both builds go through `make build`, the relink adding its
`-extldflags` via `GO_LDFLAGS` and its tags via `GO_TAGS`, so neither can
drop the `-X` that stamps the version. The version is the `VERSION` build arg
if one is given, otherwise derived from the `.git` in the context, and the
stage fails if a context with `.git` would stamp an empty version, `dev` or
`unknown` (see [Version stamping](#version-stamping)).
7. **Runtime stage** (`alpine:3.21`) — copies the static binary and
`deploy/docker-entrypoint.sh`, creates the `/var/lib/webhooker` directory for
all SQLite databases, exposes port 8080, and includes a health check against
TODO.md
+32 -343
View File
@@ -12,24 +12,14 @@ One issue per unit of work, one branch and one PR per issue:
`main` without notice. One `next` -> `main` PR accumulates the milestone;
releases are cut from `main` separately.
Issue branches do NOT touch this file — the manager maintains it on `next`.
Every branch editing `TODO.md` conflicts with every other (#112).
The tracker (https://git.eeqj.de/sneak/webhooker/issues) is the record of what
is done and what is under way. This file keeps no list of either.
# Status
The milestone (https://git.eeqj.de/sneak/webhooker/milestone/9) is the
authoritative list, and the only place to read a count or a state of play from.
This file records where the project is, not what is in flight: a sentence whose
truth depends on a branch being unmerged is wrong the moment it merges, and this
file has been wrong that way before.
The durability defect that held the tag has landed
(https://git.eeqj.de/sneak/webhooker/issues/256, commit `8d64259`). Every SQLite
handle opens with WAL journaling and a busy timeout, a bookkeeping write that
fails leaves its delivery in a recoverable state rather than a lying one, and
recovery skips a delivery that already has a successful result row. Final
pre-tag verification exercised it and confirmed it holds. Whatever the milestone
still shows open is what remains before `v1.0.0`.
What is still open for 1.0.0 is in its milestone
(https://git.eeqj.de/sneak/webhooker/milestone/9). `v1.0.0` is not tagged, and
only @sneak tags it.
Delivery is at-least-once by design, not by accident: a send whose result row
does not land is attempted again, so a receiver can see a duplicate. That is
@@ -38,338 +28,31 @@ under Rationale. It is not a defect to re-file.
# Next Step
Clear the rest of the open 1.0.0 milestone
(https://git.eeqj.de/sneak/webhooker/milestone/9) and tag `v1.0.0`. Merging
`next` into `main` is a separate act from tagging and waits on neither of those:
`next` is kept mergeable at all times, which is the point of the branch.
# Completed Steps
- 2026-08-24 Bind the plaintext HTTP listener deliberately, via `BIND_ADDRESS`
defaulting to `127.0.0.1`, and document the reverse-proxy deployment. A
hostname, an empty value or a value carrying a port is a startup error, and
the `Dockerfile` sets `0.0.0.0` because a loopback bind inside a container is
unreachable (https://git.eeqj.de/sneak/webhooker/issues/268). The same commit
removed the shutdown race: `httpServer` is built in the constructor rather
than assigned from the serving goroutine, which orders the write before every
fx hook and rules out the nil dereference a SIGTERM arriving first would have
caused, and `sentryEnabled` is an `atomic.Bool`
(https://git.eeqj.de/sneak/webhooker/issues/226)
- 2026-08-24 Remove inbound request signature verification. The entrypoint UUID
is the authentication secret, so the per-entrypoint shared secret, the
`internal/signature` package, the receiver check, the model fields and the
forms are all gone. This reverses the feature that landed earlier in the same
milestone (https://git.eeqj.de/sneak/webhooker/issues/67,
https://git.eeqj.de/sneak/webhooker/issues/279)
- 2026-08-24 Stamp the build version into the binary and render it in the UI
footer. `script/version` is the single source — `$VERSION`, else
`git describe --tags --always --dirty`, else `unknown` — so a `make build`
binary and a `make docker` image from one checkout report the same thing, and
nothing in it varies between two builds of the same commit, which the release
gate's byte-identical assertion would catch
(https://git.eeqj.de/sneak/webhooker/issues/253)
- 2026-08-24 Derive cookie `Secure` and CSRF strictness from the request
transport rather than from `WEBHOOKER_ENVIRONMENT`. Behind a real TLS proxy
with the environment left at its `dev` default, the session cookie silently
lost `Secure` while the CSRF cookie on the same response kept it.
`X-Forwarded-Proto` is now matched case-insensitively on its first
comma-separated element, so `HTTPS` and `https, http` no longer fall to the
relaxed CSRF path (https://git.eeqj.de/sneak/webhooker/issues/269)
- 2026-08-24 Roll back a failed webhook deletion instead of committing it. A
failing delete committed whatever had already succeeded, hard-deleted the
per-webhook event database anyway, and redirected as though it had worked —
orphaned config plus permanently destroyed history, reported as success. All
three delete positions now roll back with the event database intact
(https://git.eeqj.de/sneak/webhooker/issues/262)
- 2026-08-24 Name a deleted target on its historical deliveries, marked
`(deleted)`, rather than leaving the event log unable to say where a delivery
went. A deleted target's credentials stay masked exactly as a live one's, and
it cannot become deliverable again through the receiver, resubmit, replay, the
edit form or the toggle (https://git.eeqj.de/sneak/webhooker/issues/211)
- 2026-08-24 Bound both request-controlled `/metrics` label dimensions, so the
unauthenticated receiver is no longer a memory-exhaustion vector: `handler`
carries the chi route pattern, and `method` folds anything chi cannot route
onto a single `(unmatched)` sentinel. Both were reproduced before the fix —
300 random method tokens took the series count from 106 to 7,631, and path
flooding reached 62,532 — and a label audit across a live scrape found no
third unbounded dimension (https://git.eeqj.de/sneak/webhooker/issues/254,
https://git.eeqj.de/sneak/webhooker/issues/261)
- 2026-08-24 Validate `max_retries` on both target forms. `abc`, `2.7` and `-5`
silently became 0 — fire-and-forget — including on the edit path, where it
destroyed a working value, and `999999999` stored verbatim. The ceiling of 20
is the `max` both templates already declared
(https://git.eeqj.de/sneak/webhooker/issues/221)
- 2026-08-24 Resubmit a stored event as a new undelivered event, so a backend
under development can be tested against real captured traffic. Per-delivery
replay cannot serve that: it re-sends one finished delivery to its own
original target, and a target created for a dev backend has no prior delivery
to replay. Resubmit re-injects the stored event at the top of the receiver
path and fans it out to whatever targets are active now
(https://git.eeqj.de/sneak/webhooker/issues/250)
- 2026-08-20 Take an exclusive lock on `DATA_DIR` at startup, so two instances
on one directory cannot both deliver
(https://git.eeqj.de/sneak/webhooker/issues/201)
- 2026-08-20 Shut down the app when the HTTP listener fails. The `OnStart` hook
returned as soon as the serving goroutine was spawned, so a failed listen left
fx reporting RUNNING and a live process with nothing bound — invisible to
systemd and Docker restart policies
(https://git.eeqj.de/sneak/webhooker/issues/200)
- 2026-08-20 Stop target credentials leaking into the per-webhook event
databases (https://git.eeqj.de/sneak/webhooker/issues/206), log SQL with
placeholders rather than bound values
(https://git.eeqj.de/sneak/webhooker/issues/207), and fail loudly on half-set
metrics auth credentials (https://git.eeqj.de/sneak/webhooker/issues/205)
- 2026-08-20 Read queue depths with `Find`, not `Scan`. `Scan` swaps GORM's own
trace recorder in for the logging adapter, and that recorder does not
implement `gorm.ParamsFilter`, so those statements logged their bound values
interpolated and bypassed the suppression above. The two units gated green
against a `next` that lacked the other, and `next` went red when both landed
(https://git.eeqj.de/sneak/webhooker/issues/234)
- 2026-08-20 Render per-attempt delivery detail in the event log
(https://git.eeqj.de/sneak/webhooker/issues/202) and add replay of a
terminally failed delivery (https://git.eeqj.de/sneak/webhooker/issues/203)
- 2026-08-20 Expose delivery metrics on `/metrics`
(https://git.eeqj.de/sneak/webhooker/issues/209) and document the backup,
restore and upgrade procedures
(https://git.eeqj.de/sneak/webhooker/issues/210)
- 2026-08-20 Add a `webhooker resetpw` subcommand and a bootstrap banner. The
admin bootstrap password was printed once among roughly 45 fx lines, and under
`docker run -d` went to container logs subject to rotation; there was no reset
path at all, so recovery meant hand-deleting the users row, documented
nowhere. The password is read from stdin or generated, never from argv where
`/proc` would publish it (https://git.eeqj.de/sneak/webhooker/issues/208)
- 2026-08-20 Add `ALLOWED_EGRESS_CIDRS`, an allowlist-only escape hatch for the
SSRF guard, so a self-hosted proxy can forward into the operator's own
network. The guard's always-blocked set cannot be reopened by configuration
(https://git.eeqj.de/sneak/webhooker/issues/204)
- 2026-08-20 Harden operator-set target headers, which were carried unsafely
across a redirect (https://git.eeqj.de/sneak/webhooker/issues/233)
- 2026-08-20 Add a target edit form with headers and timeout fields
(https://git.eeqj.de/sneak/webhooker/issues/127)
- 2026-08-18 Raise `script/test`'s per-package timeout from 30s to 90s, matching
the org-wide backstop. `go test` applies `-timeout` per package, and
`internal/handlers` had grown past the old budget: a cache-defeated build
failed outright at `GOMAXPROCS=4`, and every run under deliberate host load
breached 30s. The measurement table lives in the script (#194)
- 2026-08-18 Re-sync `REPO_POLICIES.md` from `prompts`. The local copy was stale
and still mandated a 20s test target with a 30s timeout, which the org
replaced with a 60s cap and a 90s backstop. A synced copy is not a source;
reading it as one nearly produced a PR against `prompts` proposing a change
already merged there (#196)
- 2026-08-18 Report handler panics through the logger and answer 500. chi
v1.5.5's `Recoverer` scans for a `panic(0x` frame the runtime no longer emits,
then indexes `pkg[-1:]`, so it panicked inside its own stack printer before
writing a byte: the recovery never ran, the client got a dropped connection
instead of a 500, and the original panic was lost. A local middleware replaces
it, bounded by `MaxPanicLogLineBytes` (#187)
- 2026-08-18 Route GORM's logger through `slog` and bound it. Every `gorm.Open`
left `logger.Default` in place at `Warn` with `IgnoreRecordNotFoundError`
false, so **every record-not-found printed the fully interpolated SQL to
stdout** — including the client-chosen path on `/webhook/{uuid}` and the
submitted username on the login form, at no level the operator set and outside
`internal/logger` entirely. Three call sites, not the two the issue named
(#178)
- 2026-08-18 Bound every `slog` line against client-chosen text. Eight sites
reachable unauthenticated, found by reading every `slog` call in the tree
rather than only the one reported; the budget moved to a shared
`internal/logfield` so no second truncation exists. `DEBUG` being off by
default is not a bound and is not treated as one (#176)
- 2026-08-18 Stop a slow host turning a login-guard test into a segfault. A
non-fatal `assert` on an acquire result was dereferenced on the next line, so
one timing miss killed the whole `internal/middleware` binary and reddened CI
for unrelated PRs. The fix also removed a real production race — `acquire`
could shed a request with a slot standing free, because Go picks uniformly
among ready `select` cases (#186)
- 2026-08-18 Send the chi route pattern to Sentry rather than the concrete path.
The receiver's path carries the entrypoint capability token, so every Sentry
event from `/webhook/{uuid}` shipped a live credential to a third party.
Request `Data`, `QueryString`, `Cookies` and `Env` are dropped and headers
reduced to an allowlist (#179)
- 2026-08-18 Read form fields from the POST body only. `r.FormValue` merges the
query string, so a login could be driven by URL parameters — putting the
password somewhere that lands in access logs, proxy logs and browser history
(#160)
- 2026-08-18 Verify login credentials before spending rate-limit budget, so a
flood of wrong passwords cannot lock out the account it is guessing at. The
manager took this decision rather than stall the queue; it is flagged on the
issue for reversal (#150)
- 2026-08-18 Run all linting in Docker via `Dockerfile.lint`. Host lint was
wrong in both directions from version skew and shared caches. `script/lint`
asserts the summary line, because `--no-cache-filter` silently ignores a stage
name it does not match — the flag that makes the gate meaningful fails open
(#109)
- 2026-08-18 Serve an event's full stored body over HTTP. The list query
truncates for rendering, and that truncated value was the only way to read a
body, so the full payload was unreachable (#157)
- 2026-08-18 Bound the access log line against client-chosen text.
`internal/logfield` budgets by _encoded_ bytes, not runes, so a handler's JSON
escaping cannot multiply a field past its allowance (#146)
- 2026-08-18 Mark superseded CI commits `failure` rather than `skipped`. A
skipped run rolls up green, so a commit that was never tested reported success
(#152)
- 2026-08-18 Set `fx.StopTimeout` inside the container stop grace, so shutdown
hooks are bounded by a deadline the orchestrator will actually honour rather
than being killed mid-flush (#134)
- 2026-08-17 Bucket IPv6 rate-limit keys by `/64`. A single allocation hands out
2^64 addresses, so per-address keying let one client mint unlimited buckets.
Manager decision, recorded on the issue (#125)
- 2026-08-17 Correct release-blocking README and startup-warning inaccuracies,
including claims about behaviour the code does not have (#151)
- 2026-08-17 Fetch and verify Alpine.js at build time against
`static/vendor.sha256` instead of committing the minified blob, so the
dependency is pinned by hash rather than by trust (#145)
- 2026-08-17 Bound the event log's rendered bodies in the query itself, so a
large stored payload cannot be read into memory just to be truncated for
display (#135)
- 2026-08-17 Mask the `http` target's destination URL in the UI: it can carry a
bearer credential in its path or query, and was rendered verbatim. Manager
decision to mask unconditionally (#115)
- 2026-08-14 Bound shutdown hooks by their stop context, so a hook that hangs
cannot hold the process past its grace period (#102)
- 2026-08-14 Render templates via a buffer rather than the `ResponseWriter`, so
a template error part-way through cannot commit a 200 and then fail — the
response is written only once it is whole (#123)
- 2026-08-14 Align the session codec's max-age with the 7-day absolute cap. The
codec accepted cookies the session layer considered expired, so the cap was
enforced in one place and not the other (#108)
- 2026-08-12 Warn when `TRUSTED_PROXIES` is empty in production, where the safe
default silently discards forwarded headers and every client rate-limits as
the proxy's address (#149)
- 2026-08-12 Bound the receiver rate limit per client IP across the whole
`/webhook/*` route. The existing limiter keyed on the request path and
`/webhook/{uuid}` matches any single segment, so a client that invented a
fresh path per request minted a fresh bucket per request: the limit on the
only unauthenticated endpoint bounded nothing in aggregate, and every request
still cost an entrypoint lookup before it 404ed. An outer limiter keyed on the
client address alone now bounds that, chained in front of the unchanged
per-entrypoint limiter (#139)
- 2026-08-12 Correct release-blocking documentation inaccuracies: the README
promised manual redelivery in the present tense in three places when nothing
implements it (the same false claim also sat in the doc comment that was its
source text), the env table omitted `RETENTION_SWEEP_INTERVAL`, and `TODO.md`
itself omitted five landed units (#141)
- 2026-08-12 Make the CI gate execute the checks it reports on. The workflow now
writes a build-context fingerprint before calling `script/cibuild`, so a code
commit invalidates the `COPY` layer of the lint and builder stages while a
docs-only commit still replays from cache; a superseding run also rewrites the
`failure` status Gitea leaves on commits it cancelled and never tested.
Verified by pushing a deliberately broken test and watching CI go red (#119)
- 2026-08-12 Require a positive `RETENTION_SWEEP_INTERVAL`: a non-positive value
reached `time.NewTicker` in both the retention reaper and the archive sweeper,
panicking two goroutines with no recover after startup had already reported
success (#140)
- 2026-08-12 Bound the `X-Forwarded-For` scan's allocation to the hop cap: the
reverse walk cuts entries with `strings.LastIndexByte` instead of joining and
splitting, so a 1 MB header allocates 16 bytes rather than 1.6 MB per request
on the unauthenticated receiver. Semantics proven unchanged by differential
testing against the previous implementation (#133)
- 2026-08-12 Cap the `X-Forwarded-For` hop walk at 64 entries, so an
attacker-supplied chain cannot burn unbounded CPU in the rate-limit key
function; running off the end falls back to the peer address (#124)
- 2026-08-12 Gate forwarded-header trust behind a `TRUSTED_PROXIES` CIDR list:
all three rate limiters key on the connection's own address unless the direct
peer is a configured proxy, in which case `X-Forwarded-For` is walked right to
left for the first non-proxy hop. Default trusts nothing, and a
set-but-unparseable value aborts startup. Before this, any client could mint a
fresh bucket or drain another's by rotating a spoofed header (#88)
- 2026-08-11 Web UI cleanup: nav terminology unified on Webhooks, the Profile
settings placeholder removed, a progressive-enhancement copy button for the
entrypoint URL, and retention form copy that states the actual policy
(deletion by the reaper, 0 retains forever) (#57)
- 2026-08-11 Mask the webhook credential in delivery errors and logs: Go embeds
the request URL in `*url.Error`, so every transport failure persisted the full
Slack webhook URL into the per-webhook event database via
`DeliveryResult.Error`, a field a future REST API would have served.
`maskURLError` drops path, query and userinfo while preserving the wrapped
cause, so `errors.Is`/`As` and `Timeout()` still work and DNS, TLS and timeout
failures still read differently (#118)
- 2026-08-11 Rate-limit the public webhook receiver endpoint
(`RECEIVER_RATE_LIMIT`, default 120/min), keyed on client IP plus entrypoint
path so one entrypoint cannot exhaust another's budget; over-limit requests
get 429 with `Retry-After`. It was the one unauthenticated, internet-facing
endpoint with no limit at all (#64)
- 2026-08-11 Enforce the body size limit before CSRF parses the form:
`MaxBodySize` is now first in all four form-parsing route groups, so an
oversized request is rejected with 413 instead of being read in full by the
CSRF middleware before any cap applied (#90)
- 2026-08-11 Mask target config on the source detail page, which rendered the
stored blob verbatim and so exposed the Slack incoming-webhook URL — a bearer
credential that cannot be revoked per-holder. Config reaches the template only
as a `TargetView` of labelled fields, and header values are rendered as a
count (#113)
- 2026-08-11 Allow `retention_days` of 0 to mean retain forever, via a sentinel
written in `BeforeSave` so the GORM column default cannot win the race. Also
bounds the reaper's cutoff arithmetic: day counts above 106751 overflowed
`time.Duration` and wrapped the cutoff into the future, where every row
matched and the sweep deleted everything (#79)
- 2026-08-09 Inactivity-based session timeout: sliding idle expiry
(`SESSION_IDLE_TIMEOUT`, default `24h`) refreshed on authenticated requests,
with the 7-day absolute cap kept as an independent backstop that activity
never extends (#66)
- 2026-08-09 Restart recovery and the 60s retry sweep terminally fail an
orphaned `retrying` delivery whose target type no longer supports retries,
recording a `DeliveryResult` with the reason instead of leaving the delivery
stuck forever (#82)
- 2026-08-09 Root the delivery engine's worker pool and the retention reaper's
sweep loop at `context.Background()` rather than the fx `OnStart` hook context
(#97), which carries fx's 15s start timeout and killed both roughly fifteen
seconds after boot: the proxy silently stopped delivering webhooks entirely,
and the reaper never ran a single sweep under its default one-hour interval
- 2026-08-09 Archive writer lifecycle (#89): deleting a webhook (or its last
`database` target) evicts the cached archive writer and closes its handle
while deliberately leaving `archive-{webhookID}.db` on disk, and a new
`ArchiveSweeper` prunes idle archives on the existing
`RETENTION_SWEEP_INTERVAL` without ever creating an archive file
- 2026-08-09 Configuration parsing fails loudly on set-but-unparseable
environment values: `envInt` removed in favour of `envPositiveInt` plus a
`PORT` range check, `envBool` now parses with `strconv.ParseBool`, and
defaults apply only to unset variables (#80)
- 2026-08-07 Automatic event retention cleanup based on `retention_days`,
deleting expired events, deliveries, and delivery results from each
per-webhook event database (#63)
- 2026-08-07 Update golangci-lint to v2.12.2 (Docker image digest in
`Dockerfile`, release-archive sha256 pins in `script/bootstrap`), adopt the
canonical `.golangci.yml` (v2 `linters.settings` layout so
`lll`/`funlen`/`cyclop`/`dupl` thresholds actually apply), and fix all newly
surfaced lint findings
- 2026-07-07 Adopted scripts-to-rule-them-all: `script/` entrypoints, Makefile
shims, README Entrypoints section
- 2026-03-25 pin golangci-lint Docker image for linting (#55)
- 2026-03-18 CSRF middleware detects TLS per-request, fixing login over plain
HTTP and behind reverse proxies (#54)
- 2026-03-17 root path redirects based on auth state (#52)
- 2026-03-17 CSRF protection, SSRF prevention for HTTP delivery targets with DNS
rebinding defense, and per-IP login rate limiting (#42)
- 2026-03-17 Slack target type for incoming webhook notifications (#47)
- 2026-03-17 Dockerfile absolute paths and static linking (#49); absolute dev
DATA_DIR default and clarified env docs (#46)
- 2026-03-05 security headers middleware, session regeneration on login, request
body size limits (#41)
- 2026-03-04 tests for delivery, middleware, and session packages (#32); removed
the build-architecture global (#31)
- 2026-03-04 1.0 MVP merge: Webhook/Entrypoint/Target rename, core delivery
engine with bounded worker pool and circuit breaker, parallel fan-out,
per-webhook event databases, management UI (#16)
- 2026-03-01 repo brought to REPO_POLICIES standards; TODO.md folded into README
(#6)
@sneak runs webhooker in limited production, then tags `v1.0.0`. Merging `next`
into `main` is a separate act from tagging and waits on neither of those: `next`
is kept mergeable at all times, which is the point of the branch.
# Future Steps
- Delivery status and retry management UI. Replay of a terminally failed
delivery and per-attempt detail already landed
(https://git.eeqj.de/sneak/webhooker/issues/203,
https://git.eeqj.de/sneak/webhooker/issues/202)
- Per-webhook rate limiting in the receiver handler (per-webhook config plus
handler enforcement; global limits must not apply to receiver endpoints)
- API key authentication for programmatic access (APIKey model exists; Bearer
token middleware does not)
- Per-webhook rate limits, set in the web UI and enforced in the receiver
handler, on top of the receiver's existing limits, which `RECEIVER_RATE_LIMIT`
sets for the whole server (see Rate Limiting in the README)
- API key authentication for programmatic access (the `APIKey` model exists, but
nothing creates a key and no middleware checks one)
- REST API v1
- CRUD for webhooks, entrypoints, targets
- event viewing and filtering endpoints
- event redelivery endpoint
- OpenAPI specification
- Analytics dashboard: success rates, response times, volume
- A remember-me option at login
- Analytics in the web UI: response times summarised per webhook or per target,
and figures for all webhooks together. The webhook page already shows event,
delivery and failure counts and failure percentages, the target list counts
each target's deliveries, the event log and each event's page show every
attempt's duration, and `/metrics` carries server-wide counts and delivery
durations
- A remember-me option at login. Every session already survives a browser
restart: it lasts up to 7 days, and ends sooner after `SESSION_IDLE_TIMEOUT`
(default 24 hours) without activity
- Password reset flow for a forgotten password over the web. The authenticated
password _change_ flow already landed, and a lost password is recoverable from
the console with `webhooker resetpw`
@@ -377,7 +60,13 @@ Clear the rest of the open 1.0.0 milestone
- Later, nice to have
- email delivery target type
- SNS and S3 delivery targets
- data transformations (e.g. webhook to Slack message formatting)
- JSONL file delivery with periodic S3 upload
- webhook event search and filtering
- multi-user with role-based access control
- data transformations (e.g. a configurable Slack message format; the Slack
target sends one fixed format today)
- JSONL file delivery with periodic S3 upload (the `database` target already
archives events to SQLite files, rotated hourly, daily or monthly if set,
and the webhook page offers them as one gzipped JSON download)
- webhook event search, and filtering beyond the event log's failed and
pending views
- multi-user with role-based access control (each webhook already belongs to
one account, but there is only the account made at first boot and no way
to add another)
internal/database/database.go
+27 -2
View File
@@ -18,6 +18,7 @@ import (
"sneak.berlin/go/webhooker/internal/banner"
"sneak.berlin/go/webhooker/internal/config"
"sneak.berlin/go/webhooker/internal/datadir"
"sneak.berlin/go/webhooker/internal/db/migrations"
"sneak.berlin/go/webhooker/internal/gormlog"
"sneak.berlin/go/webhooker/internal/logger"
)
@@ -249,12 +250,21 @@ func (d *Database) connectTo(dataDir string) error {
return fmt.Errorf("migrating %s: %w", dbPath, err)
}
err = parseModels(
db, &Setting{}, &User{}, &APIKey{},
&Webhook{}, &Entrypoint{}, &Target{},
)
if err != nil {
return fmt.Errorf("connecting to %s: %w", dbPath, err)
}
return nil
}
// migrate applies the main database's SQL files. See
// internal/db/migrations.
func (d *Database) migrate() error {
// Run GORM auto-migrations
err := d.Migrate()
err := migrations.Apply(d.db, migrations.Main)
if err != nil {
d.log.Error(
"failed to run database migrations",
@@ -269,6 +279,21 @@ func (d *Database) migrate() error {
return nil
}
// parseModels has GORM parse each model for db before the handle is
// shared. GORM parses a model the first time a handle uses it, and two
// goroutines doing that at once for models that refer to each other,
// as Webhook and Target do, race inside GORM.
func parseModels(db *gorm.DB, models ...any) error {
for _, model := range models {
err := (&gorm.Statement{DB: db}).Parse(model)
if err != nil {
return fmt.Errorf("parsing model %T: %w", model, err)
}
}
return nil
}
// ensureAdminUser creates the bootstrap admin account when the
// deployment has no users at all.
func (d *Database) ensureAdminUser() error {
internal/database/event_db_isolation.go
+8 -113
View File
@@ -2,7 +2,6 @@ package database
import (
"fmt"
"log/slog"
"gorm.io/gorm"
"gorm.io/gorm/clause"
@@ -18,14 +17,14 @@ const omitAssociationsCallback = "webhooker:omit_associations"
//
// A per-webhook database holds the event tier only, but Delivery
// declares belongs-to Event and Target and the delivery engine fills
// both in memory before writing. Without this guard GORM upserts
// those parent rows here on the delivery and retry write paths,
// copying targets.config, which holds destination URLs and bearer
// credentials, into the file most likely to be backed up or handed
// to someone else. Registering the guard on the connection covers
// every write path, including writes inside a transaction and write
// paths added later. Every event-tier row this file holds is written
// explicitly, so nothing depends on the automatic save.
// both in memory before writing. Without this guard GORM upserts those
// parent rows here on the delivery and retry write paths, and the
// target, whose config holds destination URLs and bearer credentials,
// goes to a targets table this file does not have, which fails the
// write. Registering the guard on the connection
// covers every write path, including writes inside a transaction and
// write paths added later. Every event-tier row this file holds is
// written explicitly, so nothing depends on the automatic save.
func omitAssociations(db *gorm.DB) error {
omit := func(tx *gorm.DB) {
tx.Statement.Omits = append(
@@ -53,107 +52,3 @@ func omitAssociations(db *gorm.DB) error {
return nil
}
// eventDBSweptVersion is the PRAGMA user_version purgeTargetRows
// stamps into a per-webhook database once it has removed any leaked
// target rows *and* the VACUUM that removes their bytes has returned.
// Nothing else in the tree uses user_version, so 0 means "not swept
// by this build".
//
// The stamp, not the DELETE, is what records that a file is done. A
// DELETE commits on its own, so a sweep that is interrupted or whose
// VACUUM fails leaves a file whose rows are gone but whose credential
// bytes are still in the free pages -- indistinguishable, by row
// count, from a file that never leaked. Both leave the stamp unset,
// so the next open sweeps again.
const eventDBSweptVersion = 1
// purgeTargetRows deletes target rows that an earlier build's
// association upsert wrote into a per-webhook database, and rewrites
// the file so their bytes are gone with them. AutoMigrate creates a
// targets table in every one of these files because Delivery declares
// a belongs-to Target, but nothing in the event tier may put rows in
// it. The rows it did put there are junk, not history: they carry an
// empty webhook_id, and delivery rows resolve their target against
// the main database, so nothing here refers to them.
//
// The DELETE only unlinks the rows: modernc.org/sqlite leaves
// secure_delete at SQLite's default of off, so the credential bytes
// stay readable in the file's free pages and a backup of a swept file
// would still hand them over. VACUUM rewrites the file without them.
//
// This runs before every migration and is gated on
// eventDBSweptVersion, so a file pays for the rewrite once, on the
// first open that finds it unstamped, and every open after that is a
// PRAGMA read. A file this build created is stamped before its
// targets table exists, so it never vacuums at all. A failure here
// fails the open with the stamp left unset, so the sweep is retried
// rather than skipped -- a webhook whose file cannot be swept stays
// unusable instead of quietly serving from a file that still holds
// recoverable credentials.
func purgeTargetRows(
db *gorm.DB, log *slog.Logger, webhookID string,
) error {
var version int
// Row().Scan, not (*gorm.DB).Scan: see internal/gormlog.
err := db.Raw("PRAGMA user_version").Row().Scan(&version)
if err != nil {
return fmt.Errorf(
"reading sweep marker of webhook database %s: %w",
webhookID, err,
)
}
if version >= eventDBSweptVersion {
return nil
}
var purged int64
if db.Migrator().HasTable("targets") {
res := db.Exec("DELETE FROM targets")
if res.Error != nil {
return fmt.Errorf(
"purging target rows from webhook database %s: %w",
webhookID, res.Error,
)
}
purged = res.RowsAffected
// Unconditional: a zero row count here does not mean there is
// nothing to remove, only that no *live* row is left. See
// eventDBSweptVersion.
err = db.Exec("VACUUM").Error
if err != nil {
return fmt.Errorf(
"purged %d leaked target rows from webhook database "+
"%s but vacuuming it failed, so the deleted "+
"target credentials are still recoverable from "+
"the file; it stays marked unswept and the next "+
"open retries: %w",
purged, webhookID, err,
)
}
}
err = db.Exec(fmt.Sprintf(
"PRAGMA user_version = %d", eventDBSweptVersion,
)).Error
if err != nil {
return fmt.Errorf(
"marking webhook database %s swept: %w", webhookID, err,
)
}
if purged > 0 {
log.Warn(
"purged leaked target rows from per-webhook database",
"webhook_id", webhookID,
"rows", purged,
)
}
return nil
}
internal/database/event_db_isolation_test.go
+5 -382
View File
@@ -1,392 +1,15 @@
package database_test
import (
"bytes"
"database/sql"
"fmt"
"os"
"path/filepath"
"testing"
"github.com/google/uuid"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
_ "modernc.org/sqlite"
"sneak.berlin/go/webhooker/internal/database"
"sneak.berlin/go/webhooker/internal/database/databasetest"
)
// testDataDirPerm is the mode the test data directory is created
// with.
const testDataDirPerm = 0o750
// eventDBDataDir returns a data directory that a WebhookDBManager
// can be pointed at.
func eventDBDataDir(t *testing.T) string {
t.Helper()
dir := filepath.Join(t.TempDir(), "events")
require.NoError(t, os.MkdirAll(dir, testDataDirPerm))
return dir
}
// openRawEventDB opens the per-webhook database file directly,
// without the manager, so a test can put a file on disk in a state
// the manager has to cope with, or inspect one afterwards.
func openRawEventDB(
t *testing.T, dataDir, webhookID string,
) *sql.DB {
t.Helper()
path := filepath.Join(
dataDir, fmt.Sprintf("events-%s.db", webhookID),
)
sqlDB, err := sql.Open(
"sqlite",
fmt.Sprintf("file:%s?mode=rwc", path),
)
require.NoError(t, err)
t.Cleanup(func() { _ = sqlDB.Close() })
return sqlDB
}
// eventDBFileBytes reads a per-webhook database file off disk, so a
// test can assert on what the file itself still holds rather than on
// what a query returns.
func eventDBFileBytes(t *testing.T, dataDir, webhookID string) []byte {
t.Helper()
//nolint:gosec // reads a file the test just created under t.TempDir()
raw, err := os.ReadFile(filepath.Join(
dataDir, fmt.Sprintf("events-%s.db", webhookID),
))
require.NoError(t, err)
return raw
}
// eventDBUserVersion returns the PRAGMA user_version of a per-webhook
// database file, which is the marker purgeTargetRows stamps once it
// has swept and vacuumed.
func eventDBUserVersion(t *testing.T, sqlDB *sql.DB) int {
t.Helper()
var version int
require.NoError(t, sqlDB.QueryRowContext(
t.Context(), "PRAGMA user_version",
).Scan(&version))
return version
}
// clearEventDBSweptMarker resets the sweep marker to 0, which is what
// a file written by a build without the sweep looks like. Tests that
// seed a leaked row have to create the file through the manager to
// get the real targets table shape, and that stamps it.
func clearEventDBSweptMarker(t *testing.T, sqlDB *sql.DB) {
t.Helper()
_, err := sqlDB.ExecContext(t.Context(), "PRAGMA user_version = 0")
require.NoError(t, err)
}
// countTargetRows returns the number of rows in the targets table of
// a per-webhook database file, or -1 if the table does not exist.
func countTargetRows(t *testing.T, sqlDB *sql.DB) int {
t.Helper()
var tables int
require.NoError(t, sqlDB.QueryRowContext(
t.Context(),
"SELECT count(*) FROM sqlite_master "+
"WHERE type = 'table' AND name = 'targets'",
).Scan(&tables))
if tables == 0 {
return -1
}
var rows int
require.NoError(t, sqlDB.QueryRowContext(
t.Context(), "SELECT count(*) FROM targets",
).Scan(&rows))
return rows
}
// TestOpenPurgesLeakedTargetRows covers the sweep for event
// databases written by a build that let GORM upsert target rows
// into them: opening the database clears them, and opening it again
// is a no-op.
func TestOpenPurgesLeakedTargetRows(t *testing.T) {
t.Parallel()
dataDir := eventDBDataDir(t)
webhookID := uuid.New().String()
// Create the file the way the application does, so the targets
// table has exactly the shape AutoMigrate gives it, then write
// a leaked row into it the way the association upsert did.
initial := databasetest.NewWebhookDBManager(t, dataDir)
_, err := initial.GetDB(webhookID)
require.NoError(t, err)
require.NoError(t, initial.CloseAll())
seed := openRawEventDB(t, dataDir, webhookID)
_, err = seed.ExecContext(
t.Context(),
"INSERT INTO targets "+
"(id, webhook_id, name, type, config) "+
"VALUES (?, '', ?, ?, ?)",
uuid.New().String(),
"leaked-target",
"slack",
`{"webhookUrl":"https://hooks.example/T000/B000/secret"}`,
)
require.NoError(t, err)
require.Equal(t, 1, countTargetRows(t, seed))
clearEventDBSweptMarker(t, seed)
require.NoError(t, seed.Close())
mgr := databasetest.NewWebhookDBManager(t, dataDir)
_, err = mgr.GetDB(webhookID)
require.NoError(t, err)
require.NoError(t, mgr.CloseAll())
check := openRawEventDB(t, dataDir, webhookID)
assert.Zero(t, countTargetRows(t, check))
assert.Equal(
t, 1, eventDBUserVersion(t, check),
"a completed sweep must mark the file so later opens skip it",
)
require.NoError(t, check.Close())
// Idempotent: a second open leaves it at zero and does not
// error.
again := databasetest.NewWebhookDBManager(t, dataDir)
_, err = again.GetDB(webhookID)
require.NoError(t, err)
require.NoError(t, again.CloseAll())
recheck := openRawEventDB(t, dataDir, webhookID)
assert.Zero(t, countTargetRows(t, recheck))
}
// TestOpenPurgeRemovesCredentialBytes covers the sweep at the level
// that matters for a backup handed to someone else: the leaked
// credential must be gone from the raw bytes of the file, not merely
// unreachable by query. A bare DELETE unlinks the row and leaves the
// bytes readable in the free pages, so this fails without the VACUUM
// in purgeTargetRows.
func TestOpenPurgeRemovesCredentialBytes(t *testing.T) {
t.Parallel()
dataDir := eventDBDataDir(t)
webhookID := uuid.New().String()
credential := "T00000000/B00000000/" + uuid.New().String()
initial := databasetest.NewWebhookDBManager(t, dataDir)
_, err := initial.GetDB(webhookID)
require.NoError(t, err)
require.NoError(t, initial.CloseAll())
seed := openRawEventDB(t, dataDir, webhookID)
_, err = seed.ExecContext(
t.Context(),
"INSERT INTO targets "+
"(id, webhook_id, name, type, config) "+
"VALUES (?, '', ?, ?, ?)",
uuid.New().String(),
"leaked-target",
"slack",
fmt.Sprintf(
`{"webhookUrl":"https://hooks.example/%s"}`, credential,
),
)
require.NoError(t, err)
clearEventDBSweptMarker(t, seed)
require.NoError(t, seed.Close())
// The seed has to be in the file for its absence later to mean
// anything.
require.True(
t,
bytes.Contains(
eventDBFileBytes(t, dataDir, webhookID),
[]byte(credential),
),
"seeded credential is not in the file, so this test proves nothing",
)
mgr := databasetest.NewWebhookDBManager(t, dataDir)
_, err = mgr.GetDB(webhookID)
require.NoError(t, err)
require.NoError(t, mgr.CloseAll())
assert.NotContains(
t,
string(eventDBFileBytes(t, dataDir, webhookID)),
credential,
"leaked credential is still recoverable from the raw file",
)
}
// TestOpenRevacuumsAfterIncompleteSweep covers the case a row count
// cannot see: the rows are already deleted but the file was never
// vacuumed, because an earlier sweep died between the two or its
// VACUUM failed. The credential bytes are still recoverable, and the
// unset marker is the only thing that says so, so the next open must
// vacuum rather than conclude from the empty table that there is
// nothing to do.
func TestOpenRevacuumsAfterIncompleteSweep(t *testing.T) {
t.Parallel()
dataDir := eventDBDataDir(t)
webhookID := uuid.New().String()
credential := "T00000000/B00000000/" + uuid.New().String()
initial := databasetest.NewWebhookDBManager(t, dataDir)
_, err := initial.GetDB(webhookID)
require.NoError(t, err)
require.NoError(t, initial.CloseAll())
seed := openRawEventDB(t, dataDir, webhookID)
_, err = seed.ExecContext(
t.Context(),
"INSERT INTO targets "+
"(id, webhook_id, name, type, config) "+
"VALUES (?, '', ?, ?, ?)",
uuid.New().String(),
"leaked-target",
"slack",
fmt.Sprintf(
`{"webhookUrl":"https://hooks.example/%s"}`, credential,
),
)
require.NoError(t, err)
// Exactly the state an interrupted sweep leaves: rows gone,
// marker unset, bytes still in the free pages.
_, err = seed.ExecContext(t.Context(), "DELETE FROM targets")
require.NoError(t, err)
require.Zero(t, countTargetRows(t, seed))
clearEventDBSweptMarker(t, seed)
require.NoError(t, seed.Close())
require.True(
t,
bytes.Contains(
eventDBFileBytes(t, dataDir, webhookID),
[]byte(credential),
),
"the deleted row's bytes must still be in the file, or this "+
"test proves nothing",
)
mgr := databasetest.NewWebhookDBManager(t, dataDir)
_, err = mgr.GetDB(webhookID)
require.NoError(t, err)
require.NoError(t, mgr.CloseAll())
assert.NotContains(
t,
string(eventDBFileBytes(t, dataDir, webhookID)),
credential,
"an interrupted sweep was not retried, so the credential is "+
"still recoverable from the raw file",
)
check := openRawEventDB(t, dataDir, webhookID)
assert.Equal(t, 1, eventDBUserVersion(t, check))
}
// TestOpenSkipsSweptDatabase covers the other half of the marker: a
// file this build created is marked without ever being vacuumed, and
// a marked file is not swept again.
func TestOpenSkipsSweptDatabase(t *testing.T) {
t.Parallel()
dataDir := eventDBDataDir(t)
webhookID := uuid.New().String()
mgr := databasetest.NewWebhookDBManager(t, dataDir)
_, err := mgr.GetDB(webhookID)
require.NoError(t, err)
require.NoError(t, mgr.CloseAll())
marked := openRawEventDB(t, dataDir, webhookID)
assert.Equal(t, 1, eventDBUserVersion(t, marked))
// A marked file is left alone, so a row written into it survives
// a reopen. Nothing writes target rows any more; this stands in
// for the sweep having run.
_, err = marked.ExecContext(
t.Context(),
"INSERT INTO targets "+
"(id, webhook_id, name, type, config) "+
"VALUES (?, '', ?, ?, ?)",
uuid.New().String(), "sentinel", "slack", `{}`,
)
require.NoError(t, err)
require.NoError(t, marked.Close())
again := databasetest.NewWebhookDBManager(t, dataDir)
_, err = again.GetDB(webhookID)
require.NoError(t, err)
require.NoError(t, again.CloseAll())
check := openRawEventDB(t, dataDir, webhookID)
assert.Equal(
t, 1, countTargetRows(t, check),
"a marked file must not be swept again",
)
}
// TestOpenSucceedsWithoutTargetsTable covers an existing event
// database that never grew a targets table. The sweep must not fail
// startup on it.
func TestOpenSucceedsWithoutTargetsTable(t *testing.T) {
t.Parallel()
dataDir := eventDBDataDir(t)
webhookID := uuid.New().String()
seed := openRawEventDB(t, dataDir, webhookID)
_, err := seed.ExecContext(
t.Context(),
"CREATE TABLE events (id text PRIMARY KEY)",
)
require.NoError(t, err)
require.NoError(t, seed.Close())
mgr := databasetest.NewWebhookDBManager(t, dataDir)
db, err := mgr.GetDB(webhookID)
require.NoError(t, err)
assert.NotNil(t, db)
require.NoError(t, mgr.CloseAll())
}
// TestEventDBCreateOmitsAssociations covers the connection-level
// guard directly: a Delivery carrying its Event and Target in
// memory, written through the manager's handle, must store only the
@@ -394,10 +17,9 @@ func TestOpenSucceedsWithoutTargetsTable(t *testing.T) {
func TestEventDBCreateOmitsAssociations(t *testing.T) {
t.Parallel()
dataDir := eventDBDataDir(t)
webhookID := uuid.New().String()
mgr := databasetest.NewWebhookDBManager(t, dataDir)
mgr := databasetest.NewWebhookDBManager(t, t.TempDir())
db, err := mgr.GetDB(webhookID)
require.NoError(t, err)
@@ -432,8 +54,9 @@ func TestEventDBCreateOmitsAssociations(t *testing.T) {
require.NoError(t, db.Model(d).
Update("status", database.DeliveryStatusDelivered).
Error)
require.NoError(t, mgr.CloseAll())
check := openRawEventDB(t, dataDir, webhookID)
assert.Zero(t, countTargetRows(t, check))
// The file has no targets table, so the create and update above
// would have failed had GORM tried to save the target.
assert.False(t, db.Migrator().HasTable(&database.Target{}))
require.NoError(t, mgr.CloseAll())
}
internal/database/event_tier_indexes_test.go
+3 -23
View File
@@ -13,10 +13,8 @@ import (
"sneak.berlin/go/webhooker/internal/database"
)
// TestWebhookDBManager_OpenAddsEventTierIndexes verifies that opening a
// per-webhook database that predates these indexes creates them. It
// stands in for an older database file by dropping the indexes
// AutoMigrate just created, then reopening the same file.
// TestWebhookDBManager_OpenAddsEventTierIndexes verifies that a new
// per-webhook database has these indexes.
func TestWebhookDBManager_OpenAddsEventTierIndexes(t *testing.T) {
t.Parallel()
@@ -42,27 +40,9 @@ func TestWebhookDBManager_OpenAddsEventTierIndexes(t *testing.T) {
db, err := mgr.GetDB(webhookID)
require.NoError(t, err)
// A fresh database has them.
for _, ix := range indexes {
require.True(t, db.Migrator().HasIndex(ix.model, ix.name))
}
// Stand in for a database file created before the indexes existed.
for _, ix := range indexes {
require.NoError(t, db.Migrator().DropIndex(ix.model, ix.name))
require.False(t, db.Migrator().HasIndex(ix.model, ix.name))
}
// Drop the cached connection so the next open reopens the file and
// runs AutoMigrate against it, as a restart would.
require.NoError(t, mgr.CloseAll())
db, err = mgr.GetDB(webhookID)
require.NoError(t, err)
for _, ix := range indexes {
assert.True(t, db.Migrator().HasIndex(ix.model, ix.name),
"opening the existing database should create %s", ix.name)
"a new database should have %s", ix.name)
}
}
internal/database/model_event.go
+1 -2
View File
@@ -45,8 +45,7 @@ type Event struct {
// ResubmittedFromID names the event this one was copied from by
// an operator resubmit. It is nil for an event that arrived on
// the receiver, which is every event created before the column
// existed. It is not a foreign key: the source event can be
// the receiver. It is not a foreign key: the source event can be
// reaped by retention while its copies remain, and the id is
// kept as the record of where the copy came from either way.
ResubmittedFromID *string `gorm:"type:uuid;index:idx_events_resubmitted_from_id,priority:1;index:idx_events_entrypoint_id,priority:3" json:"resubmittedFromId,omitempty"`
internal/database/model_target.go
+5 -3
View File
@@ -29,9 +29,11 @@ type Target struct {
// handler that marshals the model itself.
Config string `gorm:"type:text" json:"-"` // JSON configuration
// For HTTP targets (max_retries=0 means fire-and-forget,
// >0 enables retries with backoff)
MaxRetries int `json:"maxRetries,omitempty"`
// MaxAttempts is how many times an HTTP or Slack target attempts
// each delivery in all, at least 1. 1 is a single attempt with no
// circuit breaker; above 1, a failed attempt is retried with
// backoff behind the breaker.
MaxAttempts int `json:"maxAttempts,omitempty"`
// Relations. No model marshals the record it belongs to:
// Webhook.Targets leads back here, and the JSON could loop.
internal/database/model_webhook.go
+3 -3
View File
@@ -82,7 +82,7 @@ type Webhook struct {
// value while building the insert statement, which runs after
// BeforeSave; rewriting any later than this loses that race and the
// row lands at 30 days. Living on the model also means a future call
// site — a REST API, a fixture, a migration — cannot bypass it.
// site, such as a REST API or a fixture, cannot bypass it.
func (w *Webhook) BeforeSave(_ *gorm.DB) error {
if w.RetentionDays <= 0 {
w.RetentionDays = RetentionForeverDays
@@ -98,8 +98,8 @@ func (w *Webhook) BeforeSave(_ *gorm.DB) error {
// are exempt from reaping.
//
// It accepts the RetentionForeverDays sentinel written by BeforeSave
// and, defensively, the non-positive values that rows written before
// the sentinel existed may still carry.
// and, defensively, any non-positive value, which BeforeSave treats
// as a request to retain forever.
func retainsForever(retentionDays int) bool {
return retentionDays <= 0 ||
retentionDays >= RetentionForeverDays
internal/database/models.go
-17
View File
@@ -1,17 +0,0 @@
package database
// Migrate runs database migrations for the main application database.
// Only configuration-tier models are stored in the main database.
// Event-tier models (Event, Delivery, DeliveryResult, EventTotals,
// TargetTotals, EntrypointTotals) live in
// per-webhook dedicated databases managed by WebhookDBManager.
func (d *Database) Migrate() error {
return d.db.AutoMigrate(
&Setting{},
&User{},
&APIKey{},
&Webhook{},
&Entrypoint{},
&Target{},
)
}
internal/database/retention.go
+1 -1
View File
@@ -253,7 +253,7 @@ func (r *RetentionReaper) reapWebhook(
// row in the database: the sweep then deletes every event, delivery,
// and delivery result, including ones created seconds ago. Rejecting
// out-of-range input at the form is the primary guard; saturating here
// means an old row, a migration, or a future call site cannot turn a
// means a value that reaches the row by any other path cannot turn a
// too-large retention into total data loss.
func retentionCutoff(
now time.Time,
internal/database/schema_test.go
+168
View File
@@ -0,0 +1,168 @@
package database_test
import (
"log/slog"
"net/http"
"testing"
"time"
"github.com/google/uuid"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"gorm.io/gorm"
"sneak.berlin/go/webhooker/internal/database"
"sneak.berlin/go/webhooker/internal/database/databasetest"
)
// withFixedNow returns db with GORM's clock stopped at a time in UTC,
// so that the created and updated times it writes come back from
// SQLite equal to the row written, which holds them in UTC.
func withFixedNow(db *gorm.DB) (*gorm.DB, time.Time) {
at := time.Date(2026, 10, 13, 12, 30, 45, 123456789, time.UTC)
return db.Session(&gorm.Session{
NowFunc: func() time.Time { return at },
}), at
}
// newBaseModel returns a BaseModel with a new ID.
func newBaseModel() database.BaseModel {
return database.BaseModel{ID: uuid.New().String()}
}
// assertRoundTrip writes row, which must be the only row of its
// table, and reads back the same row.
func assertRoundTrip[T any](t *testing.T, db *gorm.DB, row *T) {
t.Helper()
require.NoError(t, db.Create(row).Error)
var got T
require.NoError(t, db.First(&got).Error)
assert.Equal(t, *row, got)
}
// TestMainSchemaHoldsEveryModel writes a row of each main database
// model, every field set, into a database made from its SQL files.
func TestMainSchemaHoldsEveryModel(t *testing.T) {
t.Parallel()
mainDB, err := database.Open(
t.TempDir(), slog.New(slog.DiscardHandler),
)
require.NoError(t, err)
t.Cleanup(func() { _ = mainDB.Close() })
db, at := withFixedNow(mainDB.DB())
assertRoundTrip(t, db, &database.Setting{
Key: "session_key", Value: "value",
})
assertRoundTrip(t, db, &database.User{
BaseModel: newBaseModel(),
Username: "user",
Password: "password hash",
})
assertRoundTrip(t, db, &database.APIKey{
BaseModel: newBaseModel(),
UserID: uuid.New().String(),
Key: "key",
Description: "API key description",
LastUsedAt: &at,
})
assertRoundTrip(t, db, &database.Webhook{
BaseModel: newBaseModel(),
UserID: uuid.New().String(),
Name: "webhook",
Description: "webhook description",
RetentionDays: 7,
})
assertRoundTrip(t, db, &database.Entrypoint{
BaseModel: newBaseModel(),
WebhookID: uuid.New().String(),
Path: uuid.New().String(),
Description: "entrypoint description",
Active: true,
})
assertRoundTrip(t, db, &database.Target{
BaseModel: newBaseModel(),
WebhookID: uuid.New().String(),
Name: "target",
Type: database.TargetTypeHTTP,
Active: true,
Config: `{"url":"https://example.com/"}`,
MaxAttempts: 3,
})
}
// TestEventSchemaHoldsEveryModel does the same for a webhook's event
// database, which the manager makes from its SQL files.
func TestEventSchemaHoldsEveryModel(t *testing.T) {
t.Parallel()
mgr := databasetest.NewWebhookDBManager(t, t.TempDir())
t.Cleanup(func() { _ = mgr.CloseAll() })
events, err := mgr.GetDB(uuid.New().String())
require.NoError(t, err)
db, at := withFixedNow(events)
source := uuid.New().String()
assertRoundTrip(t, db, &database.Event{
BaseModel: newBaseModel(),
WebhookID: uuid.New().String(),
EntrypointID: uuid.New().String(),
Method: http.MethodPost,
RawQuery: "a=1",
Headers: `{"X":"Y"}`,
Body: "body",
ContentType: "text/plain",
BodyBytes: 4,
ResubmittedFromID: &source,
})
assertRoundTrip(t, db, &database.Delivery{
BaseModel: newBaseModel(),
EventID: uuid.New().String(),
TargetID: uuid.New().String(),
Status: database.DeliveryStatusDelivered,
FinishedAt: &at,
Replay: true,
})
assertRoundTrip(t, db, &database.DeliveryResult{
BaseModel: newBaseModel(),
DeliveryID: uuid.New().String(),
AttemptNum: 2,
Success: true,
StatusCode: 200,
ResponseBody: "ok",
Error: "error",
Duration: 15,
})
assertRoundTrip(t, db, &database.TargetTotals{
TargetID: uuid.New().String(),
Deliveries: 5,
Delivered: 3,
Failed: 1,
DeliveriesRemoved: 2,
FailedRemoved: 1,
})
assertRoundTrip(t, db, &database.EntrypointTotals{
EntrypointID: uuid.New().String(), LastEventAt: at,
})
// A new event database has its one row of event totals already.
require.NoError(t, database.AddEventTotals(db, database.EventTotals{
Events: 3, EventsRemoved: 1, LastEventAt: &at,
}))
var totals []database.EventTotals
require.NoError(t, db.Find(&totals).Error)
assert.Equal(t, []database.EventTotals{{
ID: 1, Events: 3, EventsRemoved: 1, LastEventAt: &at,
}}, totals)
}
internal/database/sqlite_open.go
+15 -4
View File
@@ -118,9 +118,8 @@ const SQLiteFilePerm fs.FileMode = 0o600
// SQLite still reports the absence rather than this function
// materializing an empty database the caller asked not to create.
//
// Chmod of a file that already exists is what tightens a data
// directory an earlier build left at 0644 — including a developer's
// own scratch directory — without any migration machinery.
// The mode is set on every open, whoever created the file, so a
// database or sidecar found at a wider mode is tightened too.
func reserveSQLiteFile(path string, create bool) error {
if create {
// gosec G304: the path is the database file the caller asked
@@ -242,7 +241,19 @@ func SQLiteDSN(path, mode string) string {
)
q.Add("_pragma", "journal_mode(WAL)")
return "file:" + path + "?" + q.Encode()
// SQLite reads a file: URI's path only up to the first ? or #, and
// decodes %XX escapes in it, so url.URL escapes the path. OmitHost
// keeps a relative path as "file:data/x.db"; written
// "file://data/x.db", SQLite would reject "data" as the URI's
// authority.
dsn := url.URL{
Scheme: "file",
Path: path,
OmitHost: true,
RawQuery: q.Encode(),
}
return dsn.String()
}
// OpenSQLite opens the SQLite file at path with the service's
internal/database/sqlite_open_test.go
+75
View File
@@ -2,6 +2,8 @@ package database_test
import (
"context"
"database/sql"
"os"
"path/filepath"
"strings"
"testing"
@@ -112,6 +114,79 @@ func TestMainDBAppliesPragmasOnALiveHandle(t *testing.T) {
assert.Equal(t, "10000", busy)
}
// TestOpenSQLiteOpensThePathAskedFor uses a data directory whose name
// holds ?, # and %. SQLite reads a file: URI's path only up to a ? or
// #, and decodes %41 to A, so an unescaped path sent every database in
// that directory to one file outside it.
func TestOpenSQLiteOpensThePathAskedFor(t *testing.T) {
t.Parallel()
dir := filepath.Join(t.TempDir(), "hooks#1?x%41")
require.NoError(t, os.Mkdir(dir, 0o700))
for _, name := range []string{
database.MainDBFileName,
"events-" + uuid.New().String() + ".db",
} {
path := filepath.Join(dir, name)
sqlDB, err := database.OpenSQLite(
path, database.SQLiteModeCreate,
)
require.NoError(t, err)
t.Cleanup(func() { assert.NoError(t, sqlDB.Close()) })
assertOpenedFile(t, sqlDB, path)
}
}
// TestOpenSQLiteOpensARelativePath opens a database at a path relative
// to the working directory, which is what a relative DATA_DIR such as
// the README's DATA_DIR=../webhooker-data gives OpenSQLite.
//
//nolint:paralleltest // t.Chdir moves the whole process.
func TestOpenSQLiteOpensARelativePath(t *testing.T) {
t.Chdir(t.TempDir())
require.NoError(t, os.Mkdir("data", 0o700))
path := filepath.Join("data", database.MainDBFileName)
sqlDB, err := database.OpenSQLite(path, database.SQLiteModeCreate)
require.NoError(t, err)
defer func() { require.NoError(t, sqlDB.Close()) }()
assertOpenedFile(t, sqlDB, path)
}
// assertOpenedFile checks that sqlDB is the SQLite file at path.
// database_list names the file SQLite actually opened, as an absolute
// path with symlinks resolved, so the files are compared, not the names.
func assertOpenedFile(t *testing.T, sqlDB *sql.DB, path string) {
t.Helper()
var (
seq int
schema, file string
)
require.NoError(t, sqlDB.
QueryRowContext(t.Context(), "pragma database_list").
Scan(&seq, &schema, &file))
asked, err := os.Stat(path)
require.NoError(t, err)
opened, err := os.Stat(file)
require.NoError(t, err)
assert.True(
t, os.SameFile(asked, opened),
"asked for %s, SQLite opened %s", path, file,
)
}
// TestConcurrentReaderDoesNotBlockWrites is the unit-scale form of the
// reproduction in
// https://git.eeqj.de/sneak/webhooker/issues/256: an operator's
internal/database/webhook_db_manager.go
+7 -16
View File
@@ -14,6 +14,7 @@ import (
"gorm.io/gorm"
"sneak.berlin/go/webhooker/internal/config"
"sneak.berlin/go/webhooker/internal/datadir"
"sneak.berlin/go/webhooker/internal/db/migrations"
"sneak.berlin/go/webhooker/internal/gormlog"
)
@@ -370,18 +371,7 @@ func (m *WebhookDBManager) openDB(
)
}
err = purgeTargetRows(db, m.log, webhookID)
if err != nil {
_ = sqlDB.Close()
return nil, err
}
// Run migrations for event-tier models only
err = db.AutoMigrate(
&Event{}, &Delivery{}, &DeliveryResult{},
&EventTotals{}, &TargetTotals{}, &EntrypointTotals{},
)
err = migrations.Apply(db, migrations.Events)
if err != nil {
_ = sqlDB.Close()
@@ -391,14 +381,15 @@ func (m *WebhookDBManager) openDB(
)
}
// A new database gets its row of event totals, all zero. Target
// totals rows are created by the first delivery to each target.
err = db.FirstOrCreate(&EventTotals{}).Error
err = parseModels(
db, &Event{}, &Delivery{}, &DeliveryResult{},
&EventTotals{}, &TargetTotals{}, &EntrypointTotals{},
)
if err != nil {
_ = sqlDB.Close()
return nil, fmt.Errorf(
"creating event totals for webhook database %s: %w",
"connecting to webhook database %s: %w",
webhookID, err,
)
}
internal/db/migrations/archive/000_migration.sql
+9
View File
@@ -0,0 +1,9 @@
-- Migration 000: the table recording which migrations this file has
-- had. Applied before the others; it records itself.
CREATE TABLE IF NOT EXISTS schema_migrations (
version INTEGER PRIMARY KEY,
applied_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
INSERT OR IGNORE INTO schema_migrations (version) VALUES (0);
internal/db/migrations/archive/001_schema.sql
+18
View File
@@ -0,0 +1,18 @@
-- Migration 001: the schema of a database target's archive file. The
-- archivedEvent model in internal/delivery must agree with it.
CREATE TABLE archived_events (
id integer PRIMARY KEY AUTOINCREMENT,
event_id text,
webhook_id text,
entrypoint_id text,
method text,
raw_query text,
headers text,
body text,
content_type text,
archived_at datetime
);
CREATE INDEX idx_archived_events_event_id ON archived_events (event_id);
CREATE INDEX idx_archived_events_archived_at ON archived_events (archived_at);
internal/db/migrations/events/000_migration.sql
+9
View File
@@ -0,0 +1,9 @@
-- Migration 000: the table recording which migrations this file has
-- had. Applied before the others; it records itself.
CREATE TABLE IF NOT EXISTS schema_migrations (
version INTEGER PRIMARY KEY,
applied_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
INSERT OR IGNORE INTO schema_migrations (version) VALUES (0);
internal/db/migrations/events/001_schema.sql
+98
View File
@@ -0,0 +1,98 @@
-- Migration 001: the schema of a webhook's event database. The models
-- in internal/database must agree with it. The webhook, entrypoint and
-- target ids here name rows in the main database, which has those
-- tables; this file does not.
CREATE TABLE events (
id uuid,
created_at datetime,
updated_at datetime,
deleted_at datetime,
webhook_id uuid NOT NULL,
entrypoint_id uuid NOT NULL,
method text NOT NULL,
raw_query text,
headers text,
body text,
content_type text,
body_bytes integer NOT NULL,
resubmitted_from_id uuid,
PRIMARY KEY (id)
);
CREATE INDEX idx_events_created_at ON events (created_at);
CREATE INDEX idx_events_deleted_at ON events (deleted_at);
CREATE INDEX idx_events_deleted_at_created_at
ON events (deleted_at, created_at);
CREATE INDEX idx_events_resubmitted_from_id
ON events (resubmitted_from_id, deleted_at);
CREATE INDEX idx_events_entrypoint_id
ON events (entrypoint_id, deleted_at, resubmitted_from_id, created_at);
CREATE TABLE deliveries (
id uuid,
created_at datetime,
updated_at datetime,
deleted_at datetime,
event_id uuid NOT NULL,
target_id uuid NOT NULL,
status text NOT NULL DEFAULT 'pending',
finished_at datetime,
replay numeric NOT NULL DEFAULT false,
PRIMARY KEY (id),
CONSTRAINT fk_events_deliveries
FOREIGN KEY (event_id) REFERENCES events (id)
);
CREATE INDEX idx_deliveries_deleted_at ON deliveries (deleted_at);
CREATE INDEX idx_deliveries_event_id ON deliveries (event_id, deleted_at);
CREATE INDEX idx_deliveries_status
ON deliveries (status, deleted_at, finished_at, target_id);
CREATE TABLE delivery_results (
id uuid,
created_at datetime,
updated_at datetime,
deleted_at datetime,
delivery_id uuid NOT NULL,
attempt_num integer NOT NULL,
success numeric,
status_code integer,
response_body text,
error text,
duration integer,
PRIMARY KEY (id),
CONSTRAINT fk_deliveries_delivery_results
FOREIGN KEY (delivery_id) REFERENCES deliveries (id)
);
CREATE INDEX idx_delivery_results_deleted_at
ON delivery_results (deleted_at);
CREATE INDEX idx_delivery_results_delivery_id
ON delivery_results (delivery_id, deleted_at);
CREATE TABLE event_totals (
id integer PRIMARY KEY AUTOINCREMENT,
events integer NOT NULL,
events_removed integer NOT NULL,
last_event_at datetime
);
-- The one row of event totals, all zero.
INSERT INTO event_totals (events, events_removed) VALUES (0, 0);
CREATE TABLE target_totals (
target_id uuid,
deliveries integer NOT NULL,
delivered integer NOT NULL,
failed integer NOT NULL,
deliveries_removed integer NOT NULL,
failed_removed integer NOT NULL,
PRIMARY KEY (target_id)
);
CREATE TABLE entrypoint_totals (
entrypoint_id uuid,
last_event_at datetime NOT NULL,
PRIMARY KEY (entrypoint_id)
);
internal/db/migrations/main/000_migration.sql
+9
View File
@@ -0,0 +1,9 @@
-- Migration 000: the table recording which migrations this file has
-- had. Applied before the others; it records itself.
CREATE TABLE IF NOT EXISTS schema_migrations (
version INTEGER PRIMARY KEY,
applied_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
INSERT OR IGNORE INTO schema_migrations (version) VALUES (0);
internal/db/migrations/main/001_schema.sql
+89
View File
@@ -0,0 +1,89 @@
-- Migration 001: the main database's schema. The models in
-- internal/database must agree with it.
CREATE TABLE settings (
"key" text,
value text NOT NULL,
PRIMARY KEY ("key")
);
CREATE TABLE users (
id uuid,
created_at datetime,
updated_at datetime,
deleted_at datetime,
username text NOT NULL,
password text NOT NULL,
PRIMARY KEY (id),
CONSTRAINT chk_users_username
CHECK (length(CAST(username AS BLOB)) <= 1024)
);
CREATE INDEX idx_users_deleted_at ON users (deleted_at);
CREATE UNIQUE INDEX idx_users_username ON users (username);
CREATE TABLE api_keys (
id uuid,
created_at datetime,
updated_at datetime,
deleted_at datetime,
user_id uuid NOT NULL,
"key" text NOT NULL,
description text,
last_used_at datetime,
PRIMARY KEY (id),
CONSTRAINT fk_users_api_keys FOREIGN KEY (user_id) REFERENCES users (id)
);
CREATE INDEX idx_api_keys_deleted_at ON api_keys (deleted_at);
CREATE UNIQUE INDEX idx_api_keys_key ON api_keys ("key");
CREATE TABLE webhooks (
id uuid,
created_at datetime,
updated_at datetime,
deleted_at datetime,
user_id uuid NOT NULL,
name text NOT NULL,
description text,
retention_days integer DEFAULT 30,
PRIMARY KEY (id),
CONSTRAINT fk_users_webhooks FOREIGN KEY (user_id) REFERENCES users (id)
);
CREATE INDEX idx_webhooks_deleted_at ON webhooks (deleted_at);
CREATE TABLE entrypoints (
id uuid,
created_at datetime,
updated_at datetime,
deleted_at datetime,
webhook_id uuid NOT NULL,
path text NOT NULL,
description text,
active numeric DEFAULT true,
PRIMARY KEY (id),
CONSTRAINT fk_webhooks_entrypoints
FOREIGN KEY (webhook_id) REFERENCES webhooks (id)
);
CREATE INDEX idx_entrypoints_deleted_at ON entrypoints (deleted_at);
CREATE UNIQUE INDEX idx_entrypoints_path ON entrypoints (path);
CREATE TABLE targets (
id uuid,
created_at datetime,
updated_at datetime,
deleted_at datetime,
webhook_id uuid NOT NULL,
name text NOT NULL,
type text NOT NULL,
active numeric DEFAULT true,
config text,
max_attempts integer,
PRIMARY KEY (id),
CONSTRAINT fk_webhooks_targets
FOREIGN KEY (webhook_id) REFERENCES webhooks (id)
);
CREATE INDEX idx_targets_deleted_at ON targets (deleted_at);
internal/db/migrations/migrations.go
+135
View File
@@ -0,0 +1,135 @@
// Package migrations holds the schema of each kind of SQLite file
// webhooker writes, as numbered SQL files embedded in the binary, and
// applies it when a file is opened.
//
// Each kind of file has its own directory. In each, 000_migration.sql
// creates only the schema_migrations table, and 001_schema.sql holds
// the whole schema. Before 1.0 a schema change is an edit to
// 001_schema.sql, never a new file.
package migrations
import (
"embed"
"fmt"
"io/fs"
"path"
"strconv"
"strings"
"gorm.io/gorm"
)
// The directories, one for each kind of database file.
const (
// Main is the main database, webhooker.db.
Main = "main"
// Events is a webhook's event database, events-{uuid}.db.
Events = "events"
// Archive is a database target's archive file.
Archive = "archive"
)
//go:embed main/*.sql events/*.sql archive/*.sql
var files embed.FS
// Apply runs each SQL file in dir, which is Main, Events or Archive,
// that the database has not had yet, in the order of the number its
// name starts with, and records that number in schema_migrations.
// 000_migration.sql creates that table and records itself, so it runs
// first, and only when the table is missing.
//
// It all runs in one transaction, so a failure leaves the file as it
// was.
func Apply(db *gorm.DB, dir string) error {
return db.Transaction(func(tx *gorm.DB) error {
var tables int
// Row().Scan, not (*gorm.DB).Scan: see internal/gormlog.
err := tx.Raw(
"SELECT count(*) FROM sqlite_master "+
"WHERE type = 'table' AND name = ?",
"schema_migrations",
).Row().Scan(&tables)
if err != nil {
return fmt.Errorf("looking for schema_migrations: %w", err)
}
if tables == 0 {
err = run(tx, path.Join(dir, "000_migration.sql"))
if err != nil {
return err
}
}
// fs.Glob lists the files in name order, which is number order.
names, err := fs.Glob(files, path.Join(dir, "*.sql"))
if err != nil {
return fmt.Errorf("listing migrations: %w", err)
}
for _, name := range names {
err = applyOnce(tx, name)
if err != nil {
return err
}
}
return nil
})
}
// applyOnce runs the migration file name and records its number,
// unless schema_migrations already has that number.
func applyOnce(tx *gorm.DB, name string) error {
number, _, _ := strings.Cut(path.Base(name), "_")
version, err := strconv.Atoi(number)
if err != nil {
return fmt.Errorf("numbering migration %s: %w", name, err)
}
var applied int
err = tx.Raw(
"SELECT count(*) FROM schema_migrations WHERE version = ?",
version,
).Row().Scan(&applied)
if err != nil {
return fmt.Errorf("checking migration %s: %w", name, err)
}
if applied > 0 {
return nil
}
err = run(tx, name)
if err != nil {
return err
}
err = tx.Exec(
"INSERT INTO schema_migrations (version) VALUES (?)", version,
).Error
if err != nil {
return fmt.Errorf("recording migration %s: %w", name, err)
}
return nil
}
// run executes every statement in the migration file name.
func run(tx *gorm.DB, name string) error {
script, err := files.ReadFile(name)
if err != nil {
return fmt.Errorf("reading migration %s: %w", name, err)
}
err = tx.Exec(string(script)).Error
if err != nil {
return fmt.Errorf("applying migration %s: %w", name, err)
}
return nil
}
internal/db/migrations/migrations_test.go
+57
View File
@@ -0,0 +1,57 @@
package migrations_test
import (
"database/sql"
"log/slog"
"path/filepath"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"gorm.io/driver/sqlite"
"gorm.io/gorm"
_ "modernc.org/sqlite"
"sneak.berlin/go/webhooker/internal/db/migrations"
"sneak.berlin/go/webhooker/internal/gormlog"
)
// TestApplyRunsEachFileOnce applies each kind of database file's
// migrations to a new file twice. The first time records every file.
// The second finds them all recorded and runs none, which is the only
// way it can succeed: 001_schema.sql creates tables that then exist.
func TestApplyRunsEachFileOnce(t *testing.T) {
t.Parallel()
for _, dir := range []string{
migrations.Main, migrations.Events, migrations.Archive,
} {
t.Run(dir, func(t *testing.T) {
t.Parallel()
sqlDB, err := sql.Open(
"sqlite", filepath.Join(t.TempDir(), "test.db"),
)
require.NoError(t, err)
t.Cleanup(func() { _ = sqlDB.Close() })
db, err := gorm.Open(
sqlite.Dialector{Conn: sqlDB},
&gorm.Config{
Logger: gormlog.New(slog.New(slog.DiscardHandler)),
},
)
require.NoError(t, err)
require.NoError(t, migrations.Apply(db, dir))
require.NoError(t, migrations.Apply(db, dir))
var versions string
require.NoError(t, sqlDB.QueryRowContext(t.Context(),
"SELECT group_concat(version) FROM schema_migrations",
).Scan(&versions))
assert.Equal(t, "0,1", versions)
})
}
}
internal/delivery/archive_sweeper.go
+1 -2
View File
@@ -201,8 +201,7 @@ func (s *ArchiveSweeper) sweep(ctx context.Context) {
// sweepTarget prunes the archive of a single database target.
// A missing, empty, or "never" expiry parses as a zero duration
// and is skipped entirely, so those archives keep exactly the
// behaviour they had before the sweep existed.
// and is skipped entirely, so those archives are never pruned.
func (s *ArchiveSweeper) sweepTarget(target *database.Target) {
expiry, err := parseArchiveExpiry(target.Config)
if err != nil {
internal/delivery/archive_sweeper_test.go
+6 -7
View File
@@ -22,6 +22,7 @@ import (
_ "modernc.org/sqlite" // Pure Go SQLite driver.
"sneak.berlin/go/webhooker/internal/database"
"sneak.berlin/go/webhooker/internal/database/databasetest"
"sneak.berlin/go/webhooker/internal/db/migrations"
"sneak.berlin/go/webhooker/internal/delivery"
"sneak.berlin/go/webhooker/internal/gormlog"
)
@@ -172,9 +173,7 @@ func seedArchiveFile(
)
require.NoError(t, err)
require.NoError(
t, gdb.AutoMigrate(&delivery.ExportArchivedEvent{}),
)
require.NoError(t, migrations.Apply(gdb, migrations.Archive))
for i, at := range archivedAt {
row := delivery.ExportArchivedEvent{
@@ -781,9 +780,9 @@ func TestArchiveSweep_NeverExpiryUntouched(t *testing.T) {
//
// The spec is stronger than that — a "never" archive is skipped
// before any file is touched — so the archive here exists but has
// never been migrated. Opening it at all would run AutoMigrate
// and create the archive table, which is exactly what must not
// happen.
// never been migrated. Opening it at all would apply the archive
// schema and create the archive table, which is exactly what must
// not happen.
func TestArchiveSweep_NeverExpirySkipsBeforeOpening(
t *testing.T,
) {
@@ -807,7 +806,7 @@ func TestArchiveSweep_NeverExpirySkipsBeforeOpening(
// seedUnmigratedArchive creates an archive file that exists but
// carries no archive schema, so any open of it is observable: the
// archive table appears only if something ran AutoMigrate.
// archive table appears only if something applied the schema.
func seedUnmigratedArchive(t *testing.T, path string) {
t.Helper()
internal/delivery/delivery_totals_test.go
+13 -2
View File
@@ -32,8 +32,9 @@ func targetTotals(
// TestUpdateDeliveryStatus_FinishTimeAndTargetTotals pins what a status
// write records for the webhook page's statistics: the time a delivery
// finished, set only when it becomes delivered or failed, and one more
// on its target's delivered or failed total.
// finished, set only when it becomes delivered or failed and stored in
// the same form as created_at, and one more on its target's delivered
// or failed total.
func TestUpdateDeliveryStatus_FinishTimeAndTargetTotals(t *testing.T) {
t.Parallel()
@@ -75,6 +76,16 @@ func TestUpdateDeliveryStatus_FinishTimeAndTargetTotals(t *testing.T) {
if tt.finished {
require.NotNil(t, stored.FinishedAt)
assert.False(t, stored.FinishedAt.Before(before))
var createdAt, finishedAt string
require.NoError(t, db.Raw(
`SELECT CAST(created_at AS TEXT),
CAST(finished_at AS TEXT)
FROM deliveries WHERE id = ?`, d.ID,
).Row().Scan(&createdAt, &finishedAt))
assertStoredTime(t, createdAt)
assertStoredTime(t, finishedAt)
} else {
assert.Nil(t, stored.FinishedAt)
}
internal/delivery/engine.go
+14 -10
View File
@@ -107,7 +107,7 @@ type Task struct {
TargetName string
TargetType database.TargetType
TargetConfig string
MaxRetries int
MaxAttempts int
Method string
RawQuery string
@@ -1701,8 +1701,11 @@ func writeDeliveryStatus(
database.DeliveryStatusFailed,
}).
Updates(map[string]any{
"status": status,
"finished_at": time.Now(),
"status": status,
// GORM's clock, the one that stamps created_at. A bare
// time.Now() carries a monotonic clock reading, which the
// driver would store as an " m=+…" suffix.
"finished_at": tx.NowFunc(),
})
if res.Error != nil || res.RowsAffected == 0 {
return res.Error
@@ -1766,10 +1769,10 @@ func buildEventFromTask(task *Task) database.Event {
func buildTargetFromTask(task *Task) database.Target {
target := database.Target{
Name: task.TargetName,
Type: task.TargetType,
Config: task.TargetConfig,
MaxRetries: task.MaxRetries,
Name: task.TargetName,
Type: task.TargetType,
Config: task.TargetConfig,
MaxAttempts: task.MaxAttempts,
}
target.ID = task.TargetID
@@ -1906,12 +1909,13 @@ func (e *Engine) takeForRedispatch(
return false
}
// GORM's clock, as writeDeliveryStatus explains.
res := webhookDB.
Model(&database.Delivery{}).
Where(
"id = ? AND status = ?", deliveryID, eligible,
).
UpdateColumn("updated_at", time.Now())
UpdateColumn("updated_at", webhookDB.NowFunc())
if res.Error != nil {
e.log.Error(
@@ -2024,7 +2028,7 @@ func (e *Engine) countAttemptsBatch(
// One delivery id per recorded attempt, tallied here rather than
// grouped in SQL: internal/gormlog forbids (*gorm.DB).Scan, which
// a GROUP BY into a struct would need, and an attempt row per
// delivery is bounded by the target's MaxRetries.
// delivery is bounded by the target's MaxAttempts.
var attemptIDs []string
err := webhookDB.
@@ -2102,7 +2106,7 @@ func buildRecoveryTask(
TargetName: target.Name,
TargetType: target.Type,
TargetConfig: target.Config,
MaxRetries: target.MaxRetries,
MaxAttempts: target.MaxAttempts,
Method: event.Method,
RawQuery: event.RawQuery,
Headers: event.Headers,
internal/delivery/engine_integration_test.go
+24 -41
View File
@@ -170,7 +170,7 @@ func iTask(
d database.Delivery,
event database.Event,
webhookID, targetID, name, config string,
maxRetries, attemptNum int,
maxAttempts, attemptNum int,
body *string,
) delivery.Task {
return delivery.Task{
@@ -181,7 +181,7 @@ func iTask(
TargetName: name,
TargetType: database.TargetTypeHTTP,
TargetConfig: config,
MaxRetries: maxRetries,
MaxAttempts: maxAttempts,
Method: event.Method,
Headers: event.Headers,
ContentType: event.ContentType,
@@ -242,7 +242,7 @@ func TestProcessNewTask_InlineBody(t *testing.T) {
cfg := iHTTPConfig(ts.URL)
task := iTask(
d, event, s.WebhookID, targetID,
"test-target", cfg, 0, 1, &bodyStr,
"test-target", cfg, 1, 1, &bodyStr,
)
s.Engine.ExportProcessNewTask(
@@ -293,7 +293,7 @@ func TestProcessNewTask_LargeBody_FetchFromDB(
cfg := iHTTPConfig(ts.URL)
task := iTask(
d, event, s.WebhookID, targetID,
"test-large", cfg, 0, 1, nil,
"test-large", cfg, 1, 1, nil,
)
s.Engine.ExportProcessNewTask(
@@ -320,7 +320,7 @@ func TestProcessNewTask_InvalidWebhookID(t *testing.T) {
TargetName: "test",
TargetType: database.TargetTypeHTTP,
TargetConfig: iHTTPConfig("http://localhost:9999"),
MaxRetries: 0,
MaxAttempts: 1,
Body: nil,
AttemptNum: 1,
}
@@ -645,7 +645,7 @@ func TestRecoverPendingDeliveries(t *testing.T) {
iCreateTarget(t, s.MainDB, targetID,
s.WebhookID, "recovery-target",
database.TargetTypeLog, "", 0,
database.TargetTypeLog, "", 1,
)
iSeedPendingDeliveries(
@@ -686,17 +686,17 @@ func iCreateTarget(
targetID, webhookID, name string,
targetType database.TargetType,
config string,
maxRetries int,
maxAttempts int,
) {
t.Helper()
target := database.Target{
WebhookID: webhookID,
Name: name,
Type: targetType,
Active: true,
Config: config,
MaxRetries: maxRetries,
WebhookID: webhookID,
Name: name,
Type: targetType,
Active: true,
Config: config,
MaxAttempts: maxAttempts,
}
target.ID = targetID
@@ -963,29 +963,12 @@ func TestFailUnretryableRetry_WritesNoTargetRow(
database.DeliveryStatusFailed,
)
// The table exists in the per-webhook database because GORM
// migrates the Delivery relation's model alongside it. It must
// stay empty.
var targetRows int64
require.NoError(t, s.WebhookDB.
Table("targets").
Count(&targetRows).Error)
assert.Zero(t, targetRows,
// The per-webhook database has no targets table, so writing a
// target row there would have failed the status write above.
assert.False(t, s.WebhookDB.Migrator().HasTable("targets"),
"orphaned-retry terminal failure wrote a target row "+
"into the per-webhook event database",
)
var configs []string
require.NoError(t, s.WebhookDB.
Table("targets").
Pluck("config", &configs).Error)
assert.NotContains(
t, strings.Join(configs, " "), hookURL,
)
}
func TestRecoverSingleRetry_UnknownTargetType(
@@ -1094,7 +1077,7 @@ func TestRecoverInFlight_WithPendingDeliveries(
iCreateTarget(t, s.MainDB, targetID,
s.WebhookID, "recover-target",
database.TargetTypeLog, "", 0,
database.TargetTypeLog, "", 1,
)
event := iSeedEvent(
@@ -1249,7 +1232,7 @@ func TestDeliverHTTP_CustomTargetHeaders(t *testing.T) {
task := iTask(
d, event, s.WebhookID, targetID,
"auth-target", string(cfgJSON),
0, 1, &bodyStr,
1, 1, &bodyStr,
)
s.Engine.ExportProcessNewTask(
@@ -1294,7 +1277,7 @@ func TestDeliverHTTP_TargetTimeout(t *testing.T) {
task, d := iHTTPTaskAndDelivery(
event, del, "timeout-target",
string(cfgJSON), 0, 1,
string(cfgJSON), 1, 1,
)
e.ExportDeliverHTTP(context.TODO(), db, d, task)
@@ -1356,7 +1339,7 @@ func TestDeliverHTTP_CutsStoredResponseAtMaxBodyLog(
bodyStr := event.Body
task := iTask(
del, event, s.WebhookID, targetID,
"cut-target", cfgJSON, 0, 1, &bodyStr,
"cut-target", cfgJSON, 1, 1, &bodyStr,
)
s.Engine.ExportProcessNewTask(context.TODO(), &task)
@@ -1420,7 +1403,7 @@ func iHTTPTaskAndDelivery(
event database.Event,
del database.Delivery,
name, config string,
maxRetries, attemptNum int,
maxAttempts, attemptNum int,
) (*delivery.Task, *database.Delivery) {
task := &delivery.Task{
DeliveryID: del.ID,
@@ -1430,7 +1413,7 @@ func iHTTPTaskAndDelivery(
TargetName: name,
TargetType: database.TargetTypeHTTP,
TargetConfig: config,
MaxRetries: maxRetries,
MaxAttempts: maxAttempts,
AttemptNum: attemptNum,
}
@@ -1483,7 +1466,7 @@ func TestDeliverHTTP_InvalidConfig(t *testing.T) {
)
task, d := iHTTPTaskAndDelivery(
event, del, "bad-config", `not-json`, 0, 1,
event, del, "bad-config", `not-json`, 1, 1,
)
e.ExportDeliverHTTP(context.TODO(), db, d, task)
@@ -1507,7 +1490,7 @@ func TestDeliverHTTP_InvalidConfigUnrecordedStaysPending(t *testing.T) {
)
task, d := iHTTPTaskAndDelivery(
event, del, "bad-config", `not-json`, 0, 1,
event, del, "bad-config", `not-json`, 1, 1,
)
require.NoError(t, db.Exec("drop table delivery_results").Error)
internal/delivery/engine_lifecycle_test.go
+153
View File
@@ -2,11 +2,16 @@ package delivery_test
import (
"context"
"io"
"net/http"
"net/http/httptest"
"path/filepath"
"sync"
"testing"
"time"
"github.com/google/uuid"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"go.uber.org/fx"
"gorm.io/gorm/clause"
@@ -272,6 +277,154 @@ func TestEngine_StopHookHonoursStopTimeout(t *testing.T) {
requireStopHookExpires(t, lc.hooks[0], "delivery engine")
}
// seedHeldDelivery gives the setup's webhook an http target with
// maxAttempts, pointed at a receiver that keeps every request open until
// the client gives up on it, and seeds one delivery to that target at
// status. It returns the task that sends attempt attemptNum of the
// delivery, and a channel that is closed when a request reaches the
// receiver.
func seedHeldDelivery(
t *testing.T,
s iSetup,
maxAttempts int,
status database.DeliveryStatus,
attemptNum int,
) (delivery.Task, <-chan struct{}) {
t.Helper()
arrived := make(chan struct{})
var once sync.Once
ts := httptest.NewServer(http.HandlerFunc(
func(_ http.ResponseWriter, r *http.Request) {
// The server notices the client hanging up only once the
// body has been read; until then r.Context() never ends.
_, _ = io.Copy(io.Discard, r.Body)
once.Do(func() { close(arrived) })
<-r.Context().Done()
},
))
t.Cleanup(ts.Close)
cfg := iHTTPConfig(ts.URL)
targetID := uuid.New().String()
iCreateWebhook(t, s.MainDB, s.WebhookID, "hook")
iCreateTarget(
t, s.MainDB, targetID, s.WebhookID, "held",
database.TargetTypeHTTP, cfg, maxAttempts,
)
event := iSeedEvent(t, s.WebhookDB, s.WebhookID, `{"held":true}`)
d := iSeedDelivery(t, s.WebhookDB, event.ID, targetID, status)
bodyStr := event.Body
return iTask(
d, event, s.WebhookID, targetID, "held", cfg,
maxAttempts, attemptNum, &bodyStr,
), arrived
}
// stopDuringAttempt waits until the receiver holds an attempt open, then
// stops the engine through its real stop hook.
func stopDuringAttempt(
t *testing.T, lc *recordingLifecycle, arrived <-chan struct{},
) {
t.Helper()
select {
case <-arrived:
case <-time.After(5 * time.Second):
t.Fatal("the delivery attempt never reached the receiver")
}
require.NoError(t, lc.hooks[0].OnStop(context.Background()))
}
// requireRequeued runs restart recovery on the stopped engine and
// requires it to queue task's attempt again on ch.
func requireRequeued(
t *testing.T, s iSetup, ch <-chan delivery.Task, task delivery.Task,
) {
t.Helper()
s.Engine.ExportRecoverWebhookDeliveries(
context.Background(), s.WebhookID,
)
select {
case got := <-ch:
assert.Equal(t, task.DeliveryID, got.DeliveryID)
assert.Equal(t, task.AttemptNum, got.AttemptNum)
case <-time.After(5 * time.Second):
t.Fatal("restart recovery did not queue the delivery again")
}
}
// TestEngine_StopLeavesFireAndForgetAttemptPending is the regression
// test for a stop that turned an attempt in flight into a terminal
// failure. Stopping the engine cancels the request; for a target with
// no retries that was the delivery's only attempt, recorded as failed
// with "context canceled", and nothing ever sent it again. The
// delivery must instead stay pending, with no result and no count in
// the attempt metrics, for restart recovery to send.
func TestEngine_StopLeavesFireAndForgetAttemptPending(t *testing.T) {
t.Parallel()
s := newISetup(t)
reg := mIsolate(t, s)
lc := startEngineViaHook(t, s.Engine)
task, arrived := seedHeldDelivery(
t, s, 1, database.DeliveryStatusPending, 1,
)
s.Engine.Notify([]delivery.Task{task})
stopDuringAttempt(t, lc, arrived)
iAssertStatus(
t, s.WebhookDB, task.DeliveryID, database.DeliveryStatusPending,
)
assert.Empty(t, iResults(t, s.WebhookDB, task.DeliveryID))
assert.Zero(t, mCounter(t, reg, mAttempts, mTypeHTTP))
assert.Zero(t, mHTTPDurations(t, reg))
requireRequeued(t, s, s.Engine.ExportDeliveryCh(), task)
}
// TestEngine_StopLeavesLastRetryAttemptRetrying is the same regression
// for a target with retries, on its last attempt: the cancelled attempt
// used to exhaust the retries and end the delivery failed. It must stay
// retrying with only its earlier attempt recorded, and restart recovery
// must send that last attempt again.
func TestEngine_StopLeavesLastRetryAttemptRetrying(t *testing.T) {
t.Parallel()
const maxAttempts = 2
s := newISetup(t)
lc := startEngineViaHook(t, s.Engine)
task, arrived := seedHeldDelivery(
t, s, maxAttempts, database.DeliveryStatusRetrying, maxAttempts,
)
iSeedFailedResult(t, s.WebhookDB, task.DeliveryID)
s.Engine.ExportScheduleRetry(task, 0)
stopDuringAttempt(t, lc, arrived)
iAssertStatus(
t, s.WebhookDB, task.DeliveryID, database.DeliveryStatusRetrying,
)
assert.Len(t, iResults(t, s.WebhookDB, task.DeliveryID), 1)
requireRequeued(t, s, s.Engine.ExportRetryCh(), task)
}
// deliverToArchive gives the setup's webhook a database target,
// runs one delivery to it through the running engine, and returns
// the target's ID and archive file path. The archive writer holds
internal/delivery/engine_test.go
+131 -52
View File
@@ -10,7 +10,6 @@ import (
"net/http"
"net/http/httptest"
"os"
"path/filepath"
"strconv"
"strings"
"sync"
@@ -22,12 +21,11 @@ import (
"github.com/prometheus/client_golang/prometheus"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"gorm.io/driver/sqlite"
"gorm.io/gorm"
_ "modernc.org/sqlite"
"sneak.berlin/go/webhooker/internal/database"
"sneak.berlin/go/webhooker/internal/database/databasetest"
"sneak.berlin/go/webhooker/internal/delivery"
"sneak.berlin/go/webhooker/internal/gormlog"
"sneak.berlin/go/webhooker/internal/metrics"
)
@@ -37,35 +35,18 @@ const testContentType = "application/json"
func testWebhookDB(t *testing.T) *gorm.DB {
t.Helper()
dbPath := filepath.Join(
t.TempDir(), "events-test.db",
// Opened by the manager the service uses, so these tests cannot
// pass against a schema, journal and locking settings or write
// guard production does not use.
mgr := databasetest.NewWebhookDBManagerWithLogger(
t, t.TempDir(), slog.New(slog.DiscardHandler),
)
// Opened the way the service opens a per-webhook database, so
// these tests cannot pass against journal and locking settings
// production does not use.
sqlDB, err := database.OpenSQLite(
dbPath, database.SQLiteModeCreate,
)
t.Cleanup(func() { _ = mgr.CloseAll() })
db, err := mgr.GetDB(uuid.New().String())
require.NoError(t, err)
t.Cleanup(func() { _ = sqlDB.Close() })
db, err := gorm.Open(
sqlite.Dialector{Conn: sqlDB},
&gorm.Config{Logger: gormlog.New(slog.New(slog.DiscardHandler))},
)
require.NoError(t, err)
require.NoError(t, db.AutoMigrate(
&database.Event{},
&database.Delivery{},
&database.DeliveryResult{},
&database.EventTotals{},
&database.TargetTotals{},
))
require.NoError(t, db.Create(&database.EventTotals{}).Error)
return db
}
@@ -136,6 +117,18 @@ func seedDelivery(
return d
}
// assertStoredTime asserts that text, a timestamp as SQLite holds it,
// is in the form GORM stores created_at in: the layout of
// time.Time.String, with no " m=+…" monotonic clock reading after it.
func assertStoredTime(t *testing.T, text string) {
t.Helper()
_, err := time.Parse(
"2006-01-02 15:04:05.999999999 -0700 MST", text,
)
assert.NoError(t, err, "stored as %q", text)
}
// httpDeliveryFixture holds the task and delivery needed
// for HTTP delivery tests.
type httpDeliveryFixture struct {
@@ -149,7 +142,7 @@ func buildHTTPFixture(
dlv database.Delivery,
event database.Event,
targetID, name, config string,
maxRetries, attemptNum int,
maxAttempts, attemptNum int,
) httpDeliveryFixture {
task := &delivery.Task{
DeliveryID: dlv.ID,
@@ -159,7 +152,7 @@ func buildHTTPFixture(
TargetName: name,
TargetType: database.TargetTypeHTTP,
TargetConfig: config,
MaxRetries: maxRetries,
MaxAttempts: maxAttempts,
AttemptNum: attemptNum,
}
@@ -169,10 +162,10 @@ func buildHTTPFixture(
Status: dlv.Status,
Event: event,
Target: database.Target{
Name: name,
Type: database.TargetTypeHTTP,
Config: config,
MaxRetries: maxRetries,
Name: name,
Type: database.TargetTypeHTTP,
Config: config,
MaxAttempts: maxAttempts,
},
}
d.ID = dlv.ID
@@ -284,7 +277,7 @@ func TestDeliverHTTP_Success(t *testing.T) {
cfg := newHTTPTargetConfig(ts.URL)
fix := buildHTTPFixture(
dlv, event, targetID, "test-http", cfg, 0, 1,
dlv, event, targetID, "test-http", cfg, 1, 1,
)
e.ExportDeliverHTTP(
@@ -331,7 +324,7 @@ func TestDeliverHTTP_Failure(t *testing.T) {
cfg := newHTTPTargetConfig(ts.URL)
fix := buildHTTPFixture(
dlv, event, targetID,
"test-http-fail", cfg, 0, 1,
"test-http-fail", cfg, 1, 1,
)
e.ExportDeliverHTTP(
@@ -480,14 +473,23 @@ func TestDeliverHTTP_WithRetries_Success(t *testing.T) {
)
}
func TestDeliverHTTP_MaxRetriesExhausted(t *testing.T) {
// TestDeliverHTTP_MaxAttemptsExhausted proves a target with three
// delivery attempts makes at most three: the first two failures are
// retried, the third is final, and each attempt goes through the
// target's circuit breaker.
func TestDeliverHTTP_MaxAttemptsExhausted(t *testing.T) {
t.Parallel()
const maxAttempts = 3
db := testWebhookDB(t)
var requests atomic.Int32
ts := httptest.NewServer(
http.HandlerFunc(
func(w http.ResponseWriter, _ *http.Request) {
requests.Add(1)
w.WriteHeader(http.StatusBadGateway)
},
),
@@ -496,26 +498,103 @@ func TestDeliverHTTP_MaxRetriesExhausted(t *testing.T) {
e := testEngine(t, 1)
targetID := uuid.New().String()
// It opens on the last failure only if every attempt reached it.
cb := delivery.NewTestCircuitBreaker(maxAttempts, time.Minute)
e.ExportSetCircuitBreaker(targetID, cb)
event := seedEvent(t, db, `{"retry":"exhaust"}`)
dlv := seedDelivery(
t, db, event.ID, targetID,
database.DeliveryStatusRetrying,
database.DeliveryStatusPending,
)
cfg := newHTTPTargetConfig(ts.URL)
sched := &recordingScheduler{}
for attempt := 1; attempt <= maxAttempts; attempt++ {
fix := buildHTTPFixture(
dlv, event, targetID,
"test-http-exhaust", cfg, maxAttempts, attempt,
)
e.ExportDeliverHTTPWithScheduler(
context.TODO(), db, fix.Delivery, fix.Task, sched,
)
}
assert.Equal(t, int32(maxAttempts), requests.Load())
assert.Len(t, sched.delays, maxAttempts-1,
"every failure but the last should be retried",
)
assertDeliveryStatus(t, db, dlv.ID,
database.DeliveryStatusFailed,
)
assert.Equal(t, delivery.CircuitOpen, cb.State(),
"every attempt should be counted by the circuit breaker",
)
}
// TestDeliverHTTP_SingleAttemptSkipsCircuitBreaker proves a target
// with one delivery attempt makes exactly that attempt, even while
// its circuit breaker is open, and that a failure is final.
func TestDeliverHTTP_SingleAttemptSkipsCircuitBreaker(t *testing.T) {
t.Parallel()
db := testWebhookDB(t)
var requests atomic.Int32
ts := httptest.NewServer(
http.HandlerFunc(
func(w http.ResponseWriter, _ *http.Request) {
requests.Add(1)
w.WriteHeader(http.StatusBadGateway)
},
),
)
defer ts.Close()
e := testEngine(t, 1)
targetID := uuid.New().String()
cb := e.ExportGetCircuitBreaker(targetID)
for range delivery.ExportDefaultFailureThreshold {
cb.RecordFailure()
}
require.Equal(t, delivery.CircuitOpen, cb.State())
event := seedEvent(t, db, `{"retry":"none"}`)
dlv := seedDelivery(
t, db, event.ID, targetID,
database.DeliveryStatusPending,
)
cfg := newHTTPTargetConfig(ts.URL)
fix := buildHTTPFixture(
dlv, event, targetID,
"test-http-exhaust", cfg, 3, 3,
"test-http-single", cfg, 1, 1,
)
sched := &recordingScheduler{}
e.ExportDeliverHTTPWithScheduler(
context.TODO(), db, fix.Delivery, fix.Task, sched,
)
e.ExportDeliverHTTP(
context.TODO(), db, fix.Delivery, fix.Task,
assert.Equal(t, int32(1), requests.Load(),
"the open circuit breaker should not hold the attempt back",
)
assert.Empty(t, sched.delays, "no retry should be scheduled")
assertDeliveryStatus(t, db, dlv.ID,
database.DeliveryStatusFailed,
)
assertDeliveryResult(
t, db, dlv.ID, false, http.StatusBadGateway,
)
}
func TestDeliverHTTP_SchedulesRetryOnFailure(
@@ -748,7 +827,7 @@ func seedConcurrencyTasks(
TargetName: tasks[i].Target.Name,
TargetType: tasks[i].Target.Type,
TargetConfig: tasks[i].Target.Config,
MaxRetries: 0,
MaxAttempts: 1,
AttemptNum: 1,
}
}
@@ -2058,10 +2137,10 @@ func buildSlackRetryDelivery(
Status: database.DeliveryStatusPending,
Event: event,
Target: database.Target{
Name: "test-slack-retry",
Type: database.TargetTypeSlack,
Config: cfg,
MaxRetries: 5,
Name: "test-slack-retry",
Type: database.TargetTypeSlack,
Config: cfg,
MaxAttempts: 5,
},
}
d.ID = dlv.ID
@@ -2096,11 +2175,11 @@ func TestDeliverSlack_WithRetries_SchedulesRetry(
)
task := &delivery.Task{
DeliveryID: dlv.ID,
TargetID: targetID,
TargetType: database.TargetTypeSlack,
MaxRetries: 5,
AttemptNum: 1,
DeliveryID: dlv.ID,
TargetID: targetID,
TargetType: database.TargetTypeSlack,
MaxAttempts: 5,
AttemptNum: 1,
}
e.ExportProcessDelivery(context.TODO(), db, d, task)
internal/delivery/event_db_isolation_test.go
+1 -1
View File
@@ -152,7 +152,7 @@ func TestEventDBHoldsNoTargetRowsOnFailedDelivery(t *testing.T) {
)
task := iTask(
d, event, s.WebhookID, targetID,
"leaky-target", cfg, 0, 1, &body,
"leaky-target", cfg, 1, 1, &body,
)
s.Engine.ExportProcessNewTask(context.TODO(), &task)
internal/delivery/event_timestamp_test.go
+1 -1
View File
@@ -176,7 +176,7 @@ func tsTask(
TargetName: target.Name,
TargetType: database.TargetTypeSlack,
TargetConfig: target.Config,
MaxRetries: 0,
MaxAttempts: 1,
Method: event.Method,
Headers: event.Headers,
ContentType: event.ContentType,
internal/delivery/inflight_test.go
+12 -2
View File
@@ -229,7 +229,7 @@ func TestOwnershipIsReleasedAfterDelivery(t *testing.T) {
iCreateTarget(t, s.MainDB, targetID,
s.WebhookID, "released",
database.TargetTypeLog, "", 0,
database.TargetTypeLog, "", 1,
)
event := iSeedEvent(
@@ -462,7 +462,8 @@ func TestScheduledRetryIsNotSweptDuringBackoff(t *testing.T) {
// TestRedispatchStampsTheRow pins the cadence control: a stranded
// delivery that has just been handed out is not selected again by the
// next tick a minute later.
// next tick a minute later. The stamp is stored in the same form as
// created_at.
func TestRedispatchStampsTheRow(t *testing.T) {
t.Parallel()
@@ -493,4 +494,13 @@ func TestRedispatchStampsTheRow(t *testing.T) {
"a re-dispatched delivery must be stamped so the "+
"next tick does not select it again",
)
var createdAt, updatedAt string
require.NoError(t, s.WebhookDB.Raw(
`SELECT CAST(created_at AS TEXT), CAST(updated_at AS TEXT)
FROM deliveries WHERE id = ?`, d.ID,
).Row().Scan(&createdAt, &updatedAt))
assertStoredTime(t, createdAt)
assertStoredTime(t, updatedAt)
}
internal/delivery/metrics_test.go
+10 -10
View File
@@ -291,20 +291,20 @@ func TestDeliveryMetrics_CircuitBreakerGauge(t *testing.T) {
body := event.Body
cfg := iHTTPConfig(ts.URL)
// A retry budget above the failure threshold, so the breaker
// An attempt budget above the failure threshold, so the breaker
// rather than the budget is what stops the delivery.
maxRetries := delivery.ExportDefaultFailureThreshold + 5
maxAttempts := delivery.ExportDefaultFailureThreshold + 5
// The retries below are only run if their target still exists;
// see https://git.eeqj.de/sneak/webhooker/issues/107.
iCreateTarget(
t, s.MainDB, targetID, s.WebhookID, "metrics-trip",
database.TargetTypeHTTP, cfg, maxRetries,
database.TargetTypeHTTP, cfg, maxAttempts,
)
first := iTask(
d, event, s.WebhookID, targetID,
"metrics-trip", cfg, maxRetries, 1, &body,
"metrics-trip", cfg, maxAttempts, 1, &body,
)
s.Engine.ExportProcessNewTask(context.TODO(), &first)
@@ -316,7 +316,7 @@ func TestDeliveryMetrics_CircuitBreakerGauge(t *testing.T) {
ExportDefaultFailureThreshold; attempt++ {
task := iTask(
d, event, s.WebhookID, targetID,
"metrics-trip", cfg, maxRetries, attempt, &body,
"metrics-trip", cfg, maxAttempts, attempt, &body,
)
s.Engine.ExportProcessRetryTask(
@@ -364,16 +364,16 @@ func TestDeliveryMetrics_BreakerBlockedIsNotAnAttempt(
body := event.Body
cfg := iHTTPConfig(ts.URL)
maxRetries := delivery.ExportDefaultFailureThreshold + 5
maxAttempts := delivery.ExportDefaultFailureThreshold + 5
iCreateTarget(
t, s.MainDB, targetID, s.WebhookID, "metrics-blocked",
database.TargetTypeHTTP, cfg, maxRetries,
database.TargetTypeHTTP, cfg, maxAttempts,
)
first := iTask(
d, event, s.WebhookID, targetID,
"metrics-blocked", cfg, maxRetries, 1, &body,
"metrics-blocked", cfg, maxAttempts, 1, &body,
)
s.Engine.ExportProcessNewTask(context.TODO(), &first)
@@ -382,7 +382,7 @@ func TestDeliveryMetrics_BreakerBlockedIsNotAnAttempt(
ExportDefaultFailureThreshold; attempt++ {
task := iTask(
d, event, s.WebhookID, targetID,
"metrics-blocked", cfg, maxRetries, attempt, &body,
"metrics-blocked", cfg, maxAttempts, attempt, &body,
)
s.Engine.ExportProcessRetryTask(context.TODO(), &task)
@@ -405,7 +405,7 @@ func TestDeliveryMetrics_BreakerBlockedIsNotAnAttempt(
blocked := iTask(
d, event, s.WebhookID, targetID,
"metrics-blocked", cfg, maxRetries,
"metrics-blocked", cfg, maxAttempts,
delivery.ExportDefaultFailureThreshold+1, &body,
)
internal/delivery/recovery_durability_test.go
+6 -6
View File
@@ -66,7 +66,7 @@ func TestRecoverySkipsPendingWithSuccessfulResult(
iCreateTarget(t, s.MainDB, targetID,
s.WebhookID, "already-delivered",
database.TargetTypeLog, "", 0,
database.TargetTypeLog, "", 1,
)
event := iSeedEvent(
@@ -129,7 +129,7 @@ func TestRecoveryContinuesTheAttemptNumbering(t *testing.T) {
iCreateTarget(t, s.MainDB, targetID,
s.WebhookID, "numbering",
database.TargetTypeLog, "", 0,
database.TargetTypeLog, "", 1,
)
event := iSeedEvent(
@@ -444,10 +444,10 @@ func TestFailedResultWriteWithRetriesLeavesDeliveryRecoverable(
Status: database.DeliveryStatusPending,
Event: event,
Target: database.Target{
Name: "unwritable",
Type: database.TargetTypeHTTP,
Config: iHTTPConfig(ts.URL),
MaxRetries: 3,
Name: "unwritable",
Type: database.TargetTypeHTTP,
Config: iHTTPConfig(ts.URL),
MaxAttempts: 3,
},
}
full.ID = d.ID
internal/delivery/target.go
+2 -1
View File
@@ -32,7 +32,8 @@ type Scheduler interface {
// Engine.observeAttempt, alongside the DeliveryResult it records for
// it. Deliver is also entered for attempts that never happen — an
// open circuit breaker refuses one — so the count cannot be taken
// from around this call.
// from around this call. An attempt cut off by a stop is neither
// counted nor recorded.
type Target interface {
Deliver(
ctx context.Context,
internal/delivery/target_config_view.go
+9 -14
View File
@@ -120,8 +120,8 @@ func unavailableConfigFields() []ConfigField {
}
// slackConfigFields describes a Slack target: its masked
// webhook URL and its retry count. Only the masked URL is
// shown; the full URL is the credential.
// webhook URL and its number of delivery attempts. Only the
// masked URL is shown; the full URL is the credential.
func slackConfigFields(t *database.Target) []ConfigField {
cfg, err := parseSlackConfig(t.Config)
if err != nil {
@@ -131,7 +131,7 @@ func slackConfigFields(t *database.Target) []ConfigField {
return []ConfigField{{
Label: "Webhook URL",
Value: cfg.MaskedWebhookURL(),
}, maxRetriesField(t)}
}, maxAttemptsField(t)}
}
// httpConfigFields describes an HTTP target: its destination
@@ -178,23 +178,18 @@ func httpConfigFields(t *database.Target) []ConfigField {
})
}
fields = append(fields, maxRetriesField(t))
fields = append(fields, maxAttemptsField(t))
return fields
}
// maxRetriesField describes a target's retry count, which lives
// on the target row rather than in its configuration blob. A
// stored 0 makes a single attempt, so it is shown as 1.
func maxRetriesField(t *database.Target) ConfigField {
attempts := strconv.Itoa(t.MaxRetries)
if t.MaxRetries == 0 {
attempts = "1 (fire-and-forget: no retries, no circuit breaker)"
}
// maxAttemptsField describes a target's number of delivery
// attempts, which lives on the target row rather than in its
// configuration blob.
func maxAttemptsField(t *database.Target) ConfigField {
return ConfigField{
Label: "Delivery attempts",
Value: attempts,
Value: strconv.Itoa(t.MaxAttempts),
}
}
internal/delivery/target_config_view_test.go
+20 -15
View File
@@ -32,7 +32,7 @@ const (
viewMaskedOrigin = viewExampleOrigin + "/..."
viewUnavailable = "(unavailable)"
viewExpiryNever = "never"
viewMaxRetries = "Delivery attempts"
viewMaxAttempts = "Delivery attempts"
)
func TestMaskedWebhookURL(t *testing.T) {
@@ -171,6 +171,7 @@ func slackTarget() database.Target {
Active: true,
Config: `{"webhookUrl":"` +
slackWebhookURL + `"}`,
MaxAttempts: 1,
}
}
@@ -189,28 +190,29 @@ func TestNewTargetViews_Slack(t *testing.T) {
assert.Equal(
t,
map[string]string{
"Webhook URL": slackMaskedURL,
viewMaxRetries: "1 (fire-and-forget: no retries, no circuit breaker)",
"Webhook URL": slackMaskedURL,
viewMaxAttempts: "1",
},
fieldMap(view.Config),
)
}
// TestNewTargetViews_SlackRetries proves a Slack target shows
// its retry count the same way an HTTP target does.
func TestNewTargetViews_SlackRetries(t *testing.T) {
// TestNewTargetViews_SlackAttempts proves a Slack target shows
// its number of delivery attempts the same way an HTTP target
// does.
func TestNewTargetViews_SlackAttempts(t *testing.T) {
t.Parallel()
target := slackTarget()
target.MaxRetries = 2
target.MaxAttempts = 2
view := viewFor(t, target)
assert.Equal(
t,
map[string]string{
"Webhook URL": slackMaskedURL,
viewMaxRetries: "2",
"Webhook URL": slackMaskedURL,
viewMaxAttempts: "2",
},
fieldMap(view.Config),
)
@@ -225,7 +227,7 @@ func TestNewTargetViews_HTTP(t *testing.T) {
`"timeout":30,` +
`"headers":{"Authorization":"Bearer sekrit"},` +
`"forwardQuery":true}`,
MaxRetries: 5,
MaxAttempts: 5,
})
fields := fieldMap(view.Config)
@@ -237,7 +239,7 @@ func TestNewTargetViews_HTTP(t *testing.T) {
"Timeout": "30s",
"Headers": "1 configured",
"Query string": "passed on to this target",
viewMaxRetries: "5",
viewMaxAttempts: "5",
},
fields,
)
@@ -248,19 +250,22 @@ func TestNewTargetViews_HTTP(t *testing.T) {
}
}
func TestNewTargetViews_HTTPFireAndForget(t *testing.T) {
// TestNewTargetViews_HTTPSingleAttempt proves a single attempt is
// shown as the plain number, like any other.
func TestNewTargetViews_HTTPSingleAttempt(t *testing.T) {
t.Parallel()
view := viewFor(t, database.Target{
Type: database.TargetTypeHTTP,
Config: `{"url":"` + viewExampleHook + `"}`,
Type: database.TargetTypeHTTP,
Config: `{"url":"` + viewExampleHook + `"}`,
MaxAttempts: 1,
})
assert.Equal(
t,
map[string]string{
"Destination URL": viewMaskedOrigin,
viewMaxRetries: "1 (fire-and-forget: no retries, no circuit breaker)",
viewMaxAttempts: "1",
},
fieldMap(view.Config),
)
internal/delivery/target_database_archive.go
+7 -2
View File
@@ -14,6 +14,7 @@ import (
"gorm.io/driver/sqlite"
"gorm.io/gorm"
"sneak.berlin/go/webhooker/internal/database"
"sneak.berlin/go/webhooker/internal/db/migrations"
"sneak.berlin/go/webhooker/internal/gormlog"
)
@@ -276,7 +277,11 @@ func (w *archiveWriter) write(
}
}
row.ArchivedAt = time.Now()
// GORM's clock, the one that stamps created_at in the other
// databases, so this is stored in the same form. A bare time.Now()
// carries a monotonic clock reading, which the driver would store
// as an " m=+…" suffix.
row.ArchivedAt = w.db.NowFunc()
err := w.db.Create(&row).Error
if err != nil {
@@ -335,7 +340,7 @@ func (w *archiveWriter) openMode(
)
}
err = gdb.AutoMigrate(&archivedEvent{})
err = migrations.Apply(gdb, migrations.Archive)
if err != nil {
_ = sqlDB.Close()
internal/delivery/target_database_test.go
+7
View File
@@ -150,6 +150,13 @@ func TestArchiveWriter_WritesRow(t *testing.T) {
assert.Equal(t, row.ContentType, got[0].ContentType)
assert.JSONEq(t, `{"hello":"world"}`, got[0].Body)
assert.False(t, got[0].ArchivedAt.IsZero())
var archivedAt string
require.NoError(t, w.DB().Raw(
"SELECT CAST(archived_at AS TEXT) FROM archived_events",
).Row().Scan(&archivedAt))
assertStoredTime(t, archivedAt)
}
func TestArchiveWriter_RecreatesAfterRemoval(
internal/delivery/target_headers.go
+2 -2
View File
@@ -82,8 +82,8 @@ func isReservedTargetHeader(name string) bool {
// one pair silently overwriting the other.
//
// An input with no pairs yields an empty map, which omitempty drops
// from the stored config: a target configured with no headers keeps
// the same config JSON it had before this field existed.
// from the stored config, so a target configured with no headers
// stores no headers key at all.
func ParseTargetHeaders(raw string) (map[string]string, error) {
headers := make(map[string]string)
internal/delivery/target_http.go
+57 -14
View File
@@ -53,34 +53,72 @@ type httpCore struct {
}
// deliver runs one delivery attempt through the retry core.
// A maxRetries of 0 is fire-and-forget: a single attempt is
// recorded and no circuit breaker is consulted. A positive
// maxRetries gates the attempt on the circuit breaker and
// schedules a backed-off retry on failure.
// A maxAttempts of 1 is a single attempt, recorded without
// consulting a circuit breaker. A higher maxAttempts gates the
// attempt on the circuit breaker and schedules a backed-off retry
// on failure, until maxAttempts attempts have been made.
//
// ctx is the context attempt sends its request with. Stopping the
// engine cancels it; see interruptedByStop.
func (c *httpCore) deliver(
ctx context.Context,
webhookDB *gorm.DB,
d *database.Delivery,
task *Task,
sched Scheduler,
maxRetries int,
maxAttempts int,
attempt func() attemptResult,
) {
if maxRetries == 0 {
c.fireAndForget(webhookDB, d, attempt())
if maxAttempts <= 1 {
c.fireAndForget(ctx, webhookDB, d, attempt())
return
}
c.withRetry(
webhookDB, d, task, sched, maxRetries, attempt,
ctx, webhookDB, d, task, sched, maxAttempts, attempt,
)
}
// interruptedByStop reports whether an attempt failed because the
// engine is stopping, which cancels the context its request is made
// with. Such an attempt is not recorded: no DeliveryResult, no circuit
// breaker outcome, no status change, no count in the attempt metrics.
// The delivery stays pending or retrying, and startup recovery sends
// it again on the next start.
//
// A target's own timeout leaves that context alone, so its attempt is
// still recorded as the failure it is.
func (c *httpCore) interruptedByStop(
ctx context.Context,
d *database.Delivery,
res attemptResult,
) bool {
if res.success || ctx.Err() == nil {
return false
}
c.eng.log.Warn(
"delivery attempt interrupted by shutdown; not recorded, "+
"it is sent again on the next start",
"delivery_id", d.ID,
"event_id", d.EventID,
"target_id", d.TargetID,
)
return true
}
func (c *httpCore) fireAndForget(
ctx context.Context,
webhookDB *gorm.DB,
d *database.Delivery,
res attemptResult,
) {
if c.interruptedByStop(ctx, d, res) {
return
}
c.eng.observeAttempt(d.Target.Type, res.elapsed())
err := c.eng.recordResult(
@@ -110,11 +148,12 @@ func (c *httpCore) fireAndForget(
}
func (c *httpCore) withRetry(
ctx context.Context,
webhookDB *gorm.DB,
d *database.Delivery,
task *Task,
sched Scheduler,
maxRetries int,
maxAttempts int,
attempt func() attemptResult,
) {
cb := c.getCircuitBreaker(task.TargetID)
@@ -131,6 +170,10 @@ func (c *httpCore) withRetry(
res := attempt()
if c.interruptedByStop(ctx, d, res) {
return
}
c.eng.observeAttempt(d.Target.Type, res.elapsed())
err := c.eng.recordResult(
@@ -162,7 +205,7 @@ func (c *httpCore) withRetry(
cb.RecordFailure()
c.handleRetry(
webhookDB, d, task, sched, maxRetries, attemptNum,
webhookDB, d, task, sched, maxAttempts, attemptNum,
)
}
@@ -223,10 +266,10 @@ func (c *httpCore) handleRetry(
d *database.Delivery,
task *Task,
sched Scheduler,
maxRetries int,
maxAttempts int,
attemptNum int,
) {
if attemptNum >= maxRetries {
if attemptNum >= maxAttempts {
c.eng.settleStatus(
webhookDB, d, d.Target.Type,
database.DeliveryStatusFailed,
@@ -395,8 +438,8 @@ func (t *httpTarget) Deliver(
}
t.deliver(
webhookDB, d, task, sched,
d.Target.MaxRetries, attempt,
ctx, webhookDB, d, task, sched,
d.Target.MaxAttempts, attempt,
)
}
internal/delivery/target_redact.go
+3 -3
View File
@@ -13,9 +13,9 @@ import (
const RedactionMarker = "(redacted)"
// Redactor removes one target's own credential material from
// text that target's remote peer chose: a delivery response
// body, or a delivery error stored before the delivery path
// learned to mask the URLs it embeds.
// a delivery response body, whose text the target's remote
// peer chose, and from a stored delivery error as a second
// line behind the delivery path's own URL masking.
//
// It removes byte-identical echoes of strings taken from the
// target's stored configuration, and nothing else. Anything
internal/delivery/target_slack.go
+4 -5
View File
@@ -30,9 +30,8 @@ type SlackTargetConfig struct {
// slackTarget delivers events to Slack incoming webhooks. It
// formats the event into a Slack message and posts it as
// JSON. It shares the retry core with the HTTP target: a
// MaxRetries of 0 stays single-attempt fire-and-forget
// (preserving existing Slack targets), while a positive
// MaxRetries adds backoff and circuit breaking.
// MaxAttempts of 1 is a single attempt, while a higher one
// adds backoff and circuit breaking.
type slackTarget struct {
*httpCore
@@ -82,8 +81,8 @@ func (t *slackTarget) Deliver(
}
t.deliver(
webhookDB, d, task, sched,
d.Target.MaxRetries, attempt,
ctx, webhookDB, d, task, sched,
d.Target.MaxAttempts, attempt,
)
}
internal/delivery/terminal_state_test.go
+5 -9
View File
@@ -312,13 +312,9 @@ func TestFailMissingTarget_WritesNoTargetRow(
database.DeliveryStatusFailed,
)
var configs []string
require.NoError(t, s.WebhookDB.
Table("targets").
Pluck("config", &configs).Error)
assert.Empty(t, configs,
// The per-webhook database has no targets table, so writing a
// target row there would have failed the status write above.
assert.False(t, s.WebhookDB.Migrator().HasTable("targets"),
"the deleted-target terminal path wrote a target row "+
"into the per-webhook event database",
)
@@ -747,7 +743,7 @@ func TestSendRecoveredDeliveries_TargetMissingFromMap(
iCreateTarget(
t, s.MainDB, targetID, s.WebhookID, "found-on-lookup",
database.TargetTypeLog, "", 0,
database.TargetTypeLog, "", 1,
)
event := iSeedEvent(
@@ -794,7 +790,7 @@ func TestRecoverPending_TargetUnreadable_LeavesDeliveryAlone(
iCreateTarget(
t, s.MainDB, targetID, s.WebhookID, "healthy",
database.TargetTypeLog, "", 0,
database.TargetTypeLog, "", 1,
)
event := iSeedEvent(
internal/gormlog/gormlog_test.go
+4 -2
View File
@@ -135,9 +135,11 @@ func openDB(
)
require.NoError(t, err)
require.NoError(t, gdb.AutoMigrate(&thing{}))
require.NoError(t, gdb.Exec(
"CREATE TABLE things (id text PRIMARY KEY, name text)",
).Error)
// Migration chatter is not what any of these cases is about.
// Creating the table is not what any of these cases is about.
buf.Reset()
return gdb
internal/gormlog/scan_guard_test.go
+11 -6
View File
@@ -115,8 +115,8 @@ func skipDir(name string) bool {
}
// walkNonTestGo parses every non-test .go file under root. It returns
// the directories, relative to root, it parsed a file in, along with
// every unguarded Scan it found.
// the directories, relative to root, it parsed a file in or below,
// along with every unguarded Scan it found.
func walkNonTestGo(t *testing.T, root string) (map[string]bool, []string) {
t.Helper()
@@ -155,7 +155,12 @@ func walkNonTestGo(t *testing.T, root string) (map[string]bool, []string) {
return err
}
walked[dir] = true
// The directories above count too, so that one holding
// only a nested package, as internal/db does, is not
// taken for one the walk skipped.
for ; dir != "."; dir = filepath.Dir(dir) {
walked[dir] = true
}
for _, pos := range unguardedScans(fset, file) {
hits = append(hits, relPosition(root, pos))
@@ -205,9 +210,9 @@ func TestGormScanIsNeverCalledOutsideTests(t *testing.T) {
walked, offenders := walkNonTestGo(t, root)
// The module's packages are static, templates, and every directory
// directly under cmd and internal. Each holds non-test code, so one
// the walk parsed nothing in was skipped, and a Scan there would
// pass unseen.
// directly under cmd and internal. Each holds non-test code, itself
// or in a package below it, so one the walk parsed nothing in or
// below was skipped, and a Scan there would pass unseen.
packages := []string{"static", "templates"}
for _, parent := range []string{"cmd", "internal"} {
internal/handlers/delivery_attempts_test.go
+1 -1
View File
@@ -43,7 +43,7 @@ func TestDeliveryAttempts_ReadInTheTargetTypesOwnTerms(t *testing.T) {
}
for _, tc := range cases {
t.Run(string(tc.targetType), func(t *testing.T) {
t.Run(string(tc.targetType)+" "+tc.outcome, func(t *testing.T) {
t.Parallel()
f := newRecentEventsFixture(t)
internal/handlers/delivery_replay.go
+1 -1
View File
@@ -308,7 +308,7 @@ func createReplayDelivery(
TargetName: target.Name,
TargetType: target.Type,
TargetConfig: target.Config,
MaxRetries: target.MaxRetries,
MaxAttempts: target.MaxAttempts,
Method: event.Method,
RawQuery: event.RawQuery,
Headers: event.Headers,
internal/handlers/delivery_replay_test.go
+5 -11
View File
@@ -314,21 +314,15 @@ func assertReplayTask(
)
}
// assertNoLeakedTarget proves the per-webhook database holds no target
// rows. AutoMigrate creates the table there because Delivery declares
// the relation, so it is a ROW that signals a leak: an association
// write would have upserted the whole target, plaintext config and
// all, into the event database. See
// assertNoLeakedTarget proves the per-webhook database holds no
// target: an association write would have upserted the whole target,
// plaintext config and all, into the event database. See
// https://git.eeqj.de/sneak/webhooker/issues/206.
func assertNoLeakedTarget(t *testing.T, webhookDB *gorm.DB) {
t.Helper()
var leaked int64
require.NoError(t, webhookDB.Unscoped().
Model(&database.Target{}).Count(&leaked).Error)
assert.Zero(
t, leaked,
assert.False(
t, webhookDB.Migrator().HasTable(&database.Target{}),
"replay must not write the target into the event database",
)
}
internal/handlers/delivery_result_view.go
+6 -8
View File
@@ -12,13 +12,12 @@ import (
//
// The bound is enforced here and in SQL, because this page's
// memory profile must not depend on a constant in another
// package staying where it is, and because rows predating the
// delivery engine's own cap or restored from an archive are
// not covered by it at all.
// package staying where it is, or on every stored row having
// been written by the delivery engine under its own cap.
//
// It happens to equal that engine cap, so a row written by the
// current engine reaches this one exactly and is never cut
// twice. Nothing here may assume the two differ: see view.
// engine reaches this one exactly and is never cut twice.
// Nothing here may assume the two differ: see view.
const maxRenderedResponseBytes = 4096
// deliveryResultColumns is the delivery attempt projection.
@@ -40,9 +39,8 @@ const deliveryResultColumns = "delivery_id, attempt_num, created_at, " +
//
// Both Error and ResponseBody have been through the target's
// Redactor. The engine already masks the URL out of the
// errors it stores, so for errors this is a second line
// covering rows written before it did; for response bodies it
// is the only line, and its reach is what
// errors it stores, so for errors this is a second line; for
// response bodies it is the only line, and its reach is what
// delivery.Redactor documents.
type DeliveryResultView struct {
AttemptNum int
internal/handlers/event_log.go
+1 -1
View File
@@ -496,7 +496,7 @@ const deliveryIDChunkSize = 500
//
// Each response body is cut by SQLite rather than in Go, for
// the reason deliveryResultColumns gives. How many attempts a
// delivery has is the target's MaxRetries, which the
// delivery has is bounded by the target's MaxAttempts, which the
// authenticated operator sets; how many of them reach the page
// is bounded again by maxRenderedAttempts.
func (h *Handlers) loadDeliveryResults(
internal/handlers/export_test.go
+2 -2
View File
@@ -37,10 +37,10 @@ const MaxRenderedResponseBytesForTest = maxRenderedResponseBytes
// per-delivery attempt ceiling to the handlers_test package.
const MaxRenderedAttemptsForTest = maxRenderedAttempts
// MaxTargetRetriesForTest exposes the target max_retries ceiling to
// MaxTargetAttemptsForTest exposes the target max_attempts ceiling to
// the handlers_test package, so the tests assert against the constant
// the handlers enforce rather than a number copied beside it.
const MaxTargetRetriesForTest = maxTargetRetries
const MaxTargetAttemptsForTest = maxTargetAttempts
// EventDBLeftMsgForTest and SidecarLeftMsgForTest expose the two
// messages the webhook delete handler logs when a file of the event
internal/handlers/target_attempts.go
+81
View File
@@ -0,0 +1,81 @@
package handlers
import (
"errors"
"strconv"
"strings"
)
// maxTargetAttempts bounds a target's max_attempts.
//
// Both target forms already declare max="20" on the input, so this
// enforces server-side what the UI has always advertised rather than
// introducing a new limit.
//
// The number is not cosmetic. Every attempt writes a delivery_results
// row that the event log then loads and renders, and the engine backs
// off by 2^(n-1) seconds, so attempt 20 is already about six days
// after the first. A value beyond this buys no additional durability
// and only costs rows.
const maxTargetAttempts = 20
// Errors returned when a max_attempts form value cannot be turned into
// a number of attempts.
var (
// errAttemptsInvalid signals a max_attempts form value that is not
// a whole number of at least 1.
errAttemptsInvalid = errors.New(
"must be a whole number, at least 1",
)
// errAttemptsTooLarge signals a max_attempts form value that is a
// whole number but above maxTargetAttempts. It is distinguished
// from errAttemptsInvalid so the message can name the ceiling
// instead of implying the input was not a number.
errAttemptsTooLarge = errors.New("out of range")
)
// parseMaxAttempts interprets a max_attempts form value.
//
// An ABSENT value — the field empty or not submitted — yields
// fallback, which lets the create path apply its default and the edit
// path leave the stored value alone. A value that is SET BUT INVALID
// is an error: unparseable, below 1, or above maxTargetAttempts.
//
// The distinction is the whole point of this function. Returning a
// default for input the operator typed but that did not parse would
// silently turn retries off on a store-and-forward proxy — and on the
// edit path destroy a working configuration over a typo. A default
// answers a question that was not asked; it never answers one that
// was asked badly.
func parseMaxAttempts(raw string, fallback int) (int, error) {
raw = strings.TrimSpace(raw)
if raw == "" {
return fallback, nil
}
v, err := strconv.Atoi(raw)
if err != nil || v < 1 {
return 0, errAttemptsInvalid
}
if v > maxTargetAttempts {
return 0, errAttemptsTooLarge
}
return v, nil
}
// attemptsErrorMessage returns the message the create and edit forms
// show for a rejected max_attempts value. Any error other than
// errAttemptsTooLarge falls back to the generic wording, so an
// unrecognised parse failure still produces a sensible 400.
func attemptsErrorMessage(err error) string {
if errors.Is(err, errAttemptsTooLarge) {
return errAttemptsTooLarge.Error() +
": at most " + strconv.Itoa(maxTargetAttempts) +
" attempts"
}
return errAttemptsInvalid.Error()
}
internal/handlers/target_attempts_test.go
+429
View File
@@ -0,0 +1,429 @@
package handlers_test
import (
"net/http"
"net/url"
"strconv"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/webhooker/internal/database"
"sneak.berlin/go/webhooker/internal/handlers"
)
// attemptsTargetURL is the destination the attempts-validation targets
// point at. It is a literal public address rather than a hostname so
// the SSRF check resolves nothing and a sandbox without DNS cannot
// make these cases pass or fail for the wrong reason.
const attemptsTargetURL = "https://93.184.216.34/hooks/attempts"
const (
// wayAboveCeiling is the typo'd-extra-zero case from the report.
wayAboveCeiling = "999999999"
// notANumber is the plainest garbage an operator can type, and
// the value the report submitted on the edit form.
notANumber = "abc"
// workingAttempts is the number of attempts a seeded target is
// already delivering with, which a rejected submission must not
// disturb.
workingAttempts = 2
)
// aboveCeiling is the smallest rejected whole number.
func aboveCeiling() string {
return strconv.Itoa(handlers.MaxTargetAttemptsForTest + 1)
}
// overCeilingAttempts is whole-number input past the limit, which is
// rejected with the limit named.
func overCeilingAttempts() []string {
return []string{aboveCeiling(), wayAboveCeiling}
}
// belowOneAttempts is whole-number input under the floor of one
// attempt, which is rejected with the floor named.
func belowOneAttempts() []string {
return []string{"0", "-5"}
}
// unparseableAttempts is input an operator can type into the field
// that is not a number of attempts. Each must be REJECTED: silently
// reading any of them as a default turns retries off on a
// store-and-forward proxy without saying so.
//
// The twenty-digit case is here because it parses as digits but
// overflows int, which is the one failure the field's own min/max
// attributes cannot describe.
func unparseableAttempts() []string {
return []string{
notANumber,
"2.7",
"12345678901234567890",
"1e3",
}
}
// createAttemptsForm is a complete, otherwise-valid HTTP target
// creation, so the only thing any case below varies is max_attempts.
func createAttemptsForm(attempts string) url.Values {
form := url.Values{}
form.Set("name", "attempts-target")
form.Set("type", string(database.TargetTypeHTTP))
form.Set("url", attemptsTargetURL)
if attempts != absentField {
form.Set("max_attempts", attempts)
}
return form
}
// absentField marks a field the form does not submit at all, which is
// the case that legitimately takes a default and must stay distinct
// from a field submitted with garbage in it.
const absentField = "\x00absent"
// absentAttempts is every way of saying "the operator did not set
// this", each of which takes the default rather than a 400. Blank and
// whitespace-only count as absent here because they do in the timeout
// and retention controls on the same forms; a rule the fields do not
// share would be its own surprise.
func absentAttempts() []string {
return []string{absentField, "", " "}
}
// createWithAttempts posts the target create form for a fresh webhook
// and returns the webhook and the response.
func createWithAttempts(
t *testing.T,
env *sourceTestEnv,
attempts string,
) (database.Webhook, int, string) {
t.Helper()
webhook := seedWebhookWithRetention(t, env.db, 30)
w := serveTarget(
env, http.MethodPost,
"/hook/"+webhook.ID+"/targets",
createAttemptsForm(attempts),
)
return webhook, w.Code, w.Body.String()
}
// TestTargetCreate_AttemptsAboveCeilingRejected proves the create form
// enforces a ceiling at all, and that the 400 names it — a rejection
// that does not say what the limit is leaves the operator guessing.
func TestTargetCreate_AttemptsAboveCeilingRejected(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
ceiling := strconv.Itoa(handlers.MaxTargetAttemptsForTest)
for _, attempts := range overCeilingAttempts() {
webhook, code, body := createWithAttempts(t, env, attempts)
assert.Equal(t, http.StatusBadRequest, code,
"max_attempts=%s should be rejected", attempts)
assert.Contains(t, body, ceiling,
"the rejection for %s should name the ceiling",
attempts)
assert.Empty(t,
targetsForWebhook(t, env.db, webhook.ID),
"no target should be created for %s", attempts)
}
}
// TestTargetCreate_AttemptsBelowOneRejected proves the create form
// refuses 0 and less, naming the floor: every delivery is attempted
// at least once.
func TestTargetCreate_AttemptsBelowOneRejected(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
for _, attempts := range belowOneAttempts() {
webhook, code, body := createWithAttempts(t, env, attempts)
assert.Equal(t, http.StatusBadRequest, code,
"max_attempts=%s should be rejected", attempts)
assert.Contains(t, body, "at least 1",
"the rejection for %s should name the floor",
attempts)
assert.Empty(t,
targetsForWebhook(t, env.db, webhook.ID),
"no target should be created for %s", attempts)
}
}
// TestTargetCreate_UnparseableAttemptsRejected is the core of the
// defect: each of these was accepted with HTTP 200 and stored as a
// default.
func TestTargetCreate_UnparseableAttemptsRejected(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
for _, attempts := range unparseableAttempts() {
webhook, code, body := createWithAttempts(t, env, attempts)
assert.Equal(t, http.StatusBadRequest, code,
"max_attempts=%q should be rejected, not coerced",
attempts)
assert.Contains(t, body, "whole number",
"the rejection for %q should say why", attempts)
assert.Empty(t,
targetsForWebhook(t, env.db, webhook.ID),
"no target should be created for %q", attempts)
}
}
// TestTargetCreate_ValidAttemptsStored covers the accepting half,
// including both bounds: a bound that rejects its own limit would
// make the advertised range unreachable.
func TestTargetCreate_ValidAttemptsStored(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
for _, want := range []int{1, 3, handlers.MaxTargetAttemptsForTest} {
webhook, code, body := createWithAttempts(
t, env, strconv.Itoa(want),
)
require.Equal(t, http.StatusSeeOther, code, body)
targets := targetsForWebhook(t, env.db, webhook.ID)
require.Len(t, targets, 1)
assert.Equal(t, want, targets[0].MaxAttempts)
}
}
// TestTargetCreate_AbsentAttemptsTakesDefault keeps the two cases
// distinct. An omitted field is not an operator asking for something
// invalid, so it still gets the default of one attempt rather than a
// 400 — otherwise the fix above would make the form unusable.
func TestTargetCreate_AbsentAttemptsTakesDefault(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
for _, attempts := range absentAttempts() {
webhook, code, body := createWithAttempts(t, env, attempts)
require.Equal(t, http.StatusSeeOther, code, body)
targets := targetsForWebhook(t, env.db, webhook.ID)
require.Len(t, targets, 1)
assert.Equal(t, 1, targets[0].MaxAttempts,
"an absent max_attempts should take the default")
}
}
// seedAttemptsTarget creates an HTTP target already delivering with
// workingAttempts attempts, through the real create handler.
func seedAttemptsTarget(
t *testing.T,
env *sourceTestEnv,
) (database.Webhook, database.Target) {
t.Helper()
webhook, code, body := createWithAttempts(
t, env, strconv.Itoa(workingAttempts),
)
require.Equal(t, http.StatusSeeOther, code, body)
targets := targetsForWebhook(t, env.db, webhook.ID)
require.Len(t, targets, 1)
require.Equal(t, workingAttempts, targets[0].MaxAttempts)
return webhook, targets[0]
}
// editAttemptsForm is a complete edit submission that changes the
// target's name as well, so a rejected submission can be shown to
// have written nothing at all rather than merely to have left
// max_attempts alone.
func editAttemptsForm(attempts string) url.Values {
form := url.Values{}
form.Set("name", "renamed-by-edit")
form.Set("url", attemptsTargetURL)
if attempts != absentField {
form.Set("max_attempts", attempts)
}
return form
}
// assertEditRejectedAndUnchanged submits an edit expected to fail and
// checks both halves of the requirement: the 400 explains itself, and
// the target it was submitted against is untouched.
func assertEditRejectedAndUnchanged(
t *testing.T,
env *sourceTestEnv,
attempts, wantReason string,
) {
t.Helper()
webhook, target := seedAttemptsTarget(t, env)
w := submitTargetEdit(
env, webhook.ID, target.ID, editAttemptsForm(attempts),
)
assert.Equal(t, http.StatusBadRequest, w.Code,
"max_attempts=%q should be rejected on edit", attempts)
assert.Contains(t, w.Body.String(), wantReason,
"the rejection for %q should say why", attempts)
stored := storedTarget(t, env, target.ID)
assert.Equal(t, workingAttempts, stored.MaxAttempts,
"a rejected edit must not destroy the working number "+
"of attempts with %q", attempts)
assert.Equal(t, "attempts-target", stored.Name,
"a rejected edit must write nothing at all")
}
// TestTargetEdit_UnparseableAttemptsRejected is the damaging half of
// the defect. A target delivering with retries, re-saved with a typo
// in the field, returned 200 and was left with retries disabled and
// nothing said.
func TestTargetEdit_UnparseableAttemptsRejected(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
for _, attempts := range unparseableAttempts() {
assertEditRejectedAndUnchanged(
t, env, attempts, "whole number",
)
}
}
// TestTargetEdit_AttemptsBelowOneRejected proves the floor applies
// to the edit path too.
func TestTargetEdit_AttemptsBelowOneRejected(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
for _, attempts := range belowOneAttempts() {
assertEditRejectedAndUnchanged(t, env, attempts, "at least 1")
}
}
// TestTargetEdit_AttemptsAboveCeilingRejected proves the ceiling
// applies to the edit path too, naming itself, so the two paths
// cannot disagree about what is storable.
func TestTargetEdit_AttemptsAboveCeilingRejected(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
ceiling := strconv.Itoa(handlers.MaxTargetAttemptsForTest)
for _, attempts := range overCeilingAttempts() {
assertEditRejectedAndUnchanged(t, env, attempts, ceiling)
}
}
// TestTargetEdit_ValidAttemptsStored covers the accepting half of the
// edit path, so the bounds cannot be enforced by simply refusing
// every submission.
func TestTargetEdit_ValidAttemptsStored(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
for _, want := range []int{1, 9, handlers.MaxTargetAttemptsForTest} {
webhook, target := seedAttemptsTarget(t, env)
w := submitTargetEdit(
env, webhook.ID, target.ID,
editAttemptsForm(strconv.Itoa(want)),
)
require.Equal(t,
http.StatusSeeOther, w.Code, w.Body.String(),
)
assert.Equal(t, want,
storedTarget(t, env, target.ID).MaxAttempts)
}
}
// TestTargetEdit_AbsentAttemptsLeavesStoredValue is the edit path's
// absent-versus-invalid case. The field is only offered by the forms
// for types that retry, so a submission without it must leave the
// stored count alone rather than be rejected or reset.
func TestTargetEdit_AbsentAttemptsLeavesStoredValue(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
for _, attempts := range absentAttempts() {
webhook, target := seedAttemptsTarget(t, env)
w := submitTargetEdit(
env, webhook.ID, target.ID,
editAttemptsForm(attempts),
)
require.Equal(t,
http.StatusSeeOther, w.Code, w.Body.String(),
)
assert.Equal(t, workingAttempts,
storedTarget(t, env, target.ID).MaxAttempts,
"an absent max_attempts must leave the stored "+
"count alone (%q)", attempts)
}
}
// TestTargetAttempts_CreateAndEditAgreeOnEveryCase proves the two
// paths cannot disagree, which is what let the create form and the
// edit form drift apart in the first place. Every input is submitted
// to both and the accept/reject verdicts are compared.
func TestTargetAttempts_CreateAndEditAgreeOnEveryCase(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
accepted := []string{
"1", "2",
strconv.Itoa(handlers.MaxTargetAttemptsForTest),
}
overCeiling := overCeilingAttempts()
belowOne := belowOneAttempts()
unparseable := unparseableAttempts()
cases := make(
[]string, 0,
len(accepted)+len(overCeiling)+len(belowOne)+
len(unparseable),
)
cases = append(cases, accepted...)
cases = append(cases, overCeiling...)
cases = append(cases, belowOne...)
cases = append(cases, unparseable...)
for _, attempts := range cases {
_, createCode, _ := createWithAttempts(t, env, attempts)
webhook, target := seedAttemptsTarget(t, env)
editCode := submitTargetEdit(
env, webhook.ID, target.ID,
editAttemptsForm(attempts),
).Code
assert.Equal(t,
createCode == http.StatusBadRequest,
editCode == http.StatusBadRequest,
"create and edit must agree on max_attempts=%q "+
"(create %d, edit %d)",
attempts, createCode, editCode,
)
}
}
internal/handlers/target_create.go
+20 -18
View File
@@ -102,9 +102,10 @@ func (h *Handlers) newTarget(
in targetFormInput,
) (*database.Target, string, error) {
target := &database.Target{
WebhookID: webhookID,
Type: in.Type,
Active: true,
WebhookID: webhookID,
Type: in.Type,
Active: true,
MaxAttempts: 1,
}
errMsg, err := h.setTargetFromForm(ctx, target, in)
@@ -117,9 +118,10 @@ func (h *Handlers) newTarget(
// setTargetFromForm validates a target form against the target's type
// and, when it accepts it, sets the target's name, configuration and
// retry count from it. It returns the message the form shows for
// anything it refuses, an unknown type among them, and then leaves the
// target unchanged; an error is the server's fault, as for newTarget.
// number of delivery attempts from it. It returns the message the form
// shows for anything it refuses, an unknown type among them, and then
// leaves the target unchanged; an error is the server's fault, as for
// newTarget.
// The add target form and the target edit form both go through here,
// so the two cannot come to disagree about what a target may be.
func (h *Handlers) setTargetFromForm(
@@ -136,20 +138,20 @@ func (h *Handlers) setTargetFromForm(
return errMsg, err
}
// An empty max_retries keeps the target's count: the
// fire-and-forget default of 0 for a new target, and the stored
// count for an edited one, since the forms for target types that
// do not retry have no such field. A value that is filled in but
// invalid is refused rather than becoming that count, so a typo
// cannot destroy the count a target is delivering with.
maxRetries, err := parseMaxRetries(in.MaxRetries, target.MaxRetries)
// An empty max_attempts keeps the target's count: the default of
// 1 for a new target, and the stored count for an edited one,
// since the forms for target types that do not retry have no such
// field. A value that is filled in but invalid is refused rather
// than becoming that count, so a typo cannot destroy the count a
// target is delivering with.
maxAttempts, err := parseMaxAttempts(in.MaxAttempts, target.MaxAttempts)
if err != nil {
return "Invalid delivery attempts: " + retriesErrorMessage(err), nil
return "Invalid delivery attempts: " + attemptsErrorMessage(err), nil
}
target.Name = in.Name
target.Config = configJSON
target.MaxRetries = maxRetries
target.MaxAttempts = maxAttempts
return "", nil
}
@@ -176,8 +178,8 @@ type targetFormInput struct {
// ForwardQuery is an HTTP target's checkbox that passes each
// event's query string on to it.
ForwardQuery bool
// MaxRetries is an HTTP or Slack target's max_retries.
MaxRetries string
// MaxAttempts is an HTTP or Slack target's max_attempts.
MaxAttempts string
// Expiry is a database (archive) target's row expiry.
Expiry string
// Rotation is a database (archive) target's rotation.
@@ -204,7 +206,7 @@ func targetFormInputFrom(r *http.Request) targetFormInput {
Headers: r.PostFormValue("headers"),
Timeout: r.PostFormValue("timeout"),
ForwardQuery: r.PostFormValue("forward_query") != "",
MaxRetries: r.PostFormValue("max_retries"),
MaxAttempts: r.PostFormValue("max_attempts"),
Expiry: r.PostFormValue("expiry"),
Rotation: r.PostFormValue("rotation"),
}
internal/handlers/target_create_query_test.go
+1 -1
View File
@@ -196,7 +196,7 @@ func TestHandleTargetCreate_QueryStringCannotSupplyNameOrType(
w, _ := postTargetCreate(
t, env, webhook.ID,
"name=leaky&type=slack&max_retries=9&expiry=30d&url="+
"name=leaky&type=slack&max_attempts=9&expiry=30d&url="+
url.QueryEscape(targetSecretURL),
url.Values{},
)
internal/handlers/target_create_test.go
+13 -13
View File
@@ -21,24 +21,24 @@ func TestHandleTargetCreate_EveryType(t *testing.T) {
// fields is the rest of each submission, as a query string.
cases := []struct {
targetType database.TargetType
fields string
wantConfig string
wantRetries int
targetType database.TargetType
fields string
wantConfig string
wantAttempts int
}{
{
database.TargetTypeHTTP, "timeout=12&max_retries=3",
database.TargetTypeHTTP, "timeout=12&max_attempts=3",
`{"url":"` + editOriginalURL + `","timeout":12}`, 3,
},
{
database.TargetTypeSlack, "max_retries=4",
database.TargetTypeSlack, "max_attempts=4",
`{"webhookUrl":"` + editOriginalURL + `"}`, 4,
},
{
database.TargetTypeDatabase, "expiry=720h",
`{"expiry":"720h"}`, 0,
`{"expiry":"720h"}`, 1,
},
{database.TargetTypeLog, "", "", 0},
{database.TargetTypeLog, "", "", 1},
}
for _, tc := range cases {
@@ -62,7 +62,7 @@ func TestHandleTargetCreate_EveryType(t *testing.T) {
targets := targetsForWebhook(t, env.db, webhook.ID)
require.Len(t, targets, 1)
assert.Equal(t, tc.targetType, targets[0].Type)
assert.Equal(t, tc.wantRetries, targets[0].MaxRetries)
assert.Equal(t, tc.wantAttempts, targets[0].MaxAttempts)
if tc.wantConfig == "" {
assert.Empty(t, targets[0].Config)
@@ -90,11 +90,11 @@ func TestHandleTargetCreate_RefusedFormComesBack(t *testing.T) {
{
database.TargetTypeHTTP,
"name=private&url=" + editBlockedURL +
"&timeout=12&max_retries=3",
"&timeout=12&max_attempts=3",
"Invalid target URL",
},
{
database.TargetTypeSlack, "name=no-url&max_retries=4",
database.TargetTypeSlack, "name=no-url&max_attempts=4",
"Webhook URL is required for Slack targets",
},
{
@@ -133,8 +133,8 @@ func TestHandleTargetCreate_RefusedFormComesBack(t *testing.T) {
assert.Contains(t, page, html.EscapeString(tc.reason))
// Each value comes back in a data attribute of the targets
// section named after its field (max_retries as
// data-max-retries), except url, which comes back in
// section named after its field (max_attempts as
// data-max-attempts), except url, which comes back in
// data-destination; templates/source_detail.html says why.
for field := range typed {
attr := "data-" + strings.ReplaceAll(field, "_", "-")
internal/handlers/target_edit.go
+1 -1
View File
@@ -82,7 +82,7 @@ func (h *Handlers) HandleTargetEdit() http.HandlerFunc {
Headers: cfg.Headers,
Timeout: cfg.Timeout,
ForwardQuery: cfg.ForwardQuery,
MaxRetries: strconv.Itoa(target.MaxRetries),
MaxAttempts: strconv.Itoa(target.MaxAttempts),
Expiry: cfg.Expiry,
Rotation: cfg.Rotation,
}
internal/handlers/target_edit_test.go
+14 -14
View File
@@ -117,7 +117,7 @@ func seedHTTPTarget(
form.Set("url", editOriginalURL)
form.Set("headers", headers)
form.Set("timeout", timeout)
form.Set("max_retries", "3")
form.Set("max_attempts", "3")
w := serveTarget(
env, http.MethodPost,
@@ -179,7 +179,7 @@ func editForm(targetURL, headers, timeout string) url.Values {
form.Set("url", targetURL)
form.Set("headers", headers)
form.Set("timeout", timeout)
form.Set("max_retries", "5")
form.Set("max_attempts", "5")
return form
}
@@ -280,9 +280,9 @@ func TestHandleTargetEditSubmit_Saves(t *testing.T) {
assertEditClearingRemovesThem(t, env)
})
t.Run("absent max_retries is not zeroed", func(t *testing.T) {
t.Run("absent max_attempts is kept", func(t *testing.T) {
t.Parallel()
assertEditKeepsAbsentMaxRetries(t, env)
assertEditKeepsAbsentMaxAttempts(t, env)
})
}
@@ -307,7 +307,7 @@ func assertEditChangesDestination(
reloaded := storedTarget(t, env, target.ID)
assert.Equal(t, "edited-name", reloaded.Name)
assert.Equal(t, 5, reloaded.MaxRetries)
assert.Equal(t, 5, reloaded.MaxAttempts)
assert.Equal(
t, database.TargetTypeHTTP, reloaded.Type,
"the edit form must not change a target's type",
@@ -368,25 +368,25 @@ func assertEditClearingRemovesThem(
assert.Zero(t, cfg.Timeout)
}
// Retries are offered only by the forms for target types that retry.
// An absent field means the form does not edit retries, not that
// they should be turned off.
func assertEditKeepsAbsentMaxRetries(
// Delivery attempts are offered only by the forms for target types
// that retry. An absent field means the form does not edit them, not
// that retries should be turned off.
func assertEditKeepsAbsentMaxAttempts(
t *testing.T, env *sourceTestEnv,
) {
t.Helper()
webhook, target := seedHTTPTarget(t, env, "", "")
require.Equal(t, 3, target.MaxRetries)
require.Equal(t, 3, target.MaxAttempts)
form := editForm(editOriginalURL, "", "")
form.Del("max_retries")
form.Del("max_attempts")
w := submitTargetEdit(env, webhook.ID, target.ID, form)
require.Equal(t, http.StatusSeeOther, w.Code, w.Body.String())
assert.Equal(
t, 3, storedTarget(t, env, target.ID).MaxRetries,
t, 3, storedTarget(t, env, target.ID).MaxAttempts,
)
}
@@ -659,12 +659,12 @@ func TestHandleTargetEditSubmit_RefusedFormComesBack(t *testing.T) {
{
database.TargetTypeHTTP,
"name=edited&url=" + editBlockedURL +
"&headers=X-Edited:+kept&timeout=12&max_retries=3",
"&headers=X-Edited:+kept&timeout=12&max_attempts=3",
"Invalid target URL",
},
{
database.TargetTypeSlack,
"name=edited&url=" + editOriginalURL + "&max_retries=25",
"name=edited&url=" + editOriginalURL + "&max_attempts=25",
"Invalid delivery attempts",
},
{
internal/handlers/target_retries.go
-90
View File
@@ -1,90 +0,0 @@
package handlers
import (
"errors"
"strconv"
"strings"
)
// maxTargetRetries bounds a target's max_retries.
//
// Both target forms already declare max="20" on the input, so this
// enforces server-side what the UI has always advertised rather than
// introducing a new limit.
//
// The number is not cosmetic. Every attempt writes a delivery_results
// row that the event log then loads and renders, and the engine backs
// off by 2^(n-1) seconds, so attempt 20 is already about six days
// after the first. A value beyond this buys no additional durability
// and only costs rows.
const maxTargetRetries = 20
// Errors returned when a max_retries form value cannot be turned into
// a retry count.
var (
// errRetriesInvalid signals a max_retries form value that is not
// a non-negative whole number.
errRetriesInvalid = errors.New(
"must be a whole number",
)
// errRetriesTooLarge signals a max_retries form value that is a
// whole number but above maxTargetRetries. It is distinguished
// from errRetriesInvalid so the message can name the ceiling
// instead of implying the input was not a number.
errRetriesTooLarge = errors.New("out of range")
)
// parseMaxRetries interprets a max_retries form value.
//
// An ABSENT value — the field empty or not submitted — yields
// fallback, which lets the create path apply its default and the edit
// path leave the stored value alone. A value that is SET BUT INVALID
// is an error: unparseable, negative, or above maxTargetRetries.
//
// The distinction is the whole point of this function. max_retries=0
// means fire-and-forget, so returning 0 for input the operator typed
// but that did not parse silently disables retries on a
// store-and-forward proxy — and on the edit path it destroys a
// working retry configuration over a typo. A default answers a
// question that was not asked; it never answers one that was asked
// badly.
//
// A target stored with a count above the ceiling before this
// validation existed keeps rendering and keeps delivering — nothing
// clamps the row. Re-saving it from the edit form does have to bring
// it into range, because the form submits the pre-filled value back
// and accepting it would be the ceiling not applying to the edit
// path. The 400 names the ceiling, so the fix is one field.
func parseMaxRetries(raw string, fallback int) (int, error) {
raw = strings.TrimSpace(raw)
if raw == "" {
return fallback, nil
}
v, err := strconv.Atoi(raw)
if err != nil || v < 0 {
return 0, errRetriesInvalid
}
if v > maxTargetRetries {
return 0, errRetriesTooLarge
}
return v, nil
}
// retriesErrorMessage returns the message the create and edit forms
// show for a rejected max_retries value. Any error other than
// errRetriesTooLarge falls back to the generic wording, so an
// unrecognised parse failure still produces a sensible 400.
func retriesErrorMessage(err error) string {
if errors.Is(err, errRetriesTooLarge) {
return errRetriesTooLarge.Error() +
": at most " + strconv.Itoa(maxTargetRetries) +
" attempts"
}
return errRetriesInvalid.Error() +
", or 0 for fire-and-forget"
}
internal/handlers/target_retries_test.go
-385
View File
@@ -1,385 +0,0 @@
package handlers_test
import (
"net/http"
"net/url"
"strconv"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/webhooker/internal/database"
"sneak.berlin/go/webhooker/internal/handlers"
)
// retriesTargetURL is the destination the retry-validation targets
// point at. It is a literal public address rather than a hostname so
// the SSRF check resolves nothing and a sandbox without DNS cannot
// make these cases pass or fail for the wrong reason.
const retriesTargetURL = "https://93.184.216.34/hooks/retries"
const (
// wayAboveCeiling is the typo'd-extra-zero case from the report.
wayAboveCeiling = "999999999"
// notANumber is the plainest garbage an operator can type, and
// the value the report submitted on the edit form.
notANumber = "abc"
// workingRetries is the retry count a seeded target is already
// delivering with, which a rejected submission must not disturb.
workingRetries = 2
)
// aboveCeiling is the smallest rejected whole number.
func aboveCeiling() string {
return strconv.Itoa(handlers.MaxTargetRetriesForTest + 1)
}
// overCeilingRetries is whole-number input past the limit, which is
// rejected with the limit named.
func overCeilingRetries() []string {
return []string{aboveCeiling(), wayAboveCeiling}
}
// unparseableRetries is input an operator can type into the field
// that is not a retry count. Each must be REJECTED: silently reading
// any of them as 0 turns a store-and-forward proxy into
// fire-and-forget without saying so.
//
// The twenty-digit case is here because it parses as digits but
// overflows int, which is the one failure the field's own min/max
// attributes cannot describe.
func unparseableRetries() []string {
return []string{
notANumber,
"2.7",
"-5",
"12345678901234567890",
"1e3",
}
}
// createRetriesForm is a complete, otherwise-valid HTTP target
// creation, so the only thing any case below varies is max_retries.
func createRetriesForm(retries string) url.Values {
form := url.Values{}
form.Set("name", "retries-target")
form.Set("type", string(database.TargetTypeHTTP))
form.Set("url", retriesTargetURL)
if retries != absentField {
form.Set("max_retries", retries)
}
return form
}
// absentField marks a field the form does not submit at all, which is
// the case that legitimately takes a default and must stay distinct
// from a field submitted with garbage in it.
const absentField = "\x00absent"
// absentRetries is every way of saying "the operator did not set
// this", each of which takes the default rather than a 400. Blank and
// whitespace-only count as absent here because they do in the timeout
// and retention controls on the same forms; a rule the fields do not
// share would be its own surprise.
func absentRetries() []string {
return []string{absentField, "", " "}
}
// createWithRetries posts the target create form for a fresh webhook
// and returns the webhook and the response.
func createWithRetries(
t *testing.T,
env *sourceTestEnv,
retries string,
) (database.Webhook, int, string) {
t.Helper()
webhook := seedWebhookWithRetention(t, env.db, 30)
w := serveTarget(
env, http.MethodPost,
"/hook/"+webhook.ID+"/targets",
createRetriesForm(retries),
)
return webhook, w.Code, w.Body.String()
}
// TestTargetCreate_RetriesAboveCeilingRejected proves the create form
// enforces a ceiling at all, and that the 400 names it — a rejection
// that does not say what the limit is leaves the operator guessing.
func TestTargetCreate_RetriesAboveCeilingRejected(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
ceiling := strconv.Itoa(handlers.MaxTargetRetriesForTest)
for _, retries := range overCeilingRetries() {
webhook, code, body := createWithRetries(t, env, retries)
assert.Equal(t, http.StatusBadRequest, code,
"max_retries=%s should be rejected", retries)
assert.Contains(t, body, ceiling,
"the rejection for %s should name the ceiling",
retries)
assert.Empty(t,
targetsForWebhook(t, env.db, webhook.ID),
"no target should be created for %s", retries)
}
}
// TestTargetCreate_UnparseableRetriesRejected is the core of the
// defect: each of these was accepted with HTTP 200 and stored as 0.
func TestTargetCreate_UnparseableRetriesRejected(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
for _, retries := range unparseableRetries() {
webhook, code, body := createWithRetries(t, env, retries)
assert.Equal(t, http.StatusBadRequest, code,
"max_retries=%q should be rejected, not coerced",
retries)
assert.Contains(t, body, "whole number",
"the rejection for %q should say why", retries)
assert.Empty(t,
targetsForWebhook(t, env.db, webhook.ID),
"no target should be created for %q", retries)
}
}
// TestTargetCreate_ValidRetriesStored covers the accepting half,
// including the ceiling itself: a bound that rejects its own limit
// would make the advertised maximum unreachable.
func TestTargetCreate_ValidRetriesStored(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
for _, want := range []int{0, 3, handlers.MaxTargetRetriesForTest} {
webhook, code, body := createWithRetries(
t, env, strconv.Itoa(want),
)
require.Equal(t, http.StatusSeeOther, code, body)
targets := targetsForWebhook(t, env.db, webhook.ID)
require.Len(t, targets, 1)
assert.Equal(t, want, targets[0].MaxRetries)
}
}
// TestTargetCreate_AbsentRetriesTakesDefault keeps the two cases
// distinct. An omitted field is not an operator asking for something
// invalid, so it still gets the fire-and-forget default rather than a
// 400 — otherwise the fix above would make the form unusable.
func TestTargetCreate_AbsentRetriesTakesDefault(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
for _, retries := range absentRetries() {
webhook, code, body := createWithRetries(t, env, retries)
require.Equal(t, http.StatusSeeOther, code, body)
targets := targetsForWebhook(t, env.db, webhook.ID)
require.Len(t, targets, 1)
assert.Equal(t, 0, targets[0].MaxRetries,
"an absent max_retries should take the default")
}
}
// seedRetriesTarget creates an HTTP target already delivering with
// workingRetries retries, through the real create handler.
func seedRetriesTarget(
t *testing.T,
env *sourceTestEnv,
) (database.Webhook, database.Target) {
t.Helper()
webhook, code, body := createWithRetries(
t, env, strconv.Itoa(workingRetries),
)
require.Equal(t, http.StatusSeeOther, code, body)
targets := targetsForWebhook(t, env.db, webhook.ID)
require.Len(t, targets, 1)
require.Equal(t, workingRetries, targets[0].MaxRetries)
return webhook, targets[0]
}
// editRetriesForm is a complete edit submission that changes the
// target's name as well, so a rejected submission can be shown to
// have written nothing at all rather than merely to have left
// max_retries alone.
func editRetriesForm(retries string) url.Values {
form := url.Values{}
form.Set("name", "renamed-by-edit")
form.Set("url", retriesTargetURL)
if retries != absentField {
form.Set("max_retries", retries)
}
return form
}
// assertEditRejectedAndUnchanged submits an edit expected to fail and
// checks both halves of the requirement: the 400 explains itself, and
// the target it was submitted against is untouched.
func assertEditRejectedAndUnchanged(
t *testing.T,
env *sourceTestEnv,
retries, wantReason string,
) {
t.Helper()
webhook, target := seedRetriesTarget(t, env)
w := submitTargetEdit(
env, webhook.ID, target.ID, editRetriesForm(retries),
)
assert.Equal(t, http.StatusBadRequest, w.Code,
"max_retries=%q should be rejected on edit", retries)
assert.Contains(t, w.Body.String(), wantReason,
"the rejection for %q should say why", retries)
stored := storedTarget(t, env, target.ID)
assert.Equal(t, workingRetries, stored.MaxRetries,
"a rejected edit must not destroy the working retry "+
"count with %q", retries)
assert.Equal(t, "retries-target", stored.Name,
"a rejected edit must write nothing at all")
}
// TestTargetEdit_UnparseableRetriesRejected is the damaging half of
// the defect. A target delivering with two retries, re-saved with a
// typo in the field, returned 200 and was left with retries disabled
// and nothing said.
func TestTargetEdit_UnparseableRetriesRejected(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
for _, retries := range unparseableRetries() {
assertEditRejectedAndUnchanged(
t, env, retries, "whole number",
)
}
}
// TestTargetEdit_RetriesAboveCeilingRejected proves the ceiling
// applies to the edit path too, naming itself, so the two paths
// cannot disagree about what is storable.
func TestTargetEdit_RetriesAboveCeilingRejected(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
ceiling := strconv.Itoa(handlers.MaxTargetRetriesForTest)
for _, retries := range overCeilingRetries() {
assertEditRejectedAndUnchanged(t, env, retries, ceiling)
}
}
// TestTargetEdit_ValidRetriesStored covers the accepting half of the
// edit path, so the ceiling cannot be enforced by simply refusing
// every submission.
func TestTargetEdit_ValidRetriesStored(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
for _, want := range []int{0, 9, handlers.MaxTargetRetriesForTest} {
webhook, target := seedRetriesTarget(t, env)
w := submitTargetEdit(
env, webhook.ID, target.ID,
editRetriesForm(strconv.Itoa(want)),
)
require.Equal(t,
http.StatusSeeOther, w.Code, w.Body.String(),
)
assert.Equal(t, want,
storedTarget(t, env, target.ID).MaxRetries)
}
}
// TestTargetEdit_AbsentRetriesLeavesStoredValue is the edit path's
// absent-versus-invalid case. Retries are only offered by the forms
// for types that retry, so a submission without the field must leave
// the stored count alone rather than be rejected or zeroed.
func TestTargetEdit_AbsentRetriesLeavesStoredValue(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
for _, retries := range absentRetries() {
webhook, target := seedRetriesTarget(t, env)
w := submitTargetEdit(
env, webhook.ID, target.ID,
editRetriesForm(retries),
)
require.Equal(t,
http.StatusSeeOther, w.Code, w.Body.String(),
)
assert.Equal(t, workingRetries,
storedTarget(t, env, target.ID).MaxRetries,
"an absent max_retries must leave the stored "+
"count alone (%q)", retries)
}
}
// TestTargetRetries_CreateAndEditAgreeOnEveryCase proves the two
// paths cannot disagree, which is what let the create form and the
// edit form drift apart in the first place. Every input is submitted
// to both and the accept/reject verdicts are compared.
func TestTargetRetries_CreateAndEditAgreeOnEveryCase(t *testing.T) {
t.Parallel()
env := setupSourceTest(t)
accepted := []string{
"0", "1",
strconv.Itoa(handlers.MaxTargetRetriesForTest),
}
overCeiling := overCeilingRetries()
unparseable := unparseableRetries()
cases := make(
[]string, 0,
len(accepted)+len(overCeiling)+len(unparseable),
)
cases = append(cases, accepted...)
cases = append(cases, overCeiling...)
cases = append(cases, unparseable...)
for _, retries := range cases {
_, createCode, _ := createWithRetries(t, env, retries)
webhook, target := seedRetriesTarget(t, env)
editCode := submitTargetEdit(
env, webhook.ID, target.ID,
editRetriesForm(retries),
).Code
assert.Equal(t,
createCode == http.StatusBadRequest,
editCode == http.StatusBadRequest,
"create and edit must agree on max_retries=%q "+
"(create %d, edit %d)",
retries, createCode, editCode,
)
}
}
internal/handlers/target_toggle_test.go
+1 -1
View File
@@ -59,7 +59,7 @@ func TestHandleTargetToggle_DoesNotUndoAnEdit(t *testing.T) {
stored := storedTarget(t, env, tgt.ID)
assert.False(t, stored.Active)
assert.Equal(t, "edited-name", stored.Name)
assert.Equal(t, 5, stored.MaxRetries)
assert.Equal(t, 5, stored.MaxAttempts)
assert.Equal(
t, editReplacedURL, storedHTTPConfig(t, env, tgt.ID).URL,
)
internal/handlers/ui_copy_test.go
+14 -16
View File
@@ -348,21 +348,19 @@ func TestEntrypointCopyButtonIsProgressiveEnhancement(t *testing.T) {
)
}
// maxRetriesHelp is the wording both target forms must carry. The
// delivery core makes max_retries attempts in total, not that many
// maxAttemptsHelp is the wording both target forms must carry. The
// delivery core makes max_attempts attempts in total, not that many
// retries on top of a first try (a fresh delivery starts at attempt 1
// and target_http gives up once the attempt number reaches
// max_retries), and 0 is special-cased to a single fire-and-forget
// attempt with no circuit breaker.
const maxRetriesHelp = "How many times each delivery is attempted in " +
"all, the first attempt included. 0 means a single attempt with no " +
"retries and no circuit breaker."
// max_attempts).
const maxAttemptsHelp = "How many times each delivery is attempted in " +
"all, the first attempt included."
// TestTargetFormMaxRetriesCopyMatchesBehaviour pins the max_retries
// TestTargetFormMaxAttemptsCopyMatchesBehaviour pins the max_attempts
// label, "Delivery attempts", and help text on both the create form
// (the add-target form on the webhook detail page) and the edit form,
// so the copy cannot drift back to calling the number a retry count.
func TestTargetFormMaxRetriesCopyMatchesBehaviour(t *testing.T) {
func TestTargetFormMaxAttemptsCopyMatchesBehaviour(t *testing.T) {
t.Parallel()
var h *handlers.Handlers
@@ -394,11 +392,11 @@ func TestTargetFormMaxRetriesCopyMatchesBehaviour(t *testing.T) {
assert.Contains(t, createBody, "Delivery attempts:</label>")
assert.Contains(
t, createBody, maxRetriesHelp,
"the add-target form must explain max_retries as total attempts",
t, createBody, maxAttemptsHelp,
"the add-target form must explain max_attempts as total attempts",
)
// A slack target exercises the same max_retries field while needing
// A slack target exercises the same max_attempts field while needing
// only a URL from the edit template, so the test data stays
// minimal. The Target and TargetForm keys mirror the field names
// the template reads off the handler's values.
@@ -412,8 +410,8 @@ func TestTargetFormMaxRetriesCopyMatchesBehaviour(t *testing.T) {
"Active": true,
},
"TargetForm": map[string]any{
"URL": "https://hooks.slack.com/services/x",
"MaxRetries": "3",
"URL": "https://hooks.slack.com/services/x",
"MaxAttempts": "3",
},
dataKeyError: "",
},
@@ -421,8 +419,8 @@ func TestTargetFormMaxRetriesCopyMatchesBehaviour(t *testing.T) {
assert.Contains(t, editBody, `class="label">Delivery attempts</label>`)
assert.Contains(
t, editBody, maxRetriesHelp,
"the target edit form must explain max_retries as total attempts",
t, editBody, maxAttemptsHelp,
"the target edit form must explain max_attempts as total attempts",
)
}
internal/handlers/webhook.go
+1 -1
View File
@@ -442,7 +442,7 @@ func buildDeliveryTasks(
TargetName: targets[i].Name,
TargetType: targets[i].Type,
TargetConfig: targets[i].Config,
MaxRetries: targets[i].MaxRetries,
MaxAttempts: targets[i].MaxAttempts,
Method: event.Method,
RawQuery: event.RawQuery,
Headers: event.Headers,
internal/server/alpine_browser_test.go
+7 -7
View File
@@ -354,11 +354,11 @@ func checkAddEachTargetType(ctx context.Context, t *testing.T, url string) {
}{
{
"http", "http",
"csrf_token name type url headers timeout max_retries",
"csrf_token name type url headers timeout max_attempts",
map[string]string{"url": publicTargetURL},
},
{
"slack", "slack", "csrf_token name type url max_retries",
"slack", "slack", "csrf_token name type url max_attempts",
map[string]string{"url": publicTargetURL},
},
{
@@ -630,11 +630,11 @@ func checkRefusedEdits(
values map[string]string
}{
{page + "/targets/" + targetID + "/edit", map[string]string{
"#name": "edited-target",
"#url": "http://127.0.0.1/hook",
"#headers": "X-Edited: kept",
"#timeout": "12",
"#max_retries": "3",
"#name": "edited-target",
"#url": "http://127.0.0.1/hook",
"#headers": "X-Edited: kept",
"#timeout": "12",
"#max_attempts": "3",
}},
{page + "/edit", map[string]string{
"#name": "edited-webhook",
internal/server/export_test.go
+18
View File
@@ -91,6 +91,24 @@ func NewRouterForTest(
return s.router
}
// NewRouterWithSentryForTest is NewRouterForTest with the sentryhttp
// handler registered, as a set SENTRY_DSN does in production.
func NewRouterWithSentryForTest(
t *testing.T,
log *logger.Logger,
cfg *config.Config,
mw *middleware.Middleware,
h *handlers.Handlers,
) http.Handler {
t.Helper()
s := newServerForTest(t, log, cfg, mw, h)
s.sentryEnabled.Store(true)
s.SetupRoutes()
return s.router
}
// ListenAddrForTest exposes the address the HTTP listener binds for
// a given Config, so the rendering of host and port — IPv6
// bracketing above all — can be pinned without standing up a
internal/server/routes.go
+7 -2
View File
@@ -90,8 +90,8 @@ func (s *Server) setupGlobalMiddleware() {
// recoverPanics installs on r the recoverer, answering a panic with
// page (a plain 500 when page is nil), and inside it the Sentry error
// reporting (if SENTRY_DSN is set). Repanic is true so panics still
// bubble up to the recoverer.
// reporting and transaction naming (if SENTRY_DSN is set). Repanic is
// true so panics still bubble up to the recoverer.
//
// Each admin page route group installs its own, with the error page,
// as its first middleware. A panic there is logged, reported and
@@ -105,6 +105,11 @@ func (s *Server) recoverPanics(r chi.Router, page http.Handler) {
Repanic: true,
})
r.Use(sentryHandler.Handle)
// Installed with every sentryhttp handler rather than once
// globally: in an admin page route group, the group's own
// handler finishes the transaction as the group returns, so
// a rename further out would come too late.
r.Use(nameSentryTransaction)
}
}
internal/server/sentry.go
+57 -4
View File
@@ -1,6 +1,7 @@
package server
import (
"context"
"net/http"
"net/url"
"strings"
@@ -71,10 +72,15 @@ func scrubSentryRequest(
pattern := sentryRoutePattern(hint)
// Only transaction events carry a Transaction name, and the SDK
// Only transaction events carry a Transaction name. sentryhttp
// builds it from the concrete path too (sentryhttp.go:105 via
// tracing.go:553). Rewritten on the same terms.
if event.Transaction != "" {
// tracing.go:553) and marks it SourceURL, so it is rewritten on
// the same terms. Only a name nameSentryTransaction set from the
// route pattern, which it marks SourceRoute, is kept.
namedByRoute := event.TransactionInfo != nil &&
event.TransactionInfo.Source == sentry.SourceRoute
if event.Transaction != "" && !namedByRoute {
event.Transaction = sentryTransactionName(
event.Transaction, pattern,
)
@@ -120,7 +126,8 @@ func scrubSentryRequest(
// The transaction dispatch has no such request: Span.doFinish calls
// hub.CaptureEvent (tracing.go:356), which passes a nil hint that the
// client replaces with an empty one (client.go:620-622). The pattern
// is therefore always "" there, and the callers fall back.
// is therefore always "" there, and the callers fall back. A routed
// transaction is named by nameSentryTransaction instead.
func sentryRoutePattern(hint *sentry.EventHint) string {
if hint == nil || hint.Context == nil {
return ""
@@ -142,6 +149,52 @@ func sentryRoutePattern(hint *sentry.EventHint) string {
return rctx.RoutePattern()
}
// nameSentryTransaction renames the request's Sentry transaction to
// "METHOD <route pattern>", such as "POST /h/{uuid}". sentryhttp names
// it after the concrete path, which scrubSentryRequest withholds;
// since Sentry groups transactions by name, every transaction in the
// service would otherwise land in one group per method, such as
// "POST /(redacted)".
//
// It has to run inside the sentryhttp handler, where the transaction
// is on the request context. It renames on the way out, once chi has
// routed the request, and does so in a defer so that a request whose
// handler panics is named too. The context is taken when the defer is
// set up, before routing, but the chi routing context on it is a
// pointer that chi fills in as it routes.
func nameSentryTransaction(next http.Handler) http.Handler {
return http.HandlerFunc(
func(w http.ResponseWriter, r *http.Request) {
defer setSentryTransactionName(r.Context(), r.Method)
next.ServeHTTP(w, r)
},
)
}
// setSentryTransactionName does the rename for nameSentryTransaction.
// A path that matches nothing at the top level has no pattern; its
// name is left as the SDK set it, for scrubSentryRequest to withhold.
// Inside a route group, a path that matches no route in the group, or
// a request the group's own middleware turns away before routing, has
// the group's pattern, such as "/pages/*", and is named after it.
func setSentryTransactionName(ctx context.Context, method string) {
transaction := sentry.TransactionFromContext(ctx)
rctx := chi.RouteContext(ctx)
if transaction == nil || rctx == nil {
return
}
pattern := rctx.RoutePattern()
if pattern == "" {
return
}
transaction.Name = method + " " + pattern
transaction.Source = sentry.SourceRoute
}
// sentryRouteURL rebuilds an event's request URL with the route
// pattern in place of the concrete path.
//
internal/server/sentry_test.go
+90 -7
View File
@@ -16,6 +16,7 @@ import (
"github.com/go-chi/chi"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"sneak.berlin/go/webhooker/internal/config"
"sneak.berlin/go/webhooker/internal/server"
)
@@ -130,11 +131,15 @@ func (c sentryCase) capture(t *testing.T) []*sentry.Event {
// router mirrors the one ordering these tests depend on, over the two
// route patterns they need: a recovering middleware outside, then the
// sentryhttp handler registered with Use and Repanic set, exactly as
// routes.go orders the two. The bare recover stands in for
// Middleware.Recoverer, which holds that outer slot in production; it
// is here only to keep panic stacks out of the test output. That the
// production one really does catch what sentryhttp re-raises is
// pinned separately, by TestSentryStillSeesAPanic.
// routes.go orders the two. It leaves out nameSentryTransaction,
// which routes.go installs inside the sentryhttp handler, so a
// transaction captured here keeps the SDK's name and shows what the
// hook does with a transaction that missed the rename. The bare
// recover stands in for Middleware.Recoverer, which holds that outer
// slot in production; it is here only to keep panic stacks out of the
// test output. That the production one really does catch what
// sentryhttp re-raises is pinned separately, by
// TestSentryStillSeesAPanic.
func (c sentryCase) router() http.Handler {
handler := func(_ http.ResponseWriter, r *http.Request) {
// This call is what drains the body tee and fills the
@@ -353,8 +358,9 @@ func TestSentryScrub_KeepsTheRoutingContext(t *testing.T) {
// Span.doFinish captures with a nil hint, so BeforeSendTransaction
// gets one with no context and no request: the route pattern is out of
// reach and both the URL and the SDK-built transaction name have to
// fall back. Tracing is off in this service, so no transaction event
// is produced today; the hook is a floor against that changing.
// fall back. This router has no nameSentryTransaction, so this is the
// floor under a transaction that missed the rename;
// TestSentryTransaction_NamedByRoute covers the routes as they ship.
func TestSentryScrub_RedactsTheTransactionDispatch(t *testing.T) {
t.Parallel()
@@ -376,6 +382,83 @@ func TestSentryScrub_RedactsTheTransactionDispatch(t *testing.T) {
assert.Equal(t, "POST /(redacted)", event.Transaction)
}
// TestSentryTransaction_NamedByRoute serves requests through the real
// route tree with tracing on, which the service leaves off. A routed
// request's transaction is named after its route pattern, so Sentry
// can group transactions by route, and the entrypoint UUID in the
// receiver path appears nowhere in the event. A path that matches
// nothing at the top level has no pattern, and its name is still
// withheld; one that matches no route inside a route group is named
// after the group's pattern.
func TestSentryTransaction_NamedByRoute(t *testing.T) {
t.Parallel()
// newTestEnv leaves the receiver rate limit at zero, which
// refuses every request before it reaches the receiver.
env := newTestEnvWithConfig(t, &config.Config{
DataDir: t.TempDir(),
Environment: config.EnvironmentDev,
ReceiverRateLimit: 10,
})
router := server.NewRouterWithSentryForTest(
t, env.log, env.cfg, env.mw, env.hnd,
)
for _, tc := range []struct {
method, path, want string
}{
{
http.MethodPost,
"/h/" + sentryReceiverUUID,
"POST /h/{uuid}",
},
// An admin page route group, which installs its own
// sentryhttp handler.
{http.MethodGet, "/pages/login", "GET /pages/login"},
{http.MethodGet, "/pages/unrouted", "GET /pages/*"},
{
http.MethodPost,
"/h/" + sentryReceiverUUID + "/unrouted",
"POST /(redacted)",
},
} {
t.Run(tc.want, func(t *testing.T) {
t.Parallel()
transport := &captureTransport{}
opts := server.SentryClientOptionsForTest(
"https://public@sentry.invalid/1",
"webhooker-test",
)
opts.Transport = transport
opts.EnableTracing = true
opts.TracesSampleRate = 1.0
client, err := sentry.NewClient(opts)
require.NoError(t, err)
req := httptest.NewRequestWithContext(
sentry.SetHubOnContext(
context.Background(),
sentry.NewHub(client, sentry.NewScope()),
),
tc.method, tc.path, nil,
)
router.ServeHTTP(httptest.NewRecorder(), req)
event := onlyEvent(t, transport.events)
require.Equal(t, "transaction", event.Type)
assert.Equal(t, tc.want, event.Transaction)
assert.NotContains(
t, marshalEvent(t, event), sentryReceiverUUID,
)
})
}
}
// TestSentryScrub_TransactionDispatchIsUnscrubbedWithoutTheHook pins
// that dispatch's premise the same way, since it is the one the
// service does not exercise today.
internal/session/session.go
+3 -4
View File
@@ -441,10 +441,9 @@ func (s *Session) Regenerate(
//
// Whichever comes first ends the session.
//
// A session that claims to be authenticated but carries no
// timestamps predates this check; it is treated as expired so the
// user re-authenticates rather than being granted an unbounded
// session.
// A session that claims to be authenticated but lacks the timestamp
// a deadline is measured from is treated as expired, so the user
// re-authenticates rather than being granted an unbounded session.
func (s *Session) expired(sess *sessions.Session) bool {
now := s.now()
internal/versionscript/version_script_test.go
+6 -2
View File
@@ -156,7 +156,8 @@ func TestVersion_IsStableAcrossInvocations(t *testing.T) {
// The build target is the only place composing linker flags. If a
// future edit drops either half, the binary silently reports "dev"
// again (the defect this package exists for) or fails to link on
// Alpine.
// Alpine. If it stops passing GO_TAGS, the image's static binary links
// glibc's getaddrinfo and dlopen again.
func TestMakefile_BuildComposesVersionAndExtraFlags(t *testing.T) {
t.Parallel()
@@ -164,6 +165,7 @@ func TestMakefile_BuildComposesVersionAndExtraFlags(t *testing.T) {
require.Contains(t, makefile, "-X main.version=$(VERSION)")
require.Contains(t, makefile, "$(GO_LDFLAGS)")
require.Contains(t, makefile, "-tags '$(GO_TAGS)'")
require.Contains(t, makefile, "VERSION ?= $(shell script/version)")
}
@@ -233,7 +235,9 @@ func TestDockerfile_BuildsThroughTheMakeTarget(t *testing.T) {
"a raw go build bypasses the Makefile's -X flag")
require.Contains(t, dockerfile, "ARG VERSION")
require.Contains(t, dockerfile,
`make build VERSION="$VERSION" GO_LDFLAGS='-extldflags "-static"'`)
`make build VERSION="$VERSION"`+
` GO_TAGS=netgo,osusergo,sqlite_omit_load_extension`+
` GO_LDFLAGS='-extldflags "-static"'`)
}
func read(t *testing.T, path string) string {
static/js/app.js
+3 -3
View File
@@ -139,7 +139,7 @@ document.addEventListener("alpine:init", function () {
headers: "",
timeout: "",
forwardQuery: false,
maxRetries: "",
maxAttempts: "",
expiry: "",
rotation: "",
init() {
@@ -153,7 +153,7 @@ document.addEventListener("alpine:init", function () {
this.timeout = refused.timeout;
this.forwardQuery =
this.$root.hasAttribute("data-forward-query");
this.maxRetries = refused.maxRetries;
this.maxAttempts = refused.maxAttempts;
this.expiry = refused.expiry;
this.rotation = refused.rotation;
},
@@ -173,7 +173,7 @@ document.addEventListener("alpine:init", function () {
this.headers = "";
this.timeout = "";
this.forwardQuery = false;
this.maxRetries = "";
this.maxAttempts = "";
this.expiry = "";
this.rotation = "";
this.$refs.form.reset();
templates/source_detail.html
+5 -5
View File
@@ -136,7 +136,7 @@
data-headers="{{.TargetForm.Headers}}"
data-timeout="{{.TargetForm.Timeout}}"
{{if .TargetForm.ForwardQuery}}data-forward-query{{end}}
data-max-retries="{{.TargetForm.MaxRetries}}"
data-max-attempts="{{.TargetForm.MaxAttempts}}"
data-expiry="{{.TargetForm.Expiry}}"
data-rotation="{{.TargetForm.Rotation}}">
<div class="p-4 border-b border-gray-200 flex justify-between items-center">
@@ -194,9 +194,9 @@
<div>
<div class="flex gap-2 items-center">
<label class="text-sm text-gray-700">Delivery attempts:</label>
<input type="number" name="max_retries" :value="maxRetries" placeholder="0" min="0" max="20" class="input text-sm w-24">
<input type="number" name="max_attempts" :value="maxAttempts" placeholder="1" min="1" max="20" class="input text-sm w-24">
</div>
<p class="text-xs text-gray-500 mt-1">How many times each delivery is attempted in all, the first attempt included. 0 means a single attempt with no retries and no circuit breaker.</p>
<p class="text-xs text-gray-500 mt-1">How many times each delivery is attempted in all, the first attempt included.</p>
</div>
</div>
</template>
@@ -210,9 +210,9 @@
<div>
<div class="flex gap-2 items-center">
<label class="text-sm text-gray-700">Delivery attempts:</label>
<input type="number" name="max_retries" :value="maxRetries" placeholder="0" min="0" max="20" class="input text-sm w-24">
<input type="number" name="max_attempts" :value="maxAttempts" placeholder="1" min="1" max="20" class="input text-sm w-24">
</div>
<p class="text-xs text-gray-500 mt-1">How many times each delivery is attempted in all, the first attempt included. 0 means a single attempt with no retries and no circuit breaker.</p>
<p class="text-xs text-gray-500 mt-1">How many times each delivery is attempted in all, the first attempt included.</p>
</div>
</div>
</template>
templates/target_edit.html
+3 -3
View File
@@ -89,9 +89,9 @@
{{if or (eq .Target.Type "http") (eq .Target.Type "slack")}}
<div class="form-group">
<label for="max_retries" class="label">Delivery attempts</label>
<input type="number" id="max_retries" name="max_retries" value="{{.TargetForm.MaxRetries}}" min="0" max="20" class="input">
<p class="text-xs text-gray-500 mt-1">How many times each delivery is attempted in all, the first attempt included. 0 means a single attempt with no retries and no circuit breaker.</p>
<label for="max_attempts" class="label">Delivery attempts</label>
<input type="number" id="max_attempts" name="max_attempts" value="{{.TargetForm.MaxAttempts}}" min="1" max="20" class="input">
<p class="text-xs text-gray-500 mt-1">How many times each delivery is attempted in all, the first attempt included.</p>
</div>
{{end}}