Arsitektur
The architecture.
One Rust binary. Five subsystems. Zero cloud dependencies. Every box below maps to a real module, port, or file on disk.
System topology.
Topologi proses dari biner yang dikirim: tujuh titik masuk, satu runtime, satu set penyimpanan lokal. Setiap kotak di bawah dipetakan ke modul, port, atau file nyata di disk.
lean-ctx lean-ctx serve lean-ctx serve --daemon lean-ctx -c "<cmd>" lean-ctx proxy start lean-ctx dashboard lean-ctx watch · gain --live One binary. Five subsystems. No cloud required.
Aliran Data Stage by stage.
Sheet 2 melacak satu permintaan melalui runtime, tahap demi tahap, termasuk short-circuit cache yang membuat bacaan berulang hampir gratis. Jalur shell berjalan secara paralel dengan akuntansi yang sama.
ctx_read(path, mode) · lean-ctx read - PathJail
core/pathjail.rsCanonicalises the path and rejects escapes outside the workspace root before any I/O happens.
- Session cache
hit → ~13 tokensContent-addressed lookup keyed by path + mtime/hash. Unchanged files collapse to a stub instead of re-sending content.
- AST extraction
26 languagestree-sitter parses the file into a syntax tree: signatures, imports, call edges — Lua, Luau, Kotlin and GDScript are graph-indexed too. Regex fallback for unsupported languages.
- Mode selection
10 modesauto picks the optimal of 10 read modes (full, map, signatures, diff, task, reference, aggressive, entropy, lines:N-M) from task intent and file size; structure_first biases cold medium-file code reads toward map, and a file flagged suspect on a fix task is forced to full.
- Compression
adaptive thresholdsShannon-entropy line filtering, U-curve attention placement (LITM), TF-IDF codebook and query-conditioned Information-Bottleneck fusion — an anti-inflation guard ships the file verbatim whenever framing would cost more tokens than the raw bytes.
- Token accounting
core/tokens.rsExact tiktoken counts (o200k_base; cl100k_base approximation for Claude-family models) on input and output.
- Ledger + stats
savings sign / verify-batchSavings are appended to the local ledger (Ed25519-signable), stats and the gain score update, the result streams back.
lean-ctx -c "cargo test" · IDE bash hook Kedua path berakhir di ledger yang sama: setiap peristiwa kompresi dihitung dengan matematika tokenizer yang tepat dan memberi makan gain, dashboard, dan ledger tabungan yang ditandatangani.
Kompresi engine.
Tree-sitter parses 27 languages into ASTs. 10 read modes select the right abstraction level — from full source to aggressive entropy filtering. 95+ shell patterns compress git, cargo, npm, docker, and kubectl output into compact evidence.
Explore read modesAvailable modes full → entire file, no compression signatures → fn signatures + type defs map → structural overview diff → uncommitted changes only task → query-conditioned extract aggressive → maximum compression entropy → information-dense lines reference → symbols + doc comments lines:N-M → specific line rangeSelected: signatures (420 lines → 18 lines)Memory, agents, security.
Content-addressed caching collapses re-reads to ~13 tokens. A knowledge graph persists decisions across sessions. The agent bus coordinates multiple agents without duplicating context. PathJail, shell allowlists, and TOCTOU checks enforce deny-by-default boundaries on every call.
Security modelCache 47 entries · 73% hit rateKnowledge 342 nodes · 1,205 edgesAgent bus 3 agents registeredPathJail root: /Users/dev/projectAllowlist 14 allow, 6 denyRedaction .env, credentials.*TOCTOU open-handle verify activeLedger Ed25519-signed · 0 violationsEngineering data sheet.
Tabel referensi di balik gambar: setiap permukaan dengan transport dan siklus hidupnya, tata letak di disk, lapisan pembelajaran adaptif, dan batas keamanan yang ditegakkan oleh runtime.
AModel Proses
Semua permukaan adalah biner yang sama dalam peran berbeda. Tidak ada yang memerlukan koneksi cloud; semuanya terikat lokal-pertama.
| REF | SURFACE | TRANSPORT | ENDPOINT | LIFECYCLE | PERINTAH |
|---|---|---|---|---|---|
| 01 | MCP server (stdio) | JSON-RPC over stdin/stdout | spawned per editor session | child process of the editor | lean-ctx |
| 02 | MCP server (HTTP) | MCP Streamable HTTP | localhost, configurable --host/--port | foreground or service | lean-ctx serve |
| 03 | IPC daemon | Unix Domain Socket | OS data dir, e.g. ~/Library/Application Support/lean-ctx/daemon.sock | launchd / systemd autostart | lean-ctx serve --daemon |
| 04 | Shell hook | process exec, compressed stdout | wraps IDE bash calls + interactive shells | per command | lean-ctx -c "<cmd>" |
| 05 | API proxy | HTTP (LLM API pass-through) | localhost:4444 (default) | on demand | lean-ctx proxy start |
| 06 | Web dashboard | HTTP + bearer token | localhost:3333 (default, --port) | on demand | lean-ctx dashboard |
| 07 | Terminal UI | TTY (in-place redraw) | live event stream / 1 s refresh | interactive | lean-ctx watch · gain --live |
BTata Letak Penyimpanan — Direktori XDG Lokal
State persisten adalah file biasa di bawah direktori dasar XDG: dapat diperiksa, diekspor, dihapus. Tidak ada database tersembunyi selain folder lokal ini.
| ARTIFAK | FORM | TUJUAN |
|---|---|---|
config.toml | TOML | Single config file — integration mode, compression, providers, opt-outs (config dir) |
cache/ | content-addressed | Session file cache; unchanged re-reads collapse to ~13-token stubs (cache dir) |
bm25 index | inverted index | Lexical search over code chunks + provider documents (data dir) |
context_graph/ | property graph | Imports, calls, types across files and repos — powers map mode + deep queries (data dir) |
knowledge | SQLite | Persistent facts, decisions, rooms — recalled across sessions, CCP (data dir) |
savings ledger | append-only JSONL | Every compression event; Ed25519-signable for audit (data dir) |
litm_calibration.json | JSON | Learned context-position hit rates (lost-in-the-middle calibration) (cache dir) |
events.jsonl | event stream | Live feed consumed by watch, dashboard and efficacy reports (state dir) |
CLapisan Pembelajaran Adaptif
Tujuh mekanisme pembelajaran online menyetel kompresi sesuai penggunaan nyata Anda, secara lokal, dari sinyal kualitas seperti pantulan dan kegagalan edit. Selami: Pembelajaran Adaptif →
- L1 Adaptive thresholds Online-learned compression aggressiveness from quality signals (bounces, edit failures, clean runs)
- L2 LITM calibration Empirical placement of critical context at positions the model actually attends to
- L3 Stigmergic scent field Multi-agent coordination via decaying markers: claimed, done, stuck, hot, avoid
- L4 Delta playbook Incremental checkpoint snapshots that survive context compaction
- L5 Query-conditioned IB Information-Bottleneck compression fused with query relevance
- L6 Theta-gamma chunking Wakeup facts grouped in attention-friendly bursts
- L7 Semantic dedup Likelihood-scored redundancy filtering across the session
DBatas Keamanan
Jaminan keras yang ditegakkan dalam runtime. Model keamanan →
- PathJail Every file access is canonicalised and confined to the workspace root
- IDE config-dir jail Home-level IDE/agent config dirs (~/.claude, ~/.codex, ~/.codebuddy, …) are writable only when allow_ide_config_dirs is opted in; otherwise PathJail blocks them
- Shell allowlist Deny-by-default command policy for agent-issued shell executions
- Local-first All processing on-device; dashboard binds to localhost and requires a bearer token
- Signed evidence Savings ledger entries are Ed25519-signable and batch-verifiable
Explore thesource.
LeanCTX is open source. Read the code, understand the design, contribute.