foldrun 19.2.0 → 19.2.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/docs/a2a.md +4 -4
- package/docs/agents.md +2 -2
- package/docs/budgets-and-billing.md +1 -1
- package/docs/checks.md +3 -3
- package/package.json +2 -2
package/docs/a2a.md
CHANGED
|
@@ -121,7 +121,7 @@ each is ticked. From the terminal:
|
|
|
121
121
|
`foldrun a2a publish <flow> --to <ws> --accept-risk <agent,…>` (every agent
|
|
122
122
|
accepted, as the list replaces the flow's; `--clear-accept-risk` takes it
|
|
123
123
|
out). `foldrun a2a ls --to <ws>` lists them, and
|
|
124
|
-
[`security/published-flow-secret-code`](checks#
|
|
124
|
+
[`security/published-flow-secret-code`](checks#security-published-flow-secret-code)
|
|
125
125
|
is `foldrun check`'s warning.
|
|
126
126
|
|
|
127
127
|
### An editor cannot widen a published flow
|
|
@@ -402,12 +402,12 @@ Ended tasks are kept 90 days.
|
|
|
402
402
|
and an editor cannot widen any agent of a published flow
|
|
403
403
|
([above](#an-editor-cannot-widen-a-published-flow)).
|
|
404
404
|
- **`foldrun check` warns on three shapes** of published flow (warnings, not
|
|
405
|
-
errors): [`security/published-flow-trifecta`](checks#
|
|
405
|
+
errors): [`security/published-flow-trifecta`](checks#security-published-flow-trifecta)
|
|
406
406
|
— an agent of the flow that holds something private, which a caller could
|
|
407
407
|
ask for in the answer or steer into sending;
|
|
408
|
-
[`security/published-flow-secret-code`](checks#
|
|
408
|
+
[`security/published-flow-secret-code`](checks#security-published-flow-secret-code)
|
|
409
409
|
— one that holds a secret and can run code (info once accepted); and
|
|
410
|
-
[`security/published-flow-ungated`](checks#
|
|
410
|
+
[`security/published-flow-ungated`](checks#security-published-flow-ungated)
|
|
411
411
|
— a step that acts outside the workspace with no approval or `ask:` before
|
|
412
412
|
it, which any key holder starts. Put a gate (`2!.`) on it, or take a leg
|
|
413
413
|
away.
|
package/docs/agents.md
CHANGED
|
@@ -264,7 +264,7 @@ What it may reach and send:
|
|
|
264
264
|
- **Untrusted.** What a remote answers reaches the model fenced as data from
|
|
265
265
|
another organisation's system, with invisible characters removed. An agent
|
|
266
266
|
with `remotes:` counts as reading untrusted content in the
|
|
267
|
-
[lethal-trifecta check](checks#
|
|
267
|
+
[lethal-trifecta check](checks#security-lethal-trifecta).
|
|
268
268
|
- **Limits.** `limits: {a2a: 10}` caps the messages a step sends (`a2a_send`
|
|
269
269
|
and `a2a_reply`); `a2a.status`, `a2a.send`, `a2a.reply` and `a2a.cancel` cap
|
|
270
270
|
each tool alone, so polling is capped apart from sending. A step sends at
|
|
@@ -382,7 +382,7 @@ What holds:
|
|
|
382
382
|
serve a writer with secrets and no web: a page that tells the reader to
|
|
383
383
|
send something finds nothing to send, and the writer never read the page.
|
|
384
384
|
`foldrun check` names what it holds that the parent does not
|
|
385
|
-
([`security/subagent-own-sandbox`](checks#
|
|
385
|
+
([`security/subagent-own-sandbox`](checks#security-subagent-own-sandbox)).
|
|
386
386
|
- **Only the reply comes back.** The reply is still text the parent reads —
|
|
387
387
|
it can carry an instruction — but it reaches a model whose sandbox never
|
|
388
388
|
held the page.
|
|
@@ -27,7 +27,7 @@ wins, and the step's error says which line set it: `budget: in the flow
|
|
|
27
27
|
file` or `budget: on the writer agent`.
|
|
28
28
|
| **runs at once** | `concurrency: 3` in the account's `AGENTS.md`, or Settings → Governance | the fourth run waits its turn in the queue — never refused, only later. Empty means the install's share (`FOLDRUN_ACCOUNT_CONCURRENCY`) or plan number (`FOLDRUN_PLAN_CONCURRENCY`, which applies only where billing is on), or no cap. Your own number can lower that, never raise it; a higher number comes with a plan |
|
|
29
29
|
| **the queue lane** | the plan's lane (`high` \| `normal` \| `low`); `priority: low` in the account's `AGENTS.md` lowers it, and `high` there counts only with a plan that gives it | when slots are short, accounts take turns, weighted by lane — high 3, normal 2, low 1: every account's first run goes before anyone's second, a fast lane takes three turns to a slow lane's one and never all of them, an account with runs going waits behind one with none, and a run that has waited ten minutes moves up a turn. A flow's own `priority:` orders runs within that. The cap above still holds |
|
|
30
|
-
| **compute at once** | the plan's cores, GiB and disk (below); `compute: { vcpu: 4, memory: 8Gi, disk: 40Gi }` in the account's `AGENTS.md`, or Settings → Governance, lowers it — and a workspace's and a flow's `compute:` narrow it further ([four levels](#compute-at-four-levels)) | what all the account's running steps may hold together — each step's cores, memory and disk, its `size:` class's or its own `resources:` ([agents](agents#resources
|
|
30
|
+
| **compute at once** | the plan's cores, GiB and disk (below); `compute: { vcpu: 4, memory: 8Gi, disk: 40Gi }` in the account's `AGENTS.md`, or Settings → Governance, lowers it — and a workspace's and a flow's `compute:` narrow it further ([four levels](#compute-at-four-levels)) | what all the account's running steps may hold together — each step's cores, memory and disk, its `size:` class's or its own `resources:` ([agents](agents#resources--your-own-numbers)). A step that would pass it waits to start, like a full node — `room: waiting to start — 6 of this account's 8 GiB is held by its running steps…` — and starts in turn when one of the account's steps ends ([waiting for room](#waiting-for-room)). A step that **alone** is bigger than the pool, or than the plan's most for one step, fails at once with that message: no step finishing would make room. Without a plan, the install's `FOLDRUN_ACCOUNT_VCPU` / `FOLDRUN_ACCOUNT_MEMORY_GIB` / `FOLDRUN_ACCOUNT_DISK_GIB`, or no cap. Your own number can lower it, never raise it. `foldrun usage compute` shows the pool and what is held now. Enforced on the hosted platform and any k8s install; a self-hosted Docker install caps each step at its class but not the pool |
|
|
31
31
|
| **room to start** | the install's `FOLDRUN_RUN_MEMORY_GIB`, `FOLDRUN_RUN_DISK_GIB` and `FOLDRUN_ACCOUNT_PODS` | a step whose sandbox would not fit, or whose account already has its most sandboxes running, waits to start — `room: waiting to start — …` on its trail — instead of failing. The wait is not billed and has no time limit; the run page's start-up chip shows it as `room` ([waiting for room](#waiting-for-room)) |
|
|
32
32
|
|
|
33
33
|
A cap is a literal, never an expression, so it is readable off the file. The
|
package/docs/checks.md
CHANGED
|
@@ -90,9 +90,9 @@ deploy names each finding and its rule; a `foldrun-ignore` with a reason
|
|
|
90
90
|
|
|
91
91
|
`foldrun check` stays offline. Two checks need the network, so they run on
|
|
92
92
|
the platform against the deployed copy: known vulnerabilities for exact
|
|
93
|
-
runtime pins ([`supply-chain/known-vulnerability`](#supply-
|
|
93
|
+
runtime pins ([`supply-chain/known-vulnerability`](#supply-chain-known-vulnerability))
|
|
94
94
|
and the tool text of MCP servers reached by URL
|
|
95
|
-
([`content/mcp-tool-text`](#
|
|
95
|
+
([`content/mcp-tool-text`](#content-mcp-tool-text)).
|
|
96
96
|
|
|
97
97
|
- **When you ask:** Checks → **Online checks**, `foldrun check --to <ws>
|
|
98
98
|
--online`, or `GET /api/workspaces/<ws>/check?online=1` — editor and
|
|
@@ -299,7 +299,7 @@ is the other answer, though this rule looks at the agent, not the flow.
|
|
|
299
299
|
sub-agent never gets more than its parent, so they are dropped inside the
|
|
300
300
|
delegation. Grant them to the parent, or remove them from the sub-agent.
|
|
301
301
|
A sub-agent with `sandbox: own` is not this rule's: its tools are its own
|
|
302
|
-
([below](#
|
|
302
|
+
([below](#security-subagent-own-sandbox)).
|
|
303
303
|
|
|
304
304
|
### security/subagent-own-sandbox
|
|
305
305
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "foldrun",
|
|
3
|
-
"version": "19.2.
|
|
3
|
+
"version": "19.2.2",
|
|
4
4
|
"description": "Agents are just folders. Write them, check them, run them — on your machine.",
|
|
5
5
|
"license": "FSL-1.1-ALv2",
|
|
6
6
|
"type": "module",
|
|
@@ -11,7 +11,7 @@
|
|
|
11
11
|
"node": ">=22"
|
|
12
12
|
},
|
|
13
13
|
"dependencies": {
|
|
14
|
-
"@foldrun/core": "^17.0
|
|
14
|
+
"@foldrun/core": "^17.1.0"
|
|
15
15
|
},
|
|
16
16
|
"files": [
|
|
17
17
|
"bin",
|