fix(eve): keep a single tool_result per tool-use id in persisted history - #1246
Draft
ruiconti wants to merge 1 commit into
Draft
fix(eve): keep a single tool_result per tool-use id in persisted history#1246ruiconti wants to merge 1 commit into
ruiconti wants to merge 1 commit into
Conversation
A provider-executed tool call (gateway web_search on Opus 5) whose
arguments fail to parse comes back with two results for one id: the
provider's own error-json inline in the assistant message, plus a
separately synthesized AI_InvalidToolInputError tool message from the AI
SDK. eve persisted both, so the next model call failed with
'each tool_use must have a single result. Found multiple tool_result
blocks with id'. Reproduced 4/20 on a live Opus 5 web_search eval;
0/30 after the fix.
Independent of the malformed-input string handling — the tool-call input
here is {} (a valid object), so no coercion path runs; the AI SDK itself
emits the duplicate. dedupeToolResultsByCallId keeps the first result per
id (the provider's authoritative inline outcome) and prunes emptied
messages; tool-loop logs any dropped id rather than truncating silently.
Signed-off-by: Rui Conti <ruiconti@gmail.com>
Contributor
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
Bundle + Package Summary:
|
| Area | Metric | Baseline | Current | Delta |
|---|---|---|---|---|
| Package | Packed tarball | 4.06 MB | 4.06 MB | +935 B |
| Package | Unpacked publish size | 14.76 MB | 14.76 MB | +1.5 kB |
| Package | Installed footprint | 53.91 MB | 53.92 MB | +1.5 kB |
| Package | Published files | 2776 | 2776 | 0 |
| Package | Installed files | 6016 | 6016 | 0 |
| Runtime | Unique function payloads | 2 | 2 | 0 |
| Runtime | Total function bytes | 14.63 MB | 14.63 MB | +1.4 kB |
| Runtime | Public routes | 11 | 11 | 0 |
Changed function payloads vs main (e368fcd) (2)
| Function | Status | Baseline | Current | Delta | Route changes |
|---|---|---|---|---|---|
functions/__server.func |
changed | 7.32 MB | 7.32 MB | +711 B |
none |
functions/.well-known/workflow/v1/flow.func |
changed | 7.32 MB | 7.32 MB | +711 B |
none |
eve init install
| Metric | Baseline | Current | Delta |
|---|---|---|---|
| Installed footprint | 92.32 MB | 92.32 MB | +1.5 kB |
| Installed packages | 122 | 122 | 0 |
| dependencies | 4 | 4 | 0 |
| devDependencies | 2 | 2 | 0 |
| Dependency package bytes | 29.04 MB | 29.04 MB | +1.5 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: 2026-07-27T18:41:15.112Z
- 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@0.27.6 - Package directory:
packages/eve - Tarball: 4.06 MB (
eve-0.27.6.tgz) - Unpacked payload: 14.76 MB across 2776 published files
- Installed footprint: 53.92 MB across 6016 installed files
- Installed root package: 13.48 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: 13.48 MB (25.0%)ai: 6.43 MB (11.9%)zod: 5.04 MB (9.3%)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 [########################] 11.30 MB 76.6%
Installed footprint breakdown
Installed package size
🔴 @rolldown/binding-linux-x64-gnu [########################] 18.96 MB 35.2%
🔴 eve [#################.......] 13.48 MB 25.0%
🔴 ai [########................] 6.43 MB 11.9%
🔴 zod [######..................] 5.04 MB 9.3%
🟠 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: 92.32 MB across 7884 installed files
- Installed packages: 122 total (116 transitive-only)
- dependencies: 4 direct packages totaling 29.04 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: 13.48 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 [############............] 13.48 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-0.27.6.tgz |
13.48 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 [########################] 7.32 MB 50.0%
🔴 functions/__server.func [########################] 7.32 MB 50.0%
Top Function Payloads
🟠 functions/.well-known/workflow/v1/flow.func • 1 public route • 7.32 MB
| Metric | Value |
|---|---|
| Public routes | /.well-known/workflow/v1/flow |
| Runtime | nodejs24.x |
| Handler | index.mjs |
| Payload | 7.32 MB |
| Function files | 7.32 MB across 43 files |
| Traced dependencies | 0 B |
| Signal | 🟠 Bundled file _chunks/runtime-artifacts.mjs is 1.57 MB (21.5%) |
🟠 🔎 Dependency Analysis
📦 Bundled files:
Bundled file size
🟠 _chunks/runtime-artifacts.mjs [###############.........] 1.57 MB 21.5%
🟠 index.mjs [###########.............] 1.17 MB 16.0%
🟡 _chunks/world-vercel.mjs [#########...............] 900.3 kB 12.3%
🟡 _chunks/sandbox.mjs [#######.................] 767.6 kB 10.5%
🟡 _libs/@ai-sdk/gateway+[...].mjs [####....................] 432.5 kB 5.9%
🟠 Other bundled files [########################] 2.47 MB 33.8%
🧾 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 • 10 public routes, 1 internal alias • 7.32 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 | 7.32 MB |
| Function files | 7.32 MB across 43 files |
| Traced dependencies | 0 B |
| Signal | 🟠 Bundled file _chunks/runtime-artifacts.mjs is 1.57 MB (21.5%) |
🟠 🔎 Dependency Analysis
📦 Bundled files:
Bundled file size
🟠 _chunks/runtime-artifacts.mjs [###############.........] 1.57 MB 21.5%
🟠 index.mjs [###########.............] 1.17 MB 16.0%
🟡 _chunks/world-vercel.mjs [#########...............] 900.3 kB 12.3%
🟡 _chunks/sandbox.mjs [#######.................] 767.6 kB 10.5%
🟡 _libs/@ai-sdk/gateway+[...].mjs [####....................] 432.5 kB 5.9%
🟠 Other bundled files [########################] 2.47 MB 33.8%
🧾 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: 1.76 s -> 1.76 s (-4.5 ms) vs
main (e368fcd). - Timing is informational: shared GitHub runners are too variable for a hard timing budget.
Detailed phase timings vs `main (e368fcd)`
| Phase | Baseline | Current | Delta |
|---|---|---|---|
extension.check |
12.2 ms | 1.1 ms | -11.1 ms |
project.resolve |
6.3 ms | 0.6 ms | -5.7 ms |
workspace.create |
6.9 ms | 0.8 ms | -6.1 ms |
host.prepare |
167.1 ms | 139.6 ms | -27.5 ms |
vercel.service-prefix.resolve |
2.1 ms | 2.3 ms | +0.2 ms |
nitro.create |
196.7 ms | 209.1 ms | +12.4 ms |
sandbox.prewarm |
247.1 ms | 242.5 ms | -4.6 ms |
nitro.cache.prepare |
0.3 ms | 0.3 ms | 0.0 ms |
nitro.prepare |
0.8 ms | 0.8 ms | 0.0 ms |
nitro.public-assets |
0.7 ms | 0.7 ms | 0.0 ms |
nitro.prerender |
0.6 ms | 0.6 ms | 0.0 ms |
nitro.bundle |
1.12 s | 1.15 s | +37.7 ms |
nitro.cache.write |
0.4 ms | 0.4 ms | 0.0 ms |
agent-summary.emit |
0.5 ms | 0.5 ms | 0.0 ms |
nitro.close |
0.1 ms | 0.2 ms | +0.1 ms |
output.publish |
3.5 ms | 3.7 ms | +0.2 ms |
workspace.remove |
2.3 ms | 2.4 ms | +0.1 ms |
ruiconti
marked this pull request as draft
July 27, 2026 19:06
Contributor
Author
|
Fix is upstream vercel/ai#17400. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Opus 5 turns fail intermittently with:
A provider-executed tool call (gateway
web_search) whose arguments fail to parse comes back with two results for one id:{"type":"error-json","value":{"error":"invalid_input","message":"JSON parse error..."}}AI_InvalidToolInputErrortool message from the AI SDK, inresult.response.messageseve persisted both, and the next model call replayed two
tool_resultblocks for onetool_use— which Anthropic rejects withstatusCode 400, isRetryable false, killing the turn.Scope
This is independent of the raw-JSON-string tool-argument handling in #1240. The tool-call input in the failing case is
{}(a valid object), so no coercion path runs and no eve-synthesized error is involved — the AI SDK emits the duplicate itself. The bug is structural: eve assumed one result per tool-use id but never enforced it. Fixing it offmainso it lands independently.Fix
dedupeToolResultsByCallIdruns afternormalizeProviderToolHistoryand keeps the firsttool_result/tool_errorper tool-use id — the provider's authoritative inline outcome, which precedes any synthesized follow-up — dropping later duplicates and pruning any message left empty.tool-looplogs the dropped ids rather than truncating silently. Untouched messages keep their identity (no needless copies).Verification
web_searcheval; the unit test encodes that structure.