Skip to content

feat(eve): add local self-modification - #1396

Open
prha wants to merge 1 commit into
mainfrom
prha/1_selfmod_local_subagent
Open

feat(eve): add local self-modification#1396
prha wants to merge 1 commit into
mainfrom
prha/1_selfmod_local_subagent

Conversation

@prha

@prha prha commented Jul 30, 2026

Copy link
Copy Markdown
Contributor

Description

Adds the framework-owned local development editing primitive. In local development, an agent can stage source changes for approval and apply approved bytes atomically without mutating authored files while a proposal is being generated.

This PR provides staging, stale-proposal checks, abuse limits, atomic application, rollback handling, and the core runtime plumbing. Approval and trusted review are added by the subsequent stacked PRs.

Addresses #742

How did you test your changes?

  • Focused unit, integration, and scenario tests for staging, application, sandbox behavior, and compilation.
  • pnpm typecheck
  • pnpm lint
  • pnpm guard:invariants
  • pnpm docs:check

PR Checklist

  • I linked an issue with prior discussion confirming this change is wanted
  • I ran the relevant checks from CONTRIBUTING.md
  • I added tests and documentation where relevant
  • I added a changeset if this touches the published eve package
  • DCO sign-off passes for every commit (git commit --signoff)

@vercel

vercel Bot commented Jul 30, 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 Jul 30, 2026 8:48pm
eve-docs-4759 Ready Ready Preview, v0 Jul 30, 2026 8:48pm

prha commented Jul 30, 2026

Copy link
Copy Markdown
Contributor Author

@github-actions

github-actions Bot commented Jul 30, 2026

Copy link
Copy Markdown
Contributor

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

Key takeaways

  • No notable deltas vs main (438ae8a).

Delta vs main (438ae8a)

Area Metric Baseline Current Delta
Package Packed tarball 7.62 MB 7.63 MB +3.0 kB ⚠️
Package Unpacked publish size 28.79 MB 28.80 MB +13.2 kB ⚠️
Package Installed footprint 91.26 MB 91.28 MB +13.2 kB ⚠️
Package Published files 2868 2878 +10
Package Installed files 6657 6667 +10
Runtime Unique function payloads 2 2 0
Runtime Total function bytes 16.81 MB 16.82 MB +2.5 kB ⚠️
Runtime Public routes 11 11 0
Changed function payloads vs main (438ae8a) (2)
Function Status Baseline Current Delta Route changes
functions/__server.func changed 8.41 MB 8.41 MB +1.3 kB ⚠️ none
functions/.well-known/workflow/v1/flow.func changed 8.41 MB 8.41 MB +1.3 kB ⚠️ none

eve init install

Metric Baseline Current Delta
Installed footprint 129.67 MB 129.68 MB +13.2 kB ⚠️
Installed packages 128 128 0
dependencies 4 4 0
devDependencies 2 2 0
Dependency package bytes 43.13 MB 43.14 MB +13.2 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: 2026-07-30T20:49:23.862Z
  • 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@0.29.0
  • Package directory: packages/eve
  • Tarball: 7.63 MB (eve-0.29.0.tgz)
  • Unpacked payload: 28.80 MB across 2878 published files
  • Installed footprint: 91.28 MB across 6667 installed files
  • Installed root package: 27.45 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: 27.45 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 45.7%
🟠 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                            [#######################.] 12.57 MB 43.6%
Installed footprint breakdown
Installed package size
🔴 eve                             [########################] 27.45 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 5.6%
🔴 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: 129.68 MB across 8535 installed files
  • Installed packages: 128 total (122 transitive-only)
  • dependencies: 4 direct packages totaling 43.14 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: 27.45 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                              [########################] 27.45 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-0.29.0.tgz 27.45 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     [########################] 8.41 MB 50.0%
🔴 functions/__server.func                         [########################] 8.41 MB 50.0%

Top Function Payloads

🟠 functions/.well-known/workflow/v1/flow.func • 1 public route • 8.41 MB
Metric Value
Public routes /.well-known/workflow/v1/flow
Runtime nodejs24.x
Handler index.mjs
Payload 8.41 MB
Function files 8.41 MB across 43 files
Traced dependencies 0 B
Signal 🟠 Bundled file index.mjs is 2.31 MB (27.5%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 index.mjs                       [########################] 2.31 MB 27.5%
🟠 _chunks/runtime-artifacts.mjs   [################........] 1.59 MB 19.0%
🟡 _libs/undici.mjs                [##########..............] 980.5 kB 11.7%
🟡 _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 • 8.41 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 8.41 MB
Function files 8.41 MB across 43 files
Traced dependencies 0 B
Signal 🟠 Bundled file index.mjs is 2.31 MB (27.5%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 index.mjs                       [########################] 2.31 MB 27.5%
🟠 _chunks/runtime-artifacts.mjs   [################........] 1.59 MB 19.0%
🟡 _libs/undici.mjs                [##########..............] 980.5 kB 11.7%
🟡 _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: 2.26 s -> 2.20 s (-65.5 ms) vs main (438ae8a).
  • Timing is informational: shared GitHub runners are too variable for a hard timing budget.
Detailed phase timings vs `main (438ae8a)`
Phase Baseline Current Delta
extension.check 5.8 ms 1.0 ms -4.8 ms
project.resolve 5.9 ms 0.6 ms -5.3 ms
workspace.create 1.3 ms 0.7 ms -0.6 ms
host.prepare 281.3 ms 248.7 ms -32.6 ms
vercel.service-prefix.resolve 2.5 ms 2.5 ms 0.0 ms
nitro.create 203.5 ms 231.3 ms +27.8 ms
sandbox.prewarm 452.4 ms 395.4 ms -57.0 ms
nitro.cache.prepare 0.3 ms 0.2 ms -0.1 ms
nitro.prepare 0.9 ms 1.0 ms +0.1 ms
nitro.public-assets 0.8 ms 0.8 ms 0.0 ms
nitro.prerender 0.6 ms 0.5 ms -0.1 ms
nitro.bundle 1.27 s 1.28 s +9.1 ms
nitro.cache.write 0.4 ms 0.3 ms -0.1 ms
vercel.workflow-function.materialize 25.4 ms 23.2 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 3.6 ms +0.1 ms
workspace.remove 2.1 ms 2.2 ms +0.1 ms

Signed-off-by: prha <prha@vercel.com>
artifactLocations: CompilerArtifactLocations;
diagnostics: readonly DiscoverDiagnostic[];
manifest: AgentSourceManifest;
target?: CompileTarget;

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Can we do this without this change? Ideally this PR would not touch compiler and would use a normal userspace extension. It's possible we need API changes to make that work, but that's what we should strive for.

const result = await writeAgentCompilation(
discovered,
input.artifactLocations,
input.target ?? "hosted",

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Also would not expect target to be optional here. Hard to reason about the implications of the default imo

});

const selfmodNames = subagentGraph.nodes
.filter((node) => node.agent.sandbox?.backendName === "eve-selfmod")

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Leaky that we need to check the sandbox name here. What do we need to do this in a way compatible with framework.

I have a PR open with new sandbox shape proposal here: #1408. Does that help?


const SELFMOD_DESCRIPTION =
"Immediately delegate here when the developer asks to change this eve agent or its source. Only this subagent has the live agent tree; do not use the root agent's shell or file tools to inspect or verify source before or after delegation.";
const SELFMOD_INSTRUCTIONS = `You are a development-only source editor for an eve application.

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Ideally this would live in extension as well

await mkdir(filesystemRootPath, { recursive: true });

const filesystem = new ReadWriteFs({
const writableFilesystem = new ReadWriteFs({

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Let's make this changes in a separate PR if needed as they are partly unrelated to self mod

}

/** Maps a generation-snapshot agent root back onto the stable authored app root. */
export function resolveStableAgentRoot(input: {

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Similar q re sandbox

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.

2 participants