PR #10874: feat(web_search): add Kimi global/CN web_search support

• Repository: NousResearch/hermes-agent
• Author: hcshen0111
• State: open | merged: False
• Link: https://github.com/NousResearch/hermes-agent/pull/10874

Description (problem / solution / changelog)

What does this PR do?

This PR improves Kimi web-search integration in tools/web_tools.py by adding robust dual-key support (KIMI_API_KEY or KIMI_CN_API_KEY) .

It fixes provider selection/credential-routing issues for Kimi web search and removes noisy serializer warnings caused by Kimi builtin tool calls (type="builtin_function"), while preserving backward compatibility for other web backends.

Related Issue

Resolves #11637

Type of Change

• 🐛 Bug fix (non-breaking change that fixes an issue)
• ✨ New feature (non-breaking change that adds functionality)
• 🔒 Security fix
• 📝 Documentation update
• ✅ Tests (adding or improving test coverage)
• ♻️ Refactor (no behavior change)
• 🎯 New skill (bundled or hub)

Changes Made

• Updated Kimi backend availability checks to support both KIMI_API_KEY and KIMI_CN_API_KEY.
• Added provider-aware Kimi credential resolution in:
  • tools/web_tools.py
• Added Kimi China endpoint support (https://api.moonshot.cn/v1) for web search.
• Updated Kimi chat-completion path to use OpenAI SDK for consistency with main agent/provider routing behavior.
• Added standalone .env loading in tools/web_tools.py main entrypoint (aligns local testing behavior with runtime env loading).
• Added/updated Kimi diagnostics in --show-env output (global key, CN key, resolved base URL).
• Added standardized tool_error(...) helper usage path for web tool error responses.
• Suppressed Pydantic serialization warnings for Kimi builtin tool calls using JSON-mode dumps with warnings disabled.
• Removed unused helper _get_kimi_base_url.
• Updated tests in:
  • tests/tools/test_web_tools_config.py
  • Added coverage for:
    • Kimi global-only and CN-only backend detection
    • dual-key routing preference behavior
    • Kimi credential resolution edge cases
    • required env metadata updates

How to Test

1. Run targeted tests:

   source venv/bin/activate
   python -m pytest tests/tools/test_web_tools_config.py -q
   python -m pytest tests/tools/test_web_tools_tavily.py -q

2. Configure Kimi web backend:

   ~/.hermes/config.yaml:

   web:
     backend: kimi

   ~/.hermes/.env (example):

   KIMI_CN_API_KEY=...
   # or KIMI_API_KEY=...

3. Verify runtime behavior:

   source venv/bin/activate
   python tools/web_tools.py --show-env
   python tools/web_tools.py --query "Moonshot AI Context Caching 是什么" --limit 3

Checklist

Code

• I've read the Contributing Guide
• My commit messages follow Conventional Commits (fix(scope):, feat(scope):, etc.)
• I searched for existing PRs to make sure this isn't a duplicate
• My PR contains only changes related to this fix/feature (no unrelated commits)
• I've run pytest tests/ -q and all tests pass
• I've added tests for my changes (required for bug fixes, strongly encouraged for features)
• I've tested on my platform: Linux (local CLI environment)

Documentation & Housekeeping

• I've updated relevant documentation (README, docs/, docstrings) — or N/A
  • N/A (no public docs changed in this PR)
• I've updated cli-config.yaml.example if I added/changed config keys — or N/A
  • N/A (no new config key added)
• I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — or N/A
  • N/A
• I've considered cross-platform impact (Windows, macOS) per the compatibility guide — or N/A
• I've updated tool descriptions/schemas if I changed tool behavior — or N/A
  • N/A (runtime behavior changed, schema contract unchanged)

Changed files

• tests/tools/test_web_tools_config.py (modified, +85/-0)
• tools/web_tools.py (modified, +291/-93)
• website/docs/guides/automate-with-cron.md (modified, +9/-9)
• website/docs/integrations/index.md (modified, +4/-3)
• website/docs/reference/tools-reference.md (modified, +1/-2)
• website/docs/user-guide/configuration.md (modified, +4/-3)