webclaw/crates/webclaw-server/src/error.rs
Valerio 06f151c560 feat(search): standalone web search via Serper.dev (bring-your-own-key)
Rescued from the stale perf/audit-fixes branch and ported cleanly onto
current main. OSS surfaces can now search without the hosted webclaw API
when the caller supplies their own Serper.dev key (free at serper.dev).

- webclaw-fetch::search() — calls Serper.dev directly (plain wreq client;
  a JSON API needs no fingerprinting) and, with scrape=true, fetches +
  extracts the top result pages concurrently (bounded) via the caller's
  FetchClient. parse_serper_organic() is pure and unit-tested.
- MCP `search` tool: local-first — uses SERPER_API_KEY when set, else
  falls back to the hosted webclaw API. Adds country/lang/scrape params.
- OSS REST server: POST /v1/search, gated on SERPER_API_KEY (501 when
  unset, with a setup hint). Adds ApiError::NotImplemented.
- CLI: `webclaw search <query> [--serper-key|SERPER_API_KEY] [--num]
  [--country] [--lang] [--scrape] [--format]`.

No new dependencies (reuses futures-util already in the tree). Original
work by the prior author on perf/audit-fixes; this re-applies only the
search slice onto main.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 15:10:58 +02:00

110 lines
3.2 KiB
Rust

//! API error type. Maps internal errors to HTTP status codes + JSON.
use axum::{
Json,
http::StatusCode,
response::{IntoResponse, Response},
};
use serde_json::json;
use thiserror::Error;
/// Public-facing API error. Always serializes as `{ "error": "..." }`.
/// Keep messages user-actionable; internal details belong in tracing logs.
///
/// `Unauthorized` / `NotFound` / `Internal` are kept on the enum as
/// stable variants for handlers that don't exist yet (planned: per-key
/// rate-limit responses, dynamic route 404s). Marking them dead-code-OK
/// is preferable to inventing them later in three places.
#[allow(dead_code)]
#[derive(Debug, Error)]
pub enum ApiError {
#[error("{0}")]
BadRequest(String),
#[error("unauthorized")]
Unauthorized,
#[error("not found")]
NotFound,
#[error("upstream fetch failed: {0}")]
Fetch(String),
#[error("extraction failed: {0}")]
Extract(String),
#[error("LLM provider error: {0}")]
Llm(String),
#[error("internal: {0}")]
Internal(String),
#[error("{0}")]
NotImplemented(String),
}
impl ApiError {
pub fn bad_request(msg: impl Into<String>) -> Self {
Self::BadRequest(msg.into())
}
pub fn internal(msg: impl Into<String>) -> Self {
Self::Internal(msg.into())
}
/// 501 — a capability the operator hasn't configured (e.g. search
/// without `SERPER_API_KEY`). Distinct from `BadRequest` (client's
/// fault) and `Internal` (our fault): it's a deployment-config gap.
pub fn not_implemented(msg: impl Into<String>) -> Self {
Self::NotImplemented(msg.into())
}
fn status(&self) -> StatusCode {
match self {
Self::BadRequest(_) => StatusCode::BAD_REQUEST,
Self::Unauthorized => StatusCode::UNAUTHORIZED,
Self::NotFound => StatusCode::NOT_FOUND,
Self::Fetch(_) => StatusCode::BAD_GATEWAY,
Self::Extract(_) | Self::Llm(_) => StatusCode::UNPROCESSABLE_ENTITY,
Self::Internal(_) => StatusCode::INTERNAL_SERVER_ERROR,
Self::NotImplemented(_) => StatusCode::NOT_IMPLEMENTED,
}
}
}
impl IntoResponse for ApiError {
fn into_response(self) -> Response {
let body = Json(json!({ "error": self.to_string() }));
(self.status(), body).into_response()
}
}
impl From<webclaw_fetch::FetchError> for ApiError {
fn from(e: webclaw_fetch::FetchError) -> Self {
match e {
webclaw_fetch::FetchError::InvalidUrl(msg) => {
Self::BadRequest(format!("invalid url: {msg}"))
}
other => {
let msg = other.to_string();
if msg.contains("invalid url:")
|| msg.contains("blocked private or internal address")
{
Self::BadRequest(msg)
} else {
Self::Fetch(msg)
}
}
}
}
}
impl From<webclaw_core::ExtractError> for ApiError {
fn from(e: webclaw_core::ExtractError) -> Self {
Self::Extract(e.to_string())
}
}
impl From<webclaw_llm::LlmError> for ApiError {
fn from(e: webclaw_llm::LlmError) -> Self {
Self::Llm(e.to_string())
}
}