test(e2e): cover authorized approval responses

[benpankow]

Summary

Adds fixture-owned e2e coverage for the responder-authorized HITL lifecycle introduced by this stack.

The deterministic fixture authenticates the eval driver as a fixed user and defines a tool with explicit request and response policies:

approval: {
  request: always(),
  response: ({ response, responder }) =>
    response.decision === "approve" && responder.principalId === "e2e-approval-responder"
      ? { status: "allowed" }
      : { status: "rejected", safeReason: "Unexpected eval responder." },
}

The eval asserts:

input.requested
→ approval.candidate pending
→ approval.settled approved
→ action.result completed

It uses no external OAuth provider or injected credential, so the result is deterministic and self-contained.

This also adds compiler/runtime normalization coverage for the explicit { request, response } approval object; previously only the function shorthand was accepted by runtime normalization even though the public type allowed the object form.

Depends on #1374.

Validation

• pnpm --filter agent-tools-hitl typecheck
• pnpm --filter eve typecheck
• pnpm guard:invariants
• focused authored-definition unit tests

[vercel]

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

Project	Deployment	Actions	Updated (UTC)
eve-docs	Ready	Preview	Aug 7, 2026 10:47pm
eve-docs-4759	Ready	Preview, v0	Aug 7, 2026 10:47pm

[github-actions]

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

Key takeaways

• No notable deltas vs ben/hitl-v2-docs-contracts (25a9558).

Delta vs ben/hitl-v2-docs-contracts (25a9558)

Area	Metric	Baseline	Current	Delta
Package	Packed tarball	7.64 MB	7.64 MB	+363 B ⚠️
Package	Unpacked publish size	28.65 MB	28.65 MB	+597 B ⚠️
Package	Installed footprint	71.98 MB	71.98 MB	+597 B ⚠️
Package	Published files	3012	3014	+2
Package	Installed files	6711	6713	+2
Runtime	Unique function payloads	2	2	0
Runtime	Total function bytes	16.91 MB	16.91 MB	-40 B ✅
Runtime	Public routes	13	13	0

Changed function payloads vs ben/hitl-v2-docs-contracts (25a9558) (2)

Function	Status	Baseline	Current	Delta	Route changes
functions/__server.func	changed	8.46 MB	8.46 MB	-20 B ✅	none
functions/.well-known/workflow/v1/flow.func	changed	8.46 MB	8.46 MB	-20 B ✅	none

eve init install

Metric	Baseline	Current	Delta
Installed footprint	110.39 MB	110.39 MB	+597 B ⚠️
Installed packages	121	121	0
dependencies	4	4	0
devDependencies	2	2	0
Dependency package bytes	43.06 MB	43.06 MB	+597 B ⚠️
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: 2026-08-05T15:29:50.920Z
• Route aliases: 13 public, 1 internal (14 total aliases)
• Vercel routes in config: 16
• Severity legend: 🔴 dominant/large, 🟠 notable, 🟡 watch, ⚪ small

Package Drill-Down

Package Details

• Package: eve@0.30.2
• Package directory: packages/eve
• Tarball: 7.64 MB (eve-0.30.2.tgz)
• Unpacked payload: 28.65 MB across 3014 published files
• Installed footprint: 71.98 MB across 6713 installed files
• Installed root package: 27.29 MB
• Installed dependencies: 44.68 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: 27.29 MB (37.9%)
• @rolldown/binding-linux-x64-gnu: 19.35 MB (26.9%)
• ai: 6.60 MB (9.2%)
• zod: 5.07 MB (7.0%)
• undici: 3.50 MB (4.9%)

Publish payload breakdown

Published file size
🔴 dist/src/compiled/shadcn-registry/index.js       [#################.......] 9.68 MB 33.8%
🟠 dist/src/compiled/@photon-ai/chat-adapter-ime... [####....................] 2.42 MB 8.5%
🟠 dist/src/compiled/experimental-ai-sdk-code-mo... [###.....................] 1.51 MB 5.3%
🟡 dist/src/compiled/_chunks/node/undici-DWL_MYm... [#.......................] 502.4 kB 1.8%
🟡 dist/src/compiled/_chunks/workflow/undici-DWL... [#.......................] 502.4 kB 1.8%
🔴 Other published files                            [########################] 14.03 MB 49.0%

Installed footprint breakdown

Installed package size
🔴 eve                             [########################] 27.29 MB 37.9%
🔴 @rolldown/binding-linux-x64-gnu [#################.......] 19.35 MB 26.9%
🔴 ai                              [######..................] 6.60 MB 9.2%
🔴 zod                             [####....................] 5.07 MB 7.0%
🟠 undici                          [###.....................] 3.50 MB 4.9%
🟠 nitro                           [##......................] 2.41 MB 3.3%
🔴 Other installed packages        [#######.................] 7.76 MB 10.8%

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: 110.39 MB across 8589 installed files
• Installed packages: 121 total (115 transitive-only)
• dependencies: 4 direct packages totaling 43.06 MB
• devDependencies: 2 direct packages totaling 5.04 MB
• Other transitive package files: 62.29 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 (25.3%)
• eve: 27.29 MB (24.7%)
• @rolldown/binding-linux-x64-gnu: 19.35 MB (17.5%)
• zod: 9.02 MB (8.2%)
• ai: 6.60 MB (6.0%)

Installed footprint breakdown

Installed package size
🔴 @typescript/typescript-linux-x64 [########################] 27.95 MB 25.3%
🔴 eve                              [#######################.] 27.29 MB 24.7%
🔴 @rolldown/binding-linux-x64-gnu  [#################.......] 19.35 MB 17.5%
🔴 zod                              [########................] 9.02 MB 8.2%
🔴 ai                               [######..................] 6.60 MB 6.0%
🟠 undici                           [###.....................] 3.50 MB 3.2%
🔴 Other installed packages         [##############..........] 16.67 MB 15.1%

dependencies (4)

Package	Range	Installed size	Share
@vercel/connect	0.4.3	141.0 kB	0.1%
ai	^7.0.38	6.60 MB	6.0%
eve	file:eve-0.30.2.tgz	27.29 MB	24.7%
zod	4.4.3	9.02 MB	8.2%

devDependencies (2)

Package	Range	Installed size	Share
@types/node	24.x	2.54 MB	2.3%
typescript	7.0.2	2.50 MB	2.3%

Function Drill-Down

Payload Size Graph

Unique function payload size and share of total
🔴 functions/.well-known/workflow/v1/flow.func     [########################] 8.46 MB 50.0%
🔴 functions/__server.func                         [########################] 8.46 MB 50.0%

Top Function Payloads

🟠 functions/.well-known/workflow/v1/flow.func • 1 public route • 8.46 MB

Metric	Value
Public routes	/.well-known/workflow/v1/flow
Runtime	nodejs24.x
Handler	index.mjs
Payload	8.46 MB
Function files	8.46 MB across 43 files
Traced dependencies	0 B
Signal	🟠 Bundled file index.mjs is 2.28 MB (26.9%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 index.mjs                       [#######################.] 2.28 MB 26.9%
🟠 _chunks/runtime-artifacts.mjs   [################........] 1.61 MB 19.1%
🟡 _libs/undici.mjs                [##########..............] 980.5 kB 11.6%
🟡 _chunks/sandbox.mjs             [########................] 769.0 kB 9.1%
🟡 _libs/@ai-sdk/gateway+[...].mjs [####....................] 432.8 kB 5.1%
🟠 Other bundled files             [########################] 2.38 MB 28.2%

🧾 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 • 12 public routes, 1 internal alias • 8.46 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/clear /eve/v1/session/compact /eve/v1/session/reset
Internal aliases	/__server
Runtime	nodejs24.x
Handler	index.mjs
Payload	8.46 MB
Function files	8.46 MB across 43 files
Traced dependencies	0 B
Signal	🟠 Bundled file index.mjs is 2.28 MB (26.9%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 index.mjs                       [#######################.] 2.28 MB 26.9%
🟠 _chunks/runtime-artifacts.mjs   [################........] 1.61 MB 19.1%
🟡 _libs/undici.mjs                [##########..............] 980.5 kB 11.6%
🟡 _chunks/sandbox.mjs             [########................] 769.0 kB 9.1%
🟡 _libs/@ai-sdk/gateway+[...].mjs [####....................] 432.8 kB 5.1%
🟠 Other bundled files             [########################] 2.38 MB 28.2%

🧾 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: 1.80 s -> 1.71 s (-93.3 ms) vs ben/hitl-v2-docs-contracts (25a9558).
• Timing is informational: shared GitHub runners are too variable for a hard timing budget.

Detailed phase timings vs `ben/hitl-v2-docs-contracts (25a9558)`

Phase	Baseline	Current	Delta
extension.check	7.2 ms	9.1 ms	+1.9 ms
project.resolve	1.4 ms	3.5 ms	+2.1 ms
workspace.create	14.2 ms	0.9 ms	-13.3 ms
host.prepare	143.2 ms	146.2 ms	+3.0 ms
vercel.service-prefix.resolve	1.5 ms	1.7 ms	+0.2 ms
nitro.create	179.5 ms	146.9 ms	-32.6 ms
sandbox.prewarm	267.5 ms	245.4 ms	-22.1 ms
nitro.cache.prepare	0.2 ms	0.2 ms	0.0 ms
nitro.prepare	0.6 ms	0.6 ms	0.0 ms
nitro.public-assets	0.6 ms	0.6 ms	0.0 ms
nitro.prerender	1.2 ms	0.4 ms	-0.8 ms
nitro.bundle	1.13 s	1.10 s	-33.8 ms
nitro.cache.write	0.3 ms	0.3 ms	0.0 ms
vercel.workflow-function.materialize	46.6 ms	37.4 ms	-9.2 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	2.7 ms	14.0 ms	+11.3 ms
workspace.remove	1.4 ms	1.5 ms	+0.1 ms

[vercel]

Additional Suggestions:

1. Object-form connection approval ({ request, response? }) is silently dropped at runtime, removing the human-in-the-loop approval gate.

2. Runtime tool resolver rejects object-form { request, response } approval, throwing on any tool that declares approval as an object instead of a function.