feat(ai-project-generator): conditional sprints, UX platform awareness & priority fix#201
Closed
parth0025 wants to merge 5 commits into
Closed
feat(ai-project-generator): conditional sprints, UX platform awareness & priority fix#201parth0025 wants to merge 5 commits into
parth0025 wants to merge 5 commits into
Conversation
Add a filter-driven dashboard card showing per-employee planned, logged, and estimated hours for a chosen period, with expandable per-task breakdowns, totals footer, client-side sorting, employee search, and over-budget highlighting. - Backend: getEmployeeWorkloadReport endpoint + route. Period pivots on estimated_time.Date (planned) and timesheets.LogStartTime (logged); multi-assignee aware. Role-based visibility aligned with the app-wide convention (roleType 1/2 see all filtered employees, others see only themselves). Returns all matching tasks per employee (no display cap). - Frontend: EmployeeWorkloadReportCard widget + sticky-header table, Wasabi-backed avatars via the users store, subtask indicator, team->user resolution, role-aware Edit Card fields. - Config: cardComponent.json catalog entry, i18n keys, default grid size, HomePage getComponent case. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
…load-report-widget
…load-report-widget
…s, and priority fix == 1. Conditional sprint additions (promptBuilder.js + special-sprints-guidance.md) == New prompt partial injected between sprint-guidance and task-guidance: - GitHub & Version Control Setup sprint (first sprint when source code or multi-dev is detected): 8 step-by-step tasks covering account/org setup, repo creation, SSH/HTTPS auth, branching strategy, commit conventions, PR conventions, branch protection, semantic versioning + changelogs. - Environment & Tech-Stack Setup sprint (one task per qualifying tech item): databases, backend frameworks, cloud services. Each task covers install, configure, create instance/DB, verify connection. - Test Case Guidelines sprint (when project has 2+ testable modules): 4 tasks covering what test cases are, how to write them, module-wise structure mapped to the project's own modules, and QA tracking workflow. All three are conditional — omitted when the condition is not met. == 2. UX design platform awareness (clarify/system.md + special-sprints-guidance.md) == Clarify step now asks which design/UX tool the team will use whenever the project involves screen design or wireframing. Options: Figma, Adobe XD, Penpot (open-source), Framer (code-based), Sketch (macOS), Balsamiq (low-fidelity), Miro, Let AI decide. Plan generation emits a platform-specific setup task for the chosen tool, including Figma MCP server setup (token generation, npx install, config JSON, benefits for design-to-code handoff with AI assistants). Fixed: design tools were wrongly listed in the skip list for tech-stack setup — they now correctly qualify as setup items. == 3. Priority fix (task-guidance.md + schema.md + orchestrator.js) == - Removed Urgent entirely. Only Low / Medium / High are valid — these are the three default priority values in every AlianHub installation. - Added required distribution check: if >1/3 of tasks are High the model must go back and downgrade; expected ratio is ~1-2 High, 4-6 Medium, 1-2 Low per sprint. - schema.md enum updated: "Low" | "Medium" | "High" (no Urgent). - orchestrator.js PRIORITY_NORMALIZE map drops urgent; any stale value falls through to the MEDIUM default. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Collaborator
Author
|
Closing — replaced by a clean branch without unrelated file history. New PR incoming. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Urgent, enforcedLow / Medium / Highonly (company defaults), added distribution-check rule to stop the model over-assigningHighChanges
prompts/project-plan/special-sprints-guidance.md(new file)New prompt partial wired between
sprint-guidance.mdandtask-guidance.md:prompts/clarify/system.mdprompts/project-plan/special-sprints-guidance.md— design platform sub-sectionprompts/project-plan/task-guidance.mdUrgent— onlyLow / Medium / Highare validprompts/project-plan/schema.md"priority"enum:"Low" | "Medium" | "High"(Urgent removed)Modules/AIProjectGenerator/orchestrator.jsPRIORITY_NORMALIZEmap: removedurgent: 'URGENT'; any stale value falls back to'MEDIUM'Test plan
Urgentvalues, High used sparingly🤖 Generated with Claude Code