From 8894ea0c7bc2f108c4ed19a393f47497a336851c Mon Sep 17 00:00:00 2001 From: Andreas Brenner Date: Fri, 24 Jul 2026 23:41:33 +0300 Subject: [PATCH 1/6] ANW-41 Docs: fix four broken rustdoc intra-doc links cargo doc --no-deps is warning-free. No behaviour change. --- src/doctor.rs | 2 +- src/query.rs | 2 +- src/watcher.rs | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/src/doctor.rs b/src/doctor.rs index 58f3e8d..f53f09f 100644 --- a/src/doctor.rs +++ b/src/doctor.rs @@ -46,7 +46,7 @@ pub struct DriftShape { /// `"bool"`, `"number"`, `"string"`, `"date"`, `"list"`, `"mapping"`. pub shape: &'static str, pub count: usize, - /// Up to [`DRIFT_SAMPLES_PER_SHAPE`] vault-relative paths exhibiting + /// Up to `DRIFT_SAMPLES_PER_SHAPE` vault-relative paths exhibiting /// this shape, in the order they were scanned. pub samples: Vec, } diff --git a/src/query.rs b/src/query.rs index bf301f7..786e80d 100644 --- a/src/query.rs +++ b/src/query.rs @@ -11,7 +11,7 @@ //! `__in` / `__all` are comma-separated; unknown operators are `400`. //! //! Predicates are evaluated by iterating the in-memory [`NoteStore`] and -//! applying each [`Predicate::matches`] in turn. At the documented scale +//! applying each [`Predicate`] in turn. At the documented scale //! (low-thousands-of-notes vaults) this is sub-millisecond; see //! [[ADR-009 Reverse ADR-002 In-Memory Evaluation No Tantivy]] for the //! call to keep evaluation in-memory rather than carrying a Tantivy index. diff --git a/src/watcher.rs b/src/watcher.rs index f004db0..0f7ccc0 100644 --- a/src/watcher.rs +++ b/src/watcher.rs @@ -4,7 +4,7 @@ //! [`notify::RecommendedWatcher`] over the vault root. Each native event is //! pushed into a Tokio channel; [`run_debouncer`] drains the channel, //! classifies events into [`WatchAction`]s, coalesces a 100 ms window's -//! worth into one [`Batch`], and casts the batch to the `index_writer` +//! worth into one [`WatchBatch`], and casts the batch to the `index_writer` //! named process for a single [`crate::store::NoteStore`] write. //! //! See [[ADR-003 Filesystem Change Tracking]] for the event model. @@ -27,7 +27,7 @@ use crate::vault; /// One path-scoped action derived from a native filesystem event. Always /// carries a vault-relative, forward-slash-normalized path string -- the -/// same form [`vault::Note.path`] uses. +/// same form [`vault::Note::path`] uses. /// /// The `*Tree` variants carry a directory instead of a note. Native events /// name only the directory when one is created, removed, or renamed; the From dc113b8249d42081afb205fffa4b759f9f02265a Mon Sep 17 00:00:00 2001 From: Andreas Brenner Date: Sun, 26 Jul 2026 23:44:51 +0300 Subject: [PATCH 2/6] ANW-42 Telemetry: take export config from OTEL_ environment variables only Delete the uptrace DSN parser and the {endpoint}/v1/* concatenation that produced the dead export, and build the OTLP exporters with no endpoint, headers, or protocol so the SDK reads OTEL_EXPORTER_OTLP_* itself. The SDK concatenates as naively as we did: measured against a local sink, a ?query base sends POST /?query/v1/metrics and a #fragment base sends POST /. So one check stays -- a query or fragment on OTEL_EXPORTER_OTLP_ENDPOINT fails at startup. Per-signal variables are used verbatim and need none. A protocol variable is the second startup check. The exporter picks its transport at build time and this binary ships OTLP/HTTP alone, so OTEL_EXPORTER_OTLP_PROTOCOL=grpc kept exporting over HTTP with nothing in the log -- the same silence this change removes. service.name stays a default rather than policy: an attribute set on the resource builder wins over the SDK detectors that read OTEL_SERVICE_NAME and OTEL_RESOURCE_ATTRIBUTES, so anwesen supplies its own only for keys the environment leaves alone. Telemetry-off is our own check on the endpoint variables: with none set the exporter would still build and aim at the SDK default localhost:4318. --uptrace-dsn, --otlp-endpoint, and --otlp-header stay parsed but hidden, so a deployment upgrading with them set fails naming the OTEL_ replacement instead of going quiet. Assumed hidden clap stubs are the right migration shape; clap rejecting the flags as unknown would say nothing about the replacement. Flag if a plain unknown-argument error is wanted instead. Assumed rejecting http/json alongside grpc is right: neither has a transport in this build. Flag if a build with both features is wanted instead. --- README.md | 59 ++++- src/cli.rs | 63 +++-- src/http.rs | 23 +- src/main.rs | 22 +- src/telemetry.rs | 623 +++++++++++++++++++++++++++++++++-------------- 5 files changed, 563 insertions(+), 227 deletions(-) diff --git a/README.md b/README.md index d4e2fc0..a7bb236 100644 --- a/README.md +++ b/README.md @@ -56,8 +56,7 @@ anwesen merge --vault /path/to/vault --query 'tags=adr&__anw-order=title' > ADRs ``` anwesen serve --vault [--bind ] [--log-level ] - [--uptrace-dsn | --otlp-endpoint ] - [--otlp-header ]... [--otlp-slow-request-ms ] + [--otlp-slow-request-ms ] anwesen doctor --vault anwesen merge --vault --query anwesen version @@ -69,24 +68,62 @@ anwesen version | `--bind ` | `ANWESEN_BIND` | `127.0.0.1:8080` | Listen address for `serve`. | | `--log-level ` | `ANWESEN_LOG_LEVEL` | `info` | `error`, `warn`, `info`, `debug`, or `trace`. | | `--query ` | -- | _required for `merge`_ | A `/query` query string: frontmatter predicates plus `__anw-` controls. | -| `--uptrace-dsn ` | `ANWESEN_UPTRACE_DSN` | unset | uptrace DSN (`https://@api.uptrace.dev`). Excludes `--otlp-endpoint`. | -| `--otlp-endpoint ` | `ANWESEN_OTLP_ENDPOINT` | unset | OTLP/HTTP base URL. Excludes `--uptrace-dsn`. | -| `--otlp-header ` | `ANWESEN_OTLP_HEADERS` | none | Extra export header, repeatable. The env var takes a comma-separated list. | | `--otlp-slow-request-ms` | `ANWESEN_OTLP_SLOW_REQUEST_MS` | `500` | Requests at or over this duration, or answering 5xx, also export a span. | -Every flag has a matching `ANWESEN_` environment variable, except -`--otlp-header`, whose env var is the plural `ANWESEN_OTLP_HEADERS` because it -takes a list. CLI flags win over env vars. +Every flag has a matching `ANWESEN_` environment variable. CLI flags win +over env vars. -Telemetry is off unless `--uptrace-dsn` or `--otlp-endpoint` is set. With -neither, nothing is exported and no exporter is built. The four telemetry -flags apply to `serve` only. +`--bind` and `--otlp-slow-request-ms` apply to `serve` only. Where telemetry is +exported is configured entirely through the standard `OTEL_` variables below. - **`serve`** -- run the daemon: walk the vault, build the index, watch for changes, serve the API. - **`doctor`** -- walk the vault once and report what would stop clean ingestion: unreadable files, unparseable YAML, path collisions on the HTTP surface, and frontmatter type drift (the same key carrying incompatible types across notes). Read-only; non-zero exit if any issue is found. - **`merge`** -- one-shot local generation: walk the vault, evaluate `--query`, and write the merged markdown document to stdout. No server, no HTTP. See [Local generation](#local-generation). - **`version`** -- print version and exit. +## Telemetry + +anwesen exports OTLP metrics for every request, and a span for requests at or +over `--otlp-slow-request-ms` or answering a 5xx. Export is configured through +the standard OpenTelemetry environment variables, which the SDK reads directly: + +| Variable | Meaning | +| -------------------------------------- | ---------------------------------------------------------------- | +| `OTEL_EXPORTER_OTLP_ENDPOINT` | Base URL. The SDK appends `/v1/metrics` and `/v1/traces`. | +| `OTEL_EXPORTER_OTLP_METRICS_ENDPOINT` | Full metrics URL, used as given. Overrides the base for metrics. | +| `OTEL_EXPORTER_OTLP_TRACES_ENDPOINT` | Full traces URL, used as given. Overrides the base for traces. | +| `OTEL_EXPORTER_OTLP_HEADERS` | Export headers, `key=value` comma-separated. | +| `OTEL_EXPORTER_OTLP_PROTOCOL` | `http/protobuf`, the default and the only value this build speaks. | +| `OTEL_SERVICE_NAME`, `OTEL_RESOURCE_ATTRIBUTES` | Override the `anwesen` service identity. | + +The per-signal `OTEL_EXPORTER_OTLP_METRICS_PROTOCOL` and +`OTEL_EXPORTER_OTLP_TRACES_PROTOCOL` are read the same way. + +With none of the three endpoint variables set, telemetry is off: no exporter is +built and the request middleware is not installed. + +Two settings fail at startup rather than export nowhere in silence: + +- A query or a fragment on `OTEL_EXPORTER_OTLP_ENDPOINT`. The base URL must be + a base URL; the SDK appends the signal path after whatever it is given. +- A protocol other than `http/protobuf`. The binary ships the OTLP/HTTP + transport alone, so `grpc` would keep exporting over HTTP with nothing in the + log. Point the endpoint at the collector's HTTP port, not its gRPC one. + +uptrace: + +``` +OTEL_EXPORTER_OTLP_ENDPOINT=https://api.uptrace.dev +OTEL_EXPORTER_OTLP_HEADERS=uptrace-dsn=https://TOKEN@api.uptrace.dev?grpc=4317 +``` + +Paste the DSN from Project Settings into the header verbatim, tail and all -- +it is a credential there, not an address. The endpoint is the host alone. + +Removed in 0.3.0: `--uptrace-dsn`, `--otlp-endpoint`, `--otlp-header` and their +`ANWESEN_` variables. Passing any of them fails at startup with the `OTEL_` +replacement to use. + ## HTTP API All endpoints are `GET` and return JSON unless noted. diff --git a/src/cli.rs b/src/cli.rs index 155ab5b..52e65e4 100644 --- a/src/cli.rs +++ b/src/cli.rs @@ -4,18 +4,22 @@ //! //! ```text //! anwesen serve --vault [--bind ] [--log-level ] -//! [--uptrace-dsn | --otlp-endpoint ] -//! [--otlp-header ]... [--otlp-slow-request-ms ] +//! [--otlp-slow-request-ms ] //! anwesen doctor --vault [--log-level ] //! anwesen merge --vault [--query ] [--log-level ] //! anwesen version //! ``` //! -//! `--bind` and the OTLP telemetry flags are `serve`-only ([ANW-37]); +//! `--bind` and `--otlp-slow-request-ms` are `serve`-only ([ANW-37]); //! `doctor` and `merge` do not bind a port; `version` takes no flags. Each //! flag has a matching `ANWESEN_` environment variable and CLI wins -//! over env per the manual. With no `--otlp-endpoint`/`--uptrace-dsn`, -//! telemetry is off and the server behaves exactly as without these flags. +//! over env per the manual. +//! +//! Telemetry export is configured through the standard `OTEL_EXPORTER_OTLP_*` +//! environment variables ([ANW-42](https://crvrs.youtrack.cloud/issue/ANW-42)). +//! With none of them set, telemetry is off and the server behaves as it did +//! before telemetry existed. The removed flags below are still parsed so an +//! upgrade fails loudly instead of dropping export config in silence. use std::net::SocketAddr; use std::path::PathBuf; @@ -56,25 +60,22 @@ pub struct ServeArgs { #[arg(long, env = "ANWESEN_LOG_LEVEL", default_value = "info")] pub log_level: LogLevel, - /// uptrace DSN shorthand (`https://@api.uptrace.dev`), parsed - /// into the OTLP endpoint plus an `uptrace-dsn` header. Mutually - /// exclusive with --otlp-endpoint. When this and --otlp-endpoint are - /// both unset, telemetry is fully off (ANW-37). - #[arg(long, env = "ANWESEN_UPTRACE_DSN")] + /// Removed (ANW-42): use `OTEL_EXPORTER_OTLP_ENDPOINT` plus + /// `OTEL_EXPORTER_OTLP_HEADERS=uptrace-dsn=`. Still accepted so + /// startup fails with that message rather than exporting nowhere. + #[arg(long, env = "ANWESEN_UPTRACE_DSN", hide = true)] pub uptrace_dsn: Option, - /// Generic OTLP/HTTP endpoint base URL for telemetry export. The - /// per-signal path (`/v1/metrics`, `/v1/traces`) is appended by the - /// exporter. Mutually exclusive with --uptrace-dsn. - #[arg(long, env = "ANWESEN_OTLP_ENDPOINT")] + /// Removed (ANW-42): use `OTEL_EXPORTER_OTLP_ENDPOINT`. + #[arg(long, env = "ANWESEN_OTLP_ENDPOINT", hide = true)] pub otlp_endpoint: Option, - /// Extra OTLP export header as `key=value`, repeatable. On the env var - /// (`ANWESEN_OTLP_HEADERS`) pass a comma-separated `key=value` list. + /// Removed (ANW-42): use `OTEL_EXPORTER_OTLP_HEADERS`. #[arg( long = "otlp-header", env = "ANWESEN_OTLP_HEADERS", - value_delimiter = ',' + value_delimiter = ',', + hide = true )] pub otlp_headers: Vec, @@ -172,6 +173,34 @@ mod tests { } } + /// The removed telemetry flags still parse, hidden from `--help`. Clap + /// rejecting them as unknown would say nothing about the `OTEL_` + /// replacement; the migration error in `telemetry::TelemetryConfig` + /// needs the values to reach it (ANW-42). + #[test] + fn serve_still_parses_the_removed_telemetry_flags() { + let cli = parse(&[ + "serve", + "--vault", + "/tmp/v", + "--uptrace-dsn", + "https://tok@api.uptrace.dev", + "--otlp-endpoint", + "https://collector.example.com", + "--otlp-header", + "authorization=Bearer xyz", + ]) + .expect("parse"); + match cli.command { + Command::Serve(a) => { + assert!(a.uptrace_dsn.is_some()); + assert!(a.otlp_endpoint.is_some()); + assert_eq!(a.otlp_headers, vec!["authorization=Bearer xyz".to_string()]); + } + _ => panic!("expected serve"), + } + } + #[test] fn serve_rejects_malformed_bind_at_parse_time() { let err = parse(&["serve", "--vault", "/tmp/v", "--bind", "not-an-addr"]).unwrap_err(); diff --git a/src/http.rs b/src/http.rs index 48ec78e..52d4c0f 100644 --- a/src/http.rs +++ b/src/http.rs @@ -819,18 +819,23 @@ mod tests { } /// With telemetry installed, a normal request is answered byte-for-byte - /// as without it. The exporter points at an unreachable local port, so - /// export fails instantly in the background and never touches the - /// response path. + /// as without it. The test process sets no `OTEL_EXPORTER_OTLP_*` + /// variables, so the exporter aims at the SDK default and fails in the + /// background without ever touching the response path. #[tokio::test] async fn telemetry_layer_does_not_alter_responses() { - use crate::telemetry::{self, RawTelemetryArgs, TelemetryConfig}; + use crate::telemetry::{self, OtelEnv, RawTelemetryArgs, TelemetryConfig}; - let cfg = TelemetryConfig::resolve(RawTelemetryArgs { - otlp_endpoint: Some("http://127.0.0.1:9".into()), - slow_request_ms: 500, - ..Default::default() - }) + let cfg = TelemetryConfig::resolve( + &RawTelemetryArgs { + slow_request_ms: 500, + ..Default::default() + }, + OtelEnv { + endpoint: Some("http://127.0.0.1:9".into()), + ..OtelEnv::default() + }, + ) .unwrap() .expect("telemetry on"); let tel = Arc::new(telemetry::init(cfg).expect("telemetry init")); diff --git a/src/main.rs b/src/main.rs index f573e3f..4ac8e27 100644 --- a/src/main.rs +++ b/src/main.rs @@ -10,7 +10,7 @@ use std::sync::Arc; use anwesen::app::Anwesen; use anwesen::doctor; use anwesen::merge; -use anwesen::telemetry::{self, RawTelemetryArgs, TelemetryConfig}; +use anwesen::telemetry::{self, OtelEnv, RawTelemetryArgs, TelemetryConfig}; use anyhow::Result; use clap::Parser; use hydra::Application; @@ -25,14 +25,18 @@ fn main() -> Result<()> { match cli.command { Command::Serve(args) => { init_logging(args.log_level); - // Resolve telemetry config before the supervisor starts; an - // unset endpoint leaves it `None` (export off, behaves as today). - let telemetry = match TelemetryConfig::resolve(RawTelemetryArgs { - uptrace_dsn: args.uptrace_dsn, - otlp_endpoint: args.otlp_endpoint, - otlp_headers: args.otlp_headers, - slow_request_ms: args.otlp_slow_request_ms, - })? { + // Resolve telemetry config before the supervisor starts; no + // OTEL_EXPORTER_OTLP_* endpoint leaves it `None` (export off, + // no middleware). A removed flag is a startup error (ANW-42). + let telemetry = match TelemetryConfig::resolve( + &RawTelemetryArgs { + uptrace_dsn: args.uptrace_dsn, + otlp_endpoint: args.otlp_endpoint, + otlp_headers: args.otlp_headers, + slow_request_ms: args.otlp_slow_request_ms, + }, + OtelEnv::from_env(), + )? { Some(cfg) => Some(Arc::new(telemetry::init(cfg)?)), None => None, }; diff --git a/src/telemetry.rs b/src/telemetry.rs index a685b2d..15511c6 100644 --- a/src/telemetry.rs +++ b/src/telemetry.rs @@ -12,140 +12,288 @@ //! the propagated context. Every other request stays metrics-only, so the //! ~3.6k requests/min steady state does not drown the trace backend. //! -//! When no OTLP endpoint (or uptrace DSN) is configured, [`init`] returns +//! Transport configuration comes from the standard `OTEL_EXPORTER_OTLP_*` +//! environment variables only, read by the `OpenTelemetry` SDK itself +//! ([ANW-42](https://crvrs.youtrack.cloud/issue/ANW-42)). anwesen parses no +//! addresses and appends no per-signal paths. It checks two things at +//! startup, both cases the SDK would otherwise export nowhere in silence: +//! +//! - `OTEL_EXPORTER_OTLP_ENDPOINT` carries no query or fragment, because the +//! SDK's own concatenation mangles those (measured against a sink: a +//! `?tail` base sends `POST /?tail/v1/metrics`, a `#frag` base sends +//! `POST /`). +//! - No protocol variable asks for anything but `http/protobuf`, the only +//! transport this binary is built with. +//! +//! When no endpoint variable is set, [`TelemetryConfig::resolve`] returns //! `None`, the request middleware is not installed, and the server behaves //! exactly as it did before this module existed. External installs run //! unchanged. -//! -//! Config mirrors the gestell uptrace surface (see the gestell PDR-GES-136 -//! `[otel]` section): a `uptrace_dsn` shorthand, or a generic endpoint plus -//! headers. -use std::collections::HashMap; use std::time::{Duration, SystemTime}; -use anyhow::{Context as _, anyhow, bail}; +use anyhow::{Context as _, bail}; use axum::http::HeaderMap; use opentelemetry::KeyValue; use opentelemetry::metrics::{Counter, Histogram, MeterProvider as _}; use opentelemetry::propagation::{Extractor, TextMapPropagator}; use opentelemetry::trace::{Span, SpanKind, Tracer, TracerProvider as _}; -use opentelemetry_otlp::{ - MetricExporter, Protocol, SpanExporter, WithExportConfig, WithHttpConfig, -}; +use opentelemetry_otlp::{MetricExporter, SpanExporter}; use opentelemetry_sdk::Resource; use opentelemetry_sdk::metrics::{PeriodicReader, SdkMeterProvider}; use opentelemetry_sdk::propagation::TraceContextPropagator; use opentelemetry_sdk::trace::Sampler; use opentelemetry_sdk::trace::{SdkTracer, SdkTracerProvider}; -use opentelemetry_semantic_conventions::resource::SERVICE_VERSION; +use opentelemetry_semantic_conventions::resource::{SERVICE_NAME, SERVICE_VERSION}; -/// Raw telemetry options as parsed by clap on the `serve` command. Resolved -/// into an [`Option`] by [`TelemetryConfig::resolve`]. +/// The removed telemetry options, still parsed so their presence is an error +/// rather than a silent config drop on upgrade +/// ([ANW-42](https://crvrs.youtrack.cloud/issue/ANW-42)), plus the one +/// surviving option. Resolved into an [`Option`] by +/// [`TelemetryConfig::resolve`]. #[derive(Debug, Default)] pub struct RawTelemetryArgs { - /// `--uptrace-dsn` / `ANWESEN_UPTRACE_DSN`. + /// Removed `--uptrace-dsn` / `ANWESEN_UPTRACE_DSN`. pub uptrace_dsn: Option, - /// `--otlp-endpoint` / `ANWESEN_OTLP_ENDPOINT`. + /// Removed `--otlp-endpoint` / `ANWESEN_OTLP_ENDPOINT`. pub otlp_endpoint: Option, - /// `--otlp-header` / `ANWESEN_OTLP_HEADERS`, each `key=value`. + /// Removed `--otlp-header` / `ANWESEN_OTLP_HEADERS`. pub otlp_headers: Vec, - /// `--otlp-slow-request-ms` / `ANWESEN_OTLP_SLOW_REQUEST_MS`. + /// `--otlp-slow-request-ms` / `ANWESEN_OTLP_SLOW_REQUEST_MS`. Kept: it + /// decides when anwesen emits a span, not where the export goes, and no + /// standard variable covers it. pub slow_request_ms: u64, } -/// A resolved, telemetry-on configuration. Built only when an endpoint or a -/// DSN is present; absence is represented by `Ok(None)` from [`resolve`]. +/// The OTLP transport variables the SDK reads, captured once at startup so +/// the telemetry-on decision and the startup checks stay pure functions of +/// them. Values are the raw strings; anwesen does not parse them beyond the +/// checks in [`check_generic_endpoint`] and [`check_protocols`]. +#[derive(Debug, Default, Clone, PartialEq, Eq)] +pub struct OtelEnv { + /// `OTEL_EXPORTER_OTLP_ENDPOINT`: base URL, per-signal path appended by + /// the SDK. + pub endpoint: Option, + /// `OTEL_EXPORTER_OTLP_METRICS_ENDPOINT`: full URL, used verbatim. + pub metrics_endpoint: Option, + /// `OTEL_EXPORTER_OTLP_TRACES_ENDPOINT`: full URL, used verbatim. + pub traces_endpoint: Option, + /// `OTEL_EXPORTER_OTLP_PROTOCOL`. + pub protocol: Option, + /// `OTEL_EXPORTER_OTLP_METRICS_PROTOCOL`. + pub metrics_protocol: Option, + /// `OTEL_EXPORTER_OTLP_TRACES_PROTOCOL`. + pub traces_protocol: Option, +} + +impl OtelEnv { + /// Read the transport variables from the process environment. An empty or + /// whitespace-only value counts as unset: an empty endpoint would + /// otherwise turn telemetry on and export to the SDK's `localhost:4318` + /// default. + #[must_use] + pub fn from_env() -> Self { + let var = |name: &str| { + std::env::var(name) + .ok() + .map(|v| v.trim().to_string()) + .filter(|v| !v.is_empty()) + }; + Self { + endpoint: var("OTEL_EXPORTER_OTLP_ENDPOINT"), + metrics_endpoint: var("OTEL_EXPORTER_OTLP_METRICS_ENDPOINT"), + traces_endpoint: var("OTEL_EXPORTER_OTLP_TRACES_ENDPOINT"), + protocol: var("OTEL_EXPORTER_OTLP_PROTOCOL"), + metrics_protocol: var("OTEL_EXPORTER_OTLP_METRICS_PROTOCOL"), + traces_protocol: var("OTEL_EXPORTER_OTLP_TRACES_PROTOCOL"), + } + } + + /// Whether any endpoint variable is set. No endpoint means telemetry off. + fn any_endpoint(&self) -> bool { + self.endpoint.is_some() || self.metrics_endpoint.is_some() || self.traces_endpoint.is_some() + } + + /// The endpoint to name in the startup log: the generic base when set, + /// otherwise whichever per-signal URL is. + fn describe(&self) -> &str { + self.endpoint + .as_deref() + .or(self.metrics_endpoint.as_deref()) + .or(self.traces_endpoint.as_deref()) + .unwrap_or("") + } +} + +/// A resolved, telemetry-on configuration. Built only when an endpoint +/// variable is set; absence is represented by `Ok(None)` from [`resolve`]. +/// It carries no transport settings: the exporters read those from the +/// environment themselves. /// /// [`resolve`]: TelemetryConfig::resolve #[derive(Debug, Clone, PartialEq, Eq)] pub struct TelemetryConfig { - /// OTLP/HTTP base URL. The exporter appends the per-signal path - /// (`/v1/metrics`, `/v1/traces`). - pub endpoint: String, - /// Export headers (for uptrace, the `uptrace-dsn` entry) as ordered - /// `(name, value)` pairs. - pub headers: Vec<(String, String)>, /// A request at or over this duration, or answering a 5xx, is recorded /// as a server span. pub slow_request: Duration, + /// The transport variables, kept for the startup log line only. + env: OtelEnv, } impl TelemetryConfig { - /// Resolve raw clap options into an optional config. + /// Resolve the surviving option plus the OTLP transport variables into an + /// optional config. /// - /// - Both `uptrace_dsn` and `otlp_endpoint` set is an error (they are - /// two ways to name the same endpoint). - /// - Neither set means telemetry is off: `Ok(None)`. - /// - A malformed `key=value` header or an unparseable DSN is an error, - /// surfaced at startup rather than silently dropping export. + /// - A removed flag or `ANWESEN_` variable is an error naming its `OTEL_` + /// replacement: a deployment exporting today must fail one restart + /// rather than go quiet. + /// - No endpoint variable set means telemetry is off: `Ok(None)`. + /// - A query or fragment on `OTEL_EXPORTER_OTLP_ENDPOINT` is an error. + /// - A protocol this binary cannot speak is an error. /// /// # Errors - /// Returns an error when the two endpoint sources conflict, a header is - /// not `key=value`, or the uptrace DSN cannot be parsed. - pub fn resolve(raw: RawTelemetryArgs) -> anyhow::Result> { - let slow_request = Duration::from_millis(raw.slow_request_ms); - let mut headers = parse_headers(&raw.otlp_headers)?; - - match (raw.uptrace_dsn, raw.otlp_endpoint) { - (Some(_), Some(_)) => { - bail!("--uptrace-dsn and --otlp-endpoint are mutually exclusive"); - } - (Some(dsn), None) => { - let (endpoint, dsn_header) = parse_uptrace_dsn(&dsn)?; - // The DSN header leads; any explicit --otlp-header follows. - headers.insert(0, dsn_header); - Ok(Some(Self { - endpoint, - headers, - slow_request, - })) - } - (None, Some(endpoint)) => Ok(Some(Self { - endpoint, - headers, - slow_request, - })), - (None, None) => Ok(None), + /// Returns an error when a removed option is present, when the generic + /// endpoint carries a query or a fragment, or when a protocol variable + /// asks for anything but `http/protobuf`. + pub fn resolve(raw: &RawTelemetryArgs, env: OtelEnv) -> anyhow::Result> { + check_removed(raw)?; + if !env.any_endpoint() { + return Ok(None); } + if let Some(endpoint) = &env.endpoint { + check_generic_endpoint(endpoint)?; + } + check_protocols(&env)?; + Ok(Some(Self { + slow_request: Duration::from_millis(raw.slow_request_ms), + env, + })) } } -/// Parse `key=value` header specs. Whitespace around key and value is -/// trimmed; an empty key or a spec with no `=` is an error. -fn parse_headers(specs: &[String]) -> anyhow::Result> { - let mut out = Vec::with_capacity(specs.len()); - for spec in specs { - let (k, v) = spec - .split_once('=') - .ok_or_else(|| anyhow!("OTLP header {spec:?} is not key=value"))?; - let k = k.trim(); - if k.is_empty() { - bail!("OTLP header {spec:?} has an empty key"); +/// Fail on any removed telemetry option, naming the `OTEL_` variable that +/// replaces it. Silence is the expensive failure here: an upgrade that drops +/// the export config would stop telemetry with nothing in the log. +fn check_removed(raw: &RawTelemetryArgs) -> anyhow::Result<()> { + let removed: [(&str, &str, bool); 3] = [ + ( + "--uptrace-dsn / ANWESEN_UPTRACE_DSN", + "OTEL_EXPORTER_OTLP_ENDPOINT=https://api.uptrace.dev plus \ + OTEL_EXPORTER_OTLP_HEADERS=uptrace-dsn=", + raw.uptrace_dsn.is_some(), + ), + ( + "--otlp-endpoint / ANWESEN_OTLP_ENDPOINT", + "OTEL_EXPORTER_OTLP_ENDPOINT", + raw.otlp_endpoint.is_some(), + ), + ( + "--otlp-header / ANWESEN_OTLP_HEADERS", + "OTEL_EXPORTER_OTLP_HEADERS", + !raw.otlp_headers.is_empty(), + ), + ]; + for (option, replacement, present) in removed { + if present { + bail!("{option} was removed in anwesen 0.3.0; use {replacement} instead"); } - out.push((k.to_string(), v.trim().to_string())); } - Ok(out) + Ok(()) } -/// Parse an uptrace DSN (`https://@host[:port]`) into the OTLP -/// endpoint base URL and the `uptrace-dsn` header uptrace expects. The full -/// DSN is echoed as the header value per uptrace's ingest contract. -fn parse_uptrace_dsn(dsn: &str) -> anyhow::Result<(String, (String, String))> { - let dsn = dsn.trim(); - let (scheme, rest) = dsn - .split_once("://") - .context("uptrace DSN has no scheme (expected https://@host)")?; - // Host is whatever follows the credentials `@`; a DSN with no `@` is - // treated as endpoint-only (lenient, though real uptrace DSNs carry a - // token). - let host = rest.rsplit_once('@').map_or(rest, |(_, h)| h); - let host = host.trim_end_matches('/'); - if host.is_empty() { - bail!("uptrace DSN has no host"); +/// Reject a query or fragment on `OTEL_EXPORTER_OTLP_ENDPOINT`. The SDK +/// appends the per-signal path to this value textually, so a `?grpc=4317` +/// tail sends `POST /?grpc=4317/v1/metrics` and a `#frag` tail sends +/// `POST /` -- both dead exports, neither logged. Measured against a sink on +/// opentelemetry-otlp 0.32 ([ANW-42]). A path prefix composes correctly and +/// is left alone. +/// +/// [ANW-42]: https://crvrs.youtrack.cloud/issue/ANW-42 +fn check_generic_endpoint(endpoint: &str) -> anyhow::Result<()> { + if let Some(bad) = endpoint.find(['?', '#']) { + let tail = &endpoint[bad..]; + bail!( + "OTEL_EXPORTER_OTLP_ENDPOINT {endpoint:?} has a trailing {tail:?}; \ + the exporter would append the signal path after it and export nowhere. \ + Pass the base URL alone, and put an uptrace DSN in \ + OTEL_EXPORTER_OTLP_HEADERS=uptrace-dsn=" + ); } - let endpoint = format!("{scheme}://{host}"); - Ok((endpoint, ("uptrace-dsn".to_string(), dsn.to_string()))) + Ok(()) +} + +/// The one OTLP protocol this binary speaks. `opentelemetry-otlp` is built +/// with the `http-proto` feature alone (Cargo.toml), so neither `grpc` nor +/// `http/json` has a transport behind it. +const SUPPORTED_PROTOCOL: &str = "http/protobuf"; + +/// Reject a protocol variable this binary cannot honor. The exporter builder +/// picks its transport at compile time, so `OTEL_EXPORTER_OTLP_PROTOCOL=grpc` +/// does not switch anything: the export keeps going out as HTTP protobuf, +/// with nothing in the log (measured, [ANW-42]). An operator who follows +/// uptrace's console to the gRPC port would get exactly the dead-silent +/// export this issue exists to remove, so it fails at startup instead. +/// +/// [ANW-42]: https://crvrs.youtrack.cloud/issue/ANW-42 +fn check_protocols(env: &OtelEnv) -> anyhow::Result<()> { + let vars = [ + ("OTEL_EXPORTER_OTLP_PROTOCOL", env.protocol.as_deref()), + ( + "OTEL_EXPORTER_OTLP_METRICS_PROTOCOL", + env.metrics_protocol.as_deref(), + ), + ( + "OTEL_EXPORTER_OTLP_TRACES_PROTOCOL", + env.traces_protocol.as_deref(), + ), + ]; + for (name, value) in vars { + let Some(value) = value else { continue }; + if value != SUPPORTED_PROTOCOL { + bail!( + "{name}={value:?} is not supported; this build speaks \ + {SUPPORTED_PROTOCOL} only. Unset the variable, and point the \ + endpoint at the collector's HTTP port rather than its gRPC one" + ); + } + } + Ok(()) +} + +/// The resource attributes anwesen supplies as defaults, minus every key the +/// environment already sets. +/// +/// `service.name=anwesen` and the crate version are defaults, not policy: +/// contract point 6 of [ANW-42] keeps `OTEL_SERVICE_NAME` and +/// `OTEL_RESOURCE_ATTRIBUTES` working. Attaching them unconditionally blocks +/// the override, because an attribute set on the builder wins over the one +/// the SDK's own detectors read from those variables (measured by sie). +/// +/// Only key presence matters here; the values stay the SDK's to parse. +/// +/// [ANW-42]: https://crvrs.youtrack.cloud/issue/ANW-42 +fn default_resource_attrs( + service_name: Option<&str>, + resource_attributes: Option<&str>, +) -> Vec { + let from_attrs: Vec<&str> = resource_attributes + .unwrap_or_default() + .split(',') + .filter_map(|entry| entry.split_once('=')) + .map(|(key, _)| key.trim()) + .collect(); + let set_by_env = |key: &str| { + (key == SERVICE_NAME && service_name.is_some_and(|v| !v.trim().is_empty())) + || from_attrs.contains(&key) + }; + [ + (SERVICE_NAME, "anwesen"), + (SERVICE_VERSION, env!("CARGO_PKG_VERSION")), + ] + .into_iter() + .filter(|(key, _)| !set_by_env(key)) + .map(|(key, value)| KeyValue::new(key, value)) + .collect() } /// Semantic route bucket for the `http.route` label. Coarser than the axum @@ -332,28 +480,29 @@ struct TelemetryInner { impl TelemetryInner { fn new(config: TelemetryConfig) -> anyhow::Result { - let TelemetryConfig { - endpoint, - headers, - slow_request, - } = config; - // `.with_endpoint()` is used verbatim by the exporter (the `/v1/*` - // suffix is only auto-appended for the generic OTEL env var), so we - // append the per-signal path ourselves. - let endpoint = endpoint.trim_end_matches('/').to_string(); - let header_map: HashMap = headers.into_iter().collect(); + let TelemetryConfig { slow_request, env } = config; - let resource = Resource::builder() - .with_service_name("anwesen") - .with_attribute(KeyValue::new(SERVICE_VERSION, env!("CARGO_PKG_VERSION"))) - .build(); + // Service identity is a default only: a key OTEL_SERVICE_NAME or + // OTEL_RESOURCE_ATTRIBUTES already carries is left to the SDK's own + // detectors, because a builder attribute would win over them. + let mut resource = Resource::builder(); + for attr in default_resource_attrs( + std::env::var("OTEL_SERVICE_NAME").ok().as_deref(), + std::env::var("OTEL_RESOURCE_ATTRIBUTES").ok().as_deref(), + ) { + resource = resource.with_attribute(attr); + } + let resource = resource.build(); // -- metrics: thread-based periodic reader over an OTLP/HTTP exporter. + // No endpoint, headers, or protocol here: the SDK reads + // OTEL_EXPORTER_OTLP_* itself and composes the per-signal URL + // (ANW-42). `.with_http()` picks the only transport this binary is + // built with, http/protobuf -- the default, and what anwesen sent + // before. Any other OTEL_EXPORTER_OTLP_PROTOCOL value would be + // ignored here, so `check_protocols` rejects it at startup. let metric_exporter = MetricExporter::builder() .with_http() - .with_protocol(Protocol::HttpBinary) - .with_endpoint(format!("{endpoint}/v1/metrics")) - .with_headers(header_map.clone()) .build() .context("build OTLP metric exporter")?; let reader = PeriodicReader::builder(metric_exporter) @@ -386,9 +535,6 @@ impl TelemetryInner { // -- traces: thread-based batch processor over an OTLP/HTTP exporter. let span_exporter = SpanExporter::builder() .with_http() - .with_protocol(Protocol::HttpBinary) - .with_endpoint(format!("{endpoint}/v1/traces")) - .with_headers(header_map) .build() .context("build OTLP span exporter")?; let tracer_provider = SdkTracerProvider::builder() @@ -401,7 +547,7 @@ impl TelemetryInner { let tracer = tracer_provider.tracer("anwesen"); tracing::info!( - endpoint = %endpoint, + endpoint = %env.describe(), slow_request_ms = slow_request.as_millis(), "telemetry: OTLP export enabled" ); @@ -489,93 +635,208 @@ mod tests { RawTelemetryArgs::default() } - #[test] - fn resolve_off_when_nothing_set() { - let cfg = TelemetryConfig::resolve(raw()).unwrap(); - assert!(cfg.is_none(), "no endpoint/DSN means telemetry off"); + fn generic(endpoint: &str) -> OtelEnv { + OtelEnv { + endpoint: Some(endpoint.into()), + ..OtelEnv::default() + } } #[test] - fn resolve_generic_endpoint() { - let cfg = TelemetryConfig::resolve(RawTelemetryArgs { - otlp_endpoint: Some("https://collector.example.com".into()), - otlp_headers: vec!["authorization=Bearer xyz".into()], - slow_request_ms: 500, - ..raw() - }) - .unwrap() - .expect("telemetry on"); - assert_eq!(cfg.endpoint, "https://collector.example.com"); - assert_eq!( - cfg.headers, - vec![("authorization".to_string(), "Bearer xyz".to_string())] + fn resolve_off_when_no_endpoint_variable_is_set() { + let cfg = TelemetryConfig::resolve(&raw(), OtelEnv::default()).unwrap(); + assert!(cfg.is_none(), "no OTEL_ endpoint means telemetry off"); + } + + #[test] + fn resolve_on_for_each_endpoint_variable() { + let per_signal = |field: fn(&mut OtelEnv)| { + let mut env = OtelEnv::default(); + field(&mut env); + env + }; + for env in [ + generic("https://collector.example.com"), + per_signal(|e| { + e.metrics_endpoint = Some("https://collector.example.com/v1/metrics".into()); + }), + per_signal(|e| { + e.traces_endpoint = Some("https://collector.example.com/v1/traces".into()); + }), + ] { + let cfg = TelemetryConfig::resolve( + &RawTelemetryArgs { + slow_request_ms: 250, + ..raw() + }, + env.clone(), + ) + .unwrap_or_else(|e| panic!("{env:?}: {e}")) + .expect("telemetry on"); + assert_eq!(cfg.slow_request, Duration::from_millis(250)); + } + } + + /// The tails the SDK mangles: a query lands in the query string with the + /// signal path behind it, a fragment drops the signal path entirely. + #[test] + fn resolve_rejects_a_query_or_fragment_on_the_generic_endpoint() { + for endpoint in [ + "https://api.uptrace.dev?grpc=4317", + "https://api.uptrace.dev/?grpc=4317", + "https://api.uptrace.dev:4318?grpc=4317", + "https://api.uptrace.dev#frag", + ] { + let err = TelemetryConfig::resolve(&raw(), generic(endpoint)).unwrap_err(); + assert!(err.to_string().contains("trailing"), "{endpoint}: {err}"); + } + } + + /// A path prefix composes correctly (`/otlp` -> `POST /otlp/v1/metrics`), + /// and the per-signal variables are used verbatim, tail and all. + #[test] + fn resolve_accepts_a_path_prefix_and_per_signal_tails() { + for env in [ + generic("https://collector.example.com/otlp"), + generic("https://collector.example.com/"), + OtelEnv { + metrics_endpoint: Some("https://api.uptrace.dev/v1/metrics?grpc=4317".into()), + ..OtelEnv::default() + }, + ] { + TelemetryConfig::resolve(&raw(), env.clone()) + .unwrap_or_else(|e| panic!("{env:?}: {e}")) + .expect("telemetry on"); + } + } + + /// `.with_http()` fixes the transport at compile time, so a protocol this + /// build cannot speak is a dead export with nothing in the log. + #[test] + fn resolve_rejects_a_protocol_this_build_cannot_speak() { + let with_protocol = |field: fn(&mut OtelEnv)| { + let mut env = generic("https://collector.example.com"); + field(&mut env); + env + }; + for env in [ + with_protocol(|e| e.protocol = Some("grpc".into())), + with_protocol(|e| e.protocol = Some("http/json".into())), + with_protocol(|e| e.metrics_protocol = Some("grpc".into())), + with_protocol(|e| e.traces_protocol = Some("grpc".into())), + ] { + let err = TelemetryConfig::resolve(&raw(), env.clone()) + .unwrap_err() + .to_string(); + assert!(err.contains("http/protobuf"), "{env:?}: {err}"); + } + } + + /// The default protocol is the one this build speaks, so naming it + /// explicitly is not an error. + #[test] + fn resolve_accepts_the_supported_protocol_spelled_out() { + let env = OtelEnv { + protocol: Some("http/protobuf".into()), + metrics_protocol: Some("http/protobuf".into()), + ..generic("https://collector.example.com") + }; + TelemetryConfig::resolve(&raw(), env) + .unwrap() + .expect("telemetry on"); + } + + /// Contract point 6: `service.name` stays anwesen's default only while + /// the environment supplies none. A builder attribute wins over the SDK's + /// detectors, so the default has to step aside for the override to work. + #[test] + fn service_identity_defaults_step_aside_for_the_environment() { + let keys = |attrs: &[KeyValue]| { + attrs + .iter() + .map(|kv| kv.key.as_str().to_string()) + .collect::>() + }; + + let plain = default_resource_attrs(None, None); + assert_eq!(keys(&plain), [SERVICE_NAME, SERVICE_VERSION]); + + let named = default_resource_attrs(Some("svcname-override"), None); + assert_eq!(keys(&named), [SERVICE_VERSION]); + + let attrs = default_resource_attrs( + None, + Some("deployment.environment=prod,service.name=attrs-override"), ); - assert_eq!(cfg.slow_request, Duration::from_millis(500)); + assert_eq!(keys(&attrs), [SERVICE_VERSION]); + + let versioned = default_resource_attrs(None, Some("service.version=9.9.9")); + assert_eq!(keys(&versioned), [SERVICE_NAME]); + + // An empty OTEL_SERVICE_NAME supplies nothing; the SDK ignores it too. + let empty = default_resource_attrs(Some(" "), None); + assert_eq!(keys(&empty), [SERVICE_NAME, SERVICE_VERSION]); } #[test] - fn resolve_uptrace_dsn_splits_endpoint_and_header() { - let cfg = TelemetryConfig::resolve(RawTelemetryArgs { - uptrace_dsn: Some("https://SECRET_TOKEN@api.uptrace.dev".into()), - slow_request_ms: 250, - ..raw() - }) - .unwrap() - .expect("telemetry on"); - assert_eq!(cfg.endpoint, "https://api.uptrace.dev"); - assert_eq!( - cfg.headers, - vec![( - "uptrace-dsn".to_string(), - "https://SECRET_TOKEN@api.uptrace.dev".to_string() - )] - ); - assert_eq!(cfg.slow_request, Duration::from_millis(250)); + fn resolve_rejects_the_removed_uptrace_dsn() { + let err = TelemetryConfig::resolve( + &RawTelemetryArgs { + uptrace_dsn: Some("https://tok@api.uptrace.dev".into()), + ..raw() + }, + OtelEnv::default(), + ) + .unwrap_err() + .to_string(); + assert!(err.contains("--uptrace-dsn"), "{err}"); + assert!(err.contains("OTEL_EXPORTER_OTLP_HEADERS"), "{err}"); } #[test] - fn resolve_dsn_header_leads_explicit_headers() { - let cfg = TelemetryConfig::resolve(RawTelemetryArgs { - uptrace_dsn: Some("https://tok@api.uptrace.dev".into()), - otlp_headers: vec!["x-extra=1".into()], - ..raw() - }) - .unwrap() - .expect("telemetry on"); - assert_eq!(cfg.headers[0].0, "uptrace-dsn"); - assert_eq!(cfg.headers[1], ("x-extra".to_string(), "1".to_string())); + fn resolve_rejects_the_removed_otlp_endpoint() { + let err = TelemetryConfig::resolve( + &RawTelemetryArgs { + otlp_endpoint: Some("https://collector.example.com".into()), + ..raw() + }, + OtelEnv::default(), + ) + .unwrap_err() + .to_string(); + assert!(err.contains("--otlp-endpoint"), "{err}"); + assert!(err.contains("OTEL_EXPORTER_OTLP_ENDPOINT"), "{err}"); } #[test] - fn resolve_rejects_both_endpoint_sources() { - let err = TelemetryConfig::resolve(RawTelemetryArgs { - uptrace_dsn: Some("https://tok@api.uptrace.dev".into()), - otlp_endpoint: Some("https://collector.example.com".into()), - ..raw() - }) + fn resolve_rejects_the_removed_otlp_header() { + let err = TelemetryConfig::resolve( + &RawTelemetryArgs { + otlp_headers: vec!["authorization=Bearer xyz".into()], + ..raw() + }, + OtelEnv::default(), + ) + .unwrap_err() + .to_string(); + assert!(err.contains("--otlp-header"), "{err}"); + assert!(err.contains("OTEL_EXPORTER_OTLP_HEADERS"), "{err}"); + } + + /// A removed option fails even with a correct `OTEL_` endpoint alongside + /// it: the operator's intent is in the flag, and half-applied config is + /// the silent failure this issue removes. + #[test] + fn resolve_rejects_a_removed_option_alongside_a_good_endpoint() { + let err = TelemetryConfig::resolve( + &RawTelemetryArgs { + uptrace_dsn: Some("https://tok@api.uptrace.dev".into()), + ..raw() + }, + generic("https://api.uptrace.dev"), + ) .unwrap_err(); - assert!(err.to_string().contains("mutually exclusive")); - } - - #[test] - fn resolve_rejects_malformed_header() { - let err = TelemetryConfig::resolve(RawTelemetryArgs { - otlp_endpoint: Some("https://collector.example.com".into()), - otlp_headers: vec!["no-equals-sign".into()], - ..raw() - }) - .unwrap_err(); - assert!(err.to_string().contains("key=value")); - } - - #[test] - fn resolve_rejects_dsn_without_scheme() { - let err = TelemetryConfig::resolve(RawTelemetryArgs { - uptrace_dsn: Some("tok@api.uptrace.dev".into()), - ..raw() - }) - .unwrap_err(); - assert!(err.to_string().contains("scheme")); + assert!(err.to_string().contains("removed"), "{err}"); } #[test] From d6261bd5f978efca75d2469b89d48b61907820be Mon Sep 17 00:00:00 2001 From: Andreas Brenner Date: Mon, 27 Jul 2026 00:21:23 +0300 Subject: [PATCH 3/6] ANW-44 Release: bump version to 0.3.0 --- Cargo.lock | 2 +- Cargo.toml | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 3371c27..ac93aba 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -72,7 +72,7 @@ dependencies = [ [[package]] name = "anwesen" -version = "0.2.0" +version = "0.3.0" dependencies = [ "anyhow", "axum", diff --git a/Cargo.toml b/Cargo.toml index a20fc1d..57c7492 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -1,7 +1,7 @@ [package] name = "anwesen" description = "Read-only HTTP daemon over a markdown vault, querying YAML frontmatter." -version = "0.2.0" +version = "0.3.0" edition = "2024" rust-version = "1.95" license = "BSD-3-Clause" From 30bca24b5ccdfc57293780389b524d9e2a5f0304 Mon Sep 17 00:00:00 2001 From: Andreas Brenner Date: Wed, 29 Jul 2026 22:22:12 +0300 Subject: [PATCH 4/6] ANW-45 Serve: exit nonzero when the supervisor tree fails to start Hydra's Application::run logs a start failure and returns normally, so serve exited 0 after the tree never came up. systemd read that as a clean start and Restart=on-failure never retried; anwesen was unreachable on ap for 12 hours with NRestarts=0. Anwesen carries a started flag that start() sets once the supervisor is up, and main exits 1 when it is still false after run() returns. Assumed the flag is the only seam available: run() consumes self and returns (), so the Err is not observable at the call site. Flag if a newer hydra exposes the result. --- src/app.rs | 13 +++++++++++-- src/main.rs | 13 ++++++++++++- tests/serve_start_failure.rs | 33 +++++++++++++++++++++++++++++++++ 3 files changed, 56 insertions(+), 3 deletions(-) create mode 100644 tests/serve_start_failure.rs diff --git a/src/app.rs b/src/app.rs index f3ee5fc..cc4bcf6 100644 --- a/src/app.rs +++ b/src/app.rs @@ -121,6 +121,12 @@ pub struct Anwesen { /// Request-level telemetry handle ([ANW-37]). `None` disables export and /// the request middleware entirely. pub telemetry: Option>, + /// Set once the supervisor tree is up. Hydra's `Application::run` logs a + /// start failure and returns normally, so `serve` cannot tell a clean + /// shutdown from a tree that never came up. `main` reads this after `run` + /// and exits nonzero when it is still false, which is what lets systemd + /// retry ([ANW-45](https://crvrs.youtrack.cloud/issue/ANW-45)). + pub started: Arc, } impl Anwesen { @@ -133,6 +139,7 @@ impl Anwesen { store: NoteStore::new(), health: HealthState::new(), telemetry, + started: Arc::new(AtomicBool::new(false)), } } } @@ -187,10 +194,12 @@ impl Application for Anwesen { .child_spec(), ]; - Supervisor::with_children(children) + let pid = Supervisor::with_children(children) .strategy(SupervisionStrategy::OneForOne) .start_link(SupervisorOptions::new().name("anwesen_root")) - .await + .await?; + self.started.store(true, Ordering::Release); + Ok(pid) } } diff --git a/src/main.rs b/src/main.rs index 4ac8e27..7d7a756 100644 --- a/src/main.rs +++ b/src/main.rs @@ -6,6 +6,7 @@ mod cli; use std::sync::Arc; +use std::sync::atomic::Ordering; use anwesen::app::Anwesen; use anwesen::doctor; @@ -46,12 +47,22 @@ fn main() -> Result<()> { telemetry = telemetry.is_some(), "anwesen serve: starting supervisor tree" ); + let app = Anwesen::new(args.vault, args.bind, telemetry.clone()); + let started = app.started.clone(); // Blocks until the supervisor exits (SIGTERM / SIGINT / crash). - Anwesen::new(args.vault, args.bind, telemetry.clone()).run(); + app.run(); // Flush and shut down exporters after the server loop returns. if let Some(telemetry) = telemetry { telemetry.shutdown(); } + // `run` returns normally whether the tree came up or never + // started, so a failed start would otherwise look like a clean + // exit and systemd's `Restart=on-failure` would not retry + // (ANW-45). Exit nonzero when the tree never came up. + if !started.load(Ordering::Acquire) { + tracing::error!("anwesen serve: supervisor tree failed to start"); + std::process::exit(1); + } } Command::Doctor(args) => { init_logging(args.log_level); diff --git a/tests/serve_start_failure.rs b/tests/serve_start_failure.rs new file mode 100644 index 0000000..4c01948 --- /dev/null +++ b/tests/serve_start_failure.rs @@ -0,0 +1,33 @@ +//! `anwesen serve` must exit nonzero when the supervisor tree fails to start +//! ([ANW-45](https://crvrs.youtrack.cloud/issue/ANW-45)). Hydra's +//! `Application::run` logs the failure and returns normally, so without an +//! explicit check the process exits 0 and systemd's `Restart=on-failure` +//! never retries -- the vault stayed unreachable for 12 hours on ap. +//! +//! The forced failure is a taken bind address: `http_server` binds eagerly in +//! its child spec, so the address-in-use error fails the whole start. + +use std::net::TcpListener; +use std::process::Command; + +#[test] +fn serve_exits_nonzero_when_the_tree_fails_to_start() { + let vault = tempfile::tempdir().expect("tempdir"); + // Hold the port for the lifetime of the child so its bind cannot succeed. + let held = TcpListener::bind("127.0.0.1:0").expect("bind probe port"); + let addr = held.local_addr().expect("probe addr"); + + let status = Command::new(env!("CARGO_BIN_EXE_anwesen")) + .arg("serve") + .arg("--vault") + .arg(vault.path()) + .arg("--bind") + .arg(addr.to_string()) + .status() + .expect("spawn anwesen serve"); + + assert!( + !status.success(), + "serve exited {status} after a failed supervisor start; systemd reads that as a clean exit" + ); +} From 6e07bff08aedc0342097c9d29f1f04379f2a14f6 Mon Sep 17 00:00:00 2001 From: Andreas Brenner Date: Fri, 31 Jul 2026 15:52:50 +0300 Subject: [PATCH 5/6] ANW-43 CLI: add a query subcommand writing the /query JSON offline The README claims the query engine is available offline, but only the merge half was: no subcommand produced the path / frontmatter / last_modified / etag / size projection that GET /query returns. `anwesen query` takes the same --vault and --query flags as merge and writes that document to stdout, compact, one line. src/merge.rs becomes src/oneshot.rs and holds both: one parse-and-load path, so the two subcommands cannot drift in grammar or in how strictly they read a vault. cli.rs shares one VaultQueryArgs between them for the same reason. rfc3339_z moves from http.rs to query.rs, next to the projection whose timestamp dialect it is. Assumed a trailing newline on stdout is wanted here even though merge writes none: the JSON body is one line for jq and shell pipelines, and the newline terminates it rather than joining the document. Flag if wrong. The hurl harness now compares `anwesen query` against GET /query on the fixture vault for four queries before running the suite, so a drift between the two surfaces fails CI. --- README.md | 38 ++++- src/cli.rs | 61 +++++++- src/http.rs | 10 +- src/lib.rs | 2 +- src/main.rs | 21 ++- src/merge.rs | 205 --------------------------- src/oneshot.rs | 354 ++++++++++++++++++++++++++++++++++++++++++++++ src/query.rs | 12 +- tests/run-hurl.sh | 14 ++ 9 files changed, 489 insertions(+), 228 deletions(-) delete mode 100644 src/merge.rs create mode 100644 src/oneshot.rs diff --git a/README.md b/README.md index a7bb236..f51daa3 100644 --- a/README.md +++ b/README.md @@ -22,7 +22,7 @@ Anwesen answers three kinds of question over HTTP: The frontmatter index is built once at startup and kept current by watching the vault directory. The index lives in memory; a restart rebuilds it, and there is nothing on disk to corrupt or migrate. -The same query-and-merge engine also runs offline, with no server: `anwesen merge` walks a directory, evaluates a query, and writes the merged markdown to stdout (see [Local generation](#local-generation)). +The same query-and-merge engine also runs offline, with no server. `anwesen merge` walks a directory, evaluates a query, and writes the merged markdown to stdout; `anwesen query` writes the same JSON document `GET /query` returns (see [Local generation](#local-generation)). ## Quick start @@ -52,6 +52,12 @@ Build one file out of many notes, without starting the daemon: anwesen merge --vault /path/to/vault --query 'tags=adr&__anw-order=title' > ADRs.md ``` +Ask which notes match, and what their frontmatter holds, without starting the daemon: + +``` +anwesen query --vault /path/to/vault --query 'tags=adr' | jq -r '.results[].path' +``` + ## CLI ``` @@ -59,6 +65,7 @@ anwesen serve --vault [--bind ] [--log-level ] [--otlp-slow-request-ms ] anwesen doctor --vault anwesen merge --vault --query +anwesen query --vault --query anwesen version ``` @@ -67,7 +74,7 @@ anwesen version | `--vault ` | `ANWESEN_VAULT` | _required_ | Path to the vault root. | | `--bind ` | `ANWESEN_BIND` | `127.0.0.1:8080` | Listen address for `serve`. | | `--log-level ` | `ANWESEN_LOG_LEVEL` | `info` | `error`, `warn`, `info`, `debug`, or `trace`. | -| `--query ` | -- | _required for `merge`_ | A `/query` query string: frontmatter predicates plus `__anw-` controls. | +| `--query ` | `ANWESEN_QUERY` | empty (match all) | A `/query` query string: frontmatter predicates plus `__anw-` controls. `merge` and `query` only. | | `--otlp-slow-request-ms` | `ANWESEN_OTLP_SLOW_REQUEST_MS` | `500` | Requests at or over this duration, or answering 5xx, also export a span. | Every flag has a matching `ANWESEN_` environment variable. CLI flags win @@ -79,6 +86,7 @@ exported is configured entirely through the standard `OTEL_` variables below. - **`serve`** -- run the daemon: walk the vault, build the index, watch for changes, serve the API. - **`doctor`** -- walk the vault once and report what would stop clean ingestion: unreadable files, unparseable YAML, path collisions on the HTTP surface, and frontmatter type drift (the same key carrying incompatible types across notes). Read-only; non-zero exit if any issue is found. - **`merge`** -- one-shot local generation: walk the vault, evaluate `--query`, and write the merged markdown document to stdout. No server, no HTTP. See [Local generation](#local-generation). +- **`query`** -- the same one-shot walk, writing the JSON document `GET /query` returns: which notes match, and what their frontmatter, `last_modified`, `etag` and `size` hold. No server, no HTTP. See [Local generation](#local-generation). - **`version`** -- print version and exit. ## Telemetry @@ -173,7 +181,7 @@ ISO-8601 dates and RFC 3339 datetimes are coerced to typed dates at read time, s | `__anw-order=[:asc\|:desc]` | path order | Order fragments (merge mode only). | | `__anw-kind=` | off | Refuse a mixed merge unless every matched note shares one value for the key (merge mode only). | -By default `/query` returns metadata only; fetch bodies with `/notes/`. +By default `/query` returns metadata only; fetch bodies with `/notes/`. The same JSON document is available offline, without the daemon, via `anwesen query` (see [Local generation](#local-generation)). #### Markdown-merge mode @@ -201,7 +209,11 @@ Returns vault path, note count, last index/event timestamps, watcher state, an i ## Local generation -`anwesen merge` produces the markdown-merge document on the command line, with no server and no HTTP round-trip. It walks the vault, evaluates the query, and writes the merged document to stdout: +Two subcommands answer a query on the command line, with no server and no HTTP round-trip: `merge` writes the merged markdown document, `query` writes the JSON projection. Both take the same `--vault` and `--query` flags, both walk the vault once, and both run the engine the endpoint runs -- so the output matches what the daemon would have returned for the same vault and query. + +### `merge` + +`anwesen merge` walks the vault, evaluates the query, and writes the merged document to stdout: ``` anwesen merge --vault /path/to/vault --query 'tags=adr&__anw-order=title&__anw-kind=kind' @@ -211,6 +223,24 @@ The `--query` string is the exact `/query` grammar: frontmatter predicates plus This is the materialization path: build a `CLAUDE.md`, a skill bundle, or any single file assembled from many notes, driven from a script or a one-off shell. +### `query` + +`anwesen query` answers the other half: which notes match, and what their frontmatter holds. It writes the same JSON document `GET /query` returns -- `results`, `total`, `truncated`, with `path`, `frontmatter`, `last_modified`, `etag` and `size` per row -- on one line, ready for `jq`: + +``` +anwesen query --vault /path/to/vault --query 'kind=PDR&__anw-limit=1' +``` + +```json +{"results":[{"path":"Projects/PDR-001-intro.md","frontmatter":{"kind":"PDR","num":1,"title":"PDR-001 Intro"},"last_modified":"2026-05-14T17:05:08Z","etag":"\"f657eab5...\"","size":57}],"total":2,"truncated":true} +``` + +`total` counts the full match set; `truncated` says the cap cut it. + +Bodies are elided here as they are on the endpoint; `merge` is the way to get them offline. `__anw-order` and `__anw-kind` are merge-mode controls and do not affect this output. A malformed query or an unreadable vault exits non-zero with the reason on stderr; an empty match set is an empty `results` list and exit `0`. + +A script can therefore move between the daemon and the CLI without a second parser: same shape, same field names, same timestamp dialect. + ## Design notes - **In place, read-only.** Anwesen reads the same directory Obsidian writes to and never writes back. The vault stays editable in Obsidian with no coordination, and there is no write API by design. diff --git a/src/cli.rs b/src/cli.rs index 52e65e4..32bbced 100644 --- a/src/cli.rs +++ b/src/cli.rs @@ -7,9 +7,14 @@ //! [--otlp-slow-request-ms ] //! anwesen doctor --vault [--log-level ] //! anwesen merge --vault [--query ] [--log-level ] +//! anwesen query --vault [--query ] [--log-level ] //! anwesen version //! ``` //! +//! `merge` and `query` differ only in what they write -- the merged markdown +//! document or the `/query` JSON projection ([ANW-43]) -- so they share one +//! [`VaultQueryArgs`] flag set and cannot drift. +//! //! `--bind` and `--otlp-slow-request-ms` are `serve`-only ([ANW-37]); //! `doctor` and `merge` do not bind a port; `version` takes no flags. Each //! flag has a matching `ANWESEN_` environment variable and CLI wins @@ -41,7 +46,11 @@ pub enum Command { Doctor(DoctorArgs), /// Walk the vault once, evaluate the query, and write the merged markdown /// document to stdout. One-shot; no server. Read-only. - Merge(MergeArgs), + Merge(VaultQueryArgs), + /// Walk the vault once, evaluate the query, and write the same JSON + /// document `GET /query` returns to stdout. One-shot; no server. + /// Read-only. + Query(VaultQueryArgs), /// Print the version and exit. Version, } @@ -97,8 +106,9 @@ pub struct DoctorArgs { pub log_level: LogLevel, } +/// Flags shared by the two one-shot subcommands, `merge` and `query`. #[derive(Debug, clap::Args)] -pub struct MergeArgs { +pub struct VaultQueryArgs { /// Path to the vault root. #[arg(long, env = "ANWESEN_VAULT")] pub vault: PathBuf, @@ -106,12 +116,12 @@ pub struct MergeArgs { /// Query in the `/query` query-string grammar, for example /// `tags=anwesen&__anw-kind=skill&__anw-order=order`. The `__anw-kind` /// homogeneity guard and `__anw-order` fragment ordering ride inside this - /// string -- there are no separate flags. Empty merges every note under - /// the vault root. + /// string -- there are no separate flags. `__anw-kind` and `__anw-order` + /// apply to `merge` only. Empty matches every note under the vault root. #[arg(long, env = "ANWESEN_QUERY", default_value = "")] pub query: String, - /// Log verbosity. Logs go to stderr; the merged document goes to stdout. + /// Log verbosity. Logs go to stderr; the document goes to stdout. #[arg(long, env = "ANWESEN_LOG_LEVEL", default_value = "info")] pub log_level: LogLevel, } @@ -271,6 +281,47 @@ mod tests { assert_eq!(err.kind(), clap::error::ErrorKind::UnknownArgument); } + #[test] + fn query_takes_the_same_flags_as_merge() { + let cli = parse(&[ + "query", + "--vault", + "/tmp/v", + "--query", + "tags=anwesen&__anw-limit=5", + "--log-level", + "warn", + ]) + .expect("parse"); + match cli.command { + Command::Query(a) => { + assert_eq!(a.vault, PathBuf::from("/tmp/v")); + assert_eq!(a.query, "tags=anwesen&__anw-limit=5"); + assert!(matches!(a.log_level, LogLevel::Warn)); + } + _ => panic!("expected query"), + } + } + + #[test] + fn query_requires_vault_and_defaults_the_query() { + assert!(parse(&["query"]).is_err()); + match parse(&["query", "--vault", "/tmp/v"]) + .expect("parse") + .command + { + Command::Query(a) => assert_eq!(a.query, ""), + _ => panic!("expected query"), + } + } + + #[test] + fn query_rejects_bind() { + // --bind is serve-only; query does not listen. + let err = parse(&["query", "--vault", "/tmp/v", "--bind", "0.0.0.0:9000"]).unwrap_err(); + assert_eq!(err.kind(), clap::error::ErrorKind::UnknownArgument); + } + #[test] fn version_takes_no_flags() { assert!(matches!( diff --git a/src/http.rs b/src/http.rs index 52d4c0f..1d847a9 100644 --- a/src/http.rs +++ b/src/http.rs @@ -22,7 +22,7 @@ use axum::http::{HeaderMap, HeaderValue, StatusCode}; use axum::middleware::{Next, from_fn, from_fn_with_state}; use axum::response::{IntoResponse, Response}; use axum::routing::get; -use chrono::{DateTime, SecondsFormat, Utc}; +use chrono::{DateTime, Utc}; use http_body::Body as _; use hydra::Process; use serde::Serialize; @@ -32,17 +32,11 @@ use std::path::PathBuf; use crate::app::RestartCounters; use crate::health::HealthState; +use crate::query::rfc3339_z; use crate::store::NoteStore; use crate::telemetry::{self, Telemetry, TraceHeaders}; use crate::vault::{Note, frontmatter_to_json}; -/// Canonical RFC 3339 form with a `Z` suffix -- the shape the User Manual -/// example uses for `last_modified`. Centralized here so every HTTP -/// `last_modified` field stays in the same dialect. -fn rfc3339_z(dt: DateTime) -> String { - dt.to_rfc3339_opts(SecondsFormat::Secs, true) -} - /// Shared state injected into every handler. #[derive(Clone)] pub struct HttpState { diff --git a/src/lib.rs b/src/lib.rs index 59f1689..818b23e 100644 --- a/src/lib.rs +++ b/src/lib.rs @@ -10,7 +10,7 @@ pub mod app; pub mod doctor; pub mod health; pub mod http; -pub mod merge; +pub mod oneshot; pub mod query; pub mod store; pub mod telemetry; diff --git a/src/main.rs b/src/main.rs index 7d7a756..05027d9 100644 --- a/src/main.rs +++ b/src/main.rs @@ -1,6 +1,6 @@ //! Anwesen: read-only HTTP daemon over a markdown vault. //! -//! This module wires the CLI to the `serve`, `doctor`, `merge`, and +//! This module wires the CLI to the `serve`, `doctor`, `merge`, `query`, and //! `version` subcommands. mod cli; @@ -10,7 +10,7 @@ use std::sync::atomic::Ordering; use anwesen::app::Anwesen; use anwesen::doctor; -use anwesen::merge; +use anwesen::oneshot; use anwesen::telemetry::{self, OtelEnv, RawTelemetryArgs, TelemetryConfig}; use anyhow::Result; use clap::Parser; @@ -74,13 +74,26 @@ fn main() -> Result<()> { } Command::Merge(args) => { init_logging(args.log_level); - match merge::run(&args.vault, &args.query) { + match oneshot::merge(&args.vault, &args.query) { // `print!`, not `println!`: the merged document is byte-stable // and byte-identical to the HTTP merge body, which carries no // trailing newline. An empty match set prints nothing, exit 0. Ok(doc) => print!("{doc}"), Err(e) => { - eprint!("{}", e.render()); + eprint!("{}", e.render("merge")); + std::process::exit(1); + } + } + } + Command::Query(args) => { + init_logging(args.log_level); + match oneshot::query_json(&args.vault, &args.query) { + // `println!` here, unlike `merge`: the JSON body carries no + // trailing newline either, but stdout is one document per + // line for the shells and `jq` pipelines this exists for. + Ok(doc) => println!("{doc}"), + Err(e) => { + eprint!("{}", e.render("query")); std::process::exit(1); } } diff --git a/src/merge.rs b/src/merge.rs deleted file mode 100644 index a9b6d2b..0000000 --- a/src/merge.rs +++ /dev/null @@ -1,205 +0,0 @@ -//! One-shot local markdown-merge for the `anwesen merge` subcommand ([ANW-27]). -//! -//! Walks a vault directory once (the same [`vault::scan`] as `doctor`), -//! evaluates the `--query` string, and assembles the merged markdown document -//! with [`query::execute_merge`] -- the very engine the HTTP `/query` merge -//! mode ([ANW-26]) uses. CLI and HTTP output are therefore byte-identical for -//! the same vault and query. No HTTP, no watcher, no persistent index. - -use std::fmt::Write as _; -use std::path::Path; - -use crate::query::{self, MergeError, QueryError}; -use crate::store::NoteStore; -use crate::vault::{self, ScanIssue}; - -/// Why a one-shot merge could not produce a document. -#[derive(Debug)] -pub enum MergeCliError { - /// The `--query` string did not parse. Same grammar, same message as the - /// HTTP `/query` `400`. - Query(QueryError), - /// One or more files could not be read, or their frontmatter did not - /// parse. Same hard-failure posture as `doctor`; soft warnings (e.g. a - /// non-mapping frontmatter root) are ignored, matching what `serve` - /// ingests. - Scan(Vec), - /// The `__anw-kind` homogeneity guard rejected the matched set. The - /// `String` is the same naming message the HTTP path returns as `400`, - /// surfaced here on stderr instead. - Kind(String), -} - -impl MergeCliError { - /// Render the error for stderr. One concern per line, deterministic so the - /// stderr surface is golden-testable. - #[must_use] - pub fn render(&self) -> String { - match self { - Self::Query(e) => format!("{e}\n"), - Self::Scan(issues) => { - let mut s = String::from("merge: cannot read vault\n"); - for issue in issues { - let _ = writeln!(s, " {}: {}", issue.path.display(), issue.kind); - } - s - } - Self::Kind(msg) => msg.clone(), - } - } -} - -/// Walk `vault_root`, evaluate `raw_query`, and return the merged document. -/// -/// On success the returned `String` is byte-identical to the HTTP merge body -/// for the same vault and query. An empty match set yields an empty string. -/// -/// # Errors -/// - [`MergeCliError::Query`] when `raw_query` is malformed; -/// - [`MergeCliError::Scan`] when the directory is unreadable or any file's -/// frontmatter fails to parse; -/// - [`MergeCliError::Kind`] when the `__anw-kind` homogeneity guard fails. -pub fn run(vault_root: &Path, raw_query: &str) -> Result { - let parsed = query::parse(raw_query).map_err(MergeCliError::Query)?; - - let scan = vault::scan(vault_root); - if !scan.issues.is_empty() { - return Err(MergeCliError::Scan(scan.issues)); - } - - // The merge engine reads from a NoteStore exactly as the HTTP path does; - // a one-shot `replace` is the whole "index" this subcommand needs. - let store = NoteStore::new(); - store.replace(scan.notes); - - query::execute_merge(&store, &parsed) - .map_err(|MergeError::KindGuard(msg)| MergeCliError::Kind(msg)) -} - -#[cfg(test)] -mod tests { - use super::*; - use std::fs; - use std::path::Path; - use tempfile::TempDir; - - fn write(root: &Path, rel: &str, body: &str) { - let p = root.join(rel); - if let Some(parent) = p.parent() { - fs::create_dir_all(parent).unwrap(); - } - fs::write(p, body).unwrap(); - } - - #[test] - fn merges_bodies_with_source_markers() { - let tmp = TempDir::new().unwrap(); - write(tmp.path(), "a.md", "---\nnum: 1\n---\nalpha\n"); - write(tmp.path(), "b.md", "---\nnum: 2\n---\nbeta\n"); - let out = run(tmp.path(), "").unwrap(); - // Body is frontmatter-stripped; fragments join with a blank line and - // there is no trailing newline -- byte-identical to the HTTP body. - assert_eq!( - out, - "\nalpha\n\n\n\nbeta\n" - ); - } - - #[test] - fn order_desc_then_path_tiebreak() { - let tmp = TempDir::new().unwrap(); - write(tmp.path(), "a.md", "---\nnum: 1\n---\nlow\n"); - write(tmp.path(), "b.md", "---\nnum: 3\n---\nhigh\n"); - write(tmp.path(), "c.md", "---\nnum: 2\n---\nmid\n"); - let out = run(tmp.path(), "__anw-order=num:desc").unwrap(); - let bodies: Vec<&str> = out - .lines() - .filter(|l| !l.starts_with("\nalpha\n\n\n\nbeta\n" + ); + } + + #[test] + fn order_desc_then_path_tiebreak() { + let tmp = TempDir::new().unwrap(); + write(tmp.path(), "a.md", "---\nnum: 1\n---\nlow\n"); + write(tmp.path(), "b.md", "---\nnum: 3\n---\nhigh\n"); + write(tmp.path(), "c.md", "---\nnum: 2\n---\nmid\n"); + let out = merge(tmp.path(), "__anw-order=num:desc").unwrap(); + let bodies: Vec<&str> = out + .lines() + .filter(|l| !l.starts_with("