Skip to content

fix(eve): guard late approval resume transcript - #1727

Open
ruiconti wants to merge 2 commits into
mainfrom
rui/hitl-late-approval-resume
Open

fix(eve): guard late approval resume transcript#1727
ruiconti wants to merge 2 commits into
mainfrom
rui/hitl-late-approval-resume

Conversation

@ruiconti

@ruiconti ruiconti commented Aug 6, 2026

Copy link
Copy Markdown
Contributor

What

Expand the stage-1 acceptance gate from #1578 across both real AI SDK execution surfaces:

  • immediate approval baseline;
  • approval after two complete intervening turns;
  • denial after an intervening turn;
  • one shared suffix containing two approvals with mixed approve/deny outcomes;
  • streaming resume after an intervening turn.

Each case asserts tool execution, canonical or denied output, durable history, and pending-state cleanup. The suffix-group case asserts exact call/response/result cardinality and order so duplicated stored suffixes cannot pass through SDK call-ID deduplication.

Data flow

Before: approval resume coverage restored one stored suffix directly after the original user message. Nothing exercised intervening turns, denial, grouped requests, or the streaming surface.

After: committed turns remain ahead of the restored suffix; eve appends the approval response at the tail; approved tools execute once, denied tools do not execute, and generation continues with the complete history intact.

Scope

Test-only acceptance gate for #1578. It validates AI SDK core through the real ToolLoopAgent.generate and .stream paths with MockLanguageModelV4. It does not claim to fix or validate the OpenAI-specific provider converter in #1658.

Signed-off-by: Rui Conti <ruiconti@gmail.com>
@vercel

vercel Bot commented Aug 6, 2026

Copy link
Copy Markdown
Contributor

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

Project Deployment Actions Updated (UTC)
eve-docs Ready Ready Preview Aug 6, 2026 7:36pm
eve-docs-4759 Ready Ready Preview, v0 Aug 6, 2026 7:36pm

@github-actions

github-actions Bot commented Aug 6, 2026

Copy link
Copy Markdown
Contributor

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

Key takeaways

  • No notable deltas vs main (19862cc).

Delta vs main (19862cc)

Area Metric Baseline Current Delta
Package Packed tarball 7.66 MB 7.66 MB +259 B ⚠️
Package Unpacked publish size 28.70 MB 28.70 MB 0 B ➖
Package Installed footprint 72.08 MB 72.08 MB 0 B ➖
Package Published files 3036 3036 0
Package Installed files 6744 6744 0
Runtime Unique function payloads 2 2 0
Runtime Total function bytes 16.99 MB 16.99 MB -40 B ✅
Runtime Public routes 13 13 0
Changed function payloads vs main (19862cc) (2)
Function Status Baseline Current Delta Route changes
functions/__server.func changed 8.49 MB 8.49 MB -20 B ✅ none
functions/.well-known/workflow/v1/flow.func changed 8.50 MB 8.50 MB -20 B ✅ none

eve init install

Metric Baseline Current Delta
Installed footprint 110.49 MB 110.49 MB 0 B ➖
Installed packages 121 121 0
dependencies 4 4 0
devDependencies 2 2 0
Dependency package bytes 43.16 MB 43.16 MB 0 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: 2026-08-06T17:10:12.199Z
  • 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@0.31.0
  • Package directory: packages/eve
  • Tarball: 7.66 MB (eve-0.31.0.tgz)
  • Unpacked payload: 28.70 MB across 3036 published files
  • Installed footprint: 72.08 MB across 6744 installed files
  • Installed root package: 27.34 MB
  • Installed dependencies: 44.74 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: 27.34 MB (37.9%)
  • @rolldown/binding-linux-x64-gnu: 19.35 MB (26.8%)
  • ai: 6.65 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 33.7%
🟠 dist/src/compiled/@photon-ai/chat-adapter-ime... [####....................] 2.42 MB 8.4%
🟠 dist/src/compiled/experimental-ai-sdk-code-mo... [###.....................] 1.51 MB 5.2%
🟡 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                            [########################] 14.08 MB 49.1%
Installed footprint breakdown
Installed package size
🔴 eve                             [########################] 27.34 MB 37.9%
🔴 @rolldown/binding-linux-x64-gnu [#################.......] 19.35 MB 26.8%
🔴 ai                              [######..................] 6.65 MB 9.2%
🔴 zod                             [####....................] 5.07 MB 7.0%
🟠 undici                          [###.....................] 3.50 MB 4.9%
🟠 nitro                           [##......................] 2.41 MB 3.3%
🔴 Other installed packages        [#######.................] 7.77 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: 110.49 MB across 8620 installed files
  • Installed packages: 121 total (115 transitive-only)
  • dependencies: 4 direct packages totaling 43.16 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: 27.34 MB (24.7%)
  • @rolldown/binding-linux-x64-gnu: 19.35 MB (17.5%)
  • zod: 9.02 MB (8.2%)
  • ai: 6.65 MB (6.0%)
Installed footprint breakdown
Installed package size
🔴 @typescript/typescript-linux-x64 [########################] 27.95 MB 25.3%
🔴 eve                              [#######################.] 27.34 MB 24.7%
🔴 @rolldown/binding-linux-x64-gnu  [#################.......] 19.35 MB 17.5%
🔴 zod                              [########................] 9.02 MB 8.2%
🔴 ai                               [######..................] 6.65 MB 6.0%
🟠 undici                           [###.....................] 3.50 MB 3.2%
🔴 Other installed packages         [##############..........] 16.68 MB 15.1%
dependencies (4)
Package Range Installed size Share
@vercel/connect 0.4.3 141.0 kB 0.1%
ai ^7.0.38 6.65 MB 6.0%
eve file:eve-0.31.0.tgz 27.34 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     [########################] 8.50 MB 50.0%
🔴 functions/__server.func                         [########################] 8.49 MB 50.0%

Top Function Payloads

🟠 functions/.well-known/workflow/v1/flow.func • 1 public route • 8.50 MB
Metric Value
Public routes /.well-known/workflow/v1/flow
Runtime nodejs24.x
Handler index.mjs
Payload 8.50 MB
Function files 8.50 MB across 43 files
Traced dependencies 0 B
Signal 🟠 Bundled file index.mjs is 2.31 MB (27.2%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 index.mjs                       [#######################.] 2.31 MB 27.2%
🟠 _chunks/runtime-artifacts.mjs   [################........] 1.62 MB 19.0%
🟡 _libs/undici.mjs                [##########..............] 980.5 kB 11.5%
🟡 _chunks/sandbox.mjs             [########................] 769.0 kB 9.1%
🟡 _libs/@ai-sdk/gateway+[...].mjs [####....................] 432.8 kB 5.1%
🟠 Other bundled files             [########################] 2.38 MB 28.0%

🧾 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 • 8.49 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]/clear
/eve/v1/session/[sessionId]/compact
/eve/v1/session/[sessionId]/reset
/eve/v1/session/[sessionId]/stream
Internal aliases /__server
Runtime nodejs24.x
Handler index.mjs
Payload 8.49 MB
Function files 8.49 MB across 43 files
Traced dependencies 0 B
Signal 🟠 Bundled file index.mjs is 2.31 MB (27.2%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 index.mjs                       [#######################.] 2.31 MB 27.2%
🟠 _chunks/runtime-artifacts.mjs   [################........] 1.62 MB 19.0%
🟡 _libs/undici.mjs                [##########..............] 980.5 kB 11.5%
🟡 _chunks/sandbox.mjs             [########................] 769.0 kB 9.1%
🟡 _libs/@ai-sdk/gateway+[...].mjs [####....................] 432.8 kB 5.1%
🟠 Other bundled files             [########################] 2.38 MB 28.0%

🧾 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: 2.19 s -> 2.11 s (-79.0 ms) vs main (19862cc).
  • Timing is informational: shared GitHub runners are too variable for a hard timing budget.
Detailed phase timings vs `main (19862cc)`
Phase Baseline Current Delta
extension.check 7.1 ms 9.2 ms +2.1 ms
project.resolve 1.3 ms 3.5 ms +2.2 ms
workspace.create 2.6 ms 4.3 ms +1.7 ms
host.prepare 182.8 ms 174.8 ms -8.0 ms
vercel.service-prefix.resolve 4.4 ms 2.7 ms -1.7 ms
nitro.create 216.0 ms 218.3 ms +2.3 ms
sandbox.prewarm 308.4 ms 261.4 ms -47.0 ms
nitro.cache.prepare 0.2 ms 0.4 ms +0.2 ms
nitro.prepare 0.8 ms 0.9 ms +0.1 ms
nitro.public-assets 0.8 ms 0.8 ms 0.0 ms
nitro.prerender 0.5 ms 0.6 ms +0.1 ms
nitro.bundle 1.43 s 1.40 s -28.3 ms
nitro.cache.write 0.5 ms 0.4 ms -0.1 ms
vercel.workflow-function.materialize 26.5 ms 24.2 ms -2.3 ms
agent-summary.emit 0.6 ms 0.5 ms -0.1 ms
nitro.close 0.1 ms 0.1 ms 0.0 ms
output.publish 3.8 ms 3.4 ms -0.4 ms
workspace.remove 2.4 ms 2.4 ms 0.0 ms

Signed-off-by: Rui Conti <ruiconti@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant