deel-local-cli 1.6.3 → 1.8.0
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/README.ko.md +1182 -0
- package/README.md +850 -636
- package/bin/deel.js +44 -3
- package/package.json +3 -3
- package/src/acp/map.js +1 -1
- package/src/acp/serve.js +25 -2
- package/src/agent/loop.js +41 -9
- package/src/agent/session.js +15 -9
- package/src/backend/adapter.js +277 -4
- package/src/backend/ctxsize.js +16 -2
- package/src/backend/detect.js +104 -6
- package/src/backend/price.js +197 -0
- package/src/backend/retry.js +3 -0
- package/src/backend/scanui.js +2 -1
- package/src/backend/vision.js +26 -4
- package/src/commands.js +141 -38
- package/src/completion.js +21 -2
- package/src/i18n/en.js +160 -1
- package/src/i18n/index.js +22 -0
- package/src/i18n/ja.js +152 -1
- package/src/i18n/ko.js +173 -1
- package/src/i18n/zh.js +152 -1
- package/src/oneshot.js +39 -6
- package/src/pack/selfpack.js +1 -1
- package/src/providers/anthropic.js +48 -0
- package/src/providers/bedrock.js +102 -0
- package/src/providers/custom.js +65 -0
- package/src/providers/gemini.js +64 -0
- package/src/providers/index.js +121 -0
- package/src/providers/openai.js +68 -0
- package/src/repl.js +198 -33
- package/src/report.js +3 -2
- package/src/reset.js +397 -0
- package/src/safety/audit.js +5 -2
- package/src/safety/authcmd.js +305 -0
- package/src/safety/keystore.js +53 -0
- package/src/safety/runmode.js +123 -0
- package/src/safety/secrets.js +61 -0
- package/src/safety/undo.js +3 -2
- package/src/setup.js +215 -12
- package/src/tools/desc.en.js +19 -14
- package/src/tools/index.js +141 -43
- package/src/tools/jobs.js +17 -13
- package/src/tools/lsp.js +5 -4
- package/src/tools/outline.js +7 -3
- package/src/tools/task.js +10 -6
- package/src/tools/todo.js +9 -2
- package/src/tools/verify.js +9 -3
- package/src/tools/webfetch.js +2 -1
- package/src/ui/export.js +1 -1
- package/src/ui/histline.js +67 -0
- package/src/ui/status.js +88 -3
- package/README.en.md +0 -1025
package/README.md
CHANGED
|
@@ -1,13 +1,15 @@
|
|
|
1
1
|
<div align="center">
|
|
2
2
|
|
|
3
3
|
<picture>
|
|
4
|
-
<source media="(prefers-color-scheme: dark)" srcset="docs/assets/hero-
|
|
5
|
-
<img alt="deel —
|
|
4
|
+
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/jysvai/deel-local-cli/main/docs/assets/hero-en-dark.svg">
|
|
5
|
+
<img alt="deel — stays on this machine" src="https://raw.githubusercontent.com/jysvai/deel-local-cli/main/docs/assets/hero-en-light.svg" width="620">
|
|
6
6
|
</picture>
|
|
7
7
|
|
|
8
|
-
###
|
|
8
|
+
### A coding-agent CLI that runs on local models and private gateways
|
|
9
9
|
|
|
10
|
-
|
|
10
|
+
Zero dependencies · Node 20+ · Exactly one place your source can go
|
|
11
|
+
|
|
12
|
+
Vendor APIs connect too — **only when you say so**
|
|
11
13
|
|
|
12
14
|
<br>
|
|
13
15
|
|
|
@@ -18,221 +20,279 @@
|
|
|
18
20
|
|
|
19
21
|
[](https://github.com/jysvai/deel-local-cli/actions/workflows/test.yml)
|
|
20
22
|
[](https://github.com/jysvai/deel-local-cli/actions/workflows/codeql.yml)
|
|
21
|
-
[](docs/en/develop.md)
|
|
22
24
|
|
|
23
25
|
[](https://www.npmjs.com/package/deel-local-cli?activeTab=dependencies)
|
|
24
26
|
[](package.json)
|
|
25
|
-
[](
|
|
26
|
-
[](
|
|
27
|
+
[](#where-your-data-can-go)
|
|
28
|
+
[](#where-your-data-can-go)
|
|
27
29
|
|
|
28
|
-
**[
|
|
30
|
+
**[한국어](README.ko.md)** · [Corporate review](#corporate-review-package) · [Troubleshooting](#troubleshooting) · [Full docs](docs/en/)
|
|
29
31
|
|
|
30
32
|
</div>
|
|
31
33
|
|
|
32
34
|
---
|
|
33
35
|
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
36
|
+
### The first thing you see answers the only question that matters
|
|
37
|
+
|
|
38
|
+
<picture>
|
|
39
|
+
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/jysvai/deel-local-cli/main/docs/assets/shot-head-en-dark.svg">
|
|
40
|
+
<img alt="deel startup panel: model, where it sends, link capabilities, folder, approval mode" src="https://raw.githubusercontent.com/jysvai/deel-local-cli/main/docs/assets/shot-head-en-light.svg" width="900">
|
|
41
|
+
</picture>
|
|
42
|
+
|
|
43
|
+
**`sends to this machine 127.0.0.1 ← and nowhere else`.** Not in a policy document —
|
|
44
|
+
on screen, every time you start. The `⌂` in front stays in the status bar for the whole
|
|
45
|
+
session and turns into `↗` the moment traffic would leave. A real capture, not a mockup:
|
|
46
|
+
`node tools/shot.mjs` regenerates every image on this page from a live run.
|
|
47
|
+
|
|
48
|
+
<br>
|
|
47
49
|
|
|
48
|
-
|
|
49
|
-
❯ 로그 형식 통일해줘
|
|
50
|
+
Then you give it work, and it goes and does it:
|
|
50
51
|
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
◈ Edit(src/runner.js)
|
|
56
|
-
└ 1군데
|
|
52
|
+
<picture>
|
|
53
|
+
<source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/jysvai/deel-local-cli/main/docs/assets/shot-chat-en-dark.svg">
|
|
54
|
+
<img alt="deel doing a task end to end: Grep, Read, Edit with an inline diff, and the file it wrote" src="https://raw.githubusercontent.com/jysvai/deel-local-cli/main/docs/assets/shot-chat-en-light.svg" width="900">
|
|
55
|
+
</picture>
|
|
57
56
|
|
|
58
|
-
|
|
57
|
+
Every number in that image is real — the tools ran against real files. Only the model is a
|
|
58
|
+
stub on `127.0.0.1`, so the capture is reproducible; the tool calls, the diff and the file
|
|
59
|
+
summary are what deel actually printed.
|
|
59
60
|
|
|
60
|
-
|
|
61
|
+
---
|
|
62
|
+
|
|
63
|
+
## 60 seconds
|
|
64
|
+
|
|
65
|
+
```bash
|
|
66
|
+
npm i -g deel-local-cli # 0 dependencies, no install scripts
|
|
67
|
+
deel setup # point it at Ollama, LM Studio, or your gateway
|
|
68
|
+
deel # start working in the current folder
|
|
61
69
|
```
|
|
62
70
|
|
|
71
|
+
No account, no sign-up, no telemetry. If you already run Ollama or LM Studio,
|
|
72
|
+
`deel setup` finds it — `deel scan` lists every local runtime and model on the machine.
|
|
73
|
+
|
|
63
74
|
---
|
|
64
75
|
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
- [
|
|
71
|
-
- [
|
|
72
|
-
- [
|
|
73
|
-
- [
|
|
74
|
-
- [
|
|
75
|
-
- [
|
|
76
|
-
- [
|
|
77
|
-
- [
|
|
78
|
-
- [
|
|
79
|
-
- [
|
|
80
|
-
- [
|
|
81
|
-
- [
|
|
82
|
-
- [
|
|
83
|
-
- [
|
|
84
|
-
- [
|
|
85
|
-
- [
|
|
86
|
-
- [
|
|
87
|
-
- [
|
|
88
|
-
- [
|
|
89
|
-
- [
|
|
90
|
-
- [
|
|
91
|
-
|
|
92
|
-
|
|
93
|
-
|
|
94
|
-
|
|
76
|
+
<details>
|
|
77
|
+
<summary><b>Contents</b> — every section on this page</summary>
|
|
78
|
+
|
|
79
|
+
<br>
|
|
80
|
+
|
|
81
|
+
- [Why this exists](#why-this-exists)
|
|
82
|
+
- [What's different](#whats-different)
|
|
83
|
+
- [Quick start](#quick-start)
|
|
84
|
+
- [Where your data can go](#where-your-data-can-go)
|
|
85
|
+
- [Connecting a vendor API](#connecting-a-vendor-api)
|
|
86
|
+
- [Keys that expire (corporate gateways)](#keys-that-expire-corporate-gateways)
|
|
87
|
+
- [Multiple local runtimes](#multiple-local-runtimes)
|
|
88
|
+
- [Slash commands](#slash-commands)
|
|
89
|
+
- [Work modes](#work-modes)
|
|
90
|
+
- [Simple vs developer](#simple-vs-developer)
|
|
91
|
+
- [Tools](#tools)
|
|
92
|
+
- [Korean text and Excel](#korean-text-and-excel)
|
|
93
|
+
- [Serving what you built](#serving-what-you-built)
|
|
94
|
+
- [Skills and plugins](#skills-and-plugins)
|
|
95
|
+
- [Reasoning effort](#reasoning-effort)
|
|
96
|
+
- [Auto-compaction](#auto-compaction)
|
|
97
|
+
- [Resuming a conversation](#resuming-a-conversation)
|
|
98
|
+
- [Attaching tools from outside (MCP)](#attaching-tools-from-outside-mcp)
|
|
99
|
+
- [Inside your editor (ACP)](#inside-your-editor-acp)
|
|
100
|
+
- [Keeping secrets out of the conversation](#keeping-secrets-out-of-the-conversation)
|
|
101
|
+
- [Safety](#safety)
|
|
102
|
+
- [Corporate review package](#corporate-review-package)
|
|
103
|
+
- [Configuration](#configuration)
|
|
104
|
+
- [Troubleshooting](#troubleshooting)
|
|
105
|
+
- [Development](#development)
|
|
106
|
+
- [Release notes](#release-notes)
|
|
107
|
+
|
|
108
|
+
</details>
|
|
109
|
+
|
|
110
|
+
This page is the **summary**. Each section links to the detail behind it.
|
|
111
|
+
|
|
112
|
+
| Full docs | What is in there |
|
|
95
113
|
|---|---|
|
|
96
|
-
| [
|
|
97
|
-
| [
|
|
98
|
-
| [
|
|
99
|
-
| [
|
|
100
|
-
| [
|
|
101
|
-
| [
|
|
102
|
-
| [
|
|
103
|
-
| [
|
|
104
|
-
| [
|
|
114
|
+
| [Models](docs/en/models.md) | Grade and window size · Korean-model presets · project detection |
|
|
115
|
+
| [The screen](docs/en/interface.md) | The input box · work modes · simple vs developer · what it asks about |
|
|
116
|
+
| [Tools in depth](docs/en/tools.md) | `Outline` · `Verify` · `Task` · `Jobs` · `Append` · `Def`/`Refs` · edit matching |
|
|
117
|
+
| [Korean documents and Excel](docs/en/documents.md) | hwpx/docx/pptx/**PDF** · encoding · Excel → CSV |
|
|
118
|
+
| [Extending](docs/en/extend.md) | Skills · plugins · MCP · ACP |
|
|
119
|
+
| [Speed and spend](docs/en/tuning.md) | Per-stage effort · the prefix cache · context length |
|
|
120
|
+
| [Safety and corporate review](docs/en/safety.md) | Undo · working scope · audit log · the review package |
|
|
121
|
+
| [Configuration](docs/en/config.md) · [Development](docs/en/develop.md) | Env vars · run flags · running the tests · folder layout |
|
|
122
|
+
| [Release notes](docs/en/releases.md) | [1.7.x](docs/en/releases/1.7.md) · [1.6.x](docs/en/releases/1.6.md) · [1.5.x](docs/en/releases/1.5.md) · [1.4.x](docs/en/releases/1.4.md) · [1.3.x](docs/en/releases/1.3.md) · [1.2.x](docs/en/releases/1.2.md) |
|
|
105
123
|
|
|
106
124
|
---
|
|
107
125
|
|
|
108
|
-
##
|
|
126
|
+
## Why this exists
|
|
109
127
|
|
|
110
|
-
|
|
111
|
-
|
|
128
|
+
When a corporate security policy blocks **unapproved software**, most coding-agent tools are
|
|
129
|
+
unusable: hundreds of transitive dependencies, scripts that run at install time, and no
|
|
130
|
+
one-line answer to "where does it send my code?"
|
|
112
131
|
|
|
113
|
-
deel
|
|
132
|
+
deel is built to pass that review.
|
|
114
133
|
|
|
115
134
|
| | deel |
|
|
116
135
|
|---|---|
|
|
117
|
-
|
|
|
118
|
-
|
|
|
119
|
-
|
|
|
120
|
-
|
|
|
136
|
+
| External dependencies | **0** — Node built-ins only |
|
|
137
|
+
| Install scripts | **none** — unzip and run |
|
|
138
|
+
| Where source can go | **one address** — the one you configured |
|
|
139
|
+
| Requirement | Node 20+ |
|
|
121
140
|
|
|
122
|
-
|
|
141
|
+
Verify it yourself:
|
|
123
142
|
|
|
124
143
|
```bash
|
|
125
144
|
npm view deel-local-cli dependencies # {}
|
|
126
|
-
npm view deel-local-cli scripts # install/postinstall
|
|
127
|
-
deel audit #
|
|
145
|
+
npm view deel-local-cli scripts # no install/postinstall
|
|
146
|
+
deel audit # full review sheet
|
|
128
147
|
```
|
|
129
148
|
|
|
130
149
|
---
|
|
131
150
|
|
|
132
|
-
##
|
|
151
|
+
## What's different
|
|
133
152
|
|
|
134
|
-
|
|
135
|
-
|
|
153
|
+
A handful of coding agents can talk to a local model. Far fewer were
|
|
154
|
+
**redesigned inside for running locally.**
|
|
136
155
|
|
|
137
|
-
| |
|
|
156
|
+
| | Other tools | deel |
|
|
138
157
|
|---|---|---|
|
|
139
|
-
| `/undo` |
|
|
140
|
-
|
|
|
141
|
-
|
|
|
142
|
-
|
|
|
143
|
-
| "
|
|
144
|
-
| MCP·ACP |
|
|
145
|
-
|
|
|
158
|
+
| `/undo` | rolls back files only — the conversation still believes it happened | rewinds **the conversation too** |
|
|
159
|
+
| Long conversations | pay a cost cloud tools never feel, unchanged, locally | ordering designed so the prefix cache **survives** |
|
|
160
|
+
| Edits on small models | fail on a single whitespace mismatch | 20%→**100%** success, 0 wrong-location edits |
|
|
161
|
+
| Korean models | unknown until you've run them | known **in advance** from public docs |
|
|
162
|
+
| "Done" | says so even for what wasn't checked | `/evidence` / `/export` — **unproven items included** |
|
|
163
|
+
| MCP · ACP | need an SDK | `child_process` + `JSON`, nothing else |
|
|
164
|
+
| Compliance paperwork | hand-written, drifts from reality | **generated by scanning the source** |
|
|
146
165
|
|
|
147
166
|
<br>
|
|
148
167
|
|
|
149
|
-
#### `/undo`
|
|
168
|
+
#### `/undo` rewinds the conversation along with the files
|
|
150
169
|
|
|
151
|
-
|
|
152
|
-
|
|
153
|
-
|
|
154
|
-
|
|
170
|
+
Roll back only the files and the model still believes it just made that edit
|
|
171
|
+
— it builds the next step on a premise that no longer holds, and nothing on
|
|
172
|
+
screen says otherwise. deel folds the messages back in lockstep with the
|
|
173
|
+
files. Folding can orphan a tool call, which the server answers with a 400,
|
|
174
|
+
so the same pass repairs the pairing (`repairToolPairs`).
|
|
155
175
|
|
|
156
|
-
####
|
|
176
|
+
#### Fixed the hidden reason local models get slower as a conversation grows
|
|
157
177
|
|
|
158
|
-
Ollama
|
|
159
|
-
|
|
160
|
-
|
|
161
|
-
|
|
162
|
-
|
|
163
|
-
|
|
178
|
+
Ollama and llama.cpp only reuse computation when a request's prefix exactly
|
|
179
|
+
matches the last one — change one character near the front and everything
|
|
180
|
+
after it, the whole conversation, gets recomputed. A cloud API never pays
|
|
181
|
+
this cost, so cloud-first tools have no reason to care; someone running
|
|
182
|
+
locally feels it compound every turn. deel pushes what can change per turn
|
|
183
|
+
(mode, pins) to the **end** of the prompt and sends Ollama `keep_alive: 60m`
|
|
184
|
+
so the front stays cached. The ordering is enforced by a test
|
|
185
|
+
(`test/cache.test.js`).
|
|
164
186
|
|
|
165
|
-
####
|
|
187
|
+
#### Edits actually succeed on small models
|
|
166
188
|
|
|
167
|
-
|
|
168
|
-
|
|
169
|
-
|
|
170
|
-
|
|
171
|
-
|
|
189
|
+
Small local models often can't reproduce the exact whitespace of the string
|
|
190
|
+
they're trying to edit. The internal benchmark (`npm run bench`) measured
|
|
191
|
+
20% success for the old exact-match-only approach. The current approach
|
|
192
|
+
(stepped whitespace/indent tolerance) measures **100%** — and both approaches
|
|
193
|
+
land at **0** wrong-location edits. When it's ambiguous, it says so instead
|
|
194
|
+
of guessing.
|
|
172
195
|
|
|
173
|
-
####
|
|
196
|
+
#### Korean models are known before you've ever run them
|
|
174
197
|
|
|
175
|
-
EXAONE
|
|
176
|
-
|
|
177
|
-
|
|
198
|
+
EXAONE, HyperCLOVA X, Kanana, Midm, and Solar get whatever's verifiable from
|
|
199
|
+
public documentation (e.g., whether a model is a reasoning model) applied
|
|
200
|
+
before the first prompt. Other tools meet these models cold, and it takes a
|
|
201
|
+
dozen-plus turns of trial and error before anyone learns their quirks.
|
|
178
202
|
|
|
179
|
-
#### "
|
|
203
|
+
#### "Done" comes with a receipt, not just a claim
|
|
180
204
|
|
|
181
|
-
`/evidence`
|
|
182
|
-
|
|
183
|
-
|
|
184
|
-
|
|
205
|
+
`/evidence` and `/export` record what wasn't verified alongside what was —
|
|
206
|
+
because the moment an AI coding tool is most likely to mislead someone is
|
|
207
|
+
exactly the moment it confidently says "done." `/export` is a self-contained
|
|
208
|
+
HTML file with zero outbound links, so it opens anywhere, including an
|
|
209
|
+
air-gapped network.
|
|
185
210
|
|
|
186
|
-
#### MCP
|
|
211
|
+
#### MCP and ACP, with no SDK
|
|
187
212
|
|
|
188
|
-
Model Context Protocol
|
|
189
|
-
|
|
190
|
-
`
|
|
191
|
-
|
|
213
|
+
Both the Model Context Protocol and the Agent Client Protocol are just
|
|
214
|
+
newline-delimited JSON-RPC 2.0 over stdio. deel implements both with nothing
|
|
215
|
+
but `child_process` and `JSON` — proof that zero dependencies isn't a
|
|
216
|
+
capability given up, it's a capability that was never needed.
|
|
192
217
|
|
|
193
|
-
####
|
|
218
|
+
#### Compliance paperwork it doesn't hand-write
|
|
194
219
|
|
|
195
|
-
|
|
196
|
-
|
|
197
|
-
|
|
220
|
+
The import-review report, SBOM, and audit spec that `deel pack` produces are
|
|
221
|
+
generated **by scanning the actual source**, not typed by a person.
|
|
222
|
+
Hand-written paperwork eventually drifts from reality, and the moment a
|
|
223
|
+
reviewer catches one drifted claim, they stop trusting the rest of it.
|
|
198
224
|
|
|
199
225
|
---
|
|
200
226
|
|
|
201
|
-
##
|
|
227
|
+
## Quick start
|
|
228
|
+
|
|
229
|
+
### The screen speaks your language
|
|
230
|
+
|
|
231
|
+
deel is written in Korean — the code, the function names, the comments. That part stays.
|
|
232
|
+
What you see on screen does not have to. Four screen languages ship: **한국어 · English ·
|
|
233
|
+
日本語 · 中文**.
|
|
234
|
+
|
|
235
|
+
> **How this is kept honest:** `/lang` counting the table is not enough — it can only count
|
|
236
|
+
> strings that made it *into* the table, and for a long time the tool result summaries and the
|
|
237
|
+
> thinking indicator never did. So a test starts deel in each language and reads the screen:
|
|
238
|
+
> `test/langleak.test.js` walks seven screens and fails if a Korean character shows up on an
|
|
239
|
+
> English one. It also fails on `1 files`, and on a stray `·` left dangling at the end of a line.
|
|
240
|
+
|
|
241
|
+
```bash
|
|
242
|
+
DEEL_LANG=en deel # this run only (also ja, zh)
|
|
243
|
+
/lang en # and remember it
|
|
244
|
+
/lang ja # 日本語
|
|
245
|
+
/lang zh # 中文
|
|
246
|
+
/lang # how much is translated so far
|
|
247
|
+
```
|
|
248
|
+
|
|
249
|
+
Nothing ever comes through blank. A line that has not been translated falls back to English
|
|
250
|
+
first and Korean second — so a Japanese or Chinese screen degrades to English, not to Korean —
|
|
251
|
+
and `/lang` prints exactly how many strings are covered.
|
|
252
|
+
|
|
253
|
+
What the model reads follows the same switch. Set it to English and the rules, the mode
|
|
254
|
+
instructions, and the tool descriptions all go out in English — so the model answers you in
|
|
255
|
+
English instead of Korean. That side is cheaper, too: the part of the window that ships on every
|
|
256
|
+
single request drops from about 4,900 tokens to about 3,450 — on a 32k model, from 15% of the
|
|
257
|
+
window to 10.5%.
|
|
258
|
+
|
|
259
|
+
Tool names and argument names stay Korean (`목적`, `할일`, `번호`). Those are identifiers, not
|
|
260
|
+
prose — rename them and the tool stops being called at all.
|
|
202
261
|
|
|
203
|
-
###
|
|
262
|
+
### Install
|
|
204
263
|
|
|
205
264
|
```bash
|
|
206
265
|
npm install -g deel-local-cli
|
|
207
266
|
```
|
|
208
267
|
|
|
209
|
-
|
|
268
|
+
Or skip installing entirely — there is no `npm install` step:
|
|
210
269
|
|
|
211
270
|
```bash
|
|
212
271
|
git clone https://github.com/jysvai/deel-local-cli
|
|
213
272
|
node deel-local-cli/bin/deel.js
|
|
214
273
|
```
|
|
215
274
|
|
|
216
|
-
>
|
|
217
|
-
>
|
|
275
|
+
> **Note** — do not run `npm install` in your home directory. A `node_modules` there makes every
|
|
276
|
+
> later npm command scan it and report warnings about unrelated packages. Use `-g` or `npx`.
|
|
218
277
|
|
|
219
|
-
###
|
|
278
|
+
### Point it at a model
|
|
220
279
|
|
|
221
|
-
|
|
280
|
+
Scan this machine and pick one:
|
|
222
281
|
|
|
223
282
|
```bash
|
|
224
283
|
deel scan --pick
|
|
225
284
|
```
|
|
226
285
|
|
|
227
|
-
|
|
286
|
+
Or enter an address directly (use this for a corporate gateway):
|
|
228
287
|
|
|
229
288
|
```bash
|
|
230
289
|
deel setup
|
|
231
290
|
```
|
|
232
291
|
|
|
233
|
-
###
|
|
292
|
+
### Start
|
|
234
293
|
|
|
235
|
-
|
|
294
|
+
Run `deel` in the folder you want to work in. **That folder becomes the scope — files outside it
|
|
295
|
+
cannot be read or written.**
|
|
236
296
|
|
|
237
297
|
```bash
|
|
238
298
|
cd C:\work\myproject
|
|
@@ -241,376 +301,491 @@ deel
|
|
|
241
301
|
|
|
242
302
|
---
|
|
243
303
|
|
|
244
|
-
##
|
|
304
|
+
## Where your data can go
|
|
245
305
|
|
|
246
|
-
|
|
247
|
-
|
|
248
|
-
|
|
306
|
+
A coding agent ships your whole source to a model. **The address is everything.**
|
|
307
|
+
Rather than promising in prose, the code enforces it: `src/safety/network.js` checks every request
|
|
308
|
+
and never builds one for an address that is not on the allow-list.
|
|
249
309
|
|
|
250
310
|
```
|
|
251
|
-
[A]
|
|
252
|
-
|
|
311
|
+
[A] Model gateway ────── the only path your source travels
|
|
312
|
+
One address, set in `setup`. Switching models closes the previous one.
|
|
253
313
|
|
|
254
|
-
[B]
|
|
255
|
-
GET
|
|
314
|
+
[B] Web read (WebFetch) ─ receive-only
|
|
315
|
+
GET only, zero-byte body. Private/loopback addresses refused. Every visit logged.
|
|
256
316
|
|
|
257
|
-
[C]
|
|
317
|
+
[C] Plugin fetch ─────── open only while /plugin install runs
|
|
258
318
|
|
|
259
|
-
[D] MCP
|
|
260
|
-
.deel/mcp.json
|
|
319
|
+
[D] MCP servers ──────── a separate child process, someone else's program
|
|
320
|
+
Only starts if a human writes it into .deel/mcp.json. Off by default.
|
|
261
321
|
```
|
|
262
322
|
|
|
263
|
-
A
|
|
264
|
-
|
|
265
|
-
|
|
266
|
-
|
|
323
|
+
A, B, and C are requests deel makes itself, so each one can be filtered.
|
|
324
|
+
**D is different** — an MCP server is its own process; there is no way to see
|
|
325
|
+
what sockets it opens from the outside. So under `--offline`, instead of
|
|
326
|
+
filtering its requests, deel **never starts the server at all** — it doesn't
|
|
327
|
+
claim to have blocked what it can't actually see.
|
|
267
328
|
|
|
268
|
-
`--offline`
|
|
329
|
+
Pass `--offline` and **B, C, and D are all closed** — traffic stays on this machine.
|
|
269
330
|
|
|
270
331
|
```bash
|
|
271
332
|
deel --offline
|
|
272
333
|
```
|
|
273
334
|
|
|
274
|
-
|
|
335
|
+
The destination is printed at the top of every session:
|
|
275
336
|
|
|
276
337
|
```
|
|
277
|
-
|
|
338
|
+
deel 1.8.0 ⌂ inside
|
|
339
|
+
Sends to this machine 127.0.0.1:11434 ← nowhere else
|
|
278
340
|
```
|
|
279
341
|
|
|
280
|
-
|
|
281
|
-
대화 기록·되돌리기 이력·설정은 작업 폴더의 `.deel/` 안에만 남습니다.
|
|
342
|
+
### Three run modes
|
|
282
343
|
|
|
283
|
-
|
|
284
|
-
|
|
285
|
-
|
|
344
|
+
Through 1.6 the only lock was `--offline`, and **the default was open**. One
|
|
345
|
+
line in `.deel/config.json` pointing outside was enough. The screen did show
|
|
346
|
+
`↗`, but that is a *notice*, not a lock.
|
|
347
|
+
|
|
348
|
+
| Mode | How | On an external address |
|
|
349
|
+
|---|---|---|
|
|
350
|
+
| `⌂ inside` | `deel` (default) | **Asks.** Say yes once and that connection stops asking |
|
|
351
|
+
| `↗ outside` | `deel online` · `--online` | Does not ask |
|
|
352
|
+
| `⛊ sealed` | `deel offline` · `--offline` | Ignores even remembered permission (strongest) |
|
|
353
|
+
|
|
354
|
+
**Both the address and the permission are required.** Changing the address
|
|
355
|
+
alone does not get you out.
|
|
356
|
+
|
|
357
|
+
Local and intranet ranges (`127.x` · `10.x` · `192.168.x` · `172.16-31.x`) pass
|
|
358
|
+
in all three modes — `offline` does not mean "no internet," it means "nothing
|
|
359
|
+
leaves the company."
|
|
360
|
+
|
|
361
|
+
Nothing is collected or transmitted. No telemetry, no usage stats, no crash reporting.
|
|
362
|
+
Conversation history, undo snapshots and config live only in `.deel/` inside your working folder.
|
|
363
|
+
|
|
364
|
+
> Verified by 159 checks in `npm test` (network + web + mcp), including bringing up a real
|
|
365
|
+
> server and confirming that **not a single request reaches it** when it is not allow-listed,
|
|
366
|
+
> and that an MCP server **never starts** under `--offline`.
|
|
286
367
|
|
|
287
368
|
---
|
|
288
369
|
|
|
289
|
-
##
|
|
370
|
+
## Connecting a vendor API
|
|
290
371
|
|
|
291
|
-
|
|
292
|
-
|
|
293
|
-
|
|
372
|
+
Local models are the default and that does not change. But "we have no GPU
|
|
373
|
+
in-house" and "just this one task on a bigger model" are real situations, so
|
|
374
|
+
vendor APIs can connect. **The modes above guard that door.**
|
|
294
375
|
|
|
376
|
+
```bash
|
|
377
|
+
deel setup
|
|
378
|
+
```
|
|
379
|
+
|
|
380
|
+
Instead of asking for a URL, it asks **where you're connecting**.
|
|
381
|
+
|
|
382
|
+
```
|
|
383
|
+
1. I only have a key — I'll figure out where it goes 1 blank
|
|
384
|
+
2. Enter an address (corporate gateway · local) 2 blanks
|
|
385
|
+
3. OpenAI (GPT) 1 blank
|
|
386
|
+
4. Anthropic (Claude) 1 blank
|
|
387
|
+
5. Google (Gemini) 1 blank
|
|
388
|
+
6. AWS Bedrock 2 blanks
|
|
295
389
|
```
|
|
296
|
-
$ deel scan
|
|
297
390
|
|
|
298
|
-
|
|
299
|
-
127.0.0.1 의 알려진 자리 13곳을 두드립니다. 바깥으로는 나가지 않습니다.
|
|
391
|
+
Option 1 is the point — the key prefix decides which single vendor is asked.
|
|
300
392
|
|
|
301
|
-
|
|
393
|
+
```
|
|
394
|
+
❯ sk-ant-api03-••••
|
|
395
|
+
✓ Looks like an Anthropic (Claude) key. (the key starts with sk-ant-)
|
|
396
|
+
It is not thrown at every vendor in turn.
|
|
397
|
+
```
|
|
398
|
+
|
|
399
|
+
Probing vendors one by one would send an Anthropic key to OpenAI's server and
|
|
400
|
+
then to Google's. You get a 401 and stop — but **the key has already left.**
|
|
401
|
+
So an unrecognized key is never guessed at; you are asked.
|
|
402
|
+
|
|
403
|
+
Bedrock asks for a region — five including Seoul (`ap-northeast-2`), plus
|
|
404
|
+
"enter it yourself." Claude has a different wire shape, absorbed in six places
|
|
405
|
+
([1.7.0 release notes](docs/en/releases/1.7.md#170)).
|
|
406
|
+
|
|
407
|
+
### Going outside masks secrets in file contents too
|
|
408
|
+
|
|
409
|
+
While everything stayed local, text read from files was deliberately **not**
|
|
410
|
+
masked: mask it and the model writes the mask back into the file, destroying
|
|
411
|
+
your real key.
|
|
412
|
+
|
|
413
|
+
Going outside flips that trade. One `Read` puts your whole `.env` into someone
|
|
414
|
+
else's server log, and that cannot be undone. The other side is now handled
|
|
415
|
+
elsewhere — `Write`, `Append` and `Edit` refuse to write a mask back into a file.
|
|
302
416
|
|
|
303
|
-
|
|
417
|
+
### You can see what it costs
|
|
418
|
+
|
|
419
|
+
```
|
|
420
|
+
❯ ─ 12.4s · 3 tools · ↑8.2k ↓1.1k · $0.0271
|
|
421
|
+
```
|
|
422
|
+
|
|
423
|
+
**There is no built-in price table.** Prices change whenever a vendor decides,
|
|
424
|
+
and a table baked into source would have the tool confidently printing wrong
|
|
425
|
+
amounts six months later. Write them in `.deel/config.json` — dollars per
|
|
426
|
+
million tokens:
|
|
427
|
+
|
|
428
|
+
```json
|
|
429
|
+
"요금": { "claude-opus-4-6": { "입력": 0, "출력": 0, "기준": "2026-09-01" } }
|
|
430
|
+
```
|
|
431
|
+
|
|
432
|
+
The amount is shown with **where it came from and as of when**, and after six
|
|
433
|
+
months it is marked stale. Unknown means nothing is printed — a local-only
|
|
434
|
+
session never sees money at all.
|
|
435
|
+
|
|
436
|
+
---
|
|
437
|
+
|
|
438
|
+
## Keys that expire (corporate gateways)
|
|
439
|
+
|
|
440
|
+
Corporate gateways do not hand out a fixed key. They hand out a one-hour token, behind a
|
|
441
|
+
corporate login. Pasting one in works until lunch, and then you get `HTTP 401` — a message
|
|
442
|
+
that **does not distinguish "wrong key" from "old key."** People go re-issue a key that was
|
|
443
|
+
never the problem.
|
|
444
|
+
|
|
445
|
+
So write down *how to get a key* instead of the key:
|
|
446
|
+
|
|
447
|
+
```json
|
|
448
|
+
"열쇠받기": {
|
|
449
|
+
"명령": "az account get-access-token --resource api://ai-gw --query accessToken -o tsv",
|
|
450
|
+
"수명": 3600
|
|
451
|
+
}
|
|
452
|
+
```
|
|
453
|
+
|
|
454
|
+
It runs right before a request, keeps the result in memory only, and fetches a fresh one a
|
|
455
|
+
minute before expiry — a token alive when the request left and dead when it arrived is
|
|
456
|
+
exactly that 401. On a 401 it fetches once more and retries **once**; a second 401 means you
|
|
457
|
+
genuinely lack access.
|
|
458
|
+
|
|
459
|
+
| | |
|
|
460
|
+
|---|---|
|
|
461
|
+
| You write the path | Nothing is auto-detected. Guessing at `az` on your PATH would mean you no longer know when this program runs what |
|
|
462
|
+
| Separate process | Never `import`ed — code inside our process would see other keys and the conversation |
|
|
463
|
+
| Asked once per session | Not once per fetch. Three prompts and people just press the key |
|
|
464
|
+
| Not while sealed | An `--offline` session does not go out to a login portal |
|
|
465
|
+
| Never written to disk | Memory only, for the life of the session |
|
|
466
|
+
| Banner output rejected | `Logged in as …` followed by a token gets a 400 from the gateway, indistinguishable on screen from a wrong key. The first line is shown back so you know to add `--query` |
|
|
467
|
+
|
|
468
|
+
`/status` says `Key store fetched · 52 min left` — not "stored", because we are not holding
|
|
469
|
+
it. An organisation can set the same block in the [managed policy](docs/en/config.md) file,
|
|
470
|
+
where it overrides the user's config and is never asked about.
|
|
471
|
+
|
|
472
|
+
---
|
|
473
|
+
|
|
474
|
+
## Multiple local runtimes
|
|
475
|
+
|
|
476
|
+
People rarely run just one. `deel scan` knocks on 13 known ports concurrently and identifies
|
|
477
|
+
each runtime from its **response**, not its port number — Ollama by `/api/version`,
|
|
478
|
+
LM Studio by `/api/v0/models`, llama.cpp by `/props`. Unrecognised ones are marked as a guess.
|
|
479
|
+
|
|
480
|
+
```
|
|
481
|
+
$ deel scan
|
|
482
|
+
|
|
483
|
+
✓ found 3
|
|
484
|
+
|
|
485
|
+
◆ Ollama 127.0.0.1:11434 Ollama API 36ms
|
|
304
486
|
· qwen2.5-coder:7b 7B · 4.4GB
|
|
305
487
|
· llama3.2:1b 1B · 1.2GB
|
|
306
|
-
◆ LM Studio 127.0.0.1:1234 OpenAI
|
|
488
|
+
◆ LM Studio 127.0.0.1:1234 OpenAI-compat 7ms
|
|
307
489
|
· devstral-small-2507
|
|
308
|
-
◆ llama.cpp 127.0.0.1:8080 OpenAI
|
|
490
|
+
◆ llama.cpp 127.0.0.1:8080 OpenAI-compat 7ms
|
|
309
491
|
· gemma-3-4b-it
|
|
310
492
|
|
|
311
|
-
|
|
312
|
-
|
|
313
|
-
추천 Ollama · qwen2.5-coder:7b
|
|
314
|
-
코딩용 모델 · 도구 호출을 잘하는 계열
|
|
493
|
+
Recommended Ollama · qwen2.5-coder:7b
|
|
315
494
|
```
|
|
316
495
|
|
|
317
|
-
|
|
318
|
-
LM Studio 는 `/api/v0/models`, llama.cpp 는 `/props`. 못 알아보면 `(추정)` 이라고 밝힙니다.
|
|
319
|
-
|
|
320
|
-
| 명령 | 하는 일 |
|
|
496
|
+
| Command | What it does |
|
|
321
497
|
|---|---|
|
|
322
|
-
| `deel scan` |
|
|
323
|
-
| `deel scan --pick` |
|
|
324
|
-
| `deel scan --save` |
|
|
325
|
-
| `deel scan --ports 9000,9100` |
|
|
326
|
-
| `deel scan --host
|
|
327
|
-
| `deel scan --key <키>` | 키가 필요한 로컬 서버일 때 |
|
|
498
|
+
| `deel scan` | Show what is running |
|
|
499
|
+
| `deel scan --pick` | Choose one from the list |
|
|
500
|
+
| `deel scan --save` | Register everything found |
|
|
501
|
+
| `deel scan --ports 9000,9100` | Extra ports to probe |
|
|
502
|
+
| `deel scan --host <addr>` | Defaults to `127.0.0.1` |
|
|
328
503
|
|
|
329
|
-
|
|
504
|
+
Switch with `/model` mid-conversation — **the conversation carries over.**
|
|
330
505
|
|
|
331
|
-
>
|
|
506
|
+
> **More** — It adapts to whatever model is attached · Korean models are known before they are experienced · Small windows get a smaller fixed share · On startup it reads what kind of project this folder is
|
|
332
507
|
>
|
|
333
|
-
> **[
|
|
508
|
+
> **[Models read →](docs/en/models.md#multiple-local-runtimes)**
|
|
334
509
|
|
|
335
510
|
---
|
|
336
511
|
|
|
337
|
-
##
|
|
512
|
+
## Slash commands
|
|
338
513
|
|
|
339
|
-
|
|
514
|
+
Names follow Claude Code / Codex conventions.
|
|
340
515
|
|
|
341
|
-
|
|
|
516
|
+
| Command | What it does |
|
|
342
517
|
|---|---|
|
|
343
|
-
| `/help` |
|
|
344
|
-
| `/
|
|
345
|
-
| `/
|
|
346
|
-
| `/
|
|
347
|
-
| `/consult
|
|
348
|
-
| `/export` |
|
|
349
|
-
| `/lsp [on\|off]` |
|
|
350
|
-
| `/context` |
|
|
351
|
-
| `/ctx [auto
|
|
352
|
-
| `/
|
|
353
|
-
| `/
|
|
354
|
-
| `/compact` |
|
|
355
|
-
| `/clear` |
|
|
356
|
-
| `/thread [new\|fork\|close
|
|
357
|
-
| `/learned [
|
|
358
|
-
| `/pin
|
|
359
|
-
| `/evidence [
|
|
360
|
-
| `/commit [
|
|
361
|
-
| `/model` |
|
|
362
|
-
| `/model 카드` |
|
|
363
|
-
| `/think
|
|
364
|
-
| `/think 배분
|
|
365
|
-
| `/think 자세히` |
|
|
366
|
-
| `/mode
|
|
367
|
-
| `/work [
|
|
368
|
-
| `/auto` |
|
|
369
|
-
| `/code` `/plan` `/architect` `/debug` `/ask` `/orchestrator` |
|
|
370
|
-
| `/level [
|
|
371
|
-
| `/motion [
|
|
372
|
-
| `/undo [
|
|
373
|
-
| `/diff [
|
|
374
|
-
| `/preview [
|
|
375
|
-
| `/tools` |
|
|
376
|
-
| `/skills [
|
|
377
|
-
| `/plugin [install\|remove\|pack]` |
|
|
378
|
-
| `/cost` |
|
|
379
|
-
| `/status` |
|
|
380
|
-
| `/scan [save]` |
|
|
381
|
-
| `/sessions` |
|
|
382
|
-
| `/recall
|
|
383
|
-
| `/memory` |
|
|
384
|
-
| `/mcp` |
|
|
385
|
-
| `/init` | `DEEL.md`
|
|
386
|
-
| `/exit` |
|
|
387
|
-
|
|
388
|
-
|
|
389
|
-
|
|
390
|
-
|
|
391
|
-
|
|
392
|
-
|
|
393
|
-
|
|
518
|
+
| `/help` | Command list |
|
|
519
|
+
| `/lang [ko\|en] [prompt lang]` | Screen language. **The prompt language is a separate axis** — `/lang en ko` instructs the model in Korean while answering you in English. Korean screen + English prompt cuts the 8k fixed share by 23% |
|
|
520
|
+
| `/keys` | Press keys to see what your terminal actually sends — for when new lines will not work |
|
|
521
|
+
| `/bell [on\|off]` | Ring and set the window title when a turn ends, or when deel needs an answer |
|
|
522
|
+
| `/consult <profile> <question>` | Ask a second model one question. Your current model stays put |
|
|
523
|
+
| `/export` | This conversation as a **one-page HTML report** — asked, changed, verified. Self-contained, opens on any network |
|
|
524
|
+
| `/lsp [on\|off]` | Language servers — what is installed, and whether `Def`/`Refs` are available. `off` turns post-edit diagnostics off only |
|
|
525
|
+
| `/context` | What is consuming the context window |
|
|
526
|
+
| `/ctx [auto\|number]` | Context **length** — re-read it off the model, or set it yourself |
|
|
527
|
+
| `/grade [small\|medium\|large\|auto]` | Model **grade** — how much it does on its own. A different axis from `/ctx` |
|
|
528
|
+
| `/out [number\|auto]` | Cap on a **single reply** — raise it when large files get cut |
|
|
529
|
+
| `/compact` | Summarise and fold older turns |
|
|
530
|
+
| `/clear` | Clear the conversation (keeps link and rules) |
|
|
531
|
+
| `/thread [new\|fork\|close\|n]` | Conversation threads — side work in its own context. Link and undo stay shared |
|
|
532
|
+
| `/learned [clear]` | What deel has picked up on its own — commands that work here, this model's habits |
|
|
533
|
+
| `/pin <text>` | Pin a line — folding and compaction **cannot reach it** |
|
|
534
|
+
| `/evidence [file]` | Evidence — what changed, and what proves it. **What is unproven is listed too** |
|
|
535
|
+
| `/commit [all\|preview\|title]` | Commits only what this session changed; message from the diff and the evidence. **Never pushes** |
|
|
536
|
+
| `/model` | Switch connection / model |
|
|
537
|
+
| `/model 카드` | Model card — what this model has actually done here, and what deel changed because of it |
|
|
538
|
+
| `/think <level>` | Reasoning level (`off·low·medium·high·max`) |
|
|
539
|
+
| `/think 배분 <profile>` | Per-stage profile (`even·save·deep`) |
|
|
540
|
+
| `/think 자세히` | Stage table — which stage runs at which level and cap |
|
|
541
|
+
| `/mode <mode>` | Approval policy — how much it asks (`auto` · `confirm` · `strict`) |
|
|
542
|
+
| `/work [mode]` | Work mode — what kind of work you are doing |
|
|
543
|
+
| `/auto` | Hand the wheel back — it picks the mode from what you type |
|
|
544
|
+
| `/code` `/plan` `/architect` `/debug` `/ask` `/orchestrator` | Switch work mode directly (pins it) |
|
|
545
|
+
| `/level [level]` | How much to show (`쉬움` simple · `개발자` developer) |
|
|
546
|
+
| `/motion [plain\|knight\|animal\|office\|off]` | What animates while it works — takes effect at once, and is saved |
|
|
547
|
+
| `/undo [turns]` | Revert file changes |
|
|
548
|
+
| `/diff [file]` | Files changed this session, and the changed lines |
|
|
549
|
+
| `/preview [folder\|file\|off]` | Serve what you built, right here — a browser opens with it |
|
|
550
|
+
| `/tools` | Available tools |
|
|
551
|
+
| `/skills [query\|all\|off]` | Browse, search, load skills |
|
|
552
|
+
| `/plugin [install\|remove\|pack]` | Manage plugins |
|
|
553
|
+
| `/cost` | Session usage |
|
|
554
|
+
| `/status` | Connection status |
|
|
555
|
+
| `/scan [save]` | Sweep this machine for local model servers (`save` registers them) |
|
|
556
|
+
| `/sessions` | Past conversations in this folder |
|
|
557
|
+
| `/recall <text>` | Search past conversations **by content** |
|
|
558
|
+
| `/memory` | What persists across sessions — view, add, delete |
|
|
559
|
+
| `/mcp` | Externally attached tools (MCP servers) |
|
|
560
|
+
| `/init` | Create a `DEEL.md` rules file |
|
|
561
|
+
| `/exit` | Quit |
|
|
562
|
+
|
|
563
|
+
Discovered plugin commands are invoked as `/<plugin>:<name>`, with `$ARGUMENTS` substituted.
|
|
564
|
+
|
|
565
|
+
`/scan` and `/sessions` work without leaving the session. If you just started another local
|
|
566
|
+
server or loaded a different model, `/scan save` then `/model` switches over without losing
|
|
567
|
+
the conversation.
|
|
568
|
+
|
|
569
|
+
**Without typing**
|
|
570
|
+
|
|
571
|
+
| Key | What it does |
|
|
394
572
|
|---|---|
|
|
395
|
-
| `Tab` |
|
|
396
|
-
| `Shift+Tab` |
|
|
397
|
-
| `Ctrl+O` |
|
|
398
|
-
| `↑` `↓` |
|
|
399
|
-
| `Ctrl+C` |
|
|
400
|
-
|
|
|
573
|
+
| `Tab` | Completes the `/` command you are typing. Candidates appear under the box as you type |
|
|
574
|
+
| `Shift+Tab` | Approval policy (`⏵⏵ auto` → `⏵ risky only` → `⏸ everything`) |
|
|
575
|
+
| `Ctrl+O` | Work mode (`종합` → `코드` → `계획` → …) |
|
|
576
|
+
| `↑` `↓` | Input history |
|
|
577
|
+
| `Ctrl+C` | Stops the answer in progress; twice on an empty line quits |
|
|
578
|
+
| Typing while it works, then `Enter` | Steers without throwing anything away — takes effect from the next step |
|
|
401
579
|
|
|
402
|
-
|
|
580
|
+
Korean IME composition, paste, `Ctrl+A/E` and backspace all keep working.
|
|
403
581
|
|
|
404
|
-
>
|
|
582
|
+
> **More** — Attaching a file with @ · Interrupting · Steering without stopping
|
|
405
583
|
>
|
|
406
|
-
> **[
|
|
584
|
+
> **[The screen read →](docs/en/interface.md#slash-commands)**
|
|
407
585
|
|
|
408
586
|
---
|
|
409
587
|
|
|
410
|
-
##
|
|
588
|
+
## Work modes
|
|
411
589
|
|
|
412
|
-
|
|
413
|
-
`Shift+Tab
|
|
590
|
+
What you are working on changes **which tools the model is given and how hard it thinks.**
|
|
591
|
+
Cycle with `Shift+Tab`, or type the name.
|
|
414
592
|
|
|
415
|
-
|
|
|
593
|
+
| Mode | For | Can edit files | Reasoning |
|
|
416
594
|
|---|---|---|---|
|
|
417
|
-
| `/auto` ◎
|
|
418
|
-
| `/code` ◆
|
|
419
|
-
| `/plan` ☰
|
|
420
|
-
| `/architect` ◈
|
|
421
|
-
| `/debug` ◉
|
|
422
|
-
| `/ask` ◇
|
|
423
|
-
| `/orchestrator` ❋
|
|
595
|
+
| `/auto` ◎ Auto | **Default.** Reads your message and switches for you | Yes | Normal (`save`) |
|
|
596
|
+
| `/code` ◆ Code | Writing and fixing | Yes | Normal (`save`) |
|
|
597
|
+
| `/plan` ☰ Plan | Planning first | **No** | Deep (`deep`·high) |
|
|
598
|
+
| `/architect` ◈ Architect | Shaping structure | **No** | Deep (`deep`·high) |
|
|
599
|
+
| `/debug` ◉ Debug | Finding causes | Yes | Deep, more steps (32) |
|
|
600
|
+
| `/ask` ◇ Ask | Explaining only | **No** | Shallow (`low`) |
|
|
601
|
+
| `/orchestrator` ❋ Orchestrator | Breaking up large work | Yes | Many steps (40) |
|
|
424
602
|
|
|
425
|
-
|
|
426
|
-
|
|
603
|
+
In read-only modes, `Write`, `Edit` and `Bash` are **never sent to the model at all.**
|
|
604
|
+
It is not asked politely not to edit — models forget requests. A tool that isn't there can't be used.
|
|
427
605
|
|
|
428
|
-
`/mode
|
|
606
|
+
Don't confuse this with `/mode`. They are separate axes:
|
|
429
607
|
|
|
430
|
-
- `/mode` —
|
|
431
|
-
- `/work` —
|
|
608
|
+
- `/mode` — **how much it asks you** (auto · confirm · strict)
|
|
609
|
+
- `/work` — **what kind of work you are doing** (the seven above)
|
|
432
610
|
|
|
433
|
-
`/think`
|
|
434
|
-
|
|
611
|
+
If you have explicitly set `/think` or `/mode`, your choice wins. A work mode never
|
|
612
|
+
overrides something a person chose.
|
|
435
613
|
|
|
436
|
-
>
|
|
614
|
+
> **More** — Switching by itself (Auto mode)
|
|
437
615
|
>
|
|
438
|
-
> **[
|
|
616
|
+
> **[The screen read →](docs/en/interface.md#work-modes)**
|
|
439
617
|
|
|
440
618
|
---
|
|
441
619
|
|
|
442
|
-
##
|
|
620
|
+
## Simple vs developer
|
|
443
621
|
|
|
444
|
-
|
|
445
|
-
|
|
622
|
+
Twenty commands on first launch means nothing gets chosen. Locking features away means
|
|
623
|
+
hitting a wall later. So only **what is shown** differs.
|
|
446
624
|
|
|
447
|
-
| |
|
|
625
|
+
| | Simple (`쉬움`, default) | Developer (`개발자`) |
|
|
448
626
|
|---|---|---|
|
|
449
|
-
| `/help`
|
|
450
|
-
|
|
|
451
|
-
|
|
|
627
|
+
| `/help` listing | Common commands only | Everything |
|
|
628
|
+
| Error messages | What to do about it | The original text |
|
|
629
|
+
| Safety | **Identical** | **Identical** |
|
|
452
630
|
|
|
453
|
-
`/level 개발자`
|
|
631
|
+
`/level 개발자` is saved to config and persists across sessions.
|
|
454
632
|
|
|
455
|
-
|
|
633
|
+
Two things matter here:
|
|
456
634
|
|
|
457
|
-
-
|
|
458
|
-
-
|
|
459
|
-
|
|
635
|
+
- **Hidden commands still work.** `/think high` works in simple mode. It just isn't listed.
|
|
636
|
+
- **Beginners do not get fewer safeguards.** Undo, workspace scope and dangerous-command
|
|
637
|
+
blocking are identical. A beginner needs the undo more, not less.
|
|
460
638
|
|
|
461
|
-
>
|
|
639
|
+
> **More** — The input box · You don't have to type the whole command · The box stays while it works · The picture on the left moves too and 1 more
|
|
462
640
|
>
|
|
463
|
-
> **[
|
|
641
|
+
> **[The screen read →](docs/en/interface.md#simple-vs-developer)**
|
|
464
642
|
|
|
465
643
|
---
|
|
466
644
|
|
|
467
|
-
##
|
|
645
|
+
## Tools
|
|
468
646
|
|
|
469
|
-
|
|
647
|
+
Names and arguments match Claude Code, so skills written for that convention work unchanged.
|
|
470
648
|
|
|
471
|
-
|
|
|
649
|
+
| Tool | What it does |
|
|
472
650
|
|---|---|
|
|
473
|
-
| `Read` |
|
|
474
|
-
| `Write` |
|
|
475
|
-
| `Append` |
|
|
476
|
-
| `Edit` |
|
|
477
|
-
| `Move` |
|
|
478
|
-
| `Glob` |
|
|
479
|
-
| `Grep` |
|
|
480
|
-
| `Bash` |
|
|
481
|
-
| `Skill` |
|
|
482
|
-
| `WebFetch` |
|
|
483
|
-
| `Ask` |
|
|
484
|
-
| `Recall` |
|
|
485
|
-
| `Remember` |
|
|
486
|
-
| `TodoWrite` |
|
|
487
|
-
| `Outline` |
|
|
488
|
-
| `Verify` |
|
|
489
|
-
| `Task` |
|
|
490
|
-
| `Jobs` |
|
|
491
|
-
| `Def` |
|
|
492
|
-
| `Refs` |
|
|
493
|
-
|
|
494
|
-
|
|
495
|
-
`
|
|
496
|
-
|
|
497
|
-
|
|
498
|
-
|
|
499
|
-
|
|
500
|
-
> **자세히** — Outline · Verify · Task · Def · Refs · 끝나지 않는 명령은 뒤에서 외 9개
|
|
651
|
+
| `Read` | Read a file (line numbers, `offset`/`limit`, **Excel as CSV, hwpx/docx/pptx and PDF as text**) |
|
|
652
|
+
| `Write` | Write / overwrite a file (**several at once via the `files` array**) |
|
|
653
|
+
| `Append` | Append to the end of a file — **how large files get written in pieces** |
|
|
654
|
+
| `Edit` | Replace an exact string (`replace_all`; **several sites at once via the `edits` array**) |
|
|
655
|
+
| `Move` | Move / rename files and folders — **how you restructure** (`moves` array; covered by undo) |
|
|
656
|
+
| `Glob` | Find files by name pattern |
|
|
657
|
+
| `Grep` | Regex search file contents |
|
|
658
|
+
| `Bash` | Run a command (**`background: true` for anything that does not finish**) |
|
|
659
|
+
| `Skill` | Expand a skill body (shown to the model only when skills exist) |
|
|
660
|
+
| `WebFetch` | Read a web page (read-only; hidden under `--offline`) |
|
|
661
|
+
| `Ask` | **Ask you back** at a fork — offers the choices, takes a single number |
|
|
662
|
+
| `Recall` | Search **past conversations** — the model digs up "that thing last time" itself |
|
|
663
|
+
| `Remember` | One line that outlives the session — known from the start next time |
|
|
664
|
+
| `TodoWrite` | Checklist — breaks long work into steps and shows progress |
|
|
665
|
+
| `Outline` | See a folder's **skeleton only** — tens of times cheaper than reading it whole |
|
|
666
|
+
| `Verify` | Check that what was built **actually works** |
|
|
667
|
+
| `Task` | Run one chunk of a big job in a **separate context** |
|
|
668
|
+
| `Jobs` | Inspect, read and stop **background commands** — the other half of `Bash`'s `background` |
|
|
669
|
+
| `Def` | **Where a name is defined** — only shown when a language server is installed |
|
|
670
|
+
| `Refs` | **Every place a name is used** — only shown when a language server is installed |
|
|
671
|
+
|
|
672
|
+
Nine tools here are not in Claude Code — `Append`, `Move`, `Ask`, `Recall`, `Remember`,
|
|
673
|
+
`Outline`, `Verify`, `Task`, `Jobs`. Each tool costs 150-400 tokens of schema on **every request**,
|
|
674
|
+
so a test stops you every time the list grows (`test/loop.test.js`). The last four earned
|
|
675
|
+
their cost; here is why.
|
|
676
|
+
|
|
677
|
+
> **More** — Outline · Verify · Task · Def · Refs · Commands that never finish and 9 more
|
|
501
678
|
>
|
|
502
|
-
> **[
|
|
679
|
+
> **[Tools in depth read →](docs/en/tools.md#tools)**
|
|
503
680
|
|
|
504
681
|
---
|
|
505
682
|
|
|
506
|
-
##
|
|
507
|
-
|
|
508
|
-
**CP949 로 저장된 파일은 CP949 로 되돌려 씁니다.** 인코딩을 바꾸지 않습니다.
|
|
509
|
-
엑셀(`.xlsx`)은 CSV 로, 한글·워드·파워포인트(`.hwpx`/`.docx`/`.pptx`)와
|
|
510
|
-
**PDF** 는 글로 바꿔서 읽습니다 — 전부 읽기 전용입니다.
|
|
683
|
+
## Korean text and Excel
|
|
511
684
|
|
|
512
|
-
|
|
513
|
-
|
|
514
|
-
읽히기 때문입니다.
|
|
685
|
+
**A file saved as CP949 is written back as CP949.** The encoding is never changed.
|
|
686
|
+
Excel (`.xlsx`) is read as CSV — read-only.
|
|
515
687
|
|
|
516
|
-
|
|
517
|
-
|
|
518
|
-
|
|
519
|
-
|
|
688
|
+
Old formats (`.ppt`, `.doc`, `.xls`, `.rtf`) are read by **borrowing the LibreOffice already
|
|
689
|
+
on this machine** — the same terms on which deel borrows `rg`, and nothing is ever installed.
|
|
690
|
+
With no converter it **says so definitively and stops**: what is missing, what you can do about
|
|
691
|
+
it, and not to open the file again. Turn it off with `DEEL_CONVERT=off`.
|
|
520
692
|
|
|
521
|
-
>
|
|
693
|
+
> **More** — Encoding · Excel · borrowing a converter
|
|
522
694
|
>
|
|
523
|
-
> **[
|
|
695
|
+
> **[Korean documents and Excel read →](docs/en/documents.md#korean-text-and-excel)**
|
|
524
696
|
|
|
525
697
|
---
|
|
526
698
|
|
|
527
|
-
##
|
|
699
|
+
## Serving what you built
|
|
528
700
|
|
|
529
701
|
```
|
|
530
702
|
❯ /preview
|
|
531
703
|
|
|
532
|
-
▶
|
|
533
|
-
|
|
534
|
-
|
|
535
|
-
|
|
536
|
-
|
|
704
|
+
▶ Serving http://127.0.0.1:56801/
|
|
705
|
+
showing .
|
|
706
|
+
Edit a file and the page reloads by itself.
|
|
707
|
+
Only this machine can open it (127.0.0.1). No other PC can see it.
|
|
708
|
+
Stop with /preview off · it shuts down when deel exits.
|
|
537
709
|
```
|
|
538
710
|
|
|
539
|
-
|
|
711
|
+
A browser opens with it. `/preview <folder>` picks what to serve, `/preview off` stops it.
|
|
540
712
|
|
|
541
|
-
|
|
542
|
-
|
|
543
|
-
|
|
713
|
+
**This is not the same as double-clicking the file (`file://`).** Under `file://` everything
|
|
714
|
+
below is blocked — and the error only shows up in the console while the page stays blank, so
|
|
715
|
+
you end up suspecting your own code. This is a real HTTP server, so it all works:
|
|
544
716
|
|
|
545
717
|
| | `file://` | `/preview` |
|
|
546
718
|
|---|---|---|
|
|
547
|
-
| `<script type="module">` · `import` |
|
|
548
|
-
| `fetch('
|
|
549
|
-
| `new Worker(...)` |
|
|
550
|
-
| `WebAssembly.compileStreaming` |
|
|
551
|
-
|
|
|
552
|
-
| `.glb` / `.gltf` (Three.js) |
|
|
719
|
+
| `<script type="module">` · `import` | blocked (CORS) | **works** |
|
|
720
|
+
| `fetch('./data.json')` | blocked | **works** |
|
|
721
|
+
| `new Worker(...)` | blocked | **works** |
|
|
722
|
+
| `WebAssembly.compileStreaming` | blocked (MIME) | **works** |
|
|
723
|
+
| textures · `getImageData` | tainted canvas | **works** |
|
|
724
|
+
| `.glb` / `.gltf` (Three.js) | no MIME type → silently not drawn | **works** |
|
|
553
725
|
|
|
554
|
-
|
|
726
|
+
All seven were run in a real Chrome and confirmed **7/7**.
|
|
555
727
|
|
|
556
|
-
|
|
557
|
-
|
|
558
|
-
|
|
728
|
+
Apps with a router (React Router and friends) get the first page back when you reload on a
|
|
729
|
+
deep link. Never for requests with an extension (`app.js`) though — returning HTML for a
|
|
730
|
+
missing script dies with `Unexpected token '<'`, which hides the real cause (a typo in a filename).
|
|
559
731
|
|
|
560
|
-
###
|
|
732
|
+
### It opens exactly as much as it says
|
|
561
733
|
|
|
562
|
-
|
|
734
|
+
Starting a server means opening your disk to somebody else.
|
|
563
735
|
|
|
564
|
-
- **`127.0.0.1`
|
|
565
|
-
|
|
566
|
-
-
|
|
567
|
-
-
|
|
568
|
-
|
|
569
|
-
-
|
|
570
|
-
- `deel`
|
|
736
|
+
- Bound to **`127.0.0.1` only**. `0.0.0.0` is not available at all — on an office network
|
|
737
|
+
that would let anyone read your source.
|
|
738
|
+
- Port **0** (the kernel hands out a free one). A fixed port steals someone else's.
|
|
739
|
+
- Paths cannot leave the working scope. `../` · `%2e%2e` · double encoding · absolute paths ·
|
|
740
|
+
null bytes · symlinks — eight of these are held shut by tests.
|
|
741
|
+
- **It only serves.** `POST` · `PUT` · `DELETE` are refused with 405.
|
|
742
|
+
- It shuts down when `deel` exits.
|
|
571
743
|
|
|
572
|
-
|
|
573
|
-
|
|
574
|
-
**남의 스킬은 품고 다니지 않습니다.** 켜질 때 그 PC 를 훑어 있는 것을 그대로 씁니다.
|
|
575
|
-
|
|
576
|
-
**다만 일하는 방법 일곱 가지는 품고 다닙니다.** 사내에서 새로 받은 PC 에는
|
|
577
|
-
`~/.claude/skills` 도 플러그인도 없습니다. 거기서는 방법론이 0개라 모델이 매번
|
|
578
|
-
제 나름대로 했고, 시킨 것만 겨우 하고 끝나는 얄팍한 결과가 거기서 나왔습니다.
|
|
744
|
+
---
|
|
579
745
|
|
|
580
|
-
|
|
581
|
-
|---|---|
|
|
582
|
-
| `깊이있게-만들기` | 고도화·보고용·선포용 — 최소치만 내고 끝내지 않게 |
|
|
583
|
-
| `끝까지-하기` | 시킨 것이 여러 조각일 때. 빼먹은 것은 말하게 |
|
|
584
|
-
| `차근차근-디버깅` | 재현 → 좁히기 → 원인 → 고치기 → 증명 |
|
|
585
|
-
| `검사-먼저` | 고치기 전에 실패하는 검사부터 |
|
|
586
|
-
| `찔러보기` | 되는지 모를 때 시간 정해 작게 찔러 보고 버리기 |
|
|
587
|
-
| `코드-줄이기` | 동작은 그대로 두고 읽기 쉽게 |
|
|
588
|
-
| `스스로-검토` | 다 됐다고 말하기 전에. 못 잰 것까지 말하게 |
|
|
746
|
+
## Skills and plugins
|
|
589
747
|
|
|
590
|
-
|
|
591
|
-
|
|
748
|
+
**deel does not carry skills with it.** On startup it scans the machine it is running on and uses
|
|
749
|
+
whatever is there. On a clean PC: zero. On a PC with skills installed: those skills.
|
|
592
750
|
|
|
593
751
|
```
|
|
594
|
-
|
|
595
|
-
|
|
596
|
-
|
|
597
|
-
플러그인 ~/.claude/plugins/** ~/.deel/plugins/**
|
|
752
|
+
project ./.deel/skills ./.claude/skills ./.deel/commands ./.claude/commands
|
|
753
|
+
user ~/.deel/skills ~/.claude/skills ~/.claude/commands
|
|
754
|
+
plugins ~/.claude/plugins/** ~/.deel/plugins/**
|
|
598
755
|
```
|
|
599
756
|
|
|
600
|
-
Claude Code
|
|
757
|
+
Reads the Claude Code format: `SKILL.md` with YAML front matter, `commands/*.md`, `$ARGUMENTS`.
|
|
601
758
|
|
|
602
|
-
>
|
|
759
|
+
> **More** — Loaded in three stages · Fetching plugins · Deliberately not included
|
|
603
760
|
>
|
|
604
|
-
> **[
|
|
761
|
+
> **[Extending read →](docs/en/extend.md#skills-and-plugins)**
|
|
605
762
|
|
|
606
763
|
---
|
|
607
764
|
|
|
608
|
-
|
|
765
|
+
### The hidden latency of local models — keeping the prefix cache alive
|
|
766
|
+
|
|
767
|
+
Ollama and llama.cpp reuse computation **only while the request starts the same way as the
|
|
768
|
+
last one.** Change one early character and everything after it — the entire conversation —
|
|
769
|
+
is recomputed. This is the usual hidden reason long local sessions feel slower and slower,
|
|
770
|
+
and it never shows up anywhere, because it is not an error.
|
|
771
|
+
|
|
772
|
+
deel routes every message to the right mode automatically, and that mode instruction used to
|
|
773
|
+
sit **early** in the prompt — every mode switch broke the whole cache. So the stable parts
|
|
774
|
+
(rules, folder, project fingerprint, user rules, memory, skills) are frozen at the front and
|
|
775
|
+
the per-turn parts (mode, pins) go last. A test pins this order down (`test/cache.test.js`).
|
|
776
|
+
|
|
777
|
+
Ollama also gets `keep_alive: 60m` — with the 5-minute default, the model unloads while you
|
|
778
|
+
glance at another window, and the first message after you come back recomputes everything.
|
|
779
|
+
Override with `DEEL_KEEP_ALIVE`. If you run llama.cpp directly, `--cache-reuse 256` on the
|
|
780
|
+
server side does the same job.
|
|
609
781
|
|
|
610
|
-
|
|
611
|
-
전부 세게 두면 느리고, 전부 얕게 두면 엉뚱한 길로 갑니다.
|
|
782
|
+
## Reasoning effort
|
|
612
783
|
|
|
613
|
-
|
|
784
|
+
One answer means several model calls, and **each needs a different amount of thinking.**
|
|
785
|
+
All-high is slow; all-low wanders off.
|
|
786
|
+
|
|
787
|
+
The default is **one line**. What you want to know is how hard it is thinking right now,
|
|
788
|
+
not a stage table.
|
|
614
789
|
|
|
615
790
|
```
|
|
616
791
|
$ /think
|
|
@@ -619,17 +794,17 @@ $ /think
|
|
|
619
794
|
더 세게 /think high 더 빠르게 /think low
|
|
620
795
|
```
|
|
621
796
|
|
|
622
|
-
|
|
|
797
|
+
| Profile | Character |
|
|
623
798
|
|---|---|
|
|
624
|
-
| `even`
|
|
625
|
-
| `save` (
|
|
626
|
-
| `deep`
|
|
799
|
+
| `even` | Same effort everywhere — predictable, slower |
|
|
800
|
+
| `save` (default) | Hard on the first decision only |
|
|
801
|
+
| `deep` | Everything one notch up — for hard work |
|
|
627
802
|
|
|
628
|
-
|
|
629
|
-
|
|
630
|
-
|
|
803
|
+
Set the profile with `/think 배분 절약`. **Level and profile are different axes, so the
|
|
804
|
+
commands were split** — `/think high` and `/think save` used to set different things under
|
|
805
|
+
one name, which made the screen unreadable.
|
|
631
806
|
|
|
632
|
-
|
|
807
|
+
The stage table moved to `/think 자세히` (the default at developer level).
|
|
633
808
|
|
|
634
809
|
```
|
|
635
810
|
$ /think 자세히
|
|
@@ -646,373 +821,412 @@ $ /think 자세히
|
|
|
646
821
|
컨텍스트 40,960 · 지금 찬 양 2,087
|
|
647
822
|
```
|
|
648
823
|
|
|
649
|
-
|
|
650
|
-
|
|
651
|
-
|
|
824
|
+
That second-to-last line exists for a reason: **when all three caps are equal, it is the
|
|
825
|
+
only thing that says whether that is correct.** A low known cap makes them equal, and that
|
|
826
|
+
is fine. For a while all three read `16,384` always — which meant the table said nothing.
|
|
652
827
|
|
|
653
|
-
>
|
|
828
|
+
> **More** — Context length is read off the model · /out · Truncated tool calls
|
|
654
829
|
>
|
|
655
|
-
> **[
|
|
830
|
+
> **[Speed and spend read →](docs/en/tuning.md#reasoning-effort)**
|
|
656
831
|
|
|
657
832
|
---
|
|
658
833
|
|
|
659
|
-
##
|
|
834
|
+
## Auto-compaction
|
|
660
835
|
|
|
661
|
-
|
|
662
|
-
|
|
836
|
+
At 80% context, older turns are **summarised and folded** so work continues.
|
|
837
|
+
Plain truncation makes the model forget: it re-reads files and re-fixes what it already fixed.
|
|
663
838
|
|
|
664
839
|
```
|
|
665
|
-
◱
|
|
840
|
+
◱ Folded 44 turns into a summary — 10,399 → 3,170 tokens (70% smaller)
|
|
666
841
|
```
|
|
667
842
|
|
|
668
|
-
|
|
669
|
-
|
|
670
|
-
|
|
843
|
+
The summary keeps goal / done / learned / decided / remaining. The cut point is chosen so a
|
|
844
|
+
**tool call is never separated from its result** — splitting them makes the server return 400.
|
|
845
|
+
If the summary request fails, it falls back to plain trimming rather than stopping.
|
|
671
846
|
|
|
672
|
-
`/compact`
|
|
847
|
+
`/compact` folds on demand.
|
|
673
848
|
|
|
674
849
|
---
|
|
675
850
|
|
|
676
|
-
##
|
|
851
|
+
## Resuming a conversation
|
|
677
852
|
|
|
678
|
-
|
|
679
|
-
|
|
680
|
-
|
|
853
|
+
Close the terminal by accident, or reboot, and the conversation is still there.
|
|
854
|
+
Messages are written to `.deel/sessions/` **as each one completes**, so a crash
|
|
855
|
+
loses at most the message in flight.
|
|
681
856
|
|
|
682
857
|
```
|
|
683
858
|
$ deel sessions
|
|
684
859
|
|
|
685
|
-
──
|
|
686
|
-
● 20260824-090200
|
|
687
|
-
|
|
688
|
-
· 20260824-084500 2
|
|
689
|
-
src/a.js
|
|
860
|
+
── conversations in this folder ────────────────────────────────
|
|
861
|
+
● 20260824-090200 just now 1 turn devstral-small-2507
|
|
862
|
+
fix the failing test
|
|
863
|
+
· 20260824-084500 2h ago 2 turns qwen2.5-coder:7b
|
|
864
|
+
switch src/a.js logging to the logger
|
|
690
865
|
```
|
|
691
866
|
|
|
692
|
-
|
|
|
867
|
+
| Command | What it does |
|
|
693
868
|
|---|---|
|
|
694
|
-
| `deel --continue` |
|
|
695
|
-
| `deel --resume <id>` |
|
|
696
|
-
| `deel sessions` |
|
|
697
|
-
| `deel sessions --rm <id>` |
|
|
869
|
+
| `deel --continue` | Resume the most recent conversation in this folder |
|
|
870
|
+
| `deel --resume <id>` | Resume a specific one |
|
|
871
|
+
| `deel sessions` | List what is stored |
|
|
872
|
+
| `deel sessions --rm <id>` | Delete one |
|
|
873
|
+
|
|
874
|
+
The format is `jsonl` — one message per line — so a power cut costs only the last line.
|
|
875
|
+
Resumed history keeps tool calls paired with their results, so work continues immediately.
|
|
876
|
+
Conversations older than 30 days and outside the most recent 30 are pruned automatically.
|
|
877
|
+
|
|
878
|
+
Everything lives in `.deel/sessions/` inside the working folder, and `.gitignore`
|
|
879
|
+
covers `.deel/` so it never reaches a repository.
|
|
880
|
+
|
|
881
|
+
---
|
|
882
|
+
|
|
883
|
+
## Starting over (`deel reset`)
|
|
698
884
|
|
|
699
|
-
|
|
700
|
-
|
|
701
|
-
|
|
885
|
+
Switching gateways, learned facts that went stale, handing the machine to someone else —
|
|
886
|
+
sometimes you want to go back to the beginning. Reinstalling does not do it: `~/.deel`
|
|
887
|
+
survives an install. Hence a command of its own.
|
|
702
888
|
|
|
703
|
-
|
|
704
|
-
|
|
889
|
+
```
|
|
890
|
+
$ deel reset
|
|
891
|
+
|
|
892
|
+
── what can be wiped ──────────────────────────────────────────
|
|
893
|
+
home C:\Users\me\.deel
|
|
894
|
+
working folder C:\work\myproject
|
|
895
|
+
|
|
896
|
+
connections 2
|
|
897
|
+
memory 8 lines
|
|
898
|
+
conversations 14
|
|
899
|
+
learned 2 places
|
|
900
|
+
evidence, exports, temp 6
|
|
901
|
+
plugins 3
|
|
902
|
+
sealed key DPAPI — this PC, this account only
|
|
903
|
+
|
|
904
|
+
── what is kept ───────────────────────────────────────────────
|
|
905
|
+
undo snapshots 41 needs all --hard
|
|
906
|
+
audit log 1,203 lines needs all --hard
|
|
907
|
+
written by you .deel/mcp.json · .deelignore
|
|
908
|
+
never touched, by any route.
|
|
909
|
+
```
|
|
910
|
+
|
|
911
|
+
**Bare `deel reset` wipes nothing.** It shows what exists and asks.
|
|
912
|
+
|
|
913
|
+
| Command | What goes |
|
|
914
|
+
|---|---|
|
|
915
|
+
| `deel reset model` | connections and profiles, plus the key in the OS keystore |
|
|
916
|
+
| `deel reset memory` | memory (`.deel/memory.md`) |
|
|
917
|
+
| `deel reset sessions` | conversation history |
|
|
918
|
+
| `deel reset learned` | learned facts (this PC + this folder) |
|
|
919
|
+
| `deel reset plugins` | installed plugins |
|
|
920
|
+
| `deel reset all` | everything above **except plugins** |
|
|
921
|
+
| `deel reset all --hard` | plus undo snapshots and the audit log |
|
|
922
|
+
| `--yes` | skip the question (scripts, first-time provisioning) |
|
|
923
|
+
|
|
924
|
+
What it does **not** touch matters more.
|
|
925
|
+
|
|
926
|
+
| Kept | Why |
|
|
927
|
+
|---|---|
|
|
928
|
+
| `.deel/history/` (undo snapshots) | This is the safety net offered in place of an approval prompt. `--hard` only |
|
|
929
|
+
| `.deel/audit.jsonl` | The evidence for an internal review. `--hard` only |
|
|
930
|
+
| `.deel/mcp.json` · `.deelignore` · `DEEL.md` | You wrote these by hand. **Never touched, by any route** |
|
|
931
|
+
| Everything else in the working folder | Nothing outside `.deel` and the home folder is ever reached |
|
|
932
|
+
|
|
933
|
+
It runs on a broken config. That is usually *why* someone reaches for a reset, so
|
|
934
|
+
`deel reset` starts without reading the connection — the same reason `deel --version` answers
|
|
935
|
+
without one. Plugins take time to fetch again, so they stay out of `all`; ask for them by name.
|
|
705
936
|
|
|
706
937
|
---
|
|
707
938
|
|
|
708
|
-
##
|
|
939
|
+
## Attaching tools from outside (MCP)
|
|
709
940
|
|
|
710
|
-
|
|
711
|
-
deel
|
|
941
|
+
A corporate wiki search, an issue tracker, a DB query tool — if a team publishes one as an MCP
|
|
942
|
+
server, deel uses it as a tool **without a code change**.
|
|
712
943
|
|
|
713
|
-
`.deel/mcp.json
|
|
944
|
+
Configure in `.deel/mcp.json`. A Claude Code config can be copied over verbatim:
|
|
714
945
|
|
|
715
946
|
```json
|
|
716
|
-
{ "mcpServers": { "
|
|
947
|
+
{ "mcpServers": { "wiki": { "command": "node", "args": ["wiki-mcp.js"] } } }
|
|
717
948
|
```
|
|
718
949
|
|
|
719
|
-
|
|
950
|
+
The model sees it as `mcp__wiki__search`. `/mcp` shows what is attached.
|
|
720
951
|
|
|
721
|
-
|
|
722
|
-
|
|
723
|
-
필요 없습니다.
|
|
952
|
+
**Dependencies stay at zero.** The stdio transport is nothing but newline-delimited JSON-RPC
|
|
953
|
+
2.0 over a child process's stdin/stdout, so `child_process` and `JSON` cover it. No SDK.
|
|
724
954
|
|
|
725
|
-
>
|
|
955
|
+
> **More** — But this is somebody else's program
|
|
726
956
|
>
|
|
727
|
-
> **[
|
|
957
|
+
> **[Extending read →](docs/en/extend.md#attaching-tools-from-outside-mcp)**
|
|
728
958
|
|
|
729
959
|
---
|
|
730
960
|
|
|
731
|
-
##
|
|
961
|
+
## Inside your editor (ACP)
|
|
732
962
|
|
|
733
|
-
|
|
734
|
-
IDE
|
|
735
|
-
JetBrains
|
|
963
|
+
A tool that makes you open one more terminal window stops being used after about two weeks.
|
|
964
|
+
Developers live inside the IDE. So deel speaks **ACP** (Agent Client Protocol) — Zed,
|
|
965
|
+
JetBrains, Neovim and Emacs attach to it **without changing a line on their side**.
|
|
736
966
|
|
|
737
|
-
|
|
967
|
+
One command in your editor's settings:
|
|
738
968
|
|
|
739
969
|
```
|
|
740
970
|
deel acp
|
|
741
971
|
```
|
|
742
972
|
|
|
743
|
-
|
|
744
|
-
|
|
973
|
+
The editor spawns that as a child process and exchanges newline-delimited JSON-RPC 2.0 over
|
|
974
|
+
stdio. It is not a command you type yourself.
|
|
745
975
|
|
|
746
|
-
|
|
976
|
+
**What you get once it is attached:**
|
|
747
977
|
|
|
748
|
-
|
|
|
978
|
+
| In the editor | From deel |
|
|
749
979
|
|---|---|
|
|
750
|
-
|
|
|
751
|
-
|
|
|
752
|
-
|
|
|
753
|
-
|
|
|
754
|
-
|
|
|
755
|
-
|
|
|
756
|
-
|
|
|
757
|
-
|
|
758
|
-
|
|
759
|
-
|
|
760
|
-
|
|
761
|
-
>
|
|
980
|
+
| Streaming reply pane | The model's text and its reasoning |
|
|
981
|
+
| Tool list with icons and status | `Read` is a read, `Edit` is an edit, `Bash` is an execution — **the kind is sent**, not just a name |
|
|
982
|
+
| Clickable file links | The **absolute path** of every file touched |
|
|
983
|
+
| Approval dialog | deel's safety rails, rendered as the editor's own prompt (`allow once` · `always allow` · `reject`) |
|
|
984
|
+
| Mode picker | deel's seven work modes (auto · code · plan · architect · debug · ask · orchestrator) |
|
|
985
|
+
| Stop button | Reaches the turn mid-flight, even while waiting on the model |
|
|
986
|
+
| Past conversations | Still there after a restart. They live in the **same place** as the terminal's, so a session started in the editor can be picked up with `deel --resume` |
|
|
987
|
+
|
|
988
|
+
**Still zero dependencies.** Same reason as MCP — newline-delimited JSON-RPC 2.0 is the whole
|
|
989
|
+
transport, so no SDK is needed.
|
|
990
|
+
|
|
991
|
+
> **More** — Details — the places this breaks silently
|
|
762
992
|
>
|
|
763
|
-
> **[
|
|
993
|
+
> **[Extending read →](docs/en/extend.md#inside-your-editor-acp)**
|
|
764
994
|
|
|
765
995
|
---
|
|
766
996
|
|
|
767
|
-
##
|
|
997
|
+
## Keeping secrets out of the conversation
|
|
768
998
|
|
|
769
|
-
|
|
999
|
+
People rarely paste a key. The leak is almost always **command output**.
|
|
770
1000
|
|
|
771
1001
|
```
|
|
772
1002
|
env OPENAI_API_KEY=sk-proj-…
|
|
773
|
-
git remote -v https
|
|
1003
|
+
git remote -v https://user:token@github.com/…
|
|
774
1004
|
curl -v > Authorization: Bearer eyJ…
|
|
775
|
-
|
|
1005
|
+
a failing test log the whole connection string
|
|
776
1006
|
```
|
|
777
1007
|
|
|
778
|
-
|
|
779
|
-
|
|
780
|
-
|
|
1008
|
+
That text goes to the model **and** gets written to `.deel/sessions/*.jsonl` on disk. That
|
|
1009
|
+
file is later re-read by `/recall` and can end up inside a `deel pack` bundle. Leak once and
|
|
1010
|
+
you have several copies.
|
|
781
1011
|
|
|
782
|
-
|
|
1012
|
+
So it is masked at the single point where tool output enters the conversation.
|
|
783
1013
|
|
|
784
1014
|
```
|
|
785
|
-
⏺ Bash(env | grep API)
|
|
786
|
-
⊘
|
|
1015
|
+
⏺ Bash(env | grep API) done
|
|
1016
|
+
⊘ 2 secret-looking values entered the conversation (openai · env var) — masked before the model
|
|
787
1017
|
```
|
|
788
1018
|
|
|
789
|
-
|
|
790
|
-
AWS
|
|
791
|
-
|
|
792
|
-
|
|
1019
|
+
What it looks for: private-key blocks · OpenAI/Anthropic keys · GitHub tokens · Slack tokens ·
|
|
1020
|
+
AWS keys · Google keys · JWTs · credentials embedded in URLs · `Authorization`-family headers ·
|
|
1021
|
+
env vars named `…KEY` / `…TOKEN` / `…SECRET` / `…PASSWORD`. Plus **the configured gateway key
|
|
1022
|
+
regardless of its shape** — that one is not a guess, it is a known value.
|
|
793
1023
|
|
|
794
|
-
###
|
|
1024
|
+
### File contents are deliberately not masked
|
|
795
1025
|
|
|
796
|
-
|
|
797
|
-
|
|
798
|
-
|
|
799
|
-
지우는 셈입니다.**
|
|
1026
|
+
`.env` is exactly where masking feels most tempting, and exactly where it backfires: the model
|
|
1027
|
+
sees the masked text, edits it, writes it back — and `«가림»` lands where the real key was.
|
|
1028
|
+
**Protecting the secret would destroy it.**
|
|
800
1029
|
|
|
801
|
-
|
|
1030
|
+
So on the file side it reports instead of rewriting.
|
|
802
1031
|
|
|
803
1032
|
```
|
|
804
|
-
⏺ Read(.env) 12
|
|
805
|
-
!
|
|
806
|
-
—
|
|
1033
|
+
⏺ Read(.env) 12 lines
|
|
1034
|
+
! 3 secret-looking values entered the conversation (env var)
|
|
1035
|
+
— file contents are not masked (masking them would erase the key on write-back)
|
|
807
1036
|
```
|
|
808
1037
|
|
|
809
|
-
|
|
810
|
-
|
|
1038
|
+
Saying plainly what cannot be stopped beats claiming it was stopped while corrupting the file.
|
|
1039
|
+
Either way it lands in the audit log.
|
|
811
1040
|
|
|
812
1041
|
---
|
|
813
1042
|
|
|
814
|
-
##
|
|
1043
|
+
## Safety
|
|
815
1044
|
|
|
816
|
-
|
|
1045
|
+
Instead of approval prompts, the design makes things **reversible**. The default `auto` mode
|
|
1046
|
+
does not ask.
|
|
817
1047
|
|
|
818
|
-
|
|
|
1048
|
+
| Mechanism | Detail |
|
|
819
1049
|
|---|---|
|
|
820
|
-
|
|
|
821
|
-
|
|
|
822
|
-
|
|
|
823
|
-
|
|
|
824
|
-
|
|
|
825
|
-
|
|
|
826
|
-
|
|
|
827
|
-
|
|
|
828
|
-
|
|
|
829
|
-
|
|
830
|
-
|
|
|
1050
|
+
| **Undo** | Snapshot before every write. `/undo` restores per turn. **Includes moves and deletes done through `Bash`** |
|
|
1051
|
+
| **Change display** | The changed lines are shown on every edit; `/diff` for the whole session |
|
|
1052
|
+
| **Scope** | Outside the starting folder is refused, even if the model insists |
|
|
1053
|
+
| **Blocked commands** | Only irreversible ones (disk format, recursive delete, `--force` push) |
|
|
1054
|
+
| **No re-run** | A mutating command is never retried after failure |
|
|
1055
|
+
| **Interrupt** | Ctrl+C stops mid-answer and leaves the conversation valid |
|
|
1056
|
+
| **Spin guard** | Three identical failures stop the turn, with the reason |
|
|
1057
|
+
| **Not read** | Other tools' private stores, and deel's own logs and config (the key), are refused |
|
|
1058
|
+
| **Audit log** | Everything recorded in `.deel/audit.jsonl` |
|
|
1059
|
+
|
|
1060
|
+
| Mode | Asks when |
|
|
831
1061
|
|---|---|
|
|
832
|
-
| `auto` (
|
|
833
|
-
| `confirm` |
|
|
834
|
-
| `strict` |
|
|
1062
|
+
| `auto` (default) | Never — undo is the safety net |
|
|
1063
|
+
| `confirm` | Irreversible commands only |
|
|
1064
|
+
| `strict` | All file changes and commands |
|
|
835
1065
|
|
|
836
|
-
|
|
837
|
-
|
|
838
|
-
|
|
1066
|
+
Undo history stores whole file contents, so repeated edits to large files add up. Past 32MB
|
|
1067
|
+
it keeps the **most recent 50 turns** and drops the rest. What you just did is always
|
|
1068
|
+
undoable; `/status` shows how large the history currently is.
|
|
839
1069
|
|
|
840
|
-
>
|
|
1070
|
+
> **More** — Files removed through Bash come back too · What it will not read
|
|
841
1071
|
>
|
|
842
|
-
> **[
|
|
1072
|
+
> **[Safety and corporate review read →](docs/en/safety.md#safety)**
|
|
843
1073
|
|
|
844
1074
|
---
|
|
845
1075
|
|
|
846
|
-
##
|
|
847
|
-
|
|
848
|
-
심사서와 소스를 zip 하나로 묶습니다.
|
|
1076
|
+
## Corporate review package
|
|
849
1077
|
|
|
850
1078
|
```bash
|
|
851
|
-
deel pack --out deel
|
|
1079
|
+
deel pack --out deel-import.zip
|
|
852
1080
|
```
|
|
853
1081
|
|
|
854
1082
|
```
|
|
855
|
-
|
|
856
|
-
|
|
857
|
-
|
|
858
|
-
|
|
859
|
-
|
|
860
|
-
|
|
861
|
-
|
|
862
|
-
|
|
863
|
-
포트 열기 1곳 (/preview 만)
|
|
1083
|
+
✓ deel-import.zip
|
|
1084
|
+
94 files · 509.6KB
|
|
1085
|
+
|
|
1086
|
+
Dependencies 0
|
|
1087
|
+
Install scripts none
|
|
1088
|
+
External imports 0
|
|
1089
|
+
Network calls 3 sites (configured address only)
|
|
1090
|
+
Ports opened 1 site (/preview only)
|
|
864
1091
|
```
|
|
865
1092
|
|
|
866
|
-
zip
|
|
867
|
-
|
|
868
|
-
|
|
1093
|
+
The zip carries **one document for people and two for machines.** A corporate review is
|
|
1094
|
+
not a human-only process — security feeds an SBOM to a scanner, and operations reads the
|
|
1095
|
+
audit-log spec to write SIEM ingestion rules.
|
|
869
1096
|
|
|
870
|
-
|
|
|
1097
|
+
| File | What |
|
|
871
1098
|
|---|---|
|
|
872
|
-
| `반입심사서.txt` |
|
|
873
|
-
| `sbom.cdx.json` | **SBOM (CycloneDX 1.5).**
|
|
874
|
-
| `심사명세.json` |
|
|
1099
|
+
| `반입심사서.txt` | Dependencies · install scripts · **every network and process-spawn call site found by scanning the source** (file:line) · the three outbound lanes · SHA-256 per file |
|
|
1100
|
+
| `sbom.cdx.json` | **SBOM (CycloneDX 1.5).** Feed it straight to a scanner. One component per file with SHA-256; dependencies stated as an **explicit empty array** — "not declared" and "none" are different claims |
|
|
1101
|
+
| `심사명세.json` | Egress list (per lane: when, where, what, how it's stopped, and the source location) · **audit-log spec** (field names and meanings, plus what is never recorded) · file hashes |
|
|
875
1102
|
|
|
876
1103
|
```bash
|
|
877
|
-
deel audit #
|
|
878
|
-
deel sbom #
|
|
879
|
-
deel sbom --out
|
|
880
|
-
deel sbom --only sbom #
|
|
1104
|
+
deel audit # the human-readable sheet only
|
|
1105
|
+
deel sbom # the two machine-readable ones, on stdout (deel sbom | jq)
|
|
1106
|
+
deel sbom --out review.json # to a file
|
|
1107
|
+
deel sbom --only sbom # just the SBOM
|
|
881
1108
|
```
|
|
882
1109
|
|
|
883
|
-
|
|
884
|
-
|
|
885
|
-
|
|
886
|
-
|
|
1110
|
+
All three are generated by scanning the source, never written by hand — hand-written sheets
|
|
1111
|
+
drift, and **a review document that drifts is worse than none.** Find one wrong line and the
|
|
1112
|
+
reviewer stops trusting the rest. The audit-log spec is the one hand-written part, so a test
|
|
1113
|
+
checks it against real log records on every run.
|
|
887
1114
|
|
|
888
|
-
>
|
|
1115
|
+
> **More** — Diagnosing a corporate gateway
|
|
889
1116
|
>
|
|
890
|
-
> **[
|
|
1117
|
+
> **[Safety and corporate review read →](docs/en/safety.md#corporate-review-package)**
|
|
891
1118
|
|
|
892
1119
|
---
|
|
893
1120
|
|
|
894
|
-
##
|
|
1121
|
+
## Configuration
|
|
895
1122
|
|
|
896
|
-
`~/.deel/config.json
|
|
1123
|
+
Stored in `~/.deel/config.json`. A `.deel/config.json` in the project folder takes precedence.
|
|
897
1124
|
|
|
898
|
-
>
|
|
1125
|
+
> **More** — Supported servers · Environment variables · Flags · Project rules
|
|
899
1126
|
>
|
|
900
|
-
> **[
|
|
1127
|
+
> **[Configuration read →](docs/en/config.md#configuration)**
|
|
901
1128
|
|
|
902
1129
|
---
|
|
903
1130
|
|
|
904
|
-
##
|
|
1131
|
+
## Troubleshooting
|
|
905
1132
|
|
|
906
|
-
|
|
|
1133
|
+
| Symptom | Check |
|
|
907
1134
|
|---|---|
|
|
908
|
-
|
|
|
909
|
-
|
|
|
910
|
-
|
|
|
911
|
-
|
|
|
912
|
-
|
|
|
913
|
-
| 401 / 403 |
|
|
914
|
-
|
|
|
915
|
-
|
|
|
916
|
-
|
|
|
917
|
-
|
|
|
918
|
-
| `HTTP 400`
|
|
919
|
-
| `429` · `503`
|
|
920
|
-
| `deel scan`
|
|
1135
|
+
| `address not found` | Typo, DNS, VPN / intranet connectivity |
|
|
1136
|
+
| `connection refused` | Server is down or the port differs |
|
|
1137
|
+
| certificate error | `set NODE_EXTRA_CA_CERTS=C:\path\corp-ca.pem` |
|
|
1138
|
+
| behind a proxy | `set HTTPS_PROXY=http://proxy:port` (with auth: `http://user:pw@proxy:port`). If the first screen and `/status` show `proxy …`, it is in use. Exclude hosts with `NO_PROXY=.corp.com,10.1.2.3`; turn it off entirely with `"proxy": "none"` in the config |
|
|
1139
|
+
| the proxy answers 407 | Put `user:pw@` into the proxy address. Proxies that only accept NTLM · Negotiate are not supported — ask the admin for Basic or an unauthenticated address |
|
|
1140
|
+
| 401 / 403 | Wrong key or auth header style (four are tried automatically) |
|
|
1141
|
+
| `address not permitted` | The lock did its job — pick a connection with `/model` |
|
|
1142
|
+
| Tool calls don't work | Run `deel diagnose`. Small models (1B–3B) often can't |
|
|
1143
|
+
| Empty replies | The server ignores streaming. deel retries once, then turns streaming off for the session |
|
|
1144
|
+
| Large files cut off mid-write | Check `/out` and raise it — the cap may be sitting at the 16,384 default because it could not be discovered |
|
|
1145
|
+
| Only `HTTP 400` shows | The server's own message is shown verbatim. If it is a length problem the number is read and applied automatically |
|
|
1146
|
+
| `429` · `503` shows | The gateway pushed back for a moment. deel waits and calls again, up to three times (honouring `Retry-After`). If it keeps happening, check your quota |
|
|
1147
|
+
| `deel scan` finds nothing | Server is off or on another port — use `--ports` |
|
|
921
1148
|
|
|
922
1149
|
---
|
|
923
1150
|
|
|
924
|
-
##
|
|
1151
|
+
## Development
|
|
925
1152
|
|
|
926
1153
|
```bash
|
|
927
|
-
npm test
|
|
928
|
-
npm run coverage
|
|
929
|
-
npm run verify
|
|
930
|
-
npm run bench
|
|
931
|
-
npm run demo
|
|
932
|
-
npm run check
|
|
1154
|
+
npm test Full suite (~5,890 checks; a few are TTY-dependent)
|
|
1155
|
+
npm run coverage Which lines the tests actually execute
|
|
1156
|
+
npm run verify Import + network checks only
|
|
1157
|
+
npm run bench Edit success rate
|
|
1158
|
+
npm run demo See what the UI actually looks like
|
|
1159
|
+
npm run check Syntax check every file
|
|
933
1160
|
```
|
|
934
1161
|
|
|
935
|
-
|
|
936
|
-
|
|
937
|
-
|
|
938
|
-
|
|
939
|
-
`npm test` 는 파일을 하나씩 돌리고 **파일별 종료코드**를 표로 남깁니다.
|
|
940
|
-
화면의 통과 표시가 아니라 종료코드가 CI 가 보는 값이기 때문입니다. 둘은
|
|
941
|
-
갈라질 수 있습니다 — 검사를 다 통과하고도 끝낼 때 죽으면 화면은 초록인데
|
|
942
|
-
종료코드는 1 입니다. 실제로 윈도우에서 그렇게 한 번 놓쳤습니다.
|
|
943
|
-
첫 실패에서 멈추지 않고 끝까지 돌기 때문에, 한 번 돌리면 전부 알 수 있습니다.
|
|
1162
|
+
Tests run against a **fake gateway**, so the loop, streaming, tool execution, undo and compaction
|
|
1163
|
+
are verified deterministically without any model. ZIP output is cross-checked with the real
|
|
1164
|
+
`unzip`; the TAR reader is fed archives produced by the real `tar`.
|
|
944
1165
|
|
|
945
|
-
|
|
946
|
-
|
|
947
|
-
|
|
948
|
-
|
|
949
|
-
|
|
950
|
-
✗ scan.test.js 1 19 0 0.2초
|
|
951
|
-
────────────────────────────────────────────────────────────
|
|
952
|
-
|
|
953
|
-
✗ scan.test.js — 종료코드 1
|
|
954
|
-
검사는 전부 통과했는데 종료코드만 1 입니다 —
|
|
955
|
-
끝낼 때 남은 핸들·처리 안 된 거절 때문입니다.
|
|
956
|
-
```
|
|
1166
|
+
`npm test` runs each file separately and reports **per-file exit codes**, because the exit code
|
|
1167
|
+
— not the pass marks on screen — is what CI reads, and the two can disagree: a file can pass
|
|
1168
|
+
every check and still die on the way out, leaving the screen green and the exit code 1. That
|
|
1169
|
+
happened once on Windows and cost a lot of time. The runner does not stop at the first failure,
|
|
1170
|
+
so one run tells you everything.
|
|
957
1171
|
|
|
958
|
-
|
|
|
1172
|
+
| Suite | Checks | Covers |
|
|
959
1173
|
|---|---|---|
|
|
960
|
-
| `smoke` | 20 |
|
|
961
|
-
| `loop` | 16 |
|
|
962
|
-
| `guard` | 24 |
|
|
963
|
-
| `network` | 30 |
|
|
964
|
-
| `web` | 25 |
|
|
965
|
-
| `abort` · `steer` | 16 · 15 | Ctrl+C
|
|
966
|
-
| `parallel` | 23 |
|
|
967
|
-
| `cli` | 75 |
|
|
968
|
-
| `setup` | 42 |
|
|
969
|
-
| `detect` | 66 |
|
|
970
|
-
| `modes` · `route` | 89 · 33 |
|
|
971
|
-
| `ctxsize` | 43 |
|
|
972
|
-
| `commands` · `commands-more` | 128 · 62 |
|
|
973
|
-
| `ui` · `ui2` | 60 · 40 |
|
|
974
|
-
| `encoding` · `xlsx` | 68 · 72 |
|
|
975
|
-
| `compact` | 21 |
|
|
976
|
-
| `store` | 34 |
|
|
977
|
-
| `scan` | 29 |
|
|
978
|
-
| `plugins` | 38 |
|
|
979
|
-
| `no-bundle` | 12 |
|
|
980
|
-
| `edit-bench` | 20
|
|
981
|
-
|
|
982
|
-
>
|
|
1174
|
+
| `smoke` | 20 | Tools, scope, undo, audit log |
|
|
1175
|
+
| `loop` | 16 | Agent loop, streaming, tool calls |
|
|
1176
|
+
| `guard` | 24 | **What it refuses to do** — denied edits, unknown tools, repeated mutations, out-of-scope writes |
|
|
1177
|
+
| `network` | 30 | Nothing escapes the configured address |
|
|
1178
|
+
| `web` | 25 | Web reads stay read-only |
|
|
1179
|
+
| `abort` · `steer` | 16 · 15 | Ctrl+C leaves the conversation valid · a line typed mid-turn rides the next call |
|
|
1180
|
+
| `parallel` | 23 | Read-only tools run together; checklists |
|
|
1181
|
+
| `cli` | 75 | **Spawns the real `deel`** and drives it to completion |
|
|
1182
|
+
| `setup` | 42 | First-run wizard, driven through a fake TTY |
|
|
1183
|
+
| `detect` | 66 | Identifying shape and auth from one address |
|
|
1184
|
+
| `modes` · `route` | 89 · 33 | Work modes; auto-switching from Auto |
|
|
1185
|
+
| `ctxsize` | 43 | Reading context length off the model |
|
|
1186
|
+
| `commands` · `commands-more` | 128 · 62 | Every slash command |
|
|
1187
|
+
| `ui` · `ui2` | 60 · 40 | Password masking, CJK width, status line, session list, Excel→text |
|
|
1188
|
+
| `encoding` · `xlsx` | 68 · 72 | Legacy-encoding detection; Excel reading |
|
|
1189
|
+
| `compact` | 21 | Summary folding, pairing intact, graceful fallback |
|
|
1190
|
+
| `store` | 34 | Session persistence, resume, crash recovery |
|
|
1191
|
+
| `scan` | 29 | Distinguishing multiple runtimes |
|
|
1192
|
+
| `plugins` | 38 | Plugin fetch/pack, ZIP/TAR |
|
|
1193
|
+
| `no-bundle` | 12 | Nothing foreign in the published package; test-file hygiene |
|
|
1194
|
+
| `edit-bench` | 20 cases | Edit success rate |
|
|
1195
|
+
|
|
1196
|
+
> **More** — Coverage · Layout
|
|
983
1197
|
>
|
|
984
|
-
> **[
|
|
1198
|
+
> **[Development read →](docs/en/develop.md#development)**
|
|
985
1199
|
|
|
986
1200
|
---
|
|
987
1201
|
|
|
988
|
-
##
|
|
1202
|
+
## Release notes
|
|
989
1203
|
|
|
990
|
-
|
|
|
1204
|
+
| Version | What changed |
|
|
991
1205
|
|---|---|
|
|
992
|
-
| **[1.
|
|
993
|
-
|
|
|
994
|
-
|
|
|
995
|
-
| **[1.6.0](docs/
|
|
996
|
-
| **[1.5.8](docs/
|
|
997
|
-
| **[1.5.7](docs/
|
|
998
|
-
| **[1.5.6](docs/
|
|
999
|
-
| **[1.5.5](docs/
|
|
1000
|
-
| [1.5.4](docs/
|
|
1001
|
-
| [1.5.3](docs/
|
|
1002
|
-
| [1.5.2](docs/
|
|
1003
|
-
| [1.5.1](docs/
|
|
1004
|
-
| [1.5.0](docs/
|
|
1005
|
-
| [1.4.3](docs/
|
|
1006
|
-
| [1.4.2](docs/
|
|
1007
|
-
| [1.4.1](docs/
|
|
1008
|
-
| [1.4.0](docs/
|
|
1009
|
-
| [1.3.0](docs/
|
|
1010
|
-
| [1.2.0](docs/
|
|
1011
|
-
|
|
1012
|
-
|
|
1206
|
+
| **[1.8.0](docs/en/releases/1.8.md#180)** | A full day against a gateway that hands out one-hour tokens — fetch the key instead of storing it · `deel reset` · an English screen that is actually English |
|
|
1207
|
+
| [1.7.0](docs/en/releases/1.7.md#170) | Local stays local; it goes out only when you say so — three modes · vendor setup · automatic masking · cost |
|
|
1208
|
+
| [1.6.1](docs/en/releases/1.6.md#161) | The places that made a turn spin in circles — the fence blocking `/dev/null` · old documents it could not read · images vanishing from files |
|
|
1209
|
+
| **[1.6.0](docs/en/releases/1.6.md#160)** | The things that did not work on a corporate network — proxy · 429 · Windows shell · 50k-file repos · PDF · clipboard paste · editor resume |
|
|
1210
|
+
| **[1.5.8](docs/en/releases/1.5.md#158)** | A 5MB document showed 8 lines out of 919 · a regex read as a path blocked the command |
|
|
1211
|
+
| **[1.5.7](docs/en/releases/1.5.md#157)** | Korean folders on macOS made your own files "out of scope" · paste · ESC |
|
|
1212
|
+
| **[1.5.6](docs/en/releases/1.5.md#156)** | It asks when stuck — instead of writing a question and ending the turn |
|
|
1213
|
+
| **[1.5.5](docs/en/releases/1.5.md#155)** | A plan fills the room — "only one person" was a bug, not a design |
|
|
1214
|
+
| [1.5.4](docs/en/releases/1.5.md#154) | A day passes in the room — morning to night, a wall clock, a cold coffee |
|
|
1215
|
+
| [1.5.3](docs/en/releases/1.5.md#153) | Three things a Mac user tripped over — newline hint, office stays put, one `/motion` |
|
|
1216
|
+
| [1.5.2](docs/en/releases/1.5.md#152) | Everything else the adversarial reviews turned up — where the screen was lying |
|
|
1217
|
+
| [1.5.1](docs/en/releases/1.5.md#151) | Two of the things 1.5.0 added shipped broken. This fixes them |
|
|
1218
|
+
| [1.5.0](docs/en/releases/1.5.md#150) | Line breaks exist now, the screen got fun, and it came out lighter than before |
|
|
1219
|
+
| [1.4.3](docs/en/releases/1.4.md#143) | The README explains what's different, and the review report gets its missing line |
|
|
1220
|
+
| [1.4.2](docs/en/releases/1.4.md#142) | 1.4.1 shipped before its own security fixes — this corrects that |
|
|
1221
|
+
| [1.4.1](docs/en/releases/1.4.md#141) | No new features, only what was actually found and fixed — Windows abort, ReDoS, XSS |
|
|
1222
|
+
| [1.4.0](docs/en/releases/1.4.md#140) | deel gets a face, speaks English, and sees meaning — eleven places |
|
|
1223
|
+
| [1.3.0](docs/en/releases/1.3.md#130) | Evidence instead of claims, the editor instead of a terminal — six places |
|
|
1224
|
+
| [1.2.0](docs/en/releases/1.2.md#120) | So the conversation doesn't break — six places |
|
|
1225
|
+
|
|
1226
|
+
What changed and why is in the **[release notes](docs/en/releases.md)**.
|
|
1013
1227
|
|
|
1014
1228
|
---
|
|
1015
1229
|
|
|
1016
|
-
##
|
|
1230
|
+
## Licence
|
|
1017
1231
|
|
|
1018
1232
|
[MIT](LICENSE)
|