Skip to content

fix(eve): tool loop - stop consecutive tool-error retries#1168

Open
AndrewBarba wants to merge 3 commits into
mainfrom
barba/max-consecutive-tool-errors
Open

fix(eve): tool loop - stop consecutive tool-error retries#1168
AndrewBarba wants to merge 3 commits into
mainfrom
barba/max-consecutive-tool-errors

Conversation

@AndrewBarba

@AndrewBarba AndrewBarba commented Jul 24, 2026

Copy link
Copy Markdown
Collaborator

Summary

  • stop retry loops after 10 consecutive failed tool calls by default, configurable with limits.maxConsecutiveToolErrors
  • reset the counter after successful tool progress and scope it to the active turn
  • enforce the default for fresh and previously persisted durable sessions at the loop boundary
  • fail conversation turns recoverably while returning terminal errors from tasks and subagents
  • document the behavior and include a patch changeset

Root cause

eve 0.27.3 already returns schema-validation errors to the next model prompt. A real AI SDK harness regression test confirms that the malformed call remains correctly paired with its error in history and that a later corrected call executes successfully. Models or provider adapters can still emit the same invalid arguments on fresh calls, and eve previously had no semantic stop condition other than the session token budget.

The new default stops that loop before an eleventh failed model/tool iteration without penalizing healthy, tool-heavy runs that continue producing successful results. Agents can override the default with a different positive integer.

Validation

  • pnpm test:unit — 5,378 passed, 1 skipped
  • pnpm test:integration — 542 passed
  • focused real AI SDK malformed-input recovery tests — 4 passed
  • pnpm typecheck
  • pnpm lint
  • pnpm fmt
  • pnpm guard:invariants
  • pnpm docs:check

Signed-off-by: Andrew Barba <barba@hey.com>
@vercel

vercel Bot commented Jul 24, 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, Comment, Open in v0 Jul 24, 2026 3:28pm
eve-docs-1644 Ready Ready Preview, Comment, Open in v0 Jul 24, 2026 3:28pm
eve-docs-4759 Ready Ready Preview, Comment, Open in v0 Jul 24, 2026 3:28pm

@github-actions

github-actions Bot commented Jul 24, 2026

Copy link
Copy Markdown
Contributor

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

Key takeaways

  • No notable deltas vs main (04d5814).

Delta vs main (04d5814)

Area Metric Baseline Current Delta
Package Packed tarball 4.05 MB 4.05 MB +1.9 kB ⚠️
Package Unpacked publish size 14.72 MB 14.73 MB +11.3 kB ⚠️
Package Installed footprint 53.88 MB 53.89 MB +11.3 kB ⚠️
Package Published files 2747 2749 +2
Package Installed files 5987 5989 +2
Runtime Unique function payloads 2 2 0
Runtime Total function bytes 11.67 MB 11.67 MB +4.0 kB ⚠️
Runtime Public routes 11 11 0
Changed function payloads vs main (04d5814) (2)
Function Status Baseline Current Delta Route changes
functions/.well-known/workflow/v1/flow.func changed 7.26 MB 7.27 MB +3.9 kB ⚠️ none
functions/__server.func changed 4.41 MB 4.41 MB +120 B ⚠️ none

eve init install

Metric Baseline Current Delta
Installed footprint 92.28 MB 92.29 MB +11.3 kB ⚠️
Installed packages 122 122 0
dependencies 4 4 0
devDependencies 2 2 0
Dependency package bytes 29.00 MB 29.01 MB +11.3 kB ⚠️
devDependency package bytes 5.04 MB 5.04 MB 0 B ➖
eve init dependency changes vs main (04d5814)

dependencies

  • Changed: eve@file:eve-0.27.3.tgz -> eve@file:eve-0.27.4.tgz
Build Metadata
  • Preset: vercel
  • Nitro: nitro@3.0.260610-beta
  • Output directory: apps/fixtures/weather-agent/.vercel/output
  • Build metadata timestamp: 2026-07-24T15:29:08.071Z
  • Route aliases: 11 public, 1 internal (12 total aliases)
  • Vercel routes in config: 12
  • Severity legend: 🔴 dominant/large, 🟠 notable, 🟡 watch, ⚪ small
Package Drill-Down

Package Details

  • Package: eve@0.27.4
  • Package directory: packages/eve
  • Tarball: 4.05 MB (eve-0.27.4.tgz)
  • Unpacked payload: 14.73 MB across 2749 published files
  • Installed footprint: 53.89 MB across 5989 installed files
  • Installed root package: 13.45 MB
  • Installed dependencies: 40.44 MB
  • Runtime dependencies: 1
  • Peer dependencies: 5 (4 optional)

Installed footprint is measured from an isolated temporary npm install of the packed tarball.

Heavy installed dependencies

  • @rolldown/binding-linux-x64-gnu: 18.96 MB (35.2%)
  • eve: 13.45 MB (25.0%)
  • ai: 6.43 MB (11.9%)
  • zod: 5.04 MB (9.4%)
  • nitro: 2.41 MB (4.5%)
Publish payload breakdown
Published file size
🟠 dist/src/compiled/experimental-ai-sdk-code-mo... [###.....................] 1.51 MB 10.2%
🟡 dist/src/compiled/@vercel/sandbox/index.js       [#.......................] 632.4 kB 4.3%
🟡 dist/src/compiled/_chunks/workflow/undici-C2Z... [#.......................] 502.4 kB 3.4%
🟡 dist/src/compiled/@chat-adapter/slack/index.js   [#.......................] 440.5 kB 3.0%
🟡 dist/src/compiled/@vercel/oidc/index.js          [#.......................] 379.5 kB 2.6%
🔴 Other published files                            [########################] 11.27 MB 76.5%
Installed footprint breakdown
Installed package size
🔴 @rolldown/binding-linux-x64-gnu [########################] 18.96 MB 35.2%
🔴 eve                             [#################.......] 13.45 MB 25.0%
🔴 ai                              [########................] 6.43 MB 11.9%
🔴 zod                             [######..................] 5.04 MB 9.4%
🟠 nitro                           [###.....................] 2.41 MB 4.5%
🟡 @ai-sdk/provider-utils          [#.......................] 852.0 kB 1.6%
🔴 Other installed packages        [#########...............] 6.75 MB 12.5%
Runtime dependencies (1)
Package Range Notes
nitro 3.0.260610-beta
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: 92.29 MB across 7857 installed files
  • Installed packages: 122 total (116 transitive-only)
  • dependencies: 4 direct packages totaling 29.01 MB
  • devDependencies: 2 direct packages totaling 5.04 MB
  • Other transitive package files: 58.24 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 (30.3%)
  • @rolldown/binding-linux-x64-gnu: 18.96 MB (20.5%)
  • eve: 13.45 MB (14.6%)
  • zod: 9.00 MB (9.7%)
  • ai: 6.43 MB (7.0%)
Installed footprint breakdown
Installed package size
🔴 @typescript/typescript-linux-x64 [########################] 27.95 MB 30.3%
🔴 @rolldown/binding-linux-x64-gnu  [################........] 18.96 MB 20.5%
🔴 eve                              [############............] 13.45 MB 14.6%
🔴 zod                              [########................] 9.00 MB 9.7%
🔴 ai                               [######..................] 6.43 MB 7.0%
🟠 @types/node                      [##......................] 2.54 MB 2.8%
🔴 Other installed packages         [############............] 13.97 MB 15.1%
dependencies (4)
Package Range Installed size Share
@vercel/connect 0.4.2 135.8 kB 0.1%
ai ^7.0.34 6.43 MB 7.0%
eve file:eve-0.27.4.tgz 13.45 MB 14.6%
zod 4.4.3 9.00 MB 9.7%
devDependencies (2)
Package Range Installed size Share
@types/node 24.x 2.54 MB 2.8%
typescript 7.0.2 2.50 MB 2.7%
Function Drill-Down

Payload Size Graph

Unique function payload size and share of total
🔴 functions/.well-known/workflow/v1/flow.func     [########################] 7.27 MB 62.3%
🟠 functions/__server.func                         [###############.........] 4.41 MB 37.7%

Top Function Payloads

🟠 functions/.well-known/workflow/v1/flow.func • 1 public route • 7.27 MB
Metric Value
Public routes /.well-known/workflow/v1/flow
Runtime nodejs24.x
Handler index.mjs
Payload 7.27 MB
Function files 7.27 MB across 39 files
Traced dependencies 0 B
Signal 🟠 Bundled file __eve_nitro_handler__.mjs is 2.71 MB (37.3%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 __eve_nitro_handler__.mjs       [########################] 2.71 MB 37.3%
🟡 _chunks/world-vercel.mjs        [########................] 903.2 kB 12.4%
🟡 _chunks/sandbox.mjs             [#######.................] 767.6 kB 10.6%
🟡 _libs/@ai-sdk/gateway+[...].mjs [####....................] 432.5 kB 6.0%
🟡 _chunks/token-util-B6qBs3-0.mjs [###.....................] 379.1 kB 5.2%
🟠 Other bundled files             [##################......] 2.08 MB 28.6%

🧾 Vercel Config

{
  "handler": "index.mjs",
  "launcherType": "Nodejs",
  "shouldAddHelpers": false,
  "supportsResponseStreaming": true,
  "runtime": "nodejs24.x",
  "environment": {
    "WORKFLOW_PRECONDITION_GUARD": "1",
    "NODE_OPTIONS": "--experimental-require-module"
  },
  "maxDuration": "max",
  "experimentalTriggers": [
    {
      "type": "queue/v2beta",
      "topic": "__eve776561746865722d6167656e74_wkf_workflow_*",
      "consumer": "default",
      "retryAfterSeconds": 5,
      "initialDelaySeconds": 0
    }
  ]
}

🟠 functions/__server.func • 10 public routes, 1 internal alias • 4.41 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 4.41 MB
Function files 4.41 MB across 30 files
Traced dependencies 0 B
Signal 🟠 Bundled file _chunks/runtime-artifacts.mjs is 1.41 MB (32.0%)

🟠 🔎 Dependency Analysis

📦 Bundled files:

Bundled file size
🟠 _chunks/runtime-artifacts.mjs   [########################] 1.41 MB 32.0%
🟠 _chunks/world-vercel.mjs        [###############.........] 900.3 kB 20.4%
🟠 _chunks/sandbox.mjs             [#############...........] 767.6 kB 17.4%
🟡 _chunks/token-util-B6qBs3-0.mjs [######..................] 379.1 kB 8.6%
🟡 _chunks/dist-BX517Nmz.mjs       [######..................] 348.7 kB 7.9%
🟡 Other bundled files             [##########..............] 599.1 kB 13.6%

🧾 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: 2.57 s -> 2.58 s (+3.5 ms) vs main (04d5814).
  • Timing is informational: shared GitHub runners are too variable for a hard timing budget.
Detailed phase timings vs `main (04d5814)`
Phase Baseline Current Delta
extension.check 1.2 ms 1.1 ms -0.1 ms
project.resolve 0.6 ms 0.6 ms 0.0 ms
workspace.create 0.9 ms 0.8 ms -0.1 ms
host.prepare 168.1 ms 180.7 ms +12.6 ms
vercel.service-prefix.resolve 2.3 ms 1.8 ms -0.5 ms
nitro.app.create 25.4 ms 25.8 ms +0.4 ms
nitro.app.cache.prepare 0.2 ms 0.2 ms 0.0 ms
nitro.app.prepare 0.9 ms 0.8 ms -0.1 ms
nitro.app.public-assets 0.7 ms 0.7 ms 0.0 ms
nitro.app.prerender 0.6 ms 0.5 ms -0.1 ms
nitro.app.bundle 712.4 ms 686.7 ms -25.7 ms
nitro.app.cache.write 0.4 ms 0.3 ms -0.1 ms
sandbox.prewarm 227.4 ms 264.0 ms +36.6 ms
nitro.flow.create 171.7 ms 169.5 ms -2.2 ms
nitro.flow.cache.prepare 0.2 ms 0.2 ms 0.0 ms
nitro.flow.prepare 0.8 ms 0.9 ms +0.1 ms
nitro.flow.public-assets 0.2 ms 0.2 ms 0.0 ms
nitro.flow.prerender 0.0 ms 0.0 ms 0.0 ms
nitro.flow.bundle 1.07 s 1.06 s -8.4 ms
nitro.flow.cache.write 0.4 ms 0.6 ms +0.2 ms
nitro.flow.close 0.2 ms 0.2 ms 0.0 ms
workflow.emit 177.3 ms 168.3 ms -9.0 ms
agent-summary.emit 0.6 ms 0.5 ms -0.1 ms
nitro.app.close 0.1 ms 0.1 ms 0.0 ms
output.publish 3.7 ms 3.8 ms +0.1 ms
workspace.remove 6.0 ms 5.9 ms -0.1 ms

Signed-off-by: Andrew Barba <barba@hey.com>
Signed-off-by: Andrew Barba <barba@hey.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