squeze-cli 3.0.0 → 3.0.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -1,5 +1,17 @@
1
1
  # Changelog
2
2
 
3
+ ## 3.0.2 — 2026-11-15
4
+
5
+ ### Changed
6
+ - The README has a keyword-bearing title and lead, plus a new FAQ (`#faq`) covering token-budgeted context, GitHub Copilot use, where code is sent (nowhere), supported languages, and what the benchmark does not measure. The Contents list is renumbered.
7
+ - npm metadata: `description` shortened to name the GitHub Copilot and MCP coding-agent use, and keywords expanded (`codebase-context`, `code-retrieval`, `repo-map`, `context-window`, `token-budget`, `coding-agent`, `developer-tools`, `cli`). No behaviour changes; the version constant in `src/mcp.ts` moves with the release.
8
+
9
+ ## 3.0.1 — 2026-11-15
10
+
11
+ ### Changed
12
+ - The README opens as a landing page: install and quick start, measured results with confidence intervals (including the failed non-inferiority test), a good-fit note and a not-measured note. The evidence sections are unchanged.
13
+ - npm metadata: keywords expanded, `mcpName` set to `io.github.2002-rokkam/squeze` for the MCP Registry, and `server.json` added. No code changes.
14
+
3
15
  ## 3.0.0 — 2026-11-14
4
16
 
5
17
  ### Evidence
package/README.md CHANGED
@@ -1,15 +1,41 @@
1
- # Squeze
1
+ # Squeze: token-budgeted code context for coding agents
2
2
 
3
- **Local, deterministic, token-budgeted repository context for coding agents.**
4
- Give it a task, an error or a stack trace; it returns the few verbatim, line-cited source excerpts that matter, inside a token budget you choose. It runs as a CLI, an MCP server and a VS Code / GitHub Copilot tool. No model calls, no network, no telemetry.
3
+ **Give your coding agent the right code, not the whole repository.**
5
4
 
6
- [![license](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE) ![node](https://img.shields.io/badge/node-%E2%89%A520.19-green) ![version](https://img.shields.io/badge/version-3.0.0-informational)
5
+ Squeze is a local, deterministic context engine and repository map for coding agents, including GitHub Copilot and any MCP-capable agent. Give it a task, an error or a stack trace; it returns the few verbatim, line-cited source excerpts that matter, inside a token budget you choose. It runs as a CLI, an MCP server for any MCP-capable agent, and a VS Code / GitHub Copilot extension. No model calls and no telemetry; the only network call is an optional local Ollama server for embeddings.
6
+
7
+ [![npm](https://img.shields.io/npm/v/squeze-cli)](https://www.npmjs.com/package/squeze-cli) [![downloads](https://img.shields.io/npm/dm/squeze-cli)](https://www.npmjs.com/package/squeze-cli) [![license](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE) ![node](https://img.shields.io/badge/node-%E2%89%A520.19-green)
8
+
9
+ ## Quick start
10
+
11
+ ```sh
12
+ npm install -g squeze-cli
13
+ squeze context --root . --query "where is retry backoff computed?" --budget 3000
14
+ squeze map --root .
15
+ ```
16
+
17
+ Then connect it to your agent: [MCP setup](#mcp) or the [VS Code extension](#vs-code).
18
+
19
+ ## Results at a glance
20
+
21
+ Public proof on 9 pinned open-source repositories, 360 symbol-lookup cases. Method, losses and confidence intervals are in [Evidence](#evidence).
22
+
23
+ | Metric | Result |
24
+ | --- | --- |
25
+ | Input tokens vs. a grep-and-read baseline | 87.3% fewer [84.8%, 89.2%] |
26
+ | Input tokens vs. reading the whole repository | 99.8% fewer |
27
+ | Recall (finds the defining file): squeze / grep / whole repository | 96.9% / 95.6% / 100% (ceiling) |
28
+ | Squeze vs. grep recall | not significantly different (McNemar p = 0.42) |
29
+ | Squeze vs. whole-repository recall | 3.1-point loss; the non-inferiority test at a 2-point margin **failed** |
30
+
31
+ **Good fit:** large repositories where an agent would otherwise read thousands of irrelevant lines, and repeated queries in the same session.
32
+ **Not measured:** output tokens, model answer quality and billing. No model is called in these tests.
7
33
 
8
34
  > **Status of the evidence.** Every public number in this document comes from a script in this repository and a raw result file you can inspect. The one private-repository result in section 0 of [Evidence](#evidence) is aggregate only and cannot be reproduced from this repository. For 3.0, the public non-inferiority test against whole-repository reading **failed**; section 0 gives the numbers. Section [Evidence](#evidence) lists what was measured, how, the confidence intervals and what was **not** proven. Nothing here claims 100% accuracy, answer quality or billing savings.
9
35
 
10
36
  ## Contents
11
37
 
12
- 1. [Why](#why) · 2. [Install](#install) · 3. [Use](#use) · 4. [How it works](#how-it-works) · 5. [What is new in 3.0](#what-is-new-in-30) · 6. [What is new in 2.2](#what-is-new-in-22) · 7. [Evidence](#evidence) · 8. [Configuration](#configuration) · 9. [Security model](#security-model) · 10. [Limitations](#limitations) · 11. [Reproduce](#reproduce) · 12. [Repository map](#repository-map)
38
+ 1. [Why](#why) · 2. [FAQ](#faq) · 3. [Install](#install) · 4. [Use](#use) · 5. [How it works](#how-it-works) · 6. [What is new in 3.0](#what-is-new-in-30) · 7. [What is new in 2.2](#what-is-new-in-22) · 8. [Evidence](#evidence) · 9. [Configuration](#configuration) · 10. [Security model](#security-model) · 11. [Limitations](#limitations) · 12. [Reproduce](#reproduce) · 13. [Repository map](#repository-map)
13
39
 
14
40
  ## Why
15
41
 
@@ -20,6 +46,28 @@ An agent that reads whole files to answer "where is retry backoff computed?" pay
20
46
  - **Deterministic.** The same repository state and query give byte-identical output.
21
47
  - **Local.** The only optional network call is to an Ollama server on `127.0.0.1` if you enable embeddings.
22
48
 
49
+ ## FAQ
50
+
51
+ ### How do I give a coding agent the right code without pasting the whole repository?
52
+
53
+ Ask for the task, error or stack trace inside a token budget, for example `squeze context --root . --query "where is retry backoff computed?" --budget 3000`. Squeze returns the few verbatim, line-cited excerpts that match. MCP agents use the same engine through the [MCP server](#mcp).
54
+
55
+ ### How do I use Squeze with GitHub Copilot?
56
+
57
+ Build the VSIX from this repository with `npm run package`, then install it with `code --install-extension releases/squeze-cli-3.0.2.vsix` (see [VS Code](#vs-code)). Then enable **Squeze Context**, **Expand** and **Map** in Copilot's tool picker, or write `#squeze` in a prompt.
58
+
59
+ ### Does Squeze send my code to a model or a server?
60
+
61
+ No. Squeze makes no model calls and collects no telemetry. Its only network call is optional: with `--semantic-model`, it talks to an Ollama server on `127.0.0.1` on your own machine.
62
+
63
+ ### Which languages does Squeze support?
64
+
65
+ 20 tree-sitter grammars: C, C++, C#, Go, Java, JavaScript, Python, Ruby, Rust, TypeScript and TSX, plus PHP, Kotlin, Scala, Bash, Elixir, OCaml, Objective-C, Solidity and Zig. Markdown, JSON, YAML, TOML, XML, HTML, CSS, SQL, Dockerfile, Makefile, protobuf and HCL have structural chunkers.
66
+
67
+ ### Does a smaller context make the answers better?
68
+
69
+ Not measured. The public tests measure retrieval: 87.3% fewer input tokens than a grep-and-read baseline across 360 symbol-lookup cases, and recall of 96.9% against grep's 95.6% (not statistically different). Answer quality, output tokens and billing are not measured. See [Evidence](#evidence).
70
+
23
71
  ## Install
24
72
 
25
73
  Requires Node.js 20.19 or newer.
@@ -45,8 +93,8 @@ The older `reposqueeze-v2` command name still works as an alias. Tool names chan
45
93
  ### VS Code
46
94
 
47
95
  ```sh
48
- npm run package # writes releases/squeze-cli-3.0.0.vsix
49
- code --install-extension releases/squeze-cli-3.0.0.vsix
96
+ npm run package # writes releases/squeze-cli-3.0.2.vsix
97
+ code --install-extension releases/squeze-cli-3.0.2.vsix
50
98
  ```
51
99
 
52
100
  Enable **Squeze Context**, **Expand** and **Map** in Copilot's tool picker, or write `#squeze` in a prompt. Run **Squeze: Install Copilot Instructions** once per repository for retrieval-first guidance.
@@ -300,7 +348,7 @@ The 2.1.0 profile on the 921-file repo: tokenizing the whole repository only to
300
348
 
301
349
  ### 11. Tests and robustness
302
350
 
303
- `npm test` runs 678 tests (unit, property, adversarial, MCP protocol, cache corruption and concurrency, read-only checkout). All 678 pass on the 3.0.0 tree. Two tests have wall-clock limits (a 60 s MCP request timeout and a 1 s bound on 2 MiB of adversarial text) and can fail under heavy machine load, so re-run before treating a failure as a regression.
351
+ `npm test` runs 678 tests (unit, property, adversarial, MCP protocol, cache corruption and concurrency, read-only checkout). All 678 pass on the 3.0.2 tree. Two tests have wall-clock limits (a 60 s MCP request timeout and a 1 s bound on 2 MiB of adversarial text) and can fail under heavy machine load, so re-run before treating a failure as a regression.
304
352
 
305
353
  A many-repository robustness and adversarial suite is in [bench/robustness](bench/robustness). Only a partial run was completed on the final build: 2 repositories (gin, requests), 32 commands, 0 crashes, 0 timeouts, 0 budget violations, 0 secret-regex hits in outputs ([report](benchmarks/v3/robustness-final.md)). That run flagged 4 of 8 repeat comparisons as non-identical while the machine load was about 50; serial re-runs of `map` on the same checkout were byte-identical 3 of 3 times and `context` cold and warm were identical on a second checkout, so the cause was not identified. The adversarial section did not finish and is **not** claimed.
306
354
 
package/dist/cli.cjs CHANGED
@@ -57798,7 +57798,7 @@ async function runGraph(repo, request = {}) {
57798
57798
  }
57799
57799
 
57800
57800
  // src/mcp.ts
57801
- var VERSION2 = "3.0.0";
57801
+ var VERSION2 = "3.0.2";
57802
57802
  async function serve(root, options = {}) {
57803
57803
  const { semanticModel, tools = "core", features } = typeof options === "string" ? { semanticModel: options } : options;
57804
57804
  const repo = new Engine(root, { semanticModel, features });
package/package.json CHANGED
@@ -1,8 +1,9 @@
1
1
  {
2
2
  "name": "squeze-cli",
3
+ "mcpName": "io.github.2002-rokkam/squeze",
3
4
  "displayName": "Squeze",
4
- "description": "Local, deterministic, token-budgeted code context and code graph for Copilot and MCP coding agents. Cuts the tokens (credits) an agent spends reading a repository.",
5
- "version": "3.0.0",
5
+ "description": "Local, deterministic, token-budgeted code context for GitHub Copilot and MCP coding agents. Fewer input tokens per task: cited source excerpts and a code graph.",
6
+ "version": "3.0.2",
6
7
  "publisher": "2002-rokkam",
7
8
  "license": "MIT",
8
9
  "type": "module",
@@ -38,7 +39,7 @@
38
39
  "test": "node --import tsx --test tests/*.test.ts",
39
40
  "bench": "node --import tsx scripts/benchmark.ts",
40
41
  "bench:fetch": "node scripts/fetch-bench.mjs",
41
- "package": "npm run build && vsce package --no-dependencies --allow-missing-repository -o releases/squeze-cli-3.0.0.vsix",
42
+ "package": "npm run build && vsce package --no-dependencies --allow-missing-repository -o releases/squeze-cli-3.0.2.vsix",
42
43
  "prepare": "npm run build",
43
44
  "test:editor": "node scripts/test-extension.mjs",
44
45
  "test:ui": "node --import tsx --test tests/ui/*.test.ts",
@@ -289,15 +290,30 @@
289
290
  },
290
291
  "keywords": [
291
292
  "copilot",
293
+ "github-copilot",
292
294
  "mcp",
295
+ "mcp-server",
296
+ "model-context-protocol",
297
+ "vscode-extension",
293
298
  "context",
299
+ "context-engineering",
300
+ "codebase-context",
294
301
  "code-search",
302
+ "code-retrieval",
295
303
  "code-graph",
304
+ "repository-map",
305
+ "repo-map",
296
306
  "tokens",
307
+ "token-optimization",
308
+ "token-budget",
309
+ "context-window",
297
310
  "llm",
298
311
  "agents",
299
- "tree-sitter",
300
- "repository-map"
312
+ "ai-coding-agent",
313
+ "coding-agent",
314
+ "developer-tools",
315
+ "cli",
316
+ "tree-sitter"
301
317
  ],
302
318
  "publishConfig": {
303
319
  "access": "public"