Merge pull request janhq#6929 from janhq/feat/official_jan_browser_mcp

feat: Add official jan browser mcp

Shorten flash attention flag in args

Comment out webui disable argument for ik_llama.cpp

Comment out the line that disables the llama-server webui.

Merge pull request #5 from Thireus/th/no-sign

Add NO_SIGN variable to Makefile

Merge pull request janhq#6728 from menloresearch/fix/anthropic-model-…

…load

Fix: Anthropic request to add models

Merge pull request janhq#6706 from menloresearch/qa/v0.7.0

feat: update checklist for 0.7.0

fix: correct memory suitability checks in llamacpp extension (janhq#6504

)

The previous implementation mixed model size and VRAM checks, leading to inaccurate status reporting (e.g., false RED results).
- Simplified import statement for `readGgufMetadata`.
- Fixed RAM/VRAM comparison by removing unnecessary parentheses.
- Replaced ambiguous `modelSize > usableTotalMemory` check with a clear `totalRequired > usableTotalMemory` hard‑limit condition.
- Refactored the status logic to explicitly handle the CPU‑GPU hybrid scenario, returning **YELLOW** when the total requirement fits combined memory but exceeds VRAM.
- Updated comments for better readability and maintenance.

fix: jan server api base url for prod

chore: add cicd for jan web prod

fix: Use 80% total memory for compatibility check (janhq#6321)

* fix: Use 80% total memory for compatibility check

* refactor: extract usable memory percentage to named constant

Extract the hardcoded 0.8 multiplier into a named constant
USABLE_MEMORY_PERCENTAGE for better readability and maintainability.