fix(tool): correct Windows path handling in write_file and add sessio…

[leonard9893]

…n state repair for interrupt resilience

Bug 1 (Windows path handling):

• Add _normalize_windows_path() to detect and convert Unix-style paths (e.g. /Users/zimu/...) to proper Windows paths (C:\Users...) on Windows
• Add _detect_hardcoded_username() to warn when model generates paths with hardcoded usernames (training-data contamination)
• Write_file_tool now performs parent directory existence check on Windows
• Add OS-aware path validation with warnings for wrong platform paths

Bug 2 (Session interrupt tool call loss):

• Add _validate_and_repair_session_state() to strip orphan tool_calls and trailing tool result messages after session interrupt/resume
• Fix corrupted message sequences that contain incomplete tool-call patterns (assistant with tool_calls but no matching tool results)
• Remove terminal tool/function messages so the API doesn't reject

Bug 3 (Tool execution hallucination):

• Add _detect_tool_call_hallucination() that catches model responses claiming tool execution (e.g. "I've written the file") with zero actual tool_calls — common after session resume
• On detection, inject a nudge message retrying with actual tool calls instead of accepting the hallucination as the final answer

Closes #20927

What does this PR do?

Related Issue

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

How to Test

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:

Documentation & Housekeeping

• I've updated relevant documentation (README, docs/, docstrings) — or N/A
• I've updated cli-config.yaml.example if I added/changed config keys — or N/A
• I've updated CONTRIBUTING.md or AGENTS.md if I changed architecture or workflows — or 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

For New Skills

• 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