PR #60391: fix(kimi-coding): Make tool calling works again by remove OpenAI toolSchemaMode and toolChoiceMode

• Repository: openclaw/openclaw
• Author: Eric-Guo
• State: closed | merged: True
• Link: https://github.com/openclaw/openclaw/pull/60391

Description (problem / solution / changelog)

Summary

• Problem: kimi-for-coding not usable after 2026.4.2 to current main version
• Why it matters: it cause openclaw un-usable for user, who using kimi-for-coding.
• What changed: Using anthropic style calling
• What did NOT change (scope boundary): every other part except for kimi-coding extension.

Change Type (select all)

• Bug fix
• Feature
• Refactor required for the fix
• Docs
• Security hardening
• Chore/infra

Scope (select all touched areas)

• Gateway / orchestration
• Skills / tool execution
• Auth / tokens
• Memory / storage
• Integrations
• API / contracts
• UI / DX
• CI/CD / infra

Linked Issue/PR

• Closes #60059
• Related #
• This PR fixes a bug or regression

Root Cause / Regression History (if applicable)

• Root cause: Kimi code K2.5 always work in anthropic-message format.
• Missing detection / guardrail:
• Prior context (git blame, prior PR, issue, or refactor if known):
• Why this regressed now: Unknown
• If unknown, what was ruled out:

Regression Test Plan (if applicable)

For bug fixes or regressions, name the smallest reliable test coverage that should have caught this. Otherwise write N/A.

• Coverage level that should have caught this:
  • Unit test
  • Seam / integration test
  • End-to-end test
  • Existing coverage already sufficient
• Target test or file:
• Scenario the test should lock in:
• Why this is the smallest reliable guardrail:
• Existing test that already covers this (if any):
• If no new test is added, why not:

User-visible / Behavior Changes

Before fix:

After fix:

Diagram (if applicable)

N/A

Security Impact (required)

• New permissions/capabilities?: No
• Secrets/tokens handling changed?: No
• New/changed network calls?: Yes/No
• Command/tool execution surface changed?: Yes/No
• Data access scope changed?: Yes/No
• If any Yes, explain risk + mitigation:

Repro + Verification

Environment

• OS: MacOS
• Runtime/container: brew install node@24
• Model/provider: kimi-for-coding
• Integration/channel (if any): kimi
• Relevant config (redacted): see below

{
  "version": 1,
  "profiles": {
    "kimi-coding:default": {
      "type": "api_key",
      "provider": "kimi-coding",
      "key": "sk-kimi-key"
    },
  },
  "lastGood": {
    "kimi-coding": "kimi-coding:default",
  },
  "usageStats": {
    "kimi-coding:default": {
      "lastUsed": 1775229293844,
      "errorCount": 0,
      "lastFailureAt": 1774701235004
    }
  }
}

Steps

1. Say hello or /new

Expected

• tool call executed

Actual

我来获取这篇文章并全文翻译。 <|tool_calls_section_begin|> <|tool_call_begin|> functions.web_fetch:0 <|tool_call_argument_begin|> {"url": "https://socket.dev/blog/hidden-blast-radius-of-the-axios-compromise"} <|tool_call_end|> <|tool_calls_section_end|>

Evidence

Attach at least one:

• Failing test/log before + passing after
• Trace/log snippets
• Screenshot/recording
• Perf numbers (if relevant)

Human Verification (required)

What you personally verified (not just CI), and how:

• Verified scenarios: Yew
• Edge cases checked: No

Review Conversations

• I replied to or resolved every bot review conversation I addressed in this PR.
• I left unresolved only the conversations that still need reviewer or maintainer judgment.

If a bot review conversation is addressed by this PR, resolve that conversation yourself. Do not leave bot review conversation cleanup for maintainers.

Compatibility / Migration

• Backward compatible? No
• Config/env changes? No
• Migration needed? No
• If yes, exact upgrade steps: No need

Risks and Mitigations

None

Changed files

• CHANGELOG.md (modified, +1/-0)
• extensions/kimi-coding/index.ts (modified, +2/-2)
• extensions/kimi-coding/stream.ts (modified, +0/-7)
• src/agents/pi-embedded-runner-extraparams.test.ts (modified, +25/-21)