byollm 0.1.5-beta.1 → 0.1.5

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
@@ -1,11 +1,16 @@
1
- <!-- release-note 0.1.1 -->
2
- > **`0.1.5-beta.1` is documentation only — nothing to upgrade.** `PROTOCOL_VERSION`
3
- > is still `2`, so a 0.1.0 party and a 0.1.1 party talk to each other in both
4
- > directions. No dependency, schema, wire field or on-disk shape moved.
1
+ <!-- release-note 0.1.5 -->
2
+ > **`0.1.5` carries site tools and images. Update your hub or server first.**
3
+ > `PROTOCOL_VERSION` is still `2`. `llm.tools` lets the model call a site's
4
+ > own tools, which run on the site and never on this device. It is off until
5
+ > you turn it on for a service, and every call is in `byollm log`.
6
+ > `llm.vision` and `llm.image` work on local and HTTP models. A teammate's
7
+ > images are budgeted by `community.maxImageBytes`. A teammate's large job is
8
+ > now admitted when it could fit (#5738). Full note:
9
+ > `docs/release-notes/0.1.5.md`.
5
10
  >
6
11
  > This README used to open with a stack of release notes instead of with the
7
12
  > package. The history moved to `docs/release-notes/` and `CHANGELOG.md`,
8
- > where none of it was lost. Full note: `docs/release-notes/0.1.1.md`.
13
+ > where none of it was lost.
9
14
 
10
15
  # `byollm`
11
16
 
@@ -237,12 +242,15 @@ locked to your own work — a protocol rule, not a setting you can change.
237
242
  Every payload is treated as hostile input. Breakout is structurally
238
243
  impossible: process-class backends get a fixed argv with the prompt on stdin,
239
244
  a stripped environment, an empty scratch directory and hard timeout/output
240
- caps; HTTP-class backends spawn nothing at all. The model has no tools, no
241
- retrieval and no MCP.
245
+ caps; HTTP-class backends spawn nothing at all. The model has no tools that
246
+ run on your device, no retrieval and no MCP. A site's own tools (`llm.tools`,
247
+ off until you turn it on for a service) run on the site: the daemon seals each
248
+ call to that site, logs it first, and never executes it.
242
249
 
243
250
  Prompt injection — steering what the model _says_ — is not prevented by
244
- anything and we do not claim otherwise. It is bounded here because the model
245
- has no tools and the output is inert.
251
+ anything and we do not claim otherwise. It is bounded here because nothing
252
+ the model says runs on the device: its output is inert, and a call to a site's
253
+ tool is sealed to that site and run there.
246
254
 
247
255
  Full threat model, including what the OS stops us dropping:
248
256
  [`docs/security.md`](https://github.com/oftomorrowinc/byollm/blob/main/docs/security.md).
package/dist/bin.js CHANGED
@@ -1,7 +1,7 @@
1
1
  #!/usr/bin/env node
2
2
  import {
3
3
  main
4
- } from "./chunk-HAAQJD2L.js";
4
+ } from "./chunk-LB4MGI2X.js";
5
5
 
6
6
  // src/bin.ts
7
7
  process.exitCode = await main(process.argv.slice(2));