@mutagent/cli 0.2.331 → 0.2.333

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.md CHANGED
@@ -65,11 +65,12 @@ mutagent providers mirror
65
65
  # 3. Create an Environment: the variables and secrets a sandbox gets
66
66
  mutagent env set staging GREETING=hello --secrets-from-file .env.secrets
67
67
 
68
- # 4. Run Helix on a task in a cloud sandbox and print its answer
69
- mutagent helix --env staging -p "check the deploy"
68
+ # 4. Run an agent.md folder on a task with the local Helix binary
69
+ mutagent install helix
70
+ mutagent agent run reviewer/agent.md "check the deploy"
70
71
  ```
71
72
 
72
- To run Helix on your own machine instead, install the Helix binary with `mutagent install helix`.
73
+ `mutagent architech` runs the Architech harness on a task in a cloud sandbox.
73
74
 
74
75
  ## Concepts
75
76
 
@@ -77,22 +78,22 @@ To run Helix on your own machine instead, install the Helix binary with `mutagen
77
78
  belong to in its organization. `mutagent workspaces use <name>` selects one, and `--workspace`
78
79
  overrides it for a single command.
79
80
  - **LLM provider (BYOK)**: a model provider key (OpenAI, Anthropic, Google, ...) stored in the
80
- workspace, encrypted. Helix uses it to call models in the cloud. Manage them with
81
+ workspace, encrypted. A cloud run uses it to call models. Manage them with
81
82
  `mutagent providers`.
82
83
  - **Environment**: a named set of variables and secrets an agent's tools need, such as a GitHub
83
84
  token or a database URL. Load one into a run with `--env <name>`. Values are write-only:
84
85
  `mutagent env show` prints names and fingerprints, never a value. LLM provider keys do not
85
86
  belong here.
86
- - **Helix session**: a cloud run of Helix, addressed by a reference (`hs1_...`) that is printed
87
- when the run starts. `mutagent helix session` lists sessions, attaches to them, sends input,
87
+ - **Cloud session**: a cloud run of the Architech harness, addressed by a reference (`hs1_...`)
88
+ that is printed when the run starts. `mutagent architech session` lists sessions, attaches to them, sends input,
88
89
  answers their questions, stops, checkpoints and restores them. A sandbox idle for 15 minutes is
89
90
  stopped, and an interactive session in it is checkpointed first.
90
91
  - **Managed agent**: a folder whose entry file is `agent.md` (YAML frontmatter, then the standing
91
92
  prompt). `mutagent agent deploy` stores each change as a new revision. A slot is the agent in one
92
93
  Environment (`--env`).
93
94
  - **Sandbox provider and preset**: where a cloud run executes, and the named sandbox definition it
94
- uses. Both are managed by the platform. You choose one per run with `--sandbox-provider` and
95
- `--preset`.
95
+ uses. Both are managed by the platform. You choose a sandbox provider per run with
96
+ `--sandbox-provider`.
96
97
  - **Gateway**: connects GitHub and Slack, and runs Helix when an event or a schedule fires.
97
98
 
98
99
  ## Commands
@@ -164,15 +165,26 @@ is refused unless you pass `--allow-provider-key`. Environment names use letters
164
165
  and `-` (up to 64 characters). Variable names use `A-Z`, `0-9` and `_`, and cannot start with a
165
166
  digit. An Environment holds up to 64 KiB.
166
167
 
167
- ### Run Helix in the cloud (`helix`)
168
+ ### Run Architech in the cloud (`architech`)
169
+
170
+ `mutagent architech` is the cloud form of the local `architech`. It always runs the Architech
171
+ harness in a new sandbox, so it has no `--preset` and no `--sandbox`.
168
172
 
169
173
  ```bash
170
- mutagent helix -p "plan the refactor" # Run to completion and print the final answer
171
- mutagent helix --mode json "run the tests" # Stream events as JSON lines
172
- mutagent helix --mode rpc # A steerable session: JSON commands on stdin
173
- mutagent helix --prime --mode rpc # The lean Prime agent instead of the full orchestrator
174
- mutagent helix --env staging -p "check the deploy"
175
- mutagent helix --repository acme/api --branch feat/login --mode rpc
174
+ mutagent architech -p "plan the refactor" # Run to completion and print the final answer
175
+ mutagent architech --mode json "run the tests" # Stream events as JSON lines
176
+ mutagent architech --mode rpc # A steerable session: JSON commands on stdin
177
+ mutagent architech --prime -p "plan the refactor"
178
+ mutagent architech agent --name reviewer -p "review the diff"
179
+ mutagent architech session list
180
+ mutagent architech session send <reference> "and now the tests"
181
+ mutagent architech session end <reference> --force
182
+ mutagent architech models # Models a cloud run can use, and the default
183
+ mutagent architech models default <provider/model> # Set the workspace default model
184
+
185
+ # Sandbox providers and presets
186
+ mutagent sandbox providers
187
+ mutagent sandbox presets
176
188
  ```
177
189
 
178
190
  | Run option | What it does |
@@ -183,7 +195,6 @@ mutagent helix --repository acme/api --branch feat/login --mode rpc
183
195
  | `--prime` | Run the lean Prime agent instead of the full orchestrator |
184
196
  | `--model <provider/model>` | Model to use (default: the workspace default model) |
185
197
  | `--env <name>` | Workspace Environment to load |
186
- | `--preset <name>` | Sandbox preset (default: the server's Helix preset) |
187
198
  | `--sandbox-provider <name>` | Run on this sandbox provider |
188
199
  | `--cwd <path>` | Working directory in the sandbox |
189
200
  | `--repository <owner/name>` | Run in a checkout of this GitHub repository (needs the workspace's GitHub connection) |
@@ -192,55 +203,9 @@ mutagent helix --repository acme/api --branch feat/login --mode rpc
192
203
  There is no terminal chat UI: choose `-p`, `--mode json` or `--mode rpc`. Each run prints its
193
204
  session reference (`hs1_...`) on stderr. Ctrl-C stops the session.
194
205
 
195
- ```bash
196
- # Your own agent definition
197
- mutagent helix agent "You are a test reviewer." -p "review the diff"
198
- mutagent helix agent --file reviewer.md --mode json "run the suite"
199
-
200
- # Sessions
201
- mutagent helix session list
202
- mutagent helix session attach <reference> # Watch it (--since <n> replays)
203
- mutagent helix session send <reference> "and now the tests"
204
- mutagent helix session send <reference> --type steer "stop and re-read the spec"
205
- mutagent helix session approvals <reference> # What it is waiting on (a question it asked)
206
- mutagent helix session answer <reference> <id> --value 'an option' # Answer it (--cancel denies)
207
- mutagent helix session signal <reference> --force # Stop it; the sandbox stays up
208
- mutagent helix session close-input <reference>
209
- mutagent helix session checkpoint <reference>
210
- mutagent helix session checkpoints <reference>
211
- mutagent helix session restore <reference> # Continue in a rebuilt sandbox
212
-
213
- # Models
214
- mutagent helix models # Models Helix can use, and the default
215
- mutagent helix models default <provider/model> # Set the workspace default model
216
-
217
- # Diagnostics
218
- mutagent helix version # This CLI's version and the cloud Helix version
219
- mutagent helix doctor # Helix's own diagnostics in a temporary sandbox
220
- mutagent helix smoke # Helix's smoke test in a temporary sandbox
221
-
222
- # Sandbox providers and presets a run can name
223
- mutagent sandbox providers
224
- mutagent sandbox presets
225
- ```
226
-
227
- ### Run Architech in the cloud (`architech`)
228
-
229
- `mutagent architech` is the cloud form of the local `architech`, as `mutagent helix` is of the
230
- local `helix`. It takes the same launch flags, `agent` forms and `session`, `models` and
231
- `access` verbs, and always runs the Architech harness in a new sandbox, so it has no `--preset`.
232
-
233
- ```bash
234
- mutagent architech --mode rpc # A steerable Architech session
235
- mutagent architech --prime -p "plan the refactor"
236
- mutagent architech agent --name reviewer -p "review the diff"
237
- mutagent architech session list
238
- mutagent architech session send <reference> "and now the tests"
239
- mutagent architech session end <reference> --force
240
- ```
241
-
242
- `mutagent helix --preset architech` is refused: it names the `mutagent architech` command to run
243
- instead.
206
+ `mutagent helix` and `mutagent factory` are removed. They answer `UNKNOWN_COMMAND` with what does
207
+ the job now: `mutagent agent run` for an agent.md, `mutagent install helix` for the Helix binary,
208
+ the Factory page in the web app for Agent Factory entries. See the CHANGELOG.
244
209
 
245
210
  Only an interactive session (`--mode rpc`) accepts `session send`. A send to a session whose
246
211
  sandbox was stopped for idling wakes it from its last checkpoint.
@@ -252,7 +217,6 @@ mutagent agent check invoice/agent.md # Compile and validate; n
252
217
  mutagent agent pack invoice/agent.md --output invoice.tgz
253
218
  mutagent agent run invoice/agent.md "Price three widget units." # Local, with the local Helix binary
254
219
  mutagent agent deploy invoice/agent.md --env prod
255
- mutagent helix agent @invoice-pricing --env prod -p "Price three widget units."
256
220
  mutagent agent list
257
221
  mutagent agent inspect invoice-pricing --env prod
258
222
  mutagent agent activate invoice-pricing --revision v2 --env prod # An older revision is a rollback
@@ -262,7 +226,7 @@ mutagent agent retire invoice-pricing --env prod --force
262
226
  The `agent.md` frontmatter fields `name`, `description`, `model`, `thinking`, `tools`,
263
227
  `disallowed_tools` and `skills` are a local brief. Deployment settings live in one optional
264
228
  `harness:` block (tools, skills, files, bindings, runtime). `name` is the slug, and `model` is
265
- `provider/model` as `mutagent helix models` lists it.
229
+ `provider/model` as `mutagent architech models` lists it.
266
230
 
267
231
  Each deploy of new content is the next revision (`v1`, `v2`, ...). `--no-activate` stores it
268
232
  without moving the slot. `@slug:vN` pins a revision and `@slug:latest` runs the newest one.
@@ -364,8 +328,8 @@ paths and the context of your prompts. Use it only when you mean to share all of
364
328
  | `-h, --help` | Help for any command |
365
329
  | `-v, --version` | CLI version (only before a subcommand) |
366
330
 
367
- With `mutagent helix`, put `--api-key` and `--endpoint` before `helix`
368
- (`mutagent --api-key <key> helix -p "<task>"`). After `helix` they are refused, so a model key
331
+ With `mutagent architech`, put `--api-key` and `--endpoint` before `architech`
332
+ (`mutagent --api-key <key> architech -p "<task>"`). After `architech` they are refused, so a model key
369
333
  cannot be sent as your Mutagent key.
370
334
 
371
335
  ## Scripts, CI and coding agents
@@ -380,8 +344,8 @@ mutagent providers list --json
380
344
  - **Coding agents:** run `mutagent skills install` first. It installs a skill that teaches the agent
381
345
  the CLI's workflows. To help a person sign in, run `mutagent login --browser --json`, show them the
382
346
  printed URL, and wait (the CLI polls for up to 5 minutes).
383
- - **JSON:** pass `--json` to every command except a `mutagent helix` launch, whose output is Helix's
384
- own. A response may carry `_directive` (a status card and the next step for an agent), `_links`
347
+ - **JSON:** pass `--json` to every command except a `mutagent architech` launch, whose output is the
348
+ harness's own. A response may carry `_directive` (a status card and the next step for an agent), `_links`
385
349
  (dashboard and API URLs) and `_compat` (CLI and skill versions).
386
350
  - **Destructive commands** (delete, retire, signal, cancel, ...) need `-f/--force` in every mode.
387
351
  Without it they refuse with `CONFIRMATION_REQUIRED` and send nothing. They never prompt.