foldrun 20.9.1 → 20.9.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/docs/notifications.md +7 -1
- package/docs/providers.md +37 -0
- package/docs/secrets.md +4 -0
- package/docs/tools.md +9 -0
- package/package.json +1 -1
package/docs/notifications.md
CHANGED
|
@@ -51,6 +51,12 @@ another's webhook flow and be accepted. Name no secret and nothing is
|
|
|
51
51
|
signed, which is what every existing destination keeps doing. How to check
|
|
52
52
|
it is under [Verifying a delivery](#verifying-a-delivery).
|
|
53
53
|
|
|
54
|
+
A question an agent asks mid-step (`tools: [ask]`) goes out as
|
|
55
|
+
`awaiting-approval`, as a gate does, and its webhook body also carries
|
|
56
|
+
`reason: "question"` and `question: { text, options, agent }`, so a receiver
|
|
57
|
+
can tell the two apart and show the question. `events: [asking]` subscribes
|
|
58
|
+
to questions alone, without the gates.
|
|
59
|
+
|
|
54
60
|
The default events are `failed` and `awaiting-approval`. `completed` is
|
|
55
61
|
opt-in on purpose: a schedule that works is the quiet kind of good news, and
|
|
56
62
|
a channel that pings on every success gets muted — which un-pings the
|
|
@@ -240,7 +246,7 @@ Every attempt carries these headers:
|
|
|
240
246
|
| header | |
|
|
241
247
|
|---|---|
|
|
242
248
|
| `X-Foldrun-Delivery` | the delivery's id, `dlv_…` — **the same on every attempt and every redelivery**. Dedupe on it: a receiver that took attempt 2 but timed out answering may see attempt 3 |
|
|
243
|
-
| `X-Foldrun-Event` | `failed`, `completed`, `blocked`, `awaiting-approval
|
|
249
|
+
| `X-Foldrun-Event` | `failed`, `completed`, `blocked`, `awaiting-approval` (a question too: its body has `reason: "question"`), `quarantined`, `sla`, `budget`, `room`, or `test` |
|
|
244
250
|
| `X-Foldrun-Attempt` | 1, 2, … |
|
|
245
251
|
| `X-Foldrun-Timestamp`, `X-Foldrun-Signature` | when `signing_secret:` is set — see below |
|
|
246
252
|
|
package/docs/providers.md
CHANGED
|
@@ -195,6 +195,43 @@ those families on both wires and says so in the drop line. Every other id
|
|
|
195
195
|
keeps it, because a gateway ignores a field it cannot use and an o-series,
|
|
196
196
|
gpt-5, grok or deepseek-r model wants it.
|
|
197
197
|
|
|
198
|
+
### Persian prompts, by tier (checked 11 Nov 2026)
|
|
199
|
+
|
|
200
|
+
An eval of eight Persian tasks, compared on the three tiers with **Compare
|
|
201
|
+
models** ([Evals](evals#comparing-models)). Each case pairs a deterministic
|
|
202
|
+
check, where one fits, with a judge on `max` (Opus, low effort). The subject
|
|
203
|
+
was a plain agent told to write natural Persian, keep code in Latin script
|
|
204
|
+
and use Persian digits:
|
|
205
|
+
|
|
206
|
+
| case | fast (Haiku) | default (Sonnet) | max (Opus) |
|
|
207
|
+
|---|---|---|---|
|
|
208
|
+
| half-spaces in a short paragraph | pass | pass | pass |
|
|
209
|
+
| a formal notice to a customer | fail | pass | pass |
|
|
210
|
+
| Persian digits and thousands separators | pass | pass | pass |
|
|
211
|
+
| a command kept intact in Persian text | pass | pass | pass |
|
|
212
|
+
| a one-sentence summary | pass | pass | pass |
|
|
213
|
+
| a technical translation from English | pass | pass | pass |
|
|
214
|
+
| exactly three numbered points | pass | fail | pass |
|
|
215
|
+
| Persian when asked in English | fail | pass | pass |
|
|
216
|
+
| **passed** | **6 / 8** | **7 / 8** | **8 / 8** |
|
|
217
|
+
| cost per run · time | $0.013 · 6.7 s | $0.015 · 6.5 s | $0.024 · 8.4 s |
|
|
218
|
+
|
|
219
|
+
Every tier wrote correct Persian: half-spaces where they belong, Persian
|
|
220
|
+
digits when asked, code and commands left intact inside right-to-left text.
|
|
221
|
+
The three failures were following the task, not the language:
|
|
222
|
+
|
|
223
|
+
- `fast` opened the formal notice with a line about itself and invented a
|
|
224
|
+
Persian calendar date the task never gave;
|
|
225
|
+
- `fast` made one grammatical slip («سامانه نام دامنه … رکوردهایی هستند»);
|
|
226
|
+
- `default` added an introductory line and ran one list item past its
|
|
227
|
+
ten-word limit.
|
|
228
|
+
|
|
229
|
+
So `default` is a sound default for Persian, and an agent whose output must
|
|
230
|
+
follow a strict shape (a fixed format, an exact length) earns `max`, or a
|
|
231
|
+
`verify:` that checks the shape. One run per case is a small sample — run
|
|
232
|
+
the comparison on your own agent's cases with `repeat: 3` before moving a
|
|
233
|
+
step to `fast`. The whole comparison cost $0.42 (runs and judges together).
|
|
234
|
+
|
|
198
235
|
## Why a turn stopped
|
|
199
236
|
|
|
200
237
|
Every model reply ends with a stop reason, and the model loop acts on it: run
|
package/docs/secrets.md
CHANGED
|
@@ -219,6 +219,10 @@ PATCH /api/secrets { "name": "DATAFORSEO_PASSWORD", "sites": ["api.dataforseo.
|
|
|
219
219
|
PUT /api/secrets { "name": "…", "value": "…", "sites": ["api.dataforseo.com"] } # set and bind at once
|
|
220
220
|
```
|
|
221
221
|
|
|
222
|
+
A **remote MCP server**'s `headers:` and `url:` work the same way: bind the
|
|
223
|
+
key to the server's host and the sandbox's copy of them holds `${NAME}`,
|
|
224
|
+
filled by the proxy on the way to that host alone ([MCP](tools#mcp-someone-elses-tools)).
|
|
225
|
+
|
|
222
226
|
What a program in the sandbox writes is unchanged; it sends the placeholder
|
|
223
227
|
where the value would go:
|
|
224
228
|
|
package/docs/tools.md
CHANGED
|
@@ -146,6 +146,15 @@ Both transports the SDK supports: a local process (`command:`, with `args:` and
|
|
|
146
146
|
exposes reaches the agent that grants it. `mcpServers:` in an agent's own
|
|
147
147
|
frontmatter is the inline spelling of the same thing.
|
|
148
148
|
|
|
149
|
+
A remote server is called with MCP's Streamable HTTP transport, the one the
|
|
150
|
+
current spec names; the older SSE transport, which it replaced, is not
|
|
151
|
+
offered. `${NAME}` works in `url:` and `headers:` alike. A secret **bound to
|
|
152
|
+
the server's host** ([Bound to sites](secrets#bound-to-sites)) never enters
|
|
153
|
+
the sandbox: the sandbox's copy of the server's URL and headers holds
|
|
154
|
+
`${NAME}`, and the egress proxy fills it in requests to that host and no
|
|
155
|
+
other. An unbound secret is filled before the step starts, so the sandbox
|
|
156
|
+
holds its value — bind a key you would not hand the agent.
|
|
157
|
+
|
|
149
158
|
## The library — define it once
|
|
150
159
|
|
|
151
160
|
```
|