starred/anyllm-proxy
1
0
Fork 0
mirror of https://github.com/whit3rabbit/anyllm-proxy.git synced 2026-09-21 16:00:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: release 0.14.0

Browse Source 
Move Unreleased changelog entries (RTK compression, opt-in prompt
optimizer, release binary archives, Bedrock allowlist fix, model
discovery fix) into the 0.14.0 section. Bump workspace + inter-crate
versions 0.13.0 -> 0.14.0 and the README deb filename.

Fix clippy missing_const_for_thread_local in optimize-core alloc_budget
test (const-init the thread-locals) so cargo clippy -D warnings is clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
whit3rabbit
2026-07-12 21:21:14 -05:00
co-authored by Claude Opus 4.8
parent 1c7d66cc54
commit ff03a7ebd7
12 changed files with 37 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+2
View File
@@ -10,6 +10,8 @@ Format: [Keep a Changelog](https://keepachangelog.com/en/1.1.0/). Versions follo
## [Unreleased]
## [0.14.0] - 2026-07-12
### Added
- RTK tool-output compression (`RTK_COMPRESS=true` / admin toggle): command-aware filtering
of tool-result text (test/build/git/log output) using a catalog of 55 declarative filters
Cargo.lock
Generated
+12 -12
View File
@@ -104,7 +104,7 @@ checksum = "2a4385e2e34eb35d6b3efe798b9eb88096925d87726c0798709bf56d9ed84af3"
[[package]]
name = "anyllm_batch_engine"
version = "0.13.0"
version = "0.14.0"
dependencies = [
"anyllm_translate",
"async-trait",
@@ -126,7 +126,7 @@ dependencies = [
[[package]]
name = "anyllm_client"
version = "0.13.0"
version = "0.14.0"
dependencies = [
"anyllm_translate",
"bytes",
@@ -145,7 +145,7 @@ dependencies = [
[[package]]
name = "anyllm_optimize_benches"
version = "0.13.0"
version = "0.14.0"
dependencies = [
"anyllm_optimize_core",
"anyllm_optimize_passes",
@@ -154,7 +154,7 @@ dependencies = [
[[package]]
name = "anyllm_optimize_cli"
version = "0.13.0"
version = "0.14.0"
dependencies = [
"anyhow",
"anyllm_optimize_core",
@@ -169,7 +169,7 @@ dependencies = [
[[package]]
name = "anyllm_optimize_core"
version = "0.13.0"
version = "0.14.0"
dependencies = [
"memchr",
"proptest",
@@ -180,7 +180,7 @@ dependencies = [
[[package]]
name = "anyllm_optimize_passes"
version = "0.13.0"
version = "0.14.0"
dependencies = [
"anyllm_optimize_core",
"memchr",
@@ -191,7 +191,7 @@ dependencies = [
[[package]]
name = "anyllm_optimize_scorer"
version = "0.13.0"
version = "0.14.0"
dependencies = [
"anyllm_optimize_core",
"ndarray",
@@ -205,7 +205,7 @@ dependencies = [
[[package]]
name = "anyllm_providers"
version = "0.13.0"
version = "0.14.0"
dependencies = [
"reqwest 0.12.28",
"serde",
@@ -215,7 +215,7 @@ dependencies = [
[[package]]
name = "anyllm_proxy"
version = "0.13.0"
version = "0.14.0"
dependencies = [
"anyllm_batch_engine",
"anyllm_client",
@@ -274,7 +274,7 @@ dependencies = [
[[package]]
name = "anyllm_pxpipe"
version = "0.13.0"
version = "0.14.0"
dependencies = [
"base64 0.22.1",
"font8x8",
@@ -286,7 +286,7 @@ dependencies = [
[[package]]
name = "anyllm_rtk"
version = "0.13.0"
version = "0.14.0"
dependencies = [
"regex",
"serde",
@@ -295,7 +295,7 @@ dependencies = [
[[package]]
name = "anyllm_translate"
version = "0.13.0"
version = "0.14.0"
dependencies = [
"axum 0.8.9",
"bytes",
Cargo.toml
+1 -1
View File
@@ -16,7 +16,7 @@ members = [
resolver = "2"
[workspace.package]
version = "0.13.0"
version = "0.14.0"
edition = "2021"
license = "MIT"
repository = "https://github.com/whit3rabbit/anyllm-proxy"
README.md
+1 -1
View File
@@ -18,7 +18,7 @@ brew install whit3rabbit/tap/anyllm-proxy
**Linux (Debian/Ubuntu):**
```bash
# Check https://github.com/whit3rabbit/anyllm-proxy/releases for the current filename
curl -LO https://github.com/whit3rabbit/anyllm-proxy/releases/latest/download/anyllm-proxy_0.13.0-1_amd64.deb
curl -LO https://github.com/whit3rabbit/anyllm-proxy/releases/latest/download/anyllm-proxy_0.14.0-1_amd64.deb
# arm64: replace amd64 with arm64
sudo dpkg -i anyllm-proxy_*.deb
sudo systemctl enable --now anyllm-proxy
crates/batch_engine/Cargo.toml
+1 -1
View File
@@ -7,7 +7,7 @@ license.workspace = true
repository.workspace = true
[dependencies]
anyllm_translate = { path = "../translator", version = "0.13.0" }
anyllm_translate = { path = "../translator", version = "0.14.0" }
rusqlite = { version = "0.32", features = ["bundled"] }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
crates/client/Cargo.toml
+2 -2
View File
@@ -1,7 +1,7 @@
[package]
name = "anyllm_client"
description = "Async HTTP client for Anthropic-to-OpenAI translation with retry, SSRF protection, and SSE streaming"
version = "0.13.0"
version = "0.14.0"
edition.workspace = true
license.workspace = true
repository.workspace = true
@@ -17,7 +17,7 @@ native-tls = ["reqwest/native-tls"]
rustls = ["reqwest/rustls-tls-native-roots"]
[dependencies]
anyllm_translate = { path = "../translator", version = "0.13.0" }
anyllm_translate = { path = "../translator", version = "0.14.0" }
# TLS features are controlled via the native-tls / rustls feature flags above.
reqwest = { version = "0.12", default-features = false, features = ["json", "stream", "http2"] }
tokio = { version = "1", features = ["rt", "sync", "time"] }
crates/optimizer/benches/Cargo.toml
+2 -2
View File
@@ -12,8 +12,8 @@ name = "optimize"
harness = false
[dependencies]
anyllm_optimize_core = { path = "../crates/optimize-core", version = "0.13.0" }
anyllm_optimize_passes = { path = "../crates/optimize-passes", version = "0.13.0" }
anyllm_optimize_core = { path = "../crates/optimize-core", version = "0.14.0" }
anyllm_optimize_passes = { path = "../crates/optimize-passes", version = "0.14.0" }
[dev-dependencies]
criterion = "0.5"
crates/optimizer/crates/optimize-core/tests/alloc_budget.rs
+2 -2
View File
@@ -15,8 +15,8 @@ use anyllm_optimize_core::{
};
thread_local! {
static RECORDING: Cell<bool> = Cell::new(false);
static ALLOC_COUNT: Cell<u64> = Cell::new(0);
static RECORDING: Cell<bool> = const { Cell::new(false) };
static ALLOC_COUNT: Cell<u64> = const { Cell::new(0) };
}
struct CountingAllocator;
crates/optimizer/crates/optimize-passes/Cargo.toml
+1 -1
View File
@@ -9,7 +9,7 @@ categories = ["compression", "text-processing"]
keywords = ["llm", "prompt", "compression", "openai", "anthropic"]
[dependencies]
anyllm_optimize_core = { path = "../optimize-core", version = "0.13.0" }
anyllm_optimize_core = { path = "../optimize-core", version = "0.14.0" }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
memchr = "2"
crates/optimizer/crates/optimize-scorer/Cargo.toml
+1 -1
View File
@@ -16,7 +16,7 @@ default = []
onnx = ["dep:ort", "dep:tokenizers", "dep:ndarray", "dep:rayon"]
[dependencies]
anyllm_optimize_core = { path = "../optimize-core", version = "0.13.0" }
anyllm_optimize_core = { path = "../optimize-core", version = "0.14.0" }
# Model-artifact download + sha256 verify (always compiled — the `artifact` module lets
# the proxy/CLI detect+fetch the model without pulling the ONNX Runtime stack).
sha2 = "0.10"
crates/optimizer/optimize-cli/Cargo.toml
+3 -3
View File
@@ -30,9 +30,9 @@ onnx = ["anyllm_optimize_scorer/onnx"]
tiktoken = ["dep:tiktoken-rs"]
[dependencies]
anyllm_optimize_core = { path = "../crates/optimize-core", version = "0.13.0" }
anyllm_optimize_passes = { path = "../crates/optimize-passes", version = "0.13.0" }
anyllm_optimize_scorer = { path = "../crates/optimize-scorer", version = "0.13.0" }
anyllm_optimize_core = { path = "../crates/optimize-core", version = "0.14.0" }
anyllm_optimize_passes = { path = "../crates/optimize-passes", version = "0.14.0" }
anyllm_optimize_scorer = { path = "../crates/optimize-scorer", version = "0.14.0" }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
clap = { version = "4", features = ["derive", "env"] }
crates/proxy/Cargo.toml
+9 -9
View File
@@ -13,17 +13,17 @@ name = "anyllm-proxy"
path = "src/main.rs"
[dependencies]
anyllm_translate = { path = "../translator", version = "0.13.0" }
anyllm_client = { path = "../client", version = "0.13.0" }
anyllm_batch_engine = { path = "../batch_engine", version = "0.13.0" }
anyllm_providers = { path = "../providers", version = "0.13.0", features = ["runtime-catalog"] }
anyllm_pxpipe = { path = "../pxpipe", version = "0.13.0" }
anyllm_rtk = { path = "../rtk", version = "0.13.0" }
anyllm_optimize_core = { path = "../optimizer/crates/optimize-core", version = "0.13.0" }
anyllm_optimize_passes = { path = "../optimizer/crates/optimize-passes", version = "0.13.0" }
anyllm_translate = { path = "../translator", version = "0.14.0" }
anyllm_client = { path = "../client", version = "0.14.0" }
anyllm_batch_engine = { path = "../batch_engine", version = "0.14.0" }
anyllm_providers = { path = "../providers", version = "0.14.0", features = ["runtime-catalog"] }
anyllm_pxpipe = { path = "../pxpipe", version = "0.14.0" }
anyllm_rtk = { path = "../rtk", version = "0.14.0" }
anyllm_optimize_core = { path = "../optimizer/crates/optimize-core", version = "0.14.0" }
anyllm_optimize_passes = { path = "../optimizer/crates/optimize-passes", version = "0.14.0" }
# Always compiled for the model-artifact detect/download admin flow; the heavy ONNX
# scorer inference is gated behind the proxy's `optimizer-onnx` feature (below).
anyllm_optimize_scorer = { path = "../optimizer/crates/optimize-scorer", version = "0.13.0" }
anyllm_optimize_scorer = { path = "../optimizer/crates/optimize-scorer", version = "0.14.0" }
axum = { version = "0.8", features = ["ws", "multipart"] }
tokio = { version = "1", features = ["full"] }
reqwest = { version = "0.12", default-features = false, features = ["json", "stream", "native-tls", "http2", "multipart"] }