Skip to content

feat(eve): add flag-gated task tools, undiscoverable by default - #1519

Closed
ruiconti wants to merge 1 commit into
tasks/02-foundationfrom
tasks/03-tools
Closed

feat(eve): add flag-gated task tools, undiscoverable by default#1519
ruiconti wants to merge 1 commit into
tasks/02-foundationfrom
tasks/03-tools

Conversation

@ruiconti

@ruiconti ruiconti commented Aug 1, 2026

Copy link
Copy Markdown
Contributor

Part 3/5 of the experimental.tasks stack, on top of #1518. The model-facing controls; nothing dispatches them until part 4.

What

With the flag on, the root node's harness tool map gains three tools (task_peek, task_cancel, task_sleep; task_send is part 5). Without it, the tool map, prompt, and event stream are unchanged (existing tests pass unmodified).

How each executes

  • task_peek / task_cancel are execute-less runtime actions with a new task-control kind. Before: only subagent calls carried runtimeAction and parked into the pending batch. Now these calls park the same way, and the dispatch step — which holds durable session state and world access that tool execute doesn't — runs them (part 4).
  • task_sleep executes in-loop: it records the existing durable turn sleep and returns, same as the public sleep tool.

Gating

Injection mirrors the implicit agent tool: inline definitions in createNodeHarnessTools, authored tools with the same name shadow, disableTool(name) removes, and advertised-tools hides them from any child-shaped session — root-node self-delegated children share the root's config, so session shape is the only signal separating them. Dynamic workflow interrupts reject task-control tools explicitly.

task_send is part 5; TUI presentation copy for the new names rides along.

Part of #1084.

@vercel

vercel Bot commented Aug 1, 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 7, 2026 3:36am
eve-docs-4759 Ready Ready Preview, v0 Aug 7, 2026 3:36am

@github-actions

github-actions Bot commented Aug 1, 2026

Copy link
Copy Markdown
Contributor

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

Key takeaways

  • Runtime delta: 1 changed payload.

Delta vs tasks/02-foundation (3e7e503)

Area Metric Baseline Current Delta
Package Packed tarball 7.66 MB 7.67 MB +6.4 kB ⚠️
Package Unpacked publish size 28.71 MB 28.73 MB +15.2 kB ⚠️
Package Installed footprint 72.14 MB 72.16 MB +15.2 kB ⚠️
Package Published files 3048 3053 +5
Package Installed files 6756 6761 +5
Runtime Unique function payloads 2 2 0
Runtime Total function bytes 17.03 MB 17.05 MB +14.3 kB ⚠️
Runtime Public routes 13 13 0
Changed function payloads vs tasks/02-foundation (3e7e503) (2)
Function Status Baseline Current Delta Route changes
functions/__server.func changed 8.52 MB 8.52 MB +7.1 kB ⚠️ public +/eve/v1/session/[sessionId]/clear, +/eve/v1/session/[sessionId]/compact, +/eve/v1/session/[sessionId]/reset
public -/eve/v1/session/clear, -/eve/v1/session/compact, -/eve/v1/session/reset
functions/.well-known/workflow/v1/flow.func changed 8.52 MB 8.52 MB +7.1 kB ⚠️ none

eve init install

Metric Baseline Current Delta
Installed footprint 110.55 MB 110.57 MB +15.2 kB ⚠️
Installed packages 121 121 0
dependencies 4 4 0
devDependencies 2 2 0
Dependency package bytes 43.19 MB 43.21 MB +15.2 kB ⚠️
devDependency package bytes 5.04 MB 5.04 MB 0 B ➖
eve init dependency changes vs tasks/02-foundation (3e7e503)

dependencies

  • Changed: eve@file:eve-0.30.7.tgz -> eve@file:eve-0.31.0.tgz
Build Metadata
  • Preset: vercel
  • Nitro: nitro@3.0.260610-beta
  • Output directory: apps/fixtures/weather-agent/.vercel/output
  • Build metadata timestamp: 2026-08-07T03:38:12.443Z
  • 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: 7.67 MB (eve-0.31.0.tgz)
  • Unpacked payload: 28.73 MB across 3053 published files
  • Installed footprint: 72.16 MB across 6761 installed files
  • Installed root package: 27.37 MB
  • Installed dependencies: 44.78 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: 27.37 MB (37.9%)
  • @rolldown/binding-linux-x64-gnu: 19.35 MB (26.8%)
  • ai: 6.67 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 1.7%
🟡 dist/src/compiled/_chunks/workflow/undici-DWL... [#.......................] 502.4 kB 1.7%
🔴 Other published files                            [########################] 14.11 MB 49.1%
Installed footprint breakdown
Installed package size
🔴 eve                             [########################] 27.37 MB 37.9%
🔴 @rolldown/binding-linux-x64-gnu [#################.......] 19.35 MB 26.8%
🔴 ai                              [######..................] 6.67 MB 9.2%
🔴 zod                             [####....................] 5.07 MB 7.0%
🟠 undici                          [###.....................] 3.50 MB 4.9%
🟠 nitro                           [##......................] 2.41 MB 3.3%
🔴 Other installed packages        [#######.................] 7.79 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: 110.57 MB across 8637 installed files
  • Installed packages: 121 total (115 transitive-only)
  • dependencies: 4 direct packages totaling 43.21 MB
  • devDependencies: 2 direct packages totaling 5.04 MB
  • Other transitive package files: 62.32 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: 27.37 MB (24.8%)
  • @rolldown/binding-linux-x64-gnu: 19.35 MB (17.5%)
  • zod: 9.02 MB (8.2%)
  • ai: 6.67 MB (6.0%)
Installed footprint breakdown
Installed package size
🔴 @typescript/typescript-linux-x64 [########################] 27.95 MB 25.3%
🔴 eve                              [########################] 27.37 MB 24.8%
🔴 @rolldown/binding-linux-x64-gnu  [#################.......] 19.35 MB 17.5%
🔴 zod                              [########................] 9.02 MB 8.2%
🔴 ai                               [######..................] 6.67 MB 6.0%
🟠 undici                           [###.....................] 3.50 MB 3.2%
🔴 Other installed packages         [##############..........] 16.70 MB 15.1%
dependencies (4)
Package Range Installed size Share
@vercel/connect 0.4.3 141.0 kB 0.1%
ai ^7.0.38 6.67 MB 6.0%
eve file:eve-0.31.0.tgz 27.37 MB 24.8%
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     [########################] 8.52 MB 50.0%
🔴 functions/__server.func                         [########################] 8.52 MB 50.0%

Top Function Payloads

🟠 functions/.well-known/workflow/v1/flow.func • 1 public route • 8.52 MB
Metric Value
Public routes /.well-known/workflow/v1/flow
Runtime nodejs24.x
Handler index.mjs
Payload 8.52 MB
Function files 8.52 MB across 44 files
Traced dependencies 0 B
Signal 🟠 Bundled file index.mjs is 2.34 MB (27.4%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 index.mjs                       [########################] 2.34 MB 27.4%
🟠 _chunks/runtime-artifacts.mjs   [################........] 1.62 MB 19.0%
🟡 _libs/undici.mjs                [##########..............] 980.5 kB 11.5%
🟡 _chunks/sandbox.mjs             [########................] 769.0 kB 9.0%
🟡 _libs/@ai-sdk/gateway+[...].mjs [####....................] 432.8 kB 5.1%
🟠 Other bundled files             [########################] 2.38 MB 27.9%

🧾 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 • 8.52 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 8.52 MB
Function files 8.52 MB across 44 files
Traced dependencies 0 B
Signal 🟠 Bundled file index.mjs is 2.34 MB (27.4%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 index.mjs                       [########################] 2.34 MB 27.4%
🟠 _chunks/runtime-artifacts.mjs   [################........] 1.62 MB 19.0%
🟡 _libs/undici.mjs                [##########..............] 980.5 kB 11.5%
🟡 _chunks/sandbox.mjs             [########................] 769.0 kB 9.0%
🟡 _libs/@ai-sdk/gateway+[...].mjs [####....................] 432.8 kB 5.1%
🟠 Other bundled files             [########################] 2.38 MB 27.9%

🧾 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 -> 2.40 s (+138.7 ms) vs tasks/02-foundation (3e7e503).
  • Timing is informational: shared GitHub runners are too variable for a hard timing budget.
Detailed phase timings vs `tasks/02-foundation (3e7e503)`
Phase Baseline Current Delta
extension.check 9.9 ms 1.1 ms -8.8 ms
project.resolve 3.4 ms 0.6 ms -2.8 ms
workspace.create 1.2 ms 0.7 ms -0.5 ms
host.prepare 497.0 ms 247.2 ms -249.8 ms
vercel.service-prefix.resolve 1.7 ms 1.9 ms +0.2 ms
nitro.create 202.1 ms 233.7 ms +31.6 ms
sandbox.prewarm 235.4 ms 578.6 ms +343.2 ms
nitro.cache.prepare 0.2 ms 0.2 ms 0.0 ms
nitro.prepare 0.7 ms 0.8 ms +0.1 ms
nitro.public-assets 0.7 ms 0.7 ms 0.0 ms
nitro.prerender 0.5 ms 0.5 ms 0.0 ms
nitro.bundle 1.28 s 1.30 s +25.0 ms
nitro.cache.write 0.4 ms 0.3 ms -0.1 ms
vercel.workflow-function.materialize 20.0 ms 20.7 ms +0.7 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 3.1 ms 3.2 ms +0.1 ms
workspace.remove 1.9 ms 1.8 ms -0.1 ms

definition.runtimeAction.nodeId === ROOT_RUNTIME_AGENT_NODE_ID
) {
return false;
return true;

@vercel vercel Bot Aug 1, 2026

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.

isRootOnlyFrameworkTool hides any tool whose name is in TASK_TOOL_NAMES from subagent/child sessions, so an authored tool that merely shares a task tool name (e.g. task_sleep) is wrongly hidden even when experimental.tasks is disabled.

Fix on Vercel

Injects task_peek, task_await, task_cancel, and task_sleep into the
harness tool map only when the root agent sets experimental.tasks,
following the implicit agent-tool pattern: inline definitions, authored
shadowing, disableTool support, session-shape hiding for self-delegated
children, and dispatch-time re-validation to come with the delegated
execution mode.

task_peek/task_await/task_cancel are execute-less runtime actions with
the new task-control kind — they need durable session state and world
access, so the runtime-action dispatch step will execute them.
task_sleep records the existing durable turn sleep in-loop. Dynamic
workflow interrupts reject task-control tools explicitly.

Nothing dispatches these actions yet; without the flag no tool set,
prompt, or event stream changes.

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

ruiconti commented Aug 7, 2026

Copy link
Copy Markdown
Contributor Author

Superseded by #1773. The flag and final model tools now land with their complete runtime rather than as a provisional public layer.

@ruiconti ruiconti closed this Aug 7, 2026
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