mirror of
https://github.com/0xMassi/webclaw.git
synced 2026-06-27 03:19:38 +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.
30 lines
760 B
TOML
30 lines
760 B
TOML
[package]
|
|
name = "webclaw-mcp"
|
|
description = "MCP server for webclaw web extraction toolkit"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
rust-version.workspace = true
|
|
license.workspace = true
|
|
|
|
[lints]
|
|
workspace = true
|
|
|
|
[[bin]]
|
|
name = "webclaw-mcp"
|
|
path = "src/main.rs"
|
|
|
|
[dependencies]
|
|
webclaw-core = { workspace = true }
|
|
webclaw-fetch = { workspace = true }
|
|
webclaw-llm = { workspace = true }
|
|
webclaw-pdf = { workspace = true }
|
|
rmcp = { version = "1.2", features = ["server", "macros", "transport-io", "schemars"] }
|
|
schemars = "1.0"
|
|
dotenvy = { workspace = true }
|
|
serde = { workspace = true }
|
|
serde_json = { workspace = true }
|
|
tokio = { workspace = true }
|
|
tracing = { workspace = true }
|
|
tracing-subscriber = { workspace = true }
|
|
url = "2"
|
|
dirs = "6.0.0"
|