Forbid URLs/domains/markdown links across prompt rules (runtime, platform
templates, outline/imitation/title flows) and rename "官网" placeholder to
"官网信息" with explicit instructions that links are background only.
Add sanitizeGeneratedArticleMarkdown to strip URLs, HTML images, and
"网站列表/官网列表" labels from LLM output, wired into article, prompt-rule,
template, and outline generation. Drop the site_list outline section seed
and filter blocked outline keys in the wizard so stored drafts cannot
resurrect it.
- add /questions/combination-fill endpoint with AI-driven, IP-region-aware matrix fill
- extract ip2region resolver from ops/app into shared/ipregion for cross-service use
- thread question_id filter through dashboard composite, citation summary, and collect-now
- switch template wizard from keyword inputs to brand-question selection (primary + supplemental)
- pass brand_question and supplemental_questions through assist/title/outline prompts
- add AiWaitingModal + 45s client timeout and request_timeout error mapping for long AI flows
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Tighten the analyze prompts (runtime + recommendation platform) so the
model returns 8-10 question-style search queries (哪家好/有哪些/怎么选/
价格/排名/避坑 …) instead of generic tag words, and lift the keyword cap
in normalizeAnalyzeResult from 5 to 10 to keep them. Add tests covering
the new ten-keyword window and the question-like guidance in the seeded
analyze prompt.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds an ai_point_usage_logs ledger and a reserve/refund/complete pipeline
that charges AI points for article selection optimize, template analyze
/title/outline, and KOL prompt generate/optimize. Pending reservations
are reconciled when the kol-assist worker and template-assist tasks
finish or fail, so points refund automatically on errors. Workspace now
exposes the AI quota status and a paginated usage ledger.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Introduce a generic read-through caching infrastructure and wire it into
all major tenant app services to reduce database load on hot read paths.
Key changes:
- Add `DeletePrefix` to Cache interface with memory (prefix scan) and
Redis (SCAN + DEL) implementations
- New `readthrough.go`: generic `LoadJSON` / `LoadJSONWithEmpty` helpers
backed by singleflight to prevent cache stampedes; supports jittered TTL
- New `cache_support.go`: centralized cache key builders and invalidation
helpers for all entities (workspace, brand, prompt rules, schedule tasks,
articles)
- Wire optional cache into ArticleService, BrandService, WorkspaceService,
PromptRuleService, ScheduleTaskService, TemplateService, MediaService,
PromptGenerateService via `WithCache()` builder pattern
- ScheduleDispatchWorker invalidates schedule task cache after dispatching
- ArticleService gains a new `Detail` endpoint with empty-result caching
- Update cmd entrypoints and transport handlers to propagate cache
Replace in-process generation with queue-based async execution via
RabbitMQ. Add generation task runtime for lifecycle management, article
generation payload/queue abstractions, and template-assist queue publisher.
Refactor prompt generation service to support batch generation with
per-item error tracking. Update stream hub to bridge queue events to SSE.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Implemented KnowledgeHandler for managing knowledge groups and items, including listing, creating, updating, and deleting operations.
- Added database migration scripts to create necessary tables for knowledge management, including knowledge_groups, knowledge_items, knowledge_parse_tasks, and knowledge_chunks_meta.
- Introduced prompt_rule_knowledge_groups table to associate prompt rules with knowledge groups.
- Added support for external markdown synchronization in ArticleEditorCanvas.vue.
- Implemented a new function to sync markdown from props, ensuring the editor reflects external changes.
- Introduced a removeOutlineSection function in TemplateWizardView.vue to manage outline sections dynamically.
- Updated UI components to improve user experience, including replacing a-input with a-textarea for better text handling.
- Refactored CSS styles for a cleaner layout and improved responsiveness in TemplateWizardView.vue.
- Enhanced LLM generation requests to include response format options in ark.go and client.go.
- Updated template assist logic to enforce structured outline outputs in template_assist.go.
- Added tests for outline result decoding and prompt generation to ensure robustness.
- Created migration scripts to update prompt templates with new writing requirements for top X articles.
- Added migration to harden task audit tracking by modifying audit_logs and related tables.
- Introduced operator_id to several tables for better tracking of actions.
- Updated article_templates with new prompt templates for various article types, enhancing content generation.
- Created prompt_rules and schedule_tasks tables to manage content generation rules and scheduling.
- Added foreign key constraints to articles for better data integrity.
root