fix(tools): split concatenated streamed tool-call args

[Jamesvagabond599]

What does this PR do?

Fixes streamed tool-call handling when a model emits multiple concatenated JSON tool-call argument payloads in one streamed argument buffer.

The repair splits adjacent complete JSON object payloads before reconstructing streamed mock tool calls, preventing concatenated tool-call arguments from being treated as a single invalid JSON blob.

Related Issue

Fixes tool-call argument streaming failures observed with local Hermes/Qwen-style runtime usage.

Fixes #

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

• Adds _split_concatenated_tool_call_arguments(...) handling in agent/chat_completion_helpers.py.
• Applies the splitter before streamed mock_tool_calls reconstruction.
• Adds focused regression coverage in tests/test_model_tools_tool_call_payload_repair.py.
• Preserves existing single-payload behavior and rejects incomplete/partial concatenations.

How to Test

1. ./venv/bin/python -m pytest -q tests/test_model_tools_tool_call_payload_repair.py
2. Confirm result: 3 passed.
3. Confirm the branch contains only:
   • agent/chat_completion_helpers.py
   • tests/test_model_tools_tool_call_payload_repair.py

Checklist

Code

• My commit messages follow Conventional Commits (fix(scope): ...)
• I searched for existing PRs to make sure this isn’t a duplicate
• My PR contains only changes related to this fix/feature
• I've run pytest tests/ -q and all tests pass
• I've added tests for my changes
• I've tested on my platform: Linux / Fedora

Documentation & Housekeeping

• I've updated relevant documentation — N/A, behavior-only bug fix with regression test
• I've updated cli-config.yaml.example if I added/changed config keys — N/A
• I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — N/A
• I've considered cross-platform impact — pure Python parsing helper, no OS-specific behavior
• I've updated tool descriptions/schemas if I changed tool behavior — N/A

For New Skills

[x] N/A — this PR does not add a skill

• This skill is broadly useful to most users (if bundled) — see Contributing Guide
• SKILL.md follows the standard format (frontmatter, trigger conditions, steps, pitfalls)
• No external dependencies that aren't already available (prefer stdlib, curl, existing Hermes tools)
• I've tested the skill end-to-end: hermes --toolsets skills -q "Use the X skill to do Y"

Screenshots / Logs

[alt-glitch]

Duplicate of #36039 and #25346 — same fix: splitting concatenated streamed tool-call argument payloads ({...}{...}) into separate calls via json.JSONDecoder.raw_decode(). All three target the same root cause (#25333). Consolidating effort on one of these would help maintainers avoid reviewing three near-identical implementations.