Skip to content

fix(eve): offer to repair failed self-modifications - #3294

Draft
benpankow wants to merge 1 commit into
mainfrom
benpankow/submod-fix
Draft

benpankow wants to merge 1 commit into
mainfrom
benpankow/submod-fix

Conversation

@benpankow

Copy link
Copy Markdown
Collaborator

Summary

When a self-modification later fails or behaves incorrectly, the parent now offers to send it back to self-mod for repair. For now this is conservative: it requires confirmation and only applies to failures tied to a prior self-modification. We may want to offer self-mod repair after any tool failure once we have a good way to avoid irrelevant suggestions.

Validation

Adds a unit test for the repair offer and confirmation requirement.

🤖

Signed-off-by: benpankow <ben.pankow@vercel.com>
@vercel

vercel Bot commented Sep 11, 2026

Copy link
Copy Markdown
Contributor

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

Project Deployment Actions Updated
eve-docs Ready Ready Preview, v0 Sep 11, 2026 6:56pm UTC
eve-docs-4759 Ready Ready Preview, v0 Sep 11, 2026 6:56pm UTC
eve-pkg Ready Ready Preview, v0 Sep 11, 2026 6:56pm UTC

@github-actions

Copy link
Copy Markdown
Contributor

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

Key takeaways

  • No notable deltas vs main (109a699).

Delta vs main (109a699)

Area Metric Baseline Current Delta
Package Packed tarball 8.76 MB 8.76 MB +42 B ⚠️
Package Unpacked publish size 33.01 MB 33.01 MB +192 B ⚠️
Package Installed footprint 78.50 MB 78.50 MB +192 B ⚠️
Package Published files 3945 3945 0
Package Installed files 7862 7862 0
Package Installed package instances 33 33 0
Package Distinct installed package names 32 32 0
Package Installed dependency edges 51 51 0
Package Installed optional peer edges 8 8 0
Runtime Unique function payloads 2 2 0
Runtime Total function bytes 21.11 MB 21.11 MB -80 B ✅
Runtime Public routes 18 18 0
Changed function payloads vs main (109a699) (2)
Function Status Baseline Current Delta Route changes
functions/__server.func changed 10.56 MB 10.56 MB -40 B ✅ none
functions/.well-known/workflow/v1/flow.func changed 10.56 MB 10.56 MB -40 B ✅ none

eve init install

Metric Baseline Current Delta
Installed footprint 116.60 MB 116.61 MB +192 B ⚠️
Installed packages 113 113 0
dependencies 4 4 0
devDependencies 2 2 0
Dependency package bytes 49.20 MB 49.20 MB +192 B ⚠️
devDependency package bytes 5.04 MB 5.04 MB 0 B ➖
Build Metadata
  • Preset: vercel
  • Nitro: nitro@3.0.260903-beta
  • Output directory: apps/fixtures/weather-agent/.vercel/output
  • Build metadata timestamp: 2026-09-11T18:56:04.983Z
  • Route aliases: 18 public, 1 internal (19 total aliases)
  • Vercel routes in config: 21
  • Severity legend: 🔴 dominant/large, 🟠 notable, 🟡 watch, ⚪ small
Package Drill-Down

Package Details

  • Package: eve@0.54.2
  • Package directory: packages/eve
  • Tarball: 8.76 MB (eve-0.54.2.tgz)
  • Unpacked payload: 33.01 MB across 3945 published files
  • Installed footprint: 78.50 MB across 7862 installed files
  • Installed root package: 31.58 MB
  • Installed dependencies: 46.92 MB
  • Installed package instances: 33
  • Distinct installed package names: 32
  • Installed dependency edges: 51
  • Installed optional peer edges: 8
  • Runtime dependencies: 2
  • Peer dependencies: 6 (5 optional)

Installed footprint is measured from an isolated temporary npm install of the packed tarball.
Graph metrics read only package.json files in package directories directly beneath a node_modules boundary, including nested boundaries. Each directory is one package instance; distinct names come from those manifests. Dependency edges count each unique name in dependencies or optionalDependencies per instance; optional peer edges count peerDependencies marked optional.

Heavy installed dependencies

  • eve: 31.58 MB (40.2%)
  • @rolldown/binding-linux-x64-gnu: 19.31 MB (24.6%)
  • ai: 7.08 MB (9.0%)
  • zod: 6.74 MB (8.6%)
  • undici: 3.51 MB (4.5%)
Publish payload breakdown
Published file size
🔴 dist/src/compiled/shadcn-registry/index.js       [#############...........] 9.76 MB 29.6%
🟠 dist/src/compiled/@photon-ai/chat-adapter-ime... [###.....................] 2.27 MB 6.9%
🟠 dist/src/compiled/@ai-sdk/code-mode/index.js     [#.......................] 1.03 MB 3.1%
🟡 dist/src/compiled/@vercel/blob/index.js          [#.......................] 901.4 kB 2.7%
🟡 dist/src/compiled/_chunks/workflow/signal-exi... [#.......................] 514.6 kB 1.6%
🔴 Other published files                            [########################] 18.54 MB 56.2%
Installed footprint breakdown
Installed package size
🔴 eve                             [########################] 31.58 MB 40.2%
🔴 @rolldown/binding-linux-x64-gnu [###############.........] 19.31 MB 24.6%
🔴 ai                              [#####...................] 7.08 MB 9.0%
🔴 zod                             [#####...................] 6.74 MB 8.6%
🟠 undici                          [###.....................] 3.51 MB 4.5%
🟠 nitro                           [#.......................] 1.89 MB 2.4%
🔴 Other installed packages        [######..................] 8.37 MB 10.7%
Runtime dependencies (2)
Package Range Notes
nitro 3.0.260903-beta
undici 8.9.0
Peer dependencies (6)
Package Range Notes
@opentelemetry/api ^1.0.0 optional peer
ai catalog:
braintrust ^3.0.0 optional peer
dd-trace ^6.13.0 optional peer
just-bash ^3.1.0 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: 116.61 MB across 9746 installed files
  • Installed packages: 113 total (107 transitive-only)
  • dependencies: 4 direct packages totaling 49.20 MB
  • devDependencies: 2 direct packages totaling 5.04 MB
  • Other transitive package files: 62.36 MB

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

Heavy installed dependencies

  • eve: 31.58 MB (27.1%)
  • @typescript/typescript-linux-x64: 27.95 MB (24.0%)
  • @rolldown/binding-linux-x64-gnu: 19.31 MB (16.6%)
  • zod: 10.37 MB (8.9%)
  • ai: 7.08 MB (6.1%)
Installed footprint breakdown
Installed package size
🔴 eve                              [########################] 31.58 MB 27.1%
🔴 @typescript/typescript-linux-x64 [#####################...] 27.95 MB 24.0%
🔴 @rolldown/binding-linux-x64-gnu  [###############.........] 19.31 MB 16.6%
🔴 zod                              [########................] 10.37 MB 8.9%
🔴 ai                               [#####...................] 7.08 MB 6.1%
🟠 undici                           [###.....................] 3.51 MB 3.0%
🔴 Other installed packages         [#############...........] 16.80 MB 14.4%
dependencies (4)
Package Range Installed size Share
@vercel/connect 1.0.0 167.9 kB 0.1%
ai ^7.0.93 7.08 MB 6.1%
eve file:eve-0.54.2.tgz 31.58 MB 27.1%
zod 4.5.4 10.37 MB 8.9%
devDependencies (2)
Package Range Installed size Share
@types/node 24.x 2.54 MB 2.2%
typescript 7.0.2 2.50 MB 2.1%
Function Drill-Down

Payload Size Graph

Unique function payload size and share of total
🔴 functions/.well-known/workflow/v1/flow.func     [########################] 10.56 MB 50.0%
🔴 functions/__server.func                         [########################] 10.56 MB 50.0%

Top Function Payloads

🟠 functions/.well-known/workflow/v1/flow.func • 1 public route • 10.56 MB
Metric Value
Public routes /.well-known/workflow/v1/flow
Runtime nodejs24.x
Handler index.mjs
Payload 10.56 MB
Function files 10.56 MB across 114 files
Traced dependencies 0 B
Signal 🟠 Bundled file index.mjs is 2.38 MB (22.6%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 index.mjs                        [###########.............] 2.38 MB 22.6%
🟡 _libs/undici.mjs                 [#####...................] 980.8 kB 9.3%
🟡 _chunks/esm-Fqlolk7e.mjs         [###.....................] 723.3 kB 6.9%
🟡 _chunks/chatgpt-model.mjs        [###.....................] 699.5 kB 6.6%
🟡 _chunks/signal-exit-Dsy-TT0V.mjs [###.....................] 616.2 kB 5.8%
🔴 Other bundled files              [########################] 5.16 MB 48.8%

🧾 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 • 17 public routes, 1 internal alias • 10.56 MB
Metric Value
Public routes /
/.well-known/workflow/v1/webhook/[token]
/eve/v1/activity/[token]
/eve/v1/callback/[token]
/eve/v1/connections/[name]/callback/[attemptId]/[token]
/eve/v1/connections/[name]/callback/[token]
/eve/v1/health
/eve/v1/info
/eve/v1/session
/eve/v1/session/[parentSessionId]/subagents/[callId]/[childSessionId]/stream
/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
/eve/v1/task-input/[token]
Internal aliases /__server
Runtime nodejs24.x
Handler index.mjs
Payload 10.56 MB
Function files 10.56 MB across 114 files
Traced dependencies 0 B
Signal 🟠 Bundled file index.mjs is 2.38 MB (22.6%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 index.mjs                        [###########.............] 2.38 MB 22.6%
🟡 _libs/undici.mjs                 [#####...................] 980.8 kB 9.3%
🟡 _chunks/esm-Fqlolk7e.mjs         [###.....................] 723.3 kB 6.9%
🟡 _chunks/chatgpt-model.mjs        [###.....................] 699.5 kB 6.6%
🟡 _chunks/signal-exit-Dsy-TT0V.mjs [###.....................] 616.2 kB 5.8%
🔴 Other bundled files              [########################] 5.16 MB 48.8%

🧾 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: 4.16 s -> 3.96 s (-196.6 ms) vs main (109a699).
  • Timing is informational: shared GitHub runners are too variable for a hard timing budget.
Detailed phase timings vs `main (109a699)`
Phase Baseline Current Delta
extension.check 0.6 ms 0.6 ms 0.0 ms
project.resolve 0.2 ms 0.2 ms 0.0 ms
workspace.create 0.3 ms 0.4 ms +0.1 ms
host.prepare 368.6 ms 354.3 ms -14.3 ms
vercel.service-prefix.resolve 1.1 ms 2.9 ms +1.8 ms
nitro.create 324.6 ms 364.1 ms +39.5 ms
sandbox.prewarm 473.6 ms 325.0 ms -148.6 ms
nitro.cache.prepare 0.9 ms 0.2 ms -0.7 ms
nitro.prepare 2.4 ms 0.5 ms -1.9 ms
nitro.public-assets 0.7 ms 0.5 ms -0.2 ms
nitro.prerender 0.4 ms 0.3 ms -0.1 ms
nitro.bundle 2.88 s 2.83 s -46.1 ms
nitro.cache.write 0.2 ms 0.3 ms +0.1 ms
vercel.workflow-function.materialize 98.4 ms 67.1 ms -31.3 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 4.9 ms 10.3 ms +5.4 ms
workspace.remove 1.1 ms 1.1 ms 0.0 ms

"eve": patch
---

When a self-modification later fails or behaves incorrectly, agents now offer to send the issue back for repair instead of leaving users to discover the recovery path. Repairs still require user confirmation and do not start automatically.

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The release note addresses readers as “users” twice and the first sentence is long and indirect. Please use direct address and tighten the behavior description. For example: “When a self-modification later fails or behaves incorrectly, the agent now offers to delegate a repair. It waits for your confirmation before starting.”

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