chore: move parameter and tokenizer diagnostics to debug

[leejet]

Summary

• Move CLI, context, and generation parameter dumps from verbose to debug.
• Move tokenizer vocabulary and merge counts, ggml tensor size, and Wan patch embedding channels to debug.

Related Issue / Discussion

N/A

Additional Information

N/A

Checklist

• I have read and confirmed this PR follows the contribution guidelines.

Summary by CodeRabbit

• Logging
  • Moved selected diagnostic messages about model parameters, model and tensor details, and tokenizer vocabulary and merge counts from verbose to debug level. Classification and processing behavior are unchanged.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

• Configuration used: Repository UI
• Review profile: CHILL
• Plan: Advanced
• Run ID: 03a85a11-8d96-487a-b3bf-079e183660cb

📥 Commits

Reviewing files that changed from the base of the PR and between 46362fc and 975863b.

📒 Files selected for processing (8)

• examples/cli/main.cpp
• examples/server/main.cpp
• src/model_loader.cpp
• src/pipeline/diffusion_engine.cpp
• src/tokenizers/clip_tokenizer.cpp
• src/tokenizers/gemma_tokenizer.cpp
• src/tokenizers/mistral_tokenizer.cpp
• src/tokenizers/qwen2_tokenizer.cpp

Included review availability: This review used your included allowance. Your plan provides up to 10 included reviews per hour; 8 remain after this review.

📝 Walkthrough

Selected diagnostic messages in the CLI, server, model loader, diffusion engine, and tokenizers now use debug logging instead of verbose logging. The logged values and related classification and parsing behavior remain unchanged.

Changes: Logging level updates

Layer / File(s)	Summary
Example parameter logs examples/cli/main.cpp, examples/server/main.cpp	CLI parameter summaries and server context and default generation parameter strings now use debug logging.
Model and tokenizer logs src/model_loader.cpp, src/pipeline/diffusion_engine.cpp, src/tokenizers/*	WAN classification, tensor-size, and tokenizer vocabulary and merge-count messages now use debug logging.

Priority: ⬇️ Low

Estimated code review effort: 1 (Trivial) | ~4 minutes

Change: Other

Suggested reviewers: wbruna

Merge Risk: ⚪ Minimal · up to 97586

These diagnostics now require the debug threshold rather than the verbose threshold to appear. Their values and the underlying model and tokenizer behavior are unchanged, leaving no actionable merge risk.

Pre-merge checks · 4 · 1

Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage		Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%. Docstring coverage is scoped to functions touched by this diff. Analyzed 8 functions across 8 files.	Write docstrings for the functions missing them to satisfy the coverage threshold.

Passed checks (4 passed)

Check name	Status	Explanation
Description check		The description includes all required sections. It accurately summarizes the logging-level changes, identifies no related issue, provides additional information, and confirms the contribution checklis…
Title check		The title clearly and concisely describes the main change: moving parameter and tokenizer diagnostics from verbose logging to debug logging.
Linked Issues check		Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check		Check skipped because no linked issues were found for this pull request.

• Fix all pre-merge checks with AI

✨ Finishing Touches 💡 1

📝 Generate docstrings 💡

• Commit to this branch
• Create a new PR

🧪 Generate unit tests (beta)

• Commit to this branch
• Create a new PR

• Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Warning

Some tools did not complete. Review the errors below.

🔧 Cppcheck (2.22.0)

src/pipeline/diffusion_engine.cpp

Cppcheck timed out; analysis of this file is incomplete

_{Comment @coderabbitai help to get the list of available commands.}