mirror of
https://github.com/0xMassi/webclaw.git
synced 2026-06-12 23:05:12 +02:00
02302e7a1d
Extraction ~22% faster on the corpus benchmark with byte-identical output: - hoist recompiled CSS selectors in the markdown noise path - single-pass shared og() meta parsing across vertical extractors - output-safe QuickJS gating (skip the JS VM when no candidate data) + reuse the already-parsed document instead of re-parsing - wreq connect_timeout + connection-pool tuning; dedup the retry loop Reliability + correctness: - char-boundary-safe truncation of LLM error bodies (shared helper) - HTTP connect/read timeouts on all LLM provider clients - isolate pdf-extract behind catch_unwind + spawn_blocking - OSS server: crawl inherits the shared fetch profile; ProviderChain built once in AppState; request TimeoutLayer API / safety / docs: - #[non_exhaustive] on public enums + result structs (+ builders) - #![forbid(unsafe_code)] on pure crates, deny on llm - //! crate docs + doctests; scrub bypass/vendor/target specifics from public crate docs and comments Tooling: [profile.release] lto/codegen-units/strip, MSRV pin, deny.toml + cargo-deny CI, macOS test matrix. CLI main.rs split into focused modules.
39 lines
1.4 KiB
TOML
39 lines
1.4 KiB
TOML
[package]
|
|
name = "webclaw-server"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
rust-version.workspace = true
|
|
license.workspace = true
|
|
repository.workspace = true
|
|
description = "Minimal REST API server for self-hosting webclaw extraction. Wraps the OSS extraction crates with HTTP endpoints. NOT the production hosted API at api.webclaw.io — this is a stateless, single-binary reference server for local + self-hosted deployments."
|
|
|
|
[lints]
|
|
workspace = true
|
|
|
|
[[bin]]
|
|
name = "webclaw-server"
|
|
path = "src/main.rs"
|
|
|
|
[dependencies]
|
|
webclaw-core = { workspace = true }
|
|
webclaw-fetch = { workspace = true }
|
|
webclaw-llm = { workspace = true }
|
|
webclaw-pdf = { workspace = true }
|
|
|
|
axum = { version = "0.8", features = ["macros"] }
|
|
tokio = { workspace = true }
|
|
tower-http = { version = "0.6", features = ["trace", "cors", "timeout"] }
|
|
clap = { workspace = true, features = ["derive", "env"] }
|
|
serde = { workspace = true }
|
|
serde_json = { workspace = true }
|
|
tracing = { workspace = true }
|
|
tracing-subscriber = { workspace = true, features = ["env-filter"] }
|
|
anyhow = "1"
|
|
thiserror = { workspace = true }
|
|
subtle = "2.6"
|
|
|
|
[dev-dependencies]
|
|
# `ServiceExt::oneshot` drives the router in-process for hermetic handler
|
|
# tests (no TCP listener, no network).
|
|
tower = { version = "0.5", features = ["util"] }
|
|
http-body-util = "0.1"
|