mirror of
https://github.com/whit3rabbit/anyllm-proxy.git
synced 2026-09-21 16:00:49 +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>
71 lines
1.1 KiB
Plaintext
71 lines
1.1 KiB
Plaintext
# Rust / Cargo
|
|
/target/
|
|
**/*.rs.bk
|
|
|
|
# IDE
|
|
.idea/
|
|
.vscode/
|
|
*.swp
|
|
*.swo
|
|
*~
|
|
|
|
# OS
|
|
.DS_Store
|
|
Thumbs.db
|
|
.syntext
|
|
|
|
# Environment
|
|
.env
|
|
.env.*
|
|
!.env.example
|
|
!.env.example.test
|
|
.anyllm.env
|
|
.anyllm.env.*
|
|
!.anyllm.env.example
|
|
|
|
# Debug
|
|
*.pdb
|
|
|
|
# Admin server artifacts
|
|
.admin_token
|
|
*.db
|
|
*.db-shm
|
|
*.db-wal
|
|
|
|
# TLS certificates and keys
|
|
*.p12
|
|
*.pfx
|
|
*.pem
|
|
*.key
|
|
|
|
# Tool config
|
|
.claude/
|
|
.cook/
|
|
.worktrees/
|
|
.playwright-mcp/
|
|
.mcp.json
|
|
.repowise/
|
|
.superpowers/
|
|
|
|
# Script caches and venv
|
|
scripts/.cache/
|
|
scripts/.venv/
|
|
|
|
# Admin UI build artifacts
|
|
crates/proxy/admin-ui/node_modules/
|
|
# dist/ is committed so `include_str!` works at compile time without a build step
|
|
# crates/proxy/admin-ui/dist/
|
|
.synrepo/
|
|
.eatahorse*/
|
|
# Security scanner (gate/3gate) scratch artifacts
|
|
.gate/
|
|
|
|
# optimizer: exported/downloaded ONNX model artifacts (hash-pinned, fetched via the
|
|
# `optimize-model` CLI, never committed — see crates/optimizer/scripts/export_llmlingua2.py
|
|
# and crates/optimizer/optimize-cli/src/model_fetch.rs). onnxruntime binaries live under
|
|
# target/ (already ignored) via ort's download-binaries feature.
|
|
crates/optimizer/artifacts/
|
|
*.onnx
|
|
__pycache__/
|
|
*.pyc
|