Apply local-first accumulation for chunk-level optimizer progress.

Accept incremental BERT phrase gains during optimization.

Add semantic gap tolerance and detailed gap attribution.

Improve optimizer attribution and multi-edit batch search.

Add deep LLM-input diagnostics for chunk optimization debugging.

Implement two-stage optimizer acceptance with multi-chunk batching.

Improve optimizer span selection to avoid repeated chunk edits.

Trigger rebuild on Hugging Face without app code changes.

Expand full functional documentation with algorithmic details.

Improve optimizer candidate validation and BERT goal tracking.

Implement cascade state-machine for optimizer edit escalation

Add detailed optimizer debug trace for candidate-level visibility

Tune optimizer acceptance policy and add optimization modes

Add LLM optimizer tab with iterative constrained text improvements

Apply adaptive competitor threshold for summary recommendations

Render summary recommendation details as tables

Refine semantic summary to prioritize keyword n-grams over stop words

Add summary tab with cross-metric actionable recommendations

Update title tab to show target row and keyword highlights

Add Portuguese language support across app and deployment

Add URL-based text and title import with user-agent presets

Update README with current app architecture and features

Add semantic term power table sorting controls

Add comprehensive functional documentation and README links

Enable semantic search by phrase and word terms

Move semantic search results directly under search form

Extend semantic comparison table to include phrase terms

Add semantic cleanup, canonicalization, and generic-term downweighting

Improve phrase-term importance scoring in semantic graph

Add phrase-term nodes with frequency filtering in semantic graph

Fix semantic graph: clamp conditional links <=100, remove noisy phrase nodes

Fix HF startup stability: disable full spaCy preload

Refine semantic term weighting with local-window graph and phrase terms

Trigger HF rebuild after restarting state

Add semantic word power comparison table vs competitors

Add New Project reset action for local project workflow

Improve Semantic Core UX and add competitor document analysis

Add TextAnalyst Semantic Core endpoints and modules

Add Polish language support (pl_core_news_sm)

Add Title analyzer: length, ngrams, keyword coverage, BERT semantic

Add Freq column to N-gram table: comp_occurrence shows how many competitors use the phrase

Fix count_words: isolated logic, total includes stop-words and digits

Clean restore: Smart Window ngrams + compact BM25 mirror loop

BM25 fix: hyphen-to-space in ngrams, sync corpus builder

Dual word count: total (like Word) + significant (SEO weight)

Trigger HF rebuild

BM25 Mirror: generate keywords via generate_ngrams_safe for 100% format match

Fix: count_words significant only, BERT raw text, extended garbage_chars in ngrams

Add Word Count stats block above tabs (General Stats)

Implement smart window N-gram generation: preserve stop words inside phrases