fix: handle dangling tool_use blocks for LiteLLM proxy compatibility by hendem · Pull Request #8497 · anomalyco/opencode · GitHub

Problem

When using OpenCode with LiteLLM proxies (e.g., for Vertex AI, Bedrock), session compaction fails with:

invalid_request_error: messages.2: `tool_use` ids were found without `tool_result` blocks immediately after

or:

litellm.UnsupportedParamsError: Anthropic doesn't support tool calling without `tools=` param specified

This affects users who route Anthropic/Claude API calls through corporate LiteLLM proxies and cannot modify proxy settings (e.g., modify_params=True).

Root Cause Analysis

There are two distinct issues causing these errors:

Issue 1: Missing tools parameter during compaction

When compaction runs, it calls processor.process() with tools: {} (compaction.ts:149):

const result = await processor.process({
  // ...
  tools: {},  // <-- Empty tools object
  messages: [
    ...MessageV2.toModelMessage(input.messages),  // <-- Contains tool_use/tool_result from history
    // ...
  ],
})

LiteLLM validates that if message history contains tool_use/tool_result blocks, the tools parameter must be present. While Anthropic's native API now handles this gracefully, LiteLLM enforces stricter validation.

Issue 2: Dangling tool_use blocks without tool_result

When a session is interrupted or aborted, tool calls may be left in pending or running state. The toModelMessage() function in message-v2.ts currently skips these incomplete tool calls:

if (part.state.status === "completed")
  assistantMessage.parts.push({ /* tool-result */ })
if (part.state.status === "error")
  assistantMessage.parts.push({ /* tool-result with error */ })
// pending/running are NOT handled - creates dangling tool_use!

This creates tool_use blocks in the assistant message without corresponding tool_result blocks, which Anthropic/Claude APIs strictly reject.

Solution

Fix 1: Add dummy _noop tool when message history contains tool calls

In llm.ts, detect when messages contain tool calls but no tools are provided, and inject a placeholder tool:

if (Object.keys(tools).length === 0 && hasToolCalls(input.messages)) {
  tools["_noop"] = tool({
    description: "Internal placeholder tool - not for use",
    inputSchema: jsonSchema({ type: "object", properties: {} }),
    execute: async () => ({ output: "", title: "", metadata: {} }),
  })
}

The _noop tool is excluded from activeTools so it won't be suggested or called by the LLM.

Fix 2: Convert pending/running tool calls to error results

In message-v2.ts, handle pending and running tool states by generating error tool_result blocks:

if (part.state.status === "pending" || part.state.status === "running")
  assistantMessage.parts.push({
    type: ("tool-" + part.tool) as `tool-${string}`,
    state: "output-error",
    toolCallId: part.callID,
    input: part.state.input,
    errorText: "[Tool execution was interrupted]",
    callProviderMetadata: part.metadata,
  })

This ensures every tool_use has a corresponding tool_result, satisfying Anthropic's API requirements.

Files Changed

File	Change
packages/opencode/src/session/llm.ts	Add hasToolCalls() helper and dummy _noop tool injection
packages/opencode/src/session/message-v2.ts	Handle pending/running tool states → error results
packages/opencode/test/session/message-v2.test.ts	Add test for pending/running tool conversion

Testing

Added unit test verifying pending/running tool calls are converted to error results
Manual testing needed with actual LiteLLM proxy setup

Prior Art

Commit 0af450575 attempted a fix but was later simplified away
LiteLLM has a modify_params=True workaround, but many corporate proxy deployments cannot change this setting

When sessions are compacted or interrupted, tool calls may be left in pending/running state without corresponding tool_result blocks. This causes Anthropic/Claude APIs (especially through LiteLLM proxies) to reject requests with validation errors. This change: 1. Converts pending/running tool calls to error results in toModelMessage to ensure every tool_use has a corresponding tool_result 2. Adds a dummy _noop tool when message history contains tool calls but no tools are provided (required by LiteLLM proxies) Fixes anomalyco#8246 Fixes anomalyco#2915

The following comment was made by an LLM, it may be inaccurate:

Based on my search, I found one potential duplicate/related PR:

Related PR Found

PR #8248: fix: avoid Anthropic tool-history requests without tools

fix: avoid Anthropic tool-history requests without tools #8248

Why it's related: This PR addresses a very similar issue - handling requests that contain tool calls/history but lack the tools parameter. PR #8497 includes adding a dummy _noop tool when message history contains tool calls but no tools are provided (for LiteLLM proxy compatibility), which appears to be the same problem space that PR #8248 was tackling.

Also note: PR #3243 mentioned in the description ("Fix: Each tool_use block must have a corresponding tool_result block in the next message") is the stale/conflicted PR that #8497 is intended to supersede/fix properly.

Pull request overview

This PR fixes session compaction failures when using OpenCode with LiteLLM proxies by ensuring every tool call has a corresponding tool result and that the tools parameter is present when needed.

Changes:

Pending and running tool calls now generate error tool results to prevent dangling tool_use blocks
A dummy _noop tool is added when message history contains tool calls but no tools are provided
Test coverage added for pending/running tool call conversion

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.

File	Description
packages/opencode/src/session/message-v2.ts	Adds handling for pending/running tool states to convert them to error results
packages/opencode/src/session/llm.ts	Adds dummy tool for LiteLLM proxy compatibility and helper function to detect tool calls
packages/opencode/test/session/message-v2.test.ts	Adds test coverage for pending/running tool call error result generation

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Re: Related PR #8248

Thanks for flagging the potential duplicate. I've reviewed PR #8248 and here's how this PR differs:

PR #8248 only addresses Issue 1 (missing tools parameter) and:

Only applies the fix for providers with "litellm" in their ID
Does not address dangling tool_use blocks from interrupted sessions

This PR (#8497) addresses both issues:

Missing tools parameter - Adds dummy _noop tool universally (not just LiteLLM) since other proxies may have the same validation
Dangling tool_use blocks - Converts pending/running tool calls to error results, ensuring every tool_use has a corresponding tool_result

The second fix is critical because even with the dummy tool, if there are dangling tool_use blocks from interrupted/aborted tool calls, the API will still reject the request with:

messages.2: `tool_use` ids were found without `tool_result` blocks immediately after

I'd suggest either closing #8248 in favor of this more comprehensive fix, or we could cherry-pick the provider-specific check from #8248 if the team prefers a more targeted approach for Issue 1.

Pull request overview

Copilot reviewed 4 out of 4 changed files in this pull request and generated no new comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

I've created #8658 which builds on this PR and addresses @rekram1-node's feedback from #8248.

The key change: Restricts _noop tool injection to only LiteLLM-backed providers instead of applying it unconditionally.

Detection logic:

const isLiteLLMProxy =
  provider.options?.["litellmProxy"] === true ||
  input.model.providerID.toLowerCase().includes("litellm") ||
  input.model.api.id.toLowerCase().includes("litellm")

Why this matters:

Your PR injects _noop for ALL providers unconditionally
Per @rekram1-node's comment: "There are a LOT of providers that don't have this issue... ideally this would be strictly limited to litellm"
My change adds auto-detection (provider ID contains "litellm") + explicit opt-in (litellmProxy: true option)

Config example for custom gateways:

{
  "provider": {
    "my-gateway": {
      "options": { "litellmProxy": true }
    }
  }
}

Happy to discuss merging this into your PR or keeping them separate.

What's the blocker of this PR? I need this to be merged.

Closing this pull request because it has had no updates for more than 60 days. If you plan to continue working on it, feel free to reopen or open a new PR.

Copilot AI review requested due to automatic review settings January 14, 2026 16:17

Copilot started reviewing on behalf of hendem January 14, 2026 16:17 View session

Merge branch 'dev' into fix/litellm-compaction-tool-calls

6c41388

Copilot AI reviewed Jan 14, 2026

View reviewed changes

Comment thread packages/opencode/src/session/llm.ts

Comment thread packages/opencode/src/session/llm.ts

address review: improve _noop description and add hasToolCalls tests

b734de4

hendem requested a review from Copilot January 14, 2026 16:46

Copilot started reviewing on behalf of hendem January 14, 2026 16:47 View session

Copilot AI reviewed Jan 14, 2026

View reviewed changes

github-actions Bot mentioned this pull request Jan 15, 2026

fix: anthropic patch #8566

Closed

seilk mentioned this pull request Jan 15, 2026

feat: add litellmProxy provider option for explicit LiteLLM compatibility #8658

Merged

github-actions Bot mentioned this pull request Jan 22, 2026

fix: include _noop tool in activeTools for LiteLLM proxy compatibility #9912

Merged

wcpaxx mentioned this pull request Jan 22, 2026

LiteLLM proxy error: "Anthropic doesn't support tool calling without tools=" even with litellmProxy: true (v1.1.31) #10037

Closed

thdxr force-pushed the dev branch from cbab81f to 2d3c7a0 Compare January 30, 2026 04:50

opencode-agent Bot force-pushed the dev branch from 00637c0 to 71e0ba2 Compare January 30, 2026 14:32

thdxr force-pushed the dev branch 3 times, most recently from f1ae801 to 08fa7f7 Compare January 30, 2026 14:37

jakvbs mentioned this pull request Feb 16, 2026

[FEATURE]: Preserve partial bash output for the model after abort #13809

Closed

1 task

randomm mentioned this pull request Feb 19, 2026

feat(tool-use-fix): cherry-pick upstream PR #8497 — fix dangling tool_use blocks on abort/crash randomm/opencode#218

Closed

12 tasks

github-actions Bot mentioned this pull request Feb 20, 2026

fix(core): repair interleaved text/tool-call parts in assistant messages #14456

Closed

6 tasks

This was referenced Feb 26, 2026

fix: prevent infinite retry loop from orphaned tool_use blocks #15152

Closed

fix(zen): guard against empty tool_result content in Anthropic provider #15375

Closed

This was referenced Mar 9, 2026

fix(session): fix root causes and reconstruction of tool_use/tool_result mismatch (#16749) #16751

Closed

fix: filter empty content blocks for Bedrock provider #17381

Closed

github-actions Bot mentioned this pull request Mar 21, 2026

fix: discourage _noop tool call during LiteLLM compaction #18539

Merged

6 tasks

This was referenced Apr 11, 2026

fix(opencode): ensure tool-call/tool-result pairing after normalizeMessages #22001

Closed

feat(provider): add LiteLLM provider support #22008

Closed

opencode-agent Bot force-pushed the dev branch from 2f2ed11 to 9f201d6 Compare April 16, 2026 21:55

zxkane mentioned this pull request Apr 22, 2026

fix: allow messages with tool blocks when tools array is omitted aws-samples/bedrock-access-gateway#239

Open

github-actions Bot closed this Apr 27, 2026

fix: handle dangling tool_use blocks for LiteLLM proxy compatibility by hendem · Pull Request #8497 · anomalyco/opencode · GitHub

Uh oh!

fix: handle dangling tool_use blocks for LiteLLM proxy compatibility - #8497

fix: handle dangling tool_use blocks for LiteLLM proxy compatibility#8497
hendem wants to merge 3 commits into
anomalyco:devfrom
hendem:fix/litellm-compaction-tool-calls

hendem commented Jan 14, 2026 •
edited
Loading

Uh oh!

Uh oh!

github-actions Bot commented Jan 14, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

hendem commented Jan 14, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

seilk commented Jan 15, 2026

Uh oh!

sinwoobang commented Feb 26, 2026

Uh oh!

github-actions Bot commented Apr 27, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

fix: handle dangling tool_use blocks for LiteLLM proxy compatibility by hendem · Pull Request #8497 · anomalyco/opencode · GitHub

Uh oh!

fix: handle dangling tool_use blocks for LiteLLM proxy compatibility - #8497

fix: handle dangling tool_use blocks for LiteLLM proxy compatibility#8497hendem wants to merge 3 commits intoanomalyco:devanomalyco/opencode:devfrom hendem:fix/litellm-compaction-tool-callshendem/opencode:fix/litellm-compaction-tool-callsCopy head branch name to clipboard

Conversation

hendem commented Jan 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Problem

Root Cause Analysis

Issue 1: Missing tools parameter during compaction

Issue 2: Dangling tool_use blocks without tool_result

Solution

Fix 1: Add dummy _noop tool when message history contains tool calls

Fix 2: Convert pending/running tool calls to error results

Files Changed

Testing

Related

Prior Art

Uh oh!

github-actions Bot commented Jan 14, 2026

Related PR Found

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

hendem commented Jan 14, 2026

Re: Related PR #8248

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

seilk commented Jan 15, 2026

Uh oh!

sinwoobang commented Feb 26, 2026

Uh oh!

github-actions Bot commented Apr 27, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

fix: handle dangling tool_use blocks for LiteLLM proxy compatibility#8497
hendem wants to merge 3 commits into
anomalyco:devfrom
hendem:fix/litellm-compaction-tool-calls

hendem commented Jan 14, 2026 •
edited
Loading