diff --git a/.cargo/config.toml b/.cargo/config.toml index 1302091e0..bc8c20d71 100644 --- a/.cargo/config.toml +++ b/.cargo/config.toml @@ -26,10 +26,10 @@ test_details = "test --target aarch64-apple-darwin" # native crate needs no change here. Axum (native), Cloudflare # (wasm32-unknown-unknown), Spin, the CLI (native), and integration-tests # (native) are simply not listed. -build-fastly = "build -p trusted-server-core -p trusted-server-adapter-fastly -p trusted-server-js -p trusted-server-openrtb --target wasm32-wasip1" -check-fastly = "check -p trusted-server-core -p trusted-server-adapter-fastly -p trusted-server-js -p trusted-server-openrtb --target wasm32-wasip1" -clippy-fastly = "clippy -p trusted-server-core -p trusted-server-adapter-fastly -p trusted-server-js -p trusted-server-openrtb --all-targets --all-features --target wasm32-wasip1 -- -D warnings" -test-fastly = "test -p trusted-server-core -p trusted-server-adapter-fastly -p trusted-server-js -p trusted-server-openrtb --target wasm32-wasip1" +build-fastly = "build -p trusted-server-core -p trusted-server-adapter-fastly -p trusted-server-device-fastly -p trusted-server-geo-fastly -p trusted-server-js -p trusted-server-openrtb --target wasm32-wasip1" +check-fastly = "check -p trusted-server-core -p trusted-server-adapter-fastly -p trusted-server-device-fastly -p trusted-server-geo-fastly -p trusted-server-js -p trusted-server-openrtb --target wasm32-wasip1" +clippy-fastly = "clippy -p trusted-server-core -p trusted-server-adapter-fastly -p trusted-server-device-fastly -p trusted-server-geo-fastly -p trusted-server-js -p trusted-server-openrtb --all-targets --all-features --target wasm32-wasip1 -- -D warnings" +test-fastly = "test -p trusted-server-core -p trusted-server-adapter-fastly -p trusted-server-device-fastly -p trusted-server-geo-fastly -p trusted-server-js -p trusted-server-openrtb --target wasm32-wasip1" # --- Axum adapter (native dev server) --- build-axum = "build -p trusted-server-adapter-axum" diff --git a/CLAUDE.md b/CLAUDE.md index 546a3bf52..53b50a6d2 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -20,6 +20,10 @@ crates/ trusted-server-adapter-cloudflare/ # Cloudflare Workers entry point (wasm32-unknown-unknown binary) trusted-server-adapter-spin/ # Fermyon Spin entry point (wasm32-wasip1 component) trusted-server-cli/ # Host-target `ts` operator CLI + device/ + fastly/ # trusted-server-device-fastly (opt-in TLS/H2 device provider) + edgecookie/ # vendor Edge Cookie provider crates (built-in HMAC default is in core) + geo/ # vendor geo provider crates (host geo is injected by the adapter) trusted-server-js/ # TypeScript/JS build — per-integration IIFE bundles lib/ # TS source, Vitest tests, esbuild pipeline ``` @@ -58,7 +62,9 @@ fastly compute serve # Deploy to Fastly fastly compute publish -# Run Axum dev server (native — no Viceroy) +# Run Axum dev server (native — no Viceroy). Settings load at runtime from the +# platform config store on every adapter; publish an operator config with +# `ts config push` (see trusted-server.example.toml for the template). cargo run -p trusted-server-adapter-axum # Test Axum adapter only @@ -142,6 +148,20 @@ cd crates/trusted-server-js/lib && node build-all.mjs cargo install viceroy --version 0.17.0 --locked --force ``` +### Windows (use WSL for the Linux-only tests) + +The Rust adapter tests run natively on Windows through the cargo aliases +(`cargo test-fastly` via Viceroy, `cargo test-axum`, `cargo test-cloudflare`), +and CI runs these on both `ubuntu-latest` and `windows-latest`. + +The Docker-based integration suite (`scripts/integration-tests.sh`) and the +Cloudflare worker build (`crates/trusted-server-adapter-cloudflare/build.sh`, +which uses `worker-build` + `wrangler dev`) are Linux tools. On Windows run them +inside WSL (Ubuntu) with Docker Desktop's WSL integration enabled. Provision the +WSL distro with the same toolchain as `.tool-versions` (rustup + the +`wasm32-wasip1` / `wasm32-unknown-unknown` targets, Node, Viceroy, wrangler), then +run the scripts from a clone on the WSL native filesystem for fast builds. + --- ## Coding Conventions @@ -269,12 +289,34 @@ impl core::error::Error for MyError {} ## Other guidelines +- Use US English spelling everywhere: code, identifiers, comments, + documentation, tests, commit messages, and configuration. For example, write + `color`, `behavior`, and `optimize`, not `colour`, `behaviour`, or `optimise`. + Where a term comes from an external source (for example the IAB TCF purpose + names), match that source's spelling even when it is not US English. - Use only example or fictional information in comments, tests, docs, examples, and similar non-runtime materials. (eg. for urls use: example.com domains only) - Do not write or commit real domains, customer names, credentials, configuration values, or other potentially sensitive real-world information in comments, tests, docs, or examples. +### Permission model terminology + +Permissions are the primitive. A provider declares the permissions it requires +(`required_permissions`) and the system decides whether each is _set_. Consent +is only one of several ways a permission may be established. Country or +jurisdiction rules (a `Granted` group baseline), legitimate interest, or +configuration can set a permission with no consent at all. + +- A provider that needs nothing **requires no permission**. Never write that it + "runs without any consent". +- A gated provider **runs once its required permissions are set**, by whatever + method. +- Reserve "consent" for the consent subsystem (`consent/`, `ConsentContext`, + GDPR and TCF strings) where it genuinely means a consent signal. In the + permission layer prefer "permission", "set" / "unset", and "signal" (consent + is one kind of signal, alongside privacy and opt-out signals). + --- ## Git Commit Conventions @@ -291,6 +333,41 @@ Bad: `"fix: added feature flags"` --- +## Provider Architecture + +Each vendor-differentiated capability is pluggable behind its own trait, so a +deployment selects an implementation and the core stays neutral: + +| Capability | Trait | Selector | Built-in (core) | Vendor / host crates | +| --------------------- | ---------------------------------------- | ------------------- | --------------------------------------- | ---------------------------- | +| Edge Cookie identity | `EdgeCookieProvider` (`ec/provider.rs`) | `[ec] provider` | HMAC, client-fixed (opt-in, no default) | `crates/edgecookie/` | +| Device detection | `DeviceProvider` (`ec/device.rs`) | `[device] provider` | User-Agent only (default) | `crates/device/` | +| Geo / IP intelligence | `PlatformGeo` (`platform/traits.rs`) | `[geo] provider` | Disabled, no location (default) | `crates/geo/` | + +Principles for adding or changing a provider: + +- **Core stays neutral.** The trait and the host-neutral default live in + `trusted-server-core`. Host-specific and vendor implementations live in their + own crates and are injected by the adapter (for example `build_device_provider` + and `build_geo_provider`), so core never depends on a host SDK or a vendor, and + the default request path makes no host-specific calls. +- **Providers read request evidence, not a fixed parameter set.** A provider must + be able to see everything about the request it needs (User-Agent, headers, and + host signals such as the TLS JA4 and HTTP/2 fingerprints) through an evidence + abstraction rather than a hard-coded struct of fields. Host signals come from + the host (the Fastly SDK) and are opt-in, so a neutral provider triggers no + host fingerprint calls. +- **Providers are separated by capability but composed per request, and one may + need another's output.** Geo resolves the country and region the permission + model uses, and the permission model gates whether the Edge Cookie provider + runs. Device signals gate Edge Cookie writes (the browser / bot gate). When + several vendor providers share a backend (for example a vendor's Edge Cookie, + geo, and device provider on one cloud pipeline) they share a single call per + request rather than calling independently. Give a provider the inputs and + upstream results it needs explicitly, rather than having it reach into globals. + +--- + ## Integration System Integrations register in Rust via: @@ -324,7 +401,7 @@ IntegrationRegistration::builder(ID) | --------------------- | ---------------------------------------------------------- | | `edgezero.toml` | EdgeZero app/platform manifest and logical stores | | `fastly.toml` | Fastly service configuration and build settings | -| `trusted-server.example.toml` | Source-controlled Trusted Server app-config template | +| `trusted-server.example.toml` | Source-controlled app-config template (includes the `[ec]` / `[geo]` / `[device]` provider selectors and `[geo] default_country`) | | `trusted-server.toml` | Operator-owned app config; gitignored; `ts config push` publishes it as an EdgeZero blob envelope | | `rust-toolchain.toml` | Pins Rust version to 1.95.0 | | `.env.dev` | Local development environment variables | diff --git a/Cargo.lock b/Cargo.lock index e29380b77..cf55eed9f 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -4567,6 +4567,19 @@ dependencies = [ "syn 2.0.118", ] +[[package]] +name = "serde_yaml_ng" +version = "0.10.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7b4db627b98b36d4203a7b458cf3573730f2bb591b28871d916dfa9efabfd41f" +dependencies = [ + "indexmap 2.14.0", + "itoa", + "ryu", + "serde", + "unsafe-libyaml", +] + [[package]] name = "servo_arc" version = "0.4.3" @@ -5376,6 +5389,8 @@ dependencies = [ "serde_json", "sha2 0.10.9", "trusted-server-core", + "trusted-server-device-fastly", + "trusted-server-geo-fastly", "url", "urlencoding", ] @@ -5475,6 +5490,7 @@ dependencies = [ "regex", "serde", "serde_json", + "serde_yaml_ng", "sha2 0.10.9", "subtle", "temp-env", @@ -5489,6 +5505,23 @@ dependencies = [ "web-time", ] +[[package]] +name = "trusted-server-device-fastly" +version = "0.1.0" +dependencies = [ + "fastly", + "trusted-server-core", +] + +[[package]] +name = "trusted-server-geo-fastly" +version = "0.1.0" +dependencies = [ + "error-stack", + "fastly", + "trusted-server-core", +] + [[package]] name = "trusted-server-integration-tests" version = "0.1.0" @@ -5629,6 +5662,12 @@ dependencies = [ "subtle", ] +[[package]] +name = "unsafe-libyaml" +version = "0.2.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "673aac59facbab8a9007c7f6108d11f63b603f7cabff99fabf650fea5c32b861" + [[package]] name = "untrusted" version = "0.9.0" diff --git a/Cargo.toml b/Cargo.toml index 25c367181..2bb4b91c3 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -1,6 +1,8 @@ [workspace] resolver = "2" members = [ + "crates/device/fastly", + "crates/geo/fastly", "crates/trusted-server-adapter-axum", "crates/trusted-server-adapter-cloudflare", "crates/trusted-server-adapter-fastly", @@ -95,6 +97,7 @@ rustls-pemfile = "2" scraper = "0.24.0" serde = { version = "1.0", features = ["derive"] } serde_json = "1.0.149" +serde_yaml_ng = "0.10" sha2 = "0.10.9" simple_logger = "5" spin-sdk = { version = "~6.0", default-features = false, features = ["http", "key-value", "variables"] } @@ -109,6 +112,8 @@ toml = "1.1" toml_edit = "0.23.10" tower = "0.4" trusted-server-core = { path = "crates/trusted-server-core" } +trusted-server-device-fastly = { path = "crates/device/fastly" } +trusted-server-geo-fastly = { path = "crates/geo/fastly" } trusted-server-js = { path = "crates/trusted-server-js" } trusted-server-openrtb = { path = "crates/trusted-server-openrtb" } url = "2.5.8" diff --git a/crates/device/README.md b/crates/device/README.md new file mode 100644 index 000000000..3aa4cb04a --- /dev/null +++ b/crates/device/README.md @@ -0,0 +1,10 @@ +# Device providers + +Device-detection provider crates live here, one per vendor. The Fastly provider +(`trusted-server-device-fastly`) classifies a request with the host's TLS and +HTTP/2 fingerprints; future vendor providers (for example +`crates/device/`) slot in alongside it. + +The built-in default provider (User-Agent only) ships in `trusted-server-core` +(`ec::device`). Adapters select and inject the vendor provider via +`build_device_provider`. diff --git a/crates/device/fastly/Cargo.toml b/crates/device/fastly/Cargo.toml new file mode 100644 index 000000000..3ff1b6e5e --- /dev/null +++ b/crates/device/fastly/Cargo.toml @@ -0,0 +1,18 @@ +[package] +name = "trusted-server-device-fastly" +description = "Fastly host device provider exposing opt-in TLS and HTTP/2 signals." +authors = { workspace = true } +edition = { workspace = true } +license = { workspace = true } +publish = { workspace = true } +version = { workspace = true } + +[lib] +doctest = false + +[lints] +workspace = true + +[dependencies] +trusted-server-core = { workspace = true } +fastly = { workspace = true } diff --git a/crates/device/fastly/src/lib.rs b/crates/device/fastly/src/lib.rs new file mode 100644 index 000000000..822e4cc37 --- /dev/null +++ b/crates/device/fastly/src/lib.rs @@ -0,0 +1,97 @@ +//! The Fastly device provider and host-signal capture. +//! +//! [`FastlyDeviceProvider`] strengthens the built-in User-Agent classification +//! with the host's TLS (JA4) and HTTP/2 fingerprints, for deployments on Fastly +//! Compute. It is selected by `[device] provider = "fastly"` and wired in by the +//! Fastly adapter, which injects the request info and the captured host signals. +//! +//! [`FastlyHostSignals`] captures those fingerprints from a live Fastly request +//! (`get_tls_ja4()`, `get_client_h2_fingerprint()`) into owned values, so it can +//! be shared as an injected [`HostSignals`] service that outlives the borrow of +//! the request. Capturing through the SDK is why this crate depends on the +//! `fastly` crate and builds only for the `wasm32-wasip1` target; off-host the +//! accessors return `None`, so classification degrades to User-Agent only. The +//! platform-neutral [`HostSignals`], [`RequestInfo`], and [`DeviceProvider`] +//! traits and the built-in default live in `trusted-server-core`, where the +//! `DeviceSignals` classification logic stays unit-tested. + +use std::sync::Arc; + +use fastly::Request as FastlyRequest; +use trusted_server_core::ec::device::{DeviceProvider, DeviceSignals}; +use trusted_server_core::evidence::{HostSignals, RequestInfo}; + +/// Host-computed client fingerprints captured from a live Fastly request. +/// +/// Reads the TLS JA4 and HTTP/2 fingerprints once through the Fastly SDK and +/// owns them, so the value can be injected as a [`HostSignals`] service that +/// outlives the borrow of the request it was captured from. Off-host the SDK +/// accessors return `None`, so the signals are simply absent. +#[derive(Debug, Clone, Default)] +pub struct FastlyHostSignals { + ja4: Option, + h2: Option, +} + +impl FastlyHostSignals { + /// Builds host signals from already-captured fingerprint values. + /// + /// Use this when the adapter has read the fingerprints once (for example + /// into the client metadata, or from the trusted internal headers the entry + /// point injects) and wants to share them without another SDK call. + #[must_use] + pub fn new(ja4: Option, h2: Option) -> Self { + Self { ja4, h2 } + } + + /// Captures the TLS JA4 and HTTP/2 fingerprints from a live Fastly request. + #[must_use] + pub fn from_request(req: &FastlyRequest) -> Self { + Self { + ja4: req.get_tls_ja4().map(str::to_string), + h2: req.get_client_h2_fingerprint().map(str::to_string), + } + } +} + +impl HostSignals for FastlyHostSignals { + fn ja4(&self) -> Option<&str> { + self.ja4.as_deref() + } + + fn h2(&self) -> Option<&str> { + self.h2.as_deref() + } +} + +/// The Fastly device provider, opt-in via `[device] provider = "fastly"`. +/// +/// Classifies a request with the fingerprint-strengthened +/// [`DeviceSignals::derive`], reading the User-Agent from its injected +/// [`RequestInfo`] and the TLS/HTTP-2 fingerprints from its injected +/// [`HostSignals`], so the browser/bot gate is backed by the live request. +pub struct FastlyDeviceProvider { + host_signals: Arc, +} + +impl FastlyDeviceProvider { + /// Creates the provider with its injected host signals. + #[must_use] + pub fn new(host_signals: Arc) -> Self { + Self { host_signals } + } +} + +impl DeviceProvider for FastlyDeviceProvider { + fn id(&self) -> &'static str { + "fastly" + } + + fn detect(&self, request_info: &dyn RequestInfo) -> DeviceSignals { + DeviceSignals::derive( + request_info.user_agent(), + self.host_signals.ja4(), + self.host_signals.h2(), + ) + } +} diff --git a/crates/edgecookie/README.md b/crates/edgecookie/README.md new file mode 100644 index 000000000..186b8c304 --- /dev/null +++ b/crates/edgecookie/README.md @@ -0,0 +1,9 @@ +# Edge Cookie providers + +Vendor Edge Cookie provider crates live here, one per vendor, for example +`crates/edgecookie/`. Each implements the `EdgeCookieProvider` trait +from `trusted-server-core` and is wired in by an adapter. + +The built-in default provider (HMAC over the client IP) ships in +`trusted-server-core` (`ec::provider`), so no crate is needed for it. This +directory is a placeholder until a vendor provider is added. diff --git a/crates/fastly.toml b/crates/fastly.toml new file mode 100644 index 000000000..718e87ad3 --- /dev/null +++ b/crates/fastly.toml @@ -0,0 +1,13 @@ +# Minimal Viceroy config for testing crates nested one level deeper than the +# adapters (for example `crates/device/fastly` and `crates/geo/fastly`). +# +# The shared wasm test runner in `.cargo/config.toml` starts Viceroy with +# `-C ../../fastly.toml`, resolved from the crate directory. For a two-level +# crate such as `crates/trusted-server-adapter-fastly` that reaches the +# repository root manifest. For a three-level crate it resolves here, to +# `crates/fastly.toml`. These crates' unit tests use no backends, KV stores, +# or dictionaries, only a manifest Viceroy can start from. +manifest_version = 3 +name = "trusted-server-nested-crate-tests" + +[local_server] diff --git a/crates/geo/README.md b/crates/geo/README.md new file mode 100644 index 000000000..f3c5d11fb --- /dev/null +++ b/crates/geo/README.md @@ -0,0 +1,20 @@ +# Geo providers + +Geo and IP-intelligence provider crates live here, one per implementation, each +implementing the `PlatformGeo` trait from `trusted-server-core`: + +- `crates/geo/fastly` (`trusted-server-geo-fastly`) is the host platform geo + provider for Fastly Compute, wrapping Fastly's `geo_lookup`. The Fastly adapter + injects it via `build_geo_provider`. It depends on the Fastly SDK, so it builds + only for `wasm32-wasip1`. +- Vendor geo providers (for example `crates/geo/`) will live alongside + it, one per vendor, selected by the `[geo] provider` setting. + +Whatever the source, a provider returns the same `GeoInfo` coding. The country +is an ISO 3166-1 alpha-2 code (`US`) and the region is the ISO 3166-2 subdivision +code with no country prefix (`CA`), so the Fastly and other providers feed the +same downstream rules without translation. + +The platform-neutral `PlatformGeo` trait and the `DisabledGeo` default (no +location) both live in `trusted-server-core`, so the default deployment resolves +no location until a provider is selected. diff --git a/crates/geo/fastly/Cargo.toml b/crates/geo/fastly/Cargo.toml new file mode 100644 index 000000000..d1e3c4f7c --- /dev/null +++ b/crates/geo/fastly/Cargo.toml @@ -0,0 +1,19 @@ +[package] +name = "trusted-server-geo-fastly" +description = "Fastly host geo provider backed by the Fastly geolocation API." +authors = { workspace = true } +edition = { workspace = true } +license = { workspace = true } +publish = { workspace = true } +version = { workspace = true } + +[lib] +doctest = false + +[lints] +workspace = true + +[dependencies] +trusted-server-core = { workspace = true } +error-stack = { workspace = true } +fastly = { workspace = true } diff --git a/crates/geo/fastly/src/lib.rs b/crates/geo/fastly/src/lib.rs new file mode 100644 index 000000000..a93f7dd72 --- /dev/null +++ b/crates/geo/fastly/src/lib.rs @@ -0,0 +1,45 @@ +//! The Fastly host geo provider. +//! +//! [`FastlyPlatformGeo`] implements [`PlatformGeo`] using Fastly's `geo_lookup`, +//! for deployments on Fastly Compute. It is the host platform's geo provider, +//! injected by the Fastly adapter via `build_geo_provider`; selecting a vendor +//! geo provider replaces it. +//! +//! Unlike the pure-logic device provider, this crate calls the Fastly geo SDK +//! directly, so it depends on the `fastly` crate and builds only for the +//! `wasm32-wasip1` target. The platform-neutral `PlatformGeo` trait and the +//! `DisabledGeo` default both live in `trusted-server-core`. + +use std::net::IpAddr; + +use error_stack::Report; +use fastly::geo::{Geo, geo_lookup}; +use trusted_server_core::platform::{GeoInfo, PlatformError, PlatformGeo}; + +/// Convert a Fastly [`Geo`] value into a platform-neutral [`GeoInfo`]. +fn geo_from_fastly(geo: &Geo) -> GeoInfo { + GeoInfo { + city: geo.city().to_string(), + country: geo.country_code().to_string(), + continent: format!("{:?}", geo.continent()), + latitude: geo.latitude(), + longitude: geo.longitude(), + metro_code: geo.metro_code(), + region: geo.region().map(str::to_string), + asn: None, + } +} + +/// Fastly geo-lookup implementation of [`PlatformGeo`]. +/// +/// The host platform geo provider for Fastly Compute. The adapter injects it via +/// `build_geo_provider`; selecting a vendor geo provider replaces it. +pub struct FastlyPlatformGeo; + +impl PlatformGeo for FastlyPlatformGeo { + fn lookup(&self, client_ip: Option) -> Result, Report> { + Ok(client_ip + .and_then(geo_lookup) + .map(|geo| geo_from_fastly(&geo))) + } +} diff --git a/crates/trusted-server-adapter-axum/src/app.rs b/crates/trusted-server-adapter-axum/src/app.rs index 4b71d07ce..b82561ce2 100644 --- a/crates/trusted-server-adapter-axum/src/app.rs +++ b/crates/trusted-server-adapter-axum/src/app.rs @@ -133,7 +133,7 @@ where F: FnOnce(Arc, RuntimeServices, Request) -> Fut, Fut: Future>>, { - let services = build_runtime_services(&ctx); + let services = build_runtime_services(&ctx, &state.settings); let mut req = ctx.into_request(); if let Err(error) = trusted_server_core::integrations::gpt_diagnostics::prepare_request( &state.settings, @@ -160,18 +160,10 @@ where /// malformed consent string is logged and falls back to the default /// (fail-closed) context rather than being silently swallowed. fn build_ec_context(state: &AppState, services: &RuntimeServices, req: &Request) -> EcContext { - let geo_info = services - .geo() - .lookup(services.client_info().client_ip) - .unwrap_or_else(|e| { - log::warn!("geo lookup failed: {e}"); - None - }); - EcContext::read_from_request_with_geo(&state.settings, req, services, geo_info.as_ref()) - .unwrap_or_else(|e| { - log::warn!("EC context read failed: {e:?}"); - EcContext::default() - }) + EcContext::read_from_request_resolving_geo(&state.settings, req, services).unwrap_or_else(|e| { + log::warn!("EC context read failed: {e:?}"); + EcContext::default() + }) } // --------------------------------------------------------------------------- diff --git a/crates/trusted-server-adapter-axum/src/middleware.rs b/crates/trusted-server-adapter-axum/src/middleware.rs index 45cbedc2c..8289563af 100644 --- a/crates/trusted-server-adapter-axum/src/middleware.rs +++ b/crates/trusted-server-adapter-axum/src/middleware.rs @@ -135,7 +135,14 @@ mod tests { proxy_secret = "unit-test-proxy-secret" [ec] + provider = "hmac" + + [ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" + + [geo] + default_country = "FR" + assume_single_jurisdiction = true "#, ) .expect("should load test settings"); diff --git a/crates/trusted-server-adapter-axum/src/platform.rs b/crates/trusted-server-adapter-axum/src/platform.rs index a511daab2..4886bd6e4 100644 --- a/crates/trusted-server-adapter-axum/src/platform.rs +++ b/crates/trusted-server-adapter-axum/src/platform.rs @@ -533,7 +533,10 @@ impl PlatformHttpClient for AxumPlatformHttpClient { /// KV store is [`trusted_server_core::platform::UnavailableKvStore`] — any route /// touching synthetic-ID or consent KV will degrade gracefully. A `warn` log is /// emitted once per process. -pub fn build_runtime_services(ctx: &edgezero_core::context::RequestContext) -> RuntimeServices { +pub fn build_runtime_services( + ctx: &edgezero_core::context::RequestContext, + settings: &trusted_server_core::settings::Settings, +) -> RuntimeServices { static KV_WARNED: std::sync::OnceLock<()> = std::sync::OnceLock::new(); KV_WARNED.get_or_init(|| { log::warn!( @@ -578,9 +581,12 @@ pub fn build_runtime_services(ctx: &edgezero_core::context::RequestContext) -> R // API-route integration flow by reusing a poisoned connection after a // truncated POST. Revisit pooling if profiling shows allocation cost. .http_client(Arc::new(AxumPlatformHttpClient::new())) - .geo(Arc::clone(GEO.get_or_init(|| { - Arc::new(AxumPlatformGeo) as Arc - }))) + // Route through the [geo] provider selector like the Fastly adapter, + // so the selector behaves the same on every adapter. + .geo(trusted_server_core::platform::build_geo_provider( + settings, + Arc::clone(GEO.get_or_init(|| Arc::new(AxumPlatformGeo) as Arc)), + )) .client_info(ClientInfo { client_ip, tls_protocol: None, diff --git a/crates/trusted-server-adapter-axum/tests/routes.rs b/crates/trusted-server-adapter-axum/tests/routes.rs index ed199e6bf..093268568 100644 --- a/crates/trusted-server-adapter-axum/tests/routes.rs +++ b/crates/trusted-server-adapter-axum/tests/routes.rs @@ -33,7 +33,14 @@ fn test_router() -> edgezero_core::router::RouterService { proxy_secret = "integration-test-proxy-secret" [ec] + provider = "hmac" + + [ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" + + [geo] + default_country = "FR" + assume_single_jurisdiction = true "#, ) .expect("should parse route test settings"); diff --git a/crates/trusted-server-adapter-cloudflare/src/app.rs b/crates/trusted-server-adapter-cloudflare/src/app.rs index 86ac86987..fc8d7d24e 100644 --- a/crates/trusted-server-adapter-cloudflare/src/app.rs +++ b/crates/trusted-server-adapter-cloudflare/src/app.rs @@ -127,8 +127,8 @@ fn build_state_with_settings( // Per-request RuntimeServices // --------------------------------------------------------------------------- -fn build_per_request_services(ctx: &RequestContext) -> RuntimeServices { - build_runtime_services(ctx) +fn build_per_request_services(ctx: &RequestContext, settings: &Settings) -> RuntimeServices { + build_runtime_services(ctx, settings) } /// Builds the geo-aware [`EcContext`] for consent-gated endpoints (`/auction`, @@ -140,18 +140,10 @@ fn build_per_request_services(ctx: &RequestContext) -> RuntimeServices { /// consent string is logged and falls back to the default (fail-closed) context /// rather than being silently swallowed. fn build_ec_context(settings: &Settings, services: &RuntimeServices, req: &Request) -> EcContext { - let geo_info = services - .geo() - .lookup(services.client_info().client_ip) - .unwrap_or_else(|e| { - log::warn!("geo lookup failed: {e}"); - None - }); - EcContext::read_from_request_with_geo(settings, req, services, geo_info.as_ref()) - .unwrap_or_else(|e| { - log::warn!("EC context read failed: {e:?}"); - EcContext::default() - }) + EcContext::read_from_request_resolving_geo(settings, req, services).unwrap_or_else(|e| { + log::warn!("EC context read failed: {e:?}"); + EcContext::default() + }) } // --------------------------------------------------------------------------- @@ -178,7 +170,7 @@ where let s = Arc::clone(&state); let f = f.clone(); Box::pin(async move { - let services = build_per_request_services(&ctx); + let services = build_per_request_services(&ctx, &s.settings); let mut req = ctx.into_request(); if let Err(error) = trusted_server_core::integrations::gpt_diagnostics::prepare_request( &s.settings, @@ -376,7 +368,7 @@ fn build_router(state: &Arc) -> RouterService { state: Arc, ctx: RequestContext, ) -> Result { - let services = build_per_request_services(&ctx); + let services = build_per_request_services(&ctx, &state.settings); let mut req = ctx.into_request(); if let Some(response) = deny_admin_diagnostic_fallback(&req) { return Ok(response); diff --git a/crates/trusted-server-adapter-cloudflare/src/middleware.rs b/crates/trusted-server-adapter-cloudflare/src/middleware.rs index 5b605bcff..d857b68dd 100644 --- a/crates/trusted-server-adapter-cloudflare/src/middleware.rs +++ b/crates/trusted-server-adapter-cloudflare/src/middleware.rs @@ -151,7 +151,14 @@ mod tests { proxy_secret = "unit-test-proxy-secret" [ec] + provider = "hmac" + + [ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" + + [geo] + default_country = "FR" + assume_single_jurisdiction = true "#, ) .expect("should load test settings"); diff --git a/crates/trusted-server-adapter-cloudflare/src/platform.rs b/crates/trusted-server-adapter-cloudflare/src/platform.rs index fff0bfed1..658915b73 100644 --- a/crates/trusted-server-adapter-cloudflare/src/platform.rs +++ b/crates/trusted-server-adapter-cloudflare/src/platform.rs @@ -598,7 +598,10 @@ impl PlatformSecretStore for CloudflareSecretStoreAdapter { /// Geo information is read from Cloudflare's injected request headers /// (`cf-ipcountry`, etc.) which are present on all plans; headers absent on /// the native host target simply produce empty/zero defaults. -pub fn build_runtime_services(ctx: &edgezero_core::context::RequestContext) -> RuntimeServices { +pub fn build_runtime_services( + ctx: &edgezero_core::context::RequestContext, + settings: &trusted_server_core::settings::Settings, +) -> RuntimeServices { let client_ip = extract_client_ip(ctx); #[cfg(target_arch = "wasm32")] @@ -633,7 +636,9 @@ pub fn build_runtime_services(ctx: &edgezero_core::context::RequestContext) -> R // Geo: read Cloudflare-injected headers — no #[cfg] needed; headers are // simply absent on the native host target, producing Ok(None) from lookup(). - let geo = build_geo(ctx); + // Routed through the [geo] provider selector like the Fastly adapter, so + // the selector behaves the same on every adapter. + let geo = trusted_server_core::platform::build_geo_provider(settings, Arc::new(build_geo(ctx))); RuntimeServices::builder() .config_store(config_store) @@ -641,7 +646,7 @@ pub fn build_runtime_services(ctx: &edgezero_core::context::RequestContext) -> R .kv_store(kv_store) .backend(Arc::new(NoopBackend)) .http_client(http_client) - .geo(Arc::new(geo)) + .geo(geo) .client_info(ClientInfo { client_ip, tls_protocol: None, diff --git a/crates/trusted-server-adapter-cloudflare/tests/routes.rs b/crates/trusted-server-adapter-cloudflare/tests/routes.rs index fb498ce4e..a678c6683 100644 --- a/crates/trusted-server-adapter-cloudflare/tests/routes.rs +++ b/crates/trusted-server-adapter-cloudflare/tests/routes.rs @@ -36,7 +36,14 @@ fn test_router() -> RouterService { proxy_secret = "route-test-proxy-secret" [ec] + provider = "hmac" + + [ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" + + [geo] + default_country = "FR" + assume_single_jurisdiction = true "#, ) .expect("should parse route test settings"); @@ -84,7 +91,14 @@ fn make_router() -> RouterService { origin_url = "https://origin.test-publisher.example.com" proxy_secret = "integration-test-proxy-secret" + [geo] + default_country = "FR" + assume_single_jurisdiction = true + [ec] + provider = "hmac" + + [ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" "#, ) diff --git a/crates/trusted-server-adapter-fastly/Cargo.toml b/crates/trusted-server-adapter-fastly/Cargo.toml index 47cc609b2..d0a43e670 100644 --- a/crates/trusted-server-adapter-fastly/Cargo.toml +++ b/crates/trusted-server-adapter-fastly/Cargo.toml @@ -29,6 +29,8 @@ serde = { workspace = true } serde_json = { workspace = true } sha2 = { workspace = true } trusted-server-core = { workspace = true } +trusted-server-device-fastly = { workspace = true } +trusted-server-geo-fastly = { workspace = true } url = { workspace = true } urlencoding = { workspace = true } diff --git a/crates/trusted-server-adapter-fastly/src/app.rs b/crates/trusted-server-adapter-fastly/src/app.rs index 41e5e65ee..b3c42d253 100644 --- a/crates/trusted-server-adapter-fastly/src/app.rs +++ b/crates/trusted-server-adapter-fastly/src/app.rs @@ -30,6 +30,7 @@ //! | GET | `/_ts/set-tester` | [`handle_set_tester`] | //! | GET | `/_ts/clear-tester` | [`handle_clear_tester`] | //! | OPTIONS | `/_ts/api/v1/identify` | [`cors_preflight_identify`] | +//! | POST | `/_ts/api/v1/ec/resolve` | [`handle_ec_resolve`] | //! | POST | `/auction` | [`handle_auction`] | //! | GET | `/first-party/proxy` | [`handle_first_party_proxy`] | //! | GET | `/first-party/click` | [`handle_first_party_click`] | @@ -108,18 +109,20 @@ use trusted_server_core::ec::admin::{ deny_admin_diagnostic_fallback, handle_admin_ec_lookup, handle_admin_eids_lookup, }; use trusted_server_core::ec::batch_sync::handle_batch_sync; -use trusted_server_core::ec::consent::ec_consent_withdrawn; use trusted_server_core::ec::device::DeviceSignals; use trusted_server_core::ec::identify::{cors_preflight_identify, handle_identify}; use trusted_server_core::ec::kv::KvIdentityGraph; use trusted_server_core::ec::registry::PartnerRegistry; +use trusted_server_core::ec::resolve::handle_ec_resolve; use trusted_server_core::error::{IntoHttpResponse as _, TrustedServerError}; use trusted_server_core::http_util::is_navigation_request; use trusted_server_core::integrations::{ IntegrationRegistry, ProxyDispatchInput, RequestFilterEffects, RequestFilterRegistryInput, RequestFilterRegistryOutcome, }; -use trusted_server_core::platform::{ClientInfo, GeoInfo, PlatformKvStore, RuntimeServices}; +use trusted_server_core::platform::{ + ClientInfo, GeoInfo, PlatformKvStore, RuntimeServices, build_geo_provider, +}; use trusted_server_core::proxy::{ AssetProxyCachePolicy, handle_asset_proxy_request, handle_first_party_click, handle_first_party_proxy, handle_first_party_proxy_rebuild, handle_first_party_proxy_sign, @@ -138,6 +141,7 @@ use trusted_server_core::settings_data::{ default_config_key, default_config_store_name, get_settings_from_config_store, }; use trusted_server_core::tester_cookie::{handle_clear_tester, handle_set_tester}; +use trusted_server_device_fastly::FastlyHostSignals; use crate::middleware::{AuthMiddleware, FinalizeResponseMiddleware}; use crate::platform::{ @@ -261,6 +265,23 @@ fn build_per_request_services(state: &AppState, ctx: &RequestContext) -> Runtime ..ClientInfo::default() }); + // The TLS JA4 and HTTP/2 fingerprints arrive as trusted internal headers + // injected by the entry point. They build the host-signal service a + // host-signal provider reads; Fastly always supplies the capability, so the + // service is always set even when a request carried no fingerprint. + let tls_ja4 = ctx + .request() + .headers() + .get("x-ts-tls-ja4") + .and_then(|v| v.to_str().ok()) + .map(str::to_string); + let h2_fingerprint = ctx + .request() + .headers() + .get("x-ts-h2-fingerprint") + .and_then(|v| v.to_str().ok()) + .map(str::to_string); + RuntimeServices::builder() .config_store(Arc::new(FastlyPlatformConfigStore)) .secret_store(Arc::new(FastlyPlatformSecretStore)) @@ -272,9 +293,13 @@ fn build_per_request_services(state: &AppState, ctx: &RequestContext) -> Runtime .template_assembler(Arc::new(crate::esi_assembly::FastlyTemplateAssembler)) .backend(Arc::new(FastlyPlatformBackend)) .http_client(Arc::new(FastlyPlatformHttpClient)) - .geo(Arc::new(FastlyPlatformGeo)) + .geo(build_geo_provider( + &state.settings, + Arc::new(FastlyPlatformGeo), + )) .auction_telemetry_sink(Arc::clone(&state.auction_telemetry_sink)) .client_info(client_info) + .host_signals(Arc::new(FastlyHostSignals::new(tls_ja4, h2_fingerprint))) .build() } @@ -397,7 +422,7 @@ fn build_ec_request_state( req: &Request, ) -> EcRequestState { let device_signals = device_signals_for(req); - let is_real_browser = device_signals.looks_like_browser(); + let is_real_browser = device_signals.looks_like_browser; if !is_real_browser { log::info!( "Bot gate: blocking EC operations (ja4={:?}, platform={:?}, is_mobile={})", @@ -410,34 +435,29 @@ fn build_ec_request_state( let eids_cookie = crate::extract_cookie_value(req, COOKIE_TS_EIDS); let sharedid_cookie = crate::extract_cookie_value(req, COOKIE_SHAREDID); - let geo_info = services - .geo() - .lookup(services.client_info().client_ip) - .unwrap_or_else(|e| { - log::warn!("geo lookup failed during EC setup: {e}"); - None - }); - let (ec_context, setup_error) = - match EcContext::read_from_request_with_geo(settings, req, services, geo_info.as_ref()) { + match EcContext::read_from_request_resolving_geo(settings, req, services) { Ok(mut context) => { context.set_device_signals(device_signals); (context, None) } Err(report) => (EcContext::default(), Some(report)), }; + let geo_info = ec_context.geo_info().cloned(); // Bot gate: suppress KV-backed EC writes for unrecognized clients, except - // consent withdrawals. Revocations keep the write path so tombstones stay - // authoritative even for privacy-extension-heavy clients. + // when the request carries an explicit withdrawal signal. The write path + // stays open for withdrawal so tombstones remain authoritative even for + // privacy-extension-heavy clients that do not look like known browsers. A + // merely not-permitted (pre-consent or fail-closed) request writes nothing, + // so it does not need the graph. let kv_graph = crate::maybe_identity_graph(settings); - let finalize_kv_graph = if setup_error.is_none() - && (is_real_browser || ec_consent_withdrawn(ec_context.consent())) - { - kv_graph.clone() - } else { - None - }; + let finalize_kv_graph = + if setup_error.is_none() && (is_real_browser || ec_context.storage_withdrawn()) { + kv_graph.clone() + } else { + None + }; let kv_graph = if is_real_browser { kv_graph } else { None }; EcRequestState { @@ -635,6 +655,12 @@ async fn run_named_route( } NamedRouteHandler::SetTester => handle_set_tester(&state.settings), NamedRouteHandler::ClearTester => handle_clear_tester(&state.settings), + NamedRouteHandler::EcResolve => { + // The resolve endpoint persists the identity-graph row before + // minting, so it takes the same bot-gated graph as generation: an + // unrecognized client gets no graph, and therefore no mint. + handle_ec_resolve(&state.settings, req, &ec.ec_context, ec.kv_graph.as_ref()) + } NamedRouteHandler::Auction => { // The auction reads consent data, so the consent KV store must be // available — fail closed with 503 when it is configured but @@ -709,7 +735,7 @@ async fn run_named_route( /// response finalization. fn run_batch_sync(state: &AppState, services: &RuntimeServices, req: Request) -> Response { let device_signals = device_signals_for(&req); - let is_real_browser = device_signals.looks_like_browser(); + let is_real_browser = device_signals.looks_like_browser; let eids_cookie = crate::extract_cookie_value(&req, COOKIE_TS_EIDS); let sharedid_cookie = crate::extract_cookie_value(&req, COOKIE_SHAREDID); @@ -822,7 +848,7 @@ async fn dispatch_fallback( .ec_context .generate_if_needed(&state.settings, ec.kv_graph.as_ref()) { - log::warn!("EC generation failed for publisher proxy: {err:?}"); + log::error!("EC generation failed for publisher proxy: {err:?}"); } // Publisher pages read consent data, so the consent KV store must be @@ -1054,6 +1080,7 @@ enum NamedRouteHandler { Identify, SetTester, ClearTester, + EcResolve, Auction, PageBids, FirstPartyProxy, @@ -1154,6 +1181,11 @@ const NAMED_ROUTES: &[NamedRoute] = &[ primary_methods: &[Method::GET], handler: NamedRouteHandler::ClearTester, }, + NamedRoute { + path: "/_ts/api/v1/ec/resolve", + primary_methods: &[Method::POST], + handler: NamedRouteHandler::EcResolve, + }, NamedRoute { path: "/auction", primary_methods: &[Method::POST], @@ -1251,7 +1283,7 @@ impl TrustedServerApp { let mut router = RouterService::builder() .middleware(FinalizeResponseMiddleware::new( Arc::clone(&state.settings), - Arc::new(FastlyPlatformGeo), + build_geo_provider(&state.settings, Arc::new(FastlyPlatformGeo)), )) .middleware(AuthMiddleware::new(Arc::clone(&state.settings))); @@ -1353,8 +1385,15 @@ mod tests { allowed_domains = ["*.example", "*.example.com"] [ec] + provider = "hmac" + + [ec.providers.hmac] passphrase = "test-passphrase-at-least-32-bytes!!" + [geo] + default_country = "FR" + assume_single_jurisdiction = true + [request_signing] enabled = false config_store_id = "test-config-store-id" @@ -1422,8 +1461,15 @@ mod tests { allowed_domains = ["*.example", "*.example.com"] [ec] + provider = "hmac" + + [ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" + [geo] + default_country = "FR" + assume_single_jurisdiction = true + [request_signing] enabled = false config_store_id = "test-config-store-id" @@ -1854,7 +1900,14 @@ mod tests { proxy_secret = "unit-test-proxy-secret" [ec] + provider = "hmac" + + [ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" + + [geo] + default_country = "FR" + assume_single_jurisdiction = true "#, ) .expect("should parse production-shaped settings"); @@ -2106,6 +2159,25 @@ mod tests { ); } + #[test] + fn dispatch_ec_resolve_routes_to_resolve_handler() { + // Parity guard: POST /_ts/api/v1/ec/resolve must reach the resolve + // handler, not the publisher fallback or a router-level 405. The test + // request carries no Origin, so the handler's own origin guard answers + // 403, proving the request was handled here rather than proxied to + // the publisher origin (which would error without a live backend). + let router = test_router(); + let response = + block_on(router.oneshot(empty_request(Method::POST, "/_ts/api/v1/ec/resolve"))) + .expect("should route request"); + + assert_eq!( + response.status(), + StatusCode::FORBIDDEN, + "POST ec/resolve should reach the resolve handler's origin guard, not the publisher" + ); + } + #[test] fn dispatch_fallback_attaches_ec_finalize_state() { // The publisher fallback must thread EC finalize state to the entry @@ -2493,8 +2565,15 @@ mod tests { proxy_secret = "unit-test-proxy-secret" [ec] + provider = "hmac" + + [ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" + [geo] + default_country = "FR" + assume_single_jurisdiction = true + [request_signing] enabled = false config_store_id = "test-config-store-id" @@ -2618,8 +2697,15 @@ mod tests { proxy_secret = "unit-test-proxy-secret" [ec] + provider = "hmac" + + [ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" + [geo] + default_country = "FR" + assume_single_jurisdiction = true + [request_signing] enabled = false config_store_id = "test-config-store-id" diff --git a/crates/trusted-server-adapter-fastly/src/main.rs b/crates/trusted-server-adapter-fastly/src/main.rs index a19d0485d..4e527a153 100644 --- a/crates/trusted-server-adapter-fastly/src/main.rs +++ b/crates/trusted-server-adapter-fastly/src/main.rs @@ -5,14 +5,16 @@ use edgezero_adapter_fastly::request::into_core_request; use edgezero_core::body::Body as EdgeBody; use edgezero_core::config_store::ConfigStoreHandle; use edgezero_core::error::EdgeError; -use edgezero_core::http::{Request as HttpRequest, Response as HttpResponse}; +use edgezero_core::http::{ + HeaderMap, HeaderValue, Request as HttpRequest, Response as HttpResponse, header, +}; use edgezero_core::response::IntoResponse; use error_stack::Report; use fastly::http::Method as FastlyMethod; use fastly::{Request as FastlyRequest, Response as FastlyResponse}; use trusted_server_core::cache_policy::EdgeCacheHeader; -use trusted_server_core::ec::device::DeviceSignals; +use trusted_server_core::ec::device::{DeviceProvider, DeviceSignals, build_device_provider}; use trusted_server_core::ec::finalize::ec_finalize_response; use trusted_server_core::ec::kv::KvIdentityGraph; use trusted_server_core::ec::pull_sync::{ @@ -20,12 +22,14 @@ use trusted_server_core::ec::pull_sync::{ }; use trusted_server_core::ec::registry::PartnerRegistry; use trusted_server_core::error::TrustedServerError; +use trusted_server_core::evidence::{BorrowedRequestInfo, HostSignals}; use trusted_server_core::integrations::RequestFilterEffects; -use trusted_server_core::platform::PlatformGeo as _; use trusted_server_core::platform::RuntimeServices; +use trusted_server_core::platform::build_geo_provider; use trusted_server_core::proxy::{AssetProxyCachePolicy, stream_asset_body}; use trusted_server_core::response_privacy::TerminalPrivateResponse; use trusted_server_core::settings::Settings; +use trusted_server_device_fastly::{FastlyDeviceProvider, FastlyHostSignals}; mod app; mod backend; @@ -161,7 +165,42 @@ fn edgezero_main(mut req: FastlyRequest) { // accessors only return real values on the client request, so store them in // request extensions for build_per_request_services and EC bot classification. let client_info = client_info_from_request(&req); - let device_signals = derive_device_signals(&req); + + // Strip and re-inject the TLS JA4 and HTTP/2 fingerprints from the + // authoritative Fastly SDK values, under the same trust model, so the + // EdgeZero app path can build the host-signal service from these internal + // headers (the SDK accessors return real values only on the live client + // request, not on a request rebuilt from EdgeZero HTTP types). + req.remove_header("x-ts-tls-ja4"); + req.remove_header("x-ts-h2-fingerprint"); + // Take ownership before setting: unlike the static TLS protocol/cipher + // names, these accessors borrow the request, which would otherwise conflict + // with the mutable `set_header`. + if let Some(ja4) = req.get_tls_ja4().map(str::to_string) { + req.set_header("x-ts-tls-ja4", ja4); + } + if let Some(h2) = req.get_client_h2_fingerprint().map(str::to_string) { + req.set_header("x-ts-h2-fingerprint", h2); + } + + // Derive device signals from the original FastlyRequest before conversion. + // Fastly's `get_tls_ja4()` and `get_client_h2_fingerprint()` accessors only + // return real values on the client request; a synthetic request rebuilt from + // EdgeZero HTTP types cannot expose them, which would strip the JA4/H2 class + // the EC bot gate needs and misclassify real browsers as bots. Stored in the + // request extensions so `build_ec_request_state` reads the authoritative + // signals instead of re-deriving from the reconstructed request. + // Reuse the settings snapshot already loaded for the app state rather than + // fetching and validating the config-store blob a second time per request. + let device_signals = match settings_snapshot.as_deref() { + Some(settings) => derive_device_signals(settings, &req), + None => { + log::warn!( + "EdgeZero device signals: settings unavailable, using UA-only classification" + ); + DeviceSignals::derive_ua_only(req.get_header_str("user-agent").unwrap_or("")) + } + }; // Dispatch directly through the EdgeZero router without an intermediate // fastly::Response conversion. That preserves duplicate header values such @@ -279,8 +318,12 @@ fn apply_entry_point_finalize_headers( response: &mut HttpResponse, client_ip: Option, ) { + // Route through the [geo] provider selector, so a deployment that opts + // out of geolocation makes no host geo call on the entry-point finalize + // path either. + let geo = build_geo_provider(settings, Arc::new(FastlyPlatformGeo)); let geo_info = resolve_geo_for_response(response, client_ip, |client_ip| { - FastlyPlatformGeo.lookup(client_ip).unwrap_or_else(|e| { + geo.lookup(client_ip).unwrap_or_else(|e| { log::warn!("entry-point geo lookup failed: {e}"); None }) @@ -486,16 +529,32 @@ pub(crate) fn extract_cookie_value(req: &HttpRequest, name: &str) -> Option DeviceSignals { - let ua = req.get_header_str("user-agent").unwrap_or(""); - let ja4 = req.get_tls_ja4(); - let h2_fp = req.get_client_h2_fingerprint(); - - DeviceSignals::derive(ua, ja4, h2_fp) +/// The providers read request data from injected services: device classification +/// reads only the User-Agent, borrowed here through a `BorrowedRequestInfo`, while the +/// Fastly provider also reads the TLS/H2 fingerprints captured into a +/// [`FastlyHostSignals`]. The Fastly provider, and so the fingerprint capture, is +/// built only when selected, so the default request path makes no Fastly-specific +/// fingerprint call. +pub(crate) fn derive_device_signals(settings: &Settings, req: &FastlyRequest) -> DeviceSignals { + let mut headers = HeaderMap::new(); + if let Some(value) = req + .get_header_str(header::USER_AGENT.as_str()) + .and_then(|user_agent| HeaderValue::from_str(user_agent).ok()) + { + headers.insert(header::USER_AGENT, value); + } + let client_ip = req + .get_client_ip_addr() + .map(|ip| ip.to_string()) + .unwrap_or_default(); + let request_info = BorrowedRequestInfo::new(&client_ip, Some(&headers)); + build_device_provider(settings, || { + let host_signals: Arc = Arc::new(FastlyHostSignals::from_request(req)); + Box::new(FastlyDeviceProvider::new(host_signals)) as Box + }) + .detect(&request_info) } #[cfg(test)] @@ -521,7 +580,14 @@ mod tests { origin_url = "https://origin.test-publisher.com" proxy_secret = "unit-test-proxy-secret" + [geo] + default_country = "FR" + assume_single_jurisdiction = true + [ec] + provider = "hmac" + + [ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" [request_signing] @@ -648,6 +714,10 @@ mod tests { origin_url = "https://origin.test-publisher.com" proxy_secret = "unit-test-proxy-secret" + [geo] + default_country = "FR" + assume_single_jurisdiction = true + [ec] passphrase = "test-secret-key-32-bytes-minimum" diff --git a/crates/trusted-server-adapter-fastly/src/middleware.rs b/crates/trusted-server-adapter-fastly/src/middleware.rs index 18f309c68..f7c2e401c 100644 --- a/crates/trusted-server-adapter-fastly/src/middleware.rs +++ b/crates/trusted-server-adapter-fastly/src/middleware.rs @@ -299,7 +299,14 @@ mod tests { origin_url = "https://origin.test-publisher.com" proxy_secret = "unit-test-proxy-secret" + [geo] + default_country = "FR" + assume_single_jurisdiction = true + [ec] + provider = "hmac" + + [ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" [request_signing] diff --git a/crates/trusted-server-adapter-fastly/src/platform.rs b/crates/trusted-server-adapter-fastly/src/platform.rs index 9e7920e1c..626461e60 100644 --- a/crates/trusted-server-adapter-fastly/src/platform.rs +++ b/crates/trusted-server-adapter-fastly/src/platform.rs @@ -2,21 +2,19 @@ //! `trusted-server-core::platform`. use std::io::Read as _; -use std::net::IpAddr; use std::sync::Arc; use bytes::Bytes; use edgezero_adapter_fastly::key_value_store::FastlyKvStore; use edgezero_core::key_value_store::KvError; use error_stack::{Report, ResultExt}; -use fastly::geo::{Geo, geo_lookup}; use fastly::{ConfigStore, Request, SecretStore}; use crate::backend::BackendConfig; pub(crate) use trusted_server_core::platform::UnavailableKvStore; use trusted_server_core::platform::{ - ClientInfo, GeoInfo, PlatformBackend, PlatformBackendSpec, PlatformConfigStore, PlatformError, - PlatformGeo, PlatformHttpClient, PlatformHttpRequest, PlatformImageOptimizerCrop, + ClientInfo, PlatformBackend, PlatformBackendSpec, PlatformConfigStore, PlatformError, + PlatformHttpClient, PlatformHttpRequest, PlatformImageOptimizerCrop, PlatformImageOptimizerCropMode, PlatformImageOptimizerOptions, PlatformImageOptimizerParams, PlatformImageOptimizerRegion, PlatformKvStore, PlatformPendingRequest, PlatformResponse, PlatformSecretStore, PlatformSelectResult, StoreId, StoreName, @@ -666,33 +664,12 @@ impl PlatformHttpClient for FastlyPlatformHttpClient { // FastlyPlatformGeo // --------------------------------------------------------------------------- -/// Convert a Fastly [`Geo`] value into a platform-neutral [`GeoInfo`]. -/// -/// Shared by `FastlyPlatformGeo::lookup` in `trusted-server-adapter-fastly` so -/// that field mapping is never duplicated. -fn geo_from_fastly(geo: &Geo) -> GeoInfo { - GeoInfo { - city: geo.city().to_string(), - country: geo.country_code().to_string(), - continent: format!("{:?}", geo.continent()), - latitude: geo.latitude(), - longitude: geo.longitude(), - metro_code: geo.metro_code(), - region: geo.region().map(str::to_string), - asn: None, - } -} - -/// Fastly geo-lookup implementation of [`PlatformGeo`]. -pub struct FastlyPlatformGeo; - -impl PlatformGeo for FastlyPlatformGeo { - fn lookup(&self, client_ip: Option) -> Result, Report> { - Ok(client_ip - .and_then(geo_lookup) - .map(|geo| geo_from_fastly(&geo))) - } -} +/// The Fastly host geo provider now lives in its own crate, +/// `trusted-server-geo-fastly`, so every provider implementation sits under +/// `crates//`. It is re-exported here so this module's +/// [`build_runtime_services`] and the adapter's existing call sites keep +/// referring to it through `crate::platform`. +pub(crate) use trusted_server_geo_fastly::FastlyPlatformGeo; /// Extract [`ClientInfo`] from the original Fastly request. /// diff --git a/crates/trusted-server-adapter-spin/src/app.rs b/crates/trusted-server-adapter-spin/src/app.rs index 06bb1a15a..fb469ef13 100644 --- a/crates/trusted-server-adapter-spin/src/app.rs +++ b/crates/trusted-server-adapter-spin/src/app.rs @@ -132,7 +132,8 @@ fn publisher_fallback_methods() -> [Method; 7] { // reaches the publisher origin rather than a router-level 405. // // The EC API routes that the Fastly entry point registers — POST -// `/_ts/api/v1/batch-sync`, GET/OPTIONS `/_ts/api/v1/identify` — are +// `/_ts/api/v1/batch-sync`, GET/OPTIONS `/_ts/api/v1/identify`, POST +// `/_ts/api/v1/ec/resolve` — are // intentionally absent here, matching the Axum and Cloudflare adapters: those // handlers require a platform KV `ec_store` (and, for batch-sync, a partner // registry and rate limiter) that the portability adapters do not yet wire. @@ -342,18 +343,10 @@ fn health_response() -> Response { /// falls back to the default (fail-closed) context rather than being silently /// swallowed. fn build_ec_context(settings: &Settings, services: &RuntimeServices, req: &Request) -> EcContext { - let geo_info = services - .geo() - .lookup(services.client_info().client_ip) - .unwrap_or_else(|e| { - log::warn!("geo lookup failed: {e}"); - None - }); - EcContext::read_from_request_with_geo(settings, req, services, geo_info.as_ref()) - .unwrap_or_else(|e| { - log::warn!("EC context read failed: {e:?}"); - EcContext::default() - }) + EcContext::read_from_request_resolving_geo(settings, req, services).unwrap_or_else(|e| { + log::warn!("EC context read failed: {e:?}"); + EcContext::default() + }) } fn admin_key_management_not_supported() -> Response { @@ -503,7 +496,7 @@ fn build_router(state: &Arc) -> RouterService { let discovery_handler = move |ctx: RequestContext| { let s = Arc::clone(&s); async move { - let services = build_runtime_services(&ctx); + let services = build_runtime_services(&ctx, &s.settings); let req = ctx.into_request(); Ok(handle_trusted_server_discovery(&s.settings, &services, req) .unwrap_or_else(|e| http_error(&e))) @@ -515,7 +508,7 @@ fn build_router(state: &Arc) -> RouterService { let verify_handler = move |ctx: RequestContext| { let s = Arc::clone(&s); async move { - let services = build_runtime_services(&ctx); + let services = build_runtime_services(&ctx, &s.settings); let req = ctx.into_request(); Ok(handle_verify_signature(&s.settings, &services, req) .unwrap_or_else(|e| http_error(&e))) @@ -548,7 +541,7 @@ fn build_router(state: &Arc) -> RouterService { let auction_handler = move |ctx: RequestContext| { let s = Arc::clone(&s); async move { - let services = build_runtime_services(&ctx); + let services = build_runtime_services(&ctx, &s.settings); // Request normalization (forwarded-header stripping, trusted // Host/scheme/client-IP derivation) is applied centrally by // `NormalizeMiddleware` before this handler runs, so the signed @@ -586,7 +579,7 @@ fn build_router(state: &Arc) -> RouterService { let page_bids_handler = move |ctx: RequestContext| { let s = Arc::clone(&s); async move { - let services = build_runtime_services(&ctx); + let services = build_runtime_services(&ctx, &s.settings); let mut req = ctx.into_request(); if let Err(error) = trusted_server_core::integrations::gpt_diagnostics::prepare_request( @@ -621,7 +614,7 @@ fn build_router(state: &Arc) -> RouterService { let fp_proxy_handler = move |ctx: RequestContext| { let s = Arc::clone(&s); async move { - let services = build_runtime_services(&ctx); + let services = build_runtime_services(&ctx, &s.settings); let req = ctx.into_request(); Ok(handle_first_party_proxy(&s.settings, &services, req) .await @@ -634,7 +627,7 @@ fn build_router(state: &Arc) -> RouterService { let fp_click_handler = move |ctx: RequestContext| { let s = Arc::clone(&s); async move { - let services = build_runtime_services(&ctx); + let services = build_runtime_services(&ctx, &s.settings); let req = ctx.into_request(); Ok(handle_first_party_click(&s.settings, &services, req) .await @@ -647,7 +640,7 @@ fn build_router(state: &Arc) -> RouterService { let fp_sign_handler = move |ctx: RequestContext| { let s = Arc::clone(&s); async move { - let services = build_runtime_services(&ctx); + let services = build_runtime_services(&ctx, &s.settings); let req = ctx.into_request(); Ok(handle_first_party_proxy_sign(&s.settings, &services, req) .await @@ -664,7 +657,7 @@ fn build_router(state: &Arc) -> RouterService { let fp_rebuild_handler = move |ctx: RequestContext| { let s = Arc::clone(&s); async move { - let services = build_runtime_services(&ctx); + let services = build_runtime_services(&ctx, &s.settings); let req = ctx.into_request(); Ok( handle_first_party_proxy_rebuild(&s.settings, &services, req) @@ -680,7 +673,7 @@ fn build_router(state: &Arc) -> RouterService { state: Arc, ctx: RequestContext, ) -> Result { - let services = build_runtime_services(&ctx); + let services = build_runtime_services(&ctx, &state.settings); let mut req = ctx.into_request(); if let Some(response) = deny_admin_diagnostic_fallback(&req) { return Ok(response); diff --git a/crates/trusted-server-adapter-spin/src/middleware.rs b/crates/trusted-server-adapter-spin/src/middleware.rs index 1bcede1fc..ad151e111 100644 --- a/crates/trusted-server-adapter-spin/src/middleware.rs +++ b/crates/trusted-server-adapter-spin/src/middleware.rs @@ -178,7 +178,14 @@ mod tests { proxy_secret = "unit-test-proxy-secret" [ec] + provider = "hmac" + + [ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" + + [geo] + default_country = "FR" + assume_single_jurisdiction = true "#, ) .expect("should load test settings"); diff --git a/crates/trusted-server-adapter-spin/src/platform.rs b/crates/trusted-server-adapter-spin/src/platform.rs index 492f1a518..f91b1e8e6 100644 --- a/crates/trusted-server-adapter-spin/src/platform.rs +++ b/crates/trusted-server-adapter-spin/src/platform.rs @@ -715,7 +715,10 @@ impl PlatformSecretStore for SpinSecretStoreAdapter { /// before routing. Secrets are read synchronously from Spin component /// variables because Trusted Server's platform secret trait is sync. #[must_use] -pub fn build_runtime_services(ctx: &edgezero_core::context::RequestContext) -> RuntimeServices { +pub fn build_runtime_services( + ctx: &edgezero_core::context::RequestContext, + settings: &trusted_server_core::settings::Settings, +) -> RuntimeServices { let client_ip = extract_client_ip(ctx); #[cfg(all(feature = "spin", target_arch = "wasm32"))] @@ -744,7 +747,13 @@ pub fn build_runtime_services(ctx: &edgezero_core::context::RequestContext) -> R .kv_store(kv_store) .backend(Arc::new(NoopBackend)) .http_client(http_client) - .geo(Arc::new(NullGeo)) + // Routed through the [geo] provider selector like the Fastly adapter, + // so the selector behaves the same on every adapter. Spin has no host + // geo service, so the host default resolves nothing either way. + .geo(trusted_server_core::platform::build_geo_provider( + settings, + Arc::new(NullGeo), + )) .client_info(ClientInfo { client_ip, tls_protocol: None, @@ -994,7 +1003,8 @@ mod tests { #[tokio::test(flavor = "multi_thread", worker_threads = 2)] async fn build_runtime_services_uses_noop_native_stores_without_handles() { let ctx = make_ctx_without_spin_context(); - let services = build_runtime_services(&ctx); + let services = + build_runtime_services(&ctx, &trusted_server_core::settings::Settings::default()); assert!( services.client_info().client_ip.is_none(), diff --git a/crates/trusted-server-adapter-spin/tests/routes.rs b/crates/trusted-server-adapter-spin/tests/routes.rs index f75ea687e..ce32424c4 100644 --- a/crates/trusted-server-adapter-spin/tests/routes.rs +++ b/crates/trusted-server-adapter-spin/tests/routes.rs @@ -35,7 +35,14 @@ fn test_router() -> RouterService { proxy_secret = "route-test-proxy-secret" [ec] + provider = "hmac" + + [ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" + + [geo] + default_country = "FR" + assume_single_jurisdiction = true "#, ) .expect("should parse route test settings"); diff --git a/crates/trusted-server-core/Cargo.toml b/crates/trusted-server-core/Cargo.toml index e44d46f77..8413f31ae 100644 --- a/crates/trusted-server-core/Cargo.toml +++ b/crates/trusted-server-core/Cargo.toml @@ -40,6 +40,7 @@ rand = { workspace = true } regex = { workspace = true } serde = { workspace = true } serde_json = { workspace = true } +serde_yaml_ng = { workspace = true } sha2 = { workspace = true } subtle = { workspace = true } toml = { workspace = true } @@ -59,6 +60,9 @@ getrandom = { workspace = true, features = ["js"] } uuid = { workspace = true, features = ["js"] } [features] +# Compiles in the client-fixed demonstration Edge Cookie provider. Off by +# default so production builds cannot select a fixed shared word as identity. +client-fixed-demo = [] default = [] # Exposes test-only constructors (e.g. `IntegrationRegistry::from_request_filters`) # so downstream crates can build registries with stub integrations in their tests. diff --git a/crates/trusted-server-core/src/auction/endpoints.rs b/crates/trusted-server-core/src/auction/endpoints.rs index fdf387e93..86bd7b981 100644 --- a/crates/trusted-server-core/src/auction/endpoints.rs +++ b/crates/trusted-server-core/src/auction/endpoints.rs @@ -9,7 +9,7 @@ use serde_json::Value as JsonValue; use crate::auction::formats::AdRequest; use crate::auction::orchestrator::OrchestrationResult; -use crate::consent::{consent_allows_server_side_auction, gate_eids_by_consent}; +use crate::consent::{consent_allows_server_side_auction, gate_eids_by_permissions}; use crate::constants::COOKIE_TS_EIDS; use crate::cookies::extract_cookie_value; use crate::ec::EcContext; @@ -171,8 +171,9 @@ pub async fn handle_auction( // Story 5 middleware contract: auction is a read-only EC route. // It must not generate EC IDs; it only consumes pre-routed context. - // Only forward the EC ID to auction partners when consent allows it. - let ec_id = if ec_context.ec_allowed() { + // Forward the EC ID to auction partners only when sharing is permitted: + // storage plus personalised-ad selection, the same pair that gates EIDs. + let ec_id = if ec_context.ec_sharing_allowed() { ec_context.ec_value() } else { None @@ -237,8 +238,9 @@ pub async fn handle_auction( // `ts-eids` cookie so later requests can still forward the browser's // full OpenRTB-style EID structure. // - // Gate this on the same identity-consent condition as the EC ID - // (`ec_id.is_some()`, which is already filtered by `ec_context.ec_allowed()`). + // Gate this on the same identity condition as the EC ID + // (`ec_id.is_some()`, which is already filtered by the sharing pair via + // `ec_context.ec_sharing_allowed()`). // Otherwise a US/GPC or US-Privacy opt-out context — where EC identity use is // denied but a non-personalized auction may still run — could forward // persistent client EIDs from the body/cookie, since `gate_eids_by_consent` @@ -282,10 +284,9 @@ pub async fn handle_auction( // consent gating before attaching them to the auction request. let merged_eids = merge_auction_eids(client_eids, eids); let had_eids = merged_eids.as_ref().is_some_and(|v| !v.is_empty()); - auction_request.user.eids = - gate_eids_by_consent(merged_eids, auction_request.user.consent.as_ref()); + auction_request.user.eids = gate_eids_by_permissions(merged_eids, ec_context.permissions()); if had_eids && auction_request.user.eids.is_none() { - log::warn!("Auction EIDs stripped by TCF consent gating"); + log::warn!("Auction EIDs stripped: bidstream permissions not set"); } // Create auction context @@ -616,13 +617,11 @@ mod tests { .build() } - fn make_ec_context(jurisdiction: Jurisdiction, ec_value: Option<&str>) -> EcContext { - EcContext::new_for_test( + fn make_ec_context(ec_allowed: bool, ec_value: Option<&str>) -> EcContext { + EcContext::new_for_test_gated( ec_value.map(str::to_owned), - ConsentContext { - jurisdiction, - ..ConsentContext::default() - }, + ConsentContext::default(), + ec_allowed, ) } @@ -744,7 +743,11 @@ mod tests { .geo(Arc::new(NoopGeo)) .client_info(ClientInfo::default()) .build(); - let ec_context = make_ec_context(Jurisdiction::NonRegulated, None); + let consent = ConsentContext { + jurisdiction: Jurisdiction::NonRegulated, + ..ConsentContext::default() + }; + let ec_context = EcContext::new_for_test_gated(None, consent, true); let body = json!({ "adUnits": [{ "code": "div-gpt-ad-1", @@ -798,7 +801,9 @@ mod tests { let telemetry_sink = Arc::new(RecordingTelemetrySink::default()); let services = services_with_telemetry(Arc::clone(&telemetry_sink)); let ec_id = format!("{}.ABC123", "a".repeat(64)); - let ec_context = make_ec_context(Jurisdiction::Unknown, Some(&ec_id)); + // The default consent context keeps the jurisdiction unknown, so the + // server-side auction gate fails closed; the EC gate is off to match. + let ec_context = make_ec_context(false, Some(&ec_id)); let body = json!({ "adUnits": [ @@ -995,7 +1000,7 @@ mod tests { fn resolve_auction_eids_returns_none_without_kv() { let registry = PartnerRegistry::empty(); let ec_id = format!("{}.ABC123", "a".repeat(64)); - let ec_context = make_ec_context(Jurisdiction::NonRegulated, Some(&ec_id)); + let ec_context = make_ec_context(true, Some(&ec_id)); let result = resolve_auction_eids(None, Some(®istry), &ec_context); assert!(result.is_none(), "should return None when KV is missing"); @@ -1005,7 +1010,7 @@ mod tests { fn resolve_auction_eids_returns_none_without_registry() { let kv = KvIdentityGraph::failing("test_store"); let ec_id = format!("{}.ABC123", "a".repeat(64)); - let ec_context = make_ec_context(Jurisdiction::NonRegulated, Some(&ec_id)); + let ec_context = make_ec_context(true, Some(&ec_id)); let result = resolve_auction_eids(Some(&kv), None, &ec_context); assert!( @@ -1019,7 +1024,7 @@ mod tests { let kv = KvIdentityGraph::failing("test_store"); let registry = PartnerRegistry::empty(); let ec_id = format!("{}.ABC123", "a".repeat(64)); - let ec_context = make_ec_context(Jurisdiction::Unknown, Some(&ec_id)); + let ec_context = make_ec_context(false, Some(&ec_id)); let result = resolve_auction_eids(Some(&kv), Some(®istry), &ec_context); assert!( @@ -1032,7 +1037,11 @@ mod tests { fn resolve_auction_eids_returns_none_when_no_ec() { let kv = KvIdentityGraph::failing("test_store"); let registry = PartnerRegistry::empty(); - let ec_context = make_ec_context(Jurisdiction::NonRegulated, None); + let consent = ConsentContext { + jurisdiction: Jurisdiction::NonRegulated, + ..ConsentContext::default() + }; + let ec_context = EcContext::new_for_test_gated(None, consent, true); let result = resolve_auction_eids(Some(&kv), Some(®istry), &ec_context); assert!( @@ -1046,7 +1055,7 @@ mod tests { let kv = KvIdentityGraph::failing("nonexistent_store"); let registry = PartnerRegistry::empty(); let ec_id = format!("{}.ABC123", "a".repeat(64)); - let ec_context = make_ec_context(Jurisdiction::NonRegulated, Some(&ec_id)); + let ec_context = make_ec_context(true, Some(&ec_id)); // KV store doesn't exist, so the get() call will error — should return // empty Vec (degraded mode), not None. diff --git a/crates/trusted-server-core/src/config.rs b/crates/trusted-server-core/src/config.rs index 818b6fcc5..0c4670137 100644 --- a/crates/trusted-server-core/src/config.rs +++ b/crates/trusted-server-core/src/config.rs @@ -364,7 +364,14 @@ cookie_domain = ".example.com" origin_url = "https://origin.example.com" proxy_secret = "change-me-proxy-secret" +[geo] +default_country = "FR" +assume_single_jurisdiction = true + [ec] +provider = "hmac" + +[ec.providers.hmac] passphrase = "production-secret-key-32-bytes-min" [[handlers]] diff --git a/crates/trusted-server-core/src/config_payload.rs b/crates/trusted-server-core/src/config_payload.rs index 6ede36e9c..2525a528d 100644 --- a/crates/trusted-server-core/src/config_payload.rs +++ b/crates/trusted-server-core/src/config_payload.rs @@ -154,7 +154,9 @@ mod tests { fn strings_that_look_like_json_scalars_round_trip_as_strings() { let mut original = test_settings(); original.publisher.proxy_secret = Redacted::new("1234567890".to_string()); - original.ec.passphrase = Redacted::new("12345678901234567890123456789012".to_string()); + original.ec.providers.hmac = Some(crate::settings::HmacProviderConfig { + passphrase: Redacted::new("12345678901234567890123456789012".to_string()), + }); original.handlers[0].password = Redacted::new("true".to_string()); let reconstructed = settings_from_config_blob(&envelope_json(&original)) @@ -166,8 +168,22 @@ mod tests { "numeric-looking proxy secret should remain a string" ); assert_eq!( - reconstructed.ec.passphrase.expose(), - original.ec.passphrase.expose(), + reconstructed + .ec + .providers + .hmac + .as_ref() + .expect("should reconstruct the hmac provider") + .passphrase + .expose(), + original + .ec + .providers + .hmac + .as_ref() + .expect("should keep the hmac provider") + .passphrase + .expose(), "numeric-looking passphrase should remain a string" ); assert_eq!( diff --git a/crates/trusted-server-core/src/consent/mod.rs b/crates/trusted-server-core/src/consent/mod.rs index f205a8363..ab375f070 100644 --- a/crates/trusted-server-core/src/consent/mod.rs +++ b/crates/trusted-server-core/src/consent/mod.rs @@ -54,6 +54,7 @@ use http::Request; use crate::consent_config::{ConflictMode, ConsentConfig, ConsentMode}; use crate::geo::GeoInfo; +use crate::permissions::{Permission, PermissionState}; /// Number of deciseconds in one day (86 400 seconds × 10). const DECISECONDS_PER_DAY: u64 = 86_400 * 10; @@ -322,7 +323,7 @@ fn has_eu_tcf_signal(raw_tc_present: bool, gpp_section_ids: Option<&[u16]>) -> b /// Returns the effective decoded TCF consent for enforcement decisions. #[must_use] -fn effective_tcf(ctx: &ConsentContext) -> Option<&types::TcfConsent> { +pub(crate) fn effective_tcf(ctx: &ConsentContext) -> Option<&types::TcfConsent> { ctx.tcf.as_ref().or_else(|| { let g = ctx.gpp.as_ref()?; g.eu_tcf.as_ref() @@ -475,46 +476,38 @@ pub fn build_us_privacy_from_gpc(config: &ConsentConfig) -> Option( +pub fn gate_eids_by_permissions( eids: Option>, - consent_ctx: Option<&ConsentContext>, + permissions: &PermissionState, ) -> Option> { let eids = eids?; if eids.is_empty() { return None; } - let tcf = consent_ctx.and_then(effective_tcf); - - match tcf { - Some(tcf) if allows_eid_transmission(tcf) => Some(eids), - Some(_) => { - log::info!("EIDs stripped: TCF Purpose 1 or 4 consent missing"); - None - } - None => { - // No TCF data — if GDPR applies, block EIDs as a precaution. - if consent_ctx.is_some_and(|c| c.gdpr_applies) { - log::info!("EIDs stripped: GDPR applies but no TCF consent available"); - None - } else { - Some(eids) - } - } + if permissions.is_set(Permission::StoreOnDevice) + && permissions.is_set(Permission::SelectPersonalisedAds) + { + Some(eids) + } else { + log::info!( + "EIDs stripped: necessary.operations.storage or advertising_marketing.first_party.targeted is not set in the resolved permissions" + ); + None } } @@ -522,110 +515,30 @@ pub fn gate_eids_by_consent( // EC consent gating // --------------------------------------------------------------------------- -/// Determines whether Edge Cookie (EC) creation is permitted based on the -/// user's consent and detected jurisdiction. +/// Returns `true` when the request carries a US-style storage/sale opt-out +/// signal (GPC, a GPP sale opt-out, or a US Privacy opt-out), independent of +/// jurisdiction. /// -/// The decision follows the jurisdiction's consent model: +/// This reports the signal only. Whether the opt-out changes a permission is +/// decided by the country/region map when the permission state is assembled: it +/// drops a `granted` baseline (for example a US opt-out state) and has nothing to +/// drop where the permission is `requires_signal`. Honoring it everywhere is +/// intentionally conservative. /// -/// - **GDPR (EU/UK)**: opt-in required — TCF Purpose 1 (store/access -/// information on a device) must be explicitly consented. If no TCF data is -/// available under GDPR, consent is assumed absent and EC is blocked. -/// - **US state privacy**: opt-out model — EC is allowed unless the user has -/// explicitly opted out via Global Privacy Control, GPP US sale opt-out, or -/// the US Privacy string. Explicit US opt-out signals take precedence over -/// TCF storage consent. -/// - **Non-regulated**: EC is allowed (no consent requirement). -/// - **Unknown**: fail-closed — jurisdiction cannot be determined so EC is -/// blocked as a precaution. +/// TCF consent or refusal is handled separately by +/// [`crate::ec::consent::permission_signal`], which treats a present TCF record +/// as authoritative, so this helper does not consider TCF. #[must_use] -pub fn allows_ec_creation(ctx: &ConsentContext) -> bool { - match &ctx.jurisdiction { - jurisdiction::Jurisdiction::Gdpr => { - // EU/UK: explicit opt-in required (TCF Purpose 1 = store/access device). - match effective_tcf(ctx) { - Some(tcf) => tcf.has_storage_consent(), - None => false, - } - } - jurisdiction::Jurisdiction::UsState(_) => { - // GPC is an independent opt-out signal — it always blocks EC - // creation regardless of other consent signals. - if ctx.gpc { - return false; - } - // Explicit US opt-out signals take precedence over TCF storage - // consent in US-state jurisdictions. - if ctx.gpp.as_ref().and_then(|gpp| gpp.us_sale_opt_out) == Some(true) { - return false; - } - if ctx - .us_privacy - .as_ref() - .is_some_and(|usp| usp.opt_out_sale == PrivacyFlag::Yes) - { - return false; - } - // When a CMP uses TCF in the US (e.g. Didomi), respect the TCF - // Purpose 1 decision if no explicit US opt-out signal is present. - if let Some(tcf) = effective_tcf(ctx) { - return tcf.has_storage_consent(); - } - // GPP US sale_opt_out=false is an explicit non-opt-out signal. - if let Some(gpp) = &ctx.gpp - && let Some(opted_out) = gpp.us_sale_opt_out - { - return !opted_out; - } - // Check US Privacy string when no TCF decision is present. - if let Some(usp) = &ctx.us_privacy { - return usp.opt_out_sale != PrivacyFlag::Yes; - } - // Spec §6.1.1: "In regulated jurisdictions (GDPR, US state), - // consent cookies/headers must be present for - // allows_ec_creation() to return true." No signals = block. - false - } - jurisdiction::Jurisdiction::NonRegulated => true, - // No geolocation data — cannot determine jurisdiction. - // Fail-closed: block EC creation as a precaution. - jurisdiction::Jurisdiction::Unknown => false, +pub fn has_storage_optout_signal(ctx: &ConsentContext) -> bool { + if ctx.gpc { + return true; } -} - -/// Returns `true` only when the request contains an explicit EC opt-out signal. -/// -/// This is intentionally narrower than [`allows_ec_creation`]. Some requests -/// fail closed because consent cannot be verified yet (for example, missing geo -/// or missing/undecodable consent signals in a regulated jurisdiction). Those -/// cases must block *new* EC creation, but they must not be treated as an -/// authoritative withdrawal of an already-issued EC. -#[must_use] -pub fn has_explicit_ec_withdrawal(ctx: &ConsentContext) -> bool { - match &ctx.jurisdiction { - jurisdiction::Jurisdiction::Gdpr => { - effective_tcf(ctx).is_some_and(|tcf| !tcf.has_storage_consent()) - } - jurisdiction::Jurisdiction::UsState(_) => { - if ctx.gpc { - return true; - } - if ctx.gpp.as_ref().and_then(|gpp| gpp.us_sale_opt_out) == Some(true) { - return true; - } - if ctx - .us_privacy - .as_ref() - .is_some_and(|usp| usp.opt_out_sale == PrivacyFlag::Yes) - { - return true; - } - if let Some(tcf) = effective_tcf(ctx) { - return !tcf.has_storage_consent(); - } - false - } - jurisdiction::Jurisdiction::NonRegulated | jurisdiction::Jurisdiction::Unknown => false, + if ctx.gpp.as_ref().and_then(|gpp| gpp.us_sale_opt_out) == Some(true) { + return true; } + ctx.us_privacy + .as_ref() + .is_some_and(|usp| usp.opt_out_sale == PrivacyFlag::Yes) } // --------------------------------------------------------------------------- @@ -701,9 +614,9 @@ mod tests { use http::Request; use super::{ - ConsentPipelineInput, allows_ec_creation, apply_expiration_check, - apply_tcf_conflict_resolution, build_consent_context, build_context_from_signals, - consent_allows_server_side_auction, has_explicit_ec_withdrawal, + ConsentPipelineInput, apply_expiration_check, apply_tcf_conflict_resolution, + build_consent_context, build_context_from_signals, consent_allows_server_side_auction, + gate_eids_by_permissions, has_storage_optout_signal, }; use crate::consent::jurisdiction::Jurisdiction; use crate::consent::types::{ @@ -894,7 +807,7 @@ mod tests { } #[test] - fn missing_geo_keeps_unknown_jurisdiction_and_blocks_ec_creation() { + fn missing_geo_keeps_unknown_jurisdiction() { let req = build_request(); let config = ConsentConfig::default(); @@ -912,10 +825,6 @@ mod tests { Jurisdiction::Unknown, "missing geo should keep jurisdiction unknown" ); - assert!( - !allows_ec_creation(&ctx), - "missing geo should keep EC creation fail-closed" - ); } #[test] @@ -1071,408 +980,6 @@ mod tests { ); } - // ----------------------------------------------------------------------- - // allows_ec_creation tests - // ----------------------------------------------------------------------- - - /// Helper: builds a TCF consent with configurable Purpose 1 (storage). - fn make_tcf_with_storage(has_storage: bool) -> TcfConsent { - TcfBuilder::new().with_storage(has_storage).build() - } - - #[test] - fn ec_allowed_gdpr_with_storage_consent() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::Gdpr, - tcf: Some(make_tcf_with_storage(true)), - gdpr_applies: true, - ..ConsentContext::default() - }; - assert!( - allows_ec_creation(&ctx), - "GDPR + TCF Purpose 1 consented should allow EC" - ); - } - - #[test] - fn ec_blocked_gdpr_without_storage_consent() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::Gdpr, - tcf: Some(make_tcf_with_storage(false)), - gdpr_applies: true, - ..ConsentContext::default() - }; - assert!( - !allows_ec_creation(&ctx), - "GDPR + TCF Purpose 1 not consented should block EC" - ); - } - - #[test] - fn ec_blocked_gdpr_no_tcf_data() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::Gdpr, - tcf: None, - gpp: None, - gdpr_applies: true, - ..ConsentContext::default() - }; - assert!( - !allows_ec_creation(&ctx), - "GDPR with no TCF data should block EC" - ); - } - - #[test] - fn ec_allowed_gdpr_via_gpp_embedded_tcf() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::Gdpr, - tcf: None, - gpp: Some(GppConsent { - version: 1, - section_ids: vec![2], - eu_tcf: Some(make_tcf_with_storage(true)), - us_sale_opt_out: None, - }), - gdpr_applies: true, - ..ConsentContext::default() - }; - assert!( - allows_ec_creation(&ctx), - "GDPR + GPP embedded TCF with P1 consent should allow EC" - ); - } - - #[test] - fn ec_allowed_us_state_no_optout() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("CA".to_owned()), - us_privacy: Some(UsPrivacy { - version: 1, - notice_given: PrivacyFlag::Yes, - opt_out_sale: PrivacyFlag::No, - lspa_covered: PrivacyFlag::NotApplicable, - }), - ..ConsentContext::default() - }; - assert!( - allows_ec_creation(&ctx), - "US state + no opt-out should allow EC" - ); - } - - #[test] - fn ec_blocked_us_state_opted_out() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("CA".to_owned()), - us_privacy: Some(UsPrivacy { - version: 1, - notice_given: PrivacyFlag::Yes, - opt_out_sale: PrivacyFlag::Yes, - lspa_covered: PrivacyFlag::NotApplicable, - }), - ..ConsentContext::default() - }; - assert!( - !allows_ec_creation(&ctx), - "US state + opt-out should block EC" - ); - } - - #[test] - fn ec_blocked_us_state_gpc_implies_optout() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("CA".to_owned()), - us_privacy: None, - gpc: true, - ..ConsentContext::default() - }; - assert!( - !allows_ec_creation(&ctx), - "US state + GPC=true with no US Privacy string should block EC" - ); - } - - #[test] - fn ec_blocked_us_state_no_signals() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("CA".to_owned()), - us_privacy: None, - gpc: false, - ..ConsentContext::default() - }; - assert!( - !allows_ec_creation(&ctx), - "US state + no consent signals should block EC (spec \u{a7}6.1.1: fail-closed)" - ); - } - - #[test] - fn ec_allowed_non_regulated() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::NonRegulated, - ..ConsentContext::default() - }; - assert!( - allows_ec_creation(&ctx), - "non-regulated jurisdiction should always allow EC" - ); - } - - #[test] - fn ec_blocked_unknown_jurisdiction() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::Unknown, - ..ConsentContext::default() - }; - assert!( - !allows_ec_creation(&ctx), - "unknown jurisdiction should block EC (fail-closed when geo unavailable)" - ); - assert!( - !has_explicit_ec_withdrawal(&ctx), - "unknown jurisdiction should not be treated as an explicit withdrawal" - ); - } - - #[test] - fn ec_blocked_us_state_gpc_overrides_us_privacy() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("CA".to_owned()), - us_privacy: Some(UsPrivacy { - version: 1, - notice_given: PrivacyFlag::Yes, - opt_out_sale: PrivacyFlag::No, - lspa_covered: PrivacyFlag::NotApplicable, - }), - gpc: true, - ..ConsentContext::default() - }; - assert!( - !allows_ec_creation(&ctx), - "GPC=true should block EC even when US Privacy says no opt-out" - ); - assert!( - has_explicit_ec_withdrawal(&ctx), - "GPC=true should be treated as an explicit withdrawal signal" - ); - } - - #[test] - fn ec_us_privacy_not_applicable_allows_ec() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("VA".to_owned()), - us_privacy: Some(UsPrivacy { - version: 1, - notice_given: PrivacyFlag::NotApplicable, - opt_out_sale: PrivacyFlag::NotApplicable, - lspa_covered: PrivacyFlag::NotApplicable, - }), - ..ConsentContext::default() - }; - assert!( - allows_ec_creation(&ctx), - "US Privacy with opt_out=N/A should allow EC" - ); - } - - #[test] - fn ec_allowed_us_state_tcf_with_storage_consent() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("TN".to_owned()), - tcf: Some(make_tcf_with_storage(true)), - ..ConsentContext::default() - }; - assert!( - allows_ec_creation(&ctx), - "US state + TCF Purpose 1 consented should allow EC (Didomi-style CMP)" - ); - } - - #[test] - fn ec_blocked_us_state_tcf_without_storage_consent() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("TN".to_owned()), - tcf: Some(make_tcf_with_storage(false)), - ..ConsentContext::default() - }; - assert!( - !allows_ec_creation(&ctx), - "US state + TCF Purpose 1 denied should block EC" - ); - } - - #[test] - fn ec_blocked_us_state_gpc_overrides_tcf() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("TN".to_owned()), - tcf: Some(make_tcf_with_storage(true)), - gpc: true, - ..ConsentContext::default() - }; - assert!( - !allows_ec_creation(&ctx), - "GPC should block EC even when TCF grants storage consent in US state" - ); - } - - #[test] - fn ec_blocked_us_state_us_privacy_opt_out_overrides_tcf() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("CA".to_owned()), - tcf: Some(make_tcf_with_storage(true)), - us_privacy: Some(UsPrivacy { - version: 1, - notice_given: PrivacyFlag::Yes, - opt_out_sale: PrivacyFlag::Yes, - lspa_covered: PrivacyFlag::NotApplicable, - }), - ..ConsentContext::default() - }; - assert!( - !allows_ec_creation(&ctx), - "US Privacy opt-out should take priority over TCF consent" - ); - assert!( - has_explicit_ec_withdrawal(&ctx), - "US Privacy opt-out should be treated as an explicit withdrawal" - ); - } - - #[test] - fn ec_allowed_us_state_gpp_no_sale_opt_out() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("TN".to_owned()), - gpp: Some(GppConsent { - version: 1, - section_ids: vec![7], - eu_tcf: None, - us_sale_opt_out: Some(false), - }), - ..ConsentContext::default() - }; - assert!( - allows_ec_creation(&ctx), - "US state + GPP US sale_opt_out=false should allow EC" - ); - } - - #[test] - fn ec_blocked_us_state_gpp_sale_opted_out() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("TN".to_owned()), - gpp: Some(GppConsent { - version: 1, - section_ids: vec![7], - eu_tcf: None, - us_sale_opt_out: Some(true), - }), - ..ConsentContext::default() - }; - assert!( - !allows_ec_creation(&ctx), - "US state + GPP US sale_opt_out=true should block EC" - ); - assert!( - has_explicit_ec_withdrawal(&ctx), - "GPP US sale opt-out should be treated as an explicit withdrawal" - ); - } - - #[test] - fn ec_blocked_us_state_gpc_overrides_gpp_us() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("TN".to_owned()), - gpc: true, - gpp: Some(GppConsent { - version: 1, - section_ids: vec![7], - eu_tcf: None, - us_sale_opt_out: Some(false), - }), - ..ConsentContext::default() - }; - assert!( - !allows_ec_creation(&ctx), - "GPC should block EC even when GPP US says no opt-out" - ); - } - - #[test] - fn ec_us_state_gpp_us_opt_out_overrides_tcf() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("TN".to_owned()), - tcf: Some(make_tcf_with_storage(true)), - gpp: Some(GppConsent { - version: 1, - section_ids: vec![7], - eu_tcf: None, - us_sale_opt_out: Some(true), - }), - ..ConsentContext::default() - }; - assert!( - !allows_ec_creation(&ctx), - "GPP US opt-out should take priority over TCF consent" - ); - assert!( - has_explicit_ec_withdrawal(&ctx), - "GPP US opt-out should be treated as an explicit withdrawal" - ); - } - - #[test] - fn ec_us_state_us_privacy_opt_out_overrides_gpp_non_opt_out() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("TN".to_owned()), - gpp: Some(GppConsent { - version: 1, - section_ids: vec![7], - eu_tcf: None, - us_sale_opt_out: Some(false), - }), - us_privacy: Some(UsPrivacy { - version: 1, - notice_given: PrivacyFlag::Yes, - opt_out_sale: PrivacyFlag::Yes, - lspa_covered: PrivacyFlag::NotApplicable, - }), - ..ConsentContext::default() - }; - assert!( - !allows_ec_creation(&ctx), - "US Privacy opt-out should block EC even when GPP US has no sale opt-out" - ); - assert!( - has_explicit_ec_withdrawal(&ctx), - "US Privacy opt-out should be treated as an explicit withdrawal" - ); - } - - #[test] - fn ec_us_state_gpp_no_us_section_falls_through_to_us_privacy() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::UsState("CA".to_owned()), - gpp: Some(GppConsent { - version: 1, - section_ids: vec![2], - eu_tcf: None, - us_sale_opt_out: None, - }), - us_privacy: Some(UsPrivacy { - version: 1, - notice_given: PrivacyFlag::Yes, - opt_out_sale: PrivacyFlag::No, - lspa_covered: PrivacyFlag::NotApplicable, - }), - ..ConsentContext::default() - }; - assert!( - allows_ec_creation(&ctx), - "GPP without US section should fall through to us_privacy" - ); - } - // ----------------------------------------------------------------------- // Consent KV read-fallback / write-on-change pipeline tests // ----------------------------------------------------------------------- @@ -1629,4 +1136,86 @@ mod tests { "should not persist consent without an EC ID" ); } + + #[test] + fn gate_eids_keeps_eids_when_required_permissions_are_set() { + // US maps to us-opt-out, where necessary.operations.storage and advertising_marketing.first_party.targeted + // are granted with no signal, so bidstream EIDs are transmitted. + let permissions = + crate::permissions::PermissionMaps::standard().resolve(Some("US"), None, |_| false); + let eids = Some(vec!["eid-1".to_owned()]); + assert!( + gate_eids_by_permissions(eids, &permissions).is_some(), + "EIDs should pass when necessary.operations.storage and advertising_marketing.first_party.targeted are set" + ); + } + + #[test] + fn gate_eids_strips_eids_when_a_required_permission_is_unset() { + // FR maps to gdpr-eu, where every purpose is requires_signal, so with no + // signal neither required permission is set and EIDs are stripped. + let permissions = + crate::permissions::PermissionMaps::standard().resolve(Some("FR"), None, |_| false); + let eids = Some(vec!["eid-1".to_owned()]); + assert!( + gate_eids_by_permissions(eids, &permissions).is_none(), + "EIDs should be stripped when a required permission is not set" + ); + } + + #[test] + fn gate_eids_returns_none_for_empty_input() { + let permissions = + crate::permissions::PermissionMaps::standard().resolve(Some("US"), None, |_| false); + assert!( + gate_eids_by_permissions::(None, &permissions).is_none(), + "no EIDs should resolve to None" + ); + assert!( + gate_eids_by_permissions(Some(Vec::::new()), &permissions).is_none(), + "an empty EID list should resolve to None" + ); + } + + #[test] + fn has_storage_optout_signal_detects_us_style_opt_outs() { + let gpc = ConsentContext { + gpc: true, + ..ConsentContext::default() + }; + assert!(has_storage_optout_signal(&gpc), "GPC is a storage opt-out"); + + let gpp_sale_opt_out = ConsentContext { + gpp: Some(GppConsent { + version: 1, + section_ids: vec![8], + eu_tcf: None, + us_sale_opt_out: Some(true), + }), + ..ConsentContext::default() + }; + assert!( + has_storage_optout_signal(&gpp_sale_opt_out), + "a GPP US sale opt-out is a storage opt-out" + ); + + let usp_opt_out = ConsentContext { + us_privacy: Some(UsPrivacy { + version: 1, + notice_given: PrivacyFlag::Yes, + opt_out_sale: PrivacyFlag::Yes, + lspa_covered: PrivacyFlag::No, + }), + ..ConsentContext::default() + }; + assert!( + has_storage_optout_signal(&usp_opt_out), + "a US Privacy sale opt-out is a storage opt-out" + ); + + assert!( + !has_storage_optout_signal(&ConsentContext::default()), + "no signal is not a storage opt-out" + ); + } } diff --git a/crates/trusted-server-core/src/consent/types.rs b/crates/trusted-server-core/src/consent/types.rs index 73c2bbc3f..2cf8a6a8e 100644 --- a/crates/trusted-server-core/src/consent/types.rs +++ b/crates/trusted-server-core/src/consent/types.rs @@ -149,6 +149,21 @@ pub struct ConsentContext { } impl ConsentContext { + /// Whether any consent record is present in raw form but failed to decode. + /// + /// A malformed record is not the same as no record: the visitor expressed + /// a preference that could not be read, so the permission mapping blocks + /// baseline grants (fail-closed) instead of degrading to the no-signal + /// baseline. An expired TCF record is excluded because expiry is its own + /// explicit state ([`expired`](Self::expired)): the raw string is kept for + /// proxy forwarding while the decoded record is deliberately cleared. + #[must_use] + pub fn has_malformed_record(&self) -> bool { + (self.raw_tc_string.is_some() && self.tcf.is_none() && !self.expired) + || (self.raw_gpp_string.is_some() && self.gpp.is_none()) + || (self.raw_us_privacy.is_some() && self.us_privacy.is_none()) + } + /// Returns `true` when no consent signals are present. #[must_use] pub fn is_empty(&self) -> bool { diff --git a/crates/trusted-server-core/src/constants.rs b/crates/trusted-server-core/src/constants.rs index e1152b1e7..cd710aaa4 100644 --- a/crates/trusted-server-core/src/constants.rs +++ b/crates/trusted-server-core/src/constants.rs @@ -1,6 +1,11 @@ use http::header::HeaderName; pub const COOKIE_TS_EC: &str = "ts-ec"; +/// Non-`HttpOnly` companion to [`COOKIE_TS_EC`], set when a client-cycle +/// resolve succeeds. It carries no identity (the value is `1`); it only lets +/// the page script see that an Edge Cookie exists, which the `HttpOnly` cookie +/// itself cannot, so the script does not re-post on every page view. +pub const COOKIE_TS_EC_RESOLVED: &str = "ts-ecr"; /// Cookie written by the Trusted Server JS SDK containing a standard-base64-encoded /// JSON array of Extended User IDs (`[{ source, uids }]`) from identity providers. pub const COOKIE_TS_EIDS: &str = "ts-eids"; diff --git a/crates/trusted-server-core/src/ec/consent.rs b/crates/trusted-server-core/src/ec/consent.rs index ad9f5dd29..98b864bf3 100644 --- a/crates/trusted-server-core/src/ec/consent.rs +++ b/crates/trusted-server-core/src/ec/consent.rs @@ -1,77 +1,664 @@ -//! EC-specific consent gating. +//! EC-specific permission gating, resolved through the permission model. //! -//! This module provides the public consent-check API for the EC subsystem. -//! The underlying logic lives in [`crate::consent::allows_ec_creation`]; this -//! wrapper exists so that EC callers can import from `ec::consent` and the -//! eventual migration path (renaming, adding EC-specific conditions) is -//! contained here. +//! The Edge Cookie provider advertises the [`Permission`]s its data use +//! requires. [`assemble_permissions`] resolves which permissions are set for a +//! request, from its session signals and the country it maps to, and the +//! context construction gates the provider on that state. The EC permission +//! decision lives here, in the EC subsystem, and nowhere else, so callers +//! route every EC permission check through this module rather than +//! re-deriving one. use crate::consent::ConsentContext; +use crate::permissions::{ + Acquisition, ConsentSignal, OptOutSource, Permission, PermissionMaps, PermissionState, + SignalPolicy, +}; +use crate::platform::GeoInfo; +use crate::settings::Settings; -/// Determines whether Edge Cookie creation is permitted based on the -/// user's consent and detected jurisdiction. +/// The outcome of the geo lookup for a request, separating "no location +/// resolved" from "the lookup failed". /// -/// This is the canonical entry point for EC consent checks. It delegates -/// to [`crate::consent::allows_ec_creation`] today but may diverge as -/// EC-specific consent rules evolve. +/// The two must not collapse: with no location (the provider is disabled, or +/// had no data for the address) the deployer's `[geo] default_country` +/// baseline applies, but when the lookup errored the request's location is +/// unknown in a way the deployer default must not paper over, so every +/// permission resolves to the requires-signal floor instead. +#[derive(Debug, Clone, Copy)] +pub enum GeoStatus<'a> { + /// The provider resolved a location. + Located(&'a GeoInfo), + /// The provider resolved no location, so the configured default applies. + NoLocation, + /// The lookup errored, so the requires-signal floor applies. + Failed, +} + +impl<'a> GeoStatus<'a> { + /// The resolved location, when one exists. + #[must_use] + pub fn info(self) -> Option<&'a GeoInfo> { + match self { + GeoStatus::Located(info) => Some(info), + GeoStatus::NoLocation | GeoStatus::Failed => None, + } + } +} + +impl<'a> From> for GeoStatus<'a> { + fn from(geo: Option<&'a GeoInfo>) -> Self { + match geo { + Some(info) => GeoStatus::Located(info), + None => GeoStatus::NoLocation, + } + } +} + +/// The configured `[geo] default_country` as a [`GeoInfo`], for jurisdiction +/// detection when the geo provider resolves no location. +/// +/// The consent gates (for example the server-side auction gate) detect a +/// jurisdiction from geolocation. With no location they would resolve +/// `Unknown` and fail closed even where the deployer has declared a default +/// jurisdiction, so the same fallback the permission model applies is +/// offered here: the default country and region stand in for the missing +/// location. Only the country and region carry meaning; every other field is +/// empty. A failed lookup must not use this (see [`GeoStatus::Failed`]), so +/// the caller decides when to apply it. +#[must_use] +pub fn default_location_geo(settings: &Settings) -> Option { + let (country, region) = default_location(settings); + let country = country?; + Some(GeoInfo { + city: String::new(), + country: country.to_owned(), + continent: String::new(), + latitude: 0.0, + longitude: 0.0, + metro_code: 0, + region: region.map(str::to_owned), + asn: None, + }) +} + +/// Splits the configured `[geo] default_country` into its country and region +/// parts (`US/CA` names a country and region, `US` a bare country). +fn default_location(settings: &Settings) -> (Option<&str>, Option<&str>) { + match settings.geo.default_country.as_deref() { + Some(spec) => match spec.split_once('/') { + Some((country, region)) => (Some(country), Some(region)), + None => (Some(spec), None), + }, + None => (None, None), + } +} + +/// Assembles the permission state for a request: the country/region baseline +/// from the default maps in `permissions.yaml`, augmented by the session's +/// signals. /// -/// See [`crate::consent::allows_ec_creation`] for the full decision matrix. +/// Permissions exist without a consent model. With no signal present the result +/// is simply the baseline for the request's country and region. When the geo +/// provider resolves no location, or a country/region that has no rule, the +/// deployer's configured `[geo] default_country` applies. A default is required, +/// so it is always available. A failed lookup ([`GeoStatus::Failed`]) instead +/// resolves every permission to the requires-signal floor, so an outage is +/// handled protectively rather than as the deployer's default jurisdiction. #[must_use] -pub fn ec_consent_granted(consent_context: &ConsentContext) -> bool { - crate::consent::allows_ec_creation(consent_context) +pub fn assemble_permissions( + settings: &Settings, + consent: &ConsentContext, + geo: GeoStatus<'_>, +) -> PermissionState { + let maps = PermissionMaps::standard(); + let (default_country, default_region) = match geo { + GeoStatus::Failed => (None, None), + GeoStatus::Located(_) | GeoStatus::NoLocation => default_location(settings), + }; + let info = geo.info(); + maps.resolve_with( + info.map(|info| info.country.as_str()), + info.and_then(|info| info.region.as_deref()), + default_country, + default_region, + permission_signal(consent, maps.signals()), + ) } -/// Returns `true` when the request carries an explicit EC withdrawal signal. +/// The acquisition rule for Edge Cookie storage in the request's resolved +/// jurisdiction, used to scope destructive withdrawal. /// -/// This is intentionally stricter than [`ec_consent_granted`]. A fail-closed -/// result such as unknown jurisdiction or missing consent data must not be -/// treated as an authoritative withdrawal of an already-issued EC. +/// Resolves the same rules as [`assemble_permissions`] (the request's +/// country/region, the configured default when unmatched, and the +/// requires-signal floor when the lookup failed or nothing resolves) and +/// returns the rule for [`Permission::StoreOnDevice`]. #[must_use] -pub fn ec_consent_withdrawn(consent_context: &ConsentContext) -> bool { - crate::consent::has_explicit_ec_withdrawal(consent_context) +pub fn storage_acquisition(settings: &Settings, geo: GeoStatus<'_>) -> Acquisition { + let maps = PermissionMaps::standard(); + let (default_country, default_region) = match geo { + GeoStatus::Failed => (None, None), + GeoStatus::Located(_) | GeoStatus::NoLocation => default_location(settings), + }; + let info = geo.info(); + maps.rules_or_default( + info.map(|info| info.country.as_str()), + info.and_then(|info| info.region.as_deref()), + default_country, + default_region, + ) + .map_or(Acquisition::RequiresSignal, |rules| { + rules.rule_for(Permission::StoreOnDevice) + }) +} + +/// Maps a consent context to a [`ConsentSignal`] for each permission, applying +/// the [`SignalPolicy`] the permission model parsed from `permissions.yaml`. +/// +/// This is the only place the EC subsystem reads consent signals. The policy, +/// not this function, decides which sources are authoritative, which TCF purpose +/// maps to which Data Use, and what a US-style opt-out revokes. This function +/// only decodes the request and applies that policy, so no signal-to-permission +/// policy lives in the code. +/// +/// It considers every source the policy names: a TCF record (a standalone TC +/// string or the EU TCF section of a GPP string), and the US-style opt-out +/// signals (GPC, a GPP sale opt-out, or a US Privacy opt-out). Precedence is +/// most-restrictive-first and is fixed in code, not policy: +/// +/// 1. A US-style opt-out revokes the Data Uses the policy lists, even when a +/// TCF record consents. An opt-out is an explicit user signal, so no other +/// signal may override it. +/// 2. A consent record that is present but cannot be decoded revokes +/// everything, so an unreadable expression of preference fails closed +/// instead of degrading to the no-signal baseline. +/// 3. When the policy marks TCF authoritative, a present TCF record then +/// decides the mapped Data Uses: granted where the record consents to the +/// mapped purpose, revoked where it does not, and neutral where no purpose +/// is mapped. The `authoritative` flag governs only whether TCF grants and +/// revokes apply, never whether an opt-out may be overridden. +/// +/// Whether a `Revoke` changes anything is decided by the country/region map, +/// which drops a `granted` baseline and has nothing to drop where the +/// permission is `requires_signal` or `denied`. +fn permission_signal<'a>( + consent: &'a ConsentContext, + signals: &'a SignalPolicy, +) -> impl Fn(Permission) -> ConsentSignal + 'a { + move |permission| { + if opt_out_present(consent, signals.opt_out_sources()) + && signals.opt_out_revokes(permission) + { + return ConsentSignal::Revoke; + } + if consent.has_malformed_record() { + return ConsentSignal::Revoke; + } + if signals.tcf_authoritative() + && let Some(tcf) = crate::consent::effective_tcf(consent) + { + return match signals.tcf_purpose(permission) { + Some(purpose) => { + if tcf.has_purpose_consent(usize::from(purpose)) { + ConsentSignal::Grant + } else { + ConsentSignal::Revoke + } + } + None => ConsentSignal::Neutral, + }; + } + ConsentSignal::Neutral + } +} + +/// Whether the request carries any of the `sources` a US-style opt-out is +/// declared to use. Decoding only, so the policy (not this function) decides +/// which sources count and what the opt-out revokes. +fn opt_out_present(consent: &ConsentContext, sources: &[OptOutSource]) -> bool { + sources.iter().any(|source| match source { + OptOutSource::Gpc => consent.gpc, + OptOutSource::GppSaleOptOut => { + consent.gpp.as_ref().and_then(|gpp| gpp.us_sale_opt_out) == Some(true) + } + OptOutSource::UsPrivacyOptOut => consent + .us_privacy + .as_ref() + .is_some_and(|usp| usp.opt_out_sale == crate::consent::PrivacyFlag::Yes), + }) +} + +/// Reports whether the request carries an explicit signal withdrawing Edge +/// Cookie storage, rather than merely lacking the permission. +/// +/// This separates an affirmative withdrawal (which expires the browser cookie +/// and writes the authoritative identity-graph tombstone) from suppression, +/// where the permission is simply not set for this request (which strips EC +/// response headers but must not destroy an already-issued identifier, or a +/// returning user would be permanently withdrawn before they ever get to +/// consent). +/// +/// Only a TCF record refusing storage (Purpose 1) withdraws, and only where +/// the jurisdiction's storage baseline is not `granted`: under a +/// `requires_signal` baseline the refusal is the visitor declining the very +/// signal storage depends on, while under a `granted` baseline storage never +/// depended on the record, so the refusal suppresses use without destroying +/// the identifier. US-style opt-outs (GPC, a GPP sale opt-out, or a US +/// Privacy opt-out) suppress the permissions the policy revokes but are +/// never destructive, and no signal at all is not a withdrawal. +#[must_use] +pub fn ec_storage_withdrawn(consent: &ConsentContext, storage_baseline: Acquisition) -> bool { + if let Some(tcf) = crate::consent::effective_tcf(consent) { + return !tcf.has_storage_consent() && !matches!(storage_baseline, Acquisition::Granted); + } + false } #[cfg(test)] mod tests { use super::*; - use crate::consent::jurisdiction::Jurisdiction; + use crate::consent::TcfConsent; + use crate::test_support::tests::create_test_settings; + + /// Builds a minimal decoded TCF record consenting to the given 1-indexed + /// purposes, with everything else refused. + fn tcf_with_purposes(consented: &[usize]) -> TcfConsent { + let mut purpose_consents = vec![false; 24]; + for &purpose in consented { + purpose_consents[purpose - 1] = true; + } + TcfConsent { + version: 2, + cmp_id: 0, + cmp_version: 0, + consent_screen: 0, + consent_language: "EN".to_owned(), + vendor_list_version: 0, + tcf_policy_version: 2, + created_ds: 0, + last_updated_ds: 0, + purpose_consents, + purpose_legitimate_interests: vec![false; 24], + vendor_consents: Vec::new(), + vendor_legitimate_interests: Vec::new(), + special_feature_opt_ins: vec![false; 12], + } + } + + #[test] + fn hmac_provider_is_blocked_without_a_storage_signal() { + // The test settings select the HMAC provider, which requires + // necessary.operations.storage. The configured default country (FR) + // resolves storage as requires-signal, so with no signal the + // permission is not set and the provider's requirement is not met. + let settings = create_test_settings(); + let provider = crate::ec::provider::build_provider(&settings.ec, None, None) + .expect("should build the configured provider") + .expect("should select the hmac provider"); + let state = + assemble_permissions(&settings, &ConsentContext::default(), GeoStatus::NoLocation); + assert!( + !state.all_set(provider.required_permissions()), + "the requires-signal default should not satisfy the HMAC provider without a signal" + ); + } + + fn us_ca_geo() -> GeoInfo { + GeoInfo { + city: String::new(), + country: "US".to_owned(), + continent: String::new(), + latitude: 0.0, + longitude: 0.0, + metro_code: 0, + region: Some("CA".to_owned()), + asn: None, + } + } + + #[test] + fn no_signal_uses_the_us_opt_out_baseline() { + // US/CA maps to the us-opt-out group, where every purpose is granted + // without a signal, so EC identity and bidstream EIDs are both permitted. + let settings = create_test_settings(); + let geo = us_ca_geo(); + let state = assemble_permissions( + &settings, + &ConsentContext::default(), + GeoStatus::Located(&geo), + ); + assert!( + state.is_set(Permission::StoreOnDevice) + && state.is_set(Permission::SelectPersonalisedAds), + "a US opt-out state should grant necessary.operations.storage and advertising_marketing.first_party.targeted" + ); + } + + #[test] + fn gpc_revokes_the_granted_baseline_in_a_us_opt_out_state() { + // A US-style opt-out drops a granted baseline with no jurisdiction match: + // the map granted these purposes, and GPC revokes them. + let settings = create_test_settings(); + let consent = ConsentContext { + gpc: true, + ..ConsentContext::default() + }; + let geo = us_ca_geo(); + let state = assemble_permissions(&settings, &consent, GeoStatus::Located(&geo)); + assert!( + !state.is_set(Permission::StoreOnDevice) + && !state.is_set(Permission::SelectPersonalisedAds), + "GPC should revoke the granted necessary.operations.storage and advertising_marketing.first_party.targeted baseline" + ); + } + + // ------------------------------------------------------------------ + // Opt-out precedence pinning tests. These reinstate the behavior the + // consent module enforced before the permission model: an explicit + // opt-out signal suppresses storage and sharing even when a TCF record + // consents. The permission model must never let a CMP-written record + // override the visitor's own opt-out. + // ------------------------------------------------------------------ + + #[test] + fn gpc_suppresses_storage_even_with_a_consenting_tcf_record() { + let settings = create_test_settings(); + let consent = ConsentContext { + tcf: Some(tcf_with_purposes(&[1, 4])), + gpc: true, + ..ConsentContext::default() + }; + let geo = us_ca_geo(); + let state = assemble_permissions(&settings, &consent, GeoStatus::Located(&geo)); + assert!( + !state.is_set(Permission::StoreOnDevice) + && !state.is_set(Permission::SelectPersonalisedAds), + "GPC should suppress storage and sharing even when the TCF record consents" + ); + } + + #[test] + fn us_privacy_opt_out_suppresses_storage_even_with_a_consenting_tcf_record() { + let settings = create_test_settings(); + let consent = ConsentContext { + tcf: Some(tcf_with_purposes(&[1, 4])), + us_privacy: Some(crate::consent::types::UsPrivacy { + version: 1, + notice_given: crate::consent::PrivacyFlag::Yes, + opt_out_sale: crate::consent::PrivacyFlag::Yes, + lspa_covered: crate::consent::PrivacyFlag::NotApplicable, + }), + ..ConsentContext::default() + }; + let geo = us_ca_geo(); + let state = assemble_permissions(&settings, &consent, GeoStatus::Located(&geo)); + assert!( + !state.is_set(Permission::StoreOnDevice) + && !state.is_set(Permission::SelectPersonalisedAds), + "a US Privacy opt-out should suppress storage and sharing even when the TCF record consents" + ); + } + + #[test] + fn gpp_sale_opt_out_suppresses_storage_even_with_a_consenting_tcf_record() { + let settings = create_test_settings(); + let consent = ConsentContext { + tcf: Some(tcf_with_purposes(&[1, 4])), + gpp: Some(crate::consent::types::GppConsent { + version: 1, + section_ids: vec![7], + eu_tcf: None, + us_sale_opt_out: Some(true), + }), + ..ConsentContext::default() + }; + let geo = us_ca_geo(); + let state = assemble_permissions(&settings, &consent, GeoStatus::Located(&geo)); + assert!( + !state.is_set(Permission::StoreOnDevice) + && !state.is_set(Permission::SelectPersonalisedAds), + "a GPP sale opt-out should suppress storage and sharing even when the TCF record consents" + ); + } + + #[test] + fn gpc_suppresses_storage_even_when_us_privacy_reports_no_opt_out() { + let settings = create_test_settings(); + let consent = ConsentContext { + gpc: true, + us_privacy: Some(crate::consent::types::UsPrivacy { + version: 1, + notice_given: crate::consent::PrivacyFlag::Yes, + opt_out_sale: crate::consent::PrivacyFlag::No, + lspa_covered: crate::consent::PrivacyFlag::NotApplicable, + }), + ..ConsentContext::default() + }; + let geo = us_ca_geo(); + let state = assemble_permissions(&settings, &consent, GeoStatus::Located(&geo)); + assert!( + !state.is_set(Permission::StoreOnDevice), + "any one opt-out source should suppress, whatever the others say" + ); + } + + // ------------------------------------------------------------------ + // Withdrawal scoping: only a TCF storage refusal withdraws, and only + // where the baseline did not grant storage outright. Opt-outs suppress + // use but never destroy an already-issued identifier. + // ------------------------------------------------------------------ #[test] - fn ec_consent_granted_allows_non_regulated_requests() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::NonRegulated, + fn tcf_storage_refusal_withdraws_under_a_requires_signal_baseline() { + let consent = ConsentContext { + tcf: Some(tcf_with_purposes(&[4])), ..ConsentContext::default() }; + assert!( + ec_storage_withdrawn(&consent, Acquisition::RequiresSignal), + "refusing the signal storage depends on should withdraw" + ); + } + #[test] + fn tcf_storage_refusal_does_not_withdraw_under_a_granted_baseline() { + let consent = ConsentContext { + tcf: Some(tcf_with_purposes(&[4])), + ..ConsentContext::default() + }; assert!( - ec_consent_granted(&ctx), - "non-regulated requests should be allowed" + !ec_storage_withdrawn(&consent, Acquisition::Granted), + "storage never depended on the record here, so refusal suppresses without destroying" ); } #[test] - fn ec_consent_granted_blocks_unknown_jurisdiction() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::Unknown, + fn tcf_storage_consent_is_not_a_withdrawal() { + let consent = ConsentContext { + tcf: Some(tcf_with_purposes(&[1])), ..ConsentContext::default() }; + assert!( + !ec_storage_withdrawn(&consent, Acquisition::RequiresSignal), + "a consenting record is not a withdrawal" + ); + } + #[test] + fn gpc_alone_never_withdraws() { + let consent = ConsentContext { + gpc: true, + ..ConsentContext::default() + }; assert!( - !ec_consent_granted(&ctx), - "unknown jurisdiction should fail closed" + !ec_storage_withdrawn(&consent, Acquisition::Granted) + && !ec_storage_withdrawn(&consent, Acquisition::RequiresSignal), + "GPC suppresses use for the request but never destroys the identifier" ); } #[test] - fn ec_consent_withdrawn_does_not_treat_unknown_jurisdiction_as_revocation() { - let ctx = ConsentContext { - jurisdiction: Jurisdiction::Unknown, + fn us_style_opt_outs_never_withdraw() { + let consent = ConsentContext { + us_privacy: Some(crate::consent::types::UsPrivacy { + version: 1, + notice_given: crate::consent::PrivacyFlag::Yes, + opt_out_sale: crate::consent::PrivacyFlag::Yes, + lspa_covered: crate::consent::PrivacyFlag::NotApplicable, + }), + gpp: Some(crate::consent::types::GppConsent { + version: 1, + section_ids: vec![7], + eu_tcf: None, + us_sale_opt_out: Some(true), + }), ..ConsentContext::default() }; + assert!( + !ec_storage_withdrawn(&consent, Acquisition::RequiresSignal), + "sale opt-outs suppress use but never destroy the identifier" + ); + } + #[test] + fn no_signal_is_not_a_withdrawal() { + assert!( + !ec_storage_withdrawn(&ConsentContext::default(), Acquisition::RequiresSignal), + "absence of a signal must never destroy an identifier" + ); + } + + #[test] + fn a_malformed_record_is_not_a_withdrawal() { + let consent = ConsentContext { + raw_tc_string: Some("not-a-tc-string".to_owned()), + ..ConsentContext::default() + }; + assert!( + !ec_storage_withdrawn(&consent, Acquisition::RequiresSignal), + "an unreadable record fails closed (suppression), not destructively" + ); + } + + // ------------------------------------------------------------------ + // Malformed-but-present records block baseline grants (fail closed) + // instead of degrading to the no-signal baseline. + // ------------------------------------------------------------------ + + #[test] + fn a_malformed_tcf_record_blocks_baseline_grants() { + let settings = create_test_settings(); + let consent = ConsentContext { + raw_tc_string: Some("not-a-tc-string".to_owned()), + ..ConsentContext::default() + }; + let geo = us_ca_geo(); + let state = assemble_permissions(&settings, &consent, GeoStatus::Located(&geo)); + assert!( + !state.is_set(Permission::StoreOnDevice), + "an unreadable record should block the granted baseline, not vanish" + ); + } + + #[test] + fn a_malformed_gpp_or_us_privacy_record_is_detected() { + let gpp = ConsentContext { + raw_gpp_string: Some("not-a-gpp-string".to_owned()), + ..ConsentContext::default() + }; + let usp = ConsentContext { + raw_us_privacy: Some("bogus".to_owned()), + ..ConsentContext::default() + }; + assert!( + gpp.has_malformed_record() && usp.has_malformed_record(), + "each undecodable record form should be detected" + ); + } + + #[test] + fn an_expired_tcf_record_is_not_treated_as_malformed() { + let settings = create_test_settings(); + let consent = ConsentContext { + raw_tc_string: Some("CPc-old-string".to_owned()), + expired: true, + ..ConsentContext::default() + }; + let geo = us_ca_geo(); + let state = assemble_permissions(&settings, &consent, GeoStatus::Located(&geo)); + assert!( + state.is_set(Permission::StoreOnDevice), + "expiry is its own explicit state, deliberately distinct from malformed" + ); + } + + // ------------------------------------------------------------------ + // Geo status: a failed lookup resolves at the requires-signal floor, + // while no location falls back to the configured default. + // ------------------------------------------------------------------ + + #[test] + fn a_failed_geo_lookup_resolves_to_the_requires_signal_floor() { + let mut settings = create_test_settings(); + settings.geo.default_country = Some("US/CA".to_owned()); + let state = assemble_permissions(&settings, &ConsentContext::default(), GeoStatus::Failed); + assert!( + !state.is_set(Permission::StoreOnDevice), + "a lookup failure must not fall back to the deployer default baseline" + ); + assert_eq!( + storage_acquisition(&settings, GeoStatus::Failed), + Acquisition::RequiresSignal, + "the storage baseline follows the same floor on failure" + ); + } + + #[test] + fn no_location_falls_back_to_the_configured_default() { + let mut settings = create_test_settings(); + settings.geo.default_country = Some("US/CA".to_owned()); + let state = + assemble_permissions(&settings, &ConsentContext::default(), GeoStatus::NoLocation); + assert!( + state.is_set(Permission::StoreOnDevice), + "no location should resolve at the configured default baseline" + ); + assert_eq!( + storage_acquisition(&settings, GeoStatus::NoLocation), + Acquisition::Granted, + "the storage baseline follows the default on no location" + ); + } + + #[test] + fn tcf_resolves_every_mapped_purpose_not_just_storage_and_ads() { + // A TCF record now grants or revokes every one of the eleven mapped + // purposes, not only Purpose 1 and Purpose 4. Consent to all purposes + // except Purpose 7 (measure ad performance), in a US opt-out state where + // the baseline granted them all, so a revoke is observable as a drop. + let settings = create_test_settings(); + let consented: Vec = (1..=11).filter(|&p| p != 7).collect(); + let consent = ConsentContext { + tcf: Some(tcf_with_purposes(&consented)), + ..ConsentContext::default() + }; + let geo = us_ca_geo(); + let state = assemble_permissions(&settings, &consent, GeoStatus::Located(&geo)); + + // Purpose 2 is now resolved (it was neutral before), so consent sets it. + assert!( + state.is_set(Permission::SelectBasicAds), + "Purpose 2 consent should set advertising_marketing.first_party.contextual" + ); + // Purpose 7 was refused, so the granted baseline is revoked. + assert!( + !state.is_set(Permission::MeasureAdPerformance), + "Purpose 7 refusal should revoke analytics.ad_reporting.measure_ad_performance" + ); + // The originally wired purposes still behave. assert!( - !ec_consent_withdrawn(&ctx), - "unknown jurisdiction should block creation without revoking existing EC" + state.is_set(Permission::StoreOnDevice) + && state.is_set(Permission::SelectPersonalisedAds), + "Purposes 1 and 4 remain resolved from the TCF record" ); } } diff --git a/crates/trusted-server-core/src/ec/cookies.rs b/crates/trusted-server-core/src/ec/cookies.rs index ac0e0c05b..644f8d93e 100644 --- a/crates/trusted-server-core/src/ec/cookies.rs +++ b/crates/trusted-server-core/src/ec/cookies.rs @@ -13,75 +13,35 @@ //! endpoint (`/_ts/api/v1/identify`) exposes the EC ID in its response //! body for legitimate JS use cases. -use std::borrow::Cow; - use edgezero_core::body::Body as EdgeBody; use http::{HeaderValue, Response, header}; -use crate::constants::COOKIE_TS_EC; +use crate::constants::{COOKIE_TS_EC, COOKIE_TS_EC_RESOLVED}; use crate::settings::Settings; /// Maximum age for the EC cookie (1 year in seconds). const COOKIE_MAX_AGE: i32 = 365 * 24 * 60 * 60; +/// Maximum length in bytes of an Edge Cookie identifier. +/// +/// A global bound enforced wherever an identifier enters the system (mint, +/// cookie read-back, cookie write), so no provider can emit a value the cookie +/// layer, logs, or the KV key space cannot carry. +pub(crate) const MAX_EC_ID_LEN: usize = 256; + fn is_allowed_ec_id_char(c: char) -> bool { - c.is_ascii_alphanumeric() || matches!(c, '.' | '-' | '_') + c.is_ascii_alphanumeric() || matches!(c, '.' | '-' | '_' | '~') } -// Outbound allowlist for cookie sanitization: permits [a-zA-Z0-9._-] as a -// defense-in-depth backstop when setting the Set-Cookie header. This is -// intentionally broader than the inbound format validator +// Identifier allowlist: [A-Za-z0-9._~-], the cookie-safe alphabet every +// Edge Cookie identifier must fit regardless of which provider minted it. +// This is intentionally broader than the built-in format validator // (`generation::is_valid_ec_id`), which enforces the exact -// `<64-hex>.<6-alphanumeric>` structure and is used to reject untrusted -// request values before they enter the system. +// `<64-hex>.<6-alphanumeric>` structure of the HMAC provider; an opaque +// vendor identifier only has to fit the alphabet and the length bound. #[must_use] pub(crate) fn ec_id_has_only_allowed_chars(ec_id: &str) -> bool { - ec_id.chars().all(is_allowed_ec_id_char) -} - -fn sanitize_ec_id_for_cookie(ec_id: &str) -> Cow<'_, str> { - if ec_id_has_only_allowed_chars(ec_id) { - return Cow::Borrowed(ec_id); - } - - let safe_id = ec_id - .chars() - .filter(|c| is_allowed_ec_id_char(*c)) - .collect::(); - - log::warn!( - "Stripped disallowed characters from EC ID before setting cookie (len {} -> {}); \ - callers should reject invalid request IDs before cookie creation", - ec_id.len(), - safe_id.len(), - ); - - Cow::Owned(safe_id) -} - -/// Returns `true` if every byte in `value` is a valid RFC 6265 `cookie-octet`. -/// An empty string is always rejected. -/// -/// RFC 6265 restricts cookie values to printable US-ASCII excluding whitespace, -/// double-quote, comma, semicolon, and backslash. Rejecting these characters -/// prevents header-injection attacks where a crafted value could append -/// spurious cookie attributes (e.g. `evil; Domain=.attacker.com`). -/// -/// Non-ASCII characters (multi-byte UTF-8) are always rejected because their -/// byte values exceed `0x7E`. -#[must_use] -fn is_safe_cookie_value(value: &str) -> bool { - // RFC 6265 §4.1.1 cookie-octet: - // 0x21 — '!' - // 0x23–0x2B — '#' through '+' (excludes 0x22 DQUOTE) - // 0x2D–0x3A — '-' through ':' (excludes 0x2C comma) - // 0x3C–0x5B — '<' through '[' (excludes 0x3B semicolon) - // 0x5D–0x7E — ']' through '~' (excludes 0x5C backslash, 0x7F DEL) - // All control characters (0x00–0x20) and non-ASCII (0x80+) are also excluded. - !value.is_empty() - && value - .bytes() - .all(|b| matches!(b, 0x21 | 0x23..=0x2B | 0x2D..=0x3A | 0x3C..=0x5B | 0x5D..=0x7E)) + !ec_id.is_empty() && ec_id.len() <= MAX_EC_ID_LEN && ec_id.chars().all(is_allowed_ec_id_char) } /// Formats a `Set-Cookie` header value for the EC cookie. @@ -98,61 +58,95 @@ fn format_set_cookie(domain: &str, value: &str, max_age: i32) -> String { /// /// Per spec §5.2, the EC cookie domain is computed from /// `settings.publisher.domain` (not `cookie_domain`) to ensure the EC -/// cookie is always scoped to the publisher's apex domain. The EC ID is -/// sanitized through a narrow outbound allowlist as a defense-in-depth -/// backstop against header injection. +/// cookie is always scoped to the publisher's apex domain. Callers validate +/// the identifier with [`ec_id_has_only_allowed_chars`] before this point; +/// an identifier is rejected outright rather than rewritten, so the cookie +/// value and the identity-graph key can never silently diverge. #[must_use] pub(crate) fn create_ec_cookie(settings: &Settings, ec_id: &str) -> String { - let safe_id = sanitize_ec_id_for_cookie(ec_id); - format_set_cookie( &settings.publisher.ec_cookie_domain(), - safe_id.as_ref(), + ec_id, COOKIE_MAX_AGE, ) } /// Sets the EC ID cookie on the given response. /// -/// Validates `ec_id` against RFC 6265 `cookie-octet` rules before -/// interpolation. If the value contains unsafe characters (e.g. semicolons), -/// the cookie is not set and a warning is logged. This prevents an attacker -/// from injecting spurious cookie attributes via a controlled ID value. +/// Validates `ec_id` against the identifier alphabet and length bound before +/// interpolation. An identifier that fails validation is rejected and the +/// cookie is not set, with an error logged; the value is never rewritten, so +/// a provider identifier survives byte for byte or not at all. This also +/// prevents an attacker from injecting spurious cookie attributes via a +/// controlled ID value. /// /// `cookie_domain` comes from operator configuration and is considered trusted. -/// -/// # Panics (debug only) -/// -/// Debug-asserts that `ec_id` passes [`super::generation::is_valid_ec_id`] -/// as a defense-in-depth check against cookie injection. pub fn set_ec_cookie(settings: &Settings, response: &mut Response, ec_id: &str) { - if !is_safe_cookie_value(ec_id) { - log::warn!( - "Rejecting EC ID for Set-Cookie: value of {} bytes contains characters illegal in a cookie value", - ec_id.len() + if !ec_id_has_only_allowed_chars(ec_id) { + log::error!( + "Rejecting EC ID for Set-Cookie: value of {} bytes is empty, over {} bytes, or \ + contains characters outside the identifier alphabet", + ec_id.len(), + MAX_EC_ID_LEN, ); return; } - debug_assert!( - super::generation::is_valid_ec_id(ec_id), - "EC ID must be validated before cookie creation: got '{ec_id}'" - ); - match HeaderValue::from_str(&create_ec_cookie(settings, ec_id)) { Ok(val) => { response.headers_mut().append(header::SET_COOKIE, val); } Err(e) => { - // Unreachable in practice — is_safe_cookie_value and the debug - // assertion above gate the value, and format_set_cookie emits - // only controlled bytes. Logged for defense-in-depth symmetry - // with the rejection logging above. + // Unreachable in practice: the identifier allowlist above gates + // the value, and format_set_cookie emits only controlled bytes. + // Logged for defense-in-depth symmetry with the rejection above. log::warn!("Skipping EC Set-Cookie: invalid header value: {e}"); } } } +/// Sets an Edge Cookie minted by a client-cycle provider on the response. +/// +/// Unlike [`set_ec_cookie`], the value is treated as opaque: it need not match +/// the canonical HMAC id shape, because a client-cycle provider's identifier +/// (for example a signed envelope, or the client-random demo's value) is not in +/// that format. The value is still validated against the same identifier +/// alphabet and length bound as every other identifier +/// ([`ec_id_has_only_allowed_chars`]); a value outside the bounds is rejected +/// (no cookie set) and logged, never rewritten, which prevents header +/// injection. The same `Secure`, `HttpOnly`, `SameSite=Lax`, `Path=/`, and +/// `Domain` attributes as [`set_ec_cookie`] apply. +pub(crate) fn set_provider_ec_cookie( + settings: &Settings, + response: &mut Response, + value: &str, +) { + if !ec_id_has_only_allowed_chars(value) { + log::error!( + "Rejecting provider Edge Cookie value of {} bytes: empty, over {} bytes, or outside the identifier alphabet", + value.len(), + MAX_EC_ID_LEN, + ); + return; + } + + let cookie = format_set_cookie( + &settings.publisher.ec_cookie_domain(), + value, + COOKIE_MAX_AGE, + ); + match HeaderValue::from_str(&cookie) { + Ok(val) => { + response.headers_mut().append(header::SET_COOKIE, val); + } + Err(e) => { + // Unreachable in practice: the identifier allowlist gates the value + // and format_set_cookie emits only controlled bytes. + log::warn!("Skipping provider EC Set-Cookie: invalid header value: {e}"); + } + } +} + /// Expires the EC cookie by setting `Max-Age=0`. /// /// Used when a user revokes consent — the browser will delete the cookie @@ -172,11 +166,73 @@ pub fn expire_ec_cookie(settings: &Settings, response: &mut Response) log::warn!("Skipping EC cookie expiry Set-Cookie: invalid header value: {e}"); } } + // Expire the resolved marker together with the Edge Cookie, so a page + // whose visitor later re-establishes the permission can resolve again. + let marker = format!( + "{COOKIE_TS_EC_RESOLVED}=; Domain={}; Path=/; Secure; SameSite=Lax; Max-Age=0", + settings.publisher.ec_cookie_domain(), + ); + match HeaderValue::from_str(&marker) { + Ok(val) => { + response.headers_mut().append(header::SET_COOKIE, val); + } + Err(e) => { + log::warn!("Skipping resolved-marker expiry Set-Cookie: invalid header value: {e}"); + } + } +} + +/// Sets the `non-HttpOnly` resolved-marker cookie alongside a client-cycle Edge +/// Cookie. +/// +/// The Edge Cookie itself is `HttpOnly`, so the page script cannot see it and +/// would otherwise post to the resolve endpoint on every page view. The marker +/// carries no identity (its value is `1`); it only signals that a resolve +/// succeeded. It shares the Edge Cookie's `Domain`, `Path`, `Secure`, +/// `SameSite`, and lifetime, and is expired together with it by +/// [`expire_ec_cookie`]. +pub(crate) fn set_resolved_marker_cookie(settings: &Settings, response: &mut Response) { + let cookie = format!( + "{COOKIE_TS_EC_RESOLVED}=1; Domain={}; Path=/; Secure; SameSite=Lax; Max-Age={COOKIE_MAX_AGE}", + settings.publisher.ec_cookie_domain(), + ); + match HeaderValue::from_str(&cookie) { + Ok(val) => { + response.headers_mut().append(header::SET_COOKIE, val); + } + Err(e) => { + // Unreachable in practice: the value is a constant and the domain + // comes from operator-trusted configuration. + log::warn!("Skipping resolved-marker Set-Cookie: invalid header value: {e}"); + } + } } #[cfg(test)] mod tests { use super::*; + + #[test] + fn identifier_bounds_reject_oversize_and_accept_tilde() { + assert!( + ec_id_has_only_allowed_chars("a.~-_Z9"), + "the cookie-safe alphabet includes the tilde" + ); + assert!( + !ec_id_has_only_allowed_chars(""), + "an empty identifier is rejected" + ); + let oversize = "a".repeat(MAX_EC_ID_LEN + 1); + assert!( + !ec_id_has_only_allowed_chars(&oversize), + "an identifier over the length cap is rejected" + ); + let at_cap = "a".repeat(MAX_EC_ID_LEN); + assert!( + ec_id_has_only_allowed_chars(&at_cap), + "an identifier at the length cap is accepted" + ); + } use crate::test_support::tests::create_test_settings; use http::header; @@ -226,17 +282,21 @@ mod tests { } #[test] - fn create_ec_cookie_sanitizes_disallowed_chars_in_id() { + fn set_ec_cookie_rejects_disallowed_chars_outright() { + // Rejection, never rewriting: an identifier outside the alphabet must + // not produce a cookie at all, so the cookie value and the identity + // graph key can never silently diverge. let settings = create_test_settings(); - let result = create_ec_cookie(&settings, "evil;injected\r\nfoo=bar\0baz"); - let value = result - .strip_prefix(&format!("{COOKIE_TS_EC}=")) - .and_then(|s| s.split_once(';').map(|(v, _)| v)) - .expect("should have cookie value portion"); - - assert_eq!( - value, "evilinjectedfoobarbaz", - "should strip disallowed characters and preserve safe chars" + let mut response = Response::new(EdgeBody::empty()); + set_ec_cookie( + &settings, + &mut response, + "evil;injected +foo=bar", + ); + assert!( + response.headers().get(header::SET_COOKIE).is_none(), + "an identifier outside the alphabet should set no cookie" ); } @@ -289,47 +349,6 @@ mod tests { ); } - #[test] - fn is_safe_cookie_value_rejects_empty_string() { - assert!(!is_safe_cookie_value(""), "should reject empty string"); - } - - #[test] - fn is_safe_cookie_value_accepts_valid_ec_id_characters() { - assert!( - is_safe_cookie_value("abcdef0123456789.ABCDEFabcdef"), - "should accept hex digits, dots, and alphanumeric characters" - ); - } - - #[test] - fn is_safe_cookie_value_rejects_non_ascii() { - assert!( - !is_safe_cookie_value("val\u{fc}e"), - "should reject non-ASCII UTF-8 characters" - ); - } - - #[test] - fn is_safe_cookie_value_rejects_illegal_characters() { - assert!(!is_safe_cookie_value("val;ue"), "should reject semicolon"); - assert!(!is_safe_cookie_value("val,ue"), "should reject comma"); - assert!( - !is_safe_cookie_value("val\"ue"), - "should reject double-quote" - ); - assert!(!is_safe_cookie_value("val\\ue"), "should reject backslash"); - assert!(!is_safe_cookie_value("val ue"), "should reject space"); - assert!( - !is_safe_cookie_value("val\x00ue"), - "should reject null byte" - ); - assert!( - !is_safe_cookie_value("val\x7fue"), - "should reject DEL character" - ); - } - #[test] fn expire_ec_cookie_sets_max_age_zero() { let settings = create_test_settings(); @@ -377,4 +396,64 @@ mod tests { "expiry cookie should retain the same security attributes as the live cookie" ); } + + #[test] + fn set_provider_ec_cookie_sets_opaque_value_with_security_attributes() { + let settings = create_test_settings(); + let mut response = empty_response(); + // A client-cycle value that is not the canonical HMAC id shape. + set_provider_ec_cookie(&settings, &mut response, "8473625190"); + + let cookie_str = response + .headers() + .get(header::SET_COOKIE) + .expect("should set the EC cookie") + .to_str() + .expect("should be valid UTF-8"); + + assert_eq!( + cookie_str, + format!( + "{}=8473625190; Domain=.{}; Path=/; Secure; SameSite=Lax; Max-Age={}; HttpOnly", + COOKIE_TS_EC, settings.publisher.domain, COOKIE_MAX_AGE, + ), + "an opaque provider value should be set verbatim with the standard security attributes" + ); + } + + #[test] + fn set_provider_ec_cookie_preserves_base64url_value() { + let settings = create_test_settings(); + let mut response = empty_response(); + // A base64url value (RFC 4648 section 5, unpadded) fits the identifier + // alphabet exactly and must be preserved verbatim. Standard base64 + // (`+`, `/`, `=`) is outside the alphabet, so a provider that carries + // binary data re-encodes it as base64url before minting. + let value = "abcDEF123-_x"; + set_provider_ec_cookie(&settings, &mut response, value); + + let cookie_str = response + .headers() + .get(header::SET_COOKIE) + .expect("should set the EC cookie") + .to_str() + .expect("should be valid UTF-8"); + + assert!( + cookie_str.starts_with(&format!("{COOKIE_TS_EC}={value};")), + "a base64url provider value should be preserved verbatim, got {cookie_str}" + ); + } + + #[test] + fn set_provider_ec_cookie_rejects_unsafe_value() { + let settings = create_test_settings(); + let mut response = empty_response(); + set_provider_ec_cookie(&settings, &mut response, "evil; Domain=.attacker.com"); + + assert!( + response.headers().get(header::SET_COOKIE).is_none(), + "an unsafe value must not set a cookie, preventing header injection" + ); + } } diff --git a/crates/trusted-server-core/src/ec/device.rs b/crates/trusted-server-core/src/ec/device.rs index fbefa9586..480b9e96b 100644 --- a/crates/trusted-server-core/src/ec/device.rs +++ b/crates/trusted-server-core/src/ec/device.rs @@ -1,9 +1,11 @@ //! Device signal derivation for bot detection and browser classification. //! -//! All functions in this module are pure computations — no KV I/O or Fastly -//! SDK calls. The Fastly adapter extracts raw strings from the request -//! (`get_tls_ja4()`, `get_client_h2_fingerprint()`, UA header) and passes -//! them here for classification. +//! The [`DeviceSignals`] derivation here is pure computation, with no KV I/O or +//! Fastly SDK calls. A [`DeviceProvider`] is wired by dependency injection: its +//! constructor takes the services it reads (the [`RequestInfo`] for the +//! User-Agent, and on a fingerprinting host the +//! [`HostSignals`](crate::evidence::HostSignals) for the TLS/H2 fingerprints), +//! and classifies the request from them. //! //! # Signals //! @@ -18,6 +20,8 @@ use sha2::{Digest as _, Sha256}; use super::kv_types::KvDevice; +use crate::evidence::RequestInfo; +use crate::settings::Settings; /// Device signals derived from a single request. /// @@ -33,18 +37,48 @@ pub struct DeviceSignals { /// Coarse OS family: `"mac"`, `"windows"`, `"ios"`, `"android"`, /// `"linux"`. pub platform_class: Option, - /// SHA256 prefix (12 hex chars) of the raw H2 SETTINGS string. + /// SHA256 prefix (12 hex chars) of raw H2 SETTINGS fingerprint. pub h2_fp_hash: Option, /// `true` = known browser, `false` = known bot, `None` = unknown. pub known_browser: Option, + /// Whether the request looks like a real browser, used to gate Edge Cookie + /// writes. Computed by the producing provider: the built-in provider uses a + /// User-Agent-only heuristic, while the Fastly provider strengthens it with + /// the TLS/H2 fingerprints. + pub looks_like_browser: bool, } impl DeviceSignals { - /// Derives all device signals from raw request data. + /// Derives device signals from the User-Agent alone, with no + /// host-specific TLS or HTTP/2 evidence. + /// + /// This is the default path: it touches no Fastly-specific API, so a + /// default deployment stays host-neutral. `ja4_class` and `h2_fp_hash` are + /// left absent, and the browser/bot decision uses a User-Agent-only + /// heuristic (`looks_like_browser_from_ua`). + #[must_use] + pub fn derive_ua_only(ua: &str) -> Self { + let platform_class = parse_platform_class(ua); + let looks_like_browser = looks_like_browser_from_ua(ua, platform_class.as_deref()); + + Self { + is_mobile: parse_is_mobile(ua), + ja4_class: None, + platform_class, + h2_fp_hash: None, + known_browser: None, + looks_like_browser, + } + } + + /// Derives device signals from the User-Agent strengthened with the + /// host's TLS/H2 fingerprints. /// /// `ua` is the `User-Agent` header value. `ja4` is the full JA4 hash /// from `req.get_tls_ja4()`. `h2_fp` is the raw H2 SETTINGS string - /// from `req.get_client_h2_fingerprint()`. + /// from `req.get_client_h2_fingerprint()`. These fingerprints are + /// host-specific (Fastly), so only the opt-in Fastly device provider + /// uses this path; the browser/bot gate then requires a TLS fingerprint. #[must_use] pub fn derive(ua: &str, ja4: Option<&str>, h2_fp: Option<&str>) -> Self { let is_mobile = parse_is_mobile(ua); @@ -52,6 +86,12 @@ impl DeviceSignals { let platform_class = parse_platform_class(ua); let h2_fp_hash = h2_fp.map(compute_h2_fp_hash); let known_browser = evaluate_known_browser(ja4_class.as_deref(), h2_fp_hash.as_deref()); + // The fingerprint-strengthened gate: a real browser produces a valid + // TLS fingerprint and a recognizable UA platform. Raw HTTP clients + // (curl, Python requests, Go net/http, headless scrapers) lack one or + // both. This is intentionally aimed at filtering obvious missing-signal + // traffic, not at resisting deliberate JA4 + UA spoofing. + let looks_like_browser = ja4_class.is_some() && platform_class.is_some(); Self { is_mobile, @@ -59,32 +99,10 @@ impl DeviceSignals { platform_class, h2_fp_hash, known_browser, + looks_like_browser, } } - /// Returns `true` when the request looks like a real browser. - /// - /// Checks for the presence of recognizable signals rather than matching - /// against a hardcoded signal allowlist. Real browsers always - /// produce a valid TLS probabilistic identifier (`ja4_class`) and a recognizable UA - /// platform string (`platform_class`). Raw HTTP clients (curl, Python - /// requests, Go net/http, headless scrapers) typically lack one or both. - /// - /// # Threat model - /// - /// This heuristic is intentionally aimed at filtering obvious - /// missing-signal traffic, not at resisting deliberate spoofing. A bot - /// that forges plausible JA4 and UA inputs may still pass; deeper - /// consistency checks can be added later if product requirements demand - /// stronger spoof resistance. - /// - /// `known_browser` is still computed and stored on [`KvDevice`] for - /// analytics but does not gate identity operations. - #[must_use] - pub fn looks_like_browser(&self) -> bool { - self.ja4_class.is_some() && self.platform_class.is_some() - } - /// Converts these signals into a [`KvDevice`] for KV storage. #[must_use] pub fn to_kv_device(&self) -> KvDevice { @@ -98,6 +116,88 @@ impl DeviceSignals { } } +/// A strategy for classifying a request into [`DeviceSignals`]. +/// +/// Implementations are selected by configuration. The built-in +/// [`BuiltinDeviceProvider`] is the default; a deployment can switch to another +/// provider without changing call sites. +/// +/// These signals serve identity gating and bot detection, not bid enrichment. +/// [`DeviceSignals`] deliberately carries only the coarse browser and bot +/// classification the Edge Cookie gate needs, not a full device-detection +/// result such as make, model, OS version, or screen size. A richer device +/// model for the ad request is a separate concern. +pub trait DeviceProvider: Send + Sync { + /// Returns the stable identifier for this provider, used in configuration + /// and logs. + fn id(&self) -> &'static str; + + /// Classifies the request into [`DeviceSignals`], reading the request data + /// it needs from the [`RequestInfo`] passed borrowed at call time (plus any + /// host signals injected into its constructor). + /// + /// Device signals gate identity operations and must always yield a value, + /// so this is infallible: a provider that cannot determine a signal returns + /// the unknown variant rather than failing the request. + fn detect(&self, request_info: &dyn RequestInfo) -> DeviceSignals; + + /// The permissions this provider's data use requires. + /// + /// The default is empty, so the built-in User-Agent-only provider requires + /// no permission. + fn required_permissions(&self) -> crate::permissions::PermissionSet { + crate::permissions::PermissionSet::none() + } +} + +/// The built-in device provider, the default. +/// +/// Derives [`DeviceSignals`] from the User-Agent alone via +/// [`DeviceSignals::derive_ua_only`], touching no host-specific API. It reads +/// only [`RequestInfo::user_agent`] and never a host fingerprint, so the default +/// request path stays host-neutral. +#[derive(Debug, Default)] +pub struct BuiltinDeviceProvider; + +impl BuiltinDeviceProvider { + /// Creates the built-in provider. + #[must_use] + pub fn new() -> Self { + Self + } +} + +impl DeviceProvider for BuiltinDeviceProvider { + fn id(&self) -> &'static str { + "builtin" + } + + fn detect(&self, request_info: &dyn RequestInfo) -> DeviceSignals { + DeviceSignals::derive_ua_only(request_info.user_agent()) + } +} + +/// Selects the device provider named by the `[device] provider` selector. +/// +/// Returns the built-in User-Agent-only provider unless the `fastly` selector is +/// set, in which case it builds the host-specific provider through the +/// `build_fastly` factory the adapter supplies. The factory runs only when that +/// provider is selected, so the default path captures no host fingerprints (see +/// [`BuiltinDeviceProvider`] for the host-neutral default). A +/// selected-but-unknown provider is rejected at startup by +/// [`DeviceConfig::validate_provider_selection`](crate::settings::DeviceConfig::validate_provider_selection), +/// so this falls back to the built-in provider for that case. +#[must_use] +pub fn build_device_provider( + settings: &Settings, + build_fastly: impl FnOnce() -> Box, +) -> Box { + match settings.device.provider_key() { + "fastly" => build_fastly(), + _ => Box::new(BuiltinDeviceProvider::new()), + } +} + /// Device is a desktop (confirmed via UA platform token). const MOBILE_DESKTOP: u8 = 0; /// Device is a mobile (confirmed via UA mobile token). @@ -146,11 +246,58 @@ fn parse_platform_class(ua: &str) -> Option { None } -/// Extracts Section 1 from a full JA4 string. +/// Decides whether a request looks like a real browser from the User-Agent +/// alone, with no TLS or HTTP/2 evidence. +/// +/// A real browser sends the `Mozilla/` token every major engine still emits and +/// a recognizable platform string (so `platform_class` is present), and is not +/// an obvious bot or command-line client. Raw HTTP clients (curl, Python +/// requests, Go net/http) carry no platform token, so they fail the +/// `platform_class` check; declared crawlers are caught by [`looks_like_bot_ua`]. +/// +/// # Threat model +/// +/// This is the default, host-neutral gate. It filters obvious non-browser +/// traffic but does not resist a bot that forges a complete browser +/// User-Agent. The opt-in Fastly device provider strengthens the gate with the +/// TLS/H2 fingerprints for deployments that need it. +#[must_use] +fn looks_like_browser_from_ua(ua: &str, platform_class: Option<&str>) -> bool { + platform_class.is_some() && ua.contains("Mozilla/") && !looks_like_bot_ua(ua) +} + +/// Returns `true` when the User-Agent declares a known bot, crawler, or +/// non-browser HTTP client. +/// +/// Matches common self-identifying markers case-insensitively. The `bot` marker +/// covers `Googlebot`, `bingbot`, and similar; the library markers cover HTTP +/// clients that set a recognizable platform token. +#[must_use] +fn looks_like_bot_ua(ua: &str) -> bool { + const BOT_MARKERS: &[&str] = &[ + "bot", + "crawl", + "spider", + "slurp", + "curl", + "wget", + "python-requests", + "go-http-client", + "okhttp", + "java/", + "headlesschrome", + "phantomjs", + "scrapy", + ]; + let lower = ua.to_ascii_lowercase(); + BOT_MARKERS.iter().any(|marker| lower.contains(marker)) +} + +/// Extracts Section 1 from a full JA4 fingerprint. /// /// JA4 format: `section1_section2_section3` separated by underscores. /// Section 1 identifies browser family (cipher count, extension count, -/// ALPN) without uniquely identifying a device. +/// ALPN) without uniquely fingerprinting a device. /// /// Returns `None` if the input is empty or has no underscore-delimited /// section. @@ -164,7 +311,7 @@ fn extract_ja4_section1(full_ja4: &str) -> Option { } /// Computes a 12-hex-char prefix of the SHA256 hash of the raw H2 -/// SETTINGS string. +/// SETTINGS fingerprint string. /// /// The raw string looks like `"1:65536;2:0;4:6291456;6:262144"`. #[must_use] @@ -175,7 +322,7 @@ fn compute_h2_fp_hash(raw_h2_fp: &str) -> String { hex::encode(&digest[..6]) } -/// Known browser signal allowlist. +/// Known browser fingerprint allowlist. /// /// Each entry is `(ja4_class, h2_fp_prefix, known_browser)`. /// `h2_fp_prefix` is the raw H2 SETTINGS string (not the hash) — we @@ -191,7 +338,7 @@ const KNOWN_BROWSERS: &[(&str, &str, bool)] = &[ ("t13d1717h2", "1:65536;2:0;4:131072;5:16384", true), ]; -/// Returns H2 SETTINGS hashes for the known browser allowlist. +/// Returns H2 fingerprint hashes for the known browser allowlist. /// /// Computed once on first call and cached via `OnceLock`. fn known_browser_h2_hashes() -> &'static Vec<(&'static str, String, bool)> { @@ -230,6 +377,7 @@ fn evaluate_known_browser(ja4_class: Option<&str>, h2_fp_hash: Option<&str>) -> #[cfg(test)] mod tests { use super::*; + use crate::evidence::OwnedRequestInfo; // Chrome Mac UA const CHROME_MAC_UA: &str = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) \ @@ -366,7 +514,7 @@ mod tests { assert_eq!( evaluate_known_browser(Some(ja4), Some(&h2_hash)), Some(true), - "Chrome signals should be recognized" + "Chrome fingerprint should be recognized" ); } @@ -377,7 +525,7 @@ mod tests { assert_eq!( evaluate_known_browser(Some(ja4), Some(&h2_hash)), Some(true), - "Safari signals should be recognized" + "Safari fingerprint should be recognized" ); } @@ -388,7 +536,7 @@ mod tests { assert_eq!( evaluate_known_browser(Some(ja4), Some(&h2_hash)), Some(true), - "Firefox signals should be recognized" + "Firefox fingerprint should be recognized" ); } @@ -523,7 +671,7 @@ mod tests { Some("1:65536;2:0;4:6291456;6:262144"), ); assert!( - signals.looks_like_browser(), + signals.looks_like_browser, "Chrome/Mac should look like a browser" ); } @@ -537,8 +685,8 @@ mod tests { Some("99:99;88:88"), ); assert!( - signals.looks_like_browser(), - "unknown signal combination with valid JA4 + platform should pass" + signals.looks_like_browser, + "unknown fingerprint with valid JA4 + platform should pass" ); assert_eq!(signals.known_browser, None, "should not match allowlist"); } @@ -547,17 +695,17 @@ mod tests { fn looks_like_browser_rejects_bot() { let signals = DeviceSignals::derive(BOT_UA, None, None); assert!( - !signals.looks_like_browser(), + !signals.looks_like_browser, "bot with no JA4 and no platform should be rejected" ); } #[test] fn looks_like_browser_rejects_missing_ja4() { - // Real UA but no JA4 value (e.g. HTTP/1.1 or missing SDK support) + // Real UA but no TLS fingerprint (e.g. HTTP/1.1 or missing SDK support) let signals = DeviceSignals::derive(CHROME_MAC_UA, None, Some("1:65536")); assert!( - !signals.looks_like_browser(), + !signals.looks_like_browser, "missing JA4 should be rejected even with valid UA" ); } @@ -567,8 +715,138 @@ mod tests { // Has JA4 but unrecognizable UA let signals = DeviceSignals::derive(BOT_UA, Some("t13d1516h2_abc_def"), None); assert!( - !signals.looks_like_browser(), + !signals.looks_like_browser, "unrecognizable UA should be rejected even with JA4" ); } + + #[test] + fn derive_ua_only_accepts_real_browsers_without_fingerprints() { + for ua in [ + CHROME_MAC_UA, + SAFARI_IOS_UA, + FIREFOX_MAC_UA, + CHROME_ANDROID_UA, + CHROME_WINDOWS_UA, + ] { + let signals = DeviceSignals::derive_ua_only(ua); + assert!( + signals.looks_like_browser, + "a real browser UA should pass the UA-only gate: {ua}" + ); + assert!( + signals.ja4_class.is_none() && signals.h2_fp_hash.is_none(), + "the UA-only path must not record any TLS/H2 evidence" + ); + } + } + + #[test] + fn derive_ua_only_rejects_bots_and_http_clients() { + // Declared crawlers and CLI/library clients must not pass the gate. + for ua in [ + BOT_UA, + "Mozilla/5.0 (compatible; bingbot/2.0; +http://www.bing.com/bingbot.htm)", + "curl/8.4.0", + "python-requests/2.31.0", + "Go-http-client/2.0", + "", + ] { + assert!( + !DeviceSignals::derive_ua_only(ua).looks_like_browser, + "a non-browser client should fail the UA-only gate: {ua:?}" + ); + } + } + + #[test] + fn derive_ua_only_rejects_a_browser_ua_that_declares_a_bot() { + // Newer crawlers send a full browser UA with a platform token; the bot + // marker must still reject them. + let googlebot_mobile = "Mozilla/5.0 (Linux; Android 6.0.1; Nexus 5X Build/MMB29P) \ + AppleWebKit/537.36 (KHTML, like Gecko) Chrome/146.0.0.0 Mobile Safari/537.36 \ + (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"; + assert!( + !DeviceSignals::derive_ua_only(googlebot_mobile).looks_like_browser, + "a browser-shaped UA declaring Googlebot should be rejected" + ); + } + + #[test] + fn builtin_device_provider_is_ua_only() { + let provider = BuiltinDeviceProvider::new(); + assert_eq!(provider.id(), "builtin"); + + // The built-in provider classifies from the User-Agent in the request + // info passed to `detect` alone, recording no host fingerprint. + let request_info = request_info_with_ua(CHROME_MAC_UA); + let signals = provider.detect(&request_info); + assert_eq!( + signals, + DeviceSignals::derive_ua_only(CHROME_MAC_UA), + "the built-in provider should classify from the User-Agent only" + ); + assert!( + signals.ja4_class.is_none(), + "the built-in provider must not record a JA4 class" + ); + } + + /// Builds request info carrying the given User-Agent, for provider tests. + fn request_info_with_ua(user_agent: &str) -> OwnedRequestInfo { + let mut headers = http::HeaderMap::new(); + headers.insert( + http::header::USER_AGENT, + http::HeaderValue::from_str(user_agent) + .expect("should build a valid User-Agent header"), + ); + OwnedRequestInfo::new(String::new(), headers) + } + + /// A stand-in for the host-specific provider the adapter injects, so the + /// selection logic can be tested in core without the Fastly provider crate. + struct StubFastlyProvider; + + impl DeviceProvider for StubFastlyProvider { + fn id(&self) -> &'static str { + "fastly" + } + + fn detect(&self, _request_info: &dyn RequestInfo) -> DeviceSignals { + DeviceSignals::derive_ua_only("") + } + } + + #[test] + fn builtin_device_provider_requires_no_permissions() { + assert!( + BuiltinDeviceProvider::new() + .required_permissions() + .is_empty(), + "the built-in User-Agent-only device provider requires no permissions" + ); + } + + #[test] + fn build_device_provider_defaults_to_builtin_and_selects_injected() { + // The default selector returns the built-in provider, ignoring the + // injected candidate. + let settings = crate::settings::Settings::default(); + let default = build_device_provider(&settings, || { + Box::new(StubFastlyProvider) as Box + }); + assert_eq!(default.id(), "builtin", "no selector should be UA-only"); + + // The `fastly` selector returns the provider the adapter's factory builds. + let mut fastly = crate::settings::Settings::default(); + fastly.device.provider = Some("fastly".to_owned()); + let selected = build_device_provider(&fastly, || { + Box::new(StubFastlyProvider) as Box + }); + assert_eq!( + selected.id(), + "fastly", + "the fastly selector should use the injected provider" + ); + } } diff --git a/crates/trusted-server-core/src/ec/finalize.rs b/crates/trusted-server-core/src/ec/finalize.rs index a553bb7a7..87d6a26f6 100644 --- a/crates/trusted-server-core/src/ec/finalize.rs +++ b/crates/trusted-server-core/src/ec/finalize.rs @@ -8,12 +8,10 @@ use std::collections::HashSet; use edgezero_core::body::Body as EdgeBody; use http::Response; -use super::consent::{ec_consent_granted, ec_consent_withdrawn}; use crate::settings::Settings; use super::EcContext; use super::cookies::{expire_ec_cookie, set_ec_cookie}; -use super::generation::is_valid_ec_id; use super::kv::KvIdentityGraph; use super::log_id; use super::prebid_eids::ingest_eid_cookies; @@ -29,12 +27,16 @@ const EC_RESPONSE_HEADERS: &[&str] = &[ /// Finalizes EC response behavior for all routes. /// -/// Applies withdrawal handling, last-seen updates, cookie reconciliation, -/// Prebid EID ingestion, and cookie writes for new EC generation. +/// Applies the resolved permission state, last-seen updates, cookie +/// reconciliation, Prebid EID ingestion, and cookie writes for new EC generation. /// -/// On consent withdrawal, the browser response clears the EC cookie -/// immediately and the EC identity-graph KV tombstone is the authoritative -/// revocation marker. There is no separate consent KV store to clean up. +/// When the request carries an explicit withdrawal signal (a storage opt-out or +/// a TCF record refusing storage) and the client presented a cookie, the browser +/// response clears the EC cookie immediately and the EC identity-graph KV +/// tombstone is the authoritative revocation marker. A request that is merely +/// not permitted (pre-consent or fail-closed) strips EC response headers but +/// leaves an already-issued cookie intact. There is no separate consent KV +/// store to clean up. /// /// `eids_cookie` should be the raw value of the `ts-eids` cookie extracted /// from the request *before* routing consumes it. @@ -47,19 +49,27 @@ pub fn ec_finalize_response( sharedid_cookie: Option<&str>, response: &mut Response, ) { - let consent_allows_ec = ec_consent_granted(ec_context.consent()); - let consent_withdrawn = ec_consent_withdrawn(ec_context.consent()); - - if !consent_allows_ec { - // Always strip EC-specific response headers when consent is not - // currently usable for this request. This covers both explicit - // revocation and fail-closed cases such as missing geo or undecodable - // consent input. + // Apply any response headers the active provider asked for during + // generation (for example to request more client evidence). This is empty + // unless a provider produced headers, so it is safe on every path. + for (name, value) in ec_context.response_headers() { + response.headers_mut().insert(name, value.clone()); + } + + let ec_permitted = ec_context.ec_allowed(); + + if !ec_permitted { + // Always strip EC-specific response headers when EC is not permitted for + // this request, covering both an explicit withdrawal and fail-closed + // cases such as missing geo or undecodable consent input. clear_ec_headers_on_response(response, Some(registry)); // Only expire the browser cookie and tombstone the identity-graph row - // when the request carries an explicit withdrawal signal. - if consent_withdrawn && ec_context.cookie_was_present() { + // when the request carries an explicit withdrawal signal. A pre-consent + // or fail-closed state (the permission is simply not set) strips headers + // but must not destroy an already-issued identifier, or a returning user + // would be permanently withdrawn before they ever get to consent. + if ec_context.storage_withdrawn() && ec_context.cookie_was_present() { expire_ec_cookie(settings, response); // Compute once for the authoritative identity-graph tombstones. @@ -82,8 +92,8 @@ pub fn ec_finalize_response( return; } - // Returning user: consent is granted and EC came from request. - if ec_context.ec_was_present() && !ec_context.ec_generated() && consent_allows_ec { + // Returning user: EC is permitted and came from the request. + if ec_context.ec_was_present() && !ec_context.ec_generated() && ec_permitted { if let (Some(graph), Some(ec_id)) = (kv, ec_context.ec_value()) { ingest_eid_cookies(eids_cookie, sharedid_cookie, ec_id, graph, registry); } @@ -156,13 +166,13 @@ fn withdrawal_ec_ids(ec_context: &EcContext) -> HashSet { let mut hashes = HashSet::new(); if let Some(cookie_ec_id) = ec_context.existing_cookie_ec_id() - && is_valid_ec_id(cookie_ec_id) + && ec_context.accepts_id(cookie_ec_id) { hashes.insert(cookie_ec_id.to_owned()); } if let Some(active_ec_id) = ec_context.ec_value() - && is_valid_ec_id(active_ec_id) + && ec_context.accepts_id(active_ec_id) { hashes.insert(active_ec_id.to_owned()); } @@ -219,6 +229,7 @@ mod tests { ec_was_present: bool, ec_generated: bool, jurisdiction: Jurisdiction, + ec_allowed: bool, ) -> EcContext { let consent = ConsentContext { jurisdiction, @@ -232,6 +243,7 @@ mod tests { ec_was_present, ec_generated, consent, + ec_allowed, ) } @@ -241,6 +253,7 @@ mod tests { ec_was_present: bool, ec_generated: bool, consent: ConsentContext, + ec_allowed: bool, ) -> EcContext { EcContext::new_for_test_with_cookie( ec_value.map(str::to_owned), @@ -248,6 +261,7 @@ mod tests { ec_was_present, ec_generated, consent, + ec_allowed, ) } @@ -275,7 +289,14 @@ mod tests { #[test] fn withdrawal_ec_ids_returns_cookie_ec_only_when_active_missing() { let cookie_ec = sample_ec_id("cook1e"); - let ec_context = make_context(None, Some(&cookie_ec), true, false, Jurisdiction::Unknown); + let ec_context = make_context( + None, + Some(&cookie_ec), + true, + false, + Jurisdiction::Unknown, + false, + ); let ids = withdrawal_ec_ids(&ec_context); @@ -295,6 +316,7 @@ mod tests { true, false, Jurisdiction::Unknown, + false, ); let ids = withdrawal_ec_ids(&ec_context); @@ -313,6 +335,7 @@ mod tests { true, false, Jurisdiction::Unknown, + false, ); let ids = withdrawal_ec_ids(&ec_context); @@ -331,6 +354,7 @@ mod tests { true, false, Jurisdiction::Unknown, + false, ); let ids = withdrawal_ec_ids(&ec_context); @@ -395,14 +419,17 @@ mod tests { fn finalize_withdrawal_clears_cookie_and_headers() { let settings = create_test_settings(); let ec_id = sample_ec_id("aBc123"); + // A TCF record refusing storage is the withdrawal trigger. The test + // context resolves the storage baseline at the requires-signal floor, + // where refusing the signal storage depends on is destructive. let consent = ConsentContext { - jurisdiction: Jurisdiction::UsState("CA".to_owned()), - gpc: true, + jurisdiction: Jurisdiction::Gdpr, + tcf: Some(refusing_tcf()), source: ConsentSource::Cookie, ..Default::default() }; let ec_context = - make_context_with_consent(Some(&ec_id), Some(&ec_id), true, false, consent); + make_context_with_consent(Some(&ec_id), Some(&ec_id), true, false, consent, false); let mut response = empty_response(); set_header(&mut response, "x-ts-ec", "stale"); set_header(&mut response, "x-ts-eids", "[]"); @@ -448,6 +475,65 @@ mod tests { ); } + /// A decoded TCF record refusing every purpose, storage included. + fn refusing_tcf() -> crate::consent::TcfConsent { + crate::consent::TcfConsent { + version: 2, + cmp_id: 0, + cmp_version: 0, + consent_screen: 0, + consent_language: "EN".to_owned(), + vendor_list_version: 0, + tcf_policy_version: 2, + created_ds: 0, + last_updated_ds: 0, + purpose_consents: vec![false; 24], + purpose_legitimate_interests: vec![false; 24], + vendor_consents: Vec::new(), + vendor_legitimate_interests: Vec::new(), + special_feature_opt_ins: vec![false; 12], + } + } + + #[test] + fn finalize_gpc_suppresses_headers_but_keeps_the_cookie() { + // A US-style opt-out suppresses use (headers cleared, nothing egressed) + // but is never destructive: the browser cookie is not expired, so a + // visitor who later withdraws the opt-out keeps their identity. + let settings = create_test_settings(); + let ec_id = sample_ec_id("aBc123"); + let consent = ConsentContext { + jurisdiction: Jurisdiction::UsState("CA".to_owned()), + gpc: true, + source: ConsentSource::Cookie, + ..Default::default() + }; + let ec_context = + make_context_with_consent(Some(&ec_id), Some(&ec_id), true, false, consent, false); + let mut response = empty_response(); + set_header(&mut response, "x-ts-ec", "stale"); + + let test_registry = PartnerRegistry::empty(); + ec_finalize_response( + &settings, + &ec_context, + None, + &test_registry, + None, + None, + &mut response, + ); + + assert!( + get_header(&response, "x-ts-ec").is_none(), + "the opt-out should clear the EC header" + ); + assert!( + get_header(&response, "set-cookie").is_none(), + "the opt-out should not expire the browser cookie" + ); + } + #[test] fn finalize_returning_user_with_cookie_mismatch_sets_no_header_or_cookie() { let settings = create_test_settings(); @@ -459,6 +545,7 @@ mod tests { true, false, Jurisdiction::NonRegulated, + true, ); let mut response = empty_response(); @@ -493,6 +580,7 @@ mod tests { true, false, Jurisdiction::NonRegulated, + true, ); let mut response = empty_response(); @@ -527,6 +615,7 @@ mod tests { false, true, Jurisdiction::NonRegulated, + true, ); let mut response = empty_response(); @@ -554,7 +643,7 @@ mod tests { #[test] fn finalize_denied_without_cookie_is_noop() { let settings = create_test_settings(); - let ec_context = make_context(None, None, false, false, Jurisdiction::Unknown); + let ec_context = make_context(None, None, false, false, Jurisdiction::Unknown, false); let mut response = empty_response(); let test_registry = PartnerRegistry::empty(); @@ -579,7 +668,12 @@ mod tests { } #[test] - fn finalize_unknown_jurisdiction_strips_headers_without_expiring_cookie() { + fn finalize_not_permitted_without_withdrawal_keeps_cookie() { + // When EC is not permitted (here a fail-closed unknown jurisdiction with + // no geo) but the request carries no explicit withdrawal signal, the + // response strips EC headers yet must leave an already-issued cookie + // intact. A pre-consent or transient fail-closed request must not + // permanently withdraw a returning user before they get to consent. let settings = create_test_settings(); let ec_id = sample_ec_id("unk001"); let ec_context = make_context( @@ -588,6 +682,7 @@ mod tests { true, false, Jurisdiction::Unknown, + false, ); let mut response = empty_response(); set_header(&mut response, "x-ts-ec", &ec_id); @@ -606,15 +701,78 @@ mod tests { assert!( get_header(&response, "x-ts-ec").is_none(), - "should strip EC header when consent cannot be verified" + "should strip EC header when EC is not permitted" ); assert!( get_header(&response, "x-ts-eids").is_none(), - "should strip EID header when consent cannot be verified" + "should strip EID header when EC is not permitted" + ); + assert!( + get_header(&response, "set-cookie").is_none(), + "a not-permitted request without a withdrawal signal should keep the cookie" + ); + } + + #[test] + fn set_ec_cookie_on_response_writes_the_ts_ec_cookie() { + // The positive case: when an EC value is present, the finalize path + // writes the ts-ec cookie to the browser, carrying the EC id. + let settings = create_test_settings(); + let ec_id = sample_ec_id("setck1"); + let ec_context = make_context( + Some(&ec_id), + None, + false, + true, + Jurisdiction::NonRegulated, + true, + ); + let mut response = empty_response(); + + set_ec_cookie_on_response(&settings, &ec_context, &mut response); + + let set_cookie = + get_header_str(&response, "set-cookie").expect("an EC value should write a Set-Cookie"); + assert!( + set_cookie.contains("ts-ec=") && set_cookie.contains(&ec_id), + "should write the ts-ec cookie carrying the EC id, got: {set_cookie}" ); + } + + #[test] + fn closed_permission_gate_writes_no_ec_cookie() { + // The gate: with the permission gate closed (ec_allowed = false), no + // ts-ec cookie is written, even when an EC value and a generated flag are + // present. The permission model is what suppresses the cookie. + let settings = create_test_settings(); + let ec_id = sample_ec_id("gated1"); + let ec_context = make_context( + Some(&ec_id), + None, + false, + true, + Jurisdiction::NonRegulated, + false, + ); + let mut response = empty_response(); + + // Pass a KV graph so the missing-graph guard cannot be the reason the + // cookie is suppressed; the closed gate must be doing the work. + let kv = KvIdentityGraph::failing("test_store"); + let test_registry = PartnerRegistry::empty(); + ec_finalize_response( + &settings, + &ec_context, + Some(&kv), + &test_registry, + None, + None, + &mut response, + ); + assert!( get_header(&response, "set-cookie").is_none(), - "should not expire the cookie without an explicit withdrawal signal" + "a closed permission gate must not write a ts-ec cookie" ); } } diff --git a/crates/trusted-server-core/src/ec/generation.rs b/crates/trusted-server-core/src/ec/generation.rs index 2924b7692..a3bfb1dd6 100644 --- a/crates/trusted-server-core/src/ec/generation.rs +++ b/crates/trusted-server-core/src/ec/generation.rs @@ -11,7 +11,6 @@ use rand::Rng; use sha2::Sha256; use crate::error::TrustedServerError; -use crate::settings::Settings; type HmacSha256 = Hmac; @@ -81,19 +80,39 @@ fn generate_random_suffix(length: usize) -> String { /// /// - [`TrustedServerError::EdgeCookie`] if HMAC generation fails pub fn generate_ec_id( - settings: &Settings, + passphrase: &str, client_ip: &str, ) -> Result> { - let mut mac = HmacSha256::new_from_slice(settings.ec.passphrase.expose().as_bytes()) - .change_context(TrustedServerError::EdgeCookie { + generate_hmac_ec_id(passphrase, &[client_ip]) +} + +/// Mints an Edge Cookie identifier as HMAC-SHA256 over the given parts plus a +/// random suffix, in the `{64hex}.{6alnum}` format. +/// +/// The parts are joined with a unit separator (`\u{1f}`), which cannot appear in +/// a client IP, User-Agent, JA4, or HTTP/2 fingerprint, so distinct part lists +/// cannot collide. A provider that derives identity from several request signals +/// (for example a Fastly provider over JA4, H2, IP, and UA) passes them as +/// separate parts. Each part must be pre-normalized by the caller. +/// +/// # Errors +/// +/// - [`TrustedServerError::EdgeCookie`] if HMAC generation fails +pub fn generate_hmac_ec_id( + passphrase: &str, + parts: &[&str], +) -> Result> { + let mut mac = HmacSha256::new_from_slice(passphrase.as_bytes()).change_context( + TrustedServerError::EdgeCookie { message: "Failed to create HMAC instance".to_string(), - })?; - mac.update(client_ip.as_bytes()); + }, + )?; + // A unit separator cannot occur in any part, so distinct lists never collide. + mac.update(parts.join("\u{1f}").as_bytes()); let hmac_hash = hex::encode(mac.finalize().into_bytes()); - // Append random 6-character alphanumeric suffix for additional uniqueness. - let random_suffix = generate_random_suffix(6); - let ec_id = format!("{hmac_hash}.{random_suffix}"); + // Append a random 6-character alphanumeric suffix for additional uniqueness. + let ec_id = format!("{hmac_hash}.{}", generate_random_suffix(6)); log::trace!("Generated fresh EC ID: {}", super::log_id(&ec_id)); @@ -175,7 +194,39 @@ mod tests { use super::*; use std::net::{Ipv4Addr, Ipv6Addr}; - use crate::test_support::tests::create_test_settings; + const TEST_PASSPHRASE: &str = "test-secret-key-32-bytes-minimum"; + + #[test] + fn generate_hmac_ec_id_is_stable_per_parts_and_collision_resistant() { + // The 64-char hex prefix is HMAC over the parts and is stable for the + // same parts; the random suffix varies, so compare prefixes only. + let prefix = |parts: &[&str]| { + generate_hmac_ec_id(TEST_PASSPHRASE, parts) + .expect("should generate") + .split('.') + .next() + .expect("should have a prefix") + .to_owned() + }; + + assert_eq!( + prefix(&["a", "b"]), + prefix(&["a", "b"]), + "the same parts should yield the same stable prefix" + ); + assert_ne!( + prefix(&["a", "b"]), + prefix(&["a", "c"]), + "different parts should yield a different prefix" + ); + // The unit separator prevents a join collision: ["a", "b"] must not hash + // the same as ["ab"]. + assert_ne!( + prefix(&["a", "b"]), + prefix(&["ab"]), + "the separator should prevent ['a','b'] colliding with ['ab']" + ); + } #[test] fn normalize_ipv4_unchanged() { @@ -215,8 +266,7 @@ mod tests { #[test] fn generate_produces_valid_format() { - let settings = create_test_settings(); - let ec_id = generate_ec_id(&settings, "192.168.1.1").expect("should generate EC ID"); + let ec_id = generate_ec_id(TEST_PASSPHRASE, "192.168.1.1").expect("should generate EC ID"); assert!( is_valid_ec_id(&ec_id), "should match EC ID format: {{64hex}}.{{6alnum}}, got: {ec_id}" @@ -225,10 +275,10 @@ mod tests { #[test] fn generate_same_ip_produces_consistent_hash_prefix() { - let settings = create_test_settings(); - let first = generate_ec_id(&settings, "192.168.1.1").expect("should generate first EC ID"); + let first = + generate_ec_id(TEST_PASSPHRASE, "192.168.1.1").expect("should generate first EC ID"); let second = - generate_ec_id(&settings, "192.168.1.1").expect("should generate second EC ID"); + generate_ec_id(TEST_PASSPHRASE, "192.168.1.1").expect("should generate second EC ID"); assert_eq!( ec_hash(&first), diff --git a/crates/trusted-server-core/src/ec/identify.rs b/crates/trusted-server-core/src/ec/identify.rs index 6ca251905..eaec9f5f8 100644 --- a/crates/trusted-server-core/src/ec/identify.rs +++ b/crates/trusted-server-core/src/ec/identify.rs @@ -10,7 +10,6 @@ use http::{Request, Response, StatusCode}; use url::Url; use super::auth::authenticate_bearer; -use super::consent::ec_consent_granted; use crate::error::TrustedServerError; use crate::openrtb::{Eid, Uid}; use crate::settings::Settings; @@ -62,7 +61,11 @@ pub fn handle_identify( ); }; - if !ec_consent_granted(ec_context.consent()) { + // Identify returns the partner's UID for this visitor, which is sharing + // the identity beyond the edge, so it needs the same permission pair as + // bidstream EIDs (storage plus personalised-ad selection), not only the + // provider's storage permission. + if !ec_context.ec_sharing_allowed() { return json_response_with_origin( StatusCode::FORBIDDEN, &serde_json::json!({ "consent": "denied" }), @@ -332,7 +335,6 @@ fn apply_cors_headers(response: &mut Response, origin: &str) { #[cfg(test)] mod tests { use super::*; - use crate::consent::jurisdiction::Jurisdiction; use crate::consent::types::{ConsentContext, ConsentSource}; use crate::ec::registry::PartnerRegistry; use crate::redacted::Redacted; @@ -352,13 +354,12 @@ mod tests { ); } - fn make_ec_context(jurisdiction: Jurisdiction, ec_value: Option<&str>) -> EcContext { + fn make_ec_context(ec_allowed: bool, ec_value: Option<&str>) -> EcContext { let consent = ConsentContext { - jurisdiction, source: ConsentSource::Cookie, ..ConsentContext::default() }; - EcContext::new_for_test(ec_value.map(str::to_owned), consent) + EcContext::new_for_test_gated(ec_value.map(str::to_owned), consent, ec_allowed) } fn make_test_partner(source_domain: &str, api_token: &str) -> EcPartner { @@ -472,7 +473,7 @@ mod tests { .uri("https://edge.test-publisher.com/identify") .body(EdgeBody::empty()) .expect("should build test request"); - let ec_context = make_ec_context(Jurisdiction::NonRegulated, None); + let ec_context = make_ec_context(true, None); let response = handle_identify(&settings, &kv, ®istry, &req, &ec_context) .expect("should construct unauthorized response"); @@ -514,7 +515,7 @@ mod tests { .header("authorization", "Bearer wrong-token") .body(EdgeBody::empty()) .expect("should build test request"); - let ec_context = make_ec_context(Jurisdiction::NonRegulated, None); + let ec_context = make_ec_context(true, None); let response = handle_identify(&settings, &kv, ®istry, &req, &ec_context) .expect("should construct unauthorized response"); @@ -539,7 +540,7 @@ mod tests { .header("authorization", format!("Bearer {VALID_API_TOKEN}")) .body(EdgeBody::empty()) .expect("should build test request"); - let ec_context = make_ec_context(Jurisdiction::Unknown, None); + let ec_context = make_ec_context(false, None); let response = handle_identify(&settings, &kv, ®istry, &req, &ec_context) .expect("should construct denied response"); @@ -573,7 +574,7 @@ mod tests { .header("authorization", format!("Bearer {VALID_API_TOKEN}")) .body(EdgeBody::empty()) .expect("should build test request"); - let ec_context = make_ec_context(Jurisdiction::NonRegulated, None); + let ec_context = make_ec_context(true, None); let response = handle_identify(&settings, &kv, ®istry, &req, &ec_context) .expect("should construct no-content response"); @@ -599,7 +600,7 @@ mod tests { .body(EdgeBody::empty()) .expect("should build test request"); let ec_id = format!("{}.ABC123", "a".repeat(64)); - let ec_context = make_ec_context(Jurisdiction::NonRegulated, Some(&ec_id)); + let ec_context = make_ec_context(true, Some(&ec_id)); let response = handle_identify(&settings, &kv, ®istry, &req, &ec_context) .expect("should construct degraded identify response"); @@ -652,7 +653,7 @@ mod tests { .header("origin", "https://evil.example") .body(EdgeBody::empty()) .expect("should build test request"); - let ec_context = make_ec_context(Jurisdiction::NonRegulated, None); + let ec_context = make_ec_context(true, None); let response = handle_identify(&settings, &kv, ®istry, &req, &ec_context) .expect("should construct forbidden response"); @@ -678,7 +679,7 @@ mod tests { .header("origin", "https://www.test-publisher.com") .body(EdgeBody::empty()) .expect("should build test request"); - let ec_context = make_ec_context(Jurisdiction::NonRegulated, None); + let ec_context = make_ec_context(true, None); let response = handle_identify(&settings, &kv, ®istry, &req, &ec_context) .expect("should construct no-content response with CORS headers"); diff --git a/crates/trusted-server-core/src/ec/mod.rs b/crates/trusted-server-core/src/ec/mod.rs index 840ce90d3..6c8145147 100644 --- a/crates/trusted-server-core/src/ec/mod.rs +++ b/crates/trusted-server-core/src/ec/mod.rs @@ -15,7 +15,7 @@ //! //! - auth (private) — shared Bearer-token authentication helpers //! - [`generation`] — HMAC-based ID generation, IP normalization, format helpers -//! - [`consent`] — EC-specific consent gating wrapper +//! - [`consent`]: EC-specific permission gating, with consent as one input //! - [`cookies`] — `Set-Cookie` header creation and expiration helpers //! - [`kv`] — KV Store identity graph operations (CAS, tombstones, debounce) //! - [`kv_backend`] — Platform-neutral KV primitives implemented by adapters @@ -45,9 +45,11 @@ pub mod kv_backend; pub mod kv_types; pub mod partner; pub mod prebid_eids; +pub mod provider; pub mod pull_sync; pub mod rate_limiter; pub mod registry; +pub mod resolve; /// Truncates an EC ID for safe inclusion in log messages. /// @@ -60,6 +62,8 @@ pub fn log_id(ec_id: &str) -> String { format!("{prefix}\u{2026}") } +use std::sync::Arc; + use cookie::CookieJar; use edgezero_core::body::Body as EdgeBody; use error_stack::Report; @@ -70,10 +74,13 @@ use crate::constants::COOKIE_TS_EC; use crate::cookies::handle_request_cookies; use crate::ec::cookies::ec_id_has_only_allowed_chars; use crate::error::TrustedServerError; +use crate::evidence::{BorrowedRequestInfo, HostSignals}; use crate::geo::GeoInfo; +use crate::permissions::{Acquisition, Permission, PermissionState}; use crate::platform::RuntimeServices; use crate::settings::Settings; use device::DeviceSignals; +use provider::{EdgeCookieProvider, GeneratedEdgeCookie, IdentityInput, build_provider}; use self::kv::KvIdentityGraph; use self::kv_types::KvEntry; @@ -126,7 +133,15 @@ fn request_ec_id_if_allowed(value: &str, source: &str) -> Option { /// - [`TrustedServerError::InvalidHeaderValue`] if cookie parsing fails pub fn get_ec_id(req: &Request) -> Result, Report> { let parsed = parse_ec_from_request(req)?; - let ec_id = parsed.cookie_ec.filter(|v| is_valid_ec_id(v)); + // Accept the coded form (any provider's `{code}~value` within the global + // identifier bounds) and the legacy bare HMAC form. Provider-aware + // ownership lives in `EcContext`; this helper only reads the string. + let ec_id = parsed + .cookie_ec + .filter(|v| match provider::split_provider_code(v) { + (Some(_), value) => !value.is_empty() && cookies::ec_id_has_only_allowed_chars(v), + (None, value) => is_valid_ec_id(value), + }); if let Some(ref id) = ec_id { log::trace!("Existing EC ID found: {}", log_id(id)); } @@ -152,6 +167,19 @@ pub struct EcContext { ec_generated: bool, /// The consent context for this request. consent: ConsentContext, + /// Whether the configured Edge Cookie provider's required permissions are + /// set for this request. Resolved once at construction through the + /// permission model and read via [`ec_allowed`](Self::ec_allowed). + ec_allowed: bool, + /// The permissions resolved for this request: the country/region baseline + /// augmented by the session's signals. Assembled once at construction and + /// read via [`permissions`](Self::permissions). + permissions: PermissionState, + /// The jurisdiction's acquisition rule for Edge Cookie storage, resolved + /// once at construction and used by + /// [`storage_withdrawn`](Self::storage_withdrawn) to scope destructive + /// withdrawal. Defaults to the requires-signal floor. + storage_acquisition: Acquisition, /// The normalized client IP, captured early before the request body /// is consumed. `None` when the platform cannot determine client IP. client_ip: Option, @@ -161,6 +189,37 @@ pub struct EcContext { /// Set via [`EcContext::set_device_signals`] before /// [`EcContext::generate_if_needed`] is called. device_signals: Option, + /// The host-signal service for this request, when the host supplies one + /// (the Fastly adapter registers the TLS/HTTP-2 fingerprints). `None` on a + /// host that exposes none. Injected into a provider that needs it when the + /// provider is built. + host_signals: Option>, + /// The adapter-injected Edge Cookie provider, when one is wired for this + /// request. Captured once from [`RuntimeServices`] at construction and + /// passed to [`build_provider`] on every path, so a vendor or host provider + /// resolves without core naming it. `None` for built-in-only deployments. + ec_provider: Option>, + /// The selected Edge Cookie provider (built-in or injected), built once at + /// construction. Core asks it whether an identifier is well formed + /// ([`accepts_id`](crate::ec::provider::EdgeCookieProvider::accepts_id)) so + /// an opaque vendor identifier round-trips through read-back and withdrawal + /// instead of being dropped by the built-in shape check. `None` when no + /// provider is configured. + selected_provider: Option>, + /// A snapshot of the request evidence a provider reads at generation time: + /// the request headers (so a provider can read cookies and client hints), and + /// the URL path and query string (so it can read request parameters). + /// Captured once at construction, and only when a provider is configured, so + /// a deployment with no Edge Cookie provider clones nothing. A provider reads + /// these through [`RequestInfo`](crate::evidence::RequestInfo) at generate + /// time. + request_headers: http::HeaderMap, + request_path: String, + request_query: String, + /// Response headers a provider asked to set, captured during + /// [`EcContext::generate_if_needed`] and applied to the response by EC + /// finalization. Empty for providers that set no headers. + response_headers: Vec<(http::HeaderName, http::HeaderValue)>, } impl EcContext { @@ -198,36 +257,152 @@ impl EcContext { services: &RuntimeServices, geo_info: Option<&GeoInfo>, ) -> Result> { + Self::read_from_request_with_geo_status( + settings, + req, + services, + consent::GeoStatus::from(geo_info), + ) + } + + /// Reads the EC context, resolving the location through the configured geo + /// provider first. + /// + /// This is the constructor adapters use: it runs the geo lookup itself so + /// a failed lookup is distinguished from "no location resolved". No + /// location falls back to the configured `[geo] default_country` + /// baseline, while a failure resolves every permission to the + /// requires-signal floor (see [`consent::GeoStatus`]) and is logged at + /// error level so an outage is visible. + /// + /// # Errors + /// + /// Returns [`TrustedServerError`] when the selected Edge Cookie provider + /// cannot be built, the same as + /// [`read_from_request_with_geo`](Self::read_from_request_with_geo). + pub fn read_from_request_resolving_geo( + settings: &Settings, + req: &Request, + services: &RuntimeServices, + ) -> Result> { + let lookup = services.geo().lookup(services.client_info().client_ip); + let geo_info = match &lookup { + Ok(info) => info.clone(), + Err(error) => { + log::error!( + "geo lookup failed; resolving permissions at the requires-signal floor: {error:?}" + ); + None + } + }; + let status = match (&lookup, &geo_info) { + (Err(_), _) => consent::GeoStatus::Failed, + (Ok(_), Some(info)) => consent::GeoStatus::Located(info), + (Ok(_), None) => consent::GeoStatus::NoLocation, + }; + Self::read_from_request_with_geo_status(settings, req, services, status) + } + + fn read_from_request_with_geo_status( + settings: &Settings, + req: &Request, + services: &RuntimeServices, + geo_status: consent::GeoStatus<'_>, + ) -> Result> { + let geo_info = geo_status.info(); let parsed = parse_ec_from_request(req)?; - let ec_value = parsed.cookie_ec.clone().filter(|v| is_valid_ec_id(v)); + // Build the selected provider once, injecting any host signals the host + // supplies. It is used here to decide whether the incoming cookie value + // is a usable identifier and to read its required permissions. A provider + // that needs a service the host did not supply fails to build here, which + // stops the request. Reading either needs no request data, so nothing is + // cloned from the request. + let host_signals = services.host_signals(); + let ec_provider = services.ec_provider(); + let selected_provider: Option> = + build_provider(&settings.ec, host_signals.clone(), ec_provider.clone())?.map(Arc::from); + + // Read back an existing identifier only when the selected provider + // accepts its shape, so an opaque vendor identifier (for example a signed + // envelope) round-trips instead of being silently dropped by the built-in + // shape check. With no provider configured, Trusted Server is stateless: + // an existing identifier is treated as absent so it is never used or + // egressed, while the raw cookie value stays available to withdrawal + // handling below. + let ec_value = parsed.cookie_ec.clone().filter(|v| { + selected_provider + .as_ref() + .is_some_and(|selected| provider::provider_owns_id(selected.as_ref(), v)) + }); let ec_was_present = ec_value.is_some(); if let Some(ref id) = ec_value { log::trace!("Existing EC ID found: {}", log_id(id)); } + // Snapshot the request evidence a provider reads at generation time (the + // headers, so it can read cookies and client hints, and the URL path and + // query, so it can read request parameters). Capture only when a provider + // is configured and no identifier already exists, so a no-provider + // deployment and a returning visitor clone nothing. Generation runs after + // the request body may be consumed, so the snapshot is owned. + let (request_headers, request_path, request_query) = + if selected_provider.is_some() && ec_value.is_none() { + ( + req.headers().clone(), + req.uri().path().to_owned(), + req.uri().query().unwrap_or_default().to_owned(), + ) + } else { + (http::HeaderMap::new(), String::new(), String::new()) + }; + // Capture the client IP from platform services (normalized). let client_ip = services .client_info() .client_ip .map(generation::normalize_ip); + // Jurisdiction detection for the consent gates follows the permission + // model's fallback: with no location resolved, the configured default + // country stands in, so a deployment that declared its jurisdiction is + // not treated as unknown. A failed lookup stays unknown, so the consent + // gates fail closed alongside the requires-signal floor. + let default_location = match geo_status { + consent::GeoStatus::NoLocation => consent::default_location_geo(settings), + consent::GeoStatus::Located(_) | consent::GeoStatus::Failed => None, + }; + let consent_geo = geo_info.or(default_location.as_ref()); + // Build consent context from request-local cookies, headers, and geo. let consent = consent_mod::build_consent_context(&ConsentPipelineInput { jar: parsed.jar.as_ref(), req, config: &settings.consent, - geo: geo_info, + geo: consent_geo, ec_id: None, kv_store: None, }); + // Assemble the permission state once, here, through the permission + // model, building the country/region baseline augmented by the session's + // signals. Downstream consumers read the stored result via + // [`EcContext::permissions`] and [`EcContext::ec_allowed`] rather than + // re-deriving it. + let permissions = consent::assemble_permissions(settings, &consent, geo_status); + let storage_acquisition = consent::storage_acquisition(settings, geo_status); + // With no provider selected nothing may mint or use an identifier, so + // the gate is closed rather than open by default. + let ec_allowed = selected_provider + .as_ref() + .is_some_and(|selected| permissions.all_set(selected.required_permissions())); + log::info!( - "EC context: present={}, cookie_present={}, consent_allowed={}, jurisdiction={}", + "EC context: present={}, cookie_present={}, ec_allowed={}, jurisdiction={}", ec_was_present, parsed.cookie_ec.is_some(), - consent::ec_consent_granted(&consent), + ec_allowed, consent.jurisdiction, ); @@ -237,9 +412,19 @@ impl EcContext { ec_was_present, ec_generated: false, consent, + ec_allowed, + permissions, + storage_acquisition, client_ip, geo_info: geo_info.cloned(), device_signals: None, + host_signals, + ec_provider, + selected_provider, + request_headers, + request_path, + request_query, + response_headers: Vec::new(), }) } @@ -265,22 +450,106 @@ impl EcContext { return Ok(()); } - if !consent::ec_consent_granted(&self.consent) { + // A deployment with no provider selected is stateless: nothing to + // generate, and not an error. Reuse the provider built at read time + // rather than building it again. + let Some(ec_provider) = self.selected_provider.clone() else { + log::trace!("EC generation skipped: no Edge Cookie provider configured"); + return Ok(()); + }; + + if !self.ec_allowed { log::info!( - "EC generation skipped: consent not granted (jurisdiction={})", + "EC generation skipped: required permissions not set (jurisdiction={})", self.consent.jurisdiction, ); return Ok(()); } - let client_ip = self.client_ip.as_deref().ok_or_else(|| { - Report::new(TrustedServerError::EdgeCookie { + // EC generation needs the client IP; checked after the cheap skip + // guards so a stateless deployment on a host with no client IP does not + // log spurious errors. The provider reads it borrowed at generate time + // (see [`generate_with_provider`]), so nothing is cloned here. + if self.client_ip.is_none() { + return Err(Report::new(TrustedServerError::EdgeCookie { message: "Client IP required for EC generation but unavailable".to_owned(), - }) - })?; + })); + } - let ec_id = generation::generate_ec_id(settings, client_ip)?; - log::info!("Generated new EC ID: {}", log_id(&ec_id)); + self.generate_with_provider(ec_provider.as_ref(), settings, kv) + } + + /// Derives and commits an EC identifier using a specific provider. + /// + /// Split out of [`generate_if_needed`](Self::generate_if_needed) so the + /// provider is supplied explicitly: the configured path builds it from + /// settings, and tests pass one in to observe the [`IdentityInput`] a + /// provider receives. The request evidence captured at read time (client + /// IP, headers, and the URL path and query) is passed borrowed through + /// [`RequestInfo`](crate::evidence::RequestInfo), so a provider can read + /// cookies and request parameters at generate time; the built-ins read + /// only the client IP. The skip guards (existing EC, permission gate) + /// stay in [`generate_if_needed`](Self::generate_if_needed). + /// + /// # Errors + /// + /// Returns [`TrustedServerError::EdgeCookie`] when the client IP is + /// unavailable, the provider fails to derive an identifier, or persisting a + /// generated identifier to the KV identity graph fails. + fn generate_with_provider( + &mut self, + ec_provider: &dyn EdgeCookieProvider, + settings: &Settings, + kv: Option<&KvIdentityGraph>, + ) -> Result<(), Report> { + let input = IdentityInput { + permissions: Some(&self.permissions), + consent: Some(&self.consent), + }; + // Pass the request evidence captured at read time, borrowed: the client + // IP, the request headers (so a provider reads cookies and client hints), + // and the URL path and query (so it reads request parameters). A built-in + // provider reads only the client IP; a vendor provider reads what it + // needs through [`RequestInfo`]. + let request_info = BorrowedRequestInfo::new( + self.client_ip.as_deref().unwrap_or_default(), + Some(&self.request_headers), + ) + .with_request_target(&self.request_path, &self.request_query); + let generated: GeneratedEdgeCookie = ec_provider.generate(&request_info, &input)?; + // Capture any response headers the provider asked for, even when it + // produced no identifier (for example while it still needs more client + // evidence). EC finalization applies them to the response. + self.response_headers = generated.response_headers; + let generated_id = generated + .id + .map(|value| crate::ec::provider::apply_provider_code(ec_provider, &value)); + let Some(ec_id) = generated_id else { + log::info!( + "EC generation produced no identifier (provider={}); proceeding without an EC", + ec_provider.id(), + ); + return Ok(()); + }; + // Enforce the global identifier bounds at mint: the cookie-safe + // alphabet and the length cap apply to every provider, so no + // implementation can emit a value the cookie layer or the identity + // graph cannot carry. Rejection is loud and total; the identifier is + // never rewritten. + if !ec_id_has_only_allowed_chars(&ec_id) { + return Err(Report::new(TrustedServerError::EdgeCookie { + message: format!( + "Provider `{}` produced an identifier that is empty, over {} bytes, or outside the cookie-safe alphabet", + ec_provider.id(), + cookies::MAX_EC_ID_LEN, + ), + })); + } + log::info!( + "Generated new EC ID (provider={}): {}", + ec_provider.id(), + log_id(&ec_id), + ); self.ec_value = Some(ec_id); self.ec_generated = true; @@ -297,7 +566,13 @@ impl EcContext { .as_ref() .map(DeviceSignals::to_kv_device); - if let Err(err) = graph.create_or_revive(ec_value, &entry) { + // Key the identity graph by the provider's canonical form of the + // identifier, so equivalent representations of one identity share + // one row. The built-in normalization lowercases only the HMAC + // hash segment; an opaque vendor provider overrides it to the + // identity function. + let kv_key = crate::ec::provider::provider_kv_key(ec_provider, ec_value); + if let Err(err) = graph.create_or_revive(&kv_key, &entry) { log::error!( "Failed to create or revive EC entry for id '{}' after generation: {err:?}", log_id(ec_value), @@ -319,6 +594,21 @@ impl EcContext { self.ec_value.as_deref() } + /// Returns whether `value` is a well-formed identifier for the selected + /// provider. + /// + /// Lets core validate a cookie or active identifier (for example before + /// withdrawing it) through the provider that issued it, rather than assuming + /// the built-in shape. Falls back to the built-in shape when no provider is + /// configured. + #[must_use] + pub(crate) fn accepts_id(&self, value: &str) -> bool { + self.selected_provider.as_ref().map_or_else( + || is_valid_ec_id(value), + |provider| provider::provider_owns_id(provider.as_ref(), value), + ) + } + /// Returns whether the `ts-ec` cookie was present on the incoming request. #[must_use] pub fn cookie_was_present(&self) -> bool { @@ -348,7 +638,9 @@ impl EcContext { /// /// Allows handlers to apply query-param fallback consent for the current /// request only when pre-routing consent extraction produced an empty - /// context. + /// context. Mutations do not re-derive [`ec_allowed`](Self::ec_allowed) or + /// [`permissions`](Self::permissions), which are resolved once at + /// construction. pub fn consent_mut(&mut self) -> &mut ConsentContext { &mut self.consent } @@ -365,6 +657,14 @@ impl EcContext { self.device_signals = Some(signals); } + /// Returns the response headers a provider asked to set during + /// [`generate_if_needed`](Self::generate_if_needed). Empty unless a provider + /// produced any. + #[must_use] + pub fn response_headers(&self) -> &[(http::HeaderName, http::HeaderValue)] { + &self.response_headers + } + /// Returns the device signals, if set. #[must_use] pub fn device_signals(&self) -> Option<&DeviceSignals> { @@ -377,16 +677,75 @@ impl EcContext { self.client_ip.as_deref() } + /// Returns the host-computed client fingerprints captured for this request, + /// when the host supplies them. + /// + /// The resolve path rebuilds the provider with the same injected services + /// as the organic path, so it reads the host signals captured here rather + /// than re-deriving them. + pub(crate) fn host_signals(&self) -> Option> { + self.host_signals.clone() + } + + /// Returns the adapter-injected Edge Cookie provider captured for this + /// request, or `None` for a built-in-only deployment. + pub(crate) fn ec_provider(&self) -> Option> { + self.ec_provider.clone() + } + /// Returns the pre-routing geo data, if available. #[must_use] pub fn geo_info(&self) -> Option<&GeoInfo> { self.geo_info.as_ref() } - /// Returns whether EC creation is permitted by consent for this request. + /// Returns whether the configured Edge Cookie provider's required + /// permissions are set for this request. + /// + /// Resolved once at construction through the permission model (see + /// [`consent::ec_permission_granted`]). #[must_use] pub fn ec_allowed(&self) -> bool { - consent::ec_consent_granted(&self.consent) + self.ec_allowed + } + + /// Whether the request carries an explicit signal withdrawing Edge Cookie + /// storage, scoped to the jurisdiction's storage baseline. + /// + /// See [`consent::ec_storage_withdrawn`]: only a TCF record refusing + /// storage withdraws, and only where the storage baseline is not + /// `granted`. Suppression (the permission merely not set) is reported by + /// [`ec_allowed`](Self::ec_allowed) being `false` instead. + #[must_use] + pub fn storage_withdrawn(&self) -> bool { + consent::ec_storage_withdrawn(&self.consent, self.storage_acquisition) + } + + /// Whether the Edge Cookie identifier may be shared beyond the edge for + /// this request: into the bidstream as `user.id`, in a partner identify + /// response, or in a partner sync call. + /// + /// Sharing rides on the same two permissions as bidstream EIDs (see + /// [`crate::consent::gate_eids_by_permissions`]): storage (the identifier + /// exists and is readable) and personalised-ad selection (it is shared to + /// select ads). [`ec_allowed`](Self::ec_allowed) covers only the + /// provider's own requirements, so a storage-only grant keeps first-party + /// use while withholding partner sharing. + #[must_use] + pub fn ec_sharing_allowed(&self) -> bool { + self.ec_allowed() + && self.permissions.is_set(Permission::StoreOnDevice) + && self.permissions.is_set(Permission::SelectPersonalisedAds) + } + + /// Returns the permissions resolved for this request. + /// + /// Assembled once at construction, the country/region baseline augmented by + /// the session's signals. The core gates provider execution on these, and a + /// consumer may read them for its own logic. + #[must_use] + pub fn permissions(&self) -> &PermissionState { + &self.permissions } /// Returns the existing EC cookie value for revocation handling. @@ -399,35 +758,62 @@ impl EcContext { self.cookie_ec_value.as_deref() } - /// Returns `true` when the request carried a cookie EC and the selected - /// active EC differs from that cookie value. - #[must_use] - pub fn cookie_differs_from_active_ec(&self) -> bool { - matches!( - (self.cookie_ec_value.as_deref(), self.ec_value.as_deref()), - (Some(cookie), Some(active)) if cookie != active - ) - } - /// Returns the stable EC hash prefix from the active EC value. #[must_use] pub fn ec_hash(&self) -> Option<&str> { self.ec_value.as_deref().map(generation::ec_hash) } - /// Creates a test-only `EcContext` with explicit field values. + /// Creates a test-only `EcContext` with the permission gate open. + /// + /// Use [`new_for_test_gated`](Self::new_for_test_gated) when a test needs + /// the gate closed. #[cfg(test)] #[must_use] pub fn new_for_test(ec_value: Option, consent: ConsentContext) -> Self { + Self::new_for_test_gated(ec_value, consent, true) + } + + /// Creates a test-only `EcContext` with an explicit permission gate. + /// + /// `ec_allowed` stands in for the permission decision the production path + /// resolves at construction, so a test can exercise the gate-open and + /// gate-closed branches directly. + #[cfg(test)] + #[must_use] + pub fn new_for_test_gated( + ec_value: Option, + consent: ConsentContext, + ec_allowed: bool, + ) -> Self { + let permissions = if ec_allowed { + PermissionState::new( + [Permission::StoreOnDevice, Permission::SelectPersonalisedAds] + .into_iter() + .collect(), + ) + } else { + PermissionState::default() + }; Self { ec_was_present: ec_value.is_some(), cookie_ec_value: ec_value.clone(), ec_value, ec_generated: false, consent, + ec_allowed, + permissions, + storage_acquisition: Acquisition::default(), client_ip: None, geo_info: None, device_signals: None, + host_signals: None, + ec_provider: None, + selected_provider: None, + request_headers: http::HeaderMap::new(), + request_path: String::new(), + request_query: String::new(), + response_headers: Vec::new(), } } @@ -445,9 +831,19 @@ impl EcContext { ec_value, ec_generated: false, consent, + ec_allowed: true, + storage_acquisition: Acquisition::default(), + permissions: PermissionState::default(), client_ip, geo_info: None, device_signals: None, + host_signals: None, + ec_provider: None, + selected_provider: None, + request_headers: http::HeaderMap::new(), + request_path: String::new(), + request_query: String::new(), + response_headers: Vec::new(), } } @@ -461,6 +857,7 @@ impl EcContext { ec_was_present: bool, ec_generated: bool, consent: ConsentContext, + ec_allowed: bool, ) -> Self { Self { ec_value, @@ -468,9 +865,19 @@ impl EcContext { ec_was_present, ec_generated, consent, + ec_allowed, + permissions: PermissionState::default(), + storage_acquisition: Acquisition::default(), client_ip: None, geo_info: None, device_signals: None, + host_signals: None, + ec_provider: None, + selected_provider: None, + request_headers: http::HeaderMap::new(), + request_path: String::new(), + request_query: String::new(), + response_headers: Vec::new(), } } } @@ -494,6 +901,8 @@ pub(crate) fn current_timestamp() -> u64 { #[cfg(test)] mod tests { use super::*; + use crate::ec::provider::ProviderCode; + use crate::evidence::{OwnedRequestInfo, RequestInfo}; use crate::platform::test_support::noop_services; use crate::test_support::tests::create_test_settings; @@ -512,6 +921,509 @@ mod tests { format!("{}.{suffix}", prefix_char.repeat(64)) } + /// A provider that records the `Cookie` header from the request info passed + /// to `generate`, so a test can prove request cookies reach a provider (a + /// client that stores values in cookies relies on this). + #[derive(Debug)] + struct CookieCapturingProvider { + seen_cookie: std::sync::Mutex>, + } + + impl EdgeCookieProvider for CookieCapturingProvider { + fn id(&self) -> &'static str { + "cookie-capturing" + } + + fn code(&self) -> ProviderCode { + ProviderCode::new("t0cc") + } + + fn generate( + &self, + request_info: &dyn RequestInfo, + _input: &IdentityInput<'_>, + ) -> Result> { + let cookie = request_info.header("cookie").map(ToOwned::to_owned); + *self.seen_cookie.lock().expect("should lock seen cookie") = cookie; + Ok(GeneratedEdgeCookie::default()) + } + } + + #[test] + fn a_provider_reads_request_cookies_from_the_request_info() { + // RequestInfo contract: a provider given request info that carries + // headers can read request cookies through it (a client that stores + // values in cookies relies on this). The organic generate path passes + // no header snapshot; a caller that has headers supplies them. + let mut headers = http::HeaderMap::new(); + headers.insert( + "cookie", + "client-id=abc123; ts-ec=xyz" + .parse() + .expect("should build a valid cookie header"), + ); + let request_info = OwnedRequestInfo::new("203.0.113.7".to_owned(), headers); + let provider = CookieCapturingProvider { + seen_cookie: std::sync::Mutex::new(None), + }; + + provider + .generate(&request_info, &IdentityInput::default()) + .expect("generation should succeed"); + + assert_eq!( + provider + .seen_cookie + .lock() + .expect("should lock seen cookie") + .as_deref(), + Some("client-id=abc123; ts-ec=xyz"), + "the provider should read the request cookies from the request info" + ); + } + + /// A provider whose identifiers are opaque and deliberately not the + /// built-in HMAC shape (no dot, mixed case), modeling a vendor identifier + /// such as a signed envelope. It accepts any of its own non-empty + /// identifiers. + #[derive(Debug)] + struct OpaqueIdProvider; + + impl EdgeCookieProvider for OpaqueIdProvider { + fn id(&self) -> &'static str { + "opaque" + } + + fn code(&self) -> ProviderCode { + ProviderCode::new("t0op") + } + + fn generate( + &self, + _request_info: &dyn RequestInfo, + _input: &IdentityInput<'_>, + ) -> Result> { + Ok(GeneratedEdgeCookie::default()) + } + + fn accepts_id(&self, value: &str) -> bool { + !value.is_empty() + } + } + + #[test] + fn read_from_request_round_trips_an_opaque_provider_identifier() { + use crate::platform::test_support::noop_services_with_ec_provider; + + // A vendor identifier that is deliberately not the built-in HMAC shape + // (no dot, mixed case) — the exact value the built-in check would drop. + const OPAQUE_ID: &str = "AbC123opaqueEnvelopeValueXYZ"; + const CODED_ID: &str = "t0op~AbC123opaqueEnvelopeValueXYZ"; + + let mut settings = create_test_settings(); + settings.ec.provider = Some("opaque".to_owned()); + let cookie = format!("ts-ec={CODED_ID}"); + let req = create_test_request(&[("cookie", &cookie)]); + + // With the opaque provider injected, its `accepts_id` governs read-back, + // so the identifier survives verbatim. + let services = noop_services_with_ec_provider(Arc::new(OpaqueIdProvider)); + let ec = EcContext::read_from_request(&settings, &req, &services) + .expect("should read EC context"); + assert_eq!( + ec.ec_value(), + Some(CODED_ID), + "an opaque provider identifier should round-trip through read-back verbatim" + ); + let _ = OPAQUE_ID; + + // Control: with the provider selected but not injected by the adapter, + // the request fails loudly instead of silently running stateless with + // the identifier dropped. + let err = EcContext::read_from_request(&settings, &req, &noop_services()) + .expect_err("a selected but uninjected provider should fail the request"); + assert!( + err.to_string().contains("opaque"), + "the error should name the selected provider, got: {err}" + ); + + // Control: with no provider selected at all, the identifier is treated + // as absent, so a stateless deployment never uses or egresses it. + let mut stateless = create_test_settings(); + stateless.ec.provider = None; + stateless.ec.providers.hmac = None; + let ec_without = EcContext::read_from_request(&stateless, &req, &noop_services()) + .expect("should read EC context"); + assert_eq!( + ec_without.ec_value(), + None, + "with no provider selected, an existing identifier is treated as absent" + ); + assert!( + !ec_without.ec_allowed(), + "with no provider selected, the gate stays closed" + ); + } + + /// A provider that records the request query parameter `id` and the `Cookie` + /// header it is given at generate time, proving request evidence (parameters + /// and cookies) reaches a provider through the organic generate path. + #[derive(Debug, Default)] + struct EvidenceCapturingProvider { + seen: std::sync::Mutex>, + } + + impl EdgeCookieProvider for EvidenceCapturingProvider { + fn id(&self) -> &'static str { + "evidence" + } + + fn code(&self) -> ProviderCode { + ProviderCode::new("t0ev") + } + + fn generate( + &self, + request_info: &dyn RequestInfo, + _input: &IdentityInput<'_>, + ) -> Result> { + let query_id = request_info.query_param("id").unwrap_or_default(); + let cookie = request_info.header("cookie").unwrap_or_default().to_owned(); + *self.seen.lock().expect("should lock seen evidence") = Some((query_id, cookie)); + Ok(GeneratedEdgeCookie { + id: Some("evidence-ec".to_owned()), + response_headers: Vec::new(), + }) + } + + fn accepts_id(&self, value: &str) -> bool { + !value.is_empty() + } + } + + #[test] + fn generate_passes_request_parameters_and_cookies_to_the_provider() { + use crate::platform::test_support::noop_services_with_ec_provider; + + let provider = Arc::new(EvidenceCapturingProvider::default()); + let mut settings = create_test_settings(); + settings.ec.provider = Some("evidence".to_owned()); + + // A request carrying a query parameter and a (non-EC) cookie, with no + // existing `ts-ec` cookie so the generate path runs. + let req = Request::builder() + .method("GET") + .uri("http://example.com/page?id=abc123&debug=1") + .header("cookie", "client-id=xyz789") + .body(EdgeBody::empty()) + .expect("should build request"); + + let services = noop_services_with_ec_provider(provider.clone()); + let mut ec = EcContext::read_from_request(&settings, &req, &services) + .expect("should read EC context"); + ec.generate_if_needed(&settings, None) + .expect("should run generation"); + + let seen = provider + .seen + .lock() + .expect("should lock seen evidence") + .clone(); + assert_eq!( + seen, + Some(("abc123".to_owned(), "client-id=xyz789".to_owned())), + "the provider should read the request query parameter and cookies at generate time" + ); + assert_eq!( + ec.ec_value(), + Some("t0ev~evidence-ec"), + "the identifier the provider minted should be committed under its code" + ); + } + + /// A provider that mints an opaque, mixed-case, non-HMAC identifier at the + /// edge, so a test can prove such an identifier persists to the KV identity + /// graph under its own value as the key. + #[derive(Debug)] + struct ServerOpaqueProvider; + + impl EdgeCookieProvider for ServerOpaqueProvider { + fn id(&self) -> &'static str { + "server-opaque" + } + + fn code(&self) -> ProviderCode { + ProviderCode::new("t0so") + } + + fn generate( + &self, + _request_info: &dyn RequestInfo, + _input: &IdentityInput<'_>, + ) -> Result> { + Ok(GeneratedEdgeCookie { + id: Some("Opaque_EC_Value_MixedCase_123".to_owned()), + response_headers: Vec::new(), + }) + } + + fn accepts_id(&self, value: &str) -> bool { + !value.is_empty() + } + + fn normalize_id_for_kv(&self, value: &str) -> String { + value.to_owned() + } + } + + #[test] + fn generate_persists_an_opaque_identifier_to_kv_under_its_own_key() { + use crate::platform::test_support::noop_services_with_ec_provider; + + const OPAQUE: &str = "t0so~Opaque_EC_Value_MixedCase_123"; + + let mut settings = create_test_settings(); + settings.ec.provider = Some("server-opaque".to_owned()); + let services = noop_services_with_ec_provider(Arc::new(ServerOpaqueProvider)); + let graph = KvIdentityGraph::in_memory("test-ec-store"); + + // No existing cookie, so the edge mints and persists. + let req = create_test_request(&[]); + let mut ec = EcContext::read_from_request(&settings, &req, &services) + .expect("should read EC context"); + ec.generate_if_needed(&settings, Some(&graph)) + .expect("should generate and persist"); + + assert_eq!( + ec.ec_value(), + Some(OPAQUE), + "the opaque identifier should be minted" + ); + + // The entry is stored under the full identifier verbatim. + assert!( + graph.get(OPAQUE).expect("kv get should succeed").is_some(), + "the entry should exist under the opaque identifier key" + ); + + // A lowercased key must miss, proving the key preserves case rather than + // being lowercased like the built-in HMAC form (the clash this guards). + assert!( + graph + .get(&OPAQUE.to_lowercase()) + .expect("kv get should succeed") + .is_none(), + "the KV key must be case-sensitive and verbatim, not lowercased" + ); + } + + /// A provider that mints an identifier outside the cookie-safe alphabet, + /// to prove core rejects it at mint rather than rewriting it. + #[derive(Debug)] + struct IllegalIdProvider; + + impl EdgeCookieProvider for IllegalIdProvider { + fn id(&self) -> &'static str { + "illegal" + } + + fn code(&self) -> ProviderCode { + ProviderCode::new("t0il") + } + + fn generate( + &self, + _request_info: &dyn RequestInfo, + _input: &IdentityInput<'_>, + ) -> Result> { + Ok(GeneratedEdgeCookie { + id: Some("bad;value with spaces".to_owned()), + response_headers: Vec::new(), + }) + } + + fn accepts_id(&self, _value: &str) -> bool { + true + } + } + + #[test] + fn generate_rejects_an_identifier_outside_the_cookie_safe_alphabet() { + use crate::platform::test_support::noop_services_with_ec_provider; + + let mut settings = create_test_settings(); + settings.ec.provider = Some("illegal".to_owned()); + let services = noop_services_with_ec_provider(Arc::new(IllegalIdProvider)); + let req = create_test_request(&[]); + let mut ec = EcContext::read_from_request(&settings, &req, &services) + .expect("should read EC context"); + + let err = ec + .generate_if_needed(&settings, None) + .expect_err("an identifier outside the alphabet should be rejected at mint"); + assert!( + err.to_string().contains("illegal"), + "the error should name the provider, got: {err}" + ); + assert_eq!( + ec.ec_value(), + None, + "no identifier should be committed after a mint rejection" + ); + } + + /// A provider whose identifier normalizes to a distinct canonical form, to + /// prove the identity graph is keyed by the canonical form. + #[derive(Debug)] + struct CanonicalizingProvider; + + impl EdgeCookieProvider for CanonicalizingProvider { + fn id(&self) -> &'static str { + "canonical" + } + + fn code(&self) -> ProviderCode { + ProviderCode::new("t0ca") + } + + fn generate( + &self, + _request_info: &dyn RequestInfo, + _input: &IdentityInput<'_>, + ) -> Result> { + Ok(GeneratedEdgeCookie { + id: Some("MiXeD.CaseId".to_owned()), + response_headers: Vec::new(), + }) + } + + fn accepts_id(&self, _value: &str) -> bool { + true + } + + fn normalize_id_for_kv(&self, value: &str) -> String { + value.to_ascii_lowercase() + } + } + + #[test] + fn generate_keys_the_identity_graph_by_the_normalized_identifier() { + use crate::platform::test_support::noop_services_with_ec_provider; + + let mut settings = create_test_settings(); + settings.ec.provider = Some("canonical".to_owned()); + let services = noop_services_with_ec_provider(Arc::new(CanonicalizingProvider)); + let graph = KvIdentityGraph::in_memory("test-ec-store"); + let req = create_test_request(&[]); + let mut ec = EcContext::read_from_request(&settings, &req, &services) + .expect("should read EC context"); + ec.generate_if_needed(&settings, Some(&graph)) + .expect("should generate and persist"); + + assert_eq!( + ec.ec_value(), + Some("t0ca~MiXeD.CaseId"), + "the cookie value keeps the provider's exact identifier under its code" + ); + assert!( + graph + .get("t0ca~mixed.caseid") + .expect("should read the graph") + .is_some(), + "the graph row should be keyed by the code plus the canonical form" + ); + } + + #[test] + fn hmac_mints_a_coded_identifier_and_dual_reads_the_legacy_bare_form() { + let mut settings = create_test_settings(); + // A granted-baseline default jurisdiction, so the storage permission + // is set with no signal and the mint runs. + settings.geo.default_country = Some("US/CA".to_owned()); + let req = create_test_request(&[]); + let services = crate::platform::test_support::noop_services_with_client_ip( + std::net::IpAddr::V4(std::net::Ipv4Addr::new(203, 0, 113, 7)), + ); + let mut ec = EcContext::read_from_request(&settings, &req, &services) + .expect("should read EC context"); + ec.generate_if_needed(&settings, None) + .expect("should generate"); + let minted = ec.ec_value().expect("should mint an identifier"); + assert!( + minted.starts_with("hmac~"), + "a fresh HMAC identifier should carry the hmac code, got {minted}" + ); + + // A deployed pre-envelope cookie (bare form) still reads back, so the + // migration does not orphan existing identities. + let legacy = format!("{}.ABC123", "a".repeat(64)); + let cookie = format!("ts-ec={legacy}"); + let req = create_test_request(&[("cookie", &cookie)]); + let ec = EcContext::read_from_request(&settings, &req, &noop_services()) + .expect("should read EC context"); + assert_eq!( + ec.ec_value(), + Some(legacy.as_str()), + "the legacy bare form should dual-read under the hmac provider" + ); + } + + #[test] + fn a_foreign_provider_code_is_treated_as_absent() { + // An identifier carrying another provider's code must never be adopted + // by the selected provider, so switching providers cannot silently mix + // identity populations. + let settings = create_test_settings(); + let foreign = format!("zz00~{}.ABC123", "a".repeat(64)); + let cookie = format!("ts-ec={foreign}"); + let req = create_test_request(&[("cookie", &cookie)]); + let ec = EcContext::read_from_request(&settings, &req, &noop_services()) + .expect("should read EC context"); + assert_eq!( + ec.ec_value(), + None, + "an identifier with a foreign provider code is not this provider's" + ); + } + + #[test] + fn no_location_resolves_the_consent_jurisdiction_from_the_default_country() { + use crate::consent::jurisdiction::Jurisdiction; + + let mut settings = create_test_settings(); + settings.geo.default_country = Some("US/CA".to_owned()); + let req = create_test_request(&[]); + let ec = EcContext::read_from_request(&settings, &req, &noop_services()) + .expect("should read EC context"); + assert_eq!( + ec.consent().jurisdiction, + Jurisdiction::UsState("CA".to_owned()), + "with no location the default country should decide the jurisdiction" + ); + + let mut settings = create_test_settings(); + settings.geo.default_country = Some("FR".to_owned()); + let ec = EcContext::read_from_request(&settings, &req, &noop_services()) + .expect("should read EC context"); + assert_eq!( + ec.consent().jurisdiction, + Jurisdiction::Gdpr, + "a GDPR default country should resolve the GDPR jurisdiction" + ); + } + + #[test] + fn sharing_requires_the_personalised_ads_permission_not_just_storage() { + let mut ec = + EcContext::new_for_test(Some(valid_ec_id("a", "ABC123")), ConsentContext::default()); + ec.permissions = PermissionState::new([Permission::StoreOnDevice].into_iter().collect()); + assert!(ec.ec_allowed(), "the provider gate is open"); + assert!( + !ec.ec_sharing_allowed(), + "storage alone must not allow sharing beyond the edge" + ); + } + #[test] fn read_from_request_ignores_header_ec() { let settings = create_test_settings(); diff --git a/crates/trusted-server-core/src/ec/provider.rs b/crates/trusted-server-core/src/ec/provider.rs new file mode 100644 index 000000000..4f9cead22 --- /dev/null +++ b/crates/trusted-server-core/src/ec/provider.rs @@ -0,0 +1,1024 @@ +//! Edge Cookie identity providers. +//! +//! An [`EdgeCookieProvider`] derives an Edge Cookie identifier. Providers are +//! wired by dependency injection: a provider's constructor takes the services it +//! needs (for example [`RequestInfo`] for the client IP, or [`HostSignals`] for +//! the TLS/HTTP-2 fingerprints) as `Arc`, and the composition root +//! (the adapter, through [`build_provider`]) supplies instances per request. A +//! provider that needs a service the host does not supply cannot be built, so +//! the request stops rather than silently degrading. +//! +//! The provider is selected by configuration, with no default. [`HmacProvider`] +//! is the built-in server-side implementation that derives the identifier from +//! the client IP using HMAC, the behavior Trusted Server has always shipped. + +use std::sync::Arc; + +use error_stack::Report; + +use crate::consent::ConsentContext; +use crate::error::TrustedServerError; +use crate::evidence::{HostSignals, RequestInfo}; +use crate::permissions::{Permission, PermissionSet, PermissionState}; +use crate::redacted::Redacted; +use crate::settings::Ec; + +use super::generation; + +/// The request-scoped gating context passed to [`EdgeCookieProvider::generate`]. +/// +/// Request data (client IP, User-Agent, headers, host signals) reaches a +/// provider through the services injected into its constructor, not through this +/// struct. This carries only the per-request gating context a provider may read +/// for behavior beyond gating. The gate has already confirmed the provider's +/// required permissions are set before `generate` is called. +#[derive(Default)] +pub struct IdentityInput<'a> { + /// The permissions resolved for this request, when the calling path carries + /// them. A provider reads this only for behavior beyond gating. The main + /// organic path supplies them; the publisher path passes `None`. + pub permissions: Option<&'a PermissionState>, + + /// The request's consent context, when available, for provider-specific + /// logic. The core gates on permissions, not consent, so a provider reads + /// this only to forward or record consent. [`HmacProvider`] ignores it. + pub consent: Option<&'a ConsentContext>, +} + +/// Inputs available to [`EdgeCookieProvider::resolve_from_client`]. +/// +/// Carries the value a client produced and posted to the Edge Cookie resolve +/// endpoint, alongside the same gating context as [`IdentityInput`]. Request data +/// reaches the provider through its injected services. Unlike trusted edge-derived +/// data, [`payload`](Self::payload) arrives from the browser, so an +/// implementation must verify it before deriving an identifier from it. +pub struct ClientResolveInput<'a> { + /// The raw body the client posted to the resolve endpoint. For a vendor + /// provider this is its own JSON envelope; for the built-in + /// [`ClientFixedProvider`] demo it is the fixed known word the page script + /// posts. + pub payload: &'a [u8], + + /// The permissions resolved for the resolve request. The endpoint has + /// already confirmed the provider's required permissions are set, so a + /// provider reads this only for behavior beyond gating. + pub permissions: Option<&'a PermissionState>, + + /// The resolve request's consent context, for provider-specific logic. The + /// core gates on permissions, not consent. + pub consent: Option<&'a ConsentContext>, +} + +/// The outcome of [`EdgeCookieProvider::generate`]. +/// +/// Carries the derived identifier, if any, and any response headers the provider +/// needs set on the outbound response. +#[derive(Debug, Default)] +pub struct GeneratedEdgeCookie { + /// The derived Edge Cookie identifier, or `None` when the provider produced + /// none for this request. + pub id: Option, + + /// Response headers the provider needs set on the outbound response, for + /// example to request additional client evidence on later requests. Empty + /// for providers that set no headers, such as [`HmacProvider`]. + pub response_headers: Vec<(http::HeaderName, http::HeaderValue)>, +} + +/// A strategy for deriving an Edge Cookie identifier. +/// +/// Implementations are selected by configuration and come in two types, which +/// reach the same outcome (a `ts-ec` cookie) by different routes: +/// +/// - **Server-side** (for example [`HmacProvider`]): derives the identifier at +/// the edge in [`generate`](Self::generate), and the page response sets the +/// cookie. Nothing client-side is involved. +/// - **Client-side** (for example [`ClientFixedProvider`]): defers in +/// [`generate`](Self::generate) (returns `id: None`), runs its own JavaScript +/// in the browser, and mints from the value the page posts back in +/// [`resolve_from_client`](Self::resolve_from_client), whose response sets the +/// cookie. +/// +/// A provider returns `Ok(None)` from [`generate`](Self::generate) when it +/// cannot derive an identifier at the edge, so the request proceeds without an +/// Edge Cookie rather than failing. +/// The registered short code that namespaces one Edge Cookie provider's +/// identifiers. +/// +/// Exactly four characters from `[a-z0-9]`, allocated append-only in +/// `docs/superpowers/specs/provider-code-registry.md` and never reused. The +/// code appears as the `{code}~` prefix of every identifier the provider +/// mints, so identifiers from different providers can never collide in the +/// cookie, the identity graph, or a withdrawal, and each identifier records +/// which provider created it. +#[derive(Debug, Copy, Clone, Eq, Hash, PartialEq, derive_more::Display)] +pub struct ProviderCode(&'static str); + +impl ProviderCode { + /// Creates a provider code, validating the registry format. + /// + /// # Panics + /// + /// Panics when `code` is not exactly four characters of `[a-z0-9]`. Codes + /// are compile-time literals, so the panic fires in tests and never on a + /// request path. + #[must_use] + pub const fn new(code: &'static str) -> Self { + let bytes = code.as_bytes(); + assert!( + bytes.len() == 4, + "provider code must be exactly four characters" + ); + let mut i = 0; + while i < bytes.len() { + let b = bytes[i]; + assert!( + b.is_ascii_lowercase() || b.is_ascii_digit(), + "provider code characters must be [a-z0-9]" + ); + i += 1; + } + Self(code) + } + + /// The code as a string slice. + #[must_use] + pub const fn as_str(self) -> &'static str { + self.0 + } +} + +/// The separator between a provider code and the provider's identifier value. +/// +/// The tilde is inside the cookie-safe identifier alphabet and outside the +/// built-in HMAC identifier's own characters, so a legacy bare identifier can +/// never be misread as a coded one. +pub const PROVIDER_CODE_SEPARATOR: char = '~'; + +/// Splits a full identifier into its provider-code prefix and value. +/// +/// Returns `(Some(code), value)` when the identifier starts with a well-formed +/// `{code}~` prefix, and `(None, full)` for a legacy bare identifier. The code +/// here is the raw string, not a validated [`ProviderCode`]: an unknown code +/// simply fails the ownership check against the selected provider. +#[must_use] +pub fn split_provider_code(full: &str) -> (Option<&str>, &str) { + if let Some((code, value)) = full.split_once(PROVIDER_CODE_SEPARATOR) + && code.len() == 4 + && code + .bytes() + .all(|b| b.is_ascii_lowercase() || b.is_ascii_digit()) + { + return (Some(code), value); + } + (None, full) +} + +/// Whether the selected provider owns `full` as one of its identifiers. +/// +/// A coded identifier belongs to the provider whose registered code it +/// carries, with the value part accepted by that provider's +/// [`accepts_id`](EdgeCookieProvider::accepts_id). A legacy bare identifier +/// (no code prefix) belongs only to the built-in HMAC provider, which +/// dual-reads its pre-envelope form for one release cycle so deployed cookies +/// keep working across the migration. +#[must_use] +pub fn provider_owns_id(provider: &dyn EdgeCookieProvider, full: &str) -> bool { + match split_provider_code(full) { + (Some(code), value) => code == provider.code().as_str() && provider.accepts_id(value), + (None, value) => provider.id() == "hmac" && provider.accepts_id(value), + } +} + +/// The full minted identifier for `value` under `provider`'s code. +#[must_use] +pub fn apply_provider_code(provider: &dyn EdgeCookieProvider, value: &str) -> String { + format!("{}{PROVIDER_CODE_SEPARATOR}{value}", provider.code()) +} + +/// The KV-key form of a full identifier under `provider`. +/// +/// The code prefix is preserved verbatim and the provider normalizes only its +/// own value part, so distinct providers' rows can never share a key and a +/// provider never sees another provider's syntax. +#[must_use] +pub fn provider_kv_key(provider: &dyn EdgeCookieProvider, full: &str) -> String { + match split_provider_code(full) { + (Some(code), value) => format!( + "{code}{PROVIDER_CODE_SEPARATOR}{}", + provider.normalize_id_for_kv(value) + ), + (None, value) => provider.normalize_id_for_kv(value), + } +} + +pub trait EdgeCookieProvider: Send + Sync + core::fmt::Debug { + /// Returns the stable identifier for this provider, used in configuration + /// and logs. + fn id(&self) -> &'static str; + + /// The provider's registered code, the `{code}~` namespace of every + /// identifier it mints. + /// + /// Mandatory, with no default: a provider must allocate a unique code in + /// `docs/superpowers/specs/provider-code-registry.md` before it can exist, + /// so no two providers can ever mint colliding identifiers. Core applies + /// the code at mint and checks it at read-back, and the provider itself + /// only ever sees its own value part. + fn code(&self) -> ProviderCode; + + /// Derives an Edge Cookie identifier from the provider's injected services + /// and the request's gating context. + /// + /// A server-side provider mints here. A client-side provider defers here + /// (returns `id: None`) and mints later in + /// [`resolve_from_client`](Self::resolve_from_client) from the value the page + /// posts back. + /// + /// # Errors + /// + /// Returns [`TrustedServerError::EdgeCookie`] when derivation fails. + fn generate( + &self, + request_info: &dyn RequestInfo, + input: &IdentityInput<'_>, + ) -> Result>; + + /// Returns whether `value` is a well-formed identifier this provider issues. + /// + /// Core calls this to decide whether an incoming `ts-ec` cookie value is a + /// usable Edge Cookie identifier before reading it back, keying the KV + /// identity graph, or withdrawing it. Core strips the provider's `{code}~` + /// prefix first, so this receives only the provider's own value part. + /// This keeps the identifier opaque to + /// core: a provider whose identifiers are not the built-in shape (for + /// example an opaque signed envelope) accepts its own format here, so its + /// identifier round-trips instead of being silently dropped on read-back. + /// + /// The default accepts the built-in HMAC identifier shape + /// (`<64 hex>.<6 alphanumeric>`), which is correct for [`HmacProvider`] and + /// the other core providers. + fn accepts_id(&self, value: &str) -> bool { + generation::is_valid_ec_id(value) + } + + /// Returns the KV-key form of `value` for this provider's identifiers. + /// + /// Core keys the identity graph by the returned string, so a provider whose + /// identifiers are case-sensitive or carry no separable segments returns the + /// value unchanged to avoid collapsing distinct identifiers into one key. + /// + /// The default lowercases the leading HMAC hash segment and preserves the + /// suffix, matching the built-in identifier shape. + fn normalize_id_for_kv(&self, value: &str) -> String { + generation::normalize_ec_id_for_kv(value) + } + + /// The permissions this provider's data use requires. + /// + /// Trusted Server executes the provider only when every permission returned + /// here is set. The default is empty, so a vendor-neutral provider requires + /// no permission. A provider that stores identity on the device, or shares it + /// onward, declares the matching permission so the request's country and + /// signal rules can gate it. + fn required_permissions(&self) -> PermissionSet { + PermissionSet::none() + } + + /// Derives an Edge Cookie identifier from a value the client produced and + /// posted to the resolve endpoint (`POST /_ts/api/v1/ec/resolve`). + /// + /// This is the client-side counterpart to [`generate`](Self::generate). A + /// provider that cannot derive an identifier at the edge defers from + /// `generate` (returning `id: None`, optionally with response headers that + /// trigger client-side work), and the page posts its result back here. The + /// payload arrives from the browser, so an implementation MUST verify it + /// (for example checking a signature) before trusting it. The default + /// returns no identifier, so a provider that mints entirely server-side + /// (such as [`HmacProvider`]) need not implement it. + /// + /// # Errors + /// + /// Returns [`TrustedServerError::EdgeCookie`] when processing the payload + /// fails. A payload that is merely unverified or absent yields `id: None` + /// rather than an error, so the request proceeds without an Edge Cookie. + fn resolve_from_client( + &self, + _input: &ClientResolveInput<'_>, + ) -> Result> { + Ok(GeneratedEdgeCookie::default()) + } +} + +/// The built-in HMAC Edge Cookie provider. +/// +/// Derives the identifier from the client IP (read from the [`RequestInfo`] +/// passed at call time) and the configured passphrase via +/// [`generation::generate_ec_id`]. +#[derive(Debug, Clone)] +pub struct HmacProvider { + passphrase: Redacted, +} + +impl HmacProvider { + /// Creates an HMAC provider with the given passphrase. + #[must_use] + pub fn new(passphrase: Redacted) -> Self { + Self { passphrase } + } +} + +impl EdgeCookieProvider for HmacProvider { + fn id(&self) -> &'static str { + "hmac" + } + + fn code(&self) -> ProviderCode { + ProviderCode::new("hmac") + } + + fn generate( + &self, + request_info: &dyn RequestInfo, + _input: &IdentityInput<'_>, + ) -> Result> { + let id = generation::generate_ec_id(self.passphrase.expose(), request_info.client_ip())?; + Ok(GeneratedEdgeCookie { + id: Some(id), + response_headers: Vec::new(), + }) + } + + fn required_permissions(&self) -> PermissionSet { + // The HMAC provider writes the Edge Cookie to the device, so it requires + // permission to store on the device (TCF Purpose 1). Whether that needs a + // signal is decided by the country rules, not by the provider. + PermissionSet::none().with(Permission::StoreOnDevice) + } +} + +/// The built-in host-signal Edge Cookie provider. +/// +/// Derives the identifier from the host fingerprints (TLS JA4 and HTTP/2, read +/// from the injected [`HostSignals`]) plus the client IP (from [`RequestInfo`]), +/// keyed by the configured passphrase. It is host-agnostic: it depends on the +/// `HostSignals` capability, so any host that supplies one can use it. A host +/// that supplies no `HostSignals` cannot build it, and the request stops. +#[derive(Debug, Clone)] +pub struct HostSignalProvider { + passphrase: Redacted, + host_signals: Arc, +} + +impl HostSignalProvider { + /// Creates the provider with the passphrase and its injected host signals. + #[must_use] + pub fn new(passphrase: Redacted, host_signals: Arc) -> Self { + Self { + passphrase, + host_signals, + } + } +} + +impl EdgeCookieProvider for HostSignalProvider { + fn id(&self) -> &'static str { + "host-signals" + } + + fn code(&self) -> ProviderCode { + ProviderCode::new("hs00") + } + + fn generate( + &self, + request_info: &dyn RequestInfo, + _input: &IdentityInput<'_>, + ) -> Result> { + let ja4 = self.host_signals.ja4().unwrap_or_default(); + let h2 = self.host_signals.h2().unwrap_or_default(); + // With no fingerprint at all, minting would silently degrade to an + // IP-only identifier under the host-signals name. Defer instead: no + // identity this request, and the request proceeds. + if ja4.is_empty() && h2.is_empty() { + log::warn!("Host-signal EC provider found no TLS/HTTP-2 fingerprints; deferring"); + return Ok(GeneratedEdgeCookie::default()); + } + let id = generation::generate_hmac_ec_id( + self.passphrase.expose(), + &[ja4, h2, request_info.client_ip()], + )?; + Ok(GeneratedEdgeCookie { + id: Some(id), + response_headers: Vec::new(), + }) + } + + fn required_permissions(&self) -> PermissionSet { + // Writes the Edge Cookie to the device, so it requires necessary.operations.storage + // (TCF Purpose 1), the same gate as the HMAC provider. + PermissionSet::none().with(Permission::StoreOnDevice) + } +} + +/// The fixed, known word shared by [`ClientFixedProvider`] and its page script. +/// +/// Kept cookie-safe (no characters [`set_provider_ec_cookie`] would reject) so +/// it can be used as the Edge Cookie value verbatim. The page script posts this +/// exact string; the provider mints only when the posted value matches. The +/// client copy lives in +/// `crates/trusted-server-js/lib/src/integrations/ec_client_fixed`. +/// +/// [`set_provider_ec_cookie`]: super::cookies::set_provider_ec_cookie +#[cfg(any(test, feature = "client-fixed-demo"))] +const EXPECTED_VALUE: &str = "an-ec"; + +/// A demonstration client-side provider, with no vendor coupling. +/// +/// Client and server share one fixed, known word (`EXPECTED_VALUE`). When no +/// Edge Cookie is present the page script (delivered through the tsjs bundle) +/// posts that word to `POST /_ts/api/v1/ec/resolve`, and this provider mints the +/// Edge Cookie only when the posted value matches. It defers from +/// [`generate`](EdgeCookieProvider::generate) so the page renders with no Edge +/// Cookie until the client reports back, then verifies and mints in +/// [`resolve_from_client`](EdgeCookieProvider::resolve_from_client). +/// +/// The value is verifiable precisely because it is a known constant, which is +/// the point of the demo: it exercises verify-before-mint. It is useless in +/// production, because a fixed value is not an identity and every client posts +/// the same word, so it is for demonstration and testing only. A real +/// client-side provider verifies a real payload (for example an OWID signature) +/// instead of a shared constant. +#[derive(Debug, Clone)] +#[cfg(any(test, feature = "client-fixed-demo"))] +pub struct ClientFixedProvider; + +#[cfg(any(test, feature = "client-fixed-demo"))] +impl EdgeCookieProvider for ClientFixedProvider { + fn id(&self) -> &'static str { + "client-fixed" + } + + fn code(&self) -> ProviderCode { + ProviderCode::new("cfix") + } + + fn generate( + &self, + _request_info: &dyn RequestInfo, + _input: &IdentityInput<'_>, + ) -> Result> { + // No identifier is derived at the edge: the value comes from the page + // script, which posts it to the resolve endpoint. + Ok(GeneratedEdgeCookie::default()) + } + + fn resolve_from_client( + &self, + input: &ClientResolveInput<'_>, + ) -> Result> { + // Verify the posted value against the known shared word, then mint it as + // the Edge Cookie. A value that does not match yields no Edge Cookie. + // This stands in for a real provider's verification (for example + // checking a signature) before it trusts a client-supplied value. + let matches = core::str::from_utf8(input.payload) + .map(str::trim) + .is_ok_and(|value| value == EXPECTED_VALUE); + + Ok(GeneratedEdgeCookie { + id: matches.then(|| EXPECTED_VALUE.to_owned()), + response_headers: Vec::new(), + }) + } + + fn normalize_id_for_kv(&self, value: &str) -> String { + // The fixed word has no dot separator, so the built-in default (which + // normalizes the HMAC `.` shape) would corrupt it as a + // KV key. Like any opaque-identifier provider, the value is the key. + value.to_owned() + } + + fn required_permissions(&self) -> PermissionSet { + // The provider writes the resolved value to the device as the Edge + // Cookie, so it requires necessary.operations.storage (TCF Purpose 1), the same gate + // as the HMAC provider. + PermissionSet::none().with(Permission::StoreOnDevice) + } +} + +/// Builds the Edge Cookie provider named by the `[ec] provider` selector, +/// injecting the services it needs. +/// +/// This is the composition root for the built-in providers: the adapter supplies +/// the [`HostSignals`] when the host can produce them, and this constructs the +/// selected provider. The per-request [`RequestInfo`] is passed borrowed to +/// [`generate`](EdgeCookieProvider::generate) at call time rather than stored, so +/// no request snapshot is cloned here. Returns `Ok(None)` when no provider is +/// selected, so the caller stays stateless. +/// +/// # Errors +/// +/// Returns [`TrustedServerError::EdgeCookie`] when the selected provider requires +/// a service the host did not supply (for example the host-signal provider on a +/// host that exposes no [`HostSignals`]), so a misconfigured deployment fails +/// loudly rather than minting a degraded identifier. +pub fn build_provider( + ec: &Ec, + host_signals: Option>, + injected: Option>, +) -> Result>, Report> { + let Some(key) = ec.provider.as_deref() else { + return Ok(None); + }; + let provider: Option> = match key { + // Explicit statelessness: the same meaning as omitting the selector. + "none" => None, + "hmac" => ec + .providers + .hmac + .as_ref() + .map(|config| Box::new(HmacProvider::new(config.passphrase.clone())) as _), + // The client-fixed demo provider takes no configuration or services, so + // it is built whenever it is selected. It is compiled only into test + // and demonstration builds (see [`ClientFixedProvider`]): a fixed + // shared word is not an identity, so production builds reject the + // selection outright. + #[cfg(any(test, feature = "client-fixed-demo"))] + "client-fixed" => Some(Box::new(ClientFixedProvider) as _), + #[cfg(not(any(test, feature = "client-fixed-demo")))] + "client-fixed" => { + return Err(Report::new(TrustedServerError::EdgeCookie { + message: "The client-fixed demo Edge Cookie provider is not compiled into this \ + build. It is for demonstration and testing only; enable the \ + trusted-server-core `client-fixed-demo` cargo feature to use it" + .to_owned(), + })); + } + "host-signals" => { + let signals = host_signals.ok_or_else(|| { + Report::new(TrustedServerError::EdgeCookie { + message: "The host-signals Edge Cookie provider requires a host that supplies \ + TLS/HTTP-2 fingerprints, which this host does not" + .to_owned(), + }) + })?; + ec.providers.host_signals.as_ref().map(|config| { + Box::new(HostSignalProvider::new(config.passphrase.clone(), signals)) as _ + }) + } + // Any other key names a vendor or host provider the adapter injects + // through [`RuntimeServices`](crate::platform::RuntimeServices), the same + // seam the device and geo providers use, so core never names a vendor. + // The injected provider is used when its own id matches the selected key, + // and its `[ec.providers.]` block is read by the adapter that built + // it. A selected key with no matching injected provider is a deployment + // error: fail loudly rather than silently running stateless. + other => { + let provider = injected + .filter(|provider| provider.id() == other) + .map(|provider| Box::new(SharedProvider(provider)) as _); + if provider.is_none() { + return Err(Report::new(TrustedServerError::EdgeCookie { + message: format!( + "Edge Cookie provider `{other}` is selected but this deployment's \ + adapter does not provide it" + ), + })); + } + provider + } + }; + Ok(provider) +} + +/// Adapts an injected, shared [`EdgeCookieProvider`] to the owned `Box` that +/// [`build_provider`] returns. +/// +/// A vendor or host provider is injected as an `Arc` so it can live in +/// [`RuntimeServices`](crate::platform::RuntimeServices) and be cloned per +/// request. Every method delegates to the inner provider, so its behavior is +/// unchanged. +#[derive(Debug)] +struct SharedProvider(Arc); + +impl EdgeCookieProvider for SharedProvider { + fn code(&self) -> ProviderCode { + self.0.code() + } + + fn id(&self) -> &'static str { + self.0.id() + } + + fn generate( + &self, + request_info: &dyn RequestInfo, + input: &IdentityInput<'_>, + ) -> Result> { + self.0.generate(request_info, input) + } + + fn accepts_id(&self, value: &str) -> bool { + self.0.accepts_id(value) + } + + fn normalize_id_for_kv(&self, value: &str) -> String { + self.0.normalize_id_for_kv(value) + } + + fn required_permissions(&self) -> PermissionSet { + self.0.required_permissions() + } + + fn resolve_from_client( + &self, + input: &ClientResolveInput<'_>, + ) -> Result> { + self.0.resolve_from_client(input) + } +} + +#[cfg(test)] +mod tests { + use super::*; + use crate::evidence::OwnedRequestInfo; + + #[test] + fn split_provider_code_separates_coded_and_legacy_forms() { + assert_eq!( + split_provider_code("hmac~abc.DEF123"), + (Some("hmac"), "abc.DEF123"), + "a four-character code before the first tilde splits off" + ); + assert_eq!( + split_provider_code("51dd~value~with~tildes"), + (Some("51dd"), "value~with~tildes"), + "only the first tilde splits, so a value may contain tildes" + ); + assert_eq!( + split_provider_code("abcdef.XYZ"), + (None, "abcdef.XYZ"), + "no tilde means the legacy bare form" + ); + assert_eq!( + split_provider_code("toolong~x"), + (None, "toolong~x"), + "a prefix that is not exactly four characters is not a code" + ); + assert_eq!( + split_provider_code("AB12~x"), + (None, "AB12~x"), + "uppercase is outside the code alphabet" + ); + } + + #[test] + fn provider_ownership_follows_the_code() { + let provider = HmacProvider::new(test_passphrase()); + let legacy = format!("{}.ABC123", "a".repeat(64)); + let coded = format!("hmac~{legacy}"); + let foreign = format!("zz00~{legacy}"); + assert!( + provider_owns_id(&provider, &coded), + "the provider owns identifiers carrying its own code" + ); + assert!( + provider_owns_id(&provider, &legacy), + "the built-in hmac provider dual-reads the legacy bare form" + ); + assert!( + !provider_owns_id(&provider, &foreign), + "an identifier with another provider's code is never owned" + ); + } + use crate::permissions::PermissionMaps; + use crate::redacted::Redacted; + + fn test_passphrase() -> Redacted { + Redacted::from("a-test-passphrase-32-bytes-minimum".to_owned()) + } + + fn test_request_info() -> OwnedRequestInfo { + OwnedRequestInfo::new("203.0.113.1".to_owned(), http::HeaderMap::new()) + } + + /// Test host signals with fixed JA4/H2 values. + #[derive(Debug)] + struct TestHostSignals { + ja4: Option, + h2: Option, + } + + impl HostSignals for TestHostSignals { + fn ja4(&self) -> Option<&str> { + self.ja4.as_deref() + } + fn h2(&self) -> Option<&str> { + self.h2.as_deref() + } + } + + #[test] + fn default_id_semantics_match_the_builtin_shape() { + let provider = HmacProvider::new(test_passphrase()); + + // The default `accepts_id` accepts the built-in HMAC shape and rejects + // anything else, so a built-in provider's identifiers round-trip while an + // opaque value is left to a provider that overrides the check. + let valid = format!("{}.{}", "a".repeat(64), "abc123"); + assert!(provider.accepts_id(&valid), "should accept the HMAC shape"); + assert!( + !provider.accepts_id("not-hmac-shaped"), + "should reject a non-HMAC identifier by default" + ); + + // The default `normalize_id_for_kv` lowercases the hash segment. This is + // exactly the transform that would corrupt an opaque case-sensitive + // identifier, which is why such a provider overrides it. + let mixed = format!("{}.{}", "A".repeat(64), "abc123"); + assert_eq!( + provider.normalize_id_for_kv(&mixed), + format!("{}.{}", "a".repeat(64), "abc123"), + "the default should lowercase the hash segment" + ); + } + + #[test] + fn shared_provider_delegates_id_semantics_to_the_inner_provider() { + // `SharedProvider` wraps an adapter-injected provider. It must forward + // every trait method to the inner provider, including `accepts_id` and + // `normalize_id_for_kv`; a wrapper that silently used the defaults would + // drop an opaque vendor identifier on read-back. This guards that + // delegation directly. + #[derive(Debug)] + struct Inner; + + impl EdgeCookieProvider for Inner { + fn id(&self) -> &'static str { + "inner" + } + + fn code(&self) -> ProviderCode { + ProviderCode::new("t0in") + } + + fn generate( + &self, + _request_info: &dyn RequestInfo, + _input: &IdentityInput<'_>, + ) -> Result> { + Ok(GeneratedEdgeCookie::default()) + } + + fn accepts_id(&self, value: &str) -> bool { + value == "opaque-ok" + } + + fn normalize_id_for_kv(&self, value: &str) -> String { + format!("kv:{value}") + } + } + + let shared = SharedProvider(Arc::new(Inner)); + + assert_eq!(shared.id(), "inner", "should delegate id"); + assert!( + shared.accepts_id("opaque-ok"), + "should delegate accepts_id acceptance to the inner provider" + ); + assert!( + !shared.accepts_id("something-else"), + "should delegate accepts_id rejection to the inner provider" + ); + assert_eq!( + shared.normalize_id_for_kv("x"), + "kv:x", + "should delegate normalize_id_for_kv to the inner provider" + ); + } + + #[test] + fn hmac_provider_requires_store_on_device() { + let provider = HmacProvider::new(test_passphrase()); + let required = provider.required_permissions(); + assert!( + required.contains(Permission::StoreOnDevice), + "the HMAC provider writes a cookie, so it requires necessary.operations.storage" + ); + assert!( + !required.contains(Permission::SelectPersonalisedAds), + "the HMAC provider requires no advertising permissions" + ); + } + + #[test] + fn host_signal_provider_mints_from_fingerprints_and_requires_store_on_device() { + let signals = Arc::new(TestHostSignals { + ja4: Some("t13d1516h2_8daaf6152771_e5627efa2ab1".to_owned()), + h2: Some("1:65536;4:6291456".to_owned()), + }); + let provider = HostSignalProvider::new(test_passphrase(), signals); + let request_info = test_request_info(); + let generated = provider + .generate(&request_info, &IdentityInput::default()) + .expect("should generate"); + assert!( + generated.id.is_some(), + "the host-signal provider mints an identifier from the fingerprints" + ); + assert!( + provider + .required_permissions() + .contains(Permission::StoreOnDevice), + "the host-signal provider writes a cookie, so it requires necessary.operations.storage" + ); + } + + /// A minimal provider that overrides nothing optional, used to prove the + /// trait defaults. + #[derive(Debug)] + struct MinimalProvider; + + impl EdgeCookieProvider for MinimalProvider { + fn id(&self) -> &'static str { + "minimal" + } + + fn code(&self) -> ProviderCode { + ProviderCode::new("t0mi") + } + + fn generate( + &self, + _request_info: &dyn RequestInfo, + _input: &IdentityInput<'_>, + ) -> Result> { + Ok(GeneratedEdgeCookie::default()) + } + + fn accepts_id(&self, _value: &str) -> bool { + true + } + } + + #[test] + fn a_neutral_provider_requires_no_permissions_by_default() { + // MinimalProvider does not override required_permissions, so it + // inherits the trait default of none and requires no permission. + assert!( + MinimalProvider.required_permissions().is_empty(), + "a vendor-neutral provider requires nothing by default" + ); + } + + #[test] + fn the_edge_cookie_gate_blocks_until_the_permission_is_set() { + let required = HmacProvider::new(test_passphrase()).required_permissions(); + // Empty maps with no default: every permission is the requires-signal + // floor. + let maps = PermissionMaps::empty(); + + // No signal: the provider's required permission is not set, so Trusted + // Server would not commit the Edge Cookie. + assert!( + !maps.resolve(None, None, |_| false).all_set(required), + "the floor should not run the Edge Cookie provider without the permission set" + ); + + // A grant signal for necessary.operations.storage: the provider's permission is now set. + assert!( + maps.resolve(None, None, |p| p == Permission::StoreOnDevice) + .all_set(required), + "the Edge Cookie provider runs once necessary.operations.storage is set" + ); + } + + #[test] + fn client_fixed_defers_in_generate() { + let request_info = test_request_info(); + let generated = ClientFixedProvider + .generate(&request_info, &IdentityInput::default()) + .expect("should generate"); + assert!( + generated.id.is_none(), + "client-fixed should defer in generate, deriving no edge identifier" + ); + } + + #[test] + fn client_fixed_mints_when_posted_word_matches() { + let input = ClientResolveInput { + payload: EXPECTED_VALUE.as_bytes(), + permissions: None, + consent: None, + }; + let generated = ClientFixedProvider + .resolve_from_client(&input) + .expect("should resolve"); + assert_eq!( + generated.id.as_deref(), + Some(EXPECTED_VALUE), + "the known shared word should verify and mint the Edge Cookie" + ); + } + + #[test] + fn client_fixed_rejects_unknown_word() { + let input = ClientResolveInput { + payload: b"not-the-word", + permissions: None, + consent: None, + }; + let generated = ClientFixedProvider + .resolve_from_client(&input) + .expect("should resolve"); + assert!( + generated.id.is_none(), + "a value that does not match the known word should mint no Edge Cookie" + ); + } + + #[test] + fn client_fixed_requires_store_on_device() { + assert!( + ClientFixedProvider + .required_permissions() + .contains(Permission::StoreOnDevice), + "client-fixed writes a cookie, so it requires necessary.operations.storage" + ); + } + + #[test] + fn server_side_provider_inherits_no_op_resolve_from_client() { + // HmacProvider does not override resolve_from_client, so it inherits the + // no-op default: a server-side provider does not participate in the + // client cycle. + let provider = HmacProvider::new(test_passphrase()); + let input = ClientResolveInput { + payload: b"anything", + permissions: None, + consent: None, + }; + let generated = provider + .resolve_from_client(&input) + .expect("should resolve"); + assert!( + generated.id.is_none(), + "a server-side provider inherits the no-op resolve_from_client default" + ); + } + + #[test] + fn the_fixed_word_and_marker_name_match_the_page_script() { + // The demo page script and this provider share the fixed word by + // convention; the resolved-marker cookie name is likewise shared with + // the script. Assert against the script source so a rename on either + // side fails this test instead of silently breaking the round trip. + let script = include_str!( + "../../../trusted-server-js/lib/src/integrations/ec_client_fixed/index.ts" + ); + assert!( + script.contains(&format!("const FIXED_WORD = '{EXPECTED_VALUE}'")), + "the page script's FIXED_WORD should match EXPECTED_VALUE" + ); + assert!( + script.contains(&format!( + "const MARKER_COOKIE_NAME = '{}'", + crate::constants::COOKIE_TS_EC_RESOLVED + )), + "the page script's marker cookie name should match COOKIE_TS_EC_RESOLVED" + ); + } + + #[test] + fn a_selected_but_uninjected_vendor_provider_fails_loudly() { + let ec = Ec { + provider: Some("acme".to_owned()), + ..Ec::default() + }; + + let err = build_provider(&ec, None, None) + .expect_err("selecting a provider the adapter does not inject should error"); + assert!( + err.to_string().contains("acme"), + "the error should name the selected provider, got: {err}" + ); + } + + #[test] + fn host_signal_provider_defers_without_fingerprints() { + let signals = Arc::new(TestHostSignals { + ja4: None, + h2: None, + }); + let provider = HostSignalProvider::new(test_passphrase(), signals); + let request_info = test_request_info(); + let generated = provider + .generate(&request_info, &IdentityInput::default()) + .expect("should generate"); + assert!( + generated.id.is_none(), + "with no host fingerprints the provider should defer rather than mint an IP-only identifier" + ); + } +} diff --git a/crates/trusted-server-core/src/ec/pull_sync.rs b/crates/trusted-server-core/src/ec/pull_sync.rs index 546605f8e..cca91d8fc 100644 --- a/crates/trusted-server-core/src/ec/pull_sync.rs +++ b/crates/trusted-server-core/src/ec/pull_sync.rs @@ -55,10 +55,13 @@ struct PullSyncResponse { /// Builds post-send pull-sync context from the route EC context. /// -/// Returns `None` when consent denies EC or there is no active EC ID. +/// Returns `None` when sharing is not permitted or there is no active EC ID. +/// Pull sync sends the identifier to a partner, so it needs the same +/// permission pair as bidstream EIDs (storage plus personalised-ad +/// selection), not only the provider's storage permission. #[must_use] pub fn build_pull_sync_context(ec_context: &EcContext) -> Option { - if !ec_context.ec_allowed() { + if !ec_context.ec_sharing_allowed() { return None; } diff --git a/crates/trusted-server-core/src/ec/resolve.rs b/crates/trusted-server-core/src/ec/resolve.rs new file mode 100644 index 000000000..a74f9682e --- /dev/null +++ b/crates/trusted-server-core/src/ec/resolve.rs @@ -0,0 +1,691 @@ +//! Client-cycle Edge Cookie resolution endpoint (`POST /_ts/api/v1/ec/resolve`). +//! +//! A client-side Edge Cookie provider defers on the organic page request +//! (deriving no identifier at the edge) and lets the page do the work in the +//! browser. When the page has its result it posts the value here, and this +//! endpoint hands it to the configured provider's +//! [`resolve_from_client`](super::provider::EdgeCookieProvider::resolve_from_client) +//! to mint the Edge Cookie. +//! +//! The endpoint is provider-agnostic: it bounds the body, gates on the +//! permission model (the same gate as organic generation), calls the provider, +//! and sets the cookie on its own response so the value is live for every +//! subsequent first-party request. Whether the posted value is trustworthy is +//! the provider's responsibility. The payload arrives from the browser, so a +//! real provider verifies it (for example an OWID signature) before minting. + +use edgezero_core::body::Body as EdgeBody; +use error_stack::Report; +use http::{HeaderValue, Request, Response, StatusCode, header}; + +use crate::error::TrustedServerError; +use crate::settings::Settings; + +use super::EcContext; +use super::cookies::{ + ec_id_has_only_allowed_chars, set_provider_ec_cookie, set_resolved_marker_cookie, +}; +use super::kv::KvIdentityGraph; +use super::kv_types::KvEntry; +use super::provider::{ClientResolveInput, build_provider}; + +/// Maximum size of a resolve request body. +/// +/// Client-cycle payloads (a random value, or a signed envelope such as a +/// vendor JSON payload) are small; this bound guards against an oversized body +/// before it is read into memory. +const MAX_BODY_SIZE: usize = 64 * 1024; + +/// Handles `POST /_ts/api/v1/ec/resolve`. +/// +/// The request must carry an `Origin` on the publisher's domain (this endpoint +/// sets identity state, so a foreign page must not be able to drive it) and a +/// `text/plain` or `application/json` body. Gates on the configured provider's +/// required permissions, then asks the provider to mint an Edge Cookie from +/// the posted payload. A minted identifier is persisted to the identity graph +/// before the cookie is set, so withdrawal reaches a client-set identity the +/// same way it reaches an edge-minted one; with no graph available nothing is +/// minted, matching the organic path's rule against phantom cookies. On +/// success the EC cookie and its `non-HttpOnly` resolved marker are set and the +/// status is `200`. +/// +/// Rejections: `403` for a missing or foreign `Origin`, `415` for another +/// content type, `413` for an oversized body, `400` when the provider mints an +/// identifier outside the identifier bounds, `409` when the request already +/// carries a different identity (a resolve must not silently replace one), and +/// `503` when the identity-graph write fails. When the permission gate is +/// closed, no provider is configured, no graph is available, or the provider +/// mints nothing, the response is `204` with no cookie. Every response carries +/// `Cache-Control: no-store`. +/// +/// # Errors +/// +/// Returns [`TrustedServerError`] when the provider fails to process the +/// payload. A payload that is merely unverified or absent yields a `204` +/// rather than an error. +pub fn handle_ec_resolve( + settings: &Settings, + req: Request, + ec_context: &EcContext, + kv: Option<&KvIdentityGraph>, +) -> Result, Report> { + // This endpoint sets identity state from a page script, so the posted + // request must originate from the publisher's own site. Browsers always + // send `Origin` on cross-origin POSTs and on same-origin `fetch` POSTs, + // so its absence means a non-browser caller, which has no business here. + if !origin_is_publisher(&req, settings) { + log::warn!("EC resolve rejected: missing or foreign Origin"); + return Ok(status_only(StatusCode::FORBIDDEN)); + } + + // The page script posts plain text; a vendor payload may be JSON. Anything + // else is not a resolve payload. + if !content_type_is_allowed(&req) { + return Ok(status_only(StatusCode::UNSUPPORTED_MEDIA_TYPE)); + } + + // Gate: the configured provider's required permissions must be set for + // this request, the same gate as the organic generation path. A + // client-driven resolve does not bypass the permission model. + if !ec_context.ec_allowed() { + log::info!("EC resolve skipped: required permissions not set"); + return Ok(status_only(StatusCode::NO_CONTENT)); + } + + // Rebuild the provider with the same host signals captured on the context, so + // a provider that needs a service the host cannot supply fails here. The + // client value is verified from the posted body below, not from request info. + let Some(provider) = build_provider( + &settings.ec, + ec_context.host_signals(), + ec_context.ec_provider(), + )? + else { + log::info!("EC resolve skipped: no Edge Cookie provider configured"); + return Ok(status_only(StatusCode::NO_CONTENT)); + }; + + // Bound the body before reading it into memory. + if content_length_exceeds_limit(&req, MAX_BODY_SIZE) { + return Ok(status_only(StatusCode::PAYLOAD_TOO_LARGE)); + } + let payload = req.into_body().into_bytes().unwrap_or_default(); + if payload.len() > MAX_BODY_SIZE { + return Ok(status_only(StatusCode::PAYLOAD_TOO_LARGE)); + } + + let input = ClientResolveInput { + payload: payload.as_ref(), + permissions: Some(ec_context.permissions()), + consent: Some(ec_context.consent()), + }; + + let generated = provider.resolve_from_client(&input)?; + log::debug!( + "EC resolve handled (provider={}): id {}", + provider.id(), + if generated.id.is_some() { + "minted" + } else { + "not minted" + }, + ); + + let generated_id = generated + .id + .map(|value| super::provider::apply_provider_code(provider.as_ref(), &value)); + let Some(ec_id) = generated_id else { + let mut response = status_only(StatusCode::NO_CONTENT); + for (name, value) in generated.response_headers { + response.headers_mut().insert(name, value); + } + return Ok(response); + }; + + // The same identifier bounds as the organic mint path: reject, never + // rewrite. A provider that minted an out-of-bounds identifier is a bad + // request from the client's perspective, because the posted payload + // produced an unusable identity. + if !ec_id_has_only_allowed_chars(&ec_id) { + log::error!( + "EC resolve rejected: provider `{}` minted an identifier outside the bounds", + provider.id(), + ); + return Ok(status_only(StatusCode::BAD_REQUEST)); + } + + // A resolve must not silently replace an identity the request already + // carries. The page script does not post when an identity exists, so a + // different minted identifier here is a conflict to surface, not paper + // over. + if let Some(existing) = ec_context.ec_value() + && existing != ec_id + { + log::warn!( + "EC resolve rejected: request already carries a different identity (provider={})", + provider.id(), + ); + return Ok(status_only(StatusCode::CONFLICT)); + } + + // Persist the identity-graph row before setting the cookie, keyed by the + // provider's canonical form, exactly like the organic mint path. Without + // a row, withdrawal could never reach this identity, so with no graph + // available nothing is minted (the organic path applies the same rule + // against phantom cookies). + let Some(graph) = kv else { + log::warn!("EC resolve skipped: no identity graph available, so no cookie is minted"); + return Ok(status_only(StatusCode::NO_CONTENT)); + }; + let now = super::current_timestamp(); + let mut entry = KvEntry::new( + ec_context.consent(), + ec_context.geo_info(), + now, + &settings.publisher.domain, + ); + entry.device = ec_context + .device_signals() + .map(super::device::DeviceSignals::to_kv_device); + let kv_key = super::provider::provider_kv_key(provider.as_ref(), &ec_id); + if let Err(err) = graph.create_or_revive(&kv_key, &entry) { + log::error!("EC resolve failed to write the identity-graph row: {err:?}"); + return Ok(status_only(StatusCode::SERVICE_UNAVAILABLE)); + } + + let mut response = status_only(StatusCode::OK); + + // Apply any response headers the provider asked for (for example to request + // more client evidence on a later request). Empty for the demo provider. + for (name, value) in generated.response_headers { + response.headers_mut().insert(name, value); + } + + set_provider_ec_cookie(settings, &mut response, &ec_id); + // The Edge Cookie is HttpOnly, so the page script cannot see it; the + // non-HttpOnly marker tells the script the resolve succeeded so it does + // not post again on every page view. + set_resolved_marker_cookie(settings, &mut response); + + Ok(response) +} + +/// Whether the request's `Origin` names the publisher's domain (exactly, or a +/// subdomain of it). +fn origin_is_publisher(req: &Request, settings: &Settings) -> bool { + let Some(origin) = req + .headers() + .get(header::ORIGIN) + .and_then(|value| value.to_str().ok()) + else { + return false; + }; + let Some(host) = origin + .strip_prefix("https://") + .or_else(|| origin.strip_prefix("http://")) + else { + return false; + }; + let host = host.split(':').next().unwrap_or(host); + let publisher = settings.publisher.domain.as_str(); + host.eq_ignore_ascii_case(publisher) + || host + .to_ascii_lowercase() + .ends_with(&format!(".{}", publisher.to_ascii_lowercase())) +} + +/// Whether the request's `Content-Type` is one a resolve payload may use. +fn content_type_is_allowed(req: &Request) -> bool { + req.headers() + .get(header::CONTENT_TYPE) + .and_then(|value| value.to_str().ok()) + .map(|value| value.split(';').next().unwrap_or(value).trim()) + .is_some_and(|media_type| { + media_type.eq_ignore_ascii_case("text/plain") + || media_type.eq_ignore_ascii_case("application/json") + }) +} + +/// Builds a bodiless response with the given status. Identity-resolution +/// responses must never be cached by the browser or an intermediary. +fn status_only(status: StatusCode) -> Response { + let mut response = Response::new(EdgeBody::empty()); + *response.status_mut() = status; + response + .headers_mut() + .insert(header::CACHE_CONTROL, HeaderValue::from_static("no-store")); + response +} + +/// Returns `true` when the request advertises a `Content-Length` over `limit`. +fn content_length_exceeds_limit(req: &Request, limit: usize) -> bool { + req.headers() + .get(header::CONTENT_LENGTH) + .and_then(|value| value.to_str().ok()) + .and_then(|value| value.parse::().ok()) + .is_some_and(|len| len > limit) +} + +#[cfg(test)] +mod tests { + use super::*; + use crate::consent::types::ConsentContext; + use crate::ec::provider::{EdgeCookieProvider, GeneratedEdgeCookie, IdentityInput}; + use crate::evidence::RequestInfo; + use crate::platform::test_support::noop_services_with_ec_provider; + use crate::test_support::tests::create_test_settings; + use http::Method; + use std::sync::Arc; + + fn settings_with_client_fixed() -> Settings { + let mut settings = create_test_settings(); + settings.ec.provider = Some("client-fixed".to_owned()); + settings + } + + // The fixed word shared by the client-fixed provider and its page script. + const FIXED_WORD: &str = "an-ec"; + + fn post(body: &str) -> Request { + post_with(Some("https://test-publisher.com"), Some("text/plain"), body) + } + + fn post_with( + origin: Option<&str>, + content_type: Option<&str>, + body: &str, + ) -> Request { + let mut builder = Request::builder() + .method(Method::POST) + .uri("https://test-publisher.com/_ts/api/v1/ec/resolve"); + if let Some(origin) = origin { + builder = builder.header(header::ORIGIN, origin); + } + if let Some(content_type) = content_type { + builder = builder.header(header::CONTENT_TYPE, content_type); + } + builder + .body(EdgeBody::from(body.to_owned())) + .expect("should build resolve request") + } + + fn in_memory_graph() -> crate::ec::kv::KvIdentityGraph { + crate::ec::kv::KvIdentityGraph::in_memory("test-ec-store") + } + + fn gated(ec_allowed: bool) -> EcContext { + EcContext::new_for_test_gated(None, ConsentContext::default(), ec_allowed) + } + + /// Returns whether `value` is a canonical UUID (`8-4-4-4-12` lowercase hex). + fn is_uuid(value: &str) -> bool { + let groups = [8, 4, 4, 4, 12]; + let parts: Vec<&str> = value.split('-').collect(); + parts.len() == groups.len() + && parts.iter().zip(groups).all(|(part, len)| { + part.len() == len + && part + .bytes() + .all(|b| b.is_ascii_digit() || (b'a'..=b'f').contains(&b)) + }) + } + + /// A **test-only** provider modeling a client-generated, first-party + /// identifier (a `UUID`) that the browser mints and posts back for the server + /// to set. It is not a production provider and exists only to exercise the + /// client-set Edge Cookie value path from end to end. The edge defers, the + /// page posts a value, and it must round-trip as the cookie and the KV key. + /// + /// A `UUID` has no separator, so the built-in [`normalize_id_for_kv`] default + /// would append a trailing dot and corrupt it, which is why this provider + /// (like any opaque-identifier provider) returns the value unchanged. + /// + /// [`normalize_id_for_kv`]: EdgeCookieProvider::normalize_id_for_kv + #[derive(Debug)] + struct TestIdProvider; + + impl EdgeCookieProvider for TestIdProvider { + fn id(&self) -> &'static str { + "testid" + } + + fn code(&self) -> crate::ec::provider::ProviderCode { + crate::ec::provider::ProviderCode::new("t0id") + } + + fn generate( + &self, + _request_info: &dyn RequestInfo, + _input: &IdentityInput<'_>, + ) -> Result> { + // The identifier is minted in the browser, so the edge derives nothing. + Ok(GeneratedEdgeCookie::default()) + } + + fn resolve_from_client( + &self, + input: &ClientResolveInput<'_>, + ) -> Result> { + // The page posts the identifier it generated. Accept a well-formed UUID. + let value = core::str::from_utf8(input.payload) + .unwrap_or_default() + .trim(); + if is_uuid(value) { + Ok(GeneratedEdgeCookie { + id: Some(value.to_owned()), + response_headers: Vec::new(), + }) + } else { + Ok(GeneratedEdgeCookie::default()) + } + } + + fn accepts_id(&self, value: &str) -> bool { + is_uuid(value) + } + + fn normalize_id_for_kv(&self, value: &str) -> String { + value.to_owned() + } + } + + #[test] + fn client_set_value_round_trips_through_the_ec_scenario() { + // A client-generated first-party UUID, the value the browser posts back. + const TEST_ID: &str = "3f2504e0-4f89-41d3-9a0c-0305e82c3301"; + + let provider: Arc = Arc::new(TestIdProvider); + let mut settings = create_test_settings(); + settings.ec.provider = Some("testid".to_owned()); + let services = noop_services_with_ec_provider(Arc::clone(&provider)); + + // 1. Organic first visit: no EC yet, and the edge defers because the + // identifier is generated in the browser, not derived server-side. + let organic = Request::builder() + .method(Method::GET) + .uri("https://edge.example.com/") + .body(EdgeBody::empty()) + .expect("should build organic request"); + let mut ec = EcContext::read_from_request(&settings, &organic, &services) + .expect("should read EC context"); + assert!( + ec.ec_value().is_none(), + "no EC should exist on the first visit" + ); + ec.generate_if_needed(&settings, None) + .expect("should run generation"); + assert!( + ec.ec_value().is_none(), + "a client-set provider defers minting to the browser" + ); + + // 2. The page generates its identifier and posts it to the resolve + // endpoint; the server persists the identity-graph row and sets the + // value as the EC cookie. + const CODED_TEST_ID: &str = "t0id~3f2504e0-4f89-41d3-9a0c-0305e82c3301"; + let graph = in_memory_graph(); + let response = handle_ec_resolve(&settings, post(TEST_ID), &ec, Some(&graph)) + .expect("should handle resolve"); + assert_eq!( + response.status(), + StatusCode::OK, + "a valid client-set value should return 200" + ); + let set_cookie = response + .headers() + .get(header::SET_COOKIE) + .expect("should set the EC cookie") + .to_str() + .expect("should be utf-8"); + assert!( + set_cookie.contains(CODED_TEST_ID), + "the EC cookie should carry the coded client-set identifier, got {set_cookie}" + ); + assert!( + graph + .get(CODED_TEST_ID) + .expect("should read the graph") + .is_some(), + "the resolve should persist the identity-graph row, so withdrawal can reach it" + ); + + // 3. A later request carries the EC cookie; the server reads the + // identifier back verbatim. This is the step the built-in shape check + // used to drop. + let ret = Request::builder() + .method(Method::GET) + .uri("https://edge.example.com/") + .header("cookie", format!("ts-ec={CODED_TEST_ID}")) + .body(EdgeBody::empty()) + .expect("should build return request"); + let ec2 = EcContext::read_from_request(&settings, &ret, &services) + .expect("should read EC context"); + assert_eq!( + ec2.ec_value(), + Some(CODED_TEST_ID), + "the client-set identifier should round-trip as the coded EC value" + ); + } + + #[test] + fn resolve_sets_cookie_marker_and_no_store_when_word_matches_and_allowed() { + let settings = settings_with_client_fixed(); + let graph = in_memory_graph(); + let response = handle_ec_resolve(&settings, post(FIXED_WORD), &gated(true), Some(&graph)) + .expect("should handle resolve"); + + assert_eq!( + response.status(), + StatusCode::OK, + "a verified value should return 200" + ); + let cookies: Vec = response + .headers() + .get_all(header::SET_COOKIE) + .iter() + .map(|value| value.to_str().expect("should be utf-8").to_owned()) + .collect(); + let ec_cookie = cookies + .iter() + .find(|cookie| cookie.starts_with("ts-ec=")) + .expect("should set the EC cookie"); + assert!( + ec_cookie.contains("cfix~an-ec"), + "should set the coded verified word as the EC cookie, got {ec_cookie}" + ); + assert!( + ec_cookie.contains("HttpOnly"), + "the EC cookie should be HttpOnly" + ); + assert!( + ec_cookie.contains("Secure"), + "the EC cookie should be Secure" + ); + let marker = cookies + .iter() + .find(|cookie| cookie.starts_with("ts-ecr=1")) + .expect("should set the resolved marker cookie"); + assert!( + !marker.contains("HttpOnly"), + "the marker must be readable by the page script, so not HttpOnly" + ); + assert_eq!( + response + .headers() + .get(header::CACHE_CONTROL) + .and_then(|value| value.to_str().ok()), + Some("no-store"), + "identity responses must never be cached" + ); + assert!( + graph + .get("cfix~an-ec") + .expect("should read the graph") + .is_some(), + "the resolve should persist the identity-graph row under the coded key" + ); + } + + #[test] + fn resolve_returns_204_when_not_allowed() { + let settings = settings_with_client_fixed(); + let graph = in_memory_graph(); + let response = handle_ec_resolve(&settings, post(FIXED_WORD), &gated(false), Some(&graph)) + .expect("should handle resolve"); + + assert_eq!( + response.status(), + StatusCode::NO_CONTENT, + "a closed permission gate should return 204" + ); + assert!( + response.headers().get(header::SET_COOKIE).is_none(), + "a closed gate should set no cookie" + ); + } + + #[test] + fn resolve_returns_204_when_no_provider_configured() { + let mut settings = create_test_settings(); + settings.ec.provider = None; + let graph = in_memory_graph(); + let response = handle_ec_resolve(&settings, post("123"), &gated(true), Some(&graph)) + .expect("should handle resolve"); + + assert_eq!( + response.status(), + StatusCode::NO_CONTENT, + "no configured provider should return 204" + ); + assert!( + response.headers().get(header::SET_COOKIE).is_none(), + "no configured provider should set no cookie" + ); + } + + #[test] + fn resolve_rejects_oversized_body() { + let settings = settings_with_client_fixed(); + let big = "x".repeat(MAX_BODY_SIZE + 1); + let graph = in_memory_graph(); + let response = handle_ec_resolve(&settings, post(&big), &gated(true), Some(&graph)) + .expect("should handle resolve"); + + assert_eq!( + response.status(), + StatusCode::PAYLOAD_TOO_LARGE, + "an oversized body should be rejected with 413" + ); + } + + #[test] + fn resolve_rejects_a_missing_or_foreign_origin() { + let settings = settings_with_client_fixed(); + let graph = in_memory_graph(); + for origin in [None, Some("https://attacker.example")] { + let request = post_with(origin, Some("text/plain"), FIXED_WORD); + let response = handle_ec_resolve(&settings, request, &gated(true), Some(&graph)) + .expect("should handle resolve"); + assert_eq!( + response.status(), + StatusCode::FORBIDDEN, + "an identity-setting POST must come from the publisher's own site" + ); + assert!( + response.headers().get(header::SET_COOKIE).is_none(), + "a rejected origin must set no cookie" + ); + } + } + + #[test] + fn resolve_accepts_a_publisher_subdomain_origin() { + let settings = settings_with_client_fixed(); + let graph = in_memory_graph(); + let request = post_with( + Some("https://www.test-publisher.com"), + Some("text/plain"), + FIXED_WORD, + ); + let response = handle_ec_resolve(&settings, request, &gated(true), Some(&graph)) + .expect("should handle resolve"); + assert_eq!( + response.status(), + StatusCode::OK, + "a subdomain of the publisher should be accepted" + ); + } + + #[test] + fn resolve_rejects_an_unexpected_content_type() { + let settings = settings_with_client_fixed(); + let graph = in_memory_graph(); + let request = post_with( + Some("https://test-publisher.com"), + Some("application/x-www-form-urlencoded"), + FIXED_WORD, + ); + let response = handle_ec_resolve(&settings, request, &gated(true), Some(&graph)) + .expect("should handle resolve"); + assert_eq!( + response.status(), + StatusCode::UNSUPPORTED_MEDIA_TYPE, + "only text/plain and application/json bodies are resolve payloads" + ); + } + + #[test] + fn resolve_conflicts_when_a_different_identity_already_exists() { + let settings = settings_with_client_fixed(); + let graph = in_memory_graph(); + let existing = format!("{}.ABC123", "e".repeat(64)); + let ec_context = + EcContext::new_for_test_gated(Some(existing), ConsentContext::default(), true); + let response = handle_ec_resolve(&settings, post(FIXED_WORD), &ec_context, Some(&graph)) + .expect("should handle resolve"); + assert_eq!( + response.status(), + StatusCode::CONFLICT, + "a resolve must not silently replace an existing identity" + ); + assert!( + response.headers().get(header::SET_COOKIE).is_none(), + "a conflict must set no cookie" + ); + } + + #[test] + fn resolve_mints_nothing_without_an_identity_graph() { + let settings = settings_with_client_fixed(); + let response = handle_ec_resolve(&settings, post(FIXED_WORD), &gated(true), None) + .expect("should handle resolve"); + assert_eq!( + response.status(), + StatusCode::NO_CONTENT, + "with no graph there is no row to persist, so nothing is minted" + ); + assert!( + response.headers().get(header::SET_COOKIE).is_none(), + "a cookie without a graph row would be a phantom identity" + ); + } + + #[test] + fn resolve_sets_no_cookie_for_unmatched_word() { + let settings = settings_with_client_fixed(); + let graph = in_memory_graph(); + let response = + handle_ec_resolve(&settings, post("not-the-word"), &gated(true), Some(&graph)) + .expect("should handle resolve"); + + assert_eq!( + response.status(), + StatusCode::NO_CONTENT, + "a value that fails verification should yield no cookie and a 204" + ); + assert!( + response.headers().get(header::SET_COOKIE).is_none(), + "an unmatched value should set no cookie" + ); + } +} diff --git a/crates/trusted-server-core/src/edge_cookie.rs b/crates/trusted-server-core/src/edge_cookie.rs index a4cdb4730..f3d6d2431 100644 --- a/crates/trusted-server-core/src/edge_cookie.rs +++ b/crates/trusted-server-core/src/edge_cookie.rs @@ -11,24 +11,29 @@ use crate::constants::{COOKIE_TS_EC, HEADER_X_TS_EC}; use crate::cookies::handle_request_cookies; use crate::ec::cookies::ec_id_has_only_allowed_chars; #[cfg(test)] -use crate::ec::generation::{generate_ec_id as generate_canonical_ec_id, normalize_ip}; +use crate::ec::generation::normalize_ip; +#[cfg(test)] +use crate::ec::provider::{IdentityInput, build_provider}; use crate::error::TrustedServerError; #[cfg(test)] +use crate::evidence::BorrowedRequestInfo; +#[cfg(test)] use crate::platform::RuntimeServices; #[cfg(test)] use crate::settings::Settings; -/// Generates a fresh EC ID based on client IP address. +/// Generates a fresh EC ID using the configured Edge Cookie provider. /// -/// Delegates to the canonical generator in [`crate::ec::generation`] so a -/// single normalization + HMAC path produces EC IDs. The canonical -/// `normalize_ip` format is a stable contract — EC hashes stored in KV -/// depend on it, and a divergent normalization would mint non-correlating -/// identities for the same client. +/// Routes through the pluggable provider model: the active `[ec] provider` +/// selection decides the outcome. Returns `Ok(None)` when no provider is +/// configured, so Trusted Server runs statelessly and mints no Edge Cookie. +/// `request_headers` lets a provider that derives identity from request +/// evidence read it; the built-in HMAC provider ignores it and uses only the +/// normalized client IP. /// /// # Errors /// -/// - [`TrustedServerError::EdgeCookie`] if HMAC generation fails +/// - [`TrustedServerError::EdgeCookie`] if provider generation fails /// /// Currently exercised only by tests: the production EC lifecycle generates IDs /// through [`crate::ec`]/`EcContext` rather than this edge-cookie helper. @@ -36,18 +41,43 @@ use crate::settings::Settings; pub fn generate_ec_id( settings: &Settings, services: &RuntimeServices, -) -> Result> { - // Fallback to "unknown" when client IP is unavailable (e.g., local testing). - // All such requests share the same HMAC base; the random suffix provides uniqueness. + request_headers: Option<&http::HeaderMap>, +) -> Result, Report> { + // Fall back to "unknown" when the client IP is unavailable (for example in + // local testing). All such requests share the same HMAC base; the random + // suffix provides uniqueness. let client_ip = services - .client_info + .client_info() .client_ip .map(normalize_ip) .unwrap_or_else(|| "unknown".to_string()); log::trace!("Generating fresh EC ID from normalized client context"); - generate_canonical_ec_id(settings, &client_ip) + let Some(provider) = build_provider( + &settings.ec, + services.host_signals(), + services.ec_provider(), + )? + else { + log::info!("No Edge Cookie provider configured; running statelessly"); + return Ok(None); + }; + + // The provider reads request data (the client IP, and on a fingerprinting + // host the TLS/HTTP-2 signals) borrowed at call time, so nothing is cloned. + let request_info = BorrowedRequestInfo::new(&client_ip, request_headers); + // The publisher path applies the permission gate at the call site, and the + // built-in provider reads neither the resolved permissions nor consent, so + // they are not threaded here. + let generated = provider.generate(&request_info, &IdentityInput::default())?; + let generated = crate::ec::provider::GeneratedEdgeCookie { + id: generated + .id + .map(|value| crate::ec::provider::apply_provider_code(provider.as_ref(), &value)), + response_headers: generated.response_headers, + }; + Ok(generated.id) } /// Gets an existing EC ID from the request. @@ -99,7 +129,10 @@ pub fn get_ec_id(req: &Request) -> Result, Report, -) -> Result> { +) -> Result, Report> { if let Some(id) = get_ec_id(req)? { - return Ok(id); + return Ok(Some(id)); } - // If no existing EC ID found, generate a fresh one - let ec_id = generate_ec_id(settings, services)?; - log::trace!("No existing EC ID found; generated a fresh EC ID"); + // If no existing EC ID found, generate a fresh one through the provider. + let ec_id = generate_ec_id(settings, services, Some(req.headers()))?; + if ec_id.is_some() { + log::trace!("No existing EC ID found; generated a fresh EC ID"); + } Ok(ec_id) } @@ -130,7 +165,7 @@ pub fn get_or_generate_ec_id( settings: &Settings, services: &RuntimeServices, req: &Request, -) -> Result> { +) -> Result, Report> { get_or_generate_ec_id_from_http_request(settings, services, req) } @@ -141,6 +176,7 @@ mod tests { use http::{HeaderName, header}; use std::net::{IpAddr, Ipv4Addr, Ipv6Addr}; + use crate::ec::generation::generate_ec_id as generate_canonical_ec_id; use crate::platform::test_support::{noop_services, noop_services_with_client_ip}; use crate::test_support::tests::create_test_settings; @@ -155,13 +191,24 @@ mod tests { 0x2001, 0x0db8, 0x85a3, 0x0000, 0x8a2e, 0x0370, 0x7334, 0x1234, )); - let id_here = generate_ec_id(&settings, &noop_services_with_client_ip(ip)) - .expect("should generate EC ID via edge_cookie"); - let id_canonical = generate_canonical_ec_id(&settings, &normalize_ip(ip)) + let id_here = generate_ec_id(&settings, &noop_services_with_client_ip(ip), None) + .expect("should generate EC ID via edge_cookie") + .expect("should configure the hmac provider in test settings"); + let passphrase = settings + .ec + .providers + .hmac + .as_ref() + .map(|hmac| hmac.passphrase.expose().as_str()) + .unwrap_or(""); + let id_canonical = generate_canonical_ec_id(passphrase, &normalize_ip(ip)) .expect("should generate EC ID via canonical generator"); + let bare_here = id_here + .strip_prefix("hmac~") + .expect("should carry the hmac provider code"); assert_eq!( - crate::ec::ec_hash(&id_here), + crate::ec::ec_hash(bare_here), crate::ec::ec_hash(&id_canonical), "should produce the same identity hash prefix as the canonical generator" ); @@ -178,6 +225,10 @@ mod tests { } fn is_ec_id_format(value: &str) -> bool { + // The coded envelope: hmac~<64hex>.<6alnum>. + let Some(value) = value.strip_prefix("hmac~") else { + return false; + }; let mut parts = value.split('.'); let hmac_part = match parts.next() { Some(part) => part, @@ -206,11 +257,27 @@ mod tests { fn test_generate_ec_id() { let settings: Settings = create_test_settings(); - let ec_id = generate_ec_id(&settings, &noop_services()).expect("should generate EC ID"); + let ec_id = generate_ec_id(&settings, &noop_services(), None) + .expect("should generate EC ID") + .expect("should configure the hmac provider in test settings"); log::debug!("Generated EC ID: {}", ec_id); assert!( is_ec_id_format(&ec_id), - "should match EC ID format: {{64hex}}.{{6alnum}}" + "should match the coded EC ID format: hmac~{{64hex}}.{{6alnum}}" + ); + } + + #[test] + fn generate_ec_id_returns_none_when_no_provider_is_configured() { + let mut settings = create_test_settings(); + // No provider selected: Trusted Server runs statelessly. + settings.ec.provider = None; + + let id = generate_ec_id(&settings, &noop_services(), None) + .expect("generation should not error when no provider is configured"); + assert!( + id.is_none(), + "no Edge Cookie provider should mean no Edge Cookie is minted" ); } @@ -219,10 +286,12 @@ mod tests { let settings = create_test_settings(); let ip = IpAddr::V4(Ipv4Addr::new(203, 0, 113, 1)); - let id_with_ip = generate_ec_id(&settings, &noop_services_with_client_ip(ip)) - .expect("should generate EC ID with client IP"); - let id_without_ip = generate_ec_id(&settings, &noop_services()) - .expect("should generate EC ID without client IP"); + let id_with_ip = generate_ec_id(&settings, &noop_services_with_client_ip(ip), None) + .expect("should generate EC ID with client IP") + .expect("should configure the hmac provider in test settings"); + let id_without_ip = generate_ec_id(&settings, &noop_services(), None) + .expect("should generate EC ID without client IP") + .expect("should configure the hmac provider in test settings"); let hmac_with_ip = id_with_ip.split_once('.').expect("should contain dot").0; let hmac_without_ip = id_without_ip.split_once('.').expect("should contain dot").0; @@ -235,22 +304,28 @@ mod tests { #[test] fn test_is_ec_id_format_accepts_valid_value() { - let value = format!("{}.{}", "a".repeat(64), "Ab12z9"); + let value = format!("hmac~{}.{}", "a".repeat(64), "Ab12z9"); assert!( is_ec_id_format(&value), - "should accept a valid EC ID format" + "should accept a valid coded EC ID format" ); } #[test] fn test_is_ec_id_format_rejects_invalid_values() { - let missing_suffix = "a".repeat(64); + let bare_legacy_shape = format!("{}.{}", "a".repeat(64), "Ab12z9"); + assert!( + !is_ec_id_format(&bare_legacy_shape), + "a fresh mint always carries the provider code" + ); + + let missing_suffix = format!("hmac~{}", "a".repeat(64)); assert!( !is_ec_id_format(&missing_suffix), "should reject missing suffix" ); - let invalid_hex = format!("{}.{}", "a".repeat(63) + "g", "Ab12z9"); + let invalid_hex = format!("hmac~{}.{}", "a".repeat(63) + "g", "Ab12z9"); assert!( !is_ec_id_format(&invalid_hex), "should reject non-hex HMAC content" @@ -278,7 +353,8 @@ mod tests { assert_eq!(ec_id, Some("existing_ec_id".to_string())); let ec_id = get_or_generate_ec_id(&settings, &noop_services(), &req) - .expect("should reuse header EC ID"); + .expect("should reuse header EC ID") + .expect("an existing EC should be present"); assert_eq!(ec_id, "existing_ec_id"); } @@ -294,7 +370,8 @@ mod tests { assert_eq!(ec_id, Some("existing_cookie_id".to_string())); let ec_id = get_or_generate_ec_id(&settings, &noop_services(), &req) - .expect("should reuse cookie EC ID"); + .expect("should reuse cookie EC ID") + .expect("an existing EC should be present"); assert_eq!(ec_id, "existing_cookie_id"); } @@ -326,7 +403,8 @@ mod tests { .expect("should build test request"); let ec_id = get_or_generate_ec_id_from_http_request(&settings, &noop_services(), &req) - .expect("should reuse cookie EC ID from http request"); + .expect("should reuse cookie EC ID from http request") + .expect("an existing EC should be present"); assert_eq!(ec_id, "existing_http_cookie_id"); } @@ -344,7 +422,8 @@ mod tests { let req = create_test_request(&[]); let ec_id = get_or_generate_ec_id(&settings, &noop_services(), &req) - .expect("should get or generate EC ID"); + .expect("should get or generate EC ID") + .expect("should configure the hmac provider in test settings"); assert!(!ec_id.is_empty()); } @@ -369,7 +448,8 @@ mod tests { let req = create_test_request(&[(HEADER_X_TS_EC, "evil;injected")]); let ec_id = get_or_generate_ec_id(&settings, &noop_services(), &req) - .expect("should generate fresh ID on invalid header"); + .expect("should generate fresh ID on invalid header") + .expect("should configure the hmac provider in test settings"); assert_ne!( ec_id, "evil;injected", "should not use tampered header value" diff --git a/crates/trusted-server-core/src/evidence.rs b/crates/trusted-server-core/src/evidence.rs new file mode 100644 index 000000000..804251d0b --- /dev/null +++ b/crates/trusted-server-core/src/evidence.rs @@ -0,0 +1,307 @@ +//! Service interfaces injected into providers. +//! +//! Trusted Server wires providers by dependency injection. A provider's +//! constructor takes the services it needs as `Arc`, and the adapter +//! (the composition root) supplies instances per request. A provider that needs +//! a service the host does not supply cannot be built, so the request stops +//! rather than silently degrading. +//! +//! These traits are the service interfaces. Request-scoped data outlives the +//! live request only when snapshotted, so an implementation owns its data where +//! needed ([`OwnedRequestInfo`] is the built-in owned snapshot). + +use http::HeaderMap; + +/// Read-only access to the current request's basic information. +/// +/// The request data any host can supply: the normalized client IP, the +/// User-Agent, and request headers. A provider receives it by reference at call +/// time (`generate`/`detect`), reads what it needs, and does not retain it. +pub trait RequestInfo: Send + Sync + core::fmt::Debug { + /// The normalized client IP, or `""` when the host cannot determine it. + fn client_ip(&self) -> &str; + + /// The `User-Agent` header value, or `""` when absent. + fn user_agent(&self) -> &str; + + /// An arbitrary request header by name (case-insensitive), or `None`. + /// + /// Request cookies are read through this, from the `Cookie` header (a + /// provider that stores values in cookies parses them from it). + fn header(&self, name: &str) -> Option<&str>; + + /// The names of all request headers present, for a provider that enumerates + /// evidence (for example to forward client hints). The default is empty. + fn header_names(&self) -> Vec<&str> { + Vec::new() + } + + /// The request path (the URL path, without the query string), or `""` when + /// request info was built without a URL. + /// + /// A provider reads the request target through this together with + /// [`query`](Self::query); `RequestInfo` is the evidence abstraction, so more + /// request accessors can be added here (as defaulted methods) without + /// breaking existing implementations. + fn path(&self) -> &str { + "" + } + + /// The raw request query string (the part after `?`, without the leading + /// `?`), or `""` when the request carried none. + /// + /// A provider reads request parameters through this, or the + /// [`query_param`](Self::query_param) convenience. The default is empty, for + /// request info built without a URL. + fn query(&self) -> &str { + "" + } + + /// The first value of query parameter `name`, percent-decoded, or `None` + /// when the parameter is absent. + /// + /// Parses [`query`](Self::query) with `application/x-www-form-urlencoded` + /// rules, matching how the browser encodes query parameters. + fn query_param(&self, name: &str) -> Option { + url::form_urlencoded::parse(self.query().as_bytes()) + .find_map(|(key, value)| (&*key == name).then(|| value.into_owned())) + } +} + +/// An owned [`RequestInfo`] built from a request snapshot. +/// +/// Owns the client IP and a header snapshot, for a context that cannot borrow +/// the live request for the duration of the call. The request path uses +/// [`BorrowedRequestInfo`]; this owned variant serves tests and any future +/// host whose request data cannot be borrowed. +#[derive(Debug, Default, Clone)] +pub struct OwnedRequestInfo { + client_ip: String, + headers: HeaderMap, + path: String, + query: String, +} + +impl OwnedRequestInfo { + /// Builds owned request info from the client IP and a header snapshot. + /// + /// The request target ([`path`](RequestInfo::path) and + /// [`query`](RequestInfo::query)) is empty; attach it with + /// [`with_request_target`](Self::with_request_target) when the caller has the + /// URL. + #[must_use] + pub fn new(client_ip: String, headers: HeaderMap) -> Self { + Self { + client_ip, + headers, + path: String::new(), + query: String::new(), + } + } + + /// Attaches the request target (URL path and query string) to this snapshot, + /// so a provider can read request parameters through + /// [`query_param`](RequestInfo::query_param). + #[must_use] + pub fn with_request_target(mut self, path: String, query: String) -> Self { + self.path = path; + self.query = query; + self + } +} + +impl RequestInfo for OwnedRequestInfo { + fn client_ip(&self) -> &str { + &self.client_ip + } + + fn user_agent(&self) -> &str { + self.headers + .get(http::header::USER_AGENT) + .and_then(|value| value.to_str().ok()) + .unwrap_or_default() + } + + fn header(&self, name: &str) -> Option<&str> { + self.headers.get(name).and_then(|value| value.to_str().ok()) + } + + fn header_names(&self) -> Vec<&str> { + self.headers.keys().map(http::HeaderName::as_str).collect() + } + + fn path(&self) -> &str { + &self.path + } + + fn query(&self) -> &str { + &self.query + } +} + +/// A borrowed [`RequestInfo`] over the live request, with no allocation. +/// +/// The composition root builds one per request from the normalized client IP and +/// an optional borrow of the request headers, then passes it to a provider by +/// shared reference at call time (`generate`/`detect`). It borrows rather than +/// owns, so it must not outlive the request. A provider reads it during the call +/// and does not retain it, so no per-request `HeaderMap` clone is needed. +#[derive(Debug)] +pub struct BorrowedRequestInfo<'a> { + client_ip: &'a str, + headers: Option<&'a HeaderMap>, + path: &'a str, + query: &'a str, +} + +impl<'a> BorrowedRequestInfo<'a> { + /// Borrows request info from the client IP and optional request headers. + /// + /// Pass `None` for headers on a path that only needs the client IP. The + /// request target ([`path`](RequestInfo::path) and + /// [`query`](RequestInfo::query)) is empty; attach it with + /// [`with_request_target`](Self::with_request_target) when the caller has the + /// URL. + #[must_use] + pub fn new(client_ip: &'a str, headers: Option<&'a HeaderMap>) -> Self { + Self { + client_ip, + headers, + path: "", + query: "", + } + } + + /// Attaches the borrowed request target (URL path and query string), so a + /// provider can read request parameters through + /// [`query_param`](RequestInfo::query_param). + #[must_use] + pub fn with_request_target(mut self, path: &'a str, query: &'a str) -> Self { + self.path = path; + self.query = query; + self + } +} + +impl RequestInfo for BorrowedRequestInfo<'_> { + fn client_ip(&self) -> &str { + self.client_ip + } + + fn user_agent(&self) -> &str { + self.headers + .and_then(|headers| headers.get(http::header::USER_AGENT)) + .and_then(|value| value.to_str().ok()) + .unwrap_or_default() + } + + fn header(&self, name: &str) -> Option<&str> { + self.headers + .and_then(|headers| headers.get(name)) + .and_then(|value| value.to_str().ok()) + } + + fn header_names(&self) -> Vec<&str> { + self.headers + .map(|headers| headers.keys().map(http::HeaderName::as_str).collect()) + .unwrap_or_default() + } + + fn path(&self) -> &str { + self.path + } + + fn query(&self) -> &str { + self.query + } +} + +/// Host-computed client fingerprints that are not carried in request headers. +/// +/// A host that can compute them supplies an implementation (Fastly exposes the +/// TLS JA4 and HTTP/2 fingerprints). A provider that needs them takes +/// `Arc` in its constructor; on a host that supplies none, the +/// provider cannot be built and the request stops. +pub trait HostSignals: Send + Sync + core::fmt::Debug { + /// The full JA4 TLS fingerprint, or `None` when unavailable. + fn ja4(&self) -> Option<&str>; + + /// The raw HTTP/2 SETTINGS fingerprint, or `None` when unavailable. + fn h2(&self) -> Option<&str>; +} + +#[cfg(test)] +mod tests { + use super::*; + + fn headers_with_cookie() -> HeaderMap { + let mut headers = HeaderMap::new(); + headers.insert( + "cookie", + "client-id=abc123; ts-ec=xyz" + .parse() + .expect("should parse cookie header"), + ); + headers + } + + #[test] + fn query_param_decodes_and_selects_the_first_value() { + let info = OwnedRequestInfo::new(String::new(), HeaderMap::new()) + .with_request_target("/page".to_owned(), "id=a%20b&id=second&flag=1".to_owned()); + + assert_eq!( + info.query_param("id").as_deref(), + Some("a b"), + "should percent-decode and return the first value for a repeated key" + ); + assert_eq!(info.query_param("flag").as_deref(), Some("1")); + assert_eq!( + info.query_param("missing"), + None, + "an absent parameter should be None" + ); + } + + #[test] + fn path_and_query_accessors_return_the_request_target() { + let info = OwnedRequestInfo::new(String::new(), HeaderMap::new()) + .with_request_target("/a/b".to_owned(), "x=1".to_owned()); + assert_eq!(info.path(), "/a/b"); + assert_eq!(info.query(), "x=1"); + } + + #[test] + fn request_info_defaults_to_an_empty_target() { + let info = OwnedRequestInfo::new("203.0.113.5".to_owned(), HeaderMap::new()); + assert_eq!(info.path(), "", "path should default to empty"); + assert_eq!(info.query(), "", "query should default to empty"); + assert_eq!( + info.query_param("id"), + None, + "query_param over an empty query should be None" + ); + } + + #[test] + fn a_provider_reads_cookies_from_the_header() { + let info = OwnedRequestInfo::new("203.0.113.5".to_owned(), headers_with_cookie()); + assert_eq!( + info.header("cookie"), + Some("client-id=abc123; ts-ec=xyz"), + "cookies are read through the Cookie header" + ); + } + + #[test] + fn borrowed_request_info_exposes_the_same_target() { + let headers = headers_with_cookie(); + let info = BorrowedRequestInfo::new("203.0.113.5", Some(&headers)) + .with_request_target("/page", "id=abc123"); + + assert_eq!(info.path(), "/page"); + assert_eq!(info.query(), "id=abc123"); + assert_eq!(info.query_param("id").as_deref(), Some("abc123")); + assert_eq!(info.header("cookie"), Some("client-id=abc123; ts-ec=xyz")); + } +} diff --git a/crates/trusted-server-core/src/geo.rs b/crates/trusted-server-core/src/geo.rs index 63f7907f5..22a37ad2c 100644 --- a/crates/trusted-server-core/src/geo.rs +++ b/crates/trusted-server-core/src/geo.rs @@ -59,39 +59,6 @@ fn insert_geo_header(headers: &mut http::HeaderMap, name: http::header::HeaderNa } } -use std::collections::HashSet; -use std::sync::LazyLock; - -/// EU-27 + EEA-3 (Iceland, Liechtenstein, Norway) + UK (UK GDPR). -/// -/// Two-letter ISO 3166-1 alpha-2 country codes for jurisdictions where GDPR -/// or equivalent legislation applies. Used to infer GDPR applicability from -/// IP-derived geolocation when a more authoritative signal (e.g. TCF consent -/// string) is not yet available. -static GDPR_COUNTRIES: LazyLock> = LazyLock::new(|| { - [ - // EU-27 - "AT", "BE", "BG", "HR", "CY", "CZ", "DK", "EE", "FI", "FR", "DE", "GR", "HU", "IE", "IT", - "LV", "LT", "LU", "MT", "NL", "PL", "PT", "RO", "SK", "SI", "ES", "SE", - // EEA (non-EU) - "IS", "LI", "NO", // UK GDPR - "GB", - ] - .into_iter() - .collect() -}); - -/// Returns `true` if the given two-letter country code falls under GDPR -/// jurisdiction (EU-27, EEA, or UK). -/// -/// The comparison is case-insensitive. Returns `false` for empty or -/// unrecognised codes. -#[must_use] -pub fn is_gdpr_country(country_code: &str) -> bool { - let upper = country_code.to_ascii_uppercase(); - GDPR_COUNTRIES.contains(upper.as_str()) -} - #[cfg(test)] mod tests { use super::*; @@ -217,39 +184,6 @@ mod tests { ); } - #[test] - fn is_gdpr_country_detects_eu_members() { - assert!(is_gdpr_country("DE"), "Germany is EU"); - assert!(is_gdpr_country("FR"), "France is EU"); - assert!(is_gdpr_country("IT"), "Italy is EU"); - } - - #[test] - fn is_gdpr_country_detects_eea_and_uk() { - assert!(is_gdpr_country("NO"), "Norway is EEA"); - assert!(is_gdpr_country("IS"), "Iceland is EEA"); - assert!(is_gdpr_country("GB"), "UK has UK GDPR"); - } - - #[test] - fn is_gdpr_country_rejects_non_gdpr() { - assert!(!is_gdpr_country("US"), "US is not GDPR"); - assert!(!is_gdpr_country("CN"), "China is not GDPR"); - assert!(!is_gdpr_country("BR"), "Brazil is not GDPR"); - } - - #[test] - fn is_gdpr_country_is_case_insensitive() { - assert!(is_gdpr_country("de"), "lowercase should match"); - assert!(is_gdpr_country("De"), "mixed case should match"); - } - - #[test] - fn is_gdpr_country_handles_empty_and_unknown() { - assert!(!is_gdpr_country(""), "empty string is not GDPR"); - assert!(!is_gdpr_country("XX"), "unknown code is not GDPR"); - } - #[test] fn set_response_headers_omits_region_when_none() { let geo = GeoInfo { diff --git a/crates/trusted-server-core/src/integrations/google_tag_manager.rs b/crates/trusted-server-core/src/integrations/google_tag_manager.rs index 0dfb5906f..5d1016130 100644 --- a/crates/trusted-server-core/src/integrations/google_tag_manager.rs +++ b/crates/trusted-server-core/src/integrations/google_tag_manager.rs @@ -1537,12 +1537,19 @@ origin_url = "https://origin.test-publisher.com" proxy_secret = "test-secret" [ec] +provider = "hmac" + +[ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" [integrations.google_tag_manager] enabled = true container_id = "GTM-PARSED" upstream_url = "https://custom.gtm.example" + +[geo] +default_country = "FR" +assume_single_jurisdiction = true "#; let settings = Settings::from_toml(toml_str).expect("should parse TOML"); let config = settings @@ -1570,10 +1577,17 @@ origin_url = "https://origin.test-publisher.com" proxy_secret = "test-secret" [ec] +provider = "hmac" + +[ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" [integrations.google_tag_manager] container_id = "GTM-DEFAULT" + +[geo] +default_country = "FR" +assume_single_jurisdiction = true "#; let settings = Settings::from_toml(toml_str).expect("should parse TOML"); let config = settings diff --git a/crates/trusted-server-core/src/integrations/prebid.rs b/crates/trusted-server-core/src/integrations/prebid.rs index c9b3f5ded..e60169f16 100644 --- a/crates/trusted-server-core/src/integrations/prebid.rs +++ b/crates/trusted-server-core/src/integrations/prebid.rs @@ -1841,8 +1841,9 @@ impl PrebidAuctionProvider { .map(|ac| ConsentedProvidersSettings { consented_providers: Some(ac.clone()), }), - // EIDs resolved from the KV identity graph and consent-gated - // in `handle_auction` via `gate_eids_by_consent`. + // EIDs resolved from the KV identity graph and gated on the + // resolved permission state in `handle_auction` via + // `gate_eids_by_permissions`. eids: request.user.eids.clone(), } .to_ext(), @@ -3024,7 +3025,14 @@ origin_url = "https://origin.test-publisher.com" proxy_secret = "test-secret" [ec] +provider = "hmac" + +[ec.providers.hmac] passphrase = "test-secret-key-32-bytes-minimum" + +[geo] +default_country = "FR" +assume_single_jurisdiction = true "#; /// Parse a TOML string containing only the `[integrations.prebid]` section diff --git a/crates/trusted-server-core/src/integrations/registry.rs b/crates/trusted-server-core/src/integrations/registry.rs index 280eae847..176870d4b 100644 --- a/crates/trusted-server-core/src/integrations/registry.rs +++ b/crates/trusted-server-core/src/integrations/registry.rs @@ -709,6 +709,10 @@ struct IntegrationRegistryInner { html_post_processors: Vec>, head_injectors: Vec>, request_filters: Vec>, + /// JS module IDs to include in the bundle that come from a source other than + /// a registered integration, for example a module tied to the selected Edge + /// Cookie provider. Populated in [`IntegrationRegistry::new`] from settings. + extra_js_module_ids: Vec<&'static str>, } impl Default for IntegrationRegistryInner { @@ -730,6 +734,7 @@ impl Default for IntegrationRegistryInner { html_post_processors: Vec::new(), head_injectors: Vec::new(), request_filters: Vec::new(), + extra_js_module_ids: Vec::new(), } } } @@ -867,6 +872,15 @@ impl IntegrationRegistry { } } + // A client-cycle Edge Cookie provider ships a page script that posts its + // result to the resolve endpoint. The script rides the tsjs bundle, so + // include its module when that provider is selected. The same module + // list drives both the served bundle and the injected `