Skip to content

πŸ› fix(model-runtime): strip additionalProperties and leftover $ref in Google tool schemas#13613

Merged
arvinxx merged 1 commit intocanaryfrom
fix/google-strip-unsupported-schema-keys
Apr 7, 2026
Merged

πŸ› fix(model-runtime): strip additionalProperties and leftover $ref in Google tool schemas#13613
arvinxx merged 1 commit intocanaryfrom
fix/google-strip-unsupported-schema-keys

Conversation

@arvinxx
Copy link
Copy Markdown
Member

@arvinxx arvinxx commented Apr 7, 2026

πŸ’» Change Type

  • πŸ› fix

πŸ”— Related Issue

Follow-up to #13524

πŸ”€ Description of Change

Google Gemini / Vertex AI rejects additionalProperties and $ref in function declaration schemas. PR #13524 resolved most $ref via resolveRefs() but missed two cases:

  1. additionalProperties β€” was never stripped, causing Unknown name "additionalProperties" errors
  2. $ref β€” survived when resolveRefs hit its depth limit (>10) on recursive schemas, causing Unknown name "$ref" errors

Fix: add both keys to UNSUPPORTED_SCHEMA_KEYS so sanitizeSchemaForGoogle() strips them after ref resolution.

πŸ§ͺ How to Test

  • Added/updated tests
cd packages/model-runtime && bunx vitest run src/core/contextBuilders/google.test.ts

2 new test cases:

  • Strips additionalProperties from nested schemas
  • Strips remaining $ref when resolveRefs exceeds depth limit on recursive schemas

πŸ“ Additional Information

Error reproduced with gemini-3.1-pro-preview model when user tools contain deeply nested recursive schemas with additionalProperties and $ref.

… Google tool schemas

Google Gemini / Vertex AI rejects `additionalProperties` and `$ref` in
function declaration schemas. The previous fix (PR #13524) resolved most
`$ref` via `resolveRefs()` but missed two cases:

1. `additionalProperties` was never stripped
2. `$ref` survived when `resolveRefs` hit its depth limit (>10) on
   recursive schemas

Add both keys to UNSUPPORTED_SCHEMA_KEYS so `sanitizeSchemaForGoogle()`
strips them after ref resolution.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@vercel
Copy link
Copy Markdown

vercel bot commented Apr 7, 2026

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
lobehub Ready Ready Preview, Comment Apr 7, 2026 7:49am

Request Review

Copy link
Copy Markdown
Contributor

@sourcery-ai sourcery-ai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We've reviewed this pull request using the Sourcery rules engine

@lobehubbot
Copy link
Copy Markdown
Member

@sxjeru - This is a model provider fix for Google/Gemini tool schema sanitization (stripping additionalProperties and leftover $ref). Please take a look.

Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

πŸ’‘ Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 98d2db90dc

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with πŸ‘.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

@codecov
Copy link
Copy Markdown

codecov bot commented Apr 7, 2026

Codecov Report

βœ… All modified and coverable lines are covered by tests.
βœ… Project coverage is 66.68%. Comparing base (5231bbb) to head (98d2db9).
⚠️ Report is 1 commits behind head on canary.

Additional details and impacted files
@@            Coverage Diff            @@
##           canary   #13613     +/-   ##
=========================================
  Coverage   66.68%   66.68%             
=========================================
  Files        1997     1997             
  Lines      165892   165892             
  Branches    19962    16093   -3869     
=========================================
  Hits       110628   110628             
  Misses      55140    55140             
  Partials      124      124             
Flag Coverage Ξ”
app 58.58% <ΓΈ> (ΓΈ)
database 92.60% <ΓΈ> (ΓΈ)
packages/agent-runtime 88.98% <ΓΈ> (ΓΈ)
packages/context-engine 85.51% <ΓΈ> (ΓΈ)
packages/conversation-flow 92.36% <ΓΈ> (ΓΈ)
packages/file-loaders 87.02% <ΓΈ> (ΓΈ)
packages/memory-user-memory 66.68% <ΓΈ> (ΓΈ)
packages/model-bank 99.85% <ΓΈ> (ΓΈ)
packages/model-runtime 84.64% <100.00%> (ΓΈ)
packages/prompts 65.80% <ΓΈ> (ΓΈ)
packages/python-interpreter 92.90% <ΓΈ> (ΓΈ)
packages/ssrf-safe-fetch 0.00% <ΓΈ> (ΓΈ)
packages/utils 89.74% <ΓΈ> (ΓΈ)
packages/web-crawler 88.82% <ΓΈ> (ΓΈ)

Flags with carried forward coverage won't be shown. Click here to find out more.

Components Coverage Ξ”
Store 67.12% <ΓΈ> (ΓΈ)
Services 51.45% <ΓΈ> (ΓΈ)
Server 66.37% <ΓΈ> (ΓΈ)
Libs 51.05% <ΓΈ> (ΓΈ)
Utils 91.01% <ΓΈ> (ΓΈ)
πŸš€ New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
  • πŸ“¦ JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

@arvinxx arvinxx merged commit ca01385 into canary Apr 7, 2026
34 checks passed
@arvinxx arvinxx deleted the fix/google-strip-unsupported-schema-keys branch April 7, 2026 08:08
arvinxx added a commit that referenced this pull request Apr 7, 2026
# πŸš€ release: 20260407

This release includes **148 commits**. Key updates are below.

- **Response API tool execution is more capable and reliable** β€” Added
hosted builtin tools + client-side function tools and improved tool-call
streaming/completion behavior.
[#13406](#13406)
[#13414](#13414)
[#13506](#13506)
[#13555](#13555)
- **Input and composition UX upgraded** β€” Added AI input auto-completion
and multiple chat-input stability fixes.
[#13458](#13458)
[#13551](#13551)
[#13481](#13481)
- **Model/provider compatibility improved** β€” Better Gemini/Google tool
schema handling and additional model updates.
[#13429](#13429)
[#13465](#13465)
[#13613](#13613)
- **Desktop and CLI reliability improved** β€” Gateway WebSocket support
and desktop runtime upgrades.
[#13608](#13608)
[#13550](#13550)
[#13557](#13557)
- **Security hardening continued** β€” Fixed auth and sanitization risks
and upgraded vulnerable dependencies.
[#13535](#13535)
[#13529](#13529)
[#13479](#13479)

### Models & Providers

- Added/updated support for `glm-5v-turbo`, GLM-5.1 updates, and
qwen3.5-omni series.
[#13487](#13487)
[#13405](#13405)
[#13422](#13422)
- Added additional ImageGen providers/models (Wanxiang 2.7 and Keling
from Qwen). [#13478](#13478)
- Improved Gemini/Google tool schema and compatibility handling across
runtime paths. [#13429](#13429)
[#13465](#13465)
[#13613](#13613)

### Response API & Runtime

- Added hosted builtin tools in Response API and client-side function
tool execution support.
[#13406](#13406)
[#13414](#13414)
- Improved stream tool-call argument handling and `response.completed`
output correctness.
[#13506](#13506)
[#13555](#13555)
- Improved runtime error/context handling for intervention and provider
edge cases. [#13420](#13420)
[#13607](#13607)

### Desktop App

- Bumped desktop dependencies and runtime integrations (`agent-browser`,
`electron`). [#13550](#13550)
[#13557](#13557)
- Simplified desktop release channel setup by removing nightly release
flow. [#13480](#13480)

### CLI

- Added OpenClaw migration command.
[#13566](#13566)
- Added local device binding support for `lh agent run`.
[#13277](#13277)
- Added WebSocket gateway support and reconnect reliability
improvements. [#13608](#13608)
[#13418](#13418)

### Security

- Removed risky `apiKey` fallback behavior in webapi auth path to
prevent bypass risk.
[#13535](#13535)
- Sanitized HTML artifact rendering and iframe sandboxing to reduce
XSS-to-RCE risk. [#13529](#13529)
- Upgraded nodemailer to v8 to address SMTP command injection advisory.
[#13479](#13479)

### Bug Fixes

- Fixed image generation model default switch issues.
[#13587](#13587)
- Fixed subtopic re-fork message scope behavior and agent panel reset
edge cases. [#13606](#13606)
[#13556](#13556)
- Fixed chat-input freeze on paste and mention plugin behavior.
[#13551](#13551)
[#13415](#13415)
- Fixed auth/social sign-in and settings UX edge cases.
[#13368](#13368)
[#13392](#13392)
[#13338](#13338)

### Credits

Huge thanks to these contributors:

@chriszf @hardy-one @Innei @lijian @neko @OctopusNote @rdmclin2
@rivertwilight @RylanCai @suyua9 @sxjeru @Tsuki @wangyk @WindSpiritSR
@yizhuo @YuTengjing @hezhijie0327 @arvinxx
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