squeze-cli 3.0.1 → 3.0.3

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 +1,16 @@
1
1
  # Changelog
2
2
 
3
+ ## 3.0.3 — 2026-11-15
4
+
5
+ ### Added
6
+ - An extension icon (`media/icon.png`, 256×256 PNG), referenced by the manifest `icon` field. It shows on the VS Code Marketplace listing and in the Extensions view. The npm and MCP behaviour is unchanged; the version constant in `src/mcp.ts` and `server.json` moves with the release.
7
+
8
+ ## 3.0.2 — 2026-11-15
9
+
10
+ ### Changed
11
+ - 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.
12
+ - 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.
13
+
3
14
  ## 3.0.1 — 2026-11-15
4
15
 
5
16
  ### Changed
package/README.md CHANGED
@@ -1,8 +1,8 @@
1
- # Squeze
1
+ # Squeze: token-budgeted code context for coding agents
2
2
 
3
3
  **Give your coding agent the right code, not the whole repository.**
4
4
 
5
- Squeze is a local, deterministic context engine for coding agents. 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, no network, no telemetry.
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
6
 
7
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
8
 
@@ -35,7 +35,7 @@ Public proof on 9 pinned open-source repositories, 360 symbol-lookup cases. Meth
35
35
 
36
36
  ## Contents
37
37
 
38
- 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)
39
39
 
40
40
  ## Why
41
41
 
@@ -46,6 +46,28 @@ An agent that reads whole files to answer "where is retry backoff computed?" pay
46
46
  - **Deterministic.** The same repository state and query give byte-identical output.
47
47
  - **Local.** The only optional network call is to an Ollama server on `127.0.0.1` if you enable embeddings.
48
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
+ Install **Squeze** from the VS Code Marketplace with `code --install-extension 2002-rokkam.squeze-cli` (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
+
49
71
  ## Install
50
72
 
51
73
  Requires Node.js 20.19 or newer.
@@ -70,11 +92,14 @@ The older `reposqueeze-v2` command name still works as an alias. Tool names chan
70
92
 
71
93
  ### VS Code
72
94
 
95
+ Search **Squeze** in the Extensions view, or install from the terminal:
96
+
73
97
  ```sh
74
- npm run package # writes releases/squeze-cli-3.0.1.vsix
75
- code --install-extension releases/squeze-cli-3.0.1.vsix
98
+ code --install-extension 2002-rokkam.squeze-cli # VS Code Marketplace
76
99
  ```
77
100
 
101
+ The same extension is on [Open VSX](https://open-vsx.org/extension/2002-rokkam/squeze-cli) for VSCodium and other forks. To build a VSIX from source instead, run `npm run package` (writes `releases/squeze-cli-3.0.3.vsix`) and install that file with `code --install-extension`.
102
+
78
103
  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.
79
104
 
80
105
  The extension also provides **Squeze: Open Code Explorer** (an interactive map of the code graph), **Squeze: Refresh Index** and **Squeze: Show Token Savings**. The index refreshes after file changes when `squeze.autoRefresh` is on (the default). Above 5,000 files the default index parses a candidate subset, so the graph is marked partial; timings are in [docs/SCALE_EVALUATION.md](docs/SCALE_EVALUATION.md#incremental-refresh-on-a-real-repository).
@@ -326,7 +351,7 @@ The 2.1.0 profile on the 921-file repo: tokenizing the whole repository only to
326
351
 
327
352
  ### 11. Tests and robustness
328
353
 
329
- `npm test` runs 678 tests (unit, property, adversarial, MCP protocol, cache corruption and concurrency, read-only checkout). All 678 pass on the 3.0.1 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.
354
+ `npm test` runs 678 tests (unit, property, adversarial, MCP protocol, cache corruption and concurrency, read-only checkout). All 678 pass on the 3.0.3 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.
330
355
 
331
356
  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.
332
357
 
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 = "3.0.1";
57801
+ var VERSION2 = "3.0.3";
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/media/icon.png ADDED
Binary file
package/package.json CHANGED
@@ -2,9 +2,10 @@
2
2
  "name": "squeze-cli",
3
3
  "mcpName": "io.github.2002-rokkam/squeze",
4
4
  "displayName": "Squeze",
5
- "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.",
6
- "version": "3.0.1",
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": "3.0.3",
7
7
  "publisher": "2002-rokkam",
8
+ "icon": "media/icon.png",
8
9
  "license": "MIT",
9
10
  "type": "module",
10
11
  "engines": {
@@ -39,7 +40,7 @@
39
40
  "test": "node --import tsx --test tests/*.test.ts",
40
41
  "bench": "node --import tsx scripts/benchmark.ts",
41
42
  "bench:fetch": "node scripts/fetch-bench.mjs",
42
- "package": "npm run build && vsce package --no-dependencies --allow-missing-repository -o releases/squeze-cli-3.0.1.vsix",
43
+ "package": "npm run build && vsce package --no-dependencies --allow-missing-repository -o releases/squeze-cli-3.0.3.vsix",
43
44
  "prepare": "npm run build",
44
45
  "test:editor": "node scripts/test-extension.mjs",
45
46
  "test:ui": "node --import tsx --test tests/ui/*.test.ts",
@@ -270,7 +271,7 @@
270
271
  "@types/node": "^22.0.0",
271
272
  "@types/vscode": "^1.100.0",
272
273
  "@vscode/test-electron": "^2.5.2",
273
- "@vscode/vsce": "^3.6.0",
274
+ "@vscode/vsce": "^4.1.1",
274
275
  "esbuild": "^0.25.0",
275
276
  "playwright": "^1.65.1",
276
277
  "tree-sitter-wasms": "0.1.13",
@@ -297,14 +298,22 @@
297
298
  "vscode-extension",
298
299
  "context",
299
300
  "context-engineering",
301
+ "codebase-context",
300
302
  "code-search",
303
+ "code-retrieval",
301
304
  "code-graph",
302
305
  "repository-map",
306
+ "repo-map",
303
307
  "tokens",
304
308
  "token-optimization",
309
+ "token-budget",
310
+ "context-window",
305
311
  "llm",
306
312
  "agents",
307
313
  "ai-coding-agent",
314
+ "coding-agent",
315
+ "developer-tools",
316
+ "cli",
308
317
  "tree-sitter"
309
318
  ],
310
319
  "publishConfig": {