Skip to content

fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index #1976

Closed
#1995
Closed
fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index#1976
#1995
Assignees
Astro-Han

Description

@Astro-Han
Astro-Han
opened on Aug 3, 2026

A gateway that labels two distinct streamed tool calls with the same tool_calls[].index gets them merged into one. The arguments are concatenated into invalid JSON, the second call's id and name are dropped, and nothing errors.

in: {index:0, id:"call_a", name:"read_file", args:'{"path":"a"}'}
{index:0, id:"call_b", name:"read_file", args:'{"path":"b"}'}
out: [{"toolCallId":"call_a","input":"{\"path\":\"a\"}{\"path\":\"b\"}"}]

processExistingToolCall in @ai-sdk/provider-utils only appends to arguments; it ignores the id and function.name on every delta after the first for a given index.

This is worse than the crash in #1967. The agent proceeds believing it called one tool with garbage arguments, and the second tool never runs, with no signal anywhere.

Reach. 46 providers in provider-registry.ts use the openai-compatible runtime adapter, including ollama and ollama-cloud, both status: 'ready'. vercel/ai#14277 reports that Ollama labels every tool call in a turn with index: 0 (verified there against Ollama 0.20.2/0.20.4 with qwen3-coder:30b and others, 100% failure on multi-tool turns). I reproduced the merge at the protocol layer through the real provider stack, but I have not run it end to end against a live Ollama, so that half rests on the upstream report.

Secondary case, same root. When deltas carry no index at all and a call spans more than one chunk, the ?? this.toolCalls.length fallback picks a fresh slot for the continuation and it throws Expected 'id' to be a string. No known maka path hits this today, since Google uses the native adapter, but a relay could.

Not caused by #1971. Output is byte-identical with and without that patch; it fixes a crash from sparse indices and deliberately does not widen into this. patches/README.md records both cases.

Why this isn't a one-line fix.index says which call a delta belongs to, but identity actually lives in toolCallDelta.id. The tracker keys off neither consistently, so any real fix rekeys it on id and decides what to do when a gateway violates the protocol: two distinct calls, or an explicit protocol error, but never a silent merge. That is upstream's call to make. Tracking here so it isn't rediscovered from a user report.

Upstream: vercel/ai#18333, vercel/ai#14277.

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions

    , 'i'); if (__m === '*' || __re.test(location.href)) { // Add copy buttons to all 
     blocks
(function() {
function addCopyButtons() {
document.querySelectorAll('pre code').forEach(function(codeBlock) {
if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;
codeBlock.parentElement.setAttribute('data-copy-added', 'true');
var btn = document.createElement('button');
btn.textContent = 'Copy';
btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';
btn.onmouseover = function() { this.style.opacity = '1'; };
btn.onmouseout = function() { this.style.opacity = '0.7'; };
btn.onclick = function() {
navigator.clipboard.writeText(codeBlock.textContent).then(function() {
btn.textContent = 'Copied!';
setTimeout(function() { btn.textContent = 'Copy'; }, 1500);
});
};
codeBlock.parentElement.style.position = 'relative';
codeBlock.parentElement.appendChild(btn);
});
}
addCopyButtons();
// Re-run on dynamic content
var observer = new MutationObserver(addCopyButtons);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '
fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index · Issue #1976 · apache/maka · GitHub
    Skip to content
    fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index #1976
    Closed
    #1995
    Closed
    fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index#1976
    #1995
    Assignees
    Astro-Han
    Description
    @Astro-Han
    Astro-Han
    opened on Aug 3, 2026
    A gateway that labels two distinct streamed tool calls with the same tool_calls[].index gets them merged into one. The arguments are concatenated into invalid JSON, the second call's id and name are dropped, and nothing errors.
    in: {index:0, id:"call_a", name:"read_file", args:'{"path":"a"}'}
{index:0, id:"call_b", name:"read_file", args:'{"path":"b"}'}
out: [{"toolCallId":"call_a","input":"{\"path\":\"a\"}{\"path\":\"b\"}"}]

    processExistingToolCall in @ai-sdk/provider-utils only appends to arguments; it ignores the id and function.name on every delta after the first for a given index.
    This is worse than the crash in #1967. The agent proceeds believing it called one tool with garbage arguments, and the second tool never runs, with no signal anywhere.
    Reach. 46 providers in provider-registry.ts use the openai-compatible runtime adapter, including ollama and ollama-cloud, both status: 'ready'. vercel/ai#14277 reports that Ollama labels every tool call in a turn with index: 0 (verified there against Ollama 0.20.2/0.20.4 with qwen3-coder:30b and others, 100% failure on multi-tool turns). I reproduced the merge at the protocol layer through the real provider stack, but I have not run it end to end against a live Ollama, so that half rests on the upstream report.
    Secondary case, same root. When deltas carry no index at all and a call spans more than one chunk, the ?? this.toolCalls.length fallback picks a fresh slot for the continuation and it throws Expected 'id' to be a string. No known maka path hits this today, since Google uses the native adapter, but a relay could.
    Not caused by #1971. Output is byte-identical with and without that patch; it fixes a crash from sparse indices and deliberately does not widen into this. patches/README.md records both cases.
    Why this isn't a one-line fix.index says which call a delta belongs to, but identity actually lives in toolCallDelta.id. The tracker keys off neither consistently, so any real fix rekeys it on id and decides what to do when a gateway violates the protocol: two distinct calls, or an explicit protocol error, but never a silent merge. That is upstream's call to make. Tracking here so it isn't rediscovered from a user report.
    Upstream: vercel/ai#18333, vercel/ai#14277.
    Metadata
    Metadata
    Assignees
    Labels
    No labels
    No labels
    Type
    No type
    Projects
    No projects
      Milestone
      No milestone
      Relationships
      None yet
      Development
      No branches or pull requests
      Issue actions
      
, 'i');
if (__m === '*' || __re.test(location.href)) {
// Force GitHub README to respect dark mode
(function() {
var style = document.createElement('style');
style.textContent = '
.markdown-body {
color-scheme: dark light;
}
.markdown-body pre { background: #161b22 !important; }
.markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }
.markdown-body table th, .markdown-body table td { border-color: #30363d !important; }
.markdown-body img { background: #0d1117; }
.markdown-body blockquote { border-left-color: #8b949e; }
.markdown-body hr { border-color: #30363d; }
';
document.head.appendChild(style);
})();
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index · Issue #1976 · apache/maka · GitHub
      Skip to content
      fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index #1976
      Closed
      #1995
      Closed
      fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index#1976
      #1995
      Assignees
      Astro-Han
      Description
      @Astro-Han
      Astro-Han
      opened on Aug 3, 2026
      A gateway that labels two distinct streamed tool calls with the same tool_calls[].index gets them merged into one. The arguments are concatenated into invalid JSON, the second call's id and name are dropped, and nothing errors.
      in: {index:0, id:"call_a", name:"read_file", args:'{"path":"a"}'}
{index:0, id:"call_b", name:"read_file", args:'{"path":"b"}'}
out: [{"toolCallId":"call_a","input":"{\"path\":\"a\"}{\"path\":\"b\"}"}]

      processExistingToolCall in @ai-sdk/provider-utils only appends to arguments; it ignores the id and function.name on every delta after the first for a given index.
      This is worse than the crash in #1967. The agent proceeds believing it called one tool with garbage arguments, and the second tool never runs, with no signal anywhere.
      Reach. 46 providers in provider-registry.ts use the openai-compatible runtime adapter, including ollama and ollama-cloud, both status: 'ready'. vercel/ai#14277 reports that Ollama labels every tool call in a turn with index: 0 (verified there against Ollama 0.20.2/0.20.4 with qwen3-coder:30b and others, 100% failure on multi-tool turns). I reproduced the merge at the protocol layer through the real provider stack, but I have not run it end to end against a live Ollama, so that half rests on the upstream report.
      Secondary case, same root. When deltas carry no index at all and a call spans more than one chunk, the ?? this.toolCalls.length fallback picks a fresh slot for the continuation and it throws Expected 'id' to be a string. No known maka path hits this today, since Google uses the native adapter, but a relay could.
      Not caused by #1971. Output is byte-identical with and without that patch; it fixes a crash from sparse indices and deliberately does not widen into this. patches/README.md records both cases.
      Why this isn't a one-line fix.index says which call a delta belongs to, but identity actually lives in toolCallDelta.id. The tracker keys off neither consistently, so any real fix rekeys it on id and decides what to do when a gateway violates the protocol: two distinct calls, or an explicit protocol error, but never a silent merge. That is upstream's call to make. Tracking here so it isn't rediscovered from a user report.
      Upstream: vercel/ai#18333, vercel/ai#14277.
      Metadata
      Metadata
      Assignees
      Labels
      No labels
      No labels
      Type
      No type
      Projects
      No projects
        Milestone
        No milestone
        Relationships
        None yet
        Development
        No branches or pull requests
        Issue actions
        
, 'i');
if (__m === '*' || __re.test(location.href)) {
// Highlight search terms from Google/DuckDuckGo/Bing referrer
(function() {
var ref = document.referrer;
var terms = [];
if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {
var url = new URL(ref);
var q = url.searchParams.get('q') || url.searchParams.get('p');
if (q) {
terms = q.split(/\s+/).filter(function(t) { return t.length > 2; });
}
}
if (terms.length === 0) return;
var style = document.createElement('style');
style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';
document.head.appendChild(style);
function highlight(node) {
if (node.nodeType === 3) { // text node
var text = node.textContent;
var found = false;
terms.forEach(function(term) {
var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\]\\]/g, '\\') + ')', 'gi');
if (regex.test(text)) {
found = true;
var frag = document.createDocumentFragment();
var parts = text.split(regex);
parts.forEach(function(part, i) {
if (i % 2 === 0) {
frag.appendChild(document.createTextNode(part));
} else {
var span = document.createElement('span');
span.className = 'userscript-highlight';
span.textContent = part;
frag.appendChild(span);
}
});
node.parentNode.replaceChild(frag, node);
}
});
} else if (node.nodeType === 1 && node.childNodes) { // element
var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];
if (!skipTags.includes(node.tagName)) {
Array.from(node.childNodes).forEach(highlight);
}
}
}
highlight(document.body);
// Re-highlight on dynamic content
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1 || node.nodeType === 3) highlight(node);
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index · Issue #1976 · apache/maka · GitHub
        Skip to content
        fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index #1976
        Closed
        #1995
        Closed
        fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index#1976
        #1995
        Assignees
        Astro-Han
        Description
        @Astro-Han
        Astro-Han
        opened on Aug 3, 2026
        A gateway that labels two distinct streamed tool calls with the same tool_calls[].index gets them merged into one. The arguments are concatenated into invalid JSON, the second call's id and name are dropped, and nothing errors.
        in: {index:0, id:"call_a", name:"read_file", args:'{"path":"a"}'}
{index:0, id:"call_b", name:"read_file", args:'{"path":"b"}'}
out: [{"toolCallId":"call_a","input":"{\"path\":\"a\"}{\"path\":\"b\"}"}]

        processExistingToolCall in @ai-sdk/provider-utils only appends to arguments; it ignores the id and function.name on every delta after the first for a given index.
        This is worse than the crash in #1967. The agent proceeds believing it called one tool with garbage arguments, and the second tool never runs, with no signal anywhere.
        Reach. 46 providers in provider-registry.ts use the openai-compatible runtime adapter, including ollama and ollama-cloud, both status: 'ready'. vercel/ai#14277 reports that Ollama labels every tool call in a turn with index: 0 (verified there against Ollama 0.20.2/0.20.4 with qwen3-coder:30b and others, 100% failure on multi-tool turns). I reproduced the merge at the protocol layer through the real provider stack, but I have not run it end to end against a live Ollama, so that half rests on the upstream report.
        Secondary case, same root. When deltas carry no index at all and a call spans more than one chunk, the ?? this.toolCalls.length fallback picks a fresh slot for the continuation and it throws Expected 'id' to be a string. No known maka path hits this today, since Google uses the native adapter, but a relay could.
        Not caused by #1971. Output is byte-identical with and without that patch; it fixes a crash from sparse indices and deliberately does not widen into this. patches/README.md records both cases.
        Why this isn't a one-line fix.index says which call a delta belongs to, but identity actually lives in toolCallDelta.id. The tracker keys off neither consistently, so any real fix rekeys it on id and decides what to do when a gateway violates the protocol: two distinct calls, or an explicit protocol error, but never a silent merge. That is upstream's call to make. Tracking here so it isn't rediscovered from a user report.
        Upstream: vercel/ai#18333, vercel/ai#14277.
        Metadata
        Metadata
        Assignees
        Labels
        No labels
        No labels
        Type
        No type
        Projects
        No projects
          Milestone
          No milestone
          Relationships
          None yet
          Development
          No branches or pull requests
          Issue actions
          
, 'i');
if (__m === '*' || __re.test(location.href)) {
// Strip utm_, fbclid, gclid, etc. from all links on page
(function() {
var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',
'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',
'ref', 'ref_src', 'source', 'medium', 'campaign'];
function cleanUrl(url) {
try {
var u = new URL(url, window.location.origin);
var changed = false;
trackingParams.forEach(function(p) {
if (u.searchParams.has(p)) {
u.searchParams.delete(p);
changed = true;
}
});
return changed ? u.toString() : url;
} catch (e) {
return url;
}
}
function cleanLinks() {
document.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
cleanLinks();
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1) {
if (node.tagName === 'A') cleanLinks();
node.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '
fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index · Issue #1976 · apache/maka · GitHub
          Skip to content
          fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index #1976
          Closed
          #1995
          Closed
          fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index#1976
          #1995
          Assignees
          Astro-Han
          Description
          @Astro-Han
          Astro-Han
          opened on Aug 3, 2026
          A gateway that labels two distinct streamed tool calls with the same tool_calls[].index gets them merged into one. The arguments are concatenated into invalid JSON, the second call's id and name are dropped, and nothing errors.
          in: {index:0, id:"call_a", name:"read_file", args:'{"path":"a"}'}
{index:0, id:"call_b", name:"read_file", args:'{"path":"b"}'}
out: [{"toolCallId":"call_a","input":"{\"path\":\"a\"}{\"path\":\"b\"}"}]

          processExistingToolCall in @ai-sdk/provider-utils only appends to arguments; it ignores the id and function.name on every delta after the first for a given index.
          This is worse than the crash in #1967. The agent proceeds believing it called one tool with garbage arguments, and the second tool never runs, with no signal anywhere.
          Reach. 46 providers in provider-registry.ts use the openai-compatible runtime adapter, including ollama and ollama-cloud, both status: 'ready'. vercel/ai#14277 reports that Ollama labels every tool call in a turn with index: 0 (verified there against Ollama 0.20.2/0.20.4 with qwen3-coder:30b and others, 100% failure on multi-tool turns). I reproduced the merge at the protocol layer through the real provider stack, but I have not run it end to end against a live Ollama, so that half rests on the upstream report.
          Secondary case, same root. When deltas carry no index at all and a call spans more than one chunk, the ?? this.toolCalls.length fallback picks a fresh slot for the continuation and it throws Expected 'id' to be a string. No known maka path hits this today, since Google uses the native adapter, but a relay could.
          Not caused by #1971. Output is byte-identical with and without that patch; it fixes a crash from sparse indices and deliberately does not widen into this. patches/README.md records both cases.
          Why this isn't a one-line fix.index says which call a delta belongs to, but identity actually lives in toolCallDelta.id. The tracker keys off neither consistently, so any real fix rekeys it on id and decides what to do when a gateway violates the protocol: two distinct calls, or an explicit protocol error, but never a silent merge. That is upstream's call to make. Tracking here so it isn't rediscovered from a user report.
          Upstream: vercel/ai#18333, vercel/ai#14277.
          Metadata
          Metadata
          Assignees
          Labels
          No labels
          No labels
          Type
          No type
          Projects
          No projects
            Milestone
            No milestone
            Relationships
            None yet
            Development
            No branches or pull requests
            Issue actions
            
, 'i');
if (__m === '*' || __re.test(location.href)) {
// Auto-enable theater mode on YouTube
(function() {
function tryTheater() {
var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]');
if (btn && !btn.classList.contains('activated')) {
btn.click();
}
}
// Try immediately
tryTheater();
// Try after navigation (SPA)
var lastUrl = location.href;
setInterval(function() {
if (location.href !== lastUrl) {
lastUrl = location.href;
setTimeout(tryTheater, 500);
}
}, 1000);
// Also try on player load
var observer = new MutationObserver(tryTheater);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index · Issue #1976 · apache/maka · GitHub
            Skip to content
            fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index #1976
            Closed
            #1995
            Closed
            fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index#1976
            #1995
            Assignees
            Astro-Han
            Description
            @Astro-Han
            Astro-Han
            opened on Aug 3, 2026
            A gateway that labels two distinct streamed tool calls with the same tool_calls[].index gets them merged into one. The arguments are concatenated into invalid JSON, the second call's id and name are dropped, and nothing errors.
            in: {index:0, id:"call_a", name:"read_file", args:'{"path":"a"}'}
{index:0, id:"call_b", name:"read_file", args:'{"path":"b"}'}
out: [{"toolCallId":"call_a","input":"{\"path\":\"a\"}{\"path\":\"b\"}"}]

            processExistingToolCall in @ai-sdk/provider-utils only appends to arguments; it ignores the id and function.name on every delta after the first for a given index.
            This is worse than the crash in #1967. The agent proceeds believing it called one tool with garbage arguments, and the second tool never runs, with no signal anywhere.
            Reach. 46 providers in provider-registry.ts use the openai-compatible runtime adapter, including ollama and ollama-cloud, both status: 'ready'. vercel/ai#14277 reports that Ollama labels every tool call in a turn with index: 0 (verified there against Ollama 0.20.2/0.20.4 with qwen3-coder:30b and others, 100% failure on multi-tool turns). I reproduced the merge at the protocol layer through the real provider stack, but I have not run it end to end against a live Ollama, so that half rests on the upstream report.
            Secondary case, same root. When deltas carry no index at all and a call spans more than one chunk, the ?? this.toolCalls.length fallback picks a fresh slot for the continuation and it throws Expected 'id' to be a string. No known maka path hits this today, since Google uses the native adapter, but a relay could.
            Not caused by #1971. Output is byte-identical with and without that patch; it fixes a crash from sparse indices and deliberately does not widen into this. patches/README.md records both cases.
            Why this isn't a one-line fix.index says which call a delta belongs to, but identity actually lives in toolCallDelta.id. The tracker keys off neither consistently, so any real fix rekeys it on id and decides what to do when a gateway violates the protocol: two distinct calls, or an explicit protocol error, but never a silent merge. That is upstream's call to make. Tracking here so it isn't rediscovered from a user report.
            Upstream: vercel/ai#18333, vercel/ai#14277.
            Metadata
            Metadata
            Assignees
            Labels
            No labels
            No labels
            Type
            No type
            Projects
            No projects
              Milestone
              No milestone
              Relationships
              None yet
              Development
              No branches or pull requests
              Issue actions
              
, 'i');
if (__m === '*' || __re.test(location.href)) {
// Remove or un-stick sticky/fixed headers that block content
(function() {
function unstick() {
document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) {
if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {
el.style.position = 'static';
el.style.top = 'auto';
el.style.zIndex = 'auto';
}
});
}
unstick();
var observer = new MutationObserver(unstick);
observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });
})();
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index · Issue #1976 · apache/maka · GitHub
              Skip to content
              fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index #1976
              Closed
              #1995
              Closed
              fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index#1976
              #1995
              Assignees
              Astro-Han
              Description
              @Astro-Han
              Astro-Han
              opened on Aug 3, 2026
              A gateway that labels two distinct streamed tool calls with the same tool_calls[].index gets them merged into one. The arguments are concatenated into invalid JSON, the second call's id and name are dropped, and nothing errors.
              in: {index:0, id:"call_a", name:"read_file", args:'{"path":"a"}'}
{index:0, id:"call_b", name:"read_file", args:'{"path":"b"}'}
out: [{"toolCallId":"call_a","input":"{\"path\":\"a\"}{\"path\":\"b\"}"}]

              processExistingToolCall in @ai-sdk/provider-utils only appends to arguments; it ignores the id and function.name on every delta after the first for a given index.
              This is worse than the crash in #1967. The agent proceeds believing it called one tool with garbage arguments, and the second tool never runs, with no signal anywhere.
              Reach. 46 providers in provider-registry.ts use the openai-compatible runtime adapter, including ollama and ollama-cloud, both status: 'ready'. vercel/ai#14277 reports that Ollama labels every tool call in a turn with index: 0 (verified there against Ollama 0.20.2/0.20.4 with qwen3-coder:30b and others, 100% failure on multi-tool turns). I reproduced the merge at the protocol layer through the real provider stack, but I have not run it end to end against a live Ollama, so that half rests on the upstream report.
              Secondary case, same root. When deltas carry no index at all and a call spans more than one chunk, the ?? this.toolCalls.length fallback picks a fresh slot for the continuation and it throws Expected 'id' to be a string. No known maka path hits this today, since Google uses the native adapter, but a relay could.
              Not caused by #1971. Output is byte-identical with and without that patch; it fixes a crash from sparse indices and deliberately does not widen into this. patches/README.md records both cases.
              Why this isn't a one-line fix.index says which call a delta belongs to, but identity actually lives in toolCallDelta.id. The tracker keys off neither consistently, so any real fix rekeys it on id and decides what to do when a gateway violates the protocol: two distinct calls, or an explicit protocol error, but never a silent merge. That is upstream's call to make. Tracking here so it isn't rediscovered from a user report.
              Upstream: vercel/ai#18333, vercel/ai#14277.
              Metadata
              Metadata
              Assignees
              Labels
              No labels
              No labels
              Type
              No type
              Projects
              No projects
                Milestone
                No milestone
                Relationships
                None yet
                Development
                No branches or pull requests
                Issue actions
                
, 'i');
if (__m === '*' || __re.test(location.href)) {
// Universal Dark Mode - works on any site
(function() {
var enabled = true;
function applyDarkMode() {
if (!enabled) return;
// Create style element if it doesn't exist
var style = document.getElementById('universal-dark-mode-style');
if (!style) {
style = document.createElement('style');
style.id = 'universal-dark-mode-style';
document.head.appendChild(style);
}
// Dark mode CSS - inverts colors but preserves images/video
style.textContent = '
/* Invert everything except media */
html {
filter: invert(1) hue-rotate(180deg) !important;
background: #1a1a2e !important;
}
/* Restore images, videos, iframes, canvas */
img, video, iframe, canvas, svg, picture, [style*="background-image"] {
filter: invert(1) hue-rotate(180deg) !important;
}
/* Preserve specific elements that should not be inverted */
.no-dark-mode, .no-dark-mode *,
[data-theme="light"], [data-theme="light"],
.ace_editor, .ace_editor *,
.CodeMirror, .CodeMirror *,
.monaco-editor, .monaco-editor *,
.markdown-body pre, .markdown-body pre *,
.highlight, .highlight *,
pre code, pre code * {
filter: none !important;
}
/* Fix common UI elements */
.modal, .popup, .dropdown-menu, .tooltip, .popover {
filter: invert(1) hue-rotate(180deg) !important;
background: #2d2d44 !important;
border-color: #444 !important;
}
/* Scrollbars */
::-webkit-scrollbar { background: #1a1a2e !important; }
::-webkit-scrollbar-thumb { background: #444 !important; }
::-webkit-scrollbar-thumb:hover { background: #555 !important; }
/* Selection */
::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
';
}
function removeDarkMode() {
var style = document.getElementById('universal-dark-mode-style');
if (style) style.remove();
}
// Toggle with Alt+Shift+D
document.addEventListener('keydown', function(e) {
if (e.altKey && e.shiftKey && e.key === 'D') {
e.preventDefault();
enabled = !enabled;
if (enabled) {
applyDarkMode();
console.log('[Universal Dark Mode] Enabled');
} else {
removeDarkMode();
console.log('[Universal Dark Mode] Disabled');
}
}
});
// Apply on load
applyDarkMode();
// Re-apply on dynamic content
var observer = new MutationObserver(function(mutations) {
if (enabled && !document.getElementById('universal-dark-mode-style')) {
applyDarkMode();
}
});
observer.observe(document.head, { childList: true });
console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');
})();
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();
fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index · Issue #1976 · apache/maka · GitHub
                Skip to content
                fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index #1976
                Closed
                #1995
                Closed
                fix(runtime): streamed tool calls silently merge when an OpenAI-compatible provider reuses one tool_calls index#1976
                #1995
                Assignees
                Astro-Han
                Description
                @Astro-Han
                Astro-Han
                opened on Aug 3, 2026
                A gateway that labels two distinct streamed tool calls with the same tool_calls[].index gets them merged into one. The arguments are concatenated into invalid JSON, the second call's id and name are dropped, and nothing errors.
                in: {index:0, id:"call_a", name:"read_file", args:'{"path":"a"}'}
{index:0, id:"call_b", name:"read_file", args:'{"path":"b"}'}
out: [{"toolCallId":"call_a","input":"{\"path\":\"a\"}{\"path\":\"b\"}"}]

                processExistingToolCall in @ai-sdk/provider-utils only appends to arguments; it ignores the id and function.name on every delta after the first for a given index.
                This is worse than the crash in #1967. The agent proceeds believing it called one tool with garbage arguments, and the second tool never runs, with no signal anywhere.
                Reach. 46 providers in provider-registry.ts use the openai-compatible runtime adapter, including ollama and ollama-cloud, both status: 'ready'. vercel/ai#14277 reports that Ollama labels every tool call in a turn with index: 0 (verified there against Ollama 0.20.2/0.20.4 with qwen3-coder:30b and others, 100% failure on multi-tool turns). I reproduced the merge at the protocol layer through the real provider stack, but I have not run it end to end against a live Ollama, so that half rests on the upstream report.
                Secondary case, same root. When deltas carry no index at all and a call spans more than one chunk, the ?? this.toolCalls.length fallback picks a fresh slot for the continuation and it throws Expected 'id' to be a string. No known maka path hits this today, since Google uses the native adapter, but a relay could.
                Not caused by #1971. Output is byte-identical with and without that patch; it fixes a crash from sparse indices and deliberately does not widen into this. patches/README.md records both cases.
                Why this isn't a one-line fix.index says which call a delta belongs to, but identity actually lives in toolCallDelta.id. The tracker keys off neither consistently, so any real fix rekeys it on id and decides what to do when a gateway violates the protocol: two distinct calls, or an explicit protocol error, but never a silent merge. That is upstream's call to make. Tracking here so it isn't rediscovered from a user report.
                Upstream: vercel/ai#18333, vercel/ai#14277.
                Metadata
                Metadata
                Assignees
                Labels
                No labels
                No labels
                Type
                No type
                Projects
                No projects
                  Milestone
                  No milestone
                  Relationships
                  None yet
                  Development
                  No branches or pull requests
                  Issue actions