Changelog

The product record, newest first.

A release-by-release account of features, fixes, and architectural changes currently recorded for Editiva.

v0.8

March 2026

Inspiration Sources

Scan external websites and RSS feeds for article inspiration. Article suggestions automatically prefill the work creation wizard.

Added or improved

InspirationSource and ArticleSuggestion domain entities with full CRUD API

Added or improved

ScanInspirationSourceJob — scheduled recurring Hangfire job for feed scanning

Added or improved

Article suggestion feed at /inspiration with priority sorting and filtering

Added or improved

/settings/inspiration page for managing inspiration sources

Added or improved

Work creation wizard prefill: open ?suggestion= URL param to pre-populate title and brief

v0.7

March 2026

Website Crawl + RAG MVP 2

Knowledge bases now support website crawling. HtmlWebCrawler fetches and chunks web content; pgvector handles semantic search. Content guidelines extracted in 3 passes.

Added or improved

SourceType.Website + CrawlConfig value object in domain

Added or improved

HtmlWebCrawler — fetches, strips, and chunks web pages by H2/H3 structure

Added or improved

RunWebsiteCrawlJob with IVFFlat pgvector index (lists=10) for fast ANN search

Added or improved

ContentGuidelines value object: style rules, vocabulary, structural patterns

Added or improved

3-pass guideline extraction (structure → content → synthesis) via dedicated prompts

Added or improved

Agent injection: guidelines, voice, and vocabulary inserted into every AI call with token budget caps

Added or improved

AddWebsiteCrawlSupport migration; RAG security fixes with tenant isolation

v0.6

February 2026

Webhooks + Prompt Customization

HMAC-SHA256 secured webhooks for work approval events. Per-tenant prompt overrides let you customize every AI instruction without code.

Added or improved

WebhookEndpoint aggregate + HMAC-SHA256 signature on every delivery

Added or improved

WorkApprovedWebhookHandler — fires on work approval domain event

Added or improved

Full CRUD webhook management API + frontend settings page

Added or improved

TenantPromptOverride entity — per-tenant overrides for all 20+ prompt templates

Added or improved

PromptTemplateService: DB override takes priority over filesystem template

Added or improved

/settings/prompts page with live preview of active prompt content

Added or improved

AddWebhookSupport + AddTenantPromptOverrides migrations

v0.5

February 2026

Version Restore + Export Engine

Roll back to any prior approved state. Export finished content in Markdown, HTML, DOCX, EPUB, or PDF — all server-rendered.

Added or improved

RestoreVersionCommand — rolls work back to any previously approved node snapshot

Added or improved

WorkRestored domain event dispatched on rollback

Added or improved

Export engine: MarkdownRenderer, HtmlRenderer, DocxRenderer (QuestPDF), EpubRenderer, PdfRenderer

Added or improved

GET /works/{id}/export?format= endpoint with Content-Disposition headers

Added or improved

Writer Profile system: upload writing samples → AI extracts style fingerprint

Added or improved

StyleSample, ExplicitRules, NodeVocabulary value objects in domain

Added or improved

Writer type profiles: Ghostwrite, Co-Write, Director Mode collaboration modes

v0.4

February 2026

Writer Voice & Style System

Upload writing samples. AI extracts your style fingerprint — vocabulary, tone, sentence patterns — and applies it to every output.

Added or improved

WriterProfile aggregate with style analysis via dedicated LLM prompt

Added or improved

style_analysis.md and test_voice.md prompt templates

Added or improved

Voice fingerprint injected into DraftStrategy, RevisionStrategy, and ContinuityCriticStrategy

Added or improved

ContextBudgetService: token budget caps per context type (guidelines 1200t, voice 600t, vocab 200t)

Added or improved

RetrievalContextBuilder: assembles and trims multi-source context before each AI call

Added or improved

/settings/writer-profile page with sample upload and extracted fingerprint display

v0.3

February 2026

Editorial Review (Human + AI)

Guest review links with tokenized access. AI editorial review: 6-dimensional analysis across Structure, Style, Completeness, Audience fit, Voice Consistency, and Factual Flags.

Added or improved

ReviewSession + ReviewComment aggregates with human verdict workflow

Added or improved

GuestReviewToken — time-limited signed token, reviewers need no account

Added or improved

Guest token revocation endpoint for security

Added or improved

AiReviewSession with 6-dimension scoring schema (editorial_review.schema.json)

Added or improved

RunAiReviewJob — generates structured JSON review, stores per dimension

Added or improved

GET /review/{token} public page with structured verdict UI

Added or improved

AddHumanReviewSystem + AddAiReviewSystem migrations

v0.2

February 2026

Validation Gates + Extended Brief

Three gate modes: Auto (pipeline runs end-to-end), Per-Stage (approve each phase), Per-Node (approve every section). Work preferences value object.

Added or improved

GateMode enum: Auto | PerStage | PerNode with state machine integration

Added or improved

WorkPreferences value object (GateMode, CollaborationStyle, TargetAudience)

Added or improved

ApprovalDecision value object with verdict, reviewer note, and timestamp

Added or improved

ApproveWork, ApproveNode, RejectWork commands with FluentValidation

Added or improved

WorkApprovalRequested + NodeApprovalRequested domain events

Added or improved

WorkGoal extended: Title, Brief, TargetAudience, WordCount, KeyPoints, References

Added or improved

AddValidationGates migration; AddHumanReviewSystem migration

Added or improved

Real-time SSE agent log stream with JWT-from-query-param for EventSource

v0.1

February 2026

Initial Platform

7-stage editorial pipeline, multi-tenant architecture, Knowledge Bases with pgvector, real-time SSE agent logs, and all three collaboration modes.

Added or improved

7-stage state machine: Idea → Structuring → Draft → Writing → GlobalReview → Ready → Published

Added or improved

Multi-tenant architecture: TenantId on every entity, EF Core global query filters

Added or improved

Clean Architecture: shared → domain → application → infrastructure → apps

Added or improved

Agent strategies: ArchitectStrategy, OutlineStrategy, DraftStrategy, CriticStrategy, RevisionStrategy, ContinuityCriticStrategy

Added or improved

Knowledge Base bounded context with pgvector embeddings

Added or improved

RAG retrieval wired into agent context builder

Added or improved

JWT authentication + BCrypt password hashing

Added or improved

Hangfire durable job scheduling for all pipeline steps

Added or improved

Early tenant provider key storage, now superseded by centralized AI Gateway credentials

Added or improved

Work tags (jsonb), bulk delete, usage tracking (token counts per work)