@mindstudio-ai/agent 0.1.183 → 0.1.185
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/CHANGELOG.md +18 -0
- package/README.md +3 -3
- package/dist/cli.js +124 -9
- package/dist/datasources/index.d.ts +1 -1
- package/dist/datasources/parts.d.ts +14 -0
- package/dist/datasources/source.d.ts +63 -2
- package/dist/generated/steps.d.ts +1 -0
- package/dist/generated/types.d.ts +3 -3
- package/dist/index.js +114 -27
- package/dist/index.js.map +4 -4
- package/dist/snippets.js +173 -0
- package/llms.txt +3 -0
- package/package.json +6 -1
package/CHANGELOG.md
CHANGED
|
@@ -4,6 +4,24 @@ What changed in `@mindstudio-ai/agent`, newest first, each version under its own
|
|
|
4
4
|
|
|
5
5
|
Versions before 0.1.163 aren't recorded here.
|
|
6
6
|
|
|
7
|
+
## 0.1.185
|
|
8
|
+
|
|
9
|
+
### New
|
|
10
|
+
|
|
11
|
+
- `@mindstudio-ai/agent/snippets` exports `monacoSnippets` and `blockTypeAliases` by themselves: plain data with no imports, for a code editor that runs in a browser. The main entry still exports both, but it's Node code, and a browser bundle of it has failed since 0.1.144, on its file imports. Check: browser code that imports either from `@mindstudio-ai/agent` imports it from `@mindstudio-ai/agent/snippets`.
|
|
12
|
+
|
|
13
|
+
## 0.1.184
|
|
14
|
+
|
|
15
|
+
### New
|
|
16
|
+
|
|
17
|
+
- A data source's `addMany(documents, { budgetDollars? })` adds many records at once: rows of the app's own tables rendered to text, as an array or any iterable or async iterable of `{ externalId, title, markdown, metadata?, entities?, replaces? }`, in any number. One job builds them, priced before it runs and starting on its own within the budget, and the call returns `{ documentCount, job }`. An `externalId` the source already holds is superseded when the job finishes, and unchanged markdown builds nothing. It throws `data_source_busy` while another job runs on the source and `data_source_mapped` on a source with a mapper. Check: code that loads many records by calling `add()` in a loop can give them to `addMany()` in one call.
|
|
18
|
+
|
|
19
|
+
### Changed behavior
|
|
20
|
+
|
|
21
|
+
- The platform limits `add()` to 300 calls a minute per app and answers `rate_limited` (429) past it. Check: a method that adds documents in a loop, or in a `Promise.all` larger than that, should give them to `addMany()`.
|
|
22
|
+
- A source has no limit on how many documents it holds beyond the room where it lives. `add()` doesn't throw `document_limit_reached`; it throws `data_source_full` (422) when the source has no room, and the message says how to give it more. Check: code that catches `document_limit_reached` can catch `data_source_full` instead, or drop the catch.
|
|
23
|
+
- Types only: a job's `source` may be `{ type: 'documents', documents }`, the documents an `addMany()` gave. Check: code that switches over a job's `source.type`.
|
|
24
|
+
|
|
7
25
|
## 0.1.183
|
|
8
26
|
|
|
9
27
|
### Changed behavior
|
package/README.md
CHANGED
|
@@ -675,10 +675,10 @@ import type {
|
|
|
675
675
|
|
|
676
676
|
## Snippets
|
|
677
677
|
|
|
678
|
-
A `monacoSnippets` object is exported with field metadata and output keys for every method
|
|
678
|
+
A `monacoSnippets` object is exported with field metadata and output keys for every method. It's for a code editor's completions, and an editor runs in a browser, so it has an entry of its own, `@mindstudio-ai/agent/snippets`: plain data with no imports, which any bundler can take. The main entry exports it too, but that entry is Node code and won't bundle for a browser.
|
|
679
679
|
|
|
680
680
|
```typescript
|
|
681
|
-
import { monacoSnippets } from '@mindstudio-ai/agent';
|
|
681
|
+
import { monacoSnippets } from '@mindstudio-ai/agent/snippets';
|
|
682
682
|
|
|
683
683
|
monacoSnippets.generateText;
|
|
684
684
|
// {
|
|
@@ -690,7 +690,7 @@ monacoSnippets.generateText;
|
|
|
690
690
|
For the 2 renamed step types, both the alias and original name appear as keys. A `blockTypeAliases` map is also exported for reverse-mapping:
|
|
691
691
|
|
|
692
692
|
```typescript
|
|
693
|
-
import { blockTypeAliases } from '@mindstudio-ai/agent';
|
|
693
|
+
import { blockTypeAliases } from '@mindstudio-ai/agent/snippets';
|
|
694
694
|
// { userMessage: "generateText", generatePdf: "generateAsset" }
|
|
695
695
|
```
|
|
696
696
|
|
package/dist/cli.js
CHANGED
|
@@ -306,8 +306,8 @@ var init_metadata = __esm({
|
|
|
306
306
|
"evaluateDecision": {
|
|
307
307
|
stepType: "evaluateDecision",
|
|
308
308
|
description: "Ask structured questions about text, JSON, or images and get calibrated answers from a decision model. The model returns a probability, a selected option, or a score. It does not write a reply. Each question is a noul (yes or no, as a probability from 0 to 1), a choice (one option from a set you define, with a probability for each), or a score (a rating against ordered levels). Put every question in the same call. The question id is yours: answers come back under the same ids. The model defaults to Jev (jev-latest).",
|
|
309
|
-
usageNotes: "- state is the content to judge: a string, or a JSON object or array (a record, a chat log, application state).\n- questions is a map. The key is an id you choose. It is not shown to the model. The answer comes back under the same id.\n- A noul asks a yes/no question and returns noul, a probability from 0 (no) to 1 (yes). Optional criteria.true and criteria.false say what a yes and a no mean.\n- A choice picks one option. criteria is a map of option id to a short description (or null). At most 255 options. The answer includes the winning choice, a probability for every option, and confidence.\n- A score rates the state on an ordered rubric. criteria is 2 to 10 level descriptions, low to high. The answer's score can land between levels, and includes a probability per level plus confidence.\n- An answer of type refusal means the model declined that question (GPT-6 Luna Decisions can).\n- instructions may be a string, or an object that keeps the question in one field and reference data in the others. Refer to those fields by name in backticks.\n- Send every question you need in one call. The model reads the state once and answers them together.\n- Probabilities from different models are not comparable: tune a threshold against the model, and the version, it will run on.\n- decisionModelOverride.model picks the model:\n - jev-latest (the default) is TypeSafe's current stable release, text only, up to 64k tokens. jev-preview tracks TypeSafe's newest release. Pin a version such as jev-1.13.0 when a threshold was tuned against that version.\n - clef and clef-flash run Cloudflare Clef, which also reads up to 4 PNG, JPEG, or WebP images, each at most 4 MiB and 8 MiB together, and takes at most 64 questions, each id using only letters, digits, underscore, dot, and hyphen, up to 100 characters. clef is the larger model, clef-flash the faster one. @cf/cloudflare/clef and @cf/cloudflare/clef-flash name the same two.\n - mercury-decide runs Inception's Mercury Decide, which reads up to 64k tokens and up to 16 PNG, JPEG, WebP, or GIF images, each at most 10 MiB and 14 MiB together.\n - drex-max, drex-v2.0 and drex-v1.5 run Nace.AI's Drex, served by DeepInfra, and take at most 16 questions. drex-max reads up to 262k tokens and up to 4 PNG, JPEG, WebP, or GIF images, 9 MiB together. drex-v2.0 and drex-v1.5 read text only, up to 128k tokens. nace-ai/drex-max, nace-ai/drex-v2.0 and nace-ai/drex-v1.5 name the same three.\n - gpt-6-luna-decisions runs OpenAI's Decisions API (in beta), which reads up to 922k tokens and PNG, JPEG, WebP, or GIF images of up to 20 MB each. It takes up to 200 questions, and a choice needs at least 2 options. gpt-6-luna names it too.\n- images is for a model that reads them. Pass URLs or data URLs. A model that reads none refuses the call.\n- The response model field is the version that answered.\n- Billed per input token. Output tokens are free. Each model has its own rate, and GPT-6 Luna Decisions bills a prompt over 272k tokens at twice its rate.",
|
|
310
|
-
inputSchema: { "type": "object", "properties": { "state": { "anyOf": [{ "type": "string" }, { "type": "object", "properties": {}, "required": [] }, { "type": "array", "items": {} }] }, "questions": { "type": "object", "properties": {}, "required": [], "description": "Questions to ask about the state, keyed by an id you choose." }, "images": { "type": "array", "items": { "type": "string" }, "description": "Images for a model that reads them (Clef, Clef Flash, GPT-6 Luna Decisions). Each entry is a URL or a data URL. A model that reads none refuses the call." }, "decisionModelOverride": { "type": "object", "properties": { "model": { "type": "string", "description": "Decision model: a catalog id, its vendor's name for it (`@cf/cloudflare/clef`, `gpt-6-luna`), or a version it pins (`jev-1.13.0`)" }, "config": { "type": "object", "properties": {}, "required": [], "description": "Additional model-specific configuration" } }, "required": ["model"], "description": "Optional model override. Uses the workspace's default decision model (Jev) if not specified" } }, "required": ["state", "questions"] },
|
|
309
|
+
usageNotes: "- state is the content to judge: a string, or a JSON object or array (a record, a chat log, application state).\n- questions is a map. The key is an id you choose. It is not shown to the model. The answer comes back under the same id.\n- A noul asks a yes/no question and returns noul, a probability from 0 (no) to 1 (yes). Optional criteria.true and criteria.false say what a yes and a no mean.\n- A choice picks one option. criteria is a map of option id to a short description (or null). At most 255 options. The answer includes the winning choice, a probability for every option, and confidence.\n- A score rates the state on an ordered rubric. criteria is 2 to 10 level descriptions, low to high. The answer's score can land between levels, and includes a probability per level plus confidence.\n- An answer of type refusal means the model declined that question (GPT-6 Luna Decisions can).\n- instructions may be a string, or an object that keeps the question in one field and reference data in the others. Refer to those fields by name in backticks.\n- Send every question you need in one call. The model reads the state once and answers them together.\n- Probabilities from different models are not comparable: tune a threshold against the model, and the version, it will run on.\n- decisionModelOverride.model picks the model:\n - jev-latest (the default) is TypeSafe's current stable release, text only, up to 64k tokens. jev-preview tracks TypeSafe's newest release. Pin a version such as jev-1.13.0 when a threshold was tuned against that version.\n - clef and clef-flash run Cloudflare Clef, which also reads up to 4 PNG, JPEG, or WebP images, each at most 4 MiB and 8 MiB together, and takes at most 64 questions, each id using only letters, digits, underscore, dot, and hyphen, up to 100 characters. clef is the larger model, clef-flash the faster one. @cf/cloudflare/clef and @cf/cloudflare/clef-flash name the same two.\n - mercury-decide runs Inception's Mercury Decide, which reads up to 64k tokens and up to 16 PNG, JPEG, WebP, or GIF images, each at most 10 MiB and 14 MiB together.\n - drex-max, drex-v2.0 and drex-v1.5 run Nace.AI's Drex, served by DeepInfra, and take at most 16 questions. drex-max reads up to 262k tokens and up to 4 PNG, JPEG, WebP, or GIF images, 9 MiB together. drex-v2.0 and drex-v1.5 read text only, up to 128k tokens. nace-ai/drex-max, nace-ai/drex-v2.0 and nace-ai/drex-v1.5 name the same three.\n - gpt-6-luna-decisions runs OpenAI's Decisions API (in beta), which reads up to 922k tokens and PNG, JPEG, WebP, or GIF images of up to 20 MB each. It takes up to 200 questions, and a choice needs at least 2 options. gpt-6-luna names it too.\n - gemini-decision-1 runs Google's Gemini Decision 1, which reads up to 262k tokens and PNG, JPEG, WebP, or GIF images, up to 100 MB of image data in one request. It takes 1 to 1,000 questions. A question id uses only letters, digits, underscore, and hyphen, up to 64 characters, and a choice needs 2 to 255 options. A yes/no probability is between 0.01 and 0.99.\n- images is for a model that reads them. Pass URLs or data URLs. A model that reads none refuses the call.\n- The response model field is the version that answered.\n- Billed per input token. Output tokens are free. Each model has its own rate, and GPT-6 Luna Decisions bills a prompt over 272k tokens at twice its rate.",
|
|
310
|
+
inputSchema: { "type": "object", "properties": { "state": { "anyOf": [{ "type": "string" }, { "type": "object", "properties": {}, "required": [] }, { "type": "array", "items": {} }] }, "questions": { "type": "object", "properties": {}, "required": [], "description": "Questions to ask about the state, keyed by an id you choose." }, "images": { "type": "array", "items": { "type": "string" }, "description": "Images for a model that reads them (Clef, Clef Flash, GPT-6 Luna Decisions, Gemini Decision 1). Each entry is a URL or a data URL. A model that reads none refuses the call." }, "decisionModelOverride": { "type": "object", "properties": { "model": { "type": "string", "description": "Decision model: a catalog id, its vendor's name for it (`@cf/cloudflare/clef`, `gpt-6-luna`), or a version it pins (`jev-1.13.0`)" }, "config": { "type": "object", "properties": {}, "required": [], "description": "Additional model-specific configuration" } }, "required": ["model"], "description": "Optional model override. Uses the workspace's default decision model (Jev) if not specified" } }, "required": ["state", "questions"] },
|
|
311
311
|
outputSchema: { "type": "object", "properties": { "model": { "type": "string", "description": "Versioned model id that answered, such as jev-1.13.0." }, "answers": { "type": "object", "properties": {}, "required": [], "description": "One answer per question, under the same ids." }, "usage": { "type": "object", "properties": { "input_tokens": { "type": "number" }, "output_tokens": { "type": "number" } }, "required": ["input_tokens", "output_tokens"], "description": "Token counts for the call. Input tokens are what the model bills." } }, "required": ["model", "answers", "usage"] }
|
|
312
312
|
},
|
|
313
313
|
"extractAudioFromVideo": {
|
|
@@ -1096,7 +1096,7 @@ var init_metadata = __esm({
|
|
|
1096
1096
|
stepType: "typesafeEvaluate",
|
|
1097
1097
|
description: "Use evaluateDecision: the same questions, answers and models, with decisionModelOverride in place of model. evaluateDecision's earlier name, which still runs: ask structured questions about text, JSON, or images and get calibrated answers from a decision model.",
|
|
1098
1098
|
usageNotes: "- Runs exactly as evaluateDecision does, with the same questions, answers, models and limits (see its notes), and model in place of decisionModelOverride.model.",
|
|
1099
|
-
inputSchema: { "type": "object", "properties": { "state": { "anyOf": [{ "type": "string" }, { "type": "object", "properties": {}, "required": [] }, { "type": "array", "items": {} }] }, "questions": { "type": "object", "properties": {}, "required": [], "description": "Questions to ask about the state, keyed by an id you choose." }, "model": { "type": "string", "description": "Model id or alias. Defaults to the workspace's default decision model (jev-latest). Every model evaluateDecision takes: jev-preview, a pinned version such as jev-1.13.0, clef and clef-flash, gpt-6-luna-decisions." }, "images": { "type": "array", "items": { "type": "string" }, "description": "Images for a model that reads them (Clef, Clef Flash, GPT-6 Luna Decisions). Each entry is a URL or a data URL. A model that reads none refuses the call." } }, "required": ["state", "questions"] },
|
|
1099
|
+
inputSchema: { "type": "object", "properties": { "state": { "anyOf": [{ "type": "string" }, { "type": "object", "properties": {}, "required": [] }, { "type": "array", "items": {} }] }, "questions": { "type": "object", "properties": {}, "required": [], "description": "Questions to ask about the state, keyed by an id you choose." }, "model": { "type": "string", "description": "Model id or alias. Defaults to the workspace's default decision model (jev-latest). Every model evaluateDecision takes: jev-preview, a pinned version such as jev-1.13.0, clef and clef-flash, gpt-6-luna-decisions, gemini-decision-1." }, "images": { "type": "array", "items": { "type": "string" }, "description": "Images for a model that reads them (Clef, Clef Flash, GPT-6 Luna Decisions, Gemini Decision 1). Each entry is a URL or a data URL. A model that reads none refuses the call." } }, "required": ["state", "questions"] },
|
|
1100
1100
|
outputSchema: { "type": "object", "properties": { "model": { "type": "string", "description": "Versioned model id that answered, such as jev-1.13.0." }, "answers": { "type": "object", "properties": {}, "required": [], "description": "One answer per question, under the same ids." }, "usage": { "type": "object", "properties": { "input_tokens": { "type": "number" }, "output_tokens": { "type": "number" } }, "required": ["input_tokens", "output_tokens"], "description": "Token counts for the call. Input tokens are what the model bills." } }, "required": ["model", "answers", "usage"] }
|
|
1101
1101
|
},
|
|
1102
1102
|
"updateGmailLabels": {
|
|
@@ -5108,12 +5108,46 @@ var init_files = __esm({
|
|
|
5108
5108
|
}
|
|
5109
5109
|
});
|
|
5110
5110
|
|
|
5111
|
+
// src/datasources/parts.ts
|
|
5112
|
+
import { gzipSync } from "node:zlib";
|
|
5113
|
+
async function storePart(grant, lines) {
|
|
5114
|
+
const form = new FormData();
|
|
5115
|
+
for (const [k, v] of Object.entries(grant.uploadFields)) {
|
|
5116
|
+
form.append(k, v);
|
|
5117
|
+
}
|
|
5118
|
+
form.append(
|
|
5119
|
+
"file",
|
|
5120
|
+
new Blob([new Uint8Array(gzipSync(Buffer.from(lines.join("\n") + "\n")))], {
|
|
5121
|
+
type: "application/gzip"
|
|
5122
|
+
}),
|
|
5123
|
+
`${grant.part}.ndjson.gz`
|
|
5124
|
+
);
|
|
5125
|
+
const response = await fetch(grant.uploadUrl, {
|
|
5126
|
+
method: "POST",
|
|
5127
|
+
body: form
|
|
5128
|
+
});
|
|
5129
|
+
if (!response.ok) {
|
|
5130
|
+
throw new Error(
|
|
5131
|
+
`Could not store part ${grant.part} of the documents: HTTP ${response.status}`
|
|
5132
|
+
);
|
|
5133
|
+
}
|
|
5134
|
+
}
|
|
5135
|
+
var PART_DOCUMENTS, PART_BYTES;
|
|
5136
|
+
var init_parts = __esm({
|
|
5137
|
+
"src/datasources/parts.ts"() {
|
|
5138
|
+
"use strict";
|
|
5139
|
+
PART_DOCUMENTS = 1e3;
|
|
5140
|
+
PART_BYTES = 8 * 1024 * 1024;
|
|
5141
|
+
}
|
|
5142
|
+
});
|
|
5143
|
+
|
|
5111
5144
|
// src/datasources/source.ts
|
|
5112
5145
|
import { createHash as createHash2 } from "node:crypto";
|
|
5113
5146
|
var DICTIONARY_PAGE_ENTRIES, DICTIONARY_PAGE_BYTES, REMOVE_WHERE_MAX_PAGES, DataSource;
|
|
5114
5147
|
var init_source = __esm({
|
|
5115
5148
|
"src/datasources/source.ts"() {
|
|
5116
5149
|
"use strict";
|
|
5150
|
+
init_parts();
|
|
5117
5151
|
DICTIONARY_PAGE_ENTRIES = 1e4;
|
|
5118
5152
|
DICTIONARY_PAGE_BYTES = 4e6;
|
|
5119
5153
|
REMOVE_WHERE_MAX_PAGES = 100;
|
|
@@ -5415,6 +5449,87 @@ var init_source = __esm({
|
|
|
5415
5449
|
body: bytes.toString("base64")
|
|
5416
5450
|
});
|
|
5417
5451
|
}
|
|
5452
|
+
/**
|
|
5453
|
+
* Add many documents at once, built as one job.
|
|
5454
|
+
*
|
|
5455
|
+
* For records your app renders to text: a row of its own table as a short
|
|
5456
|
+
* markdown card, in any number. Each is what a mapper's `documents()`
|
|
5457
|
+
* returns (an `externalId`, a `title`, `markdown`, and optionally
|
|
5458
|
+
* `metadata`, `entities` and `replaces`), given as an array or any iterable
|
|
5459
|
+
* or async iterable, so a generator that yields a document per row never
|
|
5460
|
+
* holds them all. {@link add} is for a file.
|
|
5461
|
+
*
|
|
5462
|
+
* ```ts
|
|
5463
|
+
* const { job } = await Claims.addMany(
|
|
5464
|
+
* claims.map((claim) => ({
|
|
5465
|
+
* externalId: claim.id,
|
|
5466
|
+
* title: claim.title,
|
|
5467
|
+
* markdown: renderCard(claim),
|
|
5468
|
+
* metadata: { firmId: claim.firmId, status: claim.status },
|
|
5469
|
+
* })),
|
|
5470
|
+
* );
|
|
5471
|
+
* ```
|
|
5472
|
+
*
|
|
5473
|
+
* The documents are stored a thousand at a time and one job registers and
|
|
5474
|
+
* builds them, planned and priced like any other; it starts on its own
|
|
5475
|
+
* within `budgetDollars`, or within its plan's projection with headroom when
|
|
5476
|
+
* none is given. The call returns once the job has started: follow it with
|
|
5477
|
+
* {@link job}, and a search sees what has been built throughout.
|
|
5478
|
+
*
|
|
5479
|
+
* The external id is a document's identity. Giving one the source already
|
|
5480
|
+
* holds supersedes that document once the job's documents are all
|
|
5481
|
+
* searchable; unchanged markdown builds nothing, and new metadata or
|
|
5482
|
+
* entities on unchanged markdown update in place. A document that fails
|
|
5483
|
+
* validation is left out and counted on the job; the rest go in. Nothing is
|
|
5484
|
+
* removed for being left out of a later call: use {@link remove} or
|
|
5485
|
+
* {@link removeWhere}.
|
|
5486
|
+
*
|
|
5487
|
+
* @throws `data_source_mapped` on a source with a mapper, which is what
|
|
5488
|
+
* makes that source's documents; `data_source_busy` while another job or
|
|
5489
|
+
* a move is in flight, since a source runs one job at a time.
|
|
5490
|
+
*/
|
|
5491
|
+
async addMany(documents, options) {
|
|
5492
|
+
const { uploadId } = await this._call("add-many/open", {
|
|
5493
|
+
slug: this._slug
|
|
5494
|
+
});
|
|
5495
|
+
const parts = [];
|
|
5496
|
+
let lines = [];
|
|
5497
|
+
let bytes = 0;
|
|
5498
|
+
let documentCount = 0;
|
|
5499
|
+
const storeLines = async () => {
|
|
5500
|
+
if (lines.length === 0) {
|
|
5501
|
+
return;
|
|
5502
|
+
}
|
|
5503
|
+
const grant = await this._call("add-many/part", {
|
|
5504
|
+
slug: this._slug,
|
|
5505
|
+
uploadId
|
|
5506
|
+
});
|
|
5507
|
+
await storePart(grant, lines);
|
|
5508
|
+
parts.push({ part: grant.part, count: lines.length });
|
|
5509
|
+
lines = [];
|
|
5510
|
+
bytes = 0;
|
|
5511
|
+
};
|
|
5512
|
+
for await (const d of documents) {
|
|
5513
|
+
const line = JSON.stringify({ o: 0, i: documentCount, d });
|
|
5514
|
+
lines.push(line);
|
|
5515
|
+
bytes += line.length;
|
|
5516
|
+
documentCount += 1;
|
|
5517
|
+
if (lines.length >= PART_DOCUMENTS || bytes >= PART_BYTES) {
|
|
5518
|
+
await storeLines();
|
|
5519
|
+
}
|
|
5520
|
+
}
|
|
5521
|
+
await storeLines();
|
|
5522
|
+
if (parts.length === 0) {
|
|
5523
|
+
return { documentCount: 0, job: null };
|
|
5524
|
+
}
|
|
5525
|
+
const { job } = await this._call("add-many/start", {
|
|
5526
|
+
slug: this._slug,
|
|
5527
|
+
uploadId,
|
|
5528
|
+
parts,
|
|
5529
|
+
...options?.budgetDollars !== void 0 ? { budgetDollars: options.budgetDollars } : {}
|
|
5530
|
+
});
|
|
5531
|
+
return { documentCount, job };
|
|
5532
|
+
}
|
|
5418
5533
|
/**
|
|
5419
5534
|
* Documents in the corpus, with ingest status.
|
|
5420
5535
|
*
|
|
@@ -10143,7 +10258,7 @@ async function startMcpServer(options) {
|
|
|
10143
10258
|
capabilities: { tools: {} },
|
|
10144
10259
|
serverInfo: {
|
|
10145
10260
|
name: "mindstudio-agent",
|
|
10146
|
-
version: "0.1.
|
|
10261
|
+
version: "0.1.185"
|
|
10147
10262
|
},
|
|
10148
10263
|
instructions: 'Welcome to MindStudio \u2014 a platform with 200+ AI models, 850+ third-party integrations, and pre-built agents.\n\nGetting started:\n1. Call `ask` with any question about the SDK \u2014 it knows every action, model, and connector and returns working code with real model IDs and config options. Examples: ask("generate an image with FLUX"), ask("what models support vision?"), ask("how do I send a Slack message?").\n2. Call `changeName` to set your display name \u2014 use your name or whatever your user calls you. This is how you\'ll appear in MindStudio request logs.\n3. If you have a profile picture, pass its public image URL to `changeProfilePicture`.\n4. For manual browsing, call `listActions` to discover all available actions.\n\nThen use the tools to generate text, images, video, audio, search the web, work with data sources, run agents, and more.\n\nImportant:\n- AI-powered actions (text generation, image generation, video, audio, etc.) cost money. Before running these, call `estimateActionCost` and confirm with the user before proceeding \u2014 unless they\'ve explicitly told you to go ahead.\n- Not all agents from `listAgents` are configured for API use. Do not try to run an agent just because it appears in the list \u2014 it will likely fail. Only run agents the user specifically asks you to run.'
|
|
10149
10264
|
});
|
|
@@ -11183,7 +11298,7 @@ function isNewerVersion(current, latest) {
|
|
|
11183
11298
|
return false;
|
|
11184
11299
|
}
|
|
11185
11300
|
async function checkForUpdate() {
|
|
11186
|
-
const currentVersion = "0.1.
|
|
11301
|
+
const currentVersion = "0.1.185";
|
|
11187
11302
|
if (!currentVersion || process.env.MINDSTUDIO_NO_UPDATE_CHECK) {
|
|
11188
11303
|
return null;
|
|
11189
11304
|
}
|
|
@@ -11218,7 +11333,7 @@ async function checkForUpdate() {
|
|
|
11218
11333
|
}
|
|
11219
11334
|
}
|
|
11220
11335
|
function printUpdateNotice(latestVersion) {
|
|
11221
|
-
const currentVersion = "0.1.
|
|
11336
|
+
const currentVersion = "0.1.185";
|
|
11222
11337
|
process.stderr.write(
|
|
11223
11338
|
`
|
|
11224
11339
|
${ansi2.cyanBright("Update available")} ${ansi2.gray(currentVersion + " \u2192")} ${ansi2.cyanBold(latestVersion)}
|
|
@@ -11231,7 +11346,7 @@ function isStandaloneBinary() {
|
|
|
11231
11346
|
return !argv1.includes("node_modules");
|
|
11232
11347
|
}
|
|
11233
11348
|
async function cmdUpdate() {
|
|
11234
|
-
const currentVersion = "0.1.
|
|
11349
|
+
const currentVersion = "0.1.185";
|
|
11235
11350
|
process.stderr.write(
|
|
11236
11351
|
` ${ansi2.gray("Current version:")} ${currentVersion}
|
|
11237
11352
|
`
|
|
@@ -11372,7 +11487,7 @@ async function cmdLogin(options) {
|
|
|
11372
11487
|
process.stderr.write("\n");
|
|
11373
11488
|
printLogo();
|
|
11374
11489
|
process.stderr.write("\n");
|
|
11375
|
-
const ver = "0.1.
|
|
11490
|
+
const ver = "0.1.185";
|
|
11376
11491
|
process.stderr.write(
|
|
11377
11492
|
` ${ansi2.bold("MindStudio Agent")} ${ver ? " " + ansi2.gray("v" + ver) : ""}
|
|
11378
11493
|
`
|
|
@@ -11702,7 +11817,7 @@ async function main() {
|
|
|
11702
11817
|
const updatePromise = command !== "mcp" && command !== "login" && command !== "update" ? checkForUpdate() : Promise.resolve(null);
|
|
11703
11818
|
try {
|
|
11704
11819
|
if (command === "version" || command === "-v") {
|
|
11705
|
-
process.stdout.write("0.1.
|
|
11820
|
+
process.stdout.write("0.1.185\n");
|
|
11706
11821
|
return;
|
|
11707
11822
|
}
|
|
11708
11823
|
if (command === "login") {
|
|
@@ -31,7 +31,7 @@
|
|
|
31
31
|
*/
|
|
32
32
|
import { DataSource, type DataSourcesTransport } from './source.js';
|
|
33
33
|
export { DataSource } from './source.js';
|
|
34
|
-
export type { AddOptions, AddResult, BranchPosition, Citation, DataSourceChunk, DataSourceDocument, DataSourceJob, DataSourceJobPlan, DataSourceJobState, DataSourcePassage, DataSourcePassagePage, DataSourceStats, DictionaryEntry, DictionaryPushResult, DictionaryRelink, DictionaryReport, DocumentMetadata, DocumentSelector, MetadataRange, MetadataValue, SearchExplain, SearchFilter, SearchHit, SearchMode, SearchOptions, SearchRan, } from './source.js';
|
|
34
|
+
export type { AddManyResult, AddOptions, AddResult, BranchPosition, Citation, DataSourceChunk, DataSourceDocument, DataSourceJob, DataSourceJobPlan, DataSourceJobState, DataSourcePassage, DataSourcePassagePage, DataSourceStats, DictionaryEntry, DictionaryPushResult, DictionaryRelink, DictionaryReport, DocumentMetadata, DocumentSelector, MetadataRange, MetadataValue, SearchExplain, SearchFilter, SearchHit, SearchMode, SearchOptions, SearchRan, } from './source.js';
|
|
35
35
|
/** The `dataSources` namespace object. */
|
|
36
36
|
export interface DataSources {
|
|
37
37
|
/**
|
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* A part: what the platform registers in one batch (its own `PART_DOCUMENTS`,
|
|
3
|
+
* the api's customerApps/AppDataSources/mapSpill.ts).
|
|
4
|
+
*/
|
|
5
|
+
export declare const PART_DOCUMENTS = 1000;
|
|
6
|
+
export declare const PART_BYTES: number;
|
|
7
|
+
/** A grant to store the next part. */
|
|
8
|
+
export interface PartGrant {
|
|
9
|
+
part: number;
|
|
10
|
+
uploadUrl: string;
|
|
11
|
+
uploadFields: Record<string, string>;
|
|
12
|
+
}
|
|
13
|
+
/** Store one part's lines under its grant. Throws when storage refuses them. */
|
|
14
|
+
export declare function storePart(grant: PartGrant, lines: string[]): Promise<void>;
|
|
@@ -1,3 +1,4 @@
|
|
|
1
|
+
import type { MappedDocument } from '../mapper/index.js';
|
|
1
2
|
/** @internal Transport: `POST /_internal/v2/datasources/<op>` with the hook token. */
|
|
2
3
|
export type DataSourcesTransport = (op: string, body: unknown) => Promise<any>;
|
|
3
4
|
/** Where a retrieved chunk came from — enough to show the user the source. */
|
|
@@ -385,6 +386,19 @@ export interface AddResult {
|
|
|
385
386
|
*/
|
|
386
387
|
job: DataSourceJob | null;
|
|
387
388
|
}
|
|
389
|
+
/** What {@link DataSource.addMany} returns. */
|
|
390
|
+
export interface AddManyResult {
|
|
391
|
+
/** How many documents were given. */
|
|
392
|
+
documentCount: number;
|
|
393
|
+
/**
|
|
394
|
+
* The job registering and building them; null only when none were given.
|
|
395
|
+
* It plans and starts on its own (within `budgetDollars`); follow it with
|
|
396
|
+
* {@link DataSource.job}. A document whose external id the source already
|
|
397
|
+
* holds is superseded when the job finishes, once every document of the
|
|
398
|
+
* call is searchable.
|
|
399
|
+
*/
|
|
400
|
+
job: DataSourceJob | null;
|
|
401
|
+
}
|
|
388
402
|
export interface DataSourceDocument {
|
|
389
403
|
id: string;
|
|
390
404
|
filename: string | null;
|
|
@@ -543,8 +557,9 @@ export interface DataSourceJobPlan {
|
|
|
543
557
|
/**
|
|
544
558
|
* A bulk ingestion job — a sync, a corpus load started from the CLI, a remap
|
|
545
559
|
* of a mapped source's raw copies, a replay of an earlier job's quarantine, a
|
|
546
|
-
* reread of the source's documents by its reader,
|
|
547
|
-
* object an {@link DataSource.add} took
|
|
560
|
+
* reread of the source's documents by its reader, the rest of one large
|
|
561
|
+
* object an {@link DataSource.add} took, or the documents a
|
|
562
|
+
* {@link DataSource.addMany} gave.
|
|
548
563
|
*/
|
|
549
564
|
export interface DataSourceJob {
|
|
550
565
|
id: string;
|
|
@@ -576,6 +591,9 @@ export interface DataSourceJob {
|
|
|
576
591
|
} | {
|
|
577
592
|
type: 'object';
|
|
578
593
|
ref: string;
|
|
594
|
+
} | {
|
|
595
|
+
type: 'documents';
|
|
596
|
+
documents: number;
|
|
579
597
|
};
|
|
580
598
|
/**
|
|
581
599
|
* Objects the mapper skipped or failed on, and documents the reader failed
|
|
@@ -907,6 +925,49 @@ export declare class DataSource {
|
|
|
907
925
|
* the source refuses it with `data_source_busy`.
|
|
908
926
|
*/
|
|
909
927
|
add(content: Buffer | Uint8Array | string, options: AddOptions): Promise<AddResult>;
|
|
928
|
+
/**
|
|
929
|
+
* Add many documents at once, built as one job.
|
|
930
|
+
*
|
|
931
|
+
* For records your app renders to text: a row of its own table as a short
|
|
932
|
+
* markdown card, in any number. Each is what a mapper's `documents()`
|
|
933
|
+
* returns (an `externalId`, a `title`, `markdown`, and optionally
|
|
934
|
+
* `metadata`, `entities` and `replaces`), given as an array or any iterable
|
|
935
|
+
* or async iterable, so a generator that yields a document per row never
|
|
936
|
+
* holds them all. {@link add} is for a file.
|
|
937
|
+
*
|
|
938
|
+
* ```ts
|
|
939
|
+
* const { job } = await Claims.addMany(
|
|
940
|
+
* claims.map((claim) => ({
|
|
941
|
+
* externalId: claim.id,
|
|
942
|
+
* title: claim.title,
|
|
943
|
+
* markdown: renderCard(claim),
|
|
944
|
+
* metadata: { firmId: claim.firmId, status: claim.status },
|
|
945
|
+
* })),
|
|
946
|
+
* );
|
|
947
|
+
* ```
|
|
948
|
+
*
|
|
949
|
+
* The documents are stored a thousand at a time and one job registers and
|
|
950
|
+
* builds them, planned and priced like any other; it starts on its own
|
|
951
|
+
* within `budgetDollars`, or within its plan's projection with headroom when
|
|
952
|
+
* none is given. The call returns once the job has started: follow it with
|
|
953
|
+
* {@link job}, and a search sees what has been built throughout.
|
|
954
|
+
*
|
|
955
|
+
* The external id is a document's identity. Giving one the source already
|
|
956
|
+
* holds supersedes that document once the job's documents are all
|
|
957
|
+
* searchable; unchanged markdown builds nothing, and new metadata or
|
|
958
|
+
* entities on unchanged markdown update in place. A document that fails
|
|
959
|
+
* validation is left out and counted on the job; the rest go in. Nothing is
|
|
960
|
+
* removed for being left out of a later call: use {@link remove} or
|
|
961
|
+
* {@link removeWhere}.
|
|
962
|
+
*
|
|
963
|
+
* @throws `data_source_mapped` on a source with a mapper, which is what
|
|
964
|
+
* makes that source's documents; `data_source_busy` while another job or
|
|
965
|
+
* a move is in flight, since a source runs one job at a time.
|
|
966
|
+
*/
|
|
967
|
+
addMany(documents: Iterable<MappedDocument> | AsyncIterable<MappedDocument>, options?: {
|
|
968
|
+
/** The job's ceiling, in dollars: it pauses there, and a plan projected over it waits for an approval. */
|
|
969
|
+
budgetDollars?: number;
|
|
970
|
+
}): Promise<AddManyResult>;
|
|
910
971
|
/**
|
|
911
972
|
* Documents in the corpus, with ingest status.
|
|
912
973
|
*
|
|
@@ -644,6 +644,7 @@ export interface StepMethods {
|
|
|
644
644
|
* - mercury-decide runs Inception's Mercury Decide, which reads up to 64k tokens and up to 16 PNG, JPEG, WebP, or GIF images, each at most 10 MiB and 14 MiB together.
|
|
645
645
|
* - drex-max, drex-v2.0 and drex-v1.5 run Nace.AI's Drex, served by DeepInfra, and take at most 16 questions. drex-max reads up to 262k tokens and up to 4 PNG, JPEG, WebP, or GIF images, 9 MiB together. drex-v2.0 and drex-v1.5 read text only, up to 128k tokens. nace-ai/drex-max, nace-ai/drex-v2.0 and nace-ai/drex-v1.5 name the same three.
|
|
646
646
|
* - gpt-6-luna-decisions runs OpenAI's Decisions API (in beta), which reads up to 922k tokens and PNG, JPEG, WebP, or GIF images of up to 20 MB each. It takes up to 200 questions, and a choice needs at least 2 options. gpt-6-luna names it too.
|
|
647
|
+
* - gemini-decision-1 runs Google's Gemini Decision 1, which reads up to 262k tokens and PNG, JPEG, WebP, or GIF images, up to 100 MB of image data in one request. It takes 1 to 1,000 questions. A question id uses only letters, digits, underscore, and hyphen, up to 64 characters, and a choice needs 2 to 255 options. A yes/no probability is between 0.01 and 0.99.
|
|
647
648
|
* - images is for a model that reads them. Pass URLs or data URLs. A model that reads none refuses the call.
|
|
648
649
|
* - The response model field is the version that answered.
|
|
649
650
|
* - Billed per input token. Output tokens are free. Each model has its own rate, and GPT-6 Luna Decisions bills a prompt over 272k tokens at twice its rate.
|
|
@@ -755,7 +755,7 @@ export interface EvaluateDecisionStepInput {
|
|
|
755
755
|
/** Ordered level descriptions, from low to high. At least 2, at most 10. */
|
|
756
756
|
criteria: string[];
|
|
757
757
|
}>;
|
|
758
|
-
/** Images for a model that reads them (Clef, Clef Flash, GPT-6 Luna Decisions). Each entry is a URL or a data URL. A model that reads none refuses the call. */
|
|
758
|
+
/** Images for a model that reads them (Clef, Clef Flash, GPT-6 Luna Decisions, Gemini Decision 1). Each entry is a URL or a data URL. A model that reads none refuses the call. */
|
|
759
759
|
images?: string[];
|
|
760
760
|
/** Optional model override. Uses the workspace's default decision model (Jev) if not specified */
|
|
761
761
|
decisionModelOverride?: {
|
|
@@ -3793,9 +3793,9 @@ export interface TypesafeEvaluateStepInput {
|
|
|
3793
3793
|
/** Ordered level descriptions, from low to high. At least 2, at most 10. */
|
|
3794
3794
|
criteria: string[];
|
|
3795
3795
|
}>;
|
|
3796
|
-
/** Model id or alias. Defaults to the workspace's default decision model (jev-latest). Every model evaluateDecision takes: jev-preview, a pinned version such as jev-1.13.0, clef and clef-flash, gpt-6-luna-decisions. */
|
|
3796
|
+
/** Model id or alias. Defaults to the workspace's default decision model (jev-latest). Every model evaluateDecision takes: jev-preview, a pinned version such as jev-1.13.0, clef and clef-flash, gpt-6-luna-decisions, gemini-decision-1. */
|
|
3797
3797
|
model?: string;
|
|
3798
|
-
/** Images for a model that reads them (Clef, Clef Flash, GPT-6 Luna Decisions). Each entry is a URL or a data URL. A model that reads none refuses the call. */
|
|
3798
|
+
/** Images for a model that reads them (Clef, Clef Flash, GPT-6 Luna Decisions, Gemini Decision 1). Each entry is a URL or a data URL. A model that reads none refuses the call. */
|
|
3799
3799
|
images?: string[];
|
|
3800
3800
|
}
|
|
3801
3801
|
export interface TypesafeEvaluateStepOutput {
|
package/dist/index.js
CHANGED
|
@@ -3706,6 +3706,35 @@ function createFiles(call, runStep) {
|
|
|
3706
3706
|
|
|
3707
3707
|
// src/datasources/source.ts
|
|
3708
3708
|
import { createHash as createHash2 } from "node:crypto";
|
|
3709
|
+
|
|
3710
|
+
// src/datasources/parts.ts
|
|
3711
|
+
import { gzipSync } from "node:zlib";
|
|
3712
|
+
var PART_DOCUMENTS = 1e3;
|
|
3713
|
+
var PART_BYTES = 8 * 1024 * 1024;
|
|
3714
|
+
async function storePart(grant, lines) {
|
|
3715
|
+
const form = new FormData();
|
|
3716
|
+
for (const [k, v] of Object.entries(grant.uploadFields)) {
|
|
3717
|
+
form.append(k, v);
|
|
3718
|
+
}
|
|
3719
|
+
form.append(
|
|
3720
|
+
"file",
|
|
3721
|
+
new Blob([new Uint8Array(gzipSync(Buffer.from(lines.join("\n") + "\n")))], {
|
|
3722
|
+
type: "application/gzip"
|
|
3723
|
+
}),
|
|
3724
|
+
`${grant.part}.ndjson.gz`
|
|
3725
|
+
);
|
|
3726
|
+
const response = await fetch(grant.uploadUrl, {
|
|
3727
|
+
method: "POST",
|
|
3728
|
+
body: form
|
|
3729
|
+
});
|
|
3730
|
+
if (!response.ok) {
|
|
3731
|
+
throw new Error(
|
|
3732
|
+
`Could not store part ${grant.part} of the documents: HTTP ${response.status}`
|
|
3733
|
+
);
|
|
3734
|
+
}
|
|
3735
|
+
}
|
|
3736
|
+
|
|
3737
|
+
// src/datasources/source.ts
|
|
3709
3738
|
var DICTIONARY_PAGE_ENTRIES = 1e4;
|
|
3710
3739
|
var DICTIONARY_PAGE_BYTES = 4e6;
|
|
3711
3740
|
var REMOVE_WHERE_MAX_PAGES = 100;
|
|
@@ -4007,6 +4036,87 @@ var DataSource = class {
|
|
|
4007
4036
|
body: bytes.toString("base64")
|
|
4008
4037
|
});
|
|
4009
4038
|
}
|
|
4039
|
+
/**
|
|
4040
|
+
* Add many documents at once, built as one job.
|
|
4041
|
+
*
|
|
4042
|
+
* For records your app renders to text: a row of its own table as a short
|
|
4043
|
+
* markdown card, in any number. Each is what a mapper's `documents()`
|
|
4044
|
+
* returns (an `externalId`, a `title`, `markdown`, and optionally
|
|
4045
|
+
* `metadata`, `entities` and `replaces`), given as an array or any iterable
|
|
4046
|
+
* or async iterable, so a generator that yields a document per row never
|
|
4047
|
+
* holds them all. {@link add} is for a file.
|
|
4048
|
+
*
|
|
4049
|
+
* ```ts
|
|
4050
|
+
* const { job } = await Claims.addMany(
|
|
4051
|
+
* claims.map((claim) => ({
|
|
4052
|
+
* externalId: claim.id,
|
|
4053
|
+
* title: claim.title,
|
|
4054
|
+
* markdown: renderCard(claim),
|
|
4055
|
+
* metadata: { firmId: claim.firmId, status: claim.status },
|
|
4056
|
+
* })),
|
|
4057
|
+
* );
|
|
4058
|
+
* ```
|
|
4059
|
+
*
|
|
4060
|
+
* The documents are stored a thousand at a time and one job registers and
|
|
4061
|
+
* builds them, planned and priced like any other; it starts on its own
|
|
4062
|
+
* within `budgetDollars`, or within its plan's projection with headroom when
|
|
4063
|
+
* none is given. The call returns once the job has started: follow it with
|
|
4064
|
+
* {@link job}, and a search sees what has been built throughout.
|
|
4065
|
+
*
|
|
4066
|
+
* The external id is a document's identity. Giving one the source already
|
|
4067
|
+
* holds supersedes that document once the job's documents are all
|
|
4068
|
+
* searchable; unchanged markdown builds nothing, and new metadata or
|
|
4069
|
+
* entities on unchanged markdown update in place. A document that fails
|
|
4070
|
+
* validation is left out and counted on the job; the rest go in. Nothing is
|
|
4071
|
+
* removed for being left out of a later call: use {@link remove} or
|
|
4072
|
+
* {@link removeWhere}.
|
|
4073
|
+
*
|
|
4074
|
+
* @throws `data_source_mapped` on a source with a mapper, which is what
|
|
4075
|
+
* makes that source's documents; `data_source_busy` while another job or
|
|
4076
|
+
* a move is in flight, since a source runs one job at a time.
|
|
4077
|
+
*/
|
|
4078
|
+
async addMany(documents2, options) {
|
|
4079
|
+
const { uploadId } = await this._call("add-many/open", {
|
|
4080
|
+
slug: this._slug
|
|
4081
|
+
});
|
|
4082
|
+
const parts = [];
|
|
4083
|
+
let lines = [];
|
|
4084
|
+
let bytes = 0;
|
|
4085
|
+
let documentCount = 0;
|
|
4086
|
+
const storeLines = async () => {
|
|
4087
|
+
if (lines.length === 0) {
|
|
4088
|
+
return;
|
|
4089
|
+
}
|
|
4090
|
+
const grant = await this._call("add-many/part", {
|
|
4091
|
+
slug: this._slug,
|
|
4092
|
+
uploadId
|
|
4093
|
+
});
|
|
4094
|
+
await storePart(grant, lines);
|
|
4095
|
+
parts.push({ part: grant.part, count: lines.length });
|
|
4096
|
+
lines = [];
|
|
4097
|
+
bytes = 0;
|
|
4098
|
+
};
|
|
4099
|
+
for await (const d of documents2) {
|
|
4100
|
+
const line = JSON.stringify({ o: 0, i: documentCount, d });
|
|
4101
|
+
lines.push(line);
|
|
4102
|
+
bytes += line.length;
|
|
4103
|
+
documentCount += 1;
|
|
4104
|
+
if (lines.length >= PART_DOCUMENTS || bytes >= PART_BYTES) {
|
|
4105
|
+
await storeLines();
|
|
4106
|
+
}
|
|
4107
|
+
}
|
|
4108
|
+
await storeLines();
|
|
4109
|
+
if (parts.length === 0) {
|
|
4110
|
+
return { documentCount: 0, job: null };
|
|
4111
|
+
}
|
|
4112
|
+
const { job } = await this._call("add-many/start", {
|
|
4113
|
+
slug: this._slug,
|
|
4114
|
+
uploadId,
|
|
4115
|
+
parts,
|
|
4116
|
+
...options?.budgetDollars !== void 0 ? { budgetDollars: options.budgetDollars } : {}
|
|
4117
|
+
});
|
|
4118
|
+
return { documentCount, job };
|
|
4119
|
+
}
|
|
4010
4120
|
/**
|
|
4011
4121
|
* Documents in the corpus, with ingest status.
|
|
4012
4122
|
*
|
|
@@ -5155,8 +5265,8 @@ var stepMetadata = {
|
|
|
5155
5265
|
"evaluateDecision": {
|
|
5156
5266
|
stepType: "evaluateDecision",
|
|
5157
5267
|
description: "Ask structured questions about text, JSON, or images and get calibrated answers from a decision model. The model returns a probability, a selected option, or a score. It does not write a reply. Each question is a noul (yes or no, as a probability from 0 to 1), a choice (one option from a set you define, with a probability for each), or a score (a rating against ordered levels). Put every question in the same call. The question id is yours: answers come back under the same ids. The model defaults to Jev (jev-latest).",
|
|
5158
|
-
usageNotes: "- state is the content to judge: a string, or a JSON object or array (a record, a chat log, application state).\n- questions is a map. The key is an id you choose. It is not shown to the model. The answer comes back under the same id.\n- A noul asks a yes/no question and returns noul, a probability from 0 (no) to 1 (yes). Optional criteria.true and criteria.false say what a yes and a no mean.\n- A choice picks one option. criteria is a map of option id to a short description (or null). At most 255 options. The answer includes the winning choice, a probability for every option, and confidence.\n- A score rates the state on an ordered rubric. criteria is 2 to 10 level descriptions, low to high. The answer's score can land between levels, and includes a probability per level plus confidence.\n- An answer of type refusal means the model declined that question (GPT-6 Luna Decisions can).\n- instructions may be a string, or an object that keeps the question in one field and reference data in the others. Refer to those fields by name in backticks.\n- Send every question you need in one call. The model reads the state once and answers them together.\n- Probabilities from different models are not comparable: tune a threshold against the model, and the version, it will run on.\n- decisionModelOverride.model picks the model:\n - jev-latest (the default) is TypeSafe's current stable release, text only, up to 64k tokens. jev-preview tracks TypeSafe's newest release. Pin a version such as jev-1.13.0 when a threshold was tuned against that version.\n - clef and clef-flash run Cloudflare Clef, which also reads up to 4 PNG, JPEG, or WebP images, each at most 4 MiB and 8 MiB together, and takes at most 64 questions, each id using only letters, digits, underscore, dot, and hyphen, up to 100 characters. clef is the larger model, clef-flash the faster one. @cf/cloudflare/clef and @cf/cloudflare/clef-flash name the same two.\n - mercury-decide runs Inception's Mercury Decide, which reads up to 64k tokens and up to 16 PNG, JPEG, WebP, or GIF images, each at most 10 MiB and 14 MiB together.\n - drex-max, drex-v2.0 and drex-v1.5 run Nace.AI's Drex, served by DeepInfra, and take at most 16 questions. drex-max reads up to 262k tokens and up to 4 PNG, JPEG, WebP, or GIF images, 9 MiB together. drex-v2.0 and drex-v1.5 read text only, up to 128k tokens. nace-ai/drex-max, nace-ai/drex-v2.0 and nace-ai/drex-v1.5 name the same three.\n - gpt-6-luna-decisions runs OpenAI's Decisions API (in beta), which reads up to 922k tokens and PNG, JPEG, WebP, or GIF images of up to 20 MB each. It takes up to 200 questions, and a choice needs at least 2 options. gpt-6-luna names it too.\n- images is for a model that reads them. Pass URLs or data URLs. A model that reads none refuses the call.\n- The response model field is the version that answered.\n- Billed per input token. Output tokens are free. Each model has its own rate, and GPT-6 Luna Decisions bills a prompt over 272k tokens at twice its rate.",
|
|
5159
|
-
inputSchema: { "type": "object", "properties": { "state": { "anyOf": [{ "type": "string" }, { "type": "object", "properties": {}, "required": [] }, { "type": "array", "items": {} }] }, "questions": { "type": "object", "properties": {}, "required": [], "description": "Questions to ask about the state, keyed by an id you choose." }, "images": { "type": "array", "items": { "type": "string" }, "description": "Images for a model that reads them (Clef, Clef Flash, GPT-6 Luna Decisions). Each entry is a URL or a data URL. A model that reads none refuses the call." }, "decisionModelOverride": { "type": "object", "properties": { "model": { "type": "string", "description": "Decision model: a catalog id, its vendor's name for it (`@cf/cloudflare/clef`, `gpt-6-luna`), or a version it pins (`jev-1.13.0`)" }, "config": { "type": "object", "properties": {}, "required": [], "description": "Additional model-specific configuration" } }, "required": ["model"], "description": "Optional model override. Uses the workspace's default decision model (Jev) if not specified" } }, "required": ["state", "questions"] },
|
|
5268
|
+
usageNotes: "- state is the content to judge: a string, or a JSON object or array (a record, a chat log, application state).\n- questions is a map. The key is an id you choose. It is not shown to the model. The answer comes back under the same id.\n- A noul asks a yes/no question and returns noul, a probability from 0 (no) to 1 (yes). Optional criteria.true and criteria.false say what a yes and a no mean.\n- A choice picks one option. criteria is a map of option id to a short description (or null). At most 255 options. The answer includes the winning choice, a probability for every option, and confidence.\n- A score rates the state on an ordered rubric. criteria is 2 to 10 level descriptions, low to high. The answer's score can land between levels, and includes a probability per level plus confidence.\n- An answer of type refusal means the model declined that question (GPT-6 Luna Decisions can).\n- instructions may be a string, or an object that keeps the question in one field and reference data in the others. Refer to those fields by name in backticks.\n- Send every question you need in one call. The model reads the state once and answers them together.\n- Probabilities from different models are not comparable: tune a threshold against the model, and the version, it will run on.\n- decisionModelOverride.model picks the model:\n - jev-latest (the default) is TypeSafe's current stable release, text only, up to 64k tokens. jev-preview tracks TypeSafe's newest release. Pin a version such as jev-1.13.0 when a threshold was tuned against that version.\n - clef and clef-flash run Cloudflare Clef, which also reads up to 4 PNG, JPEG, or WebP images, each at most 4 MiB and 8 MiB together, and takes at most 64 questions, each id using only letters, digits, underscore, dot, and hyphen, up to 100 characters. clef is the larger model, clef-flash the faster one. @cf/cloudflare/clef and @cf/cloudflare/clef-flash name the same two.\n - mercury-decide runs Inception's Mercury Decide, which reads up to 64k tokens and up to 16 PNG, JPEG, WebP, or GIF images, each at most 10 MiB and 14 MiB together.\n - drex-max, drex-v2.0 and drex-v1.5 run Nace.AI's Drex, served by DeepInfra, and take at most 16 questions. drex-max reads up to 262k tokens and up to 4 PNG, JPEG, WebP, or GIF images, 9 MiB together. drex-v2.0 and drex-v1.5 read text only, up to 128k tokens. nace-ai/drex-max, nace-ai/drex-v2.0 and nace-ai/drex-v1.5 name the same three.\n - gpt-6-luna-decisions runs OpenAI's Decisions API (in beta), which reads up to 922k tokens and PNG, JPEG, WebP, or GIF images of up to 20 MB each. It takes up to 200 questions, and a choice needs at least 2 options. gpt-6-luna names it too.\n - gemini-decision-1 runs Google's Gemini Decision 1, which reads up to 262k tokens and PNG, JPEG, WebP, or GIF images, up to 100 MB of image data in one request. It takes 1 to 1,000 questions. A question id uses only letters, digits, underscore, and hyphen, up to 64 characters, and a choice needs 2 to 255 options. A yes/no probability is between 0.01 and 0.99.\n- images is for a model that reads them. Pass URLs or data URLs. A model that reads none refuses the call.\n- The response model field is the version that answered.\n- Billed per input token. Output tokens are free. Each model has its own rate, and GPT-6 Luna Decisions bills a prompt over 272k tokens at twice its rate.",
|
|
5269
|
+
inputSchema: { "type": "object", "properties": { "state": { "anyOf": [{ "type": "string" }, { "type": "object", "properties": {}, "required": [] }, { "type": "array", "items": {} }] }, "questions": { "type": "object", "properties": {}, "required": [], "description": "Questions to ask about the state, keyed by an id you choose." }, "images": { "type": "array", "items": { "type": "string" }, "description": "Images for a model that reads them (Clef, Clef Flash, GPT-6 Luna Decisions, Gemini Decision 1). Each entry is a URL or a data URL. A model that reads none refuses the call." }, "decisionModelOverride": { "type": "object", "properties": { "model": { "type": "string", "description": "Decision model: a catalog id, its vendor's name for it (`@cf/cloudflare/clef`, `gpt-6-luna`), or a version it pins (`jev-1.13.0`)" }, "config": { "type": "object", "properties": {}, "required": [], "description": "Additional model-specific configuration" } }, "required": ["model"], "description": "Optional model override. Uses the workspace's default decision model (Jev) if not specified" } }, "required": ["state", "questions"] },
|
|
5160
5270
|
outputSchema: { "type": "object", "properties": { "model": { "type": "string", "description": "Versioned model id that answered, such as jev-1.13.0." }, "answers": { "type": "object", "properties": {}, "required": [], "description": "One answer per question, under the same ids." }, "usage": { "type": "object", "properties": { "input_tokens": { "type": "number" }, "output_tokens": { "type": "number" } }, "required": ["input_tokens", "output_tokens"], "description": "Token counts for the call. Input tokens are what the model bills." } }, "required": ["model", "answers", "usage"] }
|
|
5161
5271
|
},
|
|
5162
5272
|
"extractAudioFromVideo": {
|
|
@@ -5945,7 +6055,7 @@ var stepMetadata = {
|
|
|
5945
6055
|
stepType: "typesafeEvaluate",
|
|
5946
6056
|
description: "Use evaluateDecision: the same questions, answers and models, with decisionModelOverride in place of model. evaluateDecision's earlier name, which still runs: ask structured questions about text, JSON, or images and get calibrated answers from a decision model.",
|
|
5947
6057
|
usageNotes: "- Runs exactly as evaluateDecision does, with the same questions, answers, models and limits (see its notes), and model in place of decisionModelOverride.model.",
|
|
5948
|
-
inputSchema: { "type": "object", "properties": { "state": { "anyOf": [{ "type": "string" }, { "type": "object", "properties": {}, "required": [] }, { "type": "array", "items": {} }] }, "questions": { "type": "object", "properties": {}, "required": [], "description": "Questions to ask about the state, keyed by an id you choose." }, "model": { "type": "string", "description": "Model id or alias. Defaults to the workspace's default decision model (jev-latest). Every model evaluateDecision takes: jev-preview, a pinned version such as jev-1.13.0, clef and clef-flash, gpt-6-luna-decisions." }, "images": { "type": "array", "items": { "type": "string" }, "description": "Images for a model that reads them (Clef, Clef Flash, GPT-6 Luna Decisions). Each entry is a URL or a data URL. A model that reads none refuses the call." } }, "required": ["state", "questions"] },
|
|
6058
|
+
inputSchema: { "type": "object", "properties": { "state": { "anyOf": [{ "type": "string" }, { "type": "object", "properties": {}, "required": [] }, { "type": "array", "items": {} }] }, "questions": { "type": "object", "properties": {}, "required": [], "description": "Questions to ask about the state, keyed by an id you choose." }, "model": { "type": "string", "description": "Model id or alias. Defaults to the workspace's default decision model (jev-latest). Every model evaluateDecision takes: jev-preview, a pinned version such as jev-1.13.0, clef and clef-flash, gpt-6-luna-decisions, gemini-decision-1." }, "images": { "type": "array", "items": { "type": "string" }, "description": "Images for a model that reads them (Clef, Clef Flash, GPT-6 Luna Decisions, Gemini Decision 1). Each entry is a URL or a data URL. A model that reads none refuses the call." } }, "required": ["state", "questions"] },
|
|
5949
6059
|
outputSchema: { "type": "object", "properties": { "model": { "type": "string", "description": "Versioned model id that answered, such as jev-1.13.0." }, "answers": { "type": "object", "properties": {}, "required": [], "description": "One answer per question, under the same ids." }, "usage": { "type": "object", "properties": { "input_tokens": { "type": "number" }, "output_tokens": { "type": "number" } }, "required": ["input_tokens", "output_tokens"], "description": "Token counts for the call. Input tokens are what the model bills." } }, "required": ["model", "answers", "usage"] }
|
|
5950
6060
|
},
|
|
5951
6061
|
"updateGmailLabels": {
|
|
@@ -9544,7 +9654,6 @@ function defineJewel(method, config) {
|
|
|
9544
9654
|
}
|
|
9545
9655
|
|
|
9546
9656
|
// src/mapper/index.ts
|
|
9547
|
-
import { gzipSync } from "node:zlib";
|
|
9548
9657
|
function documents(list) {
|
|
9549
9658
|
return {
|
|
9550
9659
|
kind: "documents",
|
|
@@ -9575,8 +9684,6 @@ function deletes(externalIds) {
|
|
|
9575
9684
|
}
|
|
9576
9685
|
var DEFAULT_TIMEOUT_MS = 3e4;
|
|
9577
9686
|
var DEFAULT_CONCURRENCY2 = 4;
|
|
9578
|
-
var PART_DOCUMENTS = 1e3;
|
|
9579
|
-
var PART_BYTES = 8 * 1024 * 1024;
|
|
9580
9687
|
function errorInfo2(e) {
|
|
9581
9688
|
if (e instanceof Error) {
|
|
9582
9689
|
return { message: e.message, stack: e.stack };
|
|
@@ -9687,27 +9794,7 @@ var PartWriter = class {
|
|
|
9687
9794
|
async store(lines, objects) {
|
|
9688
9795
|
try {
|
|
9689
9796
|
const grant = await this.source._mapSpillGrant(this.spillId);
|
|
9690
|
-
|
|
9691
|
-
for (const [k, v] of Object.entries(grant.uploadFields)) {
|
|
9692
|
-
form.append(k, v);
|
|
9693
|
-
}
|
|
9694
|
-
form.append(
|
|
9695
|
-
"file",
|
|
9696
|
-
new Blob(
|
|
9697
|
-
[new Uint8Array(gzipSync(Buffer.from(lines.join("\n") + "\n")))],
|
|
9698
|
-
{ type: "application/gzip" }
|
|
9699
|
-
),
|
|
9700
|
-
`${grant.part}.ndjson.gz`
|
|
9701
|
-
);
|
|
9702
|
-
const response = await fetch(grant.uploadUrl, {
|
|
9703
|
-
method: "POST",
|
|
9704
|
-
body: form
|
|
9705
|
-
});
|
|
9706
|
-
if (!response.ok) {
|
|
9707
|
-
throw new Error(
|
|
9708
|
-
`Could not store part ${grant.part} of the documents: HTTP ${response.status}`
|
|
9709
|
-
);
|
|
9710
|
-
}
|
|
9797
|
+
await storePart(grant, lines);
|
|
9711
9798
|
this.parts.push({ part: grant.part, count: lines.length });
|
|
9712
9799
|
} catch (e) {
|
|
9713
9800
|
const err = e instanceof Error ? e : new Error(String(e));
|