mirror of
https://github.com/whit3rabbit/anyllm-proxy.git
synced 2026-09-22 08:00:51 +00:00
whit3rabbitandClaude Opus 4.8
d155bfd148
RTK (anyllm_rtk crate): command-aware filtering of tool-result text (test/build/git/log output) via a catalog of 55 declarative filters ported from OmniRoute (MIT). IO-free, deterministic, prompt-cache safe (cache_control blocks preserved byte-for-byte). Wired into the Anthropic passthrough (stream + non-stream) and OpenAI-translate paths, gated per-model via RTK_MODELS. RTK_COMPRESS env / admin toggle, rtk_compress/rtk_models runtime config. Optimizer (anyllm_optimize_* crates): opt-in Frozen-Frontier Extractive Compression of long client-sent conversation history for OpenAI Chat Completions, the Anthropic translate path, and the Anthropic passthrough path (client history only, never proxy tool-loop turns). OPTIMIZER_MODE=off|shadow| live env / admin toggle; live places a cache_control breakpoint at the frontier over raw bytes. Optional LLMLingua-2 ONNX scorer behind the optimizer-onnx feature (model fetched on demand, never bundled). New optimizer_* metrics counters and GET/POST /admin/api/optimizer/model endpoints. Both features expose runtime config + Settings UI controls and fail open on any error. Adds workspace members, CI lint/test for the optimizer-onnx feature, and gitignore rules for downloaded ONNX artifacts. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
18 lines
666 B
TOML
18 lines
666 B
TOML
[package]
|
|
name = "anyllm_rtk"
|
|
description = "Command-aware tool-output compression for the anyllm proxy (RTK port)"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
license.workspace = true
|
|
repository.workspace = true
|
|
categories = ["compression", "web-programming"]
|
|
keywords = ["anthropic", "llm", "compression", "tool-output", "rtk"]
|
|
|
|
[dependencies]
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
# Line/pattern filtering is regex-driven. Rust's `regex` crate (no lookaround,
|
|
# no backreferences) covers 52/55 vendored filters directly; the 3 lookahead
|
|
# detection patterns fail to compile and are skipped fail-open (see filter.rs).
|
|
regex = "1"
|