feat(eve): introduce authorizeResponse hook, track authz state

[benpankow]

Summary

Adds optional authorization for the person responding to a tool approval. A tool can now optionally define authorizeResponse to verify that the authenticated responder may approve this specific call:

import { defineTool } from "eve/tools";
import { always } from "eve/tools/approval";

export default defineTool({
  description: "Refund a charge.",
  inputSchema: refundSchema,
  approval: {
    policy: always(),
    // authz impl, may be omitted for current no-authz behavior
    async authorizeResponse({ request, responder, session, auth }) {
      const identity = await auth.getToken(billingApproverAuth);

      if (
        await canApproveRefund({
          identity,
          responder,
          request,
          session,
        })
      ) {
        return "allowed";
      }

      return {
        status: "rejected",
        safeReason: "You are not permitted to approve this refund.",
      };
    },
  },
  async execute(input) {
    return refund(input);
  },
});

The callback receives:

• request: the stable approval request, tool call ID, tool name, and tool input;
• responder: the identity produced by the authenticated channel ingress;
• session: read-only session identity, initiator, turn, and parent lineage;
• auth: access to getToken and requireAuth, which utilizes existing authorization flow

If the responder needs to sign in, eve parks the approval, emits authorization.required, resumes the same responder-bound attempt after callback, and runs the currently deployed authorizer again.

TokenResult now exposes the account represented by the credential:

interface TokenResult {
  token: string;
  expiresAt?: number;
  providerSubject?: string;
}

For example, a GitHub authorization provider would return the responder's GitHub user ID .

Durable state

This PR adds framework-owned session state, separate from conversation history, for approval authorization. This holds pending approvals, records for failing/timing out/approved HITL attempts, and a final record which includes the approving/cancelling actor.

Behavioral choices

• Multiple responders can validate independently against the same request.
• Duplicate clicks from one responder are idempotent.
• The first approved candidate or authenticated Cancel settles atomically.
• Settled responses wait until every approval in the original model step is terminal before tool execution/model continuation resumes.

This PR does not contain Slack presentation or public candidate/settlement events; those are layered in the following PR.

Depends on the Approve/Cancel protocol PR: #1385.

Validation

Validated as part of the consolidated stack with:

• pnpm --filter eve typecheck
• pnpm --filter eve test:unit
• focused candidate, input-request, dynamic-tool, and tool-auth tests

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
eve-docs	Ready	Preview	Jul 30, 2026 6:20pm
eve-docs-4759	Ready	Preview, v0	Jul 30, 2026 6:20pm

[github-actions]

Bundle + Package Summary: apps/fixtures/weather-agent

Key takeaways

• No notable deltas vs ben/hitl-v2-approve-cancel (ec8ad62).

Delta vs ben/hitl-v2-approve-cancel (ec8ad62)

Area	Metric	Baseline	Current	Delta
Package	Packed tarball	7.62 MB	7.63 MB	+7.0 kB ⚠️
Package	Unpacked publish size	28.80 MB	28.83 MB	+29.4 kB ⚠️
Package	Installed footprint	91.28 MB	91.30 MB	+29.4 kB ⚠️
Package	Published files	2876	2882	+6
Package	Installed files	6665	6671	+6
Runtime	Unique function payloads	2	2	0
Runtime	Total function bytes	16.81 MB	16.85 MB	+40.9 kB ⚠️
Runtime	Public routes	11	11	0

Changed function payloads vs ben/hitl-v2-approve-cancel (ec8ad62) (2)

Function	Status	Baseline	Current	Delta	Route changes
functions/__server.func	changed	8.41 MB	8.43 MB	+20.4 kB ⚠️	none
functions/.well-known/workflow/v1/flow.func	changed	8.41 MB	8.43 MB	+20.4 kB ⚠️	none

eve init install

Metric	Baseline	Current	Delta
Installed footprint	129.68 MB	129.71 MB	+29.4 kB ⚠️
Installed packages	128	128	0
dependencies	4	4	0
devDependencies	2	2	0
Dependency package bytes	43.14 MB	43.17 MB	+29.4 kB ⚠️
devDependency package bytes	5.04 MB	5.04 MB	0 B ➖

Build Metadata

• Preset: vercel
• Nitro: nitro@3.0.260610-beta
• Output directory: apps/fixtures/weather-agent/.vercel/output
• Build metadata timestamp: 2026-07-30T18:23:51.105Z
• Route aliases: 11 public, 1 internal (12 total aliases)
• Vercel routes in config: 14
• Severity legend: 🔴 dominant/large, 🟠 notable, 🟡 watch, ⚪ small

Package Drill-Down

Package Details

• Package: eve@0.28.0
• Package directory: packages/eve
• Tarball: 7.63 MB (eve-0.28.0.tgz)
• Unpacked payload: 28.83 MB across 2882 published files
• Installed footprint: 91.30 MB across 6671 installed files
• Installed root package: 27.48 MB
• Installed dependencies: 63.83 MB
• Runtime dependencies: 2
• Peer dependencies: 5 (4 optional)

Installed footprint is measured from an isolated temporary npm install of the packed tarball.

Heavy installed dependencies

• eve: 27.48 MB (30.1%)
• @rolldown/binding-linux-x64-gnu: 19.28 MB (21.1%)
• @rolldown/binding-wasm32-wasi: 10.66 MB (11.7%)
• @napi-rs/wasm-runtime: 6.56 MB (7.2%)
• ai: 6.53 MB (7.2%)

Publish payload breakdown

Published file size
🔴 dist/src/compiled/shadcn-registry/index.js       [########################] 13.15 MB 45.6%
🟠 dist/src/compiled/experimental-ai-sdk-code-mo... [###.....................] 1.51 MB 5.2%
🟡 dist/src/compiled/@vercel/sandbox/index.js       [#.......................] 632.5 kB 2.2%
🟡 dist/src/compiled/_chunks/workflow/undici-DWL... [#.......................] 502.4 kB 1.7%
🟡 dist/src/compiled/@chat-adapter/slack/index.js   [#.......................] 440.5 kB 1.5%
🔴 Other published files                            [#######################.] 12.60 MB 43.7%

Installed footprint breakdown

Installed package size
🔴 eve                             [########################] 27.48 MB 30.1%
🔴 @rolldown/binding-linux-x64-gnu [#################.......] 19.28 MB 21.1%
🔴 @rolldown/binding-wasm32-wasi   [#########...............] 10.66 MB 11.7%
🔴 @napi-rs/wasm-runtime           [######..................] 6.56 MB 7.2%
🔴 ai                              [######..................] 6.53 MB 7.2%
🔴 zod                             [####....................] 5.07 MB 5.5%
🔴 Other installed packages        [##############..........] 15.73 MB 17.2%

Runtime dependencies (2)

Package	Range	Notes
nitro	3.0.260610-beta
undici	8.9.0

Peer dependencies (5)

Package	Range	Notes
@opentelemetry/api	^1.0.0	optional peer
ai	catalog:
braintrust	^3.0.0	optional peer
just-bash	^3.0.0	optional peer
microsandbox	^0.5.0	optional peer

eve init install drill-down

eve init install details

• Command: eve init my-agent
• Package manager: npm
• Installed footprint: 129.71 MB across 8539 installed files
• Installed packages: 128 total (122 transitive-only)
• dependencies: 4 direct packages totaling 43.17 MB
• devDependencies: 2 direct packages totaling 5.04 MB
• Other transitive package files: 81.50 MB

Installed footprint is measured from an isolated temporary eve init my-agent using the current packed eve tarball.

Heavy installed dependencies

• @typescript/typescript-linux-x64: 27.95 MB (21.5%)
• eve: 27.48 MB (21.2%)
• @rolldown/binding-linux-x64-gnu: 19.28 MB (14.9%)
• @rolldown/binding-wasm32-wasi: 10.66 MB (8.2%)
• zod: 9.02 MB (7.0%)

Installed footprint breakdown

Installed package size
🔴 @typescript/typescript-linux-x64 [########################] 27.95 MB 21.5%
🔴 eve                              [########################] 27.48 MB 21.2%
🔴 @rolldown/binding-linux-x64-gnu  [#################.......] 19.28 MB 14.9%
🔴 @rolldown/binding-wasm32-wasi    [#########...............] 10.66 MB 8.2%
🔴 zod                              [########................] 9.02 MB 7.0%
🔴 @napi-rs/wasm-runtime            [######..................] 6.56 MB 5.1%
🔴 ai                               [######..................] 6.53 MB 5.0%
🔴 Other installed packages         [###################.....] 22.23 MB 17.1%

dependencies (4)

Package	Range	Installed size	Share
@vercel/connect	0.4.2	135.8 kB	0.1%
ai	^7.0.38	6.53 MB	5.0%
eve	file:eve-0.28.0.tgz	27.48 MB	21.2%
zod	4.4.3	9.02 MB	7.0%

devDependencies (2)

Package	Range	Installed size	Share
@types/node	24.x	2.54 MB	2.0%
typescript	7.0.2	2.50 MB	1.9%

Function Drill-Down

Payload Size Graph

Unique function payload size and share of total
🔴 functions/.well-known/workflow/v1/flow.func     [########################] 8.43 MB 50.0%
🔴 functions/__server.func                         [########################] 8.43 MB 50.0%

Top Function Payloads

🟠 functions/.well-known/workflow/v1/flow.func • 1 public route • 8.43 MB

Metric	Value
Public routes	/.well-known/workflow/v1/flow
Runtime	nodejs24.x
Handler	index.mjs
Payload	8.43 MB
Function files	8.43 MB across 43 files
Traced dependencies	0 B
Signal	🟠 Bundled file index.mjs is 2.33 MB (27.6%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 index.mjs                       [########################] 2.33 MB 27.6%
🟠 _chunks/runtime-artifacts.mjs   [################........] 1.59 MB 18.9%
🟡 _libs/undici.mjs                [##########..............] 980.5 kB 11.6%
🟡 _chunks/sandbox.mjs             [########................] 768.8 kB 9.1%
🟡 _libs/@ai-sdk/gateway+[...].mjs [####....................] 432.8 kB 5.1%
🟠 Other bundled files             [########################] 2.32 MB 27.6%

🧾 Vercel Config

{
  "handler": "index.mjs",
  "launcherType": "Nodejs",
  "shouldAddHelpers": false,
  "supportsResponseStreaming": true,
  "runtime": "nodejs24.x",
  "maxDuration": "max",
  "experimentalTriggers": [
    {
      "type": "queue/v2beta",
      "topic": "__eve776561746865722d6167656e74_wkf_workflow_*",
      "consumer": "default",
      "retryAfterSeconds": 5,
      "initialDelaySeconds": 0
    }
  ],
  "environment": {
    "WORKFLOW_PRECONDITION_GUARD": "1"
  }
}

---

🟠 functions/__server.func • 10 public routes, 1 internal alias • 8.43 MB

Metric	Value
Public routes	/ /eve/v1/callback/[token] /eve/v1/connections/[name]/callback/[token] /eve/v1/health /eve/v1/info /eve/v1/session /eve/v1/session/[sessionId] /eve/v1/session/[sessionId]/cancel /eve/v1/session/[sessionId]/stream /eve/v1/session/reset
Internal aliases	/__server
Runtime	nodejs24.x
Handler	index.mjs
Payload	8.43 MB
Function files	8.43 MB across 43 files
Traced dependencies	0 B
Signal	🟠 Bundled file index.mjs is 2.33 MB (27.6%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 index.mjs                       [########################] 2.33 MB 27.6%
🟠 _chunks/runtime-artifacts.mjs   [################........] 1.59 MB 18.9%
🟡 _libs/undici.mjs                [##########..............] 980.5 kB 11.6%
🟡 _chunks/sandbox.mjs             [########................] 768.8 kB 9.1%
🟡 _libs/@ai-sdk/gateway+[...].mjs [####....................] 432.8 kB 5.1%
🟠 Other bundled files             [########################] 2.32 MB 27.6%

🧾 Vercel Config

{
  "handler": "index.mjs",
  "launcherType": "Nodejs",
  "shouldAddHelpers": false,
  "supportsResponseStreaming": true,
  "runtime": "nodejs24.x"
}

Build Timing: e2e/fixtures/agent-tools-sandbox

This is an informational timing measurement inside eve build, from preflight through publication. Output-size measurement and profile writing are excluded.

Build mode: deployable Vercel build with sandbox template prewarm included.

• Build pipeline: 2.09 s -> 2.06 s (-30.6 ms) vs ben/hitl-v2-approve-cancel (ec8ad62).
• Timing is informational: shared GitHub runners are too variable for a hard timing budget.

Detailed phase timings vs `ben/hitl-v2-approve-cancel (ec8ad62)`

Phase	Baseline	Current	Delta
extension.check	11.2 ms	11.9 ms	+0.7 ms
project.resolve	3.7 ms	1.4 ms	-2.3 ms
workspace.create	1.4 ms	1.2 ms	-0.2 ms
host.prepare	201.3 ms	179.7 ms	-21.6 ms
vercel.service-prefix.resolve	2.2 ms	2.6 ms	+0.4 ms
nitro.create	205.0 ms	213.8 ms	+8.8 ms
sandbox.prewarm	331.7 ms	276.3 ms	-55.4 ms
nitro.cache.prepare	0.3 ms	0.3 ms	0.0 ms
nitro.prepare	0.9 ms	0.9 ms	0.0 ms
nitro.public-assets	0.8 ms	0.9 ms	+0.1 ms
nitro.prerender	0.6 ms	0.5 ms	-0.1 ms
nitro.bundle	1.30 s	1.34 s	+41.0 ms
nitro.cache.write	0.7 ms	0.5 ms	-0.2 ms
vercel.workflow-function.materialize	23.6 ms	21.4 ms	-2.2 ms
agent-summary.emit	0.5 ms	0.5 ms	0.0 ms
nitro.close	0.1 ms	0.1 ms	0.0 ms
output.publish	3.5 ms	3.7 ms	+0.2 ms
workspace.remove	2.3 ms	2.4 ms	+0.1 ms