@decidio/sdk 0.1.8 → 0.1.10
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 +43 -16
- package/dist/adapters/_gate.d.ts +2 -0
- package/dist/adapters/_gate.js +14 -2
- package/dist/adapters/langgraph.d.ts +13 -0
- package/dist/adapters/openai.d.ts +24 -0
- package/dist/adapters/temporal.d.ts +16 -0
- package/dist/cli.js +149 -168
- package/dist/guard.d.ts +32 -1
- package/dist/guard.js +13 -2
- package/dist/index.d.ts +46 -2
- package/dist/index.js +21 -6
- package/dist/inngest.d.ts +20 -0
- package/dist/resume.d.ts +88 -0
- package/dist/resume.js +62 -10
- package/dist/signing.d.ts +30 -0
- package/dist/signing.js +56 -0
- package/openapi.yaml +1 -1
- package/package.json +3 -3
package/README.md
CHANGED
|
@@ -23,7 +23,10 @@ prints the approve command and exits rather than approve its own request (CI can
|
|
|
23
23
|
|
|
24
24
|
Under 30 minutes, no help needed. You'll need Node 20.6+, a terminal, and a Decidio workspace
|
|
25
25
|
(request one at [decidioai.com](https://decidioai.com/#early-access) — the hosted sandbox is
|
|
26
|
-
synthetic data, safe to experiment in
|
|
26
|
+
synthetic data, safe to experiment in — and it is ONE SHARED workspace: workspace-wide views
|
|
27
|
+
like `tokens list` or `approvals` show every lab member's agents and decisions there, which is
|
|
28
|
+
the shared-lab boundary working as designed; production workspaces are per-tenant). Lab
|
|
29
|
+
workspaces have a **governed-action allowance**
|
|
27
30
|
(currently 30 actions/hour); hitting it raises a typed `DecidioRateLimitError` naming the limit
|
|
28
31
|
and reset time — nothing is routed or executed — and `tokens list` shows your remaining
|
|
29
32
|
allowance any time.
|
|
@@ -56,7 +59,9 @@ stderr each run — set `DECIDIO_API_URL` (env or `.env`) to point at another De
|
|
|
56
59
|
`init` signs you into your workspace (email + password, or paste the sign-in link from your
|
|
57
60
|
workspace email), generates the agent's Ed25519 keypair **locally** (only the public `did:key`
|
|
58
61
|
is sent), registers the agent, mints its **floor-limited API token** (limited to the agent runtime — request authorization, poll status, report signed confirmation; it cannot administer the workspace or approve anything — and your workspace session never touches the agent's disk), and writes `.env`.
|
|
59
|
-
Every later command reads `.env` from this directory automatically.
|
|
62
|
+
Every later command reads `.env` from this directory automatically. Re-running init for an
|
|
63
|
+
agent that already has a token REPLACES it — the server keeps one active token per agent, so
|
|
64
|
+
the previous one is revoked and init says so.
|
|
60
65
|
|
|
61
66
|
What `.env` contains after a successful init: `DECIDIO_API_URL`, `DECIDIO_AGENT_ID`,
|
|
62
67
|
`DECIDIO_AGENT_DID` + `DECIDIO_AGENT_KEY` (the local keypair — the key is what earns
|
|
@@ -121,11 +126,14 @@ becomes the record's execution evidence.
|
|
|
121
126
|
|
|
122
127
|
```bash
|
|
123
128
|
npx @decidio/sdk receipt <decisionId>
|
|
124
|
-
npx @decidio/sdk verify decidio-receipt-<decisionId>.json
|
|
129
|
+
npx @decidio/sdk verify --issuer <did:key:...> decidio-receipt-<decisionId>.json
|
|
125
130
|
```
|
|
126
131
|
|
|
127
|
-
|
|
128
|
-
|
|
132
|
+
Lead with the pin: `--issuer` binds the check to YOUR workspace's DID (the `receipt` command
|
|
133
|
+
prints it from the authenticated response, so it is already on your screen). An UNPINNED
|
|
134
|
+
`verify` proves internal consistency only — any keyholder could have issued such a file — and
|
|
135
|
+
says so; pinned verification proves *who*. The download is an authenticated fetch from your
|
|
136
|
+
workspace; the *verification* is fully offline — the verifier ships inside this package (no second download, no registry probe, same
|
|
129
137
|
implementation as the standalone `@decidio/verify`). The receipt is a W3C Verifiable
|
|
130
138
|
Credential: signature and content binding verify with no Decidio account and no network — the
|
|
131
139
|
evidence is yours, not ours. To also prove *who* issued it, pin your workspace's issuer:
|
|
@@ -133,7 +141,10 @@ evidence is yours, not ours. To also prove *who* issued it, pin your workspace's
|
|
|
133
141
|
record verify panel — or simply read it off the `receipt` command's output, which prints your
|
|
134
142
|
workspace's issuer DID from the authenticated response so you never have to hunt for it).
|
|
135
143
|
|
|
136
|
-
One receipt proves itself. Pass several files and their **ordering** is verified too
|
|
144
|
+
One receipt proves itself. Pass several files and their **ordering** is verified too — in
|
|
145
|
+
**seal order** (each receipt's `prevHash` links to its predecessor's `contentHash`), which is
|
|
146
|
+
the order decisions were *sealed*, not the order of their displayed decision numbers (two
|
|
147
|
+
decisions created together can seal in either order). The first
|
|
137
148
|
file is the anchor and each subsequent receipt must follow it, so verifying any consecutive
|
|
138
149
|
*segment* works — you are told whether the segment starts at your workspace's genesis or
|
|
139
150
|
mid-history, and a set spanning two different issuers is refused outright.
|
|
@@ -144,9 +155,12 @@ why the credential's own `confirmation.status` field reads `"pending"` forever.
|
|
|
144
155
|
evidence that arrives *after* the seal (your function's captured result) lives on the
|
|
145
156
|
**record**, not inside the credential bytes: the `receipt` command prints the record's current
|
|
146
157
|
tier next to the file, and with the signing key `init` wrote you'll see `application_confirmed`
|
|
147
|
-
— the wrapper's report
|
|
148
|
-
|
|
149
|
-
|
|
158
|
+
— the wrapper's report carried a signed identity proof bound to your agent, this decision, and
|
|
159
|
+
a freshness window. Precisely: the proof authenticates WHO is confirming WHAT decision — it
|
|
160
|
+
does not yet sign the captured response bytes themselves (that binding is on the receipt-v2
|
|
161
|
+
roadmap), so treat the tier as proven reporter identity, not a cryptographic hash of the
|
|
162
|
+
result. (No signing key configured? The server caps the evidence at the weaker
|
|
163
|
+
`agent_asserted`, and the SDK warns at confirm time.) Immutable seal + accruing evidence is the design, not an omission — corrections and
|
|
150
164
|
later facts supersede, they never rewrite.
|
|
151
165
|
|
|
152
166
|
One sharing note: a receipt is **not a secret, but it is not metadata-free** — it names the
|
|
@@ -162,7 +176,9 @@ npx @decidio/sdk approvals approve <the same decisionId>
|
|
|
162
176
|
Decisions are single-use: the CLI reports "already resolved — nothing changed" and exits
|
|
163
177
|
non-zero. The server answers replays idempotently — a second approve can never re-execute the
|
|
164
178
|
action. (The durable resume path has the same property: parked actions are claimed exactly
|
|
165
|
-
once, and its webhook handler fails closed without a verified signature
|
|
179
|
+
once, and its webhook handler fails closed without a verified signature — unless you
|
|
180
|
+
explicitly set `allowUnsigned: true`, which removes webhook authenticity and makes the
|
|
181
|
+
controller say so loudly at startup; never use it on an internet-reachable endpoint.)
|
|
166
182
|
|
|
167
183
|
That's the whole contract: gate → human decision → your execution → owned, verifiable evidence.
|
|
168
184
|
|
|
@@ -230,6 +246,13 @@ also allow-list resume hosts (default-deny). That's operator territory: if you r
|
|
|
230
246
|
Decidio (or we run a pilot with you), the webhook is set up then. Against the hosted sandbox,
|
|
231
247
|
use the worker — a webhook secret your server never learned would (correctly) fail closed.
|
|
232
248
|
|
|
249
|
+
**The supported argument data model is plain JSON**: `null`, booleans, strings, finite
|
|
250
|
+
numbers, arrays, and plain objects. Anything that cannot survive JSON with its meaning intact
|
|
251
|
+
— `NaN`/`Infinity`, `undefined`, `BigInt`, `Map`/`Set`/`Date`, class instances, functions,
|
|
252
|
+
circular structures — is **refused before the decision is routed or the payload signed**
|
|
253
|
+
(typed error naming the offending path), because a value that silently drifts in serialization
|
|
254
|
+
would mean a human approves one thing and your function executes another.
|
|
255
|
+
|
|
233
256
|
Either way, re-execution is **single-use on the happy path**: the parked entry is claimed before
|
|
234
257
|
execution and deleted on success, so a duplicate signal finds nothing to replay. Honest edge — if
|
|
235
258
|
your action succeeds but the process dies *before* the entry is cleared, the claim can be retried
|
|
@@ -258,7 +281,9 @@ If your agent runs on Inngest/Temporal/LangGraph, the engine *is* the durable st
|
|
|
258
281
|
`@decidio/sdk/inngest` maps the gate onto `step.waitForEvent`; `@decidio/sdk/langgraph` is a
|
|
259
282
|
drop-in via `interrupt()`; `@decidio/sdk/temporal` uses `condition` + signal;
|
|
260
283
|
`@decidio/sdk/openai` gates RunState approvals. All optional peer dependencies — the core SDK
|
|
261
|
-
imports none of them
|
|
284
|
+
imports none of them — install the engine you use alongside the SDK (`npm i inngest`,
|
|
285
|
+
`@langchain/langgraph`, `@temporalio/workflow`, or `@openai/agents`); nothing is downloaded
|
|
286
|
+
for engines you don't. Each adapter's shipped `.d.ts` header documents its wiring; `npx
|
|
262
287
|
@decidio/sdk quickstart` is the fastest runnable end-to-end.
|
|
263
288
|
|
|
264
289
|
## One surface, every runtime — and Python too
|
|
@@ -275,14 +300,15 @@ imports none of them. Each adapter's shipped `.d.ts` header documents its wiring
|
|
|
275
300
|
- `doctor` — config, connectivity, and what your current token can do
|
|
276
301
|
- `approvals [--mine] [--json]` / `approvals approve|reject <id> [reason]` — the human side, from your terminal (the list is workspace-wide; `--mine` narrows it to this directory's agent)
|
|
277
302
|
- `receipt <id>` — download a sealed decision's Authority Receipt to a `.json` file
|
|
278
|
-
- `verify [--issuer <did>] <file>...` — verify receipts offline (the canonical verifier; the standalone `@decidio/verify` package is the same implementation, for auditors who want zero Decidio dependency). Unknown flags are refused, never ignored.
|
|
279
|
-
- `tokens list` / `tokens revoke <jti>` — see and kill agent tokens (values are never re-shown; the jti is the revocation handle). Each row carries its status — `active`, `expired`, or `REVOKED <date>` — so the list confirms the revocations it performs; re-revoking is an honest no-op (exit 1)
|
|
303
|
+
- `verify [--issuer <did>] <file>...` — verify receipts offline (the canonical verifier; the standalone `@decidio/verify` package is the same implementation, for auditors who want zero Decidio dependency — the sdk's embedded copy is pinned to the previous release, so message wording may trail it one version; verdicts and semantics are conformance-locked identical). Unknown flags are refused, never ignored. Fully offline AND fully decoupled: it touches no network and reads no `.env` — a receipt verifies identically from an empty directory.
|
|
304
|
+
- `tokens list [--mine]` / `tokens revoke <jti>` — see and kill agent tokens (values are never re-shown; the jti is the revocation handle). Each row carries its status — `active`, `expired`, or `REVOKED <date>` — so the list confirms the revocations it performs; re-revoking is an honest no-op (exit 1). The list is workspace-wide (a shared workspace shows every member's agents); `--mine` narrows to this directory's agent
|
|
280
305
|
- `quickstart cleanup` — revoke the tour's token and delete its local credentials. What stays, honestly: sealed records (permanent by design) and the agent's registration row (inert without key or token; server-side deregistration is on the roadmap)
|
|
281
306
|
- `dev [--target URL]` — local relay for the resume webhook (operator setups)
|
|
282
307
|
|
|
283
308
|
The CLI's stream contract: **stdout carries results only** (safe to pipe — `--json` output is
|
|
284
|
-
pure JSON); errors, usage
|
|
285
|
-
|
|
309
|
+
pure JSON); errors, usage shown on *error* paths, and the per-run target-host announcement go
|
|
310
|
+
to **stderr**. Asked-for help (an explicit `--help`, or invoking the bare CLI) is itself a
|
|
311
|
+
result and prints on stdout. Exit codes: 0 success · 1 failure or honest no-op · 2 usage error.
|
|
286
312
|
|
|
287
313
|
Commands that administer your workspace (`init`, `approvals`, `receipt`) use a **session**
|
|
288
314
|
sign-in held in memory for that run. What lands on disk in `.env`: the agent's floor-limited
|
|
@@ -297,7 +323,8 @@ manager for production.
|
|
|
297
323
|
- `DecidioSuspendedError` — (durable mode) the action was routed and is parked for async approval; the process may exit and resume later. Not a failure.
|
|
298
324
|
- `DecidioTimeoutError` — (blocking mode only) no human decided within `pollTimeoutMs` (default 10 min); the decision stays open in Decidio, nothing executed locally.
|
|
299
325
|
|
|
300
|
-
Every error carries the `decisionId`, so a suspended or
|
|
326
|
+
Every error raised after a decision exists carries the `decisionId`, so a suspended or
|
|
327
|
+
timed-out action is always findable in
|
|
301
328
|
your queue.
|
|
302
329
|
|
|
303
330
|
## Notes
|
package/dist/adapters/_gate.d.ts
CHANGED
|
@@ -7,5 +7,7 @@ export interface GateAuth {
|
|
|
7
7
|
}
|
|
8
8
|
export declare function gateAuthorize(config: GuardConfig, ctx: ApprovalContext): Promise<GateAuth>;
|
|
9
9
|
export declare function gateConfirm(config: GuardConfig, decisionId: string, result: unknown): Promise<void>;
|
|
10
|
+
/** Normalize a resume payload ({verdict} | "approved" | ...) to a verdict string. */
|
|
10
11
|
export declare function verdictFrom(payload: any): string;
|
|
12
|
+
/** Throw the right error for a non-approving verdict; return for approved/auto_approved. */
|
|
11
13
|
export declare function assertVerdict(verdict: string, decisionId: string, reason?: string): void;
|
package/dist/adapters/_gate.js
CHANGED
|
@@ -1,5 +1,7 @@
|
|
|
1
|
-
import { DecidioBlockedError, DecidioRejectedError, signBoundProof, signConfirm } from "../index.js";
|
|
1
|
+
import { DecidioBlockedError, DecidioRejectedError, signBoundProof, signConfirm, assertJsonSafe, assertConfirmRecorded, assertSafeTransport } from "../index.js";
|
|
2
2
|
export async function gateAuthorize(config, ctx) {
|
|
3
|
+
assertJsonSafe(ctx, "describe(...)");
|
|
4
|
+
assertSafeTransport(config.apiUrl, !!config.apiToken);
|
|
3
5
|
const f = config.fetchImpl ?? fetch;
|
|
4
6
|
const resumeUrl = config.resumeUrl ?? config.resume?.resumeUrl;
|
|
5
7
|
const requesterIdentity = (config.agentKey && config.agentDid)
|
|
@@ -20,6 +22,13 @@ export async function gateAuthorize(config, ctx) {
|
|
|
20
22
|
}
|
|
21
23
|
export async function gateConfirm(config, decisionId, result) {
|
|
22
24
|
const f = config.fetchImpl ?? fetch;
|
|
25
|
+
try {
|
|
26
|
+
assertSafeTransport(config.apiUrl, !!config.apiToken);
|
|
27
|
+
}
|
|
28
|
+
catch (e) {
|
|
29
|
+
console.warn(`[decidio] confirm failed (action succeeded): ${e.message}`);
|
|
30
|
+
return;
|
|
31
|
+
}
|
|
23
32
|
try {
|
|
24
33
|
const requesterIdentity = signConfirm(decisionId, config);
|
|
25
34
|
if (!requesterIdentity)
|
|
@@ -29,8 +38,11 @@ export async function gateConfirm(config, decisionId, result) {
|
|
|
29
38
|
headers: { "content-type": "application/json", ...(config.apiToken ? { authorization: `Bearer ${config.apiToken}` } : {}) },
|
|
30
39
|
body: JSON.stringify({ decisionId, capturedResponse: result ?? null, source: "wrapper", ...(requesterIdentity ? { requesterIdentity } : {}) }),
|
|
31
40
|
});
|
|
32
|
-
if (!res.ok)
|
|
41
|
+
if (!res.ok) {
|
|
33
42
|
console.warn(`[decidio] confirm returned ${res.status} (action succeeded)`);
|
|
43
|
+
return;
|
|
44
|
+
}
|
|
45
|
+
assertConfirmRecorded(await res.json().catch(() => null), decisionId, !!requesterIdentity);
|
|
34
46
|
}
|
|
35
47
|
catch (e) {
|
|
36
48
|
console.warn(`[decidio] confirm failed (action succeeded): ${e.message}`);
|
|
@@ -1,6 +1,19 @@
|
|
|
1
1
|
import { Command } from "@langchain/langgraph";
|
|
2
2
|
import { type GuardConfig, type ApprovalContext } from "../index.js";
|
|
3
|
+
/**
|
|
4
|
+
* @decidio/sdk/langgraph — durable suspend via LangGraph's native `interrupt()`.
|
|
5
|
+
* `interrupt` finds the running graph itself (no handle needed), so the gate drops into
|
|
6
|
+
* a node: authorize → on route, interrupt() durably pauses (the checkpointer persists;
|
|
7
|
+
* the process can die) → on resume (Command(resume={verdict})) run the agent's own
|
|
8
|
+
* action + confirm. Decidio is the approval system; the host bridges its webhook to the
|
|
9
|
+
* graph resume (decidioResumeCommand). Requires @langchain/langgraph (optional peer dep).
|
|
10
|
+
*
|
|
11
|
+
* (This wiring doc ships in the .d.ts — the README points here.)
|
|
12
|
+
*/
|
|
13
|
+
/** Gate `run()` behind Decidio inside a LangGraph node. */
|
|
3
14
|
export declare function decidioGate<R>(config: GuardConfig, ctx: ApprovalContext, run: () => Promise<R>): Promise<R>;
|
|
15
|
+
/** Translate Decidio's signed resume webhook into the LangGraph resume Command. The host
|
|
16
|
+
* maps decisionId → thread_id and passes this to graph.invoke/stream. */
|
|
4
17
|
export declare function decidioResumeCommand(body: {
|
|
5
18
|
verdict?: string;
|
|
6
19
|
reason?: string;
|
|
@@ -5,6 +5,26 @@ interface RunStateLike {
|
|
|
5
5
|
approve(item: ToolApprovalItem): void;
|
|
6
6
|
reject(item: ToolApprovalItem): void;
|
|
7
7
|
}
|
|
8
|
+
/**
|
|
9
|
+
* @decidio/sdk/openai — gate OpenAI Agents SDK tool-approval interruptions through
|
|
10
|
+
* Decidio, with durable suspend via the SDK's native RunState serialization.
|
|
11
|
+
*
|
|
12
|
+
* The Agents loop surfaces tool approvals on the RunState (state.getInterruptions());
|
|
13
|
+
* you state.approve(item)/reject(item) then resume with run(agent, state). RunState
|
|
14
|
+
* serializes (state.toString() / RunState.fromString(agent, s)) — that's the durability:
|
|
15
|
+
* park the serialized state agent-side on `route`, resume on Decidio's approval.
|
|
16
|
+
*
|
|
17
|
+
* const state = result.state; // or RunState from the run
|
|
18
|
+
* const { resolved, pending } = await gateInterruptions(config, state, describe);
|
|
19
|
+
* if (pending.length) { await store.put(decisionId, state.toString()); return; } // suspend
|
|
20
|
+
* result = await run(agent, state); // all resolved → resume
|
|
21
|
+
* // on Decidio approval webhook: state = await RunState.fromString(agent, parked);
|
|
22
|
+
* // applyResume(state, item, verdict); result = await run(agent, state);
|
|
23
|
+
*
|
|
24
|
+
* Duck-typed on the state/item (no hard @openai/agents import) so it stays thin.
|
|
25
|
+
*
|
|
26
|
+
* (This wiring doc ships in the .d.ts — the README points here.)
|
|
27
|
+
*/
|
|
8
28
|
export interface Resolved {
|
|
9
29
|
item: ToolApprovalItem;
|
|
10
30
|
verdict: "approved" | "blocked";
|
|
@@ -14,9 +34,13 @@ export interface Pending {
|
|
|
14
34
|
item: ToolApprovalItem;
|
|
15
35
|
decisionId: string;
|
|
16
36
|
}
|
|
37
|
+
/** Ask Decidio for each pending tool-approval on a RunState.
|
|
38
|
+
* proceed → state.approve(item); block → state.reject(item); route → pending (a human
|
|
39
|
+
* decides via Decidio; the host parks state.toString() + resumes via applyResume). */
|
|
17
40
|
export declare function gateInterruptions(config: GuardConfig, state: RunStateLike, describe: (item: ToolApprovalItem) => ApprovalContext): Promise<{
|
|
18
41
|
resolved: Resolved[];
|
|
19
42
|
pending: Pending[];
|
|
20
43
|
}>;
|
|
44
|
+
/** Apply a Decidio verdict to a resumed RunState (after RunState.fromString). */
|
|
21
45
|
export declare function applyResume(state: RunStateLike, item: ToolApprovalItem, verdict: string): void;
|
|
22
46
|
export {};
|
|
@@ -1,6 +1,22 @@
|
|
|
1
1
|
import { type GuardConfig, type ApprovalContext } from "../index.js";
|
|
2
2
|
import { type GateAuth } from "./_gate.js";
|
|
3
|
+
/**
|
|
4
|
+
* @decidio/sdk/temporal — durable suspend via Temporal's native `condition()` + a
|
|
5
|
+
* Decidio resume signal. Strongest durability (the workflow survives worker restarts for
|
|
6
|
+
* days); the agent's action runs on resume. Requires @temporalio/workflow (optional peer).
|
|
7
|
+
*
|
|
8
|
+
* Inside your workflow:
|
|
9
|
+
* const verdicts = installDecidioSignal(); // wires the resume signal
|
|
10
|
+
* const out = await decidioGate(config, ctx, () => createOpp(o), verdicts, {
|
|
11
|
+
* authorize: () => executeActivity(authorizeActivity, ...), // HTTP belongs in activities
|
|
12
|
+
* confirm: (id, r) => executeActivity(confirmActivity, ...),
|
|
13
|
+
* });
|
|
14
|
+
* Decidio's webhook bridges to: handle.signal(decidioResumeSignal, decisionId, verdict, reason)
|
|
15
|
+
*
|
|
16
|
+
* (This wiring doc ships in the .d.ts — the README points here.)
|
|
17
|
+
*/
|
|
3
18
|
export declare const decidioResumeSignal: import("@temporalio/workflow").SignalDefinition<[string, string, (string | undefined)?]>;
|
|
19
|
+
/** Call inside the workflow to wire the resume signal; returns the verdict store. */
|
|
4
20
|
export declare function installDecidioSignal(): Map<string, {
|
|
5
21
|
verdict: string;
|
|
6
22
|
reason?: string;
|